problem_id
stringlengths 18
22
| source
stringclasses 1
value | task_type
stringclasses 1
value | in_source_id
stringlengths 13
58
| prompt
stringlengths 1.71k
18.9k
| golden_diff
stringlengths 145
5.13k
| verification_info
stringlengths 465
23.6k
| num_tokens_prompt
int64 556
4.1k
| num_tokens_diff
int64 47
1.02k
|
|---|---|---|---|---|---|---|---|---|
gh_patches_debug_4873 | rasdani/github-patches | git_diff | kornia__kornia-2054 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Crash on resize inverse - missing flag padding_mode
### Describe the bug
The inverse of resize augmentation crashes since the `padding_mode` flag is not set:
```
File "/home/miquelmr/kornia/kornia/augmentation/_2d/geometric/base.py", line 106, in inverse
output = self.inverse_transform(in_tensor, flags=flags, transform=transform, size=size)
File "/home/miquelmr/kornia/kornia/augmentation/_2d/geometric/resize.py", line 88, in inverse_transform
input, transform[:, :2, :], size, flags["resample"], flags["padding_mode"], flags["align_corners"]
KeyError: 'padding_mode
```
### Reproduction steps
```bash
import kornia.augmentation as K
import torch
img = torch.zeros((3,5,5))
aug = K.Resize(2)
transformed = aug(img)
img_transformed_inv = aug.inverse(transformed)
```
### Expected behavior
No crash
### Environment
```shell
Collecting environment information...
PyTorch version: 1.10.2
Is debug build: False
CUDA used to build PyTorch: Could not collect
ROCM used to build PyTorch: N/A
OS: Ubuntu 18.04.6 LTS (x86_64)
GCC version: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.17
Python version: 3.7.15 (default, Nov 24 2022, 21:12:53) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-4.15.0-196-generic-x86_64-with-debian-buster-sid
Is CUDA available: False
CUDA runtime version: Could not collect
GPU models and configuration:
GPU 0: NVIDIA TITAN X (Pascal)
GPU 1: NVIDIA TITAN X (Pascal)
GPU 2: NVIDIA TITAN Xp
Nvidia driver version: 520.61.05
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Versions of relevant libraries:
[pip3] mypy==0.991
[pip3] mypy-extensions==0.4.3
[pip3] numpy==1.21.5
[pip3] torch==1.10.2
[pip3] torchvision==0.2.2
[conda] blas 1.0 mkl
[conda] cudatoolkit 10.2.89 hfd86e86_1
[conda] mkl 2021.4.0 h06a4308_640
[conda] mkl-service 2.4.0 py37h7f8727e_0
[conda] mkl_fft 1.3.1 py37hd3c417c_0
[conda] mkl_random 1.2.2 py37h51133e4_0
[conda] mypy 0.991 pypi_0 pypi
[conda] mypy-extensions 0.4.3 pypi_0 pypi
[conda] numpy 1.21.5 py37h6c91a56_3
[conda] numpy-base 1.21.5 py37ha15fc14_3
[conda] pytorch 1.10.2 cpu_py37hfa7516b_0
[conda] torchvision 0.2.2 py_3 pytorch
```
### Additional context
_No response_
</issue>
<code>
[start of kornia/augmentation/_2d/geometric/resize.py]
1 from typing import Any, Dict, Optional, Tuple, Union
2
3 import torch
4
5 from kornia.augmentation import random_generator as rg
6 from kornia.augmentation._2d.geometric.base import GeometricAugmentationBase2D
7 from kornia.constants import Resample
8 from kornia.core import Tensor
9 from kornia.geometry.transform import crop_by_transform_mat, get_perspective_transform, resize
10 from kornia.utils import eye_like
11
12
13 class Resize(GeometricAugmentationBase2D):
14 """Resize to size.
15
16 Args:
17 size: Size (h, w) in pixels of the resized region or just one side.
18 side: Which side to resize, if size is only of type int.
19 resample: Resampling mode.
20 align_corners: interpolation flag.
21 antialias: if True, then image will be filtered with Gaussian before downscaling. No effect for upscaling.
22 keepdim: whether to keep the output shape the same as input (True) or broadcast it
23 to the batch form (False).
24 """
25
26 def __init__(
27 self,
28 size: Union[int, Tuple[int, int]],
29 side: str = "short",
30 resample: Union[str, int, Resample] = Resample.BILINEAR.name,
31 align_corners: bool = True,
32 antialias: bool = False,
33 p: float = 1.0,
34 return_transform: Optional[bool] = None,
35 keepdim: bool = False,
36 ) -> None:
37 super().__init__(p=1.0, return_transform=return_transform, same_on_batch=True, p_batch=p, keepdim=keepdim)
38 self._param_generator = rg.ResizeGenerator(resize_to=size, side=side)
39 self.flags = dict(
40 size=size, side=side, resample=Resample.get(resample), align_corners=align_corners, antialias=antialias
41 )
42
43 def compute_transformation(self, input: Tensor, params: Dict[str, Tensor], flags: Dict[str, Any]) -> Tensor:
44 if params["output_size"] == input.shape[-2:]:
45 return eye_like(3, input)
46
47 transform: Tensor = get_perspective_transform(params["src"], params["dst"])
48 transform = transform.expand(input.shape[0], -1, -1)
49 return transform
50
51 def apply_transform(
52 self, input: Tensor, params: Dict[str, Tensor], flags: Dict[str, Any], transform: Optional[Tensor] = None
53 ) -> Tensor:
54 B, C, _, _ = input.shape
55 out_size = tuple(params["output_size"][0].tolist())
56 out = torch.empty(B, C, *out_size, device=input.device, dtype=input.dtype)
57
58 for i in range(B):
59 x1 = int(params["src"][i, 0, 0])
60 x2 = int(params["src"][i, 1, 0]) + 1
61 y1 = int(params["src"][i, 0, 1])
62 y2 = int(params["src"][i, 3, 1]) + 1
63 out[i] = resize(
64 input[i : i + 1, :, y1:y2, x1:x2],
65 out_size,
66 interpolation=flags["resample"].name.lower(),
67 align_corners=flags["align_corners"]
68 if flags["resample"] in [Resample.BILINEAR, Resample.BICUBIC]
69 else None,
70 antialias=flags["antialias"],
71 )
72 return out
73
74 def inverse_transform(
75 self,
76 input: Tensor,
77 flags: Dict[str, Any],
78 transform: Optional[Tensor] = None,
79 size: Optional[Tuple[int, int]] = None,
80 ) -> Tensor:
81 if not isinstance(size, tuple):
82 raise TypeError(f'Expected the size be a tuple. Gotcha {type(size)}')
83
84 if not isinstance(transform, Tensor):
85 raise TypeError(f'Expected the transform be a Tensor. Gotcha {type(transform)}')
86
87 return crop_by_transform_mat(
88 input, transform[:, :2, :], size, flags["resample"], flags["padding_mode"], flags["align_corners"]
89 )
90
91
92 class LongestMaxSize(Resize):
93 """Rescale an image so that maximum side is equal to max_size, keeping the aspect ratio of the initial image.
94
95 Args:
96 max_size: maximum size of the image after the transformation.
97 """
98
99 def __init__(
100 self,
101 max_size: int,
102 resample: Union[str, int, Resample] = Resample.BILINEAR.name,
103 align_corners: bool = True,
104 p: float = 1.0,
105 return_transform: Optional[bool] = None,
106 ) -> None:
107 # TODO: Support max_size list input to randomly select from
108 super().__init__(
109 size=max_size,
110 side="long",
111 resample=resample,
112 return_transform=return_transform,
113 align_corners=align_corners,
114 p=p,
115 )
116
117
118 class SmallestMaxSize(Resize):
119 """Rescale an image so that minimum side is equal to max_size, keeping the aspect ratio of the initial image.
120
121 Args:
122 max_size: maximum size of the image after the transformation.
123 """
124
125 def __init__(
126 self,
127 max_size: int,
128 resample: Union[str, int, Resample] = Resample.BILINEAR.name,
129 align_corners: bool = True,
130 p: float = 1.0,
131 return_transform: Optional[bool] = None,
132 ) -> None:
133 # TODO: Support max_size list input to randomly select from
134 super().__init__(
135 size=max_size,
136 side="short",
137 resample=resample,
138 return_transform=return_transform,
139 align_corners=align_corners,
140 p=p,
141 )
142
[end of kornia/augmentation/_2d/geometric/resize.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/kornia/augmentation/_2d/geometric/resize.py b/kornia/augmentation/_2d/geometric/resize.py
--- a/kornia/augmentation/_2d/geometric/resize.py
+++ b/kornia/augmentation/_2d/geometric/resize.py
@@ -85,7 +85,7 @@
raise TypeError(f'Expected the transform be a Tensor. Gotcha {type(transform)}')
return crop_by_transform_mat(
- input, transform[:, :2, :], size, flags["resample"], flags["padding_mode"], flags["align_corners"]
+ input, transform[:, :2, :], size, flags["resample"].name.lower(), "zeros", flags["align_corners"]
)
| {"golden_diff": "diff --git a/kornia/augmentation/_2d/geometric/resize.py b/kornia/augmentation/_2d/geometric/resize.py\n--- a/kornia/augmentation/_2d/geometric/resize.py\n+++ b/kornia/augmentation/_2d/geometric/resize.py\n@@ -85,7 +85,7 @@\n raise TypeError(f'Expected the transform be a Tensor. Gotcha {type(transform)}')\n \n return crop_by_transform_mat(\n- input, transform[:, :2, :], size, flags[\"resample\"], flags[\"padding_mode\"], flags[\"align_corners\"]\n+ input, transform[:, :2, :], size, flags[\"resample\"].name.lower(), \"zeros\", flags[\"align_corners\"]\n )\n", "issue": "Crash on resize inverse - missing flag padding_mode\n### Describe the bug\n\nThe inverse of resize augmentation crashes since the `padding_mode` flag is not set:\r\n\r\n```\r\n File \"/home/miquelmr/kornia/kornia/augmentation/_2d/geometric/base.py\", line 106, in inverse\r\n output = self.inverse_transform(in_tensor, flags=flags, transform=transform, size=size)\r\n File \"/home/miquelmr/kornia/kornia/augmentation/_2d/geometric/resize.py\", line 88, in inverse_transform\r\n input, transform[:, :2, :], size, flags[\"resample\"], flags[\"padding_mode\"], flags[\"align_corners\"]\r\nKeyError: 'padding_mode\r\n```\n\n### Reproduction steps\n\n```bash\nimport kornia.augmentation as K\r\nimport torch\r\n\r\nimg = torch.zeros((3,5,5))\r\n\r\naug = K.Resize(2)\r\n\r\ntransformed = aug(img)\r\nimg_transformed_inv = aug.inverse(transformed)\n```\n\n\n### Expected behavior\n\nNo crash\n\n### Environment\n\n```shell\nCollecting environment information...\r\nPyTorch version: 1.10.2\r\nIs debug build: False\r\nCUDA used to build PyTorch: Could not collect\r\nROCM used to build PyTorch: N/A\r\n\r\nOS: Ubuntu 18.04.6 LTS (x86_64)\r\nGCC version: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0\r\nClang version: Could not collect\r\nCMake version: Could not collect\r\nLibc version: glibc-2.17\r\n\r\nPython version: 3.7.15 (default, Nov 24 2022, 21:12:53) [GCC 11.2.0] (64-bit runtime)\r\nPython platform: Linux-4.15.0-196-generic-x86_64-with-debian-buster-sid\r\nIs CUDA available: False\r\nCUDA runtime version: Could not collect\r\nGPU models and configuration: \r\nGPU 0: NVIDIA TITAN X (Pascal)\r\nGPU 1: NVIDIA TITAN X (Pascal)\r\nGPU 2: NVIDIA TITAN Xp\r\n\r\nNvidia driver version: 520.61.05\r\ncuDNN version: Could not collect\r\nHIP runtime version: N/A\r\nMIOpen runtime version: N/A\r\n\r\nVersions of relevant libraries:\r\n[pip3] mypy==0.991\r\n[pip3] mypy-extensions==0.4.3\r\n[pip3] numpy==1.21.5\r\n[pip3] torch==1.10.2\r\n[pip3] torchvision==0.2.2\r\n[conda] blas 1.0 mkl \r\n[conda] cudatoolkit 10.2.89 hfd86e86_1 \r\n[conda] mkl 2021.4.0 h06a4308_640 \r\n[conda] mkl-service 2.4.0 py37h7f8727e_0 \r\n[conda] mkl_fft 1.3.1 py37hd3c417c_0 \r\n[conda] mkl_random 1.2.2 py37h51133e4_0 \r\n[conda] mypy 0.991 pypi_0 pypi\r\n[conda] mypy-extensions 0.4.3 pypi_0 pypi\r\n[conda] numpy 1.21.5 py37h6c91a56_3 \r\n[conda] numpy-base 1.21.5 py37ha15fc14_3 \r\n[conda] pytorch 1.10.2 cpu_py37hfa7516b_0 \r\n[conda] torchvision 0.2.2 py_3 pytorch\n```\n\n\n### Additional context\n\n_No response_\n", "before_files": [{"content": "from typing import Any, Dict, Optional, Tuple, Union\n\nimport torch\n\nfrom kornia.augmentation import random_generator as rg\nfrom kornia.augmentation._2d.geometric.base import GeometricAugmentationBase2D\nfrom kornia.constants import Resample\nfrom kornia.core import Tensor\nfrom kornia.geometry.transform import crop_by_transform_mat, get_perspective_transform, resize\nfrom kornia.utils import eye_like\n\n\nclass Resize(GeometricAugmentationBase2D):\n \"\"\"Resize to size.\n\n Args:\n size: Size (h, w) in pixels of the resized region or just one side.\n side: Which side to resize, if size is only of type int.\n resample: Resampling mode.\n align_corners: interpolation flag.\n antialias: if True, then image will be filtered with Gaussian before downscaling. No effect for upscaling.\n keepdim: whether to keep the output shape the same as input (True) or broadcast it\n to the batch form (False).\n \"\"\"\n\n def __init__(\n self,\n size: Union[int, Tuple[int, int]],\n side: str = \"short\",\n resample: Union[str, int, Resample] = Resample.BILINEAR.name,\n align_corners: bool = True,\n antialias: bool = False,\n p: float = 1.0,\n return_transform: Optional[bool] = None,\n keepdim: bool = False,\n ) -> None:\n super().__init__(p=1.0, return_transform=return_transform, same_on_batch=True, p_batch=p, keepdim=keepdim)\n self._param_generator = rg.ResizeGenerator(resize_to=size, side=side)\n self.flags = dict(\n size=size, side=side, resample=Resample.get(resample), align_corners=align_corners, antialias=antialias\n )\n\n def compute_transformation(self, input: Tensor, params: Dict[str, Tensor], flags: Dict[str, Any]) -> Tensor:\n if params[\"output_size\"] == input.shape[-2:]:\n return eye_like(3, input)\n\n transform: Tensor = get_perspective_transform(params[\"src\"], params[\"dst\"])\n transform = transform.expand(input.shape[0], -1, -1)\n return transform\n\n def apply_transform(\n self, input: Tensor, params: Dict[str, Tensor], flags: Dict[str, Any], transform: Optional[Tensor] = None\n ) -> Tensor:\n B, C, _, _ = input.shape\n out_size = tuple(params[\"output_size\"][0].tolist())\n out = torch.empty(B, C, *out_size, device=input.device, dtype=input.dtype)\n\n for i in range(B):\n x1 = int(params[\"src\"][i, 0, 0])\n x2 = int(params[\"src\"][i, 1, 0]) + 1\n y1 = int(params[\"src\"][i, 0, 1])\n y2 = int(params[\"src\"][i, 3, 1]) + 1\n out[i] = resize(\n input[i : i + 1, :, y1:y2, x1:x2],\n out_size,\n interpolation=flags[\"resample\"].name.lower(),\n align_corners=flags[\"align_corners\"]\n if flags[\"resample\"] in [Resample.BILINEAR, Resample.BICUBIC]\n else None,\n antialias=flags[\"antialias\"],\n )\n return out\n\n def inverse_transform(\n self,\n input: Tensor,\n flags: Dict[str, Any],\n transform: Optional[Tensor] = None,\n size: Optional[Tuple[int, int]] = None,\n ) -> Tensor:\n if not isinstance(size, tuple):\n raise TypeError(f'Expected the size be a tuple. Gotcha {type(size)}')\n\n if not isinstance(transform, Tensor):\n raise TypeError(f'Expected the transform be a Tensor. Gotcha {type(transform)}')\n\n return crop_by_transform_mat(\n input, transform[:, :2, :], size, flags[\"resample\"], flags[\"padding_mode\"], flags[\"align_corners\"]\n )\n\n\nclass LongestMaxSize(Resize):\n \"\"\"Rescale an image so that maximum side is equal to max_size, keeping the aspect ratio of the initial image.\n\n Args:\n max_size: maximum size of the image after the transformation.\n \"\"\"\n\n def __init__(\n self,\n max_size: int,\n resample: Union[str, int, Resample] = Resample.BILINEAR.name,\n align_corners: bool = True,\n p: float = 1.0,\n return_transform: Optional[bool] = None,\n ) -> None:\n # TODO: Support max_size list input to randomly select from\n super().__init__(\n size=max_size,\n side=\"long\",\n resample=resample,\n return_transform=return_transform,\n align_corners=align_corners,\n p=p,\n )\n\n\nclass SmallestMaxSize(Resize):\n \"\"\"Rescale an image so that minimum side is equal to max_size, keeping the aspect ratio of the initial image.\n\n Args:\n max_size: maximum size of the image after the transformation.\n \"\"\"\n\n def __init__(\n self,\n max_size: int,\n resample: Union[str, int, Resample] = Resample.BILINEAR.name,\n align_corners: bool = True,\n p: float = 1.0,\n return_transform: Optional[bool] = None,\n ) -> None:\n # TODO: Support max_size list input to randomly select from\n super().__init__(\n size=max_size,\n side=\"short\",\n resample=resample,\n return_transform=return_transform,\n align_corners=align_corners,\n p=p,\n )\n", "path": "kornia/augmentation/_2d/geometric/resize.py"}]} | 3,040 | 164 |
gh_patches_debug_4237 | rasdani/github-patches | git_diff | great-expectations__great_expectations-2600 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
BUG with dependency: SQLAlchemy 1.4.0 for user installation
**Describe the bug**
SQLAlchemy `>= 1.4.0` breaks the imports in
https://github.com/great-expectations/great_expectations/blob/18234477693306e5e3845e69a1be78a85c639295/great_expectations/dataset/sqlalchemy_dataset.py#L42
This isn't showing up in the tests since the tests [pin the version](https://github.com/great-expectations/great_expectations/pull/2547) from above whereas the user installation doesn't
https://github.com/great-expectations/great_expectations/blob/18234477693306e5e3845e69a1be78a85c639295/setup.py#L25
The stack trace is from trying to scaffold a new suite is:
```
...
File ".../great_expectations/data_context/data_context.py", line 1421, in get_batch
return self._get_batch_v2(
File ".../great_expectations/data_context/data_context.py", line 1147, in _get_batch_v2
return validator.get_dataset()
File ".../great_expectations/validator/validator.py", line 1431, in get_dataset
return self.expectation_engine(
File ".../great_expectations/dataset/sqlalchemy_dataset.py", line 508, in __init__
self._table = sa.Table(table_name, sa.MetaData(), schema=schema)
AttributeError: 'NoneType' object has no attribute 'Table'
```
As a work around until the code is upgraded to work with `1.4.0` the version installed should be `<1.4.0`.
</issue>
<code>
[start of setup.py]
1 from setuptools import find_packages, setup
2
3 import versioneer
4
5 # Parse requirements.txt
6 with open("requirements.txt") as f:
7 required = f.read().splitlines()
8
9 # try:
10 # import pypandoc
11 # long_description = pypandoc.convert_file('README.md', 'rst')
12 # except (IOError, ImportError):
13 long_description = "Always know what to expect from your data. (See https://github.com/great-expectations/great_expectations for full description)."
14
15 config = {
16 "description": "Always know what to expect from your data.",
17 "author": "The Great Expectations Team",
18 "url": "https://github.com/great-expectations/great_expectations",
19 "author_email": "[email protected]",
20 "version": versioneer.get_version(),
21 "cmdclass": versioneer.get_cmdclass(),
22 "install_requires": required,
23 "extras_require": {
24 "spark": ["pyspark>=2.3.2"],
25 "sqlalchemy": ["sqlalchemy>=1.2"],
26 "airflow": ["apache-airflow[s3]>=1.9.0", "boto3>=1.7.3"],
27 "gcp": [
28 "google-cloud>=0.34.0",
29 "google-cloud-storage>=1.28.0",
30 "google-cloud-secret-manager>=1.0.0",
31 "pybigquery==0.4.15",
32 ],
33 "redshift": ["psycopg2>=2.8"],
34 "s3": ["boto3>=1.14"],
35 "aws_secrets": ["boto3>=1.8.7"],
36 "azure_secrets": ["azure-identity>=1.0.0", "azure-keyvault-secrets>=4.0.0"],
37 "snowflake": ["snowflake-sqlalchemy>=1.2"],
38 },
39 "packages": find_packages(exclude=["contrib*", "docs*", "tests*", "examples*"]),
40 "entry_points": {
41 "console_scripts": ["great_expectations=great_expectations.cli:main"]
42 },
43 "name": "great_expectations",
44 "long_description": long_description,
45 "license": "Apache-2.0",
46 "keywords": "data science testing pipeline data quality dataquality validation datavalidation",
47 "include_package_data": True,
48 "classifiers": [
49 "Development Status :: 4 - Beta",
50 "Intended Audience :: Developers",
51 "Intended Audience :: Science/Research",
52 "Intended Audience :: Other Audience",
53 "Topic :: Scientific/Engineering",
54 "Topic :: Software Development",
55 "Topic :: Software Development :: Testing",
56 "License :: OSI Approved :: Apache Software License",
57 "Programming Language :: Python :: 3",
58 "Programming Language :: Python :: 3.6",
59 "Programming Language :: Python :: 3.7",
60 "Programming Language :: Python :: 3.8",
61 ],
62 }
63
64 setup(**config)
65
[end of setup.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -22,7 +22,7 @@
"install_requires": required,
"extras_require": {
"spark": ["pyspark>=2.3.2"],
- "sqlalchemy": ["sqlalchemy>=1.2"],
+ "sqlalchemy": ["sqlalchemy>=1.2,<1.4.0"],
"airflow": ["apache-airflow[s3]>=1.9.0", "boto3>=1.7.3"],
"gcp": [
"google-cloud>=0.34.0",
| {"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -22,7 +22,7 @@\n \"install_requires\": required,\n \"extras_require\": {\n \"spark\": [\"pyspark>=2.3.2\"],\n- \"sqlalchemy\": [\"sqlalchemy>=1.2\"],\n+ \"sqlalchemy\": [\"sqlalchemy>=1.2,<1.4.0\"],\n \"airflow\": [\"apache-airflow[s3]>=1.9.0\", \"boto3>=1.7.3\"],\n \"gcp\": [\n \"google-cloud>=0.34.0\",\n", "issue": "BUG with dependency: SQLAlchemy 1.4.0 for user installation\n**Describe the bug**\r\n\r\nSQLAlchemy `>= 1.4.0` breaks the imports in \r\nhttps://github.com/great-expectations/great_expectations/blob/18234477693306e5e3845e69a1be78a85c639295/great_expectations/dataset/sqlalchemy_dataset.py#L42\r\n\r\nThis isn't showing up in the tests since the tests [pin the version](https://github.com/great-expectations/great_expectations/pull/2547) from above whereas the user installation doesn't\r\nhttps://github.com/great-expectations/great_expectations/blob/18234477693306e5e3845e69a1be78a85c639295/setup.py#L25\r\n\r\nThe stack trace is from trying to scaffold a new suite is:\r\n```\r\n...\r\n File \".../great_expectations/data_context/data_context.py\", line 1421, in get_batch\r\n return self._get_batch_v2(\r\n File \".../great_expectations/data_context/data_context.py\", line 1147, in _get_batch_v2\r\n return validator.get_dataset()\r\n File \".../great_expectations/validator/validator.py\", line 1431, in get_dataset\r\n return self.expectation_engine(\r\n File \".../great_expectations/dataset/sqlalchemy_dataset.py\", line 508, in __init__\r\n self._table = sa.Table(table_name, sa.MetaData(), schema=schema)\r\nAttributeError: 'NoneType' object has no attribute 'Table'\r\n```\r\n\r\nAs a work around until the code is upgraded to work with `1.4.0` the version installed should be `<1.4.0`.\n", "before_files": [{"content": "from setuptools import find_packages, setup\n\nimport versioneer\n\n# Parse requirements.txt\nwith open(\"requirements.txt\") as f:\n required = f.read().splitlines()\n\n# try:\n# import pypandoc\n# long_description = pypandoc.convert_file('README.md', 'rst')\n# except (IOError, ImportError):\nlong_description = \"Always know what to expect from your data. (See https://github.com/great-expectations/great_expectations for full description).\"\n\nconfig = {\n \"description\": \"Always know what to expect from your data.\",\n \"author\": \"The Great Expectations Team\",\n \"url\": \"https://github.com/great-expectations/great_expectations\",\n \"author_email\": \"[email protected]\",\n \"version\": versioneer.get_version(),\n \"cmdclass\": versioneer.get_cmdclass(),\n \"install_requires\": required,\n \"extras_require\": {\n \"spark\": [\"pyspark>=2.3.2\"],\n \"sqlalchemy\": [\"sqlalchemy>=1.2\"],\n \"airflow\": [\"apache-airflow[s3]>=1.9.0\", \"boto3>=1.7.3\"],\n \"gcp\": [\n \"google-cloud>=0.34.0\",\n \"google-cloud-storage>=1.28.0\",\n \"google-cloud-secret-manager>=1.0.0\",\n \"pybigquery==0.4.15\",\n ],\n \"redshift\": [\"psycopg2>=2.8\"],\n \"s3\": [\"boto3>=1.14\"],\n \"aws_secrets\": [\"boto3>=1.8.7\"],\n \"azure_secrets\": [\"azure-identity>=1.0.0\", \"azure-keyvault-secrets>=4.0.0\"],\n \"snowflake\": [\"snowflake-sqlalchemy>=1.2\"],\n },\n \"packages\": find_packages(exclude=[\"contrib*\", \"docs*\", \"tests*\", \"examples*\"]),\n \"entry_points\": {\n \"console_scripts\": [\"great_expectations=great_expectations.cli:main\"]\n },\n \"name\": \"great_expectations\",\n \"long_description\": long_description,\n \"license\": \"Apache-2.0\",\n \"keywords\": \"data science testing pipeline data quality dataquality validation datavalidation\",\n \"include_package_data\": True,\n \"classifiers\": [\n \"Development Status :: 4 - Beta\",\n \"Intended Audience :: Developers\",\n \"Intended Audience :: Science/Research\",\n \"Intended Audience :: Other Audience\",\n \"Topic :: Scientific/Engineering\",\n \"Topic :: Software Development\",\n \"Topic :: Software Development :: Testing\",\n \"License :: OSI Approved :: Apache Software License\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.6\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n ],\n}\n\nsetup(**config)\n", "path": "setup.py"}]} | 1,710 | 141 |
gh_patches_debug_26787 | rasdani/github-patches | git_diff | conan-io__conan-center-index-7037 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
[request] rapidcheck/20210702
### Package Details
* Package Name/Version: **rapidcheck/20210702**
The above-mentioned version solves issue #5205 and is not yet available as a recipe. Please add this version.
</issue>
<code>
[start of recipes/rapidcheck/all/conanfile.py]
1 from conans import CMake, ConanFile, tools
2 from conans.errors import ConanInvalidConfiguration
3 import os
4 import textwrap
5
6 required_conan_version = ">=1.33.0"
7
8
9 class RapidcheckConan(ConanFile):
10 name = "rapidcheck"
11 description = "QuickCheck clone for C++ with the goal of being simple to use with as little boilerplate as possible"
12 url = "https://github.com/conan-io/conan-center-index"
13 homepage = "https://github.com/emil-e/rapidcheck"
14 license = "BSD-2-Clause"
15 topics = "quickcheck", "testing", "property-testing"
16 exports_sources = "CMakeLists.txt"
17 generators = "cmake"
18 settings = "os", "arch", "compiler", "build_type"
19 options = {
20 "shared": [True, False],
21 "fPIC": [True, False],
22 "enable_rtti": [True, False],
23 }
24 default_options = {
25 "shared": False,
26 "fPIC": True,
27 "enable_rtti": True,
28 }
29
30 _cmake = None
31
32 @property
33 def _source_subfolder(self):
34 return "source_subfolder"
35
36 @property
37 def _build_subfolder(self):
38 return "build_subfolder"
39
40 def config_options(self):
41 if self.settings.os == "Windows":
42 del self.options.fPIC
43
44 def configure(self):
45 if self.options.shared:
46 del self.options.fPIC
47
48 def validate(self):
49 if self.settings.compiler.get_safe("cppstd"):
50 tools.check_min_cppstd(self, 11)
51 if self.settings.compiler == "Visual Studio" and self.options.shared:
52 raise ConanInvalidConfiguration("shared is not supported using Visual Studio")
53
54 def source(self):
55 tools.get(**self.conan_data["sources"][self.version],
56 destination=self._source_subfolder, strip_root=True)
57
58 def _configure_cmake(self):
59 if self._cmake:
60 return self._cmake
61 self._cmake = CMake(self)
62 self._cmake.definitions["RC_ENABLE_RTTI"] = self.options.enable_rtti
63 self._cmake.definitions["RC_ENABLE_TESTS"] = False
64 self._cmake.definitions["RC_ENABLE_EXAMPLES"] = False
65 self._cmake.configure(build_folder=self._build_subfolder)
66 return self._cmake
67
68 def build(self):
69 cmake = self._configure_cmake()
70 cmake.build()
71
72 def package(self):
73 self.copy(pattern="LICENSE*", src=self._source_subfolder, dst="licenses")
74 cmake = self._configure_cmake()
75 cmake.install()
76 tools.rmdir(os.path.join(self.package_folder, "share"))
77 self._create_cmake_module_alias_targets(
78 os.path.join(self.package_folder, self._module_file_rel_path),
79 {"rapidcheck": "rapidcheck::rapidcheck"}
80 )
81
82 @staticmethod
83 def _create_cmake_module_alias_targets(module_file, targets):
84 content = ""
85 for alias, aliased in targets.items():
86 content += textwrap.dedent("""\
87 if(TARGET {aliased} AND NOT TARGET {alias})
88 add_library({alias} INTERFACE IMPORTED)
89 set_property(TARGET {alias} PROPERTY INTERFACE_LINK_LIBRARIES {aliased})
90 endif()
91 """.format(alias=alias, aliased=aliased))
92 tools.save(module_file, content)
93
94 @property
95 def _module_subfolder(self):
96 return os.path.join("lib", "cmake")
97
98 @property
99 def _module_file_rel_path(self):
100 return os.path.join(self._module_subfolder,
101 "conan-official-{}-targets.cmake".format(self.name))
102
103 def package_info(self):
104 self.cpp_info.names["cmake_find_package"] = "rapidcheck"
105 self.cpp_info.names["cmake_find_package_multi"] = "rapidcheck"
106 self.cpp_info.builddirs.append(self._module_subfolder)
107 self.cpp_info.build_modules["cmake_find_package"] = [self._module_file_rel_path]
108 self.cpp_info.build_modules["cmake_find_package_multi"] = [self._module_file_rel_path]
109 self.cpp_info.libs = ["rapidcheck"]
110 if tools.Version(self.version) < "20201218":
111 if self.options.enable_rtti:
112 self.cpp_info.defines.append("RC_USE_RTTI")
113 else:
114 if not self.options.enable_rtti:
115 self.cpp_info.defines.append("RC_DONT_USE_RTTI")
116
[end of recipes/rapidcheck/all/conanfile.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/recipes/rapidcheck/all/conanfile.py b/recipes/rapidcheck/all/conanfile.py
--- a/recipes/rapidcheck/all/conanfile.py
+++ b/recipes/rapidcheck/all/conanfile.py
@@ -51,6 +51,9 @@
if self.settings.compiler == "Visual Studio" and self.options.shared:
raise ConanInvalidConfiguration("shared is not supported using Visual Studio")
+ if 'cci' not in self.version:
+ self.output.warn("This version has been deprecated in favor of '{}/cci.{}'".format(self.name, self.version))
+
def source(self):
tools.get(**self.conan_data["sources"][self.version],
destination=self._source_subfolder, strip_root=True)
@@ -107,7 +110,11 @@
self.cpp_info.build_modules["cmake_find_package"] = [self._module_file_rel_path]
self.cpp_info.build_modules["cmake_find_package_multi"] = [self._module_file_rel_path]
self.cpp_info.libs = ["rapidcheck"]
- if tools.Version(self.version) < "20201218":
+ # Remove after 9473 is merged.
+ version = self.version
+ if version.startswith("cci."):
+ version = version[4:]
+ if version < "20201218":
if self.options.enable_rtti:
self.cpp_info.defines.append("RC_USE_RTTI")
else:
| {"golden_diff": "diff --git a/recipes/rapidcheck/all/conanfile.py b/recipes/rapidcheck/all/conanfile.py\n--- a/recipes/rapidcheck/all/conanfile.py\n+++ b/recipes/rapidcheck/all/conanfile.py\n@@ -51,6 +51,9 @@\n if self.settings.compiler == \"Visual Studio\" and self.options.shared:\n raise ConanInvalidConfiguration(\"shared is not supported using Visual Studio\")\n \n+ if 'cci' not in self.version:\n+ self.output.warn(\"This version has been deprecated in favor of '{}/cci.{}'\".format(self.name, self.version))\n+\n def source(self):\n tools.get(**self.conan_data[\"sources\"][self.version],\n destination=self._source_subfolder, strip_root=True)\n@@ -107,7 +110,11 @@\n self.cpp_info.build_modules[\"cmake_find_package\"] = [self._module_file_rel_path]\n self.cpp_info.build_modules[\"cmake_find_package_multi\"] = [self._module_file_rel_path]\n self.cpp_info.libs = [\"rapidcheck\"]\n- if tools.Version(self.version) < \"20201218\":\n+ # Remove after 9473 is merged.\n+ version = self.version\n+ if version.startswith(\"cci.\"):\n+ version = version[4:]\n+ if version < \"20201218\":\n if self.options.enable_rtti:\n self.cpp_info.defines.append(\"RC_USE_RTTI\")\n else:\n", "issue": "[request] rapidcheck/20210702\n### Package Details\r\n * Package Name/Version: **rapidcheck/20210702**\r\n\r\nThe above-mentioned version solves issue #5205 and is not yet available as a recipe. Please add this version.\r\n\n", "before_files": [{"content": "from conans import CMake, ConanFile, tools\nfrom conans.errors import ConanInvalidConfiguration\nimport os\nimport textwrap\n\nrequired_conan_version = \">=1.33.0\"\n\n\nclass RapidcheckConan(ConanFile):\n name = \"rapidcheck\"\n description = \"QuickCheck clone for C++ with the goal of being simple to use with as little boilerplate as possible\"\n url = \"https://github.com/conan-io/conan-center-index\"\n homepage = \"https://github.com/emil-e/rapidcheck\"\n license = \"BSD-2-Clause\"\n topics = \"quickcheck\", \"testing\", \"property-testing\"\n exports_sources = \"CMakeLists.txt\"\n generators = \"cmake\"\n settings = \"os\", \"arch\", \"compiler\", \"build_type\"\n options = {\n \"shared\": [True, False],\n \"fPIC\": [True, False],\n \"enable_rtti\": [True, False],\n }\n default_options = {\n \"shared\": False,\n \"fPIC\": True,\n \"enable_rtti\": True,\n }\n\n _cmake = None\n\n @property\n def _source_subfolder(self):\n return \"source_subfolder\"\n\n @property\n def _build_subfolder(self):\n return \"build_subfolder\"\n\n def config_options(self):\n if self.settings.os == \"Windows\":\n del self.options.fPIC\n\n def configure(self):\n if self.options.shared:\n del self.options.fPIC\n\n def validate(self):\n if self.settings.compiler.get_safe(\"cppstd\"):\n tools.check_min_cppstd(self, 11)\n if self.settings.compiler == \"Visual Studio\" and self.options.shared:\n raise ConanInvalidConfiguration(\"shared is not supported using Visual Studio\")\n\n def source(self):\n tools.get(**self.conan_data[\"sources\"][self.version],\n destination=self._source_subfolder, strip_root=True)\n\n def _configure_cmake(self):\n if self._cmake:\n return self._cmake\n self._cmake = CMake(self)\n self._cmake.definitions[\"RC_ENABLE_RTTI\"] = self.options.enable_rtti\n self._cmake.definitions[\"RC_ENABLE_TESTS\"] = False\n self._cmake.definitions[\"RC_ENABLE_EXAMPLES\"] = False\n self._cmake.configure(build_folder=self._build_subfolder)\n return self._cmake\n\n def build(self):\n cmake = self._configure_cmake()\n cmake.build()\n\n def package(self):\n self.copy(pattern=\"LICENSE*\", src=self._source_subfolder, dst=\"licenses\")\n cmake = self._configure_cmake()\n cmake.install()\n tools.rmdir(os.path.join(self.package_folder, \"share\"))\n self._create_cmake_module_alias_targets(\n os.path.join(self.package_folder, self._module_file_rel_path),\n {\"rapidcheck\": \"rapidcheck::rapidcheck\"}\n )\n\n @staticmethod\n def _create_cmake_module_alias_targets(module_file, targets):\n content = \"\"\n for alias, aliased in targets.items():\n content += textwrap.dedent(\"\"\"\\\n if(TARGET {aliased} AND NOT TARGET {alias})\n add_library({alias} INTERFACE IMPORTED)\n set_property(TARGET {alias} PROPERTY INTERFACE_LINK_LIBRARIES {aliased})\n endif()\n \"\"\".format(alias=alias, aliased=aliased))\n tools.save(module_file, content)\n\n @property\n def _module_subfolder(self):\n return os.path.join(\"lib\", \"cmake\")\n\n @property\n def _module_file_rel_path(self):\n return os.path.join(self._module_subfolder,\n \"conan-official-{}-targets.cmake\".format(self.name))\n\n def package_info(self):\n self.cpp_info.names[\"cmake_find_package\"] = \"rapidcheck\"\n self.cpp_info.names[\"cmake_find_package_multi\"] = \"rapidcheck\"\n self.cpp_info.builddirs.append(self._module_subfolder)\n self.cpp_info.build_modules[\"cmake_find_package\"] = [self._module_file_rel_path]\n self.cpp_info.build_modules[\"cmake_find_package_multi\"] = [self._module_file_rel_path]\n self.cpp_info.libs = [\"rapidcheck\"]\n if tools.Version(self.version) < \"20201218\":\n if self.options.enable_rtti:\n self.cpp_info.defines.append(\"RC_USE_RTTI\")\n else:\n if not self.options.enable_rtti:\n self.cpp_info.defines.append(\"RC_DONT_USE_RTTI\")\n", "path": "recipes/rapidcheck/all/conanfile.py"}]} | 1,838 | 329 |
gh_patches_debug_4594 | rasdani/github-patches | git_diff | google__turbinia-1054 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
FileArtifactExtraction Tasks failing
From a recent run:
```
* FileArtifactExtractionTask: image_export.py failed for artifact TomcatFiles - local_path not provided.
* FileArtifactExtractionTask: image_export.py failed for artifact SshdConfigFile - local_path not provided.
* FileArtifactExtractionTask: image_export.py failed for artifact RedisConfigFile - local_path not provided.
* FileArtifactExtractionTask: image_export.py failed for artifact JupyterConfigFile - local_path not provided.
* FileArtifactExtractionTask: image_export.py failed for artifact ApacheAccessLogs - local_path not provided.
* FileArtifactExtractionTask: image_export.py failed for artifact NginxAccessLogs - local_path not provided.
* FileArtifactExtractionTask: image_export.py failed for artifact GKEDockerContainerLogs - local_path not provided.
* FileArtifactExtractionTask: image_export.py failed for artifact LinuxScheduleFiles - local_path not provided.
```
</issue>
<code>
[start of turbinia/workers/artifact.py]
1 # -*- coding: utf-8 -*-
2 # Copyright 2015 Google Inc.
3 #
4 # Licensed under the Apache License, Version 2.0 (the "License");
5 # you may not use this file except in compliance with the License.
6 # You may obtain a copy of the License at
7 #
8 # http://www.apache.org/licenses/LICENSE-2.0
9 #
10 # Unless required by applicable law or agreed to in writing, software
11 # distributed under the License is distributed on an "AS IS" BASIS,
12 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 # See the License for the specific language governing permissions and
14 # limitations under the License.
15 """Task for running Plaso."""
16
17 from __future__ import unicode_literals
18
19 import os
20
21 from turbinia import config
22 from turbinia.evidence import ExportedFileArtifact
23 from turbinia.evidence import EvidenceState as state
24 from turbinia.workers import TurbiniaTask
25
26
27 class FileArtifactExtractionTask(TurbiniaTask):
28 """Task to run image_export (log2timeline)."""
29
30 REQUIRED_STATES = [state.ATTACHED]
31
32 def __init__(self, artifact_name='FileArtifact'):
33 super(FileArtifactExtractionTask, self).__init__()
34 self.artifact_name = artifact_name
35
36 def run(self, evidence, result):
37 """Extracts artifacts using Plaso image_export.py.
38
39 Args:
40 evidence (Evidence object): The evidence we will process.
41 result (TurbiniaTaskResult): The object to place task results into.
42
43 Returns:
44 TurbiniaTaskResult object.
45 """
46 config.LoadConfig()
47
48 export_directory = os.path.join(self.output_dir, 'export')
49 image_export_log = os.path.join(
50 self.output_dir, '{0:s}.log'.format(self.id))
51
52 cmd = [
53 'sudo',
54 'image_export.py',
55 '--no-hashes',
56 '--logfile',
57 image_export_log,
58 '-w',
59 export_directory,
60 '--partitions',
61 'all',
62 '--volumes',
63 'all',
64 '--unattended',
65 '--artifact_filters',
66 self.artifact_name,
67 ]
68 if config.DEBUG_TASKS or self.task_config.get('debug_tasks'):
69 cmd.append('-d')
70
71 if evidence.credentials:
72 for credential_type, credential_data in evidence.credentials:
73 cmd.extend([
74 '--credential', '{0:s}:{1:s}'.format(
75 credential_type, credential_data)
76 ])
77
78 # Path to the source image/directory.
79 cmd.append(evidence.local_path)
80 if not evidence.local_path:
81 result.log('Tried to run image_export without local_path')
82 result.close(
83 self, False,
84 'image_export.py failed for artifact {0:s} - local_path not provided.'
85 .format(self.artifact_name))
86 return result
87
88 result.log('Running image_export as [{0:s}]'.format(' '.join(cmd)))
89
90 ret, _ = self.execute(cmd, result, log_files=[image_export_log])
91 if ret:
92 result.close(
93 self, False, 'image_export.py failed for artifact {0:s}.'.format(
94 self.artifact_name))
95 return result
96
97 for dirpath, _, filenames in os.walk(export_directory):
98 for filename in filenames:
99 exported_artifact = ExportedFileArtifact(
100 artifact_name=self.artifact_name, source_path=os.path.join(
101 dirpath, filename))
102 result.log('Adding artifact {0:s}'.format(filename))
103 result.add_evidence(exported_artifact, evidence.config)
104
105 result.close(
106 self, True, 'Extracted {0:d} new {1:s} artifacts'.format(
107 len(result.evidence), self.artifact_name))
108
109 return result
110
[end of turbinia/workers/artifact.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/turbinia/workers/artifact.py b/turbinia/workers/artifact.py
--- a/turbinia/workers/artifact.py
+++ b/turbinia/workers/artifact.py
@@ -27,7 +27,7 @@
class FileArtifactExtractionTask(TurbiniaTask):
"""Task to run image_export (log2timeline)."""
- REQUIRED_STATES = [state.ATTACHED]
+ REQUIRED_STATES = [state.ATTACHED, state.CONTAINER_MOUNTED]
def __init__(self, artifact_name='FileArtifact'):
super(FileArtifactExtractionTask, self).__init__()
| {"golden_diff": "diff --git a/turbinia/workers/artifact.py b/turbinia/workers/artifact.py\n--- a/turbinia/workers/artifact.py\n+++ b/turbinia/workers/artifact.py\n@@ -27,7 +27,7 @@\n class FileArtifactExtractionTask(TurbiniaTask):\n \"\"\"Task to run image_export (log2timeline).\"\"\"\n \n- REQUIRED_STATES = [state.ATTACHED]\n+ REQUIRED_STATES = [state.ATTACHED, state.CONTAINER_MOUNTED]\n \n def __init__(self, artifact_name='FileArtifact'):\n super(FileArtifactExtractionTask, self).__init__()\n", "issue": "FileArtifactExtraction Tasks failing\nFrom a recent run:\r\n```\r\n* FileArtifactExtractionTask: image_export.py failed for artifact TomcatFiles - local_path not provided.\r\n* FileArtifactExtractionTask: image_export.py failed for artifact SshdConfigFile - local_path not provided.\r\n* FileArtifactExtractionTask: image_export.py failed for artifact RedisConfigFile - local_path not provided.\r\n* FileArtifactExtractionTask: image_export.py failed for artifact JupyterConfigFile - local_path not provided.\r\n* FileArtifactExtractionTask: image_export.py failed for artifact ApacheAccessLogs - local_path not provided.\r\n* FileArtifactExtractionTask: image_export.py failed for artifact NginxAccessLogs - local_path not provided.\r\n* FileArtifactExtractionTask: image_export.py failed for artifact GKEDockerContainerLogs - local_path not provided.\r\n* FileArtifactExtractionTask: image_export.py failed for artifact LinuxScheduleFiles - local_path not provided.\r\n```\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n# Copyright 2015 Google Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\"\"\"Task for running Plaso.\"\"\"\n\nfrom __future__ import unicode_literals\n\nimport os\n\nfrom turbinia import config\nfrom turbinia.evidence import ExportedFileArtifact\nfrom turbinia.evidence import EvidenceState as state\nfrom turbinia.workers import TurbiniaTask\n\n\nclass FileArtifactExtractionTask(TurbiniaTask):\n \"\"\"Task to run image_export (log2timeline).\"\"\"\n\n REQUIRED_STATES = [state.ATTACHED]\n\n def __init__(self, artifact_name='FileArtifact'):\n super(FileArtifactExtractionTask, self).__init__()\n self.artifact_name = artifact_name\n\n def run(self, evidence, result):\n \"\"\"Extracts artifacts using Plaso image_export.py.\n\n Args:\n evidence (Evidence object): The evidence we will process.\n result (TurbiniaTaskResult): The object to place task results into.\n\n Returns:\n TurbiniaTaskResult object.\n \"\"\"\n config.LoadConfig()\n\n export_directory = os.path.join(self.output_dir, 'export')\n image_export_log = os.path.join(\n self.output_dir, '{0:s}.log'.format(self.id))\n\n cmd = [\n 'sudo',\n 'image_export.py',\n '--no-hashes',\n '--logfile',\n image_export_log,\n '-w',\n export_directory,\n '--partitions',\n 'all',\n '--volumes',\n 'all',\n '--unattended',\n '--artifact_filters',\n self.artifact_name,\n ]\n if config.DEBUG_TASKS or self.task_config.get('debug_tasks'):\n cmd.append('-d')\n\n if evidence.credentials:\n for credential_type, credential_data in evidence.credentials:\n cmd.extend([\n '--credential', '{0:s}:{1:s}'.format(\n credential_type, credential_data)\n ])\n\n # Path to the source image/directory.\n cmd.append(evidence.local_path)\n if not evidence.local_path:\n result.log('Tried to run image_export without local_path')\n result.close(\n self, False,\n 'image_export.py failed for artifact {0:s} - local_path not provided.'\n .format(self.artifact_name))\n return result\n\n result.log('Running image_export as [{0:s}]'.format(' '.join(cmd)))\n\n ret, _ = self.execute(cmd, result, log_files=[image_export_log])\n if ret:\n result.close(\n self, False, 'image_export.py failed for artifact {0:s}.'.format(\n self.artifact_name))\n return result\n\n for dirpath, _, filenames in os.walk(export_directory):\n for filename in filenames:\n exported_artifact = ExportedFileArtifact(\n artifact_name=self.artifact_name, source_path=os.path.join(\n dirpath, filename))\n result.log('Adding artifact {0:s}'.format(filename))\n result.add_evidence(exported_artifact, evidence.config)\n\n result.close(\n self, True, 'Extracted {0:d} new {1:s} artifacts'.format(\n len(result.evidence), self.artifact_name))\n\n return result\n", "path": "turbinia/workers/artifact.py"}]} | 1,764 | 140 |
gh_patches_debug_7292 | rasdani/github-patches | git_diff | huggingface__diffusers-721 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Example unconditional training script does not work
### Describe the bug
When running the [example unconditional training script](https://github.com/huggingface/diffusers/blob/main/examples/unconditional_image_generation/train_unconditional.py)
on GPU using `--mixed_precision=fp16`, the autocasting of accelerate will break:
```
Traceback (most recent call last):
File "<path>\train_unconditional.py", line 251, in <module>
main(args)
File "<path>\train_unconditional.py", line 145, in main
loss = F.mse_loss(noise_pred, noise)
File "<lib-path>\lib\site-packages\torch\nn\functional.py", line 3269, in mse_loss
if not (target.size() == input.size()):
AttributeError: 'dict' object has no attribute 'size'
```
This happens due to the fact that in `accelerate.utils.operations.recursively_apply` the "Mapping" class is handled using a dict initialization (=> https://github.com/huggingface/accelerate/blob/main/src/accelerate/utils/operations.py#L87). This breaks the UNet2DOutput class, because it will wrap the output in a dict (because UNet2DOutput does inherit from OrderedDict).
i.e. `UNet2DOutput(sample=sample)` will become equivalent to `UNet2DOutput(sample={'sample': sample})`.
now this could be changed in the train_unconditional.py. unfortunately this just moves the problem, as it will fail in a later stage in library code that isn't accessible to the user.
### Reproduction
Run the example script with mixed-precision set to fp16:
```
train_unconditional.py --dataset_name="huggan/pokemon" --output_dir="ddpm-test-64" --mixed_precision=fp16
```
### Logs
_No response_
### System Info
- `diffusers` version: 0.3.0
- Platform: Windows-10-10.0.22000-SP0
- Python version: 3.9.13
- PyTorch version (GPU?): 1.12.1+cu116 (True)
- Huggingface_hub version: 0.9.1
- Transformers version: 4.21.3
- Using GPU in script?: yes
- Using distributed or parallel set-up in script?: no
some comments:
* i'm running on windows 11, wrongly reported as 10 using `diffusers-cli env`
* `accelerate` version: 0.12.0
</issue>
<code>
[start of examples/unconditional_image_generation/train_unconditional.py]
1 import argparse
2 import math
3 import os
4
5 import torch
6 import torch.nn.functional as F
7
8 from accelerate import Accelerator
9 from accelerate.logging import get_logger
10 from datasets import load_dataset
11 from diffusers import DDPMPipeline, DDPMScheduler, UNet2DModel
12 from diffusers.hub_utils import init_git_repo, push_to_hub
13 from diffusers.optimization import get_scheduler
14 from diffusers.training_utils import EMAModel
15 from torchvision.transforms import (
16 CenterCrop,
17 Compose,
18 InterpolationMode,
19 Normalize,
20 RandomHorizontalFlip,
21 Resize,
22 ToTensor,
23 )
24 from tqdm.auto import tqdm
25
26
27 logger = get_logger(__name__)
28
29
30 def main(args):
31 logging_dir = os.path.join(args.output_dir, args.logging_dir)
32 accelerator = Accelerator(
33 gradient_accumulation_steps=args.gradient_accumulation_steps,
34 mixed_precision=args.mixed_precision,
35 log_with="tensorboard",
36 logging_dir=logging_dir,
37 )
38
39 model = UNet2DModel(
40 sample_size=args.resolution,
41 in_channels=3,
42 out_channels=3,
43 layers_per_block=2,
44 block_out_channels=(128, 128, 256, 256, 512, 512),
45 down_block_types=(
46 "DownBlock2D",
47 "DownBlock2D",
48 "DownBlock2D",
49 "DownBlock2D",
50 "AttnDownBlock2D",
51 "DownBlock2D",
52 ),
53 up_block_types=(
54 "UpBlock2D",
55 "AttnUpBlock2D",
56 "UpBlock2D",
57 "UpBlock2D",
58 "UpBlock2D",
59 "UpBlock2D",
60 ),
61 )
62 noise_scheduler = DDPMScheduler(num_train_timesteps=1000)
63 optimizer = torch.optim.AdamW(
64 model.parameters(),
65 lr=args.learning_rate,
66 betas=(args.adam_beta1, args.adam_beta2),
67 weight_decay=args.adam_weight_decay,
68 eps=args.adam_epsilon,
69 )
70
71 augmentations = Compose(
72 [
73 Resize(args.resolution, interpolation=InterpolationMode.BILINEAR),
74 CenterCrop(args.resolution),
75 RandomHorizontalFlip(),
76 ToTensor(),
77 Normalize([0.5], [0.5]),
78 ]
79 )
80
81 if args.dataset_name is not None:
82 dataset = load_dataset(
83 args.dataset_name,
84 args.dataset_config_name,
85 cache_dir=args.cache_dir,
86 use_auth_token=True if args.use_auth_token else None,
87 split="train",
88 )
89 else:
90 dataset = load_dataset("imagefolder", data_dir=args.train_data_dir, cache_dir=args.cache_dir, split="train")
91
92 def transforms(examples):
93 images = [augmentations(image.convert("RGB")) for image in examples["image"]]
94 return {"input": images}
95
96 dataset.set_transform(transforms)
97 train_dataloader = torch.utils.data.DataLoader(dataset, batch_size=args.train_batch_size, shuffle=True)
98
99 lr_scheduler = get_scheduler(
100 args.lr_scheduler,
101 optimizer=optimizer,
102 num_warmup_steps=args.lr_warmup_steps,
103 num_training_steps=(len(train_dataloader) * args.num_epochs) // args.gradient_accumulation_steps,
104 )
105
106 model, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
107 model, optimizer, train_dataloader, lr_scheduler
108 )
109
110 num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
111
112 ema_model = EMAModel(model, inv_gamma=args.ema_inv_gamma, power=args.ema_power, max_value=args.ema_max_decay)
113
114 if args.push_to_hub:
115 repo = init_git_repo(args, at_init=True)
116
117 if accelerator.is_main_process:
118 run = os.path.split(__file__)[-1].split(".")[0]
119 accelerator.init_trackers(run)
120
121 global_step = 0
122 for epoch in range(args.num_epochs):
123 model.train()
124 progress_bar = tqdm(total=num_update_steps_per_epoch, disable=not accelerator.is_local_main_process)
125 progress_bar.set_description(f"Epoch {epoch}")
126 for step, batch in enumerate(train_dataloader):
127 clean_images = batch["input"]
128 # Sample noise that we'll add to the images
129 noise = torch.randn(clean_images.shape).to(clean_images.device)
130 bsz = clean_images.shape[0]
131 # Sample a random timestep for each image
132 timesteps = torch.randint(
133 0, noise_scheduler.config.num_train_timesteps, (bsz,), device=clean_images.device
134 ).long()
135
136 # Add noise to the clean images according to the noise magnitude at each timestep
137 # (this is the forward diffusion process)
138 noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)
139
140 with accelerator.accumulate(model):
141 # Predict the noise residual
142 noise_pred = model(noisy_images, timesteps).sample
143 loss = F.mse_loss(noise_pred, noise)
144 accelerator.backward(loss)
145
146 accelerator.clip_grad_norm_(model.parameters(), 1.0)
147 optimizer.step()
148 lr_scheduler.step()
149 if args.use_ema:
150 ema_model.step(model)
151 optimizer.zero_grad()
152
153 # Checks if the accelerator has performed an optimization step behind the scenes
154 if accelerator.sync_gradients:
155 progress_bar.update(1)
156 global_step += 1
157
158 logs = {"loss": loss.detach().item(), "lr": lr_scheduler.get_last_lr()[0], "step": global_step}
159 if args.use_ema:
160 logs["ema_decay"] = ema_model.decay
161 progress_bar.set_postfix(**logs)
162 accelerator.log(logs, step=global_step)
163 progress_bar.close()
164
165 accelerator.wait_for_everyone()
166
167 # Generate sample images for visual inspection
168 if accelerator.is_main_process:
169 if epoch % args.save_images_epochs == 0 or epoch == args.num_epochs - 1:
170 pipeline = DDPMPipeline(
171 unet=accelerator.unwrap_model(ema_model.averaged_model if args.use_ema else model),
172 scheduler=noise_scheduler,
173 )
174
175 generator = torch.manual_seed(0)
176 # run pipeline in inference (sample random noise and denoise)
177 images = pipeline(generator=generator, batch_size=args.eval_batch_size, output_type="numpy").images
178
179 # denormalize the images and save to tensorboard
180 images_processed = (images * 255).round().astype("uint8")
181 accelerator.trackers[0].writer.add_images(
182 "test_samples", images_processed.transpose(0, 3, 1, 2), epoch
183 )
184
185 if epoch % args.save_model_epochs == 0 or epoch == args.num_epochs - 1:
186 # save the model
187 if args.push_to_hub:
188 push_to_hub(args, pipeline, repo, commit_message=f"Epoch {epoch}", blocking=False)
189 else:
190 pipeline.save_pretrained(args.output_dir)
191 accelerator.wait_for_everyone()
192
193 accelerator.end_training()
194
195
196 if __name__ == "__main__":
197 parser = argparse.ArgumentParser(description="Simple example of a training script.")
198 parser.add_argument("--local_rank", type=int, default=-1)
199 parser.add_argument("--dataset_name", type=str, default=None)
200 parser.add_argument("--dataset_config_name", type=str, default=None)
201 parser.add_argument("--train_data_dir", type=str, default=None, help="A folder containing the training data.")
202 parser.add_argument("--output_dir", type=str, default="ddpm-model-64")
203 parser.add_argument("--overwrite_output_dir", action="store_true")
204 parser.add_argument("--cache_dir", type=str, default=None)
205 parser.add_argument("--resolution", type=int, default=64)
206 parser.add_argument("--train_batch_size", type=int, default=16)
207 parser.add_argument("--eval_batch_size", type=int, default=16)
208 parser.add_argument("--num_epochs", type=int, default=100)
209 parser.add_argument("--save_images_epochs", type=int, default=10)
210 parser.add_argument("--save_model_epochs", type=int, default=10)
211 parser.add_argument("--gradient_accumulation_steps", type=int, default=1)
212 parser.add_argument("--learning_rate", type=float, default=1e-4)
213 parser.add_argument("--lr_scheduler", type=str, default="cosine")
214 parser.add_argument("--lr_warmup_steps", type=int, default=500)
215 parser.add_argument("--adam_beta1", type=float, default=0.95)
216 parser.add_argument("--adam_beta2", type=float, default=0.999)
217 parser.add_argument("--adam_weight_decay", type=float, default=1e-6)
218 parser.add_argument("--adam_epsilon", type=float, default=1e-08)
219 parser.add_argument("--use_ema", action="store_true", default=True)
220 parser.add_argument("--ema_inv_gamma", type=float, default=1.0)
221 parser.add_argument("--ema_power", type=float, default=3 / 4)
222 parser.add_argument("--ema_max_decay", type=float, default=0.9999)
223 parser.add_argument("--push_to_hub", action="store_true")
224 parser.add_argument("--use_auth_token", action="store_true")
225 parser.add_argument("--hub_token", type=str, default=None)
226 parser.add_argument("--hub_model_id", type=str, default=None)
227 parser.add_argument("--hub_private_repo", action="store_true")
228 parser.add_argument("--logging_dir", type=str, default="logs")
229 parser.add_argument(
230 "--mixed_precision",
231 type=str,
232 default="no",
233 choices=["no", "fp16", "bf16"],
234 help=(
235 "Whether to use mixed precision. Choose"
236 "between fp16 and bf16 (bfloat16). Bf16 requires PyTorch >= 1.10."
237 "and an Nvidia Ampere GPU."
238 ),
239 )
240
241 args = parser.parse_args()
242 env_local_rank = int(os.environ.get("LOCAL_RANK", -1))
243 if env_local_rank != -1 and env_local_rank != args.local_rank:
244 args.local_rank = env_local_rank
245
246 if args.dataset_name is None and args.train_data_dir is None:
247 raise ValueError("You must specify either a dataset name from the hub or a train data directory.")
248
249 main(args)
250
[end of examples/unconditional_image_generation/train_unconditional.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/examples/unconditional_image_generation/train_unconditional.py b/examples/unconditional_image_generation/train_unconditional.py
--- a/examples/unconditional_image_generation/train_unconditional.py
+++ b/examples/unconditional_image_generation/train_unconditional.py
@@ -143,7 +143,8 @@
loss = F.mse_loss(noise_pred, noise)
accelerator.backward(loss)
- accelerator.clip_grad_norm_(model.parameters(), 1.0)
+ if accelerator.sync_gradients:
+ accelerator.clip_grad_norm_(model.parameters(), 1.0)
optimizer.step()
lr_scheduler.step()
if args.use_ema:
| {"golden_diff": "diff --git a/examples/unconditional_image_generation/train_unconditional.py b/examples/unconditional_image_generation/train_unconditional.py\n--- a/examples/unconditional_image_generation/train_unconditional.py\n+++ b/examples/unconditional_image_generation/train_unconditional.py\n@@ -143,7 +143,8 @@\n loss = F.mse_loss(noise_pred, noise)\n accelerator.backward(loss)\n \n- accelerator.clip_grad_norm_(model.parameters(), 1.0)\n+ if accelerator.sync_gradients:\n+ accelerator.clip_grad_norm_(model.parameters(), 1.0)\n optimizer.step()\n lr_scheduler.step()\n if args.use_ema:\n", "issue": "Example unconditional training script does not work\n### Describe the bug\n\nWhen running the [example unconditional training script](https://github.com/huggingface/diffusers/blob/main/examples/unconditional_image_generation/train_unconditional.py)\r\non GPU using `--mixed_precision=fp16`, the autocasting of accelerate will break:\r\n\r\n```\r\nTraceback (most recent call last):\r\n File \"<path>\\train_unconditional.py\", line 251, in <module>\r\n main(args)\r\n File \"<path>\\train_unconditional.py\", line 145, in main\r\n loss = F.mse_loss(noise_pred, noise)\r\n File \"<lib-path>\\lib\\site-packages\\torch\\nn\\functional.py\", line 3269, in mse_loss\r\n if not (target.size() == input.size()):\r\nAttributeError: 'dict' object has no attribute 'size'\r\n```\r\n\r\nThis happens due to the fact that in `accelerate.utils.operations.recursively_apply` the \"Mapping\" class is handled using a dict initialization (=> https://github.com/huggingface/accelerate/blob/main/src/accelerate/utils/operations.py#L87). This breaks the UNet2DOutput class, because it will wrap the output in a dict (because UNet2DOutput does inherit from OrderedDict).\r\ni.e. `UNet2DOutput(sample=sample)` will become equivalent to `UNet2DOutput(sample={'sample': sample})`.\r\n\r\nnow this could be changed in the train_unconditional.py. unfortunately this just moves the problem, as it will fail in a later stage in library code that isn't accessible to the user.\n\n### Reproduction\n\nRun the example script with mixed-precision set to fp16:\r\n```\r\ntrain_unconditional.py --dataset_name=\"huggan/pokemon\" --output_dir=\"ddpm-test-64\" --mixed_precision=fp16\r\n```\n\n### Logs\n\n_No response_\n\n### System Info\n\n- `diffusers` version: 0.3.0\r\n- Platform: Windows-10-10.0.22000-SP0\r\n- Python version: 3.9.13\r\n- PyTorch version (GPU?): 1.12.1+cu116 (True)\r\n- Huggingface_hub version: 0.9.1\r\n- Transformers version: 4.21.3\r\n- Using GPU in script?: yes\r\n- Using distributed or parallel set-up in script?: no\r\n\r\nsome comments:\r\n* i'm running on windows 11, wrongly reported as 10 using `diffusers-cli env`\r\n* `accelerate` version: 0.12.0\n", "before_files": [{"content": "import argparse\nimport math\nimport os\n\nimport torch\nimport torch.nn.functional as F\n\nfrom accelerate import Accelerator\nfrom accelerate.logging import get_logger\nfrom datasets import load_dataset\nfrom diffusers import DDPMPipeline, DDPMScheduler, UNet2DModel\nfrom diffusers.hub_utils import init_git_repo, push_to_hub\nfrom diffusers.optimization import get_scheduler\nfrom diffusers.training_utils import EMAModel\nfrom torchvision.transforms import (\n CenterCrop,\n Compose,\n InterpolationMode,\n Normalize,\n RandomHorizontalFlip,\n Resize,\n ToTensor,\n)\nfrom tqdm.auto import tqdm\n\n\nlogger = get_logger(__name__)\n\n\ndef main(args):\n logging_dir = os.path.join(args.output_dir, args.logging_dir)\n accelerator = Accelerator(\n gradient_accumulation_steps=args.gradient_accumulation_steps,\n mixed_precision=args.mixed_precision,\n log_with=\"tensorboard\",\n logging_dir=logging_dir,\n )\n\n model = UNet2DModel(\n sample_size=args.resolution,\n in_channels=3,\n out_channels=3,\n layers_per_block=2,\n block_out_channels=(128, 128, 256, 256, 512, 512),\n down_block_types=(\n \"DownBlock2D\",\n \"DownBlock2D\",\n \"DownBlock2D\",\n \"DownBlock2D\",\n \"AttnDownBlock2D\",\n \"DownBlock2D\",\n ),\n up_block_types=(\n \"UpBlock2D\",\n \"AttnUpBlock2D\",\n \"UpBlock2D\",\n \"UpBlock2D\",\n \"UpBlock2D\",\n \"UpBlock2D\",\n ),\n )\n noise_scheduler = DDPMScheduler(num_train_timesteps=1000)\n optimizer = torch.optim.AdamW(\n model.parameters(),\n lr=args.learning_rate,\n betas=(args.adam_beta1, args.adam_beta2),\n weight_decay=args.adam_weight_decay,\n eps=args.adam_epsilon,\n )\n\n augmentations = Compose(\n [\n Resize(args.resolution, interpolation=InterpolationMode.BILINEAR),\n CenterCrop(args.resolution),\n RandomHorizontalFlip(),\n ToTensor(),\n Normalize([0.5], [0.5]),\n ]\n )\n\n if args.dataset_name is not None:\n dataset = load_dataset(\n args.dataset_name,\n args.dataset_config_name,\n cache_dir=args.cache_dir,\n use_auth_token=True if args.use_auth_token else None,\n split=\"train\",\n )\n else:\n dataset = load_dataset(\"imagefolder\", data_dir=args.train_data_dir, cache_dir=args.cache_dir, split=\"train\")\n\n def transforms(examples):\n images = [augmentations(image.convert(\"RGB\")) for image in examples[\"image\"]]\n return {\"input\": images}\n\n dataset.set_transform(transforms)\n train_dataloader = torch.utils.data.DataLoader(dataset, batch_size=args.train_batch_size, shuffle=True)\n\n lr_scheduler = get_scheduler(\n args.lr_scheduler,\n optimizer=optimizer,\n num_warmup_steps=args.lr_warmup_steps,\n num_training_steps=(len(train_dataloader) * args.num_epochs) // args.gradient_accumulation_steps,\n )\n\n model, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(\n model, optimizer, train_dataloader, lr_scheduler\n )\n\n num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)\n\n ema_model = EMAModel(model, inv_gamma=args.ema_inv_gamma, power=args.ema_power, max_value=args.ema_max_decay)\n\n if args.push_to_hub:\n repo = init_git_repo(args, at_init=True)\n\n if accelerator.is_main_process:\n run = os.path.split(__file__)[-1].split(\".\")[0]\n accelerator.init_trackers(run)\n\n global_step = 0\n for epoch in range(args.num_epochs):\n model.train()\n progress_bar = tqdm(total=num_update_steps_per_epoch, disable=not accelerator.is_local_main_process)\n progress_bar.set_description(f\"Epoch {epoch}\")\n for step, batch in enumerate(train_dataloader):\n clean_images = batch[\"input\"]\n # Sample noise that we'll add to the images\n noise = torch.randn(clean_images.shape).to(clean_images.device)\n bsz = clean_images.shape[0]\n # Sample a random timestep for each image\n timesteps = torch.randint(\n 0, noise_scheduler.config.num_train_timesteps, (bsz,), device=clean_images.device\n ).long()\n\n # Add noise to the clean images according to the noise magnitude at each timestep\n # (this is the forward diffusion process)\n noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)\n\n with accelerator.accumulate(model):\n # Predict the noise residual\n noise_pred = model(noisy_images, timesteps).sample\n loss = F.mse_loss(noise_pred, noise)\n accelerator.backward(loss)\n\n accelerator.clip_grad_norm_(model.parameters(), 1.0)\n optimizer.step()\n lr_scheduler.step()\n if args.use_ema:\n ema_model.step(model)\n optimizer.zero_grad()\n\n # Checks if the accelerator has performed an optimization step behind the scenes\n if accelerator.sync_gradients:\n progress_bar.update(1)\n global_step += 1\n\n logs = {\"loss\": loss.detach().item(), \"lr\": lr_scheduler.get_last_lr()[0], \"step\": global_step}\n if args.use_ema:\n logs[\"ema_decay\"] = ema_model.decay\n progress_bar.set_postfix(**logs)\n accelerator.log(logs, step=global_step)\n progress_bar.close()\n\n accelerator.wait_for_everyone()\n\n # Generate sample images for visual inspection\n if accelerator.is_main_process:\n if epoch % args.save_images_epochs == 0 or epoch == args.num_epochs - 1:\n pipeline = DDPMPipeline(\n unet=accelerator.unwrap_model(ema_model.averaged_model if args.use_ema else model),\n scheduler=noise_scheduler,\n )\n\n generator = torch.manual_seed(0)\n # run pipeline in inference (sample random noise and denoise)\n images = pipeline(generator=generator, batch_size=args.eval_batch_size, output_type=\"numpy\").images\n\n # denormalize the images and save to tensorboard\n images_processed = (images * 255).round().astype(\"uint8\")\n accelerator.trackers[0].writer.add_images(\n \"test_samples\", images_processed.transpose(0, 3, 1, 2), epoch\n )\n\n if epoch % args.save_model_epochs == 0 or epoch == args.num_epochs - 1:\n # save the model\n if args.push_to_hub:\n push_to_hub(args, pipeline, repo, commit_message=f\"Epoch {epoch}\", blocking=False)\n else:\n pipeline.save_pretrained(args.output_dir)\n accelerator.wait_for_everyone()\n\n accelerator.end_training()\n\n\nif __name__ == \"__main__\":\n parser = argparse.ArgumentParser(description=\"Simple example of a training script.\")\n parser.add_argument(\"--local_rank\", type=int, default=-1)\n parser.add_argument(\"--dataset_name\", type=str, default=None)\n parser.add_argument(\"--dataset_config_name\", type=str, default=None)\n parser.add_argument(\"--train_data_dir\", type=str, default=None, help=\"A folder containing the training data.\")\n parser.add_argument(\"--output_dir\", type=str, default=\"ddpm-model-64\")\n parser.add_argument(\"--overwrite_output_dir\", action=\"store_true\")\n parser.add_argument(\"--cache_dir\", type=str, default=None)\n parser.add_argument(\"--resolution\", type=int, default=64)\n parser.add_argument(\"--train_batch_size\", type=int, default=16)\n parser.add_argument(\"--eval_batch_size\", type=int, default=16)\n parser.add_argument(\"--num_epochs\", type=int, default=100)\n parser.add_argument(\"--save_images_epochs\", type=int, default=10)\n parser.add_argument(\"--save_model_epochs\", type=int, default=10)\n parser.add_argument(\"--gradient_accumulation_steps\", type=int, default=1)\n parser.add_argument(\"--learning_rate\", type=float, default=1e-4)\n parser.add_argument(\"--lr_scheduler\", type=str, default=\"cosine\")\n parser.add_argument(\"--lr_warmup_steps\", type=int, default=500)\n parser.add_argument(\"--adam_beta1\", type=float, default=0.95)\n parser.add_argument(\"--adam_beta2\", type=float, default=0.999)\n parser.add_argument(\"--adam_weight_decay\", type=float, default=1e-6)\n parser.add_argument(\"--adam_epsilon\", type=float, default=1e-08)\n parser.add_argument(\"--use_ema\", action=\"store_true\", default=True)\n parser.add_argument(\"--ema_inv_gamma\", type=float, default=1.0)\n parser.add_argument(\"--ema_power\", type=float, default=3 / 4)\n parser.add_argument(\"--ema_max_decay\", type=float, default=0.9999)\n parser.add_argument(\"--push_to_hub\", action=\"store_true\")\n parser.add_argument(\"--use_auth_token\", action=\"store_true\")\n parser.add_argument(\"--hub_token\", type=str, default=None)\n parser.add_argument(\"--hub_model_id\", type=str, default=None)\n parser.add_argument(\"--hub_private_repo\", action=\"store_true\")\n parser.add_argument(\"--logging_dir\", type=str, default=\"logs\")\n parser.add_argument(\n \"--mixed_precision\",\n type=str,\n default=\"no\",\n choices=[\"no\", \"fp16\", \"bf16\"],\n help=(\n \"Whether to use mixed precision. Choose\"\n \"between fp16 and bf16 (bfloat16). Bf16 requires PyTorch >= 1.10.\"\n \"and an Nvidia Ampere GPU.\"\n ),\n )\n\n args = parser.parse_args()\n env_local_rank = int(os.environ.get(\"LOCAL_RANK\", -1))\n if env_local_rank != -1 and env_local_rank != args.local_rank:\n args.local_rank = env_local_rank\n\n if args.dataset_name is None and args.train_data_dir is None:\n raise ValueError(\"You must specify either a dataset name from the hub or a train data directory.\")\n\n main(args)\n", "path": "examples/unconditional_image_generation/train_unconditional.py"}]} | 3,995 | 134 |
gh_patches_debug_22610 | rasdani/github-patches | git_diff | netbox-community__netbox-3427 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
API Exception with invalid choice value
### Environment
* Python version: 3.5.2
* NetBox version: 2.6.2
### Steps to Reproduce
Pass a list instead of an integer for interface type when creating an interface, e.g. `[32767]` instead of `32767`
See [forum thread](https://groups.google.com/forum/#!topic/netbox-discuss/H7xIrwVnOSM)
### Expected Behavior
Value to be rejected by API as invalid
### Observed Behavior
Exception with backtrace - makes it very hard to know where the data error was.
This is because a list is not hashable, and so the test `if data not in self._choices:` raises an exception. [Code link](https://github.com/netbox-community/netbox/blob/develop/netbox/utilities/api.py#L104)
</issue>
<code>
[start of netbox/utilities/api.py]
1 from collections import OrderedDict
2
3 import pytz
4 from django.conf import settings
5 from django.contrib.contenttypes.models import ContentType
6 from django.core.exceptions import FieldError, MultipleObjectsReturned, ObjectDoesNotExist
7 from django.db.models import ManyToManyField, ProtectedError
8 from django.http import Http404
9 from rest_framework.exceptions import APIException
10 from rest_framework.permissions import BasePermission
11 from rest_framework.relations import PrimaryKeyRelatedField, RelatedField
12 from rest_framework.response import Response
13 from rest_framework.serializers import Field, ModelSerializer, ValidationError
14 from rest_framework.viewsets import ModelViewSet as _ModelViewSet, ViewSet
15
16 from .utils import dict_to_filter_params, dynamic_import
17
18
19 class ServiceUnavailable(APIException):
20 status_code = 503
21 default_detail = "Service temporarily unavailable, please try again later."
22
23
24 class SerializerNotFound(Exception):
25 pass
26
27
28 def get_serializer_for_model(model, prefix=''):
29 """
30 Dynamically resolve and return the appropriate serializer for a model.
31 """
32 app_name, model_name = model._meta.label.split('.')
33 serializer_name = '{}.api.serializers.{}{}Serializer'.format(
34 app_name, prefix, model_name
35 )
36 try:
37 return dynamic_import(serializer_name)
38 except AttributeError:
39 raise SerializerNotFound(
40 "Could not determine serializer for {}.{} with prefix '{}'".format(app_name, model_name, prefix)
41 )
42
43
44 #
45 # Authentication
46 #
47
48 class IsAuthenticatedOrLoginNotRequired(BasePermission):
49 """
50 Returns True if the user is authenticated or LOGIN_REQUIRED is False.
51 """
52 def has_permission(self, request, view):
53 if not settings.LOGIN_REQUIRED:
54 return True
55 return request.user.is_authenticated
56
57
58 #
59 # Fields
60 #
61
62 class ChoiceField(Field):
63 """
64 Represent a ChoiceField as {'value': <DB value>, 'label': <string>}.
65 """
66 def __init__(self, choices, **kwargs):
67 self._choices = dict()
68 for k, v in choices:
69 # Unpack grouped choices
70 if type(v) in [list, tuple]:
71 for k2, v2 in v:
72 self._choices[k2] = v2
73 else:
74 self._choices[k] = v
75 super().__init__(**kwargs)
76
77 def to_representation(self, obj):
78 if obj is '':
79 return None
80 data = OrderedDict([
81 ('value', obj),
82 ('label', self._choices[obj])
83 ])
84 return data
85
86 def to_internal_value(self, data):
87
88 # Provide an explicit error message if the request is trying to write a dict
89 if type(data) is dict:
90 raise ValidationError('Value must be passed directly (e.g. "foo": 123); do not use a dictionary.')
91
92 # Check for string representations of boolean/integer values
93 if hasattr(data, 'lower'):
94 if data.lower() == 'true':
95 data = True
96 elif data.lower() == 'false':
97 data = False
98 else:
99 try:
100 data = int(data)
101 except ValueError:
102 pass
103
104 if data not in self._choices:
105 raise ValidationError("{} is not a valid choice.".format(data))
106
107 return data
108
109 @property
110 def choices(self):
111 return self._choices
112
113
114 class ContentTypeField(RelatedField):
115 """
116 Represent a ContentType as '<app_label>.<model>'
117 """
118 default_error_messages = {
119 "does_not_exist": "Invalid content type: {content_type}",
120 "invalid": "Invalid value. Specify a content type as '<app_label>.<model_name>'.",
121 }
122
123 def to_internal_value(self, data):
124 try:
125 app_label, model = data.split('.')
126 return ContentType.objects.get_by_natural_key(app_label=app_label, model=model)
127 except ObjectDoesNotExist:
128 self.fail('does_not_exist', content_type=data)
129 except (TypeError, ValueError):
130 self.fail('invalid')
131
132 def to_representation(self, obj):
133 return "{}.{}".format(obj.app_label, obj.model)
134
135
136 class TimeZoneField(Field):
137 """
138 Represent a pytz time zone.
139 """
140 def to_representation(self, obj):
141 return obj.zone if obj else None
142
143 def to_internal_value(self, data):
144 if not data:
145 return ""
146 if data not in pytz.common_timezones:
147 raise ValidationError('Unknown time zone "{}" (see pytz.common_timezones for all options)'.format(data))
148 return pytz.timezone(data)
149
150
151 class SerializedPKRelatedField(PrimaryKeyRelatedField):
152 """
153 Extends PrimaryKeyRelatedField to return a serialized object on read. This is useful for representing related
154 objects in a ManyToManyField while still allowing a set of primary keys to be written.
155 """
156 def __init__(self, serializer, **kwargs):
157 self.serializer = serializer
158 self.pk_field = kwargs.pop('pk_field', None)
159 super().__init__(**kwargs)
160
161 def to_representation(self, value):
162 return self.serializer(value, context={'request': self.context['request']}).data
163
164
165 #
166 # Serializers
167 #
168
169 # TODO: We should probably take a fresh look at exactly what we're doing with this. There might be a more elegant
170 # way to enforce model validation on the serializer.
171 class ValidatedModelSerializer(ModelSerializer):
172 """
173 Extends the built-in ModelSerializer to enforce calling clean() on the associated model during validation.
174 """
175 def validate(self, data):
176
177 # Remove custom fields data and tags (if any) prior to model validation
178 attrs = data.copy()
179 attrs.pop('custom_fields', None)
180 attrs.pop('tags', None)
181
182 # Skip ManyToManyFields
183 for field in self.Meta.model._meta.get_fields():
184 if isinstance(field, ManyToManyField):
185 attrs.pop(field.name, None)
186
187 # Run clean() on an instance of the model
188 if self.instance is None:
189 instance = self.Meta.model(**attrs)
190 else:
191 instance = self.instance
192 for k, v in attrs.items():
193 setattr(instance, k, v)
194 instance.clean()
195
196 return data
197
198
199 class WritableNestedSerializer(ModelSerializer):
200 """
201 Returns a nested representation of an object on read, but accepts only a primary key on write.
202 """
203
204 def to_internal_value(self, data):
205
206 if data is None:
207 return None
208
209 # Dictionary of related object attributes
210 if isinstance(data, dict):
211 params = dict_to_filter_params(data)
212 try:
213 return self.Meta.model.objects.get(**params)
214 except ObjectDoesNotExist:
215 raise ValidationError(
216 "Related object not found using the provided attributes: {}".format(params)
217 )
218 except MultipleObjectsReturned:
219 raise ValidationError(
220 "Multiple objects match the provided attributes: {}".format(params)
221 )
222 except FieldError as e:
223 raise ValidationError(e)
224
225 # Integer PK of related object
226 if isinstance(data, int):
227 pk = data
228 else:
229 try:
230 # PK might have been mistakenly passed as a string
231 pk = int(data)
232 except (TypeError, ValueError):
233 raise ValidationError(
234 "Related objects must be referenced by numeric ID or by dictionary of attributes. Received an "
235 "unrecognized value: {}".format(data)
236 )
237
238 # Look up object by PK
239 try:
240 return self.Meta.model.objects.get(pk=int(data))
241 except ObjectDoesNotExist:
242 raise ValidationError(
243 "Related object not found using the provided numeric ID: {}".format(pk)
244 )
245
246
247 #
248 # Viewsets
249 #
250
251 class ModelViewSet(_ModelViewSet):
252 """
253 Accept either a single object or a list of objects to create.
254 """
255 def get_serializer(self, *args, **kwargs):
256
257 # If a list of objects has been provided, initialize the serializer with many=True
258 if isinstance(kwargs.get('data', {}), list):
259 kwargs['many'] = True
260
261 return super().get_serializer(*args, **kwargs)
262
263 def get_serializer_class(self):
264
265 # If 'brief' has been passed as a query param, find and return the nested serializer for this model, if one
266 # exists
267 request = self.get_serializer_context()['request']
268 if request.query_params.get('brief', False):
269 try:
270 return get_serializer_for_model(self.queryset.model, prefix='Nested')
271 except SerializerNotFound:
272 pass
273
274 # Fall back to the hard-coded serializer class
275 return self.serializer_class
276
277 def dispatch(self, request, *args, **kwargs):
278 try:
279 return super().dispatch(request, *args, **kwargs)
280 except ProtectedError as e:
281 models = ['{} ({})'.format(o, o._meta) for o in e.protected_objects.all()]
282 msg = 'Unable to delete object. The following dependent objects were found: {}'.format(', '.join(models))
283 return self.finalize_response(
284 request,
285 Response({'detail': msg}, status=409),
286 *args,
287 **kwargs
288 )
289
290 def list(self, *args, **kwargs):
291 """
292 Call to super to allow for caching
293 """
294 return super().list(*args, **kwargs)
295
296 def retrieve(self, *args, **kwargs):
297 """
298 Call to super to allow for caching
299 """
300 return super().retrieve(*args, **kwargs)
301
302
303 class FieldChoicesViewSet(ViewSet):
304 """
305 Expose the built-in numeric values which represent static choices for a model's field.
306 """
307 permission_classes = [IsAuthenticatedOrLoginNotRequired]
308 fields = []
309
310 def __init__(self, *args, **kwargs):
311 super().__init__(*args, **kwargs)
312
313 # Compile a dict of all fields in this view
314 self._fields = OrderedDict()
315 for cls, field_list in self.fields:
316 for field_name in field_list:
317
318 model_name = cls._meta.verbose_name.lower().replace(' ', '-')
319 key = ':'.join([model_name, field_name])
320
321 serializer = get_serializer_for_model(cls)()
322 choices = []
323
324 for k, v in serializer.get_fields()[field_name].choices.items():
325 if type(v) in [list, tuple]:
326 for k2, v2 in v:
327 choices.append({
328 'value': k2,
329 'label': v2,
330 })
331 else:
332 choices.append({
333 'value': k,
334 'label': v,
335 })
336 self._fields[key] = choices
337
338 def list(self, request):
339 return Response(self._fields)
340
341 def retrieve(self, request, pk):
342 if pk not in self._fields:
343 raise Http404
344 return Response(self._fields[pk])
345
346 def get_view_name(self):
347 return "Field Choices"
348
[end of netbox/utilities/api.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/netbox/utilities/api.py b/netbox/utilities/api.py
--- a/netbox/utilities/api.py
+++ b/netbox/utilities/api.py
@@ -85,9 +85,9 @@
def to_internal_value(self, data):
- # Provide an explicit error message if the request is trying to write a dict
- if type(data) is dict:
- raise ValidationError('Value must be passed directly (e.g. "foo": 123); do not use a dictionary.')
+ # Provide an explicit error message if the request is trying to write a dict or list
+ if isinstance(data, (dict, list)):
+ raise ValidationError('Value must be passed directly (e.g. "foo": 123); do not use a dictionary or list.')
# Check for string representations of boolean/integer values
if hasattr(data, 'lower'):
@@ -101,10 +101,13 @@
except ValueError:
pass
- if data not in self._choices:
- raise ValidationError("{} is not a valid choice.".format(data))
+ try:
+ if data in self._choices:
+ return data
+ except TypeError: # Input is an unhashable type
+ pass
- return data
+ raise ValidationError("{} is not a valid choice.".format(data))
@property
def choices(self):
| {"golden_diff": "diff --git a/netbox/utilities/api.py b/netbox/utilities/api.py\n--- a/netbox/utilities/api.py\n+++ b/netbox/utilities/api.py\n@@ -85,9 +85,9 @@\n \n def to_internal_value(self, data):\n \n- # Provide an explicit error message if the request is trying to write a dict\n- if type(data) is dict:\n- raise ValidationError('Value must be passed directly (e.g. \"foo\": 123); do not use a dictionary.')\n+ # Provide an explicit error message if the request is trying to write a dict or list\n+ if isinstance(data, (dict, list)):\n+ raise ValidationError('Value must be passed directly (e.g. \"foo\": 123); do not use a dictionary or list.')\n \n # Check for string representations of boolean/integer values\n if hasattr(data, 'lower'):\n@@ -101,10 +101,13 @@\n except ValueError:\n pass\n \n- if data not in self._choices:\n- raise ValidationError(\"{} is not a valid choice.\".format(data))\n+ try:\n+ if data in self._choices:\n+ return data\n+ except TypeError: # Input is an unhashable type\n+ pass\n \n- return data\n+ raise ValidationError(\"{} is not a valid choice.\".format(data))\n \n @property\n def choices(self):\n", "issue": "API Exception with invalid choice value\n### Environment\r\n* Python version: 3.5.2\r\n* NetBox version: 2.6.2\r\n\r\n### Steps to Reproduce\r\n\r\nPass a list instead of an integer for interface type when creating an interface, e.g. `[32767]` instead of `32767`\r\n\r\nSee [forum thread](https://groups.google.com/forum/#!topic/netbox-discuss/H7xIrwVnOSM)\r\n\r\n### Expected Behavior\r\n\r\nValue to be rejected by API as invalid\r\n\r\n### Observed Behavior\r\n\r\nException with backtrace - makes it very hard to know where the data error was.\r\n\r\nThis is because a list is not hashable, and so the test `if data not in self._choices:` raises an exception. [Code link](https://github.com/netbox-community/netbox/blob/develop/netbox/utilities/api.py#L104)\r\n\r\n\n", "before_files": [{"content": "from collections import OrderedDict\n\nimport pytz\nfrom django.conf import settings\nfrom django.contrib.contenttypes.models import ContentType\nfrom django.core.exceptions import FieldError, MultipleObjectsReturned, ObjectDoesNotExist\nfrom django.db.models import ManyToManyField, ProtectedError\nfrom django.http import Http404\nfrom rest_framework.exceptions import APIException\nfrom rest_framework.permissions import BasePermission\nfrom rest_framework.relations import PrimaryKeyRelatedField, RelatedField\nfrom rest_framework.response import Response\nfrom rest_framework.serializers import Field, ModelSerializer, ValidationError\nfrom rest_framework.viewsets import ModelViewSet as _ModelViewSet, ViewSet\n\nfrom .utils import dict_to_filter_params, dynamic_import\n\n\nclass ServiceUnavailable(APIException):\n status_code = 503\n default_detail = \"Service temporarily unavailable, please try again later.\"\n\n\nclass SerializerNotFound(Exception):\n pass\n\n\ndef get_serializer_for_model(model, prefix=''):\n \"\"\"\n Dynamically resolve and return the appropriate serializer for a model.\n \"\"\"\n app_name, model_name = model._meta.label.split('.')\n serializer_name = '{}.api.serializers.{}{}Serializer'.format(\n app_name, prefix, model_name\n )\n try:\n return dynamic_import(serializer_name)\n except AttributeError:\n raise SerializerNotFound(\n \"Could not determine serializer for {}.{} with prefix '{}'\".format(app_name, model_name, prefix)\n )\n\n\n#\n# Authentication\n#\n\nclass IsAuthenticatedOrLoginNotRequired(BasePermission):\n \"\"\"\n Returns True if the user is authenticated or LOGIN_REQUIRED is False.\n \"\"\"\n def has_permission(self, request, view):\n if not settings.LOGIN_REQUIRED:\n return True\n return request.user.is_authenticated\n\n\n#\n# Fields\n#\n\nclass ChoiceField(Field):\n \"\"\"\n Represent a ChoiceField as {'value': <DB value>, 'label': <string>}.\n \"\"\"\n def __init__(self, choices, **kwargs):\n self._choices = dict()\n for k, v in choices:\n # Unpack grouped choices\n if type(v) in [list, tuple]:\n for k2, v2 in v:\n self._choices[k2] = v2\n else:\n self._choices[k] = v\n super().__init__(**kwargs)\n\n def to_representation(self, obj):\n if obj is '':\n return None\n data = OrderedDict([\n ('value', obj),\n ('label', self._choices[obj])\n ])\n return data\n\n def to_internal_value(self, data):\n\n # Provide an explicit error message if the request is trying to write a dict\n if type(data) is dict:\n raise ValidationError('Value must be passed directly (e.g. \"foo\": 123); do not use a dictionary.')\n\n # Check for string representations of boolean/integer values\n if hasattr(data, 'lower'):\n if data.lower() == 'true':\n data = True\n elif data.lower() == 'false':\n data = False\n else:\n try:\n data = int(data)\n except ValueError:\n pass\n\n if data not in self._choices:\n raise ValidationError(\"{} is not a valid choice.\".format(data))\n\n return data\n\n @property\n def choices(self):\n return self._choices\n\n\nclass ContentTypeField(RelatedField):\n \"\"\"\n Represent a ContentType as '<app_label>.<model>'\n \"\"\"\n default_error_messages = {\n \"does_not_exist\": \"Invalid content type: {content_type}\",\n \"invalid\": \"Invalid value. Specify a content type as '<app_label>.<model_name>'.\",\n }\n\n def to_internal_value(self, data):\n try:\n app_label, model = data.split('.')\n return ContentType.objects.get_by_natural_key(app_label=app_label, model=model)\n except ObjectDoesNotExist:\n self.fail('does_not_exist', content_type=data)\n except (TypeError, ValueError):\n self.fail('invalid')\n\n def to_representation(self, obj):\n return \"{}.{}\".format(obj.app_label, obj.model)\n\n\nclass TimeZoneField(Field):\n \"\"\"\n Represent a pytz time zone.\n \"\"\"\n def to_representation(self, obj):\n return obj.zone if obj else None\n\n def to_internal_value(self, data):\n if not data:\n return \"\"\n if data not in pytz.common_timezones:\n raise ValidationError('Unknown time zone \"{}\" (see pytz.common_timezones for all options)'.format(data))\n return pytz.timezone(data)\n\n\nclass SerializedPKRelatedField(PrimaryKeyRelatedField):\n \"\"\"\n Extends PrimaryKeyRelatedField to return a serialized object on read. This is useful for representing related\n objects in a ManyToManyField while still allowing a set of primary keys to be written.\n \"\"\"\n def __init__(self, serializer, **kwargs):\n self.serializer = serializer\n self.pk_field = kwargs.pop('pk_field', None)\n super().__init__(**kwargs)\n\n def to_representation(self, value):\n return self.serializer(value, context={'request': self.context['request']}).data\n\n\n#\n# Serializers\n#\n\n# TODO: We should probably take a fresh look at exactly what we're doing with this. There might be a more elegant\n# way to enforce model validation on the serializer.\nclass ValidatedModelSerializer(ModelSerializer):\n \"\"\"\n Extends the built-in ModelSerializer to enforce calling clean() on the associated model during validation.\n \"\"\"\n def validate(self, data):\n\n # Remove custom fields data and tags (if any) prior to model validation\n attrs = data.copy()\n attrs.pop('custom_fields', None)\n attrs.pop('tags', None)\n\n # Skip ManyToManyFields\n for field in self.Meta.model._meta.get_fields():\n if isinstance(field, ManyToManyField):\n attrs.pop(field.name, None)\n\n # Run clean() on an instance of the model\n if self.instance is None:\n instance = self.Meta.model(**attrs)\n else:\n instance = self.instance\n for k, v in attrs.items():\n setattr(instance, k, v)\n instance.clean()\n\n return data\n\n\nclass WritableNestedSerializer(ModelSerializer):\n \"\"\"\n Returns a nested representation of an object on read, but accepts only a primary key on write.\n \"\"\"\n\n def to_internal_value(self, data):\n\n if data is None:\n return None\n\n # Dictionary of related object attributes\n if isinstance(data, dict):\n params = dict_to_filter_params(data)\n try:\n return self.Meta.model.objects.get(**params)\n except ObjectDoesNotExist:\n raise ValidationError(\n \"Related object not found using the provided attributes: {}\".format(params)\n )\n except MultipleObjectsReturned:\n raise ValidationError(\n \"Multiple objects match the provided attributes: {}\".format(params)\n )\n except FieldError as e:\n raise ValidationError(e)\n\n # Integer PK of related object\n if isinstance(data, int):\n pk = data\n else:\n try:\n # PK might have been mistakenly passed as a string\n pk = int(data)\n except (TypeError, ValueError):\n raise ValidationError(\n \"Related objects must be referenced by numeric ID or by dictionary of attributes. Received an \"\n \"unrecognized value: {}\".format(data)\n )\n\n # Look up object by PK\n try:\n return self.Meta.model.objects.get(pk=int(data))\n except ObjectDoesNotExist:\n raise ValidationError(\n \"Related object not found using the provided numeric ID: {}\".format(pk)\n )\n\n\n#\n# Viewsets\n#\n\nclass ModelViewSet(_ModelViewSet):\n \"\"\"\n Accept either a single object or a list of objects to create.\n \"\"\"\n def get_serializer(self, *args, **kwargs):\n\n # If a list of objects has been provided, initialize the serializer with many=True\n if isinstance(kwargs.get('data', {}), list):\n kwargs['many'] = True\n\n return super().get_serializer(*args, **kwargs)\n\n def get_serializer_class(self):\n\n # If 'brief' has been passed as a query param, find and return the nested serializer for this model, if one\n # exists\n request = self.get_serializer_context()['request']\n if request.query_params.get('brief', False):\n try:\n return get_serializer_for_model(self.queryset.model, prefix='Nested')\n except SerializerNotFound:\n pass\n\n # Fall back to the hard-coded serializer class\n return self.serializer_class\n\n def dispatch(self, request, *args, **kwargs):\n try:\n return super().dispatch(request, *args, **kwargs)\n except ProtectedError as e:\n models = ['{} ({})'.format(o, o._meta) for o in e.protected_objects.all()]\n msg = 'Unable to delete object. The following dependent objects were found: {}'.format(', '.join(models))\n return self.finalize_response(\n request,\n Response({'detail': msg}, status=409),\n *args,\n **kwargs\n )\n\n def list(self, *args, **kwargs):\n \"\"\"\n Call to super to allow for caching\n \"\"\"\n return super().list(*args, **kwargs)\n\n def retrieve(self, *args, **kwargs):\n \"\"\"\n Call to super to allow for caching\n \"\"\"\n return super().retrieve(*args, **kwargs)\n\n\nclass FieldChoicesViewSet(ViewSet):\n \"\"\"\n Expose the built-in numeric values which represent static choices for a model's field.\n \"\"\"\n permission_classes = [IsAuthenticatedOrLoginNotRequired]\n fields = []\n\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n\n # Compile a dict of all fields in this view\n self._fields = OrderedDict()\n for cls, field_list in self.fields:\n for field_name in field_list:\n\n model_name = cls._meta.verbose_name.lower().replace(' ', '-')\n key = ':'.join([model_name, field_name])\n\n serializer = get_serializer_for_model(cls)()\n choices = []\n\n for k, v in serializer.get_fields()[field_name].choices.items():\n if type(v) in [list, tuple]:\n for k2, v2 in v:\n choices.append({\n 'value': k2,\n 'label': v2,\n })\n else:\n choices.append({\n 'value': k,\n 'label': v,\n })\n self._fields[key] = choices\n\n def list(self, request):\n return Response(self._fields)\n\n def retrieve(self, request, pk):\n if pk not in self._fields:\n raise Http404\n return Response(self._fields[pk])\n\n def get_view_name(self):\n return \"Field Choices\"\n", "path": "netbox/utilities/api.py"}]} | 3,970 | 309 |
gh_patches_debug_27263 | rasdani/github-patches | git_diff | netket__netket-641 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Cannot create Spin hilbert with odd sites and S=1
Reported by @fabienalet
```python
>>> import netket as nk
>>> nk.hilbert.Spin(1.0, N=3, total_sz=1.0)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py", line 88, in __init__
_check_total_sz(total_sz, N)
File "/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py", line 40, in _check_total_sz
raise Exception(
Exception: Cannot fix the total magnetization: Nspins + totalSz must be even.
```
the cuprit is the second check in here: (size is number of spins)
```python
def _check_total_sz(total_sz, size):
if total_sz is None:
return
m = round(2 * total_sz)
if np.abs(m) > size:
raise Exception(
"Cannot fix the total magnetization: 2|M| cannot " "exceed Nspins."
)
if (size + m) % 2 != 0:
raise Exception(
"Cannot fix the total magnetization: Nspins + " "totalSz must be even."
)
```
The second check works only for Spins 1/2.
Can we generalise it to always work?
I'm too tired to think how to now.
Cannot create Spin hilbert with odd sites and S=1
Reported by @fabienalet
```python
>>> import netket as nk
>>> nk.hilbert.Spin(1.0, N=3, total_sz=1.0)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py", line 88, in __init__
_check_total_sz(total_sz, N)
File "/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py", line 40, in _check_total_sz
raise Exception(
Exception: Cannot fix the total magnetization: Nspins + totalSz must be even.
```
the cuprit is the second check in here: (size is number of spins)
```python
def _check_total_sz(total_sz, size):
if total_sz is None:
return
m = round(2 * total_sz)
if np.abs(m) > size:
raise Exception(
"Cannot fix the total magnetization: 2|M| cannot " "exceed Nspins."
)
if (size + m) % 2 != 0:
raise Exception(
"Cannot fix the total magnetization: Nspins + " "totalSz must be even."
)
```
The second check works only for Spins 1/2.
Can we generalise it to always work?
I'm too tired to think how to now.
Cannot create Spin hilbert with odd sites and S=1
Reported by @fabienalet
```python
>>> import netket as nk
>>> nk.hilbert.Spin(1.0, N=3, total_sz=1.0)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py", line 88, in __init__
_check_total_sz(total_sz, N)
File "/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py", line 40, in _check_total_sz
raise Exception(
Exception: Cannot fix the total magnetization: Nspins + totalSz must be even.
```
the cuprit is the second check in here: (size is number of spins)
```python
def _check_total_sz(total_sz, size):
if total_sz is None:
return
m = round(2 * total_sz)
if np.abs(m) > size:
raise Exception(
"Cannot fix the total magnetization: 2|M| cannot " "exceed Nspins."
)
if (size + m) % 2 != 0:
raise Exception(
"Cannot fix the total magnetization: Nspins + " "totalSz must be even."
)
```
The second check works only for Spins 1/2.
Can we generalise it to always work?
I'm too tired to think how to now.
</issue>
<code>
[start of netket/hilbert/spin.py]
1 # Copyright 2021 The NetKet Authors - All rights reserved.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 from fractions import Fraction
16 from typing import Optional, List, Union, Iterable
17
18 import jax
19 from jax import numpy as jnp
20 import numpy as np
21 from netket.graph import AbstractGraph
22 from numba import jit
23
24
25 from .custom_hilbert import CustomHilbert
26 from ._deprecations import graph_to_N_depwarn
27
28
29 def _check_total_sz(total_sz, size):
30 if total_sz is None:
31 return
32
33 m = round(2 * total_sz)
34 if np.abs(m) > size:
35 raise Exception(
36 "Cannot fix the total magnetization: 2|M| cannot " "exceed Nspins."
37 )
38
39 if (size + m) % 2 != 0:
40 raise Exception(
41 "Cannot fix the total magnetization: Nspins + " "totalSz must be even."
42 )
43
44
45 @jit(nopython=True)
46 def _sum_constraint(x, total_sz):
47 return np.sum(x, axis=1) == round(2 * total_sz)
48
49
50 class Spin(CustomHilbert):
51 r"""Hilbert space obtained as tensor product of local spin states."""
52
53 def __init__(
54 self,
55 s: float,
56 N: int = 1,
57 total_sz: Optional[float] = None,
58 graph: Optional[AbstractGraph] = None,
59 ):
60 r"""Hilbert space obtained as tensor product of local spin states.
61
62 Args:
63 s: Spin at each site. Must be integer or half-integer.
64 N: Number of sites (default=1)
65 total_sz: If given, constrains the total spin of system to a particular value.
66 graph: (deprecated) a graph from which to extract the number of sites.
67
68 Examples:
69 Simple spin hilbert space.
70
71 >>> from netket.hilbert import Spin
72 >>> g = Hypercube(length=10,n_dim=2,pbc=True)
73 >>> hi = Spin(s=0.5, N=4)
74 >>> print(hi.size)
75 4
76 """
77 N = graph_to_N_depwarn(N=N, graph=graph)
78
79 local_size = round(2 * s + 1)
80 local_states = np.empty(local_size)
81
82 assert int(2 * s + 1) == local_size
83
84 for i in range(local_size):
85 local_states[i] = -round(2 * s) + 2 * i
86 local_states = local_states.tolist()
87
88 _check_total_sz(total_sz, N)
89 if total_sz is not None:
90
91 def constraints(x):
92 return _sum_constraint(x, total_sz)
93
94 else:
95 constraints = None
96
97 self._total_sz = total_sz if total_sz is None else int(total_sz)
98 self._s = s
99 self._local_size = local_size
100
101 super().__init__(local_states, N, constraints)
102
103 def __pow__(self, n):
104 if self._total_sz is None:
105 total_sz = None
106 else:
107 total_sz = total_sz * n
108
109 return Spin(self._s, self.size * n, total_sz=total_sz)
110
111 def _mul_sametype_(self, other):
112 assert type(self) == type(other)
113 if self._s == other._s:
114 if self._total_sz is None and other._total_sz is None:
115 return Spin(s=self._s, N=self.size + other.size)
116
117 return NotImplemented
118
119 def ptrace(self, sites: Union[int, List]) -> Optional["Spin"]:
120 if isinstance(sites, int):
121 sites = [sites]
122
123 for site in sites:
124 if site < 0 or site >= self.size:
125 raise ValueError(
126 f"Site {site} not in this hilbert space of site {self.size}"
127 )
128
129 if self._total_sz is not None:
130 raise TypeError(
131 "Cannot take the partial trace with a total magnetization constraint."
132 )
133
134 Nsites = len(sites)
135
136 if self.size - Nsites == 0:
137 return None
138 else:
139 return Spin(s=self._s, N=self.size - Nsites)
140
141 def __repr__(self):
142 total_sz = (
143 ", total_sz={}".format(self._total_sz) if self._total_sz is not None else ""
144 )
145 return "Spin(s={}{}, N={})".format(Fraction(self._s), total_sz, self._size)
146
147 @property
148 def _attrs(self):
149 return (self.size, self._s, self._constraint_fn)
150
151 def _random_state_legacy(self, size=None, *, out=None, rgen=None):
152 if isinstance(size, int):
153 size = (size,)
154 shape = (*size, self._size) if size is not None else (self._size,)
155
156 if out is None:
157 out = np.empty(shape=shape)
158
159 if rgen is None:
160 rgen = np.random.default_rng()
161
162 if self._total_sz is None:
163 out[:] = rgen.choice(self.local_states, size=shape)
164 else:
165 # TODO: this can most likely be done more efficiently
166 if size is not None:
167 out_r = out.reshape(-1, self._size)
168 for b in range(out_r.shape[0]):
169 self._random_state_with_constraint_legacy(out_r[b], rgen)
170 else:
171 self._random_state_with_constraint_legacy(out, rgen)
172
173 return out
174
175 def _random_state_with_constraint_legacy(self, out, rgen):
176 sites = list(range(self.size))
177 out.fill(-round(2 * self._s))
178 ss = self.size
179
180 for i in range(round(self._s * self.size) + self._total_sz):
181 s = rgen.integers(0, ss, size=())
182
183 out[sites[s]] += 2
184
185 if out[sites[s]] > round(2 * self._s - 1):
186 sites.pop(s)
187 ss -= 1
188
[end of netket/hilbert/spin.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/netket/hilbert/spin.py b/netket/hilbert/spin.py
--- a/netket/hilbert/spin.py
+++ b/netket/hilbert/spin.py
@@ -26,20 +26,31 @@
from ._deprecations import graph_to_N_depwarn
-def _check_total_sz(total_sz, size):
+def _check_total_sz(total_sz, S, size):
if total_sz is None:
return
+ local_size = 2 * S + 1
+
m = round(2 * total_sz)
- if np.abs(m) > size:
- raise Exception(
+ if np.abs(m) > size * (2 * S):
+ raise ValueError(
"Cannot fix the total magnetization: 2|M| cannot " "exceed Nspins."
)
- if (size + m) % 2 != 0:
- raise Exception(
- "Cannot fix the total magnetization: Nspins + " "totalSz must be even."
- )
+ # If half-integer spins (1/2, 3/2)
+ if local_size % 2 == 0:
+ # Check that the total magnetization is odd if odd spins or even if even # of spins
+ if (size + m) % 2 != 0:
+ raise ValueError(
+ "Cannot fix the total magnetization: Nspins + 2*totalSz must be even."
+ )
+ # else if full-integer (S=1,2)
+ else:
+ if m % 2 != 0:
+ raise ValueError(
+ "Cannot fix the total magnetization to a half-integer number"
+ )
@jit(nopython=True)
@@ -85,7 +96,7 @@
local_states[i] = -round(2 * s) + 2 * i
local_states = local_states.tolist()
- _check_total_sz(total_sz, N)
+ _check_total_sz(total_sz, s, N)
if total_sz is not None:
def constraints(x):
| {"golden_diff": "diff --git a/netket/hilbert/spin.py b/netket/hilbert/spin.py\n--- a/netket/hilbert/spin.py\n+++ b/netket/hilbert/spin.py\n@@ -26,20 +26,31 @@\n from ._deprecations import graph_to_N_depwarn\n \n \n-def _check_total_sz(total_sz, size):\n+def _check_total_sz(total_sz, S, size):\n if total_sz is None:\n return\n \n+ local_size = 2 * S + 1\n+\n m = round(2 * total_sz)\n- if np.abs(m) > size:\n- raise Exception(\n+ if np.abs(m) > size * (2 * S):\n+ raise ValueError(\n \"Cannot fix the total magnetization: 2|M| cannot \" \"exceed Nspins.\"\n )\n \n- if (size + m) % 2 != 0:\n- raise Exception(\n- \"Cannot fix the total magnetization: Nspins + \" \"totalSz must be even.\"\n- )\n+ # If half-integer spins (1/2, 3/2)\n+ if local_size % 2 == 0:\n+ # Check that the total magnetization is odd if odd spins or even if even # of spins\n+ if (size + m) % 2 != 0:\n+ raise ValueError(\n+ \"Cannot fix the total magnetization: Nspins + 2*totalSz must be even.\"\n+ )\n+ # else if full-integer (S=1,2)\n+ else:\n+ if m % 2 != 0:\n+ raise ValueError(\n+ \"Cannot fix the total magnetization to a half-integer number\"\n+ )\n \n \n @jit(nopython=True)\n@@ -85,7 +96,7 @@\n local_states[i] = -round(2 * s) + 2 * i\n local_states = local_states.tolist()\n \n- _check_total_sz(total_sz, N)\n+ _check_total_sz(total_sz, s, N)\n if total_sz is not None:\n \n def constraints(x):\n", "issue": "Cannot create Spin hilbert with odd sites and S=1\nReported by @fabienalet \r\n\r\n```python\r\n>>> import netket as nk\r\n>>> nk.hilbert.Spin(1.0, N=3, total_sz=1.0)\r\nTraceback (most recent call last):\r\n File \"<stdin>\", line 1, in <module>\r\n File \"/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py\", line 88, in __init__\r\n _check_total_sz(total_sz, N)\r\n File \"/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py\", line 40, in _check_total_sz\r\n raise Exception(\r\nException: Cannot fix the total magnetization: Nspins + totalSz must be even.\r\n```\r\n\r\nthe cuprit is the second check in here: (size is number of spins)\r\n```python\r\ndef _check_total_sz(total_sz, size):\r\n if total_sz is None:\r\n return\r\n\r\n m = round(2 * total_sz)\r\n if np.abs(m) > size:\r\n raise Exception(\r\n \"Cannot fix the total magnetization: 2|M| cannot \" \"exceed Nspins.\"\r\n )\r\n\r\n if (size + m) % 2 != 0:\r\n raise Exception(\r\n \"Cannot fix the total magnetization: Nspins + \" \"totalSz must be even.\"\r\n )\r\n```\r\n\r\nThe second check works only for Spins 1/2.\r\nCan we generalise it to always work?\r\nI'm too tired to think how to now.\r\n\nCannot create Spin hilbert with odd sites and S=1\nReported by @fabienalet \r\n\r\n```python\r\n>>> import netket as nk\r\n>>> nk.hilbert.Spin(1.0, N=3, total_sz=1.0)\r\nTraceback (most recent call last):\r\n File \"<stdin>\", line 1, in <module>\r\n File \"/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py\", line 88, in __init__\r\n _check_total_sz(total_sz, N)\r\n File \"/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py\", line 40, in _check_total_sz\r\n raise Exception(\r\nException: Cannot fix the total magnetization: Nspins + totalSz must be even.\r\n```\r\n\r\nthe cuprit is the second check in here: (size is number of spins)\r\n```python\r\ndef _check_total_sz(total_sz, size):\r\n if total_sz is None:\r\n return\r\n\r\n m = round(2 * total_sz)\r\n if np.abs(m) > size:\r\n raise Exception(\r\n \"Cannot fix the total magnetization: 2|M| cannot \" \"exceed Nspins.\"\r\n )\r\n\r\n if (size + m) % 2 != 0:\r\n raise Exception(\r\n \"Cannot fix the total magnetization: Nspins + \" \"totalSz must be even.\"\r\n )\r\n```\r\n\r\nThe second check works only for Spins 1/2.\r\nCan we generalise it to always work?\r\nI'm too tired to think how to now.\r\n\nCannot create Spin hilbert with odd sites and S=1\nReported by @fabienalet \r\n\r\n```python\r\n>>> import netket as nk\r\n>>> nk.hilbert.Spin(1.0, N=3, total_sz=1.0)\r\nTraceback (most recent call last):\r\n File \"<stdin>\", line 1, in <module>\r\n File \"/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py\", line 88, in __init__\r\n _check_total_sz(total_sz, N)\r\n File \"/home/filippovicentini/Dropbox/Ricerca/Codes/Python/netket/netket/hilbert/spin.py\", line 40, in _check_total_sz\r\n raise Exception(\r\nException: Cannot fix the total magnetization: Nspins + totalSz must be even.\r\n```\r\n\r\nthe cuprit is the second check in here: (size is number of spins)\r\n```python\r\ndef _check_total_sz(total_sz, size):\r\n if total_sz is None:\r\n return\r\n\r\n m = round(2 * total_sz)\r\n if np.abs(m) > size:\r\n raise Exception(\r\n \"Cannot fix the total magnetization: 2|M| cannot \" \"exceed Nspins.\"\r\n )\r\n\r\n if (size + m) % 2 != 0:\r\n raise Exception(\r\n \"Cannot fix the total magnetization: Nspins + \" \"totalSz must be even.\"\r\n )\r\n```\r\n\r\nThe second check works only for Spins 1/2.\r\nCan we generalise it to always work?\r\nI'm too tired to think how to now.\r\n\n", "before_files": [{"content": "# Copyright 2021 The NetKet Authors - All rights reserved.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom fractions import Fraction\nfrom typing import Optional, List, Union, Iterable\n\nimport jax\nfrom jax import numpy as jnp\nimport numpy as np\nfrom netket.graph import AbstractGraph\nfrom numba import jit\n\n\nfrom .custom_hilbert import CustomHilbert\nfrom ._deprecations import graph_to_N_depwarn\n\n\ndef _check_total_sz(total_sz, size):\n if total_sz is None:\n return\n\n m = round(2 * total_sz)\n if np.abs(m) > size:\n raise Exception(\n \"Cannot fix the total magnetization: 2|M| cannot \" \"exceed Nspins.\"\n )\n\n if (size + m) % 2 != 0:\n raise Exception(\n \"Cannot fix the total magnetization: Nspins + \" \"totalSz must be even.\"\n )\n\n\n@jit(nopython=True)\ndef _sum_constraint(x, total_sz):\n return np.sum(x, axis=1) == round(2 * total_sz)\n\n\nclass Spin(CustomHilbert):\n r\"\"\"Hilbert space obtained as tensor product of local spin states.\"\"\"\n\n def __init__(\n self,\n s: float,\n N: int = 1,\n total_sz: Optional[float] = None,\n graph: Optional[AbstractGraph] = None,\n ):\n r\"\"\"Hilbert space obtained as tensor product of local spin states.\n\n Args:\n s: Spin at each site. Must be integer or half-integer.\n N: Number of sites (default=1)\n total_sz: If given, constrains the total spin of system to a particular value.\n graph: (deprecated) a graph from which to extract the number of sites.\n\n Examples:\n Simple spin hilbert space.\n\n >>> from netket.hilbert import Spin\n >>> g = Hypercube(length=10,n_dim=2,pbc=True)\n >>> hi = Spin(s=0.5, N=4)\n >>> print(hi.size)\n 4\n \"\"\"\n N = graph_to_N_depwarn(N=N, graph=graph)\n\n local_size = round(2 * s + 1)\n local_states = np.empty(local_size)\n\n assert int(2 * s + 1) == local_size\n\n for i in range(local_size):\n local_states[i] = -round(2 * s) + 2 * i\n local_states = local_states.tolist()\n\n _check_total_sz(total_sz, N)\n if total_sz is not None:\n\n def constraints(x):\n return _sum_constraint(x, total_sz)\n\n else:\n constraints = None\n\n self._total_sz = total_sz if total_sz is None else int(total_sz)\n self._s = s\n self._local_size = local_size\n\n super().__init__(local_states, N, constraints)\n\n def __pow__(self, n):\n if self._total_sz is None:\n total_sz = None\n else:\n total_sz = total_sz * n\n\n return Spin(self._s, self.size * n, total_sz=total_sz)\n\n def _mul_sametype_(self, other):\n assert type(self) == type(other)\n if self._s == other._s:\n if self._total_sz is None and other._total_sz is None:\n return Spin(s=self._s, N=self.size + other.size)\n\n return NotImplemented\n\n def ptrace(self, sites: Union[int, List]) -> Optional[\"Spin\"]:\n if isinstance(sites, int):\n sites = [sites]\n\n for site in sites:\n if site < 0 or site >= self.size:\n raise ValueError(\n f\"Site {site} not in this hilbert space of site {self.size}\"\n )\n\n if self._total_sz is not None:\n raise TypeError(\n \"Cannot take the partial trace with a total magnetization constraint.\"\n )\n\n Nsites = len(sites)\n\n if self.size - Nsites == 0:\n return None\n else:\n return Spin(s=self._s, N=self.size - Nsites)\n\n def __repr__(self):\n total_sz = (\n \", total_sz={}\".format(self._total_sz) if self._total_sz is not None else \"\"\n )\n return \"Spin(s={}{}, N={})\".format(Fraction(self._s), total_sz, self._size)\n\n @property\n def _attrs(self):\n return (self.size, self._s, self._constraint_fn)\n\n def _random_state_legacy(self, size=None, *, out=None, rgen=None):\n if isinstance(size, int):\n size = (size,)\n shape = (*size, self._size) if size is not None else (self._size,)\n\n if out is None:\n out = np.empty(shape=shape)\n\n if rgen is None:\n rgen = np.random.default_rng()\n\n if self._total_sz is None:\n out[:] = rgen.choice(self.local_states, size=shape)\n else:\n # TODO: this can most likely be done more efficiently\n if size is not None:\n out_r = out.reshape(-1, self._size)\n for b in range(out_r.shape[0]):\n self._random_state_with_constraint_legacy(out_r[b], rgen)\n else:\n self._random_state_with_constraint_legacy(out, rgen)\n\n return out\n\n def _random_state_with_constraint_legacy(self, out, rgen):\n sites = list(range(self.size))\n out.fill(-round(2 * self._s))\n ss = self.size\n\n for i in range(round(self._s * self.size) + self._total_sz):\n s = rgen.integers(0, ss, size=())\n\n out[sites[s]] += 2\n\n if out[sites[s]] > round(2 * self._s - 1):\n sites.pop(s)\n ss -= 1\n", "path": "netket/hilbert/spin.py"}]} | 3,503 | 472 |
gh_patches_debug_10558 | rasdani/github-patches | git_diff | numpy__numpy-6174 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Documentation fix for routines.fft (Trac #1531)
_Original ticket http://projects.scipy.org/numpy/ticket/1531 on 2010-06-30 by trac user valhallasw, assigned to unknown._
http://docs.scipy.org/doc/numpy/reference/routines.fft.html reads:
```
If A = fft(a, n), then A[0] contains the zero-frequency term (the mean of the signal), which is always purely real for real inputs.
```
This is, however, incorrect. A[0] contains the zero-frequency term _multiplied by the number of data points_.
The same error is in more docs, for example http://docs.scipy.org/doc/numpy/reference/generated/numpy.fft.rfft.html#numpy.fft.rfft.
</issue>
<code>
[start of numpy/fft/info.py]
1 """
2 Discrete Fourier Transform (:mod:`numpy.fft`)
3 =============================================
4
5 .. currentmodule:: numpy.fft
6
7 Standard FFTs
8 -------------
9
10 .. autosummary::
11 :toctree: generated/
12
13 fft Discrete Fourier transform.
14 ifft Inverse discrete Fourier transform.
15 fft2 Discrete Fourier transform in two dimensions.
16 ifft2 Inverse discrete Fourier transform in two dimensions.
17 fftn Discrete Fourier transform in N-dimensions.
18 ifftn Inverse discrete Fourier transform in N dimensions.
19
20 Real FFTs
21 ---------
22
23 .. autosummary::
24 :toctree: generated/
25
26 rfft Real discrete Fourier transform.
27 irfft Inverse real discrete Fourier transform.
28 rfft2 Real discrete Fourier transform in two dimensions.
29 irfft2 Inverse real discrete Fourier transform in two dimensions.
30 rfftn Real discrete Fourier transform in N dimensions.
31 irfftn Inverse real discrete Fourier transform in N dimensions.
32
33 Hermitian FFTs
34 --------------
35
36 .. autosummary::
37 :toctree: generated/
38
39 hfft Hermitian discrete Fourier transform.
40 ihfft Inverse Hermitian discrete Fourier transform.
41
42 Helper routines
43 ---------------
44
45 .. autosummary::
46 :toctree: generated/
47
48 fftfreq Discrete Fourier Transform sample frequencies.
49 rfftfreq DFT sample frequencies (for usage with rfft, irfft).
50 fftshift Shift zero-frequency component to center of spectrum.
51 ifftshift Inverse of fftshift.
52
53
54 Background information
55 ----------------------
56
57 Fourier analysis is fundamentally a method for expressing a function as a
58 sum of periodic components, and for recovering the function from those
59 components. When both the function and its Fourier transform are
60 replaced with discretized counterparts, it is called the discrete Fourier
61 transform (DFT). The DFT has become a mainstay of numerical computing in
62 part because of a very fast algorithm for computing it, called the Fast
63 Fourier Transform (FFT), which was known to Gauss (1805) and was brought
64 to light in its current form by Cooley and Tukey [CT]_. Press et al. [NR]_
65 provide an accessible introduction to Fourier analysis and its
66 applications.
67
68 Because the discrete Fourier transform separates its input into
69 components that contribute at discrete frequencies, it has a great number
70 of applications in digital signal processing, e.g., for filtering, and in
71 this context the discretized input to the transform is customarily
72 referred to as a *signal*, which exists in the *time domain*. The output
73 is called a *spectrum* or *transform* and exists in the *frequency
74 domain*.
75
76 Implementation details
77 ----------------------
78
79 There are many ways to define the DFT, varying in the sign of the
80 exponent, normalization, etc. In this implementation, the DFT is defined
81 as
82
83 .. math::
84 A_k = \\sum_{m=0}^{n-1} a_m \\exp\\left\\{-2\\pi i{mk \\over n}\\right\\}
85 \\qquad k = 0,\\ldots,n-1.
86
87 The DFT is in general defined for complex inputs and outputs, and a
88 single-frequency component at linear frequency :math:`f` is
89 represented by a complex exponential
90 :math:`a_m = \\exp\\{2\\pi i\\,f m\\Delta t\\}`, where :math:`\\Delta t`
91 is the sampling interval.
92
93 The values in the result follow so-called "standard" order: If ``A =
94 fft(a, n)``, then ``A[0]`` contains the zero-frequency term (the mean of
95 the signal), which is always purely real for real inputs. Then ``A[1:n/2]``
96 contains the positive-frequency terms, and ``A[n/2+1:]`` contains the
97 negative-frequency terms, in order of decreasingly negative frequency.
98 For an even number of input points, ``A[n/2]`` represents both positive and
99 negative Nyquist frequency, and is also purely real for real input. For
100 an odd number of input points, ``A[(n-1)/2]`` contains the largest positive
101 frequency, while ``A[(n+1)/2]`` contains the largest negative frequency.
102 The routine ``np.fft.fftfreq(n)`` returns an array giving the frequencies
103 of corresponding elements in the output. The routine
104 ``np.fft.fftshift(A)`` shifts transforms and their frequencies to put the
105 zero-frequency components in the middle, and ``np.fft.ifftshift(A)`` undoes
106 that shift.
107
108 When the input `a` is a time-domain signal and ``A = fft(a)``, ``np.abs(A)``
109 is its amplitude spectrum and ``np.abs(A)**2`` is its power spectrum.
110 The phase spectrum is obtained by ``np.angle(A)``.
111
112 The inverse DFT is defined as
113
114 .. math::
115 a_m = \\frac{1}{n}\\sum_{k=0}^{n-1}A_k\\exp\\left\\{2\\pi i{mk\\over n}\\right\\}
116 \\qquad m = 0,\\ldots,n-1.
117
118 It differs from the forward transform by the sign of the exponential
119 argument and the default normalization by :math:`1/n`.
120
121 Normalization
122 -------------
123 The default normalization has the direct transforms unscaled and the inverse
124 transforms are scaled by :math:`1/n`. It is possible to obtain unitary
125 transforms by setting the keyword argument ``norm`` to ``"ortho"`` (default is
126 `None`) so that both direct and inverse transforms will be scaled by
127 :math:`1/\\sqrt{n}`.
128
129 Real and Hermitian transforms
130 -----------------------------
131
132 When the input is purely real, its transform is Hermitian, i.e., the
133 component at frequency :math:`f_k` is the complex conjugate of the
134 component at frequency :math:`-f_k`, which means that for real
135 inputs there is no information in the negative frequency components that
136 is not already available from the positive frequency components.
137 The family of `rfft` functions is
138 designed to operate on real inputs, and exploits this symmetry by
139 computing only the positive frequency components, up to and including the
140 Nyquist frequency. Thus, ``n`` input points produce ``n/2+1`` complex
141 output points. The inverses of this family assumes the same symmetry of
142 its input, and for an output of ``n`` points uses ``n/2+1`` input points.
143
144 Correspondingly, when the spectrum is purely real, the signal is
145 Hermitian. The `hfft` family of functions exploits this symmetry by
146 using ``n/2+1`` complex points in the input (time) domain for ``n`` real
147 points in the frequency domain.
148
149 In higher dimensions, FFTs are used, e.g., for image analysis and
150 filtering. The computational efficiency of the FFT means that it can
151 also be a faster way to compute large convolutions, using the property
152 that a convolution in the time domain is equivalent to a point-by-point
153 multiplication in the frequency domain.
154
155 Higher dimensions
156 -----------------
157
158 In two dimensions, the DFT is defined as
159
160 .. math::
161 A_{kl} = \\sum_{m=0}^{M-1} \\sum_{n=0}^{N-1}
162 a_{mn}\\exp\\left\\{-2\\pi i \\left({mk\\over M}+{nl\\over N}\\right)\\right\\}
163 \\qquad k = 0, \\ldots, M-1;\\quad l = 0, \\ldots, N-1,
164
165 which extends in the obvious way to higher dimensions, and the inverses
166 in higher dimensions also extend in the same way.
167
168 References
169 ----------
170
171 .. [CT] Cooley, James W., and John W. Tukey, 1965, "An algorithm for the
172 machine calculation of complex Fourier series," *Math. Comput.*
173 19: 297-301.
174
175 .. [NR] Press, W., Teukolsky, S., Vetterline, W.T., and Flannery, B.P.,
176 2007, *Numerical Recipes: The Art of Scientific Computing*, ch.
177 12-13. Cambridge Univ. Press, Cambridge, UK.
178
179 Examples
180 --------
181
182 For examples, see the various functions.
183
184 """
185 from __future__ import division, absolute_import, print_function
186
187 depends = ['core']
188
[end of numpy/fft/info.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/numpy/fft/info.py b/numpy/fft/info.py
--- a/numpy/fft/info.py
+++ b/numpy/fft/info.py
@@ -91,7 +91,7 @@
is the sampling interval.
The values in the result follow so-called "standard" order: If ``A =
-fft(a, n)``, then ``A[0]`` contains the zero-frequency term (the mean of
+fft(a, n)``, then ``A[0]`` contains the zero-frequency term (the sum of
the signal), which is always purely real for real inputs. Then ``A[1:n/2]``
contains the positive-frequency terms, and ``A[n/2+1:]`` contains the
negative-frequency terms, in order of decreasingly negative frequency.
| {"golden_diff": "diff --git a/numpy/fft/info.py b/numpy/fft/info.py\n--- a/numpy/fft/info.py\n+++ b/numpy/fft/info.py\n@@ -91,7 +91,7 @@\n is the sampling interval.\n \n The values in the result follow so-called \"standard\" order: If ``A =\n-fft(a, n)``, then ``A[0]`` contains the zero-frequency term (the mean of\n+fft(a, n)``, then ``A[0]`` contains the zero-frequency term (the sum of\n the signal), which is always purely real for real inputs. Then ``A[1:n/2]``\n contains the positive-frequency terms, and ``A[n/2+1:]`` contains the\n negative-frequency terms, in order of decreasingly negative frequency.\n", "issue": "Documentation fix for routines.fft (Trac #1531)\n_Original ticket http://projects.scipy.org/numpy/ticket/1531 on 2010-06-30 by trac user valhallasw, assigned to unknown._\n\nhttp://docs.scipy.org/doc/numpy/reference/routines.fft.html reads:\n\n```\nIf A = fft(a, n), then A[0] contains the zero-frequency term (the mean of the signal), which is always purely real for real inputs.\n```\n\nThis is, however, incorrect. A[0] contains the zero-frequency term _multiplied by the number of data points_.\n\nThe same error is in more docs, for example http://docs.scipy.org/doc/numpy/reference/generated/numpy.fft.rfft.html#numpy.fft.rfft.\n\n", "before_files": [{"content": "\"\"\"\nDiscrete Fourier Transform (:mod:`numpy.fft`)\n=============================================\n\n.. currentmodule:: numpy.fft\n\nStandard FFTs\n-------------\n\n.. autosummary::\n :toctree: generated/\n\n fft Discrete Fourier transform.\n ifft Inverse discrete Fourier transform.\n fft2 Discrete Fourier transform in two dimensions.\n ifft2 Inverse discrete Fourier transform in two dimensions.\n fftn Discrete Fourier transform in N-dimensions.\n ifftn Inverse discrete Fourier transform in N dimensions.\n\nReal FFTs\n---------\n\n.. autosummary::\n :toctree: generated/\n\n rfft Real discrete Fourier transform.\n irfft Inverse real discrete Fourier transform.\n rfft2 Real discrete Fourier transform in two dimensions.\n irfft2 Inverse real discrete Fourier transform in two dimensions.\n rfftn Real discrete Fourier transform in N dimensions.\n irfftn Inverse real discrete Fourier transform in N dimensions.\n\nHermitian FFTs\n--------------\n\n.. autosummary::\n :toctree: generated/\n\n hfft Hermitian discrete Fourier transform.\n ihfft Inverse Hermitian discrete Fourier transform.\n\nHelper routines\n---------------\n\n.. autosummary::\n :toctree: generated/\n\n fftfreq Discrete Fourier Transform sample frequencies.\n rfftfreq DFT sample frequencies (for usage with rfft, irfft).\n fftshift Shift zero-frequency component to center of spectrum.\n ifftshift Inverse of fftshift.\n\n\nBackground information\n----------------------\n\nFourier analysis is fundamentally a method for expressing a function as a\nsum of periodic components, and for recovering the function from those\ncomponents. When both the function and its Fourier transform are\nreplaced with discretized counterparts, it is called the discrete Fourier\ntransform (DFT). The DFT has become a mainstay of numerical computing in\npart because of a very fast algorithm for computing it, called the Fast\nFourier Transform (FFT), which was known to Gauss (1805) and was brought\nto light in its current form by Cooley and Tukey [CT]_. Press et al. [NR]_\nprovide an accessible introduction to Fourier analysis and its\napplications.\n\nBecause the discrete Fourier transform separates its input into\ncomponents that contribute at discrete frequencies, it has a great number\nof applications in digital signal processing, e.g., for filtering, and in\nthis context the discretized input to the transform is customarily\nreferred to as a *signal*, which exists in the *time domain*. The output\nis called a *spectrum* or *transform* and exists in the *frequency\ndomain*.\n\nImplementation details\n----------------------\n\nThere are many ways to define the DFT, varying in the sign of the\nexponent, normalization, etc. In this implementation, the DFT is defined\nas\n\n.. math::\n A_k = \\\\sum_{m=0}^{n-1} a_m \\\\exp\\\\left\\\\{-2\\\\pi i{mk \\\\over n}\\\\right\\\\}\n \\\\qquad k = 0,\\\\ldots,n-1.\n\nThe DFT is in general defined for complex inputs and outputs, and a\nsingle-frequency component at linear frequency :math:`f` is\nrepresented by a complex exponential\n:math:`a_m = \\\\exp\\\\{2\\\\pi i\\\\,f m\\\\Delta t\\\\}`, where :math:`\\\\Delta t`\nis the sampling interval.\n\nThe values in the result follow so-called \"standard\" order: If ``A =\nfft(a, n)``, then ``A[0]`` contains the zero-frequency term (the mean of\nthe signal), which is always purely real for real inputs. Then ``A[1:n/2]``\ncontains the positive-frequency terms, and ``A[n/2+1:]`` contains the\nnegative-frequency terms, in order of decreasingly negative frequency.\nFor an even number of input points, ``A[n/2]`` represents both positive and\nnegative Nyquist frequency, and is also purely real for real input. For\nan odd number of input points, ``A[(n-1)/2]`` contains the largest positive\nfrequency, while ``A[(n+1)/2]`` contains the largest negative frequency.\nThe routine ``np.fft.fftfreq(n)`` returns an array giving the frequencies\nof corresponding elements in the output. The routine\n``np.fft.fftshift(A)`` shifts transforms and their frequencies to put the\nzero-frequency components in the middle, and ``np.fft.ifftshift(A)`` undoes\nthat shift.\n\nWhen the input `a` is a time-domain signal and ``A = fft(a)``, ``np.abs(A)``\nis its amplitude spectrum and ``np.abs(A)**2`` is its power spectrum.\nThe phase spectrum is obtained by ``np.angle(A)``.\n\nThe inverse DFT is defined as\n\n.. math::\n a_m = \\\\frac{1}{n}\\\\sum_{k=0}^{n-1}A_k\\\\exp\\\\left\\\\{2\\\\pi i{mk\\\\over n}\\\\right\\\\}\n \\\\qquad m = 0,\\\\ldots,n-1.\n\nIt differs from the forward transform by the sign of the exponential\nargument and the default normalization by :math:`1/n`.\n\nNormalization\n-------------\nThe default normalization has the direct transforms unscaled and the inverse\ntransforms are scaled by :math:`1/n`. It is possible to obtain unitary\ntransforms by setting the keyword argument ``norm`` to ``\"ortho\"`` (default is\n`None`) so that both direct and inverse transforms will be scaled by\n:math:`1/\\\\sqrt{n}`.\n\nReal and Hermitian transforms\n-----------------------------\n\nWhen the input is purely real, its transform is Hermitian, i.e., the\ncomponent at frequency :math:`f_k` is the complex conjugate of the\ncomponent at frequency :math:`-f_k`, which means that for real\ninputs there is no information in the negative frequency components that\nis not already available from the positive frequency components.\nThe family of `rfft` functions is\ndesigned to operate on real inputs, and exploits this symmetry by\ncomputing only the positive frequency components, up to and including the\nNyquist frequency. Thus, ``n`` input points produce ``n/2+1`` complex\noutput points. The inverses of this family assumes the same symmetry of\nits input, and for an output of ``n`` points uses ``n/2+1`` input points.\n\nCorrespondingly, when the spectrum is purely real, the signal is\nHermitian. The `hfft` family of functions exploits this symmetry by\nusing ``n/2+1`` complex points in the input (time) domain for ``n`` real\npoints in the frequency domain.\n\nIn higher dimensions, FFTs are used, e.g., for image analysis and\nfiltering. The computational efficiency of the FFT means that it can\nalso be a faster way to compute large convolutions, using the property\nthat a convolution in the time domain is equivalent to a point-by-point\nmultiplication in the frequency domain.\n\nHigher dimensions\n-----------------\n\nIn two dimensions, the DFT is defined as\n\n.. math::\n A_{kl} = \\\\sum_{m=0}^{M-1} \\\\sum_{n=0}^{N-1}\n a_{mn}\\\\exp\\\\left\\\\{-2\\\\pi i \\\\left({mk\\\\over M}+{nl\\\\over N}\\\\right)\\\\right\\\\}\n \\\\qquad k = 0, \\\\ldots, M-1;\\\\quad l = 0, \\\\ldots, N-1,\n\nwhich extends in the obvious way to higher dimensions, and the inverses\nin higher dimensions also extend in the same way.\n\nReferences\n----------\n\n.. [CT] Cooley, James W., and John W. Tukey, 1965, \"An algorithm for the\n machine calculation of complex Fourier series,\" *Math. Comput.*\n 19: 297-301.\n\n.. [NR] Press, W., Teukolsky, S., Vetterline, W.T., and Flannery, B.P.,\n 2007, *Numerical Recipes: The Art of Scientific Computing*, ch.\n 12-13. Cambridge Univ. Press, Cambridge, UK.\n\nExamples\n--------\n\nFor examples, see the various functions.\n\n\"\"\"\nfrom __future__ import division, absolute_import, print_function\n\ndepends = ['core']\n", "path": "numpy/fft/info.py"}]} | 3,013 | 172 |
gh_patches_debug_17865 | rasdani/github-patches | git_diff | pypa__pipenv-6072 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Test suite immediately aborts with a successful exit code whenever a test that does a `pipenv run` executes
Check this out:
```python
$ time pytest
=============================================== test session starts ================================================
platform linux -- Python 3.8.10, pytest-6.2.5, py-1.11.0, pluggy-1.0.0
rootdir: /home/jeremy/src/github.com/pypa/pipenv, configfile: setup.cfg, testpaths: tests
plugins: timeout-2.0.1, xdist-2.4.0, flaky-3.7.0, forked-1.3.0, pypi-0.1.1
collected 274 items
tests/integration/test_cli.py ...
real 7.14s
user 4.30s
sys 0.73s
$ echo $?
0
```
I know we don't have a 7 second test suite with only 3 tests in it! Also, where did pipenv's normal test summary go?
In the example above, we've run the first 3 tests of test_cli.py and the test suite aborted when running the 4th test: `test_pipenv_site_packages`. The whole test suite aborts when we get to this `pipenv run` invocation:
https://github.com/pypa/pipenv/blob/b0ebaf054e9b47fc90f6939b2473e31863da15a3/tests/integration/test_cli.py#L52
This doesn't happen in CI. It took me **forever** to figure out what's going on here. Here's the full story:
- That call to `p.pipenv` uses `click`'s [`invoke` method](https://click.palletsprojects.com/en/8.0.x/api/#click.testing.CliRunner.invoke) internally. That method internally starts executing pipenv (note that this is happening in the same python testrunner process, there is no forking going on here!)
- Eventually we get into the actual guts of `pipenv run`, which (on my Linux machine) means we execute [this call to `os.execve` in `do_run_posix`](https://github.com/pypa/pipenv/blob/b0ebaf054e9b47fc90f6939b2473e31863da15a3/pipenv/core.py#L2451-L2455). *This completely replaces the pytest process we were in the middle of*, and when the (now just pipenv) process exits, our entire test suite grinds to a halt and exits successfully. Yikes :exploding_head:!
- This doesn't happen in CI because we actually use `do_run_nt` (:interrobang:) in CI: https://github.com/pypa/pipenv/blob/b0ebaf054e9b47fc90f6939b2473e31863da15a3/pipenv/core.py#L2499-L2502. It looks like @frostming added this in https://github.com/pypa/pipenv/pull/4757/files#diff-ef852c4ac364f946819f765a6bc26f04f1b0968f31fc512949a60fa2ab0685e8R2488, presumably as a workaround for this very problem?
- (For the record, if you're running pytest with parallelism enabled, you'll see error messages like "node down: Not properly terminated" and "replacing crashed worker gw3" as the workers turn into pipenv processes and exit).
I've been able to work around this problem by explicitly setting the `CI` environment variable when running tests locally. I'll send in a PR to improve the documentation, but we might want to rework this a bit. It feels a bit off to require people to pretend to be in CI just to run tests.
</issue>
<code>
[start of pipenv/routines/shell.py]
1 import os
2 import subprocess
3 import sys
4 from os.path import expandvars
5
6 from pipenv import environments
7 from pipenv.utils.project import ensure_project
8 from pipenv.utils.shell import cmd_list_to_shell, system_which
9 from pipenv.vendor import click
10
11
12 def do_shell(
13 project, python=False, fancy=False, shell_args=None, pypi_mirror=None, quiet=False
14 ):
15 # Ensure that virtualenv is available.
16 ensure_project(
17 project,
18 python=python,
19 validate=False,
20 pypi_mirror=pypi_mirror,
21 )
22
23 # Support shell compatibility mode.
24 if project.s.PIPENV_SHELL_FANCY:
25 fancy = True
26
27 from pipenv.shells import choose_shell
28
29 shell = choose_shell(project)
30 if not quiet:
31 click.echo("Launching subshell in virtual environment...", err=True)
32
33 fork_args = (
34 project.virtualenv_location,
35 project.project_directory,
36 shell_args,
37 )
38
39 # Set an environment variable, so we know we're in the environment.
40 # Only set PIPENV_ACTIVE after finishing reading virtualenv_location
41 # otherwise its value will be changed
42 os.environ["PIPENV_ACTIVE"] = "1"
43
44 if fancy:
45 shell.fork(*fork_args)
46 return
47
48 try:
49 shell.fork_compat(*fork_args)
50 except (AttributeError, ImportError):
51 click.echo(
52 "Compatibility mode not supported. "
53 "Trying to continue as well-configured shell...",
54 err=True,
55 )
56 shell.fork(*fork_args)
57
58
59 def do_run(project, command, args, python=False, pypi_mirror=None):
60 """Attempt to run command either pulling from project or interpreting as executable.
61
62 Args are appended to the command in [scripts] section of project if found.
63 """
64 from pipenv.cmdparse import ScriptEmptyError
65
66 env = os.environ.copy()
67
68 # Ensure that virtualenv is available.
69 ensure_project(
70 project,
71 python=python,
72 validate=False,
73 pypi_mirror=pypi_mirror,
74 )
75
76 path = env.get("PATH", "")
77 if project.virtualenv_location:
78 new_path = os.path.join(
79 project.virtualenv_location, "Scripts" if os.name == "nt" else "bin"
80 )
81 paths = path.split(os.pathsep)
82 paths.insert(0, new_path)
83 path = os.pathsep.join(paths)
84 env["VIRTUAL_ENV"] = project.virtualenv_location
85 env["PATH"] = path
86
87 # Set an environment variable, so we know we're in the environment.
88 # Only set PIPENV_ACTIVE after finishing reading virtualenv_location
89 # such as in inline_activate_virtual_environment
90 # otherwise its value will be changed
91 env["PIPENV_ACTIVE"] = "1"
92
93 try:
94 script = project.build_script(command, args)
95 cmd_string = cmd_list_to_shell([script.command] + script.args)
96 if project.s.is_verbose():
97 click.echo(click.style(f"$ {cmd_string}"), err=True)
98 except ScriptEmptyError:
99 click.echo("Can't run script {0!r}-it's empty?", err=True)
100 run_args = [project, script]
101 run_kwargs = {"env": env}
102 # We're using `do_run_nt` on CI (even if we're running on a non-nt machine)
103 # as a workaround for https://github.com/pypa/pipenv/issues/4909.
104 if os.name == "nt" or environments.PIPENV_IS_CI:
105 run_fn = do_run_nt
106 else:
107 run_fn = do_run_posix
108 run_kwargs.update({"command": command})
109 run_fn(*run_args, **run_kwargs)
110
111
112 def do_run_posix(project, script, command, env):
113 path = env.get("PATH")
114 command_path = system_which(script.command, path=path)
115 if not command_path:
116 if project.has_script(command):
117 click.echo(
118 "{}: the command {} (from {}) could not be found within {}."
119 "".format(
120 click.style("Error", fg="red", bold=True),
121 click.style(script.command, fg="yellow"),
122 click.style(command, bold=True),
123 click.style("PATH", bold=True),
124 ),
125 err=True,
126 )
127 else:
128 click.echo(
129 "{}: the command {} could not be found within {} or Pipfile's {}."
130 "".format(
131 click.style("Error", fg="red", bold=True),
132 click.style(command, fg="yellow"),
133 click.style("PATH", bold=True),
134 click.style("[scripts]", bold=True),
135 ),
136 err=True,
137 )
138 sys.exit(1)
139 os.execve(
140 command_path,
141 [command_path, *(os.path.expandvars(arg) for arg in script.args)],
142 env,
143 )
144
145
146 def do_run_nt(project, script, env):
147 p = _launch_windows_subprocess(script, env)
148 p.communicate()
149 sys.exit(p.returncode)
150
151
152 def _launch_windows_subprocess(script, env):
153 path = env.get("PATH", "")
154 command = system_which(script.command, path=path)
155
156 options = {"universal_newlines": True, "env": env}
157 script.cmd_args[1:] = [expandvars(arg) for arg in script.args]
158
159 # Command not found, maybe this is a shell built-in?
160 if not command:
161 return subprocess.Popen(script.cmdify(), shell=True, **options)
162
163 # Try to use CreateProcess directly if possible. Specifically catch
164 # Windows error 193 "Command is not a valid Win32 application" to handle
165 # a "command" that is non-executable. See pypa/pipenv#2727.
166 try:
167 return subprocess.Popen([command] + script.args, **options)
168 except OSError as e:
169 if e.winerror != 193:
170 raise
171
172 # Try shell mode to use Windows's file association for file launch.
173 return subprocess.Popen(script.cmdify(), shell=True, **options)
174
[end of pipenv/routines/shell.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/pipenv/routines/shell.py b/pipenv/routines/shell.py
--- a/pipenv/routines/shell.py
+++ b/pipenv/routines/shell.py
@@ -3,7 +3,6 @@
import sys
from os.path import expandvars
-from pipenv import environments
from pipenv.utils.project import ensure_project
from pipenv.utils.shell import cmd_list_to_shell, system_which
from pipenv.vendor import click
@@ -99,9 +98,7 @@
click.echo("Can't run script {0!r}-it's empty?", err=True)
run_args = [project, script]
run_kwargs = {"env": env}
- # We're using `do_run_nt` on CI (even if we're running on a non-nt machine)
- # as a workaround for https://github.com/pypa/pipenv/issues/4909.
- if os.name == "nt" or environments.PIPENV_IS_CI:
+ if os.name == "nt":
run_fn = do_run_nt
else:
run_fn = do_run_posix
| {"golden_diff": "diff --git a/pipenv/routines/shell.py b/pipenv/routines/shell.py\n--- a/pipenv/routines/shell.py\n+++ b/pipenv/routines/shell.py\n@@ -3,7 +3,6 @@\n import sys\n from os.path import expandvars\n \n-from pipenv import environments\n from pipenv.utils.project import ensure_project\n from pipenv.utils.shell import cmd_list_to_shell, system_which\n from pipenv.vendor import click\n@@ -99,9 +98,7 @@\n click.echo(\"Can't run script {0!r}-it's empty?\", err=True)\n run_args = [project, script]\n run_kwargs = {\"env\": env}\n- # We're using `do_run_nt` on CI (even if we're running on a non-nt machine)\n- # as a workaround for https://github.com/pypa/pipenv/issues/4909.\n- if os.name == \"nt\" or environments.PIPENV_IS_CI:\n+ if os.name == \"nt\":\n run_fn = do_run_nt\n else:\n run_fn = do_run_posix\n", "issue": "Test suite immediately aborts with a successful exit code whenever a test that does a `pipenv run` executes\nCheck this out:\r\n\r\n```python\r\n$ time pytest\r\n=============================================== test session starts ================================================\r\nplatform linux -- Python 3.8.10, pytest-6.2.5, py-1.11.0, pluggy-1.0.0\r\nrootdir: /home/jeremy/src/github.com/pypa/pipenv, configfile: setup.cfg, testpaths: tests\r\nplugins: timeout-2.0.1, xdist-2.4.0, flaky-3.7.0, forked-1.3.0, pypi-0.1.1\r\ncollected 274 items\r\n\r\ntests/integration/test_cli.py ...\r\nreal\t7.14s\r\nuser\t4.30s\r\nsys\t0.73s\r\n$ echo $?\r\n0\r\n```\r\n\r\nI know we don't have a 7 second test suite with only 3 tests in it! Also, where did pipenv's normal test summary go?\r\n\r\nIn the example above, we've run the first 3 tests of test_cli.py and the test suite aborted when running the 4th test: `test_pipenv_site_packages`. The whole test suite aborts when we get to this `pipenv run` invocation:\r\n\r\nhttps://github.com/pypa/pipenv/blob/b0ebaf054e9b47fc90f6939b2473e31863da15a3/tests/integration/test_cli.py#L52\r\n\r\nThis doesn't happen in CI. It took me **forever** to figure out what's going on here. Here's the full story:\r\n\r\n- That call to `p.pipenv` uses `click`'s [`invoke` method](https://click.palletsprojects.com/en/8.0.x/api/#click.testing.CliRunner.invoke) internally. That method internally starts executing pipenv (note that this is happening in the same python testrunner process, there is no forking going on here!)\r\n- Eventually we get into the actual guts of `pipenv run`, which (on my Linux machine) means we execute [this call to `os.execve` in `do_run_posix`](https://github.com/pypa/pipenv/blob/b0ebaf054e9b47fc90f6939b2473e31863da15a3/pipenv/core.py#L2451-L2455). *This completely replaces the pytest process we were in the middle of*, and when the (now just pipenv) process exits, our entire test suite grinds to a halt and exits successfully. Yikes :exploding_head:!\r\n- This doesn't happen in CI because we actually use `do_run_nt` (:interrobang:) in CI: https://github.com/pypa/pipenv/blob/b0ebaf054e9b47fc90f6939b2473e31863da15a3/pipenv/core.py#L2499-L2502. It looks like @frostming added this in https://github.com/pypa/pipenv/pull/4757/files#diff-ef852c4ac364f946819f765a6bc26f04f1b0968f31fc512949a60fa2ab0685e8R2488, presumably as a workaround for this very problem?\r\n- (For the record, if you're running pytest with parallelism enabled, you'll see error messages like \"node down: Not properly terminated\" and \"replacing crashed worker gw3\" as the workers turn into pipenv processes and exit).\r\n\r\nI've been able to work around this problem by explicitly setting the `CI` environment variable when running tests locally. I'll send in a PR to improve the documentation, but we might want to rework this a bit. It feels a bit off to require people to pretend to be in CI just to run tests.\n", "before_files": [{"content": "import os\nimport subprocess\nimport sys\nfrom os.path import expandvars\n\nfrom pipenv import environments\nfrom pipenv.utils.project import ensure_project\nfrom pipenv.utils.shell import cmd_list_to_shell, system_which\nfrom pipenv.vendor import click\n\n\ndef do_shell(\n project, python=False, fancy=False, shell_args=None, pypi_mirror=None, quiet=False\n):\n # Ensure that virtualenv is available.\n ensure_project(\n project,\n python=python,\n validate=False,\n pypi_mirror=pypi_mirror,\n )\n\n # Support shell compatibility mode.\n if project.s.PIPENV_SHELL_FANCY:\n fancy = True\n\n from pipenv.shells import choose_shell\n\n shell = choose_shell(project)\n if not quiet:\n click.echo(\"Launching subshell in virtual environment...\", err=True)\n\n fork_args = (\n project.virtualenv_location,\n project.project_directory,\n shell_args,\n )\n\n # Set an environment variable, so we know we're in the environment.\n # Only set PIPENV_ACTIVE after finishing reading virtualenv_location\n # otherwise its value will be changed\n os.environ[\"PIPENV_ACTIVE\"] = \"1\"\n\n if fancy:\n shell.fork(*fork_args)\n return\n\n try:\n shell.fork_compat(*fork_args)\n except (AttributeError, ImportError):\n click.echo(\n \"Compatibility mode not supported. \"\n \"Trying to continue as well-configured shell...\",\n err=True,\n )\n shell.fork(*fork_args)\n\n\ndef do_run(project, command, args, python=False, pypi_mirror=None):\n \"\"\"Attempt to run command either pulling from project or interpreting as executable.\n\n Args are appended to the command in [scripts] section of project if found.\n \"\"\"\n from pipenv.cmdparse import ScriptEmptyError\n\n env = os.environ.copy()\n\n # Ensure that virtualenv is available.\n ensure_project(\n project,\n python=python,\n validate=False,\n pypi_mirror=pypi_mirror,\n )\n\n path = env.get(\"PATH\", \"\")\n if project.virtualenv_location:\n new_path = os.path.join(\n project.virtualenv_location, \"Scripts\" if os.name == \"nt\" else \"bin\"\n )\n paths = path.split(os.pathsep)\n paths.insert(0, new_path)\n path = os.pathsep.join(paths)\n env[\"VIRTUAL_ENV\"] = project.virtualenv_location\n env[\"PATH\"] = path\n\n # Set an environment variable, so we know we're in the environment.\n # Only set PIPENV_ACTIVE after finishing reading virtualenv_location\n # such as in inline_activate_virtual_environment\n # otherwise its value will be changed\n env[\"PIPENV_ACTIVE\"] = \"1\"\n\n try:\n script = project.build_script(command, args)\n cmd_string = cmd_list_to_shell([script.command] + script.args)\n if project.s.is_verbose():\n click.echo(click.style(f\"$ {cmd_string}\"), err=True)\n except ScriptEmptyError:\n click.echo(\"Can't run script {0!r}-it's empty?\", err=True)\n run_args = [project, script]\n run_kwargs = {\"env\": env}\n # We're using `do_run_nt` on CI (even if we're running on a non-nt machine)\n # as a workaround for https://github.com/pypa/pipenv/issues/4909.\n if os.name == \"nt\" or environments.PIPENV_IS_CI:\n run_fn = do_run_nt\n else:\n run_fn = do_run_posix\n run_kwargs.update({\"command\": command})\n run_fn(*run_args, **run_kwargs)\n\n\ndef do_run_posix(project, script, command, env):\n path = env.get(\"PATH\")\n command_path = system_which(script.command, path=path)\n if not command_path:\n if project.has_script(command):\n click.echo(\n \"{}: the command {} (from {}) could not be found within {}.\"\n \"\".format(\n click.style(\"Error\", fg=\"red\", bold=True),\n click.style(script.command, fg=\"yellow\"),\n click.style(command, bold=True),\n click.style(\"PATH\", bold=True),\n ),\n err=True,\n )\n else:\n click.echo(\n \"{}: the command {} could not be found within {} or Pipfile's {}.\"\n \"\".format(\n click.style(\"Error\", fg=\"red\", bold=True),\n click.style(command, fg=\"yellow\"),\n click.style(\"PATH\", bold=True),\n click.style(\"[scripts]\", bold=True),\n ),\n err=True,\n )\n sys.exit(1)\n os.execve(\n command_path,\n [command_path, *(os.path.expandvars(arg) for arg in script.args)],\n env,\n )\n\n\ndef do_run_nt(project, script, env):\n p = _launch_windows_subprocess(script, env)\n p.communicate()\n sys.exit(p.returncode)\n\n\ndef _launch_windows_subprocess(script, env):\n path = env.get(\"PATH\", \"\")\n command = system_which(script.command, path=path)\n\n options = {\"universal_newlines\": True, \"env\": env}\n script.cmd_args[1:] = [expandvars(arg) for arg in script.args]\n\n # Command not found, maybe this is a shell built-in?\n if not command:\n return subprocess.Popen(script.cmdify(), shell=True, **options)\n\n # Try to use CreateProcess directly if possible. Specifically catch\n # Windows error 193 \"Command is not a valid Win32 application\" to handle\n # a \"command\" that is non-executable. See pypa/pipenv#2727.\n try:\n return subprocess.Popen([command] + script.args, **options)\n except OSError as e:\n if e.winerror != 193:\n raise\n\n # Try shell mode to use Windows's file association for file launch.\n return subprocess.Popen(script.cmdify(), shell=True, **options)\n", "path": "pipenv/routines/shell.py"}]} | 3,165 | 247 |
gh_patches_debug_35897 | rasdani/github-patches | git_diff | meltano__meltano-8215 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
feature: Support authenticating to Azure state backend without a connection string
### Feature scope
State backend
### Description
https://learn.microsoft.com/en-us/azure/storage/blobs/storage-quickstart-blobs-python?tabs=managed-identity%2Croles-azure-portal%2Csign-in-azure-cli#sign-in-and-connect-your-app-code-to-azure-using-defaultazurecredential
See request in
* Slack: https://meltano.slack.com/archives/CMN8HELB0/p1692386533863739?thread_ts=1692366917.319929&cid=CMN8HELB0
* Linen: https://www.linen.dev/s/meltano/t/15516560/hey-i-m-a-bit-confused-how-to-set-the-state-id-when-using-me#d65c3bd0-9e62-48dd-a616-90d4d7246d33
</issue>
<code>
[start of src/meltano/core/state_store/azure.py]
1 """StateStoreManager for Azure Blob storage backend."""
2 from __future__ import annotations
3
4 from collections.abc import Iterator
5 from contextlib import contextmanager
6 from functools import cached_property
7
8 from meltano.core.error import MeltanoError
9 from meltano.core.state_store.filesystem import (
10 CloudStateStoreManager,
11 )
12
13 AZURE_INSTALLED = True
14
15 try:
16 from azure.storage.blob import BlobServiceClient
17 except ImportError:
18 AZURE_INSTALLED = False
19
20
21 class MissingAzureError(Exception):
22 """Raised when azure is required but no installed."""
23
24 def __init__(self):
25 """Initialize a MissingAzureError."""
26 super().__init__(
27 "azure required but not installed. Install meltano[azure] to use Azure Blob Storage as a state backend.", # noqa: E501
28 )
29
30
31 @contextmanager
32 def requires_azure():
33 """Raise MissingAzureError if azure is required but missing in context.
34
35 Raises:
36 MissingAzureError: if azure is not installed.
37
38 Yields:
39 None
40 """
41 if not AZURE_INSTALLED:
42 raise MissingAzureError
43 yield
44
45
46 class AZStorageStateStoreManager(CloudStateStoreManager):
47 """State backend for Azure Blob Storage."""
48
49 label: str = "Azure Blob Storage"
50
51 def __init__(
52 self,
53 connection_string: str | None = None,
54 prefix: str | None = None,
55 **kwargs,
56 ):
57 """Initialize the BaseFilesystemStateStoreManager.
58
59 Args:
60 connection_string: connection string to use in authenticating to Azure
61 prefix: the prefix to store state at
62 kwargs: additional keyword args to pass to parent
63
64 Raises:
65 MeltanoError: If container name is not included in the URI.
66 """
67 super().__init__(**kwargs)
68 self.connection_string = connection_string
69
70 if not self.parsed.hostname:
71 raise MeltanoError(
72 f"Azure state backend URI must include a container name: {self.uri}",
73 "Verify state backend URI. Must be in the form of azure://<container>/<prefix>", # noqa: E501
74 )
75
76 self.container_name = self.parsed.hostname
77 self.prefix = prefix or self.parsed.path
78
79 @staticmethod
80 def is_file_not_found_error(err: Exception) -> bool:
81 """Check if err is equivalent to file not being found.
82
83 Args:
84 err: the err to check
85
86 Returns:
87 True if error represents file not being found, else False
88 """
89 from azure.core.exceptions import ResourceNotFoundError
90
91 return (
92 isinstance(err, ResourceNotFoundError)
93 and "ErrorCode:BlobNotFound" in err.args[0]
94 )
95
96 @cached_property
97 def client(self) -> BlobServiceClient:
98 """Get an authenticated azure.storage.blob.BlobServiceClient.
99
100 Returns:
101 An authenticated azure.storage.blob.BlobServiceClient
102
103 Raises:
104 MeltanoError: If connection string is not provided.
105 """
106 with requires_azure():
107 if self.connection_string:
108 return BlobServiceClient.from_connection_string(self.connection_string)
109
110 raise MeltanoError(
111 "Azure state backend requires a connection string",
112 "Read https://learn.microsoft.com/en-us/azure/storage/common/storage-configure-connection-string for more information.", # noqa: E501
113 )
114
115 def delete(self, file_path: str):
116 """Delete the file/blob at the given path.
117
118 Args:
119 file_path: the path to delete.
120
121 Raises:
122 Exception: if error not indicating file is not found is thrown
123 """
124 blob_client = self.client.get_blob_client(
125 container=self.container_name,
126 blob=file_path,
127 )
128 try:
129 blob_client.delete_blob()
130 except Exception as e:
131 if not self.is_file_not_found_error(e):
132 raise e
133
134 def list_all_files(self) -> Iterator[str]:
135 """List all files in the backend.
136
137 Yields:
138 The next file in the backend.
139 """
140 container_client = self.client.get_container_client(self.container_name)
141 for blob in container_client.list_blobs( # noqa: WPS526
142 name_starts_with=self.prefix.lstrip("/"),
143 ):
144 yield blob.name
145
146 def copy_file(self, src: str, dst: str) -> None:
147 """Copy a file from one location to another.
148
149 Args:
150 src: the source path
151 dst: the destination path
152 """
153 container_client = self.client.get_container_client(self.container_name)
154 src_blob_client = container_client.get_blob_client(src)
155 dst_blob_client = container_client.get_blob_client(dst)
156 dst_blob_client.start_copy_from_url(src_blob_client.url)
157
[end of src/meltano/core/state_store/azure.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/meltano/core/state_store/azure.py b/src/meltano/core/state_store/azure.py
--- a/src/meltano/core/state_store/azure.py
+++ b/src/meltano/core/state_store/azure.py
@@ -52,6 +52,7 @@
self,
connection_string: str | None = None,
prefix: str | None = None,
+ storage_account_url: str | None = None,
**kwargs,
):
"""Initialize the BaseFilesystemStateStoreManager.
@@ -59,6 +60,7 @@
Args:
connection_string: connection string to use in authenticating to Azure
prefix: the prefix to store state at
+ storage_account_url: url of the azure stroga account
kwargs: additional keyword args to pass to parent
Raises:
@@ -66,6 +68,7 @@
"""
super().__init__(**kwargs)
self.connection_string = connection_string
+ self.storage_account_url = storage_account_url
if not self.parsed.hostname:
raise MeltanoError(
@@ -104,11 +107,21 @@
MeltanoError: If connection string is not provided.
"""
with requires_azure():
+ if self.storage_account_url:
+ from azure.identity import DefaultAzureCredential
+
+ default_credential = DefaultAzureCredential()
+ return BlobServiceClient(
+ self.storage_account_url,
+ credential=default_credential,
+ )
+
if self.connection_string:
return BlobServiceClient.from_connection_string(self.connection_string)
raise MeltanoError(
- "Azure state backend requires a connection string",
+ "Azure state backend requires a connection string "
+ "or an account URL to use host credentials",
"Read https://learn.microsoft.com/en-us/azure/storage/common/storage-configure-connection-string for more information.", # noqa: E501
)
| {"golden_diff": "diff --git a/src/meltano/core/state_store/azure.py b/src/meltano/core/state_store/azure.py\n--- a/src/meltano/core/state_store/azure.py\n+++ b/src/meltano/core/state_store/azure.py\n@@ -52,6 +52,7 @@\n self,\n connection_string: str | None = None,\n prefix: str | None = None,\n+ storage_account_url: str | None = None,\n **kwargs,\n ):\n \"\"\"Initialize the BaseFilesystemStateStoreManager.\n@@ -59,6 +60,7 @@\n Args:\n connection_string: connection string to use in authenticating to Azure\n prefix: the prefix to store state at\n+ storage_account_url: url of the azure stroga account\n kwargs: additional keyword args to pass to parent\n \n Raises:\n@@ -66,6 +68,7 @@\n \"\"\"\n super().__init__(**kwargs)\n self.connection_string = connection_string\n+ self.storage_account_url = storage_account_url\n \n if not self.parsed.hostname:\n raise MeltanoError(\n@@ -104,11 +107,21 @@\n MeltanoError: If connection string is not provided.\n \"\"\"\n with requires_azure():\n+ if self.storage_account_url:\n+ from azure.identity import DefaultAzureCredential\n+\n+ default_credential = DefaultAzureCredential()\n+ return BlobServiceClient(\n+ self.storage_account_url,\n+ credential=default_credential,\n+ )\n+\n if self.connection_string:\n return BlobServiceClient.from_connection_string(self.connection_string)\n \n raise MeltanoError(\n- \"Azure state backend requires a connection string\",\n+ \"Azure state backend requires a connection string \"\n+ \"or an account URL to use host credentials\",\n \"Read https://learn.microsoft.com/en-us/azure/storage/common/storage-configure-connection-string for more information.\", # noqa: E501\n )\n", "issue": "feature: Support authenticating to Azure state backend without a connection string\n### Feature scope\r\n\r\nState backend\r\n\r\n### Description\r\n\r\nhttps://learn.microsoft.com/en-us/azure/storage/blobs/storage-quickstart-blobs-python?tabs=managed-identity%2Croles-azure-portal%2Csign-in-azure-cli#sign-in-and-connect-your-app-code-to-azure-using-defaultazurecredential\r\n\r\nSee request in\r\n\r\n* Slack: https://meltano.slack.com/archives/CMN8HELB0/p1692386533863739?thread_ts=1692366917.319929&cid=CMN8HELB0\r\n* Linen: https://www.linen.dev/s/meltano/t/15516560/hey-i-m-a-bit-confused-how-to-set-the-state-id-when-using-me#d65c3bd0-9e62-48dd-a616-90d4d7246d33\n", "before_files": [{"content": "\"\"\"StateStoreManager for Azure Blob storage backend.\"\"\"\nfrom __future__ import annotations\n\nfrom collections.abc import Iterator\nfrom contextlib import contextmanager\nfrom functools import cached_property\n\nfrom meltano.core.error import MeltanoError\nfrom meltano.core.state_store.filesystem import (\n CloudStateStoreManager,\n)\n\nAZURE_INSTALLED = True\n\ntry:\n from azure.storage.blob import BlobServiceClient\nexcept ImportError:\n AZURE_INSTALLED = False\n\n\nclass MissingAzureError(Exception):\n \"\"\"Raised when azure is required but no installed.\"\"\"\n\n def __init__(self):\n \"\"\"Initialize a MissingAzureError.\"\"\"\n super().__init__(\n \"azure required but not installed. Install meltano[azure] to use Azure Blob Storage as a state backend.\", # noqa: E501\n )\n\n\n@contextmanager\ndef requires_azure():\n \"\"\"Raise MissingAzureError if azure is required but missing in context.\n\n Raises:\n MissingAzureError: if azure is not installed.\n\n Yields:\n None\n \"\"\"\n if not AZURE_INSTALLED:\n raise MissingAzureError\n yield\n\n\nclass AZStorageStateStoreManager(CloudStateStoreManager):\n \"\"\"State backend for Azure Blob Storage.\"\"\"\n\n label: str = \"Azure Blob Storage\"\n\n def __init__(\n self,\n connection_string: str | None = None,\n prefix: str | None = None,\n **kwargs,\n ):\n \"\"\"Initialize the BaseFilesystemStateStoreManager.\n\n Args:\n connection_string: connection string to use in authenticating to Azure\n prefix: the prefix to store state at\n kwargs: additional keyword args to pass to parent\n\n Raises:\n MeltanoError: If container name is not included in the URI.\n \"\"\"\n super().__init__(**kwargs)\n self.connection_string = connection_string\n\n if not self.parsed.hostname:\n raise MeltanoError(\n f\"Azure state backend URI must include a container name: {self.uri}\",\n \"Verify state backend URI. Must be in the form of azure://<container>/<prefix>\", # noqa: E501\n )\n\n self.container_name = self.parsed.hostname\n self.prefix = prefix or self.parsed.path\n\n @staticmethod\n def is_file_not_found_error(err: Exception) -> bool:\n \"\"\"Check if err is equivalent to file not being found.\n\n Args:\n err: the err to check\n\n Returns:\n True if error represents file not being found, else False\n \"\"\"\n from azure.core.exceptions import ResourceNotFoundError\n\n return (\n isinstance(err, ResourceNotFoundError)\n and \"ErrorCode:BlobNotFound\" in err.args[0]\n )\n\n @cached_property\n def client(self) -> BlobServiceClient:\n \"\"\"Get an authenticated azure.storage.blob.BlobServiceClient.\n\n Returns:\n An authenticated azure.storage.blob.BlobServiceClient\n\n Raises:\n MeltanoError: If connection string is not provided.\n \"\"\"\n with requires_azure():\n if self.connection_string:\n return BlobServiceClient.from_connection_string(self.connection_string)\n\n raise MeltanoError(\n \"Azure state backend requires a connection string\",\n \"Read https://learn.microsoft.com/en-us/azure/storage/common/storage-configure-connection-string for more information.\", # noqa: E501\n )\n\n def delete(self, file_path: str):\n \"\"\"Delete the file/blob at the given path.\n\n Args:\n file_path: the path to delete.\n\n Raises:\n Exception: if error not indicating file is not found is thrown\n \"\"\"\n blob_client = self.client.get_blob_client(\n container=self.container_name,\n blob=file_path,\n )\n try:\n blob_client.delete_blob()\n except Exception as e:\n if not self.is_file_not_found_error(e):\n raise e\n\n def list_all_files(self) -> Iterator[str]:\n \"\"\"List all files in the backend.\n\n Yields:\n The next file in the backend.\n \"\"\"\n container_client = self.client.get_container_client(self.container_name)\n for blob in container_client.list_blobs( # noqa: WPS526\n name_starts_with=self.prefix.lstrip(\"/\"),\n ):\n yield blob.name\n\n def copy_file(self, src: str, dst: str) -> None:\n \"\"\"Copy a file from one location to another.\n\n Args:\n src: the source path\n dst: the destination path\n \"\"\"\n container_client = self.client.get_container_client(self.container_name)\n src_blob_client = container_client.get_blob_client(src)\n dst_blob_client = container_client.get_blob_client(dst)\n dst_blob_client.start_copy_from_url(src_blob_client.url)\n", "path": "src/meltano/core/state_store/azure.py"}]} | 2,154 | 424 |
gh_patches_debug_4881 | rasdani/github-patches | git_diff | open-telemetry__opentelemetry-python-contrib-2090 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Fix Falcon dependency
Falcon test cases are [failing](https://github.com/open-telemetry/opentelemetry-python/actions/runs/7202220508/job/19619933938?pr=3581) with its latest release.
</issue>
<code>
[start of opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py]
1 # Copyright The OpenTelemetry Authors
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 # DO NOT EDIT. THIS FILE WAS AUTOGENERATED FROM INSTRUMENTATION PACKAGES.
16 # RUN `python scripts/generate_instrumentation_bootstrap.py` TO REGENERATE.
17
18 libraries = [
19 {
20 "library": "aio_pika >= 7.2.0, < 10.0.0",
21 "instrumentation": "opentelemetry-instrumentation-aio-pika==0.43b0.dev",
22 },
23 {
24 "library": "aiohttp ~= 3.0",
25 "instrumentation": "opentelemetry-instrumentation-aiohttp-client==0.43b0.dev",
26 },
27 {
28 "library": "aiohttp ~= 3.0",
29 "instrumentation": "opentelemetry-instrumentation-aiohttp-server==0.43b0.dev",
30 },
31 {
32 "library": "aiopg >= 0.13.0, < 2.0.0",
33 "instrumentation": "opentelemetry-instrumentation-aiopg==0.43b0.dev",
34 },
35 {
36 "library": "asgiref ~= 3.0",
37 "instrumentation": "opentelemetry-instrumentation-asgi==0.43b0.dev",
38 },
39 {
40 "library": "asyncpg >= 0.12.0",
41 "instrumentation": "opentelemetry-instrumentation-asyncpg==0.43b0.dev",
42 },
43 {
44 "library": "boto~=2.0",
45 "instrumentation": "opentelemetry-instrumentation-boto==0.43b0.dev",
46 },
47 {
48 "library": "boto3 ~= 1.0",
49 "instrumentation": "opentelemetry-instrumentation-boto3sqs==0.43b0.dev",
50 },
51 {
52 "library": "botocore ~= 1.0",
53 "instrumentation": "opentelemetry-instrumentation-botocore==0.43b0.dev",
54 },
55 {
56 "library": "cassandra-driver ~= 3.25",
57 "instrumentation": "opentelemetry-instrumentation-cassandra==0.43b0.dev",
58 },
59 {
60 "library": "scylla-driver ~= 3.25",
61 "instrumentation": "opentelemetry-instrumentation-cassandra==0.43b0.dev",
62 },
63 {
64 "library": "celery >= 4.0, < 6.0",
65 "instrumentation": "opentelemetry-instrumentation-celery==0.43b0.dev",
66 },
67 {
68 "library": "confluent-kafka >= 1.8.2, <= 2.2.0",
69 "instrumentation": "opentelemetry-instrumentation-confluent-kafka==0.43b0.dev",
70 },
71 {
72 "library": "django >= 1.10",
73 "instrumentation": "opentelemetry-instrumentation-django==0.43b0.dev",
74 },
75 {
76 "library": "elasticsearch >= 2.0",
77 "instrumentation": "opentelemetry-instrumentation-elasticsearch==0.43b0.dev",
78 },
79 {
80 "library": "falcon >= 1.4.1, < 4.0.0",
81 "instrumentation": "opentelemetry-instrumentation-falcon==0.43b0.dev",
82 },
83 {
84 "library": "fastapi ~= 0.58",
85 "instrumentation": "opentelemetry-instrumentation-fastapi==0.43b0.dev",
86 },
87 {
88 "library": "flask >= 1.0, < 3.0",
89 "instrumentation": "opentelemetry-instrumentation-flask==0.43b0.dev",
90 },
91 {
92 "library": "werkzeug < 3.0.0",
93 "instrumentation": "opentelemetry-instrumentation-flask==0.43b0.dev",
94 },
95 {
96 "library": "grpcio ~= 1.27",
97 "instrumentation": "opentelemetry-instrumentation-grpc==0.43b0.dev",
98 },
99 {
100 "library": "httpx >= 0.18.0",
101 "instrumentation": "opentelemetry-instrumentation-httpx==0.43b0.dev",
102 },
103 {
104 "library": "jinja2 >= 2.7, < 4.0",
105 "instrumentation": "opentelemetry-instrumentation-jinja2==0.43b0.dev",
106 },
107 {
108 "library": "kafka-python >= 2.0",
109 "instrumentation": "opentelemetry-instrumentation-kafka-python==0.43b0.dev",
110 },
111 {
112 "library": "mysql-connector-python ~= 8.0",
113 "instrumentation": "opentelemetry-instrumentation-mysql==0.43b0.dev",
114 },
115 {
116 "library": "mysqlclient < 3",
117 "instrumentation": "opentelemetry-instrumentation-mysqlclient==0.43b0.dev",
118 },
119 {
120 "library": "pika >= 0.12.0",
121 "instrumentation": "opentelemetry-instrumentation-pika==0.43b0.dev",
122 },
123 {
124 "library": "psycopg2 >= 2.7.3.1",
125 "instrumentation": "opentelemetry-instrumentation-psycopg2==0.43b0.dev",
126 },
127 {
128 "library": "pymemcache >= 1.3.5, < 5",
129 "instrumentation": "opentelemetry-instrumentation-pymemcache==0.43b0.dev",
130 },
131 {
132 "library": "pymongo >= 3.1, < 5.0",
133 "instrumentation": "opentelemetry-instrumentation-pymongo==0.43b0.dev",
134 },
135 {
136 "library": "PyMySQL < 2",
137 "instrumentation": "opentelemetry-instrumentation-pymysql==0.43b0.dev",
138 },
139 {
140 "library": "pyramid >= 1.7",
141 "instrumentation": "opentelemetry-instrumentation-pyramid==0.43b0.dev",
142 },
143 {
144 "library": "redis >= 2.6",
145 "instrumentation": "opentelemetry-instrumentation-redis==0.43b0.dev",
146 },
147 {
148 "library": "remoulade >= 0.50",
149 "instrumentation": "opentelemetry-instrumentation-remoulade==0.43b0.dev",
150 },
151 {
152 "library": "requests ~= 2.0",
153 "instrumentation": "opentelemetry-instrumentation-requests==0.43b0.dev",
154 },
155 {
156 "library": "scikit-learn ~= 0.24.0",
157 "instrumentation": "opentelemetry-instrumentation-sklearn==0.43b0.dev",
158 },
159 {
160 "library": "sqlalchemy",
161 "instrumentation": "opentelemetry-instrumentation-sqlalchemy==0.43b0.dev",
162 },
163 {
164 "library": "starlette ~= 0.13.0",
165 "instrumentation": "opentelemetry-instrumentation-starlette==0.43b0.dev",
166 },
167 {
168 "library": "psutil >= 5",
169 "instrumentation": "opentelemetry-instrumentation-system-metrics==0.43b0.dev",
170 },
171 {
172 "library": "tornado >= 5.1.1",
173 "instrumentation": "opentelemetry-instrumentation-tornado==0.43b0.dev",
174 },
175 {
176 "library": "tortoise-orm >= 0.17.0",
177 "instrumentation": "opentelemetry-instrumentation-tortoiseorm==0.43b0.dev",
178 },
179 {
180 "library": "pydantic >= 1.10.2",
181 "instrumentation": "opentelemetry-instrumentation-tortoiseorm==0.43b0.dev",
182 },
183 {
184 "library": "urllib3 >= 1.0.0, < 3.0.0",
185 "instrumentation": "opentelemetry-instrumentation-urllib3==0.43b0.dev",
186 },
187 ]
188 default_instrumentations = [
189 "opentelemetry-instrumentation-aws-lambda==0.43b0.dev",
190 "opentelemetry-instrumentation-dbapi==0.43b0.dev",
191 "opentelemetry-instrumentation-logging==0.43b0.dev",
192 "opentelemetry-instrumentation-sqlite3==0.43b0.dev",
193 "opentelemetry-instrumentation-urllib==0.43b0.dev",
194 "opentelemetry-instrumentation-wsgi==0.43b0.dev",
195 ]
196
[end of opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py
--- a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py
+++ b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py
@@ -77,7 +77,7 @@
"instrumentation": "opentelemetry-instrumentation-elasticsearch==0.43b0.dev",
},
{
- "library": "falcon >= 1.4.1, < 4.0.0",
+ "library": "falcon >= 1.4.1, < 3.1.2",
"instrumentation": "opentelemetry-instrumentation-falcon==0.43b0.dev",
},
{
| {"golden_diff": "diff --git a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py\n--- a/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py\n+++ b/opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py\n@@ -77,7 +77,7 @@\n \"instrumentation\": \"opentelemetry-instrumentation-elasticsearch==0.43b0.dev\",\n },\n {\n- \"library\": \"falcon >= 1.4.1, < 4.0.0\",\n+ \"library\": \"falcon >= 1.4.1, < 3.1.2\",\n \"instrumentation\": \"opentelemetry-instrumentation-falcon==0.43b0.dev\",\n },\n {\n", "issue": "Fix Falcon dependency\nFalcon test cases are [failing](https://github.com/open-telemetry/opentelemetry-python/actions/runs/7202220508/job/19619933938?pr=3581) with its latest release.\n", "before_files": [{"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n# DO NOT EDIT. THIS FILE WAS AUTOGENERATED FROM INSTRUMENTATION PACKAGES.\n# RUN `python scripts/generate_instrumentation_bootstrap.py` TO REGENERATE.\n\nlibraries = [\n {\n \"library\": \"aio_pika >= 7.2.0, < 10.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aio-pika==0.43b0.dev\",\n },\n {\n \"library\": \"aiohttp ~= 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aiohttp-client==0.43b0.dev\",\n },\n {\n \"library\": \"aiohttp ~= 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aiohttp-server==0.43b0.dev\",\n },\n {\n \"library\": \"aiopg >= 0.13.0, < 2.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-aiopg==0.43b0.dev\",\n },\n {\n \"library\": \"asgiref ~= 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-asgi==0.43b0.dev\",\n },\n {\n \"library\": \"asyncpg >= 0.12.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-asyncpg==0.43b0.dev\",\n },\n {\n \"library\": \"boto~=2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-boto==0.43b0.dev\",\n },\n {\n \"library\": \"boto3 ~= 1.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-boto3sqs==0.43b0.dev\",\n },\n {\n \"library\": \"botocore ~= 1.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-botocore==0.43b0.dev\",\n },\n {\n \"library\": \"cassandra-driver ~= 3.25\",\n \"instrumentation\": \"opentelemetry-instrumentation-cassandra==0.43b0.dev\",\n },\n {\n \"library\": \"scylla-driver ~= 3.25\",\n \"instrumentation\": \"opentelemetry-instrumentation-cassandra==0.43b0.dev\",\n },\n {\n \"library\": \"celery >= 4.0, < 6.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-celery==0.43b0.dev\",\n },\n {\n \"library\": \"confluent-kafka >= 1.8.2, <= 2.2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-confluent-kafka==0.43b0.dev\",\n },\n {\n \"library\": \"django >= 1.10\",\n \"instrumentation\": \"opentelemetry-instrumentation-django==0.43b0.dev\",\n },\n {\n \"library\": \"elasticsearch >= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-elasticsearch==0.43b0.dev\",\n },\n {\n \"library\": \"falcon >= 1.4.1, < 4.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-falcon==0.43b0.dev\",\n },\n {\n \"library\": \"fastapi ~= 0.58\",\n \"instrumentation\": \"opentelemetry-instrumentation-fastapi==0.43b0.dev\",\n },\n {\n \"library\": \"flask >= 1.0, < 3.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-flask==0.43b0.dev\",\n },\n {\n \"library\": \"werkzeug < 3.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-flask==0.43b0.dev\",\n },\n {\n \"library\": \"grpcio ~= 1.27\",\n \"instrumentation\": \"opentelemetry-instrumentation-grpc==0.43b0.dev\",\n },\n {\n \"library\": \"httpx >= 0.18.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-httpx==0.43b0.dev\",\n },\n {\n \"library\": \"jinja2 >= 2.7, < 4.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-jinja2==0.43b0.dev\",\n },\n {\n \"library\": \"kafka-python >= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-kafka-python==0.43b0.dev\",\n },\n {\n \"library\": \"mysql-connector-python ~= 8.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-mysql==0.43b0.dev\",\n },\n {\n \"library\": \"mysqlclient < 3\",\n \"instrumentation\": \"opentelemetry-instrumentation-mysqlclient==0.43b0.dev\",\n },\n {\n \"library\": \"pika >= 0.12.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-pika==0.43b0.dev\",\n },\n {\n \"library\": \"psycopg2 >= 2.7.3.1\",\n \"instrumentation\": \"opentelemetry-instrumentation-psycopg2==0.43b0.dev\",\n },\n {\n \"library\": \"pymemcache >= 1.3.5, < 5\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymemcache==0.43b0.dev\",\n },\n {\n \"library\": \"pymongo >= 3.1, < 5.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymongo==0.43b0.dev\",\n },\n {\n \"library\": \"PyMySQL < 2\",\n \"instrumentation\": \"opentelemetry-instrumentation-pymysql==0.43b0.dev\",\n },\n {\n \"library\": \"pyramid >= 1.7\",\n \"instrumentation\": \"opentelemetry-instrumentation-pyramid==0.43b0.dev\",\n },\n {\n \"library\": \"redis >= 2.6\",\n \"instrumentation\": \"opentelemetry-instrumentation-redis==0.43b0.dev\",\n },\n {\n \"library\": \"remoulade >= 0.50\",\n \"instrumentation\": \"opentelemetry-instrumentation-remoulade==0.43b0.dev\",\n },\n {\n \"library\": \"requests ~= 2.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-requests==0.43b0.dev\",\n },\n {\n \"library\": \"scikit-learn ~= 0.24.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-sklearn==0.43b0.dev\",\n },\n {\n \"library\": \"sqlalchemy\",\n \"instrumentation\": \"opentelemetry-instrumentation-sqlalchemy==0.43b0.dev\",\n },\n {\n \"library\": \"starlette ~= 0.13.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-starlette==0.43b0.dev\",\n },\n {\n \"library\": \"psutil >= 5\",\n \"instrumentation\": \"opentelemetry-instrumentation-system-metrics==0.43b0.dev\",\n },\n {\n \"library\": \"tornado >= 5.1.1\",\n \"instrumentation\": \"opentelemetry-instrumentation-tornado==0.43b0.dev\",\n },\n {\n \"library\": \"tortoise-orm >= 0.17.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-tortoiseorm==0.43b0.dev\",\n },\n {\n \"library\": \"pydantic >= 1.10.2\",\n \"instrumentation\": \"opentelemetry-instrumentation-tortoiseorm==0.43b0.dev\",\n },\n {\n \"library\": \"urllib3 >= 1.0.0, < 3.0.0\",\n \"instrumentation\": \"opentelemetry-instrumentation-urllib3==0.43b0.dev\",\n },\n]\ndefault_instrumentations = [\n \"opentelemetry-instrumentation-aws-lambda==0.43b0.dev\",\n \"opentelemetry-instrumentation-dbapi==0.43b0.dev\",\n \"opentelemetry-instrumentation-logging==0.43b0.dev\",\n \"opentelemetry-instrumentation-sqlite3==0.43b0.dev\",\n \"opentelemetry-instrumentation-urllib==0.43b0.dev\",\n \"opentelemetry-instrumentation-wsgi==0.43b0.dev\",\n]\n", "path": "opentelemetry-instrumentation/src/opentelemetry/instrumentation/bootstrap_gen.py"}]} | 3,247 | 190 |
gh_patches_debug_34580 | rasdani/github-patches | git_diff | DDMAL__CantusDB-118 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Source create page layout could be improved
At `source-create/`, the form is not taking up all the horizontal space. This should be an easy fix by changing the column width in Bootstrap.
It would be better if we keep the same layout as the old Cantus. For example, the first three fields should be on the same row. This will make the form look more compact.
Plus, the width of the fields should be adjusted according to the expected content. For example, the `summary` field should be wider than "date".
The look is not the most important thing, but in this case, a little bit more polishing can go a long way.
</issue>
<code>
[start of django/cantusdb_project/main_app/models/source.py]
1 from django.db import models
2 from main_app.models import BaseModel
3 from django.contrib.auth import get_user_model
4
5
6 class Source(BaseModel):
7 cursus_choices = [("Monastic", "Monastic"), ("Secular", "Secular")]
8 source_status_choices = [
9 (
10 "Editing process (not all the fields have been proofread)",
11 "Editing process (not all the fields have been proofread)",
12 ),
13 ("Published / Complete", "Published / Complete"),
14 ("Published / Proofread pending", "Published / Proofread pending"),
15 ("Unpublished / Editing process", "Unpublished / Editing process"),
16 ("Unpublished / Indexing process", "Unpublished / Indexing process"),
17 ("Unpublished / Proofread pending", "Unpublished / Proofread pending"),
18 ("Unpublished / Proofreading process", "Unpublished / Proofreading process"),
19 ]
20
21 # sources with public=False cannot be accessed by its url (access denied) and do not appear in source list
22 public = models.BooleanField(blank=True, null=True)
23 # sources with visible=False can be accessed by typing in the url, but do not appear in source list
24 visible = models.BooleanField(blank=True, null=True)
25 title = models.CharField(
26 max_length=255,
27 help_text="Full Manuscript Identification (City, Archive, Shelf-mark)",
28 )
29 # the siglum field as implemented on the old Cantus is composed of both the RISM siglum and the shelfmark
30 # it is a human-readable ID for a source
31 siglum = models.CharField(max_length=63, null=True, blank=True)
32 # the RISM siglum uniquely identifies a library or holding institution
33 rism_siglum = models.ForeignKey(
34 "RismSiglum", on_delete=models.PROTECT, null=True, blank=True,
35 )
36 provenance = models.ForeignKey(
37 "Provenance",
38 on_delete=models.PROTECT,
39 help_text="If the origin is unknown, select a location where the source was "
40 "used later in its lifetime and provide details in the "
41 '"Provenance notes" field.',
42 null=True,
43 blank=True,
44 )
45 provenance_notes = models.TextField(
46 blank=True,
47 null=True,
48 help_text="More exact indication of the provenance (if necessary)",
49 )
50 full_source = models.BooleanField(blank=True, null=True)
51 date = models.CharField(
52 blank=True,
53 null=True,
54 max_length=63,
55 help_text='Date of the manuscript (e.g. "1200s", "1300-1350", etc.)',
56 )
57 century = models.ManyToManyField("Century", related_name="sources")
58 notation = models.ManyToManyField("Notation", related_name="sources")
59 cursus = models.CharField(
60 blank=True, null=True, choices=cursus_choices, max_length=63
61 )
62 # TODO: Fill this field up with JSON info when I have access to the Users
63 current_editors = models.ManyToManyField(get_user_model(), related_name="sources_edited")
64 inventoried_by = models.ManyToManyField(
65 "Indexer", related_name="sources_inventoried"
66 )
67 full_text_entered_by = models.ManyToManyField(
68 "Indexer", related_name="entered_full_text_for_sources"
69 )
70 melodies_entered_by = models.ManyToManyField(
71 "Indexer", related_name="entered_melody_for_sources"
72 )
73 proofreaders = models.ManyToManyField("Indexer", related_name="proofread_sources")
74 other_editors = models.ManyToManyField("Indexer", related_name="edited_sources")
75 segment = models.ForeignKey(
76 "Segment", on_delete=models.PROTECT, blank=True, null=True
77 )
78 source_status = models.CharField(blank=True, null=True, max_length=255)
79 complete_inventory = models.BooleanField(blank=True, null=True)
80 summary = models.TextField(blank=True, null=True)
81 liturgical_occasions = models.TextField(blank=True, null=True)
82 description = models.TextField(blank=True, null=True)
83 selected_bibliography = models.TextField(blank=True, null=True)
84 image_link = models.URLField(blank=True, null=True)
85 indexing_notes = models.TextField(blank=True, null=True)
86 indexing_date = models.TextField(blank=True, null=True)
87 json_info = models.JSONField(blank=True, null=True)
88 fragmentarium_id = models.CharField(max_length=15, blank=True, null=True)
89 dact_id = models.CharField(max_length=15, blank=True, null=True)
90
91 def number_of_chants(self) -> int:
92 """Returns the number of Chants and Sequences in this Source."""
93 return self.chant_set.count() + self.sequence_set.count()
94
95 def number_of_melodies(self) -> int:
96 """Returns the number of Chants in this Source that have melodies."""
97 return self.chant_set.filter(volpiano__isnull=False).count()
98
99 def __str__(self):
100 return self.title
101
[end of django/cantusdb_project/main_app/models/source.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/django/cantusdb_project/main_app/models/source.py b/django/cantusdb_project/main_app/models/source.py
--- a/django/cantusdb_project/main_app/models/source.py
+++ b/django/cantusdb_project/main_app/models/source.py
@@ -28,7 +28,12 @@
)
# the siglum field as implemented on the old Cantus is composed of both the RISM siglum and the shelfmark
# it is a human-readable ID for a source
- siglum = models.CharField(max_length=63, null=True, blank=True)
+ siglum = models.CharField(
+ max_length=63,
+ null=True,
+ blank=True,
+ help_text="RISM-style siglum + Shelf-mark (e.g. GB-Ob 202).",
+ )
# the RISM siglum uniquely identifies a library or holding institution
rism_siglum = models.ForeignKey(
"RismSiglum", on_delete=models.PROTECT, null=True, blank=True,
@@ -61,6 +66,9 @@
)
# TODO: Fill this field up with JSON info when I have access to the Users
current_editors = models.ManyToManyField(get_user_model(), related_name="sources_edited")
+ # created_by = models.ForeignKey(
+ # get_user_model(), related_name="sources_created", on_delete=models.PROTECT, blank=True, null=True
+ # )
inventoried_by = models.ManyToManyField(
"Indexer", related_name="sources_inventoried"
)
@@ -81,7 +89,11 @@
liturgical_occasions = models.TextField(blank=True, null=True)
description = models.TextField(blank=True, null=True)
selected_bibliography = models.TextField(blank=True, null=True)
- image_link = models.URLField(blank=True, null=True)
+ image_link = models.URLField(
+ blank=True,
+ null=True,
+ help_text='HTTP link to the image gallery of the source.',
+ )
indexing_notes = models.TextField(blank=True, null=True)
indexing_date = models.TextField(blank=True, null=True)
json_info = models.JSONField(blank=True, null=True)
| {"golden_diff": "diff --git a/django/cantusdb_project/main_app/models/source.py b/django/cantusdb_project/main_app/models/source.py\n--- a/django/cantusdb_project/main_app/models/source.py\n+++ b/django/cantusdb_project/main_app/models/source.py\n@@ -28,7 +28,12 @@\n )\n # the siglum field as implemented on the old Cantus is composed of both the RISM siglum and the shelfmark\n # it is a human-readable ID for a source\n- siglum = models.CharField(max_length=63, null=True, blank=True)\n+ siglum = models.CharField(\n+ max_length=63, \n+ null=True, \n+ blank=True,\n+ help_text=\"RISM-style siglum + Shelf-mark (e.g. GB-Ob 202).\",\n+ )\n # the RISM siglum uniquely identifies a library or holding institution\n rism_siglum = models.ForeignKey(\n \"RismSiglum\", on_delete=models.PROTECT, null=True, blank=True,\n@@ -61,6 +66,9 @@\n )\n # TODO: Fill this field up with JSON info when I have access to the Users\n current_editors = models.ManyToManyField(get_user_model(), related_name=\"sources_edited\")\n+ # created_by = models.ForeignKey(\n+ # get_user_model(), related_name=\"sources_created\", on_delete=models.PROTECT, blank=True, null=True\n+ # )\n inventoried_by = models.ManyToManyField(\n \"Indexer\", related_name=\"sources_inventoried\"\n )\n@@ -81,7 +89,11 @@\n liturgical_occasions = models.TextField(blank=True, null=True)\n description = models.TextField(blank=True, null=True)\n selected_bibliography = models.TextField(blank=True, null=True)\n- image_link = models.URLField(blank=True, null=True)\n+ image_link = models.URLField(\n+ blank=True, \n+ null=True,\n+ help_text='HTTP link to the image gallery of the source.',\n+ )\n indexing_notes = models.TextField(blank=True, null=True)\n indexing_date = models.TextField(blank=True, null=True)\n json_info = models.JSONField(blank=True, null=True)\n", "issue": "Source create page layout could be improved\nAt `source-create/`, the form is not taking up all the horizontal space. This should be an easy fix by changing the column width in Bootstrap. \r\nIt would be better if we keep the same layout as the old Cantus. For example, the first three fields should be on the same row. This will make the form look more compact. \r\nPlus, the width of the fields should be adjusted according to the expected content. For example, the `summary` field should be wider than \"date\". \r\nThe look is not the most important thing, but in this case, a little bit more polishing can go a long way. \n", "before_files": [{"content": "from django.db import models\nfrom main_app.models import BaseModel\nfrom django.contrib.auth import get_user_model\n\n\nclass Source(BaseModel):\n cursus_choices = [(\"Monastic\", \"Monastic\"), (\"Secular\", \"Secular\")]\n source_status_choices = [\n (\n \"Editing process (not all the fields have been proofread)\",\n \"Editing process (not all the fields have been proofread)\",\n ),\n (\"Published / Complete\", \"Published / Complete\"),\n (\"Published / Proofread pending\", \"Published / Proofread pending\"),\n (\"Unpublished / Editing process\", \"Unpublished / Editing process\"),\n (\"Unpublished / Indexing process\", \"Unpublished / Indexing process\"),\n (\"Unpublished / Proofread pending\", \"Unpublished / Proofread pending\"),\n (\"Unpublished / Proofreading process\", \"Unpublished / Proofreading process\"),\n ]\n\n # sources with public=False cannot be accessed by its url (access denied) and do not appear in source list\n public = models.BooleanField(blank=True, null=True)\n # sources with visible=False can be accessed by typing in the url, but do not appear in source list\n visible = models.BooleanField(blank=True, null=True)\n title = models.CharField(\n max_length=255,\n help_text=\"Full Manuscript Identification (City, Archive, Shelf-mark)\",\n )\n # the siglum field as implemented on the old Cantus is composed of both the RISM siglum and the shelfmark\n # it is a human-readable ID for a source\n siglum = models.CharField(max_length=63, null=True, blank=True)\n # the RISM siglum uniquely identifies a library or holding institution\n rism_siglum = models.ForeignKey(\n \"RismSiglum\", on_delete=models.PROTECT, null=True, blank=True,\n )\n provenance = models.ForeignKey(\n \"Provenance\",\n on_delete=models.PROTECT,\n help_text=\"If the origin is unknown, select a location where the source was \"\n \"used later in its lifetime and provide details in the \"\n '\"Provenance notes\" field.',\n null=True,\n blank=True,\n )\n provenance_notes = models.TextField(\n blank=True,\n null=True,\n help_text=\"More exact indication of the provenance (if necessary)\",\n )\n full_source = models.BooleanField(blank=True, null=True)\n date = models.CharField(\n blank=True,\n null=True,\n max_length=63,\n help_text='Date of the manuscript (e.g. \"1200s\", \"1300-1350\", etc.)',\n )\n century = models.ManyToManyField(\"Century\", related_name=\"sources\")\n notation = models.ManyToManyField(\"Notation\", related_name=\"sources\")\n cursus = models.CharField(\n blank=True, null=True, choices=cursus_choices, max_length=63\n )\n # TODO: Fill this field up with JSON info when I have access to the Users\n current_editors = models.ManyToManyField(get_user_model(), related_name=\"sources_edited\")\n inventoried_by = models.ManyToManyField(\n \"Indexer\", related_name=\"sources_inventoried\"\n )\n full_text_entered_by = models.ManyToManyField(\n \"Indexer\", related_name=\"entered_full_text_for_sources\"\n )\n melodies_entered_by = models.ManyToManyField(\n \"Indexer\", related_name=\"entered_melody_for_sources\"\n )\n proofreaders = models.ManyToManyField(\"Indexer\", related_name=\"proofread_sources\")\n other_editors = models.ManyToManyField(\"Indexer\", related_name=\"edited_sources\")\n segment = models.ForeignKey(\n \"Segment\", on_delete=models.PROTECT, blank=True, null=True\n )\n source_status = models.CharField(blank=True, null=True, max_length=255)\n complete_inventory = models.BooleanField(blank=True, null=True)\n summary = models.TextField(blank=True, null=True)\n liturgical_occasions = models.TextField(blank=True, null=True)\n description = models.TextField(blank=True, null=True)\n selected_bibliography = models.TextField(blank=True, null=True)\n image_link = models.URLField(blank=True, null=True)\n indexing_notes = models.TextField(blank=True, null=True)\n indexing_date = models.TextField(blank=True, null=True)\n json_info = models.JSONField(blank=True, null=True)\n fragmentarium_id = models.CharField(max_length=15, blank=True, null=True)\n dact_id = models.CharField(max_length=15, blank=True, null=True)\n\n def number_of_chants(self) -> int:\n \"\"\"Returns the number of Chants and Sequences in this Source.\"\"\"\n return self.chant_set.count() + self.sequence_set.count()\n\n def number_of_melodies(self) -> int:\n \"\"\"Returns the number of Chants in this Source that have melodies.\"\"\"\n return self.chant_set.filter(volpiano__isnull=False).count()\n\n def __str__(self):\n return self.title\n ", "path": "django/cantusdb_project/main_app/models/source.py"}]} | 1,938 | 496 |
gh_patches_debug_18217 | rasdani/github-patches | git_diff | ansible__ansible-37651 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
onyx_pfc_interface throws exception when using onyx version 3.6.6000
<!---
Verify first that your issue/request is not already reported on GitHub.
Also test if the latest release, and devel branch are affected too.
-->
##### ISSUE TYPE
<!--- Pick one below and delete the rest -->
- Bug Report
##### COMPONENT NAME
<!---
Name of the module, plugin, task or feature
Do not include extra details here, e.g. "vyos_command" not "the network module vyos_command" or the full path
-->
onyx_pfc_interface.py
##### ANSIBLE VERSION
<!--- Paste verbatim output from "ansible --version" between quotes below -->
```
ansible 2.6.0 (devel c1008d693c) last updated 2018/03/12 15:51:01 (GMT +000)
python version = 2.7.5 (default, Nov 6 2016, 00:28:07) [GCC 4.8.5 20150623 (Red Hat 4.8.5-11)]
```
##### CONFIGURATION
<!---
If using Ansible 2.4 or above, paste the results of "ansible-config dump --only-changed"
Otherwise, mention any settings you have changed/added/removed in ansible.cfg
(or using the ANSIBLE_* environment variables).
-->
##### OS / ENVIRONMENT
<!---
Mention the OS you are running Ansible from, and the OS you are
managing, or say "N/A" for anything that is not platform-specific.
Also mention the specific version of what you are trying to control,
e.g. if this is a network bug the version of firmware on the network device.
-->
N/A
##### SUMMARY
<!--- Explain the problem briefly -->
when running command onyx_pfc_interface on onyx network device with version 3.6.6000 or later, there is an exception.
##### STEPS TO REPRODUCE
<!---
For bugs, show exactly how to reproduce the problem, using a minimal test-case.
For new features, show how the feature would be used.
-->
run any playbook with onyx_pfc_interface
<!--- Paste example playbooks or commands between quotes below -->
```yaml
- name: Disable Lag members PFC
onyx_pfc_interface:
aggregate:
- name: Eth1/15
- name: Eth1/16
state: disabled
```
<!--- You can also paste gist.github.com links for larger files -->
##### EXPECTED RESULTS
<!--- What did you expect to happen when running the steps above? -->
pfc interface will be configured
##### ACTUAL RESULTS
<!--- What actually happened? If possible run with extra verbosity (-vvvv) -->
Command failed with exception
<!--- Paste verbatim command output between quotes below -->
```
<swi60> EXEC /bin/sh -c 'rm -f -r /root/.ansible/tmp/ansible-tmp-1520431892.25-242550331138460/ > /dev/null 2>&1 && sleep 0'
The full traceback is:
Traceback (most recent call last):
File "/tmp/ansible_gof89B/ansible_module_onyx_pfc_interface.py", line 205, in <module>
main()
File "/tmp/ansible_gof89B/ansible_module_onyx_pfc_interface.py", line 201, in main
OnyxPfcInterfaceModule.main()
File "/tmp/ansible_gof89B/ansible_modlib.zip/ansible/module_utils/network/onyx/onyx.py", line 229, in main
File "/tmp/ansible_gof89B/ansible_modlib.zip/ansible/module_utils/network/onyx/onyx.py", line 207, in run
File "/tmp/ansible_gof89B/ansible_module_onyx_pfc_interface.py", line 149, in load_current_config
for if_name, if_pfc_data in iteritems(pfc_config):
File "/tmp/ansible_gof89B/ansible_modlib.zip/ansible/module_utils/six/__init__.py", line 610, in iteritems
AttributeError: 'list' object has no attribute 'iteritems'
```
</issue>
<code>
[start of lib/ansible/modules/network/onyx/onyx_pfc_interface.py]
1 #!/usr/bin/python
2 #
3 # Copyright: Ansible Project
4 # GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)
5
6 from __future__ import absolute_import, division, print_function
7 __metaclass__ = type
8
9 ANSIBLE_METADATA = {'metadata_version': '1.1',
10 'status': ['preview'],
11 'supported_by': 'community'}
12
13 DOCUMENTATION = """
14 ---
15 module: onyx_pfc_interface
16 version_added: "2.5"
17 author: "Samer Deeb (@samerd)"
18 short_description: Manage priority flow control on ONYX network devices
19 description:
20 - This module provides declarative management of priority flow control (PFC)
21 on interfaces of Mellanox ONYX network devices.
22 notes:
23 - Tested on ONYX 3.6.4000
24 options:
25 name:
26 description:
27 - Name of the interface PFC should be configured on.
28 aggregate:
29 description: List of interfaces PFC should be configured on.
30 purge:
31 description:
32 - Purge interfaces not defined in the aggregate parameter.
33 type: bool
34 default: false
35 state:
36 description:
37 - State of the PFC configuration.
38 default: enabled
39 choices: ['enabled', 'disabled']
40 """
41
42 EXAMPLES = """
43 - name: configure PFC
44 onyx_pfc_interface:
45 name: Eth1/1
46 state: enabled
47 """
48
49 RETURN = """
50 commands:
51 description: The list of configuration mode commands to send to the device.
52 returned: always
53 type: list
54 sample:
55 - interface ethernet 1/17 dcb priority-flow-control mode on
56 """
57 from copy import deepcopy
58 import re
59
60 from ansible.module_utils.basic import AnsibleModule
61 from ansible.module_utils.network.common.utils import remove_default_spec
62 from ansible.module_utils.six import iteritems
63
64 from ansible.module_utils.network.onyx.onyx import BaseOnyxModule
65 from ansible.module_utils.network.onyx.onyx import show_cmd
66
67
68 class OnyxPfcInterfaceModule(BaseOnyxModule):
69 PFC_IF_REGEX = re.compile(
70 r"^(Eth\d+\/\d+)|(Eth\d+\/\d+\/\d+)|(Po\d+)|(Mpo\d+)$")
71
72 _purge = False
73
74 @classmethod
75 def _get_element_spec(cls):
76 return dict(
77 name=dict(type='str'),
78 state=dict(default='enabled',
79 choices=['enabled', 'disabled']),
80 )
81
82 @classmethod
83 def _get_aggregate_spec(cls, element_spec):
84 aggregate_spec = deepcopy(element_spec)
85 aggregate_spec['name'] = dict(required=True)
86
87 # remove default in aggregate spec, to handle common arguments
88 remove_default_spec(aggregate_spec)
89 return aggregate_spec
90
91 def init_module(self):
92 """ module initialization
93 """
94 element_spec = self._get_element_spec()
95 aggregate_spec = self._get_aggregate_spec(element_spec)
96 argument_spec = dict(
97 aggregate=dict(type='list', elements='dict',
98 options=aggregate_spec),
99 purge=dict(default=False, type='bool'),
100 )
101 argument_spec.update(element_spec)
102 required_one_of = [['name', 'aggregate']]
103 mutually_exclusive = [['name', 'aggregate']]
104 self._module = AnsibleModule(
105 argument_spec=argument_spec,
106 required_one_of=required_one_of,
107 mutually_exclusive=mutually_exclusive,
108 supports_check_mode=True)
109
110 def get_required_config(self):
111 self._required_config = list()
112 module_params = self._module.params
113 aggregate = module_params.get('aggregate')
114 self._purge = module_params.get('purge', False)
115 if aggregate:
116 for item in aggregate:
117 for key in item:
118 if item.get(key) is None:
119 item[key] = module_params[key]
120 self.validate_param_values(item, item)
121 req_item = item.copy()
122 self._required_config.append(req_item)
123 else:
124 params = {
125 'name': module_params['name'],
126 'state': module_params['state'],
127 }
128 self.validate_param_values(params)
129 self._required_config.append(params)
130
131 def _create_if_pfc_data(self, if_name, if_pfc_data):
132 state = self.get_config_attr(if_pfc_data, "PFC oper")
133 state = state.lower()
134 return dict(
135 name=if_name,
136 state=state)
137
138 def _get_pfc_config(self):
139 return show_cmd(self._module, "show dcb priority-flow-control")
140
141 def load_current_config(self):
142 # called in base class in run function
143 self._current_config = dict()
144 pfc_config = self._get_pfc_config()
145 if not pfc_config:
146 return
147 if 'Table 2' in pfc_config:
148 pfc_config = pfc_config['Table 2']
149 for if_name, if_pfc_data in iteritems(pfc_config):
150 match = self.PFC_IF_REGEX.match(if_name)
151 if not match:
152 continue
153 if if_pfc_data:
154 if_pfc_data = if_pfc_data[0]
155 self._current_config[if_name] = \
156 self._create_if_pfc_data(if_name, if_pfc_data)
157
158 def _get_interface_cmd_name(self, if_name):
159 if if_name.startswith('Eth'):
160 return if_name.replace("Eth", "ethernet ")
161 if if_name.startswith('Po'):
162 return if_name.replace("Po", "port-channel ")
163 if if_name.startswith('Mpo'):
164 return if_name.replace("Mpo", "mlag-port-channel ")
165 self._module.fail_json(
166 msg='invalid interface name: %s' % if_name)
167
168 def _add_if_pfc_commands(self, if_name, req_state):
169 cmd_prefix = "interface %s " % self._get_interface_cmd_name(if_name)
170
171 if req_state == 'disabled':
172 pfc_cmd = 'no dcb priority-flow-control mode force'
173 else:
174 pfc_cmd = 'dcb priority-flow-control mode on force'
175 self._commands.append(cmd_prefix + pfc_cmd)
176
177 def _gen_pfc_commands(self, if_name, curr_conf, req_state):
178 curr_state = curr_conf.get('state', 'disabled')
179 if curr_state != req_state:
180 self._add_if_pfc_commands(if_name, req_state)
181
182 def generate_commands(self):
183 req_interfaces = set()
184 for req_conf in self._required_config:
185 req_state = req_conf['state']
186 if_name = req_conf['name']
187 if req_state == 'enabled':
188 req_interfaces.add(if_name)
189 curr_conf = self._current_config.get(if_name, {})
190 self._gen_pfc_commands(if_name, curr_conf, req_state)
191 if self._purge:
192 for if_name, curr_conf in iteritems(self._current_config):
193 if if_name not in req_interfaces:
194 req_state = 'disabled'
195 self._gen_pfc_commands(if_name, curr_conf, req_state)
196
197
198 def main():
199 """ main entry point for module execution
200 """
201 OnyxPfcInterfaceModule.main()
202
203
204 if __name__ == '__main__':
205 main()
206
[end of lib/ansible/modules/network/onyx/onyx_pfc_interface.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/lib/ansible/modules/network/onyx/onyx_pfc_interface.py b/lib/ansible/modules/network/onyx/onyx_pfc_interface.py
--- a/lib/ansible/modules/network/onyx/onyx_pfc_interface.py
+++ b/lib/ansible/modules/network/onyx/onyx_pfc_interface.py
@@ -140,12 +140,20 @@
def load_current_config(self):
# called in base class in run function
+ self._os_version = self._get_os_version()
self._current_config = dict()
pfc_config = self._get_pfc_config()
if not pfc_config:
return
- if 'Table 2' in pfc_config:
- pfc_config = pfc_config['Table 2']
+ if self._os_version >= self.ONYX_API_VERSION:
+ if len(pfc_config) >= 3:
+ pfc_config = pfc_config[2]
+ else:
+ pfc_config = dict()
+ else:
+ if 'Table 2' in pfc_config:
+ pfc_config = pfc_config['Table 2']
+
for if_name, if_pfc_data in iteritems(pfc_config):
match = self.PFC_IF_REGEX.match(if_name)
if not match:
| {"golden_diff": "diff --git a/lib/ansible/modules/network/onyx/onyx_pfc_interface.py b/lib/ansible/modules/network/onyx/onyx_pfc_interface.py\n--- a/lib/ansible/modules/network/onyx/onyx_pfc_interface.py\n+++ b/lib/ansible/modules/network/onyx/onyx_pfc_interface.py\n@@ -140,12 +140,20 @@\n \n def load_current_config(self):\n # called in base class in run function\n+ self._os_version = self._get_os_version()\n self._current_config = dict()\n pfc_config = self._get_pfc_config()\n if not pfc_config:\n return\n- if 'Table 2' in pfc_config:\n- pfc_config = pfc_config['Table 2']\n+ if self._os_version >= self.ONYX_API_VERSION:\n+ if len(pfc_config) >= 3:\n+ pfc_config = pfc_config[2]\n+ else:\n+ pfc_config = dict()\n+ else:\n+ if 'Table 2' in pfc_config:\n+ pfc_config = pfc_config['Table 2']\n+\n for if_name, if_pfc_data in iteritems(pfc_config):\n match = self.PFC_IF_REGEX.match(if_name)\n if not match:\n", "issue": "onyx_pfc_interface throws exception when using onyx version 3.6.6000\n<!---\r\nVerify first that your issue/request is not already reported on GitHub.\r\nAlso test if the latest release, and devel branch are affected too.\r\n-->\r\n\r\n##### ISSUE TYPE\r\n<!--- Pick one below and delete the rest -->\r\n - Bug Report\r\n\r\n##### COMPONENT NAME\r\n<!---\r\nName of the module, plugin, task or feature\r\nDo not include extra details here, e.g. \"vyos_command\" not \"the network module vyos_command\" or the full path\r\n-->\r\nonyx_pfc_interface.py\r\n\r\n##### ANSIBLE VERSION\r\n<!--- Paste verbatim output from \"ansible --version\" between quotes below -->\r\n```\r\nansible 2.6.0 (devel c1008d693c) last updated 2018/03/12 15:51:01 (GMT +000)\r\n python version = 2.7.5 (default, Nov 6 2016, 00:28:07) [GCC 4.8.5 20150623 (Red Hat 4.8.5-11)]\r\n```\r\n\r\n##### CONFIGURATION\r\n<!---\r\nIf using Ansible 2.4 or above, paste the results of \"ansible-config dump --only-changed\"\r\nOtherwise, mention any settings you have changed/added/removed in ansible.cfg\r\n(or using the ANSIBLE_* environment variables).\r\n-->\r\n\r\n##### OS / ENVIRONMENT\r\n<!---\r\nMention the OS you are running Ansible from, and the OS you are\r\nmanaging, or say \"N/A\" for anything that is not platform-specific.\r\nAlso mention the specific version of what you are trying to control,\r\ne.g. if this is a network bug the version of firmware on the network device.\r\n-->\r\nN/A\r\n\r\n##### SUMMARY\r\n<!--- Explain the problem briefly -->\r\nwhen running command onyx_pfc_interface on onyx network device with version 3.6.6000 or later, there is an exception.\r\n\r\n##### STEPS TO REPRODUCE\r\n<!---\r\nFor bugs, show exactly how to reproduce the problem, using a minimal test-case.\r\nFor new features, show how the feature would be used.\r\n-->\r\nrun any playbook with onyx_pfc_interface\r\n\r\n<!--- Paste example playbooks or commands between quotes below -->\r\n```yaml\r\n- name: Disable Lag members PFC\r\n onyx_pfc_interface:\r\n aggregate:\r\n - name: Eth1/15\r\n - name: Eth1/16\r\n state: disabled\r\n```\r\n\r\n<!--- You can also paste gist.github.com links for larger files -->\r\n\r\n##### EXPECTED RESULTS\r\n<!--- What did you expect to happen when running the steps above? -->\r\npfc interface will be configured\r\n\r\n##### ACTUAL RESULTS\r\n<!--- What actually happened? If possible run with extra verbosity (-vvvv) -->\r\nCommand failed with exception\r\n<!--- Paste verbatim command output between quotes below -->\r\n```\r\n<swi60> EXEC /bin/sh -c 'rm -f -r /root/.ansible/tmp/ansible-tmp-1520431892.25-242550331138460/ > /dev/null 2>&1 && sleep 0'\r\nThe full traceback is:\r\nTraceback (most recent call last):\r\n File \"/tmp/ansible_gof89B/ansible_module_onyx_pfc_interface.py\", line 205, in <module>\r\n main()\r\n File \"/tmp/ansible_gof89B/ansible_module_onyx_pfc_interface.py\", line 201, in main\r\n OnyxPfcInterfaceModule.main()\r\n File \"/tmp/ansible_gof89B/ansible_modlib.zip/ansible/module_utils/network/onyx/onyx.py\", line 229, in main\r\n File \"/tmp/ansible_gof89B/ansible_modlib.zip/ansible/module_utils/network/onyx/onyx.py\", line 207, in run\r\n File \"/tmp/ansible_gof89B/ansible_module_onyx_pfc_interface.py\", line 149, in load_current_config\r\n for if_name, if_pfc_data in iteritems(pfc_config):\r\n File \"/tmp/ansible_gof89B/ansible_modlib.zip/ansible/module_utils/six/__init__.py\", line 610, in iteritems\r\nAttributeError: 'list' object has no attribute 'iteritems'\r\n```\r\n\n", "before_files": [{"content": "#!/usr/bin/python\n#\n# Copyright: Ansible Project\n# GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)\n\nfrom __future__ import absolute_import, division, print_function\n__metaclass__ = type\n\nANSIBLE_METADATA = {'metadata_version': '1.1',\n 'status': ['preview'],\n 'supported_by': 'community'}\n\nDOCUMENTATION = \"\"\"\n---\nmodule: onyx_pfc_interface\nversion_added: \"2.5\"\nauthor: \"Samer Deeb (@samerd)\"\nshort_description: Manage priority flow control on ONYX network devices\ndescription:\n - This module provides declarative management of priority flow control (PFC)\n on interfaces of Mellanox ONYX network devices.\nnotes:\n - Tested on ONYX 3.6.4000\noptions:\n name:\n description:\n - Name of the interface PFC should be configured on.\n aggregate:\n description: List of interfaces PFC should be configured on.\n purge:\n description:\n - Purge interfaces not defined in the aggregate parameter.\n type: bool\n default: false\n state:\n description:\n - State of the PFC configuration.\n default: enabled\n choices: ['enabled', 'disabled']\n\"\"\"\n\nEXAMPLES = \"\"\"\n- name: configure PFC\n onyx_pfc_interface:\n name: Eth1/1\n state: enabled\n\"\"\"\n\nRETURN = \"\"\"\ncommands:\n description: The list of configuration mode commands to send to the device.\n returned: always\n type: list\n sample:\n - interface ethernet 1/17 dcb priority-flow-control mode on\n\"\"\"\nfrom copy import deepcopy\nimport re\n\nfrom ansible.module_utils.basic import AnsibleModule\nfrom ansible.module_utils.network.common.utils import remove_default_spec\nfrom ansible.module_utils.six import iteritems\n\nfrom ansible.module_utils.network.onyx.onyx import BaseOnyxModule\nfrom ansible.module_utils.network.onyx.onyx import show_cmd\n\n\nclass OnyxPfcInterfaceModule(BaseOnyxModule):\n PFC_IF_REGEX = re.compile(\n r\"^(Eth\\d+\\/\\d+)|(Eth\\d+\\/\\d+\\/\\d+)|(Po\\d+)|(Mpo\\d+)$\")\n\n _purge = False\n\n @classmethod\n def _get_element_spec(cls):\n return dict(\n name=dict(type='str'),\n state=dict(default='enabled',\n choices=['enabled', 'disabled']),\n )\n\n @classmethod\n def _get_aggregate_spec(cls, element_spec):\n aggregate_spec = deepcopy(element_spec)\n aggregate_spec['name'] = dict(required=True)\n\n # remove default in aggregate spec, to handle common arguments\n remove_default_spec(aggregate_spec)\n return aggregate_spec\n\n def init_module(self):\n \"\"\" module initialization\n \"\"\"\n element_spec = self._get_element_spec()\n aggregate_spec = self._get_aggregate_spec(element_spec)\n argument_spec = dict(\n aggregate=dict(type='list', elements='dict',\n options=aggregate_spec),\n purge=dict(default=False, type='bool'),\n )\n argument_spec.update(element_spec)\n required_one_of = [['name', 'aggregate']]\n mutually_exclusive = [['name', 'aggregate']]\n self._module = AnsibleModule(\n argument_spec=argument_spec,\n required_one_of=required_one_of,\n mutually_exclusive=mutually_exclusive,\n supports_check_mode=True)\n\n def get_required_config(self):\n self._required_config = list()\n module_params = self._module.params\n aggregate = module_params.get('aggregate')\n self._purge = module_params.get('purge', False)\n if aggregate:\n for item in aggregate:\n for key in item:\n if item.get(key) is None:\n item[key] = module_params[key]\n self.validate_param_values(item, item)\n req_item = item.copy()\n self._required_config.append(req_item)\n else:\n params = {\n 'name': module_params['name'],\n 'state': module_params['state'],\n }\n self.validate_param_values(params)\n self._required_config.append(params)\n\n def _create_if_pfc_data(self, if_name, if_pfc_data):\n state = self.get_config_attr(if_pfc_data, \"PFC oper\")\n state = state.lower()\n return dict(\n name=if_name,\n state=state)\n\n def _get_pfc_config(self):\n return show_cmd(self._module, \"show dcb priority-flow-control\")\n\n def load_current_config(self):\n # called in base class in run function\n self._current_config = dict()\n pfc_config = self._get_pfc_config()\n if not pfc_config:\n return\n if 'Table 2' in pfc_config:\n pfc_config = pfc_config['Table 2']\n for if_name, if_pfc_data in iteritems(pfc_config):\n match = self.PFC_IF_REGEX.match(if_name)\n if not match:\n continue\n if if_pfc_data:\n if_pfc_data = if_pfc_data[0]\n self._current_config[if_name] = \\\n self._create_if_pfc_data(if_name, if_pfc_data)\n\n def _get_interface_cmd_name(self, if_name):\n if if_name.startswith('Eth'):\n return if_name.replace(\"Eth\", \"ethernet \")\n if if_name.startswith('Po'):\n return if_name.replace(\"Po\", \"port-channel \")\n if if_name.startswith('Mpo'):\n return if_name.replace(\"Mpo\", \"mlag-port-channel \")\n self._module.fail_json(\n msg='invalid interface name: %s' % if_name)\n\n def _add_if_pfc_commands(self, if_name, req_state):\n cmd_prefix = \"interface %s \" % self._get_interface_cmd_name(if_name)\n\n if req_state == 'disabled':\n pfc_cmd = 'no dcb priority-flow-control mode force'\n else:\n pfc_cmd = 'dcb priority-flow-control mode on force'\n self._commands.append(cmd_prefix + pfc_cmd)\n\n def _gen_pfc_commands(self, if_name, curr_conf, req_state):\n curr_state = curr_conf.get('state', 'disabled')\n if curr_state != req_state:\n self._add_if_pfc_commands(if_name, req_state)\n\n def generate_commands(self):\n req_interfaces = set()\n for req_conf in self._required_config:\n req_state = req_conf['state']\n if_name = req_conf['name']\n if req_state == 'enabled':\n req_interfaces.add(if_name)\n curr_conf = self._current_config.get(if_name, {})\n self._gen_pfc_commands(if_name, curr_conf, req_state)\n if self._purge:\n for if_name, curr_conf in iteritems(self._current_config):\n if if_name not in req_interfaces:\n req_state = 'disabled'\n self._gen_pfc_commands(if_name, curr_conf, req_state)\n\n\ndef main():\n \"\"\" main entry point for module execution\n \"\"\"\n OnyxPfcInterfaceModule.main()\n\n\nif __name__ == '__main__':\n main()\n", "path": "lib/ansible/modules/network/onyx/onyx_pfc_interface.py"}]} | 3,595 | 292 |
gh_patches_debug_30399 | rasdani/github-patches | git_diff | aws-powertools__powertools-lambda-python-504 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
bug: aws scalar type for AWSDateTime should include milliseconds
**What were you trying to accomplish?**
## Expected Behavior
AWSDateTime - An extended ISO 8601 date and time string in the format YYYY-MM-DDThh:mm:ss.sssZ.
## Current Behavior
AWSDateTime is not including the millisecond part `sss`.
## Possible Solution
Generate timestamps to include the milliseconds
## Steps to Reproduce (for bugs)
```python3
> print(aws_datetime())
2021-07-02T17:09:47Z
````
## Environment
* **Powertools version used**: 1.17.0
* **Packaging format (Layers, PyPi)**: PyPi
* **AWS Lambda function runtime:** Python 3.8
</issue>
<code>
[start of aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py]
1 import datetime
2 import time
3 import uuid
4
5
6 def _formatted_time(now: datetime.date, fmt: str, timezone_offset: int) -> str:
7 """String formatted time with optional timezone offset
8
9 Parameters
10 ----------
11 now : datetime.date
12 Current datetime with zero timezone offset
13 fmt : str
14 Data format before adding timezone offset
15 timezone_offset : int
16 Timezone offset in hours, defaults to 0
17 Returns
18 -------
19 str
20 Returns string formatted time with optional timezone offset
21 """
22 if timezone_offset == 0:
23 return now.strftime(fmt + "Z")
24
25 now = now + datetime.timedelta(hours=timezone_offset)
26 fmt += "+" if timezone_offset > 0 else "-"
27 fmt += str(abs(timezone_offset)).zfill(2)
28 fmt += ":00:00"
29
30 return now.strftime(fmt)
31
32
33 def make_id() -> str:
34 """ID - A unique identifier for an object. This scalar is serialized like a String but isn't meant to be
35 human-readable."""
36 return str(uuid.uuid4())
37
38
39 def aws_date(timezone_offset: int = 0) -> str:
40 """AWSDate - An extended ISO 8601 date string in the format YYYY-MM-DD.
41
42 Parameters
43 ----------
44 timezone_offset : int
45 Timezone offset, defaults to 0
46
47 Returns
48 -------
49 str
50 Returns current time as AWSDate scalar string with optional timezone offset
51 """
52 return _formatted_time(datetime.datetime.utcnow(), "%Y-%m-%d", timezone_offset)
53
54
55 def aws_time(timezone_offset: int = 0) -> str:
56 """AWSTime - An extended ISO 8601 time string in the format hh:mm:ss.sss.
57
58 Parameters
59 ----------
60 timezone_offset : int
61 Timezone offset, defaults to 0
62
63 Returns
64 -------
65 str
66 Returns current time as AWSTime scalar string with optional timezone offset
67 """
68 return _formatted_time(datetime.datetime.utcnow(), "%H:%M:%S", timezone_offset)
69
70
71 def aws_datetime(timezone_offset: int = 0) -> str:
72 """AWSDateTime - An extended ISO 8601 date and time string in the format YYYY-MM-DDThh:mm:ss.sssZ.
73
74 Parameters
75 ----------
76 timezone_offset : int
77 Timezone offset, defaults to 0
78
79 Returns
80 -------
81 str
82 Returns current time as AWSDateTime scalar string with optional timezone offset
83 """
84 return _formatted_time(datetime.datetime.utcnow(), "%Y-%m-%dT%H:%M:%S", timezone_offset)
85
86
87 def aws_timestamp() -> int:
88 """AWSTimestamp - An integer value representing the number of seconds before or after 1970-01-01-T00:00Z."""
89 return int(time.time())
90
[end of aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py b/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py
--- a/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py
+++ b/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py
@@ -19,15 +19,21 @@
str
Returns string formatted time with optional timezone offset
"""
- if timezone_offset == 0:
- return now.strftime(fmt + "Z")
+ if timezone_offset != 0:
+ now = now + datetime.timedelta(hours=timezone_offset)
+
+ datetime_str = now.strftime(fmt)
+ if fmt.endswith(".%f"):
+ datetime_str = datetime_str[:-3]
- now = now + datetime.timedelta(hours=timezone_offset)
- fmt += "+" if timezone_offset > 0 else "-"
- fmt += str(abs(timezone_offset)).zfill(2)
- fmt += ":00:00"
+ if timezone_offset == 0:
+ postfix = "Z"
+ else:
+ postfix = "+" if timezone_offset > 0 else "-"
+ postfix += str(abs(timezone_offset)).zfill(2)
+ postfix += ":00:00"
- return now.strftime(fmt)
+ return datetime_str + postfix
def make_id() -> str:
@@ -65,7 +71,7 @@
str
Returns current time as AWSTime scalar string with optional timezone offset
"""
- return _formatted_time(datetime.datetime.utcnow(), "%H:%M:%S", timezone_offset)
+ return _formatted_time(datetime.datetime.utcnow(), "%H:%M:%S.%f", timezone_offset)
def aws_datetime(timezone_offset: int = 0) -> str:
@@ -81,7 +87,7 @@
str
Returns current time as AWSDateTime scalar string with optional timezone offset
"""
- return _formatted_time(datetime.datetime.utcnow(), "%Y-%m-%dT%H:%M:%S", timezone_offset)
+ return _formatted_time(datetime.datetime.utcnow(), "%Y-%m-%dT%H:%M:%S.%f", timezone_offset)
def aws_timestamp() -> int:
| {"golden_diff": "diff --git a/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py b/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py\n--- a/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py\n+++ b/aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py\n@@ -19,15 +19,21 @@\n str\n Returns string formatted time with optional timezone offset\n \"\"\"\n- if timezone_offset == 0:\n- return now.strftime(fmt + \"Z\")\n+ if timezone_offset != 0:\n+ now = now + datetime.timedelta(hours=timezone_offset)\n+\n+ datetime_str = now.strftime(fmt)\n+ if fmt.endswith(\".%f\"):\n+ datetime_str = datetime_str[:-3]\n \n- now = now + datetime.timedelta(hours=timezone_offset)\n- fmt += \"+\" if timezone_offset > 0 else \"-\"\n- fmt += str(abs(timezone_offset)).zfill(2)\n- fmt += \":00:00\"\n+ if timezone_offset == 0:\n+ postfix = \"Z\"\n+ else:\n+ postfix = \"+\" if timezone_offset > 0 else \"-\"\n+ postfix += str(abs(timezone_offset)).zfill(2)\n+ postfix += \":00:00\"\n \n- return now.strftime(fmt)\n+ return datetime_str + postfix\n \n \n def make_id() -> str:\n@@ -65,7 +71,7 @@\n str\n Returns current time as AWSTime scalar string with optional timezone offset\n \"\"\"\n- return _formatted_time(datetime.datetime.utcnow(), \"%H:%M:%S\", timezone_offset)\n+ return _formatted_time(datetime.datetime.utcnow(), \"%H:%M:%S.%f\", timezone_offset)\n \n \n def aws_datetime(timezone_offset: int = 0) -> str:\n@@ -81,7 +87,7 @@\n str\n Returns current time as AWSDateTime scalar string with optional timezone offset\n \"\"\"\n- return _formatted_time(datetime.datetime.utcnow(), \"%Y-%m-%dT%H:%M:%S\", timezone_offset)\n+ return _formatted_time(datetime.datetime.utcnow(), \"%Y-%m-%dT%H:%M:%S.%f\", timezone_offset)\n \n \n def aws_timestamp() -> int:\n", "issue": "bug: aws scalar type for AWSDateTime should include milliseconds\n**What were you trying to accomplish?**\r\n\r\n## Expected Behavior\r\n\r\nAWSDateTime - An extended ISO 8601 date and time string in the format YYYY-MM-DDThh:mm:ss.sssZ.\r\n\r\n## Current Behavior\r\n\r\nAWSDateTime is not including the millisecond part `sss`.\r\n\r\n## Possible Solution\r\n\r\nGenerate timestamps to include the milliseconds\r\n\r\n## Steps to Reproduce (for bugs)\r\n\r\n```python3\r\n> print(aws_datetime())\r\n2021-07-02T17:09:47Z\r\n````\r\n\r\n## Environment\r\n\r\n* **Powertools version used**: 1.17.0\r\n* **Packaging format (Layers, PyPi)**: PyPi\r\n* **AWS Lambda function runtime:** Python 3.8\r\n\n", "before_files": [{"content": "import datetime\nimport time\nimport uuid\n\n\ndef _formatted_time(now: datetime.date, fmt: str, timezone_offset: int) -> str:\n \"\"\"String formatted time with optional timezone offset\n\n Parameters\n ----------\n now : datetime.date\n Current datetime with zero timezone offset\n fmt : str\n Data format before adding timezone offset\n timezone_offset : int\n Timezone offset in hours, defaults to 0\n Returns\n -------\n str\n Returns string formatted time with optional timezone offset\n \"\"\"\n if timezone_offset == 0:\n return now.strftime(fmt + \"Z\")\n\n now = now + datetime.timedelta(hours=timezone_offset)\n fmt += \"+\" if timezone_offset > 0 else \"-\"\n fmt += str(abs(timezone_offset)).zfill(2)\n fmt += \":00:00\"\n\n return now.strftime(fmt)\n\n\ndef make_id() -> str:\n \"\"\"ID - A unique identifier for an object. This scalar is serialized like a String but isn't meant to be\n human-readable.\"\"\"\n return str(uuid.uuid4())\n\n\ndef aws_date(timezone_offset: int = 0) -> str:\n \"\"\"AWSDate - An extended ISO 8601 date string in the format YYYY-MM-DD.\n\n Parameters\n ----------\n timezone_offset : int\n Timezone offset, defaults to 0\n\n Returns\n -------\n str\n Returns current time as AWSDate scalar string with optional timezone offset\n \"\"\"\n return _formatted_time(datetime.datetime.utcnow(), \"%Y-%m-%d\", timezone_offset)\n\n\ndef aws_time(timezone_offset: int = 0) -> str:\n \"\"\"AWSTime - An extended ISO 8601 time string in the format hh:mm:ss.sss.\n\n Parameters\n ----------\n timezone_offset : int\n Timezone offset, defaults to 0\n\n Returns\n -------\n str\n Returns current time as AWSTime scalar string with optional timezone offset\n \"\"\"\n return _formatted_time(datetime.datetime.utcnow(), \"%H:%M:%S\", timezone_offset)\n\n\ndef aws_datetime(timezone_offset: int = 0) -> str:\n \"\"\"AWSDateTime - An extended ISO 8601 date and time string in the format YYYY-MM-DDThh:mm:ss.sssZ.\n\n Parameters\n ----------\n timezone_offset : int\n Timezone offset, defaults to 0\n\n Returns\n -------\n str\n Returns current time as AWSDateTime scalar string with optional timezone offset\n \"\"\"\n return _formatted_time(datetime.datetime.utcnow(), \"%Y-%m-%dT%H:%M:%S\", timezone_offset)\n\n\ndef aws_timestamp() -> int:\n \"\"\"AWSTimestamp - An integer value representing the number of seconds before or after 1970-01-01-T00:00Z.\"\"\"\n return int(time.time())\n", "path": "aws_lambda_powertools/utilities/data_classes/appsync/scalar_types_utils.py"}]} | 1,514 | 488 |
gh_patches_debug_24472 | rasdani/github-patches | git_diff | readthedocs__readthedocs.org-3593 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
List of redirects doesn't say which URLs are being redirected (if exact redirects)
## Details
- Project URL: https://readthedocs.org/projects/bigchaindb/
- List of project redirects (URL): https://readthedocs.org/dashboard/bigchaindb/redirects/
## Expected Result
When I make a bunch of redirects, I would expect the list of exact redirects to say the URL being redirected (and maybe where). Maybe the list would be simple but I'd be able to click on each item to see the details (such as the URL which get redirected and where).
## Actual Result
The actual list of redirects doesn't say anything about each one, other than it's an "Exact Redirect" (as seen in the image below). Also, I can't click on a redirect to find out more information about it.
What if I want to remove one (but only one) redirect? How can I pick the one to remove?
<hr>
</issue>
<code>
[start of readthedocs/redirects/models.py]
1 """Django models for the redirects app."""
2
3 from __future__ import absolute_import
4 from builtins import object
5 from django.db import models
6 from django.utils.encoding import python_2_unicode_compatible
7 from django.utils.translation import ugettext
8 from django.utils.translation import ugettext_lazy as _
9 import logging
10 import re
11
12 from readthedocs.core.resolver import resolve_path
13 from readthedocs.projects.models import Project
14 from .managers import RedirectManager
15
16
17 log = logging.getLogger(__name__)
18
19
20 HTTP_STATUS_CHOICES = (
21 (301, _('301 - Permanent Redirect')),
22 (302, _('302 - Temporary Redirect')),
23 )
24
25 STATUS_CHOICES = (
26 (True, _('Active')),
27 (False, _('Inactive')),
28 )
29
30 TYPE_CHOICES = (
31 ('prefix', _('Prefix Redirect')),
32 ('page', _('Page Redirect')),
33 ('exact', _('Exact Redirect')),
34 ('sphinx_html', _('Sphinx HTMLDir -> HTML')),
35 ('sphinx_htmldir', _('Sphinx HTML -> HTMLDir')),
36 # ('advanced', _('Advanced')),
37 )
38
39 from_url_helptext = _('Absolute path, excluding the domain. '
40 'Example: <b>/docs/</b> or <b>/install.html</b>'
41 )
42 to_url_helptext = _('Absolute or relative URL. Examples: '
43 '<b>/tutorial/install.html</b>'
44 )
45 redirect_type_helptext = _('The type of redirect you wish to use.')
46
47
48 @python_2_unicode_compatible
49 class Redirect(models.Model):
50
51 """A HTTP redirect associated with a Project."""
52
53 project = models.ForeignKey(Project, verbose_name=_('Project'),
54 related_name='redirects')
55
56 redirect_type = models.CharField(_('Redirect Type'), max_length=255, choices=TYPE_CHOICES,
57 help_text=redirect_type_helptext)
58
59 from_url = models.CharField(_('From URL'), max_length=255,
60 db_index=True, help_text=from_url_helptext, blank=True)
61
62 to_url = models.CharField(_('To URL'), max_length=255,
63 db_index=True, help_text=to_url_helptext, blank=True)
64
65 http_status = models.SmallIntegerField(_('HTTP Status'),
66 choices=HTTP_STATUS_CHOICES,
67 default=301)
68 status = models.BooleanField(choices=STATUS_CHOICES, default=True)
69
70 create_dt = models.DateTimeField(auto_now_add=True)
71 update_dt = models.DateTimeField(auto_now=True)
72
73 objects = RedirectManager()
74
75 class Meta(object):
76 verbose_name = _('redirect')
77 verbose_name_plural = _('redirects')
78 ordering = ('-update_dt',)
79
80 def __str__(self):
81 if self.redirect_type == 'prefix':
82 return ugettext('Prefix Redirect:') + ' %s ->' % self.from_url
83 elif self.redirect_type == 'page':
84 return ugettext('Page Redirect:') + ' %s -> %s' % (
85 self.from_url,
86 self.to_url)
87 return ugettext('Redirect: %s' % self.get_redirect_type_display())
88
89 def get_full_path(self, filename, language=None, version_slug=None):
90 """
91 Return a full path for a given filename.
92
93 This will include version and language information. No protocol/domain
94 is returned.
95 """
96 # Handle explicit http redirects
97 if re.match('^https?://', filename):
98 return filename
99
100 return resolve_path(
101 project=self.project, language=language,
102 version_slug=version_slug, filename=filename
103 )
104
105 def get_redirect_path(self, path, language=None, version_slug=None):
106 method = getattr(self, 'redirect_{type}'.format(
107 type=self.redirect_type))
108 return method(path, language=language, version_slug=version_slug)
109
110 def redirect_prefix(self, path, language=None, version_slug=None):
111 if path.startswith(self.from_url):
112 log.debug('Redirecting %s', self)
113 cut_path = re.sub('^%s' % self.from_url, '', path)
114 to = self.get_full_path(
115 filename=cut_path,
116 language=language,
117 version_slug=version_slug)
118 return to
119
120 def redirect_page(self, path, language=None, version_slug=None):
121 if path == self.from_url:
122 log.debug('Redirecting %s', self)
123 to = self.get_full_path(
124 filename=self.to_url.lstrip('/'),
125 language=language,
126 version_slug=version_slug)
127 return to
128
129 def redirect_exact(self, path, **__):
130 if path == self.from_url:
131 log.debug('Redirecting %s', self)
132 return self.to_url
133 # Handle full sub-level redirects
134 if '$rest' in self.from_url:
135 match = self.from_url.split('$rest')[0]
136 if path.startswith(match):
137 cut_path = re.sub('^%s' % match, self.to_url, path)
138 return cut_path
139
140 def redirect_sphinx_html(self, path, language=None, version_slug=None):
141 for ending in ['/', '/index.html']:
142 if path.endswith(ending):
143 log.debug('Redirecting %s', self)
144 path = path[1:] # Strip leading slash.
145 to = re.sub(ending + '$', '.html', path)
146 return self.get_full_path(
147 filename=to,
148 language=language,
149 version_slug=version_slug)
150
151 def redirect_sphinx_htmldir(self, path, language=None, version_slug=None):
152 if path.endswith('.html'):
153 log.debug('Redirecting %s', self)
154 path = path[1:] # Strip leading slash.
155 to = re.sub('.html$', '/', path)
156 return self.get_full_path(
157 filename=to,
158 language=language,
159 version_slug=version_slug)
160
[end of readthedocs/redirects/models.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/readthedocs/redirects/models.py b/readthedocs/redirects/models.py
--- a/readthedocs/redirects/models.py
+++ b/readthedocs/redirects/models.py
@@ -78,13 +78,30 @@
ordering = ('-update_dt',)
def __str__(self):
- if self.redirect_type == 'prefix':
- return ugettext('Prefix Redirect:') + ' %s ->' % self.from_url
- elif self.redirect_type == 'page':
- return ugettext('Page Redirect:') + ' %s -> %s' % (
- self.from_url,
- self.to_url)
- return ugettext('Redirect: %s' % self.get_redirect_type_display())
+ redirect_text = '{type}: {from_to_url}'
+ if self.redirect_type in ['prefix', 'page', 'exact']:
+ return redirect_text.format(
+ type=self.get_redirect_type_display(),
+ from_to_url=self.get_from_to_url_display()
+ )
+ return ugettext('Redirect: {}'.format(
+ self.get_redirect_type_display())
+ )
+
+ def get_from_to_url_display(self):
+ if self.redirect_type in ['prefix', 'page', 'exact']:
+ from_url = self.from_url
+ to_url = self.to_url
+ if self.redirect_type == 'prefix':
+ to_url = '/{lang}/{version}/'.format(
+ lang=self.project.language,
+ version=self.project.default_version
+ )
+ return '{from_url} -> {to_url}'.format(
+ from_url=from_url,
+ to_url=to_url
+ )
+ return ''
def get_full_path(self, filename, language=None, version_slug=None):
"""
| {"golden_diff": "diff --git a/readthedocs/redirects/models.py b/readthedocs/redirects/models.py\n--- a/readthedocs/redirects/models.py\n+++ b/readthedocs/redirects/models.py\n@@ -78,13 +78,30 @@\n ordering = ('-update_dt',)\n \n def __str__(self):\n- if self.redirect_type == 'prefix':\n- return ugettext('Prefix Redirect:') + ' %s ->' % self.from_url\n- elif self.redirect_type == 'page':\n- return ugettext('Page Redirect:') + ' %s -> %s' % (\n- self.from_url,\n- self.to_url)\n- return ugettext('Redirect: %s' % self.get_redirect_type_display())\n+ redirect_text = '{type}: {from_to_url}'\n+ if self.redirect_type in ['prefix', 'page', 'exact']:\n+ return redirect_text.format(\n+ type=self.get_redirect_type_display(),\n+ from_to_url=self.get_from_to_url_display()\n+ )\n+ return ugettext('Redirect: {}'.format(\n+ self.get_redirect_type_display())\n+ )\n+\n+ def get_from_to_url_display(self):\n+ if self.redirect_type in ['prefix', 'page', 'exact']:\n+ from_url = self.from_url\n+ to_url = self.to_url\n+ if self.redirect_type == 'prefix':\n+ to_url = '/{lang}/{version}/'.format(\n+ lang=self.project.language,\n+ version=self.project.default_version\n+ )\n+ return '{from_url} -> {to_url}'.format(\n+ from_url=from_url,\n+ to_url=to_url\n+ )\n+ return ''\n \n def get_full_path(self, filename, language=None, version_slug=None):\n \"\"\"\n", "issue": "List of redirects doesn't say which URLs are being redirected (if exact redirects)\n## Details\n- Project URL: https://readthedocs.org/projects/bigchaindb/\n- List of project redirects (URL): https://readthedocs.org/dashboard/bigchaindb/redirects/\n## Expected Result\n\nWhen I make a bunch of redirects, I would expect the list of exact redirects to say the URL being redirected (and maybe where). Maybe the list would be simple but I'd be able to click on each item to see the details (such as the URL which get redirected and where).\n## Actual Result\n\nThe actual list of redirects doesn't say anything about each one, other than it's an \"Exact Redirect\" (as seen in the image below). Also, I can't click on a redirect to find out more information about it.\n\nWhat if I want to remove one (but only one) redirect? How can I pick the one to remove?\n\n<hr>\n\n\n\n", "before_files": [{"content": "\"\"\"Django models for the redirects app.\"\"\"\n\nfrom __future__ import absolute_import\nfrom builtins import object\nfrom django.db import models\nfrom django.utils.encoding import python_2_unicode_compatible\nfrom django.utils.translation import ugettext\nfrom django.utils.translation import ugettext_lazy as _\nimport logging\nimport re\n\nfrom readthedocs.core.resolver import resolve_path\nfrom readthedocs.projects.models import Project\nfrom .managers import RedirectManager\n\n\nlog = logging.getLogger(__name__)\n\n\nHTTP_STATUS_CHOICES = (\n (301, _('301 - Permanent Redirect')),\n (302, _('302 - Temporary Redirect')),\n)\n\nSTATUS_CHOICES = (\n (True, _('Active')),\n (False, _('Inactive')),\n)\n\nTYPE_CHOICES = (\n ('prefix', _('Prefix Redirect')),\n ('page', _('Page Redirect')),\n ('exact', _('Exact Redirect')),\n ('sphinx_html', _('Sphinx HTMLDir -> HTML')),\n ('sphinx_htmldir', _('Sphinx HTML -> HTMLDir')),\n # ('advanced', _('Advanced')),\n)\n\nfrom_url_helptext = _('Absolute path, excluding the domain. '\n 'Example: <b>/docs/</b> or <b>/install.html</b>'\n )\nto_url_helptext = _('Absolute or relative URL. Examples: '\n '<b>/tutorial/install.html</b>'\n )\nredirect_type_helptext = _('The type of redirect you wish to use.')\n\n\n@python_2_unicode_compatible\nclass Redirect(models.Model):\n\n \"\"\"A HTTP redirect associated with a Project.\"\"\"\n\n project = models.ForeignKey(Project, verbose_name=_('Project'),\n related_name='redirects')\n\n redirect_type = models.CharField(_('Redirect Type'), max_length=255, choices=TYPE_CHOICES,\n help_text=redirect_type_helptext)\n\n from_url = models.CharField(_('From URL'), max_length=255,\n db_index=True, help_text=from_url_helptext, blank=True)\n\n to_url = models.CharField(_('To URL'), max_length=255,\n db_index=True, help_text=to_url_helptext, blank=True)\n\n http_status = models.SmallIntegerField(_('HTTP Status'),\n choices=HTTP_STATUS_CHOICES,\n default=301)\n status = models.BooleanField(choices=STATUS_CHOICES, default=True)\n\n create_dt = models.DateTimeField(auto_now_add=True)\n update_dt = models.DateTimeField(auto_now=True)\n\n objects = RedirectManager()\n\n class Meta(object):\n verbose_name = _('redirect')\n verbose_name_plural = _('redirects')\n ordering = ('-update_dt',)\n\n def __str__(self):\n if self.redirect_type == 'prefix':\n return ugettext('Prefix Redirect:') + ' %s ->' % self.from_url\n elif self.redirect_type == 'page':\n return ugettext('Page Redirect:') + ' %s -> %s' % (\n self.from_url,\n self.to_url)\n return ugettext('Redirect: %s' % self.get_redirect_type_display())\n\n def get_full_path(self, filename, language=None, version_slug=None):\n \"\"\"\n Return a full path for a given filename.\n\n This will include version and language information. No protocol/domain\n is returned.\n \"\"\"\n # Handle explicit http redirects\n if re.match('^https?://', filename):\n return filename\n\n return resolve_path(\n project=self.project, language=language,\n version_slug=version_slug, filename=filename\n )\n\n def get_redirect_path(self, path, language=None, version_slug=None):\n method = getattr(self, 'redirect_{type}'.format(\n type=self.redirect_type))\n return method(path, language=language, version_slug=version_slug)\n\n def redirect_prefix(self, path, language=None, version_slug=None):\n if path.startswith(self.from_url):\n log.debug('Redirecting %s', self)\n cut_path = re.sub('^%s' % self.from_url, '', path)\n to = self.get_full_path(\n filename=cut_path,\n language=language,\n version_slug=version_slug)\n return to\n\n def redirect_page(self, path, language=None, version_slug=None):\n if path == self.from_url:\n log.debug('Redirecting %s', self)\n to = self.get_full_path(\n filename=self.to_url.lstrip('/'),\n language=language,\n version_slug=version_slug)\n return to\n\n def redirect_exact(self, path, **__):\n if path == self.from_url:\n log.debug('Redirecting %s', self)\n return self.to_url\n # Handle full sub-level redirects\n if '$rest' in self.from_url:\n match = self.from_url.split('$rest')[0]\n if path.startswith(match):\n cut_path = re.sub('^%s' % match, self.to_url, path)\n return cut_path\n\n def redirect_sphinx_html(self, path, language=None, version_slug=None):\n for ending in ['/', '/index.html']:\n if path.endswith(ending):\n log.debug('Redirecting %s', self)\n path = path[1:] # Strip leading slash.\n to = re.sub(ending + '$', '.html', path)\n return self.get_full_path(\n filename=to,\n language=language,\n version_slug=version_slug)\n\n def redirect_sphinx_htmldir(self, path, language=None, version_slug=None):\n if path.endswith('.html'):\n log.debug('Redirecting %s', self)\n path = path[1:] # Strip leading slash.\n to = re.sub('.html$', '/', path)\n return self.get_full_path(\n filename=to,\n language=language,\n version_slug=version_slug)\n", "path": "readthedocs/redirects/models.py"}]} | 2,410 | 388 |
gh_patches_debug_32440 | rasdani/github-patches | git_diff | OpenMined__PySyft-3591 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Calling syft.grid.register() twice should throw an informative error
**Is your feature request related to a problem? Please describe.**
If you call syft.grid.register() twice in the same python runtime it should raise an error describing that you can't do this - that they shoudl restart the python runtime and try again.
</issue>
<code>
[start of syft/grid/__init__.py]
1 from .network import Network
2 import sys
3 import uuid
4
5 DEFAULT_NETWORK_URL = "ws://ec2-13-59-45-128.us-east-2.compute.amazonaws.com"
6
7
8 def register(**kwargs):
9 """ Add this process as a new peer registering it in the grid network.
10
11 Returns:
12 peer: Peer Network instance.
13 """
14 try:
15 if not kwargs:
16 args = {"max_size": None, "timeout": 444, "url": DEFAULT_NETWORK_URL}
17 else:
18 args = kwargs
19
20 peer_id = str(uuid.uuid4())
21 sys.stdout.write(
22 "Connecting to OpenGrid (" + "\033[94m" + args["url"] + "\033[0m" + ") ... "
23 )
24
25 peer = Network(peer_id, **args)
26
27 sys.stdout.write("\033[92m" + "OK" + "\033[0m" + "\n")
28 sys.stdout.write("Peer ID: " + peer_id + "\n")
29
30 sys.stdout.write(
31 "\033[93m" + "DISCLAIMER" + "\033[0m"
32 ":"
33 + "\033[1m"
34 + " OpenGrid is an experimental feature currently in alpha. Do not use this to protect real-world data.\n"
35 + "\033[0m"
36 )
37
38 sys.stdout.write("Where to get help: \n")
39 sys.stdout.write(
40 " - Join our slack (https://slack.openmined.org) and ask for help in the #lib_syft channel.\n"
41 )
42 sys.stdout.write(
43 " - File a Github Issue: https://github.com/OpenMined/PySyft and add the string '#opengrid' in the issue title.\n"
44 )
45 sys.stdout.write(
46 " - Want to join in our development team? Apply here: https://forms.gle/wcH1vxzvPyDSbSVW6\n"
47 )
48 peer.start()
49 return peer
50 except Exception as e:
51 sys.stdout.write("\033[91m" + "FAIL" + "\033[0m" + "\n")
52 sys.stdout.write("You were not able to register your node.\n")
53
[end of syft/grid/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/syft/grid/__init__.py b/syft/grid/__init__.py
--- a/syft/grid/__init__.py
+++ b/syft/grid/__init__.py
@@ -4,13 +4,25 @@
DEFAULT_NETWORK_URL = "ws://ec2-13-59-45-128.us-east-2.compute.amazonaws.com"
+_registered_peer = None
+
def register(**kwargs):
""" Add this process as a new peer registering it in the grid network.
-
+
Returns:
peer: Peer Network instance.
"""
+ global _registered_peer
+
+ if isinstance(_registered_peer, Network):
+ sys.stdout.write(
+ "\033[93m" + "WARNING" + "\033[0m"
+ ":" + f" You are already a registered peer!\n{_registered_peer}\n"
+ )
+
+ return _registered_peer
+
try:
if not kwargs:
args = {"max_size": None, "timeout": 444, "url": DEFAULT_NETWORK_URL}
@@ -22,7 +34,7 @@
"Connecting to OpenGrid (" + "\033[94m" + args["url"] + "\033[0m" + ") ... "
)
- peer = Network(peer_id, **args)
+ _registered_peer = Network(peer_id, **args)
sys.stdout.write("\033[92m" + "OK" + "\033[0m" + "\n")
sys.stdout.write("Peer ID: " + peer_id + "\n")
@@ -45,8 +57,11 @@
sys.stdout.write(
" - Want to join in our development team? Apply here: https://forms.gle/wcH1vxzvPyDSbSVW6\n"
)
- peer.start()
- return peer
+
+ _registered_peer.start()
+
+ return _registered_peer
+
except Exception as e:
sys.stdout.write("\033[91m" + "FAIL" + "\033[0m" + "\n")
sys.stdout.write("You were not able to register your node.\n")
| {"golden_diff": "diff --git a/syft/grid/__init__.py b/syft/grid/__init__.py\n--- a/syft/grid/__init__.py\n+++ b/syft/grid/__init__.py\n@@ -4,13 +4,25 @@\n \n DEFAULT_NETWORK_URL = \"ws://ec2-13-59-45-128.us-east-2.compute.amazonaws.com\"\n \n+_registered_peer = None\n+\n \n def register(**kwargs):\n \"\"\" Add this process as a new peer registering it in the grid network.\n- \n+\n Returns:\n peer: Peer Network instance.\n \"\"\"\n+ global _registered_peer\n+\n+ if isinstance(_registered_peer, Network):\n+ sys.stdout.write(\n+ \"\\033[93m\" + \"WARNING\" + \"\\033[0m\"\n+ \":\" + f\" You are already a registered peer!\\n{_registered_peer}\\n\"\n+ )\n+\n+ return _registered_peer\n+\n try:\n if not kwargs:\n args = {\"max_size\": None, \"timeout\": 444, \"url\": DEFAULT_NETWORK_URL}\n@@ -22,7 +34,7 @@\n \"Connecting to OpenGrid (\" + \"\\033[94m\" + args[\"url\"] + \"\\033[0m\" + \") ... \"\n )\n \n- peer = Network(peer_id, **args)\n+ _registered_peer = Network(peer_id, **args)\n \n sys.stdout.write(\"\\033[92m\" + \"OK\" + \"\\033[0m\" + \"\\n\")\n sys.stdout.write(\"Peer ID: \" + peer_id + \"\\n\")\n@@ -45,8 +57,11 @@\n sys.stdout.write(\n \" - Want to join in our development team? Apply here: https://forms.gle/wcH1vxzvPyDSbSVW6\\n\"\n )\n- peer.start()\n- return peer\n+\n+ _registered_peer.start()\n+\n+ return _registered_peer\n+\n except Exception as e:\n sys.stdout.write(\"\\033[91m\" + \"FAIL\" + \"\\033[0m\" + \"\\n\")\n sys.stdout.write(\"You were not able to register your node.\\n\")\n", "issue": "Calling syft.grid.register() twice should throw an informative error\n**Is your feature request related to a problem? Please describe.**\r\nIf you call syft.grid.register() twice in the same python runtime it should raise an error describing that you can't do this - that they shoudl restart the python runtime and try again.\n", "before_files": [{"content": "from .network import Network\nimport sys\nimport uuid\n\nDEFAULT_NETWORK_URL = \"ws://ec2-13-59-45-128.us-east-2.compute.amazonaws.com\"\n\n\ndef register(**kwargs):\n \"\"\" Add this process as a new peer registering it in the grid network.\n \n Returns:\n peer: Peer Network instance.\n \"\"\"\n try:\n if not kwargs:\n args = {\"max_size\": None, \"timeout\": 444, \"url\": DEFAULT_NETWORK_URL}\n else:\n args = kwargs\n\n peer_id = str(uuid.uuid4())\n sys.stdout.write(\n \"Connecting to OpenGrid (\" + \"\\033[94m\" + args[\"url\"] + \"\\033[0m\" + \") ... \"\n )\n\n peer = Network(peer_id, **args)\n\n sys.stdout.write(\"\\033[92m\" + \"OK\" + \"\\033[0m\" + \"\\n\")\n sys.stdout.write(\"Peer ID: \" + peer_id + \"\\n\")\n\n sys.stdout.write(\n \"\\033[93m\" + \"DISCLAIMER\" + \"\\033[0m\"\n \":\"\n + \"\\033[1m\"\n + \" OpenGrid is an experimental feature currently in alpha. Do not use this to protect real-world data.\\n\"\n + \"\\033[0m\"\n )\n\n sys.stdout.write(\"Where to get help: \\n\")\n sys.stdout.write(\n \" - Join our slack (https://slack.openmined.org) and ask for help in the #lib_syft channel.\\n\"\n )\n sys.stdout.write(\n \" - File a Github Issue: https://github.com/OpenMined/PySyft and add the string '#opengrid' in the issue title.\\n\"\n )\n sys.stdout.write(\n \" - Want to join in our development team? Apply here: https://forms.gle/wcH1vxzvPyDSbSVW6\\n\"\n )\n peer.start()\n return peer\n except Exception as e:\n sys.stdout.write(\"\\033[91m\" + \"FAIL\" + \"\\033[0m\" + \"\\n\")\n sys.stdout.write(\"You were not able to register your node.\\n\")\n", "path": "syft/grid/__init__.py"}]} | 1,207 | 498 |
gh_patches_debug_48578 | rasdani/github-patches | git_diff | openai__gym-2683 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
py.typed not bundled in release
The latest pypi package [gym==0.23.0](https://pypi.org/project/gym/0.23.0/) does not include `py.typed`, resulting in failed `mypy` checks.
Reproduce by `pip install gym` and noting the missing file or downloading the zip from pypi (zip on GH contains the file).
</issue>
<code>
[start of setup.py]
1 import os.path
2 import sys
3 import itertools
4
5 from setuptools import find_packages, setup
6
7 # Don't import gym module here, since deps may not be installed
8 sys.path.insert(0, os.path.join(os.path.dirname(__file__), "gym"))
9 from version import VERSION
10
11 # Environment-specific dependencies.
12 extras = {
13 "atari": ["ale-py~=0.7.4"],
14 "accept-rom-license": ["autorom[accept-rom-license]~=0.4.2"],
15 "box2d": ["box2d-py==2.3.5", "pygame==2.1.0"],
16 "classic_control": ["pygame==2.1.0"],
17 "mujoco": ["mujoco_py>=1.50, <2.0"],
18 "toy_text": ["pygame==2.1.0", "scipy>=1.4.1"],
19 "other": ["lz4>=3.1.0", "opencv-python>=3.0"],
20 }
21
22 # Meta dependency groups.
23 nomujoco_blacklist = set(["mujoco", "accept-rom-license", "atari"])
24 nomujoco_groups = set(extras.keys()) - nomujoco_blacklist
25
26 extras["nomujoco"] = list(
27 itertools.chain.from_iterable(map(lambda group: extras[group], nomujoco_groups))
28 )
29
30
31 all_blacklist = set(["accept-rom-license"])
32 all_groups = set(extras.keys()) - all_blacklist
33
34 extras["all"] = list(
35 itertools.chain.from_iterable(map(lambda group: extras[group], all_groups))
36 )
37
38 setup(
39 name="gym",
40 version=VERSION,
41 description="Gym: A universal API for reinforcement learning environments",
42 url="https://www.gymlibrary.ml/",
43 author="Gym Community",
44 author_email="[email protected]",
45 license="MIT",
46 packages=[package for package in find_packages() if package.startswith("gym")],
47 zip_safe=False,
48 install_requires=[
49 "numpy>=1.18.0",
50 "cloudpickle>=1.2.0",
51 "importlib_metadata>=4.10.0; python_version < '3.10'",
52 "gym_notices>=0.0.4",
53 ],
54 extras_require=extras,
55 package_data={
56 "gym": [
57 "envs/mujoco/assets/*.xml",
58 "envs/classic_control/assets/*.png",
59 "envs/toy_text/font/*.ttf",
60 "envs/toy_text/img/*.png",
61 ]
62 },
63 tests_require=["pytest", "mock"],
64 python_requires=">=3.7",
65 classifiers=[
66 "Programming Language :: Python :: 3",
67 "Programming Language :: Python :: 3.7",
68 "Programming Language :: Python :: 3.8",
69 "Programming Language :: Python :: 3.9",
70 "Programming Language :: Python :: 3.10",
71 ],
72 )
73
[end of setup.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -58,6 +58,7 @@
"envs/classic_control/assets/*.png",
"envs/toy_text/font/*.ttf",
"envs/toy_text/img/*.png",
+ "py.typed",
]
},
tests_require=["pytest", "mock"],
| {"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -58,6 +58,7 @@\n \"envs/classic_control/assets/*.png\",\n \"envs/toy_text/font/*.ttf\",\n \"envs/toy_text/img/*.png\",\n+ \"py.typed\",\n ]\n },\n tests_require=[\"pytest\", \"mock\"],\n", "issue": "py.typed not bundled in release\nThe latest pypi package [gym==0.23.0](https://pypi.org/project/gym/0.23.0/) does not include `py.typed`, resulting in failed `mypy` checks.\r\n\r\nReproduce by `pip install gym` and noting the missing file or downloading the zip from pypi (zip on GH contains the file).\n", "before_files": [{"content": "import os.path\nimport sys\nimport itertools\n\nfrom setuptools import find_packages, setup\n\n# Don't import gym module here, since deps may not be installed\nsys.path.insert(0, os.path.join(os.path.dirname(__file__), \"gym\"))\nfrom version import VERSION\n\n# Environment-specific dependencies.\nextras = {\n \"atari\": [\"ale-py~=0.7.4\"],\n \"accept-rom-license\": [\"autorom[accept-rom-license]~=0.4.2\"],\n \"box2d\": [\"box2d-py==2.3.5\", \"pygame==2.1.0\"],\n \"classic_control\": [\"pygame==2.1.0\"],\n \"mujoco\": [\"mujoco_py>=1.50, <2.0\"],\n \"toy_text\": [\"pygame==2.1.0\", \"scipy>=1.4.1\"],\n \"other\": [\"lz4>=3.1.0\", \"opencv-python>=3.0\"],\n}\n\n# Meta dependency groups.\nnomujoco_blacklist = set([\"mujoco\", \"accept-rom-license\", \"atari\"])\nnomujoco_groups = set(extras.keys()) - nomujoco_blacklist\n\nextras[\"nomujoco\"] = list(\n itertools.chain.from_iterable(map(lambda group: extras[group], nomujoco_groups))\n)\n\n\nall_blacklist = set([\"accept-rom-license\"])\nall_groups = set(extras.keys()) - all_blacklist\n\nextras[\"all\"] = list(\n itertools.chain.from_iterable(map(lambda group: extras[group], all_groups))\n)\n\nsetup(\n name=\"gym\",\n version=VERSION,\n description=\"Gym: A universal API for reinforcement learning environments\",\n url=\"https://www.gymlibrary.ml/\",\n author=\"Gym Community\",\n author_email=\"[email protected]\",\n license=\"MIT\",\n packages=[package for package in find_packages() if package.startswith(\"gym\")],\n zip_safe=False,\n install_requires=[\n \"numpy>=1.18.0\",\n \"cloudpickle>=1.2.0\",\n \"importlib_metadata>=4.10.0; python_version < '3.10'\",\n \"gym_notices>=0.0.4\",\n ],\n extras_require=extras,\n package_data={\n \"gym\": [\n \"envs/mujoco/assets/*.xml\",\n \"envs/classic_control/assets/*.png\",\n \"envs/toy_text/font/*.ttf\",\n \"envs/toy_text/img/*.png\",\n ]\n },\n tests_require=[\"pytest\", \"mock\"],\n python_requires=\">=3.7\",\n classifiers=[\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n \"Programming Language :: Python :: 3.9\",\n \"Programming Language :: Python :: 3.10\",\n ],\n)\n", "path": "setup.py"}]} | 1,391 | 86 |
gh_patches_debug_36898 | rasdani/github-patches | git_diff | elastic__apm-agent-python-884 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
ReadTimeoutErrors on 169.254.169.254 /latest/api/token
After updating the agent to version 5.8.0 my all my Django `manage.py` commands seem to hang indefinitely and never finish and I'm first seeing:
`WARNING urllib3.connectionpool Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPConnectionPool(host='169.254.169.254', port=80): Read timed out. (read timeout=3.0)")': /latest/api/token connectionpool.py:749`
and then (after some time):
`ERROR elasticapm.transport Closing the transport connection timed out. base.py:261`
After this last error message the process just hangs indefinitely and has to be killed manually.
**To Reproduce**
I'm not able to reproduce this locally, it seems to happen exclusively in my staging/production environment on AWS.
There, it really only takes a Django management command to make it hang. For example:
```
$ python manage.py migrate
Operations to perform:
Apply all migrations: admin, auth, contenttypes, sessions
Running migrations:
No migrations to apply.
2020-07-03 13:17:19,256 WARNING urllib3.connectionpool Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPConnectionPool(host='169.254.169.254', port=80): Read timed out. (read timeout=3.0)")': /latest/api/token connectionpool.py:749
2020-07-03 13:17:27,164 ERROR elasticapm.transport Closing the transport connection timed out. base.py:261
```
**Environment**
- OS: `Linux 6094537dd0b9 4.14.181-108.257.amzn1.x86_64 elastic/apm-agent-python#1 SMP Wed May 27 02:43:03 UTC 2020 x86_64 GNU/Linux` (Docker container - python:3.8 image, docker running on Amazon Linux/2.15.2)
- Python version: 3.8.3
- Framework and version: Django 3.0.8 (same thing happens with 3.0.7)
- APM Server version: 7.5.2
- Agent version: 5.8.0 (I can confirm this **doesn't happen with v5.7.0**)
**Additional context**
The app runs on AWS ElasticBeanstalk Docker environment with python 3.8 image, pretty straight forward.
- `requirements.txt`:
<details>
<summary>Click to expand</summary>
```
appdirs==1.4.4
asgiref==3.2.10; python_version >= '3.5'
boto3==1.14.16
botocore==1.17.16
certifi==2020.6.20
cffi==1.14.0
chardet==3.0.4
cryptography==2.9.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
django-migration-linter==2.3.0
django-redis==4.12.1
django-sortedm2m==3.0.0
django-storages==1.9.1
django-widget-tweaks==1.4.8
django==3.0.8
djangorestframework-simplejwt==4.4.0
djangorestframework==3.11.0
docutils==0.15.2; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'
elastic-apm==5.8.0
factory-boy==2.12.0
faker==4.1.1; python_version >= '3.4'
future==0.18.2; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'
googlemaps==4.4.1
gunicorn==20.0.4
idna==2.10; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
jmespath==0.10.0; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'
jwcrypto==0.7
markdown==3.2.2
oauthlib==3.1.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
pillow==7.2.0
psycopg2-binary==2.8.5
pycparser==2.20; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
pyjwt==1.7.1
python-dateutil==2.8.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
python-twitter==3.5
pytz==2020.1
pyyaml==5.3.1
redis==3.5.3; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'
requests-oauthlib==1.3.0
requests==2.24.0
s3transfer==0.3.3
sentry-sdk==0.16.0
six==1.15.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
sqlparse==0.3.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
text-unidecode==1.3
twilio==6.43.0
ua-parser==0.10.0
uritemplate==3.0.1
urllib3==1.25.9; python_version != '3.4'
user-agents==2.1
```
</details>
</issue>
<code>
[start of elasticapm/utils/cloud.py]
1 # BSD 3-Clause License
2 #
3 # Copyright (c) 2019, Elasticsearch BV
4 # All rights reserved.
5 #
6 # Redistribution and use in source and binary forms, with or without
7 # modification, are permitted provided that the following conditions are met:
8 #
9 # * Redistributions of source code must retain the above copyright notice, this
10 # list of conditions and the following disclaimer.
11 #
12 # * Redistributions in binary form must reproduce the above copyright notice,
13 # this list of conditions and the following disclaimer in the documentation
14 # and/or other materials provided with the distribution.
15 #
16 # * Neither the name of the copyright holder nor the names of its
17 # contributors may be used to endorse or promote products derived from
18 # this software without specific prior written permission.
19 #
20 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
21 # AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
23 # DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
24 # FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 # DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
26 # SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
27 # CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
28 # OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30
31 import json
32 import os
33 import socket
34
35 import urllib3
36
37
38 def aws_metadata():
39 """
40 Fetch AWS metadata from the local metadata server. If metadata server is
41 not found, return an empty dictionary
42 """
43 http = urllib3.PoolManager()
44
45 try:
46 # This will throw an error if the metadata server isn't available,
47 # and will be quiet in the logs, unlike urllib3
48 socket.create_connection(("169.254.169.254", 80), 0.1)
49
50 ttl_header = {"X-aws-ec2-metadata-token-ttl-seconds": "300"}
51 token_url = "http://169.254.169.254/latest/api/token"
52 token_request = http.request("PUT", token_url, headers=ttl_header, timeout=3.0)
53 token = token_request.data.decode("utf-8")
54 aws_token_header = {"X-aws-ec2-metadata-token": token} if token else {}
55 metadata = json.loads(
56 http.request(
57 "GET",
58 "http://169.254.169.254/latest/dynamic/instance-identity/document",
59 headers=aws_token_header,
60 timeout=3.0,
61 retries=False,
62 ).data.decode("utf-8")
63 )
64
65 return {
66 "account": {"id": metadata["accountId"]},
67 "instance": {"id": metadata["instanceId"]},
68 "availability_zone": metadata["availabilityZone"],
69 "machine": {"type": metadata["instanceType"]},
70 "provider": "aws",
71 "region": metadata["region"],
72 }
73
74 except Exception:
75 # Not on an AWS box
76 return {}
77
78
79 def gcp_metadata():
80 """
81 Fetch GCP metadata from the local metadata server. If metadata server is
82 not found, return an empty dictionary
83 """
84 headers = {"Metadata-Flavor": "Google"}
85 http = urllib3.PoolManager()
86
87 try:
88 # This will throw an error if the metadata server isn't available,
89 # and will be quiet in the logs, unlike urllib3
90 socket.getaddrinfo("metadata.google.internal", 80, 0, socket.SOCK_STREAM)
91
92 metadata = json.loads(
93 http.request(
94 "GET",
95 "http://metadata.google.internal/computeMetadata/v1/?recursive=true",
96 headers=headers,
97 timeout=3.0,
98 retries=False,
99 ).data.decode("utf-8")
100 )
101
102 availability_zone = os.path.split(metadata["instance"]["zone"])[1]
103
104 return {
105 "provider": "gcp",
106 "instance": {"id": str(metadata["instance"]["id"]), "name": metadata["instance"]["name"]},
107 "project": {"id": str(metadata["project"]["numericProjectId"]), "name": metadata["project"]["projectId"]},
108 "availability_zone": availability_zone,
109 "region": availability_zone.rsplit("-", 1)[0],
110 "machine": {"type": metadata["instance"]["machineType"]},
111 }
112
113 except Exception:
114 # Not on a gcp box
115 return {}
116
117
118 def azure_metadata():
119 """
120 Fetch Azure metadata from the local metadata server. If metadata server is
121 not found, return an empty dictionary
122 """
123 headers = {"Metadata": "true"}
124 http = urllib3.PoolManager()
125
126 try:
127 # This will throw an error if the metadata server isn't available,
128 # and will be quiet in the logs, unlike urllib3
129 socket.create_connection(("169.254.169.254", 80), 0.1)
130
131 # Can't use newest metadata service version, as it's not guaranteed
132 # to be available in all regions
133 metadata = json.loads(
134 http.request(
135 "GET",
136 "http://169.254.169.254/metadata/instance/compute?api-version=2019-08-15",
137 headers=headers,
138 timeout=3.0,
139 retries=False,
140 ).data.decode("utf-8")
141 )
142
143 ret = {
144 "account": {"id": metadata["subscriptionId"]},
145 "instance": {"id": metadata["vmId"], "name": metadata["name"]},
146 "project": {"name": metadata["resourceGroupName"]},
147 "availability_zone": metadata["zone"],
148 "machine": {"type": metadata["vmSize"]},
149 "provider": "azure",
150 "region": metadata["location"],
151 }
152
153 if not ret["availability_zone"]:
154 ret.pop("availability_zone")
155 return ret
156
157 except Exception:
158 # Not on an Azure box
159 return {}
160
[end of elasticapm/utils/cloud.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/elasticapm/utils/cloud.py b/elasticapm/utils/cloud.py
--- a/elasticapm/utils/cloud.py
+++ b/elasticapm/utils/cloud.py
@@ -47,17 +47,26 @@
# and will be quiet in the logs, unlike urllib3
socket.create_connection(("169.254.169.254", 80), 0.1)
- ttl_header = {"X-aws-ec2-metadata-token-ttl-seconds": "300"}
- token_url = "http://169.254.169.254/latest/api/token"
- token_request = http.request("PUT", token_url, headers=ttl_header, timeout=3.0)
- token = token_request.data.decode("utf-8")
- aws_token_header = {"X-aws-ec2-metadata-token": token} if token else {}
+ try:
+ # This whole block is almost unnecessary. IMDSv1 will be supported
+ # indefinitely, so the only time this block is needed is if a
+ # security-conscious user has set the metadata service to require
+ # IMDSv2. Thus, the very expansive try:except: coverage.
+
+ # TODO: should we have a config option to completely disable IMDSv2 to reduce overhead?
+ ttl_header = {"X-aws-ec2-metadata-token-ttl-seconds": "300"}
+ token_url = "http://169.254.169.254/latest/api/token"
+ token_request = http.request("PUT", token_url, headers=ttl_header, timeout=1.0, retries=False)
+ token = token_request.data.decode("utf-8")
+ aws_token_header = {"X-aws-ec2-metadata-token": token} if token else {}
+ except Exception:
+ aws_token_header = {}
metadata = json.loads(
http.request(
"GET",
"http://169.254.169.254/latest/dynamic/instance-identity/document",
headers=aws_token_header,
- timeout=3.0,
+ timeout=1.0,
retries=False,
).data.decode("utf-8")
)
@@ -94,7 +103,7 @@
"GET",
"http://metadata.google.internal/computeMetadata/v1/?recursive=true",
headers=headers,
- timeout=3.0,
+ timeout=1.0,
retries=False,
).data.decode("utf-8")
)
@@ -135,7 +144,7 @@
"GET",
"http://169.254.169.254/metadata/instance/compute?api-version=2019-08-15",
headers=headers,
- timeout=3.0,
+ timeout=1.0,
retries=False,
).data.decode("utf-8")
)
| {"golden_diff": "diff --git a/elasticapm/utils/cloud.py b/elasticapm/utils/cloud.py\n--- a/elasticapm/utils/cloud.py\n+++ b/elasticapm/utils/cloud.py\n@@ -47,17 +47,26 @@\n # and will be quiet in the logs, unlike urllib3\n socket.create_connection((\"169.254.169.254\", 80), 0.1)\n \n- ttl_header = {\"X-aws-ec2-metadata-token-ttl-seconds\": \"300\"}\n- token_url = \"http://169.254.169.254/latest/api/token\"\n- token_request = http.request(\"PUT\", token_url, headers=ttl_header, timeout=3.0)\n- token = token_request.data.decode(\"utf-8\")\n- aws_token_header = {\"X-aws-ec2-metadata-token\": token} if token else {}\n+ try:\n+ # This whole block is almost unnecessary. IMDSv1 will be supported\n+ # indefinitely, so the only time this block is needed is if a\n+ # security-conscious user has set the metadata service to require\n+ # IMDSv2. Thus, the very expansive try:except: coverage.\n+\n+ # TODO: should we have a config option to completely disable IMDSv2 to reduce overhead?\n+ ttl_header = {\"X-aws-ec2-metadata-token-ttl-seconds\": \"300\"}\n+ token_url = \"http://169.254.169.254/latest/api/token\"\n+ token_request = http.request(\"PUT\", token_url, headers=ttl_header, timeout=1.0, retries=False)\n+ token = token_request.data.decode(\"utf-8\")\n+ aws_token_header = {\"X-aws-ec2-metadata-token\": token} if token else {}\n+ except Exception:\n+ aws_token_header = {}\n metadata = json.loads(\n http.request(\n \"GET\",\n \"http://169.254.169.254/latest/dynamic/instance-identity/document\",\n headers=aws_token_header,\n- timeout=3.0,\n+ timeout=1.0,\n retries=False,\n ).data.decode(\"utf-8\")\n )\n@@ -94,7 +103,7 @@\n \"GET\",\n \"http://metadata.google.internal/computeMetadata/v1/?recursive=true\",\n headers=headers,\n- timeout=3.0,\n+ timeout=1.0,\n retries=False,\n ).data.decode(\"utf-8\")\n )\n@@ -135,7 +144,7 @@\n \"GET\",\n \"http://169.254.169.254/metadata/instance/compute?api-version=2019-08-15\",\n headers=headers,\n- timeout=3.0,\n+ timeout=1.0,\n retries=False,\n ).data.decode(\"utf-8\")\n )\n", "issue": "ReadTimeoutErrors on 169.254.169.254 /latest/api/token\nAfter updating the agent to version 5.8.0 my all my Django `manage.py` commands seem to hang indefinitely and never finish and I'm first seeing: \r\n\r\n`WARNING urllib3.connectionpool Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError(\"HTTPConnectionPool(host='169.254.169.254', port=80): Read timed out. (read timeout=3.0)\")': /latest/api/token connectionpool.py:749`\r\n\r\nand then (after some time):\r\n\r\n`ERROR elasticapm.transport Closing the transport connection timed out. base.py:261`\r\n\r\nAfter this last error message the process just hangs indefinitely and has to be killed manually.\r\n\r\n**To Reproduce**\r\n\r\nI'm not able to reproduce this locally, it seems to happen exclusively in my staging/production environment on AWS.\r\nThere, it really only takes a Django management command to make it hang. For example:\r\n\r\n```\r\n$ python manage.py migrate\r\nOperations to perform:\r\n Apply all migrations: admin, auth, contenttypes, sessions\r\nRunning migrations:\r\n No migrations to apply.\r\n2020-07-03 13:17:19,256 WARNING urllib3.connectionpool Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError(\"HTTPConnectionPool(host='169.254.169.254', port=80): Read timed out. (read timeout=3.0)\")': /latest/api/token connectionpool.py:749\r\n2020-07-03 13:17:27,164 ERROR elasticapm.transport Closing the transport connection timed out. base.py:261\r\n```\r\n**Environment**\r\n- OS: `Linux 6094537dd0b9 4.14.181-108.257.amzn1.x86_64 elastic/apm-agent-python#1 SMP Wed May 27 02:43:03 UTC 2020 x86_64 GNU/Linux` (Docker container - python:3.8 image, docker running on Amazon Linux/2.15.2)\r\n- Python version: 3.8.3\r\n- Framework and version: Django 3.0.8 (same thing happens with 3.0.7)\r\n- APM Server version: 7.5.2\r\n- Agent version: 5.8.0 (I can confirm this **doesn't happen with v5.7.0**)\r\n\r\n\r\n**Additional context**\r\n\r\nThe app runs on AWS ElasticBeanstalk Docker environment with python 3.8 image, pretty straight forward.\r\n\r\n- `requirements.txt`:\r\n <details>\r\n <summary>Click to expand</summary>\r\n\r\n ```\r\n appdirs==1.4.4\r\n asgiref==3.2.10; python_version >= '3.5'\r\n boto3==1.14.16\r\n botocore==1.17.16\r\n certifi==2020.6.20\r\n cffi==1.14.0\r\n chardet==3.0.4\r\n cryptography==2.9.2; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'\r\n django-migration-linter==2.3.0\r\n django-redis==4.12.1\r\n django-sortedm2m==3.0.0\r\n django-storages==1.9.1\r\n django-widget-tweaks==1.4.8\r\n django==3.0.8\r\n djangorestframework-simplejwt==4.4.0\r\n djangorestframework==3.11.0\r\n docutils==0.15.2; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n elastic-apm==5.8.0\r\n factory-boy==2.12.0\r\n faker==4.1.1; python_version >= '3.4'\r\n future==0.18.2; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n googlemaps==4.4.1\r\n gunicorn==20.0.4\r\n idna==2.10; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n jmespath==0.10.0; python_version >= '2.6' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n jwcrypto==0.7\r\n markdown==3.2.2\r\n oauthlib==3.1.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n pillow==7.2.0\r\n psycopg2-binary==2.8.5\r\n pycparser==2.20; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n pyjwt==1.7.1\r\n python-dateutil==2.8.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n python-twitter==3.5\r\n pytz==2020.1\r\n pyyaml==5.3.1\r\n redis==3.5.3; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'\r\n requests-oauthlib==1.3.0\r\n requests==2.24.0\r\n s3transfer==0.3.3\r\n sentry-sdk==0.16.0\r\n six==1.15.0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n sqlparse==0.3.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'\r\n text-unidecode==1.3\r\n twilio==6.43.0\r\n ua-parser==0.10.0\r\n uritemplate==3.0.1\r\n urllib3==1.25.9; python_version != '3.4'\r\n user-agents==2.1\r\n ```\r\n </details>\r\n\n", "before_files": [{"content": "# BSD 3-Clause License\n#\n# Copyright (c) 2019, Elasticsearch BV\n# All rights reserved.\n#\n# Redistribution and use in source and binary forms, with or without\n# modification, are permitted provided that the following conditions are met:\n#\n# * Redistributions of source code must retain the above copyright notice, this\n# list of conditions and the following disclaimer.\n#\n# * Redistributions in binary form must reproduce the above copyright notice,\n# this list of conditions and the following disclaimer in the documentation\n# and/or other materials provided with the distribution.\n#\n# * Neither the name of the copyright holder nor the names of its\n# contributors may be used to endorse or promote products derived from\n# this software without specific prior written permission.\n#\n# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\"\n# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE\n# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE\n# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE\n# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL\n# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR\n# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER\n# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,\n# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE\n# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.\n\nimport json\nimport os\nimport socket\n\nimport urllib3\n\n\ndef aws_metadata():\n \"\"\"\n Fetch AWS metadata from the local metadata server. If metadata server is\n not found, return an empty dictionary\n \"\"\"\n http = urllib3.PoolManager()\n\n try:\n # This will throw an error if the metadata server isn't available,\n # and will be quiet in the logs, unlike urllib3\n socket.create_connection((\"169.254.169.254\", 80), 0.1)\n\n ttl_header = {\"X-aws-ec2-metadata-token-ttl-seconds\": \"300\"}\n token_url = \"http://169.254.169.254/latest/api/token\"\n token_request = http.request(\"PUT\", token_url, headers=ttl_header, timeout=3.0)\n token = token_request.data.decode(\"utf-8\")\n aws_token_header = {\"X-aws-ec2-metadata-token\": token} if token else {}\n metadata = json.loads(\n http.request(\n \"GET\",\n \"http://169.254.169.254/latest/dynamic/instance-identity/document\",\n headers=aws_token_header,\n timeout=3.0,\n retries=False,\n ).data.decode(\"utf-8\")\n )\n\n return {\n \"account\": {\"id\": metadata[\"accountId\"]},\n \"instance\": {\"id\": metadata[\"instanceId\"]},\n \"availability_zone\": metadata[\"availabilityZone\"],\n \"machine\": {\"type\": metadata[\"instanceType\"]},\n \"provider\": \"aws\",\n \"region\": metadata[\"region\"],\n }\n\n except Exception:\n # Not on an AWS box\n return {}\n\n\ndef gcp_metadata():\n \"\"\"\n Fetch GCP metadata from the local metadata server. If metadata server is\n not found, return an empty dictionary\n \"\"\"\n headers = {\"Metadata-Flavor\": \"Google\"}\n http = urllib3.PoolManager()\n\n try:\n # This will throw an error if the metadata server isn't available,\n # and will be quiet in the logs, unlike urllib3\n socket.getaddrinfo(\"metadata.google.internal\", 80, 0, socket.SOCK_STREAM)\n\n metadata = json.loads(\n http.request(\n \"GET\",\n \"http://metadata.google.internal/computeMetadata/v1/?recursive=true\",\n headers=headers,\n timeout=3.0,\n retries=False,\n ).data.decode(\"utf-8\")\n )\n\n availability_zone = os.path.split(metadata[\"instance\"][\"zone\"])[1]\n\n return {\n \"provider\": \"gcp\",\n \"instance\": {\"id\": str(metadata[\"instance\"][\"id\"]), \"name\": metadata[\"instance\"][\"name\"]},\n \"project\": {\"id\": str(metadata[\"project\"][\"numericProjectId\"]), \"name\": metadata[\"project\"][\"projectId\"]},\n \"availability_zone\": availability_zone,\n \"region\": availability_zone.rsplit(\"-\", 1)[0],\n \"machine\": {\"type\": metadata[\"instance\"][\"machineType\"]},\n }\n\n except Exception:\n # Not on a gcp box\n return {}\n\n\ndef azure_metadata():\n \"\"\"\n Fetch Azure metadata from the local metadata server. If metadata server is\n not found, return an empty dictionary\n \"\"\"\n headers = {\"Metadata\": \"true\"}\n http = urllib3.PoolManager()\n\n try:\n # This will throw an error if the metadata server isn't available,\n # and will be quiet in the logs, unlike urllib3\n socket.create_connection((\"169.254.169.254\", 80), 0.1)\n\n # Can't use newest metadata service version, as it's not guaranteed\n # to be available in all regions\n metadata = json.loads(\n http.request(\n \"GET\",\n \"http://169.254.169.254/metadata/instance/compute?api-version=2019-08-15\",\n headers=headers,\n timeout=3.0,\n retries=False,\n ).data.decode(\"utf-8\")\n )\n\n ret = {\n \"account\": {\"id\": metadata[\"subscriptionId\"]},\n \"instance\": {\"id\": metadata[\"vmId\"], \"name\": metadata[\"name\"]},\n \"project\": {\"name\": metadata[\"resourceGroupName\"]},\n \"availability_zone\": metadata[\"zone\"],\n \"machine\": {\"type\": metadata[\"vmSize\"]},\n \"provider\": \"azure\",\n \"region\": metadata[\"location\"],\n }\n\n if not ret[\"availability_zone\"]:\n ret.pop(\"availability_zone\")\n return ret\n\n except Exception:\n # Not on an Azure box\n return {}\n", "path": "elasticapm/utils/cloud.py"}]} | 3,879 | 670 |
gh_patches_debug_36580 | rasdani/github-patches | git_diff | saleor__saleor-13068 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Allow to remove shipping method
Current state:
Once the Shipping Method is assigned to the checkout, it cannot be removed by the user.
DoD:
make `checkoutShippingMethodUpdate.shippingMethodId` argument nullable
if null is passed as a value, remove the shipping method from the checkout
</issue>
<code>
[start of saleor/graphql/checkout/mutations/checkout_shipping_method_update.py]
1 from typing import Optional
2
3 import graphene
4 from django.core.exceptions import ValidationError
5
6 from ....checkout.error_codes import CheckoutErrorCode
7 from ....checkout.fetch import fetch_checkout_info, fetch_checkout_lines
8 from ....checkout.utils import (
9 delete_external_shipping_id,
10 get_checkout_metadata,
11 invalidate_checkout_prices,
12 is_shipping_required,
13 set_external_shipping_id,
14 )
15 from ....plugins.webhook.utils import APP_ID_PREFIX
16 from ....shipping import interface as shipping_interface
17 from ....shipping import models as shipping_models
18 from ....shipping.utils import convert_to_shipping_method_data
19 from ....webhook.event_types import WebhookEventAsyncType, WebhookEventSyncType
20 from ...core import ResolveInfo
21 from ...core.descriptions import ADDED_IN_34, DEPRECATED_IN_3X_INPUT
22 from ...core.doc_category import DOC_CATEGORY_CHECKOUT
23 from ...core.mutations import BaseMutation
24 from ...core.scalars import UUID
25 from ...core.types import CheckoutError
26 from ...core.utils import WebhookEventInfo, from_global_id_or_error
27 from ...plugins.dataloaders import get_plugin_manager_promise
28 from ...shipping.types import ShippingMethod
29 from ..types import Checkout
30 from .utils import ERROR_DOES_NOT_SHIP, clean_delivery_method, get_checkout
31
32
33 class CheckoutShippingMethodUpdate(BaseMutation):
34 checkout = graphene.Field(Checkout, description="An updated checkout.")
35
36 class Arguments:
37 id = graphene.ID(
38 description="The checkout's ID." + ADDED_IN_34,
39 required=False,
40 )
41 token = UUID(
42 description=f"Checkout token.{DEPRECATED_IN_3X_INPUT} Use `id` instead.",
43 required=False,
44 )
45 checkout_id = graphene.ID(
46 required=False,
47 description=(
48 f"The ID of the checkout. {DEPRECATED_IN_3X_INPUT} Use `id` instead."
49 ),
50 )
51 shipping_method_id = graphene.ID(required=True, description="Shipping method.")
52
53 class Meta:
54 description = "Updates the shipping method of the checkout."
55 doc_category = DOC_CATEGORY_CHECKOUT
56 error_type_class = CheckoutError
57 error_type_field = "checkout_errors"
58 webhook_events_info = [
59 WebhookEventInfo(
60 type=WebhookEventSyncType.SHIPPING_LIST_METHODS_FOR_CHECKOUT,
61 description=(
62 "Triggered when updating the checkout shipping method with "
63 "the external one."
64 ),
65 ),
66 WebhookEventInfo(
67 type=WebhookEventAsyncType.CHECKOUT_UPDATED,
68 description="A checkout was updated.",
69 ),
70 ]
71
72 @staticmethod
73 def _resolve_delivery_method_type(id_) -> Optional[str]:
74 if id_ is None:
75 return None
76
77 possible_types = ("ShippingMethod", APP_ID_PREFIX)
78 type_, id_ = from_global_id_or_error(id_)
79 str_type = str(type_)
80
81 if str_type not in possible_types:
82 raise ValidationError(
83 {
84 "shipping_method_id": ValidationError(
85 "ID does not belong to known shipping methods",
86 code=CheckoutErrorCode.INVALID.value,
87 )
88 }
89 )
90
91 return str_type
92
93 @classmethod
94 def perform_mutation( # type: ignore[override]
95 cls,
96 _root,
97 info: ResolveInfo,
98 /,
99 *,
100 checkout_id=None,
101 id=None,
102 shipping_method_id,
103 token=None,
104 ):
105 checkout = get_checkout(cls, info, checkout_id=checkout_id, token=token, id=id)
106
107 manager = get_plugin_manager_promise(info.context).get()
108
109 lines, unavailable_variant_pks = fetch_checkout_lines(checkout)
110 if unavailable_variant_pks:
111 not_available_variants_ids = {
112 graphene.Node.to_global_id("ProductVariant", pk)
113 for pk in unavailable_variant_pks
114 }
115 raise ValidationError(
116 {
117 "lines": ValidationError(
118 "Some of the checkout lines variants are unavailable.",
119 code=CheckoutErrorCode.UNAVAILABLE_VARIANT_IN_CHANNEL.value,
120 params={"variants": not_available_variants_ids},
121 )
122 }
123 )
124 checkout_info = fetch_checkout_info(checkout, lines, manager)
125 if not is_shipping_required(lines):
126 raise ValidationError(
127 {
128 "shipping_method": ValidationError(
129 ERROR_DOES_NOT_SHIP,
130 code=CheckoutErrorCode.SHIPPING_NOT_REQUIRED.value,
131 )
132 }
133 )
134
135 type_name = cls._resolve_delivery_method_type(shipping_method_id)
136
137 if type_name == "ShippingMethod":
138 return cls.perform_on_shipping_method(
139 info, shipping_method_id, checkout_info, lines, checkout, manager
140 )
141 return cls.perform_on_external_shipping_method(
142 info, shipping_method_id, checkout_info, lines, checkout, manager
143 )
144
145 @staticmethod
146 def _check_delivery_method(
147 checkout_info,
148 lines,
149 *,
150 delivery_method: Optional[shipping_interface.ShippingMethodData],
151 ) -> None:
152 delivery_method_is_valid = clean_delivery_method(
153 checkout_info=checkout_info,
154 lines=lines,
155 method=delivery_method,
156 )
157 if not delivery_method_is_valid or not delivery_method:
158 raise ValidationError(
159 {
160 "shipping_method": ValidationError(
161 "This shipping method is not applicable.",
162 code=CheckoutErrorCode.SHIPPING_METHOD_NOT_APPLICABLE.value,
163 )
164 }
165 )
166
167 @classmethod
168 def perform_on_shipping_method(
169 cls,
170 info: ResolveInfo,
171 shipping_method_id,
172 checkout_info,
173 lines,
174 checkout,
175 manager,
176 ):
177 shipping_method = cls.get_node_or_error(
178 info,
179 shipping_method_id,
180 only_type=ShippingMethod,
181 field="shipping_method_id",
182 qs=shipping_models.ShippingMethod.objects.prefetch_related(
183 "postal_code_rules"
184 ),
185 )
186 listing = shipping_models.ShippingMethodChannelListing.objects.filter(
187 shipping_method=shipping_method,
188 channel=checkout_info.channel,
189 ).first()
190 if not listing:
191 raise ValidationError(
192 {
193 "shipping_method": ValidationError(
194 "Shipping method not found for this channel.",
195 code=CheckoutErrorCode.NOT_FOUND.value,
196 )
197 }
198 )
199 delivery_method = convert_to_shipping_method_data(shipping_method, listing)
200
201 cls._check_delivery_method(
202 checkout_info, lines, delivery_method=delivery_method
203 )
204
205 delete_external_shipping_id(checkout=checkout)
206 checkout.shipping_method = shipping_method
207 invalidate_prices_updated_fields = invalidate_checkout_prices(
208 checkout_info, lines, manager, save=False
209 )
210 checkout.save(
211 update_fields=[
212 "shipping_method",
213 ]
214 + invalidate_prices_updated_fields
215 )
216 get_checkout_metadata(checkout).save()
217
218 cls.call_event(manager.checkout_updated, checkout)
219 return CheckoutShippingMethodUpdate(checkout=checkout)
220
221 @classmethod
222 def perform_on_external_shipping_method(
223 cls,
224 info: ResolveInfo,
225 shipping_method_id,
226 checkout_info,
227 lines,
228 checkout,
229 manager,
230 ):
231 delivery_method = manager.get_shipping_method(
232 checkout=checkout,
233 channel_slug=checkout.channel.slug,
234 shipping_method_id=shipping_method_id,
235 )
236
237 cls._check_delivery_method(
238 checkout_info, lines, delivery_method=delivery_method
239 )
240
241 set_external_shipping_id(checkout=checkout, app_shipping_id=delivery_method.id)
242 checkout.shipping_method = None
243 invalidate_prices_updated_fields = invalidate_checkout_prices(
244 checkout_info, lines, manager, save=False
245 )
246 checkout.save(
247 update_fields=[
248 "shipping_method",
249 ]
250 + invalidate_prices_updated_fields
251 )
252 get_checkout_metadata(checkout).save()
253 cls.call_event(manager.checkout_updated, checkout)
254
255 return CheckoutShippingMethodUpdate(checkout=checkout)
256
[end of saleor/graphql/checkout/mutations/checkout_shipping_method_update.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py b/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py
--- a/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py
+++ b/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py
@@ -48,7 +48,9 @@
f"The ID of the checkout. {DEPRECATED_IN_3X_INPUT} Use `id` instead."
),
)
- shipping_method_id = graphene.ID(required=True, description="Shipping method.")
+ shipping_method_id = graphene.ID(
+ required=False, default_value=None, description="Shipping method."
+ )
class Meta:
description = "Updates the shipping method of the checkout."
@@ -91,7 +93,7 @@
return str_type
@classmethod
- def perform_mutation( # type: ignore[override]
+ def perform_mutation(
cls,
_root,
info: ResolveInfo,
@@ -99,7 +101,7 @@
*,
checkout_id=None,
id=None,
- shipping_method_id,
+ shipping_method_id=None,
token=None,
):
checkout = get_checkout(cls, info, checkout_id=checkout_id, token=token, id=id)
@@ -131,6 +133,8 @@
)
}
)
+ if shipping_method_id is None:
+ return cls.remove_shipping_method(checkout, checkout_info, lines, manager)
type_name = cls._resolve_delivery_method_type(shipping_method_id)
@@ -253,3 +257,21 @@
cls.call_event(manager.checkout_updated, checkout)
return CheckoutShippingMethodUpdate(checkout=checkout)
+
+ @classmethod
+ def remove_shipping_method(cls, checkout, checkout_info, lines, manager):
+ checkout.shipping_method = None
+ delete_external_shipping_id(checkout=checkout)
+ invalidate_prices_updated_fields = invalidate_checkout_prices(
+ checkout_info, lines, manager, save=False
+ )
+ checkout.save(
+ update_fields=[
+ "shipping_method",
+ ]
+ + invalidate_prices_updated_fields
+ )
+ get_checkout_metadata(checkout).save()
+
+ cls.call_event(manager.checkout_updated, checkout)
+ return CheckoutShippingMethodUpdate(checkout=checkout)
| {"golden_diff": "diff --git a/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py b/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py\n--- a/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py\n+++ b/saleor/graphql/checkout/mutations/checkout_shipping_method_update.py\n@@ -48,7 +48,9 @@\n f\"The ID of the checkout. {DEPRECATED_IN_3X_INPUT} Use `id` instead.\"\n ),\n )\n- shipping_method_id = graphene.ID(required=True, description=\"Shipping method.\")\n+ shipping_method_id = graphene.ID(\n+ required=False, default_value=None, description=\"Shipping method.\"\n+ )\n \n class Meta:\n description = \"Updates the shipping method of the checkout.\"\n@@ -91,7 +93,7 @@\n return str_type\n \n @classmethod\n- def perform_mutation( # type: ignore[override]\n+ def perform_mutation(\n cls,\n _root,\n info: ResolveInfo,\n@@ -99,7 +101,7 @@\n *,\n checkout_id=None,\n id=None,\n- shipping_method_id,\n+ shipping_method_id=None,\n token=None,\n ):\n checkout = get_checkout(cls, info, checkout_id=checkout_id, token=token, id=id)\n@@ -131,6 +133,8 @@\n )\n }\n )\n+ if shipping_method_id is None:\n+ return cls.remove_shipping_method(checkout, checkout_info, lines, manager)\n \n type_name = cls._resolve_delivery_method_type(shipping_method_id)\n \n@@ -253,3 +257,21 @@\n cls.call_event(manager.checkout_updated, checkout)\n \n return CheckoutShippingMethodUpdate(checkout=checkout)\n+\n+ @classmethod\n+ def remove_shipping_method(cls, checkout, checkout_info, lines, manager):\n+ checkout.shipping_method = None\n+ delete_external_shipping_id(checkout=checkout)\n+ invalidate_prices_updated_fields = invalidate_checkout_prices(\n+ checkout_info, lines, manager, save=False\n+ )\n+ checkout.save(\n+ update_fields=[\n+ \"shipping_method\",\n+ ]\n+ + invalidate_prices_updated_fields\n+ )\n+ get_checkout_metadata(checkout).save()\n+\n+ cls.call_event(manager.checkout_updated, checkout)\n+ return CheckoutShippingMethodUpdate(checkout=checkout)\n", "issue": "Allow to remove shipping method\nCurrent state:\r\nOnce the Shipping Method is assigned to the checkout, it cannot be removed by the user.\r\n\r\nDoD:\r\nmake `checkoutShippingMethodUpdate.shippingMethodId` argument nullable\r\nif null is passed as a value, remove the shipping method from the checkout\n", "before_files": [{"content": "from typing import Optional\n\nimport graphene\nfrom django.core.exceptions import ValidationError\n\nfrom ....checkout.error_codes import CheckoutErrorCode\nfrom ....checkout.fetch import fetch_checkout_info, fetch_checkout_lines\nfrom ....checkout.utils import (\n delete_external_shipping_id,\n get_checkout_metadata,\n invalidate_checkout_prices,\n is_shipping_required,\n set_external_shipping_id,\n)\nfrom ....plugins.webhook.utils import APP_ID_PREFIX\nfrom ....shipping import interface as shipping_interface\nfrom ....shipping import models as shipping_models\nfrom ....shipping.utils import convert_to_shipping_method_data\nfrom ....webhook.event_types import WebhookEventAsyncType, WebhookEventSyncType\nfrom ...core import ResolveInfo\nfrom ...core.descriptions import ADDED_IN_34, DEPRECATED_IN_3X_INPUT\nfrom ...core.doc_category import DOC_CATEGORY_CHECKOUT\nfrom ...core.mutations import BaseMutation\nfrom ...core.scalars import UUID\nfrom ...core.types import CheckoutError\nfrom ...core.utils import WebhookEventInfo, from_global_id_or_error\nfrom ...plugins.dataloaders import get_plugin_manager_promise\nfrom ...shipping.types import ShippingMethod\nfrom ..types import Checkout\nfrom .utils import ERROR_DOES_NOT_SHIP, clean_delivery_method, get_checkout\n\n\nclass CheckoutShippingMethodUpdate(BaseMutation):\n checkout = graphene.Field(Checkout, description=\"An updated checkout.\")\n\n class Arguments:\n id = graphene.ID(\n description=\"The checkout's ID.\" + ADDED_IN_34,\n required=False,\n )\n token = UUID(\n description=f\"Checkout token.{DEPRECATED_IN_3X_INPUT} Use `id` instead.\",\n required=False,\n )\n checkout_id = graphene.ID(\n required=False,\n description=(\n f\"The ID of the checkout. {DEPRECATED_IN_3X_INPUT} Use `id` instead.\"\n ),\n )\n shipping_method_id = graphene.ID(required=True, description=\"Shipping method.\")\n\n class Meta:\n description = \"Updates the shipping method of the checkout.\"\n doc_category = DOC_CATEGORY_CHECKOUT\n error_type_class = CheckoutError\n error_type_field = \"checkout_errors\"\n webhook_events_info = [\n WebhookEventInfo(\n type=WebhookEventSyncType.SHIPPING_LIST_METHODS_FOR_CHECKOUT,\n description=(\n \"Triggered when updating the checkout shipping method with \"\n \"the external one.\"\n ),\n ),\n WebhookEventInfo(\n type=WebhookEventAsyncType.CHECKOUT_UPDATED,\n description=\"A checkout was updated.\",\n ),\n ]\n\n @staticmethod\n def _resolve_delivery_method_type(id_) -> Optional[str]:\n if id_ is None:\n return None\n\n possible_types = (\"ShippingMethod\", APP_ID_PREFIX)\n type_, id_ = from_global_id_or_error(id_)\n str_type = str(type_)\n\n if str_type not in possible_types:\n raise ValidationError(\n {\n \"shipping_method_id\": ValidationError(\n \"ID does not belong to known shipping methods\",\n code=CheckoutErrorCode.INVALID.value,\n )\n }\n )\n\n return str_type\n\n @classmethod\n def perform_mutation( # type: ignore[override]\n cls,\n _root,\n info: ResolveInfo,\n /,\n *,\n checkout_id=None,\n id=None,\n shipping_method_id,\n token=None,\n ):\n checkout = get_checkout(cls, info, checkout_id=checkout_id, token=token, id=id)\n\n manager = get_plugin_manager_promise(info.context).get()\n\n lines, unavailable_variant_pks = fetch_checkout_lines(checkout)\n if unavailable_variant_pks:\n not_available_variants_ids = {\n graphene.Node.to_global_id(\"ProductVariant\", pk)\n for pk in unavailable_variant_pks\n }\n raise ValidationError(\n {\n \"lines\": ValidationError(\n \"Some of the checkout lines variants are unavailable.\",\n code=CheckoutErrorCode.UNAVAILABLE_VARIANT_IN_CHANNEL.value,\n params={\"variants\": not_available_variants_ids},\n )\n }\n )\n checkout_info = fetch_checkout_info(checkout, lines, manager)\n if not is_shipping_required(lines):\n raise ValidationError(\n {\n \"shipping_method\": ValidationError(\n ERROR_DOES_NOT_SHIP,\n code=CheckoutErrorCode.SHIPPING_NOT_REQUIRED.value,\n )\n }\n )\n\n type_name = cls._resolve_delivery_method_type(shipping_method_id)\n\n if type_name == \"ShippingMethod\":\n return cls.perform_on_shipping_method(\n info, shipping_method_id, checkout_info, lines, checkout, manager\n )\n return cls.perform_on_external_shipping_method(\n info, shipping_method_id, checkout_info, lines, checkout, manager\n )\n\n @staticmethod\n def _check_delivery_method(\n checkout_info,\n lines,\n *,\n delivery_method: Optional[shipping_interface.ShippingMethodData],\n ) -> None:\n delivery_method_is_valid = clean_delivery_method(\n checkout_info=checkout_info,\n lines=lines,\n method=delivery_method,\n )\n if not delivery_method_is_valid or not delivery_method:\n raise ValidationError(\n {\n \"shipping_method\": ValidationError(\n \"This shipping method is not applicable.\",\n code=CheckoutErrorCode.SHIPPING_METHOD_NOT_APPLICABLE.value,\n )\n }\n )\n\n @classmethod\n def perform_on_shipping_method(\n cls,\n info: ResolveInfo,\n shipping_method_id,\n checkout_info,\n lines,\n checkout,\n manager,\n ):\n shipping_method = cls.get_node_or_error(\n info,\n shipping_method_id,\n only_type=ShippingMethod,\n field=\"shipping_method_id\",\n qs=shipping_models.ShippingMethod.objects.prefetch_related(\n \"postal_code_rules\"\n ),\n )\n listing = shipping_models.ShippingMethodChannelListing.objects.filter(\n shipping_method=shipping_method,\n channel=checkout_info.channel,\n ).first()\n if not listing:\n raise ValidationError(\n {\n \"shipping_method\": ValidationError(\n \"Shipping method not found for this channel.\",\n code=CheckoutErrorCode.NOT_FOUND.value,\n )\n }\n )\n delivery_method = convert_to_shipping_method_data(shipping_method, listing)\n\n cls._check_delivery_method(\n checkout_info, lines, delivery_method=delivery_method\n )\n\n delete_external_shipping_id(checkout=checkout)\n checkout.shipping_method = shipping_method\n invalidate_prices_updated_fields = invalidate_checkout_prices(\n checkout_info, lines, manager, save=False\n )\n checkout.save(\n update_fields=[\n \"shipping_method\",\n ]\n + invalidate_prices_updated_fields\n )\n get_checkout_metadata(checkout).save()\n\n cls.call_event(manager.checkout_updated, checkout)\n return CheckoutShippingMethodUpdate(checkout=checkout)\n\n @classmethod\n def perform_on_external_shipping_method(\n cls,\n info: ResolveInfo,\n shipping_method_id,\n checkout_info,\n lines,\n checkout,\n manager,\n ):\n delivery_method = manager.get_shipping_method(\n checkout=checkout,\n channel_slug=checkout.channel.slug,\n shipping_method_id=shipping_method_id,\n )\n\n cls._check_delivery_method(\n checkout_info, lines, delivery_method=delivery_method\n )\n\n set_external_shipping_id(checkout=checkout, app_shipping_id=delivery_method.id)\n checkout.shipping_method = None\n invalidate_prices_updated_fields = invalidate_checkout_prices(\n checkout_info, lines, manager, save=False\n )\n checkout.save(\n update_fields=[\n \"shipping_method\",\n ]\n + invalidate_prices_updated_fields\n )\n get_checkout_metadata(checkout).save()\n cls.call_event(manager.checkout_updated, checkout)\n\n return CheckoutShippingMethodUpdate(checkout=checkout)\n", "path": "saleor/graphql/checkout/mutations/checkout_shipping_method_update.py"}]} | 2,890 | 522 |
gh_patches_debug_26962 | rasdani/github-patches | git_diff | huggingface__peft-1584 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Loading LORA weights in `diffusers` with a `peft` backend increases in latency as more paths are added to `PYTHONPATH`
### System Info
```
accelerate==0.21.0
diffusers==0.26.3
peft==0.9.0
safetensors==0.3.3
tokenizers==0.15.2
torch==2.2.1
transformers==4.36.2
```
### Who can help?
@sayakpaul
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` folder
- [X] My own task or dataset (give details below)
### Reproduction
```python
from diffusers import DiffusionPipeline
import time
import torch
import sys
import os
import shutil
pipe_id = "stabilityai/stable-diffusion-xl-base-1.0"
pipe = DiffusionPipeline.from_pretrained(pipe_id, torch_dtype=torch.float16).to("cuda")
loras = [
{
"adapter_name": "anime"
"location": "./anime",
"weight_name": "anime.safetensors",
"token": "my_anime"
},
]
def run_dynamic_lora_inference(lora):
start_load_time = time.time()
pipe.load_lora_weights(lora["location"], weight_name=lora["weight_name"], adapter_name=lora["adapter_name"])
end_load_time = time.time()
prompt = f"Illustration of a dog in the style of {lora["token"]}"
start_fuse_time = time.time()
pipe.fuse_lora()
end_fuse_time = time.time()
start_set_adapter_time = time.time()
pipe.set_adapters(lora_name)
end_set_adapter_time = time.time()
start_inference_time = time.time()
image = pipe(
prompt, num_inference_steps=30, generator=torch.manual_seed(0)
).images[0]
end_inference_time = time.time()
start_unfuse_time = time.time()
pipe.unfuse_lora()
end_unfuse_time = time.time()
start_unload_time = time.time()
pipe.unload_lora_weights()
end_unload_time = time.time()
image.save(f"./{lora_name}.png")
print("Load time:", end_load_time - start_load_time)
print("Fuse time:", end_fuse_time - start_fuse_time)
print("Set adapter time", end_set_adapter_time - start_set_adapter_time)
print("Inference time:", end_inference_time - start_inference_time)
print("Unfuse time:", end_unfuse_time - start_unfuse_time)
print("Unload time:", end_unload_time - start_unload_time)
def add_to_python_path():
root_path = "./folders"
shutil.rmtree(root_path)
os.mkdir(root_path)
folders = [f"folder_{x}" for x in range(0, 10000)]
for folder in folders:
os.mkdir(os.path.join(root_path, folder))
sys.path.append(os.path.join(root_path, folder))
def main():
for lora in loras:
run_dynamic_lora_inference(lora)
main()
```
Flamegraph:
### Expected behavior
I run a system with a somewhat large `PYTHONPATH` that we can't truncate, and we are currently blocked from upgrading `diffusers` to any version that uses `peft` for LORA inference.
It's loosely based on this post: https://huggingface.co/blog/lora-adapters-dynamic-loading
We've observed a behavior where the time taken for `load_lora_weights` increases significantly with more paths added to `PYTHONPATH`. This can be reproduced in the example provided - with 10,000 folders added to PYTHONPATH, we get the following latencies:
```
Load time: 291.78441095352173
Fuse time: 0.12406659126281738
Set adapter time 0.06171250343322754
Inference time: 9.685987710952759
Unfuse time: 0.08063459396362305
Unload time: 0.15737533569335938
```
Benchmarking against 1, 10, 100, 1000, 10000 and 50000 entries in the `PYTHONPATH`, we get a pretty astounding increase in load latency:
Even at 100 entries, we're looking at an extra 4 seconds per `load` call which is a pretty significant increase.
We looked briefly at it and came to the conclusion that it's something to do with the way `peft` runs module imports, particularly repetitive calls to import modules, where the imports are not cached, eg, `importlib.util.find_spec` doesn't cache imports.
Instead of this behaviour, we'd expect that `load_lora_weights` retains a relatively constant load time, regardless of the length of our python path.
</issue>
<code>
[start of src/peft/import_utils.py]
1 # Copyright 2023-present the HuggingFace Inc. team.
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 import importlib
15 import importlib.metadata as importlib_metadata
16 from functools import lru_cache
17
18 import packaging.version
19
20
21 def is_bnb_available() -> bool:
22 return importlib.util.find_spec("bitsandbytes") is not None
23
24
25 def is_bnb_4bit_available() -> bool:
26 if not is_bnb_available():
27 return False
28
29 import bitsandbytes as bnb
30
31 return hasattr(bnb.nn, "Linear4bit")
32
33
34 def is_auto_gptq_available():
35 if importlib.util.find_spec("auto_gptq") is not None:
36 AUTOGPTQ_MINIMUM_VERSION = packaging.version.parse("0.5.0")
37 version_autogptq = packaging.version.parse(importlib_metadata.version("auto_gptq"))
38 if AUTOGPTQ_MINIMUM_VERSION <= version_autogptq:
39 return True
40 else:
41 raise ImportError(
42 f"Found an incompatible version of auto-gptq. Found version {version_autogptq}, "
43 f"but only versions above {AUTOGPTQ_MINIMUM_VERSION} are supported"
44 )
45
46
47 def is_optimum_available() -> bool:
48 return importlib.util.find_spec("optimum") is not None
49
50
51 @lru_cache
52 def is_torch_tpu_available(check_device=True):
53 "Checks if `torch_xla` is installed and potentially if a TPU is in the environment"
54 if importlib.util.find_spec("torch_xla") is not None:
55 if check_device:
56 # We need to check if `xla_device` can be found, will raise a RuntimeError if not
57 try:
58 import torch_xla.core.xla_model as xm
59
60 _ = xm.xla_device()
61 return True
62 except RuntimeError:
63 return False
64 return True
65 return False
66
67
68 def is_aqlm_available():
69 return importlib.util.find_spec("aqlm") is not None
70
71
72 def is_auto_awq_available():
73 return importlib.util.find_spec("awq") is not None
74
[end of src/peft/import_utils.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/peft/import_utils.py b/src/peft/import_utils.py
--- a/src/peft/import_utils.py
+++ b/src/peft/import_utils.py
@@ -18,10 +18,12 @@
import packaging.version
+@lru_cache
def is_bnb_available() -> bool:
return importlib.util.find_spec("bitsandbytes") is not None
+@lru_cache
def is_bnb_4bit_available() -> bool:
if not is_bnb_available():
return False
@@ -31,6 +33,7 @@
return hasattr(bnb.nn, "Linear4bit")
+@lru_cache
def is_auto_gptq_available():
if importlib.util.find_spec("auto_gptq") is not None:
AUTOGPTQ_MINIMUM_VERSION = packaging.version.parse("0.5.0")
@@ -44,6 +47,7 @@
)
+@lru_cache
def is_optimum_available() -> bool:
return importlib.util.find_spec("optimum") is not None
@@ -65,9 +69,11 @@
return False
+@lru_cache
def is_aqlm_available():
return importlib.util.find_spec("aqlm") is not None
+@lru_cache
def is_auto_awq_available():
return importlib.util.find_spec("awq") is not None
| {"golden_diff": "diff --git a/src/peft/import_utils.py b/src/peft/import_utils.py\n--- a/src/peft/import_utils.py\n+++ b/src/peft/import_utils.py\n@@ -18,10 +18,12 @@\n import packaging.version\n \n \n+@lru_cache\n def is_bnb_available() -> bool:\n return importlib.util.find_spec(\"bitsandbytes\") is not None\n \n \n+@lru_cache\n def is_bnb_4bit_available() -> bool:\n if not is_bnb_available():\n return False\n@@ -31,6 +33,7 @@\n return hasattr(bnb.nn, \"Linear4bit\")\n \n \n+@lru_cache\n def is_auto_gptq_available():\n if importlib.util.find_spec(\"auto_gptq\") is not None:\n AUTOGPTQ_MINIMUM_VERSION = packaging.version.parse(\"0.5.0\")\n@@ -44,6 +47,7 @@\n )\n \n \n+@lru_cache\n def is_optimum_available() -> bool:\n return importlib.util.find_spec(\"optimum\") is not None\n \n@@ -65,9 +69,11 @@\n return False\n \n \n+@lru_cache\n def is_aqlm_available():\n return importlib.util.find_spec(\"aqlm\") is not None\n \n \n+@lru_cache\n def is_auto_awq_available():\n return importlib.util.find_spec(\"awq\") is not None\n", "issue": "Loading LORA weights in `diffusers` with a `peft` backend increases in latency as more paths are added to `PYTHONPATH`\n### System Info\r\n\r\n```\r\naccelerate==0.21.0\r\ndiffusers==0.26.3\r\npeft==0.9.0\r\nsafetensors==0.3.3\r\ntokenizers==0.15.2\r\ntorch==2.2.1\r\ntransformers==4.36.2\r\n```\r\n\r\n### Who can help?\r\n\r\n@sayakpaul \r\n\r\n### Information\r\n\r\n- [ ] The official example scripts\r\n- [X] My own modified scripts\r\n\r\n### Tasks\r\n\r\n- [ ] An officially supported task in the `examples` folder\r\n- [X] My own task or dataset (give details below)\r\n\r\n### Reproduction\r\n\r\n```python\r\nfrom diffusers import DiffusionPipeline\r\nimport time\r\nimport torch\r\nimport sys\r\nimport os\r\nimport shutil\r\n\r\npipe_id = \"stabilityai/stable-diffusion-xl-base-1.0\"\r\npipe = DiffusionPipeline.from_pretrained(pipe_id, torch_dtype=torch.float16).to(\"cuda\")\r\n\r\nloras = [\r\n {\r\n \"adapter_name\": \"anime\"\r\n \"location\": \"./anime\",\r\n \"weight_name\": \"anime.safetensors\",\r\n \"token\": \"my_anime\"\r\n },\r\n]\r\n\r\ndef run_dynamic_lora_inference(lora):\r\n start_load_time = time.time()\r\n pipe.load_lora_weights(lora[\"location\"], weight_name=lora[\"weight_name\"], adapter_name=lora[\"adapter_name\"])\r\n end_load_time = time.time()\r\n prompt = f\"Illustration of a dog in the style of {lora[\"token\"]}\"\r\n\r\n start_fuse_time = time.time()\r\n pipe.fuse_lora()\r\n end_fuse_time = time.time()\r\n\r\n start_set_adapter_time = time.time()\r\n pipe.set_adapters(lora_name)\r\n end_set_adapter_time = time.time()\r\n\r\n start_inference_time = time.time()\r\n image = pipe(\r\n prompt, num_inference_steps=30, generator=torch.manual_seed(0)\r\n ).images[0]\r\n end_inference_time = time.time()\r\n\r\n start_unfuse_time = time.time()\r\n pipe.unfuse_lora()\r\n end_unfuse_time = time.time()\r\n\r\n start_unload_time = time.time()\r\n pipe.unload_lora_weights()\r\n end_unload_time = time.time()\r\n\r\n image.save(f\"./{lora_name}.png\")\r\n\r\n print(\"Load time:\", end_load_time - start_load_time)\r\n print(\"Fuse time:\", end_fuse_time - start_fuse_time)\r\n print(\"Set adapter time\", end_set_adapter_time - start_set_adapter_time)\r\n print(\"Inference time:\", end_inference_time - start_inference_time)\r\n print(\"Unfuse time:\", end_unfuse_time - start_unfuse_time)\r\n print(\"Unload time:\", end_unload_time - start_unload_time)\r\n\r\ndef add_to_python_path():\r\n root_path = \"./folders\"\r\n shutil.rmtree(root_path)\r\n os.mkdir(root_path)\r\n\r\n folders = [f\"folder_{x}\" for x in range(0, 10000)]\r\n for folder in folders:\r\n os.mkdir(os.path.join(root_path, folder))\r\n sys.path.append(os.path.join(root_path, folder))\r\n\r\ndef main():\r\n for lora in loras:\r\n run_dynamic_lora_inference(lora)\r\n\r\nmain()\r\n```\r\n\r\nFlamegraph: \r\n\r\n\r\n\r\n\r\n### Expected behavior\r\n\r\nI run a system with a somewhat large `PYTHONPATH` that we can't truncate, and we are currently blocked from upgrading `diffusers` to any version that uses `peft` for LORA inference. \r\n\r\nIt's loosely based on this post: https://huggingface.co/blog/lora-adapters-dynamic-loading\r\n\r\nWe've observed a behavior where the time taken for `load_lora_weights` increases significantly with more paths added to `PYTHONPATH`. This can be reproduced in the example provided - with 10,000 folders added to PYTHONPATH, we get the following latencies:\r\n\r\n```\r\nLoad time: 291.78441095352173\r\nFuse time: 0.12406659126281738\r\nSet adapter time 0.06171250343322754\r\nInference time: 9.685987710952759\r\nUnfuse time: 0.08063459396362305\r\nUnload time: 0.15737533569335938\r\n```\r\n\r\nBenchmarking against 1, 10, 100, 1000, 10000 and 50000 entries in the `PYTHONPATH`, we get a pretty astounding increase in load latency: \r\n\r\n\r\n\r\nEven at 100 entries, we're looking at an extra 4 seconds per `load` call which is a pretty significant increase.\r\n\r\nWe looked briefly at it and came to the conclusion that it's something to do with the way `peft` runs module imports, particularly repetitive calls to import modules, where the imports are not cached, eg, `importlib.util.find_spec` doesn't cache imports. \r\n\r\nInstead of this behaviour, we'd expect that `load_lora_weights` retains a relatively constant load time, regardless of the length of our python path. \n", "before_files": [{"content": "# Copyright 2023-present the HuggingFace Inc. team.\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\nimport importlib\nimport importlib.metadata as importlib_metadata\nfrom functools import lru_cache\n\nimport packaging.version\n\n\ndef is_bnb_available() -> bool:\n return importlib.util.find_spec(\"bitsandbytes\") is not None\n\n\ndef is_bnb_4bit_available() -> bool:\n if not is_bnb_available():\n return False\n\n import bitsandbytes as bnb\n\n return hasattr(bnb.nn, \"Linear4bit\")\n\n\ndef is_auto_gptq_available():\n if importlib.util.find_spec(\"auto_gptq\") is not None:\n AUTOGPTQ_MINIMUM_VERSION = packaging.version.parse(\"0.5.0\")\n version_autogptq = packaging.version.parse(importlib_metadata.version(\"auto_gptq\"))\n if AUTOGPTQ_MINIMUM_VERSION <= version_autogptq:\n return True\n else:\n raise ImportError(\n f\"Found an incompatible version of auto-gptq. Found version {version_autogptq}, \"\n f\"but only versions above {AUTOGPTQ_MINIMUM_VERSION} are supported\"\n )\n\n\ndef is_optimum_available() -> bool:\n return importlib.util.find_spec(\"optimum\") is not None\n\n\n@lru_cache\ndef is_torch_tpu_available(check_device=True):\n \"Checks if `torch_xla` is installed and potentially if a TPU is in the environment\"\n if importlib.util.find_spec(\"torch_xla\") is not None:\n if check_device:\n # We need to check if `xla_device` can be found, will raise a RuntimeError if not\n try:\n import torch_xla.core.xla_model as xm\n\n _ = xm.xla_device()\n return True\n except RuntimeError:\n return False\n return True\n return False\n\n\ndef is_aqlm_available():\n return importlib.util.find_spec(\"aqlm\") is not None\n\n\ndef is_auto_awq_available():\n return importlib.util.find_spec(\"awq\") is not None\n", "path": "src/peft/import_utils.py"}]} | 2,540 | 317 |
gh_patches_debug_21025 | rasdani/github-patches | git_diff | aio-libs__aiohttp-3037 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Access to socket information when using AppRunner
## Long story short
Sometimes I like to listen on port 0 to allow for any and need to access the actual port after binding.
## Expected behaviour
A public way to access socket information like the port number.
## Actual behaviour
I have to reach into the private `TCPSite._server`.
</issue>
<code>
[start of aiohttp/web_runner.py]
1 import asyncio
2 import signal
3 import socket
4 from abc import ABC, abstractmethod
5
6 from yarl import URL
7
8 from .web_app import Application
9
10
11 __all__ = ('TCPSite', 'UnixSite', 'SockSite', 'BaseRunner',
12 'AppRunner', 'ServerRunner', 'GracefulExit')
13
14
15 class GracefulExit(SystemExit):
16 code = 1
17
18
19 def _raise_graceful_exit():
20 raise GracefulExit()
21
22
23 class BaseSite(ABC):
24 __slots__ = ('_runner', '_shutdown_timeout', '_ssl_context', '_backlog',
25 '_server')
26
27 def __init__(self, runner, *,
28 shutdown_timeout=60.0, ssl_context=None,
29 backlog=128):
30 if runner.server is None:
31 raise RuntimeError("Call runner.setup() before making a site")
32 self._runner = runner
33 self._shutdown_timeout = shutdown_timeout
34 self._ssl_context = ssl_context
35 self._backlog = backlog
36 self._server = None
37
38 @property
39 @abstractmethod
40 def name(self):
41 pass # pragma: no cover
42
43 @abstractmethod
44 async def start(self):
45 self._runner._reg_site(self)
46
47 async def stop(self):
48 self._runner._check_site(self)
49 if self._server is None:
50 self._runner._unreg_site(self)
51 return # not started yet
52 self._server.close()
53 await self._server.wait_closed()
54 await self._runner.shutdown()
55 await self._runner.server.shutdown(self._shutdown_timeout)
56 self._runner._unreg_site(self)
57
58
59 class TCPSite(BaseSite):
60 __slots__ = ('_host', '_port', '_reuse_address', '_reuse_port')
61
62 def __init__(self, runner, host=None, port=None, *,
63 shutdown_timeout=60.0, ssl_context=None,
64 backlog=128, reuse_address=None,
65 reuse_port=None):
66 super().__init__(runner, shutdown_timeout=shutdown_timeout,
67 ssl_context=ssl_context, backlog=backlog)
68 if host is None:
69 host = "0.0.0.0"
70 self._host = host
71 if port is None:
72 port = 8443 if self._ssl_context else 8080
73 self._port = port
74 self._reuse_address = reuse_address
75 self._reuse_port = reuse_port
76
77 @property
78 def name(self):
79 scheme = 'https' if self._ssl_context else 'http'
80 return str(URL.build(scheme=scheme, host=self._host, port=self._port))
81
82 async def start(self):
83 await super().start()
84 loop = asyncio.get_event_loop()
85 self._server = await loop.create_server(
86 self._runner.server, self._host, self._port,
87 ssl=self._ssl_context, backlog=self._backlog,
88 reuse_address=self._reuse_address,
89 reuse_port=self._reuse_port)
90
91
92 class UnixSite(BaseSite):
93 __slots__ = ('_path', )
94
95 def __init__(self, runner, path, *,
96 shutdown_timeout=60.0, ssl_context=None,
97 backlog=128):
98 super().__init__(runner, shutdown_timeout=shutdown_timeout,
99 ssl_context=ssl_context, backlog=backlog)
100 self._path = path
101
102 @property
103 def name(self):
104 scheme = 'https' if self._ssl_context else 'http'
105 return '{}://unix:{}:'.format(scheme, self._path)
106
107 async def start(self):
108 await super().start()
109 loop = asyncio.get_event_loop()
110 self._server = await loop.create_unix_server(
111 self._runner.server, self._path,
112 ssl=self._ssl_context, backlog=self._backlog)
113
114
115 class SockSite(BaseSite):
116 __slots__ = ('_sock', '_name')
117
118 def __init__(self, runner, sock, *,
119 shutdown_timeout=60.0, ssl_context=None,
120 backlog=128):
121 super().__init__(runner, shutdown_timeout=shutdown_timeout,
122 ssl_context=ssl_context, backlog=backlog)
123 self._sock = sock
124 scheme = 'https' if self._ssl_context else 'http'
125 if hasattr(socket, 'AF_UNIX') and sock.family == socket.AF_UNIX:
126 name = '{}://unix:{}:'.format(scheme, sock.getsockname())
127 else:
128 host, port = sock.getsockname()[:2]
129 name = str(URL.build(scheme=scheme, host=host, port=port))
130 self._name = name
131
132 @property
133 def name(self):
134 return self._name
135
136 async def start(self):
137 await super().start()
138 loop = asyncio.get_event_loop()
139 self._server = await loop.create_server(
140 self._runner.server, sock=self._sock,
141 ssl=self._ssl_context, backlog=self._backlog)
142
143
144 class BaseRunner(ABC):
145 __slots__ = ('_handle_signals', '_kwargs', '_server', '_sites')
146
147 def __init__(self, *, handle_signals=False, **kwargs):
148 self._handle_signals = handle_signals
149 self._kwargs = kwargs
150 self._server = None
151 self._sites = set()
152
153 @property
154 def server(self):
155 return self._server
156
157 @property
158 def sites(self):
159 return set(self._sites)
160
161 async def setup(self):
162 loop = asyncio.get_event_loop()
163
164 if self._handle_signals:
165 try:
166 loop.add_signal_handler(signal.SIGINT, _raise_graceful_exit)
167 loop.add_signal_handler(signal.SIGTERM, _raise_graceful_exit)
168 except NotImplementedError: # pragma: no cover
169 # add_signal_handler is not implemented on Windows
170 pass
171
172 self._server = await self._make_server()
173
174 @abstractmethod
175 async def shutdown(self):
176 pass # pragma: no cover
177
178 async def cleanup(self):
179 loop = asyncio.get_event_loop()
180
181 if self._server is None:
182 # no started yet, do nothing
183 return
184
185 # The loop over sites is intentional, an exception on gather()
186 # leaves self._sites in unpredictable state.
187 # The loop guaranties that a site is either deleted on success or
188 # still present on failure
189 for site in list(self._sites):
190 await site.stop()
191 await self._cleanup_server()
192 self._server = None
193 if self._handle_signals:
194 try:
195 loop.remove_signal_handler(signal.SIGINT)
196 loop.remove_signal_handler(signal.SIGTERM)
197 except NotImplementedError: # pragma: no cover
198 # remove_signal_handler is not implemented on Windows
199 pass
200
201 @abstractmethod
202 async def _make_server(self):
203 pass # pragma: no cover
204
205 @abstractmethod
206 async def _cleanup_server(self):
207 pass # pragma: no cover
208
209 def _reg_site(self, site):
210 if site in self._sites:
211 raise RuntimeError("Site {} is already registered in runner {}"
212 .format(site, self))
213 self._sites.add(site)
214
215 def _check_site(self, site):
216 if site not in self._sites:
217 raise RuntimeError("Site {} is not registered in runner {}"
218 .format(site, self))
219
220 def _unreg_site(self, site):
221 if site not in self._sites:
222 raise RuntimeError("Site {} is not registered in runner {}"
223 .format(site, self))
224 self._sites.remove(site)
225
226
227 class ServerRunner(BaseRunner):
228 """Low-level web server runner"""
229
230 __slots__ = ('_web_server',)
231
232 def __init__(self, web_server, *, handle_signals=False, **kwargs):
233 super().__init__(handle_signals=handle_signals, **kwargs)
234 self._web_server = web_server
235
236 async def shutdown(self):
237 pass
238
239 async def _make_server(self):
240 return self._web_server
241
242 async def _cleanup_server(self):
243 pass
244
245
246 class AppRunner(BaseRunner):
247 """Web Application runner"""
248
249 __slots__ = ('_app',)
250
251 def __init__(self, app, *, handle_signals=False, **kwargs):
252 super().__init__(handle_signals=handle_signals, **kwargs)
253 if not isinstance(app, Application):
254 raise TypeError("The first argument should be web.Application "
255 "instance, got {!r}".format(app))
256 self._app = app
257
258 @property
259 def app(self):
260 return self._app
261
262 async def shutdown(self):
263 await self._app.shutdown()
264
265 async def _make_server(self):
266 loop = asyncio.get_event_loop()
267 self._app._set_loop(loop)
268 self._app.on_startup.freeze()
269 await self._app.startup()
270 self._app.freeze()
271
272 return self._app._make_handler(loop=loop, **self._kwargs)
273
274 async def _cleanup_server(self):
275 await self._app.cleanup()
276
[end of aiohttp/web_runner.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/aiohttp/web_runner.py b/aiohttp/web_runner.py
--- a/aiohttp/web_runner.py
+++ b/aiohttp/web_runner.py
@@ -148,12 +148,18 @@
self._handle_signals = handle_signals
self._kwargs = kwargs
self._server = None
- self._sites = set()
+ self._sites = []
@property
def server(self):
return self._server
+ @property
+ def addresses(self):
+ return [sock.getsockname()
+ for site in self._sites
+ for sock in site._server.sockets]
+
@property
def sites(self):
return set(self._sites)
@@ -210,7 +216,7 @@
if site in self._sites:
raise RuntimeError("Site {} is already registered in runner {}"
.format(site, self))
- self._sites.add(site)
+ self._sites.append(site)
def _check_site(self, site):
if site not in self._sites:
| {"golden_diff": "diff --git a/aiohttp/web_runner.py b/aiohttp/web_runner.py\n--- a/aiohttp/web_runner.py\n+++ b/aiohttp/web_runner.py\n@@ -148,12 +148,18 @@\n self._handle_signals = handle_signals\n self._kwargs = kwargs\n self._server = None\n- self._sites = set()\n+ self._sites = []\n \n @property\n def server(self):\n return self._server\n \n+ @property\n+ def addresses(self):\n+ return [sock.getsockname()\n+ for site in self._sites\n+ for sock in site._server.sockets]\n+\n @property\n def sites(self):\n return set(self._sites)\n@@ -210,7 +216,7 @@\n if site in self._sites:\n raise RuntimeError(\"Site {} is already registered in runner {}\"\n .format(site, self))\n- self._sites.add(site)\n+ self._sites.append(site)\n \n def _check_site(self, site):\n if site not in self._sites:\n", "issue": "Access to socket information when using AppRunner\n## Long story short\r\n\r\nSometimes I like to listen on port 0 to allow for any and need to access the actual port after binding.\r\n\r\n## Expected behaviour\r\n\r\nA public way to access socket information like the port number.\r\n\r\n## Actual behaviour\r\n\r\nI have to reach into the private `TCPSite._server`.\n", "before_files": [{"content": "import asyncio\nimport signal\nimport socket\nfrom abc import ABC, abstractmethod\n\nfrom yarl import URL\n\nfrom .web_app import Application\n\n\n__all__ = ('TCPSite', 'UnixSite', 'SockSite', 'BaseRunner',\n 'AppRunner', 'ServerRunner', 'GracefulExit')\n\n\nclass GracefulExit(SystemExit):\n code = 1\n\n\ndef _raise_graceful_exit():\n raise GracefulExit()\n\n\nclass BaseSite(ABC):\n __slots__ = ('_runner', '_shutdown_timeout', '_ssl_context', '_backlog',\n '_server')\n\n def __init__(self, runner, *,\n shutdown_timeout=60.0, ssl_context=None,\n backlog=128):\n if runner.server is None:\n raise RuntimeError(\"Call runner.setup() before making a site\")\n self._runner = runner\n self._shutdown_timeout = shutdown_timeout\n self._ssl_context = ssl_context\n self._backlog = backlog\n self._server = None\n\n @property\n @abstractmethod\n def name(self):\n pass # pragma: no cover\n\n @abstractmethod\n async def start(self):\n self._runner._reg_site(self)\n\n async def stop(self):\n self._runner._check_site(self)\n if self._server is None:\n self._runner._unreg_site(self)\n return # not started yet\n self._server.close()\n await self._server.wait_closed()\n await self._runner.shutdown()\n await self._runner.server.shutdown(self._shutdown_timeout)\n self._runner._unreg_site(self)\n\n\nclass TCPSite(BaseSite):\n __slots__ = ('_host', '_port', '_reuse_address', '_reuse_port')\n\n def __init__(self, runner, host=None, port=None, *,\n shutdown_timeout=60.0, ssl_context=None,\n backlog=128, reuse_address=None,\n reuse_port=None):\n super().__init__(runner, shutdown_timeout=shutdown_timeout,\n ssl_context=ssl_context, backlog=backlog)\n if host is None:\n host = \"0.0.0.0\"\n self._host = host\n if port is None:\n port = 8443 if self._ssl_context else 8080\n self._port = port\n self._reuse_address = reuse_address\n self._reuse_port = reuse_port\n\n @property\n def name(self):\n scheme = 'https' if self._ssl_context else 'http'\n return str(URL.build(scheme=scheme, host=self._host, port=self._port))\n\n async def start(self):\n await super().start()\n loop = asyncio.get_event_loop()\n self._server = await loop.create_server(\n self._runner.server, self._host, self._port,\n ssl=self._ssl_context, backlog=self._backlog,\n reuse_address=self._reuse_address,\n reuse_port=self._reuse_port)\n\n\nclass UnixSite(BaseSite):\n __slots__ = ('_path', )\n\n def __init__(self, runner, path, *,\n shutdown_timeout=60.0, ssl_context=None,\n backlog=128):\n super().__init__(runner, shutdown_timeout=shutdown_timeout,\n ssl_context=ssl_context, backlog=backlog)\n self._path = path\n\n @property\n def name(self):\n scheme = 'https' if self._ssl_context else 'http'\n return '{}://unix:{}:'.format(scheme, self._path)\n\n async def start(self):\n await super().start()\n loop = asyncio.get_event_loop()\n self._server = await loop.create_unix_server(\n self._runner.server, self._path,\n ssl=self._ssl_context, backlog=self._backlog)\n\n\nclass SockSite(BaseSite):\n __slots__ = ('_sock', '_name')\n\n def __init__(self, runner, sock, *,\n shutdown_timeout=60.0, ssl_context=None,\n backlog=128):\n super().__init__(runner, shutdown_timeout=shutdown_timeout,\n ssl_context=ssl_context, backlog=backlog)\n self._sock = sock\n scheme = 'https' if self._ssl_context else 'http'\n if hasattr(socket, 'AF_UNIX') and sock.family == socket.AF_UNIX:\n name = '{}://unix:{}:'.format(scheme, sock.getsockname())\n else:\n host, port = sock.getsockname()[:2]\n name = str(URL.build(scheme=scheme, host=host, port=port))\n self._name = name\n\n @property\n def name(self):\n return self._name\n\n async def start(self):\n await super().start()\n loop = asyncio.get_event_loop()\n self._server = await loop.create_server(\n self._runner.server, sock=self._sock,\n ssl=self._ssl_context, backlog=self._backlog)\n\n\nclass BaseRunner(ABC):\n __slots__ = ('_handle_signals', '_kwargs', '_server', '_sites')\n\n def __init__(self, *, handle_signals=False, **kwargs):\n self._handle_signals = handle_signals\n self._kwargs = kwargs\n self._server = None\n self._sites = set()\n\n @property\n def server(self):\n return self._server\n\n @property\n def sites(self):\n return set(self._sites)\n\n async def setup(self):\n loop = asyncio.get_event_loop()\n\n if self._handle_signals:\n try:\n loop.add_signal_handler(signal.SIGINT, _raise_graceful_exit)\n loop.add_signal_handler(signal.SIGTERM, _raise_graceful_exit)\n except NotImplementedError: # pragma: no cover\n # add_signal_handler is not implemented on Windows\n pass\n\n self._server = await self._make_server()\n\n @abstractmethod\n async def shutdown(self):\n pass # pragma: no cover\n\n async def cleanup(self):\n loop = asyncio.get_event_loop()\n\n if self._server is None:\n # no started yet, do nothing\n return\n\n # The loop over sites is intentional, an exception on gather()\n # leaves self._sites in unpredictable state.\n # The loop guaranties that a site is either deleted on success or\n # still present on failure\n for site in list(self._sites):\n await site.stop()\n await self._cleanup_server()\n self._server = None\n if self._handle_signals:\n try:\n loop.remove_signal_handler(signal.SIGINT)\n loop.remove_signal_handler(signal.SIGTERM)\n except NotImplementedError: # pragma: no cover\n # remove_signal_handler is not implemented on Windows\n pass\n\n @abstractmethod\n async def _make_server(self):\n pass # pragma: no cover\n\n @abstractmethod\n async def _cleanup_server(self):\n pass # pragma: no cover\n\n def _reg_site(self, site):\n if site in self._sites:\n raise RuntimeError(\"Site {} is already registered in runner {}\"\n .format(site, self))\n self._sites.add(site)\n\n def _check_site(self, site):\n if site not in self._sites:\n raise RuntimeError(\"Site {} is not registered in runner {}\"\n .format(site, self))\n\n def _unreg_site(self, site):\n if site not in self._sites:\n raise RuntimeError(\"Site {} is not registered in runner {}\"\n .format(site, self))\n self._sites.remove(site)\n\n\nclass ServerRunner(BaseRunner):\n \"\"\"Low-level web server runner\"\"\"\n\n __slots__ = ('_web_server',)\n\n def __init__(self, web_server, *, handle_signals=False, **kwargs):\n super().__init__(handle_signals=handle_signals, **kwargs)\n self._web_server = web_server\n\n async def shutdown(self):\n pass\n\n async def _make_server(self):\n return self._web_server\n\n async def _cleanup_server(self):\n pass\n\n\nclass AppRunner(BaseRunner):\n \"\"\"Web Application runner\"\"\"\n\n __slots__ = ('_app',)\n\n def __init__(self, app, *, handle_signals=False, **kwargs):\n super().__init__(handle_signals=handle_signals, **kwargs)\n if not isinstance(app, Application):\n raise TypeError(\"The first argument should be web.Application \"\n \"instance, got {!r}\".format(app))\n self._app = app\n\n @property\n def app(self):\n return self._app\n\n async def shutdown(self):\n await self._app.shutdown()\n\n async def _make_server(self):\n loop = asyncio.get_event_loop()\n self._app._set_loop(loop)\n self._app.on_startup.freeze()\n await self._app.startup()\n self._app.freeze()\n\n return self._app._make_handler(loop=loop, **self._kwargs)\n\n async def _cleanup_server(self):\n await self._app.cleanup()\n", "path": "aiohttp/web_runner.py"}]} | 3,273 | 240 |
gh_patches_debug_24910 | rasdani/github-patches | git_diff | pypi__warehouse-3457 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Trending Projects are not updated
I think in the past month that I've been looking at pypi.org (and even before that), the "Trending Projects" haven't changed.
</issue>
<code>
[start of warehouse/packaging/tasks.py]
1 # Licensed under the Apache License, Version 2.0 (the "License");
2 # you may not use this file except in compliance with the License.
3 # You may obtain a copy of the License at
4 #
5 # http://www.apache.org/licenses/LICENSE-2.0
6 #
7 # Unless required by applicable law or agreed to in writing, software
8 # distributed under the License is distributed on an "AS IS" BASIS,
9 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10 # See the License for the specific language governing permissions and
11 # limitations under the License.
12
13 from warehouse import tasks
14 from warehouse.cache.origin import IOriginCache
15 from warehouse.packaging.models import Project
16
17
18 @tasks.task(ignore_result=True, acks_late=True)
19 def compute_trending(request):
20 bq = request.find_service(name="gcloud.bigquery")
21 query = bq.run_sync_query(
22 """ SELECT project,
23 IF(
24 STDDEV(downloads) > 0,
25 (todays_downloads - AVG(downloads))/STDDEV(downloads),
26 NULL
27 ) as zscore
28 FROM (
29 SELECT project,
30 date,
31 downloads,
32 FIRST_VALUE(downloads) OVER (
33 PARTITION BY project
34 ORDER BY DATE DESC
35 ROWS BETWEEN UNBOUNDED PRECEDING
36 AND UNBOUNDED FOLLOWING
37 ) as todays_downloads
38 FROM (
39 SELECT file.project as project,
40 DATE(timestamp) AS date,
41 COUNT(*) as downloads
42 FROM `{table}`
43 WHERE _TABLE_SUFFIX BETWEEN
44 FORMAT_DATE(
45 "%Y%m%d",
46 DATE_ADD(CURRENT_DATE(), INTERVAL -31 day))
47 AND
48 FORMAT_DATE(
49 "%Y%m%d",
50 DATE_ADD(CURRENT_DATE(), INTERVAL -1 day))
51 GROUP BY file.project, date
52 )
53 )
54 GROUP BY project, todays_downloads
55 HAVING SUM(downloads) >= 5000
56 ORDER BY zscore DESC
57 """.format(table=request.registry.settings["warehouse.trending_table"])
58 )
59 query.use_legacy_sql = False
60 query.run()
61
62 zscores = {}
63 page_token = None
64 while True:
65 rows, total_rows, page_token = query.fetch_data(
66 max_results=1000,
67 page_token=page_token,
68 )
69
70 zscores.update(dict(rows))
71
72 if not page_token:
73 break
74
75 # We're going to "reset" all of our zscores to a steady state where they
76 # are all equal to ``None``. The next query will then set any that have a
77 # value back to the expected value.
78 (request.db.query(Project)
79 .filter(Project.zscore != None) # noqa
80 .update({Project.zscore: None}))
81
82 # We need to convert the normalized name that we get out of BigQuery and
83 # turn it into the primary key of the Project object and construct a list
84 # of primary key: new zscore, including a default of None if the item isn't
85 # in the result set.
86 query = request.db.query(Project.name, Project.normalized_name).all()
87 to_update = [
88 {"name": name, "zscore": zscores[normalized_name]}
89 for name, normalized_name in query
90 if normalized_name in zscores
91 ]
92
93 # Reflect out updated ZScores into the database.
94 request.db.bulk_update_mappings(Project, to_update)
95
96 # Trigger a purge of the trending surrogate key.
97 try:
98 cacher = request.find_service(IOriginCache)
99 except ValueError:
100 pass
101 else:
102 cacher.purge(["trending"])
103
[end of warehouse/packaging/tasks.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/warehouse/packaging/tasks.py b/warehouse/packaging/tasks.py
--- a/warehouse/packaging/tasks.py
+++ b/warehouse/packaging/tasks.py
@@ -18,7 +18,7 @@
@tasks.task(ignore_result=True, acks_late=True)
def compute_trending(request):
bq = request.find_service(name="gcloud.bigquery")
- query = bq.run_sync_query(
+ query = bq.query(
""" SELECT project,
IF(
STDDEV(downloads) > 0,
@@ -56,21 +56,11 @@
ORDER BY zscore DESC
""".format(table=request.registry.settings["warehouse.trending_table"])
)
- query.use_legacy_sql = False
- query.run()
zscores = {}
- page_token = None
- while True:
- rows, total_rows, page_token = query.fetch_data(
- max_results=1000,
- page_token=page_token,
- )
-
- zscores.update(dict(rows))
-
- if not page_token:
- break
+ for row in query.result():
+ row = dict(row)
+ zscores[row["project"]] = row["zscore"]
# We're going to "reset" all of our zscores to a steady state where they
# are all equal to ``None``. The next query will then set any that have a
| {"golden_diff": "diff --git a/warehouse/packaging/tasks.py b/warehouse/packaging/tasks.py\n--- a/warehouse/packaging/tasks.py\n+++ b/warehouse/packaging/tasks.py\n@@ -18,7 +18,7 @@\n @tasks.task(ignore_result=True, acks_late=True)\n def compute_trending(request):\n bq = request.find_service(name=\"gcloud.bigquery\")\n- query = bq.run_sync_query(\n+ query = bq.query(\n \"\"\" SELECT project,\n IF(\n STDDEV(downloads) > 0,\n@@ -56,21 +56,11 @@\n ORDER BY zscore DESC\n \"\"\".format(table=request.registry.settings[\"warehouse.trending_table\"])\n )\n- query.use_legacy_sql = False\n- query.run()\n \n zscores = {}\n- page_token = None\n- while True:\n- rows, total_rows, page_token = query.fetch_data(\n- max_results=1000,\n- page_token=page_token,\n- )\n-\n- zscores.update(dict(rows))\n-\n- if not page_token:\n- break\n+ for row in query.result():\n+ row = dict(row)\n+ zscores[row[\"project\"]] = row[\"zscore\"]\n \n # We're going to \"reset\" all of our zscores to a steady state where they\n # are all equal to ``None``. The next query will then set any that have a\n", "issue": "Trending Projects are not updated\nI think in the past month that I've been looking at pypi.org (and even before that), the \"Trending Projects\" haven't changed.\r\n\n", "before_files": [{"content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nfrom warehouse import tasks\nfrom warehouse.cache.origin import IOriginCache\nfrom warehouse.packaging.models import Project\n\n\[email protected](ignore_result=True, acks_late=True)\ndef compute_trending(request):\n bq = request.find_service(name=\"gcloud.bigquery\")\n query = bq.run_sync_query(\n \"\"\" SELECT project,\n IF(\n STDDEV(downloads) > 0,\n (todays_downloads - AVG(downloads))/STDDEV(downloads),\n NULL\n ) as zscore\n FROM (\n SELECT project,\n date,\n downloads,\n FIRST_VALUE(downloads) OVER (\n PARTITION BY project\n ORDER BY DATE DESC\n ROWS BETWEEN UNBOUNDED PRECEDING\n AND UNBOUNDED FOLLOWING\n ) as todays_downloads\n FROM (\n SELECT file.project as project,\n DATE(timestamp) AS date,\n COUNT(*) as downloads\n FROM `{table}`\n WHERE _TABLE_SUFFIX BETWEEN\n FORMAT_DATE(\n \"%Y%m%d\",\n DATE_ADD(CURRENT_DATE(), INTERVAL -31 day))\n AND\n FORMAT_DATE(\n \"%Y%m%d\",\n DATE_ADD(CURRENT_DATE(), INTERVAL -1 day))\n GROUP BY file.project, date\n )\n )\n GROUP BY project, todays_downloads\n HAVING SUM(downloads) >= 5000\n ORDER BY zscore DESC\n \"\"\".format(table=request.registry.settings[\"warehouse.trending_table\"])\n )\n query.use_legacy_sql = False\n query.run()\n\n zscores = {}\n page_token = None\n while True:\n rows, total_rows, page_token = query.fetch_data(\n max_results=1000,\n page_token=page_token,\n )\n\n zscores.update(dict(rows))\n\n if not page_token:\n break\n\n # We're going to \"reset\" all of our zscores to a steady state where they\n # are all equal to ``None``. The next query will then set any that have a\n # value back to the expected value.\n (request.db.query(Project)\n .filter(Project.zscore != None) # noqa\n .update({Project.zscore: None}))\n\n # We need to convert the normalized name that we get out of BigQuery and\n # turn it into the primary key of the Project object and construct a list\n # of primary key: new zscore, including a default of None if the item isn't\n # in the result set.\n query = request.db.query(Project.name, Project.normalized_name).all()\n to_update = [\n {\"name\": name, \"zscore\": zscores[normalized_name]}\n for name, normalized_name in query\n if normalized_name in zscores\n ]\n\n # Reflect out updated ZScores into the database.\n request.db.bulk_update_mappings(Project, to_update)\n\n # Trigger a purge of the trending surrogate key.\n try:\n cacher = request.find_service(IOriginCache)\n except ValueError:\n pass\n else:\n cacher.purge([\"trending\"])\n", "path": "warehouse/packaging/tasks.py"}]} | 1,554 | 314 |
gh_patches_debug_25848 | rasdani/github-patches | git_diff | pypa__cibuildwheel-76 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Windows wheels are not built for python 3.7
On Linux wheels are correctly built for all supported python versions. Windows however stops at python 3.6.
Looking at windows.py there seem to be no references to python 3.7
</issue>
<code>
[start of cibuildwheel/windows.py]
1 from __future__ import print_function
2 import os, tempfile, subprocess, sys, shutil
3 try:
4 from urllib2 import urlopen
5 except ImportError:
6 from urllib.request import urlopen
7 from collections import namedtuple
8 from glob import glob
9
10 from .util import prepare_command, get_build_verbosity_extra_flags, Unbuffered
11
12
13 def build(project_dir, package_name, output_dir, test_command, test_requires, before_build, build_verbosity, skip, environment):
14 # Python under AppVeyor/Windows seems to be buffering by default, giving problems interleaving subprocess call output with unflushed calls to 'print'
15 sys.stdout.flush()
16 sys.stdout = Unbuffered(sys.stdout)
17
18 # run_with_env is a cmd file that sets the right environment variables to
19 run_with_env = os.path.join(tempfile.gettempdir(), 'appveyor_run_with_env.cmd')
20 if not os.path.exists(run_with_env):
21 with open(run_with_env, 'wb') as f:
22 request = urlopen('https://github.com/ogrisel/python-appveyor-demo/raw/09a1c8672e5015a74d8f69d07add6ee803c176ec/appveyor/run_with_env.cmd')
23 f.write(request.read())
24
25 def shell(args, env=None, cwd=None):
26 # print the command executing for the logs
27 print('+ ' + ' '.join(args))
28 args = ['cmd', '/E:ON', '/V:ON', '/C', run_with_env] + args
29 return subprocess.check_call(' '.join(args), env=env, cwd=cwd)
30
31 PythonConfiguration = namedtuple('PythonConfiguration', ['version', 'arch', 'identifier', 'path'])
32 python_configurations = [
33 PythonConfiguration(version='2.7.x', arch="32", identifier='cp27-win32', path='C:\Python27'),
34 PythonConfiguration(version='2.7.x', arch="64", identifier='cp27-win_amd64', path='C:\Python27-x64'),
35 PythonConfiguration(version='3.3.x', arch="32", identifier='cp33-win32', path='C:\Python33'),
36 PythonConfiguration(version='3.3.x', arch="64", identifier='cp33-win_amd64', path='C:\Python33-x64'),
37 PythonConfiguration(version='3.4.x', arch="32", identifier='cp34-win32', path='C:\Python34'),
38 PythonConfiguration(version='3.4.x', arch="64", identifier='cp34-win_amd64', path='C:\Python34-x64'),
39 PythonConfiguration(version='3.5.x', arch="32", identifier='cp35-win32', path='C:\Python35'),
40 PythonConfiguration(version='3.5.x', arch="64", identifier='cp35-win_amd64', path='C:\Python35-x64'),
41 PythonConfiguration(version='3.6.x', arch="32", identifier='cp36-win32', path='C:\Python36'),
42 PythonConfiguration(version='3.6.x', arch="64", identifier='cp36-win_amd64', path='C:\Python36-x64'),
43 ]
44
45 abs_project_dir = os.path.abspath(project_dir)
46 temp_dir = tempfile.mkdtemp(prefix='cibuildwheel')
47 built_wheel_dir = os.path.join(temp_dir, 'built_wheel')
48
49 for config in python_configurations:
50 if skip(config.identifier):
51 print('cibuildwheel: Skipping build %s' % config.identifier, file=sys.stderr)
52 continue
53
54 # setup dirs
55 if os.path.exists(built_wheel_dir):
56 shutil.rmtree(built_wheel_dir)
57 os.makedirs(built_wheel_dir)
58
59 env = os.environ.copy()
60 # set up environment variables for run_with_env
61 env['PYTHON_VERSION'] = config.version
62 env['PYTHON_ARCH'] = config.arch
63 env['PATH'] = os.pathsep.join([
64 config.path,
65 os.path.join(config.path, 'Scripts'),
66 env['PATH']
67 ])
68 env = environment.as_dictionary(prev_environment=env)
69
70 # for the logs - check we're running the right version of python
71 shell(['python', '--version'], env=env)
72 shell(['python', '-c', '"import struct; print(struct.calcsize(\'P\') * 8)\"'], env=env)
73
74 # prepare the Python environment
75 shell(['python', '-m', 'pip', 'install', '--upgrade', 'pip'],
76 env=env)
77 shell(['pip', 'install', '--upgrade', 'setuptools'], env=env)
78 shell(['pip', 'install', 'wheel'], env=env)
79
80 # run the before_build command
81 if before_build:
82 before_build_prepared = prepare_command(before_build, project=abs_project_dir)
83 shell([before_build_prepared], env=env)
84
85 # build the wheel
86 shell(['pip', 'wheel', abs_project_dir, '-w', built_wheel_dir, '--no-deps'] + get_build_verbosity_extra_flags(build_verbosity), env=env)
87 built_wheel = glob(built_wheel_dir+'/*.whl')[0]
88
89 # install the wheel
90 shell(['pip', 'install', built_wheel], env=env)
91
92 # test the wheel
93 if test_requires:
94 shell(['pip', 'install'] + test_requires, env=env)
95 if test_command:
96 # run the tests from c:\, with an absolute path in the command
97 # (this ensures that Python runs the tests against the installed wheel
98 # and not the repo code)
99 test_command_prepared = prepare_command(test_command, project=abs_project_dir)
100 shell([test_command_prepared], cwd='c:\\', env=env)
101
102 # we're all done here; move it to output
103 shutil.move(built_wheel, output_dir)
104
[end of cibuildwheel/windows.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/cibuildwheel/windows.py b/cibuildwheel/windows.py
--- a/cibuildwheel/windows.py
+++ b/cibuildwheel/windows.py
@@ -40,6 +40,8 @@
PythonConfiguration(version='3.5.x', arch="64", identifier='cp35-win_amd64', path='C:\Python35-x64'),
PythonConfiguration(version='3.6.x', arch="32", identifier='cp36-win32', path='C:\Python36'),
PythonConfiguration(version='3.6.x', arch="64", identifier='cp36-win_amd64', path='C:\Python36-x64'),
+ PythonConfiguration(version='3.7.x', arch="32", identifier='cp37-win32', path='C:\Python37'),
+ PythonConfiguration(version='3.7.x', arch="64", identifier='cp37-win_amd64', path='C:\Python37-x64'),
]
abs_project_dir = os.path.abspath(project_dir)
@@ -50,6 +52,10 @@
if skip(config.identifier):
print('cibuildwheel: Skipping build %s' % config.identifier, file=sys.stderr)
continue
+
+ # check python & pip exist for this configuration
+ assert os.path.exists(os.path.join(config.path, 'python.exe'))
+ assert os.path.exists(os.path.join(config.path, 'Scripts', 'pip.exe'))
# setup dirs
if os.path.exists(built_wheel_dir):
| {"golden_diff": "diff --git a/cibuildwheel/windows.py b/cibuildwheel/windows.py\n--- a/cibuildwheel/windows.py\n+++ b/cibuildwheel/windows.py\n@@ -40,6 +40,8 @@\n PythonConfiguration(version='3.5.x', arch=\"64\", identifier='cp35-win_amd64', path='C:\\Python35-x64'),\n PythonConfiguration(version='3.6.x', arch=\"32\", identifier='cp36-win32', path='C:\\Python36'),\n PythonConfiguration(version='3.6.x', arch=\"64\", identifier='cp36-win_amd64', path='C:\\Python36-x64'),\n+ PythonConfiguration(version='3.7.x', arch=\"32\", identifier='cp37-win32', path='C:\\Python37'),\n+ PythonConfiguration(version='3.7.x', arch=\"64\", identifier='cp37-win_amd64', path='C:\\Python37-x64'),\n ]\n \n abs_project_dir = os.path.abspath(project_dir)\n@@ -50,6 +52,10 @@\n if skip(config.identifier):\n print('cibuildwheel: Skipping build %s' % config.identifier, file=sys.stderr)\n continue\n+ \n+ # check python & pip exist for this configuration\n+ assert os.path.exists(os.path.join(config.path, 'python.exe'))\n+ assert os.path.exists(os.path.join(config.path, 'Scripts', 'pip.exe'))\n \n # setup dirs\n if os.path.exists(built_wheel_dir):\n", "issue": "Windows wheels are not built for python 3.7\nOn Linux wheels are correctly built for all supported python versions. Windows however stops at python 3.6.\r\n\r\nLooking at windows.py there seem to be no references to python 3.7\n", "before_files": [{"content": "from __future__ import print_function\nimport os, tempfile, subprocess, sys, shutil\ntry:\n from urllib2 import urlopen\nexcept ImportError:\n from urllib.request import urlopen\nfrom collections import namedtuple\nfrom glob import glob\n\nfrom .util import prepare_command, get_build_verbosity_extra_flags, Unbuffered\n\n\ndef build(project_dir, package_name, output_dir, test_command, test_requires, before_build, build_verbosity, skip, environment):\n # Python under AppVeyor/Windows seems to be buffering by default, giving problems interleaving subprocess call output with unflushed calls to 'print'\n sys.stdout.flush()\n sys.stdout = Unbuffered(sys.stdout)\n\n # run_with_env is a cmd file that sets the right environment variables to\n run_with_env = os.path.join(tempfile.gettempdir(), 'appveyor_run_with_env.cmd')\n if not os.path.exists(run_with_env):\n with open(run_with_env, 'wb') as f:\n request = urlopen('https://github.com/ogrisel/python-appveyor-demo/raw/09a1c8672e5015a74d8f69d07add6ee803c176ec/appveyor/run_with_env.cmd')\n f.write(request.read())\n\n def shell(args, env=None, cwd=None):\n # print the command executing for the logs\n print('+ ' + ' '.join(args))\n args = ['cmd', '/E:ON', '/V:ON', '/C', run_with_env] + args\n return subprocess.check_call(' '.join(args), env=env, cwd=cwd)\n\n PythonConfiguration = namedtuple('PythonConfiguration', ['version', 'arch', 'identifier', 'path'])\n python_configurations = [\n PythonConfiguration(version='2.7.x', arch=\"32\", identifier='cp27-win32', path='C:\\Python27'),\n PythonConfiguration(version='2.7.x', arch=\"64\", identifier='cp27-win_amd64', path='C:\\Python27-x64'),\n PythonConfiguration(version='3.3.x', arch=\"32\", identifier='cp33-win32', path='C:\\Python33'),\n PythonConfiguration(version='3.3.x', arch=\"64\", identifier='cp33-win_amd64', path='C:\\Python33-x64'),\n PythonConfiguration(version='3.4.x', arch=\"32\", identifier='cp34-win32', path='C:\\Python34'),\n PythonConfiguration(version='3.4.x', arch=\"64\", identifier='cp34-win_amd64', path='C:\\Python34-x64'),\n PythonConfiguration(version='3.5.x', arch=\"32\", identifier='cp35-win32', path='C:\\Python35'),\n PythonConfiguration(version='3.5.x', arch=\"64\", identifier='cp35-win_amd64', path='C:\\Python35-x64'),\n PythonConfiguration(version='3.6.x', arch=\"32\", identifier='cp36-win32', path='C:\\Python36'),\n PythonConfiguration(version='3.6.x', arch=\"64\", identifier='cp36-win_amd64', path='C:\\Python36-x64'),\n ]\n\n abs_project_dir = os.path.abspath(project_dir)\n temp_dir = tempfile.mkdtemp(prefix='cibuildwheel')\n built_wheel_dir = os.path.join(temp_dir, 'built_wheel')\n\n for config in python_configurations:\n if skip(config.identifier):\n print('cibuildwheel: Skipping build %s' % config.identifier, file=sys.stderr)\n continue\n\n # setup dirs\n if os.path.exists(built_wheel_dir):\n shutil.rmtree(built_wheel_dir)\n os.makedirs(built_wheel_dir)\n\n env = os.environ.copy()\n # set up environment variables for run_with_env\n env['PYTHON_VERSION'] = config.version\n env['PYTHON_ARCH'] = config.arch\n env['PATH'] = os.pathsep.join([\n config.path,\n os.path.join(config.path, 'Scripts'),\n env['PATH']\n ])\n env = environment.as_dictionary(prev_environment=env)\n\n # for the logs - check we're running the right version of python\n shell(['python', '--version'], env=env)\n shell(['python', '-c', '\"import struct; print(struct.calcsize(\\'P\\') * 8)\\\"'], env=env)\n\n # prepare the Python environment\n shell(['python', '-m', 'pip', 'install', '--upgrade', 'pip'],\n env=env)\n shell(['pip', 'install', '--upgrade', 'setuptools'], env=env)\n shell(['pip', 'install', 'wheel'], env=env)\n\n # run the before_build command\n if before_build:\n before_build_prepared = prepare_command(before_build, project=abs_project_dir)\n shell([before_build_prepared], env=env)\n\n # build the wheel\n shell(['pip', 'wheel', abs_project_dir, '-w', built_wheel_dir, '--no-deps'] + get_build_verbosity_extra_flags(build_verbosity), env=env)\n built_wheel = glob(built_wheel_dir+'/*.whl')[0]\n\n # install the wheel\n shell(['pip', 'install', built_wheel], env=env)\n\n # test the wheel\n if test_requires:\n shell(['pip', 'install'] + test_requires, env=env)\n if test_command:\n # run the tests from c:\\, with an absolute path in the command\n # (this ensures that Python runs the tests against the installed wheel\n # and not the repo code)\n test_command_prepared = prepare_command(test_command, project=abs_project_dir)\n shell([test_command_prepared], cwd='c:\\\\', env=env)\n\n # we're all done here; move it to output\n shutil.move(built_wheel, output_dir)\n", "path": "cibuildwheel/windows.py"}]} | 2,101 | 347 |
gh_patches_debug_14930 | rasdani/github-patches | git_diff | mirumee__ariadne-228 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Async context_value callable is not supported
Our ASGI GraphQL app supports callable `context_value`, but it doesnt support `async` callable, so it's impossible to do any async work in it like get user form database. 😂
Example:
```python
async def resolve_context(request: Request) -> Dict:
return {"user": await get_user_for_request(request)}
graphql_app = GraphQL(schema, context_value=resolve_context)
```
</issue>
<code>
[start of ariadne/asgi.py]
1 import asyncio
2 import json
3 from typing import (
4 Any,
5 AsyncGenerator,
6 Callable,
7 Dict,
8 List,
9 Optional,
10 Union,
11 Type,
12 cast,
13 )
14
15 from graphql import GraphQLError, GraphQLSchema
16 from graphql.execution import MiddlewareManager
17 from starlette.datastructures import UploadFile
18 from starlette.requests import Request
19 from starlette.responses import HTMLResponse, JSONResponse, PlainTextResponse, Response
20 from starlette.types import Receive, Scope, Send
21 from starlette.websockets import WebSocket, WebSocketState, WebSocketDisconnect
22
23 from .constants import DATA_TYPE_JSON, DATA_TYPE_MULTIPART, PLAYGROUND_HTML
24 from .exceptions import HttpBadRequestError, HttpError
25 from .file_uploads import combine_multipart_data
26 from .format_error import format_error
27 from .graphql import graphql, subscribe
28 from .logger import log_error
29 from .types import ContextValue, ErrorFormatter, Extension, RootValue
30
31 GQL_CONNECTION_INIT = "connection_init" # Client -> Server
32 GQL_CONNECTION_ACK = "connection_ack" # Server -> Client
33 GQL_CONNECTION_ERROR = "connection_error" # Server -> Client
34
35 # NOTE: The keep alive message type does not follow the standard due to connection optimizations
36 GQL_CONNECTION_KEEP_ALIVE = "ka" # Server -> Client
37
38 GQL_CONNECTION_TERMINATE = "connection_terminate" # Client -> Server
39 GQL_START = "start" # Client -> Server
40 GQL_DATA = "data" # Server -> Client
41 GQL_ERROR = "error" # Server -> Client
42 GQL_COMPLETE = "complete" # Server -> Client
43 GQL_STOP = "stop" # Client -> Server
44
45 ExtensionList = Optional[List[Type[Extension]]]
46
47
48 class GraphQL:
49 def __init__(
50 self,
51 schema: GraphQLSchema,
52 *,
53 context_value: Optional[ContextValue] = None,
54 root_value: Optional[RootValue] = None,
55 debug: bool = False,
56 logger: Optional[str] = None,
57 error_formatter: ErrorFormatter = format_error,
58 extensions: Union[Callable[[Any], ExtensionList], ExtensionList] = None,
59 middleware: Optional[MiddlewareManager] = None,
60 keepalive: float = None,
61 ):
62 self.context_value = context_value
63 self.root_value = root_value
64 self.debug = debug
65 self.logger = logger
66 self.error_formatter = error_formatter
67 self.extensions = extensions
68 self.middleware = middleware
69 self.keepalive = keepalive
70 self.schema = schema
71
72 async def __call__(self, scope: Scope, receive: Receive, send: Send):
73 if scope["type"] == "http":
74 await self.handle_http(scope=scope, receive=receive, send=send)
75 elif scope["type"] == "websocket":
76 await self.handle_websocket(scope=scope, receive=receive, send=send)
77 else:
78 raise ValueError("Unknown scope type: %r" % (scope["type"],))
79
80 async def get_context_for_request(self, request: Any) -> Any:
81 if callable(self.context_value):
82 return self.context_value(request)
83 return self.context_value or {"request": request}
84
85 async def get_extensions_for_request(self, request: Any) -> ExtensionList:
86 if callable(self.extensions):
87 return self.extensions(request)
88 return self.extensions
89
90 async def handle_http(self, scope: Scope, receive: Receive, send: Send):
91 request = Request(scope=scope, receive=receive)
92 if request.method == "GET":
93 response = await self.render_playground(request)
94 elif request.method == "POST":
95 response = await self.graphql_http_server(request)
96 else:
97 response = Response(status_code=405)
98 await response(scope, receive, send)
99
100 async def handle_websocket(self, scope: Scope, receive: Receive, send: Send):
101 websocket = WebSocket(scope=scope, receive=receive, send=send)
102 await self.websocket_server(websocket)
103
104 async def render_playground( # pylint: disable=unused-argument
105 self, request: Request
106 ) -> Response:
107 return HTMLResponse(PLAYGROUND_HTML)
108
109 async def graphql_http_server(self, request: Request) -> Response:
110 try:
111 data = await self.extract_data_from_request(request)
112 except HttpError as error:
113 return PlainTextResponse(error.message or error.status, status_code=400)
114
115 context_value = await self.get_context_for_request(request)
116 extensions = await self.get_extensions_for_request(request)
117
118 success, response = await graphql(
119 self.schema,
120 data,
121 context_value=context_value,
122 root_value=self.root_value,
123 debug=self.debug,
124 logger=self.logger,
125 error_formatter=self.error_formatter,
126 extensions=extensions,
127 )
128 status_code = 200 if success else 400
129 return JSONResponse(response, status_code=status_code)
130
131 async def extract_data_from_request(self, request: Request):
132 content_type = request.headers.get("Content-Type", "")
133 content_type = content_type.split(";")[0]
134
135 if content_type == DATA_TYPE_JSON:
136 return await self.extract_data_from_json_request(request)
137 if content_type == DATA_TYPE_MULTIPART:
138 return await self.extract_data_from_multipart_request(request)
139
140 raise HttpBadRequestError(
141 "Posted content must be of type {} or {}".format(
142 DATA_TYPE_JSON, DATA_TYPE_MULTIPART
143 )
144 )
145
146 async def extract_data_from_json_request(self, request: Request):
147 try:
148 return await request.json()
149 except (TypeError, ValueError):
150 raise HttpBadRequestError("Request body is not a valid JSON")
151
152 async def extract_data_from_multipart_request(self, request: Request):
153 try:
154 request_body = await request.form()
155 except ValueError:
156 raise HttpBadRequestError("Request body is not a valid multipart/form-data")
157
158 try:
159 operations = json.loads(request_body.get("operations"))
160 except (TypeError, ValueError):
161 raise HttpBadRequestError(
162 "Request 'operations' multipart field is not a valid JSON"
163 )
164 try:
165 files_map = json.loads(request_body.get("map"))
166 except (TypeError, ValueError):
167 raise HttpBadRequestError(
168 "Request 'map' multipart field is not a valid JSON"
169 )
170
171 request_files = {
172 key: value
173 for key, value in request_body.items()
174 if isinstance(value, UploadFile)
175 }
176
177 return combine_multipart_data(operations, files_map, request_files)
178
179 async def websocket_server(self, websocket: WebSocket) -> None:
180 subscriptions: Dict[str, AsyncGenerator] = {}
181 await websocket.accept("graphql-ws")
182 try:
183 while (
184 websocket.client_state != WebSocketState.DISCONNECTED
185 and websocket.application_state != WebSocketState.DISCONNECTED
186 ):
187 message = await websocket.receive_json()
188 await self.handle_websocket_message(message, websocket, subscriptions)
189 except WebSocketDisconnect:
190 pass
191 finally:
192 for operation_id in subscriptions:
193 await subscriptions[operation_id].aclose()
194
195 async def handle_websocket_message(
196 self,
197 message: dict,
198 websocket: WebSocket,
199 subscriptions: Dict[str, AsyncGenerator],
200 ):
201 operation_id = cast(str, message.get("id"))
202 message_type = cast(str, message.get("type"))
203
204 if message_type == GQL_CONNECTION_INIT:
205 await websocket.send_json({"type": GQL_CONNECTION_ACK})
206 asyncio.ensure_future(self.keep_websocket_alive(websocket))
207 elif message_type == GQL_CONNECTION_TERMINATE:
208 await websocket.close()
209 elif message_type == GQL_START:
210 await self.start_websocket_subscription(
211 message.get("payload"), operation_id, websocket, subscriptions
212 )
213 elif message_type == GQL_STOP:
214 if operation_id in subscriptions:
215 await subscriptions[operation_id].aclose()
216 del subscriptions[operation_id]
217
218 async def keep_websocket_alive(self, websocket: WebSocket):
219 if not self.keepalive:
220 return
221 while websocket.application_state != WebSocketState.DISCONNECTED:
222 try:
223 await websocket.send_json({"type": GQL_CONNECTION_KEEP_ALIVE})
224 except WebSocketDisconnect:
225 return
226 await asyncio.sleep(self.keepalive)
227
228 async def start_websocket_subscription(
229 self,
230 data: Any,
231 operation_id: str,
232 websocket: WebSocket,
233 subscriptions: Dict[str, AsyncGenerator],
234 ):
235 context_value = await self.get_context_for_request(websocket)
236 success, results = await subscribe(
237 self.schema,
238 data,
239 context_value=context_value,
240 root_value=self.root_value,
241 debug=self.debug,
242 logger=self.logger,
243 error_formatter=self.error_formatter,
244 )
245 if not success:
246 results = cast(List[dict], results)
247 await websocket.send_json(
248 {"type": GQL_ERROR, "id": operation_id, "payload": results[0]}
249 )
250 else:
251 results = cast(AsyncGenerator, results)
252 subscriptions[operation_id] = results
253 asyncio.ensure_future(
254 self.observe_async_results(results, operation_id, websocket)
255 )
256
257 async def observe_async_results(
258 self, results: AsyncGenerator, operation_id: str, websocket: WebSocket
259 ) -> None:
260 try:
261 async for result in results:
262 payload = {}
263 if result.data:
264 payload["data"] = result.data
265 if result.errors:
266 for error in result.errors:
267 log_error(error, self.logger)
268 payload["errors"] = [
269 self.error_formatter(error, self.debug)
270 for error in result.errors
271 ]
272 await websocket.send_json(
273 {"type": GQL_DATA, "id": operation_id, "payload": payload}
274 )
275 except Exception as error:
276 if not isinstance(error, GraphQLError):
277 error = GraphQLError(str(error), original_error=error)
278 log_error(error, self.logger)
279 payload = {"errors": [self.error_formatter(error, self.debug)]}
280 await websocket.send_json(
281 {"type": GQL_DATA, "id": operation_id, "payload": payload}
282 )
283
284 if (
285 websocket.client_state != WebSocketState.DISCONNECTED
286 and websocket.application_state != WebSocketState.DISCONNECTED
287 ):
288 await websocket.send_json({"type": GQL_COMPLETE, "id": operation_id})
289
[end of ariadne/asgi.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/ariadne/asgi.py b/ariadne/asgi.py
--- a/ariadne/asgi.py
+++ b/ariadne/asgi.py
@@ -1,5 +1,6 @@
import asyncio
import json
+from inspect import isawaitable
from typing import (
Any,
AsyncGenerator,
@@ -79,7 +80,11 @@
async def get_context_for_request(self, request: Any) -> Any:
if callable(self.context_value):
- return self.context_value(request)
+ context = self.context_value(request)
+ if isawaitable(context):
+ context = await context
+ return context
+
return self.context_value or {"request": request}
async def get_extensions_for_request(self, request: Any) -> ExtensionList:
| {"golden_diff": "diff --git a/ariadne/asgi.py b/ariadne/asgi.py\n--- a/ariadne/asgi.py\n+++ b/ariadne/asgi.py\n@@ -1,5 +1,6 @@\n import asyncio\n import json\n+from inspect import isawaitable\n from typing import (\n Any,\n AsyncGenerator,\n@@ -79,7 +80,11 @@\n \n async def get_context_for_request(self, request: Any) -> Any:\n if callable(self.context_value):\n- return self.context_value(request)\n+ context = self.context_value(request)\n+ if isawaitable(context):\n+ context = await context\n+ return context\n+\n return self.context_value or {\"request\": request}\n \n async def get_extensions_for_request(self, request: Any) -> ExtensionList:\n", "issue": "Async context_value callable is not supported\nOur ASGI GraphQL app supports callable `context_value`, but it doesnt support `async` callable, so it's impossible to do any async work in it like get user form database. \ud83d\ude02\r\n\r\nExample:\r\n\r\n```python\r\nasync def resolve_context(request: Request) -> Dict:\r\n return {\"user\": await get_user_for_request(request)}\r\n\r\n\r\ngraphql_app = GraphQL(schema, context_value=resolve_context)\r\n```\n", "before_files": [{"content": "import asyncio\nimport json\nfrom typing import (\n Any,\n AsyncGenerator,\n Callable,\n Dict,\n List,\n Optional,\n Union,\n Type,\n cast,\n)\n\nfrom graphql import GraphQLError, GraphQLSchema\nfrom graphql.execution import MiddlewareManager\nfrom starlette.datastructures import UploadFile\nfrom starlette.requests import Request\nfrom starlette.responses import HTMLResponse, JSONResponse, PlainTextResponse, Response\nfrom starlette.types import Receive, Scope, Send\nfrom starlette.websockets import WebSocket, WebSocketState, WebSocketDisconnect\n\nfrom .constants import DATA_TYPE_JSON, DATA_TYPE_MULTIPART, PLAYGROUND_HTML\nfrom .exceptions import HttpBadRequestError, HttpError\nfrom .file_uploads import combine_multipart_data\nfrom .format_error import format_error\nfrom .graphql import graphql, subscribe\nfrom .logger import log_error\nfrom .types import ContextValue, ErrorFormatter, Extension, RootValue\n\nGQL_CONNECTION_INIT = \"connection_init\" # Client -> Server\nGQL_CONNECTION_ACK = \"connection_ack\" # Server -> Client\nGQL_CONNECTION_ERROR = \"connection_error\" # Server -> Client\n\n# NOTE: The keep alive message type does not follow the standard due to connection optimizations\nGQL_CONNECTION_KEEP_ALIVE = \"ka\" # Server -> Client\n\nGQL_CONNECTION_TERMINATE = \"connection_terminate\" # Client -> Server\nGQL_START = \"start\" # Client -> Server\nGQL_DATA = \"data\" # Server -> Client\nGQL_ERROR = \"error\" # Server -> Client\nGQL_COMPLETE = \"complete\" # Server -> Client\nGQL_STOP = \"stop\" # Client -> Server\n\nExtensionList = Optional[List[Type[Extension]]]\n\n\nclass GraphQL:\n def __init__(\n self,\n schema: GraphQLSchema,\n *,\n context_value: Optional[ContextValue] = None,\n root_value: Optional[RootValue] = None,\n debug: bool = False,\n logger: Optional[str] = None,\n error_formatter: ErrorFormatter = format_error,\n extensions: Union[Callable[[Any], ExtensionList], ExtensionList] = None,\n middleware: Optional[MiddlewareManager] = None,\n keepalive: float = None,\n ):\n self.context_value = context_value\n self.root_value = root_value\n self.debug = debug\n self.logger = logger\n self.error_formatter = error_formatter\n self.extensions = extensions\n self.middleware = middleware\n self.keepalive = keepalive\n self.schema = schema\n\n async def __call__(self, scope: Scope, receive: Receive, send: Send):\n if scope[\"type\"] == \"http\":\n await self.handle_http(scope=scope, receive=receive, send=send)\n elif scope[\"type\"] == \"websocket\":\n await self.handle_websocket(scope=scope, receive=receive, send=send)\n else:\n raise ValueError(\"Unknown scope type: %r\" % (scope[\"type\"],))\n\n async def get_context_for_request(self, request: Any) -> Any:\n if callable(self.context_value):\n return self.context_value(request)\n return self.context_value or {\"request\": request}\n\n async def get_extensions_for_request(self, request: Any) -> ExtensionList:\n if callable(self.extensions):\n return self.extensions(request)\n return self.extensions\n\n async def handle_http(self, scope: Scope, receive: Receive, send: Send):\n request = Request(scope=scope, receive=receive)\n if request.method == \"GET\":\n response = await self.render_playground(request)\n elif request.method == \"POST\":\n response = await self.graphql_http_server(request)\n else:\n response = Response(status_code=405)\n await response(scope, receive, send)\n\n async def handle_websocket(self, scope: Scope, receive: Receive, send: Send):\n websocket = WebSocket(scope=scope, receive=receive, send=send)\n await self.websocket_server(websocket)\n\n async def render_playground( # pylint: disable=unused-argument\n self, request: Request\n ) -> Response:\n return HTMLResponse(PLAYGROUND_HTML)\n\n async def graphql_http_server(self, request: Request) -> Response:\n try:\n data = await self.extract_data_from_request(request)\n except HttpError as error:\n return PlainTextResponse(error.message or error.status, status_code=400)\n\n context_value = await self.get_context_for_request(request)\n extensions = await self.get_extensions_for_request(request)\n\n success, response = await graphql(\n self.schema,\n data,\n context_value=context_value,\n root_value=self.root_value,\n debug=self.debug,\n logger=self.logger,\n error_formatter=self.error_formatter,\n extensions=extensions,\n )\n status_code = 200 if success else 400\n return JSONResponse(response, status_code=status_code)\n\n async def extract_data_from_request(self, request: Request):\n content_type = request.headers.get(\"Content-Type\", \"\")\n content_type = content_type.split(\";\")[0]\n\n if content_type == DATA_TYPE_JSON:\n return await self.extract_data_from_json_request(request)\n if content_type == DATA_TYPE_MULTIPART:\n return await self.extract_data_from_multipart_request(request)\n\n raise HttpBadRequestError(\n \"Posted content must be of type {} or {}\".format(\n DATA_TYPE_JSON, DATA_TYPE_MULTIPART\n )\n )\n\n async def extract_data_from_json_request(self, request: Request):\n try:\n return await request.json()\n except (TypeError, ValueError):\n raise HttpBadRequestError(\"Request body is not a valid JSON\")\n\n async def extract_data_from_multipart_request(self, request: Request):\n try:\n request_body = await request.form()\n except ValueError:\n raise HttpBadRequestError(\"Request body is not a valid multipart/form-data\")\n\n try:\n operations = json.loads(request_body.get(\"operations\"))\n except (TypeError, ValueError):\n raise HttpBadRequestError(\n \"Request 'operations' multipart field is not a valid JSON\"\n )\n try:\n files_map = json.loads(request_body.get(\"map\"))\n except (TypeError, ValueError):\n raise HttpBadRequestError(\n \"Request 'map' multipart field is not a valid JSON\"\n )\n\n request_files = {\n key: value\n for key, value in request_body.items()\n if isinstance(value, UploadFile)\n }\n\n return combine_multipart_data(operations, files_map, request_files)\n\n async def websocket_server(self, websocket: WebSocket) -> None:\n subscriptions: Dict[str, AsyncGenerator] = {}\n await websocket.accept(\"graphql-ws\")\n try:\n while (\n websocket.client_state != WebSocketState.DISCONNECTED\n and websocket.application_state != WebSocketState.DISCONNECTED\n ):\n message = await websocket.receive_json()\n await self.handle_websocket_message(message, websocket, subscriptions)\n except WebSocketDisconnect:\n pass\n finally:\n for operation_id in subscriptions:\n await subscriptions[operation_id].aclose()\n\n async def handle_websocket_message(\n self,\n message: dict,\n websocket: WebSocket,\n subscriptions: Dict[str, AsyncGenerator],\n ):\n operation_id = cast(str, message.get(\"id\"))\n message_type = cast(str, message.get(\"type\"))\n\n if message_type == GQL_CONNECTION_INIT:\n await websocket.send_json({\"type\": GQL_CONNECTION_ACK})\n asyncio.ensure_future(self.keep_websocket_alive(websocket))\n elif message_type == GQL_CONNECTION_TERMINATE:\n await websocket.close()\n elif message_type == GQL_START:\n await self.start_websocket_subscription(\n message.get(\"payload\"), operation_id, websocket, subscriptions\n )\n elif message_type == GQL_STOP:\n if operation_id in subscriptions:\n await subscriptions[operation_id].aclose()\n del subscriptions[operation_id]\n\n async def keep_websocket_alive(self, websocket: WebSocket):\n if not self.keepalive:\n return\n while websocket.application_state != WebSocketState.DISCONNECTED:\n try:\n await websocket.send_json({\"type\": GQL_CONNECTION_KEEP_ALIVE})\n except WebSocketDisconnect:\n return\n await asyncio.sleep(self.keepalive)\n\n async def start_websocket_subscription(\n self,\n data: Any,\n operation_id: str,\n websocket: WebSocket,\n subscriptions: Dict[str, AsyncGenerator],\n ):\n context_value = await self.get_context_for_request(websocket)\n success, results = await subscribe(\n self.schema,\n data,\n context_value=context_value,\n root_value=self.root_value,\n debug=self.debug,\n logger=self.logger,\n error_formatter=self.error_formatter,\n )\n if not success:\n results = cast(List[dict], results)\n await websocket.send_json(\n {\"type\": GQL_ERROR, \"id\": operation_id, \"payload\": results[0]}\n )\n else:\n results = cast(AsyncGenerator, results)\n subscriptions[operation_id] = results\n asyncio.ensure_future(\n self.observe_async_results(results, operation_id, websocket)\n )\n\n async def observe_async_results(\n self, results: AsyncGenerator, operation_id: str, websocket: WebSocket\n ) -> None:\n try:\n async for result in results:\n payload = {}\n if result.data:\n payload[\"data\"] = result.data\n if result.errors:\n for error in result.errors:\n log_error(error, self.logger)\n payload[\"errors\"] = [\n self.error_formatter(error, self.debug)\n for error in result.errors\n ]\n await websocket.send_json(\n {\"type\": GQL_DATA, \"id\": operation_id, \"payload\": payload}\n )\n except Exception as error:\n if not isinstance(error, GraphQLError):\n error = GraphQLError(str(error), original_error=error)\n log_error(error, self.logger)\n payload = {\"errors\": [self.error_formatter(error, self.debug)]}\n await websocket.send_json(\n {\"type\": GQL_DATA, \"id\": operation_id, \"payload\": payload}\n )\n\n if (\n websocket.client_state != WebSocketState.DISCONNECTED\n and websocket.application_state != WebSocketState.DISCONNECTED\n ):\n await websocket.send_json({\"type\": GQL_COMPLETE, \"id\": operation_id})\n", "path": "ariadne/asgi.py"}]} | 3,582 | 179 |
gh_patches_debug_5434 | rasdani/github-patches | git_diff | secdev__scapy-4403 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Scapy overides platform
Scapy exports the platform name, and could override the platform module. This is likely the issue: https://github.com/secdev/scapy/blob/b0506a1e22321eba41d5c21d26bba418de04bc8f/scapy/consts.py#L10
Here are the example:
```shell
python issue.py
<class 'str'>
<class 'module'>
```
```python
import platform
from scapy.all import *
print(type(platform))
import platform
print(type(platform))
```
</issue>
<code>
[start of scapy/consts.py]
1 # SPDX-License-Identifier: GPL-2.0-only
2 # This file is part of Scapy
3 # See https://scapy.net/ for more information
4 # Copyright (C) Philippe Biondi <[email protected]>
5
6 """
7 This file contains constants
8 """
9
10 from sys import byteorder, platform, maxsize
11 import platform as platform_lib
12
13 LINUX = platform.startswith("linux")
14 OPENBSD = platform.startswith("openbsd")
15 FREEBSD = "freebsd" in platform
16 NETBSD = platform.startswith("netbsd")
17 DARWIN = platform.startswith("darwin")
18 SOLARIS = platform.startswith("sunos")
19 WINDOWS = platform.startswith("win32")
20 WINDOWS_XP = platform_lib.release() == "XP"
21 BSD = DARWIN or FREEBSD or OPENBSD or NETBSD
22 # See https://docs.python.org/3/library/platform.html#cross-platform
23 IS_64BITS = maxsize > 2**32
24 BIG_ENDIAN = byteorder == 'big'
25 # LOOPBACK_NAME moved to conf.loopback_name
26
[end of scapy/consts.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/scapy/consts.py b/scapy/consts.py
--- a/scapy/consts.py
+++ b/scapy/consts.py
@@ -10,6 +10,20 @@
from sys import byteorder, platform, maxsize
import platform as platform_lib
+__all__ = [
+ "LINUX",
+ "OPENBSD",
+ "FREEBSD",
+ "NETBSD",
+ "DARWIN",
+ "SOLARIS",
+ "WINDOWS",
+ "WINDOWS_XP",
+ "BSD",
+ "IS_64BITS",
+ "BIG_ENDIAN",
+]
+
LINUX = platform.startswith("linux")
OPENBSD = platform.startswith("openbsd")
FREEBSD = "freebsd" in platform
| {"golden_diff": "diff --git a/scapy/consts.py b/scapy/consts.py\n--- a/scapy/consts.py\n+++ b/scapy/consts.py\n@@ -10,6 +10,20 @@\n from sys import byteorder, platform, maxsize\n import platform as platform_lib\n \n+__all__ = [\n+ \"LINUX\",\n+ \"OPENBSD\",\n+ \"FREEBSD\",\n+ \"NETBSD\",\n+ \"DARWIN\",\n+ \"SOLARIS\",\n+ \"WINDOWS\",\n+ \"WINDOWS_XP\",\n+ \"BSD\",\n+ \"IS_64BITS\",\n+ \"BIG_ENDIAN\",\n+]\n+\n LINUX = platform.startswith(\"linux\")\n OPENBSD = platform.startswith(\"openbsd\")\n FREEBSD = \"freebsd\" in platform\n", "issue": "Scapy overides platform\nScapy exports the platform name, and could override the platform module. This is likely the issue: https://github.com/secdev/scapy/blob/b0506a1e22321eba41d5c21d26bba418de04bc8f/scapy/consts.py#L10\r\n\r\nHere are the example:\r\n\r\n```shell\r\npython issue.py \r\n<class 'str'>\r\n<class 'module'>\r\n```\r\n\r\n```python\r\nimport platform\r\nfrom scapy.all import *\r\nprint(type(platform))\r\n\r\nimport platform\r\nprint(type(platform))\r\n```\n", "before_files": [{"content": "# SPDX-License-Identifier: GPL-2.0-only\n# This file is part of Scapy\n# See https://scapy.net/ for more information\n# Copyright (C) Philippe Biondi <[email protected]>\n\n\"\"\"\nThis file contains constants\n\"\"\"\n\nfrom sys import byteorder, platform, maxsize\nimport platform as platform_lib\n\nLINUX = platform.startswith(\"linux\")\nOPENBSD = platform.startswith(\"openbsd\")\nFREEBSD = \"freebsd\" in platform\nNETBSD = platform.startswith(\"netbsd\")\nDARWIN = platform.startswith(\"darwin\")\nSOLARIS = platform.startswith(\"sunos\")\nWINDOWS = platform.startswith(\"win32\")\nWINDOWS_XP = platform_lib.release() == \"XP\"\nBSD = DARWIN or FREEBSD or OPENBSD or NETBSD\n# See https://docs.python.org/3/library/platform.html#cross-platform\nIS_64BITS = maxsize > 2**32\nBIG_ENDIAN = byteorder == 'big'\n# LOOPBACK_NAME moved to conf.loopback_name\n", "path": "scapy/consts.py"}]} | 920 | 168 |
gh_patches_debug_2296 | rasdani/github-patches | git_diff | Qiskit__qiskit-5218 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Show pi in the text drawer as π
<!-- ⚠️ If you do not respect this template, your issue will be closed -->
<!-- ⚠️ Make sure to browse the opened and closed issues to confirm this idea does not exist. -->
### What is the expected enhancement?
Based on a discussion in #4931, there's interest in displaying pi in the text drawer as `π `instead of `pi`.
```
┌─────────┐ ┌─────────┐
Change from q_0: ┤ RX(pij) ├ to q_0: ┤ RX(πj) ├
└─────────┘ └─────────┘
```
To do this on all platforms requires completion of #4900 and modifying pi_check and 24 tests.
</issue>
<code>
[start of qiskit/circuit/tools/pi_check.py]
1 # This code is part of Qiskit.
2 #
3 # (C) Copyright IBM 2017, 2019.
4 #
5 # This code is licensed under the Apache License, Version 2.0. You may
6 # obtain a copy of this license in the LICENSE.txt file in the root directory
7 # of this source tree or at http://www.apache.org/licenses/LICENSE-2.0.
8 #
9 # Any modifications or derivative works of this code must retain this
10 # copyright notice, and modified files need to carry a notice indicating
11 # that they have been altered from the originals.
12 # pylint: disable=too-many-return-statements
13
14 """Check if number close to values of PI
15 """
16
17 import numpy as np
18 from qiskit.circuit.parameterexpression import ParameterExpression
19 from qiskit.exceptions import QiskitError
20
21 MAX_FRAC = 16
22 N, D = np.meshgrid(np.arange(1, MAX_FRAC+1), np.arange(1, MAX_FRAC+1))
23 FRAC_MESH = N / D * np.pi
24 RECIP_MESH = N / D / np.pi
25 POW_LIST = np.pi ** np.arange(2, 5)
26
27
28 def pi_check(inpt, eps=1e-6, output='text', ndigits=5):
29 """ Computes if a number is close to an integer
30 fraction or multiple of PI and returns the
31 corresponding string.
32
33 Args:
34 inpt (float): Number to check.
35 eps (float): EPS to check against.
36 output (str): Options are 'text' (default),
37 'latex', 'mpl', and 'qasm'.
38 ndigits (int): Number of digits to print
39 if returning raw inpt.
40
41 Returns:
42 str: string representation of output.
43
44 Raises:
45 QiskitError: if output is not a valid option.
46 """
47 if isinstance(inpt, ParameterExpression):
48 param_str = str(inpt)
49 syms = inpt._symbol_expr.expr_free_symbols
50 for sym in syms:
51 if not sym.is_number:
52 continue
53 pi = pi_check(float(sym), eps=eps, output=output, ndigits=ndigits)
54 try:
55 _ = float(pi)
56 except (ValueError, TypeError):
57 # Strip leading '-' from pi since must replace with abs(sym)
58 # in order to preserve spacing around minuses in expression
59 if pi[0] == '-':
60 pi = pi[1:]
61 param_str = param_str.replace(str(abs(sym)), pi)
62 return param_str
63 elif isinstance(inpt, str):
64 return inpt
65
66 def normalize(single_inpt):
67 if abs(single_inpt) < 1e-14:
68 return '0'
69
70 if output in ['text', 'qasm']:
71 pi = 'pi'
72 elif output == 'latex':
73 pi = '\\pi'
74 elif output == 'mpl':
75 pi = '$\\pi$'
76 else:
77 raise QiskitError('pi_check parameter output should be text, '
78 'latex, mpl, or qasm.')
79
80 neg_str = '-' if single_inpt < 0 else ''
81
82 # First check is for whole multiples of pi
83 val = single_inpt / np.pi
84 if abs(val) >= 1 - eps:
85 if abs(abs(val) - abs(round(val))) < eps:
86 val = int(abs(round(val)))
87 if abs(val) == 1:
88 str_out = '{}{}'.format(neg_str, pi)
89 else:
90 if output == 'qasm':
91 str_out = '{}{}*{}'.format(neg_str, val, pi)
92 else:
93 str_out = '{}{}{}'.format(neg_str, val, pi)
94 return str_out
95
96 # Second is a check for powers of pi
97 if abs(single_inpt) > np.pi:
98 power = np.where(abs(abs(single_inpt) - POW_LIST) < eps)
99 if power[0].shape[0]:
100 if output == 'qasm':
101 str_out = '{:.{}g}'.format(single_inpt, ndigits)
102 elif output == 'latex':
103 str_out = '{}{}^{}'.format(neg_str, pi, power[0][0] + 2)
104 elif output == 'mpl':
105 str_out = '{}{}$^{}$'.format(neg_str, pi, power[0][0] + 2)
106 else:
107 str_out = '{}{}**{}'.format(neg_str, pi, power[0][0] + 2)
108 return str_out
109
110 # Third is a check for a number larger than MAX_FRAC * pi, not a
111 # multiple or power of pi, since no fractions will exceed MAX_FRAC * pi
112 if abs(single_inpt) >= (MAX_FRAC * np.pi):
113 str_out = '{:.{}g}'.format(single_inpt, ndigits)
114 return str_out
115
116 # Fourth check is for fractions for 1*pi in the numer and any
117 # number in the denom.
118 val = np.pi / single_inpt
119 if abs(abs(val) - abs(round(val))) < eps:
120 val = int(abs(round(val)))
121 if output == 'latex':
122 str_out = '\\frac{%s%s}{%s}' % (neg_str, pi, val)
123 else:
124 str_out = '{}{}/{}'.format(neg_str, pi, val)
125 return str_out
126
127 # Fifth check is for fractions where the numer > 1*pi and numer
128 # is up to MAX_FRAC*pi and denom is up to MAX_FRAC and all
129 # fractions are reduced. Ex. 15pi/16, 2pi/5, 15pi/2, 16pi/9.
130 frac = np.where(np.abs(abs(single_inpt) - FRAC_MESH) < eps)
131 if frac[0].shape[0]:
132 numer = int(frac[1][0]) + 1
133 denom = int(frac[0][0]) + 1
134 if output == 'latex':
135 str_out = '\\frac{%s%s%s}{%s}' % (neg_str, numer, pi, denom)
136 elif output == 'qasm':
137 str_out = '{}{}*{}/{}'.format(neg_str, numer, pi, denom)
138 else:
139 str_out = '{}{}{}/{}'.format(neg_str, numer, pi, denom)
140 return str_out
141
142 # Sixth check is for fractions where the numer > 1 and numer
143 # is up to MAX_FRAC and denom is up to MAX_FRAC*pi and all
144 # fractions are reduced. Ex. 15/16pi, 2/5pi, 15/2pi, 16/9pi
145 frac = np.where(np.abs(abs(single_inpt) - RECIP_MESH) < eps)
146 if frac[0].shape[0]:
147 numer = int(frac[1][0]) + 1
148 denom = int(frac[0][0]) + 1
149 if denom == 1 and output != 'qasm':
150 denom = ''
151 if output == 'latex':
152 str_out = '\\frac{%s%s}{%s%s}' % (neg_str, numer, denom, pi)
153 elif output == 'qasm':
154 str_out = '{}{}/({}*{})'.format(neg_str, numer, denom, pi)
155 else:
156 str_out = '{}{}/{}{}'.format(neg_str, numer, denom, pi)
157 return str_out
158
159 # Nothing found
160 str_out = '{:.{}g}'.format(single_inpt, ndigits)
161 return str_out
162
163 complex_inpt = complex(inpt)
164 real, imag = map(normalize, [complex_inpt.real, complex_inpt.imag])
165
166 jstr = '\\jmath' if output == 'latex' else 'j'
167 if real == '0' and imag != '0':
168 str_out = imag + jstr
169 elif real != '0' and imag != '0':
170 op_str = '+'
171 # Remove + if imag negative except for latex fractions
172 if complex_inpt.imag < 0 and (output != 'latex' or '\\frac' not in imag):
173 op_str = ''
174 str_out = '{}{}{}{}'.format(real, op_str, imag, jstr)
175 else:
176 str_out = real
177 return str_out
178
[end of qiskit/circuit/tools/pi_check.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/qiskit/circuit/tools/pi_check.py b/qiskit/circuit/tools/pi_check.py
--- a/qiskit/circuit/tools/pi_check.py
+++ b/qiskit/circuit/tools/pi_check.py
@@ -67,7 +67,9 @@
if abs(single_inpt) < 1e-14:
return '0'
- if output in ['text', 'qasm']:
+ if output == 'text':
+ pi = 'π'
+ elif output == 'qasm':
pi = 'pi'
elif output == 'latex':
pi = '\\pi'
| {"golden_diff": "diff --git a/qiskit/circuit/tools/pi_check.py b/qiskit/circuit/tools/pi_check.py\n--- a/qiskit/circuit/tools/pi_check.py\n+++ b/qiskit/circuit/tools/pi_check.py\n@@ -67,7 +67,9 @@\n if abs(single_inpt) < 1e-14:\n return '0'\n \n- if output in ['text', 'qasm']:\n+ if output == 'text':\n+ pi = '\u03c0'\n+ elif output == 'qasm':\n pi = 'pi'\n elif output == 'latex':\n pi = '\\\\pi'\n", "issue": "Show pi in the text drawer as \u03c0\n<!-- \u26a0\ufe0f If you do not respect this template, your issue will be closed -->\r\n<!-- \u26a0\ufe0f Make sure to browse the opened and closed issues to confirm this idea does not exist. -->\r\n\r\n### What is the expected enhancement?\r\n\r\nBased on a discussion in #4931, there's interest in displaying pi in the text drawer as `\u03c0 `instead of `pi`.\r\n``` \r\n \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510 \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\r\nChange from q_0: \u2524 RX(pij) \u251c to q_0: \u2524 RX(\u03c0j) \u251c\r\n \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518 \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\r\n```\r\nTo do this on all platforms requires completion of #4900 and modifying pi_check and 24 tests.\n", "before_files": [{"content": "# This code is part of Qiskit.\n#\n# (C) Copyright IBM 2017, 2019.\n#\n# This code is licensed under the Apache License, Version 2.0. You may\n# obtain a copy of this license in the LICENSE.txt file in the root directory\n# of this source tree or at http://www.apache.org/licenses/LICENSE-2.0.\n#\n# Any modifications or derivative works of this code must retain this\n# copyright notice, and modified files need to carry a notice indicating\n# that they have been altered from the originals.\n# pylint: disable=too-many-return-statements\n\n\"\"\"Check if number close to values of PI\n\"\"\"\n\nimport numpy as np\nfrom qiskit.circuit.parameterexpression import ParameterExpression\nfrom qiskit.exceptions import QiskitError\n\nMAX_FRAC = 16\nN, D = np.meshgrid(np.arange(1, MAX_FRAC+1), np.arange(1, MAX_FRAC+1))\nFRAC_MESH = N / D * np.pi\nRECIP_MESH = N / D / np.pi\nPOW_LIST = np.pi ** np.arange(2, 5)\n\n\ndef pi_check(inpt, eps=1e-6, output='text', ndigits=5):\n \"\"\" Computes if a number is close to an integer\n fraction or multiple of PI and returns the\n corresponding string.\n\n Args:\n inpt (float): Number to check.\n eps (float): EPS to check against.\n output (str): Options are 'text' (default),\n 'latex', 'mpl', and 'qasm'.\n ndigits (int): Number of digits to print\n if returning raw inpt.\n\n Returns:\n str: string representation of output.\n\n Raises:\n QiskitError: if output is not a valid option.\n \"\"\"\n if isinstance(inpt, ParameterExpression):\n param_str = str(inpt)\n syms = inpt._symbol_expr.expr_free_symbols\n for sym in syms:\n if not sym.is_number:\n continue\n pi = pi_check(float(sym), eps=eps, output=output, ndigits=ndigits)\n try:\n _ = float(pi)\n except (ValueError, TypeError):\n # Strip leading '-' from pi since must replace with abs(sym)\n # in order to preserve spacing around minuses in expression\n if pi[0] == '-':\n pi = pi[1:]\n param_str = param_str.replace(str(abs(sym)), pi)\n return param_str\n elif isinstance(inpt, str):\n return inpt\n\n def normalize(single_inpt):\n if abs(single_inpt) < 1e-14:\n return '0'\n\n if output in ['text', 'qasm']:\n pi = 'pi'\n elif output == 'latex':\n pi = '\\\\pi'\n elif output == 'mpl':\n pi = '$\\\\pi$'\n else:\n raise QiskitError('pi_check parameter output should be text, '\n 'latex, mpl, or qasm.')\n\n neg_str = '-' if single_inpt < 0 else ''\n\n # First check is for whole multiples of pi\n val = single_inpt / np.pi\n if abs(val) >= 1 - eps:\n if abs(abs(val) - abs(round(val))) < eps:\n val = int(abs(round(val)))\n if abs(val) == 1:\n str_out = '{}{}'.format(neg_str, pi)\n else:\n if output == 'qasm':\n str_out = '{}{}*{}'.format(neg_str, val, pi)\n else:\n str_out = '{}{}{}'.format(neg_str, val, pi)\n return str_out\n\n # Second is a check for powers of pi\n if abs(single_inpt) > np.pi:\n power = np.where(abs(abs(single_inpt) - POW_LIST) < eps)\n if power[0].shape[0]:\n if output == 'qasm':\n str_out = '{:.{}g}'.format(single_inpt, ndigits)\n elif output == 'latex':\n str_out = '{}{}^{}'.format(neg_str, pi, power[0][0] + 2)\n elif output == 'mpl':\n str_out = '{}{}$^{}$'.format(neg_str, pi, power[0][0] + 2)\n else:\n str_out = '{}{}**{}'.format(neg_str, pi, power[0][0] + 2)\n return str_out\n\n # Third is a check for a number larger than MAX_FRAC * pi, not a\n # multiple or power of pi, since no fractions will exceed MAX_FRAC * pi\n if abs(single_inpt) >= (MAX_FRAC * np.pi):\n str_out = '{:.{}g}'.format(single_inpt, ndigits)\n return str_out\n\n # Fourth check is for fractions for 1*pi in the numer and any\n # number in the denom.\n val = np.pi / single_inpt\n if abs(abs(val) - abs(round(val))) < eps:\n val = int(abs(round(val)))\n if output == 'latex':\n str_out = '\\\\frac{%s%s}{%s}' % (neg_str, pi, val)\n else:\n str_out = '{}{}/{}'.format(neg_str, pi, val)\n return str_out\n\n # Fifth check is for fractions where the numer > 1*pi and numer\n # is up to MAX_FRAC*pi and denom is up to MAX_FRAC and all\n # fractions are reduced. Ex. 15pi/16, 2pi/5, 15pi/2, 16pi/9.\n frac = np.where(np.abs(abs(single_inpt) - FRAC_MESH) < eps)\n if frac[0].shape[0]:\n numer = int(frac[1][0]) + 1\n denom = int(frac[0][0]) + 1\n if output == 'latex':\n str_out = '\\\\frac{%s%s%s}{%s}' % (neg_str, numer, pi, denom)\n elif output == 'qasm':\n str_out = '{}{}*{}/{}'.format(neg_str, numer, pi, denom)\n else:\n str_out = '{}{}{}/{}'.format(neg_str, numer, pi, denom)\n return str_out\n\n # Sixth check is for fractions where the numer > 1 and numer\n # is up to MAX_FRAC and denom is up to MAX_FRAC*pi and all\n # fractions are reduced. Ex. 15/16pi, 2/5pi, 15/2pi, 16/9pi\n frac = np.where(np.abs(abs(single_inpt) - RECIP_MESH) < eps)\n if frac[0].shape[0]:\n numer = int(frac[1][0]) + 1\n denom = int(frac[0][0]) + 1\n if denom == 1 and output != 'qasm':\n denom = ''\n if output == 'latex':\n str_out = '\\\\frac{%s%s}{%s%s}' % (neg_str, numer, denom, pi)\n elif output == 'qasm':\n str_out = '{}{}/({}*{})'.format(neg_str, numer, denom, pi)\n else:\n str_out = '{}{}/{}{}'.format(neg_str, numer, denom, pi)\n return str_out\n\n # Nothing found\n str_out = '{:.{}g}'.format(single_inpt, ndigits)\n return str_out\n\n complex_inpt = complex(inpt)\n real, imag = map(normalize, [complex_inpt.real, complex_inpt.imag])\n\n jstr = '\\\\jmath' if output == 'latex' else 'j'\n if real == '0' and imag != '0':\n str_out = imag + jstr\n elif real != '0' and imag != '0':\n op_str = '+'\n # Remove + if imag negative except for latex fractions\n if complex_inpt.imag < 0 and (output != 'latex' or '\\\\frac' not in imag):\n op_str = ''\n str_out = '{}{}{}{}'.format(real, op_str, imag, jstr)\n else:\n str_out = real\n return str_out\n", "path": "qiskit/circuit/tools/pi_check.py"}]} | 2,969 | 136 |
gh_patches_debug_22411 | rasdani/github-patches | git_diff | wagtail__wagtail-730 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Allow use of MPO formatted JPEG images
Just tried loading some JPEG images into a website and was given an error "Not a valid JPEG image please use blah blah".
The images were from my Nikon D3300 which seems to create JPEG files in MPO format. This format is supported by Pillow but Wagtail is blocking them from being uploaded. I disabled the format validation and everything seemed to work fine.
</issue>
<code>
[start of wagtail/wagtailimages/fields.py]
1 import os
2
3 from PIL import Image
4
5 from django.forms.fields import ImageField
6 from django.core.exceptions import ValidationError
7 from django.utils.translation import ugettext_lazy as _
8 from django.template.defaultfilters import filesizeformat
9 from django.conf import settings
10
11
12 ALLOWED_EXTENSIONS = ['gif', 'jpg', 'jpeg', 'png']
13 SUPPORTED_FORMATS_TEXT = _("GIF, JPEG, PNG")
14
15 INVALID_IMAGE_ERROR = _(
16 "Not a supported image format. Supported formats: %s."
17 ) % SUPPORTED_FORMATS_TEXT
18
19 INVALID_IMAGE_KNOWN_FORMAT_ERROR = _(
20 "Not a valid %s image."
21 )
22
23 MAX_UPLOAD_SIZE = getattr(settings, 'WAGTAILIMAGES_MAX_UPLOAD_SIZE', 10 * 1024 * 1024)
24
25 if MAX_UPLOAD_SIZE is not None:
26 MAX_UPLOAD_SIZE_TEXT = filesizeformat(MAX_UPLOAD_SIZE)
27
28 FILE_TOO_LARGE_ERROR = _(
29 "This file is too big. Maximum filesize %s."
30 ) % (MAX_UPLOAD_SIZE_TEXT, )
31
32 FILE_TOO_LARGE_KNOWN_SIZE_ERROR = _(
33 "This file is too big (%%s). Maximum filesize %s."
34 ) % (MAX_UPLOAD_SIZE_TEXT, )
35
36 IMAGE_FIELD_HELP_TEXT = _(
37 "Supported formats: %s. Maximum filesize: %s."
38 ) % (SUPPORTED_FORMATS_TEXT, MAX_UPLOAD_SIZE_TEXT, )
39 else:
40 MAX_UPLOAD_SIZE_TEXT = ""
41 FILE_TOO_LARGE_ERROR = ""
42 FILE_TOO_LARGE_KNOWN_SIZE_ERROR = ""
43
44 IMAGE_FIELD_HELP_TEXT = _(
45 "Supported formats: %s."
46 ) % (SUPPORTED_FORMATS_TEXT, )
47
48
49 class WagtailImageField(ImageField):
50 default_error_messages = {
51 'invalid_image': INVALID_IMAGE_ERROR,
52 'invalid_image_known_format': INVALID_IMAGE_KNOWN_FORMAT_ERROR,
53 'file_too_large': FILE_TOO_LARGE_KNOWN_SIZE_ERROR,
54 }
55
56 def __init__(self, *args, **kwargs):
57 super(WagtailImageField, self).__init__(*args, **kwargs)
58
59 self.help_text = IMAGE_FIELD_HELP_TEXT
60
61 def check_image_file_format(self, f):
62 # Check file extension
63 extension = os.path.splitext(f.name)[1].lower()[1:]
64
65 if extension not in ALLOWED_EXTENSIONS:
66 raise ValidationError(self.error_messages['invalid_image'], code='invalid_image')
67
68 if hasattr(f, 'image'):
69 # Django 1.8 annotates the file object with the PIL image
70 image = f.image
71 elif not f.closed:
72 # Open image file
73 file_position = f.tell()
74 f.seek(0)
75
76 try:
77 image = Image.open(f)
78 except IOError:
79 # Uploaded file is not even an image file (or corrupted)
80 raise ValidationError(self.error_messages['invalid_image_known_format'],
81 code='invalid_image_known_format')
82
83 f.seek(file_position)
84 else:
85 # Couldn't get the PIL image, skip checking the internal file format
86 return
87
88 image_format = extension
89 if extension == 'jpg':
90 image_format = 'jpeg'
91
92 # Check that the internal format matches the extension
93 # It is possible to upload PSD files if their extension is set to jpg, png or gif. This should catch them out
94 if image.format.upper() != image_format.upper():
95 raise ValidationError(self.error_messages['invalid_image_known_format'] % (
96 image_format.upper()
97 ), code='invalid_image_known_format')
98
99 def check_image_file_size(self, f):
100 # Upload size checking can be disabled by setting max upload size to None
101 if MAX_UPLOAD_SIZE is None:
102 return
103
104 # Check the filesize
105 if f.size > MAX_UPLOAD_SIZE:
106 raise ValidationError(self.error_messages['file_too_large'] % (
107 filesizeformat(f.size),
108 ), code='file_too_large')
109
110 def to_python(self, data):
111 f = super(WagtailImageField, self).to_python(data)
112
113 if f is not None:
114 self.check_image_file_size(f)
115 self.check_image_file_format(f)
116
117 return f
118
[end of wagtail/wagtailimages/fields.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/wagtail/wagtailimages/fields.py b/wagtail/wagtailimages/fields.py
--- a/wagtail/wagtailimages/fields.py
+++ b/wagtail/wagtailimages/fields.py
@@ -85,15 +85,19 @@
# Couldn't get the PIL image, skip checking the internal file format
return
- image_format = extension
- if extension == 'jpg':
- image_format = 'jpeg'
+ image_format = extension.upper()
+ if image_format == 'JPG':
+ image_format = 'JPEG'
+
+ internal_image_format = image.format.upper()
+ if internal_image_format == 'MPO':
+ internal_image_format = 'JPEG'
# Check that the internal format matches the extension
# It is possible to upload PSD files if their extension is set to jpg, png or gif. This should catch them out
- if image.format.upper() != image_format.upper():
+ if internal_image_format != image_format:
raise ValidationError(self.error_messages['invalid_image_known_format'] % (
- image_format.upper()
+ image_format,
), code='invalid_image_known_format')
def check_image_file_size(self, f):
| {"golden_diff": "diff --git a/wagtail/wagtailimages/fields.py b/wagtail/wagtailimages/fields.py\n--- a/wagtail/wagtailimages/fields.py\n+++ b/wagtail/wagtailimages/fields.py\n@@ -85,15 +85,19 @@\n # Couldn't get the PIL image, skip checking the internal file format\n return\n \n- image_format = extension\n- if extension == 'jpg':\n- image_format = 'jpeg'\n+ image_format = extension.upper()\n+ if image_format == 'JPG':\n+ image_format = 'JPEG'\n+\n+ internal_image_format = image.format.upper()\n+ if internal_image_format == 'MPO':\n+ internal_image_format = 'JPEG'\n \n # Check that the internal format matches the extension\n # It is possible to upload PSD files if their extension is set to jpg, png or gif. This should catch them out\n- if image.format.upper() != image_format.upper():\n+ if internal_image_format != image_format:\n raise ValidationError(self.error_messages['invalid_image_known_format'] % (\n- image_format.upper()\n+ image_format,\n ), code='invalid_image_known_format')\n \n def check_image_file_size(self, f):\n", "issue": "Allow use of MPO formatted JPEG images\nJust tried loading some JPEG images into a website and was given an error \"Not a valid JPEG image please use blah blah\".\n\nThe images were from my Nikon D3300 which seems to create JPEG files in MPO format. This format is supported by Pillow but Wagtail is blocking them from being uploaded. I disabled the format validation and everything seemed to work fine.\n\n", "before_files": [{"content": "import os\n\nfrom PIL import Image\n\nfrom django.forms.fields import ImageField\nfrom django.core.exceptions import ValidationError\nfrom django.utils.translation import ugettext_lazy as _\nfrom django.template.defaultfilters import filesizeformat\nfrom django.conf import settings\n\n\nALLOWED_EXTENSIONS = ['gif', 'jpg', 'jpeg', 'png']\nSUPPORTED_FORMATS_TEXT = _(\"GIF, JPEG, PNG\")\n\nINVALID_IMAGE_ERROR = _(\n \"Not a supported image format. Supported formats: %s.\"\n) % SUPPORTED_FORMATS_TEXT\n\nINVALID_IMAGE_KNOWN_FORMAT_ERROR = _(\n \"Not a valid %s image.\"\n)\n\nMAX_UPLOAD_SIZE = getattr(settings, 'WAGTAILIMAGES_MAX_UPLOAD_SIZE', 10 * 1024 * 1024)\n\nif MAX_UPLOAD_SIZE is not None:\n MAX_UPLOAD_SIZE_TEXT = filesizeformat(MAX_UPLOAD_SIZE)\n\n FILE_TOO_LARGE_ERROR = _(\n \"This file is too big. Maximum filesize %s.\"\n ) % (MAX_UPLOAD_SIZE_TEXT, )\n\n FILE_TOO_LARGE_KNOWN_SIZE_ERROR = _(\n \"This file is too big (%%s). Maximum filesize %s.\"\n ) % (MAX_UPLOAD_SIZE_TEXT, )\n\n IMAGE_FIELD_HELP_TEXT = _(\n \"Supported formats: %s. Maximum filesize: %s.\"\n ) % (SUPPORTED_FORMATS_TEXT, MAX_UPLOAD_SIZE_TEXT, )\nelse:\n MAX_UPLOAD_SIZE_TEXT = \"\"\n FILE_TOO_LARGE_ERROR = \"\"\n FILE_TOO_LARGE_KNOWN_SIZE_ERROR = \"\"\n\n IMAGE_FIELD_HELP_TEXT = _(\n \"Supported formats: %s.\"\n ) % (SUPPORTED_FORMATS_TEXT, )\n\n\nclass WagtailImageField(ImageField):\n default_error_messages = {\n 'invalid_image': INVALID_IMAGE_ERROR,\n 'invalid_image_known_format': INVALID_IMAGE_KNOWN_FORMAT_ERROR,\n 'file_too_large': FILE_TOO_LARGE_KNOWN_SIZE_ERROR,\n }\n\n def __init__(self, *args, **kwargs):\n super(WagtailImageField, self).__init__(*args, **kwargs)\n\n self.help_text = IMAGE_FIELD_HELP_TEXT\n\n def check_image_file_format(self, f):\n # Check file extension\n extension = os.path.splitext(f.name)[1].lower()[1:]\n\n if extension not in ALLOWED_EXTENSIONS:\n raise ValidationError(self.error_messages['invalid_image'], code='invalid_image')\n\n if hasattr(f, 'image'):\n # Django 1.8 annotates the file object with the PIL image\n image = f.image\n elif not f.closed:\n # Open image file\n file_position = f.tell()\n f.seek(0)\n\n try:\n image = Image.open(f)\n except IOError:\n # Uploaded file is not even an image file (or corrupted)\n raise ValidationError(self.error_messages['invalid_image_known_format'],\n code='invalid_image_known_format')\n\n f.seek(file_position)\n else:\n # Couldn't get the PIL image, skip checking the internal file format\n return\n\n image_format = extension\n if extension == 'jpg':\n image_format = 'jpeg'\n\n # Check that the internal format matches the extension\n # It is possible to upload PSD files if their extension is set to jpg, png or gif. This should catch them out\n if image.format.upper() != image_format.upper():\n raise ValidationError(self.error_messages['invalid_image_known_format'] % (\n image_format.upper()\n ), code='invalid_image_known_format')\n\n def check_image_file_size(self, f):\n # Upload size checking can be disabled by setting max upload size to None\n if MAX_UPLOAD_SIZE is None:\n return\n\n # Check the filesize\n if f.size > MAX_UPLOAD_SIZE:\n raise ValidationError(self.error_messages['file_too_large'] % (\n filesizeformat(f.size),\n ), code='file_too_large')\n\n def to_python(self, data):\n f = super(WagtailImageField, self).to_python(data)\n\n if f is not None:\n self.check_image_file_size(f)\n self.check_image_file_format(f)\n\n return f\n", "path": "wagtail/wagtailimages/fields.py"}]} | 1,753 | 271 |
gh_patches_debug_14539 | rasdani/github-patches | git_diff | cloudtools__troposphere-1589 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add support for DataLocationResource & TableWithColumnsResource in AWS::LakeFormation::Permissions (2020, Jan 16 update)
waiting for the doc to be updated
</issue>
<code>
[start of troposphere/lakeformation.py]
1 # Copyright (c) 2012-2019, Mark Peek <[email protected]>
2 # All rights reserved.
3 #
4 # See LICENSE file for full license.
5 #
6 # *** Do not modify - this file is autogenerated ***
7 # Resource specification version: 5.3.0
8
9
10 from . import AWSObject
11 from . import AWSProperty
12
13
14 class Admins(AWSProperty):
15 props = {
16 }
17
18
19 class DataLakeSettings(AWSObject):
20 resource_type = "AWS::LakeFormation::DataLakeSettings"
21
22 props = {
23 'Admins': (Admins, False),
24 }
25
26
27 class DataLakePrincipal(AWSProperty):
28 props = {
29 'DataLakePrincipalIdentifier': (basestring, False),
30 }
31
32
33 class DatabaseResource(AWSProperty):
34 props = {
35 'Name': (basestring, False),
36 }
37
38
39 class TableResource(AWSProperty):
40 props = {
41 'DatabaseName': (basestring, False),
42 'Name': (basestring, False),
43 }
44
45
46 class Resource(AWSProperty):
47 props = {
48 'DatabaseResource': (DatabaseResource, False),
49 'TableResource': (TableResource, False),
50 }
51
52
53 class Permissions(AWSObject):
54 resource_type = "AWS::LakeFormation::Permissions"
55
56 props = {
57 'DataLakePrincipal': (DataLakePrincipal, True),
58 'Permissions': ([basestring], False),
59 'PermissionsWithGrantOption': ([basestring], False),
60 'Resource': (Resource, True),
61 }
62
[end of troposphere/lakeformation.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/troposphere/lakeformation.py b/troposphere/lakeformation.py
--- a/troposphere/lakeformation.py
+++ b/troposphere/lakeformation.py
@@ -43,10 +43,33 @@
}
+class DataLocationResource(AWSProperty):
+ props = {
+ 'S3Resource': (basestring, False),
+ }
+
+
+class ColumnWildcard(AWSProperty):
+ props = {
+ 'ExcludedColumnNames': ([basestring], False),
+ }
+
+
+class TableWithColumnsResource(AWSProperty):
+ props = {
+ 'ColumnNames': ([basestring], False),
+ 'ColumnWildcard': (ColumnWildcard, False),
+ 'DatabaseName': (basestring, False),
+ 'Name': (basestring, False),
+ }
+
+
class Resource(AWSProperty):
props = {
'DatabaseResource': (DatabaseResource, False),
+ 'DataLocationResource': (DataLocationResource, False),
'TableResource': (TableResource, False),
+ 'TableWithColumnsResource': (TableWithColumnsResource, False),
}
| {"golden_diff": "diff --git a/troposphere/lakeformation.py b/troposphere/lakeformation.py\n--- a/troposphere/lakeformation.py\n+++ b/troposphere/lakeformation.py\n@@ -43,10 +43,33 @@\n }\n \n \n+class DataLocationResource(AWSProperty):\n+ props = {\n+ 'S3Resource': (basestring, False),\n+ }\n+\n+\n+class ColumnWildcard(AWSProperty):\n+ props = {\n+ 'ExcludedColumnNames': ([basestring], False),\n+ }\n+\n+\n+class TableWithColumnsResource(AWSProperty):\n+ props = {\n+ 'ColumnNames': ([basestring], False),\n+ 'ColumnWildcard': (ColumnWildcard, False),\n+ 'DatabaseName': (basestring, False),\n+ 'Name': (basestring, False),\n+ }\n+\n+\n class Resource(AWSProperty):\n props = {\n 'DatabaseResource': (DatabaseResource, False),\n+ 'DataLocationResource': (DataLocationResource, False),\n 'TableResource': (TableResource, False),\n+ 'TableWithColumnsResource': (TableWithColumnsResource, False),\n }\n", "issue": "Add support for DataLocationResource & TableWithColumnsResource in AWS::LakeFormation::Permissions (2020, Jan 16 update)\nwaiting for the doc to be updated\n", "before_files": [{"content": "# Copyright (c) 2012-2019, Mark Peek <[email protected]>\n# All rights reserved.\n#\n# See LICENSE file for full license.\n#\n# *** Do not modify - this file is autogenerated ***\n# Resource specification version: 5.3.0\n\n\nfrom . import AWSObject\nfrom . import AWSProperty\n\n\nclass Admins(AWSProperty):\n props = {\n }\n\n\nclass DataLakeSettings(AWSObject):\n resource_type = \"AWS::LakeFormation::DataLakeSettings\"\n\n props = {\n 'Admins': (Admins, False),\n }\n\n\nclass DataLakePrincipal(AWSProperty):\n props = {\n 'DataLakePrincipalIdentifier': (basestring, False),\n }\n\n\nclass DatabaseResource(AWSProperty):\n props = {\n 'Name': (basestring, False),\n }\n\n\nclass TableResource(AWSProperty):\n props = {\n 'DatabaseName': (basestring, False),\n 'Name': (basestring, False),\n }\n\n\nclass Resource(AWSProperty):\n props = {\n 'DatabaseResource': (DatabaseResource, False),\n 'TableResource': (TableResource, False),\n }\n\n\nclass Permissions(AWSObject):\n resource_type = \"AWS::LakeFormation::Permissions\"\n\n props = {\n 'DataLakePrincipal': (DataLakePrincipal, True),\n 'Permissions': ([basestring], False),\n 'PermissionsWithGrantOption': ([basestring], False),\n 'Resource': (Resource, True),\n }\n", "path": "troposphere/lakeformation.py"}]} | 1,021 | 252 |
gh_patches_debug_35727 | rasdani/github-patches | git_diff | CTFd__CTFd-319 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Awards is not accounted in `user.place()`
[`user.place()`][user_place] is not accounting awards while [`get_standings()`][get_standings] does. This causes different ordering in scoreboard and team profile. Is this by design?
[user_place]: https://github.com/CTFd/CTFd/blob/master/CTFd/models.py#L200
[get_standings]: https://github.com/CTFd/CTFd/blob/master/CTFd/scoreboard.py#L11
</issue>
<code>
[start of CTFd/models.py]
1 import datetime
2 import hashlib
3 import json
4 import netaddr
5 from socket import inet_pton, inet_ntop, AF_INET, AF_INET6
6 from struct import unpack, pack, error as struct_error
7
8 from flask_sqlalchemy import SQLAlchemy
9 from passlib.hash import bcrypt_sha256
10 from sqlalchemy.exc import DatabaseError
11
12
13 def sha512(string):
14 return str(hashlib.sha512(string).hexdigest())
15
16
17 def ip2long(ip):
18 '''Converts a user's IP address into an integer/long'''
19 return int(netaddr.IPAddress(ip))
20
21
22 def long2ip(ip_int):
23 '''Converts a saved integer/long back into an IP address'''
24 return str(netaddr.IPAddress(ip_int))
25
26
27 db = SQLAlchemy()
28
29
30 class Pages(db.Model):
31 id = db.Column(db.Integer, primary_key=True)
32 route = db.Column(db.String(80), unique=True)
33 html = db.Column(db.Text)
34
35 def __init__(self, route, html):
36 self.route = route
37 self.html = html
38
39 def __repr__(self):
40 return "<Pages route {0}>".format(self.route)
41
42
43 class Containers(db.Model):
44 id = db.Column(db.Integer, primary_key=True)
45 name = db.Column(db.String(80))
46 buildfile = db.Column(db.Text)
47
48 def __init__(self, name, buildfile):
49 self.name = name
50 self.buildfile = buildfile
51
52 def __repr__(self):
53 return "<Container ID:(0) {1}>".format(self.id, self.name)
54
55
56 class Challenges(db.Model):
57 id = db.Column(db.Integer, primary_key=True)
58 name = db.Column(db.String(80))
59 description = db.Column(db.Text)
60 max_attempts = db.Column(db.Integer, default=0)
61 value = db.Column(db.Integer)
62 category = db.Column(db.String(80))
63 type = db.Column(db.Integer)
64 hidden = db.Column(db.Boolean)
65
66 def __init__(self, name, description, value, category, type=0):
67 self.name = name
68 self.description = description
69 self.value = value
70 self.category = category
71 self.type = type
72 # self.flags = json.dumps(flags)
73
74 def __repr__(self):
75 return '<chal %r>' % self.name
76
77
78 class Hints(db.Model):
79 id = db.Column(db.Integer, primary_key=True)
80 type = db.Column(db.Integer, default=0)
81 chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))
82 hint = db.Column(db.Text)
83 cost = db.Column(db.Integer, default=0)
84
85 def __init__(self, chal, hint, cost=0, type=0):
86 self.chal = chal
87 self.hint = hint
88 self.cost = cost
89 self.type = type
90
91 def __repr__(self):
92 return '<hint %r>' % self.hint
93
94
95 class Awards(db.Model):
96 id = db.Column(db.Integer, primary_key=True)
97 teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))
98 name = db.Column(db.String(80))
99 description = db.Column(db.Text)
100 date = db.Column(db.DateTime, default=datetime.datetime.utcnow)
101 value = db.Column(db.Integer)
102 category = db.Column(db.String(80))
103 icon = db.Column(db.Text)
104
105 def __init__(self, teamid, name, value):
106 self.teamid = teamid
107 self.name = name
108 self.value = value
109
110 def __repr__(self):
111 return '<award %r>' % self.name
112
113
114 class Tags(db.Model):
115 id = db.Column(db.Integer, primary_key=True)
116 chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))
117 tag = db.Column(db.String(80))
118
119 def __init__(self, chal, tag):
120 self.chal = chal
121 self.tag = tag
122
123 def __repr__(self):
124 return "<Tag {0} for challenge {1}>".format(self.tag, self.chal)
125
126
127 class Files(db.Model):
128 id = db.Column(db.Integer, primary_key=True)
129 chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))
130 location = db.Column(db.Text)
131
132 def __init__(self, chal, location):
133 self.chal = chal
134 self.location = location
135
136 def __repr__(self):
137 return "<File {0} for challenge {1}>".format(self.location, self.chal)
138
139
140 class Keys(db.Model):
141 id = db.Column(db.Integer, primary_key=True)
142 chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))
143 key_type = db.Column(db.Integer)
144 flag = db.Column(db.Text)
145 data = db.Column(db.Text)
146
147 def __init__(self, chal, flag, key_type):
148 self.chal = chal
149 self.flag = flag
150 self.key_type = key_type
151
152 def __repr__(self):
153 return "<Flag {0} for challenge {1}>".format(self.flag, self.chal)
154
155
156 class Teams(db.Model):
157 id = db.Column(db.Integer, primary_key=True)
158 name = db.Column(db.String(128), unique=True)
159 email = db.Column(db.String(128), unique=True)
160 password = db.Column(db.String(128))
161 website = db.Column(db.String(128))
162 affiliation = db.Column(db.String(128))
163 country = db.Column(db.String(32))
164 bracket = db.Column(db.String(32))
165 banned = db.Column(db.Boolean, default=False)
166 verified = db.Column(db.Boolean, default=False)
167 admin = db.Column(db.Boolean, default=False)
168 joined = db.Column(db.DateTime, default=datetime.datetime.utcnow)
169
170 def __init__(self, name, email, password):
171 self.name = name
172 self.email = email
173 self.password = bcrypt_sha256.encrypt(str(password))
174
175 def __repr__(self):
176 return '<team %r>' % self.name
177
178 def score(self, admin=False):
179 score = db.func.sum(Challenges.value).label('score')
180 team = db.session.query(Solves.teamid, score).join(Teams).join(Challenges).filter(Teams.banned == False, Teams.id == self.id)
181 award_score = db.func.sum(Awards.value).label('award_score')
182 award = db.session.query(award_score).filter_by(teamid=self.id)
183
184 if not admin:
185 freeze = Config.query.filter_by(key='freeze').first()
186 if freeze and freeze.value:
187 freeze = int(freeze.value)
188 freeze = datetime.datetime.utcfromtimestamp(freeze)
189 team = team.filter(Solves.date < freeze)
190 award = award.filter(Awards.date < freeze)
191
192 team = team.group_by(Solves.teamid).first()
193 award = award.first()
194
195 if team:
196 return int(team.score or 0) + int(award.award_score or 0)
197 else:
198 return 0
199
200 def place(self, admin=False):
201 score = db.func.sum(Challenges.value).label('score')
202 quickest = db.func.max(Solves.date).label('quickest')
203 teams = db.session.query(Solves.teamid).join(Teams).join(Challenges).filter(Teams.banned == False)
204
205 if not admin:
206 freeze = Config.query.filter_by(key='freeze').first()
207 if freeze and freeze.value:
208 freeze = int(freeze.value)
209 freeze = datetime.datetime.utcfromtimestamp(freeze)
210 teams = teams.filter(Solves.date < freeze)
211
212 teams = teams.group_by(Solves.teamid).order_by(score.desc(), quickest).all()
213
214 # http://codegolf.stackexchange.com/a/4712
215 try:
216 i = teams.index((self.id,)) + 1
217 k = i % 10
218 return "%d%s" % (i, "tsnrhtdd"[(i / 10 % 10 != 1) * (k < 4) * k::4])
219 except ValueError:
220 return 0
221
222
223 class Solves(db.Model):
224 __table_args__ = (db.UniqueConstraint('chalid', 'teamid'), {})
225 id = db.Column(db.Integer, primary_key=True)
226 chalid = db.Column(db.Integer, db.ForeignKey('challenges.id'))
227 teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))
228 ip = db.Column(db.String(46))
229 flag = db.Column(db.Text)
230 date = db.Column(db.DateTime, default=datetime.datetime.utcnow)
231 team = db.relationship('Teams', foreign_keys="Solves.teamid", lazy='joined')
232 chal = db.relationship('Challenges', foreign_keys="Solves.chalid", lazy='joined')
233 # value = db.Column(db.Integer)
234
235 def __init__(self, teamid, chalid, ip, flag):
236 self.ip = ip
237 self.chalid = chalid
238 self.teamid = teamid
239 self.flag = flag
240 # self.value = value
241
242 def __repr__(self):
243 return '<solve {}, {}, {}, {}>'.format(self.teamid, self.chalid, self.ip, self.flag)
244
245
246 class WrongKeys(db.Model):
247 id = db.Column(db.Integer, primary_key=True)
248 chalid = db.Column(db.Integer, db.ForeignKey('challenges.id'))
249 teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))
250 ip = db.Column(db.String(46))
251 date = db.Column(db.DateTime, default=datetime.datetime.utcnow)
252 flag = db.Column(db.Text)
253 chal = db.relationship('Challenges', foreign_keys="WrongKeys.chalid", lazy='joined')
254
255 def __init__(self, teamid, chalid, ip, flag):
256 self.ip = ip
257 self.teamid = teamid
258 self.chalid = chalid
259 self.flag = flag
260
261 def __repr__(self):
262 return '<wrong {}, {}, {}, {}>'.format(self.teamid, self.chalid, self.ip, self.flag)
263
264
265 class Unlocks(db.Model):
266 id = db.Column(db.Integer, primary_key=True)
267 teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))
268 date = db.Column(db.DateTime, default=datetime.datetime.utcnow)
269 itemid = db.Column(db.Integer)
270 model = db.Column(db.String(32))
271
272 def __init__(self, model, teamid, itemid):
273 self.model = model
274 self.teamid = teamid
275 self.itemid = itemid
276
277 def __repr__(self):
278 return '<unlock %r>' % self.teamid
279
280
281 class Tracking(db.Model):
282 id = db.Column(db.Integer, primary_key=True)
283 ip = db.Column(db.String(46))
284 team = db.Column(db.Integer, db.ForeignKey('teams.id'))
285 date = db.Column(db.DateTime, default=datetime.datetime.utcnow)
286
287 def __init__(self, ip, team):
288 self.ip = ip
289 self.team = team
290
291 def __repr__(self):
292 return '<ip %r>' % self.team
293
294
295 class Config(db.Model):
296 id = db.Column(db.Integer, primary_key=True)
297 key = db.Column(db.Text)
298 value = db.Column(db.Text)
299
300 def __init__(self, key, value):
301 self.key = key
302 self.value = value
303
[end of CTFd/models.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/CTFd/models.py b/CTFd/models.py
--- a/CTFd/models.py
+++ b/CTFd/models.py
@@ -8,6 +8,7 @@
from flask_sqlalchemy import SQLAlchemy
from passlib.hash import bcrypt_sha256
from sqlalchemy.exc import DatabaseError
+from sqlalchemy.sql.expression import union_all
def sha512(string):
@@ -198,22 +199,44 @@
return 0
def place(self, admin=False):
- score = db.func.sum(Challenges.value).label('score')
- quickest = db.func.max(Solves.date).label('quickest')
- teams = db.session.query(Solves.teamid).join(Teams).join(Challenges).filter(Teams.banned == False)
+ scores = db.session.query(
+ Solves.teamid.label('teamid'),
+ db.func.sum(Challenges.value).label('score'),
+ db.func.max(Solves.date).label('date')
+ ).join(Challenges).group_by(Solves.teamid)
+
+ awards = db.session.query(
+ Awards.teamid.label('teamid'),
+ db.func.sum(Awards.value).label('score'),
+ db.func.max(Awards.date).label('date')
+ ).group_by(Awards.teamid)
if not admin:
freeze = Config.query.filter_by(key='freeze').first()
if freeze and freeze.value:
freeze = int(freeze.value)
freeze = datetime.datetime.utcfromtimestamp(freeze)
- teams = teams.filter(Solves.date < freeze)
+ scores = scores.filter(Solves.date < freeze)
+ awards = awards.filter(Awards.date < freeze)
+
+ results = union_all(scores, awards).alias('results')
+
+ sumscore = db.func.sum(results.columns.score).label('sumscore')
+ quickest = db.func.max(results.columns.date).label('quickest')
+
+ standings_query = db.session.query(results.columns.teamid)\
+ .join(Teams)\
+ .group_by(results.columns.teamid)\
+ .order_by(sumscore.desc(), quickest)
+
+ if not admin:
+ standings_query = standings_query.filter(Teams.banned == False)
- teams = teams.group_by(Solves.teamid).order_by(score.desc(), quickest).all()
+ standings = standings_query.all()
# http://codegolf.stackexchange.com/a/4712
try:
- i = teams.index((self.id,)) + 1
+ i = standings.index((self.id,)) + 1
k = i % 10
return "%d%s" % (i, "tsnrhtdd"[(i / 10 % 10 != 1) * (k < 4) * k::4])
except ValueError:
| {"golden_diff": "diff --git a/CTFd/models.py b/CTFd/models.py\n--- a/CTFd/models.py\n+++ b/CTFd/models.py\n@@ -8,6 +8,7 @@\n from flask_sqlalchemy import SQLAlchemy\n from passlib.hash import bcrypt_sha256\n from sqlalchemy.exc import DatabaseError\n+from sqlalchemy.sql.expression import union_all\n \n \n def sha512(string):\n@@ -198,22 +199,44 @@\n return 0\n \n def place(self, admin=False):\n- score = db.func.sum(Challenges.value).label('score')\n- quickest = db.func.max(Solves.date).label('quickest')\n- teams = db.session.query(Solves.teamid).join(Teams).join(Challenges).filter(Teams.banned == False)\n+ scores = db.session.query(\n+ Solves.teamid.label('teamid'),\n+ db.func.sum(Challenges.value).label('score'),\n+ db.func.max(Solves.date).label('date')\n+ ).join(Challenges).group_by(Solves.teamid)\n+\n+ awards = db.session.query(\n+ Awards.teamid.label('teamid'),\n+ db.func.sum(Awards.value).label('score'),\n+ db.func.max(Awards.date).label('date')\n+ ).group_by(Awards.teamid)\n \n if not admin:\n freeze = Config.query.filter_by(key='freeze').first()\n if freeze and freeze.value:\n freeze = int(freeze.value)\n freeze = datetime.datetime.utcfromtimestamp(freeze)\n- teams = teams.filter(Solves.date < freeze)\n+ scores = scores.filter(Solves.date < freeze)\n+ awards = awards.filter(Awards.date < freeze)\n+\n+ results = union_all(scores, awards).alias('results')\n+\n+ sumscore = db.func.sum(results.columns.score).label('sumscore')\n+ quickest = db.func.max(results.columns.date).label('quickest')\n+\n+ standings_query = db.session.query(results.columns.teamid)\\\n+ .join(Teams)\\\n+ .group_by(results.columns.teamid)\\\n+ .order_by(sumscore.desc(), quickest)\n+\n+ if not admin:\n+ standings_query = standings_query.filter(Teams.banned == False)\n \n- teams = teams.group_by(Solves.teamid).order_by(score.desc(), quickest).all()\n+ standings = standings_query.all()\n \n # http://codegolf.stackexchange.com/a/4712\n try:\n- i = teams.index((self.id,)) + 1\n+ i = standings.index((self.id,)) + 1\n k = i % 10\n return \"%d%s\" % (i, \"tsnrhtdd\"[(i / 10 % 10 != 1) * (k < 4) * k::4])\n except ValueError:\n", "issue": "Awards is not accounted in `user.place()`\n[`user.place()`][user_place] is not accounting awards while [`get_standings()`][get_standings] does. This causes different ordering in scoreboard and team profile. Is this by design?\r\n\r\n[user_place]: https://github.com/CTFd/CTFd/blob/master/CTFd/models.py#L200\r\n[get_standings]: https://github.com/CTFd/CTFd/blob/master/CTFd/scoreboard.py#L11\r\n\n", "before_files": [{"content": "import datetime\nimport hashlib\nimport json\nimport netaddr\nfrom socket import inet_pton, inet_ntop, AF_INET, AF_INET6\nfrom struct import unpack, pack, error as struct_error\n\nfrom flask_sqlalchemy import SQLAlchemy\nfrom passlib.hash import bcrypt_sha256\nfrom sqlalchemy.exc import DatabaseError\n\n\ndef sha512(string):\n return str(hashlib.sha512(string).hexdigest())\n\n\ndef ip2long(ip):\n '''Converts a user's IP address into an integer/long'''\n return int(netaddr.IPAddress(ip))\n\n\ndef long2ip(ip_int):\n '''Converts a saved integer/long back into an IP address'''\n return str(netaddr.IPAddress(ip_int))\n\n\ndb = SQLAlchemy()\n\n\nclass Pages(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n route = db.Column(db.String(80), unique=True)\n html = db.Column(db.Text)\n\n def __init__(self, route, html):\n self.route = route\n self.html = html\n\n def __repr__(self):\n return \"<Pages route {0}>\".format(self.route)\n\n\nclass Containers(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n name = db.Column(db.String(80))\n buildfile = db.Column(db.Text)\n\n def __init__(self, name, buildfile):\n self.name = name\n self.buildfile = buildfile\n\n def __repr__(self):\n return \"<Container ID:(0) {1}>\".format(self.id, self.name)\n\n\nclass Challenges(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n name = db.Column(db.String(80))\n description = db.Column(db.Text)\n max_attempts = db.Column(db.Integer, default=0)\n value = db.Column(db.Integer)\n category = db.Column(db.String(80))\n type = db.Column(db.Integer)\n hidden = db.Column(db.Boolean)\n\n def __init__(self, name, description, value, category, type=0):\n self.name = name\n self.description = description\n self.value = value\n self.category = category\n self.type = type\n # self.flags = json.dumps(flags)\n\n def __repr__(self):\n return '<chal %r>' % self.name\n\n\nclass Hints(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n type = db.Column(db.Integer, default=0)\n chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))\n hint = db.Column(db.Text)\n cost = db.Column(db.Integer, default=0)\n\n def __init__(self, chal, hint, cost=0, type=0):\n self.chal = chal\n self.hint = hint\n self.cost = cost\n self.type = type\n\n def __repr__(self):\n return '<hint %r>' % self.hint\n\n\nclass Awards(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))\n name = db.Column(db.String(80))\n description = db.Column(db.Text)\n date = db.Column(db.DateTime, default=datetime.datetime.utcnow)\n value = db.Column(db.Integer)\n category = db.Column(db.String(80))\n icon = db.Column(db.Text)\n\n def __init__(self, teamid, name, value):\n self.teamid = teamid\n self.name = name\n self.value = value\n\n def __repr__(self):\n return '<award %r>' % self.name\n\n\nclass Tags(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))\n tag = db.Column(db.String(80))\n\n def __init__(self, chal, tag):\n self.chal = chal\n self.tag = tag\n\n def __repr__(self):\n return \"<Tag {0} for challenge {1}>\".format(self.tag, self.chal)\n\n\nclass Files(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))\n location = db.Column(db.Text)\n\n def __init__(self, chal, location):\n self.chal = chal\n self.location = location\n\n def __repr__(self):\n return \"<File {0} for challenge {1}>\".format(self.location, self.chal)\n\n\nclass Keys(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n chal = db.Column(db.Integer, db.ForeignKey('challenges.id'))\n key_type = db.Column(db.Integer)\n flag = db.Column(db.Text)\n data = db.Column(db.Text)\n\n def __init__(self, chal, flag, key_type):\n self.chal = chal\n self.flag = flag\n self.key_type = key_type\n\n def __repr__(self):\n return \"<Flag {0} for challenge {1}>\".format(self.flag, self.chal)\n\n\nclass Teams(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n name = db.Column(db.String(128), unique=True)\n email = db.Column(db.String(128), unique=True)\n password = db.Column(db.String(128))\n website = db.Column(db.String(128))\n affiliation = db.Column(db.String(128))\n country = db.Column(db.String(32))\n bracket = db.Column(db.String(32))\n banned = db.Column(db.Boolean, default=False)\n verified = db.Column(db.Boolean, default=False)\n admin = db.Column(db.Boolean, default=False)\n joined = db.Column(db.DateTime, default=datetime.datetime.utcnow)\n\n def __init__(self, name, email, password):\n self.name = name\n self.email = email\n self.password = bcrypt_sha256.encrypt(str(password))\n\n def __repr__(self):\n return '<team %r>' % self.name\n\n def score(self, admin=False):\n score = db.func.sum(Challenges.value).label('score')\n team = db.session.query(Solves.teamid, score).join(Teams).join(Challenges).filter(Teams.banned == False, Teams.id == self.id)\n award_score = db.func.sum(Awards.value).label('award_score')\n award = db.session.query(award_score).filter_by(teamid=self.id)\n\n if not admin:\n freeze = Config.query.filter_by(key='freeze').first()\n if freeze and freeze.value:\n freeze = int(freeze.value)\n freeze = datetime.datetime.utcfromtimestamp(freeze)\n team = team.filter(Solves.date < freeze)\n award = award.filter(Awards.date < freeze)\n\n team = team.group_by(Solves.teamid).first()\n award = award.first()\n\n if team:\n return int(team.score or 0) + int(award.award_score or 0)\n else:\n return 0\n\n def place(self, admin=False):\n score = db.func.sum(Challenges.value).label('score')\n quickest = db.func.max(Solves.date).label('quickest')\n teams = db.session.query(Solves.teamid).join(Teams).join(Challenges).filter(Teams.banned == False)\n\n if not admin:\n freeze = Config.query.filter_by(key='freeze').first()\n if freeze and freeze.value:\n freeze = int(freeze.value)\n freeze = datetime.datetime.utcfromtimestamp(freeze)\n teams = teams.filter(Solves.date < freeze)\n\n teams = teams.group_by(Solves.teamid).order_by(score.desc(), quickest).all()\n\n # http://codegolf.stackexchange.com/a/4712\n try:\n i = teams.index((self.id,)) + 1\n k = i % 10\n return \"%d%s\" % (i, \"tsnrhtdd\"[(i / 10 % 10 != 1) * (k < 4) * k::4])\n except ValueError:\n return 0\n\n\nclass Solves(db.Model):\n __table_args__ = (db.UniqueConstraint('chalid', 'teamid'), {})\n id = db.Column(db.Integer, primary_key=True)\n chalid = db.Column(db.Integer, db.ForeignKey('challenges.id'))\n teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))\n ip = db.Column(db.String(46))\n flag = db.Column(db.Text)\n date = db.Column(db.DateTime, default=datetime.datetime.utcnow)\n team = db.relationship('Teams', foreign_keys=\"Solves.teamid\", lazy='joined')\n chal = db.relationship('Challenges', foreign_keys=\"Solves.chalid\", lazy='joined')\n # value = db.Column(db.Integer)\n\n def __init__(self, teamid, chalid, ip, flag):\n self.ip = ip\n self.chalid = chalid\n self.teamid = teamid\n self.flag = flag\n # self.value = value\n\n def __repr__(self):\n return '<solve {}, {}, {}, {}>'.format(self.teamid, self.chalid, self.ip, self.flag)\n\n\nclass WrongKeys(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n chalid = db.Column(db.Integer, db.ForeignKey('challenges.id'))\n teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))\n ip = db.Column(db.String(46))\n date = db.Column(db.DateTime, default=datetime.datetime.utcnow)\n flag = db.Column(db.Text)\n chal = db.relationship('Challenges', foreign_keys=\"WrongKeys.chalid\", lazy='joined')\n\n def __init__(self, teamid, chalid, ip, flag):\n self.ip = ip\n self.teamid = teamid\n self.chalid = chalid\n self.flag = flag\n\n def __repr__(self):\n return '<wrong {}, {}, {}, {}>'.format(self.teamid, self.chalid, self.ip, self.flag)\n\n\nclass Unlocks(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n teamid = db.Column(db.Integer, db.ForeignKey('teams.id'))\n date = db.Column(db.DateTime, default=datetime.datetime.utcnow)\n itemid = db.Column(db.Integer)\n model = db.Column(db.String(32))\n\n def __init__(self, model, teamid, itemid):\n self.model = model\n self.teamid = teamid\n self.itemid = itemid\n\n def __repr__(self):\n return '<unlock %r>' % self.teamid\n\n\nclass Tracking(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n ip = db.Column(db.String(46))\n team = db.Column(db.Integer, db.ForeignKey('teams.id'))\n date = db.Column(db.DateTime, default=datetime.datetime.utcnow)\n\n def __init__(self, ip, team):\n self.ip = ip\n self.team = team\n\n def __repr__(self):\n return '<ip %r>' % self.team\n\n\nclass Config(db.Model):\n id = db.Column(db.Integer, primary_key=True)\n key = db.Column(db.Text)\n value = db.Column(db.Text)\n\n def __init__(self, key, value):\n self.key = key\n self.value = value\n", "path": "CTFd/models.py"}]} | 3,946 | 625 |
gh_patches_debug_31851 | rasdani/github-patches | git_diff | coala__coala-2865 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add more strings to Constants
Our Constants are located in coala/coalib/misc/Constants.py and there we hold options for `TRUE_STRINGS`. I think we should expand these true strings with more options, such as : `yep`,`ja` or even `hell yeah` (who knows what the user might come up with). Feel free to add your own suggestions if you think they fit.
</issue>
<code>
[start of coalib/misc/Constants.py]
1 # -*- coding: utf-8 -*-
2
3 import appdirs
4 import os
5 import re
6
7 # Start ignoring PyImportSortBear, PyLintBear as BUS_NAME is imported as a
8 # constant from other files.
9 from coalib import BUS_NAME
10 from coalib import VERSION
11 # Stop ignoring
12
13
14 THIS_IS_A_BUG = ('This is a bug. We are sorry for the inconvenience. '
15 'Please contact the developers for assistance.')
16
17 CRASH_MESSAGE = ('An unknown error occurred. This is a bug. We are '
18 'sorry for the inconvenience. Please contact the '
19 'developers for assistance. During execution of '
20 'coala an exception was raised. This should never '
21 'happen. When asked for, the following information '
22 'may help investigating:')
23
24 VERSION_CONFLICT_MESSAGE = ('There is a conflict in the version of a '
25 'dependency you have installed and the '
26 'requirements of coala. This may be resolved by '
27 'creating a separate virtual environment for '
28 'coala or running `pip install "%s"`. Be aware '
29 'that the latter solution might break other '
30 'python packages that depend on the currently '
31 'installed version.')
32
33 OBJ_NOT_ACCESSIBLE = '{} is not accessible and will be ignored!'
34
35 TRUE_STRINGS = ['1',
36 'on',
37 'y',
38 'yes',
39 'yeah',
40 'sure',
41 'true',
42 'definitely',
43 'yup',
44 'right',
45 'aye',
46 'positive']
47
48 FALSE_STRINGS = ['0',
49 'off',
50 'n',
51 'no',
52 'nope',
53 'nah',
54 'false',
55 'wrong',
56 'none',
57 'nay',
58 'negative']
59
60 # This string contains many unicode characters to challenge tests.
61 COMPLEX_TEST_STRING = ('4 r34l ch4ll3n63: 123 ÄÖü ABc @€¥ §&% {[( ←↓→↑ '
62 'ĦŊħ ß°^ \\\n\u2192')
63
64 # Path to the coalib directory
65 coalib_root = os.path.join(os.path.dirname(__file__),
66 os.path.pardir)
67
68 # Path to the language definition files
69 language_definitions = os.path.join(coalib_root,
70 'bearlib',
71 'languages',
72 'definitions')
73
74 system_coafile = os.path.join(coalib_root, 'default_coafile')
75
76 user_coafile = os.path.join(os.path.expanduser('~'), '.coarc')
77
78 default_coafile = '.coafile'
79
80 USER_DATA_DIR = appdirs.user_data_dir('coala', version=VERSION)
81
82 GLOBBING_SPECIAL_CHARS = '()[]|?*'
83
84 URL_REGEX = re.compile(
85 r'^(?:(?:http|ftp)[s]?://)?' # scheme
86 r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+' # domain name
87 r'(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|'
88 r'localhost|' # OR localhost
89 r'(?:\d{1,3}\.){3}\d{1,3})' # OR an ip
90 r'(?::\d+)?' # optional port number
91 r'(?:/?|[/?]\S+)$', # path
92 re.IGNORECASE)
93
[end of coalib/misc/Constants.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/coalib/misc/Constants.py b/coalib/misc/Constants.py
--- a/coalib/misc/Constants.py
+++ b/coalib/misc/Constants.py
@@ -34,27 +34,69 @@
TRUE_STRINGS = ['1',
'on',
+ 'okay',
+ 'ok',
+ 'okey-dokey',
'y',
'yes',
'yeah',
+ 'yea',
+ 'ya',
+ 'ye',
+ 'yessir',
'sure',
'true',
+ 'tru',
+ 'uh-huh',
'definitely',
'yup',
+ 'yep',
'right',
'aye',
+ 'alright',
+ 'alrighty',
+ 'hell yeah',
+ 'affirmative',
+ 'certainly',
+ 'definitely',
+ 'absolutely',
+ 'roger',
+ 'righto',
+ 'ja',
+ 'da',
+ 'si',
+ 'oui',
+ 'amen',
+ 'totally',
+ '10-4',
'positive']
FALSE_STRINGS = ['0',
'off',
'n',
'no',
+ 'nix',
'nope',
+ 'nop',
'nah',
+ 'nay',
'false',
+ 'uh-uh',
'wrong',
'none',
'nay',
+ 'hell no',
+ 'fat chance',
+ 'not a chance in hell',
+ 'not in a million years',
+ 'out of the question',
+ 'no siree',
+ 'no way',
+ 'nein',
+ 'njet',
+ 'nee',
+ 'non',
+ 'hakuna',
'negative']
# This string contains many unicode characters to challenge tests.
| {"golden_diff": "diff --git a/coalib/misc/Constants.py b/coalib/misc/Constants.py\n--- a/coalib/misc/Constants.py\n+++ b/coalib/misc/Constants.py\n@@ -34,27 +34,69 @@\n \n TRUE_STRINGS = ['1',\n 'on',\n+ 'okay',\n+ 'ok',\n+ 'okey-dokey',\n 'y',\n 'yes',\n 'yeah',\n+ 'yea',\n+ 'ya',\n+ 'ye',\n+ 'yessir',\n 'sure',\n 'true',\n+ 'tru',\n+ 'uh-huh',\n 'definitely',\n 'yup',\n+ 'yep',\n 'right',\n 'aye',\n+ 'alright',\n+ 'alrighty',\n+ 'hell yeah',\n+ 'affirmative',\n+ 'certainly',\n+ 'definitely',\n+ 'absolutely',\n+ 'roger',\n+ 'righto',\n+ 'ja',\n+ 'da',\n+ 'si',\n+ 'oui',\n+ 'amen',\n+ 'totally',\n+ '10-4',\n 'positive']\n \n FALSE_STRINGS = ['0',\n 'off',\n 'n',\n 'no',\n+ 'nix',\n 'nope',\n+ 'nop',\n 'nah',\n+ 'nay',\n 'false',\n+ 'uh-uh',\n 'wrong',\n 'none',\n 'nay',\n+ 'hell no',\n+ 'fat chance',\n+ 'not a chance in hell',\n+ 'not in a million years',\n+ 'out of the question',\n+ 'no siree',\n+ 'no way',\n+ 'nein',\n+ 'njet',\n+ 'nee',\n+ 'non',\n+ 'hakuna',\n 'negative']\n \n # This string contains many unicode characters to challenge tests.\n", "issue": "Add more strings to Constants\nOur Constants are located in coala/coalib/misc/Constants.py and there we hold options for `TRUE_STRINGS`. I think we should expand these true strings with more options, such as : `yep`,`ja` or even `hell yeah` (who knows what the user might come up with). Feel free to add your own suggestions if you think they fit.\n\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n\nimport appdirs\nimport os\nimport re\n\n# Start ignoring PyImportSortBear, PyLintBear as BUS_NAME is imported as a\n# constant from other files.\nfrom coalib import BUS_NAME\nfrom coalib import VERSION\n# Stop ignoring\n\n\nTHIS_IS_A_BUG = ('This is a bug. We are sorry for the inconvenience. '\n 'Please contact the developers for assistance.')\n\nCRASH_MESSAGE = ('An unknown error occurred. This is a bug. We are '\n 'sorry for the inconvenience. Please contact the '\n 'developers for assistance. During execution of '\n 'coala an exception was raised. This should never '\n 'happen. When asked for, the following information '\n 'may help investigating:')\n\nVERSION_CONFLICT_MESSAGE = ('There is a conflict in the version of a '\n 'dependency you have installed and the '\n 'requirements of coala. This may be resolved by '\n 'creating a separate virtual environment for '\n 'coala or running `pip install \"%s\"`. Be aware '\n 'that the latter solution might break other '\n 'python packages that depend on the currently '\n 'installed version.')\n\nOBJ_NOT_ACCESSIBLE = '{} is not accessible and will be ignored!'\n\nTRUE_STRINGS = ['1',\n 'on',\n 'y',\n 'yes',\n 'yeah',\n 'sure',\n 'true',\n 'definitely',\n 'yup',\n 'right',\n 'aye',\n 'positive']\n\nFALSE_STRINGS = ['0',\n 'off',\n 'n',\n 'no',\n 'nope',\n 'nah',\n 'false',\n 'wrong',\n 'none',\n 'nay',\n 'negative']\n\n# This string contains many unicode characters to challenge tests.\nCOMPLEX_TEST_STRING = ('4 r34l ch4ll3n63: 123 \u00c4\u00d6\u00fc ABc @\u20ac\u00a5 \u00a7&% {[( \u2190\u2193\u2192\u2191 '\n '\u0126\u014a\u0127 \u00df\u00b0^ \\\\\\n\\u2192')\n\n# Path to the coalib directory\ncoalib_root = os.path.join(os.path.dirname(__file__),\n os.path.pardir)\n\n# Path to the language definition files\nlanguage_definitions = os.path.join(coalib_root,\n 'bearlib',\n 'languages',\n 'definitions')\n\nsystem_coafile = os.path.join(coalib_root, 'default_coafile')\n\nuser_coafile = os.path.join(os.path.expanduser('~'), '.coarc')\n\ndefault_coafile = '.coafile'\n\nUSER_DATA_DIR = appdirs.user_data_dir('coala', version=VERSION)\n\nGLOBBING_SPECIAL_CHARS = '()[]|?*'\n\nURL_REGEX = re.compile(\n r'^(?:(?:http|ftp)[s]?://)?' # scheme\n r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\\.)+' # domain name\n r'(?:[A-Z]{2,6}\\.?|[A-Z0-9-]{2,}\\.?)|'\n r'localhost|' # OR localhost\n r'(?:\\d{1,3}\\.){3}\\d{1,3})' # OR an ip\n r'(?::\\d+)?' # optional port number\n r'(?:/?|[/?]\\S+)$', # path\n re.IGNORECASE)\n", "path": "coalib/misc/Constants.py"}]} | 1,558 | 429 |
gh_patches_debug_37713 | rasdani/github-patches | git_diff | coala__coala-964 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
glob/collecting: Accept strings too
the methods there want a list but `glob("string")` makes sense too (and behaves very strangely), we should support that.
</issue>
<code>
[start of coalib/collecting/Collectors.py]
1 import os
2
3 from coalib.collecting.Importers import iimport_objects
4 from coalib.misc.Decorators import yield_once
5 from coalib.misc.i18n import _
6 from coalib.parsing.Globbing import iglob
7
8
9 def _yield_if_right_kind(bear_class, kinds):
10 try:
11 if bear_class.kind() in kinds:
12 yield bear_class
13 except NotImplementedError:
14 pass
15
16
17 def _import_bears(file_path, kinds):
18 # recursive imports:
19 for bear_list in iimport_objects(file_path,
20 names='__additional_bears__',
21 types=list):
22 for bear_class in bear_list:
23 for valid_bear_class in _yield_if_right_kind(bear_class, kinds):
24 yield valid_bear_class
25 # normal import
26 for bear_class in iimport_objects(file_path,
27 attributes='kind',
28 local=True):
29 for valid_bear_class in _yield_if_right_kind(bear_class, kinds):
30 yield valid_bear_class
31
32
33 @yield_once
34 def icollect(file_paths):
35 """
36 Evaluate globs in file paths and return all matching files.
37
38 :param file_paths: list of file paths that can include globs
39 :return: iterator that yields paths of all matching files
40 """
41 for file_path in file_paths:
42 for match in iglob(file_path):
43 yield match
44
45
46 def collect_files(file_paths):
47 """
48 Evaluate globs in file paths and return all matching files
49
50 :param file_paths: list of file paths that can include globs
51 :return: list of paths of all matching files
52 """
53 return list(filter(os.path.isfile, icollect(file_paths)))
54
55
56 def collect_dirs(dir_paths):
57 """
58 Evaluate globs in directory paths and return all matching directories
59
60 :param dir_paths: list of file paths that can include globs
61 :return: list of paths of all matching directories
62 """
63 return list(filter(os.path.isdir, icollect(dir_paths)))
64
65
66 @yield_once
67 def icollect_bears(bear_dirs, bear_names, kinds, log_printer):
68 """
69 Collect all bears from bear directories that have a matching kind.
70
71 :param bear_dirs: directories that can contain bears
72 :param bear_names: names of bears
73 :param kinds: list of bear kinds to be collected
74 :param log_printer: log_printer to handle logging
75 :return: iterator that yields bear classes
76 """
77 for bear_dir in filter(os.path.isdir, icollect(bear_dirs)):
78 for bear_name in bear_names:
79 for matching_file in iglob(
80 os.path.join(bear_dir, bear_name + '.py')):
81
82 try:
83 for bear in _import_bears(matching_file, kinds):
84 yield bear
85 except:
86 log_printer.warn(_("Unable to collect bears from {file}. "
87 "Probably the file is malformed or "
88 "the module code raises an exception.")
89 .format(file=matching_file))
90
91
92 def collect_bears(bear_dirs, bear_names, kinds, log_printer):
93 """
94 Collect all bears from bear directories that have a matching kind.
95
96 :param bear_dirs: directories that can contain bears
97 :param bear_names: names of bears
98 :param kinds: list of bear kinds to be collected
99 :param log_printer: log_printer to handle logging
100 :return: list of matching bear classes
101 """
102 return list(icollect_bears(bear_dirs, bear_names, kinds, log_printer))
103
[end of coalib/collecting/Collectors.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/coalib/collecting/Collectors.py b/coalib/collecting/Collectors.py
--- a/coalib/collecting/Collectors.py
+++ b/coalib/collecting/Collectors.py
@@ -35,9 +35,12 @@
"""
Evaluate globs in file paths and return all matching files.
- :param file_paths: list of file paths that can include globs
+ :param file_paths: file path or list of such that can include globs
:return: iterator that yields paths of all matching files
"""
+ if isinstance(file_paths, str):
+ file_paths = [file_paths]
+
for file_path in file_paths:
for match in iglob(file_path):
yield match
@@ -47,7 +50,7 @@
"""
Evaluate globs in file paths and return all matching files
- :param file_paths: list of file paths that can include globs
+ :param file_paths: file path or list of such that can include globs
:return: list of paths of all matching files
"""
return list(filter(os.path.isfile, icollect(file_paths)))
@@ -57,7 +60,7 @@
"""
Evaluate globs in directory paths and return all matching directories
- :param dir_paths: list of file paths that can include globs
+ :param dir_paths: file path or list of such that can include globs
:return: list of paths of all matching directories
"""
return list(filter(os.path.isdir, icollect(dir_paths)))
@@ -68,7 +71,7 @@
"""
Collect all bears from bear directories that have a matching kind.
- :param bear_dirs: directories that can contain bears
+ :param bear_dirs: directory name or list of such that can contain bears
:param bear_names: names of bears
:param kinds: list of bear kinds to be collected
:param log_printer: log_printer to handle logging
@@ -93,7 +96,7 @@
"""
Collect all bears from bear directories that have a matching kind.
- :param bear_dirs: directories that can contain bears
+ :param bear_dirs: directory name or list of such that can contain bears
:param bear_names: names of bears
:param kinds: list of bear kinds to be collected
:param log_printer: log_printer to handle logging
| {"golden_diff": "diff --git a/coalib/collecting/Collectors.py b/coalib/collecting/Collectors.py\n--- a/coalib/collecting/Collectors.py\n+++ b/coalib/collecting/Collectors.py\n@@ -35,9 +35,12 @@\n \"\"\"\n Evaluate globs in file paths and return all matching files.\n \n- :param file_paths: list of file paths that can include globs\n+ :param file_paths: file path or list of such that can include globs\n :return: iterator that yields paths of all matching files\n \"\"\"\n+ if isinstance(file_paths, str):\n+ file_paths = [file_paths]\n+\n for file_path in file_paths:\n for match in iglob(file_path):\n yield match\n@@ -47,7 +50,7 @@\n \"\"\"\n Evaluate globs in file paths and return all matching files\n \n- :param file_paths: list of file paths that can include globs\n+ :param file_paths: file path or list of such that can include globs\n :return: list of paths of all matching files\n \"\"\"\n return list(filter(os.path.isfile, icollect(file_paths)))\n@@ -57,7 +60,7 @@\n \"\"\"\n Evaluate globs in directory paths and return all matching directories\n \n- :param dir_paths: list of file paths that can include globs\n+ :param dir_paths: file path or list of such that can include globs\n :return: list of paths of all matching directories\n \"\"\"\n return list(filter(os.path.isdir, icollect(dir_paths)))\n@@ -68,7 +71,7 @@\n \"\"\"\n Collect all bears from bear directories that have a matching kind.\n \n- :param bear_dirs: directories that can contain bears\n+ :param bear_dirs: directory name or list of such that can contain bears\n :param bear_names: names of bears\n :param kinds: list of bear kinds to be collected\n :param log_printer: log_printer to handle logging\n@@ -93,7 +96,7 @@\n \"\"\"\n Collect all bears from bear directories that have a matching kind.\n \n- :param bear_dirs: directories that can contain bears\n+ :param bear_dirs: directory name or list of such that can contain bears\n :param bear_names: names of bears\n :param kinds: list of bear kinds to be collected\n :param log_printer: log_printer to handle logging\n", "issue": "glob/collecting: Accept strings too\nthe methods there want a list but `glob(\"string\")` makes sense too (and behaves very strangely), we should support that.\n\n", "before_files": [{"content": "import os\n\nfrom coalib.collecting.Importers import iimport_objects\nfrom coalib.misc.Decorators import yield_once\nfrom coalib.misc.i18n import _\nfrom coalib.parsing.Globbing import iglob\n\n\ndef _yield_if_right_kind(bear_class, kinds):\n try:\n if bear_class.kind() in kinds:\n yield bear_class\n except NotImplementedError:\n pass\n\n\ndef _import_bears(file_path, kinds):\n # recursive imports:\n for bear_list in iimport_objects(file_path,\n names='__additional_bears__',\n types=list):\n for bear_class in bear_list:\n for valid_bear_class in _yield_if_right_kind(bear_class, kinds):\n yield valid_bear_class\n # normal import\n for bear_class in iimport_objects(file_path,\n attributes='kind',\n local=True):\n for valid_bear_class in _yield_if_right_kind(bear_class, kinds):\n yield valid_bear_class\n\n\n@yield_once\ndef icollect(file_paths):\n \"\"\"\n Evaluate globs in file paths and return all matching files.\n\n :param file_paths: list of file paths that can include globs\n :return: iterator that yields paths of all matching files\n \"\"\"\n for file_path in file_paths:\n for match in iglob(file_path):\n yield match\n\n\ndef collect_files(file_paths):\n \"\"\"\n Evaluate globs in file paths and return all matching files\n\n :param file_paths: list of file paths that can include globs\n :return: list of paths of all matching files\n \"\"\"\n return list(filter(os.path.isfile, icollect(file_paths)))\n\n\ndef collect_dirs(dir_paths):\n \"\"\"\n Evaluate globs in directory paths and return all matching directories\n\n :param dir_paths: list of file paths that can include globs\n :return: list of paths of all matching directories\n \"\"\"\n return list(filter(os.path.isdir, icollect(dir_paths)))\n\n\n@yield_once\ndef icollect_bears(bear_dirs, bear_names, kinds, log_printer):\n \"\"\"\n Collect all bears from bear directories that have a matching kind.\n\n :param bear_dirs: directories that can contain bears\n :param bear_names: names of bears\n :param kinds: list of bear kinds to be collected\n :param log_printer: log_printer to handle logging\n :return: iterator that yields bear classes\n \"\"\"\n for bear_dir in filter(os.path.isdir, icollect(bear_dirs)):\n for bear_name in bear_names:\n for matching_file in iglob(\n os.path.join(bear_dir, bear_name + '.py')):\n\n try:\n for bear in _import_bears(matching_file, kinds):\n yield bear\n except:\n log_printer.warn(_(\"Unable to collect bears from {file}. \"\n \"Probably the file is malformed or \"\n \"the module code raises an exception.\")\n .format(file=matching_file))\n\n\ndef collect_bears(bear_dirs, bear_names, kinds, log_printer):\n \"\"\"\n Collect all bears from bear directories that have a matching kind.\n\n :param bear_dirs: directories that can contain bears\n :param bear_names: names of bears\n :param kinds: list of bear kinds to be collected\n :param log_printer: log_printer to handle logging\n :return: list of matching bear classes\n \"\"\"\n return list(icollect_bears(bear_dirs, bear_names, kinds, log_printer))\n", "path": "coalib/collecting/Collectors.py"}]} | 1,538 | 553 |
gh_patches_debug_11204 | rasdani/github-patches | git_diff | svthalia__concrexit-1736 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
AttributeError: 'Event' object has no attribute 'title_en'
Sentry Issue: [CONCREXIT-6D](https://sentry.io/organizations/thalia/issues/2465590057/?referrer=github_integration)
```
AttributeError: 'Event' object has no attribute 'title_en'
(9 additional frame(s) were not displayed)
...
File "rest_framework/mixins.py", line 68, in update
self.perform_update(serializer)
File "pizzas/api/v1/viewsets.py", line 105, in perform_update
self._update_payment(
File "pizzas/api/v1/viewsets.py", line 114, in _update_payment
order.payment = create_payment(order, processed_by, payment_type)
File "payments/services.py", line 67, in create_payment
notes=payable.payment_notes,
File "pizzas/payables.py", line 21, in payment_notes
f"Food order by {self.model.member_name} "
```
</issue>
<code>
[start of website/pizzas/payables.py]
1 from django.template.defaultfilters import date
2
3 from payments import Payable, payables
4 from pizzas.models import FoodOrder
5 from pizzas.services import can_change_order
6
7
8 class FoodOrderPayable(Payable):
9 @property
10 def payment_amount(self):
11 return self.model.product.price
12
13 @property
14 def payment_topic(self):
15 start_date = date(self.model.food_event.start, "Y-m-d")
16 return f"Food {self.model.food_event.event.title_en} [{start_date}]"
17
18 @property
19 def payment_notes(self):
20 return (
21 f"Food order by {self.model.member_name} "
22 f"for {self.model.food_event.event.title_en}"
23 )
24
25 @property
26 def payment_payer(self):
27 return self.model.member
28
29 def can_manage_payment(self, member):
30 return can_change_order(member, self.model.food_event)
31
32
33 def register():
34 payables.register(FoodOrder, FoodOrderPayable)
35
[end of website/pizzas/payables.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/website/pizzas/payables.py b/website/pizzas/payables.py
--- a/website/pizzas/payables.py
+++ b/website/pizzas/payables.py
@@ -13,13 +13,13 @@
@property
def payment_topic(self):
start_date = date(self.model.food_event.start, "Y-m-d")
- return f"Food {self.model.food_event.event.title_en} [{start_date}]"
+ return f"Food {self.model.food_event.event.title} [{start_date}]"
@property
def payment_notes(self):
return (
f"Food order by {self.model.member_name} "
- f"for {self.model.food_event.event.title_en}"
+ f"for {self.model.food_event.event.title}"
)
@property
| {"golden_diff": "diff --git a/website/pizzas/payables.py b/website/pizzas/payables.py\n--- a/website/pizzas/payables.py\n+++ b/website/pizzas/payables.py\n@@ -13,13 +13,13 @@\n @property\n def payment_topic(self):\n start_date = date(self.model.food_event.start, \"Y-m-d\")\n- return f\"Food {self.model.food_event.event.title_en} [{start_date}]\"\n+ return f\"Food {self.model.food_event.event.title} [{start_date}]\"\n \n @property\n def payment_notes(self):\n return (\n f\"Food order by {self.model.member_name} \"\n- f\"for {self.model.food_event.event.title_en}\"\n+ f\"for {self.model.food_event.event.title}\"\n )\n \n @property\n", "issue": "AttributeError: 'Event' object has no attribute 'title_en'\nSentry Issue: [CONCREXIT-6D](https://sentry.io/organizations/thalia/issues/2465590057/?referrer=github_integration)\n\n```\nAttributeError: 'Event' object has no attribute 'title_en'\n(9 additional frame(s) were not displayed)\n...\n File \"rest_framework/mixins.py\", line 68, in update\n self.perform_update(serializer)\n File \"pizzas/api/v1/viewsets.py\", line 105, in perform_update\n self._update_payment(\n File \"pizzas/api/v1/viewsets.py\", line 114, in _update_payment\n order.payment = create_payment(order, processed_by, payment_type)\n File \"payments/services.py\", line 67, in create_payment\n notes=payable.payment_notes,\n File \"pizzas/payables.py\", line 21, in payment_notes\n f\"Food order by {self.model.member_name} \"\n```\n", "before_files": [{"content": "from django.template.defaultfilters import date\n\nfrom payments import Payable, payables\nfrom pizzas.models import FoodOrder\nfrom pizzas.services import can_change_order\n\n\nclass FoodOrderPayable(Payable):\n @property\n def payment_amount(self):\n return self.model.product.price\n\n @property\n def payment_topic(self):\n start_date = date(self.model.food_event.start, \"Y-m-d\")\n return f\"Food {self.model.food_event.event.title_en} [{start_date}]\"\n\n @property\n def payment_notes(self):\n return (\n f\"Food order by {self.model.member_name} \"\n f\"for {self.model.food_event.event.title_en}\"\n )\n\n @property\n def payment_payer(self):\n return self.model.member\n\n def can_manage_payment(self, member):\n return can_change_order(member, self.model.food_event)\n\n\ndef register():\n payables.register(FoodOrder, FoodOrderPayable)\n", "path": "website/pizzas/payables.py"}]} | 1,032 | 180 |
gh_patches_debug_21261 | rasdani/github-patches | git_diff | cookiecutter__cookiecutter-62 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
UnicodeEncodeError when the defualt value is used and contains non ascii characters.
Error occurs when the user uses the default unicode string.
Code:
```
if PY3:
cookiecutter_dict[key] = new_val
else:
cookiecutter_dict[key] = new_val.decode('utf-8')
```
Everything is okay in Python 3, but `new_val` is already unicode in 2.x.
</issue>
<code>
[start of cookiecutter/prompt.py]
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 """
5 cookiecutter.prompt
6 ---------------------
7
8 Functions for prompting the user for project info.
9 """
10
11 from __future__ import unicode_literals
12 import sys
13
14 PY3 = sys.version > '3'
15 if PY3:
16 iteritems = lambda d: iter(d.items())
17 else:
18 input = raw_input
19 iteritems = lambda d: d.iteritems()
20
21 def prompt_for_config(context):
22 """
23 Prompts the user to enter new config, using context as a source for the
24 field names and sample values.
25 """
26 cookiecutter_dict = {}
27
28 for key, val in iteritems(context['cookiecutter']):
29 prompt = "{0} (default is \"{1}\")? ".format(key, val)
30 new_val = input(prompt.encode('utf-8'))
31 new_val = new_val.strip()
32
33 if new_val == '':
34 new_val = val
35
36 if PY3:
37 cookiecutter_dict[key] = new_val
38 else:
39 cookiecutter_dict[key] = new_val.decode('utf-8')
40 return cookiecutter_dict
41
42
43 def query_yes_no(question, default="yes"):
44 """
45 Ask a yes/no question via `raw_input()` and return their answer.
46
47 :param question: A string that is presented to the user.
48 :param default: The presumed answer if the user just hits <Enter>.
49 It must be "yes" (the default), "no" or None (meaning
50 an answer is required of the user).
51
52 The "answer" return value is one of "yes" or "no".
53
54 Adapted from
55 http://stackoverflow.com/questions/3041986/python-command-line-yes-no-input
56 http://code.activestate.com/recipes/577058/
57
58 """
59 valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False}
60 if default is None:
61 prompt = " [y/n] "
62 elif default == "yes":
63 prompt = " [Y/n] "
64 elif default == "no":
65 prompt = " [y/N] "
66 else:
67 raise ValueError("invalid default answer: '%s'" % default)
68
69 while True:
70 sys.stdout.write(question + prompt)
71 choice = input().lower()
72
73 if default is not None and choice == '':
74 return valid[default]
75 elif choice in valid:
76 return valid[choice]
77 else:
78 sys.stdout.write("Please respond with 'yes' or 'no' "
79 "(or 'y' or 'n').\n")
80
[end of cookiecutter/prompt.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/cookiecutter/prompt.py b/cookiecutter/prompt.py
--- a/cookiecutter/prompt.py
+++ b/cookiecutter/prompt.py
@@ -18,6 +18,7 @@
input = raw_input
iteritems = lambda d: d.iteritems()
+
def prompt_for_config(context):
"""
Prompts the user to enter new config, using context as a source for the
@@ -27,16 +28,18 @@
for key, val in iteritems(context['cookiecutter']):
prompt = "{0} (default is \"{1}\")? ".format(key, val)
- new_val = input(prompt.encode('utf-8'))
+
+ if PY3:
+ new_val = input(prompt.encode('utf-8'))
+ else:
+ new_val = input(prompt.encode('utf-8')).decode('utf-8')
+
new_val = new_val.strip()
if new_val == '':
new_val = val
- if PY3:
- cookiecutter_dict[key] = new_val
- else:
- cookiecutter_dict[key] = new_val.decode('utf-8')
+ cookiecutter_dict[key] = new_val
return cookiecutter_dict
| {"golden_diff": "diff --git a/cookiecutter/prompt.py b/cookiecutter/prompt.py\n--- a/cookiecutter/prompt.py\n+++ b/cookiecutter/prompt.py\n@@ -18,6 +18,7 @@\n input = raw_input\n iteritems = lambda d: d.iteritems()\n \n+\n def prompt_for_config(context):\n \"\"\"\n Prompts the user to enter new config, using context as a source for the\n@@ -27,16 +28,18 @@\n \n for key, val in iteritems(context['cookiecutter']):\n prompt = \"{0} (default is \\\"{1}\\\")? \".format(key, val)\n- new_val = input(prompt.encode('utf-8'))\n+\n+ if PY3:\n+ new_val = input(prompt.encode('utf-8'))\n+ else:\n+ new_val = input(prompt.encode('utf-8')).decode('utf-8')\n+\n new_val = new_val.strip()\n \n if new_val == '':\n new_val = val\n \n- if PY3:\n- cookiecutter_dict[key] = new_val\n- else:\n- cookiecutter_dict[key] = new_val.decode('utf-8')\n+ cookiecutter_dict[key] = new_val\n return cookiecutter_dict\n", "issue": "UnicodeEncodeError when the defualt value is used and contains non ascii characters.\nError occurs when the user uses the default unicode string.\n\nCode:\n\n```\nif PY3:\n cookiecutter_dict[key] = new_val\nelse:\n cookiecutter_dict[key] = new_val.decode('utf-8')\n```\n\nEverything is okay in Python 3, but `new_val` is already unicode in 2.x.\n\n", "before_files": [{"content": "#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n\n\"\"\"\ncookiecutter.prompt\n---------------------\n\nFunctions for prompting the user for project info.\n\"\"\"\n\nfrom __future__ import unicode_literals\nimport sys\n\nPY3 = sys.version > '3'\nif PY3:\n iteritems = lambda d: iter(d.items())\nelse:\n input = raw_input\n iteritems = lambda d: d.iteritems()\n\ndef prompt_for_config(context):\n \"\"\"\n Prompts the user to enter new config, using context as a source for the\n field names and sample values.\n \"\"\"\n cookiecutter_dict = {}\n\n for key, val in iteritems(context['cookiecutter']):\n prompt = \"{0} (default is \\\"{1}\\\")? \".format(key, val)\n new_val = input(prompt.encode('utf-8'))\n new_val = new_val.strip()\n\n if new_val == '':\n new_val = val\n\n if PY3:\n cookiecutter_dict[key] = new_val\n else:\n cookiecutter_dict[key] = new_val.decode('utf-8')\n return cookiecutter_dict\n\n\ndef query_yes_no(question, default=\"yes\"):\n \"\"\"\n Ask a yes/no question via `raw_input()` and return their answer.\n\n :param question: A string that is presented to the user.\n :param default: The presumed answer if the user just hits <Enter>.\n It must be \"yes\" (the default), \"no\" or None (meaning\n an answer is required of the user).\n\n The \"answer\" return value is one of \"yes\" or \"no\".\n\n Adapted from\n http://stackoverflow.com/questions/3041986/python-command-line-yes-no-input\n http://code.activestate.com/recipes/577058/\n\n \"\"\"\n valid = {\"yes\": True, \"y\": True, \"ye\": True, \"no\": False, \"n\": False}\n if default is None:\n prompt = \" [y/n] \"\n elif default == \"yes\":\n prompt = \" [Y/n] \"\n elif default == \"no\":\n prompt = \" [y/N] \"\n else:\n raise ValueError(\"invalid default answer: '%s'\" % default)\n\n while True:\n sys.stdout.write(question + prompt)\n choice = input().lower()\n\n if default is not None and choice == '':\n return valid[default]\n elif choice in valid:\n return valid[choice]\n else:\n sys.stdout.write(\"Please respond with 'yes' or 'no' \"\n \"(or 'y' or 'n').\\n\")\n", "path": "cookiecutter/prompt.py"}]} | 1,348 | 281 |
gh_patches_debug_36110 | rasdani/github-patches | git_diff | DataDog__dd-agent-3643 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Missing info on fixing: Using events for service checks is deprecated in favor of monitors
It seems that you deprecated a feature without putting any information regarding how to fix it. I even googled and the only reference is the source code where you added this warning.
Please provide some information regarding what changes we are supposed to implement in order not to get these warnings.
These warnings are showing in the UI:
https://www.dropbox.com/s/xpjpmgqtk71hqze/Screenshot%202014-09-24%2015.43.22.png?dl=0
</issue>
<code>
[start of checks/network_checks.py]
1 # (C) Datadog, Inc. 2010-2016
2 # All rights reserved
3 # Licensed under Simplified BSD License (see LICENSE)
4
5 # stdlib
6 from collections import defaultdict
7 from Queue import Empty, Queue
8 import threading
9 import time
10
11 # project
12 from checks import AgentCheck
13 from checks.libs.thread_pool import Pool
14 from config import _is_affirmative
15
16 TIMEOUT = 180
17 DEFAULT_SIZE_POOL = 6
18 MAX_LOOP_ITERATIONS = 1000
19 FAILURE = "FAILURE"
20
21 class Status:
22 DOWN = "DOWN"
23 WARNING = "WARNING"
24 CRITICAL = "CRITICAL"
25 UP = "UP"
26
27
28 class EventType:
29 DOWN = "servicecheck.state_change.down"
30 UP = "servicecheck.state_change.up"
31
32
33 class NetworkCheck(AgentCheck):
34 SOURCE_TYPE_NAME = 'servicecheck'
35 SERVICE_CHECK_PREFIX = 'network_check'
36 _global_current_pool_size = 0
37
38 STATUS_TO_SERVICE_CHECK = {
39 Status.UP : AgentCheck.OK,
40 Status.WARNING : AgentCheck.WARNING,
41 Status.CRITICAL : AgentCheck.CRITICAL,
42 Status.DOWN : AgentCheck.CRITICAL,
43 }
44
45 """
46 Services checks inherits from this class.
47 This class should never be directly instanciated.
48
49 Work flow:
50 The main agent loop will call the check function for each instance for
51 each iteration of the loop.
52 The check method will make an asynchronous call to the _process method in
53 one of the thread initiated in the thread pool created in this class constructor.
54 The _process method will call the _check method of the inherited class
55 which will perform the actual check.
56
57 The _check method must return a tuple which first element is either
58 Status.UP or Status.DOWN.
59 The second element is a short error message that will be displayed
60 when the service turns down.
61
62 """
63
64 def __init__(self, name, init_config, agentConfig, instances):
65 AgentCheck.__init__(self, name, init_config, agentConfig, instances)
66
67 # A dictionary to keep track of service statuses
68 self.statuses = {}
69 self.notified = {}
70 self.nb_failures = 0
71 self.pool_size = 0
72 self.pool_started = False
73
74 # Make sure every instance has a name that we use as a unique key
75 # to keep track of statuses
76 names = []
77 for inst in instances:
78 inst_name = inst.get('name', None)
79 if not inst_name:
80 raise Exception("All instances should have a 'name' parameter,"
81 " error on instance: {0}".format(inst))
82 if inst_name in names:
83 raise Exception("Duplicate names for instances with name {0}"
84 .format(inst_name))
85 names.append(inst_name)
86
87 def stop(self):
88 self.stop_pool()
89 self.pool_started = False
90
91 def start_pool(self):
92 # The pool size should be the minimum between the number of instances
93 # and the DEFAULT_SIZE_POOL. It can also be overridden by the 'threads_count'
94 # parameter in the init_config of the check
95 self.log.info("Starting Thread Pool")
96 default_size = min(self.instance_count(), DEFAULT_SIZE_POOL)
97 self.pool_size = int(self.init_config.get('threads_count', default_size))
98
99 # To keep track on the total number of threads we should have running
100 NetworkCheck._global_current_pool_size += self.pool_size
101
102 self.pool = Pool(self.pool_size)
103
104 self.resultsq = Queue()
105 self.jobs_status = {}
106 self.jobs_results = {}
107 self.pool_started = True
108
109 def stop_pool(self):
110 self.log.info("Stopping Thread Pool")
111
112 # To keep track on the total number of threads we should have running
113 NetworkCheck._global_current_pool_size -= self.pool_size
114
115 if self.pool_started:
116 self.pool.terminate()
117 self.pool.join()
118 self.jobs_status.clear()
119 assert self.pool.get_nworkers() == 0
120
121 def restart_pool(self):
122 self.stop_pool()
123 self.start_pool()
124
125 def check(self, instance):
126 if not self.pool_started:
127 self.start_pool()
128 if threading.activeCount() > 5 * NetworkCheck._global_current_pool_size + 6:
129 # On Windows the agent runs on multiple threads because of WMI so we need an offset of 6
130 raise Exception("Thread number (%s) is exploding. Skipping this check" % threading.activeCount())
131 self._process_results()
132 self._clean()
133 name = instance.get('name', None)
134 if name is None:
135 self.log.error('Each service check must have a name')
136 return
137
138 if name not in self.jobs_status:
139 # A given instance should be processed one at a time
140 self.jobs_status[name] = time.time()
141 self.jobs_results[name] = self.pool.apply_async(self._process, args=(instance,))
142 else:
143 self.log.error("Instance: %s skipped because it's already running." % name)
144
145 def _process(self, instance):
146 try:
147 statuses = self._check(instance)
148
149 if isinstance(statuses, tuple):
150 # Assume the check only returns one service check
151 status, msg = statuses
152 self.resultsq.put((status, msg, None, instance))
153
154 elif isinstance(statuses, list):
155 for status in statuses:
156 sc_name, status, msg = status
157 self.resultsq.put((status, msg, sc_name, instance))
158
159 except Exception:
160 self.log.exception(
161 u"Failed to process instance '%s'.", instance.get('name', u"")
162 )
163 result = (FAILURE, FAILURE, FAILURE, instance)
164 self.resultsq.put(result)
165
166 def _process_results(self):
167 for i in xrange(MAX_LOOP_ITERATIONS):
168 try:
169 # We want to fetch the result in a non blocking way
170 status, msg, sc_name, instance = self.resultsq.get_nowait()
171 except Empty:
172 break
173
174 instance_name = instance['name']
175 if status == FAILURE:
176 self.nb_failures += 1
177 if self.nb_failures >= self.pool_size - 1:
178 self.nb_failures = 0
179 self.restart_pool()
180
181 # clean failed job
182 self._clean_job(instance_name)
183 continue
184
185 self.report_as_service_check(sc_name, status, instance, msg)
186
187 # FIXME: 5.3, this has been deprecated before, get rid of events
188 # Don't create any event to avoid duplicates with server side
189 # service_checks
190 skip_event = _is_affirmative(instance.get('skip_event', False))
191 if not skip_event:
192 self.warning("Using events for service checks is deprecated in favor of monitors and will be removed in future versions of the Datadog Agent.")
193 event = None
194
195 if instance_name not in self.statuses:
196 self.statuses[instance_name] = defaultdict(list)
197
198 self.statuses[instance_name][sc_name].append(status)
199
200 window = int(instance.get('window', 1))
201
202 if window > 256:
203 self.log.warning("Maximum window size (256) exceeded, defaulting it to 256")
204 window = 256
205
206 threshold = instance.get('threshold', 1)
207
208 if len(self.statuses[instance_name][sc_name]) > window:
209 self.statuses[instance_name][sc_name].pop(0)
210
211 nb_failures = self.statuses[instance_name][sc_name].count(Status.DOWN)
212
213 if nb_failures >= threshold:
214 if self.notified.get((instance_name, sc_name), Status.UP) != Status.DOWN:
215 event = self._create_status_event(sc_name, status, msg, instance)
216 self.notified[(instance_name, sc_name)] = Status.DOWN
217 else:
218 if self.notified.get((instance_name, sc_name), Status.UP) != Status.UP:
219 event = self._create_status_event(sc_name, status, msg, instance)
220 self.notified[(instance_name, sc_name)] = Status.UP
221
222 if event is not None:
223 self.events.append(event)
224
225 self._clean_job(instance_name)
226
227 def _clean_job(self, instance_name):
228 # The job is finished here, this instance can be re processed
229 if instance_name in self.jobs_status:
230 self.log.debug("Instance: %s cleaned from jobs status." % instance_name)
231 del self.jobs_status[instance_name]
232
233 # if an exception happened, log it
234 if instance_name in self.jobs_results:
235 self.log.debug("Instance: %s cleaned from jobs results." % instance_name)
236 ret = self.jobs_results[instance_name].get()
237 if isinstance(ret, Exception):
238 self.log.exception("Exception in worker thread: {0}".format(ret))
239 del self.jobs_results[instance_name]
240
241
242 def _check(self, instance):
243 """This function should be implemented by inherited classes"""
244 raise NotImplementedError
245
246
247 def _clean(self):
248 now = time.time()
249 for name, start_time in self.jobs_status.iteritems():
250 if now - start_time > TIMEOUT:
251 self.log.critical("Restarting Pool. One check is stuck: %s" % name)
252 self.restart_pool()
253 break
254
[end of checks/network_checks.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/checks/network_checks.py b/checks/network_checks.py
--- a/checks/network_checks.py
+++ b/checks/network_checks.py
@@ -3,7 +3,6 @@
# Licensed under Simplified BSD License (see LICENSE)
# stdlib
-from collections import defaultdict
from Queue import Empty, Queue
import threading
import time
@@ -11,7 +10,6 @@
# project
from checks import AgentCheck
from checks.libs.thread_pool import Pool
-from config import _is_affirmative
TIMEOUT = 180
DEFAULT_SIZE_POOL = 6
@@ -183,45 +181,6 @@
continue
self.report_as_service_check(sc_name, status, instance, msg)
-
- # FIXME: 5.3, this has been deprecated before, get rid of events
- # Don't create any event to avoid duplicates with server side
- # service_checks
- skip_event = _is_affirmative(instance.get('skip_event', False))
- if not skip_event:
- self.warning("Using events for service checks is deprecated in favor of monitors and will be removed in future versions of the Datadog Agent.")
- event = None
-
- if instance_name not in self.statuses:
- self.statuses[instance_name] = defaultdict(list)
-
- self.statuses[instance_name][sc_name].append(status)
-
- window = int(instance.get('window', 1))
-
- if window > 256:
- self.log.warning("Maximum window size (256) exceeded, defaulting it to 256")
- window = 256
-
- threshold = instance.get('threshold', 1)
-
- if len(self.statuses[instance_name][sc_name]) > window:
- self.statuses[instance_name][sc_name].pop(0)
-
- nb_failures = self.statuses[instance_name][sc_name].count(Status.DOWN)
-
- if nb_failures >= threshold:
- if self.notified.get((instance_name, sc_name), Status.UP) != Status.DOWN:
- event = self._create_status_event(sc_name, status, msg, instance)
- self.notified[(instance_name, sc_name)] = Status.DOWN
- else:
- if self.notified.get((instance_name, sc_name), Status.UP) != Status.UP:
- event = self._create_status_event(sc_name, status, msg, instance)
- self.notified[(instance_name, sc_name)] = Status.UP
-
- if event is not None:
- self.events.append(event)
-
self._clean_job(instance_name)
def _clean_job(self, instance_name):
| {"golden_diff": "diff --git a/checks/network_checks.py b/checks/network_checks.py\n--- a/checks/network_checks.py\n+++ b/checks/network_checks.py\n@@ -3,7 +3,6 @@\n # Licensed under Simplified BSD License (see LICENSE)\n \n # stdlib\n-from collections import defaultdict\n from Queue import Empty, Queue\n import threading\n import time\n@@ -11,7 +10,6 @@\n # project\n from checks import AgentCheck\n from checks.libs.thread_pool import Pool\n-from config import _is_affirmative\n \n TIMEOUT = 180\n DEFAULT_SIZE_POOL = 6\n@@ -183,45 +181,6 @@\n continue\n \n self.report_as_service_check(sc_name, status, instance, msg)\n-\n- # FIXME: 5.3, this has been deprecated before, get rid of events\n- # Don't create any event to avoid duplicates with server side\n- # service_checks\n- skip_event = _is_affirmative(instance.get('skip_event', False))\n- if not skip_event:\n- self.warning(\"Using events for service checks is deprecated in favor of monitors and will be removed in future versions of the Datadog Agent.\")\n- event = None\n-\n- if instance_name not in self.statuses:\n- self.statuses[instance_name] = defaultdict(list)\n-\n- self.statuses[instance_name][sc_name].append(status)\n-\n- window = int(instance.get('window', 1))\n-\n- if window > 256:\n- self.log.warning(\"Maximum window size (256) exceeded, defaulting it to 256\")\n- window = 256\n-\n- threshold = instance.get('threshold', 1)\n-\n- if len(self.statuses[instance_name][sc_name]) > window:\n- self.statuses[instance_name][sc_name].pop(0)\n-\n- nb_failures = self.statuses[instance_name][sc_name].count(Status.DOWN)\n-\n- if nb_failures >= threshold:\n- if self.notified.get((instance_name, sc_name), Status.UP) != Status.DOWN:\n- event = self._create_status_event(sc_name, status, msg, instance)\n- self.notified[(instance_name, sc_name)] = Status.DOWN\n- else:\n- if self.notified.get((instance_name, sc_name), Status.UP) != Status.UP:\n- event = self._create_status_event(sc_name, status, msg, instance)\n- self.notified[(instance_name, sc_name)] = Status.UP\n-\n- if event is not None:\n- self.events.append(event)\n-\n self._clean_job(instance_name)\n \n def _clean_job(self, instance_name):\n", "issue": "Missing info on fixing: Using events for service checks is deprecated in favor of monitors\nIt seems that you deprecated a feature without putting any information regarding how to fix it. I even googled and the only reference is the source code where you added this warning.\n\nPlease provide some information regarding what changes we are supposed to implement in order not to get these warnings. \n\nThese warnings are showing in the UI:\nhttps://www.dropbox.com/s/xpjpmgqtk71hqze/Screenshot%202014-09-24%2015.43.22.png?dl=0\n\n", "before_files": [{"content": "# (C) Datadog, Inc. 2010-2016\n# All rights reserved\n# Licensed under Simplified BSD License (see LICENSE)\n\n# stdlib\nfrom collections import defaultdict\nfrom Queue import Empty, Queue\nimport threading\nimport time\n\n# project\nfrom checks import AgentCheck\nfrom checks.libs.thread_pool import Pool\nfrom config import _is_affirmative\n\nTIMEOUT = 180\nDEFAULT_SIZE_POOL = 6\nMAX_LOOP_ITERATIONS = 1000\nFAILURE = \"FAILURE\"\n\nclass Status:\n DOWN = \"DOWN\"\n WARNING = \"WARNING\"\n CRITICAL = \"CRITICAL\"\n UP = \"UP\"\n\n\nclass EventType:\n DOWN = \"servicecheck.state_change.down\"\n UP = \"servicecheck.state_change.up\"\n\n\nclass NetworkCheck(AgentCheck):\n SOURCE_TYPE_NAME = 'servicecheck'\n SERVICE_CHECK_PREFIX = 'network_check'\n _global_current_pool_size = 0\n\n STATUS_TO_SERVICE_CHECK = {\n Status.UP : AgentCheck.OK,\n Status.WARNING : AgentCheck.WARNING,\n Status.CRITICAL : AgentCheck.CRITICAL,\n Status.DOWN : AgentCheck.CRITICAL,\n }\n\n \"\"\"\n Services checks inherits from this class.\n This class should never be directly instanciated.\n\n Work flow:\n The main agent loop will call the check function for each instance for\n each iteration of the loop.\n The check method will make an asynchronous call to the _process method in\n one of the thread initiated in the thread pool created in this class constructor.\n The _process method will call the _check method of the inherited class\n which will perform the actual check.\n\n The _check method must return a tuple which first element is either\n Status.UP or Status.DOWN.\n The second element is a short error message that will be displayed\n when the service turns down.\n\n \"\"\"\n\n def __init__(self, name, init_config, agentConfig, instances):\n AgentCheck.__init__(self, name, init_config, agentConfig, instances)\n\n # A dictionary to keep track of service statuses\n self.statuses = {}\n self.notified = {}\n self.nb_failures = 0\n self.pool_size = 0\n self.pool_started = False\n\n # Make sure every instance has a name that we use as a unique key\n # to keep track of statuses\n names = []\n for inst in instances:\n inst_name = inst.get('name', None)\n if not inst_name:\n raise Exception(\"All instances should have a 'name' parameter,\"\n \" error on instance: {0}\".format(inst))\n if inst_name in names:\n raise Exception(\"Duplicate names for instances with name {0}\"\n .format(inst_name))\n names.append(inst_name)\n\n def stop(self):\n self.stop_pool()\n self.pool_started = False\n\n def start_pool(self):\n # The pool size should be the minimum between the number of instances\n # and the DEFAULT_SIZE_POOL. It can also be overridden by the 'threads_count'\n # parameter in the init_config of the check\n self.log.info(\"Starting Thread Pool\")\n default_size = min(self.instance_count(), DEFAULT_SIZE_POOL)\n self.pool_size = int(self.init_config.get('threads_count', default_size))\n\n # To keep track on the total number of threads we should have running\n NetworkCheck._global_current_pool_size += self.pool_size\n\n self.pool = Pool(self.pool_size)\n\n self.resultsq = Queue()\n self.jobs_status = {}\n self.jobs_results = {}\n self.pool_started = True\n\n def stop_pool(self):\n self.log.info(\"Stopping Thread Pool\")\n\n # To keep track on the total number of threads we should have running\n NetworkCheck._global_current_pool_size -= self.pool_size\n\n if self.pool_started:\n self.pool.terminate()\n self.pool.join()\n self.jobs_status.clear()\n assert self.pool.get_nworkers() == 0\n\n def restart_pool(self):\n self.stop_pool()\n self.start_pool()\n\n def check(self, instance):\n if not self.pool_started:\n self.start_pool()\n if threading.activeCount() > 5 * NetworkCheck._global_current_pool_size + 6:\n # On Windows the agent runs on multiple threads because of WMI so we need an offset of 6\n raise Exception(\"Thread number (%s) is exploding. Skipping this check\" % threading.activeCount())\n self._process_results()\n self._clean()\n name = instance.get('name', None)\n if name is None:\n self.log.error('Each service check must have a name')\n return\n\n if name not in self.jobs_status:\n # A given instance should be processed one at a time\n self.jobs_status[name] = time.time()\n self.jobs_results[name] = self.pool.apply_async(self._process, args=(instance,))\n else:\n self.log.error(\"Instance: %s skipped because it's already running.\" % name)\n\n def _process(self, instance):\n try:\n statuses = self._check(instance)\n\n if isinstance(statuses, tuple):\n # Assume the check only returns one service check\n status, msg = statuses\n self.resultsq.put((status, msg, None, instance))\n\n elif isinstance(statuses, list):\n for status in statuses:\n sc_name, status, msg = status\n self.resultsq.put((status, msg, sc_name, instance))\n\n except Exception:\n self.log.exception(\n u\"Failed to process instance '%s'.\", instance.get('name', u\"\")\n )\n result = (FAILURE, FAILURE, FAILURE, instance)\n self.resultsq.put(result)\n\n def _process_results(self):\n for i in xrange(MAX_LOOP_ITERATIONS):\n try:\n # We want to fetch the result in a non blocking way\n status, msg, sc_name, instance = self.resultsq.get_nowait()\n except Empty:\n break\n\n instance_name = instance['name']\n if status == FAILURE:\n self.nb_failures += 1\n if self.nb_failures >= self.pool_size - 1:\n self.nb_failures = 0\n self.restart_pool()\n\n # clean failed job\n self._clean_job(instance_name)\n continue\n\n self.report_as_service_check(sc_name, status, instance, msg)\n\n # FIXME: 5.3, this has been deprecated before, get rid of events\n # Don't create any event to avoid duplicates with server side\n # service_checks\n skip_event = _is_affirmative(instance.get('skip_event', False))\n if not skip_event:\n self.warning(\"Using events for service checks is deprecated in favor of monitors and will be removed in future versions of the Datadog Agent.\")\n event = None\n\n if instance_name not in self.statuses:\n self.statuses[instance_name] = defaultdict(list)\n\n self.statuses[instance_name][sc_name].append(status)\n\n window = int(instance.get('window', 1))\n\n if window > 256:\n self.log.warning(\"Maximum window size (256) exceeded, defaulting it to 256\")\n window = 256\n\n threshold = instance.get('threshold', 1)\n\n if len(self.statuses[instance_name][sc_name]) > window:\n self.statuses[instance_name][sc_name].pop(0)\n\n nb_failures = self.statuses[instance_name][sc_name].count(Status.DOWN)\n\n if nb_failures >= threshold:\n if self.notified.get((instance_name, sc_name), Status.UP) != Status.DOWN:\n event = self._create_status_event(sc_name, status, msg, instance)\n self.notified[(instance_name, sc_name)] = Status.DOWN\n else:\n if self.notified.get((instance_name, sc_name), Status.UP) != Status.UP:\n event = self._create_status_event(sc_name, status, msg, instance)\n self.notified[(instance_name, sc_name)] = Status.UP\n\n if event is not None:\n self.events.append(event)\n\n self._clean_job(instance_name)\n\n def _clean_job(self, instance_name):\n # The job is finished here, this instance can be re processed\n if instance_name in self.jobs_status:\n self.log.debug(\"Instance: %s cleaned from jobs status.\" % instance_name)\n del self.jobs_status[instance_name]\n\n # if an exception happened, log it\n if instance_name in self.jobs_results:\n self.log.debug(\"Instance: %s cleaned from jobs results.\" % instance_name)\n ret = self.jobs_results[instance_name].get()\n if isinstance(ret, Exception):\n self.log.exception(\"Exception in worker thread: {0}\".format(ret))\n del self.jobs_results[instance_name]\n\n\n def _check(self, instance):\n \"\"\"This function should be implemented by inherited classes\"\"\"\n raise NotImplementedError\n\n\n def _clean(self):\n now = time.time()\n for name, start_time in self.jobs_status.iteritems():\n if now - start_time > TIMEOUT:\n self.log.critical(\"Restarting Pool. One check is stuck: %s\" % name)\n self.restart_pool()\n break\n", "path": "checks/network_checks.py"}]} | 3,317 | 593 |
gh_patches_debug_27241 | rasdani/github-patches | git_diff | Kinto__kinto-1025 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Should the cache backend even use transactions?
mozilla-services/kinto-fxa#33 seems to be related to the fact that we're opening a transaction to consult the authentication cache. Is this really necessary? It seems like for a cache, we don't need any of the ACID properties. /cc @leplatrem
Should the cache backend even use transactions?
mozilla-services/kinto-fxa#33 seems to be related to the fact that we're opening a transaction to consult the authentication cache. Is this really necessary? It seems like for a cache, we don't need any of the ACID properties. /cc @leplatrem
</issue>
<code>
[start of kinto/core/storage/postgresql/client.py]
1 import contextlib
2 import warnings
3 from collections import defaultdict
4
5 from kinto.core import logger
6 from kinto.core.storage import exceptions
7 from kinto.core.utils import sqlalchemy
8 import transaction as zope_transaction
9
10
11 class PostgreSQLClient(object):
12 def __init__(self, session_factory, commit_manually=True, invalidate=None):
13 self.session_factory = session_factory
14 self.commit_manually = commit_manually
15 self.invalidate = invalidate or (lambda session: None)
16
17 # # Register ujson, globally for all futur cursors
18 # with self.connect() as cursor:
19 # psycopg2.extras.register_json(cursor,
20 # globally=True,
21 # loads=json.loads)
22
23 @contextlib.contextmanager
24 def connect(self, readonly=False, force_commit=False):
25 """
26 Pulls a connection from the pool when context is entered and
27 returns it when context is exited.
28
29 A COMMIT is performed on the current transaction if everything went
30 well. Otherwise transaction is ROLLBACK, and everything cleaned up.
31 """
32 with_transaction = not readonly and self.commit_manually
33 session = None
34 try:
35 # Pull connection from pool.
36 session = self.session_factory()
37 # Start context
38 yield session
39 if not readonly and not self.commit_manually:
40 # Mark session as dirty.
41 self.invalidate(session)
42 # Success
43 if with_transaction:
44 session.commit()
45 elif force_commit:
46 # Commit like would do a succesful request.
47 zope_transaction.commit()
48
49 except sqlalchemy.exc.SQLAlchemyError as e:
50 logger.error(e)
51 if session and with_transaction:
52 session.rollback()
53 raise exceptions.BackendError(original=e)
54
55 finally:
56 if session and self.commit_manually:
57 # Give back to pool if commit done manually.
58 session.close()
59
60
61 # Reuse existing client if same URL.
62 _CLIENTS = defaultdict(dict)
63
64
65 def create_from_config(config, prefix=''):
66 """Create a PostgreSQLClient client using settings in the provided config.
67 """
68 if sqlalchemy is None:
69 message = ("PostgreSQL SQLAlchemy dependency missing. "
70 "Refer to installation section in documentation.")
71 raise ImportWarning(message)
72
73 from zope.sqlalchemy import ZopeTransactionExtension, invalidate
74 from sqlalchemy.orm import sessionmaker, scoped_session
75
76 settings = config.get_settings().copy()
77 # Custom Kinto settings, unsupported by SQLAlchemy.
78 settings.pop(prefix + 'backend', None)
79 settings.pop(prefix + 'max_fetch_size', None)
80 settings.pop(prefix + 'prefix', None)
81 transaction_per_request = settings.pop('transaction_per_request', False)
82
83 url = settings[prefix + 'url']
84 existing_client = _CLIENTS[transaction_per_request].get(url)
85 if existing_client:
86 msg = ("Reuse existing PostgreSQL connection. "
87 "Parameters %s* will be ignored." % prefix)
88 warnings.warn(msg)
89 return existing_client
90
91 # Initialize SQLAlchemy engine from settings.
92 poolclass_key = prefix + 'poolclass'
93 settings.setdefault(poolclass_key, ('kinto.core.storage.postgresql.'
94 'pool.QueuePoolWithMaxBacklog'))
95 settings[poolclass_key] = config.maybe_dotted(settings[poolclass_key])
96 engine = sqlalchemy.engine_from_config(settings, prefix=prefix, url=url)
97
98 # Initialize thread-safe session factory.
99 options = {}
100 if transaction_per_request:
101 # Plug with Pyramid transaction manager
102 options['extension'] = ZopeTransactionExtension()
103 session_factory = scoped_session(sessionmaker(bind=engine, **options))
104
105 # Store one client per URI.
106 commit_manually = (not transaction_per_request)
107 client = PostgreSQLClient(session_factory, commit_manually, invalidate)
108 _CLIENTS[transaction_per_request][url] = client
109 return client
110
[end of kinto/core/storage/postgresql/client.py]
[start of kinto/core/cache/postgresql/__init__.py]
1 from __future__ import absolute_import
2
3 import os
4
5 from kinto.core import logger
6 from kinto.core.cache import CacheBase
7 from kinto.core.storage.postgresql.client import create_from_config
8 from kinto.core.utils import json
9
10
11 class Cache(CacheBase):
12 """Cache backend using PostgreSQL.
13
14 Enable in configuration::
15
16 kinto.cache_backend = kinto.core.cache.postgresql
17
18 Database location URI can be customized::
19
20 kinto.cache_url = postgres://user:[email protected]:5432/dbname
21
22 Alternatively, username and password could also rely on system user ident
23 or even specified in :file:`~/.pgpass` (*see PostgreSQL documentation*).
24
25 .. note::
26
27 Some tables and indices are created when ``kinto migrate`` is run.
28 This requires some privileges on the database, or some error will
29 be raised.
30
31 **Alternatively**, the schema can be initialized outside the
32 python application, using the SQL file located in
33 :file:`kinto/core/cache/postgresql/schema.sql`. This allows to
34 distinguish schema manipulation privileges from schema usage.
35
36
37 A connection pool is enabled by default::
38
39 kinto.cache_pool_size = 10
40 kinto.cache_maxoverflow = 10
41 kinto.cache_max_backlog = -1
42 kinto.cache_pool_recycle = -1
43 kinto.cache_pool_timeout = 30
44 kinto.cache_poolclass =
45 kinto.core.storage.postgresql.pool.QueuePoolWithMaxBacklog
46
47 The ``max_backlog`` limits the number of threads that can be in the queue
48 waiting for a connection. Once this limit has been reached, any further
49 attempts to acquire a connection will be rejected immediately, instead of
50 locking up all threads by keeping them waiting in the queue.
51
52 See `dedicated section in SQLAlchemy documentation
53 <http://docs.sqlalchemy.org/en/rel_1_0/core/engines.html>`_
54 for default values and behaviour.
55
56 .. note::
57
58 Using a `dedicated connection pool <http://pgpool.net>`_ is still
59 recommended to allow load balancing, replication or limit the number
60 of connections used in a multi-process deployment.
61
62 :noindex:
63 """ # NOQA
64 def __init__(self, client, *args, **kwargs):
65 super(Cache, self).__init__(*args, **kwargs)
66 self.client = client
67
68 def initialize_schema(self, dry_run=False):
69 # Check if cache table exists.
70 query = """
71 SELECT 1
72 FROM information_schema.tables
73 WHERE table_name = 'cache';
74 """
75 with self.client.connect(readonly=True) as conn:
76 result = conn.execute(query)
77 if result.rowcount > 0:
78 logger.info("PostgreSQL cache schema is up-to-date.")
79 return
80
81 # Create schema
82 here = os.path.abspath(os.path.dirname(__file__))
83 sql_file = os.path.join(here, 'schema.sql')
84
85 if dry_run:
86 logger.info("Create cache schema from %s" % sql_file)
87 return
88
89 # Since called outside request, force commit.
90 schema = open(sql_file).read()
91 with self.client.connect(force_commit=True) as conn:
92 conn.execute(schema)
93 logger.info('Created PostgreSQL cache tables')
94
95 def flush(self):
96 query = """
97 DELETE FROM cache;
98 """
99 # Since called outside request (e.g. tests), force commit.
100 with self.client.connect(force_commit=True) as conn:
101 conn.execute(query)
102 logger.debug('Flushed PostgreSQL cache tables')
103
104 def ttl(self, key):
105 query = """
106 SELECT EXTRACT(SECOND FROM (ttl - now())) AS ttl
107 FROM cache
108 WHERE key = :key
109 AND ttl IS NOT NULL;
110 """
111 with self.client.connect(readonly=True) as conn:
112 result = conn.execute(query, dict(key=self.prefix + key))
113 if result.rowcount > 0:
114 return result.fetchone()['ttl']
115 return -1
116
117 def expire(self, key, ttl):
118 query = """
119 UPDATE cache SET ttl = sec2ttl(:ttl) WHERE key = :key;
120 """
121 with self.client.connect() as conn:
122 conn.execute(query, dict(ttl=ttl, key=self.prefix + key))
123
124 def set(self, key, value, ttl=None):
125 if ttl is None:
126 logger.warning("No TTL for cache key %r" % key)
127 query = """
128 WITH upsert AS (
129 UPDATE cache SET value = :value, ttl = sec2ttl(:ttl)
130 WHERE key=:key
131 RETURNING *)
132 INSERT INTO cache (key, value, ttl)
133 SELECT :key, :value, sec2ttl(:ttl)
134 WHERE NOT EXISTS (SELECT * FROM upsert)
135 """
136 value = json.dumps(value)
137 with self.client.connect() as conn:
138 conn.execute(query, dict(key=self.prefix + key,
139 value=value, ttl=ttl))
140
141 def get(self, key):
142 purge = "DELETE FROM cache WHERE ttl IS NOT NULL AND now() > ttl;"
143 query = "SELECT value FROM cache WHERE key = :key;"
144 with self.client.connect() as conn:
145 conn.execute(purge)
146 result = conn.execute(query, dict(key=self.prefix + key))
147 if result.rowcount > 0:
148 value = result.fetchone()['value']
149 return json.loads(value)
150
151 def delete(self, key):
152 query = "DELETE FROM cache WHERE key = :key"
153 with self.client.connect() as conn:
154 conn.execute(query, dict(key=self.prefix + key))
155
156
157 def load_from_config(config):
158 settings = config.get_settings()
159 client = create_from_config(config, prefix='cache_')
160 return Cache(client=client, cache_prefix=settings['cache_prefix'])
161
[end of kinto/core/cache/postgresql/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/kinto/core/cache/postgresql/__init__.py b/kinto/core/cache/postgresql/__init__.py
--- a/kinto/core/cache/postgresql/__init__.py
+++ b/kinto/core/cache/postgresql/__init__.py
@@ -156,5 +156,5 @@
def load_from_config(config):
settings = config.get_settings()
- client = create_from_config(config, prefix='cache_')
+ client = create_from_config(config, prefix='cache_', with_transaction=False)
return Cache(client=client, cache_prefix=settings['cache_prefix'])
diff --git a/kinto/core/storage/postgresql/client.py b/kinto/core/storage/postgresql/client.py
--- a/kinto/core/storage/postgresql/client.py
+++ b/kinto/core/storage/postgresql/client.py
@@ -62,7 +62,7 @@
_CLIENTS = defaultdict(dict)
-def create_from_config(config, prefix=''):
+def create_from_config(config, prefix='', with_transaction=True):
"""Create a PostgreSQLClient client using settings in the provided config.
"""
if sqlalchemy is None:
@@ -77,8 +77,9 @@
# Custom Kinto settings, unsupported by SQLAlchemy.
settings.pop(prefix + 'backend', None)
settings.pop(prefix + 'max_fetch_size', None)
+ settings.pop(prefix + 'max_size_bytes', None)
settings.pop(prefix + 'prefix', None)
- transaction_per_request = settings.pop('transaction_per_request', False)
+ transaction_per_request = with_transaction and settings.pop('transaction_per_request', False)
url = settings[prefix + 'url']
existing_client = _CLIENTS[transaction_per_request].get(url)
| {"golden_diff": "diff --git a/kinto/core/cache/postgresql/__init__.py b/kinto/core/cache/postgresql/__init__.py\n--- a/kinto/core/cache/postgresql/__init__.py\n+++ b/kinto/core/cache/postgresql/__init__.py\n@@ -156,5 +156,5 @@\n \n def load_from_config(config):\n settings = config.get_settings()\n- client = create_from_config(config, prefix='cache_')\n+ client = create_from_config(config, prefix='cache_', with_transaction=False)\n return Cache(client=client, cache_prefix=settings['cache_prefix'])\ndiff --git a/kinto/core/storage/postgresql/client.py b/kinto/core/storage/postgresql/client.py\n--- a/kinto/core/storage/postgresql/client.py\n+++ b/kinto/core/storage/postgresql/client.py\n@@ -62,7 +62,7 @@\n _CLIENTS = defaultdict(dict)\n \n \n-def create_from_config(config, prefix=''):\n+def create_from_config(config, prefix='', with_transaction=True):\n \"\"\"Create a PostgreSQLClient client using settings in the provided config.\n \"\"\"\n if sqlalchemy is None:\n@@ -77,8 +77,9 @@\n # Custom Kinto settings, unsupported by SQLAlchemy.\n settings.pop(prefix + 'backend', None)\n settings.pop(prefix + 'max_fetch_size', None)\n+ settings.pop(prefix + 'max_size_bytes', None)\n settings.pop(prefix + 'prefix', None)\n- transaction_per_request = settings.pop('transaction_per_request', False)\n+ transaction_per_request = with_transaction and settings.pop('transaction_per_request', False)\n \n url = settings[prefix + 'url']\n existing_client = _CLIENTS[transaction_per_request].get(url)\n", "issue": "Should the cache backend even use transactions?\nmozilla-services/kinto-fxa#33 seems to be related to the fact that we're opening a transaction to consult the authentication cache. Is this really necessary? It seems like for a cache, we don't need any of the ACID properties. /cc @leplatrem \n\nShould the cache backend even use transactions?\nmozilla-services/kinto-fxa#33 seems to be related to the fact that we're opening a transaction to consult the authentication cache. Is this really necessary? It seems like for a cache, we don't need any of the ACID properties. /cc @leplatrem \n\n", "before_files": [{"content": "import contextlib\nimport warnings\nfrom collections import defaultdict\n\nfrom kinto.core import logger\nfrom kinto.core.storage import exceptions\nfrom kinto.core.utils import sqlalchemy\nimport transaction as zope_transaction\n\n\nclass PostgreSQLClient(object):\n def __init__(self, session_factory, commit_manually=True, invalidate=None):\n self.session_factory = session_factory\n self.commit_manually = commit_manually\n self.invalidate = invalidate or (lambda session: None)\n\n # # Register ujson, globally for all futur cursors\n # with self.connect() as cursor:\n # psycopg2.extras.register_json(cursor,\n # globally=True,\n # loads=json.loads)\n\n @contextlib.contextmanager\n def connect(self, readonly=False, force_commit=False):\n \"\"\"\n Pulls a connection from the pool when context is entered and\n returns it when context is exited.\n\n A COMMIT is performed on the current transaction if everything went\n well. Otherwise transaction is ROLLBACK, and everything cleaned up.\n \"\"\"\n with_transaction = not readonly and self.commit_manually\n session = None\n try:\n # Pull connection from pool.\n session = self.session_factory()\n # Start context\n yield session\n if not readonly and not self.commit_manually:\n # Mark session as dirty.\n self.invalidate(session)\n # Success\n if with_transaction:\n session.commit()\n elif force_commit:\n # Commit like would do a succesful request.\n zope_transaction.commit()\n\n except sqlalchemy.exc.SQLAlchemyError as e:\n logger.error(e)\n if session and with_transaction:\n session.rollback()\n raise exceptions.BackendError(original=e)\n\n finally:\n if session and self.commit_manually:\n # Give back to pool if commit done manually.\n session.close()\n\n\n# Reuse existing client if same URL.\n_CLIENTS = defaultdict(dict)\n\n\ndef create_from_config(config, prefix=''):\n \"\"\"Create a PostgreSQLClient client using settings in the provided config.\n \"\"\"\n if sqlalchemy is None:\n message = (\"PostgreSQL SQLAlchemy dependency missing. \"\n \"Refer to installation section in documentation.\")\n raise ImportWarning(message)\n\n from zope.sqlalchemy import ZopeTransactionExtension, invalidate\n from sqlalchemy.orm import sessionmaker, scoped_session\n\n settings = config.get_settings().copy()\n # Custom Kinto settings, unsupported by SQLAlchemy.\n settings.pop(prefix + 'backend', None)\n settings.pop(prefix + 'max_fetch_size', None)\n settings.pop(prefix + 'prefix', None)\n transaction_per_request = settings.pop('transaction_per_request', False)\n\n url = settings[prefix + 'url']\n existing_client = _CLIENTS[transaction_per_request].get(url)\n if existing_client:\n msg = (\"Reuse existing PostgreSQL connection. \"\n \"Parameters %s* will be ignored.\" % prefix)\n warnings.warn(msg)\n return existing_client\n\n # Initialize SQLAlchemy engine from settings.\n poolclass_key = prefix + 'poolclass'\n settings.setdefault(poolclass_key, ('kinto.core.storage.postgresql.'\n 'pool.QueuePoolWithMaxBacklog'))\n settings[poolclass_key] = config.maybe_dotted(settings[poolclass_key])\n engine = sqlalchemy.engine_from_config(settings, prefix=prefix, url=url)\n\n # Initialize thread-safe session factory.\n options = {}\n if transaction_per_request:\n # Plug with Pyramid transaction manager\n options['extension'] = ZopeTransactionExtension()\n session_factory = scoped_session(sessionmaker(bind=engine, **options))\n\n # Store one client per URI.\n commit_manually = (not transaction_per_request)\n client = PostgreSQLClient(session_factory, commit_manually, invalidate)\n _CLIENTS[transaction_per_request][url] = client\n return client\n", "path": "kinto/core/storage/postgresql/client.py"}, {"content": "from __future__ import absolute_import\n\nimport os\n\nfrom kinto.core import logger\nfrom kinto.core.cache import CacheBase\nfrom kinto.core.storage.postgresql.client import create_from_config\nfrom kinto.core.utils import json\n\n\nclass Cache(CacheBase):\n \"\"\"Cache backend using PostgreSQL.\n\n Enable in configuration::\n\n kinto.cache_backend = kinto.core.cache.postgresql\n\n Database location URI can be customized::\n\n kinto.cache_url = postgres://user:[email protected]:5432/dbname\n\n Alternatively, username and password could also rely on system user ident\n or even specified in :file:`~/.pgpass` (*see PostgreSQL documentation*).\n\n .. note::\n\n Some tables and indices are created when ``kinto migrate`` is run.\n This requires some privileges on the database, or some error will\n be raised.\n\n **Alternatively**, the schema can be initialized outside the\n python application, using the SQL file located in\n :file:`kinto/core/cache/postgresql/schema.sql`. This allows to\n distinguish schema manipulation privileges from schema usage.\n\n\n A connection pool is enabled by default::\n\n kinto.cache_pool_size = 10\n kinto.cache_maxoverflow = 10\n kinto.cache_max_backlog = -1\n kinto.cache_pool_recycle = -1\n kinto.cache_pool_timeout = 30\n kinto.cache_poolclass =\n kinto.core.storage.postgresql.pool.QueuePoolWithMaxBacklog\n\n The ``max_backlog`` limits the number of threads that can be in the queue\n waiting for a connection. Once this limit has been reached, any further\n attempts to acquire a connection will be rejected immediately, instead of\n locking up all threads by keeping them waiting in the queue.\n\n See `dedicated section in SQLAlchemy documentation\n <http://docs.sqlalchemy.org/en/rel_1_0/core/engines.html>`_\n for default values and behaviour.\n\n .. note::\n\n Using a `dedicated connection pool <http://pgpool.net>`_ is still\n recommended to allow load balancing, replication or limit the number\n of connections used in a multi-process deployment.\n\n :noindex:\n \"\"\" # NOQA\n def __init__(self, client, *args, **kwargs):\n super(Cache, self).__init__(*args, **kwargs)\n self.client = client\n\n def initialize_schema(self, dry_run=False):\n # Check if cache table exists.\n query = \"\"\"\n SELECT 1\n FROM information_schema.tables\n WHERE table_name = 'cache';\n \"\"\"\n with self.client.connect(readonly=True) as conn:\n result = conn.execute(query)\n if result.rowcount > 0:\n logger.info(\"PostgreSQL cache schema is up-to-date.\")\n return\n\n # Create schema\n here = os.path.abspath(os.path.dirname(__file__))\n sql_file = os.path.join(here, 'schema.sql')\n\n if dry_run:\n logger.info(\"Create cache schema from %s\" % sql_file)\n return\n\n # Since called outside request, force commit.\n schema = open(sql_file).read()\n with self.client.connect(force_commit=True) as conn:\n conn.execute(schema)\n logger.info('Created PostgreSQL cache tables')\n\n def flush(self):\n query = \"\"\"\n DELETE FROM cache;\n \"\"\"\n # Since called outside request (e.g. tests), force commit.\n with self.client.connect(force_commit=True) as conn:\n conn.execute(query)\n logger.debug('Flushed PostgreSQL cache tables')\n\n def ttl(self, key):\n query = \"\"\"\n SELECT EXTRACT(SECOND FROM (ttl - now())) AS ttl\n FROM cache\n WHERE key = :key\n AND ttl IS NOT NULL;\n \"\"\"\n with self.client.connect(readonly=True) as conn:\n result = conn.execute(query, dict(key=self.prefix + key))\n if result.rowcount > 0:\n return result.fetchone()['ttl']\n return -1\n\n def expire(self, key, ttl):\n query = \"\"\"\n UPDATE cache SET ttl = sec2ttl(:ttl) WHERE key = :key;\n \"\"\"\n with self.client.connect() as conn:\n conn.execute(query, dict(ttl=ttl, key=self.prefix + key))\n\n def set(self, key, value, ttl=None):\n if ttl is None:\n logger.warning(\"No TTL for cache key %r\" % key)\n query = \"\"\"\n WITH upsert AS (\n UPDATE cache SET value = :value, ttl = sec2ttl(:ttl)\n WHERE key=:key\n RETURNING *)\n INSERT INTO cache (key, value, ttl)\n SELECT :key, :value, sec2ttl(:ttl)\n WHERE NOT EXISTS (SELECT * FROM upsert)\n \"\"\"\n value = json.dumps(value)\n with self.client.connect() as conn:\n conn.execute(query, dict(key=self.prefix + key,\n value=value, ttl=ttl))\n\n def get(self, key):\n purge = \"DELETE FROM cache WHERE ttl IS NOT NULL AND now() > ttl;\"\n query = \"SELECT value FROM cache WHERE key = :key;\"\n with self.client.connect() as conn:\n conn.execute(purge)\n result = conn.execute(query, dict(key=self.prefix + key))\n if result.rowcount > 0:\n value = result.fetchone()['value']\n return json.loads(value)\n\n def delete(self, key):\n query = \"DELETE FROM cache WHERE key = :key\"\n with self.client.connect() as conn:\n conn.execute(query, dict(key=self.prefix + key))\n\n\ndef load_from_config(config):\n settings = config.get_settings()\n client = create_from_config(config, prefix='cache_')\n return Cache(client=client, cache_prefix=settings['cache_prefix'])\n", "path": "kinto/core/cache/postgresql/__init__.py"}]} | 3,358 | 359 |
gh_patches_debug_32478 | rasdani/github-patches | git_diff | open-telemetry__opentelemetry-python-2080 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
format_baggage does not escape non-ascii in baggage keys
https://github.com/open-telemetry/opentelemetry-python/blob/4250078e43ddb24c88e19270c7af01ae63336fb9/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py#L100
The cpp implementation does this, and it looks like in python test strings there is url encoding.
https://github.com/open-telemetry/opentelemetry-cpp/blob/61d3c5e318830d10a0859befa046aa4847593764/api/include/opentelemetry/baggage/baggage.h#L174
</issue>
<code>
[start of opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py]
1 # Copyright The OpenTelemetry Authors
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 #
15 import typing
16 import urllib.parse
17
18 from opentelemetry import baggage
19 from opentelemetry.context import get_current
20 from opentelemetry.context.context import Context
21 from opentelemetry.propagators import textmap
22
23
24 class W3CBaggagePropagator(textmap.TextMapPropagator):
25 """Extracts and injects Baggage which is used to annotate telemetry."""
26
27 _MAX_HEADER_LENGTH = 8192
28 _MAX_PAIR_LENGTH = 4096
29 _MAX_PAIRS = 180
30 _BAGGAGE_HEADER_NAME = "baggage"
31
32 def extract(
33 self,
34 carrier: textmap.CarrierT,
35 context: typing.Optional[Context] = None,
36 getter: textmap.Getter = textmap.default_getter,
37 ) -> Context:
38 """Extract Baggage from the carrier.
39
40 See
41 `opentelemetry.propagators.textmap.TextMapPropagator.extract`
42 """
43
44 if context is None:
45 context = get_current()
46
47 header = _extract_first_element(
48 getter.get(carrier, self._BAGGAGE_HEADER_NAME)
49 )
50
51 if not header or len(header) > self._MAX_HEADER_LENGTH:
52 return context
53
54 baggage_entries = header.split(",")
55 total_baggage_entries = self._MAX_PAIRS
56 for entry in baggage_entries:
57 if total_baggage_entries <= 0:
58 return context
59 total_baggage_entries -= 1
60 if len(entry) > self._MAX_PAIR_LENGTH:
61 continue
62 try:
63 name, value = entry.split("=", 1)
64 except Exception: # pylint: disable=broad-except
65 continue
66 context = baggage.set_baggage(
67 urllib.parse.unquote(name).strip(),
68 urllib.parse.unquote(value).strip(),
69 context=context,
70 )
71
72 return context
73
74 def inject(
75 self,
76 carrier: textmap.CarrierT,
77 context: typing.Optional[Context] = None,
78 setter: textmap.Setter = textmap.default_setter,
79 ) -> None:
80 """Injects Baggage into the carrier.
81
82 See
83 `opentelemetry.propagators.textmap.TextMapPropagator.inject`
84 """
85 baggage_entries = baggage.get_all(context=context)
86 if not baggage_entries:
87 return
88
89 baggage_string = _format_baggage(baggage_entries)
90 setter.set(carrier, self._BAGGAGE_HEADER_NAME, baggage_string)
91
92 @property
93 def fields(self) -> typing.Set[str]:
94 """Returns a set with the fields set in `inject`."""
95 return {self._BAGGAGE_HEADER_NAME}
96
97
98 def _format_baggage(baggage_entries: typing.Mapping[str, object]) -> str:
99 return ",".join(
100 key + "=" + urllib.parse.quote_plus(str(value))
101 for key, value in baggage_entries.items()
102 )
103
104
105 def _extract_first_element(
106 items: typing.Optional[typing.Iterable[textmap.CarrierT]],
107 ) -> typing.Optional[textmap.CarrierT]:
108 if items is None:
109 return None
110 return next(iter(items), None)
111
[end of opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py b/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py
--- a/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py
+++ b/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py
@@ -13,9 +13,9 @@
# limitations under the License.
#
import typing
-import urllib.parse
+from urllib.parse import quote_plus, unquote_plus
-from opentelemetry import baggage
+from opentelemetry.baggage import get_all, set_baggage
from opentelemetry.context import get_current
from opentelemetry.context.context import Context
from opentelemetry.propagators import textmap
@@ -63,9 +63,9 @@
name, value = entry.split("=", 1)
except Exception: # pylint: disable=broad-except
continue
- context = baggage.set_baggage(
- urllib.parse.unquote(name).strip(),
- urllib.parse.unquote(value).strip(),
+ context = set_baggage(
+ unquote_plus(name).strip(),
+ unquote_plus(value).strip(),
context=context,
)
@@ -82,7 +82,7 @@
See
`opentelemetry.propagators.textmap.TextMapPropagator.inject`
"""
- baggage_entries = baggage.get_all(context=context)
+ baggage_entries = get_all(context=context)
if not baggage_entries:
return
@@ -97,7 +97,7 @@
def _format_baggage(baggage_entries: typing.Mapping[str, object]) -> str:
return ",".join(
- key + "=" + urllib.parse.quote_plus(str(value))
+ quote_plus(str(key)) + "=" + quote_plus(str(value))
for key, value in baggage_entries.items()
)
| {"golden_diff": "diff --git a/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py b/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py\n--- a/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py\n+++ b/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py\n@@ -13,9 +13,9 @@\n # limitations under the License.\n #\n import typing\n-import urllib.parse\n+from urllib.parse import quote_plus, unquote_plus\n \n-from opentelemetry import baggage\n+from opentelemetry.baggage import get_all, set_baggage\n from opentelemetry.context import get_current\n from opentelemetry.context.context import Context\n from opentelemetry.propagators import textmap\n@@ -63,9 +63,9 @@\n name, value = entry.split(\"=\", 1)\n except Exception: # pylint: disable=broad-except\n continue\n- context = baggage.set_baggage(\n- urllib.parse.unquote(name).strip(),\n- urllib.parse.unquote(value).strip(),\n+ context = set_baggage(\n+ unquote_plus(name).strip(),\n+ unquote_plus(value).strip(),\n context=context,\n )\n \n@@ -82,7 +82,7 @@\n See\n `opentelemetry.propagators.textmap.TextMapPropagator.inject`\n \"\"\"\n- baggage_entries = baggage.get_all(context=context)\n+ baggage_entries = get_all(context=context)\n if not baggage_entries:\n return\n \n@@ -97,7 +97,7 @@\n \n def _format_baggage(baggage_entries: typing.Mapping[str, object]) -> str:\n return \",\".join(\n- key + \"=\" + urllib.parse.quote_plus(str(value))\n+ quote_plus(str(key)) + \"=\" + quote_plus(str(value))\n for key, value in baggage_entries.items()\n )\n", "issue": "format_baggage does not escape non-ascii in baggage keys\nhttps://github.com/open-telemetry/opentelemetry-python/blob/4250078e43ddb24c88e19270c7af01ae63336fb9/opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py#L100\r\n\r\nThe cpp implementation does this, and it looks like in python test strings there is url encoding.\r\nhttps://github.com/open-telemetry/opentelemetry-cpp/blob/61d3c5e318830d10a0859befa046aa4847593764/api/include/opentelemetry/baggage/baggage.h#L174\n", "before_files": [{"content": "# Copyright The OpenTelemetry Authors\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n#\nimport typing\nimport urllib.parse\n\nfrom opentelemetry import baggage\nfrom opentelemetry.context import get_current\nfrom opentelemetry.context.context import Context\nfrom opentelemetry.propagators import textmap\n\n\nclass W3CBaggagePropagator(textmap.TextMapPropagator):\n \"\"\"Extracts and injects Baggage which is used to annotate telemetry.\"\"\"\n\n _MAX_HEADER_LENGTH = 8192\n _MAX_PAIR_LENGTH = 4096\n _MAX_PAIRS = 180\n _BAGGAGE_HEADER_NAME = \"baggage\"\n\n def extract(\n self,\n carrier: textmap.CarrierT,\n context: typing.Optional[Context] = None,\n getter: textmap.Getter = textmap.default_getter,\n ) -> Context:\n \"\"\"Extract Baggage from the carrier.\n\n See\n `opentelemetry.propagators.textmap.TextMapPropagator.extract`\n \"\"\"\n\n if context is None:\n context = get_current()\n\n header = _extract_first_element(\n getter.get(carrier, self._BAGGAGE_HEADER_NAME)\n )\n\n if not header or len(header) > self._MAX_HEADER_LENGTH:\n return context\n\n baggage_entries = header.split(\",\")\n total_baggage_entries = self._MAX_PAIRS\n for entry in baggage_entries:\n if total_baggage_entries <= 0:\n return context\n total_baggage_entries -= 1\n if len(entry) > self._MAX_PAIR_LENGTH:\n continue\n try:\n name, value = entry.split(\"=\", 1)\n except Exception: # pylint: disable=broad-except\n continue\n context = baggage.set_baggage(\n urllib.parse.unquote(name).strip(),\n urllib.parse.unquote(value).strip(),\n context=context,\n )\n\n return context\n\n def inject(\n self,\n carrier: textmap.CarrierT,\n context: typing.Optional[Context] = None,\n setter: textmap.Setter = textmap.default_setter,\n ) -> None:\n \"\"\"Injects Baggage into the carrier.\n\n See\n `opentelemetry.propagators.textmap.TextMapPropagator.inject`\n \"\"\"\n baggage_entries = baggage.get_all(context=context)\n if not baggage_entries:\n return\n\n baggage_string = _format_baggage(baggage_entries)\n setter.set(carrier, self._BAGGAGE_HEADER_NAME, baggage_string)\n\n @property\n def fields(self) -> typing.Set[str]:\n \"\"\"Returns a set with the fields set in `inject`.\"\"\"\n return {self._BAGGAGE_HEADER_NAME}\n\n\ndef _format_baggage(baggage_entries: typing.Mapping[str, object]) -> str:\n return \",\".join(\n key + \"=\" + urllib.parse.quote_plus(str(value))\n for key, value in baggage_entries.items()\n )\n\n\ndef _extract_first_element(\n items: typing.Optional[typing.Iterable[textmap.CarrierT]],\n) -> typing.Optional[textmap.CarrierT]:\n if items is None:\n return None\n return next(iter(items), None)\n", "path": "opentelemetry-api/src/opentelemetry/baggage/propagation/__init__.py"}]} | 1,760 | 419 |
gh_patches_debug_3291 | rasdani/github-patches | git_diff | DataDog__dd-trace-py-2708 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
0.50 bug sanic APM
Thanks for taking the time for reporting an issue!
Before reporting an issue on dd-trace-py, please be sure to provide all
necessary information.
If you're hitting a bug, make sure that you're using the latest version of this
library.
### Which version of dd-trace-py are you using?
0.50.0
### Which version of pip are you using?
19.0.3
### Which version of the libraries are you using?
Package Version
------------------- ---------
aiofiles 0.7.0
aiohttp 3.6.2
aiomysql 0.0.20
astroid 2.3.3
async-timeout 3.0.1
attrs 19.3.0
certifi 2019.9.11
cffi 1.13.2
chardet 3.0.4
Click 7.0
cryptography 2.8
ddtrace 0.50.0
Deprecated 1.2.11
elasticsearch 7.5.1
elasticsearch-async 6.2.0
h11 0.8.1
h2 3.1.1
hpack 3.0.0
hstspreload 2020.1.7
httpcore 0.3.0
httptools 0.0.13
httpx 0.9.3
hyperframe 5.2.0
idna 2.8
isort 4.3.21
lazy-object-proxy 1.4.3
mccabe 0.6.1
motor 2.4.0
multidict 5.1.0
packaging 21.0
peewee 3.13.1
pip 19.0.3
protobuf 3.17.3
pycparser 2.19
PyJWT 1.7.1
pymongo 3.11.4
PyMySQL 0.9.2
pyparsing 2.4.7
pytz 2019.3
PyYAML 5.3
requests 2.22.0
requests-async 0.5.0
rfc3986 1.3.2
sanic 21.3.4
sanic-motor 0.5.0
sanic-routing 0.6.2
sanic-scheduler 1.0.7
setuptools 40.8.0
six 1.14.0
sniffio 1.1.0
stringcase 1.2.0
tenacity 8.0.1
typed-ast 1.4.1
ujson 1.35
urllib3 1.25.6
uvloop 0.13.0
websockets 8.1
wrapt 1.11.2
yarl 1.4.2
### How can we reproduce your problem?
#### Description
It's not working patch when apply APM on Sanic
If path variable type is int on sanic route
Case code
```
@app.route('/<gam_id:int>/slot/count', methods=['GET'])
async def slot_count(request, gam_id):
try:
pass
except Exception as e:
abort(500, e)
return json(response(200, 'Complete Successfully', {}))
```
Error
```
[2021-07-13 19:50:48 +0000] [13] [ERROR] Exception occurred while handling uri: 'http://xxxxxxxxx.xxx/25/slot/count'
NoneType: None
```
### What is the result that you get?
my production env is not working on Sanic
### What is the result that you expected?
I wanna use datadog APM on my production SANIC
I made already pull request
- https://github.com/DataDog/dd-trace-py/pull/2662
</issue>
<code>
[start of ddtrace/contrib/sanic/patch.py]
1 import asyncio
2
3 import sanic
4
5 import ddtrace
6 from ddtrace import config
7 from ddtrace.constants import ANALYTICS_SAMPLE_RATE_KEY
8 from ddtrace.ext import SpanTypes
9 from ddtrace.pin import Pin
10 from ddtrace.utils.wrappers import unwrap as _u
11 from ddtrace.vendor import wrapt
12 from ddtrace.vendor.wrapt import wrap_function_wrapper as _w
13
14 from .. import trace_utils
15 from ...internal.logger import get_logger
16
17
18 log = get_logger(__name__)
19
20 config._add("sanic", dict(_default_service="sanic", distributed_tracing=True))
21
22 SANIC_PRE_21 = None
23
24
25 def update_span(span, response):
26 if isinstance(response, sanic.response.BaseHTTPResponse):
27 status_code = response.status
28 response_headers = response.headers
29 else:
30 # invalid response causes ServerError exception which must be handled
31 status_code = 500
32 response_headers = None
33 trace_utils.set_http_meta(span, config.sanic, status_code=status_code, response_headers=response_headers)
34
35
36 def _wrap_response_callback(span, callback):
37 # Only for sanic 20 and older
38 # Wrap response callbacks (either sync or async function) to set HTTP
39 # response span tags
40
41 @wrapt.function_wrapper
42 def wrap_sync(wrapped, instance, args, kwargs):
43 r = wrapped(*args, **kwargs)
44 response = args[0]
45 update_span(span, response)
46 return r
47
48 @wrapt.function_wrapper
49 async def wrap_async(wrapped, instance, args, kwargs):
50 r = await wrapped(*args, **kwargs)
51 response = args[0]
52 update_span(span, response)
53 return r
54
55 if asyncio.iscoroutinefunction(callback):
56 return wrap_async(callback)
57
58 return wrap_sync(callback)
59
60
61 async def patch_request_respond(wrapped, instance, args, kwargs):
62 # Only for sanic 21 and newer
63 # Wrap the framework response to set HTTP response span tags
64 response = await wrapped(*args, **kwargs)
65 pin = Pin._find(instance.ctx)
66 if pin is not None and pin.enabled():
67 span = pin.tracer.current_span()
68 if span is not None:
69 update_span(span, response)
70 return response
71
72
73 def _get_path(request):
74 """Get path and replace path parameter values with names if route exists."""
75 path = request.path
76 try:
77 match_info = request.match_info
78 except sanic.exceptions.SanicException:
79 return path
80 for key, value in match_info.items():
81 path = path.replace(value, f"<{key}>")
82 return path
83
84
85 async def patch_run_request_middleware(wrapped, instance, args, kwargs):
86 # Set span resource from the framework request
87 request = args[0]
88 pin = Pin._find(request.ctx)
89 if pin is not None and pin.enabled():
90 span = pin.tracer.current_span()
91 if span is not None:
92 span.resource = "{} {}".format(request.method, _get_path(request))
93 return await wrapped(*args, **kwargs)
94
95
96 def patch():
97 """Patch the instrumented methods."""
98 global SANIC_PRE_21
99
100 if getattr(sanic, "__datadog_patch", False):
101 return
102 setattr(sanic, "__datadog_patch", True)
103
104 SANIC_PRE_21 = sanic.__version__[:2] < "21"
105
106 _w("sanic", "Sanic.handle_request", patch_handle_request)
107 if not SANIC_PRE_21:
108 _w("sanic", "Sanic._run_request_middleware", patch_run_request_middleware)
109 _w(sanic.request, "Request.respond", patch_request_respond)
110
111
112 def unpatch():
113 """Unpatch the instrumented methods."""
114 _u(sanic.Sanic, "handle_request")
115 if not SANIC_PRE_21:
116 _u(sanic.Sanic, "_run_request_middleware")
117 _u(sanic.request.Request, "respond")
118 if not getattr(sanic, "__datadog_patch", False):
119 return
120 setattr(sanic, "__datadog_patch", False)
121
122
123 async def patch_handle_request(wrapped, instance, args, kwargs):
124 """Wrapper for Sanic.handle_request"""
125
126 def unwrap(request, write_callback=None, stream_callback=None, **kwargs):
127 return request, write_callback, stream_callback, kwargs
128
129 request, write_callback, stream_callback, new_kwargs = unwrap(*args, **kwargs)
130
131 if request.scheme not in ("http", "https"):
132 return await wrapped(*args, **kwargs)
133
134 pin = Pin()
135 if SANIC_PRE_21:
136 # Set span resource from the framework request
137 resource = "{} {}".format(request.method, _get_path(request))
138 else:
139 # The path is not available anymore in 21.x. Get it from
140 # the _run_request_middleware instrumented method.
141 resource = None
142 pin.onto(request.ctx)
143
144 headers = request.headers.copy()
145
146 trace_utils.activate_distributed_headers(ddtrace.tracer, int_config=config.sanic, request_headers=headers)
147
148 with pin.tracer.trace(
149 "sanic.request",
150 service=trace_utils.int_service(None, config.sanic),
151 resource=resource,
152 span_type=SpanTypes.WEB,
153 ) as span:
154 sample_rate = config.sanic.get_analytics_sample_rate(use_global_config=True)
155 if sample_rate is not None:
156 span.set_tag(ANALYTICS_SAMPLE_RATE_KEY, sample_rate)
157
158 method = request.method
159 url = "{scheme}://{host}{path}".format(scheme=request.scheme, host=request.host, path=request.path)
160 query_string = request.query_string
161 if isinstance(query_string, bytes):
162 query_string = query_string.decode()
163 trace_utils.set_http_meta(
164 span, config.sanic, method=method, url=url, query=query_string, request_headers=headers
165 )
166
167 if write_callback is not None:
168 new_kwargs["write_callback"] = _wrap_response_callback(span, write_callback)
169 if stream_callback is not None:
170 new_kwargs["stream_callback"] = _wrap_response_callback(span, stream_callback)
171
172 return await wrapped(request, **new_kwargs)
173
[end of ddtrace/contrib/sanic/patch.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/ddtrace/contrib/sanic/patch.py b/ddtrace/contrib/sanic/patch.py
--- a/ddtrace/contrib/sanic/patch.py
+++ b/ddtrace/contrib/sanic/patch.py
@@ -78,6 +78,11 @@
except sanic.exceptions.SanicException:
return path
for key, value in match_info.items():
+ try:
+ value = str(value)
+ except Exception:
+ # Best effort
+ continue
path = path.replace(value, f"<{key}>")
return path
| {"golden_diff": "diff --git a/ddtrace/contrib/sanic/patch.py b/ddtrace/contrib/sanic/patch.py\n--- a/ddtrace/contrib/sanic/patch.py\n+++ b/ddtrace/contrib/sanic/patch.py\n@@ -78,6 +78,11 @@\n except sanic.exceptions.SanicException:\n return path\n for key, value in match_info.items():\n+ try:\n+ value = str(value)\n+ except Exception:\n+ # Best effort\n+ continue\n path = path.replace(value, f\"<{key}>\")\n return path\n", "issue": "0.50 bug sanic APM\nThanks for taking the time for reporting an issue!\r\n\r\nBefore reporting an issue on dd-trace-py, please be sure to provide all\r\nnecessary information.\r\n\r\nIf you're hitting a bug, make sure that you're using the latest version of this\r\nlibrary.\r\n\r\n### Which version of dd-trace-py are you using?\r\n0.50.0\r\n\r\n### Which version of pip are you using?\r\n19.0.3\r\n\r\n### Which version of the libraries are you using?\r\nPackage Version\r\n------------------- ---------\r\naiofiles 0.7.0\r\naiohttp 3.6.2\r\naiomysql 0.0.20\r\nastroid 2.3.3\r\nasync-timeout 3.0.1\r\nattrs 19.3.0\r\ncertifi 2019.9.11\r\ncffi 1.13.2\r\nchardet 3.0.4\r\nClick 7.0\r\ncryptography 2.8\r\nddtrace 0.50.0\r\nDeprecated 1.2.11\r\nelasticsearch 7.5.1\r\nelasticsearch-async 6.2.0\r\nh11 0.8.1\r\nh2 3.1.1\r\nhpack 3.0.0\r\nhstspreload 2020.1.7\r\nhttpcore 0.3.0\r\nhttptools 0.0.13\r\nhttpx 0.9.3\r\nhyperframe 5.2.0\r\nidna 2.8\r\nisort 4.3.21\r\nlazy-object-proxy 1.4.3\r\nmccabe 0.6.1\r\nmotor 2.4.0\r\nmultidict 5.1.0\r\npackaging 21.0\r\npeewee 3.13.1\r\npip 19.0.3\r\nprotobuf 3.17.3\r\npycparser 2.19\r\nPyJWT 1.7.1\r\npymongo 3.11.4\r\nPyMySQL 0.9.2\r\npyparsing 2.4.7\r\npytz 2019.3\r\nPyYAML 5.3\r\nrequests 2.22.0\r\nrequests-async 0.5.0\r\nrfc3986 1.3.2\r\nsanic 21.3.4\r\nsanic-motor 0.5.0\r\nsanic-routing 0.6.2\r\nsanic-scheduler 1.0.7\r\nsetuptools 40.8.0\r\nsix 1.14.0\r\nsniffio 1.1.0\r\nstringcase 1.2.0\r\ntenacity 8.0.1\r\ntyped-ast 1.4.1\r\nujson 1.35\r\nurllib3 1.25.6\r\nuvloop 0.13.0\r\nwebsockets 8.1\r\nwrapt 1.11.2\r\nyarl 1.4.2\r\n\r\n### How can we reproduce your problem?\r\n#### Description\r\nIt's not working patch when apply APM on Sanic\r\nIf path variable type is int on sanic route\r\n\r\nCase code\r\n```\r\[email protected]('/<gam_id:int>/slot/count', methods=['GET'])\r\nasync def slot_count(request, gam_id):\r\n try:\r\n pass\r\n except Exception as e:\r\n abort(500, e)\r\n return json(response(200, 'Complete Successfully', {}))\r\n\r\n```\r\n\r\nError\r\n```\r\n[2021-07-13 19:50:48 +0000] [13] [ERROR] Exception occurred while handling uri: 'http://xxxxxxxxx.xxx/25/slot/count'\r\nNoneType: None\r\n\r\n```\r\n\r\n### What is the result that you get?\r\nmy production env is not working on Sanic\r\n\r\n\r\n### What is the result that you expected?\r\nI wanna use datadog APM on my production SANIC\r\n\r\nI made already pull request\r\n- https://github.com/DataDog/dd-trace-py/pull/2662\r\n\n", "before_files": [{"content": "import asyncio\n\nimport sanic\n\nimport ddtrace\nfrom ddtrace import config\nfrom ddtrace.constants import ANALYTICS_SAMPLE_RATE_KEY\nfrom ddtrace.ext import SpanTypes\nfrom ddtrace.pin import Pin\nfrom ddtrace.utils.wrappers import unwrap as _u\nfrom ddtrace.vendor import wrapt\nfrom ddtrace.vendor.wrapt import wrap_function_wrapper as _w\n\nfrom .. import trace_utils\nfrom ...internal.logger import get_logger\n\n\nlog = get_logger(__name__)\n\nconfig._add(\"sanic\", dict(_default_service=\"sanic\", distributed_tracing=True))\n\nSANIC_PRE_21 = None\n\n\ndef update_span(span, response):\n if isinstance(response, sanic.response.BaseHTTPResponse):\n status_code = response.status\n response_headers = response.headers\n else:\n # invalid response causes ServerError exception which must be handled\n status_code = 500\n response_headers = None\n trace_utils.set_http_meta(span, config.sanic, status_code=status_code, response_headers=response_headers)\n\n\ndef _wrap_response_callback(span, callback):\n # Only for sanic 20 and older\n # Wrap response callbacks (either sync or async function) to set HTTP\n # response span tags\n\n @wrapt.function_wrapper\n def wrap_sync(wrapped, instance, args, kwargs):\n r = wrapped(*args, **kwargs)\n response = args[0]\n update_span(span, response)\n return r\n\n @wrapt.function_wrapper\n async def wrap_async(wrapped, instance, args, kwargs):\n r = await wrapped(*args, **kwargs)\n response = args[0]\n update_span(span, response)\n return r\n\n if asyncio.iscoroutinefunction(callback):\n return wrap_async(callback)\n\n return wrap_sync(callback)\n\n\nasync def patch_request_respond(wrapped, instance, args, kwargs):\n # Only for sanic 21 and newer\n # Wrap the framework response to set HTTP response span tags\n response = await wrapped(*args, **kwargs)\n pin = Pin._find(instance.ctx)\n if pin is not None and pin.enabled():\n span = pin.tracer.current_span()\n if span is not None:\n update_span(span, response)\n return response\n\n\ndef _get_path(request):\n \"\"\"Get path and replace path parameter values with names if route exists.\"\"\"\n path = request.path\n try:\n match_info = request.match_info\n except sanic.exceptions.SanicException:\n return path\n for key, value in match_info.items():\n path = path.replace(value, f\"<{key}>\")\n return path\n\n\nasync def patch_run_request_middleware(wrapped, instance, args, kwargs):\n # Set span resource from the framework request\n request = args[0]\n pin = Pin._find(request.ctx)\n if pin is not None and pin.enabled():\n span = pin.tracer.current_span()\n if span is not None:\n span.resource = \"{} {}\".format(request.method, _get_path(request))\n return await wrapped(*args, **kwargs)\n\n\ndef patch():\n \"\"\"Patch the instrumented methods.\"\"\"\n global SANIC_PRE_21\n\n if getattr(sanic, \"__datadog_patch\", False):\n return\n setattr(sanic, \"__datadog_patch\", True)\n\n SANIC_PRE_21 = sanic.__version__[:2] < \"21\"\n\n _w(\"sanic\", \"Sanic.handle_request\", patch_handle_request)\n if not SANIC_PRE_21:\n _w(\"sanic\", \"Sanic._run_request_middleware\", patch_run_request_middleware)\n _w(sanic.request, \"Request.respond\", patch_request_respond)\n\n\ndef unpatch():\n \"\"\"Unpatch the instrumented methods.\"\"\"\n _u(sanic.Sanic, \"handle_request\")\n if not SANIC_PRE_21:\n _u(sanic.Sanic, \"_run_request_middleware\")\n _u(sanic.request.Request, \"respond\")\n if not getattr(sanic, \"__datadog_patch\", False):\n return\n setattr(sanic, \"__datadog_patch\", False)\n\n\nasync def patch_handle_request(wrapped, instance, args, kwargs):\n \"\"\"Wrapper for Sanic.handle_request\"\"\"\n\n def unwrap(request, write_callback=None, stream_callback=None, **kwargs):\n return request, write_callback, stream_callback, kwargs\n\n request, write_callback, stream_callback, new_kwargs = unwrap(*args, **kwargs)\n\n if request.scheme not in (\"http\", \"https\"):\n return await wrapped(*args, **kwargs)\n\n pin = Pin()\n if SANIC_PRE_21:\n # Set span resource from the framework request\n resource = \"{} {}\".format(request.method, _get_path(request))\n else:\n # The path is not available anymore in 21.x. Get it from\n # the _run_request_middleware instrumented method.\n resource = None\n pin.onto(request.ctx)\n\n headers = request.headers.copy()\n\n trace_utils.activate_distributed_headers(ddtrace.tracer, int_config=config.sanic, request_headers=headers)\n\n with pin.tracer.trace(\n \"sanic.request\",\n service=trace_utils.int_service(None, config.sanic),\n resource=resource,\n span_type=SpanTypes.WEB,\n ) as span:\n sample_rate = config.sanic.get_analytics_sample_rate(use_global_config=True)\n if sample_rate is not None:\n span.set_tag(ANALYTICS_SAMPLE_RATE_KEY, sample_rate)\n\n method = request.method\n url = \"{scheme}://{host}{path}\".format(scheme=request.scheme, host=request.host, path=request.path)\n query_string = request.query_string\n if isinstance(query_string, bytes):\n query_string = query_string.decode()\n trace_utils.set_http_meta(\n span, config.sanic, method=method, url=url, query=query_string, request_headers=headers\n )\n\n if write_callback is not None:\n new_kwargs[\"write_callback\"] = _wrap_response_callback(span, write_callback)\n if stream_callback is not None:\n new_kwargs[\"stream_callback\"] = _wrap_response_callback(span, stream_callback)\n\n return await wrapped(request, **new_kwargs)\n", "path": "ddtrace/contrib/sanic/patch.py"}]} | 3,277 | 127 |
gh_patches_debug_35121 | rasdani/github-patches | git_diff | dbt-labs__dbt-core-1129 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
deprecate sql_where
See also:
The `sql_where` config isn't actually useful and people shouldn't use it. We should:
- add a deprecation warning when `sql_where` is provided
- make `sql_where` no longer required
- revamp docs around incremental models (https://github.com/fishtown-analytics/dbt/issues/1036)
- make it easier/faster to do the "advanced" version of incremental models
</issue>
<code>
[start of dbt/links.py]
1
2 SnowflakeQuotingDocs = 'https://docs.getdbt.com/v0.10/docs/configuring-quoting'
3
[end of dbt/links.py]
[start of dbt/compilation.py]
1 import itertools
2 import os
3 import json
4 from collections import OrderedDict, defaultdict
5 import sqlparse
6
7 import dbt.utils
8 import dbt.include
9 import dbt.tracking
10
11 from dbt.utils import get_materialization, NodeType, is_type
12
13 from dbt.linker import Linker
14
15 import dbt.compat
16 import dbt.context.runtime
17 import dbt.contracts.project
18 import dbt.exceptions
19 import dbt.flags
20 import dbt.loader
21 import dbt.config
22 from dbt.contracts.graph.compiled import CompiledNode, CompiledGraph
23
24 from dbt.clients.system import write_json
25 from dbt.logger import GLOBAL_LOGGER as logger
26
27 graph_file_name = 'graph.gpickle'
28 manifest_file_name = 'manifest.json'
29
30
31 def print_compile_stats(stats):
32 names = {
33 NodeType.Model: 'models',
34 NodeType.Test: 'tests',
35 NodeType.Archive: 'archives',
36 NodeType.Analysis: 'analyses',
37 NodeType.Macro: 'macros',
38 NodeType.Operation: 'operations',
39 NodeType.Seed: 'seed files',
40 }
41
42 results = {k: 0 for k in names.keys()}
43 results.update(stats)
44
45 stat_line = ", ".join(
46 ["{} {}".format(ct, names.get(t)) for t, ct in results.items()])
47
48 logger.info("Found {}".format(stat_line))
49
50
51 def _add_prepended_cte(prepended_ctes, new_cte):
52 for dct in prepended_ctes:
53 if dct['id'] == new_cte['id']:
54 dct['sql'] = new_cte['sql']
55 return
56 prepended_ctes.append(new_cte)
57
58
59 def _extend_prepended_ctes(prepended_ctes, new_prepended_ctes):
60 for new_cte in new_prepended_ctes:
61 _add_prepended_cte(prepended_ctes, new_cte)
62
63
64 def prepend_ctes(model, manifest):
65 model, _, manifest = recursively_prepend_ctes(model, manifest)
66
67 return (model, manifest)
68
69
70 def recursively_prepend_ctes(model, manifest):
71 if model.extra_ctes_injected:
72 return (model, model.extra_ctes, manifest)
73
74 if dbt.flags.STRICT_MODE:
75 # ensure that all the nodes in this manifest are compiled
76 CompiledGraph(**manifest.to_flat_graph())
77
78 prepended_ctes = []
79
80 for cte in model.extra_ctes:
81 cte_id = cte['id']
82 cte_to_add = manifest.nodes.get(cte_id)
83 cte_to_add, new_prepended_ctes, manifest = recursively_prepend_ctes(
84 cte_to_add, manifest)
85
86 _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)
87 new_cte_name = '__dbt__CTE__{}'.format(cte_to_add.get('name'))
88 sql = ' {} as (\n{}\n)'.format(new_cte_name, cte_to_add.compiled_sql)
89 _add_prepended_cte(prepended_ctes, {'id': cte_id, 'sql': sql})
90
91 model.prepend_ctes(prepended_ctes)
92
93 manifest.nodes[model.unique_id] = model
94
95 return (model, prepended_ctes, manifest)
96
97
98 class Compiler(object):
99 def __init__(self, config):
100 self.config = config
101
102 def initialize(self):
103 dbt.clients.system.make_directory(self.config.target_path)
104 dbt.clients.system.make_directory(self.config.modules_path)
105
106 def compile_node(self, node, manifest, extra_context=None):
107 if extra_context is None:
108 extra_context = {}
109
110 logger.debug("Compiling {}".format(node.get('unique_id')))
111
112 data = node.to_dict()
113 data.update({
114 'compiled': False,
115 'compiled_sql': None,
116 'extra_ctes_injected': False,
117 'extra_ctes': [],
118 'injected_sql': None,
119 })
120 compiled_node = CompiledNode(**data)
121
122 context = dbt.context.runtime.generate(
123 compiled_node, self.config, manifest)
124 context.update(extra_context)
125
126 compiled_node.compiled_sql = dbt.clients.jinja.get_rendered(
127 node.get('raw_sql'),
128 context,
129 node)
130
131 compiled_node.compiled = True
132
133 injected_node, _ = prepend_ctes(compiled_node, manifest)
134
135 should_wrap = {NodeType.Test, NodeType.Operation}
136 if injected_node.resource_type in should_wrap:
137 # data tests get wrapped in count(*)
138 # TODO : move this somewhere more reasonable
139 if 'data' in injected_node.tags and \
140 is_type(injected_node, NodeType.Test):
141 injected_node.wrapped_sql = (
142 "select count(*) from (\n{test_sql}\n) sbq").format(
143 test_sql=injected_node.injected_sql)
144 else:
145 # don't wrap schema tests or analyses.
146 injected_node.wrapped_sql = injected_node.injected_sql
147
148 elif is_type(injected_node, NodeType.Archive):
149 # unfortunately we do everything automagically for
150 # archives. in the future it'd be nice to generate
151 # the SQL at the parser level.
152 pass
153
154 elif(is_type(injected_node, NodeType.Model) and
155 get_materialization(injected_node) == 'ephemeral'):
156 pass
157
158 else:
159 injected_node.wrapped_sql = None
160
161 return injected_node
162
163 def write_manifest_file(self, manifest):
164 """Write the manifest file to disk.
165
166 manifest should be a Manifest.
167 """
168 filename = manifest_file_name
169 manifest_path = os.path.join(self.config.target_path, filename)
170 write_json(manifest_path, manifest.serialize())
171
172 def write_graph_file(self, linker, manifest):
173 filename = graph_file_name
174 graph_path = os.path.join(self.config.target_path, filename)
175 linker.write_graph(graph_path, manifest)
176
177 def link_node(self, linker, node, manifest):
178 linker.add_node(node.unique_id)
179
180 for dependency in node.depends_on_nodes:
181 if manifest.nodes.get(dependency):
182 linker.dependency(
183 node.unique_id,
184 (manifest.nodes.get(dependency).unique_id))
185
186 else:
187 dbt.exceptions.dependency_not_found(node, dependency)
188
189 def link_graph(self, linker, manifest):
190 for node in manifest.nodes.values():
191 self.link_node(linker, node, manifest)
192
193 cycle = linker.find_cycles()
194
195 if cycle:
196 raise RuntimeError("Found a cycle: {}".format(cycle))
197
198 def get_all_projects(self):
199 all_projects = {self.config.project_name: self.config}
200 dependency_projects = dbt.utils.dependency_projects(self.config)
201
202 for project_cfg in dependency_projects:
203 name = project_cfg.project_name
204 all_projects[name] = project_cfg
205
206 if dbt.flags.STRICT_MODE:
207 dbt.contracts.project.ProjectList(**all_projects)
208
209 return all_projects
210
211 def _check_resource_uniqueness(cls, manifest):
212 names_resources = {}
213 alias_resources = {}
214
215 for resource, node in manifest.nodes.items():
216 if node.resource_type not in NodeType.refable():
217 continue
218
219 name = node.name
220 alias = "{}.{}".format(node.schema, node.alias)
221
222 existing_node = names_resources.get(name)
223 if existing_node is not None:
224 dbt.exceptions.raise_duplicate_resource_name(
225 existing_node, node)
226
227 existing_alias = alias_resources.get(alias)
228 if existing_alias is not None:
229 dbt.exceptions.raise_ambiguous_alias(
230 existing_alias, node)
231
232 names_resources[name] = node
233 alias_resources[alias] = node
234
235 def compile(self):
236 linker = Linker()
237
238 all_projects = self.get_all_projects()
239
240 manifest = dbt.loader.GraphLoader.load_all(self.config, all_projects)
241
242 self.write_manifest_file(manifest)
243
244 self._check_resource_uniqueness(manifest)
245
246 resource_fqns = manifest.get_resource_fqns()
247 disabled_fqns = [n.fqn for n in manifest.disabled]
248 self.config.warn_for_unused_resource_config_paths(resource_fqns,
249 disabled_fqns)
250
251 self.link_graph(linker, manifest)
252
253 stats = defaultdict(int)
254
255 for node_name, node in itertools.chain(
256 manifest.nodes.items(),
257 manifest.macros.items()):
258 stats[node.resource_type] += 1
259
260 self.write_graph_file(linker, manifest)
261 print_compile_stats(stats)
262
263 return manifest, linker
264
[end of dbt/compilation.py]
[start of dbt/deprecations.py]
1 from dbt.logger import GLOBAL_LOGGER as logger
2
3
4 class DBTDeprecation(object):
5 name = None
6 description = None
7
8 def show(self, *args, **kwargs):
9 if self.name not in active_deprecations:
10 desc = self.description.format(**kwargs)
11 logger.info("* Deprecation Warning: {}\n".format(desc))
12 active_deprecations.add(self.name)
13
14
15 class DBTRepositoriesDeprecation(DBTDeprecation):
16 name = "repositories"
17 description = """The dbt_project.yml configuration option 'repositories' is
18 deprecated. Please place dependencies in the `packages.yml` file instead.
19 The 'repositories' option will be removed in a future version of dbt.
20
21 For more information, see: https://docs.getdbt.com/docs/package-management
22
23 # Example packages.yml contents:
24
25 {recommendation}
26 """
27
28
29 class SeedDropExistingDeprecation(DBTDeprecation):
30 name = 'drop-existing'
31 description = """The --drop-existing argument to `dbt seed` has been
32 deprecated. Please use --full-refresh instead. The --drop-existing option
33 will be removed in a future version of dbt."""
34
35
36 def warn(name, *args, **kwargs):
37 if name not in deprecations:
38 # this should (hopefully) never happen
39 raise RuntimeError(
40 "Error showing deprecation warning: {}".format(name)
41 )
42
43 deprecations[name].show(*args, **kwargs)
44
45
46 # these are globally available
47 # since modules are only imported once, active_deprecations is a singleton
48
49 active_deprecations = set()
50
51 deprecations_list = [
52 DBTRepositoriesDeprecation(),
53 SeedDropExistingDeprecation()
54 ]
55
56 deprecations = {d.name: d for d in deprecations_list}
57
58
59 def reset_deprecations():
60 active_deprecations.clear()
61
[end of dbt/deprecations.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/dbt/compilation.py b/dbt/compilation.py
--- a/dbt/compilation.py
+++ b/dbt/compilation.py
@@ -232,6 +232,12 @@
names_resources[name] = node
alias_resources[alias] = node
+ def warn_for_deprecated_configs(self, manifest):
+ for unique_id, node in manifest.nodes.items():
+ is_model = node.resource_type == NodeType.Model
+ if is_model and 'sql_where' in node.config:
+ dbt.deprecations.warn('sql_where')
+
def compile(self):
linker = Linker()
@@ -247,6 +253,7 @@
disabled_fqns = [n.fqn for n in manifest.disabled]
self.config.warn_for_unused_resource_config_paths(resource_fqns,
disabled_fqns)
+ self.warn_for_deprecated_configs(manifest)
self.link_graph(linker, manifest)
diff --git a/dbt/deprecations.py b/dbt/deprecations.py
--- a/dbt/deprecations.py
+++ b/dbt/deprecations.py
@@ -1,4 +1,5 @@
from dbt.logger import GLOBAL_LOGGER as logger
+import dbt.links
class DBTDeprecation(object):
@@ -26,6 +27,16 @@
"""
+class SqlWhereDeprecation(DBTDeprecation):
+ name = "sql_where"
+ description = """\
+The `sql_where` option for incremental models is deprecated and will be
+ removed in a future release. Check the docs for more information
+
+ {}
+ """.format(dbt.links.IncrementalDocs)
+
+
class SeedDropExistingDeprecation(DBTDeprecation):
name = 'drop-existing'
description = """The --drop-existing argument to `dbt seed` has been
@@ -50,7 +61,8 @@
deprecations_list = [
DBTRepositoriesDeprecation(),
- SeedDropExistingDeprecation()
+ SeedDropExistingDeprecation(),
+ SqlWhereDeprecation(),
]
deprecations = {d.name: d for d in deprecations_list}
diff --git a/dbt/links.py b/dbt/links.py
--- a/dbt/links.py
+++ b/dbt/links.py
@@ -1,2 +1,3 @@
SnowflakeQuotingDocs = 'https://docs.getdbt.com/v0.10/docs/configuring-quoting'
+IncrementalDocs = 'https://docs.getdbt.com/docs/configuring-incremental-models'
| {"golden_diff": "diff --git a/dbt/compilation.py b/dbt/compilation.py\n--- a/dbt/compilation.py\n+++ b/dbt/compilation.py\n@@ -232,6 +232,12 @@\n names_resources[name] = node\n alias_resources[alias] = node\n \n+ def warn_for_deprecated_configs(self, manifest):\n+ for unique_id, node in manifest.nodes.items():\n+ is_model = node.resource_type == NodeType.Model\n+ if is_model and 'sql_where' in node.config:\n+ dbt.deprecations.warn('sql_where')\n+\n def compile(self):\n linker = Linker()\n \n@@ -247,6 +253,7 @@\n disabled_fqns = [n.fqn for n in manifest.disabled]\n self.config.warn_for_unused_resource_config_paths(resource_fqns,\n disabled_fqns)\n+ self.warn_for_deprecated_configs(manifest)\n \n self.link_graph(linker, manifest)\n \ndiff --git a/dbt/deprecations.py b/dbt/deprecations.py\n--- a/dbt/deprecations.py\n+++ b/dbt/deprecations.py\n@@ -1,4 +1,5 @@\n from dbt.logger import GLOBAL_LOGGER as logger\n+import dbt.links\n \n \n class DBTDeprecation(object):\n@@ -26,6 +27,16 @@\n \"\"\"\n \n \n+class SqlWhereDeprecation(DBTDeprecation):\n+ name = \"sql_where\"\n+ description = \"\"\"\\\n+The `sql_where` option for incremental models is deprecated and will be\n+ removed in a future release. Check the docs for more information\n+\n+ {}\n+ \"\"\".format(dbt.links.IncrementalDocs)\n+\n+\n class SeedDropExistingDeprecation(DBTDeprecation):\n name = 'drop-existing'\n description = \"\"\"The --drop-existing argument to `dbt seed` has been\n@@ -50,7 +61,8 @@\n \n deprecations_list = [\n DBTRepositoriesDeprecation(),\n- SeedDropExistingDeprecation()\n+ SeedDropExistingDeprecation(),\n+ SqlWhereDeprecation(),\n ]\n \n deprecations = {d.name: d for d in deprecations_list}\ndiff --git a/dbt/links.py b/dbt/links.py\n--- a/dbt/links.py\n+++ b/dbt/links.py\n@@ -1,2 +1,3 @@\n \n SnowflakeQuotingDocs = 'https://docs.getdbt.com/v0.10/docs/configuring-quoting'\n+IncrementalDocs = 'https://docs.getdbt.com/docs/configuring-incremental-models'\n", "issue": "deprecate sql_where\nSee also: \r\n\r\nThe `sql_where` config isn't actually useful and people shouldn't use it. We should:\r\n- add a deprecation warning when `sql_where` is provided\r\n- make `sql_where` no longer required\r\n- revamp docs around incremental models (https://github.com/fishtown-analytics/dbt/issues/1036)\r\n- make it easier/faster to do the \"advanced\" version of incremental models\n", "before_files": [{"content": "\nSnowflakeQuotingDocs = 'https://docs.getdbt.com/v0.10/docs/configuring-quoting'\n", "path": "dbt/links.py"}, {"content": "import itertools\nimport os\nimport json\nfrom collections import OrderedDict, defaultdict\nimport sqlparse\n\nimport dbt.utils\nimport dbt.include\nimport dbt.tracking\n\nfrom dbt.utils import get_materialization, NodeType, is_type\n\nfrom dbt.linker import Linker\n\nimport dbt.compat\nimport dbt.context.runtime\nimport dbt.contracts.project\nimport dbt.exceptions\nimport dbt.flags\nimport dbt.loader\nimport dbt.config\nfrom dbt.contracts.graph.compiled import CompiledNode, CompiledGraph\n\nfrom dbt.clients.system import write_json\nfrom dbt.logger import GLOBAL_LOGGER as logger\n\ngraph_file_name = 'graph.gpickle'\nmanifest_file_name = 'manifest.json'\n\n\ndef print_compile_stats(stats):\n names = {\n NodeType.Model: 'models',\n NodeType.Test: 'tests',\n NodeType.Archive: 'archives',\n NodeType.Analysis: 'analyses',\n NodeType.Macro: 'macros',\n NodeType.Operation: 'operations',\n NodeType.Seed: 'seed files',\n }\n\n results = {k: 0 for k in names.keys()}\n results.update(stats)\n\n stat_line = \", \".join(\n [\"{} {}\".format(ct, names.get(t)) for t, ct in results.items()])\n\n logger.info(\"Found {}\".format(stat_line))\n\n\ndef _add_prepended_cte(prepended_ctes, new_cte):\n for dct in prepended_ctes:\n if dct['id'] == new_cte['id']:\n dct['sql'] = new_cte['sql']\n return\n prepended_ctes.append(new_cte)\n\n\ndef _extend_prepended_ctes(prepended_ctes, new_prepended_ctes):\n for new_cte in new_prepended_ctes:\n _add_prepended_cte(prepended_ctes, new_cte)\n\n\ndef prepend_ctes(model, manifest):\n model, _, manifest = recursively_prepend_ctes(model, manifest)\n\n return (model, manifest)\n\n\ndef recursively_prepend_ctes(model, manifest):\n if model.extra_ctes_injected:\n return (model, model.extra_ctes, manifest)\n\n if dbt.flags.STRICT_MODE:\n # ensure that all the nodes in this manifest are compiled\n CompiledGraph(**manifest.to_flat_graph())\n\n prepended_ctes = []\n\n for cte in model.extra_ctes:\n cte_id = cte['id']\n cte_to_add = manifest.nodes.get(cte_id)\n cte_to_add, new_prepended_ctes, manifest = recursively_prepend_ctes(\n cte_to_add, manifest)\n\n _extend_prepended_ctes(prepended_ctes, new_prepended_ctes)\n new_cte_name = '__dbt__CTE__{}'.format(cte_to_add.get('name'))\n sql = ' {} as (\\n{}\\n)'.format(new_cte_name, cte_to_add.compiled_sql)\n _add_prepended_cte(prepended_ctes, {'id': cte_id, 'sql': sql})\n\n model.prepend_ctes(prepended_ctes)\n\n manifest.nodes[model.unique_id] = model\n\n return (model, prepended_ctes, manifest)\n\n\nclass Compiler(object):\n def __init__(self, config):\n self.config = config\n\n def initialize(self):\n dbt.clients.system.make_directory(self.config.target_path)\n dbt.clients.system.make_directory(self.config.modules_path)\n\n def compile_node(self, node, manifest, extra_context=None):\n if extra_context is None:\n extra_context = {}\n\n logger.debug(\"Compiling {}\".format(node.get('unique_id')))\n\n data = node.to_dict()\n data.update({\n 'compiled': False,\n 'compiled_sql': None,\n 'extra_ctes_injected': False,\n 'extra_ctes': [],\n 'injected_sql': None,\n })\n compiled_node = CompiledNode(**data)\n\n context = dbt.context.runtime.generate(\n compiled_node, self.config, manifest)\n context.update(extra_context)\n\n compiled_node.compiled_sql = dbt.clients.jinja.get_rendered(\n node.get('raw_sql'),\n context,\n node)\n\n compiled_node.compiled = True\n\n injected_node, _ = prepend_ctes(compiled_node, manifest)\n\n should_wrap = {NodeType.Test, NodeType.Operation}\n if injected_node.resource_type in should_wrap:\n # data tests get wrapped in count(*)\n # TODO : move this somewhere more reasonable\n if 'data' in injected_node.tags and \\\n is_type(injected_node, NodeType.Test):\n injected_node.wrapped_sql = (\n \"select count(*) from (\\n{test_sql}\\n) sbq\").format(\n test_sql=injected_node.injected_sql)\n else:\n # don't wrap schema tests or analyses.\n injected_node.wrapped_sql = injected_node.injected_sql\n\n elif is_type(injected_node, NodeType.Archive):\n # unfortunately we do everything automagically for\n # archives. in the future it'd be nice to generate\n # the SQL at the parser level.\n pass\n\n elif(is_type(injected_node, NodeType.Model) and\n get_materialization(injected_node) == 'ephemeral'):\n pass\n\n else:\n injected_node.wrapped_sql = None\n\n return injected_node\n\n def write_manifest_file(self, manifest):\n \"\"\"Write the manifest file to disk.\n\n manifest should be a Manifest.\n \"\"\"\n filename = manifest_file_name\n manifest_path = os.path.join(self.config.target_path, filename)\n write_json(manifest_path, manifest.serialize())\n\n def write_graph_file(self, linker, manifest):\n filename = graph_file_name\n graph_path = os.path.join(self.config.target_path, filename)\n linker.write_graph(graph_path, manifest)\n\n def link_node(self, linker, node, manifest):\n linker.add_node(node.unique_id)\n\n for dependency in node.depends_on_nodes:\n if manifest.nodes.get(dependency):\n linker.dependency(\n node.unique_id,\n (manifest.nodes.get(dependency).unique_id))\n\n else:\n dbt.exceptions.dependency_not_found(node, dependency)\n\n def link_graph(self, linker, manifest):\n for node in manifest.nodes.values():\n self.link_node(linker, node, manifest)\n\n cycle = linker.find_cycles()\n\n if cycle:\n raise RuntimeError(\"Found a cycle: {}\".format(cycle))\n\n def get_all_projects(self):\n all_projects = {self.config.project_name: self.config}\n dependency_projects = dbt.utils.dependency_projects(self.config)\n\n for project_cfg in dependency_projects:\n name = project_cfg.project_name\n all_projects[name] = project_cfg\n\n if dbt.flags.STRICT_MODE:\n dbt.contracts.project.ProjectList(**all_projects)\n\n return all_projects\n\n def _check_resource_uniqueness(cls, manifest):\n names_resources = {}\n alias_resources = {}\n\n for resource, node in manifest.nodes.items():\n if node.resource_type not in NodeType.refable():\n continue\n\n name = node.name\n alias = \"{}.{}\".format(node.schema, node.alias)\n\n existing_node = names_resources.get(name)\n if existing_node is not None:\n dbt.exceptions.raise_duplicate_resource_name(\n existing_node, node)\n\n existing_alias = alias_resources.get(alias)\n if existing_alias is not None:\n dbt.exceptions.raise_ambiguous_alias(\n existing_alias, node)\n\n names_resources[name] = node\n alias_resources[alias] = node\n\n def compile(self):\n linker = Linker()\n\n all_projects = self.get_all_projects()\n\n manifest = dbt.loader.GraphLoader.load_all(self.config, all_projects)\n\n self.write_manifest_file(manifest)\n\n self._check_resource_uniqueness(manifest)\n\n resource_fqns = manifest.get_resource_fqns()\n disabled_fqns = [n.fqn for n in manifest.disabled]\n self.config.warn_for_unused_resource_config_paths(resource_fqns,\n disabled_fqns)\n\n self.link_graph(linker, manifest)\n\n stats = defaultdict(int)\n\n for node_name, node in itertools.chain(\n manifest.nodes.items(),\n manifest.macros.items()):\n stats[node.resource_type] += 1\n\n self.write_graph_file(linker, manifest)\n print_compile_stats(stats)\n\n return manifest, linker\n", "path": "dbt/compilation.py"}, {"content": "from dbt.logger import GLOBAL_LOGGER as logger\n\n\nclass DBTDeprecation(object):\n name = None\n description = None\n\n def show(self, *args, **kwargs):\n if self.name not in active_deprecations:\n desc = self.description.format(**kwargs)\n logger.info(\"* Deprecation Warning: {}\\n\".format(desc))\n active_deprecations.add(self.name)\n\n\nclass DBTRepositoriesDeprecation(DBTDeprecation):\n name = \"repositories\"\n description = \"\"\"The dbt_project.yml configuration option 'repositories' is\n deprecated. Please place dependencies in the `packages.yml` file instead.\n The 'repositories' option will be removed in a future version of dbt.\n\n For more information, see: https://docs.getdbt.com/docs/package-management\n\n # Example packages.yml contents:\n\n{recommendation}\n \"\"\"\n\n\nclass SeedDropExistingDeprecation(DBTDeprecation):\n name = 'drop-existing'\n description = \"\"\"The --drop-existing argument to `dbt seed` has been\n deprecated. Please use --full-refresh instead. The --drop-existing option\n will be removed in a future version of dbt.\"\"\"\n\n\ndef warn(name, *args, **kwargs):\n if name not in deprecations:\n # this should (hopefully) never happen\n raise RuntimeError(\n \"Error showing deprecation warning: {}\".format(name)\n )\n\n deprecations[name].show(*args, **kwargs)\n\n\n# these are globally available\n# since modules are only imported once, active_deprecations is a singleton\n\nactive_deprecations = set()\n\ndeprecations_list = [\n DBTRepositoriesDeprecation(),\n SeedDropExistingDeprecation()\n]\n\ndeprecations = {d.name: d for d in deprecations_list}\n\n\ndef reset_deprecations():\n active_deprecations.clear()\n", "path": "dbt/deprecations.py"}]} | 3,719 | 578 |
gh_patches_debug_42248 | rasdani/github-patches | git_diff | bridgecrewio__checkov-2168 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
CKV_GCP_26 is not working as expected when using terraform plan output.
**Describe the bug**
CKV_GCP_26 check is not providing expected output when it is ran against terraform output json file. Check is gives the result as PASSED even if we don't have the flow logs enabled for the subnet. However if we run it against the directory where we have the .tf files then the check returns the FAILED status which is expected.
checkov version used: `2.0.236`
Terraform version used: `1.0.1`
**To Reproduce**
1. Create a sample subnet resource in a network.tf file.
```
resource "google_compute_network" "vpc" {
name = "test-vpc"
auto_create_subnetworks = "false"
routing_mode = "REGIONAL"
}
resource "google_compute_subnetwork" "private-subnet" {
name = "test-sub"
ip_cidr_range = "10.1.0.0/16"
network = google_compute_network.vpc.self_link
private_ip_google_access = true
}
```
2. terraform plan -out tf.plan
3. terraform show -json tf.plan > tf.json
4. checkov -f tf.json
5. Now run checkov -f network.tf
Both the commands will give conflicting results
```
Check: CKV_GCP_26: "Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network"
PASSED for resource: google_compute_subnetwork.private-subnet
File: /tf/tfplan.json:0-0
Guide: https://docs.bridgecrew.io/docs/bc_gcp_logging_1
```
```
Check: CKV_GCP_26: "Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network"
FAILED for resource: google_compute_subnetwork.private-subnet
File: /network.tf:6-11
Guide: https://docs.bridgecrew.io/docs/bc_gcp_logging_1
6 | resource "google_compute_subnetwork" "private-subnet" {
7 | name = var.private_subnet_name
8 | ip_cidr_range = var.private_subnet_cidr
9 | network = google_compute_network.vpc.self_link
10 | private_ip_google_access = true
11 | }
```
**Expected behavior**
The check should return the status as FAILED when running it against terraform plan output json
</issue>
<code>
[start of checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py]
1 from checkov.common.models.enums import CheckCategories
2 from checkov.common.models.consts import ANY_VALUE
3 from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck
4
5
6 class AKSApiServerAuthorizedIpRanges(BaseResourceValueCheck):
7 def __init__(self):
8 name = "Ensure AKS has an API Server Authorized IP Ranges enabled"
9 id = "CKV_AZURE_6"
10 supported_resources = ['azurerm_kubernetes_cluster']
11 categories = [CheckCategories.KUBERNETES]
12 super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)
13
14 def get_inspected_key(self):
15 return 'api_server_authorized_ip_ranges/[0]'
16
17 def get_expected_value(self):
18 return ANY_VALUE
19
20
21 check = AKSApiServerAuthorizedIpRanges()
22
[end of checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py]
[start of checkov/terraform/checks/resource/base_resource_value_check.py]
1 from abc import abstractmethod
2 from collections.abc import Iterable
3 from typing import List, Dict, Any
4
5 import dpath.util
6 import re
7 from checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck
8 from checkov.common.models.enums import CheckResult, CheckCategories
9 from checkov.common.models.consts import ANY_VALUE
10 from checkov.common.util.type_forcers import force_list
11 from checkov.terraform.graph_builder.utils import get_referenced_vertices_in_value
12 from checkov.terraform.parser_functions import handle_dynamic_values
13 from checkov.terraform.parser_utils import find_var_blocks
14
15
16
17 class BaseResourceValueCheck(BaseResourceCheck):
18 def __init__(
19 self,
20 name: str,
21 id: str,
22 categories: "Iterable[CheckCategories]",
23 supported_resources: "Iterable[str]",
24 missing_block_result: CheckResult = CheckResult.FAILED,
25 ) -> None:
26 super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)
27 self.missing_block_result = missing_block_result
28
29 @staticmethod
30 def _filter_key_path(path: str) -> List[str]:
31 """
32 Filter an attribute path to contain only named attributes by dropping array indices from the path)
33 :param path: valid JSONPath of an attribute
34 :return: List of named attributes with respect to the input JSONPath order
35 """
36 return [x for x in path.split("/") if not re.search(re.compile(r"^\[?\d+]?$"), x)]
37
38 @staticmethod
39 def _is_variable_dependant(value: Any) -> bool:
40 if not isinstance(value, str):
41 return False
42 if "${" not in value:
43 return False
44
45 if find_var_blocks(value):
46 return True
47 return False
48
49 @staticmethod
50 def _is_nesting_key(inspected_attributes: List[str], key: List[str]) -> bool:
51 """
52 Resolves whether a key is a subset of the inspected nesting attributes
53 :param inspected_attributes: list of nesting attributes
54 :param key: JSONPath key of an attribute
55 :return: True/False
56 """
57 return any(x in key for x in inspected_attributes)
58
59 def scan_resource_conf(self, conf: Dict[str, List[Any]]) -> CheckResult:
60 handle_dynamic_values(conf)
61 inspected_key = self.get_inspected_key()
62 expected_values = self.get_expected_values()
63 if dpath.search(conf, inspected_key) != {}:
64 # Inspected key exists
65 value = dpath.get(conf, inspected_key)
66 if isinstance(value, list) and len(value) == 1:
67 value = value[0]
68 if value is None:
69 return self.missing_block_result
70 if ANY_VALUE in expected_values and value is not None and (not isinstance(value, str) or value):
71 # Key is found on the configuration - if it accepts any value, the check is PASSED
72 return CheckResult.PASSED
73 if self._is_variable_dependant(value):
74 # If the tested attribute is variable-dependant, then result is PASSED
75 return CheckResult.PASSED
76 if value in expected_values:
77 return CheckResult.PASSED
78 if get_referenced_vertices_in_value(value=value, aliases={}, resources_types=[]):
79 # we don't provide resources_types as we want to stay provider agnostic
80 return CheckResult.UNKNOWN
81 return CheckResult.FAILED
82 else:
83 # Look for the configuration in a bottom-up fashion
84 inspected_attributes = self._filter_key_path(inspected_key)
85 for attribute in reversed(inspected_attributes):
86 for sub_key, sub_conf in dpath.search(conf, f"**/{attribute}", yielded=True):
87 filtered_sub_key = self._filter_key_path(sub_key)
88 # Only proceed with check if full path for key is similar - not partial match
89 if inspected_attributes == filtered_sub_key:
90 if self._is_nesting_key(inspected_attributes, filtered_sub_key):
91 if isinstance(sub_conf, list) and len(sub_conf) == 1:
92 sub_conf = sub_conf[0]
93 if sub_conf in self.get_expected_values():
94 return CheckResult.PASSED
95 if self._is_variable_dependant(sub_conf):
96 # If the tested attribute is variable-dependant, then result is PASSED
97 return CheckResult.PASSED
98
99 return self.missing_block_result
100
101 @abstractmethod
102 def get_inspected_key(self) -> str:
103 """
104 :return: JSONPath syntax path of the checked attribute
105 """
106 raise NotImplementedError()
107
108 def get_expected_values(self) -> List[Any]:
109 """
110 Override the method with the list of acceptable values if the check has more than one possible expected value, given
111 the inspected key
112 :return: List of expected values, defaults to a list of the expected value
113 """
114 return [self.get_expected_value()]
115
116 def get_expected_value(self) -> Any:
117 """
118 Returns the default expected value, governed by provider best practices
119 """
120 return True
121
122 def get_evaluated_keys(self) -> List[str]:
123 return force_list(self.get_inspected_key())
124
[end of checkov/terraform/checks/resource/base_resource_value_check.py]
[start of checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py]
1 from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck
2 from checkov.common.models.enums import CheckCategories
3 from checkov.common.models.consts import ANY_VALUE
4
5
6 class GoogleSubnetworkLoggingEnabled(BaseResourceValueCheck):
7 def __init__(self):
8 name = "Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network"
9 id = "CKV_GCP_26"
10 supported_resources = ['google_compute_subnetwork']
11 categories = [CheckCategories.LOGGING]
12 super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)
13
14 def get_inspected_key(self):
15 return 'log_config'
16
17 def get_expected_values(self):
18 return [ANY_VALUE]
19
20
21 check = GoogleSubnetworkLoggingEnabled()
22
[end of checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py b/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py
--- a/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py
+++ b/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py
@@ -1,21 +1,23 @@
-from checkov.common.models.enums import CheckCategories
+from typing import List, Any
+
from checkov.common.models.consts import ANY_VALUE
+from checkov.common.models.enums import CheckCategories
from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck
class AKSApiServerAuthorizedIpRanges(BaseResourceValueCheck):
- def __init__(self):
+ def __init__(self) -> None:
name = "Ensure AKS has an API Server Authorized IP Ranges enabled"
id = "CKV_AZURE_6"
- supported_resources = ['azurerm_kubernetes_cluster']
- categories = [CheckCategories.KUBERNETES]
+ supported_resources = ("azurerm_kubernetes_cluster",)
+ categories = (CheckCategories.KUBERNETES,)
super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)
- def get_inspected_key(self):
- return 'api_server_authorized_ip_ranges/[0]'
+ def get_inspected_key(self) -> str:
+ return "api_server_authorized_ip_ranges/[0]"
- def get_expected_value(self):
- return ANY_VALUE
+ def get_expected_values(self) -> List[Any]:
+ return [ANY_VALUE]
check = AKSApiServerAuthorizedIpRanges()
diff --git a/checkov/terraform/checks/resource/base_resource_value_check.py b/checkov/terraform/checks/resource/base_resource_value_check.py
--- a/checkov/terraform/checks/resource/base_resource_value_check.py
+++ b/checkov/terraform/checks/resource/base_resource_value_check.py
@@ -65,7 +65,7 @@
value = dpath.get(conf, inspected_key)
if isinstance(value, list) and len(value) == 1:
value = value[0]
- if value is None:
+ if value is None or (isinstance(value, list) and not value):
return self.missing_block_result
if ANY_VALUE in expected_values and value is not None and (not isinstance(value, str) or value):
# Key is found on the configuration - if it accepts any value, the check is PASSED
diff --git a/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py b/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py
--- a/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py
+++ b/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py
@@ -1,20 +1,30 @@
-from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck
-from checkov.common.models.enums import CheckCategories
+from typing import Any, List, Dict
+
from checkov.common.models.consts import ANY_VALUE
+from checkov.common.models.enums import CheckCategories, CheckResult
+from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck
class GoogleSubnetworkLoggingEnabled(BaseResourceValueCheck):
- def __init__(self):
+ def __init__(self) -> None:
name = "Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network"
id = "CKV_GCP_26"
- supported_resources = ['google_compute_subnetwork']
- categories = [CheckCategories.LOGGING]
+ supported_resources = ("google_compute_subnetwork",)
+ categories = (CheckCategories.LOGGING,)
super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)
- def get_inspected_key(self):
- return 'log_config'
+ def scan_resource_conf(self, conf: Dict[str, List[Any]]) -> CheckResult:
+ # flow logs can't be enabled for `INTERNAL_HTTPS_LOAD_BALANCER` subnetworks
+ purpose = conf.get("purpose")
+ if purpose and purpose[0] == "INTERNAL_HTTPS_LOAD_BALANCER":
+ return CheckResult.UNKNOWN
+
+ return super().scan_resource_conf(conf)
+
+ def get_inspected_key(self) -> str:
+ return "log_config"
- def get_expected_values(self):
+ def get_expected_values(self) -> List[Any]:
return [ANY_VALUE]
| {"golden_diff": "diff --git a/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py b/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py\n--- a/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py\n+++ b/checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py\n@@ -1,21 +1,23 @@\n-from checkov.common.models.enums import CheckCategories\n+from typing import List, Any\n+\n from checkov.common.models.consts import ANY_VALUE\n+from checkov.common.models.enums import CheckCategories\n from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck\n \n \n class AKSApiServerAuthorizedIpRanges(BaseResourceValueCheck):\n- def __init__(self):\n+ def __init__(self) -> None:\n name = \"Ensure AKS has an API Server Authorized IP Ranges enabled\"\n id = \"CKV_AZURE_6\"\n- supported_resources = ['azurerm_kubernetes_cluster']\n- categories = [CheckCategories.KUBERNETES]\n+ supported_resources = (\"azurerm_kubernetes_cluster\",)\n+ categories = (CheckCategories.KUBERNETES,)\n super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)\n \n- def get_inspected_key(self):\n- return 'api_server_authorized_ip_ranges/[0]'\n+ def get_inspected_key(self) -> str:\n+ return \"api_server_authorized_ip_ranges/[0]\"\n \n- def get_expected_value(self):\n- return ANY_VALUE\n+ def get_expected_values(self) -> List[Any]:\n+ return [ANY_VALUE]\n \n \n check = AKSApiServerAuthorizedIpRanges()\ndiff --git a/checkov/terraform/checks/resource/base_resource_value_check.py b/checkov/terraform/checks/resource/base_resource_value_check.py\n--- a/checkov/terraform/checks/resource/base_resource_value_check.py\n+++ b/checkov/terraform/checks/resource/base_resource_value_check.py\n@@ -65,7 +65,7 @@\n value = dpath.get(conf, inspected_key)\n if isinstance(value, list) and len(value) == 1:\n value = value[0]\n- if value is None:\n+ if value is None or (isinstance(value, list) and not value):\n return self.missing_block_result\n if ANY_VALUE in expected_values and value is not None and (not isinstance(value, str) or value):\n # Key is found on the configuration - if it accepts any value, the check is PASSED\ndiff --git a/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py b/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py\n--- a/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py\n+++ b/checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py\n@@ -1,20 +1,30 @@\n-from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck\n-from checkov.common.models.enums import CheckCategories\n+from typing import Any, List, Dict\n+\n from checkov.common.models.consts import ANY_VALUE\n+from checkov.common.models.enums import CheckCategories, CheckResult\n+from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck\n \n \n class GoogleSubnetworkLoggingEnabled(BaseResourceValueCheck):\n- def __init__(self):\n+ def __init__(self) -> None:\n name = \"Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network\"\n id = \"CKV_GCP_26\"\n- supported_resources = ['google_compute_subnetwork']\n- categories = [CheckCategories.LOGGING]\n+ supported_resources = (\"google_compute_subnetwork\",)\n+ categories = (CheckCategories.LOGGING,)\n super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)\n \n- def get_inspected_key(self):\n- return 'log_config'\n+ def scan_resource_conf(self, conf: Dict[str, List[Any]]) -> CheckResult:\n+ # flow logs can't be enabled for `INTERNAL_HTTPS_LOAD_BALANCER` subnetworks\n+ purpose = conf.get(\"purpose\")\n+ if purpose and purpose[0] == \"INTERNAL_HTTPS_LOAD_BALANCER\":\n+ return CheckResult.UNKNOWN\n+\n+ return super().scan_resource_conf(conf)\n+\n+ def get_inspected_key(self) -> str:\n+ return \"log_config\"\n \n- def get_expected_values(self):\n+ def get_expected_values(self) -> List[Any]:\n return [ANY_VALUE]\n", "issue": "CKV_GCP_26 is not working as expected when using terraform plan output.\n**Describe the bug**\r\nCKV_GCP_26 check is not providing expected output when it is ran against terraform output json file. Check is gives the result as PASSED even if we don't have the flow logs enabled for the subnet. However if we run it against the directory where we have the .tf files then the check returns the FAILED status which is expected. \r\n\r\ncheckov version used: `2.0.236`\r\nTerraform version used: `1.0.1`\r\n\r\n**To Reproduce**\r\n1. Create a sample subnet resource in a network.tf file. \r\n```\r\nresource \"google_compute_network\" \"vpc\" {\r\n name = \"test-vpc\"\r\n auto_create_subnetworks = \"false\"\r\n routing_mode = \"REGIONAL\"\r\n}\r\n\r\nresource \"google_compute_subnetwork\" \"private-subnet\" {\r\n name = \"test-sub\"\r\n ip_cidr_range = \"10.1.0.0/16\"\r\n network = google_compute_network.vpc.self_link\r\n private_ip_google_access = true\r\n}\r\n```\r\n2. terraform plan -out tf.plan\r\n3. terraform show -json tf.plan > tf.json \r\n4. checkov -f tf.json\r\n5. Now run checkov -f network.tf\r\n\r\nBoth the commands will give conflicting results\r\n\r\n```\r\nCheck: CKV_GCP_26: \"Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network\"\r\n PASSED for resource: google_compute_subnetwork.private-subnet\r\n File: /tf/tfplan.json:0-0\r\n Guide: https://docs.bridgecrew.io/docs/bc_gcp_logging_1\r\n```\r\n```\r\nCheck: CKV_GCP_26: \"Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network\"\r\n FAILED for resource: google_compute_subnetwork.private-subnet\r\n File: /network.tf:6-11\r\n Guide: https://docs.bridgecrew.io/docs/bc_gcp_logging_1\r\n\r\n 6 | resource \"google_compute_subnetwork\" \"private-subnet\" {\r\n 7 | name = var.private_subnet_name\r\n 8 | ip_cidr_range = var.private_subnet_cidr\r\n 9 | network = google_compute_network.vpc.self_link\r\n 10 | private_ip_google_access = true\r\n 11 | }\r\n```\r\n**Expected behavior**\r\nThe check should return the status as FAILED when running it against terraform plan output json\r\n\n", "before_files": [{"content": "from checkov.common.models.enums import CheckCategories\nfrom checkov.common.models.consts import ANY_VALUE\nfrom checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck\n\n\nclass AKSApiServerAuthorizedIpRanges(BaseResourceValueCheck):\n def __init__(self):\n name = \"Ensure AKS has an API Server Authorized IP Ranges enabled\"\n id = \"CKV_AZURE_6\"\n supported_resources = ['azurerm_kubernetes_cluster']\n categories = [CheckCategories.KUBERNETES]\n super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)\n\n def get_inspected_key(self):\n return 'api_server_authorized_ip_ranges/[0]'\n\n def get_expected_value(self):\n return ANY_VALUE\n\n\ncheck = AKSApiServerAuthorizedIpRanges()\n", "path": "checkov/terraform/checks/resource/azure/AKSApiServerAuthorizedIpRanges.py"}, {"content": "from abc import abstractmethod\nfrom collections.abc import Iterable\nfrom typing import List, Dict, Any\n\nimport dpath.util\nimport re\nfrom checkov.terraform.checks.resource.base_resource_check import BaseResourceCheck\nfrom checkov.common.models.enums import CheckResult, CheckCategories\nfrom checkov.common.models.consts import ANY_VALUE\nfrom checkov.common.util.type_forcers import force_list\nfrom checkov.terraform.graph_builder.utils import get_referenced_vertices_in_value\nfrom checkov.terraform.parser_functions import handle_dynamic_values\nfrom checkov.terraform.parser_utils import find_var_blocks\n\n\n\nclass BaseResourceValueCheck(BaseResourceCheck):\n def __init__(\n self,\n name: str,\n id: str,\n categories: \"Iterable[CheckCategories]\",\n supported_resources: \"Iterable[str]\",\n missing_block_result: CheckResult = CheckResult.FAILED,\n ) -> None:\n super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)\n self.missing_block_result = missing_block_result\n\n @staticmethod\n def _filter_key_path(path: str) -> List[str]:\n \"\"\"\n Filter an attribute path to contain only named attributes by dropping array indices from the path)\n :param path: valid JSONPath of an attribute\n :return: List of named attributes with respect to the input JSONPath order\n \"\"\"\n return [x for x in path.split(\"/\") if not re.search(re.compile(r\"^\\[?\\d+]?$\"), x)]\n\n @staticmethod\n def _is_variable_dependant(value: Any) -> bool:\n if not isinstance(value, str):\n return False\n if \"${\" not in value:\n return False\n\n if find_var_blocks(value):\n return True\n return False\n\n @staticmethod\n def _is_nesting_key(inspected_attributes: List[str], key: List[str]) -> bool:\n \"\"\"\n Resolves whether a key is a subset of the inspected nesting attributes\n :param inspected_attributes: list of nesting attributes\n :param key: JSONPath key of an attribute\n :return: True/False\n \"\"\"\n return any(x in key for x in inspected_attributes)\n\n def scan_resource_conf(self, conf: Dict[str, List[Any]]) -> CheckResult:\n handle_dynamic_values(conf)\n inspected_key = self.get_inspected_key()\n expected_values = self.get_expected_values()\n if dpath.search(conf, inspected_key) != {}:\n # Inspected key exists\n value = dpath.get(conf, inspected_key)\n if isinstance(value, list) and len(value) == 1:\n value = value[0]\n if value is None:\n return self.missing_block_result\n if ANY_VALUE in expected_values and value is not None and (not isinstance(value, str) or value):\n # Key is found on the configuration - if it accepts any value, the check is PASSED\n return CheckResult.PASSED\n if self._is_variable_dependant(value):\n # If the tested attribute is variable-dependant, then result is PASSED\n return CheckResult.PASSED\n if value in expected_values:\n return CheckResult.PASSED\n if get_referenced_vertices_in_value(value=value, aliases={}, resources_types=[]):\n # we don't provide resources_types as we want to stay provider agnostic\n return CheckResult.UNKNOWN\n return CheckResult.FAILED\n else:\n # Look for the configuration in a bottom-up fashion\n inspected_attributes = self._filter_key_path(inspected_key)\n for attribute in reversed(inspected_attributes):\n for sub_key, sub_conf in dpath.search(conf, f\"**/{attribute}\", yielded=True):\n filtered_sub_key = self._filter_key_path(sub_key)\n # Only proceed with check if full path for key is similar - not partial match\n if inspected_attributes == filtered_sub_key:\n if self._is_nesting_key(inspected_attributes, filtered_sub_key):\n if isinstance(sub_conf, list) and len(sub_conf) == 1:\n sub_conf = sub_conf[0]\n if sub_conf in self.get_expected_values():\n return CheckResult.PASSED\n if self._is_variable_dependant(sub_conf):\n # If the tested attribute is variable-dependant, then result is PASSED\n return CheckResult.PASSED\n\n return self.missing_block_result\n\n @abstractmethod\n def get_inspected_key(self) -> str:\n \"\"\"\n :return: JSONPath syntax path of the checked attribute\n \"\"\"\n raise NotImplementedError()\n\n def get_expected_values(self) -> List[Any]:\n \"\"\"\n Override the method with the list of acceptable values if the check has more than one possible expected value, given\n the inspected key\n :return: List of expected values, defaults to a list of the expected value\n \"\"\"\n return [self.get_expected_value()]\n\n def get_expected_value(self) -> Any:\n \"\"\"\n Returns the default expected value, governed by provider best practices\n \"\"\"\n return True\n\n def get_evaluated_keys(self) -> List[str]:\n return force_list(self.get_inspected_key())\n", "path": "checkov/terraform/checks/resource/base_resource_value_check.py"}, {"content": "from checkov.terraform.checks.resource.base_resource_value_check import BaseResourceValueCheck\nfrom checkov.common.models.enums import CheckCategories\nfrom checkov.common.models.consts import ANY_VALUE\n\n\nclass GoogleSubnetworkLoggingEnabled(BaseResourceValueCheck):\n def __init__(self):\n name = \"Ensure that VPC Flow Logs is enabled for every subnet in a VPC Network\"\n id = \"CKV_GCP_26\"\n supported_resources = ['google_compute_subnetwork']\n categories = [CheckCategories.LOGGING]\n super().__init__(name=name, id=id, categories=categories, supported_resources=supported_resources)\n\n def get_inspected_key(self):\n return 'log_config'\n\n def get_expected_values(self):\n return [ANY_VALUE]\n\n\ncheck = GoogleSubnetworkLoggingEnabled()\n", "path": "checkov/terraform/checks/resource/gcp/GoogleSubnetworkLoggingEnabled.py"}]} | 2,973 | 1,014 |
gh_patches_debug_28446 | rasdani/github-patches | git_diff | wagtail__wagtail-11577 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add system checks for `WAGTAIL_DATE_FORMAT`, `WAGTAIL_DATETIME_FORMAT`, `WAGTAIL_TIME_FORMAT` being listed in Django configured formats
### Is your proposal related to a problem?
When configuring any of the `WAGTAIL_*_FORMAT` configs, these must be included in the relevant Django formats.
https://docs.wagtail.org/en/stable/reference/settings.html#wagtail-date-format-wagtail-datetime-format-wagtail-time-format
> ...must be one of the recognised formats listed in the DATE_INPUT_FORMATS, TIME_INPUT_FORMATS, or DATETIME_INPUT_FORMATS setting respectively
This config coordination is easy to to get wrong causing non-intuitive behaviour as Wagtail/Django will fallback to defaults.
### Describe the solution you'd like
* Using the [Django system check framework](https://docs.djangoproject.com/en/5.0/topics/checks/) or similar, ensure that if there are misconfiguration issues there will be an error thrown or report at app startup.
### Describe alternatives you've considered
* Leave as is, the documentation advises what to do.
### Additional context
* An older PR had a really solid start to this but had a few questions and was only a draft. https://github.com/wagtail/wagtail/pull/6168
* It may make sense to start with a simple version of these checks as a smaller scoped PR.
### Working on this
* This would be good for anyone willing to dig deep into these configs & their Django equivalents.
* Some knowledge or learning of the way the Django system check framework works and exploration of the current usage in Wagtail.
* The PR linked above would be a good start but may not be the right way forward, it also did not have tests and tests are a must.
* View our [contributing guidelines](https://docs.wagtail.org/en/latest/contributing/index.html), add a comment to the issue once you’re ready to start.
</issue>
<code>
[start of wagtail/admin/checks.py]
1 import os
2
3 from django.core.checks import Error, Tags, Warning, register
4
5
6 @register("staticfiles")
7 def css_install_check(app_configs, **kwargs):
8 errors = []
9
10 css_path = os.path.join(
11 os.path.dirname(__file__), "static", "wagtailadmin", "css", "core.css"
12 )
13
14 if not os.path.isfile(css_path):
15 error_hint = (
16 """
17 Most likely you are running a development (non-packaged) copy of
18 Wagtail and have not built the static assets -
19 see https://docs.wagtail.org/en/latest/contributing/developing.html
20
21 File not found: %s
22 """
23 % css_path
24 )
25
26 errors.append(
27 Warning(
28 "CSS for the Wagtail admin is missing",
29 hint=error_hint,
30 id="wagtailadmin.W001",
31 )
32 )
33 return errors
34
35
36 @register(Tags.admin)
37 def base_form_class_check(app_configs, **kwargs):
38 from wagtail.admin.forms import WagtailAdminPageForm
39 from wagtail.models import get_page_models
40
41 errors = []
42
43 for cls in get_page_models():
44 if not issubclass(cls.base_form_class, WagtailAdminPageForm):
45 errors.append(
46 Error(
47 "{}.base_form_class does not extend WagtailAdminPageForm".format(
48 cls.__name__
49 ),
50 hint="Ensure that {}.{} extends WagtailAdminPageForm".format(
51 cls.base_form_class.__module__, cls.base_form_class.__name__
52 ),
53 obj=cls,
54 id="wagtailadmin.E001",
55 )
56 )
57
58 return errors
59
60
61 @register(Tags.admin)
62 def get_form_class_check(app_configs, **kwargs):
63 from wagtail.admin.forms import WagtailAdminPageForm
64 from wagtail.models import get_page_models
65
66 errors = []
67
68 for cls in get_page_models():
69 edit_handler = cls.get_edit_handler()
70 if not issubclass(edit_handler.get_form_class(), WagtailAdminPageForm):
71 errors.append(
72 Error(
73 "{cls}.get_edit_handler().get_form_class() does not extend WagtailAdminPageForm".format(
74 cls=cls.__name__
75 ),
76 hint="Ensure that the panel definition for {cls} creates a subclass of WagtailAdminPageForm".format(
77 cls=cls.__name__
78 ),
79 obj=cls,
80 id="wagtailadmin.E002",
81 )
82 )
83
84 return errors
85
86
87 @register("panels")
88 def inline_panel_model_panels_check(app_configs, **kwargs):
89 from wagtail.models import get_page_models
90
91 errors = []
92 page_models = get_page_models()
93
94 for cls in page_models:
95 errors.extend(check_panels_in_model(cls))
96
97 # filter out duplicate errors found for the same model
98 unique_errors = []
99 for error in errors:
100 if error.msg not in [e.msg for e in unique_errors]:
101 unique_errors.append(error)
102 return unique_errors
103
104
105 def check_panels_in_model(cls, context="model"):
106 """Check panels configuration uses `panels` when `edit_handler` not in use."""
107 from wagtail.admin.panels import InlinePanel, PanelGroup
108 from wagtail.models import Page
109
110 errors = []
111
112 if hasattr(cls, "get_edit_handler"):
113 # must check the InlinePanel related models
114 edit_handler = cls.get_edit_handler()
115 for tab in edit_handler.children:
116 if isinstance(tab, PanelGroup):
117 inline_panel_children = [
118 panel for panel in tab.children if isinstance(panel, InlinePanel)
119 ]
120 for inline_panel_child in inline_panel_children:
121 errors.extend(
122 check_panels_in_model(
123 inline_panel_child.db_field.related_model,
124 context="InlinePanel model",
125 )
126 )
127
128 if issubclass(cls, Page) or hasattr(cls, "edit_handler"):
129 # Pages do not need to be checked for standalone tabbed_panel usage
130 # if edit_handler is used on any model, assume config is correct
131 return errors
132
133 tabbed_panels = [
134 "content_panels",
135 "promote_panels",
136 "settings_panels",
137 ]
138
139 for panel_name in tabbed_panels:
140 class_name = cls.__name__
141 if not hasattr(cls, panel_name):
142 continue
143
144 panel_name_short = panel_name.replace("_panels", "").title()
145 error_title = "{}.{} will have no effect on {} editing".format(
146 class_name, panel_name, context
147 )
148
149 if "InlinePanel" in context:
150 error_hint = """Ensure that {} uses `panels` instead of `{}`.
151 There are no tabs on non-Page model editing within InlinePanels.""".format(
152 class_name, panel_name
153 )
154 else:
155 error_hint = """Ensure that {} uses `panels` instead of `{}`\
156 or set up an `edit_handler` if you want a tabbed editing interface.
157 There are no default tabs on non-Page models so there will be no \
158 {} tab for the {} to render in.""".format(
159 class_name, panel_name, panel_name_short, panel_name
160 )
161
162 error = Warning(error_title, hint=error_hint, obj=cls, id="wagtailadmin.W002")
163
164 errors.append(error)
165
166 return errors
167
168
169 @register("wagtailadmin_base_url")
170 def wagtail_admin_base_url_check(app_configs, **kwargs):
171 from django.conf import settings
172
173 errors = []
174
175 if getattr(settings, "WAGTAILADMIN_BASE_URL", None) is None:
176 errors.append(
177 Warning(
178 "The WAGTAILADMIN_BASE_URL setting is not defined",
179 hint="This should be the base URL used to access the Wagtail admin site. "
180 "Without this, URLs in notification emails will not display correctly.",
181 id="wagtailadmin.W003",
182 )
183 )
184
185 return errors
186
187
188 @register("file_overwrite")
189 def file_overwrite_check(app_configs, **kwargs):
190 from django import VERSION as DJANGO_VERSION
191 from django.conf import settings
192
193 if DJANGO_VERSION >= (5, 1):
194 file_storage = getattr(settings, "STORAGES")["default"]["BACKEND"]
195 else:
196 try:
197 file_storage = getattr(settings, "STORAGES")["default"]["BACKEND"]
198 except AttributeError:
199 file_storage = getattr(settings, "DEFAULT_FILE_STORAGE", None)
200
201 errors = []
202
203 if file_storage == "storages.backends.s3boto3.S3Boto3Storage" and getattr(
204 settings, "AWS_S3_FILE_OVERWRITE", True
205 ):
206 errors.append(
207 Warning(
208 "The AWS_S3_FILE_OVERWRITE setting is set to True",
209 hint="This should be set to False. The incorrect setting can cause documents and "
210 "other user-uploaded files to be silently overwritten or deleted.",
211 id="wagtailadmin.W004",
212 )
213 )
214 if file_storage == "storages.backends.azure_storage.AzureStorage" and getattr(
215 settings, "AZURE_OVERWRITE_FILES", False
216 ):
217 errors.append(
218 Warning(
219 "The AZURE_OVERWRITE_FILES setting is set to True",
220 hint="This should be set to False. The incorrect setting can cause documents and "
221 "other user-uploaded files to be silently overwritten or deleted.",
222 id="wagtailadmin.W004",
223 )
224 )
225 if file_storage == "storages.backends.gcloud.GoogleCloudStorage" and getattr(
226 settings, "GS_FILE_OVERWRITE", True
227 ):
228 errors.append(
229 Warning(
230 "The GS_FILE_OVERWRITE setting is set to True",
231 hint="This should be set to False. The incorrect setting can cause documents and "
232 "other user-uploaded files to be silently overwritten or deleted.",
233 id="wagtailadmin.W004",
234 )
235 )
236
237 return errors
238
[end of wagtail/admin/checks.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/wagtail/admin/checks.py b/wagtail/admin/checks.py
--- a/wagtail/admin/checks.py
+++ b/wagtail/admin/checks.py
@@ -235,3 +235,54 @@
)
return errors
+
+
+@register("datetime_format")
+def datetime_format_check(app_configs, **kwargs):
+ """
+ If L10N is enabled, check if WAGTAIL_* formats are compatible with Django input formats.
+ See https://docs.djangoproject.com/en/stable/topics/i18n/formatting/#creating-custom-format-files
+ See https://docs.wagtail.org/en/stable/reference/settings.html#wagtail-date-format-wagtail-datetime-format-wagtail-time-format
+ """
+
+ from django.conf import settings
+ from django.utils import formats, translation
+
+ errors = []
+
+ if not getattr(settings, "USE_L10N", False):
+ return errors
+
+ formats.FORMAT_SETTINGS = formats.FORMAT_SETTINGS.union(
+ [
+ "WAGTAIL_DATE_FORMAT",
+ "WAGTAIL_DATETIME_FORMAT",
+ "WAGTAIL_TIME_FORMAT",
+ ]
+ )
+
+ for code, label in settings.LANGUAGES:
+ with translation.override(code):
+ for wagtail_format, django_formats in [
+ ("WAGTAIL_DATE_FORMAT", "DATE_INPUT_FORMATS"),
+ ("WAGTAIL_DATETIME_FORMAT", "DATETIME_INPUT_FORMATS"),
+ ("WAGTAIL_TIME_FORMAT", "TIME_INPUT_FORMATS"),
+ ]:
+ wagtail_format_value = getattr(settings, wagtail_format, None)
+ django_formats_value = getattr(settings, django_formats, None)
+
+ if wagtail_format_value is None:
+ # Skip the iteration if wagtail_format is not present
+ continue
+
+ input_format = formats.get_format_lazy(wagtail_format_value)
+ input_formats = formats.get_format_lazy(django_formats_value)
+ if str(input_format) not in str(input_formats):
+ errors.append(
+ Error(
+ "Configuration error",
+ hint=f"{wagtail_format} {input_format} must be in {django_formats} for language {label} ({code}).",
+ )
+ )
+
+ return errors
| {"golden_diff": "diff --git a/wagtail/admin/checks.py b/wagtail/admin/checks.py\n--- a/wagtail/admin/checks.py\n+++ b/wagtail/admin/checks.py\n@@ -235,3 +235,54 @@\n )\n \n return errors\n+\n+\n+@register(\"datetime_format\")\n+def datetime_format_check(app_configs, **kwargs):\n+ \"\"\"\n+ If L10N is enabled, check if WAGTAIL_* formats are compatible with Django input formats.\n+ See https://docs.djangoproject.com/en/stable/topics/i18n/formatting/#creating-custom-format-files\n+ See https://docs.wagtail.org/en/stable/reference/settings.html#wagtail-date-format-wagtail-datetime-format-wagtail-time-format\n+ \"\"\"\n+\n+ from django.conf import settings\n+ from django.utils import formats, translation\n+\n+ errors = []\n+\n+ if not getattr(settings, \"USE_L10N\", False):\n+ return errors\n+\n+ formats.FORMAT_SETTINGS = formats.FORMAT_SETTINGS.union(\n+ [\n+ \"WAGTAIL_DATE_FORMAT\",\n+ \"WAGTAIL_DATETIME_FORMAT\",\n+ \"WAGTAIL_TIME_FORMAT\",\n+ ]\n+ )\n+\n+ for code, label in settings.LANGUAGES:\n+ with translation.override(code):\n+ for wagtail_format, django_formats in [\n+ (\"WAGTAIL_DATE_FORMAT\", \"DATE_INPUT_FORMATS\"),\n+ (\"WAGTAIL_DATETIME_FORMAT\", \"DATETIME_INPUT_FORMATS\"),\n+ (\"WAGTAIL_TIME_FORMAT\", \"TIME_INPUT_FORMATS\"),\n+ ]:\n+ wagtail_format_value = getattr(settings, wagtail_format, None)\n+ django_formats_value = getattr(settings, django_formats, None)\n+\n+ if wagtail_format_value is None:\n+ # Skip the iteration if wagtail_format is not present\n+ continue\n+\n+ input_format = formats.get_format_lazy(wagtail_format_value)\n+ input_formats = formats.get_format_lazy(django_formats_value)\n+ if str(input_format) not in str(input_formats):\n+ errors.append(\n+ Error(\n+ \"Configuration error\",\n+ hint=f\"{wagtail_format} {input_format} must be in {django_formats} for language {label} ({code}).\",\n+ )\n+ )\n+\n+ return errors\n", "issue": "Add system checks for `WAGTAIL_DATE_FORMAT`, `WAGTAIL_DATETIME_FORMAT`, `WAGTAIL_TIME_FORMAT` being listed in Django configured formats\n### Is your proposal related to a problem?\r\n\r\nWhen configuring any of the `WAGTAIL_*_FORMAT` configs, these must be included in the relevant Django formats.\r\n\r\nhttps://docs.wagtail.org/en/stable/reference/settings.html#wagtail-date-format-wagtail-datetime-format-wagtail-time-format\r\n\r\n> ...must be one of the recognised formats listed in the DATE_INPUT_FORMATS, TIME_INPUT_FORMATS, or DATETIME_INPUT_FORMATS setting respectively \r\n\r\nThis config coordination is easy to to get wrong causing non-intuitive behaviour as Wagtail/Django will fallback to defaults.\r\n\r\n### Describe the solution you'd like\r\n\r\n* Using the [Django system check framework](https://docs.djangoproject.com/en/5.0/topics/checks/) or similar, ensure that if there are misconfiguration issues there will be an error thrown or report at app startup.\r\n\r\n### Describe alternatives you've considered\r\n\r\n* Leave as is, the documentation advises what to do.\r\n\r\n### Additional context\r\n\r\n* An older PR had a really solid start to this but had a few questions and was only a draft. https://github.com/wagtail/wagtail/pull/6168\r\n* It may make sense to start with a simple version of these checks as a smaller scoped PR.\r\n\r\n### Working on this\r\n\r\n* This would be good for anyone willing to dig deep into these configs & their Django equivalents.\r\n* Some knowledge or learning of the way the Django system check framework works and exploration of the current usage in Wagtail.\r\n* The PR linked above would be a good start but may not be the right way forward, it also did not have tests and tests are a must.\r\n* View our [contributing guidelines](https://docs.wagtail.org/en/latest/contributing/index.html), add a comment to the issue once you\u2019re ready to start.\r\n\n", "before_files": [{"content": "import os\n\nfrom django.core.checks import Error, Tags, Warning, register\n\n\n@register(\"staticfiles\")\ndef css_install_check(app_configs, **kwargs):\n errors = []\n\n css_path = os.path.join(\n os.path.dirname(__file__), \"static\", \"wagtailadmin\", \"css\", \"core.css\"\n )\n\n if not os.path.isfile(css_path):\n error_hint = (\n \"\"\"\n Most likely you are running a development (non-packaged) copy of\n Wagtail and have not built the static assets -\n see https://docs.wagtail.org/en/latest/contributing/developing.html\n\n File not found: %s\n \"\"\"\n % css_path\n )\n\n errors.append(\n Warning(\n \"CSS for the Wagtail admin is missing\",\n hint=error_hint,\n id=\"wagtailadmin.W001\",\n )\n )\n return errors\n\n\n@register(Tags.admin)\ndef base_form_class_check(app_configs, **kwargs):\n from wagtail.admin.forms import WagtailAdminPageForm\n from wagtail.models import get_page_models\n\n errors = []\n\n for cls in get_page_models():\n if not issubclass(cls.base_form_class, WagtailAdminPageForm):\n errors.append(\n Error(\n \"{}.base_form_class does not extend WagtailAdminPageForm\".format(\n cls.__name__\n ),\n hint=\"Ensure that {}.{} extends WagtailAdminPageForm\".format(\n cls.base_form_class.__module__, cls.base_form_class.__name__\n ),\n obj=cls,\n id=\"wagtailadmin.E001\",\n )\n )\n\n return errors\n\n\n@register(Tags.admin)\ndef get_form_class_check(app_configs, **kwargs):\n from wagtail.admin.forms import WagtailAdminPageForm\n from wagtail.models import get_page_models\n\n errors = []\n\n for cls in get_page_models():\n edit_handler = cls.get_edit_handler()\n if not issubclass(edit_handler.get_form_class(), WagtailAdminPageForm):\n errors.append(\n Error(\n \"{cls}.get_edit_handler().get_form_class() does not extend WagtailAdminPageForm\".format(\n cls=cls.__name__\n ),\n hint=\"Ensure that the panel definition for {cls} creates a subclass of WagtailAdminPageForm\".format(\n cls=cls.__name__\n ),\n obj=cls,\n id=\"wagtailadmin.E002\",\n )\n )\n\n return errors\n\n\n@register(\"panels\")\ndef inline_panel_model_panels_check(app_configs, **kwargs):\n from wagtail.models import get_page_models\n\n errors = []\n page_models = get_page_models()\n\n for cls in page_models:\n errors.extend(check_panels_in_model(cls))\n\n # filter out duplicate errors found for the same model\n unique_errors = []\n for error in errors:\n if error.msg not in [e.msg for e in unique_errors]:\n unique_errors.append(error)\n return unique_errors\n\n\ndef check_panels_in_model(cls, context=\"model\"):\n \"\"\"Check panels configuration uses `panels` when `edit_handler` not in use.\"\"\"\n from wagtail.admin.panels import InlinePanel, PanelGroup\n from wagtail.models import Page\n\n errors = []\n\n if hasattr(cls, \"get_edit_handler\"):\n # must check the InlinePanel related models\n edit_handler = cls.get_edit_handler()\n for tab in edit_handler.children:\n if isinstance(tab, PanelGroup):\n inline_panel_children = [\n panel for panel in tab.children if isinstance(panel, InlinePanel)\n ]\n for inline_panel_child in inline_panel_children:\n errors.extend(\n check_panels_in_model(\n inline_panel_child.db_field.related_model,\n context=\"InlinePanel model\",\n )\n )\n\n if issubclass(cls, Page) or hasattr(cls, \"edit_handler\"):\n # Pages do not need to be checked for standalone tabbed_panel usage\n # if edit_handler is used on any model, assume config is correct\n return errors\n\n tabbed_panels = [\n \"content_panels\",\n \"promote_panels\",\n \"settings_panels\",\n ]\n\n for panel_name in tabbed_panels:\n class_name = cls.__name__\n if not hasattr(cls, panel_name):\n continue\n\n panel_name_short = panel_name.replace(\"_panels\", \"\").title()\n error_title = \"{}.{} will have no effect on {} editing\".format(\n class_name, panel_name, context\n )\n\n if \"InlinePanel\" in context:\n error_hint = \"\"\"Ensure that {} uses `panels` instead of `{}`.\nThere are no tabs on non-Page model editing within InlinePanels.\"\"\".format(\n class_name, panel_name\n )\n else:\n error_hint = \"\"\"Ensure that {} uses `panels` instead of `{}`\\\nor set up an `edit_handler` if you want a tabbed editing interface.\nThere are no default tabs on non-Page models so there will be no \\\n{} tab for the {} to render in.\"\"\".format(\n class_name, panel_name, panel_name_short, panel_name\n )\n\n error = Warning(error_title, hint=error_hint, obj=cls, id=\"wagtailadmin.W002\")\n\n errors.append(error)\n\n return errors\n\n\n@register(\"wagtailadmin_base_url\")\ndef wagtail_admin_base_url_check(app_configs, **kwargs):\n from django.conf import settings\n\n errors = []\n\n if getattr(settings, \"WAGTAILADMIN_BASE_URL\", None) is None:\n errors.append(\n Warning(\n \"The WAGTAILADMIN_BASE_URL setting is not defined\",\n hint=\"This should be the base URL used to access the Wagtail admin site. \"\n \"Without this, URLs in notification emails will not display correctly.\",\n id=\"wagtailadmin.W003\",\n )\n )\n\n return errors\n\n\n@register(\"file_overwrite\")\ndef file_overwrite_check(app_configs, **kwargs):\n from django import VERSION as DJANGO_VERSION\n from django.conf import settings\n\n if DJANGO_VERSION >= (5, 1):\n file_storage = getattr(settings, \"STORAGES\")[\"default\"][\"BACKEND\"]\n else:\n try:\n file_storage = getattr(settings, \"STORAGES\")[\"default\"][\"BACKEND\"]\n except AttributeError:\n file_storage = getattr(settings, \"DEFAULT_FILE_STORAGE\", None)\n\n errors = []\n\n if file_storage == \"storages.backends.s3boto3.S3Boto3Storage\" and getattr(\n settings, \"AWS_S3_FILE_OVERWRITE\", True\n ):\n errors.append(\n Warning(\n \"The AWS_S3_FILE_OVERWRITE setting is set to True\",\n hint=\"This should be set to False. The incorrect setting can cause documents and \"\n \"other user-uploaded files to be silently overwritten or deleted.\",\n id=\"wagtailadmin.W004\",\n )\n )\n if file_storage == \"storages.backends.azure_storage.AzureStorage\" and getattr(\n settings, \"AZURE_OVERWRITE_FILES\", False\n ):\n errors.append(\n Warning(\n \"The AZURE_OVERWRITE_FILES setting is set to True\",\n hint=\"This should be set to False. The incorrect setting can cause documents and \"\n \"other user-uploaded files to be silently overwritten or deleted.\",\n id=\"wagtailadmin.W004\",\n )\n )\n if file_storage == \"storages.backends.gcloud.GoogleCloudStorage\" and getattr(\n settings, \"GS_FILE_OVERWRITE\", True\n ):\n errors.append(\n Warning(\n \"The GS_FILE_OVERWRITE setting is set to True\",\n hint=\"This should be set to False. The incorrect setting can cause documents and \"\n \"other user-uploaded files to be silently overwritten or deleted.\",\n id=\"wagtailadmin.W004\",\n )\n )\n\n return errors\n", "path": "wagtail/admin/checks.py"}]} | 3,262 | 509 |
gh_patches_debug_4595 | rasdani/github-patches | git_diff | ocf__ocfweb-45 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Links in headings are broken on docs
For example:
https://dev.ocf.berkeley.edu/docs/faq/
I think this is a side-effect of overreaching CSS rules intended for the link icons.
</issue>
<code>
[start of ocfweb/component/markdown.py]
1 import re
2
3 import mistune
4 from django.core.urlresolvers import reverse
5
6 from ocfweb.caching import lru_cache
7
8 # tags of a format like: [[!meta title="Backups"]]
9 META_REGEX = re.compile('\[\[!meta ([a-z]+)="([^"]*)"\]\]')
10
11
12 class HtmlCommentsInlineLexerMixin:
13 """Strip HTML comments inside lines."""
14
15 def enable_html_comments(self):
16 self.rules.html_comment = re.compile(
17 '^<!--(.*?)-->'
18 )
19 self.default_rules.insert(0, 'html_comment')
20
21 def output_html_comment(self, m):
22 return ''
23
24
25 class HtmlCommentsBlockLexerMixin:
26 """Strip blocks which consist entirely of HTML comments."""
27
28 def enable_html_comments(self):
29 self.rules.html_comment = re.compile(
30 '^<!--(.*?)-->'
31 )
32 self.default_rules.insert(0, 'html_comment')
33
34 def parse_html_comment(self, m):
35 pass
36
37
38 class DjangoLinkInlineLexerMixin:
39 """Turn special Markdown link syntax into Django links.
40
41 In Django templates, we can use `url` tags, such as:
42 {% url 'staff-hours' %}
43 {% url 'doc' 'staff/backend/backups' %}
44
45 In Markdown, we use the following fake syntax to generate Django links:
46 [[human readable name|staff-hours]]
47 [[human readable name|doc staff/backend/backups]]
48
49 You can link to fragments with a # at the very end:
50 [[human readable name|staff-hours#something]]
51 [[human readable name|doc staff/backend/backups#something]]
52 """
53
54 split_words = re.compile('((?:\S|\\\\ )+)')
55
56 def enable_django_links(self):
57 self.rules.django_link = re.compile(
58 '^\[\[(?!\!)'
59 '([\s\S]+?)'
60 '\|'
61 '([^#]+?)'
62 '(?:#(.*?))?'
63 '\]\]'
64 )
65 self.default_rules.insert(0, 'django_link')
66
67 def output_django_link(self, m):
68 text, target, fragment = m.group(1), m.group(2), m.group(3)
69
70 def href(link, fragment):
71 if fragment:
72 return link + '#' + fragment
73 return link
74
75 words = DjangoLinkInlineLexerMixin.split_words.findall(target)
76 name, *params = words
77 return self.renderer.link(
78 link=href(reverse(name, args=params), fragment),
79 title=None,
80 text=text,
81 )
82
83
84 class HeaderRendererMixin:
85 """Mixin to render headers with auto-generated IDs (or provided IDs).
86
87 If headers are written as usual, they'll be given automatically-generated
88 IDs based on their header level and text.
89
90 Headers can also be specified with an ID at the end wrapped in curly braces:
91
92 ### My Header {my_id}
93
94 This ID will be used directly without further manipulation, and can be
95 relied on for linking.
96
97 Custom IDs can consist only of lowercase a-z, 0-9, dash, and underscore.
98
99 IDs are tracked into a table of contents which should be reset before
100 rendering a document and read afterwards.
101 """
102
103 def reset_toc(self):
104 self.toc = []
105 self.toc_ids = set()
106
107 def get_toc(self):
108 return self.toc
109
110 def header(self, text, level, raw=None):
111 custom_id_match = re.match(r'^(.*?)\s+{([a-z0-9\-_]+)}\s*$', text)
112 if custom_id_match:
113 text = custom_id_match.group(1)
114 id = custom_id_match.group(2)
115
116 if id in self.toc_ids:
117 raise ValueError('Duplicate header ID in Markdown: "{}"'.format(id))
118 else:
119 id = 'h{level}_{title}'.format(
120 level=level,
121 title=re.sub('[^a-z0-9\-_ ]', '', text.lower()).strip().replace(' ', '-'),
122 )
123
124 # dumb collision avoidance
125 while id in self.toc_ids:
126 id += '_'
127
128 self.toc.append((level, text, id))
129 self.toc_ids.add(id)
130 return '<h{level} id="{id}">{text} <a class="" href="#{id}"><span></span></a></h{level}>\n'.format(
131 level=level,
132 id=id,
133 text=text,
134 )
135
136
137 class OcfMarkdownRenderer(
138 HeaderRendererMixin,
139 mistune.Renderer,
140 ):
141 pass
142
143
144 class OcfMarkdownInlineLexer(
145 mistune.InlineLexer,
146 DjangoLinkInlineLexerMixin,
147 HtmlCommentsInlineLexerMixin,
148 ):
149 pass
150
151
152 class OcfMarkdownBlockLexer(
153 mistune.BlockLexer,
154 HtmlCommentsBlockLexerMixin,
155 ):
156 pass
157
158
159 _renderer = OcfMarkdownRenderer(
160 escape=True,
161 hard_wrap=False,
162 )
163
164 _inline = OcfMarkdownInlineLexer(_renderer)
165 _inline.enable_html_comments()
166 _inline.enable_django_links()
167
168 _block = OcfMarkdownBlockLexer(mistune.BlockGrammar())
169 _block.enable_html_comments()
170
171 _markdown = mistune.Markdown(
172 renderer=_renderer,
173 inline=_inline,
174 block=_block,
175 )
176
177
178 def markdown(text):
179 _renderer.reset_toc()
180 return _markdown(text)
181
182
183 def text_and_meta(f):
184 """Return tuple (text, meta dict) for the given file.
185
186 Meta tags are stripped from the Markdown source, but the Markdown is
187 not rendered.
188 """
189 text = f.read()
190 meta = {}
191
192 def repl(match):
193 meta[match.group(1)] = match.group(2)
194 return ''
195
196 text = META_REGEX.sub(repl, text)
197 return text, meta
198
199
200 @lru_cache()
201 def markdown_and_toc(text):
202 """Return tuple (html, toc) for the given text."""
203 html = markdown(text)
204 return html, _renderer.get_toc()
205
[end of ocfweb/component/markdown.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/ocfweb/component/markdown.py b/ocfweb/component/markdown.py
--- a/ocfweb/component/markdown.py
+++ b/ocfweb/component/markdown.py
@@ -127,7 +127,7 @@
self.toc.append((level, text, id))
self.toc_ids.add(id)
- return '<h{level} id="{id}">{text} <a class="" href="#{id}"><span></span></a></h{level}>\n'.format(
+ return '<h{level} id="{id}">{text} <a class="anchor" href="#{id}"><span></span></a></h{level}>\n'.format(
level=level,
id=id,
text=text,
| {"golden_diff": "diff --git a/ocfweb/component/markdown.py b/ocfweb/component/markdown.py\n--- a/ocfweb/component/markdown.py\n+++ b/ocfweb/component/markdown.py\n@@ -127,7 +127,7 @@\n \n self.toc.append((level, text, id))\n self.toc_ids.add(id)\n- return '<h{level} id=\"{id}\">{text} <a class=\"\" href=\"#{id}\"><span></span></a></h{level}>\\n'.format(\n+ return '<h{level} id=\"{id}\">{text} <a class=\"anchor\" href=\"#{id}\"><span></span></a></h{level}>\\n'.format(\n level=level,\n id=id,\n text=text,\n", "issue": "Links in headings are broken on docs\nFor example:\nhttps://dev.ocf.berkeley.edu/docs/faq/\n\n\nI think this is a side-effect of overreaching CSS rules intended for the link icons.\n\n", "before_files": [{"content": "import re\n\nimport mistune\nfrom django.core.urlresolvers import reverse\n\nfrom ocfweb.caching import lru_cache\n\n# tags of a format like: [[!meta title=\"Backups\"]]\nMETA_REGEX = re.compile('\\[\\[!meta ([a-z]+)=\"([^\"]*)\"\\]\\]')\n\n\nclass HtmlCommentsInlineLexerMixin:\n \"\"\"Strip HTML comments inside lines.\"\"\"\n\n def enable_html_comments(self):\n self.rules.html_comment = re.compile(\n '^<!--(.*?)-->'\n )\n self.default_rules.insert(0, 'html_comment')\n\n def output_html_comment(self, m):\n return ''\n\n\nclass HtmlCommentsBlockLexerMixin:\n \"\"\"Strip blocks which consist entirely of HTML comments.\"\"\"\n\n def enable_html_comments(self):\n self.rules.html_comment = re.compile(\n '^<!--(.*?)-->'\n )\n self.default_rules.insert(0, 'html_comment')\n\n def parse_html_comment(self, m):\n pass\n\n\nclass DjangoLinkInlineLexerMixin:\n \"\"\"Turn special Markdown link syntax into Django links.\n\n In Django templates, we can use `url` tags, such as:\n {% url 'staff-hours' %}\n {% url 'doc' 'staff/backend/backups' %}\n\n In Markdown, we use the following fake syntax to generate Django links:\n [[human readable name|staff-hours]]\n [[human readable name|doc staff/backend/backups]]\n\n You can link to fragments with a # at the very end:\n [[human readable name|staff-hours#something]]\n [[human readable name|doc staff/backend/backups#something]]\n \"\"\"\n\n split_words = re.compile('((?:\\S|\\\\\\\\ )+)')\n\n def enable_django_links(self):\n self.rules.django_link = re.compile(\n '^\\[\\[(?!\\!)'\n '([\\s\\S]+?)'\n '\\|'\n '([^#]+?)'\n '(?:#(.*?))?'\n '\\]\\]'\n )\n self.default_rules.insert(0, 'django_link')\n\n def output_django_link(self, m):\n text, target, fragment = m.group(1), m.group(2), m.group(3)\n\n def href(link, fragment):\n if fragment:\n return link + '#' + fragment\n return link\n\n words = DjangoLinkInlineLexerMixin.split_words.findall(target)\n name, *params = words\n return self.renderer.link(\n link=href(reverse(name, args=params), fragment),\n title=None,\n text=text,\n )\n\n\nclass HeaderRendererMixin:\n \"\"\"Mixin to render headers with auto-generated IDs (or provided IDs).\n\n If headers are written as usual, they'll be given automatically-generated\n IDs based on their header level and text.\n\n Headers can also be specified with an ID at the end wrapped in curly braces:\n\n ### My Header {my_id}\n\n This ID will be used directly without further manipulation, and can be\n relied on for linking.\n\n Custom IDs can consist only of lowercase a-z, 0-9, dash, and underscore.\n\n IDs are tracked into a table of contents which should be reset before\n rendering a document and read afterwards.\n \"\"\"\n\n def reset_toc(self):\n self.toc = []\n self.toc_ids = set()\n\n def get_toc(self):\n return self.toc\n\n def header(self, text, level, raw=None):\n custom_id_match = re.match(r'^(.*?)\\s+{([a-z0-9\\-_]+)}\\s*$', text)\n if custom_id_match:\n text = custom_id_match.group(1)\n id = custom_id_match.group(2)\n\n if id in self.toc_ids:\n raise ValueError('Duplicate header ID in Markdown: \"{}\"'.format(id))\n else:\n id = 'h{level}_{title}'.format(\n level=level,\n title=re.sub('[^a-z0-9\\-_ ]', '', text.lower()).strip().replace(' ', '-'),\n )\n\n # dumb collision avoidance\n while id in self.toc_ids:\n id += '_'\n\n self.toc.append((level, text, id))\n self.toc_ids.add(id)\n return '<h{level} id=\"{id}\">{text} <a class=\"\" href=\"#{id}\"><span></span></a></h{level}>\\n'.format(\n level=level,\n id=id,\n text=text,\n )\n\n\nclass OcfMarkdownRenderer(\n HeaderRendererMixin,\n mistune.Renderer,\n):\n pass\n\n\nclass OcfMarkdownInlineLexer(\n mistune.InlineLexer,\n DjangoLinkInlineLexerMixin,\n HtmlCommentsInlineLexerMixin,\n):\n pass\n\n\nclass OcfMarkdownBlockLexer(\n mistune.BlockLexer,\n HtmlCommentsBlockLexerMixin,\n):\n pass\n\n\n_renderer = OcfMarkdownRenderer(\n escape=True,\n hard_wrap=False,\n)\n\n_inline = OcfMarkdownInlineLexer(_renderer)\n_inline.enable_html_comments()\n_inline.enable_django_links()\n\n_block = OcfMarkdownBlockLexer(mistune.BlockGrammar())\n_block.enable_html_comments()\n\n_markdown = mistune.Markdown(\n renderer=_renderer,\n inline=_inline,\n block=_block,\n)\n\n\ndef markdown(text):\n _renderer.reset_toc()\n return _markdown(text)\n\n\ndef text_and_meta(f):\n \"\"\"Return tuple (text, meta dict) for the given file.\n\n Meta tags are stripped from the Markdown source, but the Markdown is\n not rendered.\n \"\"\"\n text = f.read()\n meta = {}\n\n def repl(match):\n meta[match.group(1)] = match.group(2)\n return ''\n\n text = META_REGEX.sub(repl, text)\n return text, meta\n\n\n@lru_cache()\ndef markdown_and_toc(text):\n \"\"\"Return tuple (html, toc) for the given text.\"\"\"\n html = markdown(text)\n return html, _renderer.get_toc()\n", "path": "ocfweb/component/markdown.py"}]} | 2,420 | 174 |
gh_patches_debug_28036 | rasdani/github-patches | git_diff | open-mmlab__mmdetection-3112 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
mabe a bug in version 2.1.0
I upgrade mmdetection from 2.0.0 to 2.1.0, but I can't train with this error:ValueError: need at least one array to concatenate.
So I use version 2.0.0 and all work well, so I think maybe there is a bug in version 2.1.0
</issue>
<code>
[start of mmdet/datasets/cityscapes.py]
1 # Modified from https://github.com/facebookresearch/detectron2/blob/master/detectron2/data/datasets/cityscapes.py # noqa
2 # and https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/evaluation/evalInstanceLevelSemanticLabeling.py # noqa
3
4 import glob
5 import os
6 import os.path as osp
7 import tempfile
8
9 import mmcv
10 import numpy as np
11 import pycocotools.mask as maskUtils
12 from mmcv.utils import print_log
13
14 from .builder import DATASETS
15 from .coco import CocoDataset
16
17
18 @DATASETS.register_module()
19 class CityscapesDataset(CocoDataset):
20
21 CLASSES = ('person', 'rider', 'car', 'truck', 'bus', 'train', 'motorcycle',
22 'bicycle')
23
24 def _filter_imgs(self, min_size=32):
25 """Filter images too small or without ground truths."""
26 valid_inds = []
27 ids_with_ann = set(_['image_id'] for _ in self.coco.anns.values())
28 for i, img_info in enumerate(self.data_infos):
29 img_id = img_info['id']
30 ann_ids = self.coco.getAnnIds(imgIds=[img_id])
31 ann_info = self.coco.loadAnns(ann_ids)
32 all_iscrowd = all([_['iscrowd'] for _ in ann_info])
33 if self.filter_empty_gt and (self.img_ids[i] not in ids_with_ann
34 or all_iscrowd):
35 continue
36 if min(img_info['width'], img_info['height']) >= min_size:
37 valid_inds.append(i)
38 return valid_inds
39
40 def _parse_ann_info(self, img_info, ann_info):
41 """Parse bbox and mask annotation.
42
43 Args:
44 img_info (dict): Image info of an image.
45 ann_info (list[dict]): Annotation info of an image.
46
47 Returns:
48 dict: A dict containing the following keys: bboxes, bboxes_ignore,
49 labels, masks, seg_map.
50 "masks" are already decoded into binary masks.
51 """
52 gt_bboxes = []
53 gt_labels = []
54 gt_bboxes_ignore = []
55 gt_masks_ann = []
56
57 for i, ann in enumerate(ann_info):
58 if ann.get('ignore', False):
59 continue
60 x1, y1, w, h = ann['bbox']
61 if ann['area'] <= 0 or w < 1 or h < 1:
62 continue
63 if ann['category_id'] not in self.cat_ids:
64 continue
65 bbox = [x1, y1, x1 + w, y1 + h]
66 if ann.get('iscrowd', False):
67 gt_bboxes_ignore.append(bbox)
68 else:
69 gt_bboxes.append(bbox)
70 gt_labels.append(self.cat2label[ann['category_id']])
71 gt_masks_ann.append(ann['segmentation'])
72
73 if gt_bboxes:
74 gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
75 gt_labels = np.array(gt_labels, dtype=np.int64)
76 else:
77 gt_bboxes = np.zeros((0, 4), dtype=np.float32)
78 gt_labels = np.array([], dtype=np.int64)
79
80 if gt_bboxes_ignore:
81 gt_bboxes_ignore = np.array(gt_bboxes_ignore, dtype=np.float32)
82 else:
83 gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)
84
85 ann = dict(
86 bboxes=gt_bboxes,
87 labels=gt_labels,
88 bboxes_ignore=gt_bboxes_ignore,
89 masks=gt_masks_ann,
90 seg_map=img_info['segm_file'])
91
92 return ann
93
94 def results2txt(self, results, outfile_prefix):
95 """Dump the detection results to a txt file.
96
97 Args:
98 results (list[list | tuple | ndarray]): Testing results of the
99 dataset.
100 outfile_prefix (str): The filename prefix of the json files.
101 If the prefix is "somepath/xxx",
102 the txt files will be named "somepath/xxx.txt".
103
104 Returns:
105 list[str: str]: result txt files which contains corresponding
106 instance segmentation images.
107 """
108 try:
109 import cityscapesscripts.helpers.labels as CSLabels
110 except ImportError:
111 raise ImportError('Please run "pip install citscapesscripts" to '
112 'install cityscapesscripts first.')
113 result_files = []
114 os.makedirs(outfile_prefix, exist_ok=True)
115 prog_bar = mmcv.ProgressBar(len(self))
116 for idx in range(len(self)):
117 result = results[idx]
118 filename = self.data_infos[idx]['filename']
119 basename = osp.splitext(osp.basename(filename))[0]
120 pred_txt = osp.join(outfile_prefix, basename + '_pred.txt')
121
122 bbox_result, segm_result = result
123 bboxes = np.vstack(bbox_result)
124 segms = mmcv.concat_list(segm_result)
125 labels = [
126 np.full(bbox.shape[0], i, dtype=np.int32)
127 for i, bbox in enumerate(bbox_result)
128 ]
129 labels = np.concatenate(labels)
130
131 assert len(bboxes) == len(segms) == len(labels)
132 num_instances = len(bboxes)
133 prog_bar.update()
134 with open(pred_txt, 'w') as fout:
135 for i in range(num_instances):
136 pred_class = labels[i]
137 classes = self.CLASSES[pred_class]
138 class_id = CSLabels.name2label[classes].id
139 score = bboxes[i, -1]
140 mask = maskUtils.decode(segms[i]).astype(np.uint8)
141 png_filename = osp.join(outfile_prefix,
142 basename + f'_{i}_{classes}.png')
143 mmcv.imwrite(mask, png_filename)
144 fout.write(f'{osp.basename(png_filename)} {class_id} '
145 f'{score}\n')
146 result_files.append(pred_txt)
147
148 return result_files
149
150 def format_results(self, results, txtfile_prefix=None):
151 """Format the results to txt (standard format for Cityscapes evaluation).
152
153 Args:
154 results (list): Testing results of the dataset.
155 txtfile_prefix (str | None): The prefix of txt files. It includes
156 the file path and the prefix of filename, e.g., "a/b/prefix".
157 If not specified, a temp file will be created. Default: None.
158
159 Returns:
160 tuple: (result_files, tmp_dir), result_files is a dict containing
161 the json filepaths, tmp_dir is the temporal directory created
162 for saving txt/png files when txtfile_prefix is not specified.
163 """
164 assert isinstance(results, list), 'results must be a list'
165 assert len(results) == len(self), (
166 'The length of results is not equal to the dataset len: {} != {}'.
167 format(len(results), len(self)))
168
169 assert isinstance(results, list), 'results must be a list'
170 assert len(results) == len(self), (
171 'The length of results is not equal to the dataset len: {} != {}'.
172 format(len(results), len(self)))
173
174 if txtfile_prefix is None:
175 tmp_dir = tempfile.TemporaryDirectory()
176 txtfile_prefix = osp.join(tmp_dir.name, 'results')
177 else:
178 tmp_dir = None
179 result_files = self.results2txt(results, txtfile_prefix)
180
181 return result_files, tmp_dir
182
183 def evaluate(self,
184 results,
185 metric='bbox',
186 logger=None,
187 outfile_prefix=None,
188 classwise=False,
189 proposal_nums=(100, 300, 1000),
190 iou_thrs=np.arange(0.5, 0.96, 0.05)):
191 """Evaluation in Cityscapes protocol.
192
193 Args:
194 results (list): Testing results of the dataset.
195 metric (str | list[str]): Metrics to be evaluated.
196 logger (logging.Logger | str | None): Logger used for printing
197 related information during evaluation. Default: None.
198 outfile_prefix (str | None):
199 classwise (bool): Whether to evaluating the AP for each class.
200 proposal_nums (Sequence[int]): Proposal number used for evaluating
201 recalls, such as recall@100, recall@1000.
202 Default: (100, 300, 1000).
203 iou_thrs (Sequence[float]): IoU threshold used for evaluating
204 recalls. If set to a list, the average recall of all IoUs will
205 also be computed. Default: 0.5.
206
207 Returns:
208 dict[str: float]
209 """
210 eval_results = dict()
211
212 metrics = metric.copy() if isinstance(metric, list) else [metric]
213
214 if 'cityscapes' in metrics:
215 eval_results.update(
216 self._evaluate_cityscapes(results, outfile_prefix, logger))
217 metrics.remove('cityscapes')
218
219 # left metrics are all coco metric
220 if len(metrics) > 0:
221 # create CocoDataset with CityscapesDataset annotation
222 self_coco = CocoDataset(self.ann_file, self.pipeline.transforms,
223 None, self.data_root, self.img_prefix,
224 self.seg_prefix, self.proposal_file,
225 self.test_mode, self.filter_empty_gt)
226 # TODO: remove this in the future
227 # reload annotations of correct class
228 self_coco.CLASSES = self.CLASSES
229 self_coco.data_infos = self_coco.load_annotations(self.ann_file)
230 eval_results.update(
231 self_coco.evaluate(results, metrics, logger, outfile_prefix,
232 classwise, proposal_nums, iou_thrs))
233
234 return eval_results
235
236 def _evaluate_cityscapes(self, results, txtfile_prefix, logger):
237 try:
238 import cityscapesscripts.evaluation.evalInstanceLevelSemanticLabeling as CSEval # noqa
239 except ImportError:
240 raise ImportError('Please run "pip install citscapesscripts" to '
241 'install cityscapesscripts first.')
242 msg = 'Evaluating in Cityscapes style'
243 if logger is None:
244 msg = '\n' + msg
245 print_log(msg, logger=logger)
246
247 result_files, tmp_dir = self.format_results(results, txtfile_prefix)
248
249 if tmp_dir is None:
250 result_dir = osp.join(txtfile_prefix, 'results')
251 else:
252 result_dir = osp.join(tmp_dir.name, 'results')
253
254 eval_results = {}
255 print_log(f'Evaluating results under {result_dir} ...', logger=logger)
256
257 # set global states in cityscapes evaluation API
258 CSEval.args.cityscapesPath = os.path.join(self.img_prefix, '../..')
259 CSEval.args.predictionPath = os.path.abspath(result_dir)
260 CSEval.args.predictionWalk = None
261 CSEval.args.JSONOutput = False
262 CSEval.args.colorized = False
263 CSEval.args.gtInstancesFile = os.path.join(result_dir,
264 'gtInstances.json')
265 CSEval.args.groundTruthSearch = os.path.join(
266 self.img_prefix.replace('leftImg8bit', 'gtFine'),
267 '*/*_gtFine_instanceIds.png')
268
269 groundTruthImgList = glob.glob(CSEval.args.groundTruthSearch)
270 assert len(groundTruthImgList), 'Cannot find ground truth images' \
271 f' in {CSEval.args.groundTruthSearch}.'
272 predictionImgList = []
273 for gt in groundTruthImgList:
274 predictionImgList.append(CSEval.getPrediction(gt, CSEval.args))
275 CSEval_results = CSEval.evaluateImgLists(predictionImgList,
276 groundTruthImgList,
277 CSEval.args)['averages']
278
279 eval_results['mAP'] = CSEval_results['allAp']
280 eval_results['AP@50'] = CSEval_results['allAp50%']
281 if tmp_dir is not None:
282 tmp_dir.cleanup()
283 return eval_results
284
[end of mmdet/datasets/cityscapes.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/mmdet/datasets/cityscapes.py b/mmdet/datasets/cityscapes.py
--- a/mmdet/datasets/cityscapes.py
+++ b/mmdet/datasets/cityscapes.py
@@ -121,7 +121,17 @@
bbox_result, segm_result = result
bboxes = np.vstack(bbox_result)
- segms = mmcv.concat_list(segm_result)
+ # segm results
+ if isinstance(segm_result, tuple):
+ # Some detectors use different scores for bbox and mask,
+ # like Mask Scoring R-CNN. Score of segm will be used instead
+ # of bbox score.
+ segms = mmcv.concat_list(segm_result[0])
+ mask_score = segm_result[1]
+ else:
+ # use bbox score for mask score
+ segms = mmcv.concat_list(segm_result)
+ mask_score = [bbox[-1] for bbox in bboxes]
labels = [
np.full(bbox.shape[0], i, dtype=np.int32)
for i, bbox in enumerate(bbox_result)
@@ -136,7 +146,7 @@
pred_class = labels[i]
classes = self.CLASSES[pred_class]
class_id = CSLabels.name2label[classes].id
- score = bboxes[i, -1]
+ score = mask_score[i]
mask = maskUtils.decode(segms[i]).astype(np.uint8)
png_filename = osp.join(outfile_prefix,
basename + f'_{i}_{classes}.png')
| {"golden_diff": "diff --git a/mmdet/datasets/cityscapes.py b/mmdet/datasets/cityscapes.py\n--- a/mmdet/datasets/cityscapes.py\n+++ b/mmdet/datasets/cityscapes.py\n@@ -121,7 +121,17 @@\n \n bbox_result, segm_result = result\n bboxes = np.vstack(bbox_result)\n- segms = mmcv.concat_list(segm_result)\n+ # segm results\n+ if isinstance(segm_result, tuple):\n+ # Some detectors use different scores for bbox and mask,\n+ # like Mask Scoring R-CNN. Score of segm will be used instead\n+ # of bbox score.\n+ segms = mmcv.concat_list(segm_result[0])\n+ mask_score = segm_result[1]\n+ else:\n+ # use bbox score for mask score\n+ segms = mmcv.concat_list(segm_result)\n+ mask_score = [bbox[-1] for bbox in bboxes]\n labels = [\n np.full(bbox.shape[0], i, dtype=np.int32)\n for i, bbox in enumerate(bbox_result)\n@@ -136,7 +146,7 @@\n pred_class = labels[i]\n classes = self.CLASSES[pred_class]\n class_id = CSLabels.name2label[classes].id\n- score = bboxes[i, -1]\n+ score = mask_score[i]\n mask = maskUtils.decode(segms[i]).astype(np.uint8)\n png_filename = osp.join(outfile_prefix,\n basename + f'_{i}_{classes}.png')\n", "issue": "mabe a bug in version 2.1.0\nI upgrade mmdetection from 2.0.0 to 2.1.0, but I can't train with this error:ValueError: need at least one array to concatenate.\r\nSo I use version 2.0.0 and all work well, so I think maybe there is a bug in version 2.1.0\n", "before_files": [{"content": "# Modified from https://github.com/facebookresearch/detectron2/blob/master/detectron2/data/datasets/cityscapes.py # noqa\n# and https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/evaluation/evalInstanceLevelSemanticLabeling.py # noqa\n\nimport glob\nimport os\nimport os.path as osp\nimport tempfile\n\nimport mmcv\nimport numpy as np\nimport pycocotools.mask as maskUtils\nfrom mmcv.utils import print_log\n\nfrom .builder import DATASETS\nfrom .coco import CocoDataset\n\n\[email protected]_module()\nclass CityscapesDataset(CocoDataset):\n\n CLASSES = ('person', 'rider', 'car', 'truck', 'bus', 'train', 'motorcycle',\n 'bicycle')\n\n def _filter_imgs(self, min_size=32):\n \"\"\"Filter images too small or without ground truths.\"\"\"\n valid_inds = []\n ids_with_ann = set(_['image_id'] for _ in self.coco.anns.values())\n for i, img_info in enumerate(self.data_infos):\n img_id = img_info['id']\n ann_ids = self.coco.getAnnIds(imgIds=[img_id])\n ann_info = self.coco.loadAnns(ann_ids)\n all_iscrowd = all([_['iscrowd'] for _ in ann_info])\n if self.filter_empty_gt and (self.img_ids[i] not in ids_with_ann\n or all_iscrowd):\n continue\n if min(img_info['width'], img_info['height']) >= min_size:\n valid_inds.append(i)\n return valid_inds\n\n def _parse_ann_info(self, img_info, ann_info):\n \"\"\"Parse bbox and mask annotation.\n\n Args:\n img_info (dict): Image info of an image.\n ann_info (list[dict]): Annotation info of an image.\n\n Returns:\n dict: A dict containing the following keys: bboxes, bboxes_ignore,\n labels, masks, seg_map.\n \"masks\" are already decoded into binary masks.\n \"\"\"\n gt_bboxes = []\n gt_labels = []\n gt_bboxes_ignore = []\n gt_masks_ann = []\n\n for i, ann in enumerate(ann_info):\n if ann.get('ignore', False):\n continue\n x1, y1, w, h = ann['bbox']\n if ann['area'] <= 0 or w < 1 or h < 1:\n continue\n if ann['category_id'] not in self.cat_ids:\n continue\n bbox = [x1, y1, x1 + w, y1 + h]\n if ann.get('iscrowd', False):\n gt_bboxes_ignore.append(bbox)\n else:\n gt_bboxes.append(bbox)\n gt_labels.append(self.cat2label[ann['category_id']])\n gt_masks_ann.append(ann['segmentation'])\n\n if gt_bboxes:\n gt_bboxes = np.array(gt_bboxes, dtype=np.float32)\n gt_labels = np.array(gt_labels, dtype=np.int64)\n else:\n gt_bboxes = np.zeros((0, 4), dtype=np.float32)\n gt_labels = np.array([], dtype=np.int64)\n\n if gt_bboxes_ignore:\n gt_bboxes_ignore = np.array(gt_bboxes_ignore, dtype=np.float32)\n else:\n gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)\n\n ann = dict(\n bboxes=gt_bboxes,\n labels=gt_labels,\n bboxes_ignore=gt_bboxes_ignore,\n masks=gt_masks_ann,\n seg_map=img_info['segm_file'])\n\n return ann\n\n def results2txt(self, results, outfile_prefix):\n \"\"\"Dump the detection results to a txt file.\n\n Args:\n results (list[list | tuple | ndarray]): Testing results of the\n dataset.\n outfile_prefix (str): The filename prefix of the json files.\n If the prefix is \"somepath/xxx\",\n the txt files will be named \"somepath/xxx.txt\".\n\n Returns:\n list[str: str]: result txt files which contains corresponding\n instance segmentation images.\n \"\"\"\n try:\n import cityscapesscripts.helpers.labels as CSLabels\n except ImportError:\n raise ImportError('Please run \"pip install citscapesscripts\" to '\n 'install cityscapesscripts first.')\n result_files = []\n os.makedirs(outfile_prefix, exist_ok=True)\n prog_bar = mmcv.ProgressBar(len(self))\n for idx in range(len(self)):\n result = results[idx]\n filename = self.data_infos[idx]['filename']\n basename = osp.splitext(osp.basename(filename))[0]\n pred_txt = osp.join(outfile_prefix, basename + '_pred.txt')\n\n bbox_result, segm_result = result\n bboxes = np.vstack(bbox_result)\n segms = mmcv.concat_list(segm_result)\n labels = [\n np.full(bbox.shape[0], i, dtype=np.int32)\n for i, bbox in enumerate(bbox_result)\n ]\n labels = np.concatenate(labels)\n\n assert len(bboxes) == len(segms) == len(labels)\n num_instances = len(bboxes)\n prog_bar.update()\n with open(pred_txt, 'w') as fout:\n for i in range(num_instances):\n pred_class = labels[i]\n classes = self.CLASSES[pred_class]\n class_id = CSLabels.name2label[classes].id\n score = bboxes[i, -1]\n mask = maskUtils.decode(segms[i]).astype(np.uint8)\n png_filename = osp.join(outfile_prefix,\n basename + f'_{i}_{classes}.png')\n mmcv.imwrite(mask, png_filename)\n fout.write(f'{osp.basename(png_filename)} {class_id} '\n f'{score}\\n')\n result_files.append(pred_txt)\n\n return result_files\n\n def format_results(self, results, txtfile_prefix=None):\n \"\"\"Format the results to txt (standard format for Cityscapes evaluation).\n\n Args:\n results (list): Testing results of the dataset.\n txtfile_prefix (str | None): The prefix of txt files. It includes\n the file path and the prefix of filename, e.g., \"a/b/prefix\".\n If not specified, a temp file will be created. Default: None.\n\n Returns:\n tuple: (result_files, tmp_dir), result_files is a dict containing\n the json filepaths, tmp_dir is the temporal directory created\n for saving txt/png files when txtfile_prefix is not specified.\n \"\"\"\n assert isinstance(results, list), 'results must be a list'\n assert len(results) == len(self), (\n 'The length of results is not equal to the dataset len: {} != {}'.\n format(len(results), len(self)))\n\n assert isinstance(results, list), 'results must be a list'\n assert len(results) == len(self), (\n 'The length of results is not equal to the dataset len: {} != {}'.\n format(len(results), len(self)))\n\n if txtfile_prefix is None:\n tmp_dir = tempfile.TemporaryDirectory()\n txtfile_prefix = osp.join(tmp_dir.name, 'results')\n else:\n tmp_dir = None\n result_files = self.results2txt(results, txtfile_prefix)\n\n return result_files, tmp_dir\n\n def evaluate(self,\n results,\n metric='bbox',\n logger=None,\n outfile_prefix=None,\n classwise=False,\n proposal_nums=(100, 300, 1000),\n iou_thrs=np.arange(0.5, 0.96, 0.05)):\n \"\"\"Evaluation in Cityscapes protocol.\n\n Args:\n results (list): Testing results of the dataset.\n metric (str | list[str]): Metrics to be evaluated.\n logger (logging.Logger | str | None): Logger used for printing\n related information during evaluation. Default: None.\n outfile_prefix (str | None):\n classwise (bool): Whether to evaluating the AP for each class.\n proposal_nums (Sequence[int]): Proposal number used for evaluating\n recalls, such as recall@100, recall@1000.\n Default: (100, 300, 1000).\n iou_thrs (Sequence[float]): IoU threshold used for evaluating\n recalls. If set to a list, the average recall of all IoUs will\n also be computed. Default: 0.5.\n\n Returns:\n dict[str: float]\n \"\"\"\n eval_results = dict()\n\n metrics = metric.copy() if isinstance(metric, list) else [metric]\n\n if 'cityscapes' in metrics:\n eval_results.update(\n self._evaluate_cityscapes(results, outfile_prefix, logger))\n metrics.remove('cityscapes')\n\n # left metrics are all coco metric\n if len(metrics) > 0:\n # create CocoDataset with CityscapesDataset annotation\n self_coco = CocoDataset(self.ann_file, self.pipeline.transforms,\n None, self.data_root, self.img_prefix,\n self.seg_prefix, self.proposal_file,\n self.test_mode, self.filter_empty_gt)\n # TODO: remove this in the future\n # reload annotations of correct class\n self_coco.CLASSES = self.CLASSES\n self_coco.data_infos = self_coco.load_annotations(self.ann_file)\n eval_results.update(\n self_coco.evaluate(results, metrics, logger, outfile_prefix,\n classwise, proposal_nums, iou_thrs))\n\n return eval_results\n\n def _evaluate_cityscapes(self, results, txtfile_prefix, logger):\n try:\n import cityscapesscripts.evaluation.evalInstanceLevelSemanticLabeling as CSEval # noqa\n except ImportError:\n raise ImportError('Please run \"pip install citscapesscripts\" to '\n 'install cityscapesscripts first.')\n msg = 'Evaluating in Cityscapes style'\n if logger is None:\n msg = '\\n' + msg\n print_log(msg, logger=logger)\n\n result_files, tmp_dir = self.format_results(results, txtfile_prefix)\n\n if tmp_dir is None:\n result_dir = osp.join(txtfile_prefix, 'results')\n else:\n result_dir = osp.join(tmp_dir.name, 'results')\n\n eval_results = {}\n print_log(f'Evaluating results under {result_dir} ...', logger=logger)\n\n # set global states in cityscapes evaluation API\n CSEval.args.cityscapesPath = os.path.join(self.img_prefix, '../..')\n CSEval.args.predictionPath = os.path.abspath(result_dir)\n CSEval.args.predictionWalk = None\n CSEval.args.JSONOutput = False\n CSEval.args.colorized = False\n CSEval.args.gtInstancesFile = os.path.join(result_dir,\n 'gtInstances.json')\n CSEval.args.groundTruthSearch = os.path.join(\n self.img_prefix.replace('leftImg8bit', 'gtFine'),\n '*/*_gtFine_instanceIds.png')\n\n groundTruthImgList = glob.glob(CSEval.args.groundTruthSearch)\n assert len(groundTruthImgList), 'Cannot find ground truth images' \\\n f' in {CSEval.args.groundTruthSearch}.'\n predictionImgList = []\n for gt in groundTruthImgList:\n predictionImgList.append(CSEval.getPrediction(gt, CSEval.args))\n CSEval_results = CSEval.evaluateImgLists(predictionImgList,\n groundTruthImgList,\n CSEval.args)['averages']\n\n eval_results['mAP'] = CSEval_results['allAp']\n eval_results['AP@50'] = CSEval_results['allAp50%']\n if tmp_dir is not None:\n tmp_dir.cleanup()\n return eval_results\n", "path": "mmdet/datasets/cityscapes.py"}]} | 3,956 | 356 |
gh_patches_debug_9536 | rasdani/github-patches | git_diff | ibis-project__ibis-1949 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
More informative IntegrityError on duplicate columns
```
~/Workspace/ibis/ibis/expr/schema.py in __init__(self, names, types)
32
33 if len(self._name_locs) < len(self.names):
---> 34 raise com.IntegrityError('Duplicate column names')
35
36 def __repr__(self):
IntegrityError: Duplicate column names
```
List the particular columns at least.
</issue>
<code>
[start of ibis/expr/schema.py]
1 import collections
2
3 from multipledispatch import Dispatcher
4
5 import ibis.common.exceptions as com
6 import ibis.expr.datatypes as dt
7 import ibis.util as util
8
9
10 class Schema:
11
12 """An object for holding table schema information, i.e., column names and
13 types.
14
15 Parameters
16 ----------
17 names : Sequence[str]
18 A sequence of ``str`` indicating the name of each column.
19 types : Sequence[DataType]
20 A sequence of :class:`ibis.expr.datatypes.DataType` objects
21 representing type of each column.
22 """
23
24 __slots__ = 'names', 'types', '_name_locs'
25
26 def __init__(self, names, types):
27 if not isinstance(names, list):
28 names = list(names)
29
30 self.names = names
31 self.types = list(map(dt.dtype, types))
32
33 self._name_locs = dict((v, i) for i, v in enumerate(self.names))
34
35 if len(self._name_locs) < len(self.names):
36 raise com.IntegrityError('Duplicate column names')
37
38 def __repr__(self):
39 space = 2 + max(map(len, self.names), default=0)
40 return "ibis.Schema {{{}\n}}".format(
41 util.indent(
42 ''.join(
43 '\n{}{}'.format(name.ljust(space), str(type))
44 for name, type in zip(self.names, self.types)
45 ),
46 2,
47 )
48 )
49
50 def __hash__(self):
51 return hash((type(self), tuple(self.names), tuple(self.types)))
52
53 def __len__(self):
54 return len(self.names)
55
56 def __iter__(self):
57 return iter(self.names)
58
59 def __contains__(self, name):
60 return name in self._name_locs
61
62 def __getitem__(self, name):
63 return self.types[self._name_locs[name]]
64
65 def __getstate__(self):
66 return {slot: getattr(self, slot) for slot in self.__class__.__slots__}
67
68 def __setstate__(self, instance_dict):
69 for key, value in instance_dict.items():
70 setattr(self, key, value)
71
72 def delete(self, names_to_delete):
73 for name in names_to_delete:
74 if name not in self:
75 raise KeyError(name)
76
77 new_names, new_types = [], []
78 for name, type_ in zip(self.names, self.types):
79 if name in names_to_delete:
80 continue
81 new_names.append(name)
82 new_types.append(type_)
83
84 return Schema(new_names, new_types)
85
86 @classmethod
87 def from_tuples(cls, values):
88 if not isinstance(values, (list, tuple)):
89 values = list(values)
90
91 names, types = zip(*values) if values else ([], [])
92 return Schema(names, types)
93
94 @classmethod
95 def from_dict(cls, dictionary):
96 return Schema(*zip(*dictionary.items()))
97
98 def equals(self, other, cache=None):
99 return self.names == other.names and self.types == other.types
100
101 def __eq__(self, other):
102 return self.equals(other)
103
104 def __gt__(self, other):
105 return set(self.items()) > set(other.items())
106
107 def __ge__(self, other):
108 return set(self.items()) >= set(other.items())
109
110 def append(self, schema):
111 return Schema(self.names + schema.names, self.types + schema.types)
112
113 def items(self):
114 return zip(self.names, self.types)
115
116 def name_at_position(self, i):
117 """
118 """
119 upper = len(self.names) - 1
120 if not 0 <= i <= upper:
121 raise ValueError(
122 'Column index must be between 0 and {:d}, inclusive'.format(
123 upper
124 )
125 )
126 return self.names[i]
127
128
129 class HasSchema:
130
131 """
132 Base class representing a structured dataset with a well-defined
133 schema.
134
135 Base implementation is for tables that do not reference a particular
136 concrete dataset or database table.
137 """
138
139 def __repr__(self):
140 return '{}({})'.format(type(self).__name__, repr(self.schema))
141
142 def has_schema(self):
143 return True
144
145 def equals(self, other, cache=None):
146 return type(self) == type(other) and self.schema.equals(
147 other.schema, cache=cache
148 )
149
150 def root_tables(self):
151 return [self]
152
153 @property
154 def schema(self):
155 raise NotImplementedError
156
157
158 schema = Dispatcher('schema')
159 infer = Dispatcher('infer')
160
161
162 @schema.register(Schema)
163 def identity(s):
164 return s
165
166
167 @schema.register(collections.abc.Mapping)
168 def schema_from_mapping(d):
169 return Schema.from_dict(d)
170
171
172 @schema.register(collections.abc.Iterable)
173 def schema_from_pairs(lst):
174 return Schema.from_tuples(lst)
175
176
177 @schema.register(collections.abc.Iterable, collections.abc.Iterable)
178 def schema_from_names_types(names, types):
179 return Schema(names, types)
180
[end of ibis/expr/schema.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/ibis/expr/schema.py b/ibis/expr/schema.py
--- a/ibis/expr/schema.py
+++ b/ibis/expr/schema.py
@@ -33,7 +33,11 @@
self._name_locs = dict((v, i) for i, v in enumerate(self.names))
if len(self._name_locs) < len(self.names):
- raise com.IntegrityError('Duplicate column names')
+ duplicate_names = list(self.names)
+ for v in self._name_locs.keys():
+ duplicate_names.remove(v)
+ raise com.IntegrityError(
+ 'Duplicate column name(s): {}'.format(duplicate_names))
def __repr__(self):
space = 2 + max(map(len, self.names), default=0)
| {"golden_diff": "diff --git a/ibis/expr/schema.py b/ibis/expr/schema.py\n--- a/ibis/expr/schema.py\n+++ b/ibis/expr/schema.py\n@@ -33,7 +33,11 @@\n self._name_locs = dict((v, i) for i, v in enumerate(self.names))\n \n if len(self._name_locs) < len(self.names):\n- raise com.IntegrityError('Duplicate column names')\n+ duplicate_names = list(self.names)\n+ for v in self._name_locs.keys():\n+ duplicate_names.remove(v)\n+ raise com.IntegrityError(\n+ 'Duplicate column name(s): {}'.format(duplicate_names))\n \n def __repr__(self):\n space = 2 + max(map(len, self.names), default=0)\n", "issue": "More informative IntegrityError on duplicate columns\n```\r\n~/Workspace/ibis/ibis/expr/schema.py in __init__(self, names, types)\r\n 32 \r\n 33 if len(self._name_locs) < len(self.names):\r\n---> 34 raise com.IntegrityError('Duplicate column names')\r\n 35 \r\n 36 def __repr__(self):\r\n\r\nIntegrityError: Duplicate column names\r\n```\r\n\r\nList the particular columns at least.\n", "before_files": [{"content": "import collections\n\nfrom multipledispatch import Dispatcher\n\nimport ibis.common.exceptions as com\nimport ibis.expr.datatypes as dt\nimport ibis.util as util\n\n\nclass Schema:\n\n \"\"\"An object for holding table schema information, i.e., column names and\n types.\n\n Parameters\n ----------\n names : Sequence[str]\n A sequence of ``str`` indicating the name of each column.\n types : Sequence[DataType]\n A sequence of :class:`ibis.expr.datatypes.DataType` objects\n representing type of each column.\n \"\"\"\n\n __slots__ = 'names', 'types', '_name_locs'\n\n def __init__(self, names, types):\n if not isinstance(names, list):\n names = list(names)\n\n self.names = names\n self.types = list(map(dt.dtype, types))\n\n self._name_locs = dict((v, i) for i, v in enumerate(self.names))\n\n if len(self._name_locs) < len(self.names):\n raise com.IntegrityError('Duplicate column names')\n\n def __repr__(self):\n space = 2 + max(map(len, self.names), default=0)\n return \"ibis.Schema {{{}\\n}}\".format(\n util.indent(\n ''.join(\n '\\n{}{}'.format(name.ljust(space), str(type))\n for name, type in zip(self.names, self.types)\n ),\n 2,\n )\n )\n\n def __hash__(self):\n return hash((type(self), tuple(self.names), tuple(self.types)))\n\n def __len__(self):\n return len(self.names)\n\n def __iter__(self):\n return iter(self.names)\n\n def __contains__(self, name):\n return name in self._name_locs\n\n def __getitem__(self, name):\n return self.types[self._name_locs[name]]\n\n def __getstate__(self):\n return {slot: getattr(self, slot) for slot in self.__class__.__slots__}\n\n def __setstate__(self, instance_dict):\n for key, value in instance_dict.items():\n setattr(self, key, value)\n\n def delete(self, names_to_delete):\n for name in names_to_delete:\n if name not in self:\n raise KeyError(name)\n\n new_names, new_types = [], []\n for name, type_ in zip(self.names, self.types):\n if name in names_to_delete:\n continue\n new_names.append(name)\n new_types.append(type_)\n\n return Schema(new_names, new_types)\n\n @classmethod\n def from_tuples(cls, values):\n if not isinstance(values, (list, tuple)):\n values = list(values)\n\n names, types = zip(*values) if values else ([], [])\n return Schema(names, types)\n\n @classmethod\n def from_dict(cls, dictionary):\n return Schema(*zip(*dictionary.items()))\n\n def equals(self, other, cache=None):\n return self.names == other.names and self.types == other.types\n\n def __eq__(self, other):\n return self.equals(other)\n\n def __gt__(self, other):\n return set(self.items()) > set(other.items())\n\n def __ge__(self, other):\n return set(self.items()) >= set(other.items())\n\n def append(self, schema):\n return Schema(self.names + schema.names, self.types + schema.types)\n\n def items(self):\n return zip(self.names, self.types)\n\n def name_at_position(self, i):\n \"\"\"\n \"\"\"\n upper = len(self.names) - 1\n if not 0 <= i <= upper:\n raise ValueError(\n 'Column index must be between 0 and {:d}, inclusive'.format(\n upper\n )\n )\n return self.names[i]\n\n\nclass HasSchema:\n\n \"\"\"\n Base class representing a structured dataset with a well-defined\n schema.\n\n Base implementation is for tables that do not reference a particular\n concrete dataset or database table.\n \"\"\"\n\n def __repr__(self):\n return '{}({})'.format(type(self).__name__, repr(self.schema))\n\n def has_schema(self):\n return True\n\n def equals(self, other, cache=None):\n return type(self) == type(other) and self.schema.equals(\n other.schema, cache=cache\n )\n\n def root_tables(self):\n return [self]\n\n @property\n def schema(self):\n raise NotImplementedError\n\n\nschema = Dispatcher('schema')\ninfer = Dispatcher('infer')\n\n\[email protected](Schema)\ndef identity(s):\n return s\n\n\[email protected](collections.abc.Mapping)\ndef schema_from_mapping(d):\n return Schema.from_dict(d)\n\n\[email protected](collections.abc.Iterable)\ndef schema_from_pairs(lst):\n return Schema.from_tuples(lst)\n\n\[email protected](collections.abc.Iterable, collections.abc.Iterable)\ndef schema_from_names_types(names, types):\n return Schema(names, types)\n", "path": "ibis/expr/schema.py"}]} | 2,140 | 174 |
gh_patches_debug_2006 | rasdani/github-patches | git_diff | psf__black-1892 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
s390x: test_python2/test_python2_unicode_literals can't assign to () INTERNAL ERROR
During the build of 19.10b0 in Fedora, the following test failure occurs on s390x (Big Endian) architecture:
```
======================================================================
FAIL: test_python2 (tests.test_black.BlackTestCase)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/builddir/build/BUILD/black-19.10b0/black.py", line 3754, in assert_equivalent
src_ast = parse_ast(src)
File "/builddir/build/BUILD/black-19.10b0/black.py", line 3686, in parse_ast
return ast27.parse(src)
File "/usr/lib64/python3.8/site-packages/typed_ast/ast27.py", line 50, in parse
return _ast27.parse(source, filename, mode)
File "<unknown>", line 10
SyntaxError: can't assign to ()
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib64/python3.8/unittest/mock.py", line 1342, in patched
return func(*newargs, **newkeywargs)
File "/builddir/build/BUILD/black-19.10b0/tests/test_black.py", line 543, in test_python2
black.assert_equivalent(source, actual)
File "/builddir/build/BUILD/black-19.10b0/black.py", line 3756, in assert_equivalent
raise AssertionError(
AssertionError: cannot use --safe with this file; failed to parse source file. AST error message: can't assign to () (<unknown>, line 10)
======================================================================
FAIL: test_python2_unicode_literals (tests.test_black.BlackTestCase)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/usr/lib64/python3.8/unittest/mock.py", line 1342, in patched
return func(*newargs, **newkeywargs)
File "/builddir/build/BUILD/black-19.10b0/tests/test_black.py", line 560, in test_python2_unicode_literals
black.assert_equivalent(source, actual)
File "/builddir/build/BUILD/black-19.10b0/black.py", line 3775, in assert_equivalent
raise AssertionError(
AssertionError: INTERNAL ERROR: Black produced code that is not equivalent to the source. Please report a bug on https://github.com/psf/black/issues. This diff might be helpful:
--- src
+++ dst
@@ -1,4 +1,70 @@
Module(
body=
+ ImportFrom(
+ level=
+ 0, # int
+ module=
+ '__future__', # str
+ names=
+ alias(
+ asname=
+ '_unicode_literals', # str
+ name=
+ 'unicode_literals', # str
+ ) # /alias
+ ) # /ImportFrom
+ ImportFrom(
+ level=
+ 0, # int
+ module=
+ '__future__', # str
+ names=
+ alias(
+ asname=
+ None, # NoneType
+ name=
+ 'absolute_import', # str
+ ) # /alias
+ ) # /ImportFrom
+ ImportFrom(
+ level=
+ 0, # int
+ module=
+ '__future__', # str
+ names=
+ alias(
+ asname=
+ 'lol', # str
+ name=
+ 'print_function', # str
+ ) # /alias
+ alias(
+ asname=
+ None, # NoneType
+ name=
+ 'with_function', # str
+ ) # /alias
+ ) # /ImportFrom
+ Expr(
+ value=
+ Constant(
+ value=
+ 'hello', # str
+ ) # /Constant
+ ) # /Expr
+ Expr(
+ value=
+ Constant(
+ value=
+ 'hello', # str
+ ) # /Constant
+ ) # /Expr
+ Expr(
+ value=
+ Constant(
+ value=
+ 'hello', # str
+ ) # /Constant
+ ) # /Expr
type_ignores=
) # /Module
----------------------------------------------------------------------
Ran 119 tests in 18.012s
FAILED (failures=2)
```
**To Reproduce**, run the test suite on s390x.
Here is the build log with all the commands: [build.log](https://github.com/psf/black/files/3782557/build.log)
Here is the root log with all the package versions: [root.log](https://github.com/psf/black/files/3782561/root.log)
**Expected behavior**
Test succeed an all architectures.
**Environment:**
- Version: 19.10b0
- OS and Python version: Linux, Fedora 32 on s390x, Python 3.8.0
**Does this bug also happen on master?** yes, on 6bedb5c58a7d8c25aa9509f8217bc24e9797e90d
**Additional context** The problem does not happen on the same build system with armv7hl or ppc64le.
</issue>
<code>
[start of setup.py]
1 # Copyright (C) 2020 Łukasz Langa
2 from setuptools import setup
3 import sys
4 import os
5
6 assert sys.version_info >= (3, 6, 0), "black requires Python 3.6+"
7 from pathlib import Path # noqa E402
8
9 CURRENT_DIR = Path(__file__).parent
10 sys.path.insert(0, str(CURRENT_DIR)) # for setuptools.build_meta
11
12
13 def get_long_description() -> str:
14 return (
15 (CURRENT_DIR / "README.md").read_text(encoding="utf8")
16 + "\n\n"
17 + (CURRENT_DIR / "CHANGES.md").read_text(encoding="utf8")
18 )
19
20
21 USE_MYPYC = False
22 # To compile with mypyc, a mypyc checkout must be present on the PYTHONPATH
23 if len(sys.argv) > 1 and sys.argv[1] == "--use-mypyc":
24 sys.argv.pop(1)
25 USE_MYPYC = True
26 if os.getenv("BLACK_USE_MYPYC", None) == "1":
27 USE_MYPYC = True
28
29 if USE_MYPYC:
30 mypyc_targets = [
31 "src/black/__init__.py",
32 "src/blib2to3/pytree.py",
33 "src/blib2to3/pygram.py",
34 "src/blib2to3/pgen2/parse.py",
35 "src/blib2to3/pgen2/grammar.py",
36 "src/blib2to3/pgen2/token.py",
37 "src/blib2to3/pgen2/driver.py",
38 "src/blib2to3/pgen2/pgen.py",
39 ]
40
41 from mypyc.build import mypycify
42
43 opt_level = os.getenv("MYPYC_OPT_LEVEL", "3")
44 ext_modules = mypycify(mypyc_targets, opt_level=opt_level)
45 else:
46 ext_modules = []
47
48 setup(
49 name="black",
50 use_scm_version={
51 "write_to": "src/_black_version.py",
52 "write_to_template": 'version = "{version}"\n',
53 },
54 description="The uncompromising code formatter.",
55 long_description=get_long_description(),
56 long_description_content_type="text/markdown",
57 keywords="automation formatter yapf autopep8 pyfmt gofmt rustfmt",
58 author="Łukasz Langa",
59 author_email="[email protected]",
60 url="https://github.com/psf/black",
61 project_urls={"Changelog": "https://github.com/psf/black/blob/master/CHANGES.md"},
62 license="MIT",
63 py_modules=["_black_version"],
64 ext_modules=ext_modules,
65 packages=["blackd", "black", "blib2to3", "blib2to3.pgen2", "black_primer"],
66 package_dir={"": "src"},
67 package_data={"blib2to3": ["*.txt"], "black": ["py.typed"]},
68 python_requires=">=3.6",
69 zip_safe=False,
70 install_requires=[
71 "click>=7.1.2",
72 "appdirs",
73 "toml>=0.10.1",
74 "typed-ast>=1.4.0",
75 "regex>=2020.1.8",
76 "pathspec>=0.6, <1",
77 "dataclasses>=0.6; python_version < '3.7'",
78 "typing_extensions>=3.7.4",
79 "mypy_extensions>=0.4.3",
80 ],
81 extras_require={
82 "d": ["aiohttp>=3.3.2", "aiohttp-cors"],
83 "colorama": ["colorama>=0.4.3"],
84 },
85 test_suite="tests.test_black",
86 classifiers=[
87 "Development Status :: 4 - Beta",
88 "Environment :: Console",
89 "Intended Audience :: Developers",
90 "License :: OSI Approved :: MIT License",
91 "Operating System :: OS Independent",
92 "Programming Language :: Python",
93 "Programming Language :: Python :: 3.6",
94 "Programming Language :: Python :: 3.7",
95 "Programming Language :: Python :: 3.8",
96 "Programming Language :: Python :: 3.9",
97 "Programming Language :: Python :: 3 :: Only",
98 "Topic :: Software Development :: Libraries :: Python Modules",
99 "Topic :: Software Development :: Quality Assurance",
100 ],
101 entry_points={
102 "console_scripts": [
103 "black=black:patched_main",
104 "blackd=blackd:patched_main [d]",
105 "black-primer=black_primer.cli:main",
106 ]
107 },
108 )
109
[end of setup.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -71,7 +71,7 @@
"click>=7.1.2",
"appdirs",
"toml>=0.10.1",
- "typed-ast>=1.4.0",
+ "typed-ast>=1.4.2",
"regex>=2020.1.8",
"pathspec>=0.6, <1",
"dataclasses>=0.6; python_version < '3.7'",
| {"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -71,7 +71,7 @@\n \"click>=7.1.2\",\n \"appdirs\",\n \"toml>=0.10.1\",\n- \"typed-ast>=1.4.0\",\n+ \"typed-ast>=1.4.2\",\n \"regex>=2020.1.8\",\n \"pathspec>=0.6, <1\",\n \"dataclasses>=0.6; python_version < '3.7'\",\n", "issue": "s390x: test_python2/test_python2_unicode_literals can't assign to () INTERNAL ERROR\nDuring the build of 19.10b0 in Fedora, the following test failure occurs on s390x (Big Endian) architecture:\r\n\r\n```\r\n======================================================================\r\nFAIL: test_python2 (tests.test_black.BlackTestCase)\r\n----------------------------------------------------------------------\r\nTraceback (most recent call last):\r\n File \"/builddir/build/BUILD/black-19.10b0/black.py\", line 3754, in assert_equivalent\r\n src_ast = parse_ast(src)\r\n File \"/builddir/build/BUILD/black-19.10b0/black.py\", line 3686, in parse_ast\r\n return ast27.parse(src)\r\n File \"/usr/lib64/python3.8/site-packages/typed_ast/ast27.py\", line 50, in parse\r\n return _ast27.parse(source, filename, mode)\r\n File \"<unknown>\", line 10\r\nSyntaxError: can't assign to ()\r\nDuring handling of the above exception, another exception occurred:\r\nTraceback (most recent call last):\r\n File \"/usr/lib64/python3.8/unittest/mock.py\", line 1342, in patched\r\n return func(*newargs, **newkeywargs)\r\n File \"/builddir/build/BUILD/black-19.10b0/tests/test_black.py\", line 543, in test_python2\r\n black.assert_equivalent(source, actual)\r\n File \"/builddir/build/BUILD/black-19.10b0/black.py\", line 3756, in assert_equivalent\r\n raise AssertionError(\r\nAssertionError: cannot use --safe with this file; failed to parse source file. AST error message: can't assign to () (<unknown>, line 10)\r\n======================================================================\r\nFAIL: test_python2_unicode_literals (tests.test_black.BlackTestCase)\r\n----------------------------------------------------------------------\r\nTraceback (most recent call last):\r\n File \"/usr/lib64/python3.8/unittest/mock.py\", line 1342, in patched\r\n return func(*newargs, **newkeywargs)\r\n File \"/builddir/build/BUILD/black-19.10b0/tests/test_black.py\", line 560, in test_python2_unicode_literals\r\n black.assert_equivalent(source, actual)\r\n File \"/builddir/build/BUILD/black-19.10b0/black.py\", line 3775, in assert_equivalent\r\n raise AssertionError(\r\nAssertionError: INTERNAL ERROR: Black produced code that is not equivalent to the source. Please report a bug on https://github.com/psf/black/issues. This diff might be helpful: \r\n--- src\r\n+++ dst\r\n@@ -1,4 +1,70 @@\r\n Module(\r\n body=\r\n+ ImportFrom(\r\n+ level=\r\n+ 0, # int\r\n+ module=\r\n+ '__future__', # str\r\n+ names=\r\n+ alias(\r\n+ asname=\r\n+ '_unicode_literals', # str\r\n+ name=\r\n+ 'unicode_literals', # str\r\n+ ) # /alias\r\n+ ) # /ImportFrom\r\n+ ImportFrom(\r\n+ level=\r\n+ 0, # int\r\n+ module=\r\n+ '__future__', # str\r\n+ names=\r\n+ alias(\r\n+ asname=\r\n+ None, # NoneType\r\n+ name=\r\n+ 'absolute_import', # str\r\n+ ) # /alias\r\n+ ) # /ImportFrom\r\n+ ImportFrom(\r\n+ level=\r\n+ 0, # int\r\n+ module=\r\n+ '__future__', # str\r\n+ names=\r\n+ alias(\r\n+ asname=\r\n+ 'lol', # str\r\n+ name=\r\n+ 'print_function', # str\r\n+ ) # /alias\r\n+ alias(\r\n+ asname=\r\n+ None, # NoneType\r\n+ name=\r\n+ 'with_function', # str\r\n+ ) # /alias\r\n+ ) # /ImportFrom\r\n+ Expr(\r\n+ value=\r\n+ Constant(\r\n+ value=\r\n+ 'hello', # str\r\n+ ) # /Constant\r\n+ ) # /Expr\r\n+ Expr(\r\n+ value=\r\n+ Constant(\r\n+ value=\r\n+ 'hello', # str\r\n+ ) # /Constant\r\n+ ) # /Expr\r\n+ Expr(\r\n+ value=\r\n+ Constant(\r\n+ value=\r\n+ 'hello', # str\r\n+ ) # /Constant\r\n+ ) # /Expr\r\n type_ignores=\r\n ) # /Module\r\n----------------------------------------------------------------------\r\nRan 119 tests in 18.012s\r\nFAILED (failures=2)\r\n```\r\n\r\n**To Reproduce**, run the test suite on s390x. \r\n\r\nHere is the build log with all the commands: [build.log](https://github.com/psf/black/files/3782557/build.log)\r\n\r\nHere is the root log with all the package versions: [root.log](https://github.com/psf/black/files/3782561/root.log)\r\n\r\n\r\n**Expected behavior**\r\nTest succeed an all architectures.\r\n\r\n**Environment:**\r\n\r\n- Version: 19.10b0\r\n- OS and Python version: Linux, Fedora 32 on s390x, Python 3.8.0\r\n\r\n**Does this bug also happen on master?** yes, on 6bedb5c58a7d8c25aa9509f8217bc24e9797e90d\r\n\r\n**Additional context** The problem does not happen on the same build system with armv7hl or ppc64le.\r\n\n", "before_files": [{"content": "# Copyright (C) 2020 \u0141ukasz Langa\nfrom setuptools import setup\nimport sys\nimport os\n\nassert sys.version_info >= (3, 6, 0), \"black requires Python 3.6+\"\nfrom pathlib import Path # noqa E402\n\nCURRENT_DIR = Path(__file__).parent\nsys.path.insert(0, str(CURRENT_DIR)) # for setuptools.build_meta\n\n\ndef get_long_description() -> str:\n return (\n (CURRENT_DIR / \"README.md\").read_text(encoding=\"utf8\")\n + \"\\n\\n\"\n + (CURRENT_DIR / \"CHANGES.md\").read_text(encoding=\"utf8\")\n )\n\n\nUSE_MYPYC = False\n# To compile with mypyc, a mypyc checkout must be present on the PYTHONPATH\nif len(sys.argv) > 1 and sys.argv[1] == \"--use-mypyc\":\n sys.argv.pop(1)\n USE_MYPYC = True\nif os.getenv(\"BLACK_USE_MYPYC\", None) == \"1\":\n USE_MYPYC = True\n\nif USE_MYPYC:\n mypyc_targets = [\n \"src/black/__init__.py\",\n \"src/blib2to3/pytree.py\",\n \"src/blib2to3/pygram.py\",\n \"src/blib2to3/pgen2/parse.py\",\n \"src/blib2to3/pgen2/grammar.py\",\n \"src/blib2to3/pgen2/token.py\",\n \"src/blib2to3/pgen2/driver.py\",\n \"src/blib2to3/pgen2/pgen.py\",\n ]\n\n from mypyc.build import mypycify\n\n opt_level = os.getenv(\"MYPYC_OPT_LEVEL\", \"3\")\n ext_modules = mypycify(mypyc_targets, opt_level=opt_level)\nelse:\n ext_modules = []\n\nsetup(\n name=\"black\",\n use_scm_version={\n \"write_to\": \"src/_black_version.py\",\n \"write_to_template\": 'version = \"{version}\"\\n',\n },\n description=\"The uncompromising code formatter.\",\n long_description=get_long_description(),\n long_description_content_type=\"text/markdown\",\n keywords=\"automation formatter yapf autopep8 pyfmt gofmt rustfmt\",\n author=\"\u0141ukasz Langa\",\n author_email=\"[email protected]\",\n url=\"https://github.com/psf/black\",\n project_urls={\"Changelog\": \"https://github.com/psf/black/blob/master/CHANGES.md\"},\n license=\"MIT\",\n py_modules=[\"_black_version\"],\n ext_modules=ext_modules,\n packages=[\"blackd\", \"black\", \"blib2to3\", \"blib2to3.pgen2\", \"black_primer\"],\n package_dir={\"\": \"src\"},\n package_data={\"blib2to3\": [\"*.txt\"], \"black\": [\"py.typed\"]},\n python_requires=\">=3.6\",\n zip_safe=False,\n install_requires=[\n \"click>=7.1.2\",\n \"appdirs\",\n \"toml>=0.10.1\",\n \"typed-ast>=1.4.0\",\n \"regex>=2020.1.8\",\n \"pathspec>=0.6, <1\",\n \"dataclasses>=0.6; python_version < '3.7'\",\n \"typing_extensions>=3.7.4\",\n \"mypy_extensions>=0.4.3\",\n ],\n extras_require={\n \"d\": [\"aiohttp>=3.3.2\", \"aiohttp-cors\"],\n \"colorama\": [\"colorama>=0.4.3\"],\n },\n test_suite=\"tests.test_black\",\n classifiers=[\n \"Development Status :: 4 - Beta\",\n \"Environment :: Console\",\n \"Intended Audience :: Developers\",\n \"License :: OSI Approved :: MIT License\",\n \"Operating System :: OS Independent\",\n \"Programming Language :: Python\",\n \"Programming Language :: Python :: 3.6\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n \"Programming Language :: Python :: 3.9\",\n \"Programming Language :: Python :: 3 :: Only\",\n \"Topic :: Software Development :: Libraries :: Python Modules\",\n \"Topic :: Software Development :: Quality Assurance\",\n ],\n entry_points={\n \"console_scripts\": [\n \"black=black:patched_main\",\n \"blackd=blackd:patched_main [d]\",\n \"black-primer=black_primer.cli:main\",\n ]\n },\n)\n", "path": "setup.py"}]} | 3,065 | 127 |
gh_patches_debug_39177 | rasdani/github-patches | git_diff | scikit-hep__pyhf-944 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
API: change CLs to be scalar
# Description
right now it's returning (1,) vectors
</issue>
<code>
[start of src/pyhf/cli/infer.py]
1 """The inference CLI group."""
2 import logging
3
4 import click
5 import json
6
7 from ..utils import EqDelimStringParamType
8 from ..infer import hypotest
9 from ..workspace import Workspace
10 from .. import get_backend, set_backend, optimize
11
12 log = logging.getLogger(__name__)
13
14
15 @click.group(name='infer')
16 def cli():
17 """Infererence CLI group."""
18
19
20 @cli.command()
21 @click.argument('workspace', default='-')
22 @click.option(
23 '--output-file',
24 help='The location of the output json file. If not specified, prints to screen.',
25 default=None,
26 )
27 @click.option('--measurement', default=None)
28 @click.option('-p', '--patch', multiple=True)
29 @click.option('--testpoi', default=1.0)
30 @click.option('--teststat', type=click.Choice(['q', 'qtilde']), default='qtilde')
31 @click.option(
32 '--backend',
33 type=click.Choice(['numpy', 'pytorch', 'tensorflow', 'jax', 'np', 'torch', 'tf']),
34 help='The tensor backend used for the calculation.',
35 default='numpy',
36 )
37 @click.option('--optimizer')
38 @click.option('--optconf', type=EqDelimStringParamType(), multiple=True)
39 def cls(
40 workspace,
41 output_file,
42 measurement,
43 patch,
44 testpoi,
45 teststat,
46 backend,
47 optimizer,
48 optconf,
49 ):
50 """
51 Compute CLs value(s) for a given pyhf workspace.
52
53 Example:
54
55 .. code-block:: shell
56
57 $ curl -sL https://git.io/JJYDE | pyhf cls
58
59 \b
60 {
61 "CLs_exp": [
62 0.07807427911686156,
63 0.17472571775474618,
64 0.35998495263681285,
65 0.6343568235898907,
66 0.8809947004472013
67 ],
68 "CLs_obs": 0.3599845631401915
69 }
70 """
71 with click.open_file(workspace, 'r') as specstream:
72 spec = json.load(specstream)
73
74 ws = Workspace(spec)
75
76 is_qtilde = teststat == 'qtilde'
77
78 patches = [json.loads(click.open_file(pfile, 'r').read()) for pfile in patch]
79 model = ws.model(
80 measurement_name=measurement,
81 patches=patches,
82 modifier_settings={
83 'normsys': {'interpcode': 'code4'},
84 'histosys': {'interpcode': 'code4p'},
85 },
86 )
87
88 # set the backend if not NumPy
89 if backend in ['pytorch', 'torch']:
90 set_backend("pytorch", precision="64b")
91 elif backend in ['tensorflow', 'tf']:
92 set_backend("tensorflow", precision="64b")
93 elif backend in ['jax']:
94 set_backend("jax")
95 tensorlib, _ = get_backend()
96
97 optconf = {k: v for item in optconf for k, v in item.items()}
98
99 # set the new optimizer
100 if optimizer:
101 new_optimizer = getattr(optimize, optimizer) or getattr(
102 optimize, f'{optimizer}_optimizer'
103 )
104 set_backend(tensorlib, new_optimizer(**optconf))
105
106 result = hypotest(
107 testpoi, ws.data(model), model, qtilde=is_qtilde, return_expected_set=True
108 )
109 result = {
110 'CLs_obs': tensorlib.tolist(result[0])[0],
111 'CLs_exp': tensorlib.tolist(tensorlib.reshape(result[-1], [-1])),
112 }
113
114 if output_file is None:
115 click.echo(json.dumps(result, indent=4, sort_keys=True))
116 else:
117 with open(output_file, 'w+') as out_file:
118 json.dump(result, out_file, indent=4, sort_keys=True)
119 log.debug("Written to {0:s}".format(output_file))
120
[end of src/pyhf/cli/infer.py]
[start of src/pyhf/infer/__init__.py]
1 """Inference for Statistical Models."""
2
3 from .test_statistics import qmu
4 from .. import get_backend
5 from .calculators import AsymptoticCalculator
6
7
8 def hypotest(
9 poi_test, data, pdf, init_pars=None, par_bounds=None, qtilde=False, **kwargs
10 ):
11 r"""
12 Compute :math:`p`-values and test statistics for a single value of the parameter of interest.
13
14 Example:
15 >>> import pyhf
16 >>> pyhf.set_backend("numpy")
17 >>> model = pyhf.simplemodels.hepdata_like(
18 ... signal_data=[12.0, 11.0], bkg_data=[50.0, 52.0], bkg_uncerts=[3.0, 7.0]
19 ... )
20 >>> observations = [51, 48]
21 >>> data = pyhf.tensorlib.astensor(observations + model.config.auxdata)
22 >>> test_poi = 1.0
23 >>> CLs_obs, CLs_exp_band = pyhf.infer.hypotest(
24 ... test_poi, data, model, qtilde=True, return_expected_set=True
25 ... )
26 >>> print(CLs_obs)
27 [0.05251554]
28 >>> print(CLs_exp_band)
29 [[0.00260641]
30 [0.01382066]
31 [0.06445521]
32 [0.23526104]
33 [0.57304182]]
34
35 Args:
36 poi_test (Number or Tensor): The value of the parameter of interest (POI)
37 data (Number or Tensor): The root of the calculated test statistic given the Asimov data, :math:`\sqrt{q_{\mu,A}}`
38 pdf (~pyhf.pdf.Model): The HistFactory statistical model
39 init_pars (Array or Tensor): The initial parameter values to be used for minimization
40 par_bounds (Array or Tensor): The parameter value bounds to be used for minimization
41 qtilde (Bool): When ``True`` perform the calculation using the alternative test statistic, :math:`\tilde{q}`, as defined in Equation (62) of :xref:`arXiv:1007.1727`
42
43 Keyword Args:
44 return_tail_probs (bool): Bool for returning :math:`\textrm{CL}_{s+b}` and :math:`\textrm{CL}_{b}`
45 return_expected (bool): Bool for returning :math:`\textrm{CL}_{\textrm{exp}}`
46 return_expected_set (bool): Bool for returning the :math:`(-2,-1,0,1,2)\sigma` :math:`\textrm{CL}_{\textrm{exp}}` --- the "Brazil band"
47
48 Returns:
49 Tuple of Floats and lists of Floats:
50
51 - :math:`\textrm{CL}_{s}`: The :math:`p`-value compared to the given threshold :math:`\alpha`, typically taken to be :math:`0.05`, defined in :xref:`arXiv:1007.1727` as
52
53 .. math::
54
55 \textrm{CL}_{s} = \frac{\textrm{CL}_{s+b}}{\textrm{CL}_{b}} = \frac{p_{s+b}}{1-p_{b}}
56
57 to protect against excluding signal models in which there is little sensitivity. In the case that :math:`\textrm{CL}_{s} \leq \alpha` the given signal model is excluded.
58
59 - :math:`\left[\textrm{CL}_{s+b}, \textrm{CL}_{b}\right]`: The signal + background :math:`p`-value and 1 minus the background only :math:`p`-value as defined in Equations (75) and (76) of :xref:`arXiv:1007.1727`
60
61 .. math::
62
63 \textrm{CL}_{s+b} = p_{s+b} = \int\limits_{q_{\textrm{obs}}}^{\infty} f\left(q\,\middle|s+b\right)\,dq = 1 - \Phi\left(\frac{q_{\textrm{obs}} + 1/\sigma_{s+b}^{2}}{2/\sigma_{s+b}}\right)
64
65 .. math::
66
67 \textrm{CL}_{b} = 1- p_{b} = 1 - \int\limits_{-\infty}^{q_{\textrm{obs}}} f\left(q\,\middle|b\right)\,dq = 1 - \Phi\left(\frac{q_{\textrm{obs}} - 1/\sigma_{b}^{2}}{2/\sigma_{b}}\right)
68
69 with Equations (73) and (74) for the mean
70
71 .. math::
72
73 E\left[q\right] = \frac{1 - 2\mu}{\sigma^{2}}
74
75 and variance
76
77 .. math::
78
79 V\left[q\right] = \frac{4}{\sigma^{2}}
80
81 of the test statistic :math:`q` under the background only and and signal + background hypotheses. Only returned when ``return_tail_probs`` is ``True``.
82
83 - :math:`\textrm{CL}_{s,\textrm{exp}}`: The expected :math:`\textrm{CL}_{s}` value corresponding to the test statistic under the background only hypothesis :math:`\left(\mu=0\right)`. Only returned when ``return_expected`` is ``True``.
84
85 - :math:`\textrm{CL}_{s,\textrm{exp}}` band: The set of expected :math:`\textrm{CL}_{s}` values corresponding to the median significance of variations of the signal strength from the background only hypothesis :math:`\left(\mu=0\right)` at :math:`(-2,-1,0,1,2)\sigma`. That is, the :math:`p`-values that satisfy Equation (89) of :xref:`arXiv:1007.1727`
86
87 .. math::
88
89 \textrm{band}_{N\sigma} = \mu' + \sigma\,\Phi^{-1}\left(1-\alpha\right) \pm N\sigma
90
91 for :math:`\mu'=0` and :math:`N \in \left\{-2, -1, 0, 1, 2\right\}`. These values define the boundaries of an uncertainty band sometimes referred to as the "Brazil band". Only returned when ``return_expected_set`` is ``True``.
92
93 """
94 init_pars = init_pars or pdf.config.suggested_init()
95 par_bounds = par_bounds or pdf.config.suggested_bounds()
96 tensorlib, _ = get_backend()
97
98 calc = AsymptoticCalculator(data, pdf, init_pars, par_bounds, qtilde=qtilde)
99 teststat = calc.teststatistic(poi_test)
100 sig_plus_bkg_distribution, b_only_distribution = calc.distributions(poi_test)
101
102 CLsb = sig_plus_bkg_distribution.pvalue(teststat)
103 CLb = b_only_distribution.pvalue(teststat)
104 CLs = CLsb / CLb
105 CLsb, CLb, CLs = (
106 tensorlib.reshape(CLsb, (1,)),
107 tensorlib.reshape(CLb, (1,)),
108 tensorlib.reshape(CLs, (1,)),
109 )
110
111 _returns = [CLs]
112 if kwargs.get('return_tail_probs'):
113 _returns.append([CLsb, CLb])
114 if kwargs.get('return_expected_set'):
115 CLs_exp = []
116 for n_sigma in [2, 1, 0, -1, -2]:
117
118 expected_bonly_teststat = b_only_distribution.expected_value(n_sigma)
119
120 CLs = sig_plus_bkg_distribution.pvalue(
121 expected_bonly_teststat
122 ) / b_only_distribution.pvalue(expected_bonly_teststat)
123 CLs_exp.append(tensorlib.reshape(CLs, (1,)))
124 CLs_exp = tensorlib.astensor(CLs_exp)
125 if kwargs.get('return_expected'):
126 _returns.append(CLs_exp[2])
127 _returns.append(CLs_exp)
128 elif kwargs.get('return_expected'):
129 n_sigma = 0
130 expected_bonly_teststat = b_only_distribution.expected_value(n_sigma)
131
132 CLs = sig_plus_bkg_distribution.pvalue(
133 expected_bonly_teststat
134 ) / b_only_distribution.pvalue(expected_bonly_teststat)
135 _returns.append(tensorlib.reshape(CLs, (1,)))
136 # Enforce a consistent return type of the observed CLs
137 return tuple(_returns) if len(_returns) > 1 else _returns[0]
138
139
140 __all__ = ['qmu', 'hypotest']
141
[end of src/pyhf/infer/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/pyhf/cli/infer.py b/src/pyhf/cli/infer.py
--- a/src/pyhf/cli/infer.py
+++ b/src/pyhf/cli/infer.py
@@ -107,8 +107,8 @@
testpoi, ws.data(model), model, qtilde=is_qtilde, return_expected_set=True
)
result = {
- 'CLs_obs': tensorlib.tolist(result[0])[0],
- 'CLs_exp': tensorlib.tolist(tensorlib.reshape(result[-1], [-1])),
+ 'CLs_obs': tensorlib.tolist(result[0]),
+ 'CLs_exp': [tensorlib.tolist(tensor) for tensor in result[-1]],
}
if output_file is None:
diff --git a/src/pyhf/infer/__init__.py b/src/pyhf/infer/__init__.py
--- a/src/pyhf/infer/__init__.py
+++ b/src/pyhf/infer/__init__.py
@@ -23,14 +23,10 @@
>>> CLs_obs, CLs_exp_band = pyhf.infer.hypotest(
... test_poi, data, model, qtilde=True, return_expected_set=True
... )
- >>> print(CLs_obs)
- [0.05251554]
- >>> print(CLs_exp_band)
- [[0.00260641]
- [0.01382066]
- [0.06445521]
- [0.23526104]
- [0.57304182]]
+ >>> CLs_obs
+ array(0.05251554)
+ >>> CLs_exp_band
+ [array(0.00260641), array(0.01382066), array(0.06445521), array(0.23526104), array(0.57304182)]
Args:
poi_test (Number or Tensor): The value of the parameter of interest (POI)
@@ -102,10 +98,11 @@
CLsb = sig_plus_bkg_distribution.pvalue(teststat)
CLb = b_only_distribution.pvalue(teststat)
CLs = CLsb / CLb
+ # Ensure that all CL values are 0-d tensors
CLsb, CLb, CLs = (
- tensorlib.reshape(CLsb, (1,)),
- tensorlib.reshape(CLb, (1,)),
- tensorlib.reshape(CLs, (1,)),
+ tensorlib.astensor(CLsb),
+ tensorlib.astensor(CLb),
+ tensorlib.astensor(CLs),
)
_returns = [CLs]
@@ -120,8 +117,7 @@
CLs = sig_plus_bkg_distribution.pvalue(
expected_bonly_teststat
) / b_only_distribution.pvalue(expected_bonly_teststat)
- CLs_exp.append(tensorlib.reshape(CLs, (1,)))
- CLs_exp = tensorlib.astensor(CLs_exp)
+ CLs_exp.append(tensorlib.astensor(CLs))
if kwargs.get('return_expected'):
_returns.append(CLs_exp[2])
_returns.append(CLs_exp)
@@ -132,7 +128,7 @@
CLs = sig_plus_bkg_distribution.pvalue(
expected_bonly_teststat
) / b_only_distribution.pvalue(expected_bonly_teststat)
- _returns.append(tensorlib.reshape(CLs, (1,)))
+ _returns.append(tensorlib.astensor(CLs))
# Enforce a consistent return type of the observed CLs
return tuple(_returns) if len(_returns) > 1 else _returns[0]
| {"golden_diff": "diff --git a/src/pyhf/cli/infer.py b/src/pyhf/cli/infer.py\n--- a/src/pyhf/cli/infer.py\n+++ b/src/pyhf/cli/infer.py\n@@ -107,8 +107,8 @@\n testpoi, ws.data(model), model, qtilde=is_qtilde, return_expected_set=True\n )\n result = {\n- 'CLs_obs': tensorlib.tolist(result[0])[0],\n- 'CLs_exp': tensorlib.tolist(tensorlib.reshape(result[-1], [-1])),\n+ 'CLs_obs': tensorlib.tolist(result[0]),\n+ 'CLs_exp': [tensorlib.tolist(tensor) for tensor in result[-1]],\n }\n \n if output_file is None:\ndiff --git a/src/pyhf/infer/__init__.py b/src/pyhf/infer/__init__.py\n--- a/src/pyhf/infer/__init__.py\n+++ b/src/pyhf/infer/__init__.py\n@@ -23,14 +23,10 @@\n >>> CLs_obs, CLs_exp_band = pyhf.infer.hypotest(\n ... test_poi, data, model, qtilde=True, return_expected_set=True\n ... )\n- >>> print(CLs_obs)\n- [0.05251554]\n- >>> print(CLs_exp_band)\n- [[0.00260641]\n- [0.01382066]\n- [0.06445521]\n- [0.23526104]\n- [0.57304182]]\n+ >>> CLs_obs\n+ array(0.05251554)\n+ >>> CLs_exp_band\n+ [array(0.00260641), array(0.01382066), array(0.06445521), array(0.23526104), array(0.57304182)]\n \n Args:\n poi_test (Number or Tensor): The value of the parameter of interest (POI)\n@@ -102,10 +98,11 @@\n CLsb = sig_plus_bkg_distribution.pvalue(teststat)\n CLb = b_only_distribution.pvalue(teststat)\n CLs = CLsb / CLb\n+ # Ensure that all CL values are 0-d tensors\n CLsb, CLb, CLs = (\n- tensorlib.reshape(CLsb, (1,)),\n- tensorlib.reshape(CLb, (1,)),\n- tensorlib.reshape(CLs, (1,)),\n+ tensorlib.astensor(CLsb),\n+ tensorlib.astensor(CLb),\n+ tensorlib.astensor(CLs),\n )\n \n _returns = [CLs]\n@@ -120,8 +117,7 @@\n CLs = sig_plus_bkg_distribution.pvalue(\n expected_bonly_teststat\n ) / b_only_distribution.pvalue(expected_bonly_teststat)\n- CLs_exp.append(tensorlib.reshape(CLs, (1,)))\n- CLs_exp = tensorlib.astensor(CLs_exp)\n+ CLs_exp.append(tensorlib.astensor(CLs))\n if kwargs.get('return_expected'):\n _returns.append(CLs_exp[2])\n _returns.append(CLs_exp)\n@@ -132,7 +128,7 @@\n CLs = sig_plus_bkg_distribution.pvalue(\n expected_bonly_teststat\n ) / b_only_distribution.pvalue(expected_bonly_teststat)\n- _returns.append(tensorlib.reshape(CLs, (1,)))\n+ _returns.append(tensorlib.astensor(CLs))\n # Enforce a consistent return type of the observed CLs\n return tuple(_returns) if len(_returns) > 1 else _returns[0]\n", "issue": "API: change CLs to be scalar\n# Description\r\n\r\nright now it's returning (1,) vectors\r\n\n", "before_files": [{"content": "\"\"\"The inference CLI group.\"\"\"\nimport logging\n\nimport click\nimport json\n\nfrom ..utils import EqDelimStringParamType\nfrom ..infer import hypotest\nfrom ..workspace import Workspace\nfrom .. import get_backend, set_backend, optimize\n\nlog = logging.getLogger(__name__)\n\n\[email protected](name='infer')\ndef cli():\n \"\"\"Infererence CLI group.\"\"\"\n\n\[email protected]()\[email protected]('workspace', default='-')\[email protected](\n '--output-file',\n help='The location of the output json file. If not specified, prints to screen.',\n default=None,\n)\[email protected]('--measurement', default=None)\[email protected]('-p', '--patch', multiple=True)\[email protected]('--testpoi', default=1.0)\[email protected]('--teststat', type=click.Choice(['q', 'qtilde']), default='qtilde')\[email protected](\n '--backend',\n type=click.Choice(['numpy', 'pytorch', 'tensorflow', 'jax', 'np', 'torch', 'tf']),\n help='The tensor backend used for the calculation.',\n default='numpy',\n)\[email protected]('--optimizer')\[email protected]('--optconf', type=EqDelimStringParamType(), multiple=True)\ndef cls(\n workspace,\n output_file,\n measurement,\n patch,\n testpoi,\n teststat,\n backend,\n optimizer,\n optconf,\n):\n \"\"\"\n Compute CLs value(s) for a given pyhf workspace.\n\n Example:\n\n .. code-block:: shell\n\n $ curl -sL https://git.io/JJYDE | pyhf cls\n\n \\b\n {\n \"CLs_exp\": [\n 0.07807427911686156,\n 0.17472571775474618,\n 0.35998495263681285,\n 0.6343568235898907,\n 0.8809947004472013\n ],\n \"CLs_obs\": 0.3599845631401915\n }\n \"\"\"\n with click.open_file(workspace, 'r') as specstream:\n spec = json.load(specstream)\n\n ws = Workspace(spec)\n\n is_qtilde = teststat == 'qtilde'\n\n patches = [json.loads(click.open_file(pfile, 'r').read()) for pfile in patch]\n model = ws.model(\n measurement_name=measurement,\n patches=patches,\n modifier_settings={\n 'normsys': {'interpcode': 'code4'},\n 'histosys': {'interpcode': 'code4p'},\n },\n )\n\n # set the backend if not NumPy\n if backend in ['pytorch', 'torch']:\n set_backend(\"pytorch\", precision=\"64b\")\n elif backend in ['tensorflow', 'tf']:\n set_backend(\"tensorflow\", precision=\"64b\")\n elif backend in ['jax']:\n set_backend(\"jax\")\n tensorlib, _ = get_backend()\n\n optconf = {k: v for item in optconf for k, v in item.items()}\n\n # set the new optimizer\n if optimizer:\n new_optimizer = getattr(optimize, optimizer) or getattr(\n optimize, f'{optimizer}_optimizer'\n )\n set_backend(tensorlib, new_optimizer(**optconf))\n\n result = hypotest(\n testpoi, ws.data(model), model, qtilde=is_qtilde, return_expected_set=True\n )\n result = {\n 'CLs_obs': tensorlib.tolist(result[0])[0],\n 'CLs_exp': tensorlib.tolist(tensorlib.reshape(result[-1], [-1])),\n }\n\n if output_file is None:\n click.echo(json.dumps(result, indent=4, sort_keys=True))\n else:\n with open(output_file, 'w+') as out_file:\n json.dump(result, out_file, indent=4, sort_keys=True)\n log.debug(\"Written to {0:s}\".format(output_file))\n", "path": "src/pyhf/cli/infer.py"}, {"content": "\"\"\"Inference for Statistical Models.\"\"\"\n\nfrom .test_statistics import qmu\nfrom .. import get_backend\nfrom .calculators import AsymptoticCalculator\n\n\ndef hypotest(\n poi_test, data, pdf, init_pars=None, par_bounds=None, qtilde=False, **kwargs\n):\n r\"\"\"\n Compute :math:`p`-values and test statistics for a single value of the parameter of interest.\n\n Example:\n >>> import pyhf\n >>> pyhf.set_backend(\"numpy\")\n >>> model = pyhf.simplemodels.hepdata_like(\n ... signal_data=[12.0, 11.0], bkg_data=[50.0, 52.0], bkg_uncerts=[3.0, 7.0]\n ... )\n >>> observations = [51, 48]\n >>> data = pyhf.tensorlib.astensor(observations + model.config.auxdata)\n >>> test_poi = 1.0\n >>> CLs_obs, CLs_exp_band = pyhf.infer.hypotest(\n ... test_poi, data, model, qtilde=True, return_expected_set=True\n ... )\n >>> print(CLs_obs)\n [0.05251554]\n >>> print(CLs_exp_band)\n [[0.00260641]\n [0.01382066]\n [0.06445521]\n [0.23526104]\n [0.57304182]]\n\n Args:\n poi_test (Number or Tensor): The value of the parameter of interest (POI)\n data (Number or Tensor): The root of the calculated test statistic given the Asimov data, :math:`\\sqrt{q_{\\mu,A}}`\n pdf (~pyhf.pdf.Model): The HistFactory statistical model\n init_pars (Array or Tensor): The initial parameter values to be used for minimization\n par_bounds (Array or Tensor): The parameter value bounds to be used for minimization\n qtilde (Bool): When ``True`` perform the calculation using the alternative test statistic, :math:`\\tilde{q}`, as defined in Equation (62) of :xref:`arXiv:1007.1727`\n\n Keyword Args:\n return_tail_probs (bool): Bool for returning :math:`\\textrm{CL}_{s+b}` and :math:`\\textrm{CL}_{b}`\n return_expected (bool): Bool for returning :math:`\\textrm{CL}_{\\textrm{exp}}`\n return_expected_set (bool): Bool for returning the :math:`(-2,-1,0,1,2)\\sigma` :math:`\\textrm{CL}_{\\textrm{exp}}` --- the \"Brazil band\"\n\n Returns:\n Tuple of Floats and lists of Floats:\n\n - :math:`\\textrm{CL}_{s}`: The :math:`p`-value compared to the given threshold :math:`\\alpha`, typically taken to be :math:`0.05`, defined in :xref:`arXiv:1007.1727` as\n\n .. math::\n\n \\textrm{CL}_{s} = \\frac{\\textrm{CL}_{s+b}}{\\textrm{CL}_{b}} = \\frac{p_{s+b}}{1-p_{b}}\n\n to protect against excluding signal models in which there is little sensitivity. In the case that :math:`\\textrm{CL}_{s} \\leq \\alpha` the given signal model is excluded.\n\n - :math:`\\left[\\textrm{CL}_{s+b}, \\textrm{CL}_{b}\\right]`: The signal + background :math:`p`-value and 1 minus the background only :math:`p`-value as defined in Equations (75) and (76) of :xref:`arXiv:1007.1727`\n\n .. math::\n\n \\textrm{CL}_{s+b} = p_{s+b} = \\int\\limits_{q_{\\textrm{obs}}}^{\\infty} f\\left(q\\,\\middle|s+b\\right)\\,dq = 1 - \\Phi\\left(\\frac{q_{\\textrm{obs}} + 1/\\sigma_{s+b}^{2}}{2/\\sigma_{s+b}}\\right)\n\n .. math::\n\n \\textrm{CL}_{b} = 1- p_{b} = 1 - \\int\\limits_{-\\infty}^{q_{\\textrm{obs}}} f\\left(q\\,\\middle|b\\right)\\,dq = 1 - \\Phi\\left(\\frac{q_{\\textrm{obs}} - 1/\\sigma_{b}^{2}}{2/\\sigma_{b}}\\right)\n\n with Equations (73) and (74) for the mean\n\n .. math::\n\n E\\left[q\\right] = \\frac{1 - 2\\mu}{\\sigma^{2}}\n\n and variance\n\n .. math::\n\n V\\left[q\\right] = \\frac{4}{\\sigma^{2}}\n\n of the test statistic :math:`q` under the background only and and signal + background hypotheses. Only returned when ``return_tail_probs`` is ``True``.\n\n - :math:`\\textrm{CL}_{s,\\textrm{exp}}`: The expected :math:`\\textrm{CL}_{s}` value corresponding to the test statistic under the background only hypothesis :math:`\\left(\\mu=0\\right)`. Only returned when ``return_expected`` is ``True``.\n\n - :math:`\\textrm{CL}_{s,\\textrm{exp}}` band: The set of expected :math:`\\textrm{CL}_{s}` values corresponding to the median significance of variations of the signal strength from the background only hypothesis :math:`\\left(\\mu=0\\right)` at :math:`(-2,-1,0,1,2)\\sigma`. That is, the :math:`p`-values that satisfy Equation (89) of :xref:`arXiv:1007.1727`\n\n .. math::\n\n \\textrm{band}_{N\\sigma} = \\mu' + \\sigma\\,\\Phi^{-1}\\left(1-\\alpha\\right) \\pm N\\sigma\n\n for :math:`\\mu'=0` and :math:`N \\in \\left\\{-2, -1, 0, 1, 2\\right\\}`. These values define the boundaries of an uncertainty band sometimes referred to as the \"Brazil band\". Only returned when ``return_expected_set`` is ``True``.\n\n \"\"\"\n init_pars = init_pars or pdf.config.suggested_init()\n par_bounds = par_bounds or pdf.config.suggested_bounds()\n tensorlib, _ = get_backend()\n\n calc = AsymptoticCalculator(data, pdf, init_pars, par_bounds, qtilde=qtilde)\n teststat = calc.teststatistic(poi_test)\n sig_plus_bkg_distribution, b_only_distribution = calc.distributions(poi_test)\n\n CLsb = sig_plus_bkg_distribution.pvalue(teststat)\n CLb = b_only_distribution.pvalue(teststat)\n CLs = CLsb / CLb\n CLsb, CLb, CLs = (\n tensorlib.reshape(CLsb, (1,)),\n tensorlib.reshape(CLb, (1,)),\n tensorlib.reshape(CLs, (1,)),\n )\n\n _returns = [CLs]\n if kwargs.get('return_tail_probs'):\n _returns.append([CLsb, CLb])\n if kwargs.get('return_expected_set'):\n CLs_exp = []\n for n_sigma in [2, 1, 0, -1, -2]:\n\n expected_bonly_teststat = b_only_distribution.expected_value(n_sigma)\n\n CLs = sig_plus_bkg_distribution.pvalue(\n expected_bonly_teststat\n ) / b_only_distribution.pvalue(expected_bonly_teststat)\n CLs_exp.append(tensorlib.reshape(CLs, (1,)))\n CLs_exp = tensorlib.astensor(CLs_exp)\n if kwargs.get('return_expected'):\n _returns.append(CLs_exp[2])\n _returns.append(CLs_exp)\n elif kwargs.get('return_expected'):\n n_sigma = 0\n expected_bonly_teststat = b_only_distribution.expected_value(n_sigma)\n\n CLs = sig_plus_bkg_distribution.pvalue(\n expected_bonly_teststat\n ) / b_only_distribution.pvalue(expected_bonly_teststat)\n _returns.append(tensorlib.reshape(CLs, (1,)))\n # Enforce a consistent return type of the observed CLs\n return tuple(_returns) if len(_returns) > 1 else _returns[0]\n\n\n__all__ = ['qmu', 'hypotest']\n", "path": "src/pyhf/infer/__init__.py"}]} | 4,072 | 865 |
gh_patches_debug_66455 | rasdani/github-patches | git_diff | pyca__cryptography-8319 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Incorrect docstrings in x25519 and x448 `.public_key()` methods
See:
https://github.com/pyca/cryptography/blob/127a2860740c77f45362e68e0ed7d2d108a39033/src/cryptography/hazmat/primitives/asymmetric/x25519.py#L60-L64
https://github.com/pyca/cryptography/blob/127a2860740c77f45362e68e0ed7d2d108a39033/src/cryptography/hazmat/primitives/asymmetric/x448.py#L60-L64
In both instances, the method does not return serialised bytes, but a public key object. The full [generated documentation](https://cryptography.io/en/latest/hazmat/primitives/asymmetric/x25519/#cryptography.hazmat.primitives.asymmetric.x25519.X25519PrivateKey.public_key) is correct, as are the Ed* docstrings.
</issue>
<code>
[start of src/cryptography/hazmat/primitives/asymmetric/x448.py]
1 # This file is dual licensed under the terms of the Apache License, Version
2 # 2.0, and the BSD License. See the LICENSE file in the root of this repository
3 # for complete details.
4
5
6 import abc
7
8 from cryptography.exceptions import UnsupportedAlgorithm, _Reasons
9 from cryptography.hazmat.primitives import _serialization
10
11
12 class X448PublicKey(metaclass=abc.ABCMeta):
13 @classmethod
14 def from_public_bytes(cls, data: bytes) -> "X448PublicKey":
15 from cryptography.hazmat.backends.openssl.backend import backend
16
17 if not backend.x448_supported():
18 raise UnsupportedAlgorithm(
19 "X448 is not supported by this version of OpenSSL.",
20 _Reasons.UNSUPPORTED_EXCHANGE_ALGORITHM,
21 )
22
23 return backend.x448_load_public_bytes(data)
24
25 @abc.abstractmethod
26 def public_bytes(
27 self,
28 encoding: _serialization.Encoding,
29 format: _serialization.PublicFormat,
30 ) -> bytes:
31 """
32 The serialized bytes of the public key.
33 """
34
35
36 class X448PrivateKey(metaclass=abc.ABCMeta):
37 @classmethod
38 def generate(cls) -> "X448PrivateKey":
39 from cryptography.hazmat.backends.openssl.backend import backend
40
41 if not backend.x448_supported():
42 raise UnsupportedAlgorithm(
43 "X448 is not supported by this version of OpenSSL.",
44 _Reasons.UNSUPPORTED_EXCHANGE_ALGORITHM,
45 )
46 return backend.x448_generate_key()
47
48 @classmethod
49 def from_private_bytes(cls, data: bytes) -> "X448PrivateKey":
50 from cryptography.hazmat.backends.openssl.backend import backend
51
52 if not backend.x448_supported():
53 raise UnsupportedAlgorithm(
54 "X448 is not supported by this version of OpenSSL.",
55 _Reasons.UNSUPPORTED_EXCHANGE_ALGORITHM,
56 )
57
58 return backend.x448_load_private_bytes(data)
59
60 @abc.abstractmethod
61 def public_key(self) -> X448PublicKey:
62 """
63 The serialized bytes of the public key.
64 """
65
66 @abc.abstractmethod
67 def private_bytes(
68 self,
69 encoding: _serialization.Encoding,
70 format: _serialization.PrivateFormat,
71 encryption_algorithm: _serialization.KeySerializationEncryption,
72 ) -> bytes:
73 """
74 The serialized bytes of the private key.
75 """
76
77 @abc.abstractmethod
78 def exchange(self, peer_public_key: X448PublicKey) -> bytes:
79 """
80 Performs a key exchange operation using the provided peer's public key.
81 """
82
[end of src/cryptography/hazmat/primitives/asymmetric/x448.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/cryptography/hazmat/primitives/asymmetric/x448.py b/src/cryptography/hazmat/primitives/asymmetric/x448.py
--- a/src/cryptography/hazmat/primitives/asymmetric/x448.py
+++ b/src/cryptography/hazmat/primitives/asymmetric/x448.py
@@ -60,7 +60,7 @@
@abc.abstractmethod
def public_key(self) -> X448PublicKey:
"""
- The serialized bytes of the public key.
+ Returns the public key associated with this private key
"""
@abc.abstractmethod
| {"golden_diff": "diff --git a/src/cryptography/hazmat/primitives/asymmetric/x448.py b/src/cryptography/hazmat/primitives/asymmetric/x448.py\n--- a/src/cryptography/hazmat/primitives/asymmetric/x448.py\n+++ b/src/cryptography/hazmat/primitives/asymmetric/x448.py\n@@ -60,7 +60,7 @@\n @abc.abstractmethod\n def public_key(self) -> X448PublicKey:\n \"\"\"\n- The serialized bytes of the public key.\n+ Returns the public key associated with this private key\n \"\"\"\n \n @abc.abstractmethod\n", "issue": "Incorrect docstrings in x25519 and x448 `.public_key()` methods\nSee:\r\n\r\nhttps://github.com/pyca/cryptography/blob/127a2860740c77f45362e68e0ed7d2d108a39033/src/cryptography/hazmat/primitives/asymmetric/x25519.py#L60-L64\r\n\r\nhttps://github.com/pyca/cryptography/blob/127a2860740c77f45362e68e0ed7d2d108a39033/src/cryptography/hazmat/primitives/asymmetric/x448.py#L60-L64\r\n\r\nIn both instances, the method does not return serialised bytes, but a public key object. The full [generated documentation](https://cryptography.io/en/latest/hazmat/primitives/asymmetric/x25519/#cryptography.hazmat.primitives.asymmetric.x25519.X25519PrivateKey.public_key) is correct, as are the Ed* docstrings.\n", "before_files": [{"content": "# This file is dual licensed under the terms of the Apache License, Version\n# 2.0, and the BSD License. See the LICENSE file in the root of this repository\n# for complete details.\n\n\nimport abc\n\nfrom cryptography.exceptions import UnsupportedAlgorithm, _Reasons\nfrom cryptography.hazmat.primitives import _serialization\n\n\nclass X448PublicKey(metaclass=abc.ABCMeta):\n @classmethod\n def from_public_bytes(cls, data: bytes) -> \"X448PublicKey\":\n from cryptography.hazmat.backends.openssl.backend import backend\n\n if not backend.x448_supported():\n raise UnsupportedAlgorithm(\n \"X448 is not supported by this version of OpenSSL.\",\n _Reasons.UNSUPPORTED_EXCHANGE_ALGORITHM,\n )\n\n return backend.x448_load_public_bytes(data)\n\n @abc.abstractmethod\n def public_bytes(\n self,\n encoding: _serialization.Encoding,\n format: _serialization.PublicFormat,\n ) -> bytes:\n \"\"\"\n The serialized bytes of the public key.\n \"\"\"\n\n\nclass X448PrivateKey(metaclass=abc.ABCMeta):\n @classmethod\n def generate(cls) -> \"X448PrivateKey\":\n from cryptography.hazmat.backends.openssl.backend import backend\n\n if not backend.x448_supported():\n raise UnsupportedAlgorithm(\n \"X448 is not supported by this version of OpenSSL.\",\n _Reasons.UNSUPPORTED_EXCHANGE_ALGORITHM,\n )\n return backend.x448_generate_key()\n\n @classmethod\n def from_private_bytes(cls, data: bytes) -> \"X448PrivateKey\":\n from cryptography.hazmat.backends.openssl.backend import backend\n\n if not backend.x448_supported():\n raise UnsupportedAlgorithm(\n \"X448 is not supported by this version of OpenSSL.\",\n _Reasons.UNSUPPORTED_EXCHANGE_ALGORITHM,\n )\n\n return backend.x448_load_private_bytes(data)\n\n @abc.abstractmethod\n def public_key(self) -> X448PublicKey:\n \"\"\"\n The serialized bytes of the public key.\n \"\"\"\n\n @abc.abstractmethod\n def private_bytes(\n self,\n encoding: _serialization.Encoding,\n format: _serialization.PrivateFormat,\n encryption_algorithm: _serialization.KeySerializationEncryption,\n ) -> bytes:\n \"\"\"\n The serialized bytes of the private key.\n \"\"\"\n\n @abc.abstractmethod\n def exchange(self, peer_public_key: X448PublicKey) -> bytes:\n \"\"\"\n Performs a key exchange operation using the provided peer's public key.\n \"\"\"\n", "path": "src/cryptography/hazmat/primitives/asymmetric/x448.py"}]} | 1,522 | 136 |
gh_patches_debug_30497 | rasdani/github-patches | git_diff | quantumlib__Cirq-5786 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
merge_single_qubit_gates_to_phxz raises IndexError when encountering GlobalPhaseGate
**Description of the issue**
**How to reproduce the issue**
```
cirq.merge_single_qubit_gates_to_phxz(cirq.Circuit(cirq.GlobalPhaseGate(1j).on()))
...
/src/cirq/cirq-core/cirq/linalg/decompositions.py in deconstruct_single_qubit_matrix_into_angles(mat)
88 """
89 # Anti-cancel left-vs-right phase along top row.
---> 90 right_phase = cmath.phase(mat[0, 1] * np.conj(mat[0, 0])) + math.pi
91 mat = np.dot(mat, _phase_matrix(-right_phase))
92
IndexError: index 1 is out of bounds for axis 1 with size 1
```
I also checked `merge_single_qubit_gates_to_phased_x_and_z` and it suffers from the same issue.
The problem appears to be that the rewriter passes a 1x1 matrix to `single_qubit_matrix_to_phxz` which expects a 2x2 matrix.
**Cirq version**
0.16.0.dev
</issue>
<code>
[start of cirq-core/cirq/transformers/merge_single_qubit_gates.py]
1 # Copyright 2022 The Cirq Developers
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # https://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 """Transformer passes to combine adjacent single-qubit rotations."""
16
17 from typing import Optional, TYPE_CHECKING
18
19 from cirq import protocols, circuits
20 from cirq.transformers.analytical_decompositions import single_qubit_decompositions
21 from cirq.transformers import transformer_api, transformer_primitives, merge_k_qubit_gates
22
23 if TYPE_CHECKING:
24 import cirq
25
26
27 @transformer_api.transformer
28 def merge_single_qubit_gates_to_phased_x_and_z(
29 circuit: 'cirq.AbstractCircuit',
30 *,
31 context: Optional['cirq.TransformerContext'] = None,
32 atol: float = 1e-8,
33 ) -> 'cirq.Circuit':
34 """Replaces runs of single qubit rotations with `cirq.PhasedXPowGate` and `cirq.ZPowGate`.
35
36 Specifically, any run of non-parameterized single-qubit unitaries will be replaced by an
37 optional PhasedX operation followed by an optional Z operation.
38
39 Args:
40 circuit: Input circuit to transform. It will not be modified.
41 context: `cirq.TransformerContext` storing common configurable options for transformers.
42 atol: Absolute tolerance to angle error. Larger values allow more negligible gates to be
43 dropped, smaller values increase accuracy.
44
45 Returns:
46 Copy of the transformed input circuit.
47 """
48
49 def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':
50 return [
51 g(op.qubits[0])
52 for g in single_qubit_decompositions.single_qubit_matrix_to_phased_x_z(
53 protocols.unitary(op), atol
54 )
55 ]
56
57 return merge_k_qubit_gates.merge_k_qubit_unitaries(
58 circuit, k=1, context=context, rewriter=rewriter
59 )
60
61
62 @transformer_api.transformer
63 def merge_single_qubit_gates_to_phxz(
64 circuit: 'cirq.AbstractCircuit',
65 *,
66 context: Optional['cirq.TransformerContext'] = None,
67 atol: float = 1e-8,
68 ) -> 'cirq.Circuit':
69 """Replaces runs of single qubit rotations with a single optional `cirq.PhasedXZGate`.
70
71 Specifically, any run of non-parameterized single-qubit unitaries will be replaced by an
72 optional PhasedXZ.
73
74 Args:
75 circuit: Input circuit to transform. It will not be modified.
76 context: `cirq.TransformerContext` storing common configurable options for transformers.
77 atol: Absolute tolerance to angle error. Larger values allow more negligible gates to be
78 dropped, smaller values increase accuracy.
79
80 Returns:
81 Copy of the transformed input circuit.
82 """
83
84 def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':
85 gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(protocols.unitary(op), atol)
86 return gate(op.qubits[0]) if gate else []
87
88 return merge_k_qubit_gates.merge_k_qubit_unitaries(
89 circuit, k=1, context=context, rewriter=rewriter
90 )
91
92
93 @transformer_api.transformer
94 def merge_single_qubit_moments_to_phxz(
95 circuit: 'cirq.AbstractCircuit',
96 *,
97 context: Optional['cirq.TransformerContext'] = None,
98 atol: float = 1e-8,
99 ) -> 'cirq.Circuit':
100 """Merges adjacent moments with only 1-qubit rotations to a single moment with PhasedXZ gates.
101
102 Args:
103 circuit: Input circuit to transform. It will not be modified.
104 context: `cirq.TransformerContext` storing common configurable options for transformers.
105 atol: Absolute tolerance to angle error. Larger values allow more negligible gates to be
106 dropped, smaller values increase accuracy.
107
108 Returns:
109 Copy of the transformed input circuit.
110 """
111 tags_to_ignore = set(context.tags_to_ignore) if context else set()
112
113 def can_merge_moment(m: 'cirq.Moment'):
114 return all(
115 protocols.num_qubits(op) == 1
116 and protocols.has_unitary(op)
117 and tags_to_ignore.isdisjoint(op.tags)
118 for op in m
119 )
120
121 def merge_func(m1: 'cirq.Moment', m2: 'cirq.Moment') -> Optional['cirq.Moment']:
122 if not (can_merge_moment(m1) and can_merge_moment(m2)):
123 return None
124 ret_ops = []
125 for q in m1.qubits | m2.qubits:
126 mat = protocols.unitary(circuits.Circuit(m.operation_at(q) or [] for m in [m1, m2]))
127 gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(mat, atol)
128 if gate:
129 ret_ops.append(gate(q))
130 return circuits.Moment(ret_ops)
131
132 return transformer_primitives.merge_moments(
133 circuit,
134 merge_func,
135 deep=context.deep if context else False,
136 tags_to_ignore=tuple(tags_to_ignore),
137 ).unfreeze(copy=False)
138
[end of cirq-core/cirq/transformers/merge_single_qubit_gates.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/cirq-core/cirq/transformers/merge_single_qubit_gates.py b/cirq-core/cirq/transformers/merge_single_qubit_gates.py
--- a/cirq-core/cirq/transformers/merge_single_qubit_gates.py
+++ b/cirq-core/cirq/transformers/merge_single_qubit_gates.py
@@ -16,7 +16,7 @@
from typing import Optional, TYPE_CHECKING
-from cirq import protocols, circuits
+from cirq import circuits, ops, protocols
from cirq.transformers.analytical_decompositions import single_qubit_decompositions
from cirq.transformers import transformer_api, transformer_primitives, merge_k_qubit_gates
@@ -47,11 +47,12 @@
"""
def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':
+ u = protocols.unitary(op)
+ if protocols.num_qubits(op) == 0:
+ return ops.GlobalPhaseGate(u[0, 0]).on()
return [
g(op.qubits[0])
- for g in single_qubit_decompositions.single_qubit_matrix_to_phased_x_z(
- protocols.unitary(op), atol
- )
+ for g in single_qubit_decompositions.single_qubit_matrix_to_phased_x_z(u, atol)
]
return merge_k_qubit_gates.merge_k_qubit_unitaries(
@@ -82,7 +83,10 @@
"""
def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':
- gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(protocols.unitary(op), atol)
+ u = protocols.unitary(op)
+ if protocols.num_qubits(op) == 0:
+ return ops.GlobalPhaseGate(u[0, 0]).on()
+ gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(u, atol)
return gate(op.qubits[0]) if gate else []
return merge_k_qubit_gates.merge_k_qubit_unitaries(
| {"golden_diff": "diff --git a/cirq-core/cirq/transformers/merge_single_qubit_gates.py b/cirq-core/cirq/transformers/merge_single_qubit_gates.py\n--- a/cirq-core/cirq/transformers/merge_single_qubit_gates.py\n+++ b/cirq-core/cirq/transformers/merge_single_qubit_gates.py\n@@ -16,7 +16,7 @@\n \n from typing import Optional, TYPE_CHECKING\n \n-from cirq import protocols, circuits\n+from cirq import circuits, ops, protocols\n from cirq.transformers.analytical_decompositions import single_qubit_decompositions\n from cirq.transformers import transformer_api, transformer_primitives, merge_k_qubit_gates\n \n@@ -47,11 +47,12 @@\n \"\"\"\n \n def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':\n+ u = protocols.unitary(op)\n+ if protocols.num_qubits(op) == 0:\n+ return ops.GlobalPhaseGate(u[0, 0]).on()\n return [\n g(op.qubits[0])\n- for g in single_qubit_decompositions.single_qubit_matrix_to_phased_x_z(\n- protocols.unitary(op), atol\n- )\n+ for g in single_qubit_decompositions.single_qubit_matrix_to_phased_x_z(u, atol)\n ]\n \n return merge_k_qubit_gates.merge_k_qubit_unitaries(\n@@ -82,7 +83,10 @@\n \"\"\"\n \n def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':\n- gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(protocols.unitary(op), atol)\n+ u = protocols.unitary(op)\n+ if protocols.num_qubits(op) == 0:\n+ return ops.GlobalPhaseGate(u[0, 0]).on()\n+ gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(u, atol)\n return gate(op.qubits[0]) if gate else []\n \n return merge_k_qubit_gates.merge_k_qubit_unitaries(\n", "issue": "merge_single_qubit_gates_to_phxz raises IndexError when encountering GlobalPhaseGate\n**Description of the issue**\r\n\r\n**How to reproduce the issue**\r\n\r\n```\r\ncirq.merge_single_qubit_gates_to_phxz(cirq.Circuit(cirq.GlobalPhaseGate(1j).on()))\r\n...\r\n/src/cirq/cirq-core/cirq/linalg/decompositions.py in deconstruct_single_qubit_matrix_into_angles(mat)\r\n 88 \"\"\"\r\n 89 # Anti-cancel left-vs-right phase along top row.\r\n---> 90 right_phase = cmath.phase(mat[0, 1] * np.conj(mat[0, 0])) + math.pi\r\n 91 mat = np.dot(mat, _phase_matrix(-right_phase))\r\n 92 \r\n\r\nIndexError: index 1 is out of bounds for axis 1 with size 1\r\n```\r\n\r\nI also checked `merge_single_qubit_gates_to_phased_x_and_z` and it suffers from the same issue.\r\n\r\nThe problem appears to be that the rewriter passes a 1x1 matrix to `single_qubit_matrix_to_phxz` which expects a 2x2 matrix.\r\n\r\n**Cirq version**\r\n0.16.0.dev\r\n\n", "before_files": [{"content": "# Copyright 2022 The Cirq Developers\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# https://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\n\"\"\"Transformer passes to combine adjacent single-qubit rotations.\"\"\"\n\nfrom typing import Optional, TYPE_CHECKING\n\nfrom cirq import protocols, circuits\nfrom cirq.transformers.analytical_decompositions import single_qubit_decompositions\nfrom cirq.transformers import transformer_api, transformer_primitives, merge_k_qubit_gates\n\nif TYPE_CHECKING:\n import cirq\n\n\n@transformer_api.transformer\ndef merge_single_qubit_gates_to_phased_x_and_z(\n circuit: 'cirq.AbstractCircuit',\n *,\n context: Optional['cirq.TransformerContext'] = None,\n atol: float = 1e-8,\n) -> 'cirq.Circuit':\n \"\"\"Replaces runs of single qubit rotations with `cirq.PhasedXPowGate` and `cirq.ZPowGate`.\n\n Specifically, any run of non-parameterized single-qubit unitaries will be replaced by an\n optional PhasedX operation followed by an optional Z operation.\n\n Args:\n circuit: Input circuit to transform. It will not be modified.\n context: `cirq.TransformerContext` storing common configurable options for transformers.\n atol: Absolute tolerance to angle error. Larger values allow more negligible gates to be\n dropped, smaller values increase accuracy.\n\n Returns:\n Copy of the transformed input circuit.\n \"\"\"\n\n def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':\n return [\n g(op.qubits[0])\n for g in single_qubit_decompositions.single_qubit_matrix_to_phased_x_z(\n protocols.unitary(op), atol\n )\n ]\n\n return merge_k_qubit_gates.merge_k_qubit_unitaries(\n circuit, k=1, context=context, rewriter=rewriter\n )\n\n\n@transformer_api.transformer\ndef merge_single_qubit_gates_to_phxz(\n circuit: 'cirq.AbstractCircuit',\n *,\n context: Optional['cirq.TransformerContext'] = None,\n atol: float = 1e-8,\n) -> 'cirq.Circuit':\n \"\"\"Replaces runs of single qubit rotations with a single optional `cirq.PhasedXZGate`.\n\n Specifically, any run of non-parameterized single-qubit unitaries will be replaced by an\n optional PhasedXZ.\n\n Args:\n circuit: Input circuit to transform. It will not be modified.\n context: `cirq.TransformerContext` storing common configurable options for transformers.\n atol: Absolute tolerance to angle error. Larger values allow more negligible gates to be\n dropped, smaller values increase accuracy.\n\n Returns:\n Copy of the transformed input circuit.\n \"\"\"\n\n def rewriter(op: 'cirq.CircuitOperation') -> 'cirq.OP_TREE':\n gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(protocols.unitary(op), atol)\n return gate(op.qubits[0]) if gate else []\n\n return merge_k_qubit_gates.merge_k_qubit_unitaries(\n circuit, k=1, context=context, rewriter=rewriter\n )\n\n\n@transformer_api.transformer\ndef merge_single_qubit_moments_to_phxz(\n circuit: 'cirq.AbstractCircuit',\n *,\n context: Optional['cirq.TransformerContext'] = None,\n atol: float = 1e-8,\n) -> 'cirq.Circuit':\n \"\"\"Merges adjacent moments with only 1-qubit rotations to a single moment with PhasedXZ gates.\n\n Args:\n circuit: Input circuit to transform. It will not be modified.\n context: `cirq.TransformerContext` storing common configurable options for transformers.\n atol: Absolute tolerance to angle error. Larger values allow more negligible gates to be\n dropped, smaller values increase accuracy.\n\n Returns:\n Copy of the transformed input circuit.\n \"\"\"\n tags_to_ignore = set(context.tags_to_ignore) if context else set()\n\n def can_merge_moment(m: 'cirq.Moment'):\n return all(\n protocols.num_qubits(op) == 1\n and protocols.has_unitary(op)\n and tags_to_ignore.isdisjoint(op.tags)\n for op in m\n )\n\n def merge_func(m1: 'cirq.Moment', m2: 'cirq.Moment') -> Optional['cirq.Moment']:\n if not (can_merge_moment(m1) and can_merge_moment(m2)):\n return None\n ret_ops = []\n for q in m1.qubits | m2.qubits:\n mat = protocols.unitary(circuits.Circuit(m.operation_at(q) or [] for m in [m1, m2]))\n gate = single_qubit_decompositions.single_qubit_matrix_to_phxz(mat, atol)\n if gate:\n ret_ops.append(gate(q))\n return circuits.Moment(ret_ops)\n\n return transformer_primitives.merge_moments(\n circuit,\n merge_func,\n deep=context.deep if context else False,\n tags_to_ignore=tuple(tags_to_ignore),\n ).unfreeze(copy=False)\n", "path": "cirq-core/cirq/transformers/merge_single_qubit_gates.py"}]} | 2,346 | 466 |
gh_patches_debug_38604 | rasdani/github-patches | git_diff | tensorlayer__TensorLayer-189 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Issues with ops.exit_tf function
So far I've 2 issues with this function :
- ops.exit_tf() returns an error because a session is expected as argument.
- ops.exit_tf(sess) returns "NameError: name 'exit' is not defined" when launched from an IPython console - in my case it's Spyder's internal IPython console (tested both on Mac and Windows)
Both issue are easy to solve :
- add `if sess != None:` before `sess.close()`
- use `from sys import exit as _exit` to avoid whatever is the interference that's throwing the error
Before I propose a pull request, I just wanted to check that I'm not misusing the function : I tried to use the function without an argument to easly exit tensorboard (which is a nice feature) and I'm launching it from IPyton instead of the terminal because it's seems like a usefull function to be able to include in a script (and i run my scripts from Spyder)
</issue>
<code>
[start of tensorlayer/ops.py]
1 #! /usr/bin/python
2 # -*- coding: utf8 -*-
3
4
5
6
7 import tensorflow as tf
8 import os
9 import sys
10 from sys import platform as _platform
11
12
13 def exit_tf(sess=None):
14 """Close tensorboard and nvidia-process if available
15
16 Parameters
17 ----------
18 sess : a session instance of TensorFlow
19 TensorFlow session
20 """
21 text = "[tl] Close tensorboard and nvidia-process if available"
22 sess.close()
23 # import time
24 # time.sleep(2)
25 if _platform == "linux" or _platform == "linux2":
26 print('linux: %s' % text)
27 os.system('nvidia-smi')
28 os.system('fuser 6006/tcp -k') # kill tensorboard 6006
29 os.system("nvidia-smi | grep python |awk '{print $3}'|xargs kill") # kill all nvidia-smi python process
30 elif _platform == "darwin":
31 print('OS X: %s' % text)
32 os.system("lsof -i tcp:6006 | grep -v PID | awk '{print $2}' | xargs kill") # kill tensorboard 6006
33 elif _platform == "win32":
34 print('Windows: %s' % text)
35 else:
36 print(_platform)
37 exit()
38
39 def clear_all(printable=True):
40 """Clears all the placeholder variables of keep prob,
41 including keeping probabilities of all dropout, denoising, dropconnect etc.
42
43 Parameters
44 ----------
45 printable : boolean
46 If True, print all deleted variables.
47 """
48 print('clear all .....................................')
49 gl = globals().copy()
50 for var in gl:
51 if var[0] == '_': continue
52 if 'func' in str(globals()[var]): continue
53 if 'module' in str(globals()[var]): continue
54 if 'class' in str(globals()[var]): continue
55
56 if printable:
57 print(" clear_all ------- %s" % str(globals()[var]))
58
59 del globals()[var]
60
61 # def clear_all2(vars, printable=True):
62 # """
63 # The :function:`clear_all()` Clears all the placeholder variables of keep prob,
64 # including keeping probabilities of all dropout, denoising, dropconnect
65 # Parameters
66 # ----------
67 # printable : if True, print all deleted variables.
68 # """
69 # print('clear all .....................................')
70 # for var in vars:
71 # if var[0] == '_': continue
72 # if 'func' in str(var): continue
73 # if 'module' in str(var): continue
74 # if 'class' in str(var): continue
75 #
76 # if printable:
77 # print(" clear_all ------- %s" % str(var))
78 #
79 # del var
80
81 def set_gpu_fraction(sess=None, gpu_fraction=0.3):
82 """Set the GPU memory fraction for the application.
83
84 Parameters
85 ----------
86 sess : a session instance of TensorFlow
87 TensorFlow session
88 gpu_fraction : a float
89 Fraction of GPU memory, (0 ~ 1]
90
91 References
92 ----------
93 - `TensorFlow using GPU <https://www.tensorflow.org/versions/r0.9/how_tos/using_gpu/index.html>`_
94 """
95 print(" tensorlayer: GPU MEM Fraction %f" % gpu_fraction)
96 gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_fraction)
97 sess = tf.Session(config = tf.ConfigProto(gpu_options = gpu_options))
98 return sess
99
100
101
102
103
104 def disable_print():
105 """Disable console output, ``suppress_stdout`` is recommended.
106
107 Examples
108 ---------
109 >>> print("You can see me")
110 >>> tl.ops.disable_print()
111 >>> print(" You can't see me")
112 >>> tl.ops.enable_print()
113 >>> print("You can see me")
114 """
115 # sys.stdout = os.devnull # this one kill the process
116 sys.stdout = None
117 sys.stderr = os.devnull
118
119 def enable_print():
120 """Enable console output, ``suppress_stdout`` is recommended.
121
122 Examples
123 --------
124 - see tl.ops.disable_print()
125 """
126 sys.stdout = sys.__stdout__
127 sys.stderr = sys.__stderr__
128
129
130 # class temporary_disable_print:
131 # """Temporarily disable console output.
132 #
133 # Examples
134 # ---------
135 # >>> print("You can see me")
136 # >>> with tl.ops.temporary_disable_print() as t:
137 # >>> print("You can't see me")
138 # >>> print("You can see me")
139 # """
140 # def __init__(self):
141 # pass
142 # def __enter__(self):
143 # sys.stdout = None
144 # sys.stderr = os.devnull
145 # def __exit__(self, type, value, traceback):
146 # sys.stdout = sys.__stdout__
147 # sys.stderr = sys.__stderr__
148 # return isinstance(value, TypeError)
149
150
151 from contextlib import contextmanager
152 @contextmanager
153 def suppress_stdout():
154 """Temporarily disable console output.
155
156 Examples
157 ---------
158 >>> print("You can see me")
159 >>> with tl.ops.suppress_stdout():
160 >>> print("You can't see me")
161 >>> print("You can see me")
162
163 References
164 -----------
165 - `stackoverflow <http://stackoverflow.com/questions/2125702/how-to-suppress-console-output-in-python>`_
166 """
167 with open(os.devnull, "w") as devnull:
168 old_stdout = sys.stdout
169 sys.stdout = devnull
170 try:
171 yield
172 finally:
173 sys.stdout = old_stdout
174
175
176
177 def get_site_packages_directory():
178 """Print and return the site-packages directory.
179
180 Examples
181 ---------
182 >>> loc = tl.ops.get_site_packages_directory()
183 """
184 import site
185 try:
186 loc = site.getsitepackages()
187 print(" tl.ops : site-packages in ", loc)
188 return loc
189 except:
190 print(" tl.ops : Cannot find package dir from virtual environment")
191 return False
192
193
194
195 def empty_trash():
196 """Empty trash folder.
197
198 """
199 text = "[tl] Empty the trash"
200 if _platform == "linux" or _platform == "linux2":
201 print('linux: %s' % text)
202 os.system("rm -rf ~/.local/share/Trash/*")
203 elif _platform == "darwin":
204 print('OS X: %s' % text)
205 os.system("sudo rm -rf ~/.Trash/*")
206 elif _platform == "win32":
207 print('Windows: %s' % text)
208 try:
209 os.system("rd /s c:\$Recycle.Bin") # Windows 7 or Server 2008
210 except:
211 pass
212 try:
213 os.system("rd /s c:\recycler") # Windows XP, Vista, or Server 2003
214 except:
215 pass
216 else:
217 print(_platform)
218
219 #
220
[end of tensorlayer/ops.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/tensorlayer/ops.py b/tensorlayer/ops.py
--- a/tensorlayer/ops.py
+++ b/tensorlayer/ops.py
@@ -5,36 +5,73 @@
import tensorflow as tf
+import tensorlayer as tl
import os
+import subprocess
import sys
from sys import platform as _platform
+from sys import exit as _exit
-def exit_tf(sess=None):
- """Close tensorboard and nvidia-process if available
+def exit_tf(sess=None, port=6006):
+ """Close tensorflow session, tensorboard and nvidia-process if available
Parameters
----------
sess : a session instance of TensorFlow
TensorFlow session
+ tb_port : an integer
+ TensorBoard port you want to close, 6006 is tensorboard default
"""
text = "[tl] Close tensorboard and nvidia-process if available"
- sess.close()
+ text2 = "[tl] Close tensorboard and nvidia-process not yet supported by this function (tl.ops.exit_tf) on "
+ if sess != None:
+ sess.close()
# import time
# time.sleep(2)
if _platform == "linux" or _platform == "linux2":
print('linux: %s' % text)
os.system('nvidia-smi')
- os.system('fuser 6006/tcp -k') # kill tensorboard 6006
+ os.system('fuser '+ port +'/tcp -k') # kill tensorboard 6006
os.system("nvidia-smi | grep python |awk '{print $3}'|xargs kill") # kill all nvidia-smi python process
+ _exit()
elif _platform == "darwin":
print('OS X: %s' % text)
- os.system("lsof -i tcp:6006 | grep -v PID | awk '{print $2}' | xargs kill") # kill tensorboard 6006
+ subprocess.Popen("lsof -i tcp:"+ str(port) +" | grep -v PID | awk '{print $2}' | xargs kill", shell=True) # kill tensorboard
elif _platform == "win32":
- print('Windows: %s' % text)
+ print(text2 + "Windows")
+ # TODO
else:
- print(_platform)
- exit()
+ print(text2 + _platform)
+
+def open_tb(logdir='/tmp/tensorflow', port=6006):
+ """Open tensorboard
+
+ Parameters
+ ----------
+ logdir : a string
+ Directory where your tensorboard logs are saved
+ port : an integer
+ TensorBoard port you want to open, 6006 is tensorboard default
+ """
+
+ text = "[tl] Open tensorboard, go to localhost:" + str(port) + " to access"
+ text2 = " not yet supported by this function (tl.ops.open_tb)"
+
+ if not tl.files.exists_or_mkdir(logdir, verbose=False):
+ print("[tl] Log reportory was created at %s" % logdir)
+
+ if _platform == "linux" or _platform == "linux2":
+ print('linux %s' % text2)
+ # TODO
+ elif _platform == "darwin":
+ print('OS X: %s' % text)
+ subprocess.Popen(sys.prefix + " | python -m tensorflow.tensorboard --logdir=" + logdir + " --port=" + str(port), shell=True) # open tensorboard in localhost:6006/ or whatever port you chose
+ elif _platform == "win32":
+ print('Windows%s' % text2)
+ # TODO
+ else:
+ print(_platform + text2)
def clear_all(printable=True):
"""Clears all the placeholder variables of keep prob,
| {"golden_diff": "diff --git a/tensorlayer/ops.py b/tensorlayer/ops.py\n--- a/tensorlayer/ops.py\n+++ b/tensorlayer/ops.py\n@@ -5,36 +5,73 @@\n \n \n import tensorflow as tf\n+import tensorlayer as tl\n import os\n+import subprocess\n import sys\n from sys import platform as _platform\n+from sys import exit as _exit\n \n \n-def exit_tf(sess=None):\n- \"\"\"Close tensorboard and nvidia-process if available\n+def exit_tf(sess=None, port=6006):\n+ \"\"\"Close tensorflow session, tensorboard and nvidia-process if available\n \n Parameters\n ----------\n sess : a session instance of TensorFlow\n TensorFlow session\n+ tb_port : an integer\n+ TensorBoard port you want to close, 6006 is tensorboard default\n \"\"\"\n text = \"[tl] Close tensorboard and nvidia-process if available\"\n- sess.close()\n+ text2 = \"[tl] Close tensorboard and nvidia-process not yet supported by this function (tl.ops.exit_tf) on \"\n+ if sess != None:\n+ sess.close()\n # import time\n # time.sleep(2)\n if _platform == \"linux\" or _platform == \"linux2\":\n print('linux: %s' % text)\n os.system('nvidia-smi')\n- os.system('fuser 6006/tcp -k') # kill tensorboard 6006\n+ os.system('fuser '+ port +'/tcp -k') # kill tensorboard 6006\n os.system(\"nvidia-smi | grep python |awk '{print $3}'|xargs kill\") # kill all nvidia-smi python process\n+ _exit()\n elif _platform == \"darwin\":\n print('OS X: %s' % text)\n- os.system(\"lsof -i tcp:6006 | grep -v PID | awk '{print $2}' | xargs kill\") # kill tensorboard 6006\n+ subprocess.Popen(\"lsof -i tcp:\"+ str(port) +\" | grep -v PID | awk '{print $2}' | xargs kill\", shell=True) # kill tensorboard\n elif _platform == \"win32\":\n- print('Windows: %s' % text)\n+ print(text2 + \"Windows\")\n+ # TODO\n else:\n- print(_platform)\n- exit()\n+ print(text2 + _platform)\n+ \n+def open_tb(logdir='/tmp/tensorflow', port=6006):\n+ \"\"\"Open tensorboard\n+ \n+ Parameters\n+ ----------\n+ logdir : a string\n+ Directory where your tensorboard logs are saved\n+ port : an integer\n+ TensorBoard port you want to open, 6006 is tensorboard default\n+ \"\"\"\n+\n+ text = \"[tl] Open tensorboard, go to localhost:\" + str(port) + \" to access\"\n+ text2 = \" not yet supported by this function (tl.ops.open_tb)\"\n+ \n+ if not tl.files.exists_or_mkdir(logdir, verbose=False):\n+ print(\"[tl] Log reportory was created at %s\" % logdir)\n+ \n+ if _platform == \"linux\" or _platform == \"linux2\":\n+ print('linux %s' % text2)\n+ # TODO\n+ elif _platform == \"darwin\":\n+ print('OS X: %s' % text)\n+ subprocess.Popen(sys.prefix + \" | python -m tensorflow.tensorboard --logdir=\" + logdir + \" --port=\" + str(port), shell=True) # open tensorboard in localhost:6006/ or whatever port you chose\n+ elif _platform == \"win32\":\n+ print('Windows%s' % text2)\n+ # TODO\n+ else:\n+ print(_platform + text2)\n \n def clear_all(printable=True):\n \"\"\"Clears all the placeholder variables of keep prob,\n", "issue": "Issues with ops.exit_tf function\nSo far I've 2 issues with this function :\r\n- ops.exit_tf() returns an error because a session is expected as argument.\r\n- ops.exit_tf(sess) returns \"NameError: name 'exit' is not defined\" when launched from an IPython console - in my case it's Spyder's internal IPython console (tested both on Mac and Windows)\r\n\r\nBoth issue are easy to solve :\r\n- add `if sess != None:` before `sess.close()`\r\n- use `from sys import exit as _exit` to avoid whatever is the interference that's throwing the error\r\n\r\nBefore I propose a pull request, I just wanted to check that I'm not misusing the function : I tried to use the function without an argument to easly exit tensorboard (which is a nice feature) and I'm launching it from IPyton instead of the terminal because it's seems like a usefull function to be able to include in a script (and i run my scripts from Spyder)\n", "before_files": [{"content": "#! /usr/bin/python\n# -*- coding: utf8 -*-\n\n\n\n\nimport tensorflow as tf\nimport os\nimport sys\nfrom sys import platform as _platform\n\n\ndef exit_tf(sess=None):\n \"\"\"Close tensorboard and nvidia-process if available\n\n Parameters\n ----------\n sess : a session instance of TensorFlow\n TensorFlow session\n \"\"\"\n text = \"[tl] Close tensorboard and nvidia-process if available\"\n sess.close()\n # import time\n # time.sleep(2)\n if _platform == \"linux\" or _platform == \"linux2\":\n print('linux: %s' % text)\n os.system('nvidia-smi')\n os.system('fuser 6006/tcp -k') # kill tensorboard 6006\n os.system(\"nvidia-smi | grep python |awk '{print $3}'|xargs kill\") # kill all nvidia-smi python process\n elif _platform == \"darwin\":\n print('OS X: %s' % text)\n os.system(\"lsof -i tcp:6006 | grep -v PID | awk '{print $2}' | xargs kill\") # kill tensorboard 6006\n elif _platform == \"win32\":\n print('Windows: %s' % text)\n else:\n print(_platform)\n exit()\n\ndef clear_all(printable=True):\n \"\"\"Clears all the placeholder variables of keep prob,\n including keeping probabilities of all dropout, denoising, dropconnect etc.\n\n Parameters\n ----------\n printable : boolean\n If True, print all deleted variables.\n \"\"\"\n print('clear all .....................................')\n gl = globals().copy()\n for var in gl:\n if var[0] == '_': continue\n if 'func' in str(globals()[var]): continue\n if 'module' in str(globals()[var]): continue\n if 'class' in str(globals()[var]): continue\n\n if printable:\n print(\" clear_all ------- %s\" % str(globals()[var]))\n\n del globals()[var]\n\n# def clear_all2(vars, printable=True):\n# \"\"\"\n# The :function:`clear_all()` Clears all the placeholder variables of keep prob,\n# including keeping probabilities of all dropout, denoising, dropconnect\n# Parameters\n# ----------\n# printable : if True, print all deleted variables.\n# \"\"\"\n# print('clear all .....................................')\n# for var in vars:\n# if var[0] == '_': continue\n# if 'func' in str(var): continue\n# if 'module' in str(var): continue\n# if 'class' in str(var): continue\n#\n# if printable:\n# print(\" clear_all ------- %s\" % str(var))\n#\n# del var\n\ndef set_gpu_fraction(sess=None, gpu_fraction=0.3):\n \"\"\"Set the GPU memory fraction for the application.\n\n Parameters\n ----------\n sess : a session instance of TensorFlow\n TensorFlow session\n gpu_fraction : a float\n Fraction of GPU memory, (0 ~ 1]\n\n References\n ----------\n - `TensorFlow using GPU <https://www.tensorflow.org/versions/r0.9/how_tos/using_gpu/index.html>`_\n \"\"\"\n print(\" tensorlayer: GPU MEM Fraction %f\" % gpu_fraction)\n gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_fraction)\n sess = tf.Session(config = tf.ConfigProto(gpu_options = gpu_options))\n return sess\n\n\n\n\n\ndef disable_print():\n \"\"\"Disable console output, ``suppress_stdout`` is recommended.\n\n Examples\n ---------\n >>> print(\"You can see me\")\n >>> tl.ops.disable_print()\n >>> print(\" You can't see me\")\n >>> tl.ops.enable_print()\n >>> print(\"You can see me\")\n \"\"\"\n # sys.stdout = os.devnull # this one kill the process\n sys.stdout = None\n sys.stderr = os.devnull\n\ndef enable_print():\n \"\"\"Enable console output, ``suppress_stdout`` is recommended.\n\n Examples\n --------\n - see tl.ops.disable_print()\n \"\"\"\n sys.stdout = sys.__stdout__\n sys.stderr = sys.__stderr__\n\n\n# class temporary_disable_print:\n# \"\"\"Temporarily disable console output.\n#\n# Examples\n# ---------\n# >>> print(\"You can see me\")\n# >>> with tl.ops.temporary_disable_print() as t:\n# >>> print(\"You can't see me\")\n# >>> print(\"You can see me\")\n# \"\"\"\n# def __init__(self):\n# pass\n# def __enter__(self):\n# sys.stdout = None\n# sys.stderr = os.devnull\n# def __exit__(self, type, value, traceback):\n# sys.stdout = sys.__stdout__\n# sys.stderr = sys.__stderr__\n# return isinstance(value, TypeError)\n\n\nfrom contextlib import contextmanager\n@contextmanager\ndef suppress_stdout():\n \"\"\"Temporarily disable console output.\n\n Examples\n ---------\n >>> print(\"You can see me\")\n >>> with tl.ops.suppress_stdout():\n >>> print(\"You can't see me\")\n >>> print(\"You can see me\")\n\n References\n -----------\n - `stackoverflow <http://stackoverflow.com/questions/2125702/how-to-suppress-console-output-in-python>`_\n \"\"\"\n with open(os.devnull, \"w\") as devnull:\n old_stdout = sys.stdout\n sys.stdout = devnull\n try:\n yield\n finally:\n sys.stdout = old_stdout\n\n\n\ndef get_site_packages_directory():\n \"\"\"Print and return the site-packages directory.\n\n Examples\n ---------\n >>> loc = tl.ops.get_site_packages_directory()\n \"\"\"\n import site\n try:\n loc = site.getsitepackages()\n print(\" tl.ops : site-packages in \", loc)\n return loc\n except:\n print(\" tl.ops : Cannot find package dir from virtual environment\")\n return False\n\n\n\ndef empty_trash():\n \"\"\"Empty trash folder.\n\n \"\"\"\n text = \"[tl] Empty the trash\"\n if _platform == \"linux\" or _platform == \"linux2\":\n print('linux: %s' % text)\n os.system(\"rm -rf ~/.local/share/Trash/*\")\n elif _platform == \"darwin\":\n print('OS X: %s' % text)\n os.system(\"sudo rm -rf ~/.Trash/*\")\n elif _platform == \"win32\":\n print('Windows: %s' % text)\n try:\n os.system(\"rd /s c:\\$Recycle.Bin\") # Windows 7 or Server 2008\n except:\n pass\n try:\n os.system(\"rd /s c:\\recycler\") # Windows XP, Vista, or Server 2003\n except:\n pass\n else:\n print(_platform)\n\n#\n", "path": "tensorlayer/ops.py"}]} | 2,824 | 886 |
gh_patches_debug_21467 | rasdani/github-patches | git_diff | DataDog__dd-agent-333 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Allow strings to be elements in dogstatsd sets
Right now it only counts numbers.
</issue>
<code>
[start of aggregator.py]
1 import logging
2 from time import time
3
4
5 logger = logging.getLogger(__name__)
6
7
8 class Infinity(Exception): pass
9 class UnknownValue(Exception): pass
10
11 class Metric(object):
12 """
13 A base metric class that accepts points, slices them into time intervals
14 and performs roll-ups within those intervals.
15 """
16
17 def sample(self, value, sample_rate):
18 """ Add a point to the given metric. """
19 raise NotImplementedError()
20
21 def flush(self, timestamp, interval):
22 """ Flush all metrics up to the given timestamp. """
23 raise NotImplementedError()
24
25
26 class Gauge(Metric):
27 """ A metric that tracks a value at particular points in time. """
28
29 def __init__(self, formatter, name, tags, hostname, device_name):
30 self.formatter = formatter
31 self.name = name
32 self.value = None
33 self.tags = tags
34 self.hostname = hostname
35 self.device_name = device_name
36 self.last_sample_time = None
37
38 def sample(self, value, sample_rate):
39 self.value = value
40 self.last_sample_time = time()
41
42 def flush(self, timestamp, interval):
43 if self.value is not None:
44 res = [self.formatter(
45 metric=self.name,
46 timestamp=timestamp,
47 value=self.value,
48 tags=self.tags,
49 hostname=self.hostname,
50 device_name=self.device_name
51 )]
52 self.value = None
53 return res
54
55 return []
56
57
58 class Counter(Metric):
59 """ A metric that tracks a counter value. """
60
61 def __init__(self, formatter, name, tags, hostname, device_name):
62 self.formatter = formatter
63 self.name = name
64 self.value = 0
65 self.tags = tags
66 self.hostname = hostname
67 self.device_name = device_name
68
69 def sample(self, value, sample_rate):
70 self.value += value * int(1 / sample_rate)
71 self.last_sample_time = time()
72
73 def flush(self, timestamp, interval):
74 try:
75 value = self.value / interval
76 return [self.formatter(
77 metric=self.name,
78 value=value,
79 timestamp=timestamp,
80 tags=self.tags,
81 hostname=self.hostname,
82 device_name=self.device_name
83 )]
84 finally:
85 self.value = 0
86
87
88 class Histogram(Metric):
89 """ A metric to track the distribution of a set of values. """
90
91 def __init__(self, formatter, name, tags, hostname, device_name):
92 self.formatter = formatter
93 self.name = name
94 self.count = 0
95 self.samples = []
96 self.percentiles = [0.95]
97 self.tags = tags
98 self.hostname = hostname
99 self.device_name = device_name
100
101 def sample(self, value, sample_rate):
102 self.count += int(1 / sample_rate)
103 self.samples.append(value)
104 self.last_sample_time = time()
105
106 def flush(self, ts, interval):
107 if not self.count:
108 return []
109
110 self.samples.sort()
111 length = len(self.samples)
112
113 max_ = self.samples[-1]
114 med = self.samples[int(round(length/2 - 1))]
115 avg = sum(self.samples) / float(length)
116
117 metric_aggrs = [
118 ('max', max_),
119 ('median', med),
120 ('avg', avg),
121 ('count', self.count/interval)
122 ]
123
124 metrics = [self.formatter(
125 hostname=self.hostname,
126 device_name=self.device_name,
127 tags=self.tags,
128 metric='%s.%s' % (self.name, suffix),
129 value=value,
130 timestamp=ts
131 ) for suffix, value in metric_aggrs
132 ]
133
134 for p in self.percentiles:
135 val = self.samples[int(round(p * length - 1))]
136 name = '%s.%spercentile' % (self.name, int(p * 100))
137 metrics.append(self.formatter(
138 hostname=self.hostname,
139 tags=self.tags,
140 metric=name,
141 value=val,
142 timestamp=ts
143 ))
144
145 # Reset our state.
146 self.samples = []
147 self.count = 0
148
149 return metrics
150
151
152 class Set(Metric):
153 """ A metric to track the number of unique elements in a set. """
154
155 def __init__(self, formatter, name, tags, hostname, device_name):
156 self.formatter = formatter
157 self.name = name
158 self.tags = tags
159 self.hostname = hostname
160 self.device_name = device_name
161 self.values = set()
162
163 def sample(self, value, sample_rate):
164 self.values.add(value)
165 self.last_sample_time = time()
166
167 def flush(self, timestamp, interval):
168 if not self.values:
169 return []
170 try:
171 return [self.formatter(
172 hostname=self.hostname,
173 device_name=self.device_name,
174 tags=self.tags,
175 metric=self.name,
176 value=len(self.values),
177 timestamp=timestamp
178 )]
179 finally:
180 self.values = set()
181
182
183 class Rate(Metric):
184 """ Track the rate of metrics over each flush interval """
185
186 def __init__(self, formatter, name, tags, hostname, device_name):
187 self.formatter = formatter
188 self.name = name
189 self.tags = tags
190 self.hostname = hostname
191 self.device_name = device_name
192 self.samples = []
193
194 def sample(self, value, sample_rate):
195 ts = time()
196 self.samples.append((int(ts), value))
197 self.last_sample_time = ts
198
199 def _rate(self, sample1, sample2):
200 interval = sample2[0] - sample1[0]
201 if interval == 0:
202 logger.warn('Metric %s has an interval of 0. Not flushing.' % self.name)
203 raise Infinity()
204
205 delta = sample2[1] - sample1[1]
206 if delta < 0:
207 logger.warn('Metric %s has a rate < 0. Not flushing.' % self.name)
208 raise UnknownValue()
209
210 return (delta / interval)
211
212 def flush(self, timestamp, interval):
213 if len(self.samples) < 2:
214 return []
215 try:
216 try:
217 val = self._rate(self.samples[-2], self.samples[-1])
218 except:
219 return []
220
221 return [self.formatter(
222 hostname=self.hostname,
223 device_name=self.device_name,
224 tags=self.tags,
225 metric=self.name,
226 value=val,
227 timestamp=timestamp
228 )]
229 finally:
230 self.samples = self.samples[-1:]
231
232
233
234 class MetricsAggregator(object):
235 """
236 A metric aggregator class.
237 """
238
239 def __init__(self, hostname, interval=1.0, expiry_seconds=300, formatter=None):
240 self.metrics = {}
241 self.total_count = 0
242 self.count = 0
243 self.metric_type_to_class = {
244 'g': Gauge,
245 'c': Counter,
246 'h': Histogram,
247 'ms' : Histogram,
248 's' : Set,
249 '_dd-r': Rate,
250 }
251 self.hostname = hostname
252 self.expiry_seconds = expiry_seconds
253 self.formatter = formatter or self.api_formatter
254 self.interval = float(interval)
255
256 def packets_per_second(self, interval):
257 return round(float(self.count)/interval, 2)
258
259 def submit_packets(self, packets):
260
261 for packet in packets.split("\n"):
262 self.count += 1
263 # We can have colons in tags, so split once.
264 name_and_metadata = packet.split(':', 1)
265
266 if not packet.strip():
267 continue
268
269 if len(name_and_metadata) != 2:
270 raise Exception('Unparseable packet: %s' % packet)
271
272 name = name_and_metadata[0]
273 metadata = name_and_metadata[1].split('|')
274
275 if len(metadata) < 2:
276 raise Exception('Unparseable packet: %s' % packet)
277
278 # Try to cast as an int first to avoid precision issues, then as a
279 # float.
280 try:
281 value = int(metadata[0])
282 except ValueError:
283 try:
284 value = float(metadata[0])
285 except ValueError:
286 raise Exception('Metric value must be a number: %s, %s' % name, metadata[0])
287
288 # Parse the optional values - sample rate & tags.
289 sample_rate = 1
290 tags = None
291 for m in metadata[2:]:
292 # Parse the sample rate
293 if m[0] == '@':
294 sample_rate = float(m[1:])
295 assert 0 <= sample_rate <= 1
296 elif m[0] == '#':
297 tags = tuple(sorted(m[1:].split(',')))
298
299 # Submit the metric
300 mtype = metadata[1]
301 self.submit_metric(name, value, mtype, tags=tags, sample_rate=sample_rate)
302
303 def submit_metric(self, name, value, mtype, tags=None, hostname=None,
304 device_name=None, timestamp=None, sample_rate=1):
305 # Avoid calling extra functions to dedupe tags if there are none
306 if tags is None:
307 context = (name, tuple(), hostname, device_name)
308 else:
309 context = (name, tuple(sorted(set(tags))), hostname, device_name)
310 if context not in self.metrics:
311 metric_class = self.metric_type_to_class[mtype]
312 self.metrics[context] = metric_class(self.formatter, name, tags,
313 hostname or self.hostname, device_name)
314 self.metrics[context].sample(value, sample_rate)
315
316 def gauge(self, name, value, tags=None, hostname=None, device_name=None, timestamp=None):
317 self.submit_metric(name, value, 'g', tags, hostname, device_name, timestamp)
318
319 def increment(self, name, value=1, tags=None, hostname=None, device_name=None):
320 self.submit_metric(name, value, 'c', tags, hostname, device_name)
321
322 def decrement(self, name, value=-1, tags=None, hostname=None, device_name=None):
323 self.submit_metric(name, value, 'c', tags, hostname, device_name)
324
325 def rate(self, name, value, tags=None, hostname=None, device_name=None):
326 self.submit_metric(name, value, '_dd-r', tags, hostname, device_name)
327
328 def histogram(self, name, value, tags=None, hostname=None, device_name=None):
329 self.submit_metric(name, value, 'h', tags, hostname, device_name)
330
331 def set(self, name, value, tags=None, hostname=None, device_name=None):
332 self.submit_metric(name, value, 's', tags, hostname, device_name)
333
334 def flush(self):
335 timestamp = time()
336 expiry_timestamp = timestamp - self.expiry_seconds
337
338 # Flush points and remove expired metrics. We mutate this dictionary
339 # while iterating so don't use an iterator.
340 metrics = []
341 for context, metric in self.metrics.items():
342 if metric.last_sample_time < expiry_timestamp:
343 logger.debug("%s hasn't been submitted in %ss. Expiring." % (context, self.expiry_seconds))
344 del self.metrics[context]
345 else:
346 metrics += metric.flush(timestamp, self.interval)
347
348 # Save some stats.
349 logger.debug("received %s payloads since last flush" % self.count)
350 self.total_count += self.count
351 self.count = 0
352 return metrics
353
354 def send_packet_count(self, metric_name):
355 self.submit_metric(metric_name, self.count, 'g')
356
357 def api_formatter(self, metric, value, timestamp, tags, hostname, device_name=None):
358 return {
359 'metric' : metric,
360 'points' : [(timestamp, value)],
361 'tags' : tags,
362 'host' : hostname,
363 'device_name': device_name
364 }
365
[end of aggregator.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/aggregator.py b/aggregator.py
--- a/aggregator.py
+++ b/aggregator.py
@@ -236,6 +236,9 @@
A metric aggregator class.
"""
+ # Types of metrics that allow strings
+ ALLOW_STRINGS = ['s', ]
+
def __init__(self, hostname, interval=1.0, expiry_seconds=300, formatter=None):
self.metrics = {}
self.total_count = 0
@@ -283,7 +286,13 @@
try:
value = float(metadata[0])
except ValueError:
- raise Exception('Metric value must be a number: %s, %s' % name, metadata[0])
+
+ # If the data type is Set, we will allow strings
+ if metadata[1] in self.ALLOW_STRINGS:
+ value = metadata[0]
+ else:
+ # Otherwise, raise an error saying it must be a number
+ raise Exception('Metric value must be a number: %s, %s' % (name, metadata[0]))
# Parse the optional values - sample rate & tags.
sample_rate = 1
| {"golden_diff": "diff --git a/aggregator.py b/aggregator.py\n--- a/aggregator.py\n+++ b/aggregator.py\n@@ -236,6 +236,9 @@\n A metric aggregator class.\n \"\"\"\n \n+ # Types of metrics that allow strings\n+ ALLOW_STRINGS = ['s', ]\n+\n def __init__(self, hostname, interval=1.0, expiry_seconds=300, formatter=None):\n self.metrics = {}\n self.total_count = 0\n@@ -283,7 +286,13 @@\n try:\n value = float(metadata[0])\n except ValueError:\n- raise Exception('Metric value must be a number: %s, %s' % name, metadata[0])\n+\n+ # If the data type is Set, we will allow strings\n+ if metadata[1] in self.ALLOW_STRINGS:\n+ value = metadata[0]\n+ else:\n+ # Otherwise, raise an error saying it must be a number\n+ raise Exception('Metric value must be a number: %s, %s' % (name, metadata[0]))\n \n # Parse the optional values - sample rate & tags.\n sample_rate = 1\n", "issue": "Allow strings to be elements in dogstatsd sets\nRight now it only counts numbers.\n\n", "before_files": [{"content": "import logging\nfrom time import time\n\n\nlogger = logging.getLogger(__name__)\n\n\nclass Infinity(Exception): pass\nclass UnknownValue(Exception): pass\n\nclass Metric(object):\n \"\"\"\n A base metric class that accepts points, slices them into time intervals\n and performs roll-ups within those intervals.\n \"\"\"\n\n def sample(self, value, sample_rate):\n \"\"\" Add a point to the given metric. \"\"\"\n raise NotImplementedError()\n\n def flush(self, timestamp, interval):\n \"\"\" Flush all metrics up to the given timestamp. \"\"\"\n raise NotImplementedError()\n\n\nclass Gauge(Metric):\n \"\"\" A metric that tracks a value at particular points in time. \"\"\"\n\n def __init__(self, formatter, name, tags, hostname, device_name):\n self.formatter = formatter\n self.name = name\n self.value = None\n self.tags = tags\n self.hostname = hostname\n self.device_name = device_name\n self.last_sample_time = None\n\n def sample(self, value, sample_rate):\n self.value = value\n self.last_sample_time = time()\n\n def flush(self, timestamp, interval):\n if self.value is not None:\n res = [self.formatter(\n metric=self.name,\n timestamp=timestamp,\n value=self.value,\n tags=self.tags,\n hostname=self.hostname,\n device_name=self.device_name\n )]\n self.value = None\n return res\n\n return []\n\n\nclass Counter(Metric):\n \"\"\" A metric that tracks a counter value. \"\"\"\n\n def __init__(self, formatter, name, tags, hostname, device_name):\n self.formatter = formatter\n self.name = name\n self.value = 0\n self.tags = tags\n self.hostname = hostname\n self.device_name = device_name\n\n def sample(self, value, sample_rate):\n self.value += value * int(1 / sample_rate)\n self.last_sample_time = time()\n\n def flush(self, timestamp, interval):\n try:\n value = self.value / interval\n return [self.formatter(\n metric=self.name,\n value=value,\n timestamp=timestamp,\n tags=self.tags,\n hostname=self.hostname,\n device_name=self.device_name\n )]\n finally:\n self.value = 0\n\n\nclass Histogram(Metric):\n \"\"\" A metric to track the distribution of a set of values. \"\"\"\n\n def __init__(self, formatter, name, tags, hostname, device_name):\n self.formatter = formatter\n self.name = name\n self.count = 0\n self.samples = []\n self.percentiles = [0.95]\n self.tags = tags\n self.hostname = hostname\n self.device_name = device_name\n\n def sample(self, value, sample_rate):\n self.count += int(1 / sample_rate)\n self.samples.append(value)\n self.last_sample_time = time()\n\n def flush(self, ts, interval):\n if not self.count:\n return []\n\n self.samples.sort()\n length = len(self.samples)\n\n max_ = self.samples[-1]\n med = self.samples[int(round(length/2 - 1))]\n avg = sum(self.samples) / float(length)\n\n metric_aggrs = [\n ('max', max_),\n ('median', med),\n ('avg', avg),\n ('count', self.count/interval)\n ]\n\n metrics = [self.formatter(\n hostname=self.hostname,\n device_name=self.device_name,\n tags=self.tags,\n metric='%s.%s' % (self.name, suffix),\n value=value,\n timestamp=ts\n ) for suffix, value in metric_aggrs\n ]\n\n for p in self.percentiles:\n val = self.samples[int(round(p * length - 1))]\n name = '%s.%spercentile' % (self.name, int(p * 100))\n metrics.append(self.formatter(\n hostname=self.hostname,\n tags=self.tags,\n metric=name,\n value=val,\n timestamp=ts\n ))\n\n # Reset our state.\n self.samples = []\n self.count = 0\n\n return metrics\n\n\nclass Set(Metric):\n \"\"\" A metric to track the number of unique elements in a set. \"\"\"\n\n def __init__(self, formatter, name, tags, hostname, device_name):\n self.formatter = formatter\n self.name = name\n self.tags = tags\n self.hostname = hostname\n self.device_name = device_name\n self.values = set()\n\n def sample(self, value, sample_rate):\n self.values.add(value)\n self.last_sample_time = time()\n\n def flush(self, timestamp, interval):\n if not self.values:\n return []\n try:\n return [self.formatter(\n hostname=self.hostname,\n device_name=self.device_name,\n tags=self.tags,\n metric=self.name,\n value=len(self.values),\n timestamp=timestamp\n )]\n finally:\n self.values = set()\n\n\nclass Rate(Metric):\n \"\"\" Track the rate of metrics over each flush interval \"\"\"\n\n def __init__(self, formatter, name, tags, hostname, device_name):\n self.formatter = formatter\n self.name = name\n self.tags = tags\n self.hostname = hostname\n self.device_name = device_name\n self.samples = []\n\n def sample(self, value, sample_rate):\n ts = time()\n self.samples.append((int(ts), value))\n self.last_sample_time = ts\n\n def _rate(self, sample1, sample2):\n interval = sample2[0] - sample1[0]\n if interval == 0:\n logger.warn('Metric %s has an interval of 0. Not flushing.' % self.name)\n raise Infinity()\n\n delta = sample2[1] - sample1[1]\n if delta < 0:\n logger.warn('Metric %s has a rate < 0. Not flushing.' % self.name)\n raise UnknownValue()\n\n return (delta / interval)\n\n def flush(self, timestamp, interval):\n if len(self.samples) < 2:\n return []\n try:\n try:\n val = self._rate(self.samples[-2], self.samples[-1])\n except:\n return []\n\n return [self.formatter(\n hostname=self.hostname,\n device_name=self.device_name,\n tags=self.tags,\n metric=self.name,\n value=val,\n timestamp=timestamp\n )]\n finally:\n self.samples = self.samples[-1:]\n\n\n\nclass MetricsAggregator(object):\n \"\"\"\n A metric aggregator class.\n \"\"\"\n\n def __init__(self, hostname, interval=1.0, expiry_seconds=300, formatter=None):\n self.metrics = {}\n self.total_count = 0\n self.count = 0\n self.metric_type_to_class = {\n 'g': Gauge,\n 'c': Counter,\n 'h': Histogram,\n 'ms' : Histogram,\n 's' : Set,\n '_dd-r': Rate,\n }\n self.hostname = hostname\n self.expiry_seconds = expiry_seconds\n self.formatter = formatter or self.api_formatter\n self.interval = float(interval)\n\n def packets_per_second(self, interval):\n return round(float(self.count)/interval, 2)\n\n def submit_packets(self, packets):\n\n for packet in packets.split(\"\\n\"):\n self.count += 1\n # We can have colons in tags, so split once.\n name_and_metadata = packet.split(':', 1)\n\n if not packet.strip():\n continue\n\n if len(name_and_metadata) != 2:\n raise Exception('Unparseable packet: %s' % packet)\n\n name = name_and_metadata[0]\n metadata = name_and_metadata[1].split('|')\n\n if len(metadata) < 2:\n raise Exception('Unparseable packet: %s' % packet)\n\n # Try to cast as an int first to avoid precision issues, then as a\n # float.\n try:\n value = int(metadata[0])\n except ValueError:\n try:\n value = float(metadata[0])\n except ValueError:\n raise Exception('Metric value must be a number: %s, %s' % name, metadata[0])\n\n # Parse the optional values - sample rate & tags.\n sample_rate = 1\n tags = None\n for m in metadata[2:]:\n # Parse the sample rate\n if m[0] == '@':\n sample_rate = float(m[1:])\n assert 0 <= sample_rate <= 1\n elif m[0] == '#':\n tags = tuple(sorted(m[1:].split(',')))\n\n # Submit the metric\n mtype = metadata[1]\n self.submit_metric(name, value, mtype, tags=tags, sample_rate=sample_rate)\n\n def submit_metric(self, name, value, mtype, tags=None, hostname=None,\n device_name=None, timestamp=None, sample_rate=1):\n # Avoid calling extra functions to dedupe tags if there are none\n if tags is None:\n context = (name, tuple(), hostname, device_name)\n else:\n context = (name, tuple(sorted(set(tags))), hostname, device_name)\n if context not in self.metrics:\n metric_class = self.metric_type_to_class[mtype]\n self.metrics[context] = metric_class(self.formatter, name, tags,\n hostname or self.hostname, device_name)\n self.metrics[context].sample(value, sample_rate)\n\n def gauge(self, name, value, tags=None, hostname=None, device_name=None, timestamp=None):\n self.submit_metric(name, value, 'g', tags, hostname, device_name, timestamp)\n\n def increment(self, name, value=1, tags=None, hostname=None, device_name=None):\n self.submit_metric(name, value, 'c', tags, hostname, device_name)\n\n def decrement(self, name, value=-1, tags=None, hostname=None, device_name=None):\n self.submit_metric(name, value, 'c', tags, hostname, device_name)\n\n def rate(self, name, value, tags=None, hostname=None, device_name=None):\n self.submit_metric(name, value, '_dd-r', tags, hostname, device_name)\n\n def histogram(self, name, value, tags=None, hostname=None, device_name=None):\n self.submit_metric(name, value, 'h', tags, hostname, device_name)\n\n def set(self, name, value, tags=None, hostname=None, device_name=None):\n self.submit_metric(name, value, 's', tags, hostname, device_name)\n\n def flush(self):\n timestamp = time()\n expiry_timestamp = timestamp - self.expiry_seconds\n\n # Flush points and remove expired metrics. We mutate this dictionary\n # while iterating so don't use an iterator.\n metrics = []\n for context, metric in self.metrics.items():\n if metric.last_sample_time < expiry_timestamp:\n logger.debug(\"%s hasn't been submitted in %ss. Expiring.\" % (context, self.expiry_seconds))\n del self.metrics[context]\n else:\n metrics += metric.flush(timestamp, self.interval)\n\n # Save some stats.\n logger.debug(\"received %s payloads since last flush\" % self.count)\n self.total_count += self.count\n self.count = 0\n return metrics\n\n def send_packet_count(self, metric_name):\n self.submit_metric(metric_name, self.count, 'g')\n\n def api_formatter(self, metric, value, timestamp, tags, hostname, device_name=None):\n return {\n 'metric' : metric,\n 'points' : [(timestamp, value)],\n 'tags' : tags,\n 'host' : hostname,\n 'device_name': device_name\n }\n", "path": "aggregator.py"}]} | 4,067 | 264 |
gh_patches_debug_3817 | rasdani/github-patches | git_diff | opsdroid__opsdroid-1220 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Slack connector crashes after running dance several times
# Description
Slack connector crashes after running dance several times in a row
## Steps to Reproduce
Launch opsdroid with slack connector configured with bot token
go the channel connected in and run dance 3+ times in a row
## Expected Functionality
Opsdroid keeps running fine
## Experienced Functionality
Opsdroid crashes with the following error:
```
ERROR slack.rtm.client: When calling '#process_message()' in the 'opsdroid.connector.slack' module the following error was raised: 'user'
Traceback (most recent call last):
File "C:\Users\koe4945\desktop\git\personal\ops\venv\Scripts\opsdroid-script.py", line 11, in <module>
load_entry_point('opsdroid', 'console_scripts', 'opsdroid')()
File "c:\users\koe4945\desktop\git\personal\ops\venv\lib\site-packages\click\core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "c:\users\koe4945\desktop\git\personal\ops\venv\lib\site-packages\click\core.py", line 717, in main
rv = self.invoke(ctx)
File "c:\users\koe4945\desktop\git\personal\ops\venv\lib\site-packages\click\core.py", line 1137, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "c:\users\koe4945\desktop\git\personal\ops\venv\lib\site-packages\click\core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "c:\users\koe4945\desktop\git\personal\ops\venv\lib\site-packages\click\core.py", line 555, in invoke
return callback(*args, **kwargs)
File "c:\users\koe4945\desktop\git\personal\ops\opsdroid\opsdroid\cli\start.py", line 31, in start
opsdroid.run()
File "c:\users\koe4945\desktop\git\personal\ops\opsdroid\opsdroid\core.py", line 161, in run
self.eventloop.run_until_complete(asyncio.gather(*pending))
File "C:\Users\koe4945\AppData\Local\Programs\Python\Python37\lib\asyncio\base_events.py", line 584, in run_until_complete
return future.result()
File "c:\users\koe4945\desktop\git\personal\ops\python-slackclient\slack\rtm\client.py", line 339, in _connect_and_read
await self._read_messages()
File "c:\users\koe4945\desktop\git\personal\ops\python-slackclient\slack\rtm\client.py", line 390, in _read_messages
await self._dispatch_event(event, data=payload)
File "c:\users\koe4945\desktop\git\personal\ops\python-slackclient\slack\rtm\client.py", line 437, in _dispatch_event
rtm_client=self, web_client=self._web_client, data=data
File "c:\users\koe4945\desktop\git\personal\ops\opsdroid\opsdroid\connector\slack\__init__.py", line 104, in process_message
user_info = await self.lookup_username(message["user"])
KeyError: 'user'
ERROR: Unhandled exception in opsdroid, exiting...
```
## Versions
- **Opsdroid version:** v0.16.0+62.g620590f
- **Python version:** 3.7.3
- **OS/Docker version:** Windows 10
## Configuration File
Please include your version of the configuration file below.
```yaml
connectors:
- name: slack
# required
api-token: "[...bot token...]"
```
## Additional Details
Any other details you wish to include such as screenshots, console messages, etc.
</issue>
<code>
[start of opsdroid/connector/slack/__init__.py]
1 """A connector for Slack."""
2 import logging
3 import re
4
5 import slack
6 from emoji import demojize
7
8 from opsdroid.connector import Connector, register_event
9 from opsdroid.events import Message, Reaction
10 from opsdroid.connector.slack.events import Blocks
11
12
13 _LOGGER = logging.getLogger(__name__)
14
15
16 class ConnectorSlack(Connector):
17 """A connector for Slack."""
18
19 def __init__(self, config, opsdroid=None):
20 """Create the connector."""
21 super().__init__(config, opsdroid=opsdroid)
22 _LOGGER.debug(_("Starting Slack connector"))
23 self.name = "slack"
24 self.default_target = config.get("default-room", "#general")
25 self.icon_emoji = config.get("icon-emoji", ":robot_face:")
26 self.token = config["api-token"]
27 self.timeout = config.get("connect-timeout", 10)
28 self.slack = slack.WebClient(token=self.token, run_async=True)
29 self.slack_rtm = slack.RTMClient(token=self.token, run_async=True)
30 self.websocket = None
31 self.bot_name = config.get("bot-name", "opsdroid")
32 self.auth_info = None
33 self.user_info = None
34 self.bot_id = None
35 self.known_users = {}
36 self.keepalive = None
37 self.reconnecting = False
38 self.listening = True
39 self._message_id = 0
40
41 # Register callbacks
42 slack.RTMClient.on(event="message", callback=self.process_message)
43
44 async def connect(self):
45 """Connect to the chat service."""
46 _LOGGER.info(_("Connecting to Slack"))
47
48 try:
49 # The slack library recommends you call `self.slack_rtm.start()`` here but it
50 # seems to mess with the event loop's signal handlers which breaks opsdroid.
51 # Therefore we need to directly call the private `_connect_and_read` method
52 # instead. This method also blocks so we need to dispatch it to the loop as a task.
53 self.opsdroid.eventloop.create_task(self.slack_rtm._connect_and_read())
54
55 self.auth_info = (await self.slack.api_call("auth.test")).data
56 self.user_info = (
57 await self.slack.api_call(
58 "users.info",
59 http_verb="GET",
60 params={"user": self.auth_info["user_id"]},
61 )
62 ).data
63 self.bot_id = self.user_info["user"]["profile"]["bot_id"]
64
65 _LOGGER.debug(_("Connected as %s"), self.bot_name)
66 _LOGGER.debug(_("Using icon %s"), self.icon_emoji)
67 _LOGGER.debug(_("Default room is %s"), self.default_target)
68 _LOGGER.info(_("Connected successfully"))
69 except slack.errors.SlackApiError as error:
70 _LOGGER.error(
71 _(
72 "Unable to connect to Slack due to %s - "
73 "The Slack Connector will not be available."
74 ),
75 error,
76 )
77 except Exception:
78 await self.disconnect()
79 raise
80
81 async def disconnect(self):
82 """Disconnect from Slack."""
83 await self.slack_rtm.stop()
84 self.listening = False
85
86 async def listen(self):
87 """Listen for and parse new messages."""
88
89 async def process_message(self, **payload):
90 """Process a raw message and pass it to the parser."""
91 message = payload["data"]
92
93 # Ignore own messages
94 if (
95 "subtype" in message
96 and message["subtype"] == "bot_message"
97 and message["bot_id"] == self.bot_id
98 ):
99 return
100
101 # Lookup username
102 _LOGGER.debug(_("Looking up sender username"))
103 try:
104 user_info = await self.lookup_username(message["user"])
105 except ValueError:
106 return
107
108 # Replace usernames in the message
109 _LOGGER.debug(_("Replacing userids in message with usernames"))
110 message["text"] = await self.replace_usernames(message["text"])
111
112 await self.opsdroid.parse(
113 Message(
114 message["text"],
115 user_info["name"],
116 message["channel"],
117 self,
118 raw_event=message,
119 )
120 )
121
122 @register_event(Message)
123 async def send_message(self, message):
124 """Respond with a message."""
125 _LOGGER.debug(
126 _("Responding with: '%s' in room %s"), message.text, message.target
127 )
128 await self.slack.api_call(
129 "chat.postMessage",
130 data={
131 "channel": message.target,
132 "text": message.text,
133 "as_user": False,
134 "username": self.bot_name,
135 "icon_emoji": self.icon_emoji,
136 },
137 )
138
139 @register_event(Blocks)
140 async def send_blocks(self, blocks):
141 """Respond with structured blocks."""
142 _LOGGER.debug(
143 _("Responding with interactive blocks in room %s"), blocks.target
144 )
145 await self.slack.api_call(
146 "chat.postMessage",
147 data={
148 "channel": blocks.target,
149 "username": self.bot_name,
150 "blocks": blocks.blocks,
151 "icon_emoji": self.icon_emoji,
152 },
153 )
154
155 @register_event(Reaction)
156 async def send_reaction(self, reaction):
157 """React to a message."""
158 emoji = demojize(reaction.emoji).replace(":", "")
159 _LOGGER.debug(_("Reacting with: %s"), emoji)
160 try:
161 await self.slack.api_call(
162 "reactions.add",
163 data={
164 "name": emoji,
165 "channel": reaction.target,
166 "timestamp": reaction.linked_event.raw_event["ts"],
167 },
168 )
169 except slack.errors.SlackApiError as error:
170 if "invalid_name" in str(error):
171 _LOGGER.warning(_("Slack does not support the emoji %s"), emoji)
172 else:
173 raise
174
175 async def lookup_username(self, userid):
176 """Lookup a username and cache it."""
177 if userid in self.known_users:
178 user_info = self.known_users[userid]
179 else:
180 response = await self.slack.users_info(user=userid)
181 user_info = response.data["user"]
182 if isinstance(user_info, dict):
183 self.known_users[userid] = user_info
184 else:
185 raise ValueError("Returned user is not a dict.")
186 return user_info
187
188 async def replace_usernames(self, message):
189 """Replace User ID with username in message text."""
190 userids = re.findall(r"\<\@([A-Z0-9]+)(?:\|.+)?\>", message)
191 for userid in userids:
192 user_info = await self.lookup_username(userid)
193 message = message.replace(
194 "<@{userid}>".format(userid=userid), user_info["name"]
195 )
196 return message
197
[end of opsdroid/connector/slack/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/opsdroid/connector/slack/__init__.py b/opsdroid/connector/slack/__init__.py
--- a/opsdroid/connector/slack/__init__.py
+++ b/opsdroid/connector/slack/__init__.py
@@ -90,6 +90,10 @@
"""Process a raw message and pass it to the parser."""
message = payload["data"]
+ # Ignore message edits
+ if "subtype" in message and message["subtype"] == "message_changed":
+ return
+
# Ignore own messages
if (
"subtype" in message
| {"golden_diff": "diff --git a/opsdroid/connector/slack/__init__.py b/opsdroid/connector/slack/__init__.py\n--- a/opsdroid/connector/slack/__init__.py\n+++ b/opsdroid/connector/slack/__init__.py\n@@ -90,6 +90,10 @@\n \"\"\"Process a raw message and pass it to the parser.\"\"\"\n message = payload[\"data\"]\n \n+ # Ignore message edits\n+ if \"subtype\" in message and message[\"subtype\"] == \"message_changed\":\n+ return\n+\n # Ignore own messages\n if (\n \"subtype\" in message\n", "issue": "Slack connector crashes after running dance several times\n# Description\r\nSlack connector crashes after running dance several times in a row\r\n\r\n## Steps to Reproduce\r\nLaunch opsdroid with slack connector configured with bot token\r\ngo the channel connected in and run dance 3+ times in a row\r\n\r\n## Expected Functionality\r\nOpsdroid keeps running fine\r\n\r\n\r\n## Experienced Functionality\r\nOpsdroid crashes with the following error:\r\n```\r\nERROR slack.rtm.client: When calling '#process_message()' in the 'opsdroid.connector.slack' module the following error was raised: 'user'\r\nTraceback (most recent call last):\r\n File \"C:\\Users\\koe4945\\desktop\\git\\personal\\ops\\venv\\Scripts\\opsdroid-script.py\", line 11, in <module>\r\n load_entry_point('opsdroid', 'console_scripts', 'opsdroid')()\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\venv\\lib\\site-packages\\click\\core.py\", line 764, in __call__\r\n return self.main(*args, **kwargs)\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\venv\\lib\\site-packages\\click\\core.py\", line 717, in main\r\n rv = self.invoke(ctx)\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\venv\\lib\\site-packages\\click\\core.py\", line 1137, in invoke\r\n return _process_result(sub_ctx.command.invoke(sub_ctx))\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\venv\\lib\\site-packages\\click\\core.py\", line 956, in invoke\r\n return ctx.invoke(self.callback, **ctx.params)\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\venv\\lib\\site-packages\\click\\core.py\", line 555, in invoke\r\n return callback(*args, **kwargs)\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\opsdroid\\opsdroid\\cli\\start.py\", line 31, in start\r\n opsdroid.run()\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\opsdroid\\opsdroid\\core.py\", line 161, in run\r\n self.eventloop.run_until_complete(asyncio.gather(*pending))\r\n File \"C:\\Users\\koe4945\\AppData\\Local\\Programs\\Python\\Python37\\lib\\asyncio\\base_events.py\", line 584, in run_until_complete\r\n return future.result()\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\python-slackclient\\slack\\rtm\\client.py\", line 339, in _connect_and_read\r\n await self._read_messages()\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\python-slackclient\\slack\\rtm\\client.py\", line 390, in _read_messages\r\n await self._dispatch_event(event, data=payload)\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\python-slackclient\\slack\\rtm\\client.py\", line 437, in _dispatch_event\r\n rtm_client=self, web_client=self._web_client, data=data\r\n File \"c:\\users\\koe4945\\desktop\\git\\personal\\ops\\opsdroid\\opsdroid\\connector\\slack\\__init__.py\", line 104, in process_message\r\n user_info = await self.lookup_username(message[\"user\"])\r\nKeyError: 'user'\r\nERROR: Unhandled exception in opsdroid, exiting...\r\n```\r\n\r\n## Versions\r\n- **Opsdroid version:** v0.16.0+62.g620590f\r\n- **Python version:** 3.7.3\r\n- **OS/Docker version:** Windows 10\r\n\r\n## Configuration File\r\nPlease include your version of the configuration file below.\r\n\r\n```yaml\r\nconnectors:\r\n - name: slack\r\n # required\r\n api-token: \"[...bot token...]\"\r\n\r\n```\r\n\r\n## Additional Details\r\nAny other details you wish to include such as screenshots, console messages, etc.\r\n\n", "before_files": [{"content": "\"\"\"A connector for Slack.\"\"\"\nimport logging\nimport re\n\nimport slack\nfrom emoji import demojize\n\nfrom opsdroid.connector import Connector, register_event\nfrom opsdroid.events import Message, Reaction\nfrom opsdroid.connector.slack.events import Blocks\n\n\n_LOGGER = logging.getLogger(__name__)\n\n\nclass ConnectorSlack(Connector):\n \"\"\"A connector for Slack.\"\"\"\n\n def __init__(self, config, opsdroid=None):\n \"\"\"Create the connector.\"\"\"\n super().__init__(config, opsdroid=opsdroid)\n _LOGGER.debug(_(\"Starting Slack connector\"))\n self.name = \"slack\"\n self.default_target = config.get(\"default-room\", \"#general\")\n self.icon_emoji = config.get(\"icon-emoji\", \":robot_face:\")\n self.token = config[\"api-token\"]\n self.timeout = config.get(\"connect-timeout\", 10)\n self.slack = slack.WebClient(token=self.token, run_async=True)\n self.slack_rtm = slack.RTMClient(token=self.token, run_async=True)\n self.websocket = None\n self.bot_name = config.get(\"bot-name\", \"opsdroid\")\n self.auth_info = None\n self.user_info = None\n self.bot_id = None\n self.known_users = {}\n self.keepalive = None\n self.reconnecting = False\n self.listening = True\n self._message_id = 0\n\n # Register callbacks\n slack.RTMClient.on(event=\"message\", callback=self.process_message)\n\n async def connect(self):\n \"\"\"Connect to the chat service.\"\"\"\n _LOGGER.info(_(\"Connecting to Slack\"))\n\n try:\n # The slack library recommends you call `self.slack_rtm.start()`` here but it\n # seems to mess with the event loop's signal handlers which breaks opsdroid.\n # Therefore we need to directly call the private `_connect_and_read` method\n # instead. This method also blocks so we need to dispatch it to the loop as a task.\n self.opsdroid.eventloop.create_task(self.slack_rtm._connect_and_read())\n\n self.auth_info = (await self.slack.api_call(\"auth.test\")).data\n self.user_info = (\n await self.slack.api_call(\n \"users.info\",\n http_verb=\"GET\",\n params={\"user\": self.auth_info[\"user_id\"]},\n )\n ).data\n self.bot_id = self.user_info[\"user\"][\"profile\"][\"bot_id\"]\n\n _LOGGER.debug(_(\"Connected as %s\"), self.bot_name)\n _LOGGER.debug(_(\"Using icon %s\"), self.icon_emoji)\n _LOGGER.debug(_(\"Default room is %s\"), self.default_target)\n _LOGGER.info(_(\"Connected successfully\"))\n except slack.errors.SlackApiError as error:\n _LOGGER.error(\n _(\n \"Unable to connect to Slack due to %s - \"\n \"The Slack Connector will not be available.\"\n ),\n error,\n )\n except Exception:\n await self.disconnect()\n raise\n\n async def disconnect(self):\n \"\"\"Disconnect from Slack.\"\"\"\n await self.slack_rtm.stop()\n self.listening = False\n\n async def listen(self):\n \"\"\"Listen for and parse new messages.\"\"\"\n\n async def process_message(self, **payload):\n \"\"\"Process a raw message and pass it to the parser.\"\"\"\n message = payload[\"data\"]\n\n # Ignore own messages\n if (\n \"subtype\" in message\n and message[\"subtype\"] == \"bot_message\"\n and message[\"bot_id\"] == self.bot_id\n ):\n return\n\n # Lookup username\n _LOGGER.debug(_(\"Looking up sender username\"))\n try:\n user_info = await self.lookup_username(message[\"user\"])\n except ValueError:\n return\n\n # Replace usernames in the message\n _LOGGER.debug(_(\"Replacing userids in message with usernames\"))\n message[\"text\"] = await self.replace_usernames(message[\"text\"])\n\n await self.opsdroid.parse(\n Message(\n message[\"text\"],\n user_info[\"name\"],\n message[\"channel\"],\n self,\n raw_event=message,\n )\n )\n\n @register_event(Message)\n async def send_message(self, message):\n \"\"\"Respond with a message.\"\"\"\n _LOGGER.debug(\n _(\"Responding with: '%s' in room %s\"), message.text, message.target\n )\n await self.slack.api_call(\n \"chat.postMessage\",\n data={\n \"channel\": message.target,\n \"text\": message.text,\n \"as_user\": False,\n \"username\": self.bot_name,\n \"icon_emoji\": self.icon_emoji,\n },\n )\n\n @register_event(Blocks)\n async def send_blocks(self, blocks):\n \"\"\"Respond with structured blocks.\"\"\"\n _LOGGER.debug(\n _(\"Responding with interactive blocks in room %s\"), blocks.target\n )\n await self.slack.api_call(\n \"chat.postMessage\",\n data={\n \"channel\": blocks.target,\n \"username\": self.bot_name,\n \"blocks\": blocks.blocks,\n \"icon_emoji\": self.icon_emoji,\n },\n )\n\n @register_event(Reaction)\n async def send_reaction(self, reaction):\n \"\"\"React to a message.\"\"\"\n emoji = demojize(reaction.emoji).replace(\":\", \"\")\n _LOGGER.debug(_(\"Reacting with: %s\"), emoji)\n try:\n await self.slack.api_call(\n \"reactions.add\",\n data={\n \"name\": emoji,\n \"channel\": reaction.target,\n \"timestamp\": reaction.linked_event.raw_event[\"ts\"],\n },\n )\n except slack.errors.SlackApiError as error:\n if \"invalid_name\" in str(error):\n _LOGGER.warning(_(\"Slack does not support the emoji %s\"), emoji)\n else:\n raise\n\n async def lookup_username(self, userid):\n \"\"\"Lookup a username and cache it.\"\"\"\n if userid in self.known_users:\n user_info = self.known_users[userid]\n else:\n response = await self.slack.users_info(user=userid)\n user_info = response.data[\"user\"]\n if isinstance(user_info, dict):\n self.known_users[userid] = user_info\n else:\n raise ValueError(\"Returned user is not a dict.\")\n return user_info\n\n async def replace_usernames(self, message):\n \"\"\"Replace User ID with username in message text.\"\"\"\n userids = re.findall(r\"\\<\\@([A-Z0-9]+)(?:\\|.+)?\\>\", message)\n for userid in userids:\n user_info = await self.lookup_username(userid)\n message = message.replace(\n \"<@{userid}>\".format(userid=userid), user_info[\"name\"]\n )\n return message\n", "path": "opsdroid/connector/slack/__init__.py"}]} | 3,453 | 140 |
gh_patches_debug_26296 | rasdani/github-patches | git_diff | DataDog__dd-trace-py-4432 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
"Tracing Across Processes" example crashes
<!--
Thanks for taking the time for reporting an issue!
Before reporting an issue on dd-trace-py, please be sure to provide all
necessary information.
If you're hitting a bug, make sure that you're using the latest version of this
library.
-->
### Summary of problem
Hello, I cannot get "tracing across processes" to work. Python crashes while trying to pickle the tracer context RLock. The minimal reproduction example is [the example from the ddtrace advanced usage docs](https://ddtrace.readthedocs.io/en/stable/advanced_usage.html#tracing-across-processes). I also cannot get this to work with any prior ddtrace version.
### Which version of dd-trace-py are you using?
ddtrace: 1.5.3
python: 3.9.13
### How can we reproduce your problem?
Run the `Tracing Across Processes` example [from the docs](https://ddtrace.readthedocs.io/en/stable/advanced_usage.html#tracing-across-processes)
```python
from multiprocessing import Process
import time
from ddtrace import tracer
def _target(ctx):
tracer.context_provider.activate(ctx)
with tracer.trace("proc"):
time.sleep(1)
tracer.shutdown()
with tracer.trace("work"):
proc = Process(target=_target, args=(tracer.current_trace_context(),))
proc.start()
time.sleep(1)
proc.join()
```
### What is the result that you get?
```
Traceback (most recent call last):
File "/Users/jboulanger/Library/Application Support/JetBrains/PyCharm2021.2/scratches/scratch.py", line 15, in <module>
proc.start()
File "/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 32, in __init__
super().__init__(process_obj)
File "/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_fork.py", line 19, in __init__
self._launch(process_obj)
File "/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 47, in _launch
reduction.dump(process_obj, fp)
File "/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: cannot pickle '_thread.RLock' object
Process finished with exit code 1
```
### What is the result that you expected?
I expected this to complete without crashing
</issue>
<code>
[start of ddtrace/context.py]
1 import base64
2 import threading
3 from typing import Any
4 from typing import Optional
5 from typing import TYPE_CHECKING
6 from typing import Text
7
8 from .constants import ORIGIN_KEY
9 from .constants import SAMPLING_PRIORITY_KEY
10 from .constants import USER_ID_KEY
11 from .internal.compat import NumericType
12 from .internal.compat import PY2
13 from .internal.logger import get_logger
14
15
16 if TYPE_CHECKING: # pragma: no cover
17 from .span import Span
18 from .span import _MetaDictType
19 from .span import _MetricDictType
20
21 log = get_logger(__name__)
22
23
24 class Context(object):
25 """Represents the state required to propagate a trace across execution
26 boundaries.
27 """
28
29 __slots__ = [
30 "trace_id",
31 "span_id",
32 "_lock",
33 "_meta",
34 "_metrics",
35 ]
36
37 def __init__(
38 self,
39 trace_id=None, # type: Optional[int]
40 span_id=None, # type: Optional[int]
41 dd_origin=None, # type: Optional[str]
42 sampling_priority=None, # type: Optional[float]
43 meta=None, # type: Optional[_MetaDictType]
44 metrics=None, # type: Optional[_MetricDictType]
45 lock=None, # type: Optional[threading.RLock]
46 ):
47 self._meta = meta if meta is not None else {} # type: _MetaDictType
48 self._metrics = metrics if metrics is not None else {} # type: _MetricDictType
49
50 self.trace_id = trace_id # type: Optional[int]
51 self.span_id = span_id # type: Optional[int]
52
53 if dd_origin is not None:
54 self._meta[ORIGIN_KEY] = dd_origin
55 if sampling_priority is not None:
56 self._metrics[SAMPLING_PRIORITY_KEY] = sampling_priority
57
58 if lock is not None:
59 self._lock = lock
60 else:
61 # DEV: A `forksafe.RLock` is not necessary here since Contexts
62 # are recreated by the tracer after fork
63 # https://github.com/DataDog/dd-trace-py/blob/a1932e8ddb704d259ea8a3188d30bf542f59fd8d/ddtrace/tracer.py#L489-L508
64 self._lock = threading.RLock()
65
66 def _with_span(self, span):
67 # type: (Span) -> Context
68 """Return a shallow copy of the context with the given span."""
69 return self.__class__(
70 trace_id=span.trace_id, span_id=span.span_id, meta=self._meta, metrics=self._metrics, lock=self._lock
71 )
72
73 def _update_tags(self, span):
74 # type: (Span) -> None
75 with self._lock:
76 for tag in self._meta:
77 span._meta.setdefault(tag, self._meta[tag])
78 for metric in self._metrics:
79 span._metrics.setdefault(metric, self._metrics[metric])
80
81 @property
82 def sampling_priority(self):
83 # type: () -> Optional[NumericType]
84 """Return the context sampling priority for the trace."""
85 return self._metrics.get(SAMPLING_PRIORITY_KEY)
86
87 @sampling_priority.setter
88 def sampling_priority(self, value):
89 # type: (Optional[NumericType]) -> None
90 with self._lock:
91 if value is None:
92 if SAMPLING_PRIORITY_KEY in self._metrics:
93 del self._metrics[SAMPLING_PRIORITY_KEY]
94 return
95 self._metrics[SAMPLING_PRIORITY_KEY] = value
96
97 @property
98 def _traceparent(self):
99 # type: () -> str
100 if self.trace_id is None or self.span_id is None:
101 return ""
102
103 sampled = 1 if self.sampling_priority and self.sampling_priority > 0 else 0
104 return "00-{:032x}-{:016x}-{:02x}".format(self.trace_id, self.span_id, sampled)
105
106 @property
107 def dd_origin(self):
108 # type: () -> Optional[Text]
109 """Get the origin of the trace."""
110 return self._meta.get(ORIGIN_KEY)
111
112 @dd_origin.setter
113 def dd_origin(self, value):
114 # type: (Optional[Text]) -> None
115 """Set the origin of the trace."""
116 with self._lock:
117 if value is None:
118 if ORIGIN_KEY in self._meta:
119 del self._meta[ORIGIN_KEY]
120 return
121 self._meta[ORIGIN_KEY] = value
122
123 @property
124 def dd_user_id(self):
125 # type: () -> Optional[Text]
126 """Get the user ID of the trace."""
127 user_id = self._meta.get(USER_ID_KEY)
128 if user_id:
129 if not PY2:
130 return str(base64.b64decode(user_id), encoding="utf-8")
131 else:
132 return str(base64.b64decode(user_id))
133 return None
134
135 @dd_user_id.setter
136 def dd_user_id(self, value):
137 # type: (Optional[Text]) -> None
138 """Set the user ID of the trace."""
139 with self._lock:
140 if value is None:
141 if USER_ID_KEY in self._meta:
142 del self._meta[USER_ID_KEY]
143 return
144 if not PY2:
145 value = str(base64.b64encode(bytes(value, encoding="utf-8")), encoding="utf-8")
146 else:
147 value = str(base64.b64encode(bytes(value)))
148 self._meta[USER_ID_KEY] = value
149
150 def __eq__(self, other):
151 # type: (Any) -> bool
152 if isinstance(other, Context):
153 with self._lock:
154 return (
155 self.trace_id == other.trace_id
156 and self.span_id == other.span_id
157 and self._meta == other._meta
158 and self._metrics == other._metrics
159 )
160 return False
161
162 def __repr__(self):
163 # type: () -> str
164 return "Context(trace_id=%s, span_id=%s, _meta=%s, _metrics=%s)" % (
165 self.trace_id,
166 self.span_id,
167 self._meta,
168 self._metrics,
169 )
170
171 __str__ = __repr__
172
[end of ddtrace/context.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/ddtrace/context.py b/ddtrace/context.py
--- a/ddtrace/context.py
+++ b/ddtrace/context.py
@@ -14,10 +14,20 @@
if TYPE_CHECKING: # pragma: no cover
+ from typing import Tuple
+
from .span import Span
from .span import _MetaDictType
from .span import _MetricDictType
+ _ContextState = Tuple[
+ Optional[int], # trace_id
+ Optional[int], # span_id
+ _MetaDictType, # _meta
+ _MetricDictType, # _metrics
+ ]
+
+
log = get_logger(__name__)
@@ -63,6 +73,22 @@
# https://github.com/DataDog/dd-trace-py/blob/a1932e8ddb704d259ea8a3188d30bf542f59fd8d/ddtrace/tracer.py#L489-L508
self._lock = threading.RLock()
+ def __getstate__(self):
+ # type: () -> _ContextState
+ return (
+ self.trace_id,
+ self.span_id,
+ self._meta,
+ self._metrics,
+ # Note: self._lock is not serializable
+ )
+
+ def __setstate__(self, state):
+ # type: (_ContextState) -> None
+ self.trace_id, self.span_id, self._meta, self._metrics = state
+ # We cannot serialize and lock, so we must recreate it unless we already have one
+ self._lock = threading.RLock()
+
def _with_span(self, span):
# type: (Span) -> Context
"""Return a shallow copy of the context with the given span."""
| {"golden_diff": "diff --git a/ddtrace/context.py b/ddtrace/context.py\n--- a/ddtrace/context.py\n+++ b/ddtrace/context.py\n@@ -14,10 +14,20 @@\n \n \n if TYPE_CHECKING: # pragma: no cover\n+ from typing import Tuple\n+\n from .span import Span\n from .span import _MetaDictType\n from .span import _MetricDictType\n \n+ _ContextState = Tuple[\n+ Optional[int], # trace_id\n+ Optional[int], # span_id\n+ _MetaDictType, # _meta\n+ _MetricDictType, # _metrics\n+ ]\n+\n+\n log = get_logger(__name__)\n \n \n@@ -63,6 +73,22 @@\n # https://github.com/DataDog/dd-trace-py/blob/a1932e8ddb704d259ea8a3188d30bf542f59fd8d/ddtrace/tracer.py#L489-L508\n self._lock = threading.RLock()\n \n+ def __getstate__(self):\n+ # type: () -> _ContextState\n+ return (\n+ self.trace_id,\n+ self.span_id,\n+ self._meta,\n+ self._metrics,\n+ # Note: self._lock is not serializable\n+ )\n+\n+ def __setstate__(self, state):\n+ # type: (_ContextState) -> None\n+ self.trace_id, self.span_id, self._meta, self._metrics = state\n+ # We cannot serialize and lock, so we must recreate it unless we already have one\n+ self._lock = threading.RLock()\n+\n def _with_span(self, span):\n # type: (Span) -> Context\n \"\"\"Return a shallow copy of the context with the given span.\"\"\"\n", "issue": "\"Tracing Across Processes\" example crashes\n<!--\r\nThanks for taking the time for reporting an issue!\r\n\r\nBefore reporting an issue on dd-trace-py, please be sure to provide all\r\nnecessary information.\r\n\r\nIf you're hitting a bug, make sure that you're using the latest version of this\r\nlibrary.\r\n-->\r\n\r\n### Summary of problem\r\n\r\nHello, I cannot get \"tracing across processes\" to work. Python crashes while trying to pickle the tracer context RLock. The minimal reproduction example is [the example from the ddtrace advanced usage docs](https://ddtrace.readthedocs.io/en/stable/advanced_usage.html#tracing-across-processes). I also cannot get this to work with any prior ddtrace version.\r\n\r\n### Which version of dd-trace-py are you using?\r\n\r\nddtrace: 1.5.3\r\npython: 3.9.13\r\n\r\n### How can we reproduce your problem?\r\n\r\nRun the `Tracing Across Processes` example [from the docs](https://ddtrace.readthedocs.io/en/stable/advanced_usage.html#tracing-across-processes)\r\n\r\n```python\r\nfrom multiprocessing import Process\r\nimport time\r\nfrom ddtrace import tracer\r\n\r\ndef _target(ctx):\r\n tracer.context_provider.activate(ctx)\r\n with tracer.trace(\"proc\"):\r\n time.sleep(1)\r\n tracer.shutdown()\r\n\r\nwith tracer.trace(\"work\"):\r\n proc = Process(target=_target, args=(tracer.current_trace_context(),))\r\n proc.start()\r\n time.sleep(1)\r\n proc.join()\r\n```\r\n\r\n### What is the result that you get?\r\n\r\n```\r\nTraceback (most recent call last):\r\n File \"/Users/jboulanger/Library/Application Support/JetBrains/PyCharm2021.2/scratches/scratch.py\", line 15, in <module>\r\n proc.start()\r\n File \"/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/process.py\", line 121, in start\r\n self._popen = self._Popen(self)\r\n File \"/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py\", line 224, in _Popen\r\n return _default_context.get_context().Process._Popen(process_obj)\r\n File \"/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py\", line 284, in _Popen\r\n return Popen(process_obj)\r\n File \"/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py\", line 32, in __init__\r\n super().__init__(process_obj)\r\n File \"/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_fork.py\", line 19, in __init__\r\n self._launch(process_obj)\r\n File \"/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py\", line 47, in _launch\r\n reduction.dump(process_obj, fp)\r\n File \"/usr/local/Cellar/[email protected]/3.9.13_3/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/reduction.py\", line 60, in dump\r\n ForkingPickler(file, protocol).dump(obj)\r\nTypeError: cannot pickle '_thread.RLock' object\r\nProcess finished with exit code 1\r\n```\r\n\r\n### What is the result that you expected?\r\n\r\nI expected this to complete without crashing\n", "before_files": [{"content": "import base64\nimport threading\nfrom typing import Any\nfrom typing import Optional\nfrom typing import TYPE_CHECKING\nfrom typing import Text\n\nfrom .constants import ORIGIN_KEY\nfrom .constants import SAMPLING_PRIORITY_KEY\nfrom .constants import USER_ID_KEY\nfrom .internal.compat import NumericType\nfrom .internal.compat import PY2\nfrom .internal.logger import get_logger\n\n\nif TYPE_CHECKING: # pragma: no cover\n from .span import Span\n from .span import _MetaDictType\n from .span import _MetricDictType\n\nlog = get_logger(__name__)\n\n\nclass Context(object):\n \"\"\"Represents the state required to propagate a trace across execution\n boundaries.\n \"\"\"\n\n __slots__ = [\n \"trace_id\",\n \"span_id\",\n \"_lock\",\n \"_meta\",\n \"_metrics\",\n ]\n\n def __init__(\n self,\n trace_id=None, # type: Optional[int]\n span_id=None, # type: Optional[int]\n dd_origin=None, # type: Optional[str]\n sampling_priority=None, # type: Optional[float]\n meta=None, # type: Optional[_MetaDictType]\n metrics=None, # type: Optional[_MetricDictType]\n lock=None, # type: Optional[threading.RLock]\n ):\n self._meta = meta if meta is not None else {} # type: _MetaDictType\n self._metrics = metrics if metrics is not None else {} # type: _MetricDictType\n\n self.trace_id = trace_id # type: Optional[int]\n self.span_id = span_id # type: Optional[int]\n\n if dd_origin is not None:\n self._meta[ORIGIN_KEY] = dd_origin\n if sampling_priority is not None:\n self._metrics[SAMPLING_PRIORITY_KEY] = sampling_priority\n\n if lock is not None:\n self._lock = lock\n else:\n # DEV: A `forksafe.RLock` is not necessary here since Contexts\n # are recreated by the tracer after fork\n # https://github.com/DataDog/dd-trace-py/blob/a1932e8ddb704d259ea8a3188d30bf542f59fd8d/ddtrace/tracer.py#L489-L508\n self._lock = threading.RLock()\n\n def _with_span(self, span):\n # type: (Span) -> Context\n \"\"\"Return a shallow copy of the context with the given span.\"\"\"\n return self.__class__(\n trace_id=span.trace_id, span_id=span.span_id, meta=self._meta, metrics=self._metrics, lock=self._lock\n )\n\n def _update_tags(self, span):\n # type: (Span) -> None\n with self._lock:\n for tag in self._meta:\n span._meta.setdefault(tag, self._meta[tag])\n for metric in self._metrics:\n span._metrics.setdefault(metric, self._metrics[metric])\n\n @property\n def sampling_priority(self):\n # type: () -> Optional[NumericType]\n \"\"\"Return the context sampling priority for the trace.\"\"\"\n return self._metrics.get(SAMPLING_PRIORITY_KEY)\n\n @sampling_priority.setter\n def sampling_priority(self, value):\n # type: (Optional[NumericType]) -> None\n with self._lock:\n if value is None:\n if SAMPLING_PRIORITY_KEY in self._metrics:\n del self._metrics[SAMPLING_PRIORITY_KEY]\n return\n self._metrics[SAMPLING_PRIORITY_KEY] = value\n\n @property\n def _traceparent(self):\n # type: () -> str\n if self.trace_id is None or self.span_id is None:\n return \"\"\n\n sampled = 1 if self.sampling_priority and self.sampling_priority > 0 else 0\n return \"00-{:032x}-{:016x}-{:02x}\".format(self.trace_id, self.span_id, sampled)\n\n @property\n def dd_origin(self):\n # type: () -> Optional[Text]\n \"\"\"Get the origin of the trace.\"\"\"\n return self._meta.get(ORIGIN_KEY)\n\n @dd_origin.setter\n def dd_origin(self, value):\n # type: (Optional[Text]) -> None\n \"\"\"Set the origin of the trace.\"\"\"\n with self._lock:\n if value is None:\n if ORIGIN_KEY in self._meta:\n del self._meta[ORIGIN_KEY]\n return\n self._meta[ORIGIN_KEY] = value\n\n @property\n def dd_user_id(self):\n # type: () -> Optional[Text]\n \"\"\"Get the user ID of the trace.\"\"\"\n user_id = self._meta.get(USER_ID_KEY)\n if user_id:\n if not PY2:\n return str(base64.b64decode(user_id), encoding=\"utf-8\")\n else:\n return str(base64.b64decode(user_id))\n return None\n\n @dd_user_id.setter\n def dd_user_id(self, value):\n # type: (Optional[Text]) -> None\n \"\"\"Set the user ID of the trace.\"\"\"\n with self._lock:\n if value is None:\n if USER_ID_KEY in self._meta:\n del self._meta[USER_ID_KEY]\n return\n if not PY2:\n value = str(base64.b64encode(bytes(value, encoding=\"utf-8\")), encoding=\"utf-8\")\n else:\n value = str(base64.b64encode(bytes(value)))\n self._meta[USER_ID_KEY] = value\n\n def __eq__(self, other):\n # type: (Any) -> bool\n if isinstance(other, Context):\n with self._lock:\n return (\n self.trace_id == other.trace_id\n and self.span_id == other.span_id\n and self._meta == other._meta\n and self._metrics == other._metrics\n )\n return False\n\n def __repr__(self):\n # type: () -> str\n return \"Context(trace_id=%s, span_id=%s, _meta=%s, _metrics=%s)\" % (\n self.trace_id,\n self.span_id,\n self._meta,\n self._metrics,\n )\n\n __str__ = __repr__\n", "path": "ddtrace/context.py"}]} | 3,201 | 414 |
gh_patches_debug_38411 | rasdani/github-patches | git_diff | cloud-custodian__cloud-custodian-5275 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Support for EFS Lifecycles
According to this, it's not an available action: https://cloudcustodian.io/docs/aws/resources/efs.html
Console and CLI instructions from AWS are here: https://docs.aws.amazon.com/efs/latest/ug/enable-lifecycle-management.html
</issue>
<code>
[start of c7n/resources/efs.py]
1 # Copyright 2015-2017 Capital One Services, LLC
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 from __future__ import absolute_import, division, print_function, unicode_literals
15
16 from c7n.actions import Action
17 from c7n.filters.kms import KmsRelatedFilter
18 from c7n.manager import resources
19 from c7n.filters.vpc import SecurityGroupFilter, SubnetFilter
20 from c7n.query import QueryResourceManager, ChildResourceManager, TypeInfo
21 from c7n.tags import universal_augment
22 from c7n.utils import local_session, type_schema, get_retry
23
24
25 @resources.register('efs')
26 class ElasticFileSystem(QueryResourceManager):
27
28 class resource_type(TypeInfo):
29 service = 'efs'
30 enum_spec = ('describe_file_systems', 'FileSystems', None)
31 id = 'FileSystemId'
32 name = 'Name'
33 date = 'CreationTime'
34 dimension = 'FileSystemId'
35 arn_type = 'file-system'
36 permission_prefix = arn_service = 'elasticfilesystem'
37 filter_name = 'FileSystemId'
38 filter_type = 'scalar'
39 universal_taggable = True
40
41 augment = universal_augment
42
43
44 @resources.register('efs-mount-target')
45 class ElasticFileSystemMountTarget(ChildResourceManager):
46
47 class resource_type(TypeInfo):
48 service = 'efs'
49 parent_spec = ('efs', 'FileSystemId', None)
50 enum_spec = ('describe_mount_targets', 'MountTargets', None)
51 permission_prefix = 'elasticfilesystem'
52 name = id = 'MountTargetId'
53 filter_name = 'MountTargetId'
54 filter_type = 'scalar'
55 arn = False
56
57
58 @ElasticFileSystemMountTarget.filter_registry.register('subnet')
59 class Subnet(SubnetFilter):
60
61 RelatedIdsExpression = "SubnetId"
62
63
64 @ElasticFileSystemMountTarget.filter_registry.register('security-group')
65 class SecurityGroup(SecurityGroupFilter):
66
67 efs_group_cache = None
68
69 RelatedIdsExpression = ""
70
71 def get_related_ids(self, resources):
72
73 if self.efs_group_cache:
74 group_ids = set()
75 for r in resources:
76 group_ids.update(
77 self.efs_group_cache.get(r['MountTargetId'], ()))
78 return list(group_ids)
79
80 client = local_session(self.manager.session_factory).client('efs')
81 groups = {}
82 group_ids = set()
83 retry = get_retry(('Throttled',), 12)
84
85 for r in resources:
86 groups[r['MountTargetId']] = retry(
87 client.describe_mount_target_security_groups,
88 MountTargetId=r['MountTargetId'])['SecurityGroups']
89 group_ids.update(groups[r['MountTargetId']])
90
91 self.efs_group_cache = groups
92 return list(group_ids)
93
94
95 @ElasticFileSystem.filter_registry.register('kms-key')
96 class KmsFilter(KmsRelatedFilter):
97 """
98 Filter a resource by its associcated kms key and optionally the aliasname
99 of the kms key by using 'c7n:AliasName'
100
101 :example:
102
103 .. code-block:: yaml
104
105 policies:
106 - name: efs-kms-key-filters
107 resource: efs
108 filters:
109 - type: kms-key
110 key: c7n:AliasName
111 value: "^(alias/aws/)"
112 op: regex
113 """
114 RelatedIdsExpression = 'KmsKeyId'
115
116
117 @ElasticFileSystem.action_registry.register('delete')
118 class Delete(Action):
119
120 schema = type_schema('delete')
121 permissions = ('elasticfilesystem:DescribeMountTargets',
122 'elasticfilesystem:DeleteMountTarget',
123 'elasticfilesystem:DeleteFileSystem')
124
125 def process(self, resources):
126 client = local_session(self.manager.session_factory).client('efs')
127 self.unmount_filesystems(resources)
128 retry = get_retry(('FileSystemInUse',), 12)
129 for r in resources:
130 retry(client.delete_file_system, FileSystemId=r['FileSystemId'])
131
132 def unmount_filesystems(self, resources):
133 client = local_session(self.manager.session_factory).client('efs')
134 for r in resources:
135 if not r['NumberOfMountTargets']:
136 continue
137 for t in client.describe_mount_targets(
138 FileSystemId=r['FileSystemId'])['MountTargets']:
139 client.delete_mount_target(MountTargetId=t['MountTargetId'])
140
[end of c7n/resources/efs.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/c7n/resources/efs.py b/c7n/resources/efs.py
--- a/c7n/resources/efs.py
+++ b/c7n/resources/efs.py
@@ -13,13 +13,15 @@
# limitations under the License.
from __future__ import absolute_import, division, print_function, unicode_literals
-from c7n.actions import Action
+from c7n.actions import Action, BaseAction
+from c7n.exceptions import PolicyValidationError
from c7n.filters.kms import KmsRelatedFilter
from c7n.manager import resources
from c7n.filters.vpc import SecurityGroupFilter, SubnetFilter
from c7n.query import QueryResourceManager, ChildResourceManager, TypeInfo
from c7n.tags import universal_augment
from c7n.utils import local_session, type_schema, get_retry
+from .aws import shape_validate
@resources.register('efs')
@@ -137,3 +139,57 @@
for t in client.describe_mount_targets(
FileSystemId=r['FileSystemId'])['MountTargets']:
client.delete_mount_target(MountTargetId=t['MountTargetId'])
+
+
[email protected]_registry.register('configure-lifecycle-policy')
+class ConfigureLifecycle(BaseAction):
+ """Enable/disable lifecycle policy for efs.
+
+ :example:
+
+ .. code-block:: yaml
+
+ policies:
+ - name: efs-apply-lifecycle
+ resource: efs
+ actions:
+ - type: configure-lifecycle-policy
+ state: enable
+ rules:
+ - 'TransitionToIA': 'AFTER_7_DAYS'
+
+ """
+ schema = type_schema(
+ 'configure-lifecycle-policy',
+ state={'enum': ['enable', 'disable']},
+ rules={
+ 'type': 'array',
+ 'items': {'type': 'object'}},
+ required=['state'])
+
+ permissions = ('elasticfilesystem:PutLifecycleConfiguration',)
+ shape = 'PutLifecycleConfigurationRequest'
+
+ def validate(self):
+ if self.data.get('state') == 'enable' and 'rules' not in self.data:
+ raise PolicyValidationError(
+ 'rules are required to enable lifecycle configuration %s' % (self.manager.data))
+ if self.data.get('state') == 'disable' and 'rules' in self.data:
+ raise PolicyValidationError(
+ 'rules not required to disable lifecycle configuration %s' % (self.manager.data))
+ if self.data.get('rules'):
+ attrs = {}
+ attrs['LifecyclePolicies'] = self.data['rules']
+ attrs['FileSystemId'] = 'PolicyValidator'
+ return shape_validate(attrs, self.shape, 'efs')
+
+ def process(self, resources):
+ client = local_session(self.manager.session_factory).client('efs')
+ op_map = {'enable': self.data.get('rules'), 'disable': []}
+ for r in resources:
+ try:
+ client.put_lifecycle_configuration(
+ FileSystemId=r['FileSystemId'],
+ LifecyclePolicies=op_map.get(self.data.get('state')))
+ except client.exceptions.FileSystemNotFound:
+ continue
| {"golden_diff": "diff --git a/c7n/resources/efs.py b/c7n/resources/efs.py\n--- a/c7n/resources/efs.py\n+++ b/c7n/resources/efs.py\n@@ -13,13 +13,15 @@\n # limitations under the License.\n from __future__ import absolute_import, division, print_function, unicode_literals\n \n-from c7n.actions import Action\n+from c7n.actions import Action, BaseAction\n+from c7n.exceptions import PolicyValidationError\n from c7n.filters.kms import KmsRelatedFilter\n from c7n.manager import resources\n from c7n.filters.vpc import SecurityGroupFilter, SubnetFilter\n from c7n.query import QueryResourceManager, ChildResourceManager, TypeInfo\n from c7n.tags import universal_augment\n from c7n.utils import local_session, type_schema, get_retry\n+from .aws import shape_validate\n \n \n @resources.register('efs')\n@@ -137,3 +139,57 @@\n for t in client.describe_mount_targets(\n FileSystemId=r['FileSystemId'])['MountTargets']:\n client.delete_mount_target(MountTargetId=t['MountTargetId'])\n+\n+\[email protected]_registry.register('configure-lifecycle-policy')\n+class ConfigureLifecycle(BaseAction):\n+ \"\"\"Enable/disable lifecycle policy for efs.\n+\n+ :example:\n+\n+ .. code-block:: yaml\n+\n+ policies:\n+ - name: efs-apply-lifecycle\n+ resource: efs\n+ actions:\n+ - type: configure-lifecycle-policy\n+ state: enable\n+ rules:\n+ - 'TransitionToIA': 'AFTER_7_DAYS'\n+\n+ \"\"\"\n+ schema = type_schema(\n+ 'configure-lifecycle-policy',\n+ state={'enum': ['enable', 'disable']},\n+ rules={\n+ 'type': 'array',\n+ 'items': {'type': 'object'}},\n+ required=['state'])\n+\n+ permissions = ('elasticfilesystem:PutLifecycleConfiguration',)\n+ shape = 'PutLifecycleConfigurationRequest'\n+\n+ def validate(self):\n+ if self.data.get('state') == 'enable' and 'rules' not in self.data:\n+ raise PolicyValidationError(\n+ 'rules are required to enable lifecycle configuration %s' % (self.manager.data))\n+ if self.data.get('state') == 'disable' and 'rules' in self.data:\n+ raise PolicyValidationError(\n+ 'rules not required to disable lifecycle configuration %s' % (self.manager.data))\n+ if self.data.get('rules'):\n+ attrs = {}\n+ attrs['LifecyclePolicies'] = self.data['rules']\n+ attrs['FileSystemId'] = 'PolicyValidator'\n+ return shape_validate(attrs, self.shape, 'efs')\n+\n+ def process(self, resources):\n+ client = local_session(self.manager.session_factory).client('efs')\n+ op_map = {'enable': self.data.get('rules'), 'disable': []}\n+ for r in resources:\n+ try:\n+ client.put_lifecycle_configuration(\n+ FileSystemId=r['FileSystemId'],\n+ LifecyclePolicies=op_map.get(self.data.get('state')))\n+ except client.exceptions.FileSystemNotFound:\n+ continue\n", "issue": "Support for EFS Lifecycles\nAccording to this, it's not an available action: https://cloudcustodian.io/docs/aws/resources/efs.html\r\n\r\nConsole and CLI instructions from AWS are here: https://docs.aws.amazon.com/efs/latest/ug/enable-lifecycle-management.html\n", "before_files": [{"content": "# Copyright 2015-2017 Capital One Services, LLC\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\nfrom __future__ import absolute_import, division, print_function, unicode_literals\n\nfrom c7n.actions import Action\nfrom c7n.filters.kms import KmsRelatedFilter\nfrom c7n.manager import resources\nfrom c7n.filters.vpc import SecurityGroupFilter, SubnetFilter\nfrom c7n.query import QueryResourceManager, ChildResourceManager, TypeInfo\nfrom c7n.tags import universal_augment\nfrom c7n.utils import local_session, type_schema, get_retry\n\n\[email protected]('efs')\nclass ElasticFileSystem(QueryResourceManager):\n\n class resource_type(TypeInfo):\n service = 'efs'\n enum_spec = ('describe_file_systems', 'FileSystems', None)\n id = 'FileSystemId'\n name = 'Name'\n date = 'CreationTime'\n dimension = 'FileSystemId'\n arn_type = 'file-system'\n permission_prefix = arn_service = 'elasticfilesystem'\n filter_name = 'FileSystemId'\n filter_type = 'scalar'\n universal_taggable = True\n\n augment = universal_augment\n\n\[email protected]('efs-mount-target')\nclass ElasticFileSystemMountTarget(ChildResourceManager):\n\n class resource_type(TypeInfo):\n service = 'efs'\n parent_spec = ('efs', 'FileSystemId', None)\n enum_spec = ('describe_mount_targets', 'MountTargets', None)\n permission_prefix = 'elasticfilesystem'\n name = id = 'MountTargetId'\n filter_name = 'MountTargetId'\n filter_type = 'scalar'\n arn = False\n\n\[email protected]_registry.register('subnet')\nclass Subnet(SubnetFilter):\n\n RelatedIdsExpression = \"SubnetId\"\n\n\[email protected]_registry.register('security-group')\nclass SecurityGroup(SecurityGroupFilter):\n\n efs_group_cache = None\n\n RelatedIdsExpression = \"\"\n\n def get_related_ids(self, resources):\n\n if self.efs_group_cache:\n group_ids = set()\n for r in resources:\n group_ids.update(\n self.efs_group_cache.get(r['MountTargetId'], ()))\n return list(group_ids)\n\n client = local_session(self.manager.session_factory).client('efs')\n groups = {}\n group_ids = set()\n retry = get_retry(('Throttled',), 12)\n\n for r in resources:\n groups[r['MountTargetId']] = retry(\n client.describe_mount_target_security_groups,\n MountTargetId=r['MountTargetId'])['SecurityGroups']\n group_ids.update(groups[r['MountTargetId']])\n\n self.efs_group_cache = groups\n return list(group_ids)\n\n\[email protected]_registry.register('kms-key')\nclass KmsFilter(KmsRelatedFilter):\n \"\"\"\n Filter a resource by its associcated kms key and optionally the aliasname\n of the kms key by using 'c7n:AliasName'\n\n :example:\n\n .. code-block:: yaml\n\n policies:\n - name: efs-kms-key-filters\n resource: efs\n filters:\n - type: kms-key\n key: c7n:AliasName\n value: \"^(alias/aws/)\"\n op: regex\n \"\"\"\n RelatedIdsExpression = 'KmsKeyId'\n\n\[email protected]_registry.register('delete')\nclass Delete(Action):\n\n schema = type_schema('delete')\n permissions = ('elasticfilesystem:DescribeMountTargets',\n 'elasticfilesystem:DeleteMountTarget',\n 'elasticfilesystem:DeleteFileSystem')\n\n def process(self, resources):\n client = local_session(self.manager.session_factory).client('efs')\n self.unmount_filesystems(resources)\n retry = get_retry(('FileSystemInUse',), 12)\n for r in resources:\n retry(client.delete_file_system, FileSystemId=r['FileSystemId'])\n\n def unmount_filesystems(self, resources):\n client = local_session(self.manager.session_factory).client('efs')\n for r in resources:\n if not r['NumberOfMountTargets']:\n continue\n for t in client.describe_mount_targets(\n FileSystemId=r['FileSystemId'])['MountTargets']:\n client.delete_mount_target(MountTargetId=t['MountTargetId'])\n", "path": "c7n/resources/efs.py"}]} | 1,940 | 695 |
gh_patches_debug_28943 | rasdani/github-patches | git_diff | comic__grand-challenge.org-1020 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Replace links in the challenge copying command
People might use full url links in the page HTML, use a regex to replace the links using the new challenge short name.
</issue>
<code>
[start of app/grandchallenge/challenges/management/commands/copy_challenge.py]
1 from django.core.management import BaseCommand, CommandError
2
3 from grandchallenge.challenges.models import Challenge
4 from grandchallenge.pages.models import Page
5
6
7 class Command(BaseCommand):
8 help = "Creates a copy of a challenge"
9
10 challenge_fields = [
11 "creator",
12 "description",
13 "educational",
14 "disclaimer",
15 "require_participant_review",
16 "use_registration_page",
17 "registration_page_text",
18 "use_evaluation",
19 "logo",
20 "banner",
21 ]
22
23 challenge_m2m_fields = [
24 "task_types",
25 "modalities",
26 "structures",
27 ]
28
29 config_fields = [
30 "use_teams",
31 "score_title",
32 "score_jsonpath",
33 "score_error_jsonpath",
34 "score_default_sort",
35 "score_decimal_places",
36 "extra_results_columns",
37 "scoring_method_choice",
38 "result_display_choice",
39 "allow_submission_comments",
40 "display_submission_comments",
41 "supplementary_file_choice",
42 "supplementary_file_label",
43 "supplementary_file_help_text",
44 "show_supplementary_file_link",
45 "publication_url_choice",
46 "show_publication_url",
47 "daily_submission_limit",
48 "submission_page_html",
49 "auto_publish_new_results",
50 "display_all_metrics",
51 "submission_join_key",
52 ]
53
54 page_fields = [
55 "title",
56 "permission_lvl",
57 "order",
58 "display_title",
59 "hidden",
60 "html",
61 ]
62
63 def add_arguments(self, parser):
64 parser.add_argument("source", type=str)
65 parser.add_argument("dest", type=str)
66
67 def handle(self, *args, **options):
68 src_name = options.pop("source")
69 dest_name = options.pop("dest")
70
71 if src_name.lower() == dest_name.lower():
72 raise CommandError("Source and dest names must be different")
73
74 src_challenge = Challenge.objects.get(short_name__iexact=src_name)
75 dest_challenge = self._create_new_challenge(
76 src_challenge=src_challenge, dest_name=dest_name
77 )
78
79 self._copy_m2m_fields(
80 src_challenge=src_challenge, dest_challenge=dest_challenge
81 )
82 self._copy_evaluation_config(
83 src_challenge=src_challenge, dest_challenge=dest_challenge
84 )
85 self._copy_pages(
86 src_challenge=src_challenge, dest_challenge=dest_challenge
87 )
88 self._copy_admins(
89 src_challenge=src_challenge, dest_challenge=dest_challenge
90 )
91
92 def _create_new_challenge(self, *, src_challenge, dest_name):
93 new_challenge = Challenge(
94 short_name=dest_name,
95 **{f: getattr(src_challenge, f) for f in self.challenge_fields},
96 )
97 new_challenge.full_clean()
98 new_challenge.save()
99 return new_challenge
100
101 def _copy_m2m_fields(self, *, src_challenge, dest_challenge):
102 for f in self.challenge_m2m_fields:
103 src_m2m = getattr(src_challenge, f)
104 dest_m2m = getattr(dest_challenge, f)
105 dest_m2m.set(src_m2m.all())
106
107 def _copy_evaluation_config(self, *, src_challenge, dest_challenge):
108 src_config = src_challenge.evaluation_config
109 dest_config = dest_challenge.evaluation_config
110
111 for attr in self.config_fields:
112 setattr(dest_config, attr, getattr(src_config, attr))
113
114 dest_config.save()
115
116 def _copy_pages(self, *, src_challenge, dest_challenge):
117 src_pages = src_challenge.page_set.all()
118
119 for src_page in src_pages:
120 Page.objects.create(
121 challenge=dest_challenge,
122 **{f: getattr(src_page, f) for f in self.page_fields},
123 )
124
125 def _copy_admins(self, *, src_challenge, dest_challenge):
126 for u in src_challenge.get_admins():
127 dest_challenge.add_admin(u)
128
[end of app/grandchallenge/challenges/management/commands/copy_challenge.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/app/grandchallenge/challenges/management/commands/copy_challenge.py b/app/grandchallenge/challenges/management/commands/copy_challenge.py
--- a/app/grandchallenge/challenges/management/commands/copy_challenge.py
+++ b/app/grandchallenge/challenges/management/commands/copy_challenge.py
@@ -1,3 +1,6 @@
+import re
+
+from django.contrib.sites.models import Site
from django.core.management import BaseCommand, CommandError
from grandchallenge.challenges.models import Challenge
@@ -57,7 +60,6 @@
"order",
"display_title",
"hidden",
- "html",
]
def add_arguments(self, parser):
@@ -113,12 +115,24 @@
dest_config.save()
+ def _substitute_urls(self, html, domain, old, new):
+ quote_replace = r"href='([^']*)'"
+ regex = fr'href="[^/]*//{old}.{domain}([^""]*)"'
+ html = re.sub(quote_replace, r'href="\1"', html)
+ return re.sub(regex, fr'href="https://{new}.{domain}\1"', html,)
+
def _copy_pages(self, *, src_challenge, dest_challenge):
src_pages = src_challenge.page_set.all()
+ site = Site.objects.get_current()
+ domain = site.domain
+ old = src_challenge.short_name
+ new = dest_challenge.short_name
+
for src_page in src_pages:
Page.objects.create(
challenge=dest_challenge,
+ html=self._substitute_urls(src_page.html, domain, old, new),
**{f: getattr(src_page, f) for f in self.page_fields},
)
| {"golden_diff": "diff --git a/app/grandchallenge/challenges/management/commands/copy_challenge.py b/app/grandchallenge/challenges/management/commands/copy_challenge.py\n--- a/app/grandchallenge/challenges/management/commands/copy_challenge.py\n+++ b/app/grandchallenge/challenges/management/commands/copy_challenge.py\n@@ -1,3 +1,6 @@\n+import re\n+\n+from django.contrib.sites.models import Site\n from django.core.management import BaseCommand, CommandError\n \n from grandchallenge.challenges.models import Challenge\n@@ -57,7 +60,6 @@\n \"order\",\n \"display_title\",\n \"hidden\",\n- \"html\",\n ]\n \n def add_arguments(self, parser):\n@@ -113,12 +115,24 @@\n \n dest_config.save()\n \n+ def _substitute_urls(self, html, domain, old, new):\n+ quote_replace = r\"href='([^']*)'\"\n+ regex = fr'href=\"[^/]*//{old}.{domain}([^\"\"]*)\"'\n+ html = re.sub(quote_replace, r'href=\"\\1\"', html)\n+ return re.sub(regex, fr'href=\"https://{new}.{domain}\\1\"', html,)\n+\n def _copy_pages(self, *, src_challenge, dest_challenge):\n src_pages = src_challenge.page_set.all()\n \n+ site = Site.objects.get_current()\n+ domain = site.domain\n+ old = src_challenge.short_name\n+ new = dest_challenge.short_name\n+\n for src_page in src_pages:\n Page.objects.create(\n challenge=dest_challenge,\n+ html=self._substitute_urls(src_page.html, domain, old, new),\n **{f: getattr(src_page, f) for f in self.page_fields},\n )\n", "issue": "Replace links in the challenge copying command\nPeople might use full url links in the page HTML, use a regex to replace the links using the new challenge short name.\n", "before_files": [{"content": "from django.core.management import BaseCommand, CommandError\n\nfrom grandchallenge.challenges.models import Challenge\nfrom grandchallenge.pages.models import Page\n\n\nclass Command(BaseCommand):\n help = \"Creates a copy of a challenge\"\n\n challenge_fields = [\n \"creator\",\n \"description\",\n \"educational\",\n \"disclaimer\",\n \"require_participant_review\",\n \"use_registration_page\",\n \"registration_page_text\",\n \"use_evaluation\",\n \"logo\",\n \"banner\",\n ]\n\n challenge_m2m_fields = [\n \"task_types\",\n \"modalities\",\n \"structures\",\n ]\n\n config_fields = [\n \"use_teams\",\n \"score_title\",\n \"score_jsonpath\",\n \"score_error_jsonpath\",\n \"score_default_sort\",\n \"score_decimal_places\",\n \"extra_results_columns\",\n \"scoring_method_choice\",\n \"result_display_choice\",\n \"allow_submission_comments\",\n \"display_submission_comments\",\n \"supplementary_file_choice\",\n \"supplementary_file_label\",\n \"supplementary_file_help_text\",\n \"show_supplementary_file_link\",\n \"publication_url_choice\",\n \"show_publication_url\",\n \"daily_submission_limit\",\n \"submission_page_html\",\n \"auto_publish_new_results\",\n \"display_all_metrics\",\n \"submission_join_key\",\n ]\n\n page_fields = [\n \"title\",\n \"permission_lvl\",\n \"order\",\n \"display_title\",\n \"hidden\",\n \"html\",\n ]\n\n def add_arguments(self, parser):\n parser.add_argument(\"source\", type=str)\n parser.add_argument(\"dest\", type=str)\n\n def handle(self, *args, **options):\n src_name = options.pop(\"source\")\n dest_name = options.pop(\"dest\")\n\n if src_name.lower() == dest_name.lower():\n raise CommandError(\"Source and dest names must be different\")\n\n src_challenge = Challenge.objects.get(short_name__iexact=src_name)\n dest_challenge = self._create_new_challenge(\n src_challenge=src_challenge, dest_name=dest_name\n )\n\n self._copy_m2m_fields(\n src_challenge=src_challenge, dest_challenge=dest_challenge\n )\n self._copy_evaluation_config(\n src_challenge=src_challenge, dest_challenge=dest_challenge\n )\n self._copy_pages(\n src_challenge=src_challenge, dest_challenge=dest_challenge\n )\n self._copy_admins(\n src_challenge=src_challenge, dest_challenge=dest_challenge\n )\n\n def _create_new_challenge(self, *, src_challenge, dest_name):\n new_challenge = Challenge(\n short_name=dest_name,\n **{f: getattr(src_challenge, f) for f in self.challenge_fields},\n )\n new_challenge.full_clean()\n new_challenge.save()\n return new_challenge\n\n def _copy_m2m_fields(self, *, src_challenge, dest_challenge):\n for f in self.challenge_m2m_fields:\n src_m2m = getattr(src_challenge, f)\n dest_m2m = getattr(dest_challenge, f)\n dest_m2m.set(src_m2m.all())\n\n def _copy_evaluation_config(self, *, src_challenge, dest_challenge):\n src_config = src_challenge.evaluation_config\n dest_config = dest_challenge.evaluation_config\n\n for attr in self.config_fields:\n setattr(dest_config, attr, getattr(src_config, attr))\n\n dest_config.save()\n\n def _copy_pages(self, *, src_challenge, dest_challenge):\n src_pages = src_challenge.page_set.all()\n\n for src_page in src_pages:\n Page.objects.create(\n challenge=dest_challenge,\n **{f: getattr(src_page, f) for f in self.page_fields},\n )\n\n def _copy_admins(self, *, src_challenge, dest_challenge):\n for u in src_challenge.get_admins():\n dest_challenge.add_admin(u)\n", "path": "app/grandchallenge/challenges/management/commands/copy_challenge.py"}]} | 1,684 | 386 |
gh_patches_debug_58008 | rasdani/github-patches | git_diff | marshmallow-code__webargs-385 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Fix compatibility with Falcon 2.0
Tests are currently failing when Falcon 2.0.0 is installed.
</issue>
<code>
[start of setup.py]
1 # -*- coding: utf-8 -*-
2 import sys
3 import re
4 from setuptools import setup, find_packages
5
6 INSTALL_REQUIRES = ["marshmallow>=2.15.2"]
7 if sys.version_info[0] < 3:
8 INSTALL_REQUIRES.append("simplejson>=2.1.0")
9
10 FRAMEWORKS = [
11 "Flask>=0.12.2",
12 "Django>=1.11.16",
13 "bottle>=0.12.13",
14 "tornado>=4.5.2",
15 "pyramid>=1.9.1",
16 "webapp2>=3.0.0b1",
17 "falcon>=1.4.0",
18 'aiohttp>=3.0.0; python_version >= "3.5"',
19 ]
20 EXTRAS_REQUIRE = {
21 "frameworks": FRAMEWORKS,
22 "tests": [
23 "pytest",
24 "mock",
25 "webtest==2.0.32",
26 'webtest-aiohttp==2.0.0; python_version >= "3.5"',
27 'pytest-aiohttp>=0.3.0; python_version >= "3.5"',
28 ]
29 + FRAMEWORKS,
30 "lint": [
31 'mypy==0.650; python_version >= "3.5"',
32 "flake8==3.6.0",
33 'flake8-bugbear==18.8.0; python_version >= "3.5"',
34 "pre-commit==1.13.0",
35 ],
36 }
37 EXTRAS_REQUIRE["dev"] = EXTRAS_REQUIRE["tests"] + EXTRAS_REQUIRE["lint"] + ["tox"]
38
39
40 def find_version(fname):
41 """Attempts to find the version number in the file names fname.
42 Raises RuntimeError if not found.
43 """
44 version = ""
45 with open(fname, "r") as fp:
46 reg = re.compile(r'__version__ = [\'"]([^\'"]*)[\'"]')
47 for line in fp:
48 m = reg.match(line)
49 if m:
50 version = m.group(1)
51 break
52 if not version:
53 raise RuntimeError("Cannot find version information")
54 return version
55
56
57 def read(fname):
58 with open(fname) as fp:
59 content = fp.read()
60 return content
61
62
63 setup(
64 name="webargs",
65 version=find_version("src/webargs/__init__.py"),
66 description=(
67 "Declarative parsing and validation of HTTP request objects, "
68 "with built-in support for popular web frameworks, including "
69 "Flask, Django, Bottle, Tornado, Pyramid, webapp2, Falcon, and aiohttp."
70 ),
71 long_description=read("README.rst"),
72 author="Steven Loria",
73 author_email="[email protected]",
74 url="https://github.com/marshmallow-code/webargs",
75 packages=find_packages("src"),
76 package_dir={"": "src"},
77 install_requires=INSTALL_REQUIRES,
78 extras_require=EXTRAS_REQUIRE,
79 license="MIT",
80 zip_safe=False,
81 keywords=(
82 "webargs",
83 "http",
84 "flask",
85 "django",
86 "bottle",
87 "tornado",
88 "aiohttp",
89 "webapp2",
90 "request",
91 "arguments",
92 "validation",
93 "parameters",
94 "rest",
95 "api",
96 "marshmallow",
97 ),
98 classifiers=[
99 "Development Status :: 5 - Production/Stable",
100 "Intended Audience :: Developers",
101 "License :: OSI Approved :: MIT License",
102 "Natural Language :: English",
103 "Programming Language :: Python :: 2",
104 "Programming Language :: Python :: 2.7",
105 "Programming Language :: Python :: 3",
106 "Programming Language :: Python :: 3.5",
107 "Programming Language :: Python :: 3.6",
108 "Programming Language :: Python :: 3.7",
109 "Topic :: Internet :: WWW/HTTP :: Dynamic Content",
110 "Topic :: Internet :: WWW/HTTP :: WSGI :: Application",
111 ],
112 test_suite="tests",
113 project_urls={
114 "Changelog": "https://webargs.readthedocs.io/en/latest/changelog.html",
115 "Issues": "https://github.com/marshmallow-code/webargs/issues",
116 "Funding": "https://opencollective.com/marshmallow",
117 "Tidelift": "https://tidelift.com/subscription/pkg/pypi-webargs?utm_source=pypi-marshmallow&utm_medium=pypi", # noqa
118 },
119 )
120
[end of setup.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -14,7 +14,7 @@
"tornado>=4.5.2",
"pyramid>=1.9.1",
"webapp2>=3.0.0b1",
- "falcon>=1.4.0",
+ "falcon>=1.4.0,<2.0",
'aiohttp>=3.0.0; python_version >= "3.5"',
]
EXTRAS_REQUIRE = {
| {"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -14,7 +14,7 @@\n \"tornado>=4.5.2\",\n \"pyramid>=1.9.1\",\n \"webapp2>=3.0.0b1\",\n- \"falcon>=1.4.0\",\n+ \"falcon>=1.4.0,<2.0\",\n 'aiohttp>=3.0.0; python_version >= \"3.5\"',\n ]\n EXTRAS_REQUIRE = {\n", "issue": "Fix compatibility with Falcon 2.0\nTests are currently failing when Falcon 2.0.0 is installed.\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\nimport sys\nimport re\nfrom setuptools import setup, find_packages\n\nINSTALL_REQUIRES = [\"marshmallow>=2.15.2\"]\nif sys.version_info[0] < 3:\n INSTALL_REQUIRES.append(\"simplejson>=2.1.0\")\n\nFRAMEWORKS = [\n \"Flask>=0.12.2\",\n \"Django>=1.11.16\",\n \"bottle>=0.12.13\",\n \"tornado>=4.5.2\",\n \"pyramid>=1.9.1\",\n \"webapp2>=3.0.0b1\",\n \"falcon>=1.4.0\",\n 'aiohttp>=3.0.0; python_version >= \"3.5\"',\n]\nEXTRAS_REQUIRE = {\n \"frameworks\": FRAMEWORKS,\n \"tests\": [\n \"pytest\",\n \"mock\",\n \"webtest==2.0.32\",\n 'webtest-aiohttp==2.0.0; python_version >= \"3.5\"',\n 'pytest-aiohttp>=0.3.0; python_version >= \"3.5\"',\n ]\n + FRAMEWORKS,\n \"lint\": [\n 'mypy==0.650; python_version >= \"3.5\"',\n \"flake8==3.6.0\",\n 'flake8-bugbear==18.8.0; python_version >= \"3.5\"',\n \"pre-commit==1.13.0\",\n ],\n}\nEXTRAS_REQUIRE[\"dev\"] = EXTRAS_REQUIRE[\"tests\"] + EXTRAS_REQUIRE[\"lint\"] + [\"tox\"]\n\n\ndef find_version(fname):\n \"\"\"Attempts to find the version number in the file names fname.\n Raises RuntimeError if not found.\n \"\"\"\n version = \"\"\n with open(fname, \"r\") as fp:\n reg = re.compile(r'__version__ = [\\'\"]([^\\'\"]*)[\\'\"]')\n for line in fp:\n m = reg.match(line)\n if m:\n version = m.group(1)\n break\n if not version:\n raise RuntimeError(\"Cannot find version information\")\n return version\n\n\ndef read(fname):\n with open(fname) as fp:\n content = fp.read()\n return content\n\n\nsetup(\n name=\"webargs\",\n version=find_version(\"src/webargs/__init__.py\"),\n description=(\n \"Declarative parsing and validation of HTTP request objects, \"\n \"with built-in support for popular web frameworks, including \"\n \"Flask, Django, Bottle, Tornado, Pyramid, webapp2, Falcon, and aiohttp.\"\n ),\n long_description=read(\"README.rst\"),\n author=\"Steven Loria\",\n author_email=\"[email protected]\",\n url=\"https://github.com/marshmallow-code/webargs\",\n packages=find_packages(\"src\"),\n package_dir={\"\": \"src\"},\n install_requires=INSTALL_REQUIRES,\n extras_require=EXTRAS_REQUIRE,\n license=\"MIT\",\n zip_safe=False,\n keywords=(\n \"webargs\",\n \"http\",\n \"flask\",\n \"django\",\n \"bottle\",\n \"tornado\",\n \"aiohttp\",\n \"webapp2\",\n \"request\",\n \"arguments\",\n \"validation\",\n \"parameters\",\n \"rest\",\n \"api\",\n \"marshmallow\",\n ),\n classifiers=[\n \"Development Status :: 5 - Production/Stable\",\n \"Intended Audience :: Developers\",\n \"License :: OSI Approved :: MIT License\",\n \"Natural Language :: English\",\n \"Programming Language :: Python :: 2\",\n \"Programming Language :: Python :: 2.7\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.5\",\n \"Programming Language :: Python :: 3.6\",\n \"Programming Language :: Python :: 3.7\",\n \"Topic :: Internet :: WWW/HTTP :: Dynamic Content\",\n \"Topic :: Internet :: WWW/HTTP :: WSGI :: Application\",\n ],\n test_suite=\"tests\",\n project_urls={\n \"Changelog\": \"https://webargs.readthedocs.io/en/latest/changelog.html\",\n \"Issues\": \"https://github.com/marshmallow-code/webargs/issues\",\n \"Funding\": \"https://opencollective.com/marshmallow\",\n \"Tidelift\": \"https://tidelift.com/subscription/pkg/pypi-webargs?utm_source=pypi-marshmallow&utm_medium=pypi\", # noqa\n },\n)\n", "path": "setup.py"}]} | 1,791 | 123 |
gh_patches_debug_41585 | rasdani/github-patches | git_diff | napari__napari-5309 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add cadenced runs for benchmarking slicing
## Description
The goal of this task is to ensure that any existing benchmarking tools are running as expected. And that the output of those tasks can be easily used to detect performance changes in napari.
## Motivation
Slicing is a core part of napari and it's critical that any changes to the related code does not substantially negatively impact performance of slicing. Many of the existing ASV benchmarks measure the time and memory used during layer initialization and slicing, which could be affect by this project.
## Output
The key output of this task is to have some way of easily detecting when the performance of napari changes at some regular interval (e.g. daily, weekly) based on the existing ASV benchmarks. This could be as simple as using `asv publish` after running `asv continuous` in the existing GitHub workflow to generate static HTML that can be downloaded and rendered locally. Alternatively, the report could be entirely text based as long as it's easy to find any changes in performance.
We should also have some way to trigger a full benchmark run for a PR related to async slicing that also generates a similar report, but that could be done in a follow-up PR. This task can also be broken down as needed.
## Notes
need to add workflow runs for benchmarking
Jaime can support
Relevant previous PRs
- https://github.com/napari/napari/pull/4554
- https://github.com/napari/napari/pull/4656
<hr>
### KCP update:
Issues with the `Benchmark` workflow have been resolved in https://github.com/napari/napari/pull/5083
Unfortunately I introduced a regression which I'm fixing in https://github.com/napari/napari/pull/5246
</issue>
<code>
[start of napari/benchmarks/benchmark_qt_slicing.py]
1 # See "Writing benchmarks" in the asv docs for more information.
2 # https://asv.readthedocs.io/en/latest/writing_benchmarks.html
3 # or the napari documentation on benchmarking
4 # https://github.com/napari/napari/blob/main/docs/BENCHMARKS.md
5
6 import time
7
8 import numpy as np
9 import zarr
10 from qtpy.QtWidgets import QApplication
11
12 import napari
13 from napari.layers import Image
14
15 SAMPLE_PARAMS = {
16 'skin_data': {
17 # napari-bio-sample-data
18 'shape': (1280, 960, 3),
19 'chunk_shape': (512, 512, 3),
20 'dtype': 'uint8',
21 },
22 'jrc_hela-2 (scale 3)': {
23 # s3://janelia-cosem-datasets/jrc_hela-2/jrc_hela-2.n5
24 'shape': (796, 200, 1500),
25 'dtype': 'uint16',
26 'chunk_shape': (64, 64, 64),
27 },
28 }
29
30
31 def get_image_params():
32 # chunksizes = [(64,64,64), (256,256,256), (512,512,512)]
33 latencies = [0.05 * i for i in range(0, 3)]
34 datanames = SAMPLE_PARAMS.keys()
35 params = (latencies, datanames)
36
37 return params
38
39
40 class SlowMemoryStore(zarr.storage.MemoryStore):
41 def __init__(self, load_delay, *args, **kwargs):
42 self.load_delay = load_delay
43 super().__init__(*args, **kwargs)
44
45 def __getitem__(self, item: str):
46 time.sleep(self.load_delay)
47 return super().__getitem__(item)
48
49
50 class AsyncImage2DSuite:
51 params = get_image_params()
52
53 def setup(self, latency, dataname):
54 shape = SAMPLE_PARAMS[dataname]['shape']
55 chunk_shape = SAMPLE_PARAMS[dataname]['chunk_shape']
56 dtype = SAMPLE_PARAMS[dataname]['dtype']
57
58 store = SlowMemoryStore(load_delay=latency)
59 self.data = zarr.zeros(
60 shape,
61 chunks=chunk_shape,
62 dtype=dtype,
63 store=store,
64 )
65
66 self.layer = Image(self.data)
67
68 def time_create_layer(self, *args):
69 """Time to create an image layer."""
70 Image(self.data)
71
72 def time_set_view_slice(self, *args):
73 """Time to set view slice."""
74 self.layer._set_view_slice()
75
76 def time_refresh(self, *args):
77 """Time to refresh view."""
78 self.layer.refresh()
79
80
81 class QtViewerAsyncImage2DSuite:
82 params = get_image_params()
83
84 def setup(self, latency, dataname):
85 shape = SAMPLE_PARAMS[dataname]['shape']
86 chunk_shape = SAMPLE_PARAMS[dataname]['chunk_shape']
87 dtype = SAMPLE_PARAMS[dataname]['dtype']
88
89 if len(shape) == 3 and shape[2] == 3:
90 # Skip 2D RGB tests -- scrolling does not apply
91 self.viewer = None
92 raise NotImplementedError
93
94 store = SlowMemoryStore(load_delay=latency)
95 _ = QApplication.instance() or QApplication([])
96 self.data = zarr.zeros(
97 shape,
98 chunks=chunk_shape,
99 dtype=dtype,
100 store=store,
101 )
102
103 self.viewer = napari.Viewer()
104 self.viewer.add_image(self.data)
105
106 def time_z_scroll(self, *args):
107 layers_to_scroll = 4
108 for z in range(layers_to_scroll):
109 z = z * (self.data.shape[2] // layers_to_scroll)
110 self.viewer.dims.set_current_step(0, z)
111
112 def teardown(self, *args):
113 if self.viewer is not None:
114 self.viewer.window.close()
115
116
117 class QtViewerAsyncPointsSuite:
118 n_points = [2**i for i in range(12, 18)]
119 params = n_points
120
121 def setup(self, n_points):
122 _ = QApplication.instance() or QApplication([])
123
124 np.random.seed(0)
125 self.viewer = napari.Viewer()
126 # Fake image layer to set bounds. Is this really needed?
127 self.empty_image = np.zeros((512, 512, 512), dtype="uint8")
128 self.viewer.add_image(self.empty_image)
129 self.point_data = np.random.randint(512, size=(n_points, 3))
130 self.viewer.add_points(self.point_data)
131
132 def time_z_scroll(self, *args):
133 for z in range(self.empty_image.shape[0]):
134 self.viewer.dims.set_current_step(0, z)
135
136 def teardown(self, *args):
137 self.viewer.window.close()
138
139
140 class QtViewerAsyncPointsAndImage2DSuite:
141 n_points = [2**i for i in range(12, 18, 2)]
142 chunksize = [256, 512, 1024]
143 latency = [0.05 * i for i in range(0, 3)]
144 params = (n_points, latency, chunksize)
145
146 def setup(self, n_points, latency, chunksize):
147 store = SlowMemoryStore(load_delay=latency)
148 _ = QApplication.instance() or QApplication([])
149
150 np.random.seed(0)
151
152 self.image_data = zarr.zeros(
153 (64, 2048, 2048),
154 chunks=(1, chunksize, chunksize),
155 dtype='uint8',
156 store=store,
157 )
158
159 self.viewer = napari.Viewer()
160 self.viewer.add_image(self.image_data)
161 self.point_data = np.random.randint(512, size=(n_points, 3))
162 self.viewer.add_points(self.point_data)
163
164 def time_z_scroll(self, *args):
165 for z in range(self.image_data.shape[0]):
166 self.viewer.dims.set_current_step(0, z)
167
168 def teardown(self, *args):
169 self.viewer.window.close()
170
[end of napari/benchmarks/benchmark_qt_slicing.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/napari/benchmarks/benchmark_qt_slicing.py b/napari/benchmarks/benchmark_qt_slicing.py
--- a/napari/benchmarks/benchmark_qt_slicing.py
+++ b/napari/benchmarks/benchmark_qt_slicing.py
@@ -48,7 +48,12 @@
class AsyncImage2DSuite:
+ """TODO: these benchmarks are skipped. Remove the NotImplementedError in
+ setup to enable.
+ """
+
params = get_image_params()
+ timeout = 300
def setup(self, latency, dataname):
shape = SAMPLE_PARAMS[dataname]['shape']
@@ -64,6 +69,7 @@
)
self.layer = Image(self.data)
+ raise NotImplementedError
def time_create_layer(self, *args):
"""Time to create an image layer."""
@@ -79,7 +85,12 @@
class QtViewerAsyncImage2DSuite:
+ """TODO: these benchmarks are skipped. Remove the NotImplementedError in
+ setup to enable.
+ """
+
params = get_image_params()
+ timeout = 300
def setup(self, latency, dataname):
shape = SAMPLE_PARAMS[dataname]['shape']
@@ -102,6 +113,7 @@
self.viewer = napari.Viewer()
self.viewer.add_image(self.data)
+ raise NotImplementedError
def time_z_scroll(self, *args):
layers_to_scroll = 4
@@ -115,6 +127,10 @@
class QtViewerAsyncPointsSuite:
+ """TODO: these benchmarks are skipped. Remove the NotImplementedError in
+ setup to enable.
+ """
+
n_points = [2**i for i in range(12, 18)]
params = n_points
@@ -128,6 +144,7 @@
self.viewer.add_image(self.empty_image)
self.point_data = np.random.randint(512, size=(n_points, 3))
self.viewer.add_points(self.point_data)
+ raise NotImplementedError
def time_z_scroll(self, *args):
for z in range(self.empty_image.shape[0]):
@@ -138,10 +155,15 @@
class QtViewerAsyncPointsAndImage2DSuite:
+ """TODO: these benchmarks are skipped. Remove the NotImplementedError in
+ setup to enable.
+ """
+
n_points = [2**i for i in range(12, 18, 2)]
chunksize = [256, 512, 1024]
latency = [0.05 * i for i in range(0, 3)]
params = (n_points, latency, chunksize)
+ timeout = 600
def setup(self, n_points, latency, chunksize):
store = SlowMemoryStore(load_delay=latency)
@@ -160,6 +182,7 @@
self.viewer.add_image(self.image_data)
self.point_data = np.random.randint(512, size=(n_points, 3))
self.viewer.add_points(self.point_data)
+ raise NotImplementedError
def time_z_scroll(self, *args):
for z in range(self.image_data.shape[0]):
| {"golden_diff": "diff --git a/napari/benchmarks/benchmark_qt_slicing.py b/napari/benchmarks/benchmark_qt_slicing.py\n--- a/napari/benchmarks/benchmark_qt_slicing.py\n+++ b/napari/benchmarks/benchmark_qt_slicing.py\n@@ -48,7 +48,12 @@\n \n \n class AsyncImage2DSuite:\n+ \"\"\"TODO: these benchmarks are skipped. Remove the NotImplementedError in\n+ setup to enable.\n+ \"\"\"\n+\n params = get_image_params()\n+ timeout = 300\n \n def setup(self, latency, dataname):\n shape = SAMPLE_PARAMS[dataname]['shape']\n@@ -64,6 +69,7 @@\n )\n \n self.layer = Image(self.data)\n+ raise NotImplementedError\n \n def time_create_layer(self, *args):\n \"\"\"Time to create an image layer.\"\"\"\n@@ -79,7 +85,12 @@\n \n \n class QtViewerAsyncImage2DSuite:\n+ \"\"\"TODO: these benchmarks are skipped. Remove the NotImplementedError in\n+ setup to enable.\n+ \"\"\"\n+\n params = get_image_params()\n+ timeout = 300\n \n def setup(self, latency, dataname):\n shape = SAMPLE_PARAMS[dataname]['shape']\n@@ -102,6 +113,7 @@\n \n self.viewer = napari.Viewer()\n self.viewer.add_image(self.data)\n+ raise NotImplementedError\n \n def time_z_scroll(self, *args):\n layers_to_scroll = 4\n@@ -115,6 +127,10 @@\n \n \n class QtViewerAsyncPointsSuite:\n+ \"\"\"TODO: these benchmarks are skipped. Remove the NotImplementedError in\n+ setup to enable.\n+ \"\"\"\n+\n n_points = [2**i for i in range(12, 18)]\n params = n_points\n \n@@ -128,6 +144,7 @@\n self.viewer.add_image(self.empty_image)\n self.point_data = np.random.randint(512, size=(n_points, 3))\n self.viewer.add_points(self.point_data)\n+ raise NotImplementedError\n \n def time_z_scroll(self, *args):\n for z in range(self.empty_image.shape[0]):\n@@ -138,10 +155,15 @@\n \n \n class QtViewerAsyncPointsAndImage2DSuite:\n+ \"\"\"TODO: these benchmarks are skipped. Remove the NotImplementedError in\n+ setup to enable.\n+ \"\"\"\n+\n n_points = [2**i for i in range(12, 18, 2)]\n chunksize = [256, 512, 1024]\n latency = [0.05 * i for i in range(0, 3)]\n params = (n_points, latency, chunksize)\n+ timeout = 600\n \n def setup(self, n_points, latency, chunksize):\n store = SlowMemoryStore(load_delay=latency)\n@@ -160,6 +182,7 @@\n self.viewer.add_image(self.image_data)\n self.point_data = np.random.randint(512, size=(n_points, 3))\n self.viewer.add_points(self.point_data)\n+ raise NotImplementedError\n \n def time_z_scroll(self, *args):\n for z in range(self.image_data.shape[0]):\n", "issue": "Add cadenced runs for benchmarking slicing\n## Description\n\nThe goal of this task is to ensure that any existing benchmarking tools are running as expected. And that the output of those tasks can be easily used to detect performance changes in napari.\n\n## Motivation\n\nSlicing is a core part of napari and it's critical that any changes to the related code does not substantially negatively impact performance of slicing. Many of the existing ASV benchmarks measure the time and memory used during layer initialization and slicing, which could be affect by this project.\n\n## Output\n\nThe key output of this task is to have some way of easily detecting when the performance of napari changes at some regular interval (e.g. daily, weekly) based on the existing ASV benchmarks. This could be as simple as using `asv publish` after running `asv continuous` in the existing GitHub workflow to generate static HTML that can be downloaded and rendered locally. Alternatively, the report could be entirely text based as long as it's easy to find any changes in performance.\n\nWe should also have some way to trigger a full benchmark run for a PR related to async slicing that also generates a similar report, but that could be done in a follow-up PR. This task can also be broken down as needed.\n\n## Notes\nneed to add workflow runs for benchmarking\n\nJaime can support\n\nRelevant previous PRs\n- https://github.com/napari/napari/pull/4554\n- https://github.com/napari/napari/pull/4656\n\n\n<hr>\n\n### KCP update:\n\nIssues with the `Benchmark` workflow have been resolved in https://github.com/napari/napari/pull/5083\n\nUnfortunately I introduced a regression which I'm fixing in https://github.com/napari/napari/pull/5246\n", "before_files": [{"content": "# See \"Writing benchmarks\" in the asv docs for more information.\n# https://asv.readthedocs.io/en/latest/writing_benchmarks.html\n# or the napari documentation on benchmarking\n# https://github.com/napari/napari/blob/main/docs/BENCHMARKS.md\n\nimport time\n\nimport numpy as np\nimport zarr\nfrom qtpy.QtWidgets import QApplication\n\nimport napari\nfrom napari.layers import Image\n\nSAMPLE_PARAMS = {\n 'skin_data': {\n # napari-bio-sample-data\n 'shape': (1280, 960, 3),\n 'chunk_shape': (512, 512, 3),\n 'dtype': 'uint8',\n },\n 'jrc_hela-2 (scale 3)': {\n # s3://janelia-cosem-datasets/jrc_hela-2/jrc_hela-2.n5\n 'shape': (796, 200, 1500),\n 'dtype': 'uint16',\n 'chunk_shape': (64, 64, 64),\n },\n}\n\n\ndef get_image_params():\n # chunksizes = [(64,64,64), (256,256,256), (512,512,512)]\n latencies = [0.05 * i for i in range(0, 3)]\n datanames = SAMPLE_PARAMS.keys()\n params = (latencies, datanames)\n\n return params\n\n\nclass SlowMemoryStore(zarr.storage.MemoryStore):\n def __init__(self, load_delay, *args, **kwargs):\n self.load_delay = load_delay\n super().__init__(*args, **kwargs)\n\n def __getitem__(self, item: str):\n time.sleep(self.load_delay)\n return super().__getitem__(item)\n\n\nclass AsyncImage2DSuite:\n params = get_image_params()\n\n def setup(self, latency, dataname):\n shape = SAMPLE_PARAMS[dataname]['shape']\n chunk_shape = SAMPLE_PARAMS[dataname]['chunk_shape']\n dtype = SAMPLE_PARAMS[dataname]['dtype']\n\n store = SlowMemoryStore(load_delay=latency)\n self.data = zarr.zeros(\n shape,\n chunks=chunk_shape,\n dtype=dtype,\n store=store,\n )\n\n self.layer = Image(self.data)\n\n def time_create_layer(self, *args):\n \"\"\"Time to create an image layer.\"\"\"\n Image(self.data)\n\n def time_set_view_slice(self, *args):\n \"\"\"Time to set view slice.\"\"\"\n self.layer._set_view_slice()\n\n def time_refresh(self, *args):\n \"\"\"Time to refresh view.\"\"\"\n self.layer.refresh()\n\n\nclass QtViewerAsyncImage2DSuite:\n params = get_image_params()\n\n def setup(self, latency, dataname):\n shape = SAMPLE_PARAMS[dataname]['shape']\n chunk_shape = SAMPLE_PARAMS[dataname]['chunk_shape']\n dtype = SAMPLE_PARAMS[dataname]['dtype']\n\n if len(shape) == 3 and shape[2] == 3:\n # Skip 2D RGB tests -- scrolling does not apply\n self.viewer = None\n raise NotImplementedError\n\n store = SlowMemoryStore(load_delay=latency)\n _ = QApplication.instance() or QApplication([])\n self.data = zarr.zeros(\n shape,\n chunks=chunk_shape,\n dtype=dtype,\n store=store,\n )\n\n self.viewer = napari.Viewer()\n self.viewer.add_image(self.data)\n\n def time_z_scroll(self, *args):\n layers_to_scroll = 4\n for z in range(layers_to_scroll):\n z = z * (self.data.shape[2] // layers_to_scroll)\n self.viewer.dims.set_current_step(0, z)\n\n def teardown(self, *args):\n if self.viewer is not None:\n self.viewer.window.close()\n\n\nclass QtViewerAsyncPointsSuite:\n n_points = [2**i for i in range(12, 18)]\n params = n_points\n\n def setup(self, n_points):\n _ = QApplication.instance() or QApplication([])\n\n np.random.seed(0)\n self.viewer = napari.Viewer()\n # Fake image layer to set bounds. Is this really needed?\n self.empty_image = np.zeros((512, 512, 512), dtype=\"uint8\")\n self.viewer.add_image(self.empty_image)\n self.point_data = np.random.randint(512, size=(n_points, 3))\n self.viewer.add_points(self.point_data)\n\n def time_z_scroll(self, *args):\n for z in range(self.empty_image.shape[0]):\n self.viewer.dims.set_current_step(0, z)\n\n def teardown(self, *args):\n self.viewer.window.close()\n\n\nclass QtViewerAsyncPointsAndImage2DSuite:\n n_points = [2**i for i in range(12, 18, 2)]\n chunksize = [256, 512, 1024]\n latency = [0.05 * i for i in range(0, 3)]\n params = (n_points, latency, chunksize)\n\n def setup(self, n_points, latency, chunksize):\n store = SlowMemoryStore(load_delay=latency)\n _ = QApplication.instance() or QApplication([])\n\n np.random.seed(0)\n\n self.image_data = zarr.zeros(\n (64, 2048, 2048),\n chunks=(1, chunksize, chunksize),\n dtype='uint8',\n store=store,\n )\n\n self.viewer = napari.Viewer()\n self.viewer.add_image(self.image_data)\n self.point_data = np.random.randint(512, size=(n_points, 3))\n self.viewer.add_points(self.point_data)\n\n def time_z_scroll(self, *args):\n for z in range(self.image_data.shape[0]):\n self.viewer.dims.set_current_step(0, z)\n\n def teardown(self, *args):\n self.viewer.window.close()\n", "path": "napari/benchmarks/benchmark_qt_slicing.py"}]} | 2,683 | 730 |
gh_patches_debug_19737 | rasdani/github-patches | git_diff | biopython__biopython-3247 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Should we remove/replace Bio.Alphabet?
Filing this meta-issue, since we don't seem to have a single place discussing this on GitHub.
**My (likely biased) summary from those discussions is no one likes the current alphabet system, and most people ignore it.**
Biopython has a complicated hard to use legacy alphabet system in ``Bio.Alphabet`` which is used as a typing system (e.g. can't do reverse-complement on a protein), can store some useful information like the expected letters, if gapped and the gap character (although only one), and a stop codon symbol (although only one).
The objects in ``Bio.Alphabet`` cover three-letter alphabets as well as the more commonly used one-letter alphabets, although the ``Seq`` object effectively assumes the later only. Three-letter alphabets can be used with the array-based ``MutableSeq`` object, but it is very fragile and many things break - thus #1681.
Note we do not (currently) validate the expected letters when making a sequence object with an alphabet with an explicit set of expected letters - #1040.
Discussion on #1674 (hiding alphabets) has meant we now hide the alphabet in the ``Seq`` object representation if it is the default alphabet. Discussion there, and on #1681, and on the mailing list suggests going further and *removing* ``Bio.Alphabet`` entirely.
Note that removal is not as simple as it might sound - it will require some delicate modifications, for example several of the parsers in ``Bio.SeqIO`` use the alphabet to store the sequence type (important metadata in more than one file format).
I personally do like the typing system aspect of the alphabet system, but think we only need a much simpler DNA/RNA/nucleotide/protein/other system (more like an enum). I started looking at that on this branch which aimed to break as little existing code as possible: https://github.com/peterjc/biopython/tree/alpha_lite
</issue>
<code>
[start of Bio/Alphabet/__init__.py]
1 # Copyright 2000-2002 by Andrew Dalke.
2 # Revisions copyright 2007-2010 by Peter Cock.
3 # All rights reserved.
4 #
5 # This file is part of the Biopython distribution and governed by your
6 # choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
7 # Please see the LICENSE file that should have been included as part of this
8 # package.
9 """Alphabets were previously used to declare sequence type and letters (OBSOLETE).
10
11 The design of Bio.Aphabet included a number of historic design choices
12 which, with the benefit of hindsight, were regretable. Bio.Alphabet was
13 therefore removed from Biopython in release 1.78. Instead, the molecule type is
14 included as an annotation on SeqRecords where appropriate.
15
16 Please see
17 https://github.com/biopython/biopython/issues/3156
18 for examples showing how to transition from Bio.Alphabet to molecule type
19 annotations.
20 """
21
22 raise ImportError(
23 "Bio.Alphabet has been removed from Biopython. In many cases, the alphabet can simply be ignored and removed from scripts. In a few cases, you may need to specify the ``molecule_type`` as an annotation on a SeqRecord for your script to work correctly. Please see https://github.com/biopython/biopython/issues/3156 for more information."
24 )
25
[end of Bio/Alphabet/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/Bio/Alphabet/__init__.py b/Bio/Alphabet/__init__.py
--- a/Bio/Alphabet/__init__.py
+++ b/Bio/Alphabet/__init__.py
@@ -13,12 +13,10 @@
therefore removed from Biopython in release 1.78. Instead, the molecule type is
included as an annotation on SeqRecords where appropriate.
-Please see
-https://github.com/biopython/biopython/issues/3156
-for examples showing how to transition from Bio.Alphabet to molecule type
-annotations.
+Please see https://biopython.org/wiki/Alphabet for examples showing how to
+transition from Bio.Alphabet to molecule type annotations.
"""
raise ImportError(
- "Bio.Alphabet has been removed from Biopython. In many cases, the alphabet can simply be ignored and removed from scripts. In a few cases, you may need to specify the ``molecule_type`` as an annotation on a SeqRecord for your script to work correctly. Please see https://github.com/biopython/biopython/issues/3156 for more information."
+ "Bio.Alphabet has been removed from Biopython. In many cases, the alphabet can simply be ignored and removed from scripts. In a few cases, you may need to specify the ``molecule_type`` as an annotation on a SeqRecord for your script to work correctly. Please see https://biopython.org/wiki/Alphabet for more information."
)
| {"golden_diff": "diff --git a/Bio/Alphabet/__init__.py b/Bio/Alphabet/__init__.py\n--- a/Bio/Alphabet/__init__.py\n+++ b/Bio/Alphabet/__init__.py\n@@ -13,12 +13,10 @@\n therefore removed from Biopython in release 1.78. Instead, the molecule type is\n included as an annotation on SeqRecords where appropriate.\n \n-Please see\n-https://github.com/biopython/biopython/issues/3156\n-for examples showing how to transition from Bio.Alphabet to molecule type\n-annotations.\n+Please see https://biopython.org/wiki/Alphabet for examples showing how to\n+transition from Bio.Alphabet to molecule type annotations.\n \"\"\"\n \n raise ImportError(\n- \"Bio.Alphabet has been removed from Biopython. In many cases, the alphabet can simply be ignored and removed from scripts. In a few cases, you may need to specify the ``molecule_type`` as an annotation on a SeqRecord for your script to work correctly. Please see https://github.com/biopython/biopython/issues/3156 for more information.\"\n+ \"Bio.Alphabet has been removed from Biopython. In many cases, the alphabet can simply be ignored and removed from scripts. In a few cases, you may need to specify the ``molecule_type`` as an annotation on a SeqRecord for your script to work correctly. Please see https://biopython.org/wiki/Alphabet for more information.\"\n )\n", "issue": "Should we remove/replace Bio.Alphabet?\nFiling this meta-issue, since we don't seem to have a single place discussing this on GitHub.\r\n\r\n**My (likely biased) summary from those discussions is no one likes the current alphabet system, and most people ignore it.**\r\n\r\nBiopython has a complicated hard to use legacy alphabet system in ``Bio.Alphabet`` which is used as a typing system (e.g. can't do reverse-complement on a protein), can store some useful information like the expected letters, if gapped and the gap character (although only one), and a stop codon symbol (although only one).\r\n\r\nThe objects in ``Bio.Alphabet`` cover three-letter alphabets as well as the more commonly used one-letter alphabets, although the ``Seq`` object effectively assumes the later only. Three-letter alphabets can be used with the array-based ``MutableSeq`` object, but it is very fragile and many things break - thus #1681.\r\n\r\nNote we do not (currently) validate the expected letters when making a sequence object with an alphabet with an explicit set of expected letters - #1040.\r\n\r\nDiscussion on #1674 (hiding alphabets) has meant we now hide the alphabet in the ``Seq`` object representation if it is the default alphabet. Discussion there, and on #1681, and on the mailing list suggests going further and *removing* ``Bio.Alphabet`` entirely.\r\n\r\nNote that removal is not as simple as it might sound - it will require some delicate modifications, for example several of the parsers in ``Bio.SeqIO`` use the alphabet to store the sequence type (important metadata in more than one file format).\r\n\r\nI personally do like the typing system aspect of the alphabet system, but think we only need a much simpler DNA/RNA/nucleotide/protein/other system (more like an enum). I started looking at that on this branch which aimed to break as little existing code as possible: https://github.com/peterjc/biopython/tree/alpha_lite\r\n\n", "before_files": [{"content": "# Copyright 2000-2002 by Andrew Dalke.\n# Revisions copyright 2007-2010 by Peter Cock.\n# All rights reserved.\n#\n# This file is part of the Biopython distribution and governed by your\n# choice of the \"Biopython License Agreement\" or the \"BSD 3-Clause License\".\n# Please see the LICENSE file that should have been included as part of this\n# package.\n\"\"\"Alphabets were previously used to declare sequence type and letters (OBSOLETE).\n\nThe design of Bio.Aphabet included a number of historic design choices\nwhich, with the benefit of hindsight, were regretable. Bio.Alphabet was\ntherefore removed from Biopython in release 1.78. Instead, the molecule type is\nincluded as an annotation on SeqRecords where appropriate.\n\nPlease see\nhttps://github.com/biopython/biopython/issues/3156\nfor examples showing how to transition from Bio.Alphabet to molecule type\nannotations.\n\"\"\"\n\nraise ImportError(\n \"Bio.Alphabet has been removed from Biopython. In many cases, the alphabet can simply be ignored and removed from scripts. In a few cases, you may need to specify the ``molecule_type`` as an annotation on a SeqRecord for your script to work correctly. Please see https://github.com/biopython/biopython/issues/3156 for more information.\"\n)\n", "path": "Bio/Alphabet/__init__.py"}]} | 1,318 | 329 |
gh_patches_debug_711 | rasdani/github-patches | git_diff | dmlc__gluon-nlp-184 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
API doc examples are currently not easy to copy/paste
users may want to use a snippet from example directly, so making the notebooks copy-friendly is important
currently the code blocks have python shell prefix ">>>" in them. see http://gluon-nlp.mxnet.io/api/notes/data_api.html
</issue>
<code>
[start of docs/conf.py]
1 # -*- coding: utf-8 -*-
2 #
3 # documentation build configuration file, created by
4 # sphinx-quickstart on Thu Jul 23 19:40:08 2015.
5 #
6 # This file is execfile()d with the current directory set to its
7 # containing dir.
8 #
9 # Note that not all possible configuration values are present in this
10 # autogenerated file.
11 #
12 # All configuration values have a default; values that are commented out
13 # serve to show the default.
14 import sys
15 import os, subprocess
16 import shlex
17 import recommonmark
18 import sphinx_gallery
19 from recommonmark.parser import CommonMarkParser
20 from recommonmark.transform import AutoStructify
21
22 # If extensions (or modules to document with autodoc) are in another directory,
23 # add these directories to sys.path here. If the directory is relative to the
24 # documentation root, use os.path.abspath to make it absolute, like shown here.
25 curr_path = os.path.dirname(os.path.abspath(os.path.expanduser(__file__)))
26 sys.path.insert(0, os.path.join(curr_path, '..'))
27
28 # -- General configuration ------------------------------------------------
29
30 # Version information.
31 import gluonnlp as nlp
32 version = nlp.__version__
33 release = nlp.__version__
34
35 # General information about the project.
36 project = u'gluonnlp'
37 author = u'%s developers' % project
38 copyright = u'2018, %s' % author
39 github_doc_root = 'http://gluon-nlp.mxnet.io/{}/'.format(str(version))
40
41 # add markdown parser
42 CommonMarkParser.github_doc_root = github_doc_root
43 source_parsers = {
44 '.md': CommonMarkParser
45 }
46
47 # Add any Sphinx extension module names here, as strings. They can be
48 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom ones
49 extensions = [
50 'sphinx.ext.autodoc',
51 'sphinx.ext.autosummary',
52 'sphinx.ext.intersphinx',
53 'sphinx.ext.viewcode',
54 'sphinx.ext.napoleon',
55 'sphinx.ext.mathjax',
56 'sphinx_gallery.gen_gallery',
57 'nbsphinx',
58 ]
59
60 # Add any paths that contain templates here, relative to this directory.
61 templates_path = ['_templates']
62
63 nbsphinx_kernel_name = 'python3'
64 nbsphinx_allow_errors = True
65 nbsphinx_timeout = 1200
66 html_sourcelink_suffix = ''
67
68 nbsphinx_prolog = """
69 {% set paths = env.docname.split('/') %}
70
71 .. only:: html
72
73 :download:`[Download] <{{ "../%s.zip"|format(paths[1]) }}>`
74 """
75
76 # The suffix(es) of source filenames.
77 # You can specify multiple suffix as a list of string:
78 # source_suffix = ['.rst', '.md']
79 source_suffix = ['.rst', '.ipynb', '.md']
80
81 # The encoding of source files.
82 #source_encoding = 'utf-8-sig'
83
84 # generate autosummary even if no references
85 autosummary_generate = True
86
87 # The master toctree document.
88 master_doc = 'index'
89
90 # The language for content autogenerated by Sphinx. Refer to documentation
91 # for a list of supported languages.
92 #
93 # This is also used if you do content translation via gettext catalogs.
94 # Usually you set "language" from the command line for these cases.
95 language = None
96
97 # There are two options for replacing |today|: either, you set today to some
98 # non-false value, then it is used:
99 #today = ''
100 # Else, today_fmt is used as the format for a strftime call.
101 #today_fmt = '%B %d, %Y'
102
103 # The name of an image file (relative to this directory) to place at the top
104 # of the sidebar.
105 html_logo = '_static/gluon_white.png'
106
107 # The name of an image file (relative to this directory) to use as a favicon of
108 # the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
109 # pixels large.
110 html_favicon = '_static/gluon_s2.png'
111
112 # List of patterns, relative to source directory, that match files and
113 # directories to ignore when looking for source files.
114 exclude_patterns = ['_build', '**.ipynb_checkpoints']
115
116 # The reST default role (used for this markup: `text`) to use for all
117 # documents.
118 #default_role = None
119
120 # If true, '()' will be appended to :func: etc. cross-reference text.
121 #add_function_parentheses = True
122
123 # If true, the current module name will be prepended to all description
124 # unit titles (such as .. function::).
125 #add_module_names = True
126
127 # If true, sectionauthor and moduleauthor directives will be shown in the
128 # output. They are ignored by default.
129 #show_authors = False
130
131 # The name of the Pygments (syntax highlighting) style to use.
132 pygments_style = 'sphinx'
133
134 # A list of ignored prefixes for module index sorting.
135 #modindex_common_prefix = []
136
137 # If true, keep warnings as "system message" paragraphs in the built documents.
138 #keep_warnings = False
139
140 # If true, `todo` and `todoList` produce output, else they produce nothing.
141 todo_include_todos = False
142
143 # -- Options for HTML output ----------------------------------------------
144
145 # The theme is set by the make target
146 html_theme = os.environ.get('NNVM_THEME', 'rtd')
147
148 on_rtd = os.environ.get('READTHEDOCS', None) == 'True'
149 # only import rtd theme and set it if want to build docs locally
150 if not on_rtd and html_theme == 'rtd':
151 import sphinx_rtd_theme
152 html_theme = 'sphinx_rtd_theme'
153 html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
154
155 # Add any paths that contain custom static files (such as style sheets) here,
156 # relative to this directory. They are copied after the builtin static files,
157 # so a file named "default.css" will overwrite the builtin "default.css".
158 html_static_path = ['_static']
159
160 # Output file base name for HTML help builder.
161 htmlhelp_basename = project + 'doc'
162
163 # -- Options for LaTeX output ---------------------------------------------
164 latex_elements = {
165 }
166
167 # Grouping the document tree into LaTeX files. List of tuples
168 # (source start file, target name, title,
169 # author, documentclass [howto, manual, or own class]).
170 latex_documents = [
171 (master_doc, '%s.tex' % project, project,
172 author, 'manual'),
173 ]
174
175 # hook for doxygen
176 def run_doxygen(folder):
177 """Run the doxygen make command in the designated folder."""
178 try:
179 #retcode = subprocess.call("cd %s; make doc" % folder, shell=True)
180 retcode = subprocess.call("rm -rf _build/html/doxygen", shell=True)
181 retcode = subprocess.call("mkdir -p _build/html", shell=True)
182 retcode = subprocess.call("cp -rf doxygen/html _build/html/doxygen", shell=True)
183 if retcode < 0:
184 sys.stderr.write("doxygen terminated by signal %s" % (-retcode))
185 except OSError as e:
186 sys.stderr.write("doxygen execution failed: %s" % e)
187
188 intersphinx_mapping = {
189 'python': ('https://docs.python.org/{.major}'.format(sys.version_info), None),
190 'mxnet': ('https://mxnet.apache.org/', None),
191 'numpy': ('http://docs.scipy.org/doc/numpy/', None),
192 'scipy': ('http://docs.scipy.org/doc/scipy/reference', None),
193 'matplotlib': ('http://matplotlib.org/', None),
194 'nltk': ('http://www.nltk.org/', None),
195 }
196
197
198 from sphinx_gallery.sorting import ExplicitOrder
199
200 examples_dirs = []
201 gallery_dirs = []
202
203 subsection_order = ExplicitOrder([])
204
205 def generate_doxygen_xml(app):
206 """Run the doxygen make commands if we're on the ReadTheDocs server"""
207 run_doxygen('..')
208
209 def setup(app):
210 # Add hook for building doxygen xml when needed
211 # no c++ API for now
212 app.connect("builder-inited", generate_doxygen_xml)
213 app.add_config_value('recommonmark_config', {
214 'url_resolver': lambda url: github_doc_root + url,
215 'auto_doc_ref': True
216 }, True)
217 app.add_transform(AutoStructify)
218 app.add_javascript('google_analytics.js')
219
220
221 sphinx_gallery_conf = {
222 'backreferences_dir': 'gen_modules/backreferences',
223 'doc_module': ('gluonnlp', 'mxnet', 'numpy'),
224 'reference_url': {
225 'gluonnlp': None,
226 'numpy': 'http://docs.scipy.org/doc/numpy-1.9.1'},
227 'examples_dirs': examples_dirs,
228 'gallery_dirs': gallery_dirs,
229 'subsection_order': subsection_order,
230 'find_mayavi_figures': False,
231 'filename_pattern': '.py',
232 'expected_failing_examples': []
233 }
234
235 # Napoleon settings
236 napoleon_use_ivar = True
237
238
[end of docs/conf.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/docs/conf.py b/docs/conf.py
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -216,6 +216,7 @@
}, True)
app.add_transform(AutoStructify)
app.add_javascript('google_analytics.js')
+ app.add_javascript('copybutton.js')
sphinx_gallery_conf = {
| {"golden_diff": "diff --git a/docs/conf.py b/docs/conf.py\n--- a/docs/conf.py\n+++ b/docs/conf.py\n@@ -216,6 +216,7 @@\n }, True)\n app.add_transform(AutoStructify)\n app.add_javascript('google_analytics.js')\n+ app.add_javascript('copybutton.js')\n \n \n sphinx_gallery_conf = {\n", "issue": "API doc examples are currently not easy to copy/paste\nusers may want to use a snippet from example directly, so making the notebooks copy-friendly is important\r\n\r\ncurrently the code blocks have python shell prefix \">>>\" in them. see http://gluon-nlp.mxnet.io/api/notes/data_api.html\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n#\n# documentation build configuration file, created by\n# sphinx-quickstart on Thu Jul 23 19:40:08 2015.\n#\n# This file is execfile()d with the current directory set to its\n# containing dir.\n#\n# Note that not all possible configuration values are present in this\n# autogenerated file.\n#\n# All configuration values have a default; values that are commented out\n# serve to show the default.\nimport sys\nimport os, subprocess\nimport shlex\nimport recommonmark\nimport sphinx_gallery\nfrom recommonmark.parser import CommonMarkParser\nfrom recommonmark.transform import AutoStructify\n\n# If extensions (or modules to document with autodoc) are in another directory,\n# add these directories to sys.path here. If the directory is relative to the\n# documentation root, use os.path.abspath to make it absolute, like shown here.\ncurr_path = os.path.dirname(os.path.abspath(os.path.expanduser(__file__)))\nsys.path.insert(0, os.path.join(curr_path, '..'))\n\n# -- General configuration ------------------------------------------------\n\n# Version information.\nimport gluonnlp as nlp\nversion = nlp.__version__\nrelease = nlp.__version__\n\n# General information about the project.\nproject = u'gluonnlp'\nauthor = u'%s developers' % project\ncopyright = u'2018, %s' % author\ngithub_doc_root = 'http://gluon-nlp.mxnet.io/{}/'.format(str(version))\n\n# add markdown parser\nCommonMarkParser.github_doc_root = github_doc_root\nsource_parsers = {\n '.md': CommonMarkParser\n}\n\n# Add any Sphinx extension module names here, as strings. They can be\n# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom ones\nextensions = [\n 'sphinx.ext.autodoc',\n 'sphinx.ext.autosummary',\n 'sphinx.ext.intersphinx',\n 'sphinx.ext.viewcode',\n 'sphinx.ext.napoleon',\n 'sphinx.ext.mathjax',\n 'sphinx_gallery.gen_gallery',\n 'nbsphinx',\n]\n\n# Add any paths that contain templates here, relative to this directory.\ntemplates_path = ['_templates']\n\nnbsphinx_kernel_name = 'python3'\nnbsphinx_allow_errors = True\nnbsphinx_timeout = 1200\nhtml_sourcelink_suffix = ''\n\nnbsphinx_prolog = \"\"\"\n{% set paths = env.docname.split('/') %}\n\n.. only:: html\n\n :download:`[Download] <{{ \"../%s.zip\"|format(paths[1]) }}>`\n\"\"\"\n\n# The suffix(es) of source filenames.\n# You can specify multiple suffix as a list of string:\n# source_suffix = ['.rst', '.md']\nsource_suffix = ['.rst', '.ipynb', '.md']\n\n# The encoding of source files.\n#source_encoding = 'utf-8-sig'\n\n# generate autosummary even if no references\nautosummary_generate = True\n\n# The master toctree document.\nmaster_doc = 'index'\n\n# The language for content autogenerated by Sphinx. Refer to documentation\n# for a list of supported languages.\n#\n# This is also used if you do content translation via gettext catalogs.\n# Usually you set \"language\" from the command line for these cases.\nlanguage = None\n\n# There are two options for replacing |today|: either, you set today to some\n# non-false value, then it is used:\n#today = ''\n# Else, today_fmt is used as the format for a strftime call.\n#today_fmt = '%B %d, %Y'\n\n# The name of an image file (relative to this directory) to place at the top\n# of the sidebar.\nhtml_logo = '_static/gluon_white.png'\n\n# The name of an image file (relative to this directory) to use as a favicon of\n# the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32\n# pixels large.\nhtml_favicon = '_static/gluon_s2.png'\n\n# List of patterns, relative to source directory, that match files and\n# directories to ignore when looking for source files.\nexclude_patterns = ['_build', '**.ipynb_checkpoints']\n\n# The reST default role (used for this markup: `text`) to use for all\n# documents.\n#default_role = None\n\n# If true, '()' will be appended to :func: etc. cross-reference text.\n#add_function_parentheses = True\n\n# If true, the current module name will be prepended to all description\n# unit titles (such as .. function::).\n#add_module_names = True\n\n# If true, sectionauthor and moduleauthor directives will be shown in the\n# output. They are ignored by default.\n#show_authors = False\n\n# The name of the Pygments (syntax highlighting) style to use.\npygments_style = 'sphinx'\n\n# A list of ignored prefixes for module index sorting.\n#modindex_common_prefix = []\n\n# If true, keep warnings as \"system message\" paragraphs in the built documents.\n#keep_warnings = False\n\n# If true, `todo` and `todoList` produce output, else they produce nothing.\ntodo_include_todos = False\n\n# -- Options for HTML output ----------------------------------------------\n\n# The theme is set by the make target\nhtml_theme = os.environ.get('NNVM_THEME', 'rtd')\n\non_rtd = os.environ.get('READTHEDOCS', None) == 'True'\n# only import rtd theme and set it if want to build docs locally\nif not on_rtd and html_theme == 'rtd':\n import sphinx_rtd_theme\n html_theme = 'sphinx_rtd_theme'\n html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]\n\n# Add any paths that contain custom static files (such as style sheets) here,\n# relative to this directory. They are copied after the builtin static files,\n# so a file named \"default.css\" will overwrite the builtin \"default.css\".\nhtml_static_path = ['_static']\n\n# Output file base name for HTML help builder.\nhtmlhelp_basename = project + 'doc'\n\n# -- Options for LaTeX output ---------------------------------------------\nlatex_elements = {\n}\n\n# Grouping the document tree into LaTeX files. List of tuples\n# (source start file, target name, title,\n# author, documentclass [howto, manual, or own class]).\nlatex_documents = [\n (master_doc, '%s.tex' % project, project,\n author, 'manual'),\n]\n\n# hook for doxygen\ndef run_doxygen(folder):\n \"\"\"Run the doxygen make command in the designated folder.\"\"\"\n try:\n #retcode = subprocess.call(\"cd %s; make doc\" % folder, shell=True)\n retcode = subprocess.call(\"rm -rf _build/html/doxygen\", shell=True)\n retcode = subprocess.call(\"mkdir -p _build/html\", shell=True)\n retcode = subprocess.call(\"cp -rf doxygen/html _build/html/doxygen\", shell=True)\n if retcode < 0:\n sys.stderr.write(\"doxygen terminated by signal %s\" % (-retcode))\n except OSError as e:\n sys.stderr.write(\"doxygen execution failed: %s\" % e)\n\nintersphinx_mapping = {\n 'python': ('https://docs.python.org/{.major}'.format(sys.version_info), None),\n 'mxnet': ('https://mxnet.apache.org/', None),\n 'numpy': ('http://docs.scipy.org/doc/numpy/', None),\n 'scipy': ('http://docs.scipy.org/doc/scipy/reference', None),\n 'matplotlib': ('http://matplotlib.org/', None),\n 'nltk': ('http://www.nltk.org/', None),\n}\n\n\nfrom sphinx_gallery.sorting import ExplicitOrder\n\nexamples_dirs = []\ngallery_dirs = []\n\nsubsection_order = ExplicitOrder([])\n\ndef generate_doxygen_xml(app):\n \"\"\"Run the doxygen make commands if we're on the ReadTheDocs server\"\"\"\n run_doxygen('..')\n\ndef setup(app):\n # Add hook for building doxygen xml when needed\n # no c++ API for now\n app.connect(\"builder-inited\", generate_doxygen_xml)\n app.add_config_value('recommonmark_config', {\n 'url_resolver': lambda url: github_doc_root + url,\n 'auto_doc_ref': True\n }, True)\n app.add_transform(AutoStructify)\n app.add_javascript('google_analytics.js')\n\n\nsphinx_gallery_conf = {\n 'backreferences_dir': 'gen_modules/backreferences',\n 'doc_module': ('gluonnlp', 'mxnet', 'numpy'),\n'reference_url': {\n 'gluonnlp': None,\n 'numpy': 'http://docs.scipy.org/doc/numpy-1.9.1'},\n 'examples_dirs': examples_dirs,\n 'gallery_dirs': gallery_dirs,\n 'subsection_order': subsection_order,\n 'find_mayavi_figures': False,\n 'filename_pattern': '.py',\n 'expected_failing_examples': []\n}\n\n# Napoleon settings\nnapoleon_use_ivar = True\n\n", "path": "docs/conf.py"}]} | 3,195 | 80 |
gh_patches_debug_33949 | rasdani/github-patches | git_diff | xonsh__xonsh-522 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Feature-request: Static configuration file as a command line option
I suggest that an option to the commandline --config_file is added that allows the user to specify a file location for a static configuration file. (http://xonsh.org/xonshconfig.html)
This would allow portable usage of xonsh, e.g. install python and xonsh on a usb and bring the shell on a stick.
</issue>
<code>
[start of xonsh/main.py]
1 # -*- coding: utf-8 -*-
2 """The main xonsh script."""
3 import os
4 import sys
5 import shlex
6 import signal
7 import builtins
8 import subprocess
9 from argparse import ArgumentParser, Namespace
10 from contextlib import contextmanager
11
12 from xonsh import __version__
13 from xonsh.shell import Shell
14 from xonsh.pretty import pprint
15 from xonsh.jobs import ignore_sigtstp
16
17 parser = ArgumentParser(description='xonsh')
18 parser.add_argument('-V', '--version',
19 action='version',
20 version='/'.join(('xonsh', __version__)),
21 help='show version information and exit')
22 parser.add_argument('-c',
23 help="Run a single command and exit",
24 dest='command',
25 required=False,
26 default=None)
27 parser.add_argument('-i',
28 help='force running in interactive mode',
29 dest='force_interactive',
30 action='store_true',
31 default=False)
32 parser.add_argument('-l',
33 help='run as a login shell',
34 dest='login',
35 action='store_true',
36 default=False)
37 parser.add_argument('--no-rc',
38 help="Do not load the .xonshrc file",
39 dest='norc',
40 action='store_true',
41 default=False)
42 parser.add_argument('-D',
43 dest='defines',
44 help='define an environment variable, in the form of '
45 '-DNAME=VAL. May be used many times.',
46 metavar='ITEM',
47 nargs='*',
48 default=None)
49 parser.add_argument('--shell-type',
50 help='What kind of shell should be used. '
51 'Possible options: readline, prompt_toolkit. '
52 'Warning! If set this overrides $SHELL_TYPE variable.',
53 dest='shell_type',
54 choices=('readline', 'prompt_toolkit'),
55 default=None)
56 parser.add_argument('file',
57 metavar='script-file',
58 help='If present, execute the script in script-file'
59 ' and exit',
60 nargs='?',
61 default=None)
62 parser.add_argument('args',
63 metavar='args',
64 help='Additional arguments to the script specified'
65 ' by script-file',
66 nargs='*',
67 default=[])
68
69
70 def _pprint_displayhook(value):
71 if value is not None:
72 builtins._ = value
73 pprint(value)
74
75
76 def premain(argv=None):
77 """Setup for main xonsh entry point, returns parsed arguments."""
78 args = parser.parse_args(argv)
79 shell_kwargs = {'shell_type': args.shell_type}
80 if args.norc:
81 shell_kwargs['ctx'] = {}
82 setattr(sys, 'displayhook', _pprint_displayhook)
83 shell = builtins.__xonsh_shell__ = Shell(**shell_kwargs)
84 from xonsh import imphooks
85 env = builtins.__xonsh_env__
86 if args.defines is not None:
87 env.update([x.split('=', 1) for x in args.defines])
88 if args.login:
89 env['XONSH_LOGIN'] = True
90 env['XONSH_INTERACTIVE'] = False
91 return args
92
93
94 def main(argv=None):
95 """Main entry point for xonsh cli."""
96 args = premain(argv)
97 env = builtins.__xonsh_env__
98 shell = builtins.__xonsh_shell__
99 if args.command is not None:
100 # run a single command and exit
101 shell.default(args.command)
102 elif args.file is not None:
103 # run a script contained in a file
104 if os.path.isfile(args.file):
105 with open(args.file) as f:
106 code = f.read()
107 code = code if code.endswith('\n') else code + '\n'
108 env['ARGS'] = [args.file] + args.args
109 code = shell.execer.compile(code, mode='exec', glbs=shell.ctx)
110 shell.execer.exec(code, mode='exec', glbs=shell.ctx)
111 else:
112 print('xonsh: {0}: No such file or directory.'.format(args.file))
113 elif not sys.stdin.isatty() and not args.force_interactive:
114 # run a script given on stdin
115 code = sys.stdin.read()
116 code = code if code.endswith('\n') else code + '\n'
117 code = shell.execer.compile(code, mode='exec', glbs=shell.ctx)
118 shell.execer.exec(code, mode='exec', glbs=shell.ctx)
119 else:
120 # otherwise, enter the shell
121 env['XONSH_INTERACTIVE'] = True
122 ignore_sigtstp()
123 shell.cmdloop()
124 postmain(args)
125
126
127 def postmain(args=None):
128 """Teardown for main xonsh entry point, accepts parsed arguments."""
129 del builtins.__xonsh_shell__
130
131
132 @contextmanager
133 def main_context(argv=None):
134 """Generator that runs pre- and post-main() functions. This has two iterations.
135 The first yields the shell. The second returns None but cleans
136 up the shell.
137 """
138 args = premain(argv)
139 yield builtins.__xonsh_shell__
140 postmain(args)
141
142
143
144 if __name__ == '__main__':
145 main()
146
[end of xonsh/main.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/xonsh/main.py b/xonsh/main.py
--- a/xonsh/main.py
+++ b/xonsh/main.py
@@ -2,11 +2,8 @@
"""The main xonsh script."""
import os
import sys
-import shlex
-import signal
import builtins
-import subprocess
-from argparse import ArgumentParser, Namespace
+from argparse import ArgumentParser, ArgumentTypeError
from contextlib import contextmanager
from xonsh import __version__
@@ -14,6 +11,18 @@
from xonsh.pretty import pprint
from xonsh.jobs import ignore_sigtstp
+def path_argument(s):
+ """Return a path only if the path is actually legal
+
+ This is very similar to argparse.FileType, except that it doesn't return
+ an open file handle, but rather simply validates the path."""
+
+ s = os.path.abspath(os.path.expanduser(s))
+ if not os.path.isfile(s):
+ raise ArgumentTypeError('"%s" must be a valid path to a file' % s)
+ return s
+
+
parser = ArgumentParser(description='xonsh')
parser.add_argument('-V', '--version',
action='version',
@@ -34,6 +43,10 @@
dest='login',
action='store_true',
default=False)
+parser.add_argument('--config-path',
+ help='specify a custom static configuration file',
+ dest='config_path',
+ type=path_argument)
parser.add_argument('--no-rc',
help="Do not load the .xonshrc file",
dest='norc',
@@ -79,6 +92,8 @@
shell_kwargs = {'shell_type': args.shell_type}
if args.norc:
shell_kwargs['ctx'] = {}
+ if args.config_path:
+ shell_kwargs['ctx']= {'XONSHCONFIG': args.config_path}
setattr(sys, 'displayhook', _pprint_displayhook)
shell = builtins.__xonsh_shell__ = Shell(**shell_kwargs)
from xonsh import imphooks
| {"golden_diff": "diff --git a/xonsh/main.py b/xonsh/main.py\n--- a/xonsh/main.py\n+++ b/xonsh/main.py\n@@ -2,11 +2,8 @@\n \"\"\"The main xonsh script.\"\"\"\n import os\n import sys\n-import shlex\n-import signal\n import builtins\n-import subprocess\n-from argparse import ArgumentParser, Namespace\n+from argparse import ArgumentParser, ArgumentTypeError\n from contextlib import contextmanager\n \n from xonsh import __version__\n@@ -14,6 +11,18 @@\n from xonsh.pretty import pprint\n from xonsh.jobs import ignore_sigtstp\n \n+def path_argument(s):\n+ \"\"\"Return a path only if the path is actually legal\n+\n+ This is very similar to argparse.FileType, except that it doesn't return\n+ an open file handle, but rather simply validates the path.\"\"\"\n+\n+ s = os.path.abspath(os.path.expanduser(s))\n+ if not os.path.isfile(s):\n+ raise ArgumentTypeError('\"%s\" must be a valid path to a file' % s)\n+ return s\n+\n+\n parser = ArgumentParser(description='xonsh')\n parser.add_argument('-V', '--version',\n action='version',\n@@ -34,6 +43,10 @@\n dest='login',\n action='store_true',\n default=False)\n+parser.add_argument('--config-path',\n+ help='specify a custom static configuration file',\n+ dest='config_path',\n+ type=path_argument)\n parser.add_argument('--no-rc',\n help=\"Do not load the .xonshrc file\",\n dest='norc',\n@@ -79,6 +92,8 @@\n shell_kwargs = {'shell_type': args.shell_type}\n if args.norc:\n shell_kwargs['ctx'] = {}\n+ if args.config_path:\n+ shell_kwargs['ctx']= {'XONSHCONFIG': args.config_path}\n setattr(sys, 'displayhook', _pprint_displayhook)\n shell = builtins.__xonsh_shell__ = Shell(**shell_kwargs)\n from xonsh import imphooks\n", "issue": "Feature-request: Static configuration file as a command line option\nI suggest that an option to the commandline --config_file is added that allows the user to specify a file location for a static configuration file. (http://xonsh.org/xonshconfig.html)\n\nThis would allow portable usage of xonsh, e.g. install python and xonsh on a usb and bring the shell on a stick. \n\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\n\"\"\"The main xonsh script.\"\"\"\nimport os\nimport sys\nimport shlex\nimport signal\nimport builtins\nimport subprocess\nfrom argparse import ArgumentParser, Namespace\nfrom contextlib import contextmanager\n\nfrom xonsh import __version__\nfrom xonsh.shell import Shell\nfrom xonsh.pretty import pprint\nfrom xonsh.jobs import ignore_sigtstp\n\nparser = ArgumentParser(description='xonsh')\nparser.add_argument('-V', '--version',\n action='version',\n version='/'.join(('xonsh', __version__)),\n help='show version information and exit')\nparser.add_argument('-c',\n help=\"Run a single command and exit\",\n dest='command',\n required=False,\n default=None)\nparser.add_argument('-i',\n help='force running in interactive mode',\n dest='force_interactive',\n action='store_true',\n default=False)\nparser.add_argument('-l',\n help='run as a login shell',\n dest='login',\n action='store_true',\n default=False)\nparser.add_argument('--no-rc',\n help=\"Do not load the .xonshrc file\",\n dest='norc',\n action='store_true',\n default=False)\nparser.add_argument('-D',\n dest='defines',\n help='define an environment variable, in the form of '\n '-DNAME=VAL. May be used many times.',\n metavar='ITEM',\n nargs='*',\n default=None)\nparser.add_argument('--shell-type',\n help='What kind of shell should be used. '\n 'Possible options: readline, prompt_toolkit. '\n 'Warning! If set this overrides $SHELL_TYPE variable.',\n dest='shell_type',\n choices=('readline', 'prompt_toolkit'),\n default=None)\nparser.add_argument('file',\n metavar='script-file',\n help='If present, execute the script in script-file'\n ' and exit',\n nargs='?',\n default=None)\nparser.add_argument('args',\n metavar='args',\n help='Additional arguments to the script specified'\n ' by script-file',\n nargs='*',\n default=[])\n\n\ndef _pprint_displayhook(value):\n if value is not None:\n builtins._ = value\n pprint(value)\n\n\ndef premain(argv=None):\n \"\"\"Setup for main xonsh entry point, returns parsed arguments.\"\"\"\n args = parser.parse_args(argv)\n shell_kwargs = {'shell_type': args.shell_type}\n if args.norc:\n shell_kwargs['ctx'] = {}\n setattr(sys, 'displayhook', _pprint_displayhook)\n shell = builtins.__xonsh_shell__ = Shell(**shell_kwargs)\n from xonsh import imphooks\n env = builtins.__xonsh_env__\n if args.defines is not None:\n env.update([x.split('=', 1) for x in args.defines])\n if args.login:\n env['XONSH_LOGIN'] = True\n env['XONSH_INTERACTIVE'] = False\n return args\n\n\ndef main(argv=None):\n \"\"\"Main entry point for xonsh cli.\"\"\"\n args = premain(argv)\n env = builtins.__xonsh_env__\n shell = builtins.__xonsh_shell__\n if args.command is not None:\n # run a single command and exit\n shell.default(args.command)\n elif args.file is not None:\n # run a script contained in a file\n if os.path.isfile(args.file):\n with open(args.file) as f:\n code = f.read()\n code = code if code.endswith('\\n') else code + '\\n'\n env['ARGS'] = [args.file] + args.args\n code = shell.execer.compile(code, mode='exec', glbs=shell.ctx)\n shell.execer.exec(code, mode='exec', glbs=shell.ctx)\n else:\n print('xonsh: {0}: No such file or directory.'.format(args.file))\n elif not sys.stdin.isatty() and not args.force_interactive:\n # run a script given on stdin\n code = sys.stdin.read()\n code = code if code.endswith('\\n') else code + '\\n'\n code = shell.execer.compile(code, mode='exec', glbs=shell.ctx)\n shell.execer.exec(code, mode='exec', glbs=shell.ctx)\n else:\n # otherwise, enter the shell\n env['XONSH_INTERACTIVE'] = True\n ignore_sigtstp()\n shell.cmdloop()\n postmain(args)\n\n\ndef postmain(args=None):\n \"\"\"Teardown for main xonsh entry point, accepts parsed arguments.\"\"\"\n del builtins.__xonsh_shell__\n\n\n@contextmanager\ndef main_context(argv=None):\n \"\"\"Generator that runs pre- and post-main() functions. This has two iterations.\n The first yields the shell. The second returns None but cleans\n up the shell.\n \"\"\"\n args = premain(argv)\n yield builtins.__xonsh_shell__\n postmain(args)\n\n\n\nif __name__ == '__main__':\n main()\n", "path": "xonsh/main.py"}]} | 2,033 | 453 |
gh_patches_debug_29947 | rasdani/github-patches | git_diff | fossasia__open-event-server-7152 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
My Sessions: Server is returning duplicated data
**Describe the bug**
My Session is showing session's multiple times
**Expected behaviour**
Server should return session only once
**Screenshots**
[](http://www.youtube.com/watch?v=EMXLyCehYCM "multiple session")
Responses for Reference :
https://github.com/fossasia/open-event-frontend/pull/3811#issuecomment-575883439
https://github.com/fossasia/open-event-frontend/pull/3811#issuecomment-575882180
</issue>
<code>
[start of app/api/sessions.py]
1 from flask_jwt_extended import current_user
2 from flask_rest_jsonapi import ResourceDetail, ResourceList, ResourceRelationship
3
4 from app.api.bootstrap import api
5 from app.api.events import Event
6 from app.api.helpers.custom_forms import validate_custom_form_constraints_request
7 from app.api.helpers.db import get_count, safe_query, safe_query_kwargs, save_to_db
8 from app.api.helpers.errors import ForbiddenError
9 from app.api.helpers.files import make_frontend_url
10 from app.api.helpers.mail import send_email_new_session, send_email_session_accept_reject
11 from app.api.helpers.notification import (
12 send_notif_new_session_organizer,
13 send_notif_session_accept_reject,
14 )
15 from app.api.helpers.permission_manager import has_access
16 from app.api.helpers.query import event_query
17 from app.api.helpers.speaker import can_edit_after_cfs_ends
18 from app.api.helpers.utilities import require_relationship
19 from app.api.schema.sessions import SessionSchema
20 from app.models import db
21 from app.models.microlocation import Microlocation
22 from app.models.session import Session
23 from app.models.session_speaker_link import SessionsSpeakersLink
24 from app.models.session_type import SessionType
25 from app.models.speaker import Speaker
26 from app.models.track import Track
27 from app.models.user import User
28 from app.settings import get_settings
29
30
31 class SessionListPost(ResourceList):
32 """
33 List Sessions
34 """
35
36 def before_post(self, args, kwargs, data):
37 """
38 before post method to check for required relationship and proper permission
39 :param args:
40 :param kwargs:
41 :param data:
42 :return:
43 """
44 require_relationship(['event', 'track'], data)
45 data['creator_id'] = current_user.id
46 if (
47 get_count(
48 db.session.query(Event).filter_by(
49 id=int(data['event']), is_sessions_speakers_enabled=False
50 )
51 )
52 > 0
53 ):
54 raise ForbiddenError({'pointer': ''}, "Sessions are disabled for this Event")
55
56 data['complex_field_values'] = validate_custom_form_constraints_request(
57 'session', self.schema, Session(event_id=data['event']), data
58 )
59
60 def after_create_object(self, session, data, view_kwargs):
61 """
62 method to send email for creation of new session
63 mails session link to the concerned user
64 :param session:
65 :param data:
66 :param view_kwargs:
67 :return:
68 """
69 if session.event.get_owner():
70 event_name = session.event.name
71 owner = session.event.get_owner()
72 owner_email = owner.email
73 event = session.event
74 link = make_frontend_url(
75 "/events/{}/sessions/{}".format(event.identifier, session.id)
76 )
77 send_email_new_session(owner_email, event_name, link)
78 send_notif_new_session_organizer(owner, event_name, link, session.id)
79
80 for speaker in session.speakers:
81 session_speaker_link = SessionsSpeakersLink(
82 session_state=session.state,
83 session_id=session.id,
84 event_id=session.event.id,
85 speaker_id=speaker.id,
86 )
87 save_to_db(session_speaker_link, "Session Speaker Link Saved")
88
89 decorators = (api.has_permission('create_event'),)
90 schema = SessionSchema
91 data_layer = {
92 'session': db.session,
93 'model': Session,
94 'methods': {'after_create_object': after_create_object},
95 }
96
97
98 class SessionList(ResourceList):
99 """
100 List Sessions
101 """
102
103 def query(self, view_kwargs):
104 """
105 query method for SessionList class
106 :param view_kwargs:
107 :return:
108 """
109 query_ = self.session.query(Session)
110 if view_kwargs.get('track_id') is not None:
111 track = safe_query_kwargs(Track, view_kwargs, 'track_id')
112 query_ = query_.join(Track).filter(Track.id == track.id)
113 if view_kwargs.get('session_type_id') is not None:
114 session_type = safe_query_kwargs(SessionType, view_kwargs, 'session_type_id')
115 query_ = query_.join(SessionType).filter(SessionType.id == session_type.id)
116 if view_kwargs.get('microlocation_id') is not None:
117 microlocation = safe_query_kwargs(
118 Microlocation, view_kwargs, 'microlocation_id',
119 )
120 query_ = query_.join(Microlocation).filter(
121 Microlocation.id == microlocation.id
122 )
123 if view_kwargs.get('user_id') is not None:
124 user = safe_query_kwargs(User, view_kwargs, 'user_id')
125 query_ = (
126 query_.join(User)
127 .join(Speaker)
128 .filter(
129 (
130 User.id == user.id
131 or Session.speakers.any(Speaker.user_id == user.id)
132 )
133 )
134 )
135 query_ = event_query(query_, view_kwargs)
136 if view_kwargs.get('speaker_id'):
137 speaker = safe_query_kwargs(Speaker, view_kwargs, 'speaker_id')
138 # session-speaker :: many-to-many relationship
139 query_ = Session.query.filter(Session.speakers.any(id=speaker.id))
140
141 return query_
142
143 view_kwargs = True
144 methods = ['GET']
145 schema = SessionSchema
146 data_layer = {'session': db.session, 'model': Session, 'methods': {'query': query}}
147
148
149 class SessionDetail(ResourceDetail):
150 """
151 Session detail by id
152 """
153
154 def before_get_object(self, view_kwargs):
155 """
156 before get method to get the resource id for fetching details
157 :param view_kwargs:
158 :return:
159 """
160 if view_kwargs.get('event_identifier'):
161 event = safe_query(
162 Event, 'identifier', view_kwargs['event_identifier'], 'identifier'
163 )
164 view_kwargs['event_id'] = event.id
165
166 def before_update_object(self, session, data, view_kwargs):
167 """
168 before update method to verify if session is locked before updating session object
169 :param event:
170 :param data:
171 :param view_kwargs:
172 :return:
173 """
174 if session.is_locked:
175 if not (
176 has_access('is_admin')
177 or has_access('is_organizer', event_id=session.event_id)
178 ):
179 raise ForbiddenError(
180 {'source': '/data/attributes/is-locked'},
181 "You don't have enough permissions to change this property",
182 )
183
184 if session.is_locked and data.get('is_locked') != session.is_locked:
185 raise ForbiddenError(
186 {'source': '/data/attributes/is-locked'},
187 "Locked sessions cannot be edited",
188 )
189
190 if not can_edit_after_cfs_ends(session.event_id):
191 raise ForbiddenError(
192 {'source': ''}, "Cannot edit session after the call for speaker is ended"
193 )
194
195 data['complex_field_values'] = validate_custom_form_constraints_request(
196 'session', self.resource.schema, session, data
197 )
198
199 def after_update_object(self, session, data, view_kwargs):
200 """ Send email if session accepted or rejected """
201
202 if (
203 'state' in data
204 and data.get('send_email', None)
205 and (session.state == 'accepted' or session.state == 'rejected')
206 ):
207
208 event = session.event
209 # Email for speaker
210 speakers = session.speakers
211 for speaker in speakers:
212 frontend_url = get_settings()['frontend_url']
213 link = "{}/events/{}/sessions/{}".format(
214 frontend_url, event.identifier, session.id
215 )
216 if not speaker.is_email_overridden:
217 send_email_session_accept_reject(speaker.email, session, link)
218 send_notif_session_accept_reject(
219 speaker, session.title, session.state, link, session.id
220 )
221
222 # Email for owner
223 if session.event.get_owner():
224 owner = session.event.get_owner()
225 owner_email = owner.email
226 frontend_url = get_settings()['frontend_url']
227 link = "{}/events/{}/sessions/{}".format(
228 frontend_url, event.identifier, session.id
229 )
230 send_email_session_accept_reject(owner_email, session, link)
231 send_notif_session_accept_reject(
232 owner, session.title, session.state, link, session.id
233 )
234 if 'state' in data:
235 entry_count = SessionsSpeakersLink.query.filter_by(session_id=session.id)
236 if entry_count.count() == 0:
237 is_patch_request = False
238 else:
239 is_patch_request = True
240
241 if is_patch_request:
242 for focus_session in entry_count:
243 focus_session.session_state = session.state
244 db.session.commit()
245 else:
246 current_session = Session.query.filter_by(id=session.id).first()
247 for speaker in current_session.speakers:
248 session_speaker_link = SessionsSpeakersLink(
249 session_state=session.state,
250 session_id=session.id,
251 event_id=session.event.id,
252 speaker_id=speaker.id,
253 )
254 save_to_db(session_speaker_link, "Session Speaker Link Saved")
255
256 decorators = (api.has_permission('is_speaker_for_session', methods="PATCH,DELETE"),)
257 schema = SessionSchema
258 data_layer = {
259 'session': db.session,
260 'model': Session,
261 'methods': {
262 'before_update_object': before_update_object,
263 'before_get_object': before_get_object,
264 'after_update_object': after_update_object,
265 },
266 }
267
268
269 class SessionRelationshipRequired(ResourceRelationship):
270 """
271 Session Relationship
272 """
273
274 schema = SessionSchema
275 decorators = (api.has_permission('is_speaker_for_session', methods="PATCH,DELETE"),)
276 methods = ['GET', 'PATCH']
277 data_layer = {'session': db.session, 'model': Session}
278
279
280 class SessionRelationshipOptional(ResourceRelationship):
281 """
282 Session Relationship
283 """
284
285 schema = SessionSchema
286 decorators = (api.has_permission('is_speaker_for_session', methods="PATCH,DELETE"),)
287 data_layer = {'session': db.session, 'model': Session}
288
[end of app/api/sessions.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/app/api/sessions.py b/app/api/sessions.py
--- a/app/api/sessions.py
+++ b/app/api/sessions.py
@@ -1,5 +1,7 @@
+from flask import request
from flask_jwt_extended import current_user
from flask_rest_jsonapi import ResourceDetail, ResourceList, ResourceRelationship
+from flask_rest_jsonapi.querystring import QueryStringManager as QSManager
from app.api.bootstrap import api
from app.api.events import Event
@@ -95,6 +97,28 @@
}
+def get_distinct_sort_fields(schema, model, sort=True):
+ """Due to the poor code of flask-rest-jsonapi, distinct query needed
+ in sessions API to remove duplicate sessions can't be sorted on
+ returning subquery, thus we need to add all sort fields in distinct
+ group and repeat it in sort group as well"""
+ fields = []
+ qs = QSManager(request.args, schema)
+ for sort_opt in qs.sorting:
+ field = sort_opt['field']
+ if not hasattr(model, field):
+ continue
+ field = getattr(model, field)
+ if sort:
+ field = getattr(field, sort_opt['order'])()
+ fields.append(field)
+ field = Session.id
+ if sort:
+ field = field.desc()
+ fields.append(field)
+ return fields
+
+
class SessionList(ResourceList):
"""
List Sessions
@@ -131,6 +155,8 @@
or Session.speakers.any(Speaker.user_id == user.id)
)
)
+ .distinct(*get_distinct_sort_fields(SessionSchema, Session, sort=False))
+ .order_by(*get_distinct_sort_fields(SessionSchema, Session))
)
query_ = event_query(query_, view_kwargs)
if view_kwargs.get('speaker_id'):
| {"golden_diff": "diff --git a/app/api/sessions.py b/app/api/sessions.py\n--- a/app/api/sessions.py\n+++ b/app/api/sessions.py\n@@ -1,5 +1,7 @@\n+from flask import request\n from flask_jwt_extended import current_user\n from flask_rest_jsonapi import ResourceDetail, ResourceList, ResourceRelationship\n+from flask_rest_jsonapi.querystring import QueryStringManager as QSManager\n \n from app.api.bootstrap import api\n from app.api.events import Event\n@@ -95,6 +97,28 @@\n }\n \n \n+def get_distinct_sort_fields(schema, model, sort=True):\n+ \"\"\"Due to the poor code of flask-rest-jsonapi, distinct query needed\n+ in sessions API to remove duplicate sessions can't be sorted on\n+ returning subquery, thus we need to add all sort fields in distinct\n+ group and repeat it in sort group as well\"\"\"\n+ fields = []\n+ qs = QSManager(request.args, schema)\n+ for sort_opt in qs.sorting:\n+ field = sort_opt['field']\n+ if not hasattr(model, field):\n+ continue\n+ field = getattr(model, field)\n+ if sort:\n+ field = getattr(field, sort_opt['order'])()\n+ fields.append(field)\n+ field = Session.id\n+ if sort:\n+ field = field.desc()\n+ fields.append(field)\n+ return fields\n+\n+\n class SessionList(ResourceList):\n \"\"\"\n List Sessions\n@@ -131,6 +155,8 @@\n or Session.speakers.any(Speaker.user_id == user.id)\n )\n )\n+ .distinct(*get_distinct_sort_fields(SessionSchema, Session, sort=False))\n+ .order_by(*get_distinct_sort_fields(SessionSchema, Session))\n )\n query_ = event_query(query_, view_kwargs)\n if view_kwargs.get('speaker_id'):\n", "issue": "My Sessions: Server is returning duplicated data\n**Describe the bug**\r\nMy Session is showing session's multiple times \r\n\r\n\r\n**Expected behaviour**\r\nServer should return session only once\r\n\r\n**Screenshots**\r\n[](http://www.youtube.com/watch?v=EMXLyCehYCM \"multiple session\")\r\n\r\nResponses for Reference :\r\nhttps://github.com/fossasia/open-event-frontend/pull/3811#issuecomment-575883439\r\nhttps://github.com/fossasia/open-event-frontend/pull/3811#issuecomment-575882180\n", "before_files": [{"content": "from flask_jwt_extended import current_user\nfrom flask_rest_jsonapi import ResourceDetail, ResourceList, ResourceRelationship\n\nfrom app.api.bootstrap import api\nfrom app.api.events import Event\nfrom app.api.helpers.custom_forms import validate_custom_form_constraints_request\nfrom app.api.helpers.db import get_count, safe_query, safe_query_kwargs, save_to_db\nfrom app.api.helpers.errors import ForbiddenError\nfrom app.api.helpers.files import make_frontend_url\nfrom app.api.helpers.mail import send_email_new_session, send_email_session_accept_reject\nfrom app.api.helpers.notification import (\n send_notif_new_session_organizer,\n send_notif_session_accept_reject,\n)\nfrom app.api.helpers.permission_manager import has_access\nfrom app.api.helpers.query import event_query\nfrom app.api.helpers.speaker import can_edit_after_cfs_ends\nfrom app.api.helpers.utilities import require_relationship\nfrom app.api.schema.sessions import SessionSchema\nfrom app.models import db\nfrom app.models.microlocation import Microlocation\nfrom app.models.session import Session\nfrom app.models.session_speaker_link import SessionsSpeakersLink\nfrom app.models.session_type import SessionType\nfrom app.models.speaker import Speaker\nfrom app.models.track import Track\nfrom app.models.user import User\nfrom app.settings import get_settings\n\n\nclass SessionListPost(ResourceList):\n \"\"\"\n List Sessions\n \"\"\"\n\n def before_post(self, args, kwargs, data):\n \"\"\"\n before post method to check for required relationship and proper permission\n :param args:\n :param kwargs:\n :param data:\n :return:\n \"\"\"\n require_relationship(['event', 'track'], data)\n data['creator_id'] = current_user.id\n if (\n get_count(\n db.session.query(Event).filter_by(\n id=int(data['event']), is_sessions_speakers_enabled=False\n )\n )\n > 0\n ):\n raise ForbiddenError({'pointer': ''}, \"Sessions are disabled for this Event\")\n\n data['complex_field_values'] = validate_custom_form_constraints_request(\n 'session', self.schema, Session(event_id=data['event']), data\n )\n\n def after_create_object(self, session, data, view_kwargs):\n \"\"\"\n method to send email for creation of new session\n mails session link to the concerned user\n :param session:\n :param data:\n :param view_kwargs:\n :return:\n \"\"\"\n if session.event.get_owner():\n event_name = session.event.name\n owner = session.event.get_owner()\n owner_email = owner.email\n event = session.event\n link = make_frontend_url(\n \"/events/{}/sessions/{}\".format(event.identifier, session.id)\n )\n send_email_new_session(owner_email, event_name, link)\n send_notif_new_session_organizer(owner, event_name, link, session.id)\n\n for speaker in session.speakers:\n session_speaker_link = SessionsSpeakersLink(\n session_state=session.state,\n session_id=session.id,\n event_id=session.event.id,\n speaker_id=speaker.id,\n )\n save_to_db(session_speaker_link, \"Session Speaker Link Saved\")\n\n decorators = (api.has_permission('create_event'),)\n schema = SessionSchema\n data_layer = {\n 'session': db.session,\n 'model': Session,\n 'methods': {'after_create_object': after_create_object},\n }\n\n\nclass SessionList(ResourceList):\n \"\"\"\n List Sessions\n \"\"\"\n\n def query(self, view_kwargs):\n \"\"\"\n query method for SessionList class\n :param view_kwargs:\n :return:\n \"\"\"\n query_ = self.session.query(Session)\n if view_kwargs.get('track_id') is not None:\n track = safe_query_kwargs(Track, view_kwargs, 'track_id')\n query_ = query_.join(Track).filter(Track.id == track.id)\n if view_kwargs.get('session_type_id') is not None:\n session_type = safe_query_kwargs(SessionType, view_kwargs, 'session_type_id')\n query_ = query_.join(SessionType).filter(SessionType.id == session_type.id)\n if view_kwargs.get('microlocation_id') is not None:\n microlocation = safe_query_kwargs(\n Microlocation, view_kwargs, 'microlocation_id',\n )\n query_ = query_.join(Microlocation).filter(\n Microlocation.id == microlocation.id\n )\n if view_kwargs.get('user_id') is not None:\n user = safe_query_kwargs(User, view_kwargs, 'user_id')\n query_ = (\n query_.join(User)\n .join(Speaker)\n .filter(\n (\n User.id == user.id\n or Session.speakers.any(Speaker.user_id == user.id)\n )\n )\n )\n query_ = event_query(query_, view_kwargs)\n if view_kwargs.get('speaker_id'):\n speaker = safe_query_kwargs(Speaker, view_kwargs, 'speaker_id')\n # session-speaker :: many-to-many relationship\n query_ = Session.query.filter(Session.speakers.any(id=speaker.id))\n\n return query_\n\n view_kwargs = True\n methods = ['GET']\n schema = SessionSchema\n data_layer = {'session': db.session, 'model': Session, 'methods': {'query': query}}\n\n\nclass SessionDetail(ResourceDetail):\n \"\"\"\n Session detail by id\n \"\"\"\n\n def before_get_object(self, view_kwargs):\n \"\"\"\n before get method to get the resource id for fetching details\n :param view_kwargs:\n :return:\n \"\"\"\n if view_kwargs.get('event_identifier'):\n event = safe_query(\n Event, 'identifier', view_kwargs['event_identifier'], 'identifier'\n )\n view_kwargs['event_id'] = event.id\n\n def before_update_object(self, session, data, view_kwargs):\n \"\"\"\n before update method to verify if session is locked before updating session object\n :param event:\n :param data:\n :param view_kwargs:\n :return:\n \"\"\"\n if session.is_locked:\n if not (\n has_access('is_admin')\n or has_access('is_organizer', event_id=session.event_id)\n ):\n raise ForbiddenError(\n {'source': '/data/attributes/is-locked'},\n \"You don't have enough permissions to change this property\",\n )\n\n if session.is_locked and data.get('is_locked') != session.is_locked:\n raise ForbiddenError(\n {'source': '/data/attributes/is-locked'},\n \"Locked sessions cannot be edited\",\n )\n\n if not can_edit_after_cfs_ends(session.event_id):\n raise ForbiddenError(\n {'source': ''}, \"Cannot edit session after the call for speaker is ended\"\n )\n\n data['complex_field_values'] = validate_custom_form_constraints_request(\n 'session', self.resource.schema, session, data\n )\n\n def after_update_object(self, session, data, view_kwargs):\n \"\"\" Send email if session accepted or rejected \"\"\"\n\n if (\n 'state' in data\n and data.get('send_email', None)\n and (session.state == 'accepted' or session.state == 'rejected')\n ):\n\n event = session.event\n # Email for speaker\n speakers = session.speakers\n for speaker in speakers:\n frontend_url = get_settings()['frontend_url']\n link = \"{}/events/{}/sessions/{}\".format(\n frontend_url, event.identifier, session.id\n )\n if not speaker.is_email_overridden:\n send_email_session_accept_reject(speaker.email, session, link)\n send_notif_session_accept_reject(\n speaker, session.title, session.state, link, session.id\n )\n\n # Email for owner\n if session.event.get_owner():\n owner = session.event.get_owner()\n owner_email = owner.email\n frontend_url = get_settings()['frontend_url']\n link = \"{}/events/{}/sessions/{}\".format(\n frontend_url, event.identifier, session.id\n )\n send_email_session_accept_reject(owner_email, session, link)\n send_notif_session_accept_reject(\n owner, session.title, session.state, link, session.id\n )\n if 'state' in data:\n entry_count = SessionsSpeakersLink.query.filter_by(session_id=session.id)\n if entry_count.count() == 0:\n is_patch_request = False\n else:\n is_patch_request = True\n\n if is_patch_request:\n for focus_session in entry_count:\n focus_session.session_state = session.state\n db.session.commit()\n else:\n current_session = Session.query.filter_by(id=session.id).first()\n for speaker in current_session.speakers:\n session_speaker_link = SessionsSpeakersLink(\n session_state=session.state,\n session_id=session.id,\n event_id=session.event.id,\n speaker_id=speaker.id,\n )\n save_to_db(session_speaker_link, \"Session Speaker Link Saved\")\n\n decorators = (api.has_permission('is_speaker_for_session', methods=\"PATCH,DELETE\"),)\n schema = SessionSchema\n data_layer = {\n 'session': db.session,\n 'model': Session,\n 'methods': {\n 'before_update_object': before_update_object,\n 'before_get_object': before_get_object,\n 'after_update_object': after_update_object,\n },\n }\n\n\nclass SessionRelationshipRequired(ResourceRelationship):\n \"\"\"\n Session Relationship\n \"\"\"\n\n schema = SessionSchema\n decorators = (api.has_permission('is_speaker_for_session', methods=\"PATCH,DELETE\"),)\n methods = ['GET', 'PATCH']\n data_layer = {'session': db.session, 'model': Session}\n\n\nclass SessionRelationshipOptional(ResourceRelationship):\n \"\"\"\n Session Relationship\n \"\"\"\n\n schema = SessionSchema\n decorators = (api.has_permission('is_speaker_for_session', methods=\"PATCH,DELETE\"),)\n data_layer = {'session': db.session, 'model': Session}\n", "path": "app/api/sessions.py"}]} | 3,535 | 407 |
gh_patches_debug_33692 | rasdani/github-patches | git_diff | openshift__openshift-ansible-2092 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
[BUG] iptable insert
The following doesn't appear to handle a situation where the last rule in the INPUT chain is a DROP and we've witnessed behavior where the installer is appending the etcd 8443 rule after the DROP.
"os_firewall_manage_iptables.py" line 155 of 273
```
# Naively assume that if the last row is a REJECT rule, then
# we can add insert our rule right before it, otherwise we
# assume that we can just append the rule.
if (last_rule_num and last_rule_target
and last_rule_target == 'REJECT'):
# insert rule
cmd = self.cmd + ['-I', self.jump_rule_chain,
str(last_rule_num)]
else:
# append rule
cmd = self.cmd + ['-A', self.jump_rule_chain]
```
Suggested Fix
```
# Naively assume that if the last row is a REJECT rule, then
# we can add insert our rule right before it, otherwise we
# assume that we can just append the rule.
if (last_rule_num and last_rule_target
and ( last_rule_target == 'REJECT' || last_rule_target == 'DROP')):
# insert rule
cmd = self.cmd + ['-I', self.jump_rule_chain,
str(last_rule_num)]
else:
# append rule
cmd = self.cmd + ['-A', self.jump_rule_chain]
cmd += ['-j', self.chain]
```
</issue>
<code>
[start of roles/os_firewall/library/os_firewall_manage_iptables.py]
1 #!/usr/bin/python
2 # -*- coding: utf-8 -*-
3 # vim: expandtab:tabstop=4:shiftwidth=4
4 # pylint: disable=fixme, missing-docstring
5 from subprocess import call, check_output
6
7 DOCUMENTATION = '''
8 ---
9 module: os_firewall_manage_iptables
10 short_description: This module manages iptables rules for a given chain
11 author: Jason DeTiberus
12 requirements: [ ]
13 '''
14 EXAMPLES = '''
15 '''
16
17
18 class IpTablesError(Exception):
19 def __init__(self, msg, cmd, exit_code, output):
20 super(IpTablesError, self).__init__(msg)
21 self.msg = msg
22 self.cmd = cmd
23 self.exit_code = exit_code
24 self.output = output
25
26
27 class IpTablesAddRuleError(IpTablesError):
28 pass
29
30
31 class IpTablesRemoveRuleError(IpTablesError):
32 pass
33
34
35 class IpTablesSaveError(IpTablesError):
36 pass
37
38
39 class IpTablesCreateChainError(IpTablesError):
40 def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long
41 super(IpTablesCreateChainError, self).__init__(msg, cmd, exit_code,
42 output)
43 self.chain = chain
44
45
46 class IpTablesCreateJumpRuleError(IpTablesError):
47 def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long
48 super(IpTablesCreateJumpRuleError, self).__init__(msg, cmd, exit_code,
49 output)
50 self.chain = chain
51
52
53 # TODO: impliment rollbacks for any events that where successful and an
54 # exception was thrown later. for example, when the chain is created
55 # successfully, but the add/remove rule fails.
56 class IpTablesManager(object): # pylint: disable=too-many-instance-attributes
57 def __init__(self, module):
58 self.module = module
59 self.ip_version = module.params['ip_version']
60 self.check_mode = module.check_mode
61 self.chain = module.params['chain']
62 self.create_jump_rule = module.params['create_jump_rule']
63 self.jump_rule_chain = module.params['jump_rule_chain']
64 self.cmd = self.gen_cmd()
65 self.save_cmd = self.gen_save_cmd()
66 self.output = []
67 self.changed = False
68
69 def save(self):
70 try:
71 self.output.append(check_output(self.save_cmd,
72 stderr=subprocess.STDOUT))
73 except subprocess.CalledProcessError as ex:
74 raise IpTablesSaveError(
75 msg="Failed to save iptables rules",
76 cmd=ex.cmd, exit_code=ex.returncode, output=ex.output)
77
78 def verify_chain(self):
79 if not self.chain_exists():
80 self.create_chain()
81 if self.create_jump_rule and not self.jump_rule_exists():
82 self.create_jump()
83
84 def add_rule(self, port, proto):
85 rule = self.gen_rule(port, proto)
86 if not self.rule_exists(rule):
87 self.verify_chain()
88
89 if self.check_mode:
90 self.changed = True
91 self.output.append("Create rule for %s %s" % (proto, port))
92 else:
93 cmd = self.cmd + ['-A'] + rule
94 try:
95 self.output.append(check_output(cmd))
96 self.changed = True
97 self.save()
98 except subprocess.CalledProcessError as ex:
99 raise IpTablesCreateChainError(
100 chain=self.chain,
101 msg="Failed to create rule for "
102 "%s %s" % (proto, port),
103 cmd=ex.cmd, exit_code=ex.returncode,
104 output=ex.output)
105
106 def remove_rule(self, port, proto):
107 rule = self.gen_rule(port, proto)
108 if self.rule_exists(rule):
109 if self.check_mode:
110 self.changed = True
111 self.output.append("Remove rule for %s %s" % (proto, port))
112 else:
113 cmd = self.cmd + ['-D'] + rule
114 try:
115 self.output.append(check_output(cmd))
116 self.changed = True
117 self.save()
118 except subprocess.CalledProcessError as ex:
119 raise IpTablesRemoveRuleError(
120 chain=self.chain,
121 msg="Failed to remove rule for %s %s" % (proto, port),
122 cmd=ex.cmd, exit_code=ex.returncode, output=ex.output)
123
124 def rule_exists(self, rule):
125 check_cmd = self.cmd + ['-C'] + rule
126 return True if call(check_cmd) == 0 else False
127
128 def gen_rule(self, port, proto):
129 return [self.chain, '-p', proto, '-m', 'state', '--state', 'NEW',
130 '-m', proto, '--dport', str(port), '-j', 'ACCEPT']
131
132 def create_jump(self):
133 if self.check_mode:
134 self.changed = True
135 self.output.append("Create jump rule for chain %s" % self.chain)
136 else:
137 try:
138 cmd = self.cmd + ['-L', self.jump_rule_chain, '--line-numbers']
139 output = check_output(cmd, stderr=subprocess.STDOUT)
140
141 # break the input rules into rows and columns
142 input_rules = [s.split() for s in output.split('\n')]
143
144 # Find the last numbered rule
145 last_rule_num = None
146 last_rule_target = None
147 for rule in input_rules[:-1]:
148 if rule:
149 try:
150 last_rule_num = int(rule[0])
151 except ValueError:
152 continue
153 last_rule_target = rule[1]
154
155 # Naively assume that if the last row is a REJECT rule, then
156 # we can add insert our rule right before it, otherwise we
157 # assume that we can just append the rule.
158 if (last_rule_num and last_rule_target
159 and last_rule_target == 'REJECT'):
160 # insert rule
161 cmd = self.cmd + ['-I', self.jump_rule_chain,
162 str(last_rule_num)]
163 else:
164 # append rule
165 cmd = self.cmd + ['-A', self.jump_rule_chain]
166 cmd += ['-j', self.chain]
167 output = check_output(cmd, stderr=subprocess.STDOUT)
168 self.changed = True
169 self.output.append(output)
170 self.save()
171 except subprocess.CalledProcessError as ex:
172 if '--line-numbers' in ex.cmd:
173 raise IpTablesCreateJumpRuleError(
174 chain=self.chain,
175 msg=("Failed to query existing " +
176 self.jump_rule_chain +
177 " rules to determine jump rule location"),
178 cmd=ex.cmd, exit_code=ex.returncode,
179 output=ex.output)
180 else:
181 raise IpTablesCreateJumpRuleError(
182 chain=self.chain,
183 msg=("Failed to create jump rule for chain " +
184 self.chain),
185 cmd=ex.cmd, exit_code=ex.returncode,
186 output=ex.output)
187
188 def create_chain(self):
189 if self.check_mode:
190 self.changed = True
191 self.output.append("Create chain %s" % self.chain)
192 else:
193 try:
194 cmd = self.cmd + ['-N', self.chain]
195 self.output.append(check_output(cmd,
196 stderr=subprocess.STDOUT))
197 self.changed = True
198 self.output.append("Successfully created chain %s" %
199 self.chain)
200 self.save()
201 except subprocess.CalledProcessError as ex:
202 raise IpTablesCreateChainError(
203 chain=self.chain,
204 msg="Failed to create chain: %s" % self.chain,
205 cmd=ex.cmd, exit_code=ex.returncode, output=ex.output
206 )
207
208 def jump_rule_exists(self):
209 cmd = self.cmd + ['-C', self.jump_rule_chain, '-j', self.chain]
210 return True if call(cmd) == 0 else False
211
212 def chain_exists(self):
213 cmd = self.cmd + ['-L', self.chain]
214 return True if call(cmd) == 0 else False
215
216 def gen_cmd(self):
217 cmd = 'iptables' if self.ip_version == 'ipv4' else 'ip6tables'
218 return ["/usr/sbin/%s" % cmd]
219
220 def gen_save_cmd(self): # pylint: disable=no-self-use
221 return ['/usr/libexec/iptables/iptables.init', 'save']
222
223
224 def main():
225 module = AnsibleModule(
226 argument_spec=dict(
227 name=dict(required=True),
228 action=dict(required=True, choices=['add', 'remove',
229 'verify_chain']),
230 chain=dict(required=False, default='OS_FIREWALL_ALLOW'),
231 create_jump_rule=dict(required=False, type='bool', default=True),
232 jump_rule_chain=dict(required=False, default='INPUT'),
233 protocol=dict(required=False, choices=['tcp', 'udp']),
234 port=dict(required=False, type='int'),
235 ip_version=dict(required=False, default='ipv4',
236 choices=['ipv4', 'ipv6']),
237 ),
238 supports_check_mode=True
239 )
240
241 action = module.params['action']
242 protocol = module.params['protocol']
243 port = module.params['port']
244
245 if action in ['add', 'remove']:
246 if not protocol:
247 error = "protocol is required when action is %s" % action
248 module.fail_json(msg=error)
249 if not port:
250 error = "port is required when action is %s" % action
251 module.fail_json(msg=error)
252
253 iptables_manager = IpTablesManager(module)
254
255 try:
256 if action == 'add':
257 iptables_manager.add_rule(port, protocol)
258 elif action == 'remove':
259 iptables_manager.remove_rule(port, protocol)
260 elif action == 'verify_chain':
261 iptables_manager.verify_chain()
262 except IpTablesError as ex:
263 module.fail_json(msg=ex.msg)
264
265 return module.exit_json(changed=iptables_manager.changed,
266 output=iptables_manager.output)
267
268
269 # pylint: disable=redefined-builtin, unused-wildcard-import, wildcard-import
270 # import module snippets
271 from ansible.module_utils.basic import *
272 if __name__ == '__main__':
273 main()
274
[end of roles/os_firewall/library/os_firewall_manage_iptables.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/roles/os_firewall/library/os_firewall_manage_iptables.py b/roles/os_firewall/library/os_firewall_manage_iptables.py
--- a/roles/os_firewall/library/os_firewall_manage_iptables.py
+++ b/roles/os_firewall/library/os_firewall_manage_iptables.py
@@ -37,14 +37,14 @@
class IpTablesCreateChainError(IpTablesError):
- def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long
+ def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long, redefined-outer-name
super(IpTablesCreateChainError, self).__init__(msg, cmd, exit_code,
output)
self.chain = chain
class IpTablesCreateJumpRuleError(IpTablesError):
- def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long
+ def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long, redefined-outer-name
super(IpTablesCreateJumpRuleError, self).__init__(msg, cmd, exit_code,
output)
self.chain = chain
@@ -152,11 +152,11 @@
continue
last_rule_target = rule[1]
- # Naively assume that if the last row is a REJECT rule, then
- # we can add insert our rule right before it, otherwise we
+ # Naively assume that if the last row is a REJECT or DROP rule,
+ # then we can insert our rule right before it, otherwise we
# assume that we can just append the rule.
if (last_rule_num and last_rule_target
- and last_rule_target == 'REJECT'):
+ and last_rule_target in ['REJECT', 'DROP']):
# insert rule
cmd = self.cmd + ['-I', self.jump_rule_chain,
str(last_rule_num)]
| {"golden_diff": "diff --git a/roles/os_firewall/library/os_firewall_manage_iptables.py b/roles/os_firewall/library/os_firewall_manage_iptables.py\n--- a/roles/os_firewall/library/os_firewall_manage_iptables.py\n+++ b/roles/os_firewall/library/os_firewall_manage_iptables.py\n@@ -37,14 +37,14 @@\n \n \n class IpTablesCreateChainError(IpTablesError):\n- def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long\n+ def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long, redefined-outer-name\n super(IpTablesCreateChainError, self).__init__(msg, cmd, exit_code,\n output)\n self.chain = chain\n \n \n class IpTablesCreateJumpRuleError(IpTablesError):\n- def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long\n+ def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long, redefined-outer-name\n super(IpTablesCreateJumpRuleError, self).__init__(msg, cmd, exit_code,\n output)\n self.chain = chain\n@@ -152,11 +152,11 @@\n continue\n last_rule_target = rule[1]\n \n- # Naively assume that if the last row is a REJECT rule, then\n- # we can add insert our rule right before it, otherwise we\n+ # Naively assume that if the last row is a REJECT or DROP rule,\n+ # then we can insert our rule right before it, otherwise we\n # assume that we can just append the rule.\n if (last_rule_num and last_rule_target\n- and last_rule_target == 'REJECT'):\n+ and last_rule_target in ['REJECT', 'DROP']):\n # insert rule\n cmd = self.cmd + ['-I', self.jump_rule_chain,\n str(last_rule_num)]\n", "issue": "[BUG] iptable insert \nThe following doesn't appear to handle a situation where the last rule in the INPUT chain is a DROP and we've witnessed behavior where the installer is appending the etcd 8443 rule after the DROP. \n\n\"os_firewall_manage_iptables.py\" line 155 of 273\n\n```\n # Naively assume that if the last row is a REJECT rule, then\n # we can add insert our rule right before it, otherwise we\n # assume that we can just append the rule.\n if (last_rule_num and last_rule_target\n and last_rule_target == 'REJECT'):\n # insert rule\n cmd = self.cmd + ['-I', self.jump_rule_chain,\n str(last_rule_num)]\n else:\n # append rule\n cmd = self.cmd + ['-A', self.jump_rule_chain]\n```\n\nSuggested Fix\n\n```\n # Naively assume that if the last row is a REJECT rule, then\n # we can add insert our rule right before it, otherwise we\n # assume that we can just append the rule.\n if (last_rule_num and last_rule_target\n and ( last_rule_target == 'REJECT' || last_rule_target == 'DROP')):\n # insert rule\n cmd = self.cmd + ['-I', self.jump_rule_chain,\n str(last_rule_num)]\n else:\n # append rule\n cmd = self.cmd + ['-A', self.jump_rule_chain]\n cmd += ['-j', self.chain]\n```\n\n", "before_files": [{"content": "#!/usr/bin/python\n# -*- coding: utf-8 -*-\n# vim: expandtab:tabstop=4:shiftwidth=4\n# pylint: disable=fixme, missing-docstring\nfrom subprocess import call, check_output\n\nDOCUMENTATION = '''\n---\nmodule: os_firewall_manage_iptables\nshort_description: This module manages iptables rules for a given chain\nauthor: Jason DeTiberus\nrequirements: [ ]\n'''\nEXAMPLES = '''\n'''\n\n\nclass IpTablesError(Exception):\n def __init__(self, msg, cmd, exit_code, output):\n super(IpTablesError, self).__init__(msg)\n self.msg = msg\n self.cmd = cmd\n self.exit_code = exit_code\n self.output = output\n\n\nclass IpTablesAddRuleError(IpTablesError):\n pass\n\n\nclass IpTablesRemoveRuleError(IpTablesError):\n pass\n\n\nclass IpTablesSaveError(IpTablesError):\n pass\n\n\nclass IpTablesCreateChainError(IpTablesError):\n def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long\n super(IpTablesCreateChainError, self).__init__(msg, cmd, exit_code,\n output)\n self.chain = chain\n\n\nclass IpTablesCreateJumpRuleError(IpTablesError):\n def __init__(self, chain, msg, cmd, exit_code, output): # pylint: disable=too-many-arguments, line-too-long\n super(IpTablesCreateJumpRuleError, self).__init__(msg, cmd, exit_code,\n output)\n self.chain = chain\n\n\n# TODO: impliment rollbacks for any events that where successful and an\n# exception was thrown later. for example, when the chain is created\n# successfully, but the add/remove rule fails.\nclass IpTablesManager(object): # pylint: disable=too-many-instance-attributes\n def __init__(self, module):\n self.module = module\n self.ip_version = module.params['ip_version']\n self.check_mode = module.check_mode\n self.chain = module.params['chain']\n self.create_jump_rule = module.params['create_jump_rule']\n self.jump_rule_chain = module.params['jump_rule_chain']\n self.cmd = self.gen_cmd()\n self.save_cmd = self.gen_save_cmd()\n self.output = []\n self.changed = False\n\n def save(self):\n try:\n self.output.append(check_output(self.save_cmd,\n stderr=subprocess.STDOUT))\n except subprocess.CalledProcessError as ex:\n raise IpTablesSaveError(\n msg=\"Failed to save iptables rules\",\n cmd=ex.cmd, exit_code=ex.returncode, output=ex.output)\n\n def verify_chain(self):\n if not self.chain_exists():\n self.create_chain()\n if self.create_jump_rule and not self.jump_rule_exists():\n self.create_jump()\n\n def add_rule(self, port, proto):\n rule = self.gen_rule(port, proto)\n if not self.rule_exists(rule):\n self.verify_chain()\n\n if self.check_mode:\n self.changed = True\n self.output.append(\"Create rule for %s %s\" % (proto, port))\n else:\n cmd = self.cmd + ['-A'] + rule\n try:\n self.output.append(check_output(cmd))\n self.changed = True\n self.save()\n except subprocess.CalledProcessError as ex:\n raise IpTablesCreateChainError(\n chain=self.chain,\n msg=\"Failed to create rule for \"\n \"%s %s\" % (proto, port),\n cmd=ex.cmd, exit_code=ex.returncode,\n output=ex.output)\n\n def remove_rule(self, port, proto):\n rule = self.gen_rule(port, proto)\n if self.rule_exists(rule):\n if self.check_mode:\n self.changed = True\n self.output.append(\"Remove rule for %s %s\" % (proto, port))\n else:\n cmd = self.cmd + ['-D'] + rule\n try:\n self.output.append(check_output(cmd))\n self.changed = True\n self.save()\n except subprocess.CalledProcessError as ex:\n raise IpTablesRemoveRuleError(\n chain=self.chain,\n msg=\"Failed to remove rule for %s %s\" % (proto, port),\n cmd=ex.cmd, exit_code=ex.returncode, output=ex.output)\n\n def rule_exists(self, rule):\n check_cmd = self.cmd + ['-C'] + rule\n return True if call(check_cmd) == 0 else False\n\n def gen_rule(self, port, proto):\n return [self.chain, '-p', proto, '-m', 'state', '--state', 'NEW',\n '-m', proto, '--dport', str(port), '-j', 'ACCEPT']\n\n def create_jump(self):\n if self.check_mode:\n self.changed = True\n self.output.append(\"Create jump rule for chain %s\" % self.chain)\n else:\n try:\n cmd = self.cmd + ['-L', self.jump_rule_chain, '--line-numbers']\n output = check_output(cmd, stderr=subprocess.STDOUT)\n\n # break the input rules into rows and columns\n input_rules = [s.split() for s in output.split('\\n')]\n\n # Find the last numbered rule\n last_rule_num = None\n last_rule_target = None\n for rule in input_rules[:-1]:\n if rule:\n try:\n last_rule_num = int(rule[0])\n except ValueError:\n continue\n last_rule_target = rule[1]\n\n # Naively assume that if the last row is a REJECT rule, then\n # we can add insert our rule right before it, otherwise we\n # assume that we can just append the rule.\n if (last_rule_num and last_rule_target\n and last_rule_target == 'REJECT'):\n # insert rule\n cmd = self.cmd + ['-I', self.jump_rule_chain,\n str(last_rule_num)]\n else:\n # append rule\n cmd = self.cmd + ['-A', self.jump_rule_chain]\n cmd += ['-j', self.chain]\n output = check_output(cmd, stderr=subprocess.STDOUT)\n self.changed = True\n self.output.append(output)\n self.save()\n except subprocess.CalledProcessError as ex:\n if '--line-numbers' in ex.cmd:\n raise IpTablesCreateJumpRuleError(\n chain=self.chain,\n msg=(\"Failed to query existing \" +\n self.jump_rule_chain +\n \" rules to determine jump rule location\"),\n cmd=ex.cmd, exit_code=ex.returncode,\n output=ex.output)\n else:\n raise IpTablesCreateJumpRuleError(\n chain=self.chain,\n msg=(\"Failed to create jump rule for chain \" +\n self.chain),\n cmd=ex.cmd, exit_code=ex.returncode,\n output=ex.output)\n\n def create_chain(self):\n if self.check_mode:\n self.changed = True\n self.output.append(\"Create chain %s\" % self.chain)\n else:\n try:\n cmd = self.cmd + ['-N', self.chain]\n self.output.append(check_output(cmd,\n stderr=subprocess.STDOUT))\n self.changed = True\n self.output.append(\"Successfully created chain %s\" %\n self.chain)\n self.save()\n except subprocess.CalledProcessError as ex:\n raise IpTablesCreateChainError(\n chain=self.chain,\n msg=\"Failed to create chain: %s\" % self.chain,\n cmd=ex.cmd, exit_code=ex.returncode, output=ex.output\n )\n\n def jump_rule_exists(self):\n cmd = self.cmd + ['-C', self.jump_rule_chain, '-j', self.chain]\n return True if call(cmd) == 0 else False\n\n def chain_exists(self):\n cmd = self.cmd + ['-L', self.chain]\n return True if call(cmd) == 0 else False\n\n def gen_cmd(self):\n cmd = 'iptables' if self.ip_version == 'ipv4' else 'ip6tables'\n return [\"/usr/sbin/%s\" % cmd]\n\n def gen_save_cmd(self): # pylint: disable=no-self-use\n return ['/usr/libexec/iptables/iptables.init', 'save']\n\n\ndef main():\n module = AnsibleModule(\n argument_spec=dict(\n name=dict(required=True),\n action=dict(required=True, choices=['add', 'remove',\n 'verify_chain']),\n chain=dict(required=False, default='OS_FIREWALL_ALLOW'),\n create_jump_rule=dict(required=False, type='bool', default=True),\n jump_rule_chain=dict(required=False, default='INPUT'),\n protocol=dict(required=False, choices=['tcp', 'udp']),\n port=dict(required=False, type='int'),\n ip_version=dict(required=False, default='ipv4',\n choices=['ipv4', 'ipv6']),\n ),\n supports_check_mode=True\n )\n\n action = module.params['action']\n protocol = module.params['protocol']\n port = module.params['port']\n\n if action in ['add', 'remove']:\n if not protocol:\n error = \"protocol is required when action is %s\" % action\n module.fail_json(msg=error)\n if not port:\n error = \"port is required when action is %s\" % action\n module.fail_json(msg=error)\n\n iptables_manager = IpTablesManager(module)\n\n try:\n if action == 'add':\n iptables_manager.add_rule(port, protocol)\n elif action == 'remove':\n iptables_manager.remove_rule(port, protocol)\n elif action == 'verify_chain':\n iptables_manager.verify_chain()\n except IpTablesError as ex:\n module.fail_json(msg=ex.msg)\n\n return module.exit_json(changed=iptables_manager.changed,\n output=iptables_manager.output)\n\n\n# pylint: disable=redefined-builtin, unused-wildcard-import, wildcard-import\n# import module snippets\nfrom ansible.module_utils.basic import *\nif __name__ == '__main__':\n main()\n", "path": "roles/os_firewall/library/os_firewall_manage_iptables.py"}]} | 3,741 | 481 |
gh_patches_debug_23517 | rasdani/github-patches | git_diff | hydroshare__hydroshare-2550 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Can't add user via admin panel
</issue>
<code>
[start of hs_core/admin.py]
1 from mezzanine.pages.admin import PageAdmin
2 from django.contrib.gis import admin
3 from django.contrib.contenttypes.admin import GenericTabularInline
4 from .models import *
5
6 class InlineResourceFiles(GenericTabularInline):
7 model = ResourceFile
8
9 class GenericResourceAdmin(PageAdmin):
10 inlines = PageAdmin.inlines + [InlineResourceFiles]
11
12 admin.site.register(GenericResource, GenericResourceAdmin)
13
[end of hs_core/admin.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/hs_core/admin.py b/hs_core/admin.py
--- a/hs_core/admin.py
+++ b/hs_core/admin.py
@@ -1,12 +1,35 @@
-from mezzanine.pages.admin import PageAdmin
+from django import forms
+from django.contrib.auth.admin import UserAdmin
+from django.contrib.auth.forms import UserCreationForm
+from django.contrib.auth.models import User
from django.contrib.gis import admin
from django.contrib.contenttypes.admin import GenericTabularInline
+from django.utils.translation import ugettext_lazy as _
+
+from mezzanine.pages.admin import PageAdmin
+
from .models import *
+
+class UserCreationFormExtended(UserCreationForm):
+ def __init__(self, *args, **kwargs):
+ super(UserCreationFormExtended, self).__init__(*args, **kwargs)
+ self.fields['email'] = forms.EmailField(label=_("E-mail"), max_length=75)
+
+UserAdmin.add_form = UserCreationFormExtended
+UserAdmin.add_fieldsets = (
+ (None, {
+ 'classes': ('wide',),
+ 'fields': ('email', 'username', 'password1', 'password2',)
+ }),
+)
+
class InlineResourceFiles(GenericTabularInline):
model = ResourceFile
class GenericResourceAdmin(PageAdmin):
inlines = PageAdmin.inlines + [InlineResourceFiles]
+admin.site.unregister(User)
+admin.site.register(User, UserAdmin)
admin.site.register(GenericResource, GenericResourceAdmin)
| {"golden_diff": "diff --git a/hs_core/admin.py b/hs_core/admin.py\n--- a/hs_core/admin.py\n+++ b/hs_core/admin.py\n@@ -1,12 +1,35 @@\n-from mezzanine.pages.admin import PageAdmin\n+from django import forms\n+from django.contrib.auth.admin import UserAdmin\n+from django.contrib.auth.forms import UserCreationForm\n+from django.contrib.auth.models import User\n from django.contrib.gis import admin\n from django.contrib.contenttypes.admin import GenericTabularInline\n+from django.utils.translation import ugettext_lazy as _\n+\n+from mezzanine.pages.admin import PageAdmin\n+\n from .models import *\n \n+\n+class UserCreationFormExtended(UserCreationForm):\n+ def __init__(self, *args, **kwargs):\n+ super(UserCreationFormExtended, self).__init__(*args, **kwargs)\n+ self.fields['email'] = forms.EmailField(label=_(\"E-mail\"), max_length=75)\n+\n+UserAdmin.add_form = UserCreationFormExtended\n+UserAdmin.add_fieldsets = (\n+ (None, {\n+ 'classes': ('wide',),\n+ 'fields': ('email', 'username', 'password1', 'password2',)\n+ }),\n+)\n+\n class InlineResourceFiles(GenericTabularInline):\n model = ResourceFile\n \n class GenericResourceAdmin(PageAdmin):\n inlines = PageAdmin.inlines + [InlineResourceFiles]\n \n+admin.site.unregister(User)\n+admin.site.register(User, UserAdmin)\n admin.site.register(GenericResource, GenericResourceAdmin)\n", "issue": "Can't add user via admin panel\n\n", "before_files": [{"content": "from mezzanine.pages.admin import PageAdmin\nfrom django.contrib.gis import admin\nfrom django.contrib.contenttypes.admin import GenericTabularInline\nfrom .models import *\n\nclass InlineResourceFiles(GenericTabularInline):\n model = ResourceFile\n\nclass GenericResourceAdmin(PageAdmin):\n inlines = PageAdmin.inlines + [InlineResourceFiles]\n\nadmin.site.register(GenericResource, GenericResourceAdmin)\n", "path": "hs_core/admin.py"}]} | 644 | 328 |
gh_patches_debug_36251 | rasdani/github-patches | git_diff | electricitymaps__electricitymaps-contrib-2194 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Data for region Canaries Islands
Hello, I had a look at https://www.electricitymap.org/ , it is quite interesting and a very good job ! But there is a mistake for canarias islands : you indicate generation from gas, but the LNG terminals have not been built and commissioned yet ! The mistakes comes probablyfrom bad understanding of datas published by Red Electrica de España : the amount indicated by them as "turbina de gas" and "ciclo combinado" refers to amount produced by combined cycle and open cycle gas turbine, but these plants are still operated on liquidfuel, awaiting for natural gas availability !
</issue>
<code>
[start of parsers/ES_CN.py]
1 #!/usr/bin/env python3
2
3 import logging
4
5 # The arrow library is used to handle datetimes
6 from arrow import get
7 # The request library is used to fetch content through HTTP
8 from requests import Session
9 from ree import (ElHierro, GranCanaria, Gomera, LanzaroteFuerteventura,
10 LaPalma, Tenerife)
11 from .lib.exceptions import ParserException
12 from .lib.validation import validate
13
14
15 # Minimum valid zone demand. This is used to eliminate some cases
16 # where generation for one or more modes is obviously missing.
17 FLOORS = {
18 'ES-CN-FVLZ': 50,
19 'ES-CN-GC': 150,
20 'ES-CN-IG': 3,
21 'ES-CN-LP': 10,
22 'ES-CN-TE': 150,
23 'ES-CN-HI': 2
24 }
25
26 # TODO: Remove verify SSL config when working without it.
27 def fetch_island_data(zone_key, session):
28 if zone_key == 'ES-CN-FVLZ':
29 lanzarote_fuerteventura_data = LanzaroteFuerteventura(session, verify=False).get_all()
30 if not lanzarote_fuerteventura_data:
31 raise ParserException(zone_key, "LanzaroteFuerteventura not response")
32 else:
33 return lanzarote_fuerteventura_data
34 elif zone_key == 'ES-CN-GC':
35 gran_canaria_data = GranCanaria(session, verify=False).get_all()
36 if not gran_canaria_data:
37 raise ParserException(zone_key, "GranCanaria not response")
38 else:
39 return gran_canaria_data
40 elif zone_key == 'ES-CN-IG':
41 gomera_data = Gomera(session, verify=False).get_all()
42 if not gomera_data:
43 raise ParserException(zone_key, "Gomera not response")
44 else:
45 return gomera_data
46 elif zone_key == 'ES-CN-LP':
47 la_palma_data = LaPalma(session, verify=False).get_all()
48 if not la_palma_data:
49 raise ParserException(zone_key, "LaPalma not response")
50 else:
51 return la_palma_data
52 elif zone_key == 'ES-CN-TE':
53 tenerife_data = Tenerife(session, verify=False).get_all()
54 if not tenerife_data:
55 raise ParserException(zone_key, "Tenerife not response")
56 else:
57 return tenerife_data
58 elif zone_key == 'ES-CN-HI':
59 el_hierro_data = ElHierro(session, verify=False).get_all()
60 if not el_hierro_data:
61 raise ParserException(zone_key, "ElHierro not response")
62 else:
63 return el_hierro_data
64 else:
65 raise ParserException(zone_key, 'Can\'t read this country code {0}'.format(zone_key))
66
67
68 def fetch_consumption(zone_key='ES-CN', session=None, target_datetime=None, logger=None):
69 if target_datetime:
70 raise NotImplementedError('This parser is not yet able to parse past dates')
71
72 ses = session or Session()
73 island_data = fetch_island_data(zone_key, ses)
74 data = []
75 for response in island_data:
76 response_data = {
77 'zoneKey': zone_key,
78 'datetime': get(response.timestamp).datetime,
79 'consumption': response.demand,
80 'source': 'demanda.ree.es'
81 }
82
83 data.append(response_data)
84
85 return data
86
87
88 def fetch_production(zone_key, session=None, target_datetime=None,
89 logger=logging.getLogger(__name__)):
90 if target_datetime:
91 raise NotImplementedError('This parser is not yet able to parse past dates')
92
93 ses = session or Session()
94 island_data = fetch_island_data(zone_key, ses)
95 data = []
96
97 if zone_key == 'ES-CN-HI':
98 for response in island_data:
99 if response.production() > 0:
100 response_data = {
101 'zoneKey': zone_key,
102 'datetime': get(response.timestamp).datetime,
103 'production': {
104 'coal': 0.0,
105 'gas': round(response.gas + response.combined, 2),
106 'solar': round(response.solar, 2),
107 'oil': round(response.vapor + response.diesel, 2),
108 'wind': round(response.wind, 2),
109 'hydro': 0.0,
110 'biomass': 0.0,
111 'nuclear': 0.0,
112 'geothermal': 0.0
113 },
114 'storage': {
115 'hydro': round(-response.hydraulic, 2),
116 'battery': 0.0
117 },
118 'source': 'demanda.ree.es',
119 }
120 response_data = validate(response_data, logger,
121 floor=FLOORS[zone_key])
122
123 if response_data:
124 # append if valid
125 data.append(response_data)
126
127 else:
128 for response in island_data:
129 if response.production() > 0:
130 response_data = {
131 'zoneKey': zone_key,
132 'datetime': get(response.timestamp).datetime,
133 'production': {
134 'coal': 0.0,
135 'gas': round(response.gas + response.combined, 2),
136 'solar': round(response.solar, 2),
137 'oil': round(response.vapor + response.diesel, 2),
138 'wind': round(response.wind, 2),
139 'hydro': round(response.hydraulic, 2),
140 'biomass': 0.0,
141 'nuclear': 0.0,
142 'geothermal': 0.0
143 },
144 'storage': {
145 'hydro': 0.0,
146 'battery': 0.0
147 },
148 'source': 'demanda.ree.es',
149 }
150 response_data = validate(response_data, logger,
151 floor=FLOORS[zone_key])
152
153 if response_data:
154 # append if valid
155 data.append(response_data)
156
157 return data
158
159
160 if __name__ == '__main__':
161 session = Session
162 print("# ES-CN-FVLZ")
163 print(fetch_consumption('ES-CN-FVLZ', session))
164 print(fetch_production('ES-CN-FVLZ', session))
165 print("# ES-CN-GC")
166 print(fetch_consumption('ES-CN-GC', session))
167 print(fetch_production('ES-CN-GC', session))
168 print("# ES-CN-IG")
169 print(fetch_consumption('ES-CN-IG', session))
170 print(fetch_production('ES-CN-IG', session))
171 print("# ES-CN-LP")
172 print(fetch_consumption('ES-CN-LP', session))
173 print(fetch_production('ES-CN-LP', session))
174 print("# ES-CN-TE")
175 print(fetch_consumption('ES-CN-TE', session))
176 print(fetch_production('ES-CN-TE', session))
177 print("# ES-CN-HI")
178 print(fetch_consumption('ES-CN-HI', session))
179 print(fetch_production('ES-CN-HI', session))
180
[end of parsers/ES_CN.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/parsers/ES_CN.py b/parsers/ES_CN.py
--- a/parsers/ES_CN.py
+++ b/parsers/ES_CN.py
@@ -23,6 +23,7 @@
'ES-CN-HI': 2
}
+
# TODO: Remove verify SSL config when working without it.
def fetch_island_data(zone_key, session):
if zone_key == 'ES-CN-FVLZ':
@@ -94,6 +95,10 @@
island_data = fetch_island_data(zone_key, ses)
data = []
+ # NOTE the LNG terminals are not built yet, so power generated by "gas" or "combined" is actually using oil.
+ # Recheck this every 6 months and move to gas key if there has been a change.
+ # Last checked - 2020/02/01
+
if zone_key == 'ES-CN-HI':
for response in island_data:
if response.production() > 0:
@@ -102,9 +107,9 @@
'datetime': get(response.timestamp).datetime,
'production': {
'coal': 0.0,
- 'gas': round(response.gas + response.combined, 2),
+ 'gas': 0.0,
'solar': round(response.solar, 2),
- 'oil': round(response.vapor + response.diesel, 2),
+ 'oil': round(response.vapor + response.diesel + response.gas + response.combined, 2),
'wind': round(response.wind, 2),
'hydro': 0.0,
'biomass': 0.0,
@@ -132,9 +137,9 @@
'datetime': get(response.timestamp).datetime,
'production': {
'coal': 0.0,
- 'gas': round(response.gas + response.combined, 2),
+ 'gas': 0.0,
'solar': round(response.solar, 2),
- 'oil': round(response.vapor + response.diesel, 2),
+ 'oil': round(response.vapor + response.diesel + response.gas + response.combined, 2),
'wind': round(response.wind, 2),
'hydro': round(response.hydraulic, 2),
'biomass': 0.0,
| {"golden_diff": "diff --git a/parsers/ES_CN.py b/parsers/ES_CN.py\n--- a/parsers/ES_CN.py\n+++ b/parsers/ES_CN.py\n@@ -23,6 +23,7 @@\n 'ES-CN-HI': 2\n }\n \n+\n # TODO: Remove verify SSL config when working without it.\n def fetch_island_data(zone_key, session):\n if zone_key == 'ES-CN-FVLZ':\n@@ -94,6 +95,10 @@\n island_data = fetch_island_data(zone_key, ses)\n data = []\n \n+ # NOTE the LNG terminals are not built yet, so power generated by \"gas\" or \"combined\" is actually using oil.\n+ # Recheck this every 6 months and move to gas key if there has been a change.\n+ # Last checked - 2020/02/01\n+\n if zone_key == 'ES-CN-HI':\n for response in island_data:\n if response.production() > 0:\n@@ -102,9 +107,9 @@\n 'datetime': get(response.timestamp).datetime,\n 'production': {\n 'coal': 0.0,\n- 'gas': round(response.gas + response.combined, 2),\n+ 'gas': 0.0,\n 'solar': round(response.solar, 2),\n- 'oil': round(response.vapor + response.diesel, 2),\n+ 'oil': round(response.vapor + response.diesel + response.gas + response.combined, 2),\n 'wind': round(response.wind, 2),\n 'hydro': 0.0,\n 'biomass': 0.0,\n@@ -132,9 +137,9 @@\n 'datetime': get(response.timestamp).datetime,\n 'production': {\n 'coal': 0.0,\n- 'gas': round(response.gas + response.combined, 2),\n+ 'gas': 0.0,\n 'solar': round(response.solar, 2),\n- 'oil': round(response.vapor + response.diesel, 2),\n+ 'oil': round(response.vapor + response.diesel + response.gas + response.combined, 2),\n 'wind': round(response.wind, 2),\n 'hydro': round(response.hydraulic, 2),\n 'biomass': 0.0,\n", "issue": "Data for region Canaries Islands\nHello, I had a look at https://www.electricitymap.org/ , it is quite interesting and a very good job ! But there is a mistake for canarias islands : you indicate generation from gas, but the LNG terminals have not been built and commissioned yet ! The mistakes comes probablyfrom bad understanding of datas published by Red Electrica de Espa\u00f1a : the amount indicated by them as \"turbina de gas\" and \"ciclo combinado\" refers to amount produced by combined cycle and open cycle gas turbine, but these plants are still operated on liquidfuel, awaiting for natural gas availability ! \n", "before_files": [{"content": "#!/usr/bin/env python3\n\nimport logging\n\n# The arrow library is used to handle datetimes\nfrom arrow import get\n# The request library is used to fetch content through HTTP\nfrom requests import Session\nfrom ree import (ElHierro, GranCanaria, Gomera, LanzaroteFuerteventura,\n LaPalma, Tenerife)\nfrom .lib.exceptions import ParserException\nfrom .lib.validation import validate\n\n\n# Minimum valid zone demand. This is used to eliminate some cases\n# where generation for one or more modes is obviously missing.\nFLOORS = {\n 'ES-CN-FVLZ': 50,\n 'ES-CN-GC': 150,\n 'ES-CN-IG': 3,\n 'ES-CN-LP': 10,\n 'ES-CN-TE': 150,\n 'ES-CN-HI': 2\n}\n\n# TODO: Remove verify SSL config when working without it.\ndef fetch_island_data(zone_key, session):\n if zone_key == 'ES-CN-FVLZ':\n lanzarote_fuerteventura_data = LanzaroteFuerteventura(session, verify=False).get_all()\n if not lanzarote_fuerteventura_data:\n raise ParserException(zone_key, \"LanzaroteFuerteventura not response\")\n else:\n return lanzarote_fuerteventura_data\n elif zone_key == 'ES-CN-GC':\n gran_canaria_data = GranCanaria(session, verify=False).get_all()\n if not gran_canaria_data:\n raise ParserException(zone_key, \"GranCanaria not response\")\n else:\n return gran_canaria_data\n elif zone_key == 'ES-CN-IG':\n gomera_data = Gomera(session, verify=False).get_all()\n if not gomera_data:\n raise ParserException(zone_key, \"Gomera not response\")\n else:\n return gomera_data\n elif zone_key == 'ES-CN-LP':\n la_palma_data = LaPalma(session, verify=False).get_all()\n if not la_palma_data:\n raise ParserException(zone_key, \"LaPalma not response\")\n else:\n return la_palma_data\n elif zone_key == 'ES-CN-TE':\n tenerife_data = Tenerife(session, verify=False).get_all()\n if not tenerife_data:\n raise ParserException(zone_key, \"Tenerife not response\")\n else:\n return tenerife_data\n elif zone_key == 'ES-CN-HI':\n el_hierro_data = ElHierro(session, verify=False).get_all()\n if not el_hierro_data:\n raise ParserException(zone_key, \"ElHierro not response\")\n else:\n return el_hierro_data\n else:\n raise ParserException(zone_key, 'Can\\'t read this country code {0}'.format(zone_key))\n\n\ndef fetch_consumption(zone_key='ES-CN', session=None, target_datetime=None, logger=None):\n if target_datetime:\n raise NotImplementedError('This parser is not yet able to parse past dates')\n \n ses = session or Session()\n island_data = fetch_island_data(zone_key, ses)\n data = []\n for response in island_data:\n response_data = {\n 'zoneKey': zone_key,\n 'datetime': get(response.timestamp).datetime,\n 'consumption': response.demand,\n 'source': 'demanda.ree.es'\n }\n\n data.append(response_data)\n\n return data\n\n\ndef fetch_production(zone_key, session=None, target_datetime=None,\n logger=logging.getLogger(__name__)):\n if target_datetime:\n raise NotImplementedError('This parser is not yet able to parse past dates')\n \n ses = session or Session()\n island_data = fetch_island_data(zone_key, ses)\n data = []\n\n if zone_key == 'ES-CN-HI':\n for response in island_data:\n if response.production() > 0:\n response_data = {\n 'zoneKey': zone_key,\n 'datetime': get(response.timestamp).datetime,\n 'production': {\n 'coal': 0.0,\n 'gas': round(response.gas + response.combined, 2),\n 'solar': round(response.solar, 2),\n 'oil': round(response.vapor + response.diesel, 2),\n 'wind': round(response.wind, 2),\n 'hydro': 0.0,\n 'biomass': 0.0,\n 'nuclear': 0.0,\n 'geothermal': 0.0\n },\n 'storage': {\n 'hydro': round(-response.hydraulic, 2),\n 'battery': 0.0\n },\n 'source': 'demanda.ree.es',\n }\n response_data = validate(response_data, logger,\n floor=FLOORS[zone_key])\n\n if response_data:\n # append if valid\n data.append(response_data)\n\n else:\n for response in island_data:\n if response.production() > 0:\n response_data = {\n 'zoneKey': zone_key,\n 'datetime': get(response.timestamp).datetime,\n 'production': {\n 'coal': 0.0,\n 'gas': round(response.gas + response.combined, 2),\n 'solar': round(response.solar, 2),\n 'oil': round(response.vapor + response.diesel, 2),\n 'wind': round(response.wind, 2),\n 'hydro': round(response.hydraulic, 2),\n 'biomass': 0.0,\n 'nuclear': 0.0,\n 'geothermal': 0.0\n },\n 'storage': {\n 'hydro': 0.0,\n 'battery': 0.0\n },\n 'source': 'demanda.ree.es',\n }\n response_data = validate(response_data, logger,\n floor=FLOORS[zone_key])\n\n if response_data:\n # append if valid\n data.append(response_data)\n\n return data\n\n\nif __name__ == '__main__':\n session = Session\n print(\"# ES-CN-FVLZ\")\n print(fetch_consumption('ES-CN-FVLZ', session))\n print(fetch_production('ES-CN-FVLZ', session))\n print(\"# ES-CN-GC\")\n print(fetch_consumption('ES-CN-GC', session))\n print(fetch_production('ES-CN-GC', session))\n print(\"# ES-CN-IG\")\n print(fetch_consumption('ES-CN-IG', session))\n print(fetch_production('ES-CN-IG', session))\n print(\"# ES-CN-LP\")\n print(fetch_consumption('ES-CN-LP', session))\n print(fetch_production('ES-CN-LP', session))\n print(\"# ES-CN-TE\")\n print(fetch_consumption('ES-CN-TE', session))\n print(fetch_production('ES-CN-TE', session))\n print(\"# ES-CN-HI\")\n print(fetch_consumption('ES-CN-HI', session))\n print(fetch_production('ES-CN-HI', session))\n", "path": "parsers/ES_CN.py"}]} | 2,623 | 531 |
gh_patches_debug_1531 | rasdani/github-patches | git_diff | conda__conda-5496 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
An unexpected error has occurred.
An unexpected error has occurred.
Please consider posting the following information to the
conda GitHub issue tracker at:
https://github.com/conda/conda/issues
Current conda install:
platform : win-64
conda version : 4.3.21
conda is private : False
conda-env version : 4.3.21
conda-build version : not installed
python version : 3.6.1.final.0
requests version : 2.14.2
root environment : C:\ProgramData\Anaconda3 (read only)
default environment : C:\ProgramData\Anaconda3
envs directories : C:\Users\eric\AppData\Local\conda\conda\envs
C:\ProgramData\Anaconda3\envs
C:\Users\eric\.conda\envs
package cache : C:\ProgramData\Anaconda3\pkgs
C:\Users\eric\AppData\Local\conda\conda\pkgs
channel URLs : https://conda.anaconda.org/anaconda-fusion/win-64
https://conda.anaconda.org/anaconda-fusion/noarch
https://repo.continuum.io/pkgs/free/win-64
https://repo.continuum.io/pkgs/free/noarch
https://repo.continuum.io/pkgs/r/win-64
https://repo.continuum.io/pkgs/r/noarch
https://repo.continuum.io/pkgs/pro/win-64
https://repo.continuum.io/pkgs/pro/noarch
https://repo.continuum.io/pkgs/msys2/win-64
https://repo.continuum.io/pkgs/msys2/noarch
config file : C:\Users\eric\.condarc
netrc file : None
offline mode : False
user-agent : conda/4.3.21 requests/2.14.2 CPython/3.6.1 Windows/10 Windows/10.0.10240
administrator : False
`$ C:\ProgramData\Anaconda3\Scripts\conda-script.py ..checkenv cmd.exe C:\ProgramData\Anaconda3`
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\lib\site-packages\conda\cli\main.py", line 167, in main
import conda.cli.activate as activate
File "C:\ProgramData\Anaconda3\lib\site-packages\conda\cli\activate.py", line 12, in <module>
from ..utils import shells
File "C:\ProgramData\Anaconda3\lib\site-packages\conda\utils.py", line 13, in <module>
from .gateways.disk.read import compute_md5sum
File "C:\ProgramData\Anaconda3\lib\site-packages\conda\gateways\disk\read.py", line 22, in <module>
from ...models.channel import Channel
File "C:\ProgramData\Anaconda3\lib\site-packages\conda\models\channel.py", line 9, in <module>
from ..base.context import context
File "C:\ProgramData\Anaconda3\lib\site-packages\conda\base\context.py", line 18, in <module>
from .._vendor.auxlib.path import expand
File "C:\ProgramData\Anaconda3\lib\site-packages\conda\_vendor\auxlib\path.py", line 8, in <module>
import pkg_resources
File "<frozen importlib._bootstrap>", line 961, in _find_and_load
File "<frozen importlib._bootstrap>", line 950, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 646, in _load_unlocked
File "<frozen importlib._bootstrap>", line 616, in _load_backward_compatible
File "C:\ProgramData\Anaconda3\lib\site-packages\setuptools-27.2.0-py3.6.egg\pkg_resources\__init__.py", line 2985, in <module>
@_call_aside
File "C:\ProgramData\Anaconda3\lib\site-packages\setuptools-27.2.0-py3.6.egg\pkg_resources\__init__.py", line 2971, in _call_aside
f(*args, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\setuptools-27.2.0-py3.6.egg\pkg_resources\__init__.py", line 3013, in _initialize_master_working_set
dist.activate(replace=False)
File "C:\ProgramData\Anaconda3\lib\site-packages\setuptools-27.2.0-py3.6.egg\pkg_resources\__init__.py", line 2544, in activate
declare_namespace(pkg)
File "C:\ProgramData\Anaconda3\lib\site-packages\setuptools-27.2.0-py3.6.egg\pkg_resources\__init__.py", line 2118, in declare_namespace
_handle_ns(packageName, path_item)
File "C:\ProgramData\Anaconda3\lib\site-packages\setuptools-27.2.0-py3.6.egg\pkg_resources\__init__.py", line 2058, in _handle_ns
_rebuild_mod_path(path, packageName, module)
File "C:\ProgramData\Anaconda3\lib\site-packages\setuptools-27.2.0-py3.6.egg\pkg_resources\__init__.py", line 2087, in _rebuild_mod_path
orig_path.sort(key=position_in_sys_path)
AttributeError: '_NamespacePath' object has no attribute 'sort'
C:\Users\eric>
</issue>
<code>
[start of conda/_vendor/auxlib/path.py]
1 # -*- coding: utf-8 -*-
2 from __future__ import print_function, division, absolute_import
3 from distutils.sysconfig import get_python_lib
4 from logging import getLogger
5 from os import chdir, getcwd
6 from os.path import abspath, dirname, exists, expanduser, expandvars, isdir, isfile, join, sep
7 try:
8 import pkg_resources
9 except ImportError:
10 pkg_resources = None
11 import sys
12
13 log = getLogger(__name__)
14
15
16 ROOT_PATH = abspath(sep)
17
18
19 def site_packages_paths():
20 if hasattr(sys, 'real_prefix'):
21 # in a virtualenv
22 log.debug('searching virtualenv')
23 return tuple(p for p in sys.path if p.endswith('site-packages'))
24 else:
25 # not in a virtualenv
26 log.debug('searching outside virtualenv') # pragma: no cover
27 return tuple(get_python_lib(), ) # pragma: no cover
28
29
30 class PackageFile(object):
31
32 def __init__(self, file_path, package_name):
33 self.file_path = file_path
34 self.package_name = package_name
35
36 def __enter__(self):
37 self.file_handle = open_package_file(self.file_path, self.package_name)
38 return self.file_handle
39
40 def __exit__(self, *args):
41 self.file_handle.close()
42
43
44 class ChangePath(object):
45
46 def __init__(self, path):
47 self.dirpath = dirname(path) if isfile(path) else path
48 if not isdir(self.dirpath):
49 raise IOError('File or directory not found: {0}'.format(path))
50
51 def __enter__(self):
52 self.cwd = getcwd()
53 chdir(self.dirpath)
54 return self
55
56 def __exit__(self, *args):
57 chdir(self.cwd)
58
59
60 def open_package_file(file_path, package_name):
61 file_path = expand(file_path)
62
63 # look for file at relative path
64 if exists(file_path):
65 log.info("found real file {0}".format(file_path))
66 return open(file_path)
67
68 # look for file in package resources
69 if (package_name and pkg_resources is not None and
70 pkg_resources.resource_exists(package_name, file_path)):
71 log.info("found package resource file {0} for package {1}".format(file_path, package_name))
72 return pkg_resources.resource_stream(package_name, file_path)
73
74 # look for file in site-packages
75 package_path = find_file_in_site_packages(file_path, package_name)
76 if package_path:
77 return open(package_path) # pragma: no cover
78
79 msg = "file for module [{0}] cannot be found at path {1}".format(package_name, file_path)
80 log.error(msg)
81 raise IOError(msg)
82
83
84 def find_file_in_site_packages(file_path, package_name):
85 package_path = package_name.replace('.', '/')
86 for site_packages_path in site_packages_paths():
87 test_path = join(site_packages_path, package_path, file_path)
88 if exists(test_path):
89 log.info("found site-package file {0} for package {1}".format(file_path, package_name))
90 return test_path
91 else:
92 log.error("No file found at {0}.".format(test_path))
93 return None
94
95
96 def expand(path):
97 return abspath(expanduser(expandvars(path)))
98
99
100 def absdirname(path):
101 return abspath(expanduser(dirname(path)))
102
[end of conda/_vendor/auxlib/path.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/conda/_vendor/auxlib/path.py b/conda/_vendor/auxlib/path.py
--- a/conda/_vendor/auxlib/path.py
+++ b/conda/_vendor/auxlib/path.py
@@ -6,7 +6,7 @@
from os.path import abspath, dirname, exists, expanduser, expandvars, isdir, isfile, join, sep
try:
import pkg_resources
-except ImportError:
+except Exception:
pkg_resources = None
import sys
| {"golden_diff": "diff --git a/conda/_vendor/auxlib/path.py b/conda/_vendor/auxlib/path.py\n--- a/conda/_vendor/auxlib/path.py\n+++ b/conda/_vendor/auxlib/path.py\n@@ -6,7 +6,7 @@\n from os.path import abspath, dirname, exists, expanduser, expandvars, isdir, isfile, join, sep\n try:\n import pkg_resources\n-except ImportError:\n+except Exception:\n pkg_resources = None\n import sys\n", "issue": "An unexpected error has occurred.\nAn unexpected error has occurred.\r\nPlease consider posting the following information to the\r\nconda GitHub issue tracker at:\r\n\r\n https://github.com/conda/conda/issues\r\n\r\nCurrent conda install:\r\n\r\n platform : win-64\r\n conda version : 4.3.21\r\n conda is private : False\r\n conda-env version : 4.3.21\r\n conda-build version : not installed\r\n python version : 3.6.1.final.0\r\n requests version : 2.14.2\r\n root environment : C:\\ProgramData\\Anaconda3 (read only)\r\n default environment : C:\\ProgramData\\Anaconda3\r\n envs directories : C:\\Users\\eric\\AppData\\Local\\conda\\conda\\envs\r\n C:\\ProgramData\\Anaconda3\\envs\r\n C:\\Users\\eric\\.conda\\envs\r\n package cache : C:\\ProgramData\\Anaconda3\\pkgs\r\n C:\\Users\\eric\\AppData\\Local\\conda\\conda\\pkgs\r\n channel URLs : https://conda.anaconda.org/anaconda-fusion/win-64\r\n https://conda.anaconda.org/anaconda-fusion/noarch\r\n https://repo.continuum.io/pkgs/free/win-64\r\n https://repo.continuum.io/pkgs/free/noarch\r\n https://repo.continuum.io/pkgs/r/win-64\r\n https://repo.continuum.io/pkgs/r/noarch\r\n https://repo.continuum.io/pkgs/pro/win-64\r\n https://repo.continuum.io/pkgs/pro/noarch\r\n https://repo.continuum.io/pkgs/msys2/win-64\r\n https://repo.continuum.io/pkgs/msys2/noarch\r\n config file : C:\\Users\\eric\\.condarc\r\n netrc file : None\r\n offline mode : False\r\n user-agent : conda/4.3.21 requests/2.14.2 CPython/3.6.1 Windows/10 Windows/10.0.10240\r\n administrator : False\r\n\r\n`$ C:\\ProgramData\\Anaconda3\\Scripts\\conda-script.py ..checkenv cmd.exe C:\\ProgramData\\Anaconda3`\r\n\r\n\r\n\r\n\r\n Traceback (most recent call last):\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\conda\\cli\\main.py\", line 167, in main\r\n import conda.cli.activate as activate\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\conda\\cli\\activate.py\", line 12, in <module>\r\n from ..utils import shells\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\conda\\utils.py\", line 13, in <module>\r\n from .gateways.disk.read import compute_md5sum\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\conda\\gateways\\disk\\read.py\", line 22, in <module>\r\n from ...models.channel import Channel\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\conda\\models\\channel.py\", line 9, in <module>\r\n from ..base.context import context\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\conda\\base\\context.py\", line 18, in <module>\r\n from .._vendor.auxlib.path import expand\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\conda\\_vendor\\auxlib\\path.py\", line 8, in <module>\r\n import pkg_resources\r\n File \"<frozen importlib._bootstrap>\", line 961, in _find_and_load\r\n File \"<frozen importlib._bootstrap>\", line 950, in _find_and_load_unlocked\r\n File \"<frozen importlib._bootstrap>\", line 646, in _load_unlocked\r\n File \"<frozen importlib._bootstrap>\", line 616, in _load_backward_compatible\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg\\pkg_resources\\__init__.py\", line 2985, in <module>\r\n @_call_aside\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg\\pkg_resources\\__init__.py\", line 2971, in _call_aside\r\n f(*args, **kwargs)\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg\\pkg_resources\\__init__.py\", line 3013, in _initialize_master_working_set\r\n dist.activate(replace=False)\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg\\pkg_resources\\__init__.py\", line 2544, in activate\r\n declare_namespace(pkg)\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg\\pkg_resources\\__init__.py\", line 2118, in declare_namespace\r\n _handle_ns(packageName, path_item)\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg\\pkg_resources\\__init__.py\", line 2058, in _handle_ns\r\n _rebuild_mod_path(path, packageName, module)\r\n File \"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\setuptools-27.2.0-py3.6.egg\\pkg_resources\\__init__.py\", line 2087, in _rebuild_mod_path\r\n orig_path.sort(key=position_in_sys_path)\r\n AttributeError: '_NamespacePath' object has no attribute 'sort'\r\n\r\n\r\nC:\\Users\\eric>\n", "before_files": [{"content": "# -*- coding: utf-8 -*-\nfrom __future__ import print_function, division, absolute_import\nfrom distutils.sysconfig import get_python_lib\nfrom logging import getLogger\nfrom os import chdir, getcwd\nfrom os.path import abspath, dirname, exists, expanduser, expandvars, isdir, isfile, join, sep\ntry:\n import pkg_resources\nexcept ImportError:\n pkg_resources = None\nimport sys\n\nlog = getLogger(__name__)\n\n\nROOT_PATH = abspath(sep)\n\n\ndef site_packages_paths():\n if hasattr(sys, 'real_prefix'):\n # in a virtualenv\n log.debug('searching virtualenv')\n return tuple(p for p in sys.path if p.endswith('site-packages'))\n else:\n # not in a virtualenv\n log.debug('searching outside virtualenv') # pragma: no cover\n return tuple(get_python_lib(), ) # pragma: no cover\n\n\nclass PackageFile(object):\n\n def __init__(self, file_path, package_name):\n self.file_path = file_path\n self.package_name = package_name\n\n def __enter__(self):\n self.file_handle = open_package_file(self.file_path, self.package_name)\n return self.file_handle\n\n def __exit__(self, *args):\n self.file_handle.close()\n\n\nclass ChangePath(object):\n\n def __init__(self, path):\n self.dirpath = dirname(path) if isfile(path) else path\n if not isdir(self.dirpath):\n raise IOError('File or directory not found: {0}'.format(path))\n\n def __enter__(self):\n self.cwd = getcwd()\n chdir(self.dirpath)\n return self\n\n def __exit__(self, *args):\n chdir(self.cwd)\n\n\ndef open_package_file(file_path, package_name):\n file_path = expand(file_path)\n\n # look for file at relative path\n if exists(file_path):\n log.info(\"found real file {0}\".format(file_path))\n return open(file_path)\n\n # look for file in package resources\n if (package_name and pkg_resources is not None and\n pkg_resources.resource_exists(package_name, file_path)):\n log.info(\"found package resource file {0} for package {1}\".format(file_path, package_name))\n return pkg_resources.resource_stream(package_name, file_path)\n\n # look for file in site-packages\n package_path = find_file_in_site_packages(file_path, package_name)\n if package_path:\n return open(package_path) # pragma: no cover\n\n msg = \"file for module [{0}] cannot be found at path {1}\".format(package_name, file_path)\n log.error(msg)\n raise IOError(msg)\n\n\ndef find_file_in_site_packages(file_path, package_name):\n package_path = package_name.replace('.', '/')\n for site_packages_path in site_packages_paths():\n test_path = join(site_packages_path, package_path, file_path)\n if exists(test_path):\n log.info(\"found site-package file {0} for package {1}\".format(file_path, package_name))\n return test_path\n else:\n log.error(\"No file found at {0}.\".format(test_path))\n return None\n\n\ndef expand(path):\n return abspath(expanduser(expandvars(path)))\n\n\ndef absdirname(path):\n return abspath(expanduser(dirname(path)))\n", "path": "conda/_vendor/auxlib/path.py"}]} | 2,829 | 109 |
gh_patches_debug_14239 | rasdani/github-patches | git_diff | RUCAIBox__RecBole-692 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
[🐛BUG] case_study.py 中， 输入的用户id只有一个时， full_sort_topk 报错
代码
```python3
import torch
import pandas as pd
from recbole.model.general_recommender.bpr import BPR
from recbole.config import Config
from recbole.data import create_dataset, data_preparation
from recbole.utils.case_study import full_sort_topk
param_dict = {
'use_gpu': False
}
# 加载 BPR 模型
bpr_model_path = "D:\\source\\recbole-0.2.0\\app\\ex\\saved\\BPR-Jan-18-2021_14-03-52.pth"
bpr_config = Config(model='BPR',
dataset='ml-100k',
config_dict=param_dict)
dataset = create_dataset(bpr_config)
train_data, valid_data, test_data = data_preparation(bpr_config, dataset)
bpr_model = BPR(bpr_config, train_data)
checkpoint = torch.load(bpr_model_path)
bpr_model.load_state_dict(checkpoint['state_dict'])
bpr_model.eval()
uid_series = dataset.token2id(dataset.uid_field, ['200']) # 原始数据集中的用户id，变换为训练内部使用的索引id
full_sort_topk(uid_series, bpr_model, test_data, 10)
```
报错信息
Traceback (most recent call last):
File "D:/source/recbole-0.2.0/app/ex/bpr_predict_ml100k.py", line 33, in <module>
full_sort_topk(uid_series, bpr_model, test_data, 10)
File "D:\source\recbole-0.2.0\recbole\utils\case_study.py", line 87, in full_sort_topk
scores = full_sort_scores(uid_series, model, test_data)
File "D:\Anaconda3\envs\pytorch\lib\site-packages\torch\autograd\grad_mode.py", line 26, in decorate_context
return func(*args, **kwargs)
File "D:\source\recbole-0.2.0\recbole\utils\case_study.py", line 45, in full_sort_scores
history_row = torch.cat([torch.full_like(hist_iid, i) for i, hist_iid in enumerate(history_item)])
RuntimeError: zero-dimensional tensor (at position 0) cannot be concatenated
</issue>
<code>
[start of recbole/utils/case_study.py]
1 # @Time : 2020/12/25
2 # @Author : Yushuo Chen
3 # @Email : [email protected]
4
5 # UPDATE
6 # @Time : 2020/12/25
7 # @Author : Yushuo Chen
8 # @email : [email protected]
9
10 """
11 recbole.utils.case_study
12 #####################################
13 """
14
15 import numpy as np
16 import torch
17
18 from recbole.data.dataloader.general_dataloader import GeneralFullDataLoader
19 from recbole.data.dataloader.sequential_dataloader import SequentialFullDataLoader
20
21
22 @torch.no_grad()
23 def full_sort_scores(uid_series, model, test_data):
24 """Calculate the scores of all items for each user in uid_series.
25
26 Note:
27 The score of [pad] and history items will be set into -inf.
28
29 Args:
30 uid_series (numpy.ndarray): User id series
31 model (AbstractRecommender): Model to predict
32 test_data (AbstractDataLoader): The test_data of model
33
34 Returns:
35 torch.Tensor: the scores of all items for each user in uid_series.
36 """
37 uid_field = test_data.dataset.uid_field
38 dataset = test_data.dataset
39 model.eval()
40
41 if isinstance(test_data, GeneralFullDataLoader):
42 index = np.isin(test_data.user_df[uid_field].numpy(), uid_series)
43 input_interaction = test_data.user_df[index]
44 history_item = test_data.uid2history_item[input_interaction[uid_field]]
45 history_row = torch.cat([torch.full_like(hist_iid, i) for i, hist_iid in enumerate(history_item)])
46 history_col = torch.cat(list(history_item))
47 history_index = history_row, history_col
48 elif isinstance(test_data, SequentialFullDataLoader):
49 index = np.isin(test_data.uid_list, uid_series)
50 input_interaction = test_data.augmentation(
51 test_data.item_list_index[index], test_data.target_index[index], test_data.item_list_length[index]
52 )
53 history_index = None
54 else:
55 raise NotImplementedError
56
57 # Get scores of all items
58 try:
59 scores = model.full_sort_predict(input_interaction)
60 except NotImplementedError:
61 input_interaction = input_interaction.repeat(dataset.item_num)
62 input_interaction.update(test_data.get_item_feature().repeat(len(uid_series)))
63 scores = model.predict(input_interaction)
64
65 scores = scores.view(-1, dataset.item_num)
66 scores[:, 0] = -np.inf # set scores of [pad] to -inf
67 if history_index is not None:
68 scores[history_index] = -np.inf # set scores of history items to -inf
69
70 return scores
71
72
73 def full_sort_topk(uid_series, model, test_data, k):
74 """Calculate the top-k items' scores and ids for each user in uid_series.
75
76 Args:
77 uid_series (numpy.ndarray): User id series
78 model (AbstractRecommender): Model to predict
79 test_data (AbstractDataLoader): The test_data of model
80 k (int): The top-k items.
81
82 Returns:
83 tuple:
84 - topk_scores (torch.Tensor): The scores of topk items.
85 - topk_index (torch.Tensor): The index of topk items, which is also the internal ids of items.
86 """
87 scores = full_sort_scores(uid_series, model, test_data)
88 return torch.topk(scores, k)
89
[end of recbole/utils/case_study.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/recbole/utils/case_study.py b/recbole/utils/case_study.py
--- a/recbole/utils/case_study.py
+++ b/recbole/utils/case_study.py
@@ -41,7 +41,7 @@
if isinstance(test_data, GeneralFullDataLoader):
index = np.isin(test_data.user_df[uid_field].numpy(), uid_series)
input_interaction = test_data.user_df[index]
- history_item = test_data.uid2history_item[input_interaction[uid_field]]
+ history_item = test_data.uid2history_item[input_interaction[uid_field].numpy()]
history_row = torch.cat([torch.full_like(hist_iid, i) for i, hist_iid in enumerate(history_item)])
history_col = torch.cat(list(history_item))
history_index = history_row, history_col
| {"golden_diff": "diff --git a/recbole/utils/case_study.py b/recbole/utils/case_study.py\n--- a/recbole/utils/case_study.py\n+++ b/recbole/utils/case_study.py\n@@ -41,7 +41,7 @@\n if isinstance(test_data, GeneralFullDataLoader):\n index = np.isin(test_data.user_df[uid_field].numpy(), uid_series)\n input_interaction = test_data.user_df[index]\n- history_item = test_data.uid2history_item[input_interaction[uid_field]]\n+ history_item = test_data.uid2history_item[input_interaction[uid_field].numpy()]\n history_row = torch.cat([torch.full_like(hist_iid, i) for i, hist_iid in enumerate(history_item)])\n history_col = torch.cat(list(history_item))\n history_index = history_row, history_col\n", "issue": "[\ud83d\udc1bBUG] case_study.py \u4e2d\uff0c \u8f93\u5165\u7684\u7528\u6237id\u53ea\u6709\u4e00\u4e2a\u65f6\uff0c full_sort_topk \u62a5\u9519\n\u4ee3\u7801\r\n```python3\r\nimport torch\r\nimport pandas as pd\r\n\r\nfrom recbole.model.general_recommender.bpr import BPR\r\nfrom recbole.config import Config\r\nfrom recbole.data import create_dataset, data_preparation\r\nfrom recbole.utils.case_study import full_sort_topk\r\n\r\nparam_dict = {\r\n 'use_gpu': False\r\n}\r\n\r\n# \u52a0\u8f7d BPR \u6a21\u578b\r\nbpr_model_path = \"D:\\\\source\\\\recbole-0.2.0\\\\app\\\\ex\\\\saved\\\\BPR-Jan-18-2021_14-03-52.pth\"\r\nbpr_config = Config(model='BPR',\r\n dataset='ml-100k',\r\n config_dict=param_dict)\r\ndataset = create_dataset(bpr_config)\r\ntrain_data, valid_data, test_data = data_preparation(bpr_config, dataset)\r\n\r\nbpr_model = BPR(bpr_config, train_data)\r\ncheckpoint = torch.load(bpr_model_path)\r\nbpr_model.load_state_dict(checkpoint['state_dict'])\r\nbpr_model.eval()\r\n\r\nuid_series = dataset.token2id(dataset.uid_field, ['200']) # \u539f\u59cb\u6570\u636e\u96c6\u4e2d\u7684\u7528\u6237id\uff0c\u53d8\u6362\u4e3a\u8bad\u7ec3\u5185\u90e8\u4f7f\u7528\u7684\u7d22\u5f15id\r\n\r\nfull_sort_topk(uid_series, bpr_model, test_data, 10)\r\n```\r\n\r\n\u62a5\u9519\u4fe1\u606f\r\nTraceback (most recent call last):\r\n File \"D:/source/recbole-0.2.0/app/ex/bpr_predict_ml100k.py\", line 33, in <module>\r\n full_sort_topk(uid_series, bpr_model, test_data, 10)\r\n File \"D:\\source\\recbole-0.2.0\\recbole\\utils\\case_study.py\", line 87, in full_sort_topk\r\n scores = full_sort_scores(uid_series, model, test_data)\r\n File \"D:\\Anaconda3\\envs\\pytorch\\lib\\site-packages\\torch\\autograd\\grad_mode.py\", line 26, in decorate_context\r\n return func(*args, **kwargs)\r\n File \"D:\\source\\recbole-0.2.0\\recbole\\utils\\case_study.py\", line 45, in full_sort_scores\r\n history_row = torch.cat([torch.full_like(hist_iid, i) for i, hist_iid in enumerate(history_item)])\r\nRuntimeError: zero-dimensional tensor (at position 0) cannot be concatenated\n", "before_files": [{"content": "# @Time : 2020/12/25\n# @Author : Yushuo Chen\n# @Email : [email protected]\n\n# UPDATE\n# @Time : 2020/12/25\n# @Author : Yushuo Chen\n# @email : [email protected]\n\n\"\"\"\nrecbole.utils.case_study\n#####################################\n\"\"\"\n\nimport numpy as np\nimport torch\n\nfrom recbole.data.dataloader.general_dataloader import GeneralFullDataLoader\nfrom recbole.data.dataloader.sequential_dataloader import SequentialFullDataLoader\n\n\[email protected]_grad()\ndef full_sort_scores(uid_series, model, test_data):\n \"\"\"Calculate the scores of all items for each user in uid_series.\n\n Note:\n The score of [pad] and history items will be set into -inf.\n\n Args:\n uid_series (numpy.ndarray): User id series\n model (AbstractRecommender): Model to predict\n test_data (AbstractDataLoader): The test_data of model\n\n Returns:\n torch.Tensor: the scores of all items for each user in uid_series.\n \"\"\"\n uid_field = test_data.dataset.uid_field\n dataset = test_data.dataset\n model.eval()\n\n if isinstance(test_data, GeneralFullDataLoader):\n index = np.isin(test_data.user_df[uid_field].numpy(), uid_series)\n input_interaction = test_data.user_df[index]\n history_item = test_data.uid2history_item[input_interaction[uid_field]]\n history_row = torch.cat([torch.full_like(hist_iid, i) for i, hist_iid in enumerate(history_item)])\n history_col = torch.cat(list(history_item))\n history_index = history_row, history_col\n elif isinstance(test_data, SequentialFullDataLoader):\n index = np.isin(test_data.uid_list, uid_series)\n input_interaction = test_data.augmentation(\n test_data.item_list_index[index], test_data.target_index[index], test_data.item_list_length[index]\n )\n history_index = None\n else:\n raise NotImplementedError\n\n # Get scores of all items\n try:\n scores = model.full_sort_predict(input_interaction)\n except NotImplementedError:\n input_interaction = input_interaction.repeat(dataset.item_num)\n input_interaction.update(test_data.get_item_feature().repeat(len(uid_series)))\n scores = model.predict(input_interaction)\n\n scores = scores.view(-1, dataset.item_num)\n scores[:, 0] = -np.inf # set scores of [pad] to -inf\n if history_index is not None:\n scores[history_index] = -np.inf # set scores of history items to -inf\n\n return scores\n\n\ndef full_sort_topk(uid_series, model, test_data, k):\n \"\"\"Calculate the top-k items' scores and ids for each user in uid_series.\n\n Args:\n uid_series (numpy.ndarray): User id series\n model (AbstractRecommender): Model to predict\n test_data (AbstractDataLoader): The test_data of model\n k (int): The top-k items.\n\n Returns:\n tuple:\n - topk_scores (torch.Tensor): The scores of topk items.\n - topk_index (torch.Tensor): The index of topk items, which is also the internal ids of items.\n \"\"\"\n scores = full_sort_scores(uid_series, model, test_data)\n return torch.topk(scores, k)\n", "path": "recbole/utils/case_study.py"}]} | 1,988 | 175 |
gh_patches_debug_21908 | rasdani/github-patches | git_diff | Lightning-AI__pytorch-lightning-1453 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Propose to save new model before deleting previous ones in ModelCheckpointing
## 🚀 Feature
<!-- A clear and concise description of the feature proposal -->
In an edge case, the trainer deleted previous model and then was killed because of system error before successfully saving new model. Thus all the models were lost.
I understand specifying save_top_k > 1 helps, and saving before deleting leads to larger disk consumption. But it might be good to provide an option for this?
### Motivation
<!-- Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too -->
### Pitch
<!-- A clear and concise description of what you want to happen. -->
in the worst case, you have two but never none...
### Alternatives
<!-- A clear and concise description of any alternative solutions or features you've considered, if any. -->
### Additional context
<!-- Add any other context or screenshots about the feature request here. -->
</issue>
<code>
[start of pytorch_lightning/callbacks/model_checkpoint.py]
1 """
2 Model Checkpointing
3 ===================
4
5 Automatically save model checkpoints during training.
6
7 """
8
9 import os
10 import re
11
12 import numpy as np
13
14 from pytorch_lightning import _logger as log
15 from pytorch_lightning.callbacks.base import Callback
16 from pytorch_lightning.utilities import rank_zero_warn
17
18
19 class ModelCheckpoint(Callback):
20 r"""
21 Save the model after every epoch.
22
23 Args:
24 filepath: path to save the model file.
25 Can contain named formatting options to be auto-filled.
26
27 Example::
28
29 # custom path
30 # saves a file like: my/path/epoch_0.ckpt
31 >>> checkpoint_callback = ModelCheckpoint('my/path/')
32
33 # save any arbitrary metrics like `val_loss`, etc. in name
34 # saves a file like: my/path/epoch=2-val_loss=0.2_other_metric=0.3.ckpt
35 >>> checkpoint_callback = ModelCheckpoint(
36 ... filepath='my/path/{epoch}-{val_loss:.2f}-{other_metric:.2f}'
37 ... )
38
39 monitor: quantity to monitor.
40 verbose: verbosity mode. Default: ``False``.
41 save_top_k: if `save_top_k == k`,
42 the best k models according to
43 the quantity monitored will be saved.
44 if ``save_top_k == 0``, no models are saved.
45 if ``save_top_k == -1``, all models are saved.
46 Please note that the monitors are checked every `period` epochs.
47 if ``save_top_k >= 2`` and the callback is called multiple
48 times inside an epoch, the name of the saved file will be
49 appended with a version count starting with `v0`.
50 mode: one of {auto, min, max}.
51 If ``save_top_k != 0``, the decision
52 to overwrite the current save file is made
53 based on either the maximization or the
54 minimization of the monitored quantity. For `val_acc`,
55 this should be `max`, for `val_loss` this should
56 be `min`, etc. In `auto` mode, the direction is
57 automatically inferred from the name of the monitored quantity.
58 save_weights_only: if ``True``, then only the model's weights will be
59 saved (``model.save_weights(filepath)``), else the full model
60 is saved (``model.save(filepath)``).
61 period: Interval (number of epochs) between checkpoints.
62
63 Example::
64
65 >>> from pytorch_lightning import Trainer
66 >>> from pytorch_lightning.callbacks import ModelCheckpoint
67
68 # saves checkpoints to 'my/path/' whenever 'val_loss' has a new min
69 >>> checkpoint_callback = ModelCheckpoint(filepath='my/path/')
70 >>> trainer = Trainer(checkpoint_callback=checkpoint_callback)
71
72 # save epoch and val_loss in name
73 # saves a file like: my/path/sample-mnist_epoch=02_val_loss=0.32.ckpt
74 >>> checkpoint_callback = ModelCheckpoint(
75 ... filepath='my/path/sample-mnist_{epoch:02d}-{val_loss:.2f}'
76 ... )
77
78 """
79
80 def __init__(self, filepath: str, monitor: str = 'val_loss', verbose: bool = False,
81 save_top_k: int = 1, save_weights_only: bool = False,
82 mode: str = 'auto', period: int = 1, prefix: str = ''):
83 super().__init__()
84 if save_top_k > 0 and os.path.isdir(filepath) and len(os.listdir(filepath)) > 0:
85 rank_zero_warn(
86 f"Checkpoint directory {filepath} exists and is not empty with save_top_k != 0."
87 "All files in this directory will be deleted when a checkpoint is saved!"
88 )
89
90 self.monitor = monitor
91 self.verbose = verbose
92 if os.path.isdir(filepath):
93 self.dirpath, self.filename = filepath, '{epoch}'
94 else:
95 self.dirpath, self.filename = os.path.split(filepath)
96
97 os.makedirs(self.dirpath, exist_ok=True)
98 self.save_top_k = save_top_k
99 self.save_weights_only = save_weights_only
100 self.period = period
101 self.epoch_last_check = None
102 self.prefix = prefix
103 self.best_k_models = {}
104 # {filename: monitor}
105 self.kth_best_model = ''
106 self.best = 0
107 self.save_function = None
108
109 mode_dict = {
110 'min': (np.less, np.Inf, 'min'),
111 'max': (np.greater, -np.Inf, 'max'),
112 'auto': (np.greater, -np.Inf, 'max') if 'acc' in self.monitor or self.monitor.startswith('fmeasure')
113 else (np.less, np.Inf, 'min'),
114 }
115
116 if mode not in mode_dict:
117 rank_zero_warn(f'ModelCheckpoint mode {mode} is unknown, fallback to auto mode.', RuntimeWarning)
118 mode = 'auto'
119
120 self.monitor_op, self.kth_value, self.mode = mode_dict[mode]
121
122 def _del_model(self, filepath):
123 os.remove(filepath)
124
125 def _save_model(self, filepath):
126 # make paths
127 os.makedirs(os.path.dirname(filepath), exist_ok=True)
128
129 # delegate the saving to the model
130 if self.save_function is not None:
131 self.save_function(filepath)
132 else:
133 raise ValueError(".save_function() not set")
134
135 def check_monitor_top_k(self, current):
136 less_than_k_models = len(self.best_k_models) < self.save_top_k
137 if less_than_k_models:
138 return True
139 return self.monitor_op(current, self.best_k_models[self.kth_best_model])
140
141 def format_checkpoint_name(self, epoch, metrics, ver=None):
142 """Generate a filename according to the defined template.
143
144 Example::
145
146 >>> tmpdir = os.path.dirname(__file__)
147 >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{epoch}'))
148 >>> os.path.basename(ckpt.format_checkpoint_name(0, {}))
149 'epoch=0.ckpt'
150 >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{epoch:03d}'))
151 >>> os.path.basename(ckpt.format_checkpoint_name(5, {}))
152 'epoch=005.ckpt'
153 >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{epoch}-{val_loss:.2f}'))
154 >>> os.path.basename(ckpt.format_checkpoint_name(2, dict(val_loss=0.123456)))
155 'epoch=2-val_loss=0.12.ckpt'
156 >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{missing:d}'))
157 >>> os.path.basename(ckpt.format_checkpoint_name(0, {}))
158 'missing=0.ckpt'
159 """
160 # check if user passed in keys to the string
161 groups = re.findall(r'(\{.*?)[:\}]', self.filename)
162
163 if len(groups) == 0:
164 # default name
165 filename = f'{self.prefix}_ckpt_epoch_{epoch}'
166 else:
167 metrics['epoch'] = epoch
168 filename = self.filename
169 for tmp in groups:
170 name = tmp[1:]
171 filename = filename.replace(tmp, name + '={' + name)
172 if name not in metrics:
173 metrics[name] = 0
174 filename = filename.format(**metrics)
175 str_ver = f'_v{ver}' if ver is not None else ''
176 filepath = os.path.join(self.dirpath, self.prefix + filename + str_ver + '.ckpt')
177 return filepath
178
179 def on_validation_end(self, trainer, pl_module):
180 # only run on main process
181 if trainer.proc_rank != 0:
182 return
183
184 metrics = trainer.callback_metrics
185 epoch = trainer.current_epoch
186 if self.save_top_k == 0:
187 # no models are saved
188 return
189 if self.epoch_last_check is not None and (epoch - self.epoch_last_check) < self.period:
190 # skipping in this term
191 return
192
193 self.epoch_last_check = epoch
194
195 filepath = self.format_checkpoint_name(epoch, metrics)
196 version_cnt = 0
197 while os.path.isfile(filepath):
198 filepath = self.format_checkpoint_name(epoch, metrics, ver=version_cnt)
199 # this epoch called before
200 version_cnt += 1
201
202 if self.save_top_k != -1:
203 current = metrics.get(self.monitor)
204
205 if current is None:
206 rank_zero_warn(f'Can save best model only with {self.monitor} available, skipping.', RuntimeWarning)
207 elif self.check_monitor_top_k(current):
208 self._do_check_save(filepath, current, epoch)
209 elif self.verbose > 0:
210 log.info(f'\nEpoch {epoch:05d}: {self.monitor} was not in top {self.save_top_k}')
211
212 else:
213 if self.verbose > 0:
214 log.info(f'\nEpoch {epoch:05d}: saving model to {filepath}')
215 self._save_model(filepath)
216
217 def _do_check_save(self, filepath, current, epoch):
218 # remove kth
219 if len(self.best_k_models) == self.save_top_k and self.save_top_k > 0:
220 delpath = self.kth_best_model
221 self.best_k_models.pop(self.kth_best_model)
222 self._del_model(delpath)
223
224 self.best_k_models[filepath] = current
225 if len(self.best_k_models) == self.save_top_k:
226 # monitor dict has reached k elements
227 _op = max if self.mode == 'min' else min
228 self.kth_best_model = _op(self.best_k_models,
229 key=self.best_k_models.get)
230 self.kth_value = self.best_k_models[self.kth_best_model]
231
232 _op = min if self.mode == 'min' else max
233 self.best = _op(self.best_k_models.values())
234
235 if self.verbose > 0:
236 log.info(
237 f'\nEpoch {epoch:05d}: {self.monitor} reached'
238 f' {current:0.5f} (best {self.best:0.5f}), saving model to'
239 f' {filepath} as top {self.save_top_k}')
240 self._save_model(filepath)
241
[end of pytorch_lightning/callbacks/model_checkpoint.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/pytorch_lightning/callbacks/model_checkpoint.py b/pytorch_lightning/callbacks/model_checkpoint.py
--- a/pytorch_lightning/callbacks/model_checkpoint.py
+++ b/pytorch_lightning/callbacks/model_checkpoint.py
@@ -216,10 +216,12 @@
def _do_check_save(self, filepath, current, epoch):
# remove kth
+
+ del_list = []
if len(self.best_k_models) == self.save_top_k and self.save_top_k > 0:
delpath = self.kth_best_model
self.best_k_models.pop(self.kth_best_model)
- self._del_model(delpath)
+ del_list.append(delpath)
self.best_k_models[filepath] = current
if len(self.best_k_models) == self.save_top_k:
@@ -238,3 +240,7 @@
f' {current:0.5f} (best {self.best:0.5f}), saving model to'
f' {filepath} as top {self.save_top_k}')
self._save_model(filepath)
+
+ for cur_path in del_list:
+ if cur_path != filepath:
+ self._del_model(cur_path)
| {"golden_diff": "diff --git a/pytorch_lightning/callbacks/model_checkpoint.py b/pytorch_lightning/callbacks/model_checkpoint.py\n--- a/pytorch_lightning/callbacks/model_checkpoint.py\n+++ b/pytorch_lightning/callbacks/model_checkpoint.py\n@@ -216,10 +216,12 @@\n \n def _do_check_save(self, filepath, current, epoch):\n # remove kth\n+\n+ del_list = []\n if len(self.best_k_models) == self.save_top_k and self.save_top_k > 0:\n delpath = self.kth_best_model\n self.best_k_models.pop(self.kth_best_model)\n- self._del_model(delpath)\n+ del_list.append(delpath)\n \n self.best_k_models[filepath] = current\n if len(self.best_k_models) == self.save_top_k:\n@@ -238,3 +240,7 @@\n f' {current:0.5f} (best {self.best:0.5f}), saving model to'\n f' {filepath} as top {self.save_top_k}')\n self._save_model(filepath)\n+\n+ for cur_path in del_list:\n+ if cur_path != filepath:\n+ self._del_model(cur_path)\n", "issue": "Propose to save new model before deleting previous ones in ModelCheckpointing\n## \ud83d\ude80 Feature\r\n<!-- A clear and concise description of the feature proposal -->\r\nIn an edge case, the trainer deleted previous model and then was killed because of system error before successfully saving new model. Thus all the models were lost.\r\nI understand specifying save_top_k > 1 helps, and saving before deleting leads to larger disk consumption. But it might be good to provide an option for this?\r\n### Motivation\r\n\r\n<!-- Please outline the motivation for the proposal. Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too -->\r\n\r\n### Pitch\r\n\r\n<!-- A clear and concise description of what you want to happen. -->\r\nin the worst case, you have two but never none...\r\n\r\n### Alternatives\r\n\r\n<!-- A clear and concise description of any alternative solutions or features you've considered, if any. -->\r\n\r\n### Additional context\r\n\r\n<!-- Add any other context or screenshots about the feature request here. -->\r\n\n", "before_files": [{"content": "\"\"\"\nModel Checkpointing\n===================\n\nAutomatically save model checkpoints during training.\n\n\"\"\"\n\nimport os\nimport re\n\nimport numpy as np\n\nfrom pytorch_lightning import _logger as log\nfrom pytorch_lightning.callbacks.base import Callback\nfrom pytorch_lightning.utilities import rank_zero_warn\n\n\nclass ModelCheckpoint(Callback):\n r\"\"\"\n Save the model after every epoch.\n\n Args:\n filepath: path to save the model file.\n Can contain named formatting options to be auto-filled.\n\n Example::\n\n # custom path\n # saves a file like: my/path/epoch_0.ckpt\n >>> checkpoint_callback = ModelCheckpoint('my/path/')\n\n # save any arbitrary metrics like `val_loss`, etc. in name\n # saves a file like: my/path/epoch=2-val_loss=0.2_other_metric=0.3.ckpt\n >>> checkpoint_callback = ModelCheckpoint(\n ... filepath='my/path/{epoch}-{val_loss:.2f}-{other_metric:.2f}'\n ... )\n\n monitor: quantity to monitor.\n verbose: verbosity mode. Default: ``False``.\n save_top_k: if `save_top_k == k`,\n the best k models according to\n the quantity monitored will be saved.\n if ``save_top_k == 0``, no models are saved.\n if ``save_top_k == -1``, all models are saved.\n Please note that the monitors are checked every `period` epochs.\n if ``save_top_k >= 2`` and the callback is called multiple\n times inside an epoch, the name of the saved file will be\n appended with a version count starting with `v0`.\n mode: one of {auto, min, max}.\n If ``save_top_k != 0``, the decision\n to overwrite the current save file is made\n based on either the maximization or the\n minimization of the monitored quantity. For `val_acc`,\n this should be `max`, for `val_loss` this should\n be `min`, etc. In `auto` mode, the direction is\n automatically inferred from the name of the monitored quantity.\n save_weights_only: if ``True``, then only the model's weights will be\n saved (``model.save_weights(filepath)``), else the full model\n is saved (``model.save(filepath)``).\n period: Interval (number of epochs) between checkpoints.\n\n Example::\n\n >>> from pytorch_lightning import Trainer\n >>> from pytorch_lightning.callbacks import ModelCheckpoint\n\n # saves checkpoints to 'my/path/' whenever 'val_loss' has a new min\n >>> checkpoint_callback = ModelCheckpoint(filepath='my/path/')\n >>> trainer = Trainer(checkpoint_callback=checkpoint_callback)\n\n # save epoch and val_loss in name\n # saves a file like: my/path/sample-mnist_epoch=02_val_loss=0.32.ckpt\n >>> checkpoint_callback = ModelCheckpoint(\n ... filepath='my/path/sample-mnist_{epoch:02d}-{val_loss:.2f}'\n ... )\n\n \"\"\"\n\n def __init__(self, filepath: str, monitor: str = 'val_loss', verbose: bool = False,\n save_top_k: int = 1, save_weights_only: bool = False,\n mode: str = 'auto', period: int = 1, prefix: str = ''):\n super().__init__()\n if save_top_k > 0 and os.path.isdir(filepath) and len(os.listdir(filepath)) > 0:\n rank_zero_warn(\n f\"Checkpoint directory {filepath} exists and is not empty with save_top_k != 0.\"\n \"All files in this directory will be deleted when a checkpoint is saved!\"\n )\n\n self.monitor = monitor\n self.verbose = verbose\n if os.path.isdir(filepath):\n self.dirpath, self.filename = filepath, '{epoch}'\n else:\n self.dirpath, self.filename = os.path.split(filepath)\n\n os.makedirs(self.dirpath, exist_ok=True)\n self.save_top_k = save_top_k\n self.save_weights_only = save_weights_only\n self.period = period\n self.epoch_last_check = None\n self.prefix = prefix\n self.best_k_models = {}\n # {filename: monitor}\n self.kth_best_model = ''\n self.best = 0\n self.save_function = None\n\n mode_dict = {\n 'min': (np.less, np.Inf, 'min'),\n 'max': (np.greater, -np.Inf, 'max'),\n 'auto': (np.greater, -np.Inf, 'max') if 'acc' in self.monitor or self.monitor.startswith('fmeasure')\n else (np.less, np.Inf, 'min'),\n }\n\n if mode not in mode_dict:\n rank_zero_warn(f'ModelCheckpoint mode {mode} is unknown, fallback to auto mode.', RuntimeWarning)\n mode = 'auto'\n\n self.monitor_op, self.kth_value, self.mode = mode_dict[mode]\n\n def _del_model(self, filepath):\n os.remove(filepath)\n\n def _save_model(self, filepath):\n # make paths\n os.makedirs(os.path.dirname(filepath), exist_ok=True)\n\n # delegate the saving to the model\n if self.save_function is not None:\n self.save_function(filepath)\n else:\n raise ValueError(\".save_function() not set\")\n\n def check_monitor_top_k(self, current):\n less_than_k_models = len(self.best_k_models) < self.save_top_k\n if less_than_k_models:\n return True\n return self.monitor_op(current, self.best_k_models[self.kth_best_model])\n\n def format_checkpoint_name(self, epoch, metrics, ver=None):\n \"\"\"Generate a filename according to the defined template.\n\n Example::\n\n >>> tmpdir = os.path.dirname(__file__)\n >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{epoch}'))\n >>> os.path.basename(ckpt.format_checkpoint_name(0, {}))\n 'epoch=0.ckpt'\n >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{epoch:03d}'))\n >>> os.path.basename(ckpt.format_checkpoint_name(5, {}))\n 'epoch=005.ckpt'\n >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{epoch}-{val_loss:.2f}'))\n >>> os.path.basename(ckpt.format_checkpoint_name(2, dict(val_loss=0.123456)))\n 'epoch=2-val_loss=0.12.ckpt'\n >>> ckpt = ModelCheckpoint(os.path.join(tmpdir, '{missing:d}'))\n >>> os.path.basename(ckpt.format_checkpoint_name(0, {}))\n 'missing=0.ckpt'\n \"\"\"\n # check if user passed in keys to the string\n groups = re.findall(r'(\\{.*?)[:\\}]', self.filename)\n\n if len(groups) == 0:\n # default name\n filename = f'{self.prefix}_ckpt_epoch_{epoch}'\n else:\n metrics['epoch'] = epoch\n filename = self.filename\n for tmp in groups:\n name = tmp[1:]\n filename = filename.replace(tmp, name + '={' + name)\n if name not in metrics:\n metrics[name] = 0\n filename = filename.format(**metrics)\n str_ver = f'_v{ver}' if ver is not None else ''\n filepath = os.path.join(self.dirpath, self.prefix + filename + str_ver + '.ckpt')\n return filepath\n\n def on_validation_end(self, trainer, pl_module):\n # only run on main process\n if trainer.proc_rank != 0:\n return\n\n metrics = trainer.callback_metrics\n epoch = trainer.current_epoch\n if self.save_top_k == 0:\n # no models are saved\n return\n if self.epoch_last_check is not None and (epoch - self.epoch_last_check) < self.period:\n # skipping in this term\n return\n\n self.epoch_last_check = epoch\n\n filepath = self.format_checkpoint_name(epoch, metrics)\n version_cnt = 0\n while os.path.isfile(filepath):\n filepath = self.format_checkpoint_name(epoch, metrics, ver=version_cnt)\n # this epoch called before\n version_cnt += 1\n\n if self.save_top_k != -1:\n current = metrics.get(self.monitor)\n\n if current is None:\n rank_zero_warn(f'Can save best model only with {self.monitor} available, skipping.', RuntimeWarning)\n elif self.check_monitor_top_k(current):\n self._do_check_save(filepath, current, epoch)\n elif self.verbose > 0:\n log.info(f'\\nEpoch {epoch:05d}: {self.monitor} was not in top {self.save_top_k}')\n\n else:\n if self.verbose > 0:\n log.info(f'\\nEpoch {epoch:05d}: saving model to {filepath}')\n self._save_model(filepath)\n\n def _do_check_save(self, filepath, current, epoch):\n # remove kth\n if len(self.best_k_models) == self.save_top_k and self.save_top_k > 0:\n delpath = self.kth_best_model\n self.best_k_models.pop(self.kth_best_model)\n self._del_model(delpath)\n\n self.best_k_models[filepath] = current\n if len(self.best_k_models) == self.save_top_k:\n # monitor dict has reached k elements\n _op = max if self.mode == 'min' else min\n self.kth_best_model = _op(self.best_k_models,\n key=self.best_k_models.get)\n self.kth_value = self.best_k_models[self.kth_best_model]\n\n _op = min if self.mode == 'min' else max\n self.best = _op(self.best_k_models.values())\n\n if self.verbose > 0:\n log.info(\n f'\\nEpoch {epoch:05d}: {self.monitor} reached'\n f' {current:0.5f} (best {self.best:0.5f}), saving model to'\n f' {filepath} as top {self.save_top_k}')\n self._save_model(filepath)\n", "path": "pytorch_lightning/callbacks/model_checkpoint.py"}]} | 3,568 | 270 |
gh_patches_debug_57934 | rasdani/github-patches | git_diff | scrapy__scrapy-1905 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
response.body is duplicate
Access the [text page(not mine)](http://files.qidian.com/Author4/3615059/88542882.txt) by browsers or wget and you will find the response content is not duplicate, but scrapy's `response.body` is duplicate. I had tried set the scrapy's headers same as a real brower's, but it is still duplicate.
Just use the follow sample code, and you will find the issue.
```
scrapy shell "http://files.qidian.com/Author4/3615059/88542882.txt"
```
Sorry for my bad english.
</issue>
<code>
[start of scrapy/utils/gz.py]
1 import struct
2
3 try:
4 from cStringIO import StringIO as BytesIO
5 except ImportError:
6 from io import BytesIO
7 from gzip import GzipFile
8
9 import six
10 import re
11
12 # - Python>=3.5 GzipFile's read() has issues returning leftover
13 # uncompressed data when input is corrupted
14 # (regression or bug-fix compared to Python 3.4)
15 # - read1(), which fetches data before raising EOFError on next call
16 # works here but is only available from Python>=3.3
17 # - scrapy does not support Python 3.2
18 # - Python 2.7 GzipFile works fine with standard read() + extrabuf
19 if six.PY2:
20 def read1(gzf, size=-1):
21 return gzf.read(size)
22 else:
23 def read1(gzf, size=-1):
24 return gzf.read1(size)
25
26
27 def gunzip(data):
28 """Gunzip the given data and return as much data as possible.
29
30 This is resilient to CRC checksum errors.
31 """
32 f = GzipFile(fileobj=BytesIO(data))
33 output = b''
34 chunk = b'.'
35 while chunk:
36 try:
37 chunk = read1(f, 8196)
38 output += chunk
39 except (IOError, EOFError, struct.error):
40 # complete only if there is some data, otherwise re-raise
41 # see issue 87 about catching struct.error
42 # some pages are quite small so output is '' and f.extrabuf
43 # contains the whole page content
44 if output or getattr(f, 'extrabuf', None):
45 try:
46 output += f.extrabuf
47 finally:
48 break
49 else:
50 raise
51 return output
52
53 _is_gzipped = re.compile(br'^application/(x-)?gzip\b', re.I).search
54 _is_octetstream = re.compile(br'^(application|binary)/octet-stream\b', re.I).search
55
56 def is_gzipped(response):
57 """Return True if the response is gzipped, or False otherwise"""
58 ctype = response.headers.get('Content-Type', b'')
59 cenc = response.headers.get('Content-Encoding', b'').lower()
60 return (_is_gzipped(ctype) or
61 (_is_octetstream(ctype) and cenc in (b'gzip', b'x-gzip')))
62
[end of scrapy/utils/gz.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/scrapy/utils/gz.py b/scrapy/utils/gz.py
--- a/scrapy/utils/gz.py
+++ b/scrapy/utils/gz.py
@@ -43,7 +43,7 @@
# contains the whole page content
if output or getattr(f, 'extrabuf', None):
try:
- output += f.extrabuf
+ output += f.extrabuf[-f.extrasize:]
finally:
break
else:
| {"golden_diff": "diff --git a/scrapy/utils/gz.py b/scrapy/utils/gz.py\n--- a/scrapy/utils/gz.py\n+++ b/scrapy/utils/gz.py\n@@ -43,7 +43,7 @@\n # contains the whole page content\n if output or getattr(f, 'extrabuf', None):\n try:\n- output += f.extrabuf\n+ output += f.extrabuf[-f.extrasize:]\n finally:\n break\n else:\n", "issue": "response.body is duplicate\nAccess the [text page(not mine)](http://files.qidian.com/Author4/3615059/88542882.txt) by browsers or wget and you will find the response content is not duplicate, but scrapy's `response.body` is duplicate. I had tried set the scrapy's headers same as a real brower's, but it is still duplicate.\n\nJust use the follow sample code, and you will find the issue.\n\n```\nscrapy shell \"http://files.qidian.com/Author4/3615059/88542882.txt\"\n```\n\nSorry for my bad english. \n\n", "before_files": [{"content": "import struct\n\ntry:\n from cStringIO import StringIO as BytesIO\nexcept ImportError:\n from io import BytesIO\nfrom gzip import GzipFile\n\nimport six\nimport re\n\n# - Python>=3.5 GzipFile's read() has issues returning leftover\n# uncompressed data when input is corrupted\n# (regression or bug-fix compared to Python 3.4)\n# - read1(), which fetches data before raising EOFError on next call\n# works here but is only available from Python>=3.3\n# - scrapy does not support Python 3.2\n# - Python 2.7 GzipFile works fine with standard read() + extrabuf\nif six.PY2:\n def read1(gzf, size=-1):\n return gzf.read(size)\nelse:\n def read1(gzf, size=-1):\n return gzf.read1(size)\n\n\ndef gunzip(data):\n \"\"\"Gunzip the given data and return as much data as possible.\n\n This is resilient to CRC checksum errors.\n \"\"\"\n f = GzipFile(fileobj=BytesIO(data))\n output = b''\n chunk = b'.'\n while chunk:\n try:\n chunk = read1(f, 8196)\n output += chunk\n except (IOError, EOFError, struct.error):\n # complete only if there is some data, otherwise re-raise\n # see issue 87 about catching struct.error\n # some pages are quite small so output is '' and f.extrabuf\n # contains the whole page content\n if output or getattr(f, 'extrabuf', None):\n try:\n output += f.extrabuf\n finally:\n break\n else:\n raise\n return output\n\n_is_gzipped = re.compile(br'^application/(x-)?gzip\\b', re.I).search\n_is_octetstream = re.compile(br'^(application|binary)/octet-stream\\b', re.I).search\n\ndef is_gzipped(response):\n \"\"\"Return True if the response is gzipped, or False otherwise\"\"\"\n ctype = response.headers.get('Content-Type', b'')\n cenc = response.headers.get('Content-Encoding', b'').lower()\n return (_is_gzipped(ctype) or\n (_is_octetstream(ctype) and cenc in (b'gzip', b'x-gzip')))\n", "path": "scrapy/utils/gz.py"}]} | 1,319 | 107 |
gh_patches_debug_31615 | rasdani/github-patches | git_diff | DDMAL__CantusDB-1313 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Users assigned to Bower sources should be able to edit sequences in those sources
Currently, only project managers can edit sequences. Debra requests that editors should be able to be assigned to Bower sources and edit the sequences contained therein.
</issue>
<code>
[start of django/cantusdb_project/main_app/views/sequence.py]
1 from django.views.generic import DetailView, ListView, UpdateView
2 from main_app.models import Sequence
3 from django.db.models import Q
4 from main_app.forms import SequenceEditForm
5 from django.contrib.auth.mixins import LoginRequiredMixin
6 from django.contrib import messages
7 from django.contrib.auth.mixins import UserPassesTestMixin
8 from django.core.exceptions import PermissionDenied
9 from main_app.permissions import (
10 user_can_view_sequence,
11 user_can_edit_sequences,
12 )
13
14
15 class SequenceDetailView(DetailView):
16 """
17 Displays a single Sequence object. Accessed with ``sequences/<int:pk>``
18 """
19
20 model = Sequence
21 context_object_name = "sequence"
22 template_name = "sequence_detail.html"
23
24 def get_context_data(self, **kwargs):
25 sequence = self.get_object()
26 user = self.request.user
27
28 # if the sequence's source isn't published,
29 # only logged-in users should be able to view the sequence's detail page
30 if not user_can_view_sequence(user, sequence):
31 raise PermissionDenied()
32
33 context = super().get_context_data(**kwargs)
34 context["concordances"] = (
35 Sequence.objects.filter(cantus_id=sequence.cantus_id)
36 .select_related("source")
37 .order_by("siglum")
38 )
39 context["user_can_edit_sequence"] = user_can_edit_sequences(user)
40 return context
41
42
43 class SequenceListView(ListView):
44 """
45 Displays a list of Sequence objects. Accessed with ``sequences/``
46 """
47
48 paginate_by = 100
49 context_object_name = "sequences"
50 template_name = "sequence_list.html"
51
52 def get_queryset(self):
53 queryset = Sequence.objects.select_related("source")
54 display_unpublished = self.request.user.is_authenticated
55 if display_unpublished:
56 q_obj_filter = Q()
57 else:
58 q_obj_filter = Q(source__published=True)
59
60 if self.request.GET.get("incipit"):
61 incipit = self.request.GET.get("incipit")
62 q_obj_filter &= Q(incipit__icontains=incipit)
63 if self.request.GET.get("siglum"):
64 siglum = self.request.GET.get("siglum")
65 q_obj_filter &= Q(siglum__icontains=siglum)
66 if self.request.GET.get("cantus_id"):
67 cantus_id = self.request.GET.get("cantus_id")
68 q_obj_filter &= Q(cantus_id__icontains=cantus_id)
69
70 return queryset.filter(q_obj_filter).order_by("siglum", "s_sequence")
71
72
73 class SequenceEditView(LoginRequiredMixin, UserPassesTestMixin, UpdateView):
74 template_name = "sequence_edit.html"
75 model = Sequence
76 form_class = SequenceEditForm
77 pk_url_kwarg = "sequence_id"
78
79 def form_valid(self, form):
80 form.instance.last_updated_by = self.request.user
81 messages.success(
82 self.request,
83 "Sequence updated successfully!",
84 )
85 return super().form_valid(form)
86
87 def test_func(self):
88 user = self.request.user
89 return user_can_edit_sequences(user)
90
[end of django/cantusdb_project/main_app/views/sequence.py]
[start of django/cantusdb_project/main_app/permissions.py]
1 from django.db.models import Q
2 from typing import Optional
3 from main_app.models import (
4 Source,
5 Chant,
6 Sequence,
7 )
8 from users.models import User
9
10
11 def user_can_edit_chants_in_source(user: User, source: Optional[Source]) -> bool:
12 """
13 Checks if the user can edit Chants in a given Source.
14 Used in ChantDetail, ChantList, ChantCreate, ChantDelete, ChantEdit,
15 ChantEditSyllabification, and SourceDetail views.
16 """
17 if user.is_anonymous or (source is None):
18 return False
19
20 source_id = source.id
21 user_is_assigned_to_source: bool = user.sources_user_can_edit.filter(
22 id=source_id
23 ).exists()
24
25 user_is_project_manager: bool = user.groups.filter(name="project manager").exists()
26 user_is_editor: bool = user.groups.filter(name="editor").exists()
27 user_is_contributor: bool = user.groups.filter(name="contributor").exists()
28
29 return (
30 (user_is_project_manager)
31 or (user_is_editor and user_is_assigned_to_source)
32 or (user_is_editor and source.created_by == user)
33 or (user_is_contributor and user_is_assigned_to_source)
34 or (user_is_contributor and source.created_by == user)
35 )
36
37
38 def user_can_proofread_chant(user: User, chant: Chant) -> bool:
39 """
40 Checks if the user can access the proofreading page of a given Source.
41 Used in SourceEditChantsView.
42 """
43 source_id = chant.source.id
44 if user.is_anonymous:
45 return False
46 user_is_assigned_to_source: bool = user.sources_user_can_edit.filter(
47 id=source_id
48 ).exists()
49
50 user_is_project_manager: bool = user.groups.filter(name="project manager").exists()
51 user_is_editor: bool = user.groups.filter(name="editor").exists()
52
53 return (user_is_project_manager) or (user_is_editor and user_is_assigned_to_source)
54
55
56 def user_can_view_source(user: User, source: Source) -> bool:
57 """
58 Checks if the user can view an unpublished Source on the site.
59 Used in ChantDetail, SequenceDetail, and SourceDetail views.
60 """
61 user_is_authenticated: bool = user.is_authenticated
62 return (source.published) or (user_is_authenticated)
63
64
65 def user_can_view_chant(user: User, chant: Chant) -> bool:
66 """
67 Checks if the user can view a Chant belonging to an unpublished Source on the site.
68 Used in ChantDetail, SequenceDetail, and SourceDetail views.
69 """
70 source = chant.source
71 user_is_authenticated: bool = user.is_authenticated
72 return (source is not None) and ((source.published) or (user_is_authenticated))
73
74
75 def user_can_view_sequence(user: User, sequence: Sequence) -> bool:
76 """
77 Checks if the user can view a Sequence belonging to an unpublished Source on the site.
78 Used in ChantDetail, SequenceDetail, and SourceDetail views.
79 """
80 source = sequence.source
81 user_is_authenticated: bool = user.is_authenticated
82 return (source is not None) and ((source.published) or (user_is_authenticated))
83
84
85 def user_can_edit_sequences(user: User) -> bool:
86 """
87 Checks if the user has permission to edit a Sequence object.
88 Used in SequenceDetail and SequenceEdit views.
89 """
90 return user.groups.filter(name="project manager").exists()
91
92
93 def user_can_create_sources(user: User) -> bool:
94 """
95 Checks if the user has permission to create a Source object.
96 Used in SourceCreateView.
97 """
98
99 return user.groups.filter(
100 Q(name="project manager") | Q(name="editor") | Q(name="contributor")
101 ).exists()
102
103
104 def user_can_edit_source(user: User, source: Source) -> bool:
105 """
106 Checks if the user has permission to edit a Source object.
107 Used in SourceDetail, SourceEdit, and SourceDelete views.
108 """
109 if user.is_anonymous:
110 return False
111 source_id = source.id
112 assigned_to_source = user.sources_user_can_edit.filter(id=source_id)
113
114 is_project_manager: bool = user.groups.filter(name="project manager").exists()
115 is_editor: bool = user.groups.filter(name="editor").exists()
116 is_contributor: bool = user.groups.filter(name="contributor").exists()
117
118 return (
119 (is_project_manager)
120 or (is_editor and assigned_to_source)
121 or (is_editor and source.created_by == user)
122 or (is_contributor and source.created_by == user)
123 )
124
125
126 def user_can_view_user_detail(viewing_user: User, user: User) -> bool:
127 """
128 Checks if the user can view the user detail pages of regular users in the database or just indexers.
129 Used in UserDetailView.
130 """
131 return viewing_user.is_authenticated or user.is_indexer
132
133
134 def user_can_manage_source_editors(user: User) -> bool:
135 """
136 Checks if the user has permission to change the editors assigned to a Source.
137 Used in SourceDetailView.
138 """
139 return user.is_staff or user.groups.filter(name="project manager").exists()
140
[end of django/cantusdb_project/main_app/permissions.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/django/cantusdb_project/main_app/permissions.py b/django/cantusdb_project/main_app/permissions.py
--- a/django/cantusdb_project/main_app/permissions.py
+++ b/django/cantusdb_project/main_app/permissions.py
@@ -82,12 +82,31 @@
return (source is not None) and ((source.published) or (user_is_authenticated))
-def user_can_edit_sequences(user: User) -> bool:
+def user_can_edit_sequences(user: User, sequence: Sequence) -> bool:
"""
Checks if the user has permission to edit a Sequence object.
Used in SequenceDetail and SequenceEdit views.
"""
- return user.groups.filter(name="project manager").exists()
+ source = sequence.source
+ if user.is_anonymous or (source is None):
+ return False
+
+ source_id = source.id
+ user_is_assigned_to_source: bool = user.sources_user_can_edit.filter(
+ id=source_id
+ ).exists()
+
+ user_is_project_manager: bool = user.groups.filter(name="project manager").exists()
+ user_is_editor: bool = user.groups.filter(name="editor").exists()
+ user_is_contributor: bool = user.groups.filter(name="contributor").exists()
+
+ return (
+ (user_is_project_manager)
+ or (user_is_editor and user_is_assigned_to_source)
+ or (user_is_editor and source.created_by == user)
+ or (user_is_contributor and user_is_assigned_to_source)
+ or (user_is_contributor and source.created_by == user)
+ )
def user_can_create_sources(user: User) -> bool:
diff --git a/django/cantusdb_project/main_app/views/sequence.py b/django/cantusdb_project/main_app/views/sequence.py
--- a/django/cantusdb_project/main_app/views/sequence.py
+++ b/django/cantusdb_project/main_app/views/sequence.py
@@ -36,7 +36,7 @@
.select_related("source")
.order_by("siglum")
)
- context["user_can_edit_sequence"] = user_can_edit_sequences(user)
+ context["user_can_edit_sequence"] = user_can_edit_sequences(user, sequence)
return context
@@ -86,4 +86,5 @@
def test_func(self):
user = self.request.user
- return user_can_edit_sequences(user)
+ sequence = self.get_object()
+ return user_can_edit_sequences(user, sequence)
| {"golden_diff": "diff --git a/django/cantusdb_project/main_app/permissions.py b/django/cantusdb_project/main_app/permissions.py\n--- a/django/cantusdb_project/main_app/permissions.py\n+++ b/django/cantusdb_project/main_app/permissions.py\n@@ -82,12 +82,31 @@\n return (source is not None) and ((source.published) or (user_is_authenticated))\n \n \n-def user_can_edit_sequences(user: User) -> bool:\n+def user_can_edit_sequences(user: User, sequence: Sequence) -> bool:\n \"\"\"\n Checks if the user has permission to edit a Sequence object.\n Used in SequenceDetail and SequenceEdit views.\n \"\"\"\n- return user.groups.filter(name=\"project manager\").exists()\n+ source = sequence.source\n+ if user.is_anonymous or (source is None):\n+ return False\n+\n+ source_id = source.id\n+ user_is_assigned_to_source: bool = user.sources_user_can_edit.filter(\n+ id=source_id\n+ ).exists()\n+\n+ user_is_project_manager: bool = user.groups.filter(name=\"project manager\").exists()\n+ user_is_editor: bool = user.groups.filter(name=\"editor\").exists()\n+ user_is_contributor: bool = user.groups.filter(name=\"contributor\").exists()\n+\n+ return (\n+ (user_is_project_manager)\n+ or (user_is_editor and user_is_assigned_to_source)\n+ or (user_is_editor and source.created_by == user)\n+ or (user_is_contributor and user_is_assigned_to_source)\n+ or (user_is_contributor and source.created_by == user)\n+ )\n \n \n def user_can_create_sources(user: User) -> bool:\ndiff --git a/django/cantusdb_project/main_app/views/sequence.py b/django/cantusdb_project/main_app/views/sequence.py\n--- a/django/cantusdb_project/main_app/views/sequence.py\n+++ b/django/cantusdb_project/main_app/views/sequence.py\n@@ -36,7 +36,7 @@\n .select_related(\"source\")\n .order_by(\"siglum\")\n )\n- context[\"user_can_edit_sequence\"] = user_can_edit_sequences(user)\n+ context[\"user_can_edit_sequence\"] = user_can_edit_sequences(user, sequence)\n return context\n \n \n@@ -86,4 +86,5 @@\n \n def test_func(self):\n user = self.request.user\n- return user_can_edit_sequences(user)\n+ sequence = self.get_object()\n+ return user_can_edit_sequences(user, sequence)\n", "issue": "Users assigned to Bower sources should be able to edit sequences in those sources\nCurrently, only project managers can edit sequences. Debra requests that editors should be able to be assigned to Bower sources and edit the sequences contained therein.\n", "before_files": [{"content": "from django.views.generic import DetailView, ListView, UpdateView\nfrom main_app.models import Sequence\nfrom django.db.models import Q\nfrom main_app.forms import SequenceEditForm\nfrom django.contrib.auth.mixins import LoginRequiredMixin\nfrom django.contrib import messages\nfrom django.contrib.auth.mixins import UserPassesTestMixin\nfrom django.core.exceptions import PermissionDenied\nfrom main_app.permissions import (\n user_can_view_sequence,\n user_can_edit_sequences,\n)\n\n\nclass SequenceDetailView(DetailView):\n \"\"\"\n Displays a single Sequence object. Accessed with ``sequences/<int:pk>``\n \"\"\"\n\n model = Sequence\n context_object_name = \"sequence\"\n template_name = \"sequence_detail.html\"\n\n def get_context_data(self, **kwargs):\n sequence = self.get_object()\n user = self.request.user\n\n # if the sequence's source isn't published,\n # only logged-in users should be able to view the sequence's detail page\n if not user_can_view_sequence(user, sequence):\n raise PermissionDenied()\n\n context = super().get_context_data(**kwargs)\n context[\"concordances\"] = (\n Sequence.objects.filter(cantus_id=sequence.cantus_id)\n .select_related(\"source\")\n .order_by(\"siglum\")\n )\n context[\"user_can_edit_sequence\"] = user_can_edit_sequences(user)\n return context\n\n\nclass SequenceListView(ListView):\n \"\"\"\n Displays a list of Sequence objects. Accessed with ``sequences/``\n \"\"\"\n\n paginate_by = 100\n context_object_name = \"sequences\"\n template_name = \"sequence_list.html\"\n\n def get_queryset(self):\n queryset = Sequence.objects.select_related(\"source\")\n display_unpublished = self.request.user.is_authenticated\n if display_unpublished:\n q_obj_filter = Q()\n else:\n q_obj_filter = Q(source__published=True)\n\n if self.request.GET.get(\"incipit\"):\n incipit = self.request.GET.get(\"incipit\")\n q_obj_filter &= Q(incipit__icontains=incipit)\n if self.request.GET.get(\"siglum\"):\n siglum = self.request.GET.get(\"siglum\")\n q_obj_filter &= Q(siglum__icontains=siglum)\n if self.request.GET.get(\"cantus_id\"):\n cantus_id = self.request.GET.get(\"cantus_id\")\n q_obj_filter &= Q(cantus_id__icontains=cantus_id)\n\n return queryset.filter(q_obj_filter).order_by(\"siglum\", \"s_sequence\")\n\n\nclass SequenceEditView(LoginRequiredMixin, UserPassesTestMixin, UpdateView):\n template_name = \"sequence_edit.html\"\n model = Sequence\n form_class = SequenceEditForm\n pk_url_kwarg = \"sequence_id\"\n\n def form_valid(self, form):\n form.instance.last_updated_by = self.request.user\n messages.success(\n self.request,\n \"Sequence updated successfully!\",\n )\n return super().form_valid(form)\n\n def test_func(self):\n user = self.request.user\n return user_can_edit_sequences(user)\n", "path": "django/cantusdb_project/main_app/views/sequence.py"}, {"content": "from django.db.models import Q\nfrom typing import Optional\nfrom main_app.models import (\n Source,\n Chant,\n Sequence,\n)\nfrom users.models import User\n\n\ndef user_can_edit_chants_in_source(user: User, source: Optional[Source]) -> bool:\n \"\"\"\n Checks if the user can edit Chants in a given Source.\n Used in ChantDetail, ChantList, ChantCreate, ChantDelete, ChantEdit,\n ChantEditSyllabification, and SourceDetail views.\n \"\"\"\n if user.is_anonymous or (source is None):\n return False\n\n source_id = source.id\n user_is_assigned_to_source: bool = user.sources_user_can_edit.filter(\n id=source_id\n ).exists()\n\n user_is_project_manager: bool = user.groups.filter(name=\"project manager\").exists()\n user_is_editor: bool = user.groups.filter(name=\"editor\").exists()\n user_is_contributor: bool = user.groups.filter(name=\"contributor\").exists()\n\n return (\n (user_is_project_manager)\n or (user_is_editor and user_is_assigned_to_source)\n or (user_is_editor and source.created_by == user)\n or (user_is_contributor and user_is_assigned_to_source)\n or (user_is_contributor and source.created_by == user)\n )\n\n\ndef user_can_proofread_chant(user: User, chant: Chant) -> bool:\n \"\"\"\n Checks if the user can access the proofreading page of a given Source.\n Used in SourceEditChantsView.\n \"\"\"\n source_id = chant.source.id\n if user.is_anonymous:\n return False\n user_is_assigned_to_source: bool = user.sources_user_can_edit.filter(\n id=source_id\n ).exists()\n\n user_is_project_manager: bool = user.groups.filter(name=\"project manager\").exists()\n user_is_editor: bool = user.groups.filter(name=\"editor\").exists()\n\n return (user_is_project_manager) or (user_is_editor and user_is_assigned_to_source)\n\n\ndef user_can_view_source(user: User, source: Source) -> bool:\n \"\"\"\n Checks if the user can view an unpublished Source on the site.\n Used in ChantDetail, SequenceDetail, and SourceDetail views.\n \"\"\"\n user_is_authenticated: bool = user.is_authenticated\n return (source.published) or (user_is_authenticated)\n\n\ndef user_can_view_chant(user: User, chant: Chant) -> bool:\n \"\"\"\n Checks if the user can view a Chant belonging to an unpublished Source on the site.\n Used in ChantDetail, SequenceDetail, and SourceDetail views.\n \"\"\"\n source = chant.source\n user_is_authenticated: bool = user.is_authenticated\n return (source is not None) and ((source.published) or (user_is_authenticated))\n\n\ndef user_can_view_sequence(user: User, sequence: Sequence) -> bool:\n \"\"\"\n Checks if the user can view a Sequence belonging to an unpublished Source on the site.\n Used in ChantDetail, SequenceDetail, and SourceDetail views.\n \"\"\"\n source = sequence.source\n user_is_authenticated: bool = user.is_authenticated\n return (source is not None) and ((source.published) or (user_is_authenticated))\n\n\ndef user_can_edit_sequences(user: User) -> bool:\n \"\"\"\n Checks if the user has permission to edit a Sequence object.\n Used in SequenceDetail and SequenceEdit views.\n \"\"\"\n return user.groups.filter(name=\"project manager\").exists()\n\n\ndef user_can_create_sources(user: User) -> bool:\n \"\"\"\n Checks if the user has permission to create a Source object.\n Used in SourceCreateView.\n \"\"\"\n\n return user.groups.filter(\n Q(name=\"project manager\") | Q(name=\"editor\") | Q(name=\"contributor\")\n ).exists()\n\n\ndef user_can_edit_source(user: User, source: Source) -> bool:\n \"\"\"\n Checks if the user has permission to edit a Source object.\n Used in SourceDetail, SourceEdit, and SourceDelete views.\n \"\"\"\n if user.is_anonymous:\n return False\n source_id = source.id\n assigned_to_source = user.sources_user_can_edit.filter(id=source_id)\n\n is_project_manager: bool = user.groups.filter(name=\"project manager\").exists()\n is_editor: bool = user.groups.filter(name=\"editor\").exists()\n is_contributor: bool = user.groups.filter(name=\"contributor\").exists()\n\n return (\n (is_project_manager)\n or (is_editor and assigned_to_source)\n or (is_editor and source.created_by == user)\n or (is_contributor and source.created_by == user)\n )\n\n\ndef user_can_view_user_detail(viewing_user: User, user: User) -> bool:\n \"\"\"\n Checks if the user can view the user detail pages of regular users in the database or just indexers.\n Used in UserDetailView.\n \"\"\"\n return viewing_user.is_authenticated or user.is_indexer\n\n\ndef user_can_manage_source_editors(user: User) -> bool:\n \"\"\"\n Checks if the user has permission to change the editors assigned to a Source.\n Used in SourceDetailView.\n \"\"\"\n return user.is_staff or user.groups.filter(name=\"project manager\").exists()\n", "path": "django/cantusdb_project/main_app/permissions.py"}]} | 2,879 | 556 |
gh_patches_debug_26561 | rasdani/github-patches | git_diff | OpenEnergyPlatform__oeplatform-611 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Fix OEO page and add OEO pages to navigation bar
- [x] Fix linebreak in link (Dipl.-Ing.)
- [x] Add Daniel to list
- [x] Add pages to navigation bar
</issue>
<code>
[start of ontology/views.py]
1 from django.shortcuts import render, HttpResponse, redirect, Http404
2 from django.views import View
3 from rdflib import Graph, RDFS
4 from oeplatform.settings import ONTOLOGY_FOLDER
5 from collections import OrderedDict
6
7 import os
8 import re
9
10
11 def collect_modules(path):
12 modules = dict()
13 for file in os.listdir(path):
14 if not os.path.isdir(os.path.join(path,file)):
15 match = re.match("^(?P<filename>.*)\.(?P<extension>\w+)$", file)
16 filename, extension = match.groups()
17 if filename not in modules:
18 modules[filename] = dict(extensions=[], comment="No description found")
19 if extension == "owl":
20 g = Graph()
21 g.parse(os.path.join(path, file))
22 root = dict(g.namespaces())['']
23 comments = g.objects(root, RDFS.comment)
24 try:
25 modules[filename]["comment"] = next(comments)
26 except StopIteration:
27 modules[filename]["comment"] = "No description found"
28 modules[filename]["extensions"].append(extension)
29 return modules
30
31 class OntologyOverview(View):
32 def get(self, request, ontology, module_or_id=None, version=None, imports=False):
33 versions = os.listdir(f"{ONTOLOGY_FOLDER}/{ontology}")
34 if not version:
35 version = max((d for d in versions), key=lambda d:[int(x) for x in d.split(".")])
36
37 if "text/html" in request.headers.get("accept","").split(","):
38 main_module = collect_modules(f"{ONTOLOGY_FOLDER}/{ontology}/{version}")
39 main_module_name = list(main_module.keys())[0]
40 main_module = main_module[main_module_name]
41 main_module["name"] = main_module_name
42 submodules = collect_modules(f"{ONTOLOGY_FOLDER}/{ontology}/{version}/modules")
43 # Collect all file names
44
45 imports = collect_modules(f"{ONTOLOGY_FOLDER}/{ontology}/{version}/imports")
46
47 return render(request, "ontology/oeo.html", dict(
48 ontology=ontology,
49 version=version,
50 main_module=main_module,
51 submodules=submodules.items(),
52 imports=imports.items()
53 ))
54 else:
55 module_name = None
56 if module_or_id:
57 if imports:
58 submodules = collect_modules(f"{ONTOLOGY_FOLDER}/{ontology}/{version}/imports")
59 else:
60 submodules = collect_modules(f"{ONTOLOGY_FOLDER}/{ontology}/{version}/modules")
61 # If module_or_id is the name of a valid submodule, use this module
62 if module_or_id in submodules:
63 module_name = module_or_id
64 if imports:
65 return redirect(f"/ontology/{ontology}/releases/{version}/imports/{module_name}.owl")
66 else:
67 return redirect(f"/ontology/{ontology}/releases/{version}/{module_name}.owl")
68 # If no module was requested or the requested id was not a module, serve main ontology
69 if module_name is None:
70 main_module = collect_modules(f"{ONTOLOGY_FOLDER}/{ontology}/{version}")
71 module_name = list(main_module.keys())[0]
72 return redirect(f"/ontology/{ontology}/releases/{version}/{module_name}.owl")
73
74
75 class OntologyStatics(View):
76 def get(self, request, ontology, file, version=None, extension=None, imports=False):
77 """
78 Returns the requested file `{file}.{extension}` of version `version`
79 of ontology `ontology`
80
81 :param version: default: highest version in folder
82 :param extension: default: `.owl`
83 :return:
84 """
85
86 if not extension:
87 extension = "owl"
88 if not version:
89 version = max((d for d in os.listdir(f"{ONTOLOGY_FOLDER}/{ontology}")), key=lambda d:[int(x) for x in d.split(".")])
90 if imports:
91 file_path = f"{ONTOLOGY_FOLDER}/{ontology}/{version}/imports/{file}.{extension}"
92 else:
93 file_path = f"{ONTOLOGY_FOLDER}/{ontology}/{version}/{file}.{extension}"
94 if os.path.exists(file_path):
95 with open(file_path, "br") as f:
96 response = HttpResponse(f, content_type="application/rdf+xml; charset=utf-8")
97 response["Content-Disposition"] = f'attachment; filename="{file}.{extension}"'
98 return response
99 else:
100 file_path = f"{ONTOLOGY_FOLDER}/{ontology}/{version}/modules/{file}.{extension}"
101 if not os.path.exists(file_path):
102 raise Http404
103 with open(file_path, "br") as f:
104 response = HttpResponse(f, content_type="application/rdf+xml; charset=utf-8")
105 response["Content-Disposition"] = f'attachment; filename="{file}.{extension}"'
106 return response
[end of ontology/views.py]
[start of ontology/urls.py]
1 from django.conf.urls import url
2 from django.conf.urls.static import static
3 from django.views.generic import TemplateView, RedirectView
4 from os import walk
5 from ontology import views
6 from oeplatform import settings
7
8 urlpatterns = [
9 url(r"^$", TemplateView.as_view(template_name="ontology/about.html")),
10 url(r"^ontology/oeo-steering-committee$",
11 TemplateView.as_view(template_name="ontology/oeo-steering-committee.html"),
12 name="oeo-s-c"),
13 url(r"^(?P<ontology>[\w_-]+)\/releases(\/v?(?P<version>[\d\.]+))?\/imports\/(?P<file>[\w_-]+)(.(?P<extension>[\w_-]+))?$",
14 views.OntologyStatics.as_view(), {"imports": True}),
15
16 url(r"^(?P<ontology>[\w_-]+)\/releases(\/v?(?P<version>[\d\.]+))?\/(?P<file>[\w_-]+)(.(?P<extension>[\w_-]+))?$",
17 views.OntologyStatics.as_view()),
18
19 url(r"^(?P<ontology>[\w_-]+)\/imports\/(?P<module_or_id>[\w\d_-]+)",
20 views.OntologyOverview.as_view(), {"imports": True}),
21
22 url(r"^(?P<ontology>[\w_-]+)(/(?P<module_or_id>[\w\d_-]+))?",
23 views.OntologyOverview.as_view()),
24
25 ]
26
[end of ontology/urls.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/ontology/urls.py b/ontology/urls.py
--- a/ontology/urls.py
+++ b/ontology/urls.py
@@ -7,9 +7,11 @@
urlpatterns = [
url(r"^$", TemplateView.as_view(template_name="ontology/about.html")),
- url(r"^ontology/oeo-steering-committee$",
+ url(r"^ontology/$", TemplateView.as_view(template_name="ontology/about.html")),
+ url(r"^oeo-steering-committee/$",
TemplateView.as_view(template_name="ontology/oeo-steering-committee.html"),
name="oeo-s-c"),
+ url(r"^ontology/oeo-steering-committee/$", TemplateView.as_view(template_name="ontology/oeo-steering-committee.html")),
url(r"^(?P<ontology>[\w_-]+)\/releases(\/v?(?P<version>[\d\.]+))?\/imports\/(?P<file>[\w_-]+)(.(?P<extension>[\w_-]+))?$",
views.OntologyStatics.as_view(), {"imports": True}),
diff --git a/ontology/views.py b/ontology/views.py
--- a/ontology/views.py
+++ b/ontology/views.py
@@ -30,6 +30,8 @@
class OntologyOverview(View):
def get(self, request, ontology, module_or_id=None, version=None, imports=False):
+ if not os.path.exists(f"{ONTOLOGY_FOLDER}/{ontology}"):
+ raise Http404
versions = os.listdir(f"{ONTOLOGY_FOLDER}/{ontology}")
if not version:
version = max((d for d in versions), key=lambda d:[int(x) for x in d.split(".")])
| {"golden_diff": "diff --git a/ontology/urls.py b/ontology/urls.py\n--- a/ontology/urls.py\n+++ b/ontology/urls.py\n@@ -7,9 +7,11 @@\n \n urlpatterns = [\n url(r\"^$\", TemplateView.as_view(template_name=\"ontology/about.html\")),\n- url(r\"^ontology/oeo-steering-committee$\",\n+ url(r\"^ontology/$\", TemplateView.as_view(template_name=\"ontology/about.html\")),\n+ url(r\"^oeo-steering-committee/$\",\n TemplateView.as_view(template_name=\"ontology/oeo-steering-committee.html\"),\n name=\"oeo-s-c\"),\n+ url(r\"^ontology/oeo-steering-committee/$\", TemplateView.as_view(template_name=\"ontology/oeo-steering-committee.html\")),\n url(r\"^(?P<ontology>[\\w_-]+)\\/releases(\\/v?(?P<version>[\\d\\.]+))?\\/imports\\/(?P<file>[\\w_-]+)(.(?P<extension>[\\w_-]+))?$\",\n views.OntologyStatics.as_view(), {\"imports\": True}),\n \ndiff --git a/ontology/views.py b/ontology/views.py\n--- a/ontology/views.py\n+++ b/ontology/views.py\n@@ -30,6 +30,8 @@\n \n class OntologyOverview(View):\n def get(self, request, ontology, module_or_id=None, version=None, imports=False):\n+ if not os.path.exists(f\"{ONTOLOGY_FOLDER}/{ontology}\"):\n+ raise Http404\n versions = os.listdir(f\"{ONTOLOGY_FOLDER}/{ontology}\")\n if not version:\n version = max((d for d in versions), key=lambda d:[int(x) for x in d.split(\".\")])\n", "issue": "Fix OEO page and add OEO pages to navigation bar\n- [x] Fix linebreak in link (Dipl.-Ing.)\r\n- [x] Add Daniel to list\r\n- [x] Add pages to navigation bar\n", "before_files": [{"content": "from django.shortcuts import render, HttpResponse, redirect, Http404\nfrom django.views import View\nfrom rdflib import Graph, RDFS\nfrom oeplatform.settings import ONTOLOGY_FOLDER\nfrom collections import OrderedDict\n\nimport os\nimport re\n\n\ndef collect_modules(path):\n modules = dict()\n for file in os.listdir(path):\n if not os.path.isdir(os.path.join(path,file)):\n match = re.match(\"^(?P<filename>.*)\\.(?P<extension>\\w+)$\", file)\n filename, extension = match.groups()\n if filename not in modules:\n modules[filename] = dict(extensions=[], comment=\"No description found\")\n if extension == \"owl\":\n g = Graph()\n g.parse(os.path.join(path, file))\n root = dict(g.namespaces())['']\n comments = g.objects(root, RDFS.comment)\n try:\n modules[filename][\"comment\"] = next(comments)\n except StopIteration:\n modules[filename][\"comment\"] = \"No description found\"\n modules[filename][\"extensions\"].append(extension)\n return modules\n\nclass OntologyOverview(View):\n def get(self, request, ontology, module_or_id=None, version=None, imports=False):\n versions = os.listdir(f\"{ONTOLOGY_FOLDER}/{ontology}\")\n if not version:\n version = max((d for d in versions), key=lambda d:[int(x) for x in d.split(\".\")])\n\n if \"text/html\" in request.headers.get(\"accept\",\"\").split(\",\"):\n main_module = collect_modules(f\"{ONTOLOGY_FOLDER}/{ontology}/{version}\")\n main_module_name = list(main_module.keys())[0]\n main_module = main_module[main_module_name]\n main_module[\"name\"] = main_module_name\n submodules = collect_modules(f\"{ONTOLOGY_FOLDER}/{ontology}/{version}/modules\")\n # Collect all file names\n\n imports = collect_modules(f\"{ONTOLOGY_FOLDER}/{ontology}/{version}/imports\")\n\n return render(request, \"ontology/oeo.html\", dict(\n ontology=ontology,\n version=version,\n main_module=main_module,\n submodules=submodules.items(),\n imports=imports.items()\n ))\n else:\n module_name = None\n if module_or_id:\n if imports:\n submodules = collect_modules(f\"{ONTOLOGY_FOLDER}/{ontology}/{version}/imports\")\n else:\n submodules = collect_modules(f\"{ONTOLOGY_FOLDER}/{ontology}/{version}/modules\")\n # If module_or_id is the name of a valid submodule, use this module\n if module_or_id in submodules:\n module_name = module_or_id\n if imports:\n return redirect(f\"/ontology/{ontology}/releases/{version}/imports/{module_name}.owl\")\n else:\n return redirect(f\"/ontology/{ontology}/releases/{version}/{module_name}.owl\")\n # If no module was requested or the requested id was not a module, serve main ontology\n if module_name is None:\n main_module = collect_modules(f\"{ONTOLOGY_FOLDER}/{ontology}/{version}\")\n module_name = list(main_module.keys())[0]\n return redirect(f\"/ontology/{ontology}/releases/{version}/{module_name}.owl\")\n\n\nclass OntologyStatics(View):\n def get(self, request, ontology, file, version=None, extension=None, imports=False):\n \"\"\"\n Returns the requested file `{file}.{extension}` of version `version`\n of ontology `ontology`\n\n :param version: default: highest version in folder\n :param extension: default: `.owl`\n :return:\n \"\"\"\n\n if not extension:\n extension = \"owl\"\n if not version:\n version = max((d for d in os.listdir(f\"{ONTOLOGY_FOLDER}/{ontology}\")), key=lambda d:[int(x) for x in d.split(\".\")])\n if imports:\n file_path = f\"{ONTOLOGY_FOLDER}/{ontology}/{version}/imports/{file}.{extension}\"\n else:\n file_path = f\"{ONTOLOGY_FOLDER}/{ontology}/{version}/{file}.{extension}\"\n if os.path.exists(file_path):\n with open(file_path, \"br\") as f:\n response = HttpResponse(f, content_type=\"application/rdf+xml; charset=utf-8\")\n response[\"Content-Disposition\"] = f'attachment; filename=\"{file}.{extension}\"'\n return response\n else:\n file_path = f\"{ONTOLOGY_FOLDER}/{ontology}/{version}/modules/{file}.{extension}\"\n if not os.path.exists(file_path):\n raise Http404\n with open(file_path, \"br\") as f:\n response = HttpResponse(f, content_type=\"application/rdf+xml; charset=utf-8\")\n response[\"Content-Disposition\"] = f'attachment; filename=\"{file}.{extension}\"'\n return response", "path": "ontology/views.py"}, {"content": "from django.conf.urls import url\nfrom django.conf.urls.static import static\nfrom django.views.generic import TemplateView, RedirectView\nfrom os import walk\nfrom ontology import views\nfrom oeplatform import settings\n\nurlpatterns = [\n url(r\"^$\", TemplateView.as_view(template_name=\"ontology/about.html\")),\n url(r\"^ontology/oeo-steering-committee$\",\n TemplateView.as_view(template_name=\"ontology/oeo-steering-committee.html\"),\n name=\"oeo-s-c\"),\n url(r\"^(?P<ontology>[\\w_-]+)\\/releases(\\/v?(?P<version>[\\d\\.]+))?\\/imports\\/(?P<file>[\\w_-]+)(.(?P<extension>[\\w_-]+))?$\",\n views.OntologyStatics.as_view(), {\"imports\": True}),\n\n url(r\"^(?P<ontology>[\\w_-]+)\\/releases(\\/v?(?P<version>[\\d\\.]+))?\\/(?P<file>[\\w_-]+)(.(?P<extension>[\\w_-]+))?$\",\n views.OntologyStatics.as_view()),\n\n url(r\"^(?P<ontology>[\\w_-]+)\\/imports\\/(?P<module_or_id>[\\w\\d_-]+)\",\n views.OntologyOverview.as_view(), {\"imports\": True}),\n\n url(r\"^(?P<ontology>[\\w_-]+)(/(?P<module_or_id>[\\w\\d_-]+))?\",\n views.OntologyOverview.as_view()),\n\n]\n", "path": "ontology/urls.py"}]} | 2,186 | 377 |
gh_patches_debug_36747 | rasdani/github-patches | git_diff | CiviWiki__OpenCiviWiki-1037 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Move forms from `api/forms.py` to the `accounts/forms.py`
## Idea summary
There are several account/profile forms defined in [`api/forms.py`](https://github.com/CiviWiki/OpenCiviWiki/blob/develop/project/api/forms.py). Those forms should be moved to [`accounts/forms.py`](https://github.com/CiviWiki/OpenCiviWiki/blob/develop/project/accounts/forms.py) or deleted if they are duplicate code.
**Update:** the code in `api/forms.py` is actually redundant, so may simply be deleted.
## Task
The steps to complete this task are:
- [x] [fork this repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo) and clone it to your local computer
- [x] set up a local development environment as [outlined in our Contributing Guide](https://github.com/CiviWiki/OpenCiviWiki/blob/develop/CONTRIBUTING.md#development)
- [x] delete the file `api/forms.py`
- [x] commit your changes
- [x] push your code to GitHub
- [x] [open a pull request](https://docs.github.com/en/github/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request) against the `main` branch in this repository
</issue>
<code>
[start of project/api/forms.py]
1 from django import forms
2 from django.core.files.images import get_image_dimensions
3 from django.contrib.auth import get_user_model
4 from accounts.models import Profile
5
6
7 class UpdatePassword(forms.ModelForm):
8 """
9 Form for updating User Password
10 """
11
12 class Meta:
13 model = get_user_model()
14 fields = ["password", "verify"]
15
16 password = forms.CharField(
17 label="Password",
18 widget=forms.PasswordInput(
19 attrs={
20 "class": "form-control",
21 "placeholder": "Password",
22 "required": "True",
23 }
24 ),
25 )
26 verify = forms.CharField(
27 label="Password Verify",
28 widget=forms.PasswordInput(
29 attrs={
30 "class": "form-control",
31 "placeholder": "Password Verify",
32 "required": "True",
33 }
34 ),
35 help_text="Please retype your password.",
36 )
37
38 def clean(self):
39 """
40 Verifies that the passwords match
41 """
42 clean_data = super(UpdatePassword, self).clean()
43 if "password" in clean_data and "verify" in clean_data:
44 if clean_data["password"] != clean_data["verify"]:
45 raise forms.ValidationError("Passwords don't match.")
46 else:
47 raise forms.ValidationError("Both password fields need to be filled out.")
48 return clean_data
49
50
51 class UpdateProfileImage(forms.ModelForm):
52 """
53 Form for updating profile image
54 """
55
56 class Meta:
57 model = Profile
58 fields = ["profile_image"]
59
60 profile_image = forms.ImageField()
61
62 def clean_profile_image(self):
63 """
64 This function is used to make sure that profile images follow Civiwiki standards.
65
66 Requirements:
67 - Height cannot exceed 960px
68 - Width cannot exceed 1280px
69 - Image must be (jpg, jpeg, pjeg, png)
70 - File size cannot exceed 2MB
71 """
72 profile_image = self.cleaned_data["profile_image"]
73
74 try:
75 w, h = get_image_dimensions(profile_image)
76
77 # validate dimensions
78 max_height = 960
79 max_width = 1280
80 if w > max_width or h > max_height:
81 raise forms.ValidationError(
82 u"Please use an image that is {w} x {h} pixels or smaller.".format(
83 w=max_width, h=max_height
84 )
85 )
86
87 # validate content type
88 main, sub = profile_image.content_type.split("/")
89 if not (main == "image" and sub in ["jpg", "jpeg", "pjpeg", "png"]):
90 raise forms.ValidationError(u"Please use a JPEG or PNG image.")
91
92 # validate file size
93 if len(profile_image) > (2000 * 1024):
94 raise forms.ValidationError(
95 "Profile image file size may not exceed 2MB."
96 )
97
98 except AttributeError:
99 pass
100
101 return profile_image
102
[end of project/api/forms.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/project/api/forms.py b/project/api/forms.py
deleted file mode 100644
--- a/project/api/forms.py
+++ /dev/null
@@ -1,101 +0,0 @@
-from django import forms
-from django.core.files.images import get_image_dimensions
-from django.contrib.auth import get_user_model
-from accounts.models import Profile
-
-
-class UpdatePassword(forms.ModelForm):
- """
- Form for updating User Password
- """
-
- class Meta:
- model = get_user_model()
- fields = ["password", "verify"]
-
- password = forms.CharField(
- label="Password",
- widget=forms.PasswordInput(
- attrs={
- "class": "form-control",
- "placeholder": "Password",
- "required": "True",
- }
- ),
- )
- verify = forms.CharField(
- label="Password Verify",
- widget=forms.PasswordInput(
- attrs={
- "class": "form-control",
- "placeholder": "Password Verify",
- "required": "True",
- }
- ),
- help_text="Please retype your password.",
- )
-
- def clean(self):
- """
- Verifies that the passwords match
- """
- clean_data = super(UpdatePassword, self).clean()
- if "password" in clean_data and "verify" in clean_data:
- if clean_data["password"] != clean_data["verify"]:
- raise forms.ValidationError("Passwords don't match.")
- else:
- raise forms.ValidationError("Both password fields need to be filled out.")
- return clean_data
-
-
-class UpdateProfileImage(forms.ModelForm):
- """
- Form for updating profile image
- """
-
- class Meta:
- model = Profile
- fields = ["profile_image"]
-
- profile_image = forms.ImageField()
-
- def clean_profile_image(self):
- """
- This function is used to make sure that profile images follow Civiwiki standards.
-
- Requirements:
- - Height cannot exceed 960px
- - Width cannot exceed 1280px
- - Image must be (jpg, jpeg, pjeg, png)
- - File size cannot exceed 2MB
- """
- profile_image = self.cleaned_data["profile_image"]
-
- try:
- w, h = get_image_dimensions(profile_image)
-
- # validate dimensions
- max_height = 960
- max_width = 1280
- if w > max_width or h > max_height:
- raise forms.ValidationError(
- u"Please use an image that is {w} x {h} pixels or smaller.".format(
- w=max_width, h=max_height
- )
- )
-
- # validate content type
- main, sub = profile_image.content_type.split("/")
- if not (main == "image" and sub in ["jpg", "jpeg", "pjpeg", "png"]):
- raise forms.ValidationError(u"Please use a JPEG or PNG image.")
-
- # validate file size
- if len(profile_image) > (2000 * 1024):
- raise forms.ValidationError(
- "Profile image file size may not exceed 2MB."
- )
-
- except AttributeError:
- pass
-
- return profile_image
| {"golden_diff": "diff --git a/project/api/forms.py b/project/api/forms.py\ndeleted file mode 100644\n--- a/project/api/forms.py\n+++ /dev/null\n@@ -1,101 +0,0 @@\n-from django import forms\n-from django.core.files.images import get_image_dimensions\n-from django.contrib.auth import get_user_model\n-from accounts.models import Profile\n-\n-\n-class UpdatePassword(forms.ModelForm):\n- \"\"\"\n- Form for updating User Password\n- \"\"\"\n-\n- class Meta:\n- model = get_user_model()\n- fields = [\"password\", \"verify\"]\n-\n- password = forms.CharField(\n- label=\"Password\",\n- widget=forms.PasswordInput(\n- attrs={\n- \"class\": \"form-control\",\n- \"placeholder\": \"Password\",\n- \"required\": \"True\",\n- }\n- ),\n- )\n- verify = forms.CharField(\n- label=\"Password Verify\",\n- widget=forms.PasswordInput(\n- attrs={\n- \"class\": \"form-control\",\n- \"placeholder\": \"Password Verify\",\n- \"required\": \"True\",\n- }\n- ),\n- help_text=\"Please retype your password.\",\n- )\n-\n- def clean(self):\n- \"\"\"\n- Verifies that the passwords match\n- \"\"\"\n- clean_data = super(UpdatePassword, self).clean()\n- if \"password\" in clean_data and \"verify\" in clean_data:\n- if clean_data[\"password\"] != clean_data[\"verify\"]:\n- raise forms.ValidationError(\"Passwords don't match.\")\n- else:\n- raise forms.ValidationError(\"Both password fields need to be filled out.\")\n- return clean_data\n-\n-\n-class UpdateProfileImage(forms.ModelForm):\n- \"\"\"\n- Form for updating profile image\n- \"\"\"\n-\n- class Meta:\n- model = Profile\n- fields = [\"profile_image\"]\n-\n- profile_image = forms.ImageField()\n-\n- def clean_profile_image(self):\n- \"\"\"\n- This function is used to make sure that profile images follow Civiwiki standards.\n-\n- Requirements:\n- - Height cannot exceed 960px\n- - Width cannot exceed 1280px\n- - Image must be (jpg, jpeg, pjeg, png)\n- - File size cannot exceed 2MB\n- \"\"\"\n- profile_image = self.cleaned_data[\"profile_image\"]\n-\n- try:\n- w, h = get_image_dimensions(profile_image)\n-\n- # validate dimensions\n- max_height = 960\n- max_width = 1280\n- if w > max_width or h > max_height:\n- raise forms.ValidationError(\n- u\"Please use an image that is {w} x {h} pixels or smaller.\".format(\n- w=max_width, h=max_height\n- )\n- )\n-\n- # validate content type\n- main, sub = profile_image.content_type.split(\"/\")\n- if not (main == \"image\" and sub in [\"jpg\", \"jpeg\", \"pjpeg\", \"png\"]):\n- raise forms.ValidationError(u\"Please use a JPEG or PNG image.\")\n-\n- # validate file size\n- if len(profile_image) > (2000 * 1024):\n- raise forms.ValidationError(\n- \"Profile image file size may not exceed 2MB.\"\n- )\n-\n- except AttributeError:\n- pass\n-\n- return profile_image\n", "issue": "Move forms from `api/forms.py` to the `accounts/forms.py`\n## Idea summary\r\n\r\nThere are several account/profile forms defined in [`api/forms.py`](https://github.com/CiviWiki/OpenCiviWiki/blob/develop/project/api/forms.py). Those forms should be moved to [`accounts/forms.py`](https://github.com/CiviWiki/OpenCiviWiki/blob/develop/project/accounts/forms.py) or deleted if they are duplicate code.\r\n\r\n**Update:** the code in `api/forms.py` is actually redundant, so may simply be deleted.\r\n\r\n## Task\r\n\r\nThe steps to complete this task are:\r\n\r\n- [x] [fork this repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo) and clone it to your local computer\r\n- [x] set up a local development environment as [outlined in our Contributing Guide](https://github.com/CiviWiki/OpenCiviWiki/blob/develop/CONTRIBUTING.md#development)\r\n- [x] delete the file `api/forms.py`\r\n- [x] commit your changes\r\n- [x] push your code to GitHub\r\n- [x] [open a pull request](https://docs.github.com/en/github/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request) against the `main` branch in this repository\n", "before_files": [{"content": "from django import forms\nfrom django.core.files.images import get_image_dimensions\nfrom django.contrib.auth import get_user_model\nfrom accounts.models import Profile\n\n\nclass UpdatePassword(forms.ModelForm):\n \"\"\"\n Form for updating User Password\n \"\"\"\n\n class Meta:\n model = get_user_model()\n fields = [\"password\", \"verify\"]\n\n password = forms.CharField(\n label=\"Password\",\n widget=forms.PasswordInput(\n attrs={\n \"class\": \"form-control\",\n \"placeholder\": \"Password\",\n \"required\": \"True\",\n }\n ),\n )\n verify = forms.CharField(\n label=\"Password Verify\",\n widget=forms.PasswordInput(\n attrs={\n \"class\": \"form-control\",\n \"placeholder\": \"Password Verify\",\n \"required\": \"True\",\n }\n ),\n help_text=\"Please retype your password.\",\n )\n\n def clean(self):\n \"\"\"\n Verifies that the passwords match\n \"\"\"\n clean_data = super(UpdatePassword, self).clean()\n if \"password\" in clean_data and \"verify\" in clean_data:\n if clean_data[\"password\"] != clean_data[\"verify\"]:\n raise forms.ValidationError(\"Passwords don't match.\")\n else:\n raise forms.ValidationError(\"Both password fields need to be filled out.\")\n return clean_data\n\n\nclass UpdateProfileImage(forms.ModelForm):\n \"\"\"\n Form for updating profile image\n \"\"\"\n\n class Meta:\n model = Profile\n fields = [\"profile_image\"]\n\n profile_image = forms.ImageField()\n\n def clean_profile_image(self):\n \"\"\"\n This function is used to make sure that profile images follow Civiwiki standards.\n\n Requirements:\n - Height cannot exceed 960px\n - Width cannot exceed 1280px\n - Image must be (jpg, jpeg, pjeg, png)\n - File size cannot exceed 2MB\n \"\"\"\n profile_image = self.cleaned_data[\"profile_image\"]\n\n try:\n w, h = get_image_dimensions(profile_image)\n\n # validate dimensions\n max_height = 960\n max_width = 1280\n if w > max_width or h > max_height:\n raise forms.ValidationError(\n u\"Please use an image that is {w} x {h} pixels or smaller.\".format(\n w=max_width, h=max_height\n )\n )\n\n # validate content type\n main, sub = profile_image.content_type.split(\"/\")\n if not (main == \"image\" and sub in [\"jpg\", \"jpeg\", \"pjpeg\", \"png\"]):\n raise forms.ValidationError(u\"Please use a JPEG or PNG image.\")\n\n # validate file size\n if len(profile_image) > (2000 * 1024):\n raise forms.ValidationError(\n \"Profile image file size may not exceed 2MB.\"\n )\n\n except AttributeError:\n pass\n\n return profile_image\n", "path": "project/api/forms.py"}]} | 1,632 | 745 |
gh_patches_debug_31243 | rasdani/github-patches | git_diff | quantumlib__Cirq-4330 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
`cirq.X**1` should be `_PauliX` instead of `XPowGate`
**Description of the issue**
As @ybc1991 pointed out - the type of `cirq.X**1` should be `_PauliX` instead of `XPowGate`. Context: https://github.com/quantumlib/Cirq/pull/4165/files#r646844399.
Discussed on Cirq Cynque on June 9th 2021:
- We should just fix this
- That would make the output type value-dependent. -- that is true, but it should be fine this direction, because _PauliX is a subclass of the XPowGate
**How to reproduce the issue**
```
print(type(cirq.X), type(cirq.X**1))
# Prints:
# <class 'cirq.ops.pauli_gates._PauliX'> <class 'cirq.ops.common_gates.XPowGate'>
```
</issue>
<code>
[start of cirq-core/cirq/ops/pauli_gates.py]
1 # Copyright 2018 The Cirq Developers
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # https://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14 import abc
15 from typing import Any, cast, Tuple, TYPE_CHECKING, Union, Dict
16
17 from cirq._doc import document
18 from cirq.ops import common_gates, raw_types, identity
19 from cirq.type_workarounds import NotImplementedType
20
21
22 if TYPE_CHECKING:
23 import cirq
24 from cirq.ops.pauli_string import SingleQubitPauliStringGateOperation
25 from cirq.value.product_state import (
26 _XEigenState,
27 _YEigenState,
28 _ZEigenState,
29 ) # coverage: ignore
30
31
32 class Pauli(raw_types.Gate, metaclass=abc.ABCMeta):
33 """Represents the Pauli gates.
34
35 This is an abstract class with no public subclasses. The only instances
36 of private subclasses are the X, Y, or Z Pauli gates defined below.
37 """
38
39 _XYZ = None # type: Tuple[Pauli, Pauli, Pauli]
40
41 @staticmethod
42 def by_index(index: int) -> 'Pauli':
43 return Pauli._XYZ[index % 3]
44
45 @staticmethod
46 def by_relative_index(p: 'Pauli', relative_index: int) -> 'Pauli':
47 return Pauli._XYZ[(p._index + relative_index) % 3]
48
49 def __init__(self, index: int, name: str) -> None:
50 self._index = index
51 self._name = name
52
53 def num_qubits(self):
54 return 1
55
56 def _commutes_(self, other: Any, atol: float) -> Union[bool, NotImplementedType, None]:
57 if not isinstance(other, Pauli):
58 return NotImplemented
59 return self is other
60
61 def third(self, second: 'Pauli') -> 'Pauli':
62 return Pauli._XYZ[(-self._index - second._index) % 3]
63
64 def relative_index(self, second: 'Pauli') -> int:
65 """Relative index of self w.r.t. second in the (X, Y, Z) cycle."""
66 return (self._index - second._index + 1) % 3 - 1
67
68 def phased_pauli_product(
69 self, other: Union['cirq.Pauli', 'identity.IdentityGate']
70 ) -> Tuple[complex, Union['cirq.Pauli', 'identity.IdentityGate']]:
71 if self == other:
72 return 1, identity.I
73 if other is identity.I:
74 return 1, self
75 return 1j ** cast(Pauli, other).relative_index(self), self.third(cast(Pauli, other))
76
77 def __gt__(self, other):
78 if not isinstance(other, Pauli):
79 return NotImplemented
80 return (self._index - other._index) % 3 == 1
81
82 def __lt__(self, other):
83 if not isinstance(other, Pauli):
84 return NotImplemented
85 return (other._index - self._index) % 3 == 1
86
87 def on(self, *qubits: 'cirq.Qid') -> 'SingleQubitPauliStringGateOperation':
88 """Returns an application of this gate to the given qubits.
89
90 Args:
91 *qubits: The collection of qubits to potentially apply the gate to.
92 """
93 if len(qubits) != 1:
94 raise ValueError(f'Expected a single qubit, got <{qubits!r}>.')
95 from cirq.ops.pauli_string import SingleQubitPauliStringGateOperation
96
97 return SingleQubitPauliStringGateOperation(self, qubits[0])
98
99 @property
100 def _canonical_exponent(self):
101 """Overrides EigenGate._canonical_exponent in subclasses."""
102 return 1
103
104
105 class _PauliX(Pauli, common_gates.XPowGate):
106 def __init__(self):
107 Pauli.__init__(self, index=0, name='X')
108 common_gates.XPowGate.__init__(self, exponent=1.0)
109
110 def __pow__(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:
111 return common_gates.XPowGate(exponent=exponent)
112
113 def _with_exponent(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:
114 return self.__pow__(exponent)
115
116 @classmethod
117 def _from_json_dict_(cls, exponent, global_shift, **kwargs):
118 assert global_shift == 0
119 assert exponent == 1
120 return Pauli._XYZ[0]
121
122 @property
123 def basis(self: '_PauliX') -> Dict[int, '_XEigenState']:
124 from cirq.value.product_state import _XEigenState
125
126 return {
127 +1: _XEigenState(+1),
128 -1: _XEigenState(-1),
129 }
130
131
132 class _PauliY(Pauli, common_gates.YPowGate):
133 def __init__(self):
134 Pauli.__init__(self, index=1, name='Y')
135 common_gates.YPowGate.__init__(self, exponent=1.0)
136
137 def __pow__(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:
138 return common_gates.YPowGate(exponent=exponent)
139
140 def _with_exponent(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:
141 return self.__pow__(exponent)
142
143 @classmethod
144 def _from_json_dict_(cls, exponent, global_shift, **kwargs):
145 assert global_shift == 0
146 assert exponent == 1
147 return Pauli._XYZ[1]
148
149 @property
150 def basis(self: '_PauliY') -> Dict[int, '_YEigenState']:
151 from cirq.value.product_state import _YEigenState
152
153 return {
154 +1: _YEigenState(+1),
155 -1: _YEigenState(-1),
156 }
157
158
159 class _PauliZ(Pauli, common_gates.ZPowGate):
160 def __init__(self):
161 Pauli.__init__(self, index=2, name='Z')
162 common_gates.ZPowGate.__init__(self, exponent=1.0)
163
164 def __pow__(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:
165 return common_gates.ZPowGate(exponent=exponent)
166
167 def _with_exponent(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:
168 return self.__pow__(exponent)
169
170 @classmethod
171 def _from_json_dict_(cls, exponent, global_shift, **kwargs):
172 assert global_shift == 0
173 assert exponent == 1
174 return Pauli._XYZ[2]
175
176 @property
177 def basis(self: '_PauliZ') -> Dict[int, '_ZEigenState']:
178 from cirq.value.product_state import _ZEigenState
179
180 return {
181 +1: _ZEigenState(+1),
182 -1: _ZEigenState(-1),
183 }
184
185
186 X = _PauliX()
187 document(
188 X,
189 """The Pauli X gate.
190
191 Matrix:
192
193 [[0, 1],
194 [1, 0]]
195 """,
196 )
197
198 Y = _PauliY()
199 document(
200 Y,
201 """The Pauli Y gate.
202
203 Matrix:
204
205 [[0, -i],
206 [i, 0]]
207 """,
208 )
209
210 Z = _PauliZ()
211 document(
212 Z,
213 """The Pauli Z gate.
214
215 Matrix:
216
217 [[1, 0],
218 [0, -1]]
219 """,
220 )
221
222 Pauli._XYZ = (X, Y, Z)
223
[end of cirq-core/cirq/ops/pauli_gates.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/cirq-core/cirq/ops/pauli_gates.py b/cirq-core/cirq/ops/pauli_gates.py
--- a/cirq-core/cirq/ops/pauli_gates.py
+++ b/cirq-core/cirq/ops/pauli_gates.py
@@ -108,7 +108,7 @@
common_gates.XPowGate.__init__(self, exponent=1.0)
def __pow__(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:
- return common_gates.XPowGate(exponent=exponent)
+ return common_gates.XPowGate(exponent=exponent) if exponent != 1 else _PauliX()
def _with_exponent(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:
return self.__pow__(exponent)
@@ -135,7 +135,7 @@
common_gates.YPowGate.__init__(self, exponent=1.0)
def __pow__(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:
- return common_gates.YPowGate(exponent=exponent)
+ return common_gates.YPowGate(exponent=exponent) if exponent != 1 else _PauliY()
def _with_exponent(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:
return self.__pow__(exponent)
@@ -162,7 +162,7 @@
common_gates.ZPowGate.__init__(self, exponent=1.0)
def __pow__(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:
- return common_gates.ZPowGate(exponent=exponent)
+ return common_gates.ZPowGate(exponent=exponent) if exponent != 1 else _PauliZ()
def _with_exponent(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:
return self.__pow__(exponent)
| {"golden_diff": "diff --git a/cirq-core/cirq/ops/pauli_gates.py b/cirq-core/cirq/ops/pauli_gates.py\n--- a/cirq-core/cirq/ops/pauli_gates.py\n+++ b/cirq-core/cirq/ops/pauli_gates.py\n@@ -108,7 +108,7 @@\n common_gates.XPowGate.__init__(self, exponent=1.0)\n \n def __pow__(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:\n- return common_gates.XPowGate(exponent=exponent)\n+ return common_gates.XPowGate(exponent=exponent) if exponent != 1 else _PauliX()\n \n def _with_exponent(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:\n return self.__pow__(exponent)\n@@ -135,7 +135,7 @@\n common_gates.YPowGate.__init__(self, exponent=1.0)\n \n def __pow__(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:\n- return common_gates.YPowGate(exponent=exponent)\n+ return common_gates.YPowGate(exponent=exponent) if exponent != 1 else _PauliY()\n \n def _with_exponent(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:\n return self.__pow__(exponent)\n@@ -162,7 +162,7 @@\n common_gates.ZPowGate.__init__(self, exponent=1.0)\n \n def __pow__(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:\n- return common_gates.ZPowGate(exponent=exponent)\n+ return common_gates.ZPowGate(exponent=exponent) if exponent != 1 else _PauliZ()\n \n def _with_exponent(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:\n return self.__pow__(exponent)\n", "issue": "`cirq.X**1` should be `_PauliX` instead of `XPowGate`\n**Description of the issue**\r\n\r\nAs @ybc1991 pointed out - the type of `cirq.X**1` should be `_PauliX` instead of `XPowGate`. Context: https://github.com/quantumlib/Cirq/pull/4165/files#r646844399. \r\n\r\nDiscussed on Cirq Cynque on June 9th 2021:\r\n- We should just fix this \r\n- That would make the output type value-dependent. -- that is true, but it should be fine this direction, because _PauliX is a subclass of the XPowGate\r\n\r\n\r\n**How to reproduce the issue**\r\n\r\n```\r\nprint(type(cirq.X), type(cirq.X**1))\r\n# Prints:\r\n# <class 'cirq.ops.pauli_gates._PauliX'> <class 'cirq.ops.common_gates.XPowGate'>\r\n```\r\n\n", "before_files": [{"content": "# Copyright 2018 The Cirq Developers\n#\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# https://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\nimport abc\nfrom typing import Any, cast, Tuple, TYPE_CHECKING, Union, Dict\n\nfrom cirq._doc import document\nfrom cirq.ops import common_gates, raw_types, identity\nfrom cirq.type_workarounds import NotImplementedType\n\n\nif TYPE_CHECKING:\n import cirq\n from cirq.ops.pauli_string import SingleQubitPauliStringGateOperation\n from cirq.value.product_state import (\n _XEigenState,\n _YEigenState,\n _ZEigenState,\n ) # coverage: ignore\n\n\nclass Pauli(raw_types.Gate, metaclass=abc.ABCMeta):\n \"\"\"Represents the Pauli gates.\n\n This is an abstract class with no public subclasses. The only instances\n of private subclasses are the X, Y, or Z Pauli gates defined below.\n \"\"\"\n\n _XYZ = None # type: Tuple[Pauli, Pauli, Pauli]\n\n @staticmethod\n def by_index(index: int) -> 'Pauli':\n return Pauli._XYZ[index % 3]\n\n @staticmethod\n def by_relative_index(p: 'Pauli', relative_index: int) -> 'Pauli':\n return Pauli._XYZ[(p._index + relative_index) % 3]\n\n def __init__(self, index: int, name: str) -> None:\n self._index = index\n self._name = name\n\n def num_qubits(self):\n return 1\n\n def _commutes_(self, other: Any, atol: float) -> Union[bool, NotImplementedType, None]:\n if not isinstance(other, Pauli):\n return NotImplemented\n return self is other\n\n def third(self, second: 'Pauli') -> 'Pauli':\n return Pauli._XYZ[(-self._index - second._index) % 3]\n\n def relative_index(self, second: 'Pauli') -> int:\n \"\"\"Relative index of self w.r.t. second in the (X, Y, Z) cycle.\"\"\"\n return (self._index - second._index + 1) % 3 - 1\n\n def phased_pauli_product(\n self, other: Union['cirq.Pauli', 'identity.IdentityGate']\n ) -> Tuple[complex, Union['cirq.Pauli', 'identity.IdentityGate']]:\n if self == other:\n return 1, identity.I\n if other is identity.I:\n return 1, self\n return 1j ** cast(Pauli, other).relative_index(self), self.third(cast(Pauli, other))\n\n def __gt__(self, other):\n if not isinstance(other, Pauli):\n return NotImplemented\n return (self._index - other._index) % 3 == 1\n\n def __lt__(self, other):\n if not isinstance(other, Pauli):\n return NotImplemented\n return (other._index - self._index) % 3 == 1\n\n def on(self, *qubits: 'cirq.Qid') -> 'SingleQubitPauliStringGateOperation':\n \"\"\"Returns an application of this gate to the given qubits.\n\n Args:\n *qubits: The collection of qubits to potentially apply the gate to.\n \"\"\"\n if len(qubits) != 1:\n raise ValueError(f'Expected a single qubit, got <{qubits!r}>.')\n from cirq.ops.pauli_string import SingleQubitPauliStringGateOperation\n\n return SingleQubitPauliStringGateOperation(self, qubits[0])\n\n @property\n def _canonical_exponent(self):\n \"\"\"Overrides EigenGate._canonical_exponent in subclasses.\"\"\"\n return 1\n\n\nclass _PauliX(Pauli, common_gates.XPowGate):\n def __init__(self):\n Pauli.__init__(self, index=0, name='X')\n common_gates.XPowGate.__init__(self, exponent=1.0)\n\n def __pow__(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:\n return common_gates.XPowGate(exponent=exponent)\n\n def _with_exponent(self: '_PauliX', exponent: 'cirq.TParamVal') -> common_gates.XPowGate:\n return self.__pow__(exponent)\n\n @classmethod\n def _from_json_dict_(cls, exponent, global_shift, **kwargs):\n assert global_shift == 0\n assert exponent == 1\n return Pauli._XYZ[0]\n\n @property\n def basis(self: '_PauliX') -> Dict[int, '_XEigenState']:\n from cirq.value.product_state import _XEigenState\n\n return {\n +1: _XEigenState(+1),\n -1: _XEigenState(-1),\n }\n\n\nclass _PauliY(Pauli, common_gates.YPowGate):\n def __init__(self):\n Pauli.__init__(self, index=1, name='Y')\n common_gates.YPowGate.__init__(self, exponent=1.0)\n\n def __pow__(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:\n return common_gates.YPowGate(exponent=exponent)\n\n def _with_exponent(self: '_PauliY', exponent: 'cirq.TParamVal') -> common_gates.YPowGate:\n return self.__pow__(exponent)\n\n @classmethod\n def _from_json_dict_(cls, exponent, global_shift, **kwargs):\n assert global_shift == 0\n assert exponent == 1\n return Pauli._XYZ[1]\n\n @property\n def basis(self: '_PauliY') -> Dict[int, '_YEigenState']:\n from cirq.value.product_state import _YEigenState\n\n return {\n +1: _YEigenState(+1),\n -1: _YEigenState(-1),\n }\n\n\nclass _PauliZ(Pauli, common_gates.ZPowGate):\n def __init__(self):\n Pauli.__init__(self, index=2, name='Z')\n common_gates.ZPowGate.__init__(self, exponent=1.0)\n\n def __pow__(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:\n return common_gates.ZPowGate(exponent=exponent)\n\n def _with_exponent(self: '_PauliZ', exponent: 'cirq.TParamVal') -> common_gates.ZPowGate:\n return self.__pow__(exponent)\n\n @classmethod\n def _from_json_dict_(cls, exponent, global_shift, **kwargs):\n assert global_shift == 0\n assert exponent == 1\n return Pauli._XYZ[2]\n\n @property\n def basis(self: '_PauliZ') -> Dict[int, '_ZEigenState']:\n from cirq.value.product_state import _ZEigenState\n\n return {\n +1: _ZEigenState(+1),\n -1: _ZEigenState(-1),\n }\n\n\nX = _PauliX()\ndocument(\n X,\n \"\"\"The Pauli X gate.\n\n Matrix:\n\n [[0, 1],\n [1, 0]]\n \"\"\",\n)\n\nY = _PauliY()\ndocument(\n Y,\n \"\"\"The Pauli Y gate.\n\n Matrix:\n\n [[0, -i],\n [i, 0]]\n \"\"\",\n)\n\nZ = _PauliZ()\ndocument(\n Z,\n \"\"\"The Pauli Z gate.\n\n Matrix:\n\n [[1, 0],\n [0, -1]]\n \"\"\",\n)\n\nPauli._XYZ = (X, Y, Z)\n", "path": "cirq-core/cirq/ops/pauli_gates.py"}]} | 3,182 | 493 |
gh_patches_debug_1240 | rasdani/github-patches | git_diff | mindsdb__lightwood-603 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
:wrench: Add default logging level environment variable
## Task
Add a `LIGHTWOOD_LOG` environment variable that controls the default logging level for lightwood. It should be possible to set values for it so that `DEBUG`, `INFO`, `WARNING`, `ERROR` and `CRITICAL` are all possible options. The logger lightwood uses is declared and exported [here](https://github.com/mindsdb/lightwood/blob/stable/lightwood/helpers/log.py).
## Steps :male_detective: :female_detective:
- Fork the Lightwood repository, checkout the `staging` branch and from it create a new one.
- Implement the necessary changes.
- Check that only the appropriate logs are getting through. For this, you can run any of the integration tests, like [`test_boston_housing`](https://github.com/mindsdb/lightwood/blob/stable/tests/integration/basic/test_boston_housing.py), and analyze the output.
- Make the PR and address any comments that reviewers might make.
## Additional rewards :1st_place_medal:
Each documentation PR brings :one: point for entry into the draw for a :computer: Deep Learning Laptop powered by the NVIDIA RTX 3080 Max-Q GPU or other swag :shirt: :bear: . For more info check out https://mindsdb.com/hacktoberfest/
</issue>
<code>
[start of lightwood/helpers/log.py]
1 import logging
2 import os
3
4
5 def initialize_log():
6 pid = os.getpid()
7 logging.basicConfig()
8 log = logging.getLogger(f'lightwood-{pid}')
9 log.setLevel(logging.DEBUG)
10 return log
11
12
13 log = initialize_log()
14
[end of lightwood/helpers/log.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/lightwood/helpers/log.py b/lightwood/helpers/log.py
--- a/lightwood/helpers/log.py
+++ b/lightwood/helpers/log.py
@@ -6,7 +6,8 @@
pid = os.getpid()
logging.basicConfig()
log = logging.getLogger(f'lightwood-{pid}')
- log.setLevel(logging.DEBUG)
+ log_level = os.environ.get('LIGHTWOOD_LOG', 'DEBUG')
+ log.setLevel(log_level)
return log
| {"golden_diff": "diff --git a/lightwood/helpers/log.py b/lightwood/helpers/log.py\n--- a/lightwood/helpers/log.py\n+++ b/lightwood/helpers/log.py\n@@ -6,7 +6,8 @@\n pid = os.getpid()\n logging.basicConfig()\n log = logging.getLogger(f'lightwood-{pid}')\n- log.setLevel(logging.DEBUG)\n+ log_level = os.environ.get('LIGHTWOOD_LOG', 'DEBUG')\n+ log.setLevel(log_level)\n return log\n", "issue": ":wrench: Add default logging level environment variable\n## Task\r\n\r\nAdd a `LIGHTWOOD_LOG` environment variable that controls the default logging level for lightwood. It should be possible to set values for it so that `DEBUG`, `INFO`, `WARNING`, `ERROR` and `CRITICAL` are all possible options. The logger lightwood uses is declared and exported [here](https://github.com/mindsdb/lightwood/blob/stable/lightwood/helpers/log.py).\r\n\r\n## Steps :male_detective: :female_detective: \r\n\r\n- Fork the Lightwood repository, checkout the `staging` branch and from it create a new one.\r\n- Implement the necessary changes.\r\n- Check that only the appropriate logs are getting through. For this, you can run any of the integration tests, like [`test_boston_housing`](https://github.com/mindsdb/lightwood/blob/stable/tests/integration/basic/test_boston_housing.py), and analyze the output.\r\n- Make the PR and address any comments that reviewers might make.\r\n\r\n## Additional rewards :1st_place_medal: \r\n\r\nEach documentation PR brings :one: point for entry into the draw for a :computer: Deep Learning Laptop powered by the NVIDIA RTX 3080 Max-Q GPU or other swag :shirt: :bear: . For more info check out https://mindsdb.com/hacktoberfest/\n", "before_files": [{"content": "import logging\nimport os\n\n\ndef initialize_log():\n pid = os.getpid()\n logging.basicConfig()\n log = logging.getLogger(f'lightwood-{pid}')\n log.setLevel(logging.DEBUG)\n return log\n\n\nlog = initialize_log()\n", "path": "lightwood/helpers/log.py"}]} | 891 | 99 |
gh_patches_debug_2089 | rasdani/github-patches | git_diff | OpenMined__PySyft-4708 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add Windows to CI
## Description
Add windows to the CI tests as a separate step for say python 3.8 and torch==1.6.0 initially just to get things working. Then if it works expand to all versions to see any potential issues.
## Definition of Done
This ticket is done when we know what does and doesn't run on Windows in CI from the current "fast" tests and the new "slow" tests. Post a screenshot and link to CI here when it's running.
</issue>
<code>
[start of src/syft/lib/torch/__init__.py]
1 # stdlib
2 from typing import Dict
3 from typing import Union
4
5 # third party
6 from packaging import version
7 import torch
8
9 # syft relative
10 from . import parameter # noqa: 401
11 from . import uppercase_tensor # noqa: 401
12 from ...ast.globals import Globals
13 from .allowlist import allowlist
14
15 TORCH_VERSION = version.parse(torch.__version__)
16
17
18 def get_return_type(support_dict: Union[str, Dict[str, str]]) -> str:
19 if isinstance(support_dict, str):
20 return support_dict
21 else:
22 return support_dict["return_type"]
23
24
25 def version_supported(support_dict: Union[str, Dict[str, str]]) -> bool:
26 if isinstance(support_dict, str):
27 return True
28 else:
29 return TORCH_VERSION >= version.parse(support_dict["min_version"])
30
31
32 def create_torch_ast() -> Globals:
33 ast = Globals()
34
35 # most methods work in all versions and have a single return type
36 # for the more complicated ones we pass a dict with keys like return_type and
37 # min_version
38 for method, return_type_name_or_dict in allowlist.items():
39 if version_supported(support_dict=return_type_name_or_dict):
40 return_type = get_return_type(support_dict=return_type_name_or_dict)
41 if return_type == "unknown":
42 # this allows us to import them for testing
43 continue
44 ast.add_path(
45 path=method, framework_reference=torch, return_type_name=return_type
46 )
47 # add all the torch.nn.Parameter hooks
48 if method.startswith("torch.Tensor."):
49 method = method.replace("torch.Tensor.", "torch.nn.Parameter.")
50 return_type = return_type.replace("torch.Tensor", "torch.nn.Parameter")
51 ast.add_path(
52 path=method, framework_reference=torch, return_type_name=return_type
53 )
54 else:
55 print(f"Skipping torch.{method} not supported in {TORCH_VERSION}")
56
57 for klass in ast.classes:
58 klass.create_pointer_class()
59 klass.create_send_method()
60 klass.create_serialization_methods()
61 klass.create_storable_object_attr_convenience_methods()
62 return ast
63
[end of src/syft/lib/torch/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/syft/lib/torch/__init__.py b/src/syft/lib/torch/__init__.py
--- a/src/syft/lib/torch/__init__.py
+++ b/src/syft/lib/torch/__init__.py
@@ -12,7 +12,7 @@
from ...ast.globals import Globals
from .allowlist import allowlist
-TORCH_VERSION = version.parse(torch.__version__)
+TORCH_VERSION = version.parse(torch.__version__.split("+")[0])
def get_return_type(support_dict: Union[str, Dict[str, str]]) -> str:
| {"golden_diff": "diff --git a/src/syft/lib/torch/__init__.py b/src/syft/lib/torch/__init__.py\n--- a/src/syft/lib/torch/__init__.py\n+++ b/src/syft/lib/torch/__init__.py\n@@ -12,7 +12,7 @@\n from ...ast.globals import Globals\n from .allowlist import allowlist\n \n-TORCH_VERSION = version.parse(torch.__version__)\n+TORCH_VERSION = version.parse(torch.__version__.split(\"+\")[0])\n \n \n def get_return_type(support_dict: Union[str, Dict[str, str]]) -> str:\n", "issue": "Add Windows to CI\n## Description\r\nAdd windows to the CI tests as a separate step for say python 3.8 and torch==1.6.0 initially just to get things working. Then if it works expand to all versions to see any potential issues.\r\n\r\n## Definition of Done\r\nThis ticket is done when we know what does and doesn't run on Windows in CI from the current \"fast\" tests and the new \"slow\" tests. Post a screenshot and link to CI here when it's running.\n", "before_files": [{"content": "# stdlib\nfrom typing import Dict\nfrom typing import Union\n\n# third party\nfrom packaging import version\nimport torch\n\n# syft relative\nfrom . import parameter # noqa: 401\nfrom . import uppercase_tensor # noqa: 401\nfrom ...ast.globals import Globals\nfrom .allowlist import allowlist\n\nTORCH_VERSION = version.parse(torch.__version__)\n\n\ndef get_return_type(support_dict: Union[str, Dict[str, str]]) -> str:\n if isinstance(support_dict, str):\n return support_dict\n else:\n return support_dict[\"return_type\"]\n\n\ndef version_supported(support_dict: Union[str, Dict[str, str]]) -> bool:\n if isinstance(support_dict, str):\n return True\n else:\n return TORCH_VERSION >= version.parse(support_dict[\"min_version\"])\n\n\ndef create_torch_ast() -> Globals:\n ast = Globals()\n\n # most methods work in all versions and have a single return type\n # for the more complicated ones we pass a dict with keys like return_type and\n # min_version\n for method, return_type_name_or_dict in allowlist.items():\n if version_supported(support_dict=return_type_name_or_dict):\n return_type = get_return_type(support_dict=return_type_name_or_dict)\n if return_type == \"unknown\":\n # this allows us to import them for testing\n continue\n ast.add_path(\n path=method, framework_reference=torch, return_type_name=return_type\n )\n # add all the torch.nn.Parameter hooks\n if method.startswith(\"torch.Tensor.\"):\n method = method.replace(\"torch.Tensor.\", \"torch.nn.Parameter.\")\n return_type = return_type.replace(\"torch.Tensor\", \"torch.nn.Parameter\")\n ast.add_path(\n path=method, framework_reference=torch, return_type_name=return_type\n )\n else:\n print(f\"Skipping torch.{method} not supported in {TORCH_VERSION}\")\n\n for klass in ast.classes:\n klass.create_pointer_class()\n klass.create_send_method()\n klass.create_serialization_methods()\n klass.create_storable_object_attr_convenience_methods()\n return ast\n", "path": "src/syft/lib/torch/__init__.py"}]} | 1,231 | 131 |
gh_patches_debug_11012 | rasdani/github-patches | git_diff | pytorch__vision-3545 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Places365 dataset redundant path.join under _check_integrity
## 🐛 Bug
Redundant path.join at line 165 under _check_integrity in torchvision/datasets/places365.py
path.join is already called at line 116 and line 131 under load_categories and load_file_list
cc @pmeier
</issue>
<code>
[start of torchvision/datasets/places365.py]
1 import os
2 from os import path
3 from typing import Any, Callable, Dict, List, Optional, Tuple
4 from urllib.parse import urljoin
5
6 from .folder import default_loader
7 from .utils import verify_str_arg, check_integrity, download_and_extract_archive
8 from .vision import VisionDataset
9
10
11 class Places365(VisionDataset):
12 r"""`Places365 <http://places2.csail.mit.edu/index.html>`_ classification dataset.
13
14 Args:
15 root (string): Root directory of the Places365 dataset.
16 split (string, optional): The dataset split. Can be one of ``train-standard`` (default), ``train-challendge``,
17 ``val``.
18 small (bool, optional): If ``True``, uses the small images, i. e. resized to 256 x 256 pixels, instead of the
19 high resolution ones.
20 download (bool, optional): If ``True``, downloads the dataset components and places them in ``root``. Already
21 downloaded archives are not downloaded again.
22 transform (callable, optional): A function/transform that takes in an PIL image
23 and returns a transformed version. E.g, ``transforms.RandomCrop``
24 target_transform (callable, optional): A function/transform that takes in the
25 target and transforms it.
26 loader (callable, optional): A function to load an image given its path.
27
28 Attributes:
29 classes (list): List of the class names.
30 class_to_idx (dict): Dict with items (class_name, class_index).
31 imgs (list): List of (image path, class_index) tuples
32 targets (list): The class_index value for each image in the dataset
33
34 Raises:
35 RuntimeError: If ``download is False`` and the meta files, i. e. the devkit, are not present or corrupted.
36 RuntimeError: If ``download is True`` and the image archive is already extracted.
37 """
38 _SPLITS = ("train-standard", "train-challenge", "val")
39 _BASE_URL = "http://data.csail.mit.edu/places/places365/"
40 # {variant: (archive, md5)}
41 _DEVKIT_META = {
42 "standard": ("filelist_places365-standard.tar", "35a0585fee1fa656440f3ab298f8479c"),
43 "challenge": ("filelist_places365-challenge.tar", "70a8307e459c3de41690a7c76c931734"),
44 }
45 # (file, md5)
46 _CATEGORIES_META = ("categories_places365.txt", "06c963b85866bd0649f97cb43dd16673")
47 # {split: (file, md5)}
48 _FILE_LIST_META = {
49 "train-standard": ("places365_train_standard.txt", "30f37515461640559006b8329efbed1a"),
50 "train-challenge": ("places365_train_challenge.txt", "b2931dc997b8c33c27e7329c073a6b57"),
51 "val": ("places365_val.txt", "e9f2fd57bfd9d07630173f4e8708e4b1"),
52 }
53 # {(split, small): (file, md5)}
54 _IMAGES_META = {
55 ("train-standard", False): ("train_large_places365standard.tar", "67e186b496a84c929568076ed01a8aa1"),
56 ("train-challenge", False): ("train_large_places365challenge.tar", "605f18e68e510c82b958664ea134545f"),
57 ("val", False): ("val_large.tar", "9b71c4993ad89d2d8bcbdc4aef38042f"),
58 ("train-standard", True): ("train_256_places365standard.tar", "53ca1c756c3d1e7809517cc47c5561c5"),
59 ("train-challenge", True): ("train_256_places365challenge.tar", "741915038a5e3471ec7332404dfb64ef"),
60 ("val", True): ("val_256.tar", "e27b17d8d44f4af9a78502beb927f808"),
61 }
62
63 def __init__(
64 self,
65 root: str,
66 split: str = "train-standard",
67 small: bool = False,
68 download: bool = False,
69 transform: Optional[Callable] = None,
70 target_transform: Optional[Callable] = None,
71 loader: Callable[[str], Any] = default_loader,
72 ) -> None:
73 super().__init__(root, transform=transform, target_transform=target_transform)
74
75 self.split = self._verify_split(split)
76 self.small = small
77 self.loader = loader
78
79 self.classes, self.class_to_idx = self.load_categories(download)
80 self.imgs, self.targets = self.load_file_list(download)
81
82 if download:
83 self.download_images()
84
85 def __getitem__(self, index: int) -> Tuple[Any, Any]:
86 file, target = self.imgs[index]
87 image = self.loader(file)
88
89 if self.transforms is not None:
90 image, target = self.transforms(image, target)
91
92 return image, target
93
94 def __len__(self) -> int:
95 return len(self.imgs)
96
97 @property
98 def variant(self) -> str:
99 return "challenge" if "challenge" in self.split else "standard"
100
101 @property
102 def images_dir(self) -> str:
103 size = "256" if self.small else "large"
104 if self.split.startswith("train"):
105 dir = f"data_{size}_{self.variant}"
106 else:
107 dir = f"{self.split}_{size}"
108 return path.join(self.root, dir)
109
110 def load_categories(self, download: bool = True) -> Tuple[List[str], Dict[str, int]]:
111 def process(line: str) -> Tuple[str, int]:
112 cls, idx = line.split()
113 return cls, int(idx)
114
115 file, md5 = self._CATEGORIES_META
116 file = path.join(self.root, file)
117 if not self._check_integrity(file, md5, download):
118 self.download_devkit()
119
120 with open(file, "r") as fh:
121 class_to_idx = dict(process(line) for line in fh)
122
123 return sorted(class_to_idx.keys()), class_to_idx
124
125 def load_file_list(self, download: bool = True) -> Tuple[List[Tuple[str, int]], List[int]]:
126 def process(line: str, sep="/") -> Tuple[str, int]:
127 image, idx = line.split()
128 return path.join(self.images_dir, image.lstrip(sep).replace(sep, os.sep)), int(idx)
129
130 file, md5 = self._FILE_LIST_META[self.split]
131 file = path.join(self.root, file)
132 if not self._check_integrity(file, md5, download):
133 self.download_devkit()
134
135 with open(file, "r") as fh:
136 images = [process(line) for line in fh]
137
138 _, targets = zip(*images)
139 return images, list(targets)
140
141 def download_devkit(self) -> None:
142 file, md5 = self._DEVKIT_META[self.variant]
143 download_and_extract_archive(urljoin(self._BASE_URL, file), self.root, md5=md5)
144
145 def download_images(self) -> None:
146 if path.exists(self.images_dir):
147 raise RuntimeError(
148 f"The directory {self.images_dir} already exists. If you want to re-download or re-extract the images, "
149 f"delete the directory."
150 )
151
152 file, md5 = self._IMAGES_META[(self.split, self.small)]
153 download_and_extract_archive(urljoin(self._BASE_URL, file), self.root, md5=md5)
154
155 if self.split.startswith("train"):
156 os.rename(self.images_dir.rsplit("_", 1)[0], self.images_dir)
157
158 def extra_repr(self) -> str:
159 return "\n".join(("Split: {split}", "Small: {small}")).format(**self.__dict__)
160
161 def _verify_split(self, split: str) -> str:
162 return verify_str_arg(split, "split", self._SPLITS)
163
164 def _check_integrity(self, file: str, md5: str, download: bool) -> bool:
165 integrity = check_integrity(path.join(self.root, file), md5=md5)
166 if not integrity and not download:
167 raise RuntimeError(
168 f"The file {file} does not exist or is corrupted. You can set download=True to download it."
169 )
170 return integrity
171
[end of torchvision/datasets/places365.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/torchvision/datasets/places365.py b/torchvision/datasets/places365.py
--- a/torchvision/datasets/places365.py
+++ b/torchvision/datasets/places365.py
@@ -162,7 +162,7 @@
return verify_str_arg(split, "split", self._SPLITS)
def _check_integrity(self, file: str, md5: str, download: bool) -> bool:
- integrity = check_integrity(path.join(self.root, file), md5=md5)
+ integrity = check_integrity(file, md5=md5)
if not integrity and not download:
raise RuntimeError(
f"The file {file} does not exist or is corrupted. You can set download=True to download it."
| {"golden_diff": "diff --git a/torchvision/datasets/places365.py b/torchvision/datasets/places365.py\n--- a/torchvision/datasets/places365.py\n+++ b/torchvision/datasets/places365.py\n@@ -162,7 +162,7 @@\n return verify_str_arg(split, \"split\", self._SPLITS)\n \n def _check_integrity(self, file: str, md5: str, download: bool) -> bool:\n- integrity = check_integrity(path.join(self.root, file), md5=md5)\n+ integrity = check_integrity(file, md5=md5)\n if not integrity and not download:\n raise RuntimeError(\n f\"The file {file} does not exist or is corrupted. You can set download=True to download it.\"\n", "issue": "Places365 dataset redundant path.join under _check_integrity\n## \ud83d\udc1b Bug\r\n\r\nRedundant path.join at line 165 under _check_integrity in torchvision/datasets/places365.py\r\n\r\npath.join is already called at line 116 and line 131 under load_categories and load_file_list\n\ncc @pmeier\n", "before_files": [{"content": "import os\nfrom os import path\nfrom typing import Any, Callable, Dict, List, Optional, Tuple\nfrom urllib.parse import urljoin\n\nfrom .folder import default_loader\nfrom .utils import verify_str_arg, check_integrity, download_and_extract_archive\nfrom .vision import VisionDataset\n\n\nclass Places365(VisionDataset):\n r\"\"\"`Places365 <http://places2.csail.mit.edu/index.html>`_ classification dataset.\n\n Args:\n root (string): Root directory of the Places365 dataset.\n split (string, optional): The dataset split. Can be one of ``train-standard`` (default), ``train-challendge``,\n ``val``.\n small (bool, optional): If ``True``, uses the small images, i. e. resized to 256 x 256 pixels, instead of the\n high resolution ones.\n download (bool, optional): If ``True``, downloads the dataset components and places them in ``root``. Already\n downloaded archives are not downloaded again.\n transform (callable, optional): A function/transform that takes in an PIL image\n and returns a transformed version. E.g, ``transforms.RandomCrop``\n target_transform (callable, optional): A function/transform that takes in the\n target and transforms it.\n loader (callable, optional): A function to load an image given its path.\n\n Attributes:\n classes (list): List of the class names.\n class_to_idx (dict): Dict with items (class_name, class_index).\n imgs (list): List of (image path, class_index) tuples\n targets (list): The class_index value for each image in the dataset\n\n Raises:\n RuntimeError: If ``download is False`` and the meta files, i. e. the devkit, are not present or corrupted.\n RuntimeError: If ``download is True`` and the image archive is already extracted.\n \"\"\"\n _SPLITS = (\"train-standard\", \"train-challenge\", \"val\")\n _BASE_URL = \"http://data.csail.mit.edu/places/places365/\"\n # {variant: (archive, md5)}\n _DEVKIT_META = {\n \"standard\": (\"filelist_places365-standard.tar\", \"35a0585fee1fa656440f3ab298f8479c\"),\n \"challenge\": (\"filelist_places365-challenge.tar\", \"70a8307e459c3de41690a7c76c931734\"),\n }\n # (file, md5)\n _CATEGORIES_META = (\"categories_places365.txt\", \"06c963b85866bd0649f97cb43dd16673\")\n # {split: (file, md5)}\n _FILE_LIST_META = {\n \"train-standard\": (\"places365_train_standard.txt\", \"30f37515461640559006b8329efbed1a\"),\n \"train-challenge\": (\"places365_train_challenge.txt\", \"b2931dc997b8c33c27e7329c073a6b57\"),\n \"val\": (\"places365_val.txt\", \"e9f2fd57bfd9d07630173f4e8708e4b1\"),\n }\n # {(split, small): (file, md5)}\n _IMAGES_META = {\n (\"train-standard\", False): (\"train_large_places365standard.tar\", \"67e186b496a84c929568076ed01a8aa1\"),\n (\"train-challenge\", False): (\"train_large_places365challenge.tar\", \"605f18e68e510c82b958664ea134545f\"),\n (\"val\", False): (\"val_large.tar\", \"9b71c4993ad89d2d8bcbdc4aef38042f\"),\n (\"train-standard\", True): (\"train_256_places365standard.tar\", \"53ca1c756c3d1e7809517cc47c5561c5\"),\n (\"train-challenge\", True): (\"train_256_places365challenge.tar\", \"741915038a5e3471ec7332404dfb64ef\"),\n (\"val\", True): (\"val_256.tar\", \"e27b17d8d44f4af9a78502beb927f808\"),\n }\n\n def __init__(\n self,\n root: str,\n split: str = \"train-standard\",\n small: bool = False,\n download: bool = False,\n transform: Optional[Callable] = None,\n target_transform: Optional[Callable] = None,\n loader: Callable[[str], Any] = default_loader,\n ) -> None:\n super().__init__(root, transform=transform, target_transform=target_transform)\n\n self.split = self._verify_split(split)\n self.small = small\n self.loader = loader\n\n self.classes, self.class_to_idx = self.load_categories(download)\n self.imgs, self.targets = self.load_file_list(download)\n\n if download:\n self.download_images()\n\n def __getitem__(self, index: int) -> Tuple[Any, Any]:\n file, target = self.imgs[index]\n image = self.loader(file)\n\n if self.transforms is not None:\n image, target = self.transforms(image, target)\n\n return image, target\n\n def __len__(self) -> int:\n return len(self.imgs)\n\n @property\n def variant(self) -> str:\n return \"challenge\" if \"challenge\" in self.split else \"standard\"\n\n @property\n def images_dir(self) -> str:\n size = \"256\" if self.small else \"large\"\n if self.split.startswith(\"train\"):\n dir = f\"data_{size}_{self.variant}\"\n else:\n dir = f\"{self.split}_{size}\"\n return path.join(self.root, dir)\n\n def load_categories(self, download: bool = True) -> Tuple[List[str], Dict[str, int]]:\n def process(line: str) -> Tuple[str, int]:\n cls, idx = line.split()\n return cls, int(idx)\n\n file, md5 = self._CATEGORIES_META\n file = path.join(self.root, file)\n if not self._check_integrity(file, md5, download):\n self.download_devkit()\n\n with open(file, \"r\") as fh:\n class_to_idx = dict(process(line) for line in fh)\n\n return sorted(class_to_idx.keys()), class_to_idx\n\n def load_file_list(self, download: bool = True) -> Tuple[List[Tuple[str, int]], List[int]]:\n def process(line: str, sep=\"/\") -> Tuple[str, int]:\n image, idx = line.split()\n return path.join(self.images_dir, image.lstrip(sep).replace(sep, os.sep)), int(idx)\n\n file, md5 = self._FILE_LIST_META[self.split]\n file = path.join(self.root, file)\n if not self._check_integrity(file, md5, download):\n self.download_devkit()\n\n with open(file, \"r\") as fh:\n images = [process(line) for line in fh]\n\n _, targets = zip(*images)\n return images, list(targets)\n\n def download_devkit(self) -> None:\n file, md5 = self._DEVKIT_META[self.variant]\n download_and_extract_archive(urljoin(self._BASE_URL, file), self.root, md5=md5)\n\n def download_images(self) -> None:\n if path.exists(self.images_dir):\n raise RuntimeError(\n f\"The directory {self.images_dir} already exists. If you want to re-download or re-extract the images, \"\n f\"delete the directory.\"\n )\n\n file, md5 = self._IMAGES_META[(self.split, self.small)]\n download_and_extract_archive(urljoin(self._BASE_URL, file), self.root, md5=md5)\n\n if self.split.startswith(\"train\"):\n os.rename(self.images_dir.rsplit(\"_\", 1)[0], self.images_dir)\n\n def extra_repr(self) -> str:\n return \"\\n\".join((\"Split: {split}\", \"Small: {small}\")).format(**self.__dict__)\n\n def _verify_split(self, split: str) -> str:\n return verify_str_arg(split, \"split\", self._SPLITS)\n\n def _check_integrity(self, file: str, md5: str, download: bool) -> bool:\n integrity = check_integrity(path.join(self.root, file), md5=md5)\n if not integrity and not download:\n raise RuntimeError(\n f\"The file {file} does not exist or is corrupted. You can set download=True to download it.\"\n )\n return integrity\n", "path": "torchvision/datasets/places365.py"}]} | 3,066 | 181 |
gh_patches_debug_18381 | rasdani/github-patches | git_diff | svthalia__concrexit-3155 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
ThaliaPay batch push throttled by Moneybird
Whenever we process a ThaliaPay batch, we are throttled by Moneybird on the amount of API requests we make.
This is most likely due to saving the bank accounts which are pushed to moneybird when the post_save signal is triggered.
This shouldn't be triggered when the last_used field of the bank account is updated, but it is.
Potential fix:
Make sure that updated_fields is passed (correctly) with the post_save signal for bank accounts.
</issue>
<code>
[start of website/payments/services.py]
1 """The services defined by the payments package."""
2 import datetime
3 from typing import Union
4
5 from django.conf import settings
6 from django.core import mail
7 from django.db.models import Model, Q, QuerySet, Sum
8 from django.urls import reverse
9 from django.utils import timezone
10 from django.utils.translation import gettext_lazy as _
11
12 from members.models import Member
13 from utils.snippets import send_email
14
15 from .exceptions import PaymentError
16 from .models import BankAccount, Payment, PaymentUser
17 from .payables import Payable, payables
18 from .signals import processed_batch
19
20
21 def create_payment(
22 model_payable: Union[Model, Payable],
23 processed_by: Member,
24 pay_type: Union[Payment.CASH, Payment.CARD, Payment.WIRE, Payment.TPAY],
25 ) -> Payment:
26 """Create a new payment from a payable object.
27
28 :param model_payable: Payable or Model object
29 :param processed_by: PaymentUser that processed this payment
30 :param pay_type: Payment type
31 :return: Payment object
32 """
33 if pay_type not in (Payment.CASH, Payment.CARD, Payment.WIRE, Payment.TPAY):
34 raise PaymentError("Invalid payment type")
35
36 if isinstance(model_payable, Payable):
37 payable = model_payable
38 else:
39 payable = payables.get_payable(model_payable)
40
41 payer = (
42 PaymentUser.objects.get(pk=payable.payment_payer.pk)
43 if payable.payment_payer
44 else None
45 )
46
47 if not (
48 (payer and payer == processed_by and pay_type == Payment.TPAY)
49 or (payable.can_manage_payment(processed_by) and pay_type != Payment.TPAY)
50 ):
51 raise PaymentError(
52 _("User processing payment does not have the right permissions")
53 )
54
55 if payable.payment_amount == 0:
56 raise PaymentError(_("Payment amount 0 is not accepted"))
57
58 if pay_type == Payment.TPAY and not payer.tpay_enabled:
59 raise PaymentError(_("This user does not have Thalia Pay enabled"))
60
61 if not payable.paying_allowed:
62 raise PaymentError(_("Payment restricted"))
63
64 if payable.payment is not None:
65 payable.payment.amount = payable.payment_amount
66 payable.payment.notes = payable.payment_notes
67 payable.payment.topic = payable.payment_topic
68 payable.payment.paid_by = payer
69 payable.payment.processed_by = processed_by
70 payable.payment.type = pay_type
71 payable.payment.save()
72 else:
73 payable.payment = Payment.objects.create(
74 processed_by=processed_by,
75 amount=payable.payment_amount,
76 notes=payable.payment_notes,
77 topic=payable.payment_topic,
78 paid_by=payer,
79 type=pay_type,
80 )
81 return payable.payment
82
83
84 def delete_payment(model: Model, member: Member = None, ignore_change_window=False):
85 """Remove a payment from a payable object.
86
87 :param model: Payable or Model object
88 :param member: member deleting the payment
89 :param ignore_change_window: ignore the payment change window
90 :return:
91 """
92 payable = payables.get_payable(model)
93
94 if member and not payable.can_manage_payment(member):
95 raise PaymentError(
96 _("User deleting payment does not have the right permissions.")
97 )
98
99 payment = payable.payment
100 if (
101 payment.created_at
102 < timezone.now() - timezone.timedelta(seconds=settings.PAYMENT_CHANGE_WINDOW)
103 and not ignore_change_window
104 ):
105 raise PaymentError(_("This payment cannot be deleted anymore."))
106 if payment.batch and payment.batch.processed:
107 raise PaymentError(
108 _("This payment has already been processed and hence cannot be deleted.")
109 )
110
111 payable.payment = None
112 payable.model.save()
113 payment.delete()
114
115
116 def update_last_used(queryset: QuerySet, date: datetime.date = None) -> int:
117 """Update the last used field of a BankAccount queryset.
118
119 :param queryset: Queryset of BankAccounts
120 :param date: date to set last_used to
121 :return: number of affected rows
122 """
123 if not date:
124 date = timezone.now().date()
125
126 result = queryset.filter(
127 (Q(valid_from__gte=timezone.now()) & Q(valid_until__lt=timezone.now()))
128 | Q(valid_until=None)
129 ).update(last_used=date)
130 return result
131
132
133 def revoke_old_mandates() -> int:
134 """Revoke all mandates that have not been used for 36 months or more.
135
136 :return: number of affected rows
137 """
138 return BankAccount.objects.filter(
139 last_used__lte=(timezone.now() - timezone.timedelta(days=36 * 30))
140 ).update(valid_until=timezone.now().date())
141
142
143 def process_batch(batch):
144 """Process a Thalia Pay batch.
145
146 :param batch: the batch to be processed
147 :return:
148 """
149 batch.processed = True
150
151 payments = batch.payments_set.select_related("paid_by")
152 for payment in payments:
153 bank_account = payment.paid_by.bank_accounts.last()
154 if not bank_account: # pragma: no cover
155 # This should not happen, cannot haver, does not happen (right... ;p), but if it does, we don't want to crash, but just remove the payment from the batch (make it unprocessed)
156 payment.batch = None
157 payment.save()
158 else:
159 bank_account.last_used = batch.withdrawal_date
160 bank_account.save()
161
162 batch.save()
163 processed_batch.send(sender=None, instance=batch)
164
165 send_tpay_batch_processing_emails(batch)
166
167
168 def derive_next_mandate_no(member) -> str:
169 accounts = (
170 BankAccount.objects.filter(owner=PaymentUser.objects.get(pk=member.pk))
171 .exclude(mandate_no=None)
172 .filter(mandate_no__regex=BankAccount.MANDATE_NO_DEFAULT_REGEX)
173 )
174 new_mandate_no = 1 + max(
175 (int(account.mandate_no.split("-")[1]) for account in accounts), default=0
176 )
177 return f"{member.pk}-{new_mandate_no}"
178
179
180 def send_tpay_batch_processing_emails(batch):
181 """Send withdrawal notice emails to all members in a batch."""
182 member_payments = batch.payments_set.values("paid_by").annotate(total=Sum("amount"))
183 with mail.get_connection() as connection:
184 for member_row in member_payments:
185 member = PaymentUser.objects.get(pk=member_row["paid_by"])
186 total_amount = member_row["total"]
187
188 send_email(
189 to=[member.email],
190 subject="Thalia Pay withdrawal notice",
191 txt_template="payments/email/tpay_withdrawal_notice_mail.txt",
192 html_template="payments/email/tpay_withdrawal_notice_mail.html",
193 connection=connection,
194 context={
195 "name": member.get_full_name(),
196 "batch": batch,
197 "bank_account": member.bank_accounts.filter(
198 mandate_no__isnull=False
199 ).last(),
200 "creditor_id": settings.SEPA_CREDITOR_ID,
201 "payments": batch.payments_set.filter(paid_by=member),
202 "total_amount": total_amount,
203 "payments_url": (
204 settings.BASE_URL
205 + reverse(
206 "payments:payment-list",
207 )
208 ),
209 },
210 )
211 return len(member_payments)
212
213
214 def execute_data_minimisation(dry_run=False):
215 """Anonymizes payments older than 7 years."""
216 # Sometimes years are 366 days of course, but better delete 1 or 2 days early than late
217 payment_deletion_period = timezone.now().date() - timezone.timedelta(days=365 * 7)
218 bankaccount_deletion_period = timezone.now() - datetime.timedelta(days=31 * 13)
219
220 queryset_payments = Payment.objects.filter(
221 created_at__lte=payment_deletion_period
222 ).exclude(paid_by__isnull=True)
223
224 # Delete bank accounts that are not valid anymore, and have not been used in the last 13 months
225 # (13 months is the required time we need to keep the mandates for)
226 queryset_bankaccounts = BankAccount.objects.all()
227 queryset_bankaccounts = queryset_bankaccounts.filter(
228 valid_until__lt=timezone.now()
229 ) # We must always keep valid bank accounts. so we only select the ones that are not valid anymore (valid_until < now)
230 queryset_bankaccounts = queryset_bankaccounts.exclude( # Also keep bank accounts that
231 Q(
232 owner__paid_payment_set__type=Payment.TPAY
233 ), # are used for Thalia Pay payments, AND
234 Q(
235 owner__paid_payment_set__batch__isnull=True
236 ) # have a payment that is in no batch, OR
237 | Q(
238 owner__paid_payment_set__batch__processed=False
239 ) # have an unprocessed batch, OR
240 | Q(
241 owner__paid_payment_set__batch__processing_date__gt=bankaccount_deletion_period # or have a processed batch that is not older than 13 months
242 ),
243 )
244
245 if not dry_run:
246 queryset_payments.update(paid_by=None, processed_by=None)
247 queryset_bankaccounts.delete()
248 return queryset_payments
249
[end of website/payments/services.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/website/payments/services.py b/website/payments/services.py
--- a/website/payments/services.py
+++ b/website/payments/services.py
@@ -152,12 +152,13 @@
for payment in payments:
bank_account = payment.paid_by.bank_accounts.last()
if not bank_account: # pragma: no cover
- # This should not happen, cannot haver, does not happen (right... ;p), but if it does, we don't want to crash, but just remove the payment from the batch (make it unprocessed)
+ # This should not happen, cannot happen, does not happen (right... ;p)
+ # but if it does, we don't want to crash, but just remove the payment from the batch (make it unprocessed)
payment.batch = None
payment.save()
else:
bank_account.last_used = batch.withdrawal_date
- bank_account.save()
+ bank_account.save(update_fields=["last_used"])
batch.save()
processed_batch.send(sender=None, instance=batch)
| {"golden_diff": "diff --git a/website/payments/services.py b/website/payments/services.py\n--- a/website/payments/services.py\n+++ b/website/payments/services.py\n@@ -152,12 +152,13 @@\n for payment in payments:\n bank_account = payment.paid_by.bank_accounts.last()\n if not bank_account: # pragma: no cover\n- # This should not happen, cannot haver, does not happen (right... ;p), but if it does, we don't want to crash, but just remove the payment from the batch (make it unprocessed)\n+ # This should not happen, cannot happen, does not happen (right... ;p)\n+ # but if it does, we don't want to crash, but just remove the payment from the batch (make it unprocessed)\n payment.batch = None\n payment.save()\n else:\n bank_account.last_used = batch.withdrawal_date\n- bank_account.save()\n+ bank_account.save(update_fields=[\"last_used\"])\n \n batch.save()\n processed_batch.send(sender=None, instance=batch)\n", "issue": "ThaliaPay batch push throttled by Moneybird\nWhenever we process a ThaliaPay batch, we are throttled by Moneybird on the amount of API requests we make.\r\nThis is most likely due to saving the bank accounts which are pushed to moneybird when the post_save signal is triggered.\r\nThis shouldn't be triggered when the last_used field of the bank account is updated, but it is.\r\n\r\nPotential fix:\r\nMake sure that updated_fields is passed (correctly) with the post_save signal for bank accounts.\n", "before_files": [{"content": "\"\"\"The services defined by the payments package.\"\"\"\nimport datetime\nfrom typing import Union\n\nfrom django.conf import settings\nfrom django.core import mail\nfrom django.db.models import Model, Q, QuerySet, Sum\nfrom django.urls import reverse\nfrom django.utils import timezone\nfrom django.utils.translation import gettext_lazy as _\n\nfrom members.models import Member\nfrom utils.snippets import send_email\n\nfrom .exceptions import PaymentError\nfrom .models import BankAccount, Payment, PaymentUser\nfrom .payables import Payable, payables\nfrom .signals import processed_batch\n\n\ndef create_payment(\n model_payable: Union[Model, Payable],\n processed_by: Member,\n pay_type: Union[Payment.CASH, Payment.CARD, Payment.WIRE, Payment.TPAY],\n) -> Payment:\n \"\"\"Create a new payment from a payable object.\n\n :param model_payable: Payable or Model object\n :param processed_by: PaymentUser that processed this payment\n :param pay_type: Payment type\n :return: Payment object\n \"\"\"\n if pay_type not in (Payment.CASH, Payment.CARD, Payment.WIRE, Payment.TPAY):\n raise PaymentError(\"Invalid payment type\")\n\n if isinstance(model_payable, Payable):\n payable = model_payable\n else:\n payable = payables.get_payable(model_payable)\n\n payer = (\n PaymentUser.objects.get(pk=payable.payment_payer.pk)\n if payable.payment_payer\n else None\n )\n\n if not (\n (payer and payer == processed_by and pay_type == Payment.TPAY)\n or (payable.can_manage_payment(processed_by) and pay_type != Payment.TPAY)\n ):\n raise PaymentError(\n _(\"User processing payment does not have the right permissions\")\n )\n\n if payable.payment_amount == 0:\n raise PaymentError(_(\"Payment amount 0 is not accepted\"))\n\n if pay_type == Payment.TPAY and not payer.tpay_enabled:\n raise PaymentError(_(\"This user does not have Thalia Pay enabled\"))\n\n if not payable.paying_allowed:\n raise PaymentError(_(\"Payment restricted\"))\n\n if payable.payment is not None:\n payable.payment.amount = payable.payment_amount\n payable.payment.notes = payable.payment_notes\n payable.payment.topic = payable.payment_topic\n payable.payment.paid_by = payer\n payable.payment.processed_by = processed_by\n payable.payment.type = pay_type\n payable.payment.save()\n else:\n payable.payment = Payment.objects.create(\n processed_by=processed_by,\n amount=payable.payment_amount,\n notes=payable.payment_notes,\n topic=payable.payment_topic,\n paid_by=payer,\n type=pay_type,\n )\n return payable.payment\n\n\ndef delete_payment(model: Model, member: Member = None, ignore_change_window=False):\n \"\"\"Remove a payment from a payable object.\n\n :param model: Payable or Model object\n :param member: member deleting the payment\n :param ignore_change_window: ignore the payment change window\n :return:\n \"\"\"\n payable = payables.get_payable(model)\n\n if member and not payable.can_manage_payment(member):\n raise PaymentError(\n _(\"User deleting payment does not have the right permissions.\")\n )\n\n payment = payable.payment\n if (\n payment.created_at\n < timezone.now() - timezone.timedelta(seconds=settings.PAYMENT_CHANGE_WINDOW)\n and not ignore_change_window\n ):\n raise PaymentError(_(\"This payment cannot be deleted anymore.\"))\n if payment.batch and payment.batch.processed:\n raise PaymentError(\n _(\"This payment has already been processed and hence cannot be deleted.\")\n )\n\n payable.payment = None\n payable.model.save()\n payment.delete()\n\n\ndef update_last_used(queryset: QuerySet, date: datetime.date = None) -> int:\n \"\"\"Update the last used field of a BankAccount queryset.\n\n :param queryset: Queryset of BankAccounts\n :param date: date to set last_used to\n :return: number of affected rows\n \"\"\"\n if not date:\n date = timezone.now().date()\n\n result = queryset.filter(\n (Q(valid_from__gte=timezone.now()) & Q(valid_until__lt=timezone.now()))\n | Q(valid_until=None)\n ).update(last_used=date)\n return result\n\n\ndef revoke_old_mandates() -> int:\n \"\"\"Revoke all mandates that have not been used for 36 months or more.\n\n :return: number of affected rows\n \"\"\"\n return BankAccount.objects.filter(\n last_used__lte=(timezone.now() - timezone.timedelta(days=36 * 30))\n ).update(valid_until=timezone.now().date())\n\n\ndef process_batch(batch):\n \"\"\"Process a Thalia Pay batch.\n\n :param batch: the batch to be processed\n :return:\n \"\"\"\n batch.processed = True\n\n payments = batch.payments_set.select_related(\"paid_by\")\n for payment in payments:\n bank_account = payment.paid_by.bank_accounts.last()\n if not bank_account: # pragma: no cover\n # This should not happen, cannot haver, does not happen (right... ;p), but if it does, we don't want to crash, but just remove the payment from the batch (make it unprocessed)\n payment.batch = None\n payment.save()\n else:\n bank_account.last_used = batch.withdrawal_date\n bank_account.save()\n\n batch.save()\n processed_batch.send(sender=None, instance=batch)\n\n send_tpay_batch_processing_emails(batch)\n\n\ndef derive_next_mandate_no(member) -> str:\n accounts = (\n BankAccount.objects.filter(owner=PaymentUser.objects.get(pk=member.pk))\n .exclude(mandate_no=None)\n .filter(mandate_no__regex=BankAccount.MANDATE_NO_DEFAULT_REGEX)\n )\n new_mandate_no = 1 + max(\n (int(account.mandate_no.split(\"-\")[1]) for account in accounts), default=0\n )\n return f\"{member.pk}-{new_mandate_no}\"\n\n\ndef send_tpay_batch_processing_emails(batch):\n \"\"\"Send withdrawal notice emails to all members in a batch.\"\"\"\n member_payments = batch.payments_set.values(\"paid_by\").annotate(total=Sum(\"amount\"))\n with mail.get_connection() as connection:\n for member_row in member_payments:\n member = PaymentUser.objects.get(pk=member_row[\"paid_by\"])\n total_amount = member_row[\"total\"]\n\n send_email(\n to=[member.email],\n subject=\"Thalia Pay withdrawal notice\",\n txt_template=\"payments/email/tpay_withdrawal_notice_mail.txt\",\n html_template=\"payments/email/tpay_withdrawal_notice_mail.html\",\n connection=connection,\n context={\n \"name\": member.get_full_name(),\n \"batch\": batch,\n \"bank_account\": member.bank_accounts.filter(\n mandate_no__isnull=False\n ).last(),\n \"creditor_id\": settings.SEPA_CREDITOR_ID,\n \"payments\": batch.payments_set.filter(paid_by=member),\n \"total_amount\": total_amount,\n \"payments_url\": (\n settings.BASE_URL\n + reverse(\n \"payments:payment-list\",\n )\n ),\n },\n )\n return len(member_payments)\n\n\ndef execute_data_minimisation(dry_run=False):\n \"\"\"Anonymizes payments older than 7 years.\"\"\"\n # Sometimes years are 366 days of course, but better delete 1 or 2 days early than late\n payment_deletion_period = timezone.now().date() - timezone.timedelta(days=365 * 7)\n bankaccount_deletion_period = timezone.now() - datetime.timedelta(days=31 * 13)\n\n queryset_payments = Payment.objects.filter(\n created_at__lte=payment_deletion_period\n ).exclude(paid_by__isnull=True)\n\n # Delete bank accounts that are not valid anymore, and have not been used in the last 13 months\n # (13 months is the required time we need to keep the mandates for)\n queryset_bankaccounts = BankAccount.objects.all()\n queryset_bankaccounts = queryset_bankaccounts.filter(\n valid_until__lt=timezone.now()\n ) # We must always keep valid bank accounts. so we only select the ones that are not valid anymore (valid_until < now)\n queryset_bankaccounts = queryset_bankaccounts.exclude( # Also keep bank accounts that\n Q(\n owner__paid_payment_set__type=Payment.TPAY\n ), # are used for Thalia Pay payments, AND\n Q(\n owner__paid_payment_set__batch__isnull=True\n ) # have a payment that is in no batch, OR\n | Q(\n owner__paid_payment_set__batch__processed=False\n ) # have an unprocessed batch, OR\n | Q(\n owner__paid_payment_set__batch__processing_date__gt=bankaccount_deletion_period # or have a processed batch that is not older than 13 months\n ),\n )\n\n if not dry_run:\n queryset_payments.update(paid_by=None, processed_by=None)\n queryset_bankaccounts.delete()\n return queryset_payments\n", "path": "website/payments/services.py"}]} | 3,249 | 236 |
gh_patches_debug_37129 | rasdani/github-patches | git_diff | streamlink__streamlink-2912 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
[bug] CDNBG - multiple issues
## Bug Report
1. BITelevision should be removed from the plugin and/or wiki/info pages, as it no longer exists.
2. Inlife.bg shouldn't be listed as supported under CDNbg.
3. Tvbulgare.bg should be listed as supported in inlife.bg's place (latter shares the former's stream)
4. Mu-vi.tv gives an error.
5. CDNBG should cover VTK - the national military channel
6. Kanal3's livestream is not found.
7. CDNBG should cover Cherno More - the regional channel for Varna, Bulgaria.
### Reproduction steps / Explicit stream URLs to test
1. https://bitelevision.com/ is not a thing anymore.
2. Inlife.bg can't be opened and shouldn't be listed - it is a 'media partner' that restreams https://tvbulgare.bg/, which could be put in as a replacement for it.
3. https://tvbulgare.bg/ - No playable streams found.
4. http://mu-vi.tv/LiveStreams/pages/Live.aspx - Error: Unable to open URL.
5. https://www.armymedia.bg/
6. https://kanal3.bg/live
7. https://www.chernomore.bg/
</issue>
<code>
[start of src/streamlink/plugins/cdnbg.py]
1 import logging
2 import re
3
4 from streamlink.compat import urlparse
5 from streamlink.plugin import Plugin
6 from streamlink.plugin.api import useragents
7 from streamlink.plugin.api import validate
8 from streamlink.stream import HLSStream
9 from streamlink.utils import update_scheme
10
11 log = logging.getLogger(__name__)
12
13
14 class CDNBG(Plugin):
15 url_re = re.compile(r"""
16 https?://(?:www\.)?(?:
17 tv\.bnt\.bg/\w+(?:/\w+)?|
18 bitelevision\.com/live|
19 nova\.bg/live|
20 kanal3\.bg/live|
21 bgonair\.bg/tvonline|
22 inlife\.bg|
23 mmtvmusic\.com/live|
24 mu-vi\.tv/LiveStreams/pages/Live\.aspx|
25 videochanel\.bstv\.bg|
26 live\.bstv\.bg|
27 bloombergtv.bg/video
28 )/?
29 """, re.VERBOSE)
30 iframe_re = re.compile(r"iframe .*?src=\"((?:https?(?::|:))?//(?:\w+\.)?cdn.bg/live[^\"]+)\"", re.DOTALL)
31 sdata_re = re.compile(r"sdata\.src.*?=.*?(?P<q>[\"'])(?P<url>http.*?)(?P=q)")
32 hls_file_re = re.compile(r"(src|file): (?P<q>[\"'])(?P<url>(https?:)?//.+?m3u8.*?)(?P=q)")
33 hls_src_re = re.compile(r"video src=(?P<url>http[^ ]+m3u8[^ ]*)")
34
35 stream_schema = validate.Schema(
36 validate.any(
37 validate.all(validate.transform(sdata_re.search), validate.get("url")),
38 validate.all(validate.transform(hls_file_re.search), validate.get("url")),
39 validate.all(validate.transform(hls_src_re.search), validate.get("url")),
40 )
41 )
42
43 @classmethod
44 def can_handle_url(cls, url):
45 return cls.url_re.match(url) is not None
46
47 def find_iframe(self, res):
48 p = urlparse(self.url)
49 for url in self.iframe_re.findall(res.text):
50 if "googletagmanager" not in url:
51 url = url.replace(":", ":")
52 if url.startswith("//"):
53 return "{0}:{1}".format(p.scheme, url)
54 else:
55 return url
56
57 def _get_streams(self):
58 self.session.http.headers.update({"User-Agent": useragents.CHROME})
59 res = self.session.http.get(self.url)
60 iframe_url = self.find_iframe(res)
61
62 if iframe_url:
63 log.debug("Found iframe: {0}", iframe_url)
64 res = self.session.http.get(iframe_url, headers={"Referer": self.url})
65 stream_url = update_scheme(self.url, self.stream_schema.validate(res.text))
66 log.warning("SSL Verification disabled.")
67 return HLSStream.parse_variant_playlist(self.session,
68 stream_url,
69 verify=False)
70
71
72 __plugin__ = CDNBG
73
[end of src/streamlink/plugins/cdnbg.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/streamlink/plugins/cdnbg.py b/src/streamlink/plugins/cdnbg.py
--- a/src/streamlink/plugins/cdnbg.py
+++ b/src/streamlink/plugins/cdnbg.py
@@ -15,16 +15,15 @@
url_re = re.compile(r"""
https?://(?:www\.)?(?:
tv\.bnt\.bg/\w+(?:/\w+)?|
- bitelevision\.com/live|
nova\.bg/live|
- kanal3\.bg/live|
bgonair\.bg/tvonline|
- inlife\.bg|
mmtvmusic\.com/live|
mu-vi\.tv/LiveStreams/pages/Live\.aspx|
- videochanel\.bstv\.bg|
live\.bstv\.bg|
- bloombergtv.bg/video
+ bloombergtv.bg/video|
+ armymedia.bg|
+ chernomore.bg|
+ i.cdn.bg/live/
)/?
""", re.VERBOSE)
iframe_re = re.compile(r"iframe .*?src=\"((?:https?(?::|:))?//(?:\w+\.)?cdn.bg/live[^\"]+)\"", re.DOTALL)
@@ -44,23 +43,26 @@
def can_handle_url(cls, url):
return cls.url_re.match(url) is not None
- def find_iframe(self, res):
- p = urlparse(self.url)
- for url in self.iframe_re.findall(res.text):
- if "googletagmanager" not in url:
- url = url.replace(":", ":")
- if url.startswith("//"):
- return "{0}:{1}".format(p.scheme, url)
+ def find_iframe(self, url):
+ self.session.http.headers.update({"User-Agent": useragents.CHROME})
+ res = self.session.http.get(self.url)
+ p = urlparse(url)
+ for iframe_url in self.iframe_re.findall(res.text):
+ if "googletagmanager" not in iframe_url:
+ log.debug("Found iframe: {0}", iframe_url)
+ iframe_url = iframe_url.replace(":", ":")
+ if iframe_url.startswith("//"):
+ return "{0}:{1}".format(p.scheme, iframe_url)
else:
- return url
+ return iframe_url
def _get_streams(self):
- self.session.http.headers.update({"User-Agent": useragents.CHROME})
- res = self.session.http.get(self.url)
- iframe_url = self.find_iframe(res)
+ if "i.cdn.bg/live/" in self.url:
+ iframe_url = self.url
+ else:
+ iframe_url = self.find_iframe(self.url)
if iframe_url:
- log.debug("Found iframe: {0}", iframe_url)
res = self.session.http.get(iframe_url, headers={"Referer": self.url})
stream_url = update_scheme(self.url, self.stream_schema.validate(res.text))
log.warning("SSL Verification disabled.")
| {"golden_diff": "diff --git a/src/streamlink/plugins/cdnbg.py b/src/streamlink/plugins/cdnbg.py\n--- a/src/streamlink/plugins/cdnbg.py\n+++ b/src/streamlink/plugins/cdnbg.py\n@@ -15,16 +15,15 @@\n url_re = re.compile(r\"\"\"\n https?://(?:www\\.)?(?:\n tv\\.bnt\\.bg/\\w+(?:/\\w+)?|\n- bitelevision\\.com/live|\n nova\\.bg/live|\n- kanal3\\.bg/live|\n bgonair\\.bg/tvonline|\n- inlife\\.bg|\n mmtvmusic\\.com/live|\n mu-vi\\.tv/LiveStreams/pages/Live\\.aspx|\n- videochanel\\.bstv\\.bg|\n live\\.bstv\\.bg|\n- bloombergtv.bg/video\n+ bloombergtv.bg/video|\n+ armymedia.bg|\n+ chernomore.bg|\n+ i.cdn.bg/live/\n )/?\n \"\"\", re.VERBOSE)\n iframe_re = re.compile(r\"iframe .*?src=\\\"((?:https?(?::|:))?//(?:\\w+\\.)?cdn.bg/live[^\\\"]+)\\\"\", re.DOTALL)\n@@ -44,23 +43,26 @@\n def can_handle_url(cls, url):\n return cls.url_re.match(url) is not None\n \n- def find_iframe(self, res):\n- p = urlparse(self.url)\n- for url in self.iframe_re.findall(res.text):\n- if \"googletagmanager\" not in url:\n- url = url.replace(\":\", \":\")\n- if url.startswith(\"//\"):\n- return \"{0}:{1}\".format(p.scheme, url)\n+ def find_iframe(self, url):\n+ self.session.http.headers.update({\"User-Agent\": useragents.CHROME})\n+ res = self.session.http.get(self.url)\n+ p = urlparse(url)\n+ for iframe_url in self.iframe_re.findall(res.text):\n+ if \"googletagmanager\" not in iframe_url:\n+ log.debug(\"Found iframe: {0}\", iframe_url)\n+ iframe_url = iframe_url.replace(\":\", \":\")\n+ if iframe_url.startswith(\"//\"):\n+ return \"{0}:{1}\".format(p.scheme, iframe_url)\n else:\n- return url\n+ return iframe_url\n \n def _get_streams(self):\n- self.session.http.headers.update({\"User-Agent\": useragents.CHROME})\n- res = self.session.http.get(self.url)\n- iframe_url = self.find_iframe(res)\n+ if \"i.cdn.bg/live/\" in self.url:\n+ iframe_url = self.url\n+ else:\n+ iframe_url = self.find_iframe(self.url)\n \n if iframe_url:\n- log.debug(\"Found iframe: {0}\", iframe_url)\n res = self.session.http.get(iframe_url, headers={\"Referer\": self.url})\n stream_url = update_scheme(self.url, self.stream_schema.validate(res.text))\n log.warning(\"SSL Verification disabled.\")\n", "issue": "[bug] CDNBG - multiple issues\n## Bug Report\r\n1. BITelevision should be removed from the plugin and/or wiki/info pages, as it no longer exists.\r\n2. Inlife.bg shouldn't be listed as supported under CDNbg.\r\n3. Tvbulgare.bg should be listed as supported in inlife.bg's place (latter shares the former's stream)\r\n4. Mu-vi.tv gives an error.\r\n5. CDNBG should cover VTK - the national military channel\r\n6. Kanal3's livestream is not found.\r\n7. CDNBG should cover Cherno More - the regional channel for Varna, Bulgaria.\r\n\r\n### Reproduction steps / Explicit stream URLs to test\r\n1. https://bitelevision.com/ is not a thing anymore.\r\n2. Inlife.bg can't be opened and shouldn't be listed - it is a 'media partner' that restreams https://tvbulgare.bg/, which could be put in as a replacement for it.\r\n3. https://tvbulgare.bg/ - No playable streams found.\r\n4. http://mu-vi.tv/LiveStreams/pages/Live.aspx - Error: Unable to open URL.\r\n5. https://www.armymedia.bg/\r\n6. https://kanal3.bg/live\r\n7. https://www.chernomore.bg/\n", "before_files": [{"content": "import logging\nimport re\n\nfrom streamlink.compat import urlparse\nfrom streamlink.plugin import Plugin\nfrom streamlink.plugin.api import useragents\nfrom streamlink.plugin.api import validate\nfrom streamlink.stream import HLSStream\nfrom streamlink.utils import update_scheme\n\nlog = logging.getLogger(__name__)\n\n\nclass CDNBG(Plugin):\n url_re = re.compile(r\"\"\"\n https?://(?:www\\.)?(?:\n tv\\.bnt\\.bg/\\w+(?:/\\w+)?|\n bitelevision\\.com/live|\n nova\\.bg/live|\n kanal3\\.bg/live|\n bgonair\\.bg/tvonline|\n inlife\\.bg|\n mmtvmusic\\.com/live|\n mu-vi\\.tv/LiveStreams/pages/Live\\.aspx|\n videochanel\\.bstv\\.bg|\n live\\.bstv\\.bg|\n bloombergtv.bg/video\n )/?\n \"\"\", re.VERBOSE)\n iframe_re = re.compile(r\"iframe .*?src=\\\"((?:https?(?::|:))?//(?:\\w+\\.)?cdn.bg/live[^\\\"]+)\\\"\", re.DOTALL)\n sdata_re = re.compile(r\"sdata\\.src.*?=.*?(?P<q>[\\\"'])(?P<url>http.*?)(?P=q)\")\n hls_file_re = re.compile(r\"(src|file): (?P<q>[\\\"'])(?P<url>(https?:)?//.+?m3u8.*?)(?P=q)\")\n hls_src_re = re.compile(r\"video src=(?P<url>http[^ ]+m3u8[^ ]*)\")\n\n stream_schema = validate.Schema(\n validate.any(\n validate.all(validate.transform(sdata_re.search), validate.get(\"url\")),\n validate.all(validate.transform(hls_file_re.search), validate.get(\"url\")),\n validate.all(validate.transform(hls_src_re.search), validate.get(\"url\")),\n )\n )\n\n @classmethod\n def can_handle_url(cls, url):\n return cls.url_re.match(url) is not None\n\n def find_iframe(self, res):\n p = urlparse(self.url)\n for url in self.iframe_re.findall(res.text):\n if \"googletagmanager\" not in url:\n url = url.replace(\":\", \":\")\n if url.startswith(\"//\"):\n return \"{0}:{1}\".format(p.scheme, url)\n else:\n return url\n\n def _get_streams(self):\n self.session.http.headers.update({\"User-Agent\": useragents.CHROME})\n res = self.session.http.get(self.url)\n iframe_url = self.find_iframe(res)\n\n if iframe_url:\n log.debug(\"Found iframe: {0}\", iframe_url)\n res = self.session.http.get(iframe_url, headers={\"Referer\": self.url})\n stream_url = update_scheme(self.url, self.stream_schema.validate(res.text))\n log.warning(\"SSL Verification disabled.\")\n return HLSStream.parse_variant_playlist(self.session,\n stream_url,\n verify=False)\n\n\n__plugin__ = CDNBG\n", "path": "src/streamlink/plugins/cdnbg.py"}]} | 1,614 | 670 |
gh_patches_debug_26388 | rasdani/github-patches | git_diff | sunpy__sunpy-3592 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add map.sample_at_coords()
Currently to sample the data in a map at a series of coordinates, one has to do (e.g. see [here](http://docs.sunpy.org/en/stable/generated/gallery/plotting/great_arc_example.html)):
```python
pixels = np.asarray(np.rint(m.world_to_pixel(great_arc.coordinates())), dtype=int)
x = pixels[0, :]
y = pixels[1, :]
intensity_along_arc = m.data[y, x]
```
It would be nice if there was a method `sample_at_coords(coords)` that automatically did this under the hood.
</issue>
<code>
[start of sunpy/map/maputils.py]
1 """
2 This submodule provides utility functions to act on `sunpy.map.GenericMap` instances.
3 """
4 from itertools import chain, product
5
6 import numpy as np
7
8 import astropy.units as u
9 from astropy.coordinates import SkyCoord
10
11 from sunpy.coordinates import Helioprojective
12
13 __all__ = ['all_pixel_indices_from_map', 'all_coordinates_from_map',
14 'map_edges', 'solar_angular_radius', 'contains_full_disk',
15 'is_all_off_disk', 'is_all_on_disk', 'contains_limb',
16 'coordinate_is_on_solar_disk', 'on_disk_bounding_coordinates']
17
18
19 def all_pixel_indices_from_map(smap):
20 """
21 Returns pixel pair indices of every pixel in a map.
22
23 Parameters
24 ----------
25 smap : `~sunpy.map.GenericMap`
26 A SunPy map.
27
28 Returns
29 -------
30 `~numpy.array`
31 A `numpy.array` with the all the pixel indices built from the
32 dimensions of the map.
33 """
34 return np.meshgrid(*[np.arange(v.value) for v in smap.dimensions]) * u.pix
35
36
37 def all_coordinates_from_map(smap):
38 """
39 Returns the coordinates of every pixel in a map.
40
41 Parameters
42 ----------
43 smap : `~sunpy.map.GenericMap`
44 A SunPy map.
45
46 Returns
47 -------
48 `~astropy.coordinates.SkyCoord`
49 An two-dimensional array of sky coordinates in the coordinate
50 system "coordinate_system".
51 """
52 x, y = all_pixel_indices_from_map(smap)
53 return smap.pixel_to_world(x, y)
54
55
56 def map_edges(smap):
57 """
58 Returns the pixel locations of the edges of an input map.
59
60 Parameters
61 ----------
62 smap : `~sunpy.map.GenericMap`
63 A SunPy map.
64
65 Returns
66 -------
67 top, bottom, left_hand_side, right_hand_side : `~astropy.units.Quantity`
68 Returns the pixel locations at the edge of the map;
69 the zeroth, first, second and third tuple values
70 return the top, bottom, left hand side and right
71 hand side pixel locations respectively of the input map.
72 """
73 # Calculate all the edge pixels
74 nx, ny = smap.dimensions.x.value, smap.dimensions.y.value
75 top = list(product(np.arange(nx), [ny - 1])) * u.pix
76 bottom = list(product(np.arange(nx), [0])) * u.pix
77 left_hand_side = list(product([0], np.arange(ny))) * u.pix
78 right_hand_side = list(product([nx - 1], np.arange(ny))) * u.pix
79 return top, bottom, left_hand_side, right_hand_side
80
81
82 @u.quantity_input
83 def solar_angular_radius(coordinates):
84 """
85 Calculates the solar angular radius as seen by the observer.
86
87 The tangent of the angular size of the Sun is equal to the radius
88 of the Sun divided by the distance between the observer and the
89 center of the Sun.
90
91 Parameters
92 ----------
93 coordinates : `~astropy.coordinates.SkyCoord`, `~sunpy.coordinates.frames.Helioprojective`
94 The input coordinate. The coordinate frame must be
95 `~sunpy.coordinates.Helioprojective`.
96
97 Returns
98 -------
99 angle : `~astropy.units.Quantity`
100 The solar angular radius.
101 """
102 return np.arctan(coordinates.rsun / coordinates.observer.radius)
103
104
105 def contains_full_disk(smap):
106 """
107 Checks if a map contains the full disk of the Sun.
108
109 A map contains the full disk of the Sun if the following two
110 conditions are met: (1) all the coordinates at the edge of the map are
111 more than solar angular radius from the center of the Sun and, (2) the
112 map is not all off disk. If both these conditions are met, the
113 function returns `True`. Otherwise, the function returns `False`.
114
115 Parameters
116 ----------
117 smap : `~sunpy.map.GenericMap`
118 A map in helioprojective Cartesian coordinates.
119
120 Returns
121 -------
122 `~bool`
123 Returns `False` if any of the coordinates at the edge of the map
124 are less than one solar radius away from the center of the Sun.
125
126 Notes
127 -----
128 This function checks if the image coordinates include the solar disk.
129 Therefore this function would return `True` for a coronagraph image
130 such as from LASCO/C3 or STEREO/SECCHI COR1 since the solar disk is
131 within the field of the view of the instrument (although no emission
132 from the disk itself is present in the data.)
133 """
134 # Calculate all the edge pixels
135 edges = map_edges(smap)
136 edge_pixels = list(chain.from_iterable([edges[0], edges[1], edges[2], edges[3]]))
137 x = [p[0] for p in edge_pixels] * u.pix
138 y = [p[1] for p in edge_pixels] * u.pix
139
140 # Calculate the edge of the world
141 edge_of_world = smap.pixel_to_world(x, y)
142
143 # Calculate the distance of the edge of the world in solar radii
144 coordinate_angles = np.sqrt(edge_of_world.Tx ** 2 + edge_of_world.Ty ** 2)
145
146 # Test if all the edge pixels are more than one solar radius distant
147 # and that the whole map is not all off disk.
148 return np.all(coordinate_angles > solar_angular_radius(edge_of_world)) and ~is_all_off_disk(smap)
149
150
151 @u.quantity_input
152 def coordinate_is_on_solar_disk(coordinates):
153 """
154 Checks if the helioprojective Cartesian coordinates are on the solar disk.
155
156 The check is performed by comparing the coordinate's angular distance
157 to the angular size of the solar radius. The solar disk is assumed to be
158 a circle i.e., solar oblateness and other effects that cause the solar disk to
159 be non-circular are not taken in to account.
160
161 Parameters
162 ----------
163 coordinates : `~astropy.coordinates.SkyCoord`, `~sunpy.coordinates.frames.Helioprojective`
164 The input coordinate. The coordinate frame must be
165 `~sunpy.coordinates.Helioprojective`.
166
167 Returns
168 -------
169 `~bool`
170 Returns `True` if the coordinate is on disk, `False` otherwise.
171 """
172
173 if not isinstance(coordinates.frame, Helioprojective):
174 raise ValueError('The input coordinate(s) must be in the Helioprojective Cartesian frame.')
175 # Calculate the angle of every pixel from the center of the Sun and compare it the angular
176 # radius of the Sun.
177 return np.sqrt(coordinates.Tx ** 2 + coordinates.Ty ** 2) < solar_angular_radius(coordinates)
178
179
180 def is_all_off_disk(smap):
181 """
182 Checks if none of the coordinates in the `~sunpy.map.GenericMap` are on the solar disk.
183
184 The check is performed by calculating the angle of every pixel from
185 the center of the Sun. If they are all greater than the angular
186 radius of the Sun, then the function returns `True`. Otherwise, the function
187 returns `False`.
188
189 Parameters
190 ----------
191 smap : `~sunpy.map.GenericMap`
192 A map in helioprojective Cartesian coordinates.
193
194 Returns
195 -------
196 `~bool`
197 Returns `True` if all map pixels have an angular radius greater than
198 the angular radius of the Sun.
199
200 Notes
201 -----
202 For coronagraph images such as those from LASCO C2 and C3 the full disk is
203 within the field of view of the instrument, but the solar disk itself is not imaged.
204 For such images this function will return `False`.
205 """
206 return np.all(~coordinate_is_on_solar_disk(all_coordinates_from_map(smap)))
207
208
209 def is_all_on_disk(smap):
210 """
211 Checks if all of the coordinates in the `~sunpy.map.GenericMap` are on the solar disk.
212
213 The check is performed by calculating the angle of every pixel from
214 the center of the Sun. If they are all less than the angular
215 radius of the Sun, then the function returns `True`. Otherwise, the function
216 returns `False`.
217
218 Parameters
219 ----------
220 smap : `~sunpy.map.GenericMap`
221 A map in helioprojective Cartesian coordinates.
222
223 Returns
224 -------
225 `~bool`
226 Returns `True` if all map coordinates have an angular radius less than
227 the angular radius of the Sun.
228 """
229 return np.all(coordinate_is_on_solar_disk(all_coordinates_from_map(smap)))
230
231
232 def contains_limb(smap):
233 """
234 Checks if a map contains any part of the solar limb or equivalently whether
235 the map contains both on-disk and off-disk pixels.
236
237 The check is performed by calculating the angular distance of every pixel from
238 the center of the Sun. If at least one pixel is on disk (less than the solar
239 angular radius) and at least one pixel is off disk (greater than the solar
240 angular distance), the function returns `True`. Otherwise, the function
241 returns `False`.
242
243 Parameters
244 ----------
245 smap : `~sunpy.map.GenericMap`
246 A map in helioprojective Cartesian coordinates.
247
248 Returns
249 -------
250 `~bool`
251 Returns `True` If at least one coordinate of the map is on disk and at
252 least one coordinate of the map is off disk.
253
254 Notes
255 -----
256 For coronagraph images such as those from LASCO C2 and C3 the full disk is
257 within the field of view of the instrument, but the solar disk itself is not imaged.
258 For such images this function will return `True`.
259 """
260 on_disk = coordinate_is_on_solar_disk(all_coordinates_from_map(smap))
261 return np.logical_and(np.any(on_disk), np.any(~on_disk))
262
263
264 def on_disk_bounding_coordinates(smap):
265 """
266 Returns the the bottom left and top right coordinates of the smallest
267 rectangular region that contains all the on disk coordinates of the input map.
268
269 Parameters
270 ----------
271 smap : `~sunpy.map.GenericMap`
272 A map in helioprojective Cartesian coordinates.
273
274 Returns
275 -------
276 `~astropy.coordinates.SkyCoord`
277 A `~astropy.coordinates.SkyCoord` of length 2 such that the
278 first entry is the bottom left coordinate and the second entry is the
279 top right coordinate of the smallest rectangular region that contains
280 all the on-disk pixels in the input map.
281 """
282 # Check that the input map is not all off disk.
283 if is_all_off_disk(smap):
284 raise ValueError("The entire map is off disk.")
285
286 # Get all the coordinates from the input map
287 coordinates = all_coordinates_from_map(smap)
288
289 # Find which coordinates are on the disk
290 on_disk = coordinate_is_on_solar_disk(coordinates)
291 on_disk_coordinates = coordinates[on_disk]
292
293 # The bottom left and top right coordinates that contain
294 # the on disk coordinates.
295 tx = on_disk_coordinates.Tx.value
296 ty = on_disk_coordinates.Ty.value
297 return SkyCoord([np.nanmin(tx), np.nanmax(tx)] * u.arcsec,
298 [np.nanmin(ty), np.nanmax(ty)] * u.arcsec,
299 frame=Helioprojective, observer=smap.observer_coordinate)
300
[end of sunpy/map/maputils.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/sunpy/map/maputils.py b/sunpy/map/maputils.py
--- a/sunpy/map/maputils.py
+++ b/sunpy/map/maputils.py
@@ -11,9 +11,10 @@
from sunpy.coordinates import Helioprojective
__all__ = ['all_pixel_indices_from_map', 'all_coordinates_from_map',
- 'map_edges', 'solar_angular_radius', 'contains_full_disk',
- 'is_all_off_disk', 'is_all_on_disk', 'contains_limb',
- 'coordinate_is_on_solar_disk', 'on_disk_bounding_coordinates']
+ 'map_edges', 'solar_angular_radius', 'sample_at_coords',
+ 'contains_full_disk', 'is_all_off_disk', 'is_all_on_disk',
+ 'contains_limb', 'coordinate_is_on_solar_disk',
+ 'on_disk_bounding_coordinates']
def all_pixel_indices_from_map(smap):
@@ -102,6 +103,27 @@
return np.arctan(coordinates.rsun / coordinates.observer.radius)
+def sample_at_coords(smap, coordinates):
+ """
+ Samples the data in a map at given series of coordinates.
+ Uses nearest-neighbor interpolation of coordinates in map, as
+ it effectively uses array indexing.
+
+ Parameters
+ ----------
+ smap : `~sunpy.map.GenericMap`
+ A SunPy map.
+ coordinates : `~astropy.coordinates.SkyCoord`
+ Input coordinates.
+ Returns
+ -------
+ `numpy.array`
+ A `numpy.array` corresponding to the data obtained from the map,
+ at the input coordinates.
+ """
+ return smap.data[smap.wcs.world_to_array_index(coordinates)]
+
+
def contains_full_disk(smap):
"""
Checks if a map contains the full disk of the Sun.
| {"golden_diff": "diff --git a/sunpy/map/maputils.py b/sunpy/map/maputils.py\n--- a/sunpy/map/maputils.py\n+++ b/sunpy/map/maputils.py\n@@ -11,9 +11,10 @@\n from sunpy.coordinates import Helioprojective\n \n __all__ = ['all_pixel_indices_from_map', 'all_coordinates_from_map',\n- 'map_edges', 'solar_angular_radius', 'contains_full_disk',\n- 'is_all_off_disk', 'is_all_on_disk', 'contains_limb',\n- 'coordinate_is_on_solar_disk', 'on_disk_bounding_coordinates']\n+ 'map_edges', 'solar_angular_radius', 'sample_at_coords',\n+ 'contains_full_disk', 'is_all_off_disk', 'is_all_on_disk',\n+ 'contains_limb', 'coordinate_is_on_solar_disk',\n+ 'on_disk_bounding_coordinates']\n \n \n def all_pixel_indices_from_map(smap):\n@@ -102,6 +103,27 @@\n return np.arctan(coordinates.rsun / coordinates.observer.radius)\n \n \n+def sample_at_coords(smap, coordinates):\n+ \"\"\"\n+ Samples the data in a map at given series of coordinates.\n+ Uses nearest-neighbor interpolation of coordinates in map, as\n+ it effectively uses array indexing.\n+\n+ Parameters\n+ ----------\n+ smap : `~sunpy.map.GenericMap`\n+ A SunPy map.\n+ coordinates : `~astropy.coordinates.SkyCoord`\n+ Input coordinates.\n+ Returns\n+ -------\n+ `numpy.array`\n+ A `numpy.array` corresponding to the data obtained from the map,\n+ at the input coordinates.\n+ \"\"\"\n+ return smap.data[smap.wcs.world_to_array_index(coordinates)]\n+\n+\n def contains_full_disk(smap):\n \"\"\"\n Checks if a map contains the full disk of the Sun.\n", "issue": "Add map.sample_at_coords()\nCurrently to sample the data in a map at a series of coordinates, one has to do (e.g. see [here](http://docs.sunpy.org/en/stable/generated/gallery/plotting/great_arc_example.html)):\r\n```python\r\npixels = np.asarray(np.rint(m.world_to_pixel(great_arc.coordinates())), dtype=int)\r\nx = pixels[0, :]\r\ny = pixels[1, :]\r\nintensity_along_arc = m.data[y, x]\r\n```\r\n\r\nIt would be nice if there was a method `sample_at_coords(coords)` that automatically did this under the hood.\n", "before_files": [{"content": "\"\"\"\nThis submodule provides utility functions to act on `sunpy.map.GenericMap` instances.\n\"\"\"\nfrom itertools import chain, product\n\nimport numpy as np\n\nimport astropy.units as u\nfrom astropy.coordinates import SkyCoord\n\nfrom sunpy.coordinates import Helioprojective\n\n__all__ = ['all_pixel_indices_from_map', 'all_coordinates_from_map',\n 'map_edges', 'solar_angular_radius', 'contains_full_disk',\n 'is_all_off_disk', 'is_all_on_disk', 'contains_limb',\n 'coordinate_is_on_solar_disk', 'on_disk_bounding_coordinates']\n\n\ndef all_pixel_indices_from_map(smap):\n \"\"\"\n Returns pixel pair indices of every pixel in a map.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A SunPy map.\n\n Returns\n -------\n `~numpy.array`\n A `numpy.array` with the all the pixel indices built from the\n dimensions of the map.\n \"\"\"\n return np.meshgrid(*[np.arange(v.value) for v in smap.dimensions]) * u.pix\n\n\ndef all_coordinates_from_map(smap):\n \"\"\"\n Returns the coordinates of every pixel in a map.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A SunPy map.\n\n Returns\n -------\n `~astropy.coordinates.SkyCoord`\n An two-dimensional array of sky coordinates in the coordinate\n system \"coordinate_system\".\n \"\"\"\n x, y = all_pixel_indices_from_map(smap)\n return smap.pixel_to_world(x, y)\n\n\ndef map_edges(smap):\n \"\"\"\n Returns the pixel locations of the edges of an input map.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A SunPy map.\n\n Returns\n -------\n top, bottom, left_hand_side, right_hand_side : `~astropy.units.Quantity`\n Returns the pixel locations at the edge of the map;\n the zeroth, first, second and third tuple values\n return the top, bottom, left hand side and right\n hand side pixel locations respectively of the input map.\n \"\"\"\n # Calculate all the edge pixels\n nx, ny = smap.dimensions.x.value, smap.dimensions.y.value\n top = list(product(np.arange(nx), [ny - 1])) * u.pix\n bottom = list(product(np.arange(nx), [0])) * u.pix\n left_hand_side = list(product([0], np.arange(ny))) * u.pix\n right_hand_side = list(product([nx - 1], np.arange(ny))) * u.pix\n return top, bottom, left_hand_side, right_hand_side\n\n\[email protected]_input\ndef solar_angular_radius(coordinates):\n \"\"\"\n Calculates the solar angular radius as seen by the observer.\n\n The tangent of the angular size of the Sun is equal to the radius\n of the Sun divided by the distance between the observer and the\n center of the Sun.\n\n Parameters\n ----------\n coordinates : `~astropy.coordinates.SkyCoord`, `~sunpy.coordinates.frames.Helioprojective`\n The input coordinate. The coordinate frame must be\n `~sunpy.coordinates.Helioprojective`.\n\n Returns\n -------\n angle : `~astropy.units.Quantity`\n The solar angular radius.\n \"\"\"\n return np.arctan(coordinates.rsun / coordinates.observer.radius)\n\n\ndef contains_full_disk(smap):\n \"\"\"\n Checks if a map contains the full disk of the Sun.\n\n A map contains the full disk of the Sun if the following two\n conditions are met: (1) all the coordinates at the edge of the map are\n more than solar angular radius from the center of the Sun and, (2) the\n map is not all off disk. If both these conditions are met, the\n function returns `True`. Otherwise, the function returns `False`.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A map in helioprojective Cartesian coordinates.\n\n Returns\n -------\n `~bool`\n Returns `False` if any of the coordinates at the edge of the map\n are less than one solar radius away from the center of the Sun.\n\n Notes\n -----\n This function checks if the image coordinates include the solar disk.\n Therefore this function would return `True` for a coronagraph image\n such as from LASCO/C3 or STEREO/SECCHI COR1 since the solar disk is\n within the field of the view of the instrument (although no emission\n from the disk itself is present in the data.)\n \"\"\"\n # Calculate all the edge pixels\n edges = map_edges(smap)\n edge_pixels = list(chain.from_iterable([edges[0], edges[1], edges[2], edges[3]]))\n x = [p[0] for p in edge_pixels] * u.pix\n y = [p[1] for p in edge_pixels] * u.pix\n\n # Calculate the edge of the world\n edge_of_world = smap.pixel_to_world(x, y)\n\n # Calculate the distance of the edge of the world in solar radii\n coordinate_angles = np.sqrt(edge_of_world.Tx ** 2 + edge_of_world.Ty ** 2)\n\n # Test if all the edge pixels are more than one solar radius distant\n # and that the whole map is not all off disk.\n return np.all(coordinate_angles > solar_angular_radius(edge_of_world)) and ~is_all_off_disk(smap)\n\n\[email protected]_input\ndef coordinate_is_on_solar_disk(coordinates):\n \"\"\"\n Checks if the helioprojective Cartesian coordinates are on the solar disk.\n\n The check is performed by comparing the coordinate's angular distance\n to the angular size of the solar radius. The solar disk is assumed to be\n a circle i.e., solar oblateness and other effects that cause the solar disk to\n be non-circular are not taken in to account.\n\n Parameters\n ----------\n coordinates : `~astropy.coordinates.SkyCoord`, `~sunpy.coordinates.frames.Helioprojective`\n The input coordinate. The coordinate frame must be\n `~sunpy.coordinates.Helioprojective`.\n\n Returns\n -------\n `~bool`\n Returns `True` if the coordinate is on disk, `False` otherwise.\n \"\"\"\n\n if not isinstance(coordinates.frame, Helioprojective):\n raise ValueError('The input coordinate(s) must be in the Helioprojective Cartesian frame.')\n # Calculate the angle of every pixel from the center of the Sun and compare it the angular\n # radius of the Sun.\n return np.sqrt(coordinates.Tx ** 2 + coordinates.Ty ** 2) < solar_angular_radius(coordinates)\n\n\ndef is_all_off_disk(smap):\n \"\"\"\n Checks if none of the coordinates in the `~sunpy.map.GenericMap` are on the solar disk.\n\n The check is performed by calculating the angle of every pixel from\n the center of the Sun. If they are all greater than the angular\n radius of the Sun, then the function returns `True`. Otherwise, the function\n returns `False`.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A map in helioprojective Cartesian coordinates.\n\n Returns\n -------\n `~bool`\n Returns `True` if all map pixels have an angular radius greater than\n the angular radius of the Sun.\n\n Notes\n -----\n For coronagraph images such as those from LASCO C2 and C3 the full disk is\n within the field of view of the instrument, but the solar disk itself is not imaged.\n For such images this function will return `False`.\n \"\"\"\n return np.all(~coordinate_is_on_solar_disk(all_coordinates_from_map(smap)))\n\n\ndef is_all_on_disk(smap):\n \"\"\"\n Checks if all of the coordinates in the `~sunpy.map.GenericMap` are on the solar disk.\n\n The check is performed by calculating the angle of every pixel from\n the center of the Sun. If they are all less than the angular\n radius of the Sun, then the function returns `True`. Otherwise, the function\n returns `False`.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A map in helioprojective Cartesian coordinates.\n\n Returns\n -------\n `~bool`\n Returns `True` if all map coordinates have an angular radius less than\n the angular radius of the Sun.\n \"\"\"\n return np.all(coordinate_is_on_solar_disk(all_coordinates_from_map(smap)))\n\n\ndef contains_limb(smap):\n \"\"\"\n Checks if a map contains any part of the solar limb or equivalently whether\n the map contains both on-disk and off-disk pixels.\n\n The check is performed by calculating the angular distance of every pixel from\n the center of the Sun. If at least one pixel is on disk (less than the solar\n angular radius) and at least one pixel is off disk (greater than the solar\n angular distance), the function returns `True`. Otherwise, the function\n returns `False`.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A map in helioprojective Cartesian coordinates.\n\n Returns\n -------\n `~bool`\n Returns `True` If at least one coordinate of the map is on disk and at\n least one coordinate of the map is off disk.\n\n Notes\n -----\n For coronagraph images such as those from LASCO C2 and C3 the full disk is\n within the field of view of the instrument, but the solar disk itself is not imaged.\n For such images this function will return `True`.\n \"\"\"\n on_disk = coordinate_is_on_solar_disk(all_coordinates_from_map(smap))\n return np.logical_and(np.any(on_disk), np.any(~on_disk))\n\n\ndef on_disk_bounding_coordinates(smap):\n \"\"\"\n Returns the the bottom left and top right coordinates of the smallest\n rectangular region that contains all the on disk coordinates of the input map.\n\n Parameters\n ----------\n smap : `~sunpy.map.GenericMap`\n A map in helioprojective Cartesian coordinates.\n\n Returns\n -------\n `~astropy.coordinates.SkyCoord`\n A `~astropy.coordinates.SkyCoord` of length 2 such that the\n first entry is the bottom left coordinate and the second entry is the\n top right coordinate of the smallest rectangular region that contains\n all the on-disk pixels in the input map.\n \"\"\"\n # Check that the input map is not all off disk.\n if is_all_off_disk(smap):\n raise ValueError(\"The entire map is off disk.\")\n\n # Get all the coordinates from the input map\n coordinates = all_coordinates_from_map(smap)\n\n # Find which coordinates are on the disk\n on_disk = coordinate_is_on_solar_disk(coordinates)\n on_disk_coordinates = coordinates[on_disk]\n\n # The bottom left and top right coordinates that contain\n # the on disk coordinates.\n tx = on_disk_coordinates.Tx.value\n ty = on_disk_coordinates.Ty.value\n return SkyCoord([np.nanmin(tx), np.nanmax(tx)] * u.arcsec,\n [np.nanmin(ty), np.nanmax(ty)] * u.arcsec,\n frame=Helioprojective, observer=smap.observer_coordinate)\n", "path": "sunpy/map/maputils.py"}]} | 3,935 | 410 |
gh_patches_debug_9547 | rasdani/github-patches | git_diff | opensearch-project__opensearch-build-537 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
[BUG] BWC test suite does not run on Jenkins
**Describe the bug**
BWC test job fails to run Jenkins due to misconfigured directory to kick off tests.
```
Running ./bundle-workflow/src/run_bwc_test.py --s3-bucket <artifact_s3_bucket> --opensearch-version 1.1.0 --build-id 163 --architecture x64 --test-run-id 6 ...
2021-09-17 21:50:08 INFO Switching to temporary work_dir: /tmp/tmp70l5b7_e
Traceback (most recent call last):
File "/var/jenkins/workspace/bwc-test/bundle-workflow/src/run_bwc_test.py", line 31, in <module>
sys.exit(main())
File "/var/jenkins/workspace/bwc-test/bundle-workflow/src/run_bwc_test.py", line 26, in main
args.s3_bucket, args.build_id, args.opensearch_version, args.architecture, cur_dir)
File "/var/jenkins/workspace/bwc-test/bundle-workflow/src/manifests/bundle_manifest.py", line 85, in from_s3
S3Bucket(bucket_name).download_file(manifest_s3_path, work_dir)
File "/var/jenkins/workspace/bwc-test/bundle-workflow/src/aws/s3_bucket.py", line 99, in download_file
local_dir = Path(dest)
File "/usr/lib64/python3.7/pathlib.py", line 1027, in __new__
self = cls._from_parts(args, init=False)
File "/usr/lib64/python3.7/pathlib.py", line 674, in _from_parts
drv, root, parts = self._parse_args(args)
File "/usr/lib64/python3.7/pathlib.py", line 658, in _parse_args
a = os.fspath(a)
TypeError: expected str, bytes or os.PathLike object, not NoneType
```
**To Reproduce**
Run `/bundle-workflow/src/test.sh bwc-test --s3-bucket <artifact_s3_bucket> --opensearch-version 1.1.0 --build-id 163 --architecture x64 --test-run-id 6`
</issue>
<code>
[start of bundle-workflow/src/manifests/bundle_manifest.py]
1 # SPDX-License-Identifier: Apache-2.0
2 #
3 # The OpenSearch Contributors require contributions made to
4 # this file be licensed under the Apache-2.0 license or a
5 # compatible open source license.
6
7 import os
8
9 from aws.s3_bucket import S3Bucket
10 from manifests.manifest import Manifest
11
12
13 class BundleManifest(Manifest):
14 """
15 A BundleManifest is an immutable view of the outputs from a assemble step
16 The manifest contains information about the bundle that was built (in the `assemble` section),
17 and the components that made up the bundle in the `components` section.
18
19 The format for schema version 1.0 is:
20 schema-version: "1.0"
21 build:
22 name: string
23 version: string
24 architecture: x64 or arm64
25 location: /relative/path/to/tarball
26 components:
27 - name: string
28 repository: URL of git repository
29 ref: git ref that was built (sha, branch, or tag)
30 commit_id: The actual git commit ID that was built (i.e. the resolved "ref")
31 location: /relative/path/to/artifact
32 """
33
34 SCHEMA = {
35 "build": {
36 "required": True,
37 "type": "dict",
38 "schema": {
39 "architecture": {"required": True, "type": "string"},
40 "id": {"required": True, "type": "string"},
41 "location": {"required": True, "type": "string"},
42 "name": {"required": True, "type": "string"},
43 "version": {"required": True, "type": "string"},
44 },
45 },
46 "schema-version": {"required": True, "type": "string", "allowed": ["1.0"]},
47 "components": {
48 "required": True,
49 "type": "list",
50 "schema": {
51 "type": "dict",
52 "schema": {
53 "commit_id": {"required": True, "type": "string"},
54 "location": {"required": True, "type": "string"},
55 "name": {"required": True, "type": "string"},
56 "ref": {"required": True, "type": "string"},
57 "repository": {"required": True, "type": "string"},
58 },
59 },
60 },
61 }
62
63 def __init__(self, data):
64 super().__init__(data)
65 self.build = self.Build(data["build"])
66 self.components = list(
67 map(lambda entry: self.Component(entry), data["components"])
68 )
69
70 def __to_dict__(self):
71 return {
72 "schema-version": "1.0",
73 "build": self.build.__to_dict__(),
74 "components": list(
75 map(lambda component: component.__to_dict__(), self.components)
76 ),
77 }
78
79 @staticmethod
80 def from_s3(bucket_name, build_id, opensearch_version, architecture, work_dir=None):
81 work_dir = work_dir if not None else str(os.getcwd())
82 manifest_s3_path = BundleManifest.get_bundle_manifest_relative_location(
83 build_id, opensearch_version, architecture
84 )
85 S3Bucket(bucket_name).download_file(manifest_s3_path, work_dir)
86 with open("manifest.yml", "r") as file:
87 bundle_manifest = BundleManifest.from_file(file)
88 os.remove(os.path.realpath(os.path.join(work_dir, "manifest.yml")))
89 return bundle_manifest
90
91 @staticmethod
92 def get_tarball_relative_location(build_id, opensearch_version, architecture):
93 return f"bundles/{opensearch_version}/{build_id}/{architecture}/opensearch-{opensearch_version}-linux-{architecture}.tar.gz"
94
95 @staticmethod
96 def get_tarball_name(opensearch_version, architecture):
97 return f"opensearch-{opensearch_version}-linux-{architecture}.tar.gz"
98
99 @staticmethod
100 def get_bundle_manifest_relative_location(
101 build_id, opensearch_version, architecture
102 ):
103 return f"bundles/{opensearch_version}/{build_id}/{architecture}/manifest.yml"
104
105 class Build:
106 def __init__(self, data):
107 self.name = data["name"]
108 self.version = data["version"]
109 self.architecture = data["architecture"]
110 self.location = data["location"]
111 self.id = data["id"]
112
113 def __to_dict__(self):
114 return {
115 "name": self.name,
116 "version": self.version,
117 "architecture": self.architecture,
118 "location": self.location,
119 "id": self.id,
120 }
121
122 class Component:
123 def __init__(self, data):
124 self.name = data["name"]
125 self.repository = data["repository"]
126 self.ref = data["ref"]
127 self.commit_id = data["commit_id"]
128 self.location = data["location"]
129
130 def __to_dict__(self):
131 return {
132 "name": self.name,
133 "repository": self.repository,
134 "ref": self.ref,
135 "commit_id": self.commit_id,
136 "location": self.location,
137 }
138
[end of bundle-workflow/src/manifests/bundle_manifest.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/bundle-workflow/src/manifests/bundle_manifest.py b/bundle-workflow/src/manifests/bundle_manifest.py
--- a/bundle-workflow/src/manifests/bundle_manifest.py
+++ b/bundle-workflow/src/manifests/bundle_manifest.py
@@ -83,8 +83,7 @@
build_id, opensearch_version, architecture
)
S3Bucket(bucket_name).download_file(manifest_s3_path, work_dir)
- with open("manifest.yml", "r") as file:
- bundle_manifest = BundleManifest.from_file(file)
+ bundle_manifest = BundleManifest.from_path(os.path.join(work_dir, 'manifest.yml'))
os.remove(os.path.realpath(os.path.join(work_dir, "manifest.yml")))
return bundle_manifest
| {"golden_diff": "diff --git a/bundle-workflow/src/manifests/bundle_manifest.py b/bundle-workflow/src/manifests/bundle_manifest.py\n--- a/bundle-workflow/src/manifests/bundle_manifest.py\n+++ b/bundle-workflow/src/manifests/bundle_manifest.py\n@@ -83,8 +83,7 @@\n build_id, opensearch_version, architecture\n )\n S3Bucket(bucket_name).download_file(manifest_s3_path, work_dir)\n- with open(\"manifest.yml\", \"r\") as file:\n- bundle_manifest = BundleManifest.from_file(file)\n+ bundle_manifest = BundleManifest.from_path(os.path.join(work_dir, 'manifest.yml'))\n os.remove(os.path.realpath(os.path.join(work_dir, \"manifest.yml\")))\n return bundle_manifest\n", "issue": "[BUG] BWC test suite does not run on Jenkins\n**Describe the bug**\r\nBWC test job fails to run Jenkins due to misconfigured directory to kick off tests. \r\n\r\n```\r\nRunning ./bundle-workflow/src/run_bwc_test.py --s3-bucket <artifact_s3_bucket> --opensearch-version 1.1.0 --build-id 163 --architecture x64 --test-run-id 6 ...\r\n2021-09-17 21:50:08 INFO Switching to temporary work_dir: /tmp/tmp70l5b7_e\r\nTraceback (most recent call last):\r\n File \"/var/jenkins/workspace/bwc-test/bundle-workflow/src/run_bwc_test.py\", line 31, in <module>\r\n sys.exit(main())\r\n File \"/var/jenkins/workspace/bwc-test/bundle-workflow/src/run_bwc_test.py\", line 26, in main\r\n args.s3_bucket, args.build_id, args.opensearch_version, args.architecture, cur_dir)\r\n File \"/var/jenkins/workspace/bwc-test/bundle-workflow/src/manifests/bundle_manifest.py\", line 85, in from_s3\r\n S3Bucket(bucket_name).download_file(manifest_s3_path, work_dir)\r\n File \"/var/jenkins/workspace/bwc-test/bundle-workflow/src/aws/s3_bucket.py\", line 99, in download_file\r\n local_dir = Path(dest)\r\n File \"/usr/lib64/python3.7/pathlib.py\", line 1027, in __new__\r\n self = cls._from_parts(args, init=False)\r\n File \"/usr/lib64/python3.7/pathlib.py\", line 674, in _from_parts\r\n drv, root, parts = self._parse_args(args)\r\n File \"/usr/lib64/python3.7/pathlib.py\", line 658, in _parse_args\r\n a = os.fspath(a)\r\nTypeError: expected str, bytes or os.PathLike object, not NoneType\r\n```\r\n\r\n**To Reproduce**\r\nRun `/bundle-workflow/src/test.sh bwc-test --s3-bucket <artifact_s3_bucket> --opensearch-version 1.1.0 --build-id 163 --architecture x64 --test-run-id 6`\r\n\n", "before_files": [{"content": "# SPDX-License-Identifier: Apache-2.0\n#\n# The OpenSearch Contributors require contributions made to\n# this file be licensed under the Apache-2.0 license or a\n# compatible open source license.\n\nimport os\n\nfrom aws.s3_bucket import S3Bucket\nfrom manifests.manifest import Manifest\n\n\nclass BundleManifest(Manifest):\n \"\"\"\n A BundleManifest is an immutable view of the outputs from a assemble step\n The manifest contains information about the bundle that was built (in the `assemble` section),\n and the components that made up the bundle in the `components` section.\n\n The format for schema version 1.0 is:\n schema-version: \"1.0\"\n build:\n name: string\n version: string\n architecture: x64 or arm64\n location: /relative/path/to/tarball\n components:\n - name: string\n repository: URL of git repository\n ref: git ref that was built (sha, branch, or tag)\n commit_id: The actual git commit ID that was built (i.e. the resolved \"ref\")\n location: /relative/path/to/artifact\n \"\"\"\n\n SCHEMA = {\n \"build\": {\n \"required\": True,\n \"type\": \"dict\",\n \"schema\": {\n \"architecture\": {\"required\": True, \"type\": \"string\"},\n \"id\": {\"required\": True, \"type\": \"string\"},\n \"location\": {\"required\": True, \"type\": \"string\"},\n \"name\": {\"required\": True, \"type\": \"string\"},\n \"version\": {\"required\": True, \"type\": \"string\"},\n },\n },\n \"schema-version\": {\"required\": True, \"type\": \"string\", \"allowed\": [\"1.0\"]},\n \"components\": {\n \"required\": True,\n \"type\": \"list\",\n \"schema\": {\n \"type\": \"dict\",\n \"schema\": {\n \"commit_id\": {\"required\": True, \"type\": \"string\"},\n \"location\": {\"required\": True, \"type\": \"string\"},\n \"name\": {\"required\": True, \"type\": \"string\"},\n \"ref\": {\"required\": True, \"type\": \"string\"},\n \"repository\": {\"required\": True, \"type\": \"string\"},\n },\n },\n },\n }\n\n def __init__(self, data):\n super().__init__(data)\n self.build = self.Build(data[\"build\"])\n self.components = list(\n map(lambda entry: self.Component(entry), data[\"components\"])\n )\n\n def __to_dict__(self):\n return {\n \"schema-version\": \"1.0\",\n \"build\": self.build.__to_dict__(),\n \"components\": list(\n map(lambda component: component.__to_dict__(), self.components)\n ),\n }\n\n @staticmethod\n def from_s3(bucket_name, build_id, opensearch_version, architecture, work_dir=None):\n work_dir = work_dir if not None else str(os.getcwd())\n manifest_s3_path = BundleManifest.get_bundle_manifest_relative_location(\n build_id, opensearch_version, architecture\n )\n S3Bucket(bucket_name).download_file(manifest_s3_path, work_dir)\n with open(\"manifest.yml\", \"r\") as file:\n bundle_manifest = BundleManifest.from_file(file)\n os.remove(os.path.realpath(os.path.join(work_dir, \"manifest.yml\")))\n return bundle_manifest\n\n @staticmethod\n def get_tarball_relative_location(build_id, opensearch_version, architecture):\n return f\"bundles/{opensearch_version}/{build_id}/{architecture}/opensearch-{opensearch_version}-linux-{architecture}.tar.gz\"\n\n @staticmethod\n def get_tarball_name(opensearch_version, architecture):\n return f\"opensearch-{opensearch_version}-linux-{architecture}.tar.gz\"\n\n @staticmethod\n def get_bundle_manifest_relative_location(\n build_id, opensearch_version, architecture\n ):\n return f\"bundles/{opensearch_version}/{build_id}/{architecture}/manifest.yml\"\n\n class Build:\n def __init__(self, data):\n self.name = data[\"name\"]\n self.version = data[\"version\"]\n self.architecture = data[\"architecture\"]\n self.location = data[\"location\"]\n self.id = data[\"id\"]\n\n def __to_dict__(self):\n return {\n \"name\": self.name,\n \"version\": self.version,\n \"architecture\": self.architecture,\n \"location\": self.location,\n \"id\": self.id,\n }\n\n class Component:\n def __init__(self, data):\n self.name = data[\"name\"]\n self.repository = data[\"repository\"]\n self.ref = data[\"ref\"]\n self.commit_id = data[\"commit_id\"]\n self.location = data[\"location\"]\n\n def __to_dict__(self):\n return {\n \"name\": self.name,\n \"repository\": self.repository,\n \"ref\": self.ref,\n \"commit_id\": self.commit_id,\n \"location\": self.location,\n }\n", "path": "bundle-workflow/src/manifests/bundle_manifest.py"}]} | 2,440 | 168 |
gh_patches_debug_23260 | rasdani/github-patches | git_diff | beeware__toga-1637 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
False positive "Multiple candidiate toga backends"
**Describe the bug**
When using a development version of *toga*, a `RuntimeError` of multiple candidate toga backends is raised with the same backend. Stacktrace example:
```
Traceback (most recent call last):
File "C:\Users\sagi\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\sagi\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "C:\Users\sagi\PycharmProjects\toga\examples\canvas\canvas\__main__.py", line 4, in <module>
main().main_loop()
File "C:\Users\sagi\PycharmProjects\toga\examples\canvas\canvas\app.py", line 565, in main
return ExampleCanvasApp('Canvas', 'org.beeware.widgets.canvas')
File "C:\Users\sagi\PycharmProjects\toga\src\core\src\toga\app.py", line 308, in __init__
self.factory = get_platform_factory()
File "C:\Users\sagi\PycharmProjects\toga\src\core\src\toga\platform.py", line 106, in get_platform_factory
raise RuntimeError(
RuntimeError: Multiple candidiate toga backends found: ('toga_winforms' (windows), 'toga_winforms' (windows)). Uninstall the backends you don't require, or use TOGA_BACKEND to specify a backend.
```
**To Reproduce**
Steps to reproduce the behavior:
1. Open a new virtual environment
2. Go to src\core
3. Run `pip install -e .`
4. Go to src\winforms
5. Run `pip install -e .`
6. Go to example\canvas (or any other example application)
7. Run `python -m canvas`
**Expected behavior**
`RuntimeError` should not be raised in that case.
**Environment:**
- Operating System: Windows
- Python version: 3.10.6
- Software versions:
- Briefcase: latest
- Toga: latest
</issue>
<code>
[start of src/core/src/toga/platform.py]
1 import importlib
2 import os
3 import sys
4 import warnings
5 from functools import lru_cache
6
7 try:
8 # Usually, the pattern is "import module; if it doesn't exist,
9 # import the shim". However, we need the 3.10 API for entry_points,
10 # as the 3.8 didn't support the `groups` argument to entry_points.
11 # Therefore, we try to import the compatibility shim first; and fall
12 # back to the stdlib module if the shim isn't there.
13 from importlib_metadata import entry_points
14 except ImportError:
15 from importlib.metadata import entry_points
16
17
18 # Map python sys.platform with toga platforms names
19 _TOGA_PLATFORMS = {
20 'android': 'android',
21 'darwin': 'macOS',
22 'ios': 'iOS',
23 'linux': 'linux',
24 'tvos': 'tvOS',
25 'watchos': 'watchOS',
26 'wearos': 'wearOS',
27 'emscripten': 'web',
28 'win32': 'windows',
29 }
30
31
32 try:
33 current_platform = os.environ['TOGA_PLATFORM']
34 except KeyError:
35 # Rely on `sys.getandroidapilevel`, which only exists on Android; see
36 # https://github.com/beeware/Python-Android-support/issues/8
37 if hasattr(sys, 'getandroidapilevel'):
38 current_platform = 'android'
39 else:
40 current_platform = _TOGA_PLATFORMS.get(sys.platform)
41
42
43 @lru_cache(maxsize=1)
44 def get_platform_factory(factory=None):
45 """ This function figures out what the current host platform is and
46 imports the adequate factory. The factory is the interface to all platform
47 specific implementations.
48
49 If the TOGA_BACKEND environment variable is set, the factory will be loaded
50 from that module.
51
52 Returns: The suitable factory for the current host platform.
53
54 Raises:
55 RuntimeError: If no supported host platform can be identified.
56 """
57
58 ######################################################################
59 # 2022-09: Backwards compatibility
60 ######################################################################
61 # factory no longer used
62 if factory:
63 warnings.warn("The factory argument is no longer used.", DeprecationWarning)
64 ######################################################################
65 # End backwards compatibility.
66 ######################################################################
67
68 toga_backends = entry_points(group='toga.backends')
69 if not toga_backends:
70 raise RuntimeError("No toga backend could be loaded.")
71
72 backend_value = os.environ.get('TOGA_BACKEND')
73 if backend_value:
74 try:
75 factory = importlib.import_module(f'{backend_value}.factory')
76 except ModuleNotFoundError:
77 toga_backends_values = ', '.join([f'{backend.value!r}' for backend in toga_backends])
78 raise RuntimeError(
79 f"The backend specified by TOGA_BACKEND ({backend_value!r}) "
80 f"could not be loaded. It should be one of: {toga_backends_values}."
81 )
82 else:
83 if len(toga_backends) == 1:
84 backend = list(toga_backends)[0]
85 else:
86 # multiple backends are installed: choose the one that matches the host platform
87 matching_backends = [
88 backend
89 for backend in toga_backends
90 if backend.name == current_platform
91 ]
92 if len(matching_backends) == 0:
93 toga_backends_string = ', '.join([
94 f'{backend.value!r} ({backend.name})'
95 for backend in toga_backends
96 ])
97 raise RuntimeError(
98 f"Multiple Toga backends are installed ({toga_backends_string}), "
99 f"but none of them match your current platform ({current_platform!r})."
100 )
101 if len(matching_backends) > 1:
102 toga_backends_string = ', '.join([
103 f'{backend.value!r} ({backend.name})'
104 for backend in matching_backends
105 ])
106 raise RuntimeError(
107 f"Multiple candidiate toga backends found: ({toga_backends_string}). "
108 "Uninstall the backends you don't require, or use "
109 "TOGA_BACKEND to specify a backend."
110 )
111 backend = matching_backends[0]
112 factory = importlib.import_module(f'{backend.value}.factory')
113 return factory
114
[end of src/core/src/toga/platform.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/core/src/toga/platform.py b/src/core/src/toga/platform.py
--- a/src/core/src/toga/platform.py
+++ b/src/core/src/toga/platform.py
@@ -67,7 +67,7 @@
toga_backends = entry_points(group='toga.backends')
if not toga_backends:
- raise RuntimeError("No toga backend could be loaded.")
+ raise RuntimeError("No Toga backend could be loaded.")
backend_value = os.environ.get('TOGA_BACKEND')
if backend_value:
@@ -80,8 +80,14 @@
f"could not be loaded. It should be one of: {toga_backends_values}."
)
else:
+ # As of Setuptools 65.5, entry points are returned duplicated if the
+ # package is installed editable. Use a set to ensure that each entry point
+ # is only returned once.
+ # See https://github.com/pypa/setuptools/issues/3649
+ toga_backends = sorted(set(toga_backends))
+
if len(toga_backends) == 1:
- backend = list(toga_backends)[0]
+ backend = toga_backends[0]
else:
# multiple backends are installed: choose the one that matches the host platform
matching_backends = [
| {"golden_diff": "diff --git a/src/core/src/toga/platform.py b/src/core/src/toga/platform.py\n--- a/src/core/src/toga/platform.py\n+++ b/src/core/src/toga/platform.py\n@@ -67,7 +67,7 @@\n \n toga_backends = entry_points(group='toga.backends')\n if not toga_backends:\n- raise RuntimeError(\"No toga backend could be loaded.\")\n+ raise RuntimeError(\"No Toga backend could be loaded.\")\n \n backend_value = os.environ.get('TOGA_BACKEND')\n if backend_value:\n@@ -80,8 +80,14 @@\n f\"could not be loaded. It should be one of: {toga_backends_values}.\"\n )\n else:\n+ # As of Setuptools 65.5, entry points are returned duplicated if the\n+ # package is installed editable. Use a set to ensure that each entry point\n+ # is only returned once.\n+ # See https://github.com/pypa/setuptools/issues/3649\n+ toga_backends = sorted(set(toga_backends))\n+\n if len(toga_backends) == 1:\n- backend = list(toga_backends)[0]\n+ backend = toga_backends[0]\n else:\n # multiple backends are installed: choose the one that matches the host platform\n matching_backends = [\n", "issue": "False positive \"Multiple candidiate toga backends\"\n**Describe the bug**\r\nWhen using a development version of *toga*, a `RuntimeError` of multiple candidate toga backends is raised with the same backend. Stacktrace example:\r\n\r\n```\r\nTraceback (most recent call last):\r\n File \"C:\\Users\\sagi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\runpy.py\", line 196, in _run_module_as_main\r\n return _run_code(code, main_globals, None,\r\n File \"C:\\Users\\sagi\\AppData\\Local\\Programs\\Python\\Python310\\lib\\runpy.py\", line 86, in _run_code\r\n exec(code, run_globals)\r\n File \"C:\\Users\\sagi\\PycharmProjects\\toga\\examples\\canvas\\canvas\\__main__.py\", line 4, in <module>\r\n main().main_loop()\r\n File \"C:\\Users\\sagi\\PycharmProjects\\toga\\examples\\canvas\\canvas\\app.py\", line 565, in main\r\n return ExampleCanvasApp('Canvas', 'org.beeware.widgets.canvas')\r\n File \"C:\\Users\\sagi\\PycharmProjects\\toga\\src\\core\\src\\toga\\app.py\", line 308, in __init__\r\n self.factory = get_platform_factory()\r\n File \"C:\\Users\\sagi\\PycharmProjects\\toga\\src\\core\\src\\toga\\platform.py\", line 106, in get_platform_factory\r\n raise RuntimeError(\r\nRuntimeError: Multiple candidiate toga backends found: ('toga_winforms' (windows), 'toga_winforms' (windows)). Uninstall the backends you don't require, or use TOGA_BACKEND to specify a backend.\r\n```\r\n\r\n**To Reproduce**\r\nSteps to reproduce the behavior:\r\n1. Open a new virtual environment\r\n2. Go to src\\core\r\n3. Run `pip install -e .`\r\n4. Go to src\\winforms\r\n5. Run `pip install -e .`\r\n6. Go to example\\canvas (or any other example application)\r\n7. Run `python -m canvas`\r\n\r\n**Expected behavior**\r\n`RuntimeError` should not be raised in that case.\r\n\r\n**Environment:**\r\n - Operating System: Windows\r\n - Python version: 3.10.6\r\n - Software versions:\r\n - Briefcase: latest\r\n - Toga: latest\r\n\n", "before_files": [{"content": "import importlib\nimport os\nimport sys\nimport warnings\nfrom functools import lru_cache\n\ntry:\n # Usually, the pattern is \"import module; if it doesn't exist,\n # import the shim\". However, we need the 3.10 API for entry_points,\n # as the 3.8 didn't support the `groups` argument to entry_points.\n # Therefore, we try to import the compatibility shim first; and fall\n # back to the stdlib module if the shim isn't there.\n from importlib_metadata import entry_points\nexcept ImportError:\n from importlib.metadata import entry_points\n\n\n# Map python sys.platform with toga platforms names\n_TOGA_PLATFORMS = {\n 'android': 'android',\n 'darwin': 'macOS',\n 'ios': 'iOS',\n 'linux': 'linux',\n 'tvos': 'tvOS',\n 'watchos': 'watchOS',\n 'wearos': 'wearOS',\n 'emscripten': 'web',\n 'win32': 'windows',\n}\n\n\ntry:\n current_platform = os.environ['TOGA_PLATFORM']\nexcept KeyError:\n # Rely on `sys.getandroidapilevel`, which only exists on Android; see\n # https://github.com/beeware/Python-Android-support/issues/8\n if hasattr(sys, 'getandroidapilevel'):\n current_platform = 'android'\n else:\n current_platform = _TOGA_PLATFORMS.get(sys.platform)\n\n\n@lru_cache(maxsize=1)\ndef get_platform_factory(factory=None):\n \"\"\" This function figures out what the current host platform is and\n imports the adequate factory. The factory is the interface to all platform\n specific implementations.\n\n If the TOGA_BACKEND environment variable is set, the factory will be loaded\n from that module.\n\n Returns: The suitable factory for the current host platform.\n\n Raises:\n RuntimeError: If no supported host platform can be identified.\n \"\"\"\n\n ######################################################################\n # 2022-09: Backwards compatibility\n ######################################################################\n # factory no longer used\n if factory:\n warnings.warn(\"The factory argument is no longer used.\", DeprecationWarning)\n ######################################################################\n # End backwards compatibility.\n ######################################################################\n\n toga_backends = entry_points(group='toga.backends')\n if not toga_backends:\n raise RuntimeError(\"No toga backend could be loaded.\")\n\n backend_value = os.environ.get('TOGA_BACKEND')\n if backend_value:\n try:\n factory = importlib.import_module(f'{backend_value}.factory')\n except ModuleNotFoundError:\n toga_backends_values = ', '.join([f'{backend.value!r}' for backend in toga_backends])\n raise RuntimeError(\n f\"The backend specified by TOGA_BACKEND ({backend_value!r}) \"\n f\"could not be loaded. It should be one of: {toga_backends_values}.\"\n )\n else:\n if len(toga_backends) == 1:\n backend = list(toga_backends)[0]\n else:\n # multiple backends are installed: choose the one that matches the host platform\n matching_backends = [\n backend\n for backend in toga_backends\n if backend.name == current_platform\n ]\n if len(matching_backends) == 0:\n toga_backends_string = ', '.join([\n f'{backend.value!r} ({backend.name})'\n for backend in toga_backends\n ])\n raise RuntimeError(\n f\"Multiple Toga backends are installed ({toga_backends_string}), \"\n f\"but none of them match your current platform ({current_platform!r}).\"\n )\n if len(matching_backends) > 1:\n toga_backends_string = ', '.join([\n f'{backend.value!r} ({backend.name})'\n for backend in matching_backends\n ])\n raise RuntimeError(\n f\"Multiple candidiate toga backends found: ({toga_backends_string}). \"\n \"Uninstall the backends you don't require, or use \"\n \"TOGA_BACKEND to specify a backend.\"\n )\n backend = matching_backends[0]\n factory = importlib.import_module(f'{backend.value}.factory')\n return factory\n", "path": "src/core/src/toga/platform.py"}]} | 2,207 | 302 |
gh_patches_debug_9053 | rasdani/github-patches | git_diff | encode__httpx-234 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Bug in the 0.7.0 packaging
I've tried to upgrade to 0.7.0 and it exploded with a
```
$ poetry update
Updating dependencies
Resolving dependencies... (1.0s)
Package operations: 0 installs, 1 update, 0 removals
- Updating httpx (0.6.8 -> 0.7.0)
[EnvCommandError]
Command ['/Users/pablo/Library/Caches/pypoetry/virtualenvs/drop-eventsng-1aNj3rOl-py3.7/bin/python', '-m', 'pip', 'install', '--no-deps', '-U', 'httpx==0.7.0'] errored with the following return code 1, and output:
Collecting httpx==0.7.0
Using cached https://files.pythonhosted.org/packages/12/b3/fdd6e528a3385e2149ad42cc4e9b54e326d532e3e79a86e7cfdaea45723e/httpx-0.7.0.tar.gz
ERROR: Command errored out with exit status 1:
command: /Users/pablo/Library/Caches/pypoetry/virtualenvs/drop-eventsng-1aNj3rOl-py3.7/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py'"'"'; __file__='"'"'/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base pip-egg-info
cwd: /private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/
Complete output (7 lines):
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py", line 45, in <module>
long_description=get_long_description(),
File "/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py", line 26, in get_long_description
with open("CHANGELOG.md", encoding="utf8") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'CHANGELOG.md'
----------------------------------------
ERROR: Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output.
```
</issue>
<code>
[start of setup.py]
1 #!/usr/bin/env python
2 # -*- coding: utf-8 -*-
3
4 import re
5 from pathlib import Path
6
7 from setuptools import setup
8
9
10 def get_version(package):
11 """
12 Return package version as listed in `__version__` in `init.py`.
13 """
14 version = Path(package, "__version__.py").read_text()
15 return re.search("__version__ = ['\"]([^'\"]+)['\"]", version).group(1)
16
17
18 def get_long_description():
19 """
20 Return the README.
21 """
22 long_description = ""
23 with open("README.md", encoding="utf8") as f:
24 long_description += f.read()
25 long_description += "\n\n"
26 with open("CHANGELOG.md", encoding="utf8") as f:
27 long_description += f.read()
28 return long_description
29
30
31 def get_packages(package):
32 """
33 Return root package and all sub-packages.
34 """
35 return [str(path.parent) for path in Path(package).glob("**/__init__.py")]
36
37
38 setup(
39 name="httpx",
40 python_requires=">=3.6",
41 version=get_version("httpx"),
42 url="https://github.com/encode/httpx",
43 license="BSD",
44 description="The next generation HTTP client.",
45 long_description=get_long_description(),
46 long_description_content_type="text/markdown",
47 author="Tom Christie",
48 author_email="[email protected]",
49 package_data={"httpx": ["py.typed"]},
50 packages=get_packages("httpx"),
51 install_requires=[
52 "certifi",
53 "chardet==3.*",
54 "h11==0.8.*",
55 "h2==3.*",
56 "hstspreload",
57 "idna==2.*",
58 "rfc3986==1.*",
59 ],
60 classifiers=[
61 "Development Status :: 3 - Alpha",
62 "Environment :: Web Environment",
63 "Intended Audience :: Developers",
64 "License :: OSI Approved :: BSD License",
65 "Operating System :: OS Independent",
66 "Topic :: Internet :: WWW/HTTP",
67 "Programming Language :: Python :: 3",
68 "Programming Language :: Python :: 3.6",
69 "Programming Language :: Python :: 3.7",
70 "Programming Language :: Python :: 3.8",
71 ],
72 )
73
[end of setup.py]
[start of httpx/__version__.py]
1 __title__ = "httpx"
2 __description__ = "A next generation HTTP client, for Python 3."
3 __version__ = "0.7.0"
4
[end of httpx/__version__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/httpx/__version__.py b/httpx/__version__.py
--- a/httpx/__version__.py
+++ b/httpx/__version__.py
@@ -1,3 +1,3 @@
__title__ = "httpx"
__description__ = "A next generation HTTP client, for Python 3."
-__version__ = "0.7.0"
+__version__ = "0.7.1"
diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -48,6 +48,7 @@
author_email="[email protected]",
package_data={"httpx": ["py.typed"]},
packages=get_packages("httpx"),
+ include_package_data=True,
install_requires=[
"certifi",
"chardet==3.*",
| {"golden_diff": "diff --git a/httpx/__version__.py b/httpx/__version__.py\n--- a/httpx/__version__.py\n+++ b/httpx/__version__.py\n@@ -1,3 +1,3 @@\n __title__ = \"httpx\"\n __description__ = \"A next generation HTTP client, for Python 3.\"\n-__version__ = \"0.7.0\"\n+__version__ = \"0.7.1\"\ndiff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -48,6 +48,7 @@\n author_email=\"[email protected]\",\n package_data={\"httpx\": [\"py.typed\"]},\n packages=get_packages(\"httpx\"),\n+ include_package_data=True,\n install_requires=[\n \"certifi\",\n \"chardet==3.*\",\n", "issue": "Bug in the 0.7.0 packaging\nI've tried to upgrade to 0.7.0 and it exploded with a\r\n\r\n```\r\n$ poetry update\r\nUpdating dependencies\r\nResolving dependencies... (1.0s)\r\n\r\n\r\nPackage operations: 0 installs, 1 update, 0 removals\r\n\r\n - Updating httpx (0.6.8 -> 0.7.0)\r\n\r\n[EnvCommandError]\r\nCommand ['/Users/pablo/Library/Caches/pypoetry/virtualenvs/drop-eventsng-1aNj3rOl-py3.7/bin/python', '-m', 'pip', 'install', '--no-deps', '-U', 'httpx==0.7.0'] errored with the following return code 1, and output:\r\nCollecting httpx==0.7.0\r\n Using cached https://files.pythonhosted.org/packages/12/b3/fdd6e528a3385e2149ad42cc4e9b54e326d532e3e79a86e7cfdaea45723e/httpx-0.7.0.tar.gz\r\n ERROR: Command errored out with exit status 1:\r\n command: /Users/pablo/Library/Caches/pypoetry/virtualenvs/drop-eventsng-1aNj3rOl-py3.7/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '\"'\"'/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py'\"'\"'; __file__='\"'\"'/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py'\"'\"';f=getattr(tokenize, '\"'\"'open'\"'\"', open)(__file__);code=f.read().replace('\"'\"'\\r\\n'\"'\"', '\"'\"'\\n'\"'\"');f.close();exec(compile(code, __file__, '\"'\"'exec'\"'\"'))' egg_info --egg-base pip-egg-info\r\n cwd: /private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/\r\n Complete output (7 lines):\r\n Traceback (most recent call last):\r\n File \"<string>\", line 1, in <module>\r\n File \"/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py\", line 45, in <module>\r\n long_description=get_long_description(),\r\n File \"/private/var/folders/x4/txc7_0pn6zlfb30cs_0sh5mm0000gn/T/pip-install-jq6aut9d/httpx/setup.py\", line 26, in get_long_description\r\n with open(\"CHANGELOG.md\", encoding=\"utf8\") as f:\r\n FileNotFoundError: [Errno 2] No such file or directory: 'CHANGELOG.md'\r\n ----------------------------------------\r\nERROR: Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output.\r\n```\n", "before_files": [{"content": "#!/usr/bin/env python\n# -*- coding: utf-8 -*-\n\nimport re\nfrom pathlib import Path\n\nfrom setuptools import setup\n\n\ndef get_version(package):\n \"\"\"\n Return package version as listed in `__version__` in `init.py`.\n \"\"\"\n version = Path(package, \"__version__.py\").read_text()\n return re.search(\"__version__ = ['\\\"]([^'\\\"]+)['\\\"]\", version).group(1)\n\n\ndef get_long_description():\n \"\"\"\n Return the README.\n \"\"\"\n long_description = \"\"\n with open(\"README.md\", encoding=\"utf8\") as f:\n long_description += f.read()\n long_description += \"\\n\\n\"\n with open(\"CHANGELOG.md\", encoding=\"utf8\") as f:\n long_description += f.read()\n return long_description\n\n\ndef get_packages(package):\n \"\"\"\n Return root package and all sub-packages.\n \"\"\"\n return [str(path.parent) for path in Path(package).glob(\"**/__init__.py\")]\n\n\nsetup(\n name=\"httpx\",\n python_requires=\">=3.6\",\n version=get_version(\"httpx\"),\n url=\"https://github.com/encode/httpx\",\n license=\"BSD\",\n description=\"The next generation HTTP client.\",\n long_description=get_long_description(),\n long_description_content_type=\"text/markdown\",\n author=\"Tom Christie\",\n author_email=\"[email protected]\",\n package_data={\"httpx\": [\"py.typed\"]},\n packages=get_packages(\"httpx\"),\n install_requires=[\n \"certifi\",\n \"chardet==3.*\",\n \"h11==0.8.*\",\n \"h2==3.*\",\n \"hstspreload\",\n \"idna==2.*\",\n \"rfc3986==1.*\",\n ],\n classifiers=[\n \"Development Status :: 3 - Alpha\",\n \"Environment :: Web Environment\",\n \"Intended Audience :: Developers\",\n \"License :: OSI Approved :: BSD License\",\n \"Operating System :: OS Independent\",\n \"Topic :: Internet :: WWW/HTTP\",\n \"Programming Language :: Python :: 3\",\n \"Programming Language :: Python :: 3.6\",\n \"Programming Language :: Python :: 3.7\",\n \"Programming Language :: Python :: 3.8\",\n ],\n)\n", "path": "setup.py"}, {"content": "__title__ = \"httpx\"\n__description__ = \"A next generation HTTP client, for Python 3.\"\n__version__ = \"0.7.0\"\n", "path": "httpx/__version__.py"}]} | 1,963 | 183 |
gh_patches_debug_19085 | rasdani/github-patches | git_diff | liqd__a4-meinberlin-811 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Use <time> element for dates
This way screen readers (and other ATs) know that it should be read as a date.
</issue>
<code>
[start of meinberlin/apps/contrib/templatetags/contrib_tags.py]
1 from django import template
2 from django.template.loader import render_to_string
3
4 register = template.Library()
5
6
7 @register.assignment_tag
8 def include_template_string(template, **kwargs):
9 rendered_template = render_to_string(template, kwargs)
10 return str(rendered_template)
11
12
13 @register.assignment_tag
14 def combined_url_parameter(request_query_dict, **kwargs):
15 combined_query_dict = request_query_dict.copy()
16 for key in kwargs:
17 combined_query_dict.setlist(key, [kwargs[key]])
18 encoded_parameter = '?' + combined_query_dict.urlencode()
19 return encoded_parameter
20
21
22 @register.assignment_tag
23 def filter_has_perm(perm, user, objects):
24 """Filter a list of objects based on user permissions."""
25 if not hasattr(user, 'has_perm'):
26 # If the swapped user model does not support permissions, all objects
27 # will be returned. This is taken from rules.templatetags.has_perm.
28 return objects
29 else:
30 return [obj for obj in objects if user.has_perm(perm, obj)]
31
32
33 @register.filter
34 def percentage(value, max_value):
35 return round(value / max_value * 100)
36
37
38 @register.assignment_tag
39 def project_tile_image(project):
40 return project.tile_image or project.image or None
41
42
43 @register.assignment_tag
44 def project_tile_image_copyright(project):
45 if project.tile_image:
46 return project.tile_image_copyright
47 elif project.image:
48 return project.image_copyright
49 else:
50 return None
51
[end of meinberlin/apps/contrib/templatetags/contrib_tags.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/meinberlin/apps/contrib/templatetags/contrib_tags.py b/meinberlin/apps/contrib/templatetags/contrib_tags.py
--- a/meinberlin/apps/contrib/templatetags/contrib_tags.py
+++ b/meinberlin/apps/contrib/templatetags/contrib_tags.py
@@ -1,5 +1,8 @@
from django import template
+from django.forms.utils import flatatt
+from django.template import defaultfilters
from django.template.loader import render_to_string
+from django.utils.safestring import mark_safe
register = template.Library()
@@ -48,3 +51,18 @@
return project.image_copyright
else:
return None
+
+
[email protected]_tag()
+def html_date(value, displayfmt=None, datetimefmt='c', **kwargs):
+ """Format a date and wrap it in a html <time> element.
+
+ Additional html attributes may be provided as kwargs (e.g. 'class').
+ """
+ displaydate = defaultfilters.date(value, displayfmt)
+ datetime = defaultfilters.date(value, datetimefmt)
+ attribs = flatatt(kwargs)
+ result = '<time %s datetime="%s">%s</time>' % (attribs,
+ datetime,
+ displaydate)
+ return mark_safe(result)
| {"golden_diff": "diff --git a/meinberlin/apps/contrib/templatetags/contrib_tags.py b/meinberlin/apps/contrib/templatetags/contrib_tags.py\n--- a/meinberlin/apps/contrib/templatetags/contrib_tags.py\n+++ b/meinberlin/apps/contrib/templatetags/contrib_tags.py\n@@ -1,5 +1,8 @@\n from django import template\n+from django.forms.utils import flatatt\n+from django.template import defaultfilters\n from django.template.loader import render_to_string\n+from django.utils.safestring import mark_safe\n \n register = template.Library()\n \n@@ -48,3 +51,18 @@\n return project.image_copyright\n else:\n return None\n+\n+\[email protected]_tag()\n+def html_date(value, displayfmt=None, datetimefmt='c', **kwargs):\n+ \"\"\"Format a date and wrap it in a html <time> element.\n+\n+ Additional html attributes may be provided as kwargs (e.g. 'class').\n+ \"\"\"\n+ displaydate = defaultfilters.date(value, displayfmt)\n+ datetime = defaultfilters.date(value, datetimefmt)\n+ attribs = flatatt(kwargs)\n+ result = '<time %s datetime=\"%s\">%s</time>' % (attribs,\n+ datetime,\n+ displaydate)\n+ return mark_safe(result)\n", "issue": "Use <time> element for dates\nThis way screen readers (and other ATs) know that it should be read as a date.\n", "before_files": [{"content": "from django import template\nfrom django.template.loader import render_to_string\n\nregister = template.Library()\n\n\[email protected]_tag\ndef include_template_string(template, **kwargs):\n rendered_template = render_to_string(template, kwargs)\n return str(rendered_template)\n\n\[email protected]_tag\ndef combined_url_parameter(request_query_dict, **kwargs):\n combined_query_dict = request_query_dict.copy()\n for key in kwargs:\n combined_query_dict.setlist(key, [kwargs[key]])\n encoded_parameter = '?' + combined_query_dict.urlencode()\n return encoded_parameter\n\n\[email protected]_tag\ndef filter_has_perm(perm, user, objects):\n \"\"\"Filter a list of objects based on user permissions.\"\"\"\n if not hasattr(user, 'has_perm'):\n # If the swapped user model does not support permissions, all objects\n # will be returned. This is taken from rules.templatetags.has_perm.\n return objects\n else:\n return [obj for obj in objects if user.has_perm(perm, obj)]\n\n\[email protected]\ndef percentage(value, max_value):\n return round(value / max_value * 100)\n\n\[email protected]_tag\ndef project_tile_image(project):\n return project.tile_image or project.image or None\n\n\[email protected]_tag\ndef project_tile_image_copyright(project):\n if project.tile_image:\n return project.tile_image_copyright\n elif project.image:\n return project.image_copyright\n else:\n return None\n", "path": "meinberlin/apps/contrib/templatetags/contrib_tags.py"}]} | 989 | 296 |
gh_patches_debug_13218 | rasdani/github-patches | git_diff | getredash__redash-3298 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Pending invitation links broken in latest version
<!--
We use GitHub only for bug reports 🐛
Anything else should be posted to https://discuss.redash.io 👫
🚨For support, help & questions use https://discuss.redash.io/c/support
💡For feature requests & ideas use https://discuss.redash.io/c/feature-requests
**Found a security vulnerability?** Please email [email protected] to report any security vulnerabilities. We will acknowledge receipt of your vulnerability and strive to send you regular updates about our progress. If you're curious about the status of your disclosure please feel free to email us again. If you want to encrypt your disclosure email, you can use this PGP key.
-->
### Issue Summary
It looks like the change in #3261 doesn't handle the case of existing users that haven't accepted their invitations yet, so users trying to sign up using invitations created in a previous version incorrectly get the "This invitation has already been accepted" message. https://github.com/getredash/redash/pull/3229/files#diff-a0c5448134fdb627ae48d25bad76393fR40
I was able to fix this in our org with:
```sql
UPDATE users
SET details = '{"is_invitation_pending": true}'::json
WHERE password_hash IS NULL
```
Maybe this case should be handled in the migration here? https://github.com/getredash/redash/blob/master/migrations/versions/e7f8a917aa8e_add_user_details_json_column.py
### Steps to Reproduce
1. Send invitation from a version prior to #3229 and #3261
2. Upgrade to current master
3. Try to access the invitation link
Any other info e.g. Why do you consider this to be a bug? What did you expect to happen instead?
### Technical details:
* Redash Version:
* Browser/OS:
* How did you install Redash:
</issue>
<code>
[start of redash/handlers/authentication.py]
1 import logging
2
3 from flask import abort, flash, redirect, render_template, request, url_for
4
5 from flask_login import current_user, login_required, login_user, logout_user
6 from redash import __version__, limiter, models, settings
7 from redash.authentication import current_org, get_login_url, get_next_path
8 from redash.authentication.account import (BadSignature, SignatureExpired,
9 send_password_reset_email,
10 send_verify_email,
11 validate_token)
12 from redash.handlers import routes
13 from redash.handlers.base import json_response, org_scoped_rule
14 from redash.version_check import get_latest_version
15 from sqlalchemy.orm.exc import NoResultFound
16
17 logger = logging.getLogger(__name__)
18
19
20 def get_google_auth_url(next_path):
21 if settings.MULTI_ORG:
22 google_auth_url = url_for('google_oauth.authorize_org', next=next_path, org_slug=current_org.slug)
23 else:
24 google_auth_url = url_for('google_oauth.authorize', next=next_path)
25 return google_auth_url
26
27
28 def render_token_login_page(template, org_slug, token):
29 try:
30 user_id = validate_token(token)
31 org = current_org._get_current_object()
32 user = models.User.get_by_id_and_org(user_id, org)
33 except NoResultFound:
34 logger.exception("Bad user id in token. Token= , User id= %s, Org=%s", user_id, token, org_slug)
35 return render_template("error.html", error_message="Invalid invite link. Please ask for a new one."), 400
36 except (SignatureExpired, BadSignature):
37 logger.exception("Failed to verify invite token: %s, org=%s", token, org_slug)
38 return render_template("error.html",
39 error_message="Your invite link has expired. Please ask for a new one."), 400
40
41 if not user.is_invitation_pending:
42 return render_template("error.html",
43 error_message=("This invitation has already been accepted. "
44 "Please try resetting your password instead.")), 400
45
46 status_code = 200
47 if request.method == 'POST':
48 if 'password' not in request.form:
49 flash('Bad Request')
50 status_code = 400
51 elif not request.form['password']:
52 flash('Cannot use empty password.')
53 status_code = 400
54 elif len(request.form['password']) < 6:
55 flash('Password length is too short (<6).')
56 status_code = 400
57 else:
58 user.is_invitation_pending = False
59 user.hash_password(request.form['password'])
60 models.db.session.add(user)
61 login_user(user)
62 models.db.session.commit()
63 return redirect(url_for('redash.index', org_slug=org_slug))
64
65 google_auth_url = get_google_auth_url(url_for('redash.index', org_slug=org_slug))
66
67 return render_template(template,
68 show_google_openid=settings.GOOGLE_OAUTH_ENABLED,
69 google_auth_url=google_auth_url,
70 show_saml_login=current_org.get_setting('auth_saml_enabled'),
71 show_remote_user_login=settings.REMOTE_USER_LOGIN_ENABLED,
72 show_ldap_login=settings.LDAP_LOGIN_ENABLED,
73 org_slug=org_slug,
74 user=user), status_code
75
76
77 @routes.route(org_scoped_rule('/invite/<token>'), methods=['GET', 'POST'])
78 def invite(token, org_slug=None):
79 return render_token_login_page("invite.html", org_slug, token)
80
81
82 @routes.route(org_scoped_rule('/reset/<token>'), methods=['GET', 'POST'])
83 def reset(token, org_slug=None):
84 return render_token_login_page("reset.html", org_slug, token)
85
86
87 @routes.route(org_scoped_rule('/verify/<token>'), methods=['GET'])
88 def verify(token, org_slug=None):
89 try:
90 user_id = validate_token(token)
91 org = current_org._get_current_object()
92 user = models.User.get_by_id_and_org(user_id, org)
93 except (BadSignature, NoResultFound):
94 logger.exception("Failed to verify email verification token: %s, org=%s", token, org_slug)
95 return render_template("error.html",
96 error_message="Your verification link is invalid. Please ask for a new one."), 400
97
98 user.is_email_verified = True
99 models.db.session.add(user)
100 models.db.session.commit()
101
102 return render_template("verify.html", org_slug=org_slug)
103
104
105 @routes.route(org_scoped_rule('/forgot'), methods=['GET', 'POST'])
106 def forgot_password(org_slug=None):
107 if not current_org.get_setting('auth_password_login_enabled'):
108 abort(404)
109
110 submitted = False
111 if request.method == 'POST' and request.form['email']:
112 submitted = True
113 email = request.form['email']
114 try:
115 org = current_org._get_current_object()
116 user = models.User.get_by_email_and_org(email, org)
117 send_password_reset_email(user)
118 except NoResultFound:
119 logging.error("No user found for forgot password: %s", email)
120
121 return render_template("forgot.html", submitted=submitted)
122
123
124 @routes.route(org_scoped_rule('/verification_email'), methods=['POST'])
125 def verification_email(org_slug=None):
126 if not current_user.is_email_verified:
127 send_verify_email(current_user, current_org)
128
129 return json_response({
130 "message": "Please check your email inbox in order to verify your email address."
131 })
132
133
134 @routes.route(org_scoped_rule('/login'), methods=['GET', 'POST'])
135 @limiter.limit(settings.THROTTLE_LOGIN_PATTERN)
136 def login(org_slug=None):
137 # We intentionally use == as otherwise it won't actually use the proxy. So weird :O
138 # noinspection PyComparisonWithNone
139 if current_org == None and not settings.MULTI_ORG:
140 return redirect('/setup')
141 elif current_org == None:
142 return redirect('/')
143
144 index_url = url_for('redash.index', org_slug=org_slug)
145 unsafe_next_path = request.args.get('next', index_url)
146 next_path = get_next_path(unsafe_next_path)
147 if current_user.is_authenticated:
148 return redirect(next_path)
149
150 if request.method == 'POST':
151 try:
152 org = current_org._get_current_object()
153 user = models.User.get_by_email_and_org(request.form['email'], org)
154 if user and not user.is_disabled and user.verify_password(request.form['password']):
155 remember = ('remember' in request.form)
156 login_user(user, remember=remember)
157 return redirect(next_path)
158 else:
159 flash("Wrong email or password.")
160 except NoResultFound:
161 flash("Wrong email or password.")
162
163 google_auth_url = get_google_auth_url(next_path)
164
165 return render_template("login.html",
166 org_slug=org_slug,
167 next=next_path,
168 email=request.form.get('email', ''),
169 show_google_openid=settings.GOOGLE_OAUTH_ENABLED,
170 google_auth_url=google_auth_url,
171 show_password_login=current_org.get_setting('auth_password_login_enabled'),
172 show_saml_login=current_org.get_setting('auth_saml_enabled'),
173 show_remote_user_login=settings.REMOTE_USER_LOGIN_ENABLED,
174 show_ldap_login=settings.LDAP_LOGIN_ENABLED)
175
176
177 @routes.route(org_scoped_rule('/logout'))
178 def logout(org_slug=None):
179 logout_user()
180 return redirect(get_login_url(next=None))
181
182
183 def base_href():
184 if settings.MULTI_ORG:
185 base_href = url_for('redash.index', _external=True, org_slug=current_org.slug)
186 else:
187 base_href = url_for('redash.index', _external=True)
188
189 return base_href
190
191
192 def date_format_config():
193 date_format = current_org.get_setting('date_format')
194 date_format_list = set(["DD/MM/YY", "MM/DD/YY", "YYYY-MM-DD", settings.DATE_FORMAT])
195 return {
196 'dateFormat': date_format,
197 'dateFormatList': list(date_format_list),
198 'dateTimeFormat': "{0} HH:mm".format(date_format),
199 }
200
201
202 def client_config():
203 if not current_user.is_api_user() and current_user.is_authenticated:
204 client_config = {
205 'newVersionAvailable': bool(get_latest_version()),
206 'version': __version__
207 }
208 else:
209 client_config = {}
210
211 defaults = {
212 'allowScriptsInUserInput': settings.ALLOW_SCRIPTS_IN_USER_INPUT,
213 'showPermissionsControl': current_org.get_setting("feature_show_permissions_control"),
214 'allowCustomJSVisualizations': settings.FEATURE_ALLOW_CUSTOM_JS_VISUALIZATIONS,
215 'autoPublishNamedQueries': settings.FEATURE_AUTO_PUBLISH_NAMED_QUERIES,
216 'mailSettingsMissing': settings.MAIL_DEFAULT_SENDER is None,
217 'dashboardRefreshIntervals': settings.DASHBOARD_REFRESH_INTERVALS,
218 'queryRefreshIntervals': settings.QUERY_REFRESH_INTERVALS,
219 'googleLoginEnabled': settings.GOOGLE_OAUTH_ENABLED,
220 'pageSize': settings.PAGE_SIZE,
221 'pageSizeOptions': settings.PAGE_SIZE_OPTIONS,
222 }
223
224 client_config.update(defaults)
225 client_config.update({
226 'basePath': base_href()
227 })
228 client_config.update(date_format_config())
229
230 return client_config
231
232
233 @routes.route('/api/config', methods=['GET'])
234 def config(org_slug=None):
235 return json_response({
236 'org_slug': current_org.slug,
237 'client_config': client_config()
238 })
239
240
241 @routes.route(org_scoped_rule('/api/session'), methods=['GET'])
242 @login_required
243 def session(org_slug=None):
244 if current_user.is_api_user():
245 user = {
246 'permissions': [],
247 'apiKey': current_user.id
248 }
249 else:
250 user = {
251 'profile_image_url': current_user.profile_image_url,
252 'id': current_user.id,
253 'name': current_user.name,
254 'email': current_user.email,
255 'groups': current_user.group_ids,
256 'permissions': current_user.permissions,
257 'is_email_verified': current_user.is_email_verified
258 }
259
260 return json_response({
261 'user': user,
262 'org_slug': current_org.slug,
263 'client_config': client_config()
264 })
265
[end of redash/handlers/authentication.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/redash/handlers/authentication.py b/redash/handlers/authentication.py
--- a/redash/handlers/authentication.py
+++ b/redash/handlers/authentication.py
@@ -38,7 +38,7 @@
return render_template("error.html",
error_message="Your invite link has expired. Please ask for a new one."), 400
- if not user.is_invitation_pending:
+ if user.details.get('is_invitation_pending') is False:
return render_template("error.html",
error_message=("This invitation has already been accepted. "
"Please try resetting your password instead.")), 400
| {"golden_diff": "diff --git a/redash/handlers/authentication.py b/redash/handlers/authentication.py\n--- a/redash/handlers/authentication.py\n+++ b/redash/handlers/authentication.py\n@@ -38,7 +38,7 @@\n return render_template(\"error.html\",\n error_message=\"Your invite link has expired. Please ask for a new one.\"), 400\n \n- if not user.is_invitation_pending:\n+ if user.details.get('is_invitation_pending') is False:\n return render_template(\"error.html\",\n error_message=(\"This invitation has already been accepted. \"\n \"Please try resetting your password instead.\")), 400\n", "issue": "Pending invitation links broken in latest version\n\r\n<!--\r\n\r\nWe use GitHub only for bug reports \ud83d\udc1b\r\n\r\nAnything else should be posted to https://discuss.redash.io \ud83d\udc6b\r\n\r\n\ud83d\udea8For support, help & questions use https://discuss.redash.io/c/support\r\n\ud83d\udca1For feature requests & ideas use https://discuss.redash.io/c/feature-requests\r\n\r\n**Found a security vulnerability?** Please email [email protected] to report any security vulnerabilities. We will acknowledge receipt of your vulnerability and strive to send you regular updates about our progress. If you're curious about the status of your disclosure please feel free to email us again. If you want to encrypt your disclosure email, you can use this PGP key.\r\n\r\n-->\r\n\r\n### Issue Summary\r\n\r\nIt looks like the change in #3261 doesn't handle the case of existing users that haven't accepted their invitations yet, so users trying to sign up using invitations created in a previous version incorrectly get the \"This invitation has already been accepted\" message. https://github.com/getredash/redash/pull/3229/files#diff-a0c5448134fdb627ae48d25bad76393fR40\r\n\r\nI was able to fix this in our org with:\r\n\r\n```sql\r\nUPDATE users\r\nSET details = '{\"is_invitation_pending\": true}'::json\r\nWHERE password_hash IS NULL\r\n```\r\n\r\nMaybe this case should be handled in the migration here? https://github.com/getredash/redash/blob/master/migrations/versions/e7f8a917aa8e_add_user_details_json_column.py\r\n\r\n### Steps to Reproduce\r\n\r\n1. Send invitation from a version prior to #3229 and #3261 \r\n2. Upgrade to current master\r\n3. Try to access the invitation link\r\n\r\nAny other info e.g. Why do you consider this to be a bug? What did you expect to happen instead?\r\n\r\n### Technical details:\r\n\r\n* Redash Version:\r\n* Browser/OS:\r\n* How did you install Redash:\r\n\n", "before_files": [{"content": "import logging\n\nfrom flask import abort, flash, redirect, render_template, request, url_for\n\nfrom flask_login import current_user, login_required, login_user, logout_user\nfrom redash import __version__, limiter, models, settings\nfrom redash.authentication import current_org, get_login_url, get_next_path\nfrom redash.authentication.account import (BadSignature, SignatureExpired,\n send_password_reset_email,\n send_verify_email,\n validate_token)\nfrom redash.handlers import routes\nfrom redash.handlers.base import json_response, org_scoped_rule\nfrom redash.version_check import get_latest_version\nfrom sqlalchemy.orm.exc import NoResultFound\n\nlogger = logging.getLogger(__name__)\n\n\ndef get_google_auth_url(next_path):\n if settings.MULTI_ORG:\n google_auth_url = url_for('google_oauth.authorize_org', next=next_path, org_slug=current_org.slug)\n else:\n google_auth_url = url_for('google_oauth.authorize', next=next_path)\n return google_auth_url\n\n\ndef render_token_login_page(template, org_slug, token):\n try:\n user_id = validate_token(token)\n org = current_org._get_current_object()\n user = models.User.get_by_id_and_org(user_id, org)\n except NoResultFound:\n logger.exception(\"Bad user id in token. Token= , User id= %s, Org=%s\", user_id, token, org_slug)\n return render_template(\"error.html\", error_message=\"Invalid invite link. Please ask for a new one.\"), 400\n except (SignatureExpired, BadSignature):\n logger.exception(\"Failed to verify invite token: %s, org=%s\", token, org_slug)\n return render_template(\"error.html\",\n error_message=\"Your invite link has expired. Please ask for a new one.\"), 400\n\n if not user.is_invitation_pending:\n return render_template(\"error.html\",\n error_message=(\"This invitation has already been accepted. \"\n \"Please try resetting your password instead.\")), 400\n\n status_code = 200\n if request.method == 'POST':\n if 'password' not in request.form:\n flash('Bad Request')\n status_code = 400\n elif not request.form['password']:\n flash('Cannot use empty password.')\n status_code = 400\n elif len(request.form['password']) < 6:\n flash('Password length is too short (<6).')\n status_code = 400\n else:\n user.is_invitation_pending = False\n user.hash_password(request.form['password'])\n models.db.session.add(user)\n login_user(user)\n models.db.session.commit()\n return redirect(url_for('redash.index', org_slug=org_slug))\n\n google_auth_url = get_google_auth_url(url_for('redash.index', org_slug=org_slug))\n\n return render_template(template,\n show_google_openid=settings.GOOGLE_OAUTH_ENABLED,\n google_auth_url=google_auth_url,\n show_saml_login=current_org.get_setting('auth_saml_enabled'),\n show_remote_user_login=settings.REMOTE_USER_LOGIN_ENABLED,\n show_ldap_login=settings.LDAP_LOGIN_ENABLED,\n org_slug=org_slug,\n user=user), status_code\n\n\[email protected](org_scoped_rule('/invite/<token>'), methods=['GET', 'POST'])\ndef invite(token, org_slug=None):\n return render_token_login_page(\"invite.html\", org_slug, token)\n\n\[email protected](org_scoped_rule('/reset/<token>'), methods=['GET', 'POST'])\ndef reset(token, org_slug=None):\n return render_token_login_page(\"reset.html\", org_slug, token)\n\n\[email protected](org_scoped_rule('/verify/<token>'), methods=['GET'])\ndef verify(token, org_slug=None):\n try:\n user_id = validate_token(token)\n org = current_org._get_current_object()\n user = models.User.get_by_id_and_org(user_id, org)\n except (BadSignature, NoResultFound):\n logger.exception(\"Failed to verify email verification token: %s, org=%s\", token, org_slug)\n return render_template(\"error.html\",\n error_message=\"Your verification link is invalid. Please ask for a new one.\"), 400\n\n user.is_email_verified = True\n models.db.session.add(user)\n models.db.session.commit()\n\n return render_template(\"verify.html\", org_slug=org_slug)\n\n\[email protected](org_scoped_rule('/forgot'), methods=['GET', 'POST'])\ndef forgot_password(org_slug=None):\n if not current_org.get_setting('auth_password_login_enabled'):\n abort(404)\n\n submitted = False\n if request.method == 'POST' and request.form['email']:\n submitted = True\n email = request.form['email']\n try:\n org = current_org._get_current_object()\n user = models.User.get_by_email_and_org(email, org)\n send_password_reset_email(user)\n except NoResultFound:\n logging.error(\"No user found for forgot password: %s\", email)\n\n return render_template(\"forgot.html\", submitted=submitted)\n\n\[email protected](org_scoped_rule('/verification_email'), methods=['POST'])\ndef verification_email(org_slug=None):\n if not current_user.is_email_verified:\n send_verify_email(current_user, current_org)\n\n return json_response({\n \"message\": \"Please check your email inbox in order to verify your email address.\"\n })\n\n\[email protected](org_scoped_rule('/login'), methods=['GET', 'POST'])\[email protected](settings.THROTTLE_LOGIN_PATTERN)\ndef login(org_slug=None):\n # We intentionally use == as otherwise it won't actually use the proxy. So weird :O\n # noinspection PyComparisonWithNone\n if current_org == None and not settings.MULTI_ORG:\n return redirect('/setup')\n elif current_org == None:\n return redirect('/')\n\n index_url = url_for('redash.index', org_slug=org_slug)\n unsafe_next_path = request.args.get('next', index_url)\n next_path = get_next_path(unsafe_next_path)\n if current_user.is_authenticated:\n return redirect(next_path)\n\n if request.method == 'POST':\n try:\n org = current_org._get_current_object()\n user = models.User.get_by_email_and_org(request.form['email'], org)\n if user and not user.is_disabled and user.verify_password(request.form['password']):\n remember = ('remember' in request.form)\n login_user(user, remember=remember)\n return redirect(next_path)\n else:\n flash(\"Wrong email or password.\")\n except NoResultFound:\n flash(\"Wrong email or password.\")\n\n google_auth_url = get_google_auth_url(next_path)\n\n return render_template(\"login.html\",\n org_slug=org_slug,\n next=next_path,\n email=request.form.get('email', ''),\n show_google_openid=settings.GOOGLE_OAUTH_ENABLED,\n google_auth_url=google_auth_url,\n show_password_login=current_org.get_setting('auth_password_login_enabled'),\n show_saml_login=current_org.get_setting('auth_saml_enabled'),\n show_remote_user_login=settings.REMOTE_USER_LOGIN_ENABLED,\n show_ldap_login=settings.LDAP_LOGIN_ENABLED)\n\n\[email protected](org_scoped_rule('/logout'))\ndef logout(org_slug=None):\n logout_user()\n return redirect(get_login_url(next=None))\n\n\ndef base_href():\n if settings.MULTI_ORG:\n base_href = url_for('redash.index', _external=True, org_slug=current_org.slug)\n else:\n base_href = url_for('redash.index', _external=True)\n\n return base_href\n\n\ndef date_format_config():\n date_format = current_org.get_setting('date_format')\n date_format_list = set([\"DD/MM/YY\", \"MM/DD/YY\", \"YYYY-MM-DD\", settings.DATE_FORMAT])\n return {\n 'dateFormat': date_format,\n 'dateFormatList': list(date_format_list),\n 'dateTimeFormat': \"{0} HH:mm\".format(date_format),\n }\n\n\ndef client_config():\n if not current_user.is_api_user() and current_user.is_authenticated:\n client_config = {\n 'newVersionAvailable': bool(get_latest_version()),\n 'version': __version__\n }\n else:\n client_config = {}\n\n defaults = {\n 'allowScriptsInUserInput': settings.ALLOW_SCRIPTS_IN_USER_INPUT,\n 'showPermissionsControl': current_org.get_setting(\"feature_show_permissions_control\"),\n 'allowCustomJSVisualizations': settings.FEATURE_ALLOW_CUSTOM_JS_VISUALIZATIONS,\n 'autoPublishNamedQueries': settings.FEATURE_AUTO_PUBLISH_NAMED_QUERIES,\n 'mailSettingsMissing': settings.MAIL_DEFAULT_SENDER is None,\n 'dashboardRefreshIntervals': settings.DASHBOARD_REFRESH_INTERVALS,\n 'queryRefreshIntervals': settings.QUERY_REFRESH_INTERVALS,\n 'googleLoginEnabled': settings.GOOGLE_OAUTH_ENABLED,\n 'pageSize': settings.PAGE_SIZE,\n 'pageSizeOptions': settings.PAGE_SIZE_OPTIONS,\n }\n\n client_config.update(defaults)\n client_config.update({\n 'basePath': base_href()\n })\n client_config.update(date_format_config())\n\n return client_config\n\n\[email protected]('/api/config', methods=['GET'])\ndef config(org_slug=None):\n return json_response({\n 'org_slug': current_org.slug,\n 'client_config': client_config()\n })\n\n\[email protected](org_scoped_rule('/api/session'), methods=['GET'])\n@login_required\ndef session(org_slug=None):\n if current_user.is_api_user():\n user = {\n 'permissions': [],\n 'apiKey': current_user.id\n }\n else:\n user = {\n 'profile_image_url': current_user.profile_image_url,\n 'id': current_user.id,\n 'name': current_user.name,\n 'email': current_user.email,\n 'groups': current_user.group_ids,\n 'permissions': current_user.permissions,\n 'is_email_verified': current_user.is_email_verified\n }\n\n return json_response({\n 'user': user,\n 'org_slug': current_org.slug,\n 'client_config': client_config()\n })\n", "path": "redash/handlers/authentication.py"}]} | 3,821 | 142 |
gh_patches_debug_356 | rasdani/github-patches | git_diff | zigpy__zha-device-handlers-4 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Missing import for types breaking LocalDataCluster
</issue>
<code>
[start of zhaquirks/__init__.py]
1 import importlib
2 import pkgutil
3 from zigpy.quirks import CustomCluster
4 from zigpy.util import ListenableMixin
5
6 UNKNOWN = 'Unknown'
7
8
9 class Bus(ListenableMixin):
10
11 def __init__(self, *args, **kwargs):
12 super().__init__(*args, **kwargs)
13 self._listeners = {}
14
15
16 class LocalDataCluster(CustomCluster):
17
18 def __init__(self, *args, **kwargs):
19 super().__init__(*args, **kwargs)
20
21 async def read_attributes_raw(self, attributes, manufacturer=None):
22 attributes = [types.uint16_t(a) for a in attributes]
23 v = [self._attr_cache.get(attr) for attr in attributes]
24 return v
25
26 def _update_attribute(self, attrid, value):
27 super()._update_attribute(attrid, value)
28
29
30 class EventableCluster(CustomCluster):
31
32 def __init__(self, *args, **kwargs):
33 super().__init__(*args, **kwargs)
34
35 def handle_cluster_request(self, tsn, command_id, args):
36 super().handle_cluster_request(tsn, command_id, args)
37 if self.server_commands is not None and\
38 self.server_commands.get(command_id) is not None:
39 self.listener_event(
40 'zha_send_event',
41 self,
42 self.server_commands.get(command_id)[0],
43 args
44 )
45
46 def _update_attribute(self, attrid, value):
47 super()._update_attribute(attrid, value)
48 self.listener_event(
49 'zha_send_event',
50 self,
51 'attribute_updated',
52 {
53 'attribute_id': attrid,
54 'attribute_name': self.attributes.get(attrid, [UNKNOWN])[0],
55 'value': value
56 }
57 )
58
59 name = __name__
60 path = __path__
61 for importer, modname, ispkg in pkgutil.walk_packages(
62 path=path,
63 prefix=name +'.'
64 ):
65 importlib.import_module(modname)
66
[end of zhaquirks/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/zhaquirks/__init__.py b/zhaquirks/__init__.py
--- a/zhaquirks/__init__.py
+++ b/zhaquirks/__init__.py
@@ -2,6 +2,7 @@
import pkgutil
from zigpy.quirks import CustomCluster
from zigpy.util import ListenableMixin
+import zigpy.types as types
UNKNOWN = 'Unknown'
| {"golden_diff": "diff --git a/zhaquirks/__init__.py b/zhaquirks/__init__.py\n--- a/zhaquirks/__init__.py\n+++ b/zhaquirks/__init__.py\n@@ -2,6 +2,7 @@\n import pkgutil\n from zigpy.quirks import CustomCluster\n from zigpy.util import ListenableMixin\n+import zigpy.types as types\n \n UNKNOWN = 'Unknown'\n", "issue": "Missing import for types breaking LocalDataCluster\n\n", "before_files": [{"content": "import importlib\nimport pkgutil\nfrom zigpy.quirks import CustomCluster\nfrom zigpy.util import ListenableMixin\n\nUNKNOWN = 'Unknown'\n\n\nclass Bus(ListenableMixin):\n\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n self._listeners = {}\n\n\nclass LocalDataCluster(CustomCluster):\n\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n\n async def read_attributes_raw(self, attributes, manufacturer=None):\n attributes = [types.uint16_t(a) for a in attributes]\n v = [self._attr_cache.get(attr) for attr in attributes]\n return v\n\n def _update_attribute(self, attrid, value):\n super()._update_attribute(attrid, value)\n\n\nclass EventableCluster(CustomCluster):\n\n def __init__(self, *args, **kwargs):\n super().__init__(*args, **kwargs)\n\n def handle_cluster_request(self, tsn, command_id, args):\n super().handle_cluster_request(tsn, command_id, args)\n if self.server_commands is not None and\\\n self.server_commands.get(command_id) is not None:\n self.listener_event(\n 'zha_send_event',\n self,\n self.server_commands.get(command_id)[0],\n args\n )\n\n def _update_attribute(self, attrid, value):\n super()._update_attribute(attrid, value)\n self.listener_event(\n 'zha_send_event',\n self,\n 'attribute_updated',\n {\n 'attribute_id': attrid,\n 'attribute_name': self.attributes.get(attrid, [UNKNOWN])[0],\n 'value': value\n }\n )\n\nname = __name__\npath = __path__\nfor importer, modname, ispkg in pkgutil.walk_packages(\n path=path,\n prefix=name +'.'\n ):\n importlib.import_module(modname)\n", "path": "zhaquirks/__init__.py"}]} | 1,091 | 90 |
gh_patches_debug_597 | rasdani/github-patches | git_diff | pex-tool__pex-1610 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Release 2.1.66
On the docket:
+ [x] Support specifying foreign platforms in full detail. #1597
+ [x] Respect PEX_ROOT in PEXEnvironment.mount. #1599
+ [x] Be able to see what .pex file is run from the list of system processes #1604
</issue>
<code>
[start of pex/version.py]
1 # Copyright 2015 Pants project contributors (see CONTRIBUTORS.md).
2 # Licensed under the Apache License, Version 2.0 (see LICENSE).
3
4 __version__ = "2.1.65"
5
[end of pex/version.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/pex/version.py b/pex/version.py
--- a/pex/version.py
+++ b/pex/version.py
@@ -1,4 +1,4 @@
# Copyright 2015 Pants project contributors (see CONTRIBUTORS.md).
# Licensed under the Apache License, Version 2.0 (see LICENSE).
-__version__ = "2.1.65"
+__version__ = "2.1.66"
| {"golden_diff": "diff --git a/pex/version.py b/pex/version.py\n--- a/pex/version.py\n+++ b/pex/version.py\n@@ -1,4 +1,4 @@\n # Copyright 2015 Pants project contributors (see CONTRIBUTORS.md).\n # Licensed under the Apache License, Version 2.0 (see LICENSE).\n \n-__version__ = \"2.1.65\"\n+__version__ = \"2.1.66\"\n", "issue": "Release 2.1.66\nOn the docket:\r\n+ [x] Support specifying foreign platforms in full detail. #1597\r\n+ [x] Respect PEX_ROOT in PEXEnvironment.mount. #1599 \r\n+ [x] Be able to see what .pex file is run from the list of system processes #1604 \n", "before_files": [{"content": "# Copyright 2015 Pants project contributors (see CONTRIBUTORS.md).\n# Licensed under the Apache License, Version 2.0 (see LICENSE).\n\n__version__ = \"2.1.65\"\n", "path": "pex/version.py"}]} | 663 | 96 |
gh_patches_debug_34708 | rasdani/github-patches | git_diff | biolab__orange3-text-692 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Preprocess Text: consider pos tags when filtering tokens
**Describe the bug**
If pos tags exists before filtering, final pos tags don't match the tokens. This is because tokens are filtered independently from pos tags and only zipped at the end.
**To Reproduce**
Steps to reproduce the behavior:
1. Corpus
2. Preprocess Text (have POS tagger before filtering on stopwords)
3. Check the result in Corpus Viewer
**Expected behavior**
If pos tags exist, they are filtered together with tokens.
**Orange version:**
3.30.dev
**Text add-on version:**
1.6.dev
**Screenshots**
<img width="509" alt="Screen Shot 2021-07-21 at 15 13 50" src="https://user-images.githubusercontent.com/12524972/126494455-90d78da1-d0d3-4a02-be65-e176268c4c73.png">
**Operating system:**
OSX
**Additional context**
/
</issue>
<code>
[start of orangecontrib/text/preprocess/filter.py]
1 from typing import List, Callable
2 import os
3 import re
4
5 import numpy as np
6 from gensim import corpora
7 from nltk.corpus import stopwords
8
9 from Orange.data.io import detect_encoding
10 from Orange.util import wrap_callback, dummy_callback
11
12 from orangecontrib.text import Corpus
13 from orangecontrib.text.misc import wait_nltk_data
14 from orangecontrib.text.preprocess import TokenizedPreprocessor
15
16 __all__ = ['BaseTokenFilter', 'StopwordsFilter', 'LexiconFilter',
17 'RegexpFilter', 'FrequencyFilter', 'MostFrequentTokensFilter',
18 'PosTagFilter']
19
20
21 class BaseTokenFilter(TokenizedPreprocessor):
22 def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:
23 if callback is None:
24 callback = dummy_callback
25 corpus = super().__call__(corpus, wrap_callback(callback, end=0.2))
26 return self._filter_tokens(corpus, wrap_callback(callback, start=0.2))
27
28 def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:
29 callback(0, "Filtering...")
30 tokens = [self._preprocess(tokens) for tokens in corpus.tokens]
31 corpus.store_tokens(tokens)
32 return corpus
33
34 def _preprocess(self, tokens: List) -> List:
35 return list(filter(self._check, tokens))
36
37 def _check(self, token: str) -> bool:
38 raise NotImplementedError
39
40
41 class FileWordListMixin:
42 def __init__(self, path: str = None):
43 self._lexicon = self.from_file(path)
44
45 @staticmethod
46 def from_file(path):
47 if not path:
48 return set()
49
50 for encoding in ('utf-8', None, detect_encoding(path)):
51 try:
52 with open(path, encoding=encoding) as f:
53 return set(line.strip() for line in f)
54 except UnicodeDecodeError:
55 continue
56 # No encoding worked, raise
57 raise UnicodeError("Couldn't determine file encoding")
58
59
60 class StopwordsFilter(BaseTokenFilter, FileWordListMixin):
61 """ Remove tokens present in NLTK's language specific lists or a file. """
62 name = 'Stopwords'
63
64 @wait_nltk_data
65 def __init__(self, language='English', path: str = None):
66 super().__init__()
67 FileWordListMixin.__init__(self, path)
68 self.__stopwords = set(x.strip() for x in
69 stopwords.words(language.lower())) \
70 if language else []
71
72 @staticmethod
73 @wait_nltk_data
74 def supported_languages():
75 # get NLTK list of stopwords
76 stopwords_listdir = []
77 try:
78 stopwords_listdir = [file for file in
79 os.listdir(stopwords._get_root())
80 if file.islower()]
81 except LookupError: # when no NLTK data is available
82 pass
83
84 return sorted(file.capitalize() for file in stopwords_listdir)
85
86 def _check(self, token):
87 return token not in self.__stopwords and token not in self._lexicon
88
89
90 class LexiconFilter(BaseTokenFilter, FileWordListMixin):
91 """ Keep only tokens present in a file. """
92 name = 'Lexicon'
93
94 def _check(self, token):
95 return not self._lexicon or token in self._lexicon
96
97
98 class RegexpFilter(BaseTokenFilter):
99 """ Remove tokens matching this regular expressions. """
100 name = 'Regexp'
101
102 def __init__(self, pattern=r'\.|,|:|!|\?'):
103 self._pattern = pattern
104 # Compiled Regexes are NOT deepcopy-able and hence to make Corpus deepcopy-able
105 # we cannot store then (due to Corpus also storing used_preprocessor for BoW compute values).
106 # To bypass the problem regex is compiled before every __call__ and discarded right after.
107 self.regex = None
108
109 def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:
110 self.regex = re.compile(self._pattern)
111 corpus = super().__call__(corpus, callback)
112 self.regex = None
113 return corpus
114
115 @staticmethod
116 def validate_regexp(regexp):
117 try:
118 re.compile(regexp)
119 return True
120 except re.error:
121 return False
122
123 def _check(self, token):
124 return not self.regex.match(token)
125
126
127 class FitDictionaryFilter(BaseTokenFilter):
128 def __init__(self):
129 self._lexicon = None
130 self._dictionary = None
131
132 def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:
133 if callback is None:
134 callback = dummy_callback
135 corpus = TokenizedPreprocessor.__call__(
136 self, corpus, wrap_callback(callback, end=0.2))
137 callback(0.2, "Fitting filter...")
138 self._fit(corpus)
139 return self._filter_tokens(corpus, wrap_callback(callback, start=0.6))
140
141 def _fit(self, corpus: Corpus):
142 raise NotImplemented
143
144 def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:
145 callback(0, "Filtering...")
146 tokens = [self._preprocess(tokens) for tokens in corpus.tokens]
147 corpus.store_tokens(tokens, self._dictionary)
148 return corpus
149
150 def _check(self, token):
151 assert self._lexicon is not None
152 assert self._dictionary is not None
153 return token in self._lexicon
154
155
156 class FrequencyFilter(FitDictionaryFilter):
157 """Remove tokens with document frequency outside this range;
158 use either absolute or relative frequency. """
159 name = 'Document frequency'
160
161 def __init__(self, min_df=0., max_df=1.):
162 super().__init__()
163 self._corpus_len = 0
164 self._max_df = max_df
165 self._min_df = min_df
166
167 def _fit(self, corpus: Corpus):
168 self._corpus_len = len(corpus)
169 self._dictionary = corpora.Dictionary(corpus.tokens)
170 self._dictionary.filter_extremes(self.min_df, self.max_df, None)
171 self._lexicon = set(self._dictionary.token2id.keys())
172
173 @property
174 def max_df(self):
175 if isinstance(self._max_df, int):
176 return self._max_df / self._corpus_len if self._corpus_len else 1.
177 else:
178 return self._max_df
179
180 @property
181 def min_df(self):
182 if isinstance(self._min_df, float):
183 return int(self._corpus_len * self._min_df) or 1
184 else:
185 return self._min_df
186
187
188 class MostFrequentTokensFilter(FitDictionaryFilter):
189 """Keep most frequent tokens."""
190 name = 'Most frequent tokens'
191
192 def __init__(self, keep_n=None):
193 super().__init__()
194 self._keep_n = keep_n
195
196 def _fit(self, corpus: Corpus):
197 self._dictionary = corpora.Dictionary(corpus.tokens)
198 self._dictionary.filter_extremes(0, 1, self._keep_n)
199 self._lexicon = set(self._dictionary.token2id.keys())
200
201
202 class PosTagFilter(BaseTokenFilter):
203 """Keep selected POS tags."""
204 name = 'POS tags'
205
206 def __init__(self, tags=None):
207 self._tags = set(i.strip().upper() for i in tags.split(","))
208
209 def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:
210 if callback is None:
211 callback = dummy_callback
212 corpus = super().__call__(corpus, wrap_callback(callback, end=0.2))
213 return self._filter_tokens(corpus, wrap_callback(callback, start=0.2))
214
215 @staticmethod
216 def validate_tags(tags):
217 # should we keep a dict of existing POS tags and compare them with
218 # input?
219 return len(tags.split(",")) > 0
220
221 def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:
222 if corpus.pos_tags is None:
223 return corpus
224 callback(0, "Filtering...")
225 filtered_tags = []
226 filtered_tokens = []
227 for tags, tokens in zip(corpus.pos_tags, corpus.tokens):
228 tmp_tags = []
229 tmp_tokens = []
230 for tag, token in zip(tags, tokens):
231 # should we consider partial matches, i.e. "NN" for "NNS"?
232 if tag in self._tags:
233 tmp_tags.append(tag)
234 tmp_tokens.append(token)
235 filtered_tags.append(tmp_tags)
236 filtered_tokens.append(tmp_tokens)
237 corpus.store_tokens(filtered_tokens)
238 corpus.pos_tags = filtered_tags
239 return corpus
240
241 def _check(self, token: str) -> bool:
242 pass
243
[end of orangecontrib/text/preprocess/filter.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/orangecontrib/text/preprocess/filter.py b/orangecontrib/text/preprocess/filter.py
--- a/orangecontrib/text/preprocess/filter.py
+++ b/orangecontrib/text/preprocess/filter.py
@@ -1,3 +1,4 @@
+from itertools import compress
from typing import List, Callable
import os
import re
@@ -25,14 +26,27 @@
corpus = super().__call__(corpus, wrap_callback(callback, end=0.2))
return self._filter_tokens(corpus, wrap_callback(callback, start=0.2))
- def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:
+ def _filter_tokens(self, corpus: Corpus, callback: Callable,
+ dictionary=None) -> Corpus:
callback(0, "Filtering...")
- tokens = [self._preprocess(tokens) for tokens in corpus.tokens]
- corpus.store_tokens(tokens)
+ filtered_tokens = []
+ filtered_tags = []
+ for i, tokens in enumerate(corpus.tokens):
+ filter_map = self._preprocess(tokens)
+ filtered_tokens.append(list(compress(tokens, filter_map)))
+ if corpus.pos_tags is not None:
+ filtered_tags.append(list(compress(corpus.pos_tags[i],
+ filter_map)))
+ if dictionary is None:
+ corpus.store_tokens(filtered_tokens)
+ else:
+ corpus.store_tokens(filtered_tokens, dictionary)
+ if filtered_tags:
+ corpus.pos_tags = np.array(filtered_tags, dtype=object)
return corpus
def _preprocess(self, tokens: List) -> List:
- return list(filter(self._check, tokens))
+ return [self._check(token) for token in tokens]
def _check(self, token: str) -> bool:
raise NotImplementedError
@@ -141,10 +155,10 @@
def _fit(self, corpus: Corpus):
raise NotImplemented
- def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:
- callback(0, "Filtering...")
- tokens = [self._preprocess(tokens) for tokens in corpus.tokens]
- corpus.store_tokens(tokens, self._dictionary)
+ def _filter_tokens(self, corpus: Corpus, callback: Callable,
+ dictionary=None) -> Corpus:
+ corpus = super()._filter_tokens(corpus, callback,
+ dictionary=self._dictionary)
return corpus
def _check(self, token):
| {"golden_diff": "diff --git a/orangecontrib/text/preprocess/filter.py b/orangecontrib/text/preprocess/filter.py\n--- a/orangecontrib/text/preprocess/filter.py\n+++ b/orangecontrib/text/preprocess/filter.py\n@@ -1,3 +1,4 @@\n+from itertools import compress\n from typing import List, Callable\n import os\n import re\n@@ -25,14 +26,27 @@\n corpus = super().__call__(corpus, wrap_callback(callback, end=0.2))\n return self._filter_tokens(corpus, wrap_callback(callback, start=0.2))\n \n- def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:\n+ def _filter_tokens(self, corpus: Corpus, callback: Callable,\n+ dictionary=None) -> Corpus:\n callback(0, \"Filtering...\")\n- tokens = [self._preprocess(tokens) for tokens in corpus.tokens]\n- corpus.store_tokens(tokens)\n+ filtered_tokens = []\n+ filtered_tags = []\n+ for i, tokens in enumerate(corpus.tokens):\n+ filter_map = self._preprocess(tokens)\n+ filtered_tokens.append(list(compress(tokens, filter_map)))\n+ if corpus.pos_tags is not None:\n+ filtered_tags.append(list(compress(corpus.pos_tags[i],\n+ filter_map)))\n+ if dictionary is None:\n+ corpus.store_tokens(filtered_tokens)\n+ else:\n+ corpus.store_tokens(filtered_tokens, dictionary)\n+ if filtered_tags:\n+ corpus.pos_tags = np.array(filtered_tags, dtype=object)\n return corpus\n \n def _preprocess(self, tokens: List) -> List:\n- return list(filter(self._check, tokens))\n+ return [self._check(token) for token in tokens]\n \n def _check(self, token: str) -> bool:\n raise NotImplementedError\n@@ -141,10 +155,10 @@\n def _fit(self, corpus: Corpus):\n raise NotImplemented\n \n- def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:\n- callback(0, \"Filtering...\")\n- tokens = [self._preprocess(tokens) for tokens in corpus.tokens]\n- corpus.store_tokens(tokens, self._dictionary)\n+ def _filter_tokens(self, corpus: Corpus, callback: Callable,\n+ dictionary=None) -> Corpus:\n+ corpus = super()._filter_tokens(corpus, callback,\n+ dictionary=self._dictionary)\n return corpus\n \n def _check(self, token):\n", "issue": "Preprocess Text: consider pos tags when filtering tokens\n**Describe the bug**\r\nIf pos tags exists before filtering, final pos tags don't match the tokens. This is because tokens are filtered independently from pos tags and only zipped at the end.\r\n\r\n**To Reproduce**\r\nSteps to reproduce the behavior:\r\n1. Corpus\r\n2. Preprocess Text (have POS tagger before filtering on stopwords)\r\n3. Check the result in Corpus Viewer\r\n\r\n**Expected behavior**\r\nIf pos tags exist, they are filtered together with tokens.\r\n\r\n**Orange version:**\r\n3.30.dev\r\n\r\n**Text add-on version:**\r\n1.6.dev\r\n\r\n**Screenshots**\r\n<img width=\"509\" alt=\"Screen Shot 2021-07-21 at 15 13 50\" src=\"https://user-images.githubusercontent.com/12524972/126494455-90d78da1-d0d3-4a02-be65-e176268c4c73.png\">\r\n\r\n**Operating system:**\r\nOSX\r\n\r\n**Additional context**\r\n/\r\n\n", "before_files": [{"content": "from typing import List, Callable\nimport os\nimport re\n\nimport numpy as np\nfrom gensim import corpora\nfrom nltk.corpus import stopwords\n\nfrom Orange.data.io import detect_encoding\nfrom Orange.util import wrap_callback, dummy_callback\n\nfrom orangecontrib.text import Corpus\nfrom orangecontrib.text.misc import wait_nltk_data\nfrom orangecontrib.text.preprocess import TokenizedPreprocessor\n\n__all__ = ['BaseTokenFilter', 'StopwordsFilter', 'LexiconFilter',\n 'RegexpFilter', 'FrequencyFilter', 'MostFrequentTokensFilter',\n 'PosTagFilter']\n\n\nclass BaseTokenFilter(TokenizedPreprocessor):\n def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:\n if callback is None:\n callback = dummy_callback\n corpus = super().__call__(corpus, wrap_callback(callback, end=0.2))\n return self._filter_tokens(corpus, wrap_callback(callback, start=0.2))\n\n def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:\n callback(0, \"Filtering...\")\n tokens = [self._preprocess(tokens) for tokens in corpus.tokens]\n corpus.store_tokens(tokens)\n return corpus\n\n def _preprocess(self, tokens: List) -> List:\n return list(filter(self._check, tokens))\n\n def _check(self, token: str) -> bool:\n raise NotImplementedError\n\n\nclass FileWordListMixin:\n def __init__(self, path: str = None):\n self._lexicon = self.from_file(path)\n\n @staticmethod\n def from_file(path):\n if not path:\n return set()\n\n for encoding in ('utf-8', None, detect_encoding(path)):\n try:\n with open(path, encoding=encoding) as f:\n return set(line.strip() for line in f)\n except UnicodeDecodeError:\n continue\n # No encoding worked, raise\n raise UnicodeError(\"Couldn't determine file encoding\")\n\n\nclass StopwordsFilter(BaseTokenFilter, FileWordListMixin):\n \"\"\" Remove tokens present in NLTK's language specific lists or a file. \"\"\"\n name = 'Stopwords'\n\n @wait_nltk_data\n def __init__(self, language='English', path: str = None):\n super().__init__()\n FileWordListMixin.__init__(self, path)\n self.__stopwords = set(x.strip() for x in\n stopwords.words(language.lower())) \\\n if language else []\n\n @staticmethod\n @wait_nltk_data\n def supported_languages():\n # get NLTK list of stopwords\n stopwords_listdir = []\n try:\n stopwords_listdir = [file for file in\n os.listdir(stopwords._get_root())\n if file.islower()]\n except LookupError: # when no NLTK data is available\n pass\n\n return sorted(file.capitalize() for file in stopwords_listdir)\n\n def _check(self, token):\n return token not in self.__stopwords and token not in self._lexicon\n\n\nclass LexiconFilter(BaseTokenFilter, FileWordListMixin):\n \"\"\" Keep only tokens present in a file. \"\"\"\n name = 'Lexicon'\n\n def _check(self, token):\n return not self._lexicon or token in self._lexicon\n\n\nclass RegexpFilter(BaseTokenFilter):\n \"\"\" Remove tokens matching this regular expressions. \"\"\"\n name = 'Regexp'\n\n def __init__(self, pattern=r'\\.|,|:|!|\\?'):\n self._pattern = pattern\n # Compiled Regexes are NOT deepcopy-able and hence to make Corpus deepcopy-able\n # we cannot store then (due to Corpus also storing used_preprocessor for BoW compute values).\n # To bypass the problem regex is compiled before every __call__ and discarded right after.\n self.regex = None\n\n def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:\n self.regex = re.compile(self._pattern)\n corpus = super().__call__(corpus, callback)\n self.regex = None\n return corpus\n\n @staticmethod\n def validate_regexp(regexp):\n try:\n re.compile(regexp)\n return True\n except re.error:\n return False\n\n def _check(self, token):\n return not self.regex.match(token)\n\n\nclass FitDictionaryFilter(BaseTokenFilter):\n def __init__(self):\n self._lexicon = None\n self._dictionary = None\n\n def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:\n if callback is None:\n callback = dummy_callback\n corpus = TokenizedPreprocessor.__call__(\n self, corpus, wrap_callback(callback, end=0.2))\n callback(0.2, \"Fitting filter...\")\n self._fit(corpus)\n return self._filter_tokens(corpus, wrap_callback(callback, start=0.6))\n\n def _fit(self, corpus: Corpus):\n raise NotImplemented\n\n def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:\n callback(0, \"Filtering...\")\n tokens = [self._preprocess(tokens) for tokens in corpus.tokens]\n corpus.store_tokens(tokens, self._dictionary)\n return corpus\n\n def _check(self, token):\n assert self._lexicon is not None\n assert self._dictionary is not None\n return token in self._lexicon\n\n\nclass FrequencyFilter(FitDictionaryFilter):\n \"\"\"Remove tokens with document frequency outside this range;\n use either absolute or relative frequency. \"\"\"\n name = 'Document frequency'\n\n def __init__(self, min_df=0., max_df=1.):\n super().__init__()\n self._corpus_len = 0\n self._max_df = max_df\n self._min_df = min_df\n\n def _fit(self, corpus: Corpus):\n self._corpus_len = len(corpus)\n self._dictionary = corpora.Dictionary(corpus.tokens)\n self._dictionary.filter_extremes(self.min_df, self.max_df, None)\n self._lexicon = set(self._dictionary.token2id.keys())\n\n @property\n def max_df(self):\n if isinstance(self._max_df, int):\n return self._max_df / self._corpus_len if self._corpus_len else 1.\n else:\n return self._max_df\n\n @property\n def min_df(self):\n if isinstance(self._min_df, float):\n return int(self._corpus_len * self._min_df) or 1\n else:\n return self._min_df\n\n\nclass MostFrequentTokensFilter(FitDictionaryFilter):\n \"\"\"Keep most frequent tokens.\"\"\"\n name = 'Most frequent tokens'\n\n def __init__(self, keep_n=None):\n super().__init__()\n self._keep_n = keep_n\n\n def _fit(self, corpus: Corpus):\n self._dictionary = corpora.Dictionary(corpus.tokens)\n self._dictionary.filter_extremes(0, 1, self._keep_n)\n self._lexicon = set(self._dictionary.token2id.keys())\n\n\nclass PosTagFilter(BaseTokenFilter):\n \"\"\"Keep selected POS tags.\"\"\"\n name = 'POS tags'\n\n def __init__(self, tags=None):\n self._tags = set(i.strip().upper() for i in tags.split(\",\"))\n\n def __call__(self, corpus: Corpus, callback: Callable = None) -> Corpus:\n if callback is None:\n callback = dummy_callback\n corpus = super().__call__(corpus, wrap_callback(callback, end=0.2))\n return self._filter_tokens(corpus, wrap_callback(callback, start=0.2))\n\n @staticmethod\n def validate_tags(tags):\n # should we keep a dict of existing POS tags and compare them with\n # input?\n return len(tags.split(\",\")) > 0\n\n def _filter_tokens(self, corpus: Corpus, callback: Callable) -> Corpus:\n if corpus.pos_tags is None:\n return corpus\n callback(0, \"Filtering...\")\n filtered_tags = []\n filtered_tokens = []\n for tags, tokens in zip(corpus.pos_tags, corpus.tokens):\n tmp_tags = []\n tmp_tokens = []\n for tag, token in zip(tags, tokens):\n # should we consider partial matches, i.e. \"NN\" for \"NNS\"?\n if tag in self._tags:\n tmp_tags.append(tag)\n tmp_tokens.append(token)\n filtered_tags.append(tmp_tags)\n filtered_tokens.append(tmp_tokens)\n corpus.store_tokens(filtered_tokens)\n corpus.pos_tags = filtered_tags\n return corpus\n\n def _check(self, token: str) -> bool:\n pass\n", "path": "orangecontrib/text/preprocess/filter.py"}]} | 3,286 | 534 |
gh_patches_debug_26471 | rasdani/github-patches | git_diff | lmfit__lmfit-py-247 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
compatibility issue with Ipython4
hi,
I get this error experementing with Ipython4:
```
D:\WinPythonQt5\basedir34\build\winpython-3.4.3.amd64_build0\python-3.4.3.amd64\lib\site-packages\IPython\html.py:14: ShimWarning: The `IPython.html` package has been deprecated. You should import from `notebook` instead. `IPython.html.widgets` has moved to `ipywidgets`.
"`IPython.html.widgets` has moved to `ipywidgets`.", ShimWarning)
```
``` python3
python-3.4.3.amd64\lib\site-packages\lmfit\ui\ipy_fitter.py in <module>()
21 else:
22 # as of IPython 3.x:
---> 23 from IPython.html.widgets import Dropdown
24 from IPython.html.widgets import Button
25 from IPython.html.widgets import Box
ImportError: No module named 'widgets'
```
</issue>
<code>
[start of lmfit/ui/ipy_fitter.py]
1 import warnings
2 import numpy as np
3
4 from ..model import Model
5
6 from .basefitter import MPLFitter, _COMMON_DOC, _COMMON_EXAMPLES_DOC
7
8 # Note: If IPython is not available of the version is < 2,
9 # this module will not be imported, and a different Fitter.
10
11 import IPython
12 from IPython.display import display, clear_output
13 # Widgets were only experimental in IPython 2.x, but this does work there.
14 # Handle the change in naming from 2.x to 3.x.
15 IPY2 = IPython.release.version_info[0] == 2
16 if IPY2:
17 from IPython.html.widgets import DropdownWidget as Dropdown
18 from IPython.html.widgets import ButtonWidget as Button
19 from IPython.html.widgets import ContainerWidget as HBox
20 from IPython.html.widgets import FloatTextWidget as FloatText
21 from IPython.html.widgets import CheckboxWidget as Checkbox
22 class HBox(Box):
23 def __init__(*args, **kwargs):
24 self.add_class('hbox')
25 super(self, HBox).__init__(*args, **kwargs)
26 else:
27 # as of IPython 3.x:
28 from IPython.html.widgets import Dropdown
29 from IPython.html.widgets import Button
30 from IPython.html.widgets import HBox
31 from IPython.html.widgets import FloatText
32 from IPython.html.widgets import Checkbox
33
34
35 class ParameterWidgetGroup(object):
36 """Construct several widgets that together represent a Parameter.
37
38 This will only be used if IPython is available."""
39 def __init__(self, par):
40 self.par = par
41
42 # Define widgets.
43 self.value_text = FloatText(description=par.name,
44 min=self.par.min, max=self.par.max)
45 self.value_text.width = 100
46 self.min_text = FloatText(description='min', max=self.par.max)
47 self.min_text.width = 100
48 self.max_text = FloatText(description='max', min=self.par.min)
49 self.max_text.width = 100
50 self.min_checkbox = Checkbox(description='min')
51 self.max_checkbox = Checkbox(description='max')
52 self.vary_checkbox = Checkbox(description='vary')
53
54 # Set widget values and visibility.
55 if par.value is not None:
56 self.value_text.value = self.par.value
57 min_unset = self.par.min is None or self.par.min == -np.inf
58 max_unset = self.par.max is None or self.par.max == np.inf
59 self.min_checkbox.value = not min_unset
60 self.min_text.visible = not min_unset
61 self.min_text.value = self.par.min
62 self.max_checkbox.value = not max_unset
63 self.max_text.visible = not max_unset
64 self.max_text.value = self.par.max
65 self.vary_checkbox.value = self.par.vary
66
67 # Configure widgets to sync with par attributes.
68 self.value_text.on_trait_change(self._on_value_change, 'value')
69 self.min_text.on_trait_change(self._on_min_value_change, 'value')
70 self.max_text.on_trait_change(self._on_max_value_change, 'value')
71 self.min_checkbox.on_trait_change(self._on_min_checkbox_change,
72 'value')
73 self.max_checkbox.on_trait_change(self._on_max_checkbox_change,
74 'value')
75 self.vary_checkbox.on_trait_change(self._on_vary_change, 'value')
76
77 def _on_value_change(self, name, value):
78 self.par.value = value
79
80 def _on_min_checkbox_change(self, name, value):
81 self.min_text.visible = value
82 if value:
83 # -np.inf does not play well with a numerical text field,
84 # so set min to -1 if activated (and back to -inf if deactivated).
85 self.min_text.value = -1
86 self.par.min = self.min_text.value
87 self.value_text.min = self.min_text.value
88 else:
89 self.par.min = None
90
91 def _on_max_checkbox_change(self, name, value):
92 self.max_text.visible = value
93 if value:
94 # np.inf does not play well with a numerical text field,
95 # so set max to 1 if activated (and back to inf if deactivated).
96 self.max_text.value = 1
97 self.par.max = self.max_text.value
98 self.value_text.max = self.max_text.value
99 else:
100 self.par.max = None
101
102 def _on_min_value_change(self, name, value):
103 self.par.min = value
104 self.value_text.min = value
105 self.max_text.min = value
106
107 def _on_max_value_change(self, name, value):
108 self.par.max = value
109 self.value_text.max = value
110 self.min_text.max = value
111
112 def _on_vary_change(self, name, value):
113 self.par.vary = value
114 # self.value_text.disabled = not value
115
116 def close(self):
117 # one convenience method to close (i.e., hide and disconnect) all
118 # widgets in this group
119 self.value_text.close()
120 self.min_text.close()
121 self.max_text.close()
122 self.vary_checkbox.close()
123 self.min_checkbox.close()
124 self.max_checkbox.close()
125
126 def _repr_html_(self):
127 box = HBox()
128 box.children = [self.value_text, self.vary_checkbox,
129 self.min_checkbox, self.min_text,
130 self.max_checkbox, self.max_text]
131 display(box)
132
133 # Make it easy to set the widget attributes directly.
134 @property
135 def value(self):
136 return self.value_text.value
137
138 @value.setter
139 def value(self, value):
140 self.value_text.value = value
141
142 @property
143 def vary(self):
144 return self.vary_checkbox.value
145
146 @vary.setter
147 def vary(self, value):
148 self.vary_checkbox.value = value
149
150 @property
151 def min(self):
152 return self.min_text.value
153
154 @min.setter
155 def min(self, value):
156 self.min_text.value = value
157
158 @property
159 def max(self):
160 return self.max_text.value
161
162 @max.setter
163 def max(self, value):
164 self.max_text.value = value
165
166 @property
167 def name(self):
168 return self.par.name
169
170
171 class NotebookFitter(MPLFitter):
172 __doc__ = _COMMON_DOC + """
173 If IPython is available, it uses the IPython notebook's rich display
174 to fit data interactively in a web-based GUI. The Parameters are
175 represented in a web-based form that is kept in sync with `current_params`.
176 All subclasses to Model, including user-defined ones, are shown in a
177 drop-down menu.
178
179 Clicking the "Fit" button updates a plot, as above, and updates the
180 Parameters in the form to reflect the best fit.
181
182 Parameters
183 ----------
184 data : array-like
185 model : lmfit.Model
186 optional initial Model to use, maybe be set or changed later
187 all_models : list
188 optional list of Models to populate drop-down menu, by default
189 all built-in and user-defined subclasses of Model are used
190
191 Additional Parameters
192 ---------------------
193 axes_style : dictionary representing style keyword arguments to be
194 passed through to `Axes.set(...)`
195 data_style : dictionary representing style keyword arguments to be passed
196 through to the matplotlib `plot()` command the plots the data points
197 init_style : dictionary representing style keyword arguments to be passed
198 through to the matplotlib `plot()` command the plots the initial fit
199 line
200 best_style : dictionary representing style keyword arguments to be passed
201 through to the matplotlib `plot()` command the plots the best fit
202 line
203 **kwargs : independent variables or extra arguments, passed like `x=x`
204 """ + _COMMON_EXAMPLES_DOC
205 def __init__(self, data, model=None, all_models=None, axes_style={},
206 data_style={}, init_style={}, best_style={}, **kwargs):
207 # Dropdown menu of all subclasses of Model, incl. user-defined.
208 self.models_menu = Dropdown()
209 # Dropbox API is very different between IPy 2.x and 3.x.
210 if IPY2:
211 if all_models is None:
212 all_models = dict([(m.__name__, m) for m in Model.__subclasses__()])
213 self.models_menu.values = all_models
214 else:
215 if all_models is None:
216 all_models = [(m.__name__, m) for m in Model.__subclasses__()]
217 self.models_menu.options = all_models
218 self.models_menu.on_trait_change(self._on_model_value_change,
219 'value')
220 # Button to trigger fitting.
221 self.fit_button = Button(description='Fit')
222 self.fit_button.on_click(self._on_fit_button_click)
223
224 # Button to trigger guessing.
225 self.guess_button = Button(description='Auto-Guess')
226 self.guess_button.on_click(self._on_guess_button_click)
227
228 # Parameter widgets are not built here. They are (re-)built when
229 # the model is (re-)set.
230 super(NotebookFitter, self).__init__(data, model, axes_style,
231 data_style, init_style,
232 best_style, **kwargs)
233
234 def _repr_html_(self):
235 display(self.models_menu)
236 button_box = HBox()
237 button_box.children = [self.fit_button, self.guess_button]
238 display(button_box)
239 for pw in self.param_widgets:
240 display(pw)
241 self.plot()
242
243 def guess(self):
244 guessing_successful = super(NotebookFitter, self).guess()
245 self.guess_button.disabled = not guessing_successful
246
247 def _finalize_model(self, value):
248 first_run = not hasattr(self, 'param_widgets')
249 if not first_run:
250 # Remove all Parameter widgets, and replace them with widgets
251 # for the new model.
252 for pw in self.param_widgets:
253 pw.close()
254 self.models_menu.value = value
255 self.param_widgets = [ParameterWidgetGroup(p)
256 for _, p in self._current_params.items()]
257 if not first_run:
258 for pw in self.param_widgets:
259 display(pw)
260
261 def _finalize_params(self):
262 for pw in self.param_widgets:
263 pw.value = self._current_params[pw.name].value
264 pw.min = self._current_params[pw.name].min
265 pw.max = self._current_params[pw.name].max
266 pw.vary = self._current_params[pw.name].vary
267
268 def plot(self):
269 clear_output(wait=True)
270 super(NotebookFitter, self).plot()
271
272 def fit(self):
273 super(NotebookFitter, self).fit()
274 self.plot()
275
[end of lmfit/ui/ipy_fitter.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/lmfit/ui/ipy_fitter.py b/lmfit/ui/ipy_fitter.py
--- a/lmfit/ui/ipy_fitter.py
+++ b/lmfit/ui/ipy_fitter.py
@@ -13,6 +13,7 @@
# Widgets were only experimental in IPython 2.x, but this does work there.
# Handle the change in naming from 2.x to 3.x.
IPY2 = IPython.release.version_info[0] == 2
+IPY3 = IPython.release.version_info[0] == 3
if IPY2:
from IPython.html.widgets import DropdownWidget as Dropdown
from IPython.html.widgets import ButtonWidget as Button
@@ -23,13 +24,20 @@
def __init__(*args, **kwargs):
self.add_class('hbox')
super(self, HBox).__init__(*args, **kwargs)
-else:
+elif IPY3:
# as of IPython 3.x:
from IPython.html.widgets import Dropdown
from IPython.html.widgets import Button
from IPython.html.widgets import HBox
from IPython.html.widgets import FloatText
from IPython.html.widgets import Checkbox
+else:
+ # as of IPython 4.x+:
+ from ipywidgets import Dropdown
+ from ipywidgets import Button
+ from ipywidgets import Box
+ from ipywidgets import FloatText
+ from ipywidgets import Checkbox
class ParameterWidgetGroup(object):
| {"golden_diff": "diff --git a/lmfit/ui/ipy_fitter.py b/lmfit/ui/ipy_fitter.py\n--- a/lmfit/ui/ipy_fitter.py\n+++ b/lmfit/ui/ipy_fitter.py\n@@ -13,6 +13,7 @@\n # Widgets were only experimental in IPython 2.x, but this does work there.\n # Handle the change in naming from 2.x to 3.x.\n IPY2 = IPython.release.version_info[0] == 2\n+IPY3 = IPython.release.version_info[0] == 3\n if IPY2:\n from IPython.html.widgets import DropdownWidget as Dropdown\n from IPython.html.widgets import ButtonWidget as Button\n@@ -23,13 +24,20 @@\n def __init__(*args, **kwargs):\n self.add_class('hbox')\n super(self, HBox).__init__(*args, **kwargs)\n-else:\n+elif IPY3:\n # as of IPython 3.x:\n from IPython.html.widgets import Dropdown\n from IPython.html.widgets import Button\n from IPython.html.widgets import HBox\n from IPython.html.widgets import FloatText\n from IPython.html.widgets import Checkbox\n+else:\n+ # as of IPython 4.x+:\n+ from ipywidgets import Dropdown\n+ from ipywidgets import Button\n+ from ipywidgets import Box\n+ from ipywidgets import FloatText\n+ from ipywidgets import Checkbox\n \n \n class ParameterWidgetGroup(object):\n", "issue": "compatibility issue with Ipython4\nhi,\n\nI get this error experementing with Ipython4:\n\n```\nD:\\WinPythonQt5\\basedir34\\build\\winpython-3.4.3.amd64_build0\\python-3.4.3.amd64\\lib\\site-packages\\IPython\\html.py:14: ShimWarning: The `IPython.html` package has been deprecated. You should import from `notebook` instead. `IPython.html.widgets` has moved to `ipywidgets`.\n \"`IPython.html.widgets` has moved to `ipywidgets`.\", ShimWarning)\n```\n\n``` python3\npython-3.4.3.amd64\\lib\\site-packages\\lmfit\\ui\\ipy_fitter.py in <module>()\n 21 else:\n 22 # as of IPython 3.x:\n---> 23 from IPython.html.widgets import Dropdown\n 24 from IPython.html.widgets import Button\n 25 from IPython.html.widgets import Box\n\nImportError: No module named 'widgets'\n```\n\n", "before_files": [{"content": "import warnings\nimport numpy as np\n\nfrom ..model import Model\n\nfrom .basefitter import MPLFitter, _COMMON_DOC, _COMMON_EXAMPLES_DOC\n\n# Note: If IPython is not available of the version is < 2,\n# this module will not be imported, and a different Fitter.\n\nimport IPython\nfrom IPython.display import display, clear_output\n# Widgets were only experimental in IPython 2.x, but this does work there.\n# Handle the change in naming from 2.x to 3.x.\nIPY2 = IPython.release.version_info[0] == 2\nif IPY2:\n from IPython.html.widgets import DropdownWidget as Dropdown\n from IPython.html.widgets import ButtonWidget as Button\n from IPython.html.widgets import ContainerWidget as HBox\n from IPython.html.widgets import FloatTextWidget as FloatText\n from IPython.html.widgets import CheckboxWidget as Checkbox\n class HBox(Box):\n def __init__(*args, **kwargs):\n self.add_class('hbox')\n super(self, HBox).__init__(*args, **kwargs)\nelse:\n # as of IPython 3.x:\n from IPython.html.widgets import Dropdown\n from IPython.html.widgets import Button\n from IPython.html.widgets import HBox\n from IPython.html.widgets import FloatText\n from IPython.html.widgets import Checkbox\n\n\nclass ParameterWidgetGroup(object):\n \"\"\"Construct several widgets that together represent a Parameter.\n\n This will only be used if IPython is available.\"\"\"\n def __init__(self, par):\n self.par = par\n\n # Define widgets.\n self.value_text = FloatText(description=par.name,\n min=self.par.min, max=self.par.max)\n self.value_text.width = 100\n self.min_text = FloatText(description='min', max=self.par.max)\n self.min_text.width = 100\n self.max_text = FloatText(description='max', min=self.par.min)\n self.max_text.width = 100\n self.min_checkbox = Checkbox(description='min')\n self.max_checkbox = Checkbox(description='max')\n self.vary_checkbox = Checkbox(description='vary')\n\n # Set widget values and visibility.\n if par.value is not None:\n self.value_text.value = self.par.value\n min_unset = self.par.min is None or self.par.min == -np.inf\n max_unset = self.par.max is None or self.par.max == np.inf\n self.min_checkbox.value = not min_unset\n self.min_text.visible = not min_unset\n self.min_text.value = self.par.min\n self.max_checkbox.value = not max_unset\n self.max_text.visible = not max_unset\n self.max_text.value = self.par.max\n self.vary_checkbox.value = self.par.vary\n\n # Configure widgets to sync with par attributes.\n self.value_text.on_trait_change(self._on_value_change, 'value')\n self.min_text.on_trait_change(self._on_min_value_change, 'value')\n self.max_text.on_trait_change(self._on_max_value_change, 'value')\n self.min_checkbox.on_trait_change(self._on_min_checkbox_change,\n 'value')\n self.max_checkbox.on_trait_change(self._on_max_checkbox_change,\n 'value')\n self.vary_checkbox.on_trait_change(self._on_vary_change, 'value')\n\n def _on_value_change(self, name, value):\n self.par.value = value\n\n def _on_min_checkbox_change(self, name, value):\n self.min_text.visible = value\n if value:\n # -np.inf does not play well with a numerical text field,\n # so set min to -1 if activated (and back to -inf if deactivated).\n self.min_text.value = -1\n self.par.min = self.min_text.value\n self.value_text.min = self.min_text.value\n else:\n self.par.min = None\n\n def _on_max_checkbox_change(self, name, value):\n self.max_text.visible = value\n if value:\n # np.inf does not play well with a numerical text field,\n # so set max to 1 if activated (and back to inf if deactivated).\n self.max_text.value = 1\n self.par.max = self.max_text.value\n self.value_text.max = self.max_text.value\n else:\n self.par.max = None\n\n def _on_min_value_change(self, name, value):\n self.par.min = value\n self.value_text.min = value\n self.max_text.min = value\n\n def _on_max_value_change(self, name, value):\n self.par.max = value\n self.value_text.max = value\n self.min_text.max = value\n\n def _on_vary_change(self, name, value):\n self.par.vary = value\n # self.value_text.disabled = not value\n\n def close(self):\n # one convenience method to close (i.e., hide and disconnect) all\n # widgets in this group\n self.value_text.close()\n self.min_text.close()\n self.max_text.close()\n self.vary_checkbox.close()\n self.min_checkbox.close()\n self.max_checkbox.close()\n\n def _repr_html_(self):\n box = HBox()\n box.children = [self.value_text, self.vary_checkbox,\n self.min_checkbox, self.min_text,\n self.max_checkbox, self.max_text]\n display(box)\n\n # Make it easy to set the widget attributes directly.\n @property\n def value(self):\n return self.value_text.value\n\n @value.setter\n def value(self, value):\n self.value_text.value = value\n\n @property\n def vary(self):\n return self.vary_checkbox.value\n\n @vary.setter\n def vary(self, value):\n self.vary_checkbox.value = value\n\n @property\n def min(self):\n return self.min_text.value\n\n @min.setter\n def min(self, value):\n self.min_text.value = value\n\n @property\n def max(self):\n return self.max_text.value\n\n @max.setter\n def max(self, value):\n self.max_text.value = value\n\n @property\n def name(self):\n return self.par.name\n\n\nclass NotebookFitter(MPLFitter):\n __doc__ = _COMMON_DOC + \"\"\"\n If IPython is available, it uses the IPython notebook's rich display\n to fit data interactively in a web-based GUI. The Parameters are\n represented in a web-based form that is kept in sync with `current_params`.\n All subclasses to Model, including user-defined ones, are shown in a\n drop-down menu.\n\n Clicking the \"Fit\" button updates a plot, as above, and updates the\n Parameters in the form to reflect the best fit.\n\n Parameters\n ----------\n data : array-like\n model : lmfit.Model\n optional initial Model to use, maybe be set or changed later\n all_models : list\n optional list of Models to populate drop-down menu, by default\n all built-in and user-defined subclasses of Model are used\n\n Additional Parameters\n ---------------------\n axes_style : dictionary representing style keyword arguments to be\n passed through to `Axes.set(...)`\n data_style : dictionary representing style keyword arguments to be passed\n through to the matplotlib `plot()` command the plots the data points\n init_style : dictionary representing style keyword arguments to be passed\n through to the matplotlib `plot()` command the plots the initial fit\n line\n best_style : dictionary representing style keyword arguments to be passed\n through to the matplotlib `plot()` command the plots the best fit\n line\n **kwargs : independent variables or extra arguments, passed like `x=x`\n \"\"\" + _COMMON_EXAMPLES_DOC\n def __init__(self, data, model=None, all_models=None, axes_style={},\n data_style={}, init_style={}, best_style={}, **kwargs):\n # Dropdown menu of all subclasses of Model, incl. user-defined.\n self.models_menu = Dropdown()\n # Dropbox API is very different between IPy 2.x and 3.x.\n if IPY2:\n if all_models is None:\n all_models = dict([(m.__name__, m) for m in Model.__subclasses__()])\n self.models_menu.values = all_models\n else:\n if all_models is None:\n all_models = [(m.__name__, m) for m in Model.__subclasses__()]\n self.models_menu.options = all_models\n self.models_menu.on_trait_change(self._on_model_value_change,\n 'value')\n # Button to trigger fitting.\n self.fit_button = Button(description='Fit')\n self.fit_button.on_click(self._on_fit_button_click)\n\n # Button to trigger guessing.\n self.guess_button = Button(description='Auto-Guess')\n self.guess_button.on_click(self._on_guess_button_click)\n\n # Parameter widgets are not built here. They are (re-)built when\n # the model is (re-)set.\n super(NotebookFitter, self).__init__(data, model, axes_style,\n data_style, init_style,\n best_style, **kwargs)\n\n def _repr_html_(self):\n display(self.models_menu)\n button_box = HBox()\n button_box.children = [self.fit_button, self.guess_button]\n display(button_box)\n for pw in self.param_widgets:\n display(pw)\n self.plot()\n\n def guess(self):\n guessing_successful = super(NotebookFitter, self).guess()\n self.guess_button.disabled = not guessing_successful\n\n def _finalize_model(self, value):\n first_run = not hasattr(self, 'param_widgets')\n if not first_run:\n # Remove all Parameter widgets, and replace them with widgets\n # for the new model.\n for pw in self.param_widgets:\n pw.close()\n self.models_menu.value = value\n self.param_widgets = [ParameterWidgetGroup(p)\n for _, p in self._current_params.items()]\n if not first_run:\n for pw in self.param_widgets:\n display(pw)\n\n def _finalize_params(self):\n for pw in self.param_widgets:\n pw.value = self._current_params[pw.name].value\n pw.min = self._current_params[pw.name].min\n pw.max = self._current_params[pw.name].max\n pw.vary = self._current_params[pw.name].vary\n\n def plot(self):\n clear_output(wait=True)\n super(NotebookFitter, self).plot()\n\n def fit(self):\n super(NotebookFitter, self).fit()\n self.plot()\n", "path": "lmfit/ui/ipy_fitter.py"}]} | 3,790 | 335 |
gh_patches_debug_12361 | rasdani/github-patches | git_diff | carpentries__amy-2333 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Prepare AMY staging instance for actual use
New test AMY server is running, but it lacks some features from the other server.
- [x] Run fixtures (should be accompanied by #2239)
- [x] Scaffold non-admin users for AMY database
- [ ] Add default admin user
</issue>
<code>
[start of amy/workshops/management/commands/create_superuser.py]
1 from django.core.management.base import BaseCommand, CommandError
2
3 from communityroles.models import CommunityRole, CommunityRoleConfig
4 from workshops.models import Person
5
6
7 class Command(BaseCommand):
8 args = "no arguments"
9 help = 'Create a superuser called "admin" with password "admin".'
10
11 def handle(self, *args, **options):
12 try:
13 admin = Person.objects.create_superuser(
14 username="admin",
15 personal="admin",
16 family="admin",
17 email="[email protected]",
18 password="admin",
19 )
20 print("Created admin user")
21
22 role_config = CommunityRoleConfig.objects.get(name="instructor")
23 CommunityRole.objects.create(
24 config=role_config,
25 person=admin,
26 )
27 print("Assigned Instructor community role to admin user")
28
29 except Exception as e:
30 raise CommandError("Failed to create admin: {0}".format(str(e)))
31
[end of amy/workshops/management/commands/create_superuser.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/amy/workshops/management/commands/create_superuser.py b/amy/workshops/management/commands/create_superuser.py
--- a/amy/workshops/management/commands/create_superuser.py
+++ b/amy/workshops/management/commands/create_superuser.py
@@ -9,9 +9,15 @@
help = 'Create a superuser called "admin" with password "admin".'
def handle(self, *args, **options):
+ username = "admin"
+
+ if Person.objects.filter(username=username).exists():
+ print("Admin user exists, quitting.")
+ return
+
try:
admin = Person.objects.create_superuser(
- username="admin",
+ username=username,
personal="admin",
family="admin",
email="[email protected]",
| {"golden_diff": "diff --git a/amy/workshops/management/commands/create_superuser.py b/amy/workshops/management/commands/create_superuser.py\n--- a/amy/workshops/management/commands/create_superuser.py\n+++ b/amy/workshops/management/commands/create_superuser.py\n@@ -9,9 +9,15 @@\n help = 'Create a superuser called \"admin\" with password \"admin\".'\n \n def handle(self, *args, **options):\n+ username = \"admin\"\n+\n+ if Person.objects.filter(username=username).exists():\n+ print(\"Admin user exists, quitting.\")\n+ return\n+\n try:\n admin = Person.objects.create_superuser(\n- username=\"admin\",\n+ username=username,\n personal=\"admin\",\n family=\"admin\",\n email=\"[email protected]\",\n", "issue": "Prepare AMY staging instance for actual use\nNew test AMY server is running, but it lacks some features from the other server.\r\n\r\n- [x] Run fixtures (should be accompanied by #2239)\r\n- [x] Scaffold non-admin users for AMY database\r\n- [ ] Add default admin user\n", "before_files": [{"content": "from django.core.management.base import BaseCommand, CommandError\n\nfrom communityroles.models import CommunityRole, CommunityRoleConfig\nfrom workshops.models import Person\n\n\nclass Command(BaseCommand):\n args = \"no arguments\"\n help = 'Create a superuser called \"admin\" with password \"admin\".'\n\n def handle(self, *args, **options):\n try:\n admin = Person.objects.create_superuser(\n username=\"admin\",\n personal=\"admin\",\n family=\"admin\",\n email=\"[email protected]\",\n password=\"admin\",\n )\n print(\"Created admin user\")\n\n role_config = CommunityRoleConfig.objects.get(name=\"instructor\")\n CommunityRole.objects.create(\n config=role_config,\n person=admin,\n )\n print(\"Assigned Instructor community role to admin user\")\n\n except Exception as e:\n raise CommandError(\"Failed to create admin: {0}\".format(str(e)))\n", "path": "amy/workshops/management/commands/create_superuser.py"}]} | 853 | 170 |
gh_patches_debug_22821 | rasdani/github-patches | git_diff | pyg-team__pytorch_geometric-5094 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
New attribute `self._load_hook` in linear class since 2.03 will raise KeyError when executing `load_state_dict` fucntion
### 🐛 Describe the bug
In Pytorch, the function `load_state_dict(state_dict, strict)` allows empty dict `state_dict=={}` when `strict` is False.
However, from version 2.03 the linear class in `torch_geometric.nn.dense.linear.py` has a new attribute `self._load_hook`, and when we execute `Linear(xxxx).load_state_dict({}, strict=False)`, the linear class will execute the `self._lazy_load_hook` function as follows
```
def _lazy_load_hook(self, state_dict, prefix, local_metadata, strict,
missing_keys, unexpected_keys, error_msgs):
weight = state_dict[prefix + 'weight']
if is_uninitialized_parameter(weight):
self.in_channels = -1
self.weight = nn.parameter.UninitializedParameter()
if not hasattr(self, '_hook'):
self._hook = self.register_forward_pre_hook(
self.initialize_parameters)
elif is_uninitialized_parameter(self.weight):
self.in_channels = weight.size(-1)
self.weight.materialize((self.out_channels, self.in_channels))
if hasattr(self, '_hook'):
self._hook.remove()
delattr(self, '_hook')
```
Since the `state_dict` is empty, the line `weight = state_dict[prefix + 'weight']` will report KeyError.
### Environment
* PyG version:
* PyTorch version:
* OS:
* Python version:
* CUDA/cuDNN version:
* How you installed PyTorch and PyG (`conda`, `pip`, source):
* Any other relevant information (*e.g.*, version of `torch-scatter`):
</issue>
<code>
[start of torch_geometric/nn/dense/linear.py]
1 import copy
2 import math
3 from typing import Any, Optional
4
5 import torch
6 import torch.nn.functional as F
7 from torch import Tensor, nn
8 from torch.nn.parameter import Parameter
9
10 from torch_geometric.nn import inits
11
12
13 def is_uninitialized_parameter(x: Any) -> bool:
14 if not hasattr(nn.parameter, 'UninitializedParameter'):
15 return False
16 return isinstance(x, nn.parameter.UninitializedParameter)
17
18
19 class Linear(torch.nn.Module):
20 r"""Applies a linear tranformation to the incoming data
21
22 .. math::
23 \mathbf{x}^{\prime} = \mathbf{x} \mathbf{W}^{\top} + \mathbf{b}
24
25 similar to :class:`torch.nn.Linear`.
26 It supports lazy initialization and customizable weight and bias
27 initialization.
28
29 Args:
30 in_channels (int): Size of each input sample. Will be initialized
31 lazily in case it is given as :obj:`-1`.
32 out_channels (int): Size of each output sample.
33 bias (bool, optional): If set to :obj:`False`, the layer will not learn
34 an additive bias. (default: :obj:`True`)
35 weight_initializer (str, optional): The initializer for the weight
36 matrix (:obj:`"glorot"`, :obj:`"uniform"`, :obj:`"kaiming_uniform"`
37 or :obj:`None`).
38 If set to :obj:`None`, will match default weight initialization of
39 :class:`torch.nn.Linear`. (default: :obj:`None`)
40 bias_initializer (str, optional): The initializer for the bias vector
41 (:obj:`"zeros"` or :obj:`None`).
42 If set to :obj:`None`, will match default bias initialization of
43 :class:`torch.nn.Linear`. (default: :obj:`None`)
44
45 Shapes:
46 - **input:** features :math:`(*, F_{in})`
47 - **output:** features :math:`(*, F_{out})`
48 """
49 def __init__(self, in_channels: int, out_channels: int, bias: bool = True,
50 weight_initializer: Optional[str] = None,
51 bias_initializer: Optional[str] = None):
52 super().__init__()
53 self.in_channels = in_channels
54 self.out_channels = out_channels
55 self.weight_initializer = weight_initializer
56 self.bias_initializer = bias_initializer
57
58 if in_channels > 0:
59 self.weight = Parameter(torch.Tensor(out_channels, in_channels))
60 else:
61 self.weight = nn.parameter.UninitializedParameter()
62 self._hook = self.register_forward_pre_hook(
63 self.initialize_parameters)
64
65 if bias:
66 self.bias = Parameter(torch.Tensor(out_channels))
67 else:
68 self.register_parameter('bias', None)
69
70 self._load_hook = self._register_load_state_dict_pre_hook(
71 self._lazy_load_hook)
72
73 self.reset_parameters()
74
75 def __deepcopy__(self, memo):
76 out = Linear(self.in_channels, self.out_channels, self.bias
77 is not None, self.weight_initializer,
78 self.bias_initializer)
79 if self.in_channels > 0:
80 out.weight = copy.deepcopy(self.weight, memo)
81 if self.bias is not None:
82 out.bias = copy.deepcopy(self.bias, memo)
83 return out
84
85 def reset_parameters(self):
86 if self.in_channels <= 0:
87 pass
88 elif self.weight_initializer == 'glorot':
89 inits.glorot(self.weight)
90 elif self.weight_initializer == 'uniform':
91 bound = 1.0 / math.sqrt(self.weight.size(-1))
92 torch.nn.init.uniform_(self.weight.data, -bound, bound)
93 elif self.weight_initializer == 'kaiming_uniform':
94 inits.kaiming_uniform(self.weight, fan=self.in_channels,
95 a=math.sqrt(5))
96 elif self.weight_initializer is None:
97 inits.kaiming_uniform(self.weight, fan=self.in_channels,
98 a=math.sqrt(5))
99 else:
100 raise RuntimeError(f"Linear layer weight initializer "
101 f"'{self.weight_initializer}' is not supported")
102
103 if self.bias is None or self.in_channels <= 0:
104 pass
105 elif self.bias_initializer == 'zeros':
106 inits.zeros(self.bias)
107 elif self.bias_initializer is None:
108 inits.uniform(self.in_channels, self.bias)
109 else:
110 raise RuntimeError(f"Linear layer bias initializer "
111 f"'{self.bias_initializer}' is not supported")
112
113 def forward(self, x: Tensor) -> Tensor:
114 r"""
115 Args:
116 x (Tensor): The features.
117 """
118 return F.linear(x, self.weight, self.bias)
119
120 @torch.no_grad()
121 def initialize_parameters(self, module, input):
122 if is_uninitialized_parameter(self.weight):
123 self.in_channels = input[0].size(-1)
124 self.weight.materialize((self.out_channels, self.in_channels))
125 self.reset_parameters()
126 self._hook.remove()
127 delattr(self, '_hook')
128
129 def _save_to_state_dict(self, destination, prefix, keep_vars):
130 if is_uninitialized_parameter(self.weight):
131 destination[prefix + 'weight'] = self.weight
132 else:
133 destination[prefix + 'weight'] = self.weight.detach()
134 if self.bias is not None:
135 destination[prefix + 'bias'] = self.bias.detach()
136
137 def _lazy_load_hook(self, state_dict, prefix, local_metadata, strict,
138 missing_keys, unexpected_keys, error_msgs):
139
140 weight = state_dict[prefix + 'weight']
141 if is_uninitialized_parameter(weight):
142 self.in_channels = -1
143 self.weight = nn.parameter.UninitializedParameter()
144 if not hasattr(self, '_hook'):
145 self._hook = self.register_forward_pre_hook(
146 self.initialize_parameters)
147
148 elif is_uninitialized_parameter(self.weight):
149 self.in_channels = weight.size(-1)
150 self.weight.materialize((self.out_channels, self.in_channels))
151 if hasattr(self, '_hook'):
152 self._hook.remove()
153 delattr(self, '_hook')
154
155 def __repr__(self) -> str:
156 return (f'{self.__class__.__name__}({self.in_channels}, '
157 f'{self.out_channels}, bias={self.bias is not None})')
158
159
160 class HeteroLinear(torch.nn.Module):
161 r"""Applies separate linear tranformations to the incoming data according
162 to types
163
164 .. math::
165 \mathbf{x}^{\prime}_{\kappa} = \mathbf{x}_{\kappa}
166 \mathbf{W}^{\top}_{\kappa} + \mathbf{b}_{\kappa}
167
168 for type :math:`\kappa`.
169 It supports lazy initialization and customizable weight and bias
170 initialization.
171
172 Args:
173 in_channels (int): Size of each input sample. Will be initialized
174 lazily in case it is given as :obj:`-1`.
175 out_channels (int): Size of each output sample.
176 num_types (int): The number of types.
177 **kwargs (optional): Additional arguments of
178 :class:`torch_geometric.nn.Linear`.
179
180 Shapes:
181 - **input:**
182 features :math:`(*, F_{in})`,
183 type vector :math:`(*)`
184 - **output:** features :math:`(*, F_{out})`
185 """
186 def __init__(self, in_channels: int, out_channels: int, num_types: int,
187 **kwargs):
188 super().__init__()
189
190 self.in_channels = in_channels
191 self.out_channels = out_channels
192
193 self.lins = torch.nn.ModuleList([
194 Linear(in_channels, out_channels, **kwargs)
195 for _ in range(num_types)
196 ])
197
198 self.reset_parameters()
199
200 def reset_parameters(self):
201 for lin in self.lins:
202 lin.reset_parameters()
203
204 def forward(self, x: Tensor, type_vec: Tensor) -> Tensor:
205 r"""
206 Args:
207 x (Tensor): The input features.
208 type_vec (LongTensor): A vector that maps each entry to a type.
209 """
210 out = x.new_empty(x.size(0), self.out_channels)
211 for i, lin in enumerate(self.lins):
212 mask = type_vec == i
213 out[mask] = lin(x[mask])
214 return out
215
216 def __repr__(self) -> str:
217 return (f'{self.__class__.__name__}({self.in_channels}, '
218 f'{self.out_channels}, bias={self.lins[0].bias is not None})')
219
[end of torch_geometric/nn/dense/linear.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/torch_geometric/nn/dense/linear.py b/torch_geometric/nn/dense/linear.py
--- a/torch_geometric/nn/dense/linear.py
+++ b/torch_geometric/nn/dense/linear.py
@@ -137,15 +137,16 @@
def _lazy_load_hook(self, state_dict, prefix, local_metadata, strict,
missing_keys, unexpected_keys, error_msgs):
- weight = state_dict[prefix + 'weight']
- if is_uninitialized_parameter(weight):
+ weight = state_dict.get(prefix + 'weight', None)
+
+ if weight is not None and is_uninitialized_parameter(weight):
self.in_channels = -1
self.weight = nn.parameter.UninitializedParameter()
if not hasattr(self, '_hook'):
self._hook = self.register_forward_pre_hook(
self.initialize_parameters)
- elif is_uninitialized_parameter(self.weight):
+ elif weight is not None and is_uninitialized_parameter(self.weight):
self.in_channels = weight.size(-1)
self.weight.materialize((self.out_channels, self.in_channels))
if hasattr(self, '_hook'):
| {"golden_diff": "diff --git a/torch_geometric/nn/dense/linear.py b/torch_geometric/nn/dense/linear.py\n--- a/torch_geometric/nn/dense/linear.py\n+++ b/torch_geometric/nn/dense/linear.py\n@@ -137,15 +137,16 @@\n def _lazy_load_hook(self, state_dict, prefix, local_metadata, strict,\n missing_keys, unexpected_keys, error_msgs):\n \n- weight = state_dict[prefix + 'weight']\n- if is_uninitialized_parameter(weight):\n+ weight = state_dict.get(prefix + 'weight', None)\n+\n+ if weight is not None and is_uninitialized_parameter(weight):\n self.in_channels = -1\n self.weight = nn.parameter.UninitializedParameter()\n if not hasattr(self, '_hook'):\n self._hook = self.register_forward_pre_hook(\n self.initialize_parameters)\n \n- elif is_uninitialized_parameter(self.weight):\n+ elif weight is not None and is_uninitialized_parameter(self.weight):\n self.in_channels = weight.size(-1)\n self.weight.materialize((self.out_channels, self.in_channels))\n if hasattr(self, '_hook'):\n", "issue": "New attribute `self._load_hook` in linear class since 2.03 will raise KeyError when executing `load_state_dict` fucntion\n### \ud83d\udc1b Describe the bug\r\n\r\nIn Pytorch, the function `load_state_dict(state_dict, strict)` allows empty dict `state_dict=={}` when `strict` is False. \r\nHowever, from version 2.03 the linear class in `torch_geometric.nn.dense.linear.py` has a new attribute `self._load_hook`, and when we execute `Linear(xxxx).load_state_dict({}, strict=False)`, the linear class will execute the `self._lazy_load_hook` function as follows\r\n```\r\n def _lazy_load_hook(self, state_dict, prefix, local_metadata, strict,\r\n missing_keys, unexpected_keys, error_msgs):\r\n\r\n weight = state_dict[prefix + 'weight']\r\n if is_uninitialized_parameter(weight):\r\n self.in_channels = -1\r\n self.weight = nn.parameter.UninitializedParameter()\r\n if not hasattr(self, '_hook'):\r\n self._hook = self.register_forward_pre_hook(\r\n self.initialize_parameters)\r\n\r\n elif is_uninitialized_parameter(self.weight):\r\n self.in_channels = weight.size(-1)\r\n self.weight.materialize((self.out_channels, self.in_channels))\r\n if hasattr(self, '_hook'):\r\n self._hook.remove()\r\n delattr(self, '_hook')\r\n```\r\nSince the `state_dict` is empty, the line `weight = state_dict[prefix + 'weight']` will report KeyError. \r\n\r\n### Environment\r\n\r\n* PyG version:\r\n* PyTorch version:\r\n* OS:\r\n* Python version:\r\n* CUDA/cuDNN version:\r\n* How you installed PyTorch and PyG (`conda`, `pip`, source):\r\n* Any other relevant information (*e.g.*, version of `torch-scatter`):\r\n\n", "before_files": [{"content": "import copy\nimport math\nfrom typing import Any, Optional\n\nimport torch\nimport torch.nn.functional as F\nfrom torch import Tensor, nn\nfrom torch.nn.parameter import Parameter\n\nfrom torch_geometric.nn import inits\n\n\ndef is_uninitialized_parameter(x: Any) -> bool:\n if not hasattr(nn.parameter, 'UninitializedParameter'):\n return False\n return isinstance(x, nn.parameter.UninitializedParameter)\n\n\nclass Linear(torch.nn.Module):\n r\"\"\"Applies a linear tranformation to the incoming data\n\n .. math::\n \\mathbf{x}^{\\prime} = \\mathbf{x} \\mathbf{W}^{\\top} + \\mathbf{b}\n\n similar to :class:`torch.nn.Linear`.\n It supports lazy initialization and customizable weight and bias\n initialization.\n\n Args:\n in_channels (int): Size of each input sample. Will be initialized\n lazily in case it is given as :obj:`-1`.\n out_channels (int): Size of each output sample.\n bias (bool, optional): If set to :obj:`False`, the layer will not learn\n an additive bias. (default: :obj:`True`)\n weight_initializer (str, optional): The initializer for the weight\n matrix (:obj:`\"glorot\"`, :obj:`\"uniform\"`, :obj:`\"kaiming_uniform\"`\n or :obj:`None`).\n If set to :obj:`None`, will match default weight initialization of\n :class:`torch.nn.Linear`. (default: :obj:`None`)\n bias_initializer (str, optional): The initializer for the bias vector\n (:obj:`\"zeros\"` or :obj:`None`).\n If set to :obj:`None`, will match default bias initialization of\n :class:`torch.nn.Linear`. (default: :obj:`None`)\n\n Shapes:\n - **input:** features :math:`(*, F_{in})`\n - **output:** features :math:`(*, F_{out})`\n \"\"\"\n def __init__(self, in_channels: int, out_channels: int, bias: bool = True,\n weight_initializer: Optional[str] = None,\n bias_initializer: Optional[str] = None):\n super().__init__()\n self.in_channels = in_channels\n self.out_channels = out_channels\n self.weight_initializer = weight_initializer\n self.bias_initializer = bias_initializer\n\n if in_channels > 0:\n self.weight = Parameter(torch.Tensor(out_channels, in_channels))\n else:\n self.weight = nn.parameter.UninitializedParameter()\n self._hook = self.register_forward_pre_hook(\n self.initialize_parameters)\n\n if bias:\n self.bias = Parameter(torch.Tensor(out_channels))\n else:\n self.register_parameter('bias', None)\n\n self._load_hook = self._register_load_state_dict_pre_hook(\n self._lazy_load_hook)\n\n self.reset_parameters()\n\n def __deepcopy__(self, memo):\n out = Linear(self.in_channels, self.out_channels, self.bias\n is not None, self.weight_initializer,\n self.bias_initializer)\n if self.in_channels > 0:\n out.weight = copy.deepcopy(self.weight, memo)\n if self.bias is not None:\n out.bias = copy.deepcopy(self.bias, memo)\n return out\n\n def reset_parameters(self):\n if self.in_channels <= 0:\n pass\n elif self.weight_initializer == 'glorot':\n inits.glorot(self.weight)\n elif self.weight_initializer == 'uniform':\n bound = 1.0 / math.sqrt(self.weight.size(-1))\n torch.nn.init.uniform_(self.weight.data, -bound, bound)\n elif self.weight_initializer == 'kaiming_uniform':\n inits.kaiming_uniform(self.weight, fan=self.in_channels,\n a=math.sqrt(5))\n elif self.weight_initializer is None:\n inits.kaiming_uniform(self.weight, fan=self.in_channels,\n a=math.sqrt(5))\n else:\n raise RuntimeError(f\"Linear layer weight initializer \"\n f\"'{self.weight_initializer}' is not supported\")\n\n if self.bias is None or self.in_channels <= 0:\n pass\n elif self.bias_initializer == 'zeros':\n inits.zeros(self.bias)\n elif self.bias_initializer is None:\n inits.uniform(self.in_channels, self.bias)\n else:\n raise RuntimeError(f\"Linear layer bias initializer \"\n f\"'{self.bias_initializer}' is not supported\")\n\n def forward(self, x: Tensor) -> Tensor:\n r\"\"\"\n Args:\n x (Tensor): The features.\n \"\"\"\n return F.linear(x, self.weight, self.bias)\n\n @torch.no_grad()\n def initialize_parameters(self, module, input):\n if is_uninitialized_parameter(self.weight):\n self.in_channels = input[0].size(-1)\n self.weight.materialize((self.out_channels, self.in_channels))\n self.reset_parameters()\n self._hook.remove()\n delattr(self, '_hook')\n\n def _save_to_state_dict(self, destination, prefix, keep_vars):\n if is_uninitialized_parameter(self.weight):\n destination[prefix + 'weight'] = self.weight\n else:\n destination[prefix + 'weight'] = self.weight.detach()\n if self.bias is not None:\n destination[prefix + 'bias'] = self.bias.detach()\n\n def _lazy_load_hook(self, state_dict, prefix, local_metadata, strict,\n missing_keys, unexpected_keys, error_msgs):\n\n weight = state_dict[prefix + 'weight']\n if is_uninitialized_parameter(weight):\n self.in_channels = -1\n self.weight = nn.parameter.UninitializedParameter()\n if not hasattr(self, '_hook'):\n self._hook = self.register_forward_pre_hook(\n self.initialize_parameters)\n\n elif is_uninitialized_parameter(self.weight):\n self.in_channels = weight.size(-1)\n self.weight.materialize((self.out_channels, self.in_channels))\n if hasattr(self, '_hook'):\n self._hook.remove()\n delattr(self, '_hook')\n\n def __repr__(self) -> str:\n return (f'{self.__class__.__name__}({self.in_channels}, '\n f'{self.out_channels}, bias={self.bias is not None})')\n\n\nclass HeteroLinear(torch.nn.Module):\n r\"\"\"Applies separate linear tranformations to the incoming data according\n to types\n\n .. math::\n \\mathbf{x}^{\\prime}_{\\kappa} = \\mathbf{x}_{\\kappa}\n \\mathbf{W}^{\\top}_{\\kappa} + \\mathbf{b}_{\\kappa}\n\n for type :math:`\\kappa`.\n It supports lazy initialization and customizable weight and bias\n initialization.\n\n Args:\n in_channels (int): Size of each input sample. Will be initialized\n lazily in case it is given as :obj:`-1`.\n out_channels (int): Size of each output sample.\n num_types (int): The number of types.\n **kwargs (optional): Additional arguments of\n :class:`torch_geometric.nn.Linear`.\n\n Shapes:\n - **input:**\n features :math:`(*, F_{in})`,\n type vector :math:`(*)`\n - **output:** features :math:`(*, F_{out})`\n \"\"\"\n def __init__(self, in_channels: int, out_channels: int, num_types: int,\n **kwargs):\n super().__init__()\n\n self.in_channels = in_channels\n self.out_channels = out_channels\n\n self.lins = torch.nn.ModuleList([\n Linear(in_channels, out_channels, **kwargs)\n for _ in range(num_types)\n ])\n\n self.reset_parameters()\n\n def reset_parameters(self):\n for lin in self.lins:\n lin.reset_parameters()\n\n def forward(self, x: Tensor, type_vec: Tensor) -> Tensor:\n r\"\"\"\n Args:\n x (Tensor): The input features.\n type_vec (LongTensor): A vector that maps each entry to a type.\n \"\"\"\n out = x.new_empty(x.size(0), self.out_channels)\n for i, lin in enumerate(self.lins):\n mask = type_vec == i\n out[mask] = lin(x[mask])\n return out\n\n def __repr__(self) -> str:\n return (f'{self.__class__.__name__}({self.in_channels}, '\n f'{self.out_channels}, bias={self.lins[0].bias is not None})')\n", "path": "torch_geometric/nn/dense/linear.py"}]} | 3,300 | 252 |
gh_patches_debug_4328 | rasdani/github-patches | git_diff | pytorch__TensorRT-2311 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Upstream Dynamo Backend to Torch
- Add a hook in the Torch repo to secure the namespace `"tensorrt"` and have it point to `"torch_tensorrt"`
- Add necessary imports and skipped tests
- Raise a PR in Torch to add this functionality
</issue>
<code>
[start of py/torch_tensorrt/dynamo/backend/backends.py]
1 from __future__ import annotations
2
3 import logging
4 from functools import partial
5 from typing import Any, Callable, Sequence
6
7 import torch
8 import torch._dynamo as td
9 from torch._functorch.aot_autograd import aot_module_simplified, make_boxed_compiler
10 from torch_tensorrt.dynamo import CompilationSettings
11 from torch_tensorrt.dynamo.compile import compile_module
12 from torch_tensorrt.dynamo.lowering._decompositions import get_decompositions
13 from torch_tensorrt.dynamo.lowering._pre_aot_lowering import pre_aot_substitutions
14 from torch_tensorrt.dynamo.utils import parse_dynamo_kwargs
15
16 logger = logging.getLogger(__name__)
17
18
19 @td.register_backend(name="torch_tensorrt") # type: ignore[misc]
20 def torch_tensorrt_backend(
21 gm: torch.fx.GraphModule, sample_inputs: Sequence[torch.Tensor], **kwargs: Any
22 ) -> torch.nn.Module:
23 # Set log level at the top of compilation (torch_tensorrt.dynamo)
24 if (
25 (
26 "options" in kwargs
27 and "debug" in kwargs["options"]
28 and kwargs["options"]["debug"]
29 )
30 or ("debug" in kwargs and kwargs["debug"])
31 ) and logger.parent:
32 logger.parent.setLevel(logging.DEBUG)
33
34 DEFAULT_BACKEND = aot_torch_tensorrt_aten_backend
35
36 compiled_mod: torch.nn.Module = DEFAULT_BACKEND(gm, sample_inputs, **kwargs)
37 return compiled_mod
38
39
40 @td.register_backend(name="aot_torch_tensorrt_aten") # type: ignore[misc]
41 def aot_torch_tensorrt_aten_backend(
42 gm: torch.fx.GraphModule, sample_inputs: Sequence[torch.Tensor], **kwargs: Any
43 ) -> torch.nn.Module:
44 settings = parse_dynamo_kwargs(kwargs)
45
46 custom_backend = partial(
47 _pretraced_backend,
48 settings=settings,
49 )
50
51 # Perform Pre-AOT Lowering for Module-Level Replacement
52 gm = pre_aot_substitutions(gm)
53
54 # Invoke AOTAutograd to translate operators to aten
55 return aot_module_simplified(
56 gm,
57 sample_inputs,
58 fw_compiler=make_boxed_compiler(custom_backend),
59 decompositions=get_decompositions(settings.enable_experimental_decompositions),
60 )
61
62
63 def _pretraced_backend(
64 gm: torch.fx.GraphModule,
65 sample_inputs: Sequence[torch.Tensor],
66 settings: CompilationSettings = CompilationSettings(),
67 ) -> torch.fx.GraphModule | Callable[..., Any]:
68 """Helper function to manage translation of traced FX module to TRT engines
69
70 Args:
71 module: FX GraphModule to convert
72 inputs: Inputs to the module
73 settings: Compilation settings
74 Returns:
75 Compiled FX GraphModule
76 """
77 try:
78 logger.debug("Post-AOT Autograd graph:\n" + str(gm.graph))
79
80 trt_compiled = compile_module(
81 gm,
82 sample_inputs,
83 settings=settings,
84 )
85 return trt_compiled
86 except AssertionError:
87 if not settings.pass_through_build_failures:
88 logger.warning(
89 "TRT conversion failed on the subgraph. See trace above. "
90 + "Returning GraphModule forward instead.",
91 exc_info=True,
92 )
93 return gm.forward
94 else:
95 logger.critical(
96 "Halting compilation on build failure since "
97 + "pass_through_build_failures was specified as True. "
98 + "To return the default Torch implementation and avoid "
99 + "halting compilation on engine build failures, "
100 + "specify pass_through_build_failures=False."
101 )
102 raise
103
[end of py/torch_tensorrt/dynamo/backend/backends.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/py/torch_tensorrt/dynamo/backend/backends.py b/py/torch_tensorrt/dynamo/backend/backends.py
--- a/py/torch_tensorrt/dynamo/backend/backends.py
+++ b/py/torch_tensorrt/dynamo/backend/backends.py
@@ -16,6 +16,7 @@
logger = logging.getLogger(__name__)
[email protected]_backend(name="tensorrt") # type: ignore[misc]
@td.register_backend(name="torch_tensorrt") # type: ignore[misc]
def torch_tensorrt_backend(
gm: torch.fx.GraphModule, sample_inputs: Sequence[torch.Tensor], **kwargs: Any
| {"golden_diff": "diff --git a/py/torch_tensorrt/dynamo/backend/backends.py b/py/torch_tensorrt/dynamo/backend/backends.py\n--- a/py/torch_tensorrt/dynamo/backend/backends.py\n+++ b/py/torch_tensorrt/dynamo/backend/backends.py\n@@ -16,6 +16,7 @@\n logger = logging.getLogger(__name__)\n \n \[email protected]_backend(name=\"tensorrt\") # type: ignore[misc]\n @td.register_backend(name=\"torch_tensorrt\") # type: ignore[misc]\n def torch_tensorrt_backend(\n gm: torch.fx.GraphModule, sample_inputs: Sequence[torch.Tensor], **kwargs: Any\n", "issue": "Upstream Dynamo Backend to Torch\n- Add a hook in the Torch repo to secure the namespace `\"tensorrt\"` and have it point to `\"torch_tensorrt\"`\r\n- Add necessary imports and skipped tests\r\n- Raise a PR in Torch to add this functionality\n", "before_files": [{"content": "from __future__ import annotations\n\nimport logging\nfrom functools import partial\nfrom typing import Any, Callable, Sequence\n\nimport torch\nimport torch._dynamo as td\nfrom torch._functorch.aot_autograd import aot_module_simplified, make_boxed_compiler\nfrom torch_tensorrt.dynamo import CompilationSettings\nfrom torch_tensorrt.dynamo.compile import compile_module\nfrom torch_tensorrt.dynamo.lowering._decompositions import get_decompositions\nfrom torch_tensorrt.dynamo.lowering._pre_aot_lowering import pre_aot_substitutions\nfrom torch_tensorrt.dynamo.utils import parse_dynamo_kwargs\n\nlogger = logging.getLogger(__name__)\n\n\[email protected]_backend(name=\"torch_tensorrt\") # type: ignore[misc]\ndef torch_tensorrt_backend(\n gm: torch.fx.GraphModule, sample_inputs: Sequence[torch.Tensor], **kwargs: Any\n) -> torch.nn.Module:\n # Set log level at the top of compilation (torch_tensorrt.dynamo)\n if (\n (\n \"options\" in kwargs\n and \"debug\" in kwargs[\"options\"]\n and kwargs[\"options\"][\"debug\"]\n )\n or (\"debug\" in kwargs and kwargs[\"debug\"])\n ) and logger.parent:\n logger.parent.setLevel(logging.DEBUG)\n\n DEFAULT_BACKEND = aot_torch_tensorrt_aten_backend\n\n compiled_mod: torch.nn.Module = DEFAULT_BACKEND(gm, sample_inputs, **kwargs)\n return compiled_mod\n\n\[email protected]_backend(name=\"aot_torch_tensorrt_aten\") # type: ignore[misc]\ndef aot_torch_tensorrt_aten_backend(\n gm: torch.fx.GraphModule, sample_inputs: Sequence[torch.Tensor], **kwargs: Any\n) -> torch.nn.Module:\n settings = parse_dynamo_kwargs(kwargs)\n\n custom_backend = partial(\n _pretraced_backend,\n settings=settings,\n )\n\n # Perform Pre-AOT Lowering for Module-Level Replacement\n gm = pre_aot_substitutions(gm)\n\n # Invoke AOTAutograd to translate operators to aten\n return aot_module_simplified(\n gm,\n sample_inputs,\n fw_compiler=make_boxed_compiler(custom_backend),\n decompositions=get_decompositions(settings.enable_experimental_decompositions),\n )\n\n\ndef _pretraced_backend(\n gm: torch.fx.GraphModule,\n sample_inputs: Sequence[torch.Tensor],\n settings: CompilationSettings = CompilationSettings(),\n) -> torch.fx.GraphModule | Callable[..., Any]:\n \"\"\"Helper function to manage translation of traced FX module to TRT engines\n\n Args:\n module: FX GraphModule to convert\n inputs: Inputs to the module\n settings: Compilation settings\n Returns:\n Compiled FX GraphModule\n \"\"\"\n try:\n logger.debug(\"Post-AOT Autograd graph:\\n\" + str(gm.graph))\n\n trt_compiled = compile_module(\n gm,\n sample_inputs,\n settings=settings,\n )\n return trt_compiled\n except AssertionError:\n if not settings.pass_through_build_failures:\n logger.warning(\n \"TRT conversion failed on the subgraph. See trace above. \"\n + \"Returning GraphModule forward instead.\",\n exc_info=True,\n )\n return gm.forward\n else:\n logger.critical(\n \"Halting compilation on build failure since \"\n + \"pass_through_build_failures was specified as True. \"\n + \"To return the default Torch implementation and avoid \"\n + \"halting compilation on engine build failures, \"\n + \"specify pass_through_build_failures=False.\"\n )\n raise\n", "path": "py/torch_tensorrt/dynamo/backend/backends.py"}]} | 1,563 | 139 |
gh_patches_debug_3116 | rasdani/github-patches | git_diff | rasterio__rasterio-490 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
rio merge error
When running `rio merge` on the latest version (`0.27`), I am receiving this error:
```
Traceback (most recent call last):
File "/Users/dnomadb/venv/bin/rio", line 11, in <module>
sys.exit(main_group())
File "/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py", line 700, in __call__
return self.main(*args, **kwargs)
File "/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py", line 680, in main
rv = self.invoke(ctx)
File "/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py", line 1027, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py", line 873, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py", line 508, in invoke
return callback(*args, **kwargs)
File "/Users/dnomadb/venv/lib/python2.7/site-packages/click/decorators.py", line 16, in new_func
return f(get_current_context(), *args, **kwargs)
File "/Users/dnomadb/venv/lib/python2.7/site-packages/rasterio/rio/merge.py", line 54, in merge
from rasterio.tools.merge import merge as merge_tool
ImportError: No module named tools.merge
```
When reverting back to `0.26`, I don't see it and the operation completes as expected.
cc @sgillies
</issue>
<code>
[start of setup.py]
1 #!/usr/bin/env python
2
3 # Two environmental variables influence this script.
4 #
5 # GDAL_CONFIG: the path to a gdal-config program that points to GDAL headers,
6 # libraries, and data files.
7 #
8 # PACKAGE_DATA: if defined, GDAL and PROJ4 data files will be copied into the
9 # source or binary distribution. This is essential when creating self-contained
10 # binary wheels.
11
12 import logging
13 import os
14 import pprint
15 import shutil
16 import subprocess
17 import sys
18
19 from setuptools import setup
20 from setuptools.extension import Extension
21
22 logging.basicConfig()
23 log = logging.getLogger()
24
25 # python -W all setup.py ...
26 if 'all' in sys.warnoptions:
27 log.level = logging.DEBUG
28
29 def check_output(cmd):
30 # since subprocess.check_output doesn't exist in 2.6
31 # we wrap it here.
32 try:
33 out = subprocess.check_output(cmd)
34 return out.decode('utf')
35 except AttributeError:
36 # For some reasone check_output doesn't exist
37 # So fall back on Popen
38 p = subprocess.Popen(cmd, stdout=subprocess.PIPE)
39 out, err = p.communicate()
40 return out
41
42 def copy_data_tree(datadir, destdir):
43 try:
44 shutil.rmtree(destdir)
45 except OSError:
46 pass
47 shutil.copytree(datadir, destdir)
48
49 # Parse the version from the rasterio module.
50 with open('rasterio/__init__.py') as f:
51 for line in f:
52 if line.find("__version__") >= 0:
53 version = line.split("=")[1].strip()
54 version = version.strip('"')
55 version = version.strip("'")
56 continue
57
58 with open('VERSION.txt', 'w') as f:
59 f.write(version)
60
61 # Use Cython if available.
62 try:
63 from Cython.Build import cythonize
64 except ImportError:
65 cythonize = None
66
67 # By default we'll try to get options via gdal-config. On systems without,
68 # options will need to be set in setup.cfg or on the setup command line.
69 include_dirs = []
70 library_dirs = []
71 libraries = []
72 extra_link_args = []
73 gdal_output = [None]*3
74
75 try:
76 import numpy
77 include_dirs.append(numpy.get_include())
78 except ImportError:
79 log.critical("Numpy and its headers are required to run setup(). Exiting.")
80 sys.exit(1)
81
82 try:
83 gdal_config = os.environ.get('GDAL_CONFIG', 'gdal-config')
84 for i, flag in enumerate(("--cflags", "--libs", "--datadir")):
85 gdal_output[i] = check_output([gdal_config, flag]).strip()
86
87 for item in gdal_output[0].split():
88 if item.startswith("-I"):
89 include_dirs.extend(item[2:].split(":"))
90 for item in gdal_output[1].split():
91 if item.startswith("-L"):
92 library_dirs.extend(item[2:].split(":"))
93 elif item.startswith("-l"):
94 libraries.append(item[2:])
95 else:
96 # e.g. -framework GDAL
97 extra_link_args.append(item)
98
99 except Exception as e:
100 if os.name == "nt":
101 log.info(("Building on Windows requires extra options to setup.py to locate needed GDAL files.\n"
102 "More information is available in the README."))
103 else:
104 log.warning("Failed to get options via gdal-config: %s", str(e))
105
106
107 # Conditionally copy the GDAL data. To be used in conjunction with
108 # the bdist_wheel command to make self-contained binary wheels.
109 if os.environ.get('PACKAGE_DATA'):
110 destdir = 'rasterio/gdal_data'
111 if gdal_output[2]:
112 log.info("Copying gdal data from %s" % gdal_output[2])
113 copy_data_tree(gdal_output[2], destdir)
114 else:
115 # check to see if GDAL_DATA is defined
116 gdal_data = os.environ.get('GDAL_DATA', None)
117 if gdal_data:
118 log.info("Copying gdal_data from %s" % gdal_data)
119 copy_data_tree(gdal_data, destdir)
120
121 # Conditionally copy PROJ.4 data.
122 projdatadir = os.environ.get('PROJ_LIB', '/usr/local/share/proj')
123 if os.path.exists(projdatadir):
124 log.info("Copying proj_data from %s" % projdatadir)
125 copy_data_tree(projdatadir, 'rasterio/proj_data')
126
127 ext_options = dict(
128 include_dirs=include_dirs,
129 library_dirs=library_dirs,
130 libraries=libraries,
131 extra_link_args=extra_link_args)
132
133 if not os.name == "nt":
134 # These options fail on Windows if using Visual Studio
135 ext_options['extra_compile_args'] = ['-Wno-unused-parameter',
136 '-Wno-unused-function']
137
138 log.debug('ext_options:\n%s', pprint.pformat(ext_options))
139
140 # When building from a repo, Cython is required.
141 if os.path.exists("MANIFEST.in") and "clean" not in sys.argv:
142 log.info("MANIFEST.in found, presume a repo, cythonizing...")
143 if not cythonize:
144 log.critical(
145 "Cython.Build.cythonize not found. "
146 "Cython is required to build from a repo.")
147 sys.exit(1)
148 ext_modules = cythonize([
149 Extension(
150 'rasterio._base', ['rasterio/_base.pyx'], **ext_options),
151 Extension(
152 'rasterio._io', ['rasterio/_io.pyx'], **ext_options),
153 Extension(
154 'rasterio._copy', ['rasterio/_copy.pyx'], **ext_options),
155 Extension(
156 'rasterio._features', ['rasterio/_features.pyx'], **ext_options),
157 Extension(
158 'rasterio._drivers', ['rasterio/_drivers.pyx'], **ext_options),
159 Extension(
160 'rasterio._warp', ['rasterio/_warp.pyx'], **ext_options),
161 Extension(
162 'rasterio._fill', ['rasterio/_fill.pyx', 'rasterio/rasterfill.cpp'], **ext_options),
163 Extension(
164 'rasterio._err', ['rasterio/_err.pyx'], **ext_options),
165 Extension(
166 'rasterio._example', ['rasterio/_example.pyx'], **ext_options),
167 ], quiet=True)
168
169 # If there's no manifest template, as in an sdist, we just specify .c files.
170 else:
171 ext_modules = [
172 Extension(
173 'rasterio._base', ['rasterio/_base.c'], **ext_options),
174 Extension(
175 'rasterio._io', ['rasterio/_io.c'], **ext_options),
176 Extension(
177 'rasterio._copy', ['rasterio/_copy.c'], **ext_options),
178 Extension(
179 'rasterio._features', ['rasterio/_features.c'], **ext_options),
180 Extension(
181 'rasterio._drivers', ['rasterio/_drivers.c'], **ext_options),
182 Extension(
183 'rasterio._warp', ['rasterio/_warp.cpp'], **ext_options),
184 Extension(
185 'rasterio._fill', ['rasterio/_fill.cpp', 'rasterio/rasterfill.cpp'], **ext_options),
186 Extension(
187 'rasterio._err', ['rasterio/_err.c'], **ext_options),
188 Extension(
189 'rasterio._example', ['rasterio/_example.c'], **ext_options),
190 ]
191
192 with open('README.rst') as f:
193 readme = f.read()
194
195 # Runtime requirements.
196 inst_reqs = [
197 'affine>=1.0',
198 'cligj>=0.2.0',
199 'Numpy>=1.7',
200 'snuggs>=1.3.1',
201 'click-plugins']
202
203 if sys.version_info < (3, 4):
204 inst_reqs.append('enum34')
205
206 setup_args = dict(
207 name='rasterio',
208 version=version,
209 description="Fast and direct raster I/O for use with Numpy and SciPy",
210 long_description=readme,
211 classifiers=[
212 'Development Status :: 4 - Beta',
213 'Intended Audience :: Developers',
214 'Intended Audience :: Information Technology',
215 'Intended Audience :: Science/Research',
216 'License :: OSI Approved :: BSD License',
217 'Programming Language :: C',
218 'Programming Language :: Python :: 2.6',
219 'Programming Language :: Python :: 2.7',
220 'Programming Language :: Python :: 3.3',
221 'Programming Language :: Python :: 3.4',
222 'Topic :: Multimedia :: Graphics :: Graphics Conversion',
223 'Topic :: Scientific/Engineering :: GIS'],
224 keywords='raster gdal',
225 author='Sean Gillies',
226 author_email='[email protected]',
227 url='https://github.com/mapbox/rasterio',
228 license='BSD',
229 package_dir={'': '.'},
230 packages=['rasterio', 'rasterio.rio'],
231 entry_points='''
232 [console_scripts]
233 rio=rasterio.rio.main:main_group
234
235 [rasterio.rio_commands]
236 bounds=rasterio.rio.features:bounds
237 calc=rasterio.rio.calc:calc
238 clip=rasterio.rio.convert:clip
239 convert=rasterio.rio.convert:convert
240 edit-info=rasterio.rio.info:edit
241 env=rasterio.rio.info:env
242 info=rasterio.rio.info:info
243 insp=rasterio.rio.info:insp
244 mask=rasterio.rio.features:mask
245 merge=rasterio.rio.merge:merge
246 overview=rasterio.rio.overview:overview
247 rasterize=rasterio.rio.features:rasterize
248 sample=rasterio.rio.sample:sample
249 shapes=rasterio.rio.features:shapes
250 stack=rasterio.rio.bands:stack
251 warp=rasterio.rio.warp:warp
252 transform=rasterio.rio.info:transform
253 ''',
254 include_package_data=True,
255 ext_modules=ext_modules,
256 zip_safe=False,
257 install_requires=inst_reqs,
258 extras_require={
259 'ipython': ['ipython>=2.0']})
260
261 if os.environ.get('PACKAGE_DATA'):
262 setup_args['package_data'] = {'rasterio': ['gdal_data/*', 'proj_data/*']}
263
264 setup(**setup_args)
265
[end of setup.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/setup.py b/setup.py
--- a/setup.py
+++ b/setup.py
@@ -227,7 +227,7 @@
url='https://github.com/mapbox/rasterio',
license='BSD',
package_dir={'': '.'},
- packages=['rasterio', 'rasterio.rio'],
+ packages=['rasterio', 'rasterio.rio', 'rasterio.tools'],
entry_points='''
[console_scripts]
rio=rasterio.rio.main:main_group
| {"golden_diff": "diff --git a/setup.py b/setup.py\n--- a/setup.py\n+++ b/setup.py\n@@ -227,7 +227,7 @@\n url='https://github.com/mapbox/rasterio',\n license='BSD',\n package_dir={'': '.'},\n- packages=['rasterio', 'rasterio.rio'],\n+ packages=['rasterio', 'rasterio.rio', 'rasterio.tools'],\n entry_points='''\n [console_scripts]\n rio=rasterio.rio.main:main_group\n", "issue": "rio merge error\nWhen running `rio merge` on the latest version (`0.27`), I am receiving this error:\n\n```\nTraceback (most recent call last):\n File \"/Users/dnomadb/venv/bin/rio\", line 11, in <module>\n sys.exit(main_group())\n File \"/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py\", line 700, in __call__\n return self.main(*args, **kwargs)\n File \"/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py\", line 680, in main\n rv = self.invoke(ctx)\n File \"/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py\", line 1027, in invoke\n return _process_result(sub_ctx.command.invoke(sub_ctx))\n File \"/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py\", line 873, in invoke\n return ctx.invoke(self.callback, **ctx.params)\n File \"/Users/dnomadb/venv/lib/python2.7/site-packages/click/core.py\", line 508, in invoke\n return callback(*args, **kwargs)\n File \"/Users/dnomadb/venv/lib/python2.7/site-packages/click/decorators.py\", line 16, in new_func\n return f(get_current_context(), *args, **kwargs)\n File \"/Users/dnomadb/venv/lib/python2.7/site-packages/rasterio/rio/merge.py\", line 54, in merge\n from rasterio.tools.merge import merge as merge_tool\nImportError: No module named tools.merge\n```\n\nWhen reverting back to `0.26`, I don't see it and the operation completes as expected.\n\ncc @sgillies \n\n", "before_files": [{"content": "#!/usr/bin/env python\n\n# Two environmental variables influence this script.\n#\n# GDAL_CONFIG: the path to a gdal-config program that points to GDAL headers,\n# libraries, and data files.\n#\n# PACKAGE_DATA: if defined, GDAL and PROJ4 data files will be copied into the\n# source or binary distribution. This is essential when creating self-contained\n# binary wheels.\n\nimport logging\nimport os\nimport pprint\nimport shutil\nimport subprocess\nimport sys\n\nfrom setuptools import setup\nfrom setuptools.extension import Extension\n\nlogging.basicConfig()\nlog = logging.getLogger()\n\n# python -W all setup.py ...\nif 'all' in sys.warnoptions:\n log.level = logging.DEBUG\n\ndef check_output(cmd):\n # since subprocess.check_output doesn't exist in 2.6\n # we wrap it here.\n try:\n out = subprocess.check_output(cmd)\n return out.decode('utf')\n except AttributeError:\n # For some reasone check_output doesn't exist\n # So fall back on Popen\n p = subprocess.Popen(cmd, stdout=subprocess.PIPE)\n out, err = p.communicate()\n return out\n\ndef copy_data_tree(datadir, destdir):\n try:\n shutil.rmtree(destdir)\n except OSError:\n pass\n shutil.copytree(datadir, destdir)\n\n# Parse the version from the rasterio module.\nwith open('rasterio/__init__.py') as f:\n for line in f:\n if line.find(\"__version__\") >= 0:\n version = line.split(\"=\")[1].strip()\n version = version.strip('\"')\n version = version.strip(\"'\")\n continue\n\nwith open('VERSION.txt', 'w') as f:\n f.write(version)\n\n# Use Cython if available.\ntry:\n from Cython.Build import cythonize\nexcept ImportError:\n cythonize = None\n\n# By default we'll try to get options via gdal-config. On systems without,\n# options will need to be set in setup.cfg or on the setup command line.\ninclude_dirs = []\nlibrary_dirs = []\nlibraries = []\nextra_link_args = []\ngdal_output = [None]*3\n\ntry:\n import numpy\n include_dirs.append(numpy.get_include())\nexcept ImportError:\n log.critical(\"Numpy and its headers are required to run setup(). Exiting.\")\n sys.exit(1)\n\ntry:\n gdal_config = os.environ.get('GDAL_CONFIG', 'gdal-config')\n for i, flag in enumerate((\"--cflags\", \"--libs\", \"--datadir\")):\n gdal_output[i] = check_output([gdal_config, flag]).strip()\n\n for item in gdal_output[0].split():\n if item.startswith(\"-I\"):\n include_dirs.extend(item[2:].split(\":\"))\n for item in gdal_output[1].split():\n if item.startswith(\"-L\"):\n library_dirs.extend(item[2:].split(\":\"))\n elif item.startswith(\"-l\"):\n libraries.append(item[2:])\n else:\n # e.g. -framework GDAL\n extra_link_args.append(item)\n\nexcept Exception as e:\n if os.name == \"nt\":\n log.info((\"Building on Windows requires extra options to setup.py to locate needed GDAL files.\\n\"\n \"More information is available in the README.\"))\n else:\n log.warning(\"Failed to get options via gdal-config: %s\", str(e))\n\n\n# Conditionally copy the GDAL data. To be used in conjunction with\n# the bdist_wheel command to make self-contained binary wheels.\nif os.environ.get('PACKAGE_DATA'):\n destdir = 'rasterio/gdal_data'\n if gdal_output[2]:\n log.info(\"Copying gdal data from %s\" % gdal_output[2])\n copy_data_tree(gdal_output[2], destdir)\n else:\n # check to see if GDAL_DATA is defined\n gdal_data = os.environ.get('GDAL_DATA', None)\n if gdal_data:\n log.info(\"Copying gdal_data from %s\" % gdal_data)\n copy_data_tree(gdal_data, destdir)\n\n # Conditionally copy PROJ.4 data.\n projdatadir = os.environ.get('PROJ_LIB', '/usr/local/share/proj')\n if os.path.exists(projdatadir):\n log.info(\"Copying proj_data from %s\" % projdatadir)\n copy_data_tree(projdatadir, 'rasterio/proj_data')\n\next_options = dict(\n include_dirs=include_dirs,\n library_dirs=library_dirs,\n libraries=libraries,\n extra_link_args=extra_link_args)\n\nif not os.name == \"nt\":\n # These options fail on Windows if using Visual Studio\n ext_options['extra_compile_args'] = ['-Wno-unused-parameter',\n '-Wno-unused-function']\n\nlog.debug('ext_options:\\n%s', pprint.pformat(ext_options))\n\n# When building from a repo, Cython is required.\nif os.path.exists(\"MANIFEST.in\") and \"clean\" not in sys.argv:\n log.info(\"MANIFEST.in found, presume a repo, cythonizing...\")\n if not cythonize:\n log.critical(\n \"Cython.Build.cythonize not found. \"\n \"Cython is required to build from a repo.\")\n sys.exit(1)\n ext_modules = cythonize([\n Extension(\n 'rasterio._base', ['rasterio/_base.pyx'], **ext_options),\n Extension(\n 'rasterio._io', ['rasterio/_io.pyx'], **ext_options),\n Extension(\n 'rasterio._copy', ['rasterio/_copy.pyx'], **ext_options),\n Extension(\n 'rasterio._features', ['rasterio/_features.pyx'], **ext_options),\n Extension(\n 'rasterio._drivers', ['rasterio/_drivers.pyx'], **ext_options),\n Extension(\n 'rasterio._warp', ['rasterio/_warp.pyx'], **ext_options),\n Extension(\n 'rasterio._fill', ['rasterio/_fill.pyx', 'rasterio/rasterfill.cpp'], **ext_options),\n Extension(\n 'rasterio._err', ['rasterio/_err.pyx'], **ext_options),\n Extension(\n 'rasterio._example', ['rasterio/_example.pyx'], **ext_options),\n ], quiet=True)\n\n# If there's no manifest template, as in an sdist, we just specify .c files.\nelse:\n ext_modules = [\n Extension(\n 'rasterio._base', ['rasterio/_base.c'], **ext_options),\n Extension(\n 'rasterio._io', ['rasterio/_io.c'], **ext_options),\n Extension(\n 'rasterio._copy', ['rasterio/_copy.c'], **ext_options),\n Extension(\n 'rasterio._features', ['rasterio/_features.c'], **ext_options),\n Extension(\n 'rasterio._drivers', ['rasterio/_drivers.c'], **ext_options),\n Extension(\n 'rasterio._warp', ['rasterio/_warp.cpp'], **ext_options),\n Extension(\n 'rasterio._fill', ['rasterio/_fill.cpp', 'rasterio/rasterfill.cpp'], **ext_options),\n Extension(\n 'rasterio._err', ['rasterio/_err.c'], **ext_options),\n Extension(\n 'rasterio._example', ['rasterio/_example.c'], **ext_options),\n ]\n\nwith open('README.rst') as f:\n readme = f.read()\n\n# Runtime requirements.\ninst_reqs = [\n 'affine>=1.0',\n 'cligj>=0.2.0',\n 'Numpy>=1.7',\n 'snuggs>=1.3.1',\n 'click-plugins']\n\nif sys.version_info < (3, 4):\n inst_reqs.append('enum34')\n\nsetup_args = dict(\n name='rasterio',\n version=version,\n description=\"Fast and direct raster I/O for use with Numpy and SciPy\",\n long_description=readme,\n classifiers=[\n 'Development Status :: 4 - Beta',\n 'Intended Audience :: Developers',\n 'Intended Audience :: Information Technology',\n 'Intended Audience :: Science/Research',\n 'License :: OSI Approved :: BSD License',\n 'Programming Language :: C',\n 'Programming Language :: Python :: 2.6',\n 'Programming Language :: Python :: 2.7',\n 'Programming Language :: Python :: 3.3',\n 'Programming Language :: Python :: 3.4',\n 'Topic :: Multimedia :: Graphics :: Graphics Conversion',\n 'Topic :: Scientific/Engineering :: GIS'],\n keywords='raster gdal',\n author='Sean Gillies',\n author_email='[email protected]',\n url='https://github.com/mapbox/rasterio',\n license='BSD',\n package_dir={'': '.'},\n packages=['rasterio', 'rasterio.rio'],\n entry_points='''\n [console_scripts]\n rio=rasterio.rio.main:main_group\n\n [rasterio.rio_commands]\n bounds=rasterio.rio.features:bounds\n calc=rasterio.rio.calc:calc\n clip=rasterio.rio.convert:clip\n convert=rasterio.rio.convert:convert\n edit-info=rasterio.rio.info:edit\n env=rasterio.rio.info:env\n info=rasterio.rio.info:info\n insp=rasterio.rio.info:insp\n mask=rasterio.rio.features:mask\n merge=rasterio.rio.merge:merge\n overview=rasterio.rio.overview:overview\n rasterize=rasterio.rio.features:rasterize\n sample=rasterio.rio.sample:sample\n shapes=rasterio.rio.features:shapes\n stack=rasterio.rio.bands:stack\n warp=rasterio.rio.warp:warp\n transform=rasterio.rio.info:transform\n ''',\n include_package_data=True,\n ext_modules=ext_modules,\n zip_safe=False,\n install_requires=inst_reqs,\n extras_require={\n 'ipython': ['ipython>=2.0']})\n\nif os.environ.get('PACKAGE_DATA'):\n setup_args['package_data'] = {'rasterio': ['gdal_data/*', 'proj_data/*']}\n\nsetup(**setup_args)\n", "path": "setup.py"}]} | 3,894 | 117 |
gh_patches_debug_32299 | rasdani/github-patches | git_diff | spack__spack-32550 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
spfft: inherit from ROCmPackage
Following https://github.com/spack/spack/pull/31207#issuecomment-1161932478 this PR adapts `spfft` the same way by inheriting from `ROCmPackage`.
Also for this one, I would ask one of the reviewer if they can test it works correctly.
</issue>
<code>
[start of var/spack/repos/builtin/packages/spfft/package.py]
1 # Copyright 2013-2022 Lawrence Livermore National Security, LLC and other
2 # Spack Project Developers. See the top-level COPYRIGHT file for details.
3 #
4 # SPDX-License-Identifier: (Apache-2.0 OR MIT)
5
6
7 from spack.package import *
8
9
10 class Spfft(CMakePackage, CudaPackage):
11 """Sparse 3D FFT library with MPI, OpenMP, CUDA and ROCm support."""
12
13 homepage = "https://github.com/eth-cscs/SpFFT"
14 url = "https://github.com/eth-cscs/SpFFT/archive/v0.9.8.zip"
15 git = "https://github.com/eth-cscs/SpFFT.git"
16
17 maintainers = ["AdhocMan", "haampie"]
18
19 version("develop", branch="develop")
20 version("master", branch="master")
21
22 version("1.0.6", sha256="e1b927c61f8abbb4a9937653f917169e6253e8c40b850df491594310943ca14b")
23 version("1.0.5", sha256="2a59d856286ea8559f00a32fc38f9f7546209cfa90112232a5288a69689a6e05")
24 version("1.0.4", sha256="41e63880d95343da0d8c3dbe5bfb3d46a1d612199cc9cc13a936f1628a7fdb8e")
25 version("1.0.3", sha256="4f87734e3582ef96ddc0402d0db78cfc173bed9cab3e0d9c6a6bf8b660d69559")
26 version("1.0.2", sha256="9b1296bda0b9ec3d37c74fd64354a01ebc6e2da7cb026c1f821882160b03c692")
27 version("1.0.1", sha256="f8ab706309776cfbd2bfd8e29a6a9ffb5c8f3cd62399bf82db1e416ae5c490c8")
28 version("1.0.0", sha256="bd98897aa6734563ec63cd84168e731ef2e2bbc01a574c6dc59b74475742b6ee")
29 version("0.9.13", sha256="5ccc93c9362bec14cfb6e31dd0e7ae7e48db0453ab49ebc9722041b69db759ef")
30 version("0.9.12", sha256="1f7bf5164dcceb0e3bbce7d6ff9faef3145ad17cf3430149d40a98c43c010acc")
31 version("0.9.11", sha256="36542a60378e8672654188dee006975ef9e10f502791459ff7ebf4b38451cb9b")
32 version("0.9.10", sha256="9cbbb7ba5e53e17eeb45e809841d8272e5333f739c2442a99c3e255c1ddec3e9")
33 version("0.9.9", sha256="a8fd7a2d767716bb73185ca03bf4c106c6981b79130f3e456e5d2e744a2b3ba0")
34 version("0.9.8", sha256="f49fa51316bbfa68309e951d2375e1f6904120c93868cbe13bc2974c0b801a3f")
35
36 variant("openmp", default=True, description="Build with OpenMP support")
37 variant("mpi", default=True, description="enable MPI")
38 variant("single_precision", default=False, description="Sinlge precision")
39 variant("gpu_direct", default=False, description="GPU aware MPI")
40 variant("static", default=False, description="build static library")
41 variant("fortran", default=False, description="enable fortran")
42 variant(
43 "build_type",
44 default="Release",
45 description="CMake build type",
46 values=("Debug", "Release", "RelWithDebInfo"),
47 )
48 depends_on("fftw-api@3")
49 depends_on("mpi", when="+mpi")
50 depends_on("[email protected]:", type="build")
51
52 # ROCM variants + dependencies
53 variant("rocm", default=False, description="Use ROCm backend")
54
55 depends_on("cuda@:10", when="@:0.9.11 +cuda")
56
57 with when("+rocm"):
58 # FindHIP cmake script only works for < 4.1
59 depends_on("hip@:4.0", when="@:1.0.1")
60 # Workaround for compiler bug in ROCm 4.5 added in SpFFT 1.0.6
61 depends_on("hip@:4.3.1", when="@:1.0.5")
62 depends_on("hip")
63 depends_on("rocfft")
64 # rocFFT and hipFFT have split with latest versions
65 depends_on("hipfft", when="^[email protected]:")
66
67 amdgpu_targets = (
68 "gfx701",
69 "gfx801",
70 "gfx802",
71 "gfx803",
72 "gfx900",
73 "gfx906",
74 "gfx908",
75 "gfx1010",
76 "gfx1011",
77 "gfx1012",
78 )
79 variant("amdgpu_target", default="gfx803,gfx900,gfx906", multi=True, values=amdgpu_targets)
80
81 # Fix compilation error in some cases due to missing include statement
82 # before version 1.0.3
83 patch("0001-fix-missing-limits-include.patch", when="@:1.0.2")
84
85 def cmake_args(self):
86 spec = self.spec
87 args = [
88 self.define_from_variant("SPFFT_OMP", "openmp"),
89 self.define_from_variant("SPFFT_MPI", "mpi"),
90 self.define_from_variant("SPFFT_SINGLE_PRECISION", "single_precision"),
91 self.define_from_variant("SPFFT_GPU_DIRECT", "gpu_direct"),
92 self.define_from_variant("SPFFT_FORTRAN", "fortran"),
93 self.define_from_variant("SPFFT_STATIC", "static"),
94 ]
95
96 if spec.satisfies("+cuda"):
97 args += ["-DSPFFT_GPU_BACKEND=CUDA"]
98
99 cuda_arch = self.spec.variants["cuda_arch"].value
100 if cuda_arch[0] != "none":
101 args += [self.define("CMAKE_CUDA_ARCHITECTURES", cuda_arch)]
102
103 if spec.satisfies("+rocm"):
104 archs = ",".join(self.spec.variants["amdgpu_target"].value)
105 args += [
106 "-DSPFFT_GPU_BACKEND=ROCM",
107 "-DHIP_ROOT_DIR={0}".format(spec["hip"].prefix),
108 "-DHIP_HCC_FLAGS=--amdgpu-target={0}".format(archs),
109 "-DHIP_CXX_COMPILER={0}".format(self.spec["hip"].hipcc),
110 ]
111
112 if "fftw" in spec:
113 args += ["-DSPFFT_FFTW_LIB=FFTW"]
114 elif "intel-mkl" in spec:
115 args += ["-DSPFFT_FFTW_LIB=MKL"]
116
117 return args
118
[end of var/spack/repos/builtin/packages/spfft/package.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/var/spack/repos/builtin/packages/spfft/package.py b/var/spack/repos/builtin/packages/spfft/package.py
--- a/var/spack/repos/builtin/packages/spfft/package.py
+++ b/var/spack/repos/builtin/packages/spfft/package.py
@@ -7,7 +7,7 @@
from spack.package import *
-class Spfft(CMakePackage, CudaPackage):
+class Spfft(CMakePackage, CudaPackage, ROCmPackage):
"""Sparse 3D FFT library with MPI, OpenMP, CUDA and ROCm support."""
homepage = "https://github.com/eth-cscs/SpFFT"
@@ -49,9 +49,6 @@
depends_on("mpi", when="+mpi")
depends_on("[email protected]:", type="build")
- # ROCM variants + dependencies
- variant("rocm", default=False, description="Use ROCm backend")
-
depends_on("cuda@:10", when="@:0.9.11 +cuda")
with when("+rocm"):
@@ -59,25 +56,10 @@
depends_on("hip@:4.0", when="@:1.0.1")
# Workaround for compiler bug in ROCm 4.5 added in SpFFT 1.0.6
depends_on("hip@:4.3.1", when="@:1.0.5")
- depends_on("hip")
depends_on("rocfft")
# rocFFT and hipFFT have split with latest versions
depends_on("hipfft", when="^[email protected]:")
- amdgpu_targets = (
- "gfx701",
- "gfx801",
- "gfx802",
- "gfx803",
- "gfx900",
- "gfx906",
- "gfx908",
- "gfx1010",
- "gfx1011",
- "gfx1012",
- )
- variant("amdgpu_target", default="gfx803,gfx900,gfx906", multi=True, values=amdgpu_targets)
-
# Fix compilation error in some cases due to missing include statement
# before version 1.0.3
patch("0001-fix-missing-limits-include.patch", when="@:1.0.2")
| {"golden_diff": "diff --git a/var/spack/repos/builtin/packages/spfft/package.py b/var/spack/repos/builtin/packages/spfft/package.py\n--- a/var/spack/repos/builtin/packages/spfft/package.py\n+++ b/var/spack/repos/builtin/packages/spfft/package.py\n@@ -7,7 +7,7 @@\n from spack.package import *\n \n \n-class Spfft(CMakePackage, CudaPackage):\n+class Spfft(CMakePackage, CudaPackage, ROCmPackage):\n \"\"\"Sparse 3D FFT library with MPI, OpenMP, CUDA and ROCm support.\"\"\"\n \n homepage = \"https://github.com/eth-cscs/SpFFT\"\n@@ -49,9 +49,6 @@\n depends_on(\"mpi\", when=\"+mpi\")\n depends_on(\"[email protected]:\", type=\"build\")\n \n- # ROCM variants + dependencies\n- variant(\"rocm\", default=False, description=\"Use ROCm backend\")\n-\n depends_on(\"cuda@:10\", when=\"@:0.9.11 +cuda\")\n \n with when(\"+rocm\"):\n@@ -59,25 +56,10 @@\n depends_on(\"hip@:4.0\", when=\"@:1.0.1\")\n # Workaround for compiler bug in ROCm 4.5 added in SpFFT 1.0.6\n depends_on(\"hip@:4.3.1\", when=\"@:1.0.5\")\n- depends_on(\"hip\")\n depends_on(\"rocfft\")\n # rocFFT and hipFFT have split with latest versions\n depends_on(\"hipfft\", when=\"^[email protected]:\")\n \n- amdgpu_targets = (\n- \"gfx701\",\n- \"gfx801\",\n- \"gfx802\",\n- \"gfx803\",\n- \"gfx900\",\n- \"gfx906\",\n- \"gfx908\",\n- \"gfx1010\",\n- \"gfx1011\",\n- \"gfx1012\",\n- )\n- variant(\"amdgpu_target\", default=\"gfx803,gfx900,gfx906\", multi=True, values=amdgpu_targets)\n-\n # Fix compilation error in some cases due to missing include statement\n # before version 1.0.3\n patch(\"0001-fix-missing-limits-include.patch\", when=\"@:1.0.2\")\n", "issue": "spfft: inherit from ROCmPackage\nFollowing https://github.com/spack/spack/pull/31207#issuecomment-1161932478 this PR adapts `spfft` the same way by inheriting from `ROCmPackage`.\r\n\r\nAlso for this one, I would ask one of the reviewer if they can test it works correctly.\n", "before_files": [{"content": "# Copyright 2013-2022 Lawrence Livermore National Security, LLC and other\n# Spack Project Developers. See the top-level COPYRIGHT file for details.\n#\n# SPDX-License-Identifier: (Apache-2.0 OR MIT)\n\n\nfrom spack.package import *\n\n\nclass Spfft(CMakePackage, CudaPackage):\n \"\"\"Sparse 3D FFT library with MPI, OpenMP, CUDA and ROCm support.\"\"\"\n\n homepage = \"https://github.com/eth-cscs/SpFFT\"\n url = \"https://github.com/eth-cscs/SpFFT/archive/v0.9.8.zip\"\n git = \"https://github.com/eth-cscs/SpFFT.git\"\n\n maintainers = [\"AdhocMan\", \"haampie\"]\n\n version(\"develop\", branch=\"develop\")\n version(\"master\", branch=\"master\")\n\n version(\"1.0.6\", sha256=\"e1b927c61f8abbb4a9937653f917169e6253e8c40b850df491594310943ca14b\")\n version(\"1.0.5\", sha256=\"2a59d856286ea8559f00a32fc38f9f7546209cfa90112232a5288a69689a6e05\")\n version(\"1.0.4\", sha256=\"41e63880d95343da0d8c3dbe5bfb3d46a1d612199cc9cc13a936f1628a7fdb8e\")\n version(\"1.0.3\", sha256=\"4f87734e3582ef96ddc0402d0db78cfc173bed9cab3e0d9c6a6bf8b660d69559\")\n version(\"1.0.2\", sha256=\"9b1296bda0b9ec3d37c74fd64354a01ebc6e2da7cb026c1f821882160b03c692\")\n version(\"1.0.1\", sha256=\"f8ab706309776cfbd2bfd8e29a6a9ffb5c8f3cd62399bf82db1e416ae5c490c8\")\n version(\"1.0.0\", sha256=\"bd98897aa6734563ec63cd84168e731ef2e2bbc01a574c6dc59b74475742b6ee\")\n version(\"0.9.13\", sha256=\"5ccc93c9362bec14cfb6e31dd0e7ae7e48db0453ab49ebc9722041b69db759ef\")\n version(\"0.9.12\", sha256=\"1f7bf5164dcceb0e3bbce7d6ff9faef3145ad17cf3430149d40a98c43c010acc\")\n version(\"0.9.11\", sha256=\"36542a60378e8672654188dee006975ef9e10f502791459ff7ebf4b38451cb9b\")\n version(\"0.9.10\", sha256=\"9cbbb7ba5e53e17eeb45e809841d8272e5333f739c2442a99c3e255c1ddec3e9\")\n version(\"0.9.9\", sha256=\"a8fd7a2d767716bb73185ca03bf4c106c6981b79130f3e456e5d2e744a2b3ba0\")\n version(\"0.9.8\", sha256=\"f49fa51316bbfa68309e951d2375e1f6904120c93868cbe13bc2974c0b801a3f\")\n\n variant(\"openmp\", default=True, description=\"Build with OpenMP support\")\n variant(\"mpi\", default=True, description=\"enable MPI\")\n variant(\"single_precision\", default=False, description=\"Sinlge precision\")\n variant(\"gpu_direct\", default=False, description=\"GPU aware MPI\")\n variant(\"static\", default=False, description=\"build static library\")\n variant(\"fortran\", default=False, description=\"enable fortran\")\n variant(\n \"build_type\",\n default=\"Release\",\n description=\"CMake build type\",\n values=(\"Debug\", \"Release\", \"RelWithDebInfo\"),\n )\n depends_on(\"fftw-api@3\")\n depends_on(\"mpi\", when=\"+mpi\")\n depends_on(\"[email protected]:\", type=\"build\")\n\n # ROCM variants + dependencies\n variant(\"rocm\", default=False, description=\"Use ROCm backend\")\n\n depends_on(\"cuda@:10\", when=\"@:0.9.11 +cuda\")\n\n with when(\"+rocm\"):\n # FindHIP cmake script only works for < 4.1\n depends_on(\"hip@:4.0\", when=\"@:1.0.1\")\n # Workaround for compiler bug in ROCm 4.5 added in SpFFT 1.0.6\n depends_on(\"hip@:4.3.1\", when=\"@:1.0.5\")\n depends_on(\"hip\")\n depends_on(\"rocfft\")\n # rocFFT and hipFFT have split with latest versions\n depends_on(\"hipfft\", when=\"^[email protected]:\")\n\n amdgpu_targets = (\n \"gfx701\",\n \"gfx801\",\n \"gfx802\",\n \"gfx803\",\n \"gfx900\",\n \"gfx906\",\n \"gfx908\",\n \"gfx1010\",\n \"gfx1011\",\n \"gfx1012\",\n )\n variant(\"amdgpu_target\", default=\"gfx803,gfx900,gfx906\", multi=True, values=amdgpu_targets)\n\n # Fix compilation error in some cases due to missing include statement\n # before version 1.0.3\n patch(\"0001-fix-missing-limits-include.patch\", when=\"@:1.0.2\")\n\n def cmake_args(self):\n spec = self.spec\n args = [\n self.define_from_variant(\"SPFFT_OMP\", \"openmp\"),\n self.define_from_variant(\"SPFFT_MPI\", \"mpi\"),\n self.define_from_variant(\"SPFFT_SINGLE_PRECISION\", \"single_precision\"),\n self.define_from_variant(\"SPFFT_GPU_DIRECT\", \"gpu_direct\"),\n self.define_from_variant(\"SPFFT_FORTRAN\", \"fortran\"),\n self.define_from_variant(\"SPFFT_STATIC\", \"static\"),\n ]\n\n if spec.satisfies(\"+cuda\"):\n args += [\"-DSPFFT_GPU_BACKEND=CUDA\"]\n\n cuda_arch = self.spec.variants[\"cuda_arch\"].value\n if cuda_arch[0] != \"none\":\n args += [self.define(\"CMAKE_CUDA_ARCHITECTURES\", cuda_arch)]\n\n if spec.satisfies(\"+rocm\"):\n archs = \",\".join(self.spec.variants[\"amdgpu_target\"].value)\n args += [\n \"-DSPFFT_GPU_BACKEND=ROCM\",\n \"-DHIP_ROOT_DIR={0}\".format(spec[\"hip\"].prefix),\n \"-DHIP_HCC_FLAGS=--amdgpu-target={0}\".format(archs),\n \"-DHIP_CXX_COMPILER={0}\".format(self.spec[\"hip\"].hipcc),\n ]\n\n if \"fftw\" in spec:\n args += [\"-DSPFFT_FFTW_LIB=FFTW\"]\n elif \"intel-mkl\" in spec:\n args += [\"-DSPFFT_FFTW_LIB=MKL\"]\n\n return args\n", "path": "var/spack/repos/builtin/packages/spfft/package.py"}]} | 2,841 | 543 |
gh_patches_debug_782 | rasdani/github-patches | git_diff | safe-global__safe-config-service-76 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Serve static files with Nginx
When running the application with Nginx as reverse-proxy, static files (such as Admin CSS) are not correctly collected and served
</issue>
<code>
[start of src/config/settings.py]
1 """
2 Django settings for safe_client_config_service project.
3
4 Generated by 'django-admin startproject' using Django 3.2.
5
6 For more information on this file, see
7 https://docs.djangoproject.com/en/3.2/topics/settings/
8
9 For the full list of settings and their values, see
10 https://docs.djangoproject.com/en/3.2/ref/settings/
11 """
12 import os
13 from distutils.util import strtobool
14 from pathlib import Path
15
16 # Build paths inside the project like this: BASE_DIR / 'subdir'.
17 BASE_DIR = Path(__file__).resolve().parent.parent
18
19 # Quick-start development settings - unsuitable for production
20 # See https://docs.djangoproject.com/en/3.2/howto/deployment/checklist/
21
22 # SECURITY WARNING: keep the secret key used in production secret!
23 SECRET_KEY = os.getenv("SECRET_KEY", None)
24
25 # SECURITY WARNING: don't run with debug turned on in production!
26 DEBUG = bool(strtobool(os.getenv("DEBUG", "false")))
27
28 # https://docs.djangoproject.com/en/3.2/ref/settings/#std:setting-ALLOWED_HOSTS
29 allowed_hosts = os.getenv("DJANGO_ALLOWED_HOSTS", ".localhost,127.0.0.1,[::1]")
30 ALLOWED_HOSTS = [allowed_host.strip() for allowed_host in allowed_hosts.split(",")]
31
32 # Application definition
33
34 REST_FRAMEWORK = {
35 # https://www.django-rest-framework.org/api-guide/renderers/
36 "DEFAULT_RENDERER_CLASSES": [
37 "djangorestframework_camel_case.render.CamelCaseJSONRenderer",
38 ]
39 }
40
41 INSTALLED_APPS = [
42 "safe_apps.apps.AppsConfig",
43 "django.contrib.admin",
44 "django.contrib.auth",
45 "django.contrib.contenttypes",
46 "django.contrib.sessions",
47 "django.contrib.messages",
48 "django.contrib.staticfiles",
49 "rest_framework",
50 ]
51
52 MIDDLEWARE = [
53 "config.middleware.LoggingMiddleware",
54 "django.middleware.security.SecurityMiddleware",
55 "django.contrib.sessions.middleware.SessionMiddleware",
56 "django.middleware.common.CommonMiddleware",
57 "django.middleware.csrf.CsrfViewMiddleware",
58 "django.contrib.auth.middleware.AuthenticationMiddleware",
59 "django.contrib.messages.middleware.MessageMiddleware",
60 "django.middleware.clickjacking.XFrameOptionsMiddleware",
61 ]
62
63 CACHES = {
64 "default": {
65 "BACKEND": "django.core.cache.backends.locmem.LocMemCache",
66 },
67 "safe-apps": {
68 "BACKEND": "django.core.cache.backends.locmem.LocMemCache",
69 },
70 }
71
72 LOGGING = {
73 "version": 1,
74 "disable_existing_loggers": False,
75 "formatters": {
76 "short": {"format": "%(asctime)s %(message)s"},
77 "verbose": {
78 "format": "%(asctime)s [%(levelname)s] [%(processName)s] %(message)s"
79 },
80 },
81 "handlers": {
82 "console": {
83 "class": "logging.StreamHandler",
84 "formatter": "verbose",
85 },
86 "console_short": {
87 "class": "logging.StreamHandler",
88 "formatter": "short",
89 },
90 },
91 "root": {
92 "handlers": ["console"],
93 "level": os.getenv("ROOT_LOG_LEVEL", "INFO"),
94 },
95 "loggers": {
96 "LoggingMiddleware": {
97 "handlers": ["console_short"],
98 "level": "INFO",
99 "propagate": False,
100 },
101 },
102 }
103
104 ROOT_URLCONF = "config.urls"
105
106 TEMPLATES = [
107 {
108 "BACKEND": "django.template.backends.django.DjangoTemplates",
109 "DIRS": [],
110 "APP_DIRS": True,
111 "OPTIONS": {
112 "context_processors": [
113 "django.template.context_processors.debug",
114 "django.template.context_processors.request",
115 "django.contrib.auth.context_processors.auth",
116 "django.contrib.messages.context_processors.messages",
117 ],
118 },
119 },
120 ]
121
122 WSGI_APPLICATION = "config.wsgi.application"
123
124 # Database
125 # https://docs.djangoproject.com/en/3.2/ref/settings/#databases
126
127 DATABASES = {
128 "default": {
129 "ENGINE": "django.db.backends.postgresql",
130 "NAME": os.getenv("POSTGRES_NAME", "postgres"),
131 "USER": os.getenv("POSTGRES_USER", "postgres"),
132 "PASSWORD": os.getenv("POSTGRES_PASSWORD", "postgres"),
133 "HOST": os.getenv("POSTGRES_HOST", "db"),
134 "PORT": os.getenv("POSTGRES_PORT", "5432"),
135 }
136 }
137
138 # Password validation
139 # https://docs.djangoproject.com/en/3.2/ref/settings/#auth-password-validators
140
141 AUTH_PASSWORD_VALIDATORS = [
142 {
143 "NAME": "django.contrib.auth.password_validation.UserAttributeSimilarityValidator",
144 },
145 {
146 "NAME": "django.contrib.auth.password_validation.MinimumLengthValidator",
147 },
148 {
149 "NAME": "django.contrib.auth.password_validation.CommonPasswordValidator",
150 },
151 {
152 "NAME": "django.contrib.auth.password_validation.NumericPasswordValidator",
153 },
154 ]
155
156 # Internationalization
157 # https://docs.djangoproject.com/en/3.2/topics/i18n/
158
159 LANGUAGE_CODE = "en-us"
160
161 TIME_ZONE = "UTC"
162
163 USE_I18N = True
164
165 USE_L10N = True
166
167 USE_TZ = True
168
169 # Static files (CSS, JavaScript, Images)
170 # https://docs.djangoproject.com/en/3.2/howto/static-files/
171
172 STATIC_URL = "/static/"
173
174 # Default primary key field type
175 # https://docs.djangoproject.com/en/3.2/ref/settings/#default-auto-field
176
177 DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"
178
[end of src/config/settings.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/config/settings.py b/src/config/settings.py
--- a/src/config/settings.py
+++ b/src/config/settings.py
@@ -171,6 +171,8 @@
STATIC_URL = "/static/"
+STATIC_ROOT = "staticfiles"
+
# Default primary key field type
# https://docs.djangoproject.com/en/3.2/ref/settings/#default-auto-field
| {"golden_diff": "diff --git a/src/config/settings.py b/src/config/settings.py\n--- a/src/config/settings.py\n+++ b/src/config/settings.py\n@@ -171,6 +171,8 @@\n \n STATIC_URL = \"/static/\"\n \n+STATIC_ROOT = \"staticfiles\"\n+\n # Default primary key field type\n # https://docs.djangoproject.com/en/3.2/ref/settings/#default-auto-field\n", "issue": "Serve static files with Nginx\nWhen running the application with Nginx as reverse-proxy, static files (such as Admin CSS) are not correctly collected and served\n", "before_files": [{"content": "\"\"\"\nDjango settings for safe_client_config_service project.\n\nGenerated by 'django-admin startproject' using Django 3.2.\n\nFor more information on this file, see\nhttps://docs.djangoproject.com/en/3.2/topics/settings/\n\nFor the full list of settings and their values, see\nhttps://docs.djangoproject.com/en/3.2/ref/settings/\n\"\"\"\nimport os\nfrom distutils.util import strtobool\nfrom pathlib import Path\n\n# Build paths inside the project like this: BASE_DIR / 'subdir'.\nBASE_DIR = Path(__file__).resolve().parent.parent\n\n# Quick-start development settings - unsuitable for production\n# See https://docs.djangoproject.com/en/3.2/howto/deployment/checklist/\n\n# SECURITY WARNING: keep the secret key used in production secret!\nSECRET_KEY = os.getenv(\"SECRET_KEY\", None)\n\n# SECURITY WARNING: don't run with debug turned on in production!\nDEBUG = bool(strtobool(os.getenv(\"DEBUG\", \"false\")))\n\n# https://docs.djangoproject.com/en/3.2/ref/settings/#std:setting-ALLOWED_HOSTS\nallowed_hosts = os.getenv(\"DJANGO_ALLOWED_HOSTS\", \".localhost,127.0.0.1,[::1]\")\nALLOWED_HOSTS = [allowed_host.strip() for allowed_host in allowed_hosts.split(\",\")]\n\n# Application definition\n\nREST_FRAMEWORK = {\n # https://www.django-rest-framework.org/api-guide/renderers/\n \"DEFAULT_RENDERER_CLASSES\": [\n \"djangorestframework_camel_case.render.CamelCaseJSONRenderer\",\n ]\n}\n\nINSTALLED_APPS = [\n \"safe_apps.apps.AppsConfig\",\n \"django.contrib.admin\",\n \"django.contrib.auth\",\n \"django.contrib.contenttypes\",\n \"django.contrib.sessions\",\n \"django.contrib.messages\",\n \"django.contrib.staticfiles\",\n \"rest_framework\",\n]\n\nMIDDLEWARE = [\n \"config.middleware.LoggingMiddleware\",\n \"django.middleware.security.SecurityMiddleware\",\n \"django.contrib.sessions.middleware.SessionMiddleware\",\n \"django.middleware.common.CommonMiddleware\",\n \"django.middleware.csrf.CsrfViewMiddleware\",\n \"django.contrib.auth.middleware.AuthenticationMiddleware\",\n \"django.contrib.messages.middleware.MessageMiddleware\",\n \"django.middleware.clickjacking.XFrameOptionsMiddleware\",\n]\n\nCACHES = {\n \"default\": {\n \"BACKEND\": \"django.core.cache.backends.locmem.LocMemCache\",\n },\n \"safe-apps\": {\n \"BACKEND\": \"django.core.cache.backends.locmem.LocMemCache\",\n },\n}\n\nLOGGING = {\n \"version\": 1,\n \"disable_existing_loggers\": False,\n \"formatters\": {\n \"short\": {\"format\": \"%(asctime)s %(message)s\"},\n \"verbose\": {\n \"format\": \"%(asctime)s [%(levelname)s] [%(processName)s] %(message)s\"\n },\n },\n \"handlers\": {\n \"console\": {\n \"class\": \"logging.StreamHandler\",\n \"formatter\": \"verbose\",\n },\n \"console_short\": {\n \"class\": \"logging.StreamHandler\",\n \"formatter\": \"short\",\n },\n },\n \"root\": {\n \"handlers\": [\"console\"],\n \"level\": os.getenv(\"ROOT_LOG_LEVEL\", \"INFO\"),\n },\n \"loggers\": {\n \"LoggingMiddleware\": {\n \"handlers\": [\"console_short\"],\n \"level\": \"INFO\",\n \"propagate\": False,\n },\n },\n}\n\nROOT_URLCONF = \"config.urls\"\n\nTEMPLATES = [\n {\n \"BACKEND\": \"django.template.backends.django.DjangoTemplates\",\n \"DIRS\": [],\n \"APP_DIRS\": True,\n \"OPTIONS\": {\n \"context_processors\": [\n \"django.template.context_processors.debug\",\n \"django.template.context_processors.request\",\n \"django.contrib.auth.context_processors.auth\",\n \"django.contrib.messages.context_processors.messages\",\n ],\n },\n },\n]\n\nWSGI_APPLICATION = \"config.wsgi.application\"\n\n# Database\n# https://docs.djangoproject.com/en/3.2/ref/settings/#databases\n\nDATABASES = {\n \"default\": {\n \"ENGINE\": \"django.db.backends.postgresql\",\n \"NAME\": os.getenv(\"POSTGRES_NAME\", \"postgres\"),\n \"USER\": os.getenv(\"POSTGRES_USER\", \"postgres\"),\n \"PASSWORD\": os.getenv(\"POSTGRES_PASSWORD\", \"postgres\"),\n \"HOST\": os.getenv(\"POSTGRES_HOST\", \"db\"),\n \"PORT\": os.getenv(\"POSTGRES_PORT\", \"5432\"),\n }\n}\n\n# Password validation\n# https://docs.djangoproject.com/en/3.2/ref/settings/#auth-password-validators\n\nAUTH_PASSWORD_VALIDATORS = [\n {\n \"NAME\": \"django.contrib.auth.password_validation.UserAttributeSimilarityValidator\",\n },\n {\n \"NAME\": \"django.contrib.auth.password_validation.MinimumLengthValidator\",\n },\n {\n \"NAME\": \"django.contrib.auth.password_validation.CommonPasswordValidator\",\n },\n {\n \"NAME\": \"django.contrib.auth.password_validation.NumericPasswordValidator\",\n },\n]\n\n# Internationalization\n# https://docs.djangoproject.com/en/3.2/topics/i18n/\n\nLANGUAGE_CODE = \"en-us\"\n\nTIME_ZONE = \"UTC\"\n\nUSE_I18N = True\n\nUSE_L10N = True\n\nUSE_TZ = True\n\n# Static files (CSS, JavaScript, Images)\n# https://docs.djangoproject.com/en/3.2/howto/static-files/\n\nSTATIC_URL = \"/static/\"\n\n# Default primary key field type\n# https://docs.djangoproject.com/en/3.2/ref/settings/#default-auto-field\n\nDEFAULT_AUTO_FIELD = \"django.db.models.BigAutoField\"\n", "path": "src/config/settings.py"}]} | 2,185 | 84 |
gh_patches_debug_15947 | rasdani/github-patches | git_diff | mesonbuild__meson-6952 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
`meson_options.txt` cannot be used to specify negative integer values
*Actual:*
When trying to specify a negative number in `meson_options.txt`, I get the error `Arguments may only be string, int, bool, or array of those.`.
*Expected:*
No error is raised, and negative values are accepted.
*Rationale:*
These options are ideal for setting defaults for build configuration via `#mesondefine`. It's fairly common for integer options to treat zero and negative values as having special meanings. And even if not, sometimes you'd like to have negative values as options.
*Workaround:*
- Add a second option for the special meaning (ugh!)
- Pass the option as a string, and use `#define` instead of `#mesondefine` (ugh!)
*Details:*
The error is raised here:
https://github.com/mesonbuild/meson/blob/6e865fc08d0d13b3846d00e80c9f3ea090645fb8/mesonbuild/optinterpreter.py#L170
The culprit looks like it may be here: https://github.com/mesonbuild/meson/blob/6e865fc08d0d13b3846d00e80c9f3ea090645fb8/mesonbuild/mparser.py#L107
</issue>
<code>
[start of mesonbuild/optinterpreter.py]
1 # Copyright 2013-2014 The Meson development team
2
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6
7 # http://www.apache.org/licenses/LICENSE-2.0
8
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 import re
16 import functools
17 import typing as T
18
19 from . import mparser
20 from . import coredata
21 from . import mesonlib
22 from . import compilers
23
24 forbidden_option_names = set(coredata.builtin_options.keys())
25 forbidden_prefixes = [lang + '_' for lang in compilers.all_languages] + ['b_', 'backend_']
26 reserved_prefixes = ['cross_']
27
28 def is_invalid_name(name: str, *, log: bool = True) -> bool:
29 if name in forbidden_option_names:
30 return True
31 pref = name.split('_')[0] + '_'
32 if pref in forbidden_prefixes:
33 return True
34 if pref in reserved_prefixes:
35 if log:
36 from . import mlog
37 mlog.deprecation('Option uses prefix "%s", which is reserved for Meson. This will become an error in the future.' % pref)
38 return False
39
40 class OptionException(mesonlib.MesonException):
41 pass
42
43
44 def permitted_kwargs(permitted):
45 """Function that validates kwargs for options."""
46 def _wraps(func):
47 @functools.wraps(func)
48 def _inner(name, description, kwargs):
49 bad = [a for a in kwargs.keys() if a not in permitted]
50 if bad:
51 raise OptionException('Invalid kwargs for option "{}": "{}"'.format(
52 name, ' '.join(bad)))
53 return func(description, kwargs)
54 return _inner
55 return _wraps
56
57
58 optname_regex = re.compile('[^a-zA-Z0-9_-]')
59
60 @permitted_kwargs({'value', 'yield'})
61 def StringParser(description, kwargs):
62 return coredata.UserStringOption(description,
63 kwargs.get('value', ''),
64 kwargs.get('choices', []),
65 kwargs.get('yield', coredata.default_yielding))
66
67 @permitted_kwargs({'value', 'yield'})
68 def BooleanParser(description, kwargs):
69 return coredata.UserBooleanOption(description,
70 kwargs.get('value', True),
71 kwargs.get('yield', coredata.default_yielding))
72
73 @permitted_kwargs({'value', 'yield', 'choices'})
74 def ComboParser(description, kwargs):
75 if 'choices' not in kwargs:
76 raise OptionException('Combo option missing "choices" keyword.')
77 choices = kwargs['choices']
78 if not isinstance(choices, list):
79 raise OptionException('Combo choices must be an array.')
80 for i in choices:
81 if not isinstance(i, str):
82 raise OptionException('Combo choice elements must be strings.')
83 return coredata.UserComboOption(description,
84 choices,
85 kwargs.get('value', choices[0]),
86 kwargs.get('yield', coredata.default_yielding),)
87
88
89 @permitted_kwargs({'value', 'min', 'max', 'yield'})
90 def IntegerParser(description, kwargs):
91 if 'value' not in kwargs:
92 raise OptionException('Integer option must contain value argument.')
93 inttuple = (kwargs.get('min', None), kwargs.get('max', None), kwargs['value'])
94 return coredata.UserIntegerOption(description,
95 inttuple,
96 kwargs.get('yield', coredata.default_yielding))
97
98 # FIXME: Cannot use FeatureNew while parsing options because we parse it before
99 # reading options in project(). See func_project() in interpreter.py
100 #@FeatureNew('array type option()', '0.44.0')
101 @permitted_kwargs({'value', 'yield', 'choices'})
102 def string_array_parser(description, kwargs):
103 if 'choices' in kwargs:
104 choices = kwargs['choices']
105 if not isinstance(choices, list):
106 raise OptionException('Array choices must be an array.')
107 for i in choices:
108 if not isinstance(i, str):
109 raise OptionException('Array choice elements must be strings.')
110 value = kwargs.get('value', choices)
111 else:
112 choices = None
113 value = kwargs.get('value', [])
114 if not isinstance(value, list):
115 raise OptionException('Array choices must be passed as an array.')
116 return coredata.UserArrayOption(description,
117 value,
118 choices=choices,
119 yielding=kwargs.get('yield', coredata.default_yielding))
120
121 @permitted_kwargs({'value', 'yield'})
122 def FeatureParser(description, kwargs):
123 return coredata.UserFeatureOption(description,
124 kwargs.get('value', 'auto'),
125 yielding=kwargs.get('yield', coredata.default_yielding))
126
127 option_types = {'string': StringParser,
128 'boolean': BooleanParser,
129 'combo': ComboParser,
130 'integer': IntegerParser,
131 'array': string_array_parser,
132 'feature': FeatureParser,
133 } # type: T.Dict[str, T.Callable[[str, T.Dict], coredata.UserOption]]
134
135 class OptionInterpreter:
136 def __init__(self, subproject):
137 self.options = {}
138 self.subproject = subproject
139
140 def process(self, option_file):
141 try:
142 with open(option_file, 'r', encoding='utf8') as f:
143 ast = mparser.Parser(f.read(), option_file).parse()
144 except mesonlib.MesonException as me:
145 me.file = option_file
146 raise me
147 if not isinstance(ast, mparser.CodeBlockNode):
148 e = OptionException('Option file is malformed.')
149 e.lineno = ast.lineno()
150 e.file = option_file
151 raise e
152 for cur in ast.lines:
153 try:
154 self.evaluate_statement(cur)
155 except Exception as e:
156 e.lineno = cur.lineno
157 e.colno = cur.colno
158 e.file = option_file
159 raise e
160
161 def reduce_single(self, arg):
162 if isinstance(arg, str):
163 return arg
164 elif isinstance(arg, (mparser.StringNode, mparser.BooleanNode,
165 mparser.NumberNode)):
166 return arg.value
167 elif isinstance(arg, mparser.ArrayNode):
168 return [self.reduce_single(curarg) for curarg in arg.args.arguments]
169 else:
170 raise OptionException('Arguments may only be string, int, bool, or array of those.')
171
172 def reduce_arguments(self, args):
173 assert(isinstance(args, mparser.ArgumentNode))
174 if args.incorrect_order():
175 raise OptionException('All keyword arguments must be after positional arguments.')
176 reduced_pos = [self.reduce_single(arg) for arg in args.arguments]
177 reduced_kw = {}
178 for key in args.kwargs.keys():
179 if not isinstance(key, mparser.IdNode):
180 raise OptionException('Keyword argument name is not a string.')
181 a = args.kwargs[key]
182 reduced_kw[key.value] = self.reduce_single(a)
183 return reduced_pos, reduced_kw
184
185 def evaluate_statement(self, node):
186 if not isinstance(node, mparser.FunctionNode):
187 raise OptionException('Option file may only contain option definitions')
188 func_name = node.func_name
189 if func_name != 'option':
190 raise OptionException('Only calls to option() are allowed in option files.')
191 (posargs, kwargs) = self.reduce_arguments(node.args)
192
193 # FIXME: Cannot use FeatureNew while parsing options because we parse
194 # it before reading options in project(). See func_project() in
195 # interpreter.py
196 #if 'yield' in kwargs:
197 # FeatureNew('option yield', '0.45.0').use(self.subproject)
198
199 if 'type' not in kwargs:
200 raise OptionException('Option call missing mandatory "type" keyword argument')
201 opt_type = kwargs.pop('type')
202 if opt_type not in option_types:
203 raise OptionException('Unknown type %s.' % opt_type)
204 if len(posargs) != 1:
205 raise OptionException('Option() must have one (and only one) positional argument')
206 opt_name = posargs[0]
207 if not isinstance(opt_name, str):
208 raise OptionException('Positional argument must be a string.')
209 if optname_regex.search(opt_name) is not None:
210 raise OptionException('Option names can only contain letters, numbers or dashes.')
211 if is_invalid_name(opt_name):
212 raise OptionException('Option name %s is reserved.' % opt_name)
213 if self.subproject != '':
214 opt_name = self.subproject + ':' + opt_name
215 opt = option_types[opt_type](opt_name, kwargs.pop('description', ''), kwargs)
216 if opt.description == '':
217 opt.description = opt_name
218 self.options[opt_name] = opt
219
[end of mesonbuild/optinterpreter.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/mesonbuild/optinterpreter.py b/mesonbuild/optinterpreter.py
--- a/mesonbuild/optinterpreter.py
+++ b/mesonbuild/optinterpreter.py
@@ -166,6 +166,16 @@
return arg.value
elif isinstance(arg, mparser.ArrayNode):
return [self.reduce_single(curarg) for curarg in arg.args.arguments]
+ elif isinstance(arg, mparser.UMinusNode):
+ res = self.reduce_single(arg.value)
+ if not isinstance(res, (int, float)):
+ raise OptionException('Token after "-" is not a number')
+ return -res
+ elif isinstance(arg, mparser.NotNode):
+ res = self.reduce_single(arg.value)
+ if not isinstance(res, bool):
+ raise OptionException('Token after "not" is not a a boolean')
+ return not res
else:
raise OptionException('Arguments may only be string, int, bool, or array of those.')
| {"golden_diff": "diff --git a/mesonbuild/optinterpreter.py b/mesonbuild/optinterpreter.py\n--- a/mesonbuild/optinterpreter.py\n+++ b/mesonbuild/optinterpreter.py\n@@ -166,6 +166,16 @@\n return arg.value\n elif isinstance(arg, mparser.ArrayNode):\n return [self.reduce_single(curarg) for curarg in arg.args.arguments]\n+ elif isinstance(arg, mparser.UMinusNode):\n+ res = self.reduce_single(arg.value)\n+ if not isinstance(res, (int, float)):\n+ raise OptionException('Token after \"-\" is not a number')\n+ return -res\n+ elif isinstance(arg, mparser.NotNode):\n+ res = self.reduce_single(arg.value)\n+ if not isinstance(res, bool):\n+ raise OptionException('Token after \"not\" is not a a boolean')\n+ return not res\n else:\n raise OptionException('Arguments may only be string, int, bool, or array of those.')\n", "issue": "`meson_options.txt` cannot be used to specify negative integer values\n*Actual:*\r\nWhen trying to specify a negative number in `meson_options.txt`, I get the error `Arguments may only be string, int, bool, or array of those.`.\r\n\r\n*Expected:*\r\nNo error is raised, and negative values are accepted.\r\n\r\n*Rationale:*\r\nThese options are ideal for setting defaults for build configuration via `#mesondefine`. It's fairly common for integer options to treat zero and negative values as having special meanings. And even if not, sometimes you'd like to have negative values as options.\r\n\r\n*Workaround:*\r\n- Add a second option for the special meaning (ugh!)\r\n- Pass the option as a string, and use `#define` instead of `#mesondefine` (ugh!)\r\n\r\n*Details:*\r\nThe error is raised here:\r\nhttps://github.com/mesonbuild/meson/blob/6e865fc08d0d13b3846d00e80c9f3ea090645fb8/mesonbuild/optinterpreter.py#L170\r\n\r\nThe culprit looks like it may be here: https://github.com/mesonbuild/meson/blob/6e865fc08d0d13b3846d00e80c9f3ea090645fb8/mesonbuild/mparser.py#L107\n", "before_files": [{"content": "# Copyright 2013-2014 The Meson development team\n\n# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n\n# http://www.apache.org/licenses/LICENSE-2.0\n\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport re\nimport functools\nimport typing as T\n\nfrom . import mparser\nfrom . import coredata\nfrom . import mesonlib\nfrom . import compilers\n\nforbidden_option_names = set(coredata.builtin_options.keys())\nforbidden_prefixes = [lang + '_' for lang in compilers.all_languages] + ['b_', 'backend_']\nreserved_prefixes = ['cross_']\n\ndef is_invalid_name(name: str, *, log: bool = True) -> bool:\n if name in forbidden_option_names:\n return True\n pref = name.split('_')[0] + '_'\n if pref in forbidden_prefixes:\n return True\n if pref in reserved_prefixes:\n if log:\n from . import mlog\n mlog.deprecation('Option uses prefix \"%s\", which is reserved for Meson. This will become an error in the future.' % pref)\n return False\n\nclass OptionException(mesonlib.MesonException):\n pass\n\n\ndef permitted_kwargs(permitted):\n \"\"\"Function that validates kwargs for options.\"\"\"\n def _wraps(func):\n @functools.wraps(func)\n def _inner(name, description, kwargs):\n bad = [a for a in kwargs.keys() if a not in permitted]\n if bad:\n raise OptionException('Invalid kwargs for option \"{}\": \"{}\"'.format(\n name, ' '.join(bad)))\n return func(description, kwargs)\n return _inner\n return _wraps\n\n\noptname_regex = re.compile('[^a-zA-Z0-9_-]')\n\n@permitted_kwargs({'value', 'yield'})\ndef StringParser(description, kwargs):\n return coredata.UserStringOption(description,\n kwargs.get('value', ''),\n kwargs.get('choices', []),\n kwargs.get('yield', coredata.default_yielding))\n\n@permitted_kwargs({'value', 'yield'})\ndef BooleanParser(description, kwargs):\n return coredata.UserBooleanOption(description,\n kwargs.get('value', True),\n kwargs.get('yield', coredata.default_yielding))\n\n@permitted_kwargs({'value', 'yield', 'choices'})\ndef ComboParser(description, kwargs):\n if 'choices' not in kwargs:\n raise OptionException('Combo option missing \"choices\" keyword.')\n choices = kwargs['choices']\n if not isinstance(choices, list):\n raise OptionException('Combo choices must be an array.')\n for i in choices:\n if not isinstance(i, str):\n raise OptionException('Combo choice elements must be strings.')\n return coredata.UserComboOption(description,\n choices,\n kwargs.get('value', choices[0]),\n kwargs.get('yield', coredata.default_yielding),)\n\n\n@permitted_kwargs({'value', 'min', 'max', 'yield'})\ndef IntegerParser(description, kwargs):\n if 'value' not in kwargs:\n raise OptionException('Integer option must contain value argument.')\n inttuple = (kwargs.get('min', None), kwargs.get('max', None), kwargs['value'])\n return coredata.UserIntegerOption(description,\n inttuple,\n kwargs.get('yield', coredata.default_yielding))\n\n# FIXME: Cannot use FeatureNew while parsing options because we parse it before\n# reading options in project(). See func_project() in interpreter.py\n#@FeatureNew('array type option()', '0.44.0')\n@permitted_kwargs({'value', 'yield', 'choices'})\ndef string_array_parser(description, kwargs):\n if 'choices' in kwargs:\n choices = kwargs['choices']\n if not isinstance(choices, list):\n raise OptionException('Array choices must be an array.')\n for i in choices:\n if not isinstance(i, str):\n raise OptionException('Array choice elements must be strings.')\n value = kwargs.get('value', choices)\n else:\n choices = None\n value = kwargs.get('value', [])\n if not isinstance(value, list):\n raise OptionException('Array choices must be passed as an array.')\n return coredata.UserArrayOption(description,\n value,\n choices=choices,\n yielding=kwargs.get('yield', coredata.default_yielding))\n\n@permitted_kwargs({'value', 'yield'})\ndef FeatureParser(description, kwargs):\n return coredata.UserFeatureOption(description,\n kwargs.get('value', 'auto'),\n yielding=kwargs.get('yield', coredata.default_yielding))\n\noption_types = {'string': StringParser,\n 'boolean': BooleanParser,\n 'combo': ComboParser,\n 'integer': IntegerParser,\n 'array': string_array_parser,\n 'feature': FeatureParser,\n } # type: T.Dict[str, T.Callable[[str, T.Dict], coredata.UserOption]]\n\nclass OptionInterpreter:\n def __init__(self, subproject):\n self.options = {}\n self.subproject = subproject\n\n def process(self, option_file):\n try:\n with open(option_file, 'r', encoding='utf8') as f:\n ast = mparser.Parser(f.read(), option_file).parse()\n except mesonlib.MesonException as me:\n me.file = option_file\n raise me\n if not isinstance(ast, mparser.CodeBlockNode):\n e = OptionException('Option file is malformed.')\n e.lineno = ast.lineno()\n e.file = option_file\n raise e\n for cur in ast.lines:\n try:\n self.evaluate_statement(cur)\n except Exception as e:\n e.lineno = cur.lineno\n e.colno = cur.colno\n e.file = option_file\n raise e\n\n def reduce_single(self, arg):\n if isinstance(arg, str):\n return arg\n elif isinstance(arg, (mparser.StringNode, mparser.BooleanNode,\n mparser.NumberNode)):\n return arg.value\n elif isinstance(arg, mparser.ArrayNode):\n return [self.reduce_single(curarg) for curarg in arg.args.arguments]\n else:\n raise OptionException('Arguments may only be string, int, bool, or array of those.')\n\n def reduce_arguments(self, args):\n assert(isinstance(args, mparser.ArgumentNode))\n if args.incorrect_order():\n raise OptionException('All keyword arguments must be after positional arguments.')\n reduced_pos = [self.reduce_single(arg) for arg in args.arguments]\n reduced_kw = {}\n for key in args.kwargs.keys():\n if not isinstance(key, mparser.IdNode):\n raise OptionException('Keyword argument name is not a string.')\n a = args.kwargs[key]\n reduced_kw[key.value] = self.reduce_single(a)\n return reduced_pos, reduced_kw\n\n def evaluate_statement(self, node):\n if not isinstance(node, mparser.FunctionNode):\n raise OptionException('Option file may only contain option definitions')\n func_name = node.func_name\n if func_name != 'option':\n raise OptionException('Only calls to option() are allowed in option files.')\n (posargs, kwargs) = self.reduce_arguments(node.args)\n\n # FIXME: Cannot use FeatureNew while parsing options because we parse\n # it before reading options in project(). See func_project() in\n # interpreter.py\n #if 'yield' in kwargs:\n # FeatureNew('option yield', '0.45.0').use(self.subproject)\n\n if 'type' not in kwargs:\n raise OptionException('Option call missing mandatory \"type\" keyword argument')\n opt_type = kwargs.pop('type')\n if opt_type not in option_types:\n raise OptionException('Unknown type %s.' % opt_type)\n if len(posargs) != 1:\n raise OptionException('Option() must have one (and only one) positional argument')\n opt_name = posargs[0]\n if not isinstance(opt_name, str):\n raise OptionException('Positional argument must be a string.')\n if optname_regex.search(opt_name) is not None:\n raise OptionException('Option names can only contain letters, numbers or dashes.')\n if is_invalid_name(opt_name):\n raise OptionException('Option name %s is reserved.' % opt_name)\n if self.subproject != '':\n opt_name = self.subproject + ':' + opt_name\n opt = option_types[opt_type](opt_name, kwargs.pop('description', ''), kwargs)\n if opt.description == '':\n opt.description = opt_name\n self.options[opt_name] = opt\n", "path": "mesonbuild/optinterpreter.py"}]} | 3,293 | 214 |
gh_patches_debug_61106 | rasdani/github-patches | git_diff | pre-commit__pre-commit-2272 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add GIT_HTTP_PROXY_AUTHMETHOD to kept environment variables
### describe your issue
On the cluster I work on, there’s a proxy. It’s… Let’s just say that proxy is being a pain, and to make it work we have to set the environment variable GIT_HTTP_PROXY_AUTHMETHOD.
In pre_commit/git.py however, only a small subset of variables are kept, and that one is not among them. So, sure, I can (and did) edit the script to keep that one too (and it works now) but it’s not ideal.
### pre-commit --version
pre-commit 2.17.0
### .pre-commit-config.yaml
```yaml
Not relevant
```
### ~/.cache/pre-commit/pre-commit.log (if present)
_No response_
</issue>
<code>
[start of pre_commit/git.py]
1 from __future__ import annotations
2
3 import logging
4 import os.path
5 import sys
6 from typing import MutableMapping
7
8 from pre_commit.errors import FatalError
9 from pre_commit.util import CalledProcessError
10 from pre_commit.util import cmd_output
11 from pre_commit.util import cmd_output_b
12
13 logger = logging.getLogger(__name__)
14
15 # see #2046
16 NO_FS_MONITOR = ('-c', 'core.useBuiltinFSMonitor=false')
17
18
19 def zsplit(s: str) -> list[str]:
20 s = s.strip('\0')
21 if s:
22 return s.split('\0')
23 else:
24 return []
25
26
27 def no_git_env(
28 _env: MutableMapping[str, str] | None = None,
29 ) -> dict[str, str]:
30 # Too many bugs dealing with environment variables and GIT:
31 # https://github.com/pre-commit/pre-commit/issues/300
32 # In git 2.6.3 (maybe others), git exports GIT_WORK_TREE while running
33 # pre-commit hooks
34 # In git 1.9.1 (maybe others), git exports GIT_DIR and GIT_INDEX_FILE
35 # while running pre-commit hooks in submodules.
36 # GIT_DIR: Causes git clone to clone wrong thing
37 # GIT_INDEX_FILE: Causes 'error invalid object ...' during commit
38 _env = _env if _env is not None else os.environ
39 return {
40 k: v for k, v in _env.items()
41 if not k.startswith('GIT_') or
42 k.startswith(('GIT_CONFIG_KEY_', 'GIT_CONFIG_VALUE_')) or
43 k in {
44 'GIT_EXEC_PATH', 'GIT_SSH', 'GIT_SSH_COMMAND', 'GIT_SSL_CAINFO',
45 'GIT_SSL_NO_VERIFY', 'GIT_CONFIG_COUNT',
46 }
47 }
48
49
50 def get_root() -> str:
51 # Git 2.25 introduced a change to "rev-parse --show-toplevel" that exposed
52 # underlying volumes for Windows drives mapped with SUBST. We use
53 # "rev-parse --show-cdup" to get the appropriate path, but must perform
54 # an extra check to see if we are in the .git directory.
55 try:
56 root = os.path.abspath(
57 cmd_output('git', 'rev-parse', '--show-cdup')[1].strip(),
58 )
59 git_dir = os.path.abspath(get_git_dir())
60 except CalledProcessError:
61 raise FatalError(
62 'git failed. Is it installed, and are you in a Git repository '
63 'directory?',
64 )
65 if os.path.samefile(root, git_dir):
66 raise FatalError(
67 'git toplevel unexpectedly empty! make sure you are not '
68 'inside the `.git` directory of your repository.',
69 )
70 return root
71
72
73 def get_git_dir(git_root: str = '.') -> str:
74 opts = ('--git-common-dir', '--git-dir')
75 _, out, _ = cmd_output('git', 'rev-parse', *opts, cwd=git_root)
76 for line, opt in zip(out.splitlines(), opts):
77 if line != opt: # pragma: no branch (git < 2.5)
78 return os.path.normpath(os.path.join(git_root, line))
79 else:
80 raise AssertionError('unreachable: no git dir')
81
82
83 def get_remote_url(git_root: str) -> str:
84 _, out, _ = cmd_output('git', 'config', 'remote.origin.url', cwd=git_root)
85 return out.strip()
86
87
88 def is_in_merge_conflict() -> bool:
89 git_dir = get_git_dir('.')
90 return (
91 os.path.exists(os.path.join(git_dir, 'MERGE_MSG')) and
92 os.path.exists(os.path.join(git_dir, 'MERGE_HEAD'))
93 )
94
95
96 def parse_merge_msg_for_conflicts(merge_msg: bytes) -> list[str]:
97 # Conflicted files start with tabs
98 return [
99 line.lstrip(b'#').strip().decode()
100 for line in merge_msg.splitlines()
101 # '#\t' for git 2.4.1
102 if line.startswith((b'\t', b'#\t'))
103 ]
104
105
106 def get_conflicted_files() -> set[str]:
107 logger.info('Checking merge-conflict files only.')
108 # Need to get the conflicted files from the MERGE_MSG because they could
109 # have resolved the conflict by choosing one side or the other
110 with open(os.path.join(get_git_dir('.'), 'MERGE_MSG'), 'rb') as f:
111 merge_msg = f.read()
112 merge_conflict_filenames = parse_merge_msg_for_conflicts(merge_msg)
113
114 # This will get the rest of the changes made after the merge.
115 # If they resolved the merge conflict by choosing a mesh of both sides
116 # this will also include the conflicted files
117 tree_hash = cmd_output('git', 'write-tree')[1].strip()
118 merge_diff_filenames = zsplit(
119 cmd_output(
120 'git', 'diff', '--name-only', '--no-ext-diff', '-z',
121 '-m', tree_hash, 'HEAD', 'MERGE_HEAD',
122 )[1],
123 )
124 return set(merge_conflict_filenames) | set(merge_diff_filenames)
125
126
127 def get_staged_files(cwd: str | None = None) -> list[str]:
128 return zsplit(
129 cmd_output(
130 'git', 'diff', '--staged', '--name-only', '--no-ext-diff', '-z',
131 # Everything except for D
132 '--diff-filter=ACMRTUXB',
133 cwd=cwd,
134 )[1],
135 )
136
137
138 def intent_to_add_files() -> list[str]:
139 _, stdout, _ = cmd_output(
140 'git', 'status', '--ignore-submodules', '--porcelain', '-z',
141 )
142 parts = list(reversed(zsplit(stdout)))
143 intent_to_add = []
144 while parts:
145 line = parts.pop()
146 status, filename = line[:3], line[3:]
147 if status[0] in {'C', 'R'}: # renames / moves have an additional arg
148 parts.pop()
149 if status[1] == 'A':
150 intent_to_add.append(filename)
151 return intent_to_add
152
153
154 def get_all_files() -> list[str]:
155 return zsplit(cmd_output('git', 'ls-files', '-z')[1])
156
157
158 def get_changed_files(old: str, new: str) -> list[str]:
159 diff_cmd = ('git', 'diff', '--name-only', '--no-ext-diff', '-z')
160 try:
161 _, out, _ = cmd_output(*diff_cmd, f'{old}...{new}')
162 except CalledProcessError: # pragma: no cover (new git)
163 # on newer git where old and new do not have a merge base git fails
164 # so we try a full diff (this is what old git did for us!)
165 _, out, _ = cmd_output(*diff_cmd, f'{old}..{new}')
166
167 return zsplit(out)
168
169
170 def head_rev(remote: str) -> str:
171 _, out, _ = cmd_output('git', 'ls-remote', '--exit-code', remote, 'HEAD')
172 return out.split()[0]
173
174
175 def has_diff(*args: str, repo: str = '.') -> bool:
176 cmd = ('git', 'diff', '--quiet', '--no-ext-diff', *args)
177 return cmd_output_b(*cmd, cwd=repo, retcode=None)[0] == 1
178
179
180 def has_core_hookpaths_set() -> bool:
181 _, out, _ = cmd_output_b('git', 'config', 'core.hooksPath', retcode=None)
182 return bool(out.strip())
183
184
185 def init_repo(path: str, remote: str) -> None:
186 if os.path.isdir(remote):
187 remote = os.path.abspath(remote)
188
189 git = ('git', *NO_FS_MONITOR)
190 env = no_git_env()
191 # avoid the user's template so that hooks do not recurse
192 cmd_output_b(*git, 'init', '--template=', path, env=env)
193 cmd_output_b(*git, 'remote', 'add', 'origin', remote, cwd=path, env=env)
194
195
196 def commit(repo: str = '.') -> None:
197 env = no_git_env()
198 name, email = 'pre-commit', '[email protected]'
199 env['GIT_AUTHOR_NAME'] = env['GIT_COMMITTER_NAME'] = name
200 env['GIT_AUTHOR_EMAIL'] = env['GIT_COMMITTER_EMAIL'] = email
201 cmd = ('git', 'commit', '--no-edit', '--no-gpg-sign', '-n', '-minit')
202 cmd_output_b(*cmd, cwd=repo, env=env)
203
204
205 def git_path(name: str, repo: str = '.') -> str:
206 _, out, _ = cmd_output('git', 'rev-parse', '--git-path', name, cwd=repo)
207 return os.path.join(repo, out.strip())
208
209
210 def check_for_cygwin_mismatch() -> None:
211 """See https://github.com/pre-commit/pre-commit/issues/354"""
212 if sys.platform in ('cygwin', 'win32'): # pragma: no cover (windows)
213 is_cygwin_python = sys.platform == 'cygwin'
214 try:
215 toplevel = get_root()
216 except FatalError: # skip the check if we're not in a git repo
217 return
218 is_cygwin_git = toplevel.startswith('/')
219
220 if is_cygwin_python ^ is_cygwin_git:
221 exe_type = {True: '(cygwin)', False: '(windows)'}
222 logger.warn(
223 f'pre-commit has detected a mix of cygwin python / git\n'
224 f'This combination is not supported, it is likely you will '
225 f'receive an error later in the program.\n'
226 f'Make sure to use cygwin git+python while using cygwin\n'
227 f'These can be installed through the cygwin installer.\n'
228 f' - python {exe_type[is_cygwin_python]}\n'
229 f' - git {exe_type[is_cygwin_git]}\n',
230 )
231
[end of pre_commit/git.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/pre_commit/git.py b/pre_commit/git.py
--- a/pre_commit/git.py
+++ b/pre_commit/git.py
@@ -43,6 +43,7 @@
k in {
'GIT_EXEC_PATH', 'GIT_SSH', 'GIT_SSH_COMMAND', 'GIT_SSL_CAINFO',
'GIT_SSL_NO_VERIFY', 'GIT_CONFIG_COUNT',
+ 'GIT_HTTP_PROXY_AUTHMETHOD',
}
}
| {"golden_diff": "diff --git a/pre_commit/git.py b/pre_commit/git.py\n--- a/pre_commit/git.py\n+++ b/pre_commit/git.py\n@@ -43,6 +43,7 @@\n k in {\n 'GIT_EXEC_PATH', 'GIT_SSH', 'GIT_SSH_COMMAND', 'GIT_SSL_CAINFO',\n 'GIT_SSL_NO_VERIFY', 'GIT_CONFIG_COUNT',\n+ 'GIT_HTTP_PROXY_AUTHMETHOD',\n }\n }\n", "issue": "Add GIT_HTTP_PROXY_AUTHMETHOD to kept environment variables\n### describe your issue\n\nOn the cluster I work on, there\u2019s a proxy. It\u2019s\u2026 Let\u2019s just say that proxy is being a pain, and to make it work we have to set the environment variable GIT_HTTP_PROXY_AUTHMETHOD.\r\n\r\nIn pre_commit/git.py however, only a small subset of variables are kept, and that one is not among them. So, sure, I can (and did) edit the script to keep that one too (and it works now) but it\u2019s not ideal.\n\n### pre-commit --version\n\npre-commit 2.17.0\n\n### .pre-commit-config.yaml\n\n```yaml\nNot relevant\n```\n\n\n### ~/.cache/pre-commit/pre-commit.log (if present)\n\n_No response_\n", "before_files": [{"content": "from __future__ import annotations\n\nimport logging\nimport os.path\nimport sys\nfrom typing import MutableMapping\n\nfrom pre_commit.errors import FatalError\nfrom pre_commit.util import CalledProcessError\nfrom pre_commit.util import cmd_output\nfrom pre_commit.util import cmd_output_b\n\nlogger = logging.getLogger(__name__)\n\n# see #2046\nNO_FS_MONITOR = ('-c', 'core.useBuiltinFSMonitor=false')\n\n\ndef zsplit(s: str) -> list[str]:\n s = s.strip('\\0')\n if s:\n return s.split('\\0')\n else:\n return []\n\n\ndef no_git_env(\n _env: MutableMapping[str, str] | None = None,\n) -> dict[str, str]:\n # Too many bugs dealing with environment variables and GIT:\n # https://github.com/pre-commit/pre-commit/issues/300\n # In git 2.6.3 (maybe others), git exports GIT_WORK_TREE while running\n # pre-commit hooks\n # In git 1.9.1 (maybe others), git exports GIT_DIR and GIT_INDEX_FILE\n # while running pre-commit hooks in submodules.\n # GIT_DIR: Causes git clone to clone wrong thing\n # GIT_INDEX_FILE: Causes 'error invalid object ...' during commit\n _env = _env if _env is not None else os.environ\n return {\n k: v for k, v in _env.items()\n if not k.startswith('GIT_') or\n k.startswith(('GIT_CONFIG_KEY_', 'GIT_CONFIG_VALUE_')) or\n k in {\n 'GIT_EXEC_PATH', 'GIT_SSH', 'GIT_SSH_COMMAND', 'GIT_SSL_CAINFO',\n 'GIT_SSL_NO_VERIFY', 'GIT_CONFIG_COUNT',\n }\n }\n\n\ndef get_root() -> str:\n # Git 2.25 introduced a change to \"rev-parse --show-toplevel\" that exposed\n # underlying volumes for Windows drives mapped with SUBST. We use\n # \"rev-parse --show-cdup\" to get the appropriate path, but must perform\n # an extra check to see if we are in the .git directory.\n try:\n root = os.path.abspath(\n cmd_output('git', 'rev-parse', '--show-cdup')[1].strip(),\n )\n git_dir = os.path.abspath(get_git_dir())\n except CalledProcessError:\n raise FatalError(\n 'git failed. Is it installed, and are you in a Git repository '\n 'directory?',\n )\n if os.path.samefile(root, git_dir):\n raise FatalError(\n 'git toplevel unexpectedly empty! make sure you are not '\n 'inside the `.git` directory of your repository.',\n )\n return root\n\n\ndef get_git_dir(git_root: str = '.') -> str:\n opts = ('--git-common-dir', '--git-dir')\n _, out, _ = cmd_output('git', 'rev-parse', *opts, cwd=git_root)\n for line, opt in zip(out.splitlines(), opts):\n if line != opt: # pragma: no branch (git < 2.5)\n return os.path.normpath(os.path.join(git_root, line))\n else:\n raise AssertionError('unreachable: no git dir')\n\n\ndef get_remote_url(git_root: str) -> str:\n _, out, _ = cmd_output('git', 'config', 'remote.origin.url', cwd=git_root)\n return out.strip()\n\n\ndef is_in_merge_conflict() -> bool:\n git_dir = get_git_dir('.')\n return (\n os.path.exists(os.path.join(git_dir, 'MERGE_MSG')) and\n os.path.exists(os.path.join(git_dir, 'MERGE_HEAD'))\n )\n\n\ndef parse_merge_msg_for_conflicts(merge_msg: bytes) -> list[str]:\n # Conflicted files start with tabs\n return [\n line.lstrip(b'#').strip().decode()\n for line in merge_msg.splitlines()\n # '#\\t' for git 2.4.1\n if line.startswith((b'\\t', b'#\\t'))\n ]\n\n\ndef get_conflicted_files() -> set[str]:\n logger.info('Checking merge-conflict files only.')\n # Need to get the conflicted files from the MERGE_MSG because they could\n # have resolved the conflict by choosing one side or the other\n with open(os.path.join(get_git_dir('.'), 'MERGE_MSG'), 'rb') as f:\n merge_msg = f.read()\n merge_conflict_filenames = parse_merge_msg_for_conflicts(merge_msg)\n\n # This will get the rest of the changes made after the merge.\n # If they resolved the merge conflict by choosing a mesh of both sides\n # this will also include the conflicted files\n tree_hash = cmd_output('git', 'write-tree')[1].strip()\n merge_diff_filenames = zsplit(\n cmd_output(\n 'git', 'diff', '--name-only', '--no-ext-diff', '-z',\n '-m', tree_hash, 'HEAD', 'MERGE_HEAD',\n )[1],\n )\n return set(merge_conflict_filenames) | set(merge_diff_filenames)\n\n\ndef get_staged_files(cwd: str | None = None) -> list[str]:\n return zsplit(\n cmd_output(\n 'git', 'diff', '--staged', '--name-only', '--no-ext-diff', '-z',\n # Everything except for D\n '--diff-filter=ACMRTUXB',\n cwd=cwd,\n )[1],\n )\n\n\ndef intent_to_add_files() -> list[str]:\n _, stdout, _ = cmd_output(\n 'git', 'status', '--ignore-submodules', '--porcelain', '-z',\n )\n parts = list(reversed(zsplit(stdout)))\n intent_to_add = []\n while parts:\n line = parts.pop()\n status, filename = line[:3], line[3:]\n if status[0] in {'C', 'R'}: # renames / moves have an additional arg\n parts.pop()\n if status[1] == 'A':\n intent_to_add.append(filename)\n return intent_to_add\n\n\ndef get_all_files() -> list[str]:\n return zsplit(cmd_output('git', 'ls-files', '-z')[1])\n\n\ndef get_changed_files(old: str, new: str) -> list[str]:\n diff_cmd = ('git', 'diff', '--name-only', '--no-ext-diff', '-z')\n try:\n _, out, _ = cmd_output(*diff_cmd, f'{old}...{new}')\n except CalledProcessError: # pragma: no cover (new git)\n # on newer git where old and new do not have a merge base git fails\n # so we try a full diff (this is what old git did for us!)\n _, out, _ = cmd_output(*diff_cmd, f'{old}..{new}')\n\n return zsplit(out)\n\n\ndef head_rev(remote: str) -> str:\n _, out, _ = cmd_output('git', 'ls-remote', '--exit-code', remote, 'HEAD')\n return out.split()[0]\n\n\ndef has_diff(*args: str, repo: str = '.') -> bool:\n cmd = ('git', 'diff', '--quiet', '--no-ext-diff', *args)\n return cmd_output_b(*cmd, cwd=repo, retcode=None)[0] == 1\n\n\ndef has_core_hookpaths_set() -> bool:\n _, out, _ = cmd_output_b('git', 'config', 'core.hooksPath', retcode=None)\n return bool(out.strip())\n\n\ndef init_repo(path: str, remote: str) -> None:\n if os.path.isdir(remote):\n remote = os.path.abspath(remote)\n\n git = ('git', *NO_FS_MONITOR)\n env = no_git_env()\n # avoid the user's template so that hooks do not recurse\n cmd_output_b(*git, 'init', '--template=', path, env=env)\n cmd_output_b(*git, 'remote', 'add', 'origin', remote, cwd=path, env=env)\n\n\ndef commit(repo: str = '.') -> None:\n env = no_git_env()\n name, email = 'pre-commit', '[email protected]'\n env['GIT_AUTHOR_NAME'] = env['GIT_COMMITTER_NAME'] = name\n env['GIT_AUTHOR_EMAIL'] = env['GIT_COMMITTER_EMAIL'] = email\n cmd = ('git', 'commit', '--no-edit', '--no-gpg-sign', '-n', '-minit')\n cmd_output_b(*cmd, cwd=repo, env=env)\n\n\ndef git_path(name: str, repo: str = '.') -> str:\n _, out, _ = cmd_output('git', 'rev-parse', '--git-path', name, cwd=repo)\n return os.path.join(repo, out.strip())\n\n\ndef check_for_cygwin_mismatch() -> None:\n \"\"\"See https://github.com/pre-commit/pre-commit/issues/354\"\"\"\n if sys.platform in ('cygwin', 'win32'): # pragma: no cover (windows)\n is_cygwin_python = sys.platform == 'cygwin'\n try:\n toplevel = get_root()\n except FatalError: # skip the check if we're not in a git repo\n return\n is_cygwin_git = toplevel.startswith('/')\n\n if is_cygwin_python ^ is_cygwin_git:\n exe_type = {True: '(cygwin)', False: '(windows)'}\n logger.warn(\n f'pre-commit has detected a mix of cygwin python / git\\n'\n f'This combination is not supported, it is likely you will '\n f'receive an error later in the program.\\n'\n f'Make sure to use cygwin git+python while using cygwin\\n'\n f'These can be installed through the cygwin installer.\\n'\n f' - python {exe_type[is_cygwin_python]}\\n'\n f' - git {exe_type[is_cygwin_git]}\\n',\n )\n", "path": "pre_commit/git.py"}]} | 3,478 | 92 |
gh_patches_debug_27231 | rasdani/github-patches | git_diff | vllm-project__vllm-4886 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
[New Model]: Phi-2 support for LoRA
### The model to consider.
Microsoft/Phi-2 with LoRA
### The closest model vllm already supports.
_No response_
### What's your difficulty of supporting the model you want?
_No response_
</issue>
<code>
[start of vllm/model_executor/models/phi.py]
1 # coding=utf-8
2 # Adapted from
3 # https://huggingface.co/microsoft/phi-1_5/blob/main/modeling_phi.py
4 # Copyright 2023 The vLLM team.
5 # Copyright (c) Microsoft Corporation.
6 # Licensed under the MIT license.
7 #
8 # BSD 3-Clause License
9 #
10 # Copyright (c) 2022, Tri Dao, [email protected].
11 # All rights reserved.
12 #
13 # Redistribution and use in source and binary forms, with or without
14 # modification, are permitted provided that the following conditions are met:
15 #
16 # * Redistributions of source code must retain the above copyright notice, this
17 # list of conditions and the following disclaimer.
18 #
19 # * Redistributions in binary form must reproduce the above copyright notice,
20 # this list of conditions and the following disclaimer in the documentation
21 # and/or other materials provided with the distribution.
22 #
23 # * Neither the name of the copyright holder nor the names of its
24 # contributors may be used to endorse or promote products derived from
25 # this software without specific prior written permission.
26 #
27 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
28 # AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
29 # IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
30 # DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
31 # FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
32 # DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
33 # SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
34 # CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
35 # OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
36 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
37 """Inference-only Phi-1.5 model compatible with HuggingFace weights."""
38 from typing import Iterable, List, Optional, Tuple
39
40 import torch
41 from torch import nn
42 from transformers import PretrainedConfig
43
44 from vllm.attention import Attention, AttentionMetadata
45 from vllm.config import CacheConfig
46 from vllm.distributed import get_tensor_model_parallel_world_size
47 from vllm.model_executor.layers.activation import get_act_fn
48 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
49 QKVParallelLinear,
50 RowParallelLinear)
51 from vllm.model_executor.layers.logits_processor import LogitsProcessor
52 from vllm.model_executor.layers.quantization.base_config import (
53 QuantizationConfig)
54 from vllm.model_executor.layers.rotary_embedding import get_rope
55 from vllm.model_executor.layers.sampler import Sampler
56 from vllm.model_executor.layers.vocab_parallel_embedding import (
57 ParallelLMHead, VocabParallelEmbedding)
58 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
59 from vllm.model_executor.sampling_metadata import SamplingMetadata
60 from vllm.sequence import SamplerOutput
61
62
63 class PhiAttention(nn.Module):
64
65 def __init__(self,
66 config: PretrainedConfig,
67 cache_config: Optional[CacheConfig] = None,
68 quant_config: Optional[QuantizationConfig] = None):
69 super().__init__()
70 self.total_num_heads = config.num_attention_heads
71 self.hidden_size = config.hidden_size
72 self.head_size = self.hidden_size // self.total_num_heads
73
74 tensor_model_parallel_world_size = (
75 get_tensor_model_parallel_world_size())
76 assert self.total_num_heads % tensor_model_parallel_world_size == 0
77 self.num_heads = (self.total_num_heads //
78 tensor_model_parallel_world_size)
79
80 # pylint: disable=C0103
81 self.qkv_proj = QKVParallelLinear(
82 self.hidden_size,
83 self.head_size,
84 self.total_num_heads,
85 bias=True,
86 quant_config=quant_config,
87 )
88 self.dense = RowParallelLinear(
89 self.hidden_size,
90 self.hidden_size,
91 quant_config=quant_config,
92 )
93
94 scaling = self.head_size**-0.5
95 rotary_dim = int(config.partial_rotary_factor *
96 (config.hidden_size // config.num_attention_heads))
97 assert rotary_dim % 2 == 0
98
99 # pylint: disable=C0301
100 # Refer to:
101 # https://huggingface.co/microsoft/phi-1_5/blob/d212a789620c380ff32ca1d1ee9943a777360987/modeling_phi.py#L518
102 rope_theta = 10000
103 max_position_embeddings = getattr(config, "n_positions", 2048)
104 self.rotary_emb = get_rope(
105 self.head_size,
106 rotary_dim=rotary_dim,
107 max_position=max_position_embeddings,
108 base=rope_theta,
109 )
110 self.attn = Attention(self.num_heads,
111 self.head_size,
112 scaling,
113 cache_config=cache_config)
114
115 def forward(
116 self,
117 position_ids: torch.Tensor,
118 hidden_states: torch.Tensor,
119 kv_cache: torch.Tensor,
120 attn_metadata: AttentionMetadata,
121 ) -> torch.Tensor:
122 qkv, _ = self.qkv_proj(hidden_states)
123 q, k, v = qkv.chunk(chunks=3, dim=-1)
124 q, k = self.rotary_emb(position_ids, q, k)
125 attn_output = self.attn(q, k, v, kv_cache, attn_metadata)
126 output, _ = self.dense(attn_output)
127 return output
128
129
130 class PhiMLP(nn.Module):
131
132 def __init__(self,
133 config: PretrainedConfig,
134 quant_config: Optional[QuantizationConfig] = None):
135 super().__init__()
136
137 n_inner = getattr(config, "n_inner", None)
138 n_inner = n_inner if n_inner is not None else 4 * config.hidden_size
139
140 self.fc1 = ColumnParallelLinear(
141 config.hidden_size,
142 n_inner,
143 quant_config=quant_config,
144 )
145 self.fc2 = RowParallelLinear(
146 n_inner,
147 config.hidden_size,
148 quant_config=quant_config,
149 )
150 self.act = get_act_fn(config.hidden_act, quant_config, n_inner)
151
152 def forward(self, hidden_states):
153 hidden_states, _ = self.fc1(hidden_states)
154 hidden_states = self.act(hidden_states)
155 hidden_states, _ = self.fc2(hidden_states)
156 return hidden_states
157
158
159 class PhiLayer(nn.Module):
160
161 def __init__(self,
162 config: PretrainedConfig,
163 cache_config: Optional[CacheConfig] = None,
164 quant_config: Optional[QuantizationConfig] = None):
165 super().__init__()
166 self.input_layernorm = nn.LayerNorm(config.hidden_size,
167 eps=config.layer_norm_eps)
168 self.self_attn = PhiAttention(config, cache_config, quant_config)
169 self.mlp = PhiMLP(config, quant_config)
170
171 def forward(
172 self,
173 position_ids: torch.Tensor,
174 hidden_states: torch.Tensor,
175 kv_cache: torch.Tensor,
176 attn_metadata: AttentionMetadata,
177 ) -> torch.Tensor:
178 residual = hidden_states
179 hidden_states = self.input_layernorm(hidden_states)
180 attn_outputs = self.self_attn(
181 position_ids=position_ids,
182 hidden_states=hidden_states,
183 kv_cache=kv_cache,
184 attn_metadata=attn_metadata,
185 )
186 feed_forward_hidden_states = self.mlp(hidden_states)
187 hidden_states = attn_outputs + feed_forward_hidden_states + residual
188 return hidden_states
189
190
191 class PhiModel(nn.Module):
192
193 def __init__(self,
194 config: PretrainedConfig,
195 cache_config: Optional[CacheConfig] = None,
196 quant_config: Optional[QuantizationConfig] = None):
197 super().__init__()
198 self.config = config
199 self.quant_config = quant_config
200 self.embed_tokens = VocabParallelEmbedding(config.vocab_size,
201 config.hidden_size)
202 self.layers = nn.ModuleList([
203 PhiLayer(config, cache_config, quant_config)
204 for _ in range(config.num_hidden_layers)
205 ])
206 self.final_layernorm = nn.LayerNorm(config.hidden_size,
207 eps=config.layer_norm_eps)
208
209 def forward(
210 self,
211 input_ids: torch.Tensor,
212 positions: torch.Tensor,
213 kv_caches: List[torch.Tensor],
214 attn_metadata: AttentionMetadata,
215 ) -> torch.Tensor:
216 hidden_states = self.embed_tokens(input_ids)
217 for i in range(self.config.num_hidden_layers):
218 layer = self.layers[i]
219 hidden_states = layer(
220 positions,
221 hidden_states,
222 kv_caches[i],
223 attn_metadata,
224 )
225
226 hidden_states = self.final_layernorm(hidden_states)
227
228 return hidden_states
229
230
231 class PhiForCausalLM(nn.Module):
232
233 def __init__(self,
234 config: PretrainedConfig,
235 cache_config: Optional[CacheConfig] = None,
236 quant_config: Optional[QuantizationConfig] = None):
237 super().__init__()
238 self.config = config
239 self.quant_config = quant_config
240
241 self.model = PhiModel(config, cache_config, quant_config)
242
243 self.lm_head = ParallelLMHead(config.vocab_size,
244 config.hidden_size,
245 bias=True)
246 self.logits_processor = LogitsProcessor(config.vocab_size)
247 self.sampler = Sampler()
248
249 def forward(
250 self,
251 input_ids: torch.Tensor,
252 positions: torch.Tensor,
253 kv_caches: List[torch.Tensor],
254 attn_metadata: AttentionMetadata,
255 ) -> torch.Tensor:
256 hidden_states = self.model(input_ids, positions, kv_caches,
257 attn_metadata)
258
259 return hidden_states
260
261 def compute_logits(self, hidden_states: torch.Tensor,
262 sampling_metadata: SamplingMetadata) -> torch.Tensor:
263 logits = self.logits_processor(self.lm_head.weight, hidden_states,
264 sampling_metadata, self.lm_head.bias)
265 return logits
266
267 def sample(
268 self,
269 logits: torch.Tensor,
270 sampling_metadata: SamplingMetadata,
271 ) -> Optional[SamplerOutput]:
272 next_tokens = self.sampler(logits, sampling_metadata)
273 return next_tokens
274
275 def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
276 stacked_params_mapping = [
277 # (param_name, shard_name, shard_id)
278 ("qkv_proj", "q_proj", "q"),
279 ("qkv_proj", "k_proj", "k"),
280 ("qkv_proj", "v_proj", "v")
281 ]
282 params_dict = dict(self.named_parameters())
283
284 for name, loaded_weight in weights:
285 if "rotary_emb.inv_freq" in name:
286 continue
287
288 for (param_name, weight_name, shard_id) in stacked_params_mapping:
289 if weight_name not in name:
290 continue
291 name = name.replace(weight_name, param_name)
292 # Skip loading extra bias for GPTQ models.
293 if name.endswith(".bias") and name not in params_dict:
294 continue
295 param = params_dict[name]
296 weight_loader = param.weight_loader
297 weight_loader(param, loaded_weight, shard_id)
298 break
299 else:
300 # Skip loading extra bias for GPTQ models.
301 if name.endswith(".bias") and name not in params_dict:
302 continue
303 # pylint: disable=E1136
304
305 param = params_dict[name]
306 weight_loader = getattr(param, "weight_loader",
307 default_weight_loader)
308 weight_loader(param, loaded_weight)
309
[end of vllm/model_executor/models/phi.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/vllm/model_executor/models/phi.py b/vllm/model_executor/models/phi.py
--- a/vllm/model_executor/models/phi.py
+++ b/vllm/model_executor/models/phi.py
@@ -42,7 +42,7 @@
from transformers import PretrainedConfig
from vllm.attention import Attention, AttentionMetadata
-from vllm.config import CacheConfig
+from vllm.config import CacheConfig, LoRAConfig
from vllm.distributed import get_tensor_model_parallel_world_size
from vllm.model_executor.layers.activation import get_act_fn
from vllm.model_executor.layers.linear import (ColumnParallelLinear,
@@ -229,11 +229,32 @@
class PhiForCausalLM(nn.Module):
-
- def __init__(self,
- config: PretrainedConfig,
- cache_config: Optional[CacheConfig] = None,
- quant_config: Optional[QuantizationConfig] = None):
+ packed_modules_mapping = {
+ "qkv_proj": [
+ "q_proj",
+ "k_proj",
+ "v_proj",
+ ]
+ }
+
+ # LoRA specific attributes
+ supported_lora_modules = [
+ "qkv_proj",
+ "dense",
+ "fc1",
+ "fc2",
+ ]
+ embedding_modules = {}
+ embedding_padding_modules = []
+
+ def __init__(
+ self,
+ config: PretrainedConfig,
+ cache_config: Optional[CacheConfig] = None,
+ quant_config: Optional[QuantizationConfig] = None,
+ lora_config: Optional[LoRAConfig] = None,
+ ):
+ del lora_config # Unused.
super().__init__()
self.config = config
self.quant_config = quant_config
| {"golden_diff": "diff --git a/vllm/model_executor/models/phi.py b/vllm/model_executor/models/phi.py\n--- a/vllm/model_executor/models/phi.py\n+++ b/vllm/model_executor/models/phi.py\n@@ -42,7 +42,7 @@\n from transformers import PretrainedConfig\n \n from vllm.attention import Attention, AttentionMetadata\n-from vllm.config import CacheConfig\n+from vllm.config import CacheConfig, LoRAConfig\n from vllm.distributed import get_tensor_model_parallel_world_size\n from vllm.model_executor.layers.activation import get_act_fn\n from vllm.model_executor.layers.linear import (ColumnParallelLinear,\n@@ -229,11 +229,32 @@\n \n \n class PhiForCausalLM(nn.Module):\n-\n- def __init__(self,\n- config: PretrainedConfig,\n- cache_config: Optional[CacheConfig] = None,\n- quant_config: Optional[QuantizationConfig] = None):\n+ packed_modules_mapping = {\n+ \"qkv_proj\": [\n+ \"q_proj\",\n+ \"k_proj\",\n+ \"v_proj\",\n+ ]\n+ }\n+\n+ # LoRA specific attributes\n+ supported_lora_modules = [\n+ \"qkv_proj\",\n+ \"dense\",\n+ \"fc1\",\n+ \"fc2\",\n+ ]\n+ embedding_modules = {}\n+ embedding_padding_modules = []\n+\n+ def __init__(\n+ self,\n+ config: PretrainedConfig,\n+ cache_config: Optional[CacheConfig] = None,\n+ quant_config: Optional[QuantizationConfig] = None,\n+ lora_config: Optional[LoRAConfig] = None,\n+ ):\n+ del lora_config # Unused.\n super().__init__()\n self.config = config\n self.quant_config = quant_config\n", "issue": "[New Model]: Phi-2 support for LoRA\n### The model to consider.\n\nMicrosoft/Phi-2 with LoRA\n\n### The closest model vllm already supports.\n\n_No response_\n\n### What's your difficulty of supporting the model you want?\n\n_No response_\n", "before_files": [{"content": "# coding=utf-8\n# Adapted from\n# https://huggingface.co/microsoft/phi-1_5/blob/main/modeling_phi.py\n# Copyright 2023 The vLLM team.\n# Copyright (c) Microsoft Corporation.\n# Licensed under the MIT license.\n#\n# BSD 3-Clause License\n#\n# Copyright (c) 2022, Tri Dao, [email protected].\n# All rights reserved.\n#\n# Redistribution and use in source and binary forms, with or without\n# modification, are permitted provided that the following conditions are met:\n#\n# * Redistributions of source code must retain the above copyright notice, this\n# list of conditions and the following disclaimer.\n#\n# * Redistributions in binary form must reproduce the above copyright notice,\n# this list of conditions and the following disclaimer in the documentation\n# and/or other materials provided with the distribution.\n#\n# * Neither the name of the copyright holder nor the names of its\n# contributors may be used to endorse or promote products derived from\n# this software without specific prior written permission.\n#\n# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS \"AS IS\"\n# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE\n# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE\n# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE\n# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL\n# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR\n# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER\n# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,\n# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE\n# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.\n\"\"\"Inference-only Phi-1.5 model compatible with HuggingFace weights.\"\"\"\nfrom typing import Iterable, List, Optional, Tuple\n\nimport torch\nfrom torch import nn\nfrom transformers import PretrainedConfig\n\nfrom vllm.attention import Attention, AttentionMetadata\nfrom vllm.config import CacheConfig\nfrom vllm.distributed import get_tensor_model_parallel_world_size\nfrom vllm.model_executor.layers.activation import get_act_fn\nfrom vllm.model_executor.layers.linear import (ColumnParallelLinear,\n QKVParallelLinear,\n RowParallelLinear)\nfrom vllm.model_executor.layers.logits_processor import LogitsProcessor\nfrom vllm.model_executor.layers.quantization.base_config import (\n QuantizationConfig)\nfrom vllm.model_executor.layers.rotary_embedding import get_rope\nfrom vllm.model_executor.layers.sampler import Sampler\nfrom vllm.model_executor.layers.vocab_parallel_embedding import (\n ParallelLMHead, VocabParallelEmbedding)\nfrom vllm.model_executor.model_loader.weight_utils import default_weight_loader\nfrom vllm.model_executor.sampling_metadata import SamplingMetadata\nfrom vllm.sequence import SamplerOutput\n\n\nclass PhiAttention(nn.Module):\n\n def __init__(self,\n config: PretrainedConfig,\n cache_config: Optional[CacheConfig] = None,\n quant_config: Optional[QuantizationConfig] = None):\n super().__init__()\n self.total_num_heads = config.num_attention_heads\n self.hidden_size = config.hidden_size\n self.head_size = self.hidden_size // self.total_num_heads\n\n tensor_model_parallel_world_size = (\n get_tensor_model_parallel_world_size())\n assert self.total_num_heads % tensor_model_parallel_world_size == 0\n self.num_heads = (self.total_num_heads //\n tensor_model_parallel_world_size)\n\n # pylint: disable=C0103\n self.qkv_proj = QKVParallelLinear(\n self.hidden_size,\n self.head_size,\n self.total_num_heads,\n bias=True,\n quant_config=quant_config,\n )\n self.dense = RowParallelLinear(\n self.hidden_size,\n self.hidden_size,\n quant_config=quant_config,\n )\n\n scaling = self.head_size**-0.5\n rotary_dim = int(config.partial_rotary_factor *\n (config.hidden_size // config.num_attention_heads))\n assert rotary_dim % 2 == 0\n\n # pylint: disable=C0301\n # Refer to:\n # https://huggingface.co/microsoft/phi-1_5/blob/d212a789620c380ff32ca1d1ee9943a777360987/modeling_phi.py#L518\n rope_theta = 10000\n max_position_embeddings = getattr(config, \"n_positions\", 2048)\n self.rotary_emb = get_rope(\n self.head_size,\n rotary_dim=rotary_dim,\n max_position=max_position_embeddings,\n base=rope_theta,\n )\n self.attn = Attention(self.num_heads,\n self.head_size,\n scaling,\n cache_config=cache_config)\n\n def forward(\n self,\n position_ids: torch.Tensor,\n hidden_states: torch.Tensor,\n kv_cache: torch.Tensor,\n attn_metadata: AttentionMetadata,\n ) -> torch.Tensor:\n qkv, _ = self.qkv_proj(hidden_states)\n q, k, v = qkv.chunk(chunks=3, dim=-1)\n q, k = self.rotary_emb(position_ids, q, k)\n attn_output = self.attn(q, k, v, kv_cache, attn_metadata)\n output, _ = self.dense(attn_output)\n return output\n\n\nclass PhiMLP(nn.Module):\n\n def __init__(self,\n config: PretrainedConfig,\n quant_config: Optional[QuantizationConfig] = None):\n super().__init__()\n\n n_inner = getattr(config, \"n_inner\", None)\n n_inner = n_inner if n_inner is not None else 4 * config.hidden_size\n\n self.fc1 = ColumnParallelLinear(\n config.hidden_size,\n n_inner,\n quant_config=quant_config,\n )\n self.fc2 = RowParallelLinear(\n n_inner,\n config.hidden_size,\n quant_config=quant_config,\n )\n self.act = get_act_fn(config.hidden_act, quant_config, n_inner)\n\n def forward(self, hidden_states):\n hidden_states, _ = self.fc1(hidden_states)\n hidden_states = self.act(hidden_states)\n hidden_states, _ = self.fc2(hidden_states)\n return hidden_states\n\n\nclass PhiLayer(nn.Module):\n\n def __init__(self,\n config: PretrainedConfig,\n cache_config: Optional[CacheConfig] = None,\n quant_config: Optional[QuantizationConfig] = None):\n super().__init__()\n self.input_layernorm = nn.LayerNorm(config.hidden_size,\n eps=config.layer_norm_eps)\n self.self_attn = PhiAttention(config, cache_config, quant_config)\n self.mlp = PhiMLP(config, quant_config)\n\n def forward(\n self,\n position_ids: torch.Tensor,\n hidden_states: torch.Tensor,\n kv_cache: torch.Tensor,\n attn_metadata: AttentionMetadata,\n ) -> torch.Tensor:\n residual = hidden_states\n hidden_states = self.input_layernorm(hidden_states)\n attn_outputs = self.self_attn(\n position_ids=position_ids,\n hidden_states=hidden_states,\n kv_cache=kv_cache,\n attn_metadata=attn_metadata,\n )\n feed_forward_hidden_states = self.mlp(hidden_states)\n hidden_states = attn_outputs + feed_forward_hidden_states + residual\n return hidden_states\n\n\nclass PhiModel(nn.Module):\n\n def __init__(self,\n config: PretrainedConfig,\n cache_config: Optional[CacheConfig] = None,\n quant_config: Optional[QuantizationConfig] = None):\n super().__init__()\n self.config = config\n self.quant_config = quant_config\n self.embed_tokens = VocabParallelEmbedding(config.vocab_size,\n config.hidden_size)\n self.layers = nn.ModuleList([\n PhiLayer(config, cache_config, quant_config)\n for _ in range(config.num_hidden_layers)\n ])\n self.final_layernorm = nn.LayerNorm(config.hidden_size,\n eps=config.layer_norm_eps)\n\n def forward(\n self,\n input_ids: torch.Tensor,\n positions: torch.Tensor,\n kv_caches: List[torch.Tensor],\n attn_metadata: AttentionMetadata,\n ) -> torch.Tensor:\n hidden_states = self.embed_tokens(input_ids)\n for i in range(self.config.num_hidden_layers):\n layer = self.layers[i]\n hidden_states = layer(\n positions,\n hidden_states,\n kv_caches[i],\n attn_metadata,\n )\n\n hidden_states = self.final_layernorm(hidden_states)\n\n return hidden_states\n\n\nclass PhiForCausalLM(nn.Module):\n\n def __init__(self,\n config: PretrainedConfig,\n cache_config: Optional[CacheConfig] = None,\n quant_config: Optional[QuantizationConfig] = None):\n super().__init__()\n self.config = config\n self.quant_config = quant_config\n\n self.model = PhiModel(config, cache_config, quant_config)\n\n self.lm_head = ParallelLMHead(config.vocab_size,\n config.hidden_size,\n bias=True)\n self.logits_processor = LogitsProcessor(config.vocab_size)\n self.sampler = Sampler()\n\n def forward(\n self,\n input_ids: torch.Tensor,\n positions: torch.Tensor,\n kv_caches: List[torch.Tensor],\n attn_metadata: AttentionMetadata,\n ) -> torch.Tensor:\n hidden_states = self.model(input_ids, positions, kv_caches,\n attn_metadata)\n\n return hidden_states\n\n def compute_logits(self, hidden_states: torch.Tensor,\n sampling_metadata: SamplingMetadata) -> torch.Tensor:\n logits = self.logits_processor(self.lm_head.weight, hidden_states,\n sampling_metadata, self.lm_head.bias)\n return logits\n\n def sample(\n self,\n logits: torch.Tensor,\n sampling_metadata: SamplingMetadata,\n ) -> Optional[SamplerOutput]:\n next_tokens = self.sampler(logits, sampling_metadata)\n return next_tokens\n\n def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):\n stacked_params_mapping = [\n # (param_name, shard_name, shard_id)\n (\"qkv_proj\", \"q_proj\", \"q\"),\n (\"qkv_proj\", \"k_proj\", \"k\"),\n (\"qkv_proj\", \"v_proj\", \"v\")\n ]\n params_dict = dict(self.named_parameters())\n\n for name, loaded_weight in weights:\n if \"rotary_emb.inv_freq\" in name:\n continue\n\n for (param_name, weight_name, shard_id) in stacked_params_mapping:\n if weight_name not in name:\n continue\n name = name.replace(weight_name, param_name)\n # Skip loading extra bias for GPTQ models.\n if name.endswith(\".bias\") and name not in params_dict:\n continue\n param = params_dict[name]\n weight_loader = param.weight_loader\n weight_loader(param, loaded_weight, shard_id)\n break\n else:\n # Skip loading extra bias for GPTQ models.\n if name.endswith(\".bias\") and name not in params_dict:\n continue\n # pylint: disable=E1136\n\n param = params_dict[name]\n weight_loader = getattr(param, \"weight_loader\",\n default_weight_loader)\n weight_loader(param, loaded_weight)\n", "path": "vllm/model_executor/models/phi.py"}]} | 3,874 | 402 |
gh_patches_debug_28828 | rasdani/github-patches | git_diff | edgedb__edgedb-1753 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Rename some string handling functions and deprecate the old versions.
From discussion in Slack a point was raised:
> Just noticed something now of an engineering nature though:
> https://edgedb.com/docs/edgeql/funcops/string#function::std::str_lpad
> This reminded me of similar methods in Rust that were eventually deprecated in favour of calling them "start" and "end" instead of "right" and "left" due to languages that write right to left (and even up to down):
> https://doc.rust-lang.org/std/primitive.str.html#method.trim_left
> The new methods did the exact same thing but were just given different names, while the old method names were left alone to accommodate legacy code.
This means that we want to rename string handling functions to use "start" and "end" such as `std::str_trim_start`, etc. The old functions should remain for some time, but they need to be marked as deprecated. To this end we also introduce a `deprecated` annotation which can mark deprecated items as well as provide a useful note like what should be used instead.
The documentation needs to include deprecated functions, but they should also be clearly labeled as such.
</issue>
<code>
[start of edb/edgeql/pygments/meta.py]
1 # AUTOGENERATED BY EdgeDB WITH
2 # $ edb gen-meta-grammars edgeql
3
4
5 from __future__ import annotations
6
7
8 class EdgeQL:
9 reserved_keywords = (
10 "__source__",
11 "__std__",
12 "__subject__",
13 "__type__",
14 "abort",
15 "alter",
16 "analyze",
17 "and",
18 "anyarray",
19 "anytuple",
20 "anytype",
21 "begin",
22 "case",
23 "check",
24 "commit",
25 "configure",
26 "create",
27 "deallocate",
28 "declare",
29 "delete",
30 "describe",
31 "detached",
32 "discard",
33 "distinct",
34 "do",
35 "drop",
36 "else",
37 "empty",
38 "end",
39 "execute",
40 "exists",
41 "explain",
42 "extending",
43 "fetch",
44 "filter",
45 "for",
46 "get",
47 "global",
48 "grant",
49 "group",
50 "if",
51 "ilike",
52 "import",
53 "in",
54 "insert",
55 "introspect",
56 "is",
57 "like",
58 "limit",
59 "listen",
60 "load",
61 "lock",
62 "match",
63 "module",
64 "move",
65 "not",
66 "notify",
67 "offset",
68 "optional",
69 "or",
70 "order",
71 "over",
72 "partition",
73 "policy",
74 "populate",
75 "prepare",
76 "raise",
77 "refresh",
78 "reindex",
79 "release",
80 "reset",
81 "revoke",
82 "rollback",
83 "select",
84 "set",
85 "start",
86 "typeof",
87 "union",
88 "update",
89 "variadic",
90 "when",
91 "window",
92 "with",
93 )
94 unreserved_keywords = (
95 "abstract",
96 "after",
97 "alias",
98 "all",
99 "allow",
100 "annotation",
101 "as",
102 "asc",
103 "assignment",
104 "before",
105 "by",
106 "cardinality",
107 "cast",
108 "config",
109 "constraint",
110 "current",
111 "database",
112 "ddl",
113 "default",
114 "deferrable",
115 "deferred",
116 "delegated",
117 "desc",
118 "emit",
119 "explicit",
120 "expression",
121 "final",
122 "first",
123 "from",
124 "function",
125 "implicit",
126 "index",
127 "infix",
128 "inheritable",
129 "into",
130 "isolation",
131 "json",
132 "last",
133 "link",
134 "migration",
135 "multi",
136 "named",
137 "object",
138 "of",
139 "oids",
140 "on",
141 "only",
142 "operator",
143 "overloaded",
144 "postfix",
145 "prefix",
146 "property",
147 "pseudo",
148 "read",
149 "rename",
150 "repeatable",
151 "required",
152 "restrict",
153 "role",
154 "roles",
155 "savepoint",
156 "scalar",
157 "schema",
158 "sdl",
159 "serializable",
160 "session",
161 "single",
162 "source",
163 "superuser",
164 "system",
165 "target",
166 "ternary",
167 "text",
168 "then",
169 "to",
170 "transaction",
171 "type",
172 "using",
173 "verbose",
174 "view",
175 "write",
176 )
177 bool_literals = (
178 "false",
179 "true",
180 )
181 type_builtins = (
182 "BaseObject",
183 "Object",
184 "anyenum",
185 "anyfloat",
186 "anyint",
187 "anynumeric",
188 "anyreal",
189 "anyscalar",
190 "array",
191 "bigint",
192 "bool",
193 "bytes",
194 "datetime",
195 "decimal",
196 "duration",
197 "enum",
198 "float32",
199 "float64",
200 "int16",
201 "int32",
202 "int64",
203 "json",
204 "local_date",
205 "local_datetime",
206 "local_time",
207 "sequence",
208 "str",
209 "tuple",
210 "uuid",
211 )
212 module_builtins = (
213 "cal",
214 "cfg",
215 "math",
216 "schema",
217 "std",
218 "stdgraphql",
219 "sys",
220 )
221 constraint_builtins = (
222 "constraint",
223 "exclusive",
224 "expression",
225 "len_value",
226 "max_ex_value",
227 "max_len_value",
228 "max_value",
229 "min_ex_value",
230 "min_len_value",
231 "min_value",
232 "one_of",
233 "regexp",
234 )
235 fn_builtins = (
236 "abs",
237 "advisory_lock",
238 "advisory_unlock",
239 "advisory_unlock_all",
240 "all",
241 "any",
242 "array_agg",
243 "array_get",
244 "array_join",
245 "array_unpack",
246 "bytes_get_bit",
247 "ceil",
248 "contains",
249 "count",
250 "date_get",
251 "datetime_current",
252 "datetime_get",
253 "datetime_of_statement",
254 "datetime_of_transaction",
255 "datetime_truncate",
256 "duration_to_seconds",
257 "duration_truncate",
258 "enumerate",
259 "find",
260 "floor",
261 "get_current_database",
262 "get_transaction_isolation",
263 "get_version",
264 "get_version_as_str",
265 "json_array_unpack",
266 "json_get",
267 "json_object_unpack",
268 "json_typeof",
269 "len",
270 "lg",
271 "ln",
272 "log",
273 "max",
274 "mean",
275 "min",
276 "random",
277 "re_match",
278 "re_match_all",
279 "re_replace",
280 "re_test",
281 "round",
282 "sleep",
283 "stddev",
284 "stddev_pop",
285 "str_lower",
286 "str_lpad",
287 "str_ltrim",
288 "str_repeat",
289 "str_rpad",
290 "str_rtrim",
291 "str_split",
292 "str_title",
293 "str_trim",
294 "str_upper",
295 "sum",
296 "time_get",
297 "to_bigint",
298 "to_datetime",
299 "to_decimal",
300 "to_duration",
301 "to_float32",
302 "to_float64",
303 "to_int16",
304 "to_int32",
305 "to_int64",
306 "to_json",
307 "to_local_date",
308 "to_local_datetime",
309 "to_local_time",
310 "to_str",
311 "uuid_generate_v1mc",
312 "var",
313 "var_pop",
314 )
315 operators = (
316 "!=",
317 "%",
318 "*",
319 "+",
320 "++",
321 "-",
322 "/",
323 "//",
324 ":=",
325 "<",
326 "<=",
327 "=",
328 ">",
329 ">=",
330 "?!=",
331 "?=",
332 "??",
333 "^",
334 )
335 navigation = (
336 ".<",
337 ".>",
338 "@",
339 ".",
340 )
341
[end of edb/edgeql/pygments/meta.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/edb/edgeql/pygments/meta.py b/edb/edgeql/pygments/meta.py
--- a/edb/edgeql/pygments/meta.py
+++ b/edb/edgeql/pygments/meta.py
@@ -106,6 +106,7 @@
"cardinality",
"cast",
"config",
+ "conflict",
"constraint",
"current",
"database",
@@ -139,13 +140,17 @@
"oids",
"on",
"only",
+ "onto",
"operator",
"overloaded",
+ "owned",
"postfix",
"prefix",
"property",
+ "proposed",
"pseudo",
"read",
+ "reject",
"rename",
"repeatable",
"required",
@@ -169,6 +174,7 @@
"to",
"transaction",
"type",
+ "unless",
"using",
"verbose",
"view",
@@ -285,12 +291,16 @@
"str_lower",
"str_lpad",
"str_ltrim",
+ "str_pad_end",
+ "str_pad_start",
"str_repeat",
"str_rpad",
"str_rtrim",
"str_split",
"str_title",
"str_trim",
+ "str_trim_end",
+ "str_trim_start",
"str_upper",
"sum",
"time_get",
| {"golden_diff": "diff --git a/edb/edgeql/pygments/meta.py b/edb/edgeql/pygments/meta.py\n--- a/edb/edgeql/pygments/meta.py\n+++ b/edb/edgeql/pygments/meta.py\n@@ -106,6 +106,7 @@\n \"cardinality\",\n \"cast\",\n \"config\",\n+ \"conflict\",\n \"constraint\",\n \"current\",\n \"database\",\n@@ -139,13 +140,17 @@\n \"oids\",\n \"on\",\n \"only\",\n+ \"onto\",\n \"operator\",\n \"overloaded\",\n+ \"owned\",\n \"postfix\",\n \"prefix\",\n \"property\",\n+ \"proposed\",\n \"pseudo\",\n \"read\",\n+ \"reject\",\n \"rename\",\n \"repeatable\",\n \"required\",\n@@ -169,6 +174,7 @@\n \"to\",\n \"transaction\",\n \"type\",\n+ \"unless\",\n \"using\",\n \"verbose\",\n \"view\",\n@@ -285,12 +291,16 @@\n \"str_lower\",\n \"str_lpad\",\n \"str_ltrim\",\n+ \"str_pad_end\",\n+ \"str_pad_start\",\n \"str_repeat\",\n \"str_rpad\",\n \"str_rtrim\",\n \"str_split\",\n \"str_title\",\n \"str_trim\",\n+ \"str_trim_end\",\n+ \"str_trim_start\",\n \"str_upper\",\n \"sum\",\n \"time_get\",\n", "issue": "Rename some string handling functions and deprecate the old versions.\nFrom discussion in Slack a point was raised:\r\n> Just noticed something now of an engineering nature though:\r\n> https://edgedb.com/docs/edgeql/funcops/string#function::std::str_lpad\r\n> This reminded me of similar methods in Rust that were eventually deprecated in favour of calling them \"start\" and \"end\" instead of \"right\" and \"left\" due to languages that write right to left (and even up to down):\r\n> https://doc.rust-lang.org/std/primitive.str.html#method.trim_left\r\n> The new methods did the exact same thing but were just given different names, while the old method names were left alone to accommodate legacy code.\r\n\r\nThis means that we want to rename string handling functions to use \"start\" and \"end\" such as `std::str_trim_start`, etc. The old functions should remain for some time, but they need to be marked as deprecated. To this end we also introduce a `deprecated` annotation which can mark deprecated items as well as provide a useful note like what should be used instead.\r\n\r\nThe documentation needs to include deprecated functions, but they should also be clearly labeled as such.\n", "before_files": [{"content": "# AUTOGENERATED BY EdgeDB WITH\n# $ edb gen-meta-grammars edgeql\n\n\nfrom __future__ import annotations\n\n\nclass EdgeQL:\n reserved_keywords = (\n \"__source__\",\n \"__std__\",\n \"__subject__\",\n \"__type__\",\n \"abort\",\n \"alter\",\n \"analyze\",\n \"and\",\n \"anyarray\",\n \"anytuple\",\n \"anytype\",\n \"begin\",\n \"case\",\n \"check\",\n \"commit\",\n \"configure\",\n \"create\",\n \"deallocate\",\n \"declare\",\n \"delete\",\n \"describe\",\n \"detached\",\n \"discard\",\n \"distinct\",\n \"do\",\n \"drop\",\n \"else\",\n \"empty\",\n \"end\",\n \"execute\",\n \"exists\",\n \"explain\",\n \"extending\",\n \"fetch\",\n \"filter\",\n \"for\",\n \"get\",\n \"global\",\n \"grant\",\n \"group\",\n \"if\",\n \"ilike\",\n \"import\",\n \"in\",\n \"insert\",\n \"introspect\",\n \"is\",\n \"like\",\n \"limit\",\n \"listen\",\n \"load\",\n \"lock\",\n \"match\",\n \"module\",\n \"move\",\n \"not\",\n \"notify\",\n \"offset\",\n \"optional\",\n \"or\",\n \"order\",\n \"over\",\n \"partition\",\n \"policy\",\n \"populate\",\n \"prepare\",\n \"raise\",\n \"refresh\",\n \"reindex\",\n \"release\",\n \"reset\",\n \"revoke\",\n \"rollback\",\n \"select\",\n \"set\",\n \"start\",\n \"typeof\",\n \"union\",\n \"update\",\n \"variadic\",\n \"when\",\n \"window\",\n \"with\",\n )\n unreserved_keywords = (\n \"abstract\",\n \"after\",\n \"alias\",\n \"all\",\n \"allow\",\n \"annotation\",\n \"as\",\n \"asc\",\n \"assignment\",\n \"before\",\n \"by\",\n \"cardinality\",\n \"cast\",\n \"config\",\n \"constraint\",\n \"current\",\n \"database\",\n \"ddl\",\n \"default\",\n \"deferrable\",\n \"deferred\",\n \"delegated\",\n \"desc\",\n \"emit\",\n \"explicit\",\n \"expression\",\n \"final\",\n \"first\",\n \"from\",\n \"function\",\n \"implicit\",\n \"index\",\n \"infix\",\n \"inheritable\",\n \"into\",\n \"isolation\",\n \"json\",\n \"last\",\n \"link\",\n \"migration\",\n \"multi\",\n \"named\",\n \"object\",\n \"of\",\n \"oids\",\n \"on\",\n \"only\",\n \"operator\",\n \"overloaded\",\n \"postfix\",\n \"prefix\",\n \"property\",\n \"pseudo\",\n \"read\",\n \"rename\",\n \"repeatable\",\n \"required\",\n \"restrict\",\n \"role\",\n \"roles\",\n \"savepoint\",\n \"scalar\",\n \"schema\",\n \"sdl\",\n \"serializable\",\n \"session\",\n \"single\",\n \"source\",\n \"superuser\",\n \"system\",\n \"target\",\n \"ternary\",\n \"text\",\n \"then\",\n \"to\",\n \"transaction\",\n \"type\",\n \"using\",\n \"verbose\",\n \"view\",\n \"write\",\n )\n bool_literals = (\n \"false\",\n \"true\",\n )\n type_builtins = (\n \"BaseObject\",\n \"Object\",\n \"anyenum\",\n \"anyfloat\",\n \"anyint\",\n \"anynumeric\",\n \"anyreal\",\n \"anyscalar\",\n \"array\",\n \"bigint\",\n \"bool\",\n \"bytes\",\n \"datetime\",\n \"decimal\",\n \"duration\",\n \"enum\",\n \"float32\",\n \"float64\",\n \"int16\",\n \"int32\",\n \"int64\",\n \"json\",\n \"local_date\",\n \"local_datetime\",\n \"local_time\",\n \"sequence\",\n \"str\",\n \"tuple\",\n \"uuid\",\n )\n module_builtins = (\n \"cal\",\n \"cfg\",\n \"math\",\n \"schema\",\n \"std\",\n \"stdgraphql\",\n \"sys\",\n )\n constraint_builtins = (\n \"constraint\",\n \"exclusive\",\n \"expression\",\n \"len_value\",\n \"max_ex_value\",\n \"max_len_value\",\n \"max_value\",\n \"min_ex_value\",\n \"min_len_value\",\n \"min_value\",\n \"one_of\",\n \"regexp\",\n )\n fn_builtins = (\n \"abs\",\n \"advisory_lock\",\n \"advisory_unlock\",\n \"advisory_unlock_all\",\n \"all\",\n \"any\",\n \"array_agg\",\n \"array_get\",\n \"array_join\",\n \"array_unpack\",\n \"bytes_get_bit\",\n \"ceil\",\n \"contains\",\n \"count\",\n \"date_get\",\n \"datetime_current\",\n \"datetime_get\",\n \"datetime_of_statement\",\n \"datetime_of_transaction\",\n \"datetime_truncate\",\n \"duration_to_seconds\",\n \"duration_truncate\",\n \"enumerate\",\n \"find\",\n \"floor\",\n \"get_current_database\",\n \"get_transaction_isolation\",\n \"get_version\",\n \"get_version_as_str\",\n \"json_array_unpack\",\n \"json_get\",\n \"json_object_unpack\",\n \"json_typeof\",\n \"len\",\n \"lg\",\n \"ln\",\n \"log\",\n \"max\",\n \"mean\",\n \"min\",\n \"random\",\n \"re_match\",\n \"re_match_all\",\n \"re_replace\",\n \"re_test\",\n \"round\",\n \"sleep\",\n \"stddev\",\n \"stddev_pop\",\n \"str_lower\",\n \"str_lpad\",\n \"str_ltrim\",\n \"str_repeat\",\n \"str_rpad\",\n \"str_rtrim\",\n \"str_split\",\n \"str_title\",\n \"str_trim\",\n \"str_upper\",\n \"sum\",\n \"time_get\",\n \"to_bigint\",\n \"to_datetime\",\n \"to_decimal\",\n \"to_duration\",\n \"to_float32\",\n \"to_float64\",\n \"to_int16\",\n \"to_int32\",\n \"to_int64\",\n \"to_json\",\n \"to_local_date\",\n \"to_local_datetime\",\n \"to_local_time\",\n \"to_str\",\n \"uuid_generate_v1mc\",\n \"var\",\n \"var_pop\",\n )\n operators = (\n \"!=\",\n \"%\",\n \"*\",\n \"+\",\n \"++\",\n \"-\",\n \"/\",\n \"//\",\n \":=\",\n \"<\",\n \"<=\",\n \"=\",\n \">\",\n \">=\",\n \"?!=\",\n \"?=\",\n \"??\",\n \"^\",\n )\n navigation = (\n \".<\",\n \".>\",\n \"@\",\n \".\",\n )\n", "path": "edb/edgeql/pygments/meta.py"}]} | 3,225 | 335 |
gh_patches_debug_16886 | rasdani/github-patches | git_diff | urllib3__urllib3-2335 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Add decode_content parameter to top-level APIs
Like the title says, add `decode_content` to the top-level APIs `urllib3.request()`.
See https://github.com/urllib3/urllib3/commit/ddf7361ac0467431a2f3df6ba346c9c506c29d56 for an example.
</issue>
<code>
[start of src/urllib3/__init__.py]
1 """
2 Python HTTP library with thread-safe connection pooling, file post support, user friendly, and more
3 """
4
5 # Set default logging handler to avoid "No handler found" warnings.
6 import logging
7 import warnings
8 from logging import NullHandler
9 from typing import Mapping, Optional, Type, Union
10
11 from . import exceptions
12 from ._collections import HTTPHeaderDict
13 from ._version import __version__
14 from .connection import _TYPE_BODY
15 from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool, connection_from_url
16 from .filepost import _TYPE_FIELDS, encode_multipart_formdata
17 from .poolmanager import PoolManager, ProxyManager, proxy_from_url
18 from .response import BaseHTTPResponse, HTTPResponse
19 from .util.request import make_headers
20 from .util.retry import Retry
21 from .util.timeout import Timeout
22
23 __author__ = "Andrey Petrov ([email protected])"
24 __license__ = "MIT"
25 __version__ = __version__
26
27 __all__ = (
28 "HTTPConnectionPool",
29 "HTTPHeaderDict",
30 "HTTPSConnectionPool",
31 "PoolManager",
32 "ProxyManager",
33 "HTTPResponse",
34 "Retry",
35 "Timeout",
36 "add_stderr_logger",
37 "connection_from_url",
38 "disable_warnings",
39 "encode_multipart_formdata",
40 "make_headers",
41 "proxy_from_url",
42 "request",
43 )
44
45 logging.getLogger(__name__).addHandler(NullHandler())
46
47
48 def add_stderr_logger(level: int = logging.DEBUG) -> logging.StreamHandler:
49 """
50 Helper for quickly adding a StreamHandler to the logger. Useful for
51 debugging.
52
53 Returns the handler after adding it.
54 """
55 # This method needs to be in this __init__.py to get the __name__ correct
56 # even if urllib3 is vendored within another package.
57 logger = logging.getLogger(__name__)
58 handler = logging.StreamHandler()
59 handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(message)s"))
60 logger.addHandler(handler)
61 logger.setLevel(level)
62 logger.debug("Added a stderr logging handler to logger: %s", __name__)
63 return handler
64
65
66 # ... Clean up.
67 del NullHandler
68
69
70 # All warning filters *must* be appended unless you're really certain that they
71 # shouldn't be: otherwise, it's very hard for users to use most Python
72 # mechanisms to silence them.
73 # SecurityWarning's always go off by default.
74 warnings.simplefilter("always", exceptions.SecurityWarning, append=True)
75 # InsecurePlatformWarning's don't vary between requests, so we keep it default.
76 warnings.simplefilter("default", exceptions.InsecurePlatformWarning, append=True)
77 # SNIMissingWarnings should go off only once.
78 warnings.simplefilter("default", exceptions.SNIMissingWarning, append=True)
79
80
81 def disable_warnings(category: Type[Warning] = exceptions.HTTPWarning) -> None:
82 """
83 Helper for quickly disabling all urllib3 warnings.
84 """
85 warnings.simplefilter("ignore", category)
86
87
88 _DEFAULT_POOL = PoolManager()
89
90
91 def request(
92 method: str,
93 url: str,
94 *,
95 body: Optional[_TYPE_BODY] = None,
96 fields: Optional[_TYPE_FIELDS] = None,
97 headers: Optional[Mapping[str, str]] = None,
98 preload_content: Optional[bool] = True,
99 redirect: Optional[bool] = True,
100 retries: Optional[Union[Retry, bool, int]] = None,
101 timeout: Optional[Union[Timeout, float, int]] = 3,
102 ) -> BaseHTTPResponse:
103 """
104 A convenience, top-level request method. It uses a module-global ``PoolManager`` instance.
105 Therefore, its side effects could be shared across dependencies relying on it.
106 To avoid side effects create a new ``PoolManager`` instance and use it instead.
107 The method does not accept low-level ``**urlopen_kw`` keyword arguments.
108 """
109
110 return _DEFAULT_POOL.request(
111 method,
112 url,
113 body=body,
114 fields=fields,
115 headers=headers,
116 preload_content=preload_content,
117 redirect=redirect,
118 retries=retries,
119 timeout=timeout,
120 )
121
[end of src/urllib3/__init__.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/src/urllib3/__init__.py b/src/urllib3/__init__.py
--- a/src/urllib3/__init__.py
+++ b/src/urllib3/__init__.py
@@ -96,6 +96,7 @@
fields: Optional[_TYPE_FIELDS] = None,
headers: Optional[Mapping[str, str]] = None,
preload_content: Optional[bool] = True,
+ decode_content: Optional[bool] = True,
redirect: Optional[bool] = True,
retries: Optional[Union[Retry, bool, int]] = None,
timeout: Optional[Union[Timeout, float, int]] = 3,
@@ -114,6 +115,7 @@
fields=fields,
headers=headers,
preload_content=preload_content,
+ decode_content=decode_content,
redirect=redirect,
retries=retries,
timeout=timeout,
| {"golden_diff": "diff --git a/src/urllib3/__init__.py b/src/urllib3/__init__.py\n--- a/src/urllib3/__init__.py\n+++ b/src/urllib3/__init__.py\n@@ -96,6 +96,7 @@\n fields: Optional[_TYPE_FIELDS] = None,\n headers: Optional[Mapping[str, str]] = None,\n preload_content: Optional[bool] = True,\n+ decode_content: Optional[bool] = True,\n redirect: Optional[bool] = True,\n retries: Optional[Union[Retry, bool, int]] = None,\n timeout: Optional[Union[Timeout, float, int]] = 3,\n@@ -114,6 +115,7 @@\n fields=fields,\n headers=headers,\n preload_content=preload_content,\n+ decode_content=decode_content,\n redirect=redirect,\n retries=retries,\n timeout=timeout,\n", "issue": "Add decode_content parameter to top-level APIs\nLike the title says, add `decode_content` to the top-level APIs `urllib3.request()`.\r\n\r\nSee https://github.com/urllib3/urllib3/commit/ddf7361ac0467431a2f3df6ba346c9c506c29d56 for an example.\n", "before_files": [{"content": "\"\"\"\nPython HTTP library with thread-safe connection pooling, file post support, user friendly, and more\n\"\"\"\n\n# Set default logging handler to avoid \"No handler found\" warnings.\nimport logging\nimport warnings\nfrom logging import NullHandler\nfrom typing import Mapping, Optional, Type, Union\n\nfrom . import exceptions\nfrom ._collections import HTTPHeaderDict\nfrom ._version import __version__\nfrom .connection import _TYPE_BODY\nfrom .connectionpool import HTTPConnectionPool, HTTPSConnectionPool, connection_from_url\nfrom .filepost import _TYPE_FIELDS, encode_multipart_formdata\nfrom .poolmanager import PoolManager, ProxyManager, proxy_from_url\nfrom .response import BaseHTTPResponse, HTTPResponse\nfrom .util.request import make_headers\nfrom .util.retry import Retry\nfrom .util.timeout import Timeout\n\n__author__ = \"Andrey Petrov ([email protected])\"\n__license__ = \"MIT\"\n__version__ = __version__\n\n__all__ = (\n \"HTTPConnectionPool\",\n \"HTTPHeaderDict\",\n \"HTTPSConnectionPool\",\n \"PoolManager\",\n \"ProxyManager\",\n \"HTTPResponse\",\n \"Retry\",\n \"Timeout\",\n \"add_stderr_logger\",\n \"connection_from_url\",\n \"disable_warnings\",\n \"encode_multipart_formdata\",\n \"make_headers\",\n \"proxy_from_url\",\n \"request\",\n)\n\nlogging.getLogger(__name__).addHandler(NullHandler())\n\n\ndef add_stderr_logger(level: int = logging.DEBUG) -> logging.StreamHandler:\n \"\"\"\n Helper for quickly adding a StreamHandler to the logger. Useful for\n debugging.\n\n Returns the handler after adding it.\n \"\"\"\n # This method needs to be in this __init__.py to get the __name__ correct\n # even if urllib3 is vendored within another package.\n logger = logging.getLogger(__name__)\n handler = logging.StreamHandler()\n handler.setFormatter(logging.Formatter(\"%(asctime)s %(levelname)s %(message)s\"))\n logger.addHandler(handler)\n logger.setLevel(level)\n logger.debug(\"Added a stderr logging handler to logger: %s\", __name__)\n return handler\n\n\n# ... Clean up.\ndel NullHandler\n\n\n# All warning filters *must* be appended unless you're really certain that they\n# shouldn't be: otherwise, it's very hard for users to use most Python\n# mechanisms to silence them.\n# SecurityWarning's always go off by default.\nwarnings.simplefilter(\"always\", exceptions.SecurityWarning, append=True)\n# InsecurePlatformWarning's don't vary between requests, so we keep it default.\nwarnings.simplefilter(\"default\", exceptions.InsecurePlatformWarning, append=True)\n# SNIMissingWarnings should go off only once.\nwarnings.simplefilter(\"default\", exceptions.SNIMissingWarning, append=True)\n\n\ndef disable_warnings(category: Type[Warning] = exceptions.HTTPWarning) -> None:\n \"\"\"\n Helper for quickly disabling all urllib3 warnings.\n \"\"\"\n warnings.simplefilter(\"ignore\", category)\n\n\n_DEFAULT_POOL = PoolManager()\n\n\ndef request(\n method: str,\n url: str,\n *,\n body: Optional[_TYPE_BODY] = None,\n fields: Optional[_TYPE_FIELDS] = None,\n headers: Optional[Mapping[str, str]] = None,\n preload_content: Optional[bool] = True,\n redirect: Optional[bool] = True,\n retries: Optional[Union[Retry, bool, int]] = None,\n timeout: Optional[Union[Timeout, float, int]] = 3,\n) -> BaseHTTPResponse:\n \"\"\"\n A convenience, top-level request method. It uses a module-global ``PoolManager`` instance.\n Therefore, its side effects could be shared across dependencies relying on it.\n To avoid side effects create a new ``PoolManager`` instance and use it instead.\n The method does not accept low-level ``**urlopen_kw`` keyword arguments.\n \"\"\"\n\n return _DEFAULT_POOL.request(\n method,\n url,\n body=body,\n fields=fields,\n headers=headers,\n preload_content=preload_content,\n redirect=redirect,\n retries=retries,\n timeout=timeout,\n )\n", "path": "src/urllib3/__init__.py"}]} | 1,760 | 203 |
gh_patches_debug_24800 | rasdani/github-patches | git_diff | cookiecutter__cookiecutter-1493 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Need help with generating GUID/UUID values for context variables
* Cookiecutter version: 1.6
* Template project url: none
* Python version: 3.7 (virtual env created using win python 3.7 x64)
* Operating System: Windows 10, 64 Bit
### Description:
First off many thanks for creating this project !
Here is some context of what I am trying to do and where I need some guidance
* I am trying to use CC to generate new a Visual Studio 2017 solution and project files with a particular folder/file organization that I like
* I was able to most of it working but for the below:
* Parts of the above project, solution files involves generating several unique GUIDs
* my first approach was creating a `pre_gen_project.py` inside the `hooks` folder and update/create new variables that could be added to the ones loaded from `cookiecutter.json` or entered by the user
* I was however blocked as I could not figure out how to access the context being used by CC and the jinja2 engine
* I proceeded to go over the many issues on github and found some related ones like the following: #60, #102, #180, #288 but no clear answer on how to achieve what I'd like
* I also followed some others issues that suggested creating custom jinja2 extension/filter (#944) but I couldnt figure out how or where to put them in the template folder so the cookiecutter.exe can identify them and pick them up
* Lastly, I also tried going over the CC source code and tried to create a new executable from my script (similar to `cli.py`) that passes the guids via the `extra_context` to `cookiecutter.main(...)` but ran into some other problems that I am still trying to figure out
Appreciate any pointers on how I can inject GUID values for the context variables
</issue>
<code>
[start of cookiecutter/extensions.py]
1 """Jinja2 extensions."""
2 import json
3 import string
4 from secrets import choice
5
6 from jinja2.ext import Extension
7 from slugify import slugify as pyslugify
8
9
10 class JsonifyExtension(Extension):
11 """Jinja2 extension to convert a Python object to JSON."""
12
13 def __init__(self, environment):
14 """Initialize the extension with the given environment."""
15 super(JsonifyExtension, self).__init__(environment)
16
17 def jsonify(obj):
18 return json.dumps(obj, sort_keys=True, indent=4)
19
20 environment.filters['jsonify'] = jsonify
21
22
23 class RandomStringExtension(Extension):
24 """Jinja2 extension to create a random string."""
25
26 def __init__(self, environment):
27 """Jinja2 Extension Constructor."""
28 super(RandomStringExtension, self).__init__(environment)
29
30 def random_ascii_string(length, punctuation=False):
31 if punctuation:
32 corpus = "".join((string.ascii_letters, string.punctuation))
33 else:
34 corpus = string.ascii_letters
35 return "".join(choice(corpus) for _ in range(length))
36
37 environment.globals.update(random_ascii_string=random_ascii_string)
38
39
40 class SlugifyExtension(Extension):
41 """Jinja2 Extension to slugify string."""
42
43 def __init__(self, environment):
44 """Jinja2 Extension constructor."""
45 super(SlugifyExtension, self).__init__(environment)
46
47 def slugify(value, **kwargs):
48 """Slugifies the value."""
49 return pyslugify(value, **kwargs)
50
51 environment.filters['slugify'] = slugify
52
[end of cookiecutter/extensions.py]
[start of cookiecutter/environment.py]
1 """Jinja2 environment and extensions loading."""
2 from jinja2 import Environment, StrictUndefined
3
4 from cookiecutter.exceptions import UnknownExtension
5
6
7 class ExtensionLoaderMixin(object):
8 """Mixin providing sane loading of extensions specified in a given context.
9
10 The context is being extracted from the keyword arguments before calling
11 the next parent class in line of the child.
12 """
13
14 def __init__(self, **kwargs):
15 """Initialize the Jinja2 Environment object while loading extensions.
16
17 Does the following:
18
19 1. Establishes default_extensions (currently just a Time feature)
20 2. Reads extensions set in the cookiecutter.json _extensions key.
21 3. Attempts to load the extensions. Provides useful error if fails.
22 """
23 context = kwargs.pop('context', {})
24
25 default_extensions = [
26 'cookiecutter.extensions.JsonifyExtension',
27 'cookiecutter.extensions.RandomStringExtension',
28 'cookiecutter.extensions.SlugifyExtension',
29 'jinja2_time.TimeExtension',
30 ]
31 extensions = default_extensions + self._read_extensions(context)
32
33 try:
34 super(ExtensionLoaderMixin, self).__init__(extensions=extensions, **kwargs)
35 except ImportError as err:
36 raise UnknownExtension('Unable to load extension: {}'.format(err))
37
38 def _read_extensions(self, context):
39 """Return list of extensions as str to be passed on to the Jinja2 env.
40
41 If context does not contain the relevant info, return an empty
42 list instead.
43 """
44 try:
45 extensions = context['cookiecutter']['_extensions']
46 except KeyError:
47 return []
48 else:
49 return [str(ext) for ext in extensions]
50
51
52 class StrictEnvironment(ExtensionLoaderMixin, Environment):
53 """Create strict Jinja2 environment.
54
55 Jinja2 environment will raise error on undefined variable in template-
56 rendering context.
57 """
58
59 def __init__(self, **kwargs):
60 """Set the standard Cookiecutter StrictEnvironment.
61
62 Also loading extensions defined in cookiecutter.json's _extensions key.
63 """
64 super(StrictEnvironment, self).__init__(undefined=StrictUndefined, **kwargs)
65
[end of cookiecutter/environment.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/cookiecutter/environment.py b/cookiecutter/environment.py
--- a/cookiecutter/environment.py
+++ b/cookiecutter/environment.py
@@ -26,6 +26,7 @@
'cookiecutter.extensions.JsonifyExtension',
'cookiecutter.extensions.RandomStringExtension',
'cookiecutter.extensions.SlugifyExtension',
+ 'cookiecutter.extensions.UUIDExtension',
'jinja2_time.TimeExtension',
]
extensions = default_extensions + self._read_extensions(context)
diff --git a/cookiecutter/extensions.py b/cookiecutter/extensions.py
--- a/cookiecutter/extensions.py
+++ b/cookiecutter/extensions.py
@@ -1,6 +1,7 @@
"""Jinja2 extensions."""
import json
import string
+import uuid
from secrets import choice
from jinja2.ext import Extension
@@ -49,3 +50,17 @@
return pyslugify(value, **kwargs)
environment.filters['slugify'] = slugify
+
+
+class UUIDExtension(Extension):
+ """Jinja2 Extension to generate uuid4 string."""
+
+ def __init__(self, environment):
+ """Jinja2 Extension constructor."""
+ super(UUIDExtension, self).__init__(environment)
+
+ def uuid4():
+ """Generate UUID4."""
+ return str(uuid.uuid4())
+
+ environment.globals.update(uuid4=uuid4)
| {"golden_diff": "diff --git a/cookiecutter/environment.py b/cookiecutter/environment.py\n--- a/cookiecutter/environment.py\n+++ b/cookiecutter/environment.py\n@@ -26,6 +26,7 @@\n 'cookiecutter.extensions.JsonifyExtension',\n 'cookiecutter.extensions.RandomStringExtension',\n 'cookiecutter.extensions.SlugifyExtension',\n+ 'cookiecutter.extensions.UUIDExtension',\n 'jinja2_time.TimeExtension',\n ]\n extensions = default_extensions + self._read_extensions(context)\ndiff --git a/cookiecutter/extensions.py b/cookiecutter/extensions.py\n--- a/cookiecutter/extensions.py\n+++ b/cookiecutter/extensions.py\n@@ -1,6 +1,7 @@\n \"\"\"Jinja2 extensions.\"\"\"\n import json\n import string\n+import uuid\n from secrets import choice\n \n from jinja2.ext import Extension\n@@ -49,3 +50,17 @@\n return pyslugify(value, **kwargs)\n \n environment.filters['slugify'] = slugify\n+\n+\n+class UUIDExtension(Extension):\n+ \"\"\"Jinja2 Extension to generate uuid4 string.\"\"\"\n+\n+ def __init__(self, environment):\n+ \"\"\"Jinja2 Extension constructor.\"\"\"\n+ super(UUIDExtension, self).__init__(environment)\n+\n+ def uuid4():\n+ \"\"\"Generate UUID4.\"\"\"\n+ return str(uuid.uuid4())\n+\n+ environment.globals.update(uuid4=uuid4)\n", "issue": "Need help with generating GUID/UUID values for context variables\n* Cookiecutter version: 1.6\r\n* Template project url: none\r\n* Python version: 3.7 (virtual env created using win python 3.7 x64)\r\n* Operating System: Windows 10, 64 Bit\r\n\r\n### Description:\r\n\r\nFirst off many thanks for creating this project !\r\nHere is some context of what I am trying to do and where I need some guidance\r\n* I am trying to use CC to generate new a Visual Studio 2017 solution and project files with a particular folder/file organization that I like\r\n* I was able to most of it working but for the below:\r\n* Parts of the above project, solution files involves generating several unique GUIDs\r\n* my first approach was creating a `pre_gen_project.py` inside the `hooks` folder and update/create new variables that could be added to the ones loaded from `cookiecutter.json` or entered by the user\r\n* I was however blocked as I could not figure out how to access the context being used by CC and the jinja2 engine \r\n* I proceeded to go over the many issues on github and found some related ones like the following: #60, #102, #180, #288 but no clear answer on how to achieve what I'd like\r\n* I also followed some others issues that suggested creating custom jinja2 extension/filter (#944) but I couldnt figure out how or where to put them in the template folder so the cookiecutter.exe can identify them and pick them up\r\n* Lastly, I also tried going over the CC source code and tried to create a new executable from my script (similar to `cli.py`) that passes the guids via the `extra_context` to `cookiecutter.main(...)` but ran into some other problems that I am still trying to figure out\r\n\r\nAppreciate any pointers on how I can inject GUID values for the context variables\n", "before_files": [{"content": "\"\"\"Jinja2 extensions.\"\"\"\nimport json\nimport string\nfrom secrets import choice\n\nfrom jinja2.ext import Extension\nfrom slugify import slugify as pyslugify\n\n\nclass JsonifyExtension(Extension):\n \"\"\"Jinja2 extension to convert a Python object to JSON.\"\"\"\n\n def __init__(self, environment):\n \"\"\"Initialize the extension with the given environment.\"\"\"\n super(JsonifyExtension, self).__init__(environment)\n\n def jsonify(obj):\n return json.dumps(obj, sort_keys=True, indent=4)\n\n environment.filters['jsonify'] = jsonify\n\n\nclass RandomStringExtension(Extension):\n \"\"\"Jinja2 extension to create a random string.\"\"\"\n\n def __init__(self, environment):\n \"\"\"Jinja2 Extension Constructor.\"\"\"\n super(RandomStringExtension, self).__init__(environment)\n\n def random_ascii_string(length, punctuation=False):\n if punctuation:\n corpus = \"\".join((string.ascii_letters, string.punctuation))\n else:\n corpus = string.ascii_letters\n return \"\".join(choice(corpus) for _ in range(length))\n\n environment.globals.update(random_ascii_string=random_ascii_string)\n\n\nclass SlugifyExtension(Extension):\n \"\"\"Jinja2 Extension to slugify string.\"\"\"\n\n def __init__(self, environment):\n \"\"\"Jinja2 Extension constructor.\"\"\"\n super(SlugifyExtension, self).__init__(environment)\n\n def slugify(value, **kwargs):\n \"\"\"Slugifies the value.\"\"\"\n return pyslugify(value, **kwargs)\n\n environment.filters['slugify'] = slugify\n", "path": "cookiecutter/extensions.py"}, {"content": "\"\"\"Jinja2 environment and extensions loading.\"\"\"\nfrom jinja2 import Environment, StrictUndefined\n\nfrom cookiecutter.exceptions import UnknownExtension\n\n\nclass ExtensionLoaderMixin(object):\n \"\"\"Mixin providing sane loading of extensions specified in a given context.\n\n The context is being extracted from the keyword arguments before calling\n the next parent class in line of the child.\n \"\"\"\n\n def __init__(self, **kwargs):\n \"\"\"Initialize the Jinja2 Environment object while loading extensions.\n\n Does the following:\n\n 1. Establishes default_extensions (currently just a Time feature)\n 2. Reads extensions set in the cookiecutter.json _extensions key.\n 3. Attempts to load the extensions. Provides useful error if fails.\n \"\"\"\n context = kwargs.pop('context', {})\n\n default_extensions = [\n 'cookiecutter.extensions.JsonifyExtension',\n 'cookiecutter.extensions.RandomStringExtension',\n 'cookiecutter.extensions.SlugifyExtension',\n 'jinja2_time.TimeExtension',\n ]\n extensions = default_extensions + self._read_extensions(context)\n\n try:\n super(ExtensionLoaderMixin, self).__init__(extensions=extensions, **kwargs)\n except ImportError as err:\n raise UnknownExtension('Unable to load extension: {}'.format(err))\n\n def _read_extensions(self, context):\n \"\"\"Return list of extensions as str to be passed on to the Jinja2 env.\n\n If context does not contain the relevant info, return an empty\n list instead.\n \"\"\"\n try:\n extensions = context['cookiecutter']['_extensions']\n except KeyError:\n return []\n else:\n return [str(ext) for ext in extensions]\n\n\nclass StrictEnvironment(ExtensionLoaderMixin, Environment):\n \"\"\"Create strict Jinja2 environment.\n\n Jinja2 environment will raise error on undefined variable in template-\n rendering context.\n \"\"\"\n\n def __init__(self, **kwargs):\n \"\"\"Set the standard Cookiecutter StrictEnvironment.\n\n Also loading extensions defined in cookiecutter.json's _extensions key.\n \"\"\"\n super(StrictEnvironment, self).__init__(undefined=StrictUndefined, **kwargs)\n", "path": "cookiecutter/environment.py"}]} | 1,968 | 311 |
gh_patches_debug_8560 | rasdani/github-patches | git_diff | uccser__cs-unplugged-197 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
Remove topic query from homepage
When the homepage is loaded, a database query is performed. This is currently not needed and should be removed.
Remove topic query from homepage
When the homepage is loaded, a database query is performed. This is currently not needed and should be removed.
</issue>
<code>
[start of csunplugged/general/views.py]
1 from django.views.generic import TemplateView
2
3
4 class GeneralIndexView(TemplateView):
5 template_name = 'general/index.html'
6
7 def get_context_data(self, **kwargs):
8 # TODO: Investigate if importing model from another
9 # app is sensible/best approach.
10 from topics.models import Topic
11 context = super(GeneralIndexView, self).get_context_data(**kwargs)
12 context['total_topics'] = Topic.objects.count()
13 return context
14
15
16 class GeneralAboutView(TemplateView):
17 template_name = 'general/about.html'
18
[end of csunplugged/general/views.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/csunplugged/general/views.py b/csunplugged/general/views.py
--- a/csunplugged/general/views.py
+++ b/csunplugged/general/views.py
@@ -4,14 +4,6 @@
class GeneralIndexView(TemplateView):
template_name = 'general/index.html'
- def get_context_data(self, **kwargs):
- # TODO: Investigate if importing model from another
- # app is sensible/best approach.
- from topics.models import Topic
- context = super(GeneralIndexView, self).get_context_data(**kwargs)
- context['total_topics'] = Topic.objects.count()
- return context
-
class GeneralAboutView(TemplateView):
template_name = 'general/about.html'
| {"golden_diff": "diff --git a/csunplugged/general/views.py b/csunplugged/general/views.py\n--- a/csunplugged/general/views.py\n+++ b/csunplugged/general/views.py\n@@ -4,14 +4,6 @@\n class GeneralIndexView(TemplateView):\n template_name = 'general/index.html'\n \n- def get_context_data(self, **kwargs):\n- # TODO: Investigate if importing model from another\n- # app is sensible/best approach.\n- from topics.models import Topic\n- context = super(GeneralIndexView, self).get_context_data(**kwargs)\n- context['total_topics'] = Topic.objects.count()\n- return context\n-\n \n class GeneralAboutView(TemplateView):\n template_name = 'general/about.html'\n", "issue": "Remove topic query from homepage\nWhen the homepage is loaded, a database query is performed. This is currently not needed and should be removed.\nRemove topic query from homepage\nWhen the homepage is loaded, a database query is performed. This is currently not needed and should be removed.\n", "before_files": [{"content": "from django.views.generic import TemplateView\n\n\nclass GeneralIndexView(TemplateView):\n template_name = 'general/index.html'\n\n def get_context_data(self, **kwargs):\n # TODO: Investigate if importing model from another\n # app is sensible/best approach.\n from topics.models import Topic\n context = super(GeneralIndexView, self).get_context_data(**kwargs)\n context['total_topics'] = Topic.objects.count()\n return context\n\n\nclass GeneralAboutView(TemplateView):\n template_name = 'general/about.html'\n", "path": "csunplugged/general/views.py"}]} | 739 | 165 |
gh_patches_debug_17381 | rasdani/github-patches | git_diff | pypi__warehouse-6368 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
API tokens: Remove @token and pypi: cases
At some point in the future (perhaps at the end of the API token beta?), support for `@token` as a token username and `pypi:` as a token prefix should end in favor of `__token__` and `pypi-`, respectively.
See #6287, #6342.
cc @brainwane @di @ewdurbin @dstufft
</issue>
<code>
[start of warehouse/macaroons/services.py]
1 # Licensed under the Apache License, Version 2.0 (the "License");
2 # you may not use this file except in compliance with the License.
3 # You may obtain a copy of the License at
4 #
5 # http://www.apache.org/licenses/LICENSE-2.0
6 #
7 # Unless required by applicable law or agreed to in writing, software
8 # distributed under the License is distributed on an "AS IS" BASIS,
9 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10 # See the License for the specific language governing permissions and
11 # limitations under the License.
12
13 import datetime
14 import json
15 import uuid
16
17 import pymacaroons
18
19 from pymacaroons.exceptions import MacaroonDeserializationException
20 from sqlalchemy.orm import joinedload
21 from sqlalchemy.orm.exc import NoResultFound
22 from zope.interface import implementer
23
24 from warehouse.accounts.models import User
25 from warehouse.macaroons.caveats import InvalidMacaroon, Verifier
26 from warehouse.macaroons.interfaces import IMacaroonService
27 from warehouse.macaroons.models import Macaroon
28
29
30 @implementer(IMacaroonService)
31 class DatabaseMacaroonService:
32 def __init__(self, db_session):
33 self.db = db_session
34
35 def _extract_raw_macaroon(self, prefixed_macaroon):
36 """
37 Returns the base64-encoded macaroon component of a PyPI macaroon,
38 dropping the prefix.
39
40 Returns None if the macaroon is None, has no prefix, or has the
41 wrong prefix.
42 """
43 if prefixed_macaroon is None:
44 return None
45
46 prefix, split, raw_macaroon = prefixed_macaroon.partition("-")
47 # TODO: Remove ':' as an acceptable delimiter for tokens (GH-6345)
48 if prefix != "pypi" or not split:
49 prefix, _, raw_macaroon = prefixed_macaroon.partition(":")
50
51 if prefix != "pypi":
52 return None
53
54 return raw_macaroon
55
56 def find_macaroon(self, macaroon_id):
57 """
58 Returns a macaroon model from the DB by its identifier.
59 Returns None if no macaroon has the given ID.
60 """
61 try:
62 dm = (
63 self.db.query(Macaroon)
64 .options(joinedload("user"))
65 .filter(Macaroon.id == uuid.UUID(macaroon_id))
66 .one()
67 )
68 except NoResultFound:
69 return None
70
71 return dm
72
73 def find_userid(self, raw_macaroon):
74 """
75 Returns the id of the user associated with the given raw (serialized)
76 macaroon.
77 """
78 raw_macaroon = self._extract_raw_macaroon(raw_macaroon)
79 if raw_macaroon is None:
80 return None
81
82 try:
83 m = pymacaroons.Macaroon.deserialize(raw_macaroon)
84 except MacaroonDeserializationException:
85 return None
86
87 dm = self.find_macaroon(m.identifier.decode())
88
89 if dm is None:
90 return None
91
92 return dm.user.id
93
94 def verify(self, raw_macaroon, context, principals, permission):
95 """
96 Returns True if the given raw (serialized) macaroon is
97 valid for the context, principals, and requested permission.
98
99 Raises InvalidMacaroon if the macaroon is not valid.
100 """
101 raw_macaroon = self._extract_raw_macaroon(raw_macaroon)
102 if raw_macaroon is None:
103 raise InvalidMacaroon("malformed or nonexistent macaroon")
104
105 try:
106 m = pymacaroons.Macaroon.deserialize(raw_macaroon)
107 except MacaroonDeserializationException:
108 raise InvalidMacaroon("malformed macaroon")
109
110 dm = self.find_macaroon(m.identifier.decode())
111
112 if dm is None:
113 raise InvalidMacaroon("deleted or nonexistent macaroon")
114
115 verifier = Verifier(m, context, principals, permission)
116 if verifier.verify(dm.key):
117 dm.last_used = datetime.datetime.now()
118 return True
119
120 raise InvalidMacaroon("invalid macaroon")
121
122 def create_macaroon(self, location, user_id, description, caveats):
123 """
124 Returns a tuple of a new raw (serialized) macaroon and its DB model.
125 The description provided is not embedded into the macaroon, only stored
126 in the DB model.
127 """
128 user = self.db.query(User).filter(User.id == user_id).one()
129
130 dm = Macaroon(user=user, description=description, caveats=caveats)
131 self.db.add(dm)
132 self.db.flush()
133
134 m = pymacaroons.Macaroon(
135 location=location,
136 identifier=str(dm.id),
137 key=dm.key,
138 version=pymacaroons.MACAROON_V2,
139 )
140 m.add_first_party_caveat(json.dumps(caveats))
141 serialized_macaroon = f"pypi-{m.serialize()}"
142 return serialized_macaroon, dm
143
144 def delete_macaroon(self, macaroon_id):
145 """
146 Deletes a macaroon from the DB by its identifier.
147 """
148 dm = self.find_macaroon(macaroon_id)
149 self.db.delete(dm)
150 self.db.flush()
151
152 def get_macaroon_by_description(self, user_id, description):
153 """
154 Returns a macaroon model from the DB with the given description,
155 if one exists for the given user.
156
157 Returns None if the user doesn't have a macaroon with this description.
158 """
159 try:
160 dm = (
161 self.db.query(Macaroon)
162 .options(joinedload("user"))
163 .filter(Macaroon.description == description)
164 .filter(Macaroon.user_id == user_id)
165 .one()
166 )
167 except NoResultFound:
168 return None
169
170 return dm
171
172
173 def database_macaroon_factory(context, request):
174 return DatabaseMacaroonService(request.db)
175
[end of warehouse/macaroons/services.py]
[start of warehouse/macaroons/auth_policy.py]
1 # Licensed under the Apache License, Version 2.0 (the "License");
2 # you may not use this file except in compliance with the License.
3 # You may obtain a copy of the License at
4 #
5 # http://www.apache.org/licenses/LICENSE-2.0
6 #
7 # Unless required by applicable law or agreed to in writing, software
8 # distributed under the License is distributed on an "AS IS" BASIS,
9 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10 # See the License for the specific language governing permissions and
11 # limitations under the License.
12
13 import base64
14
15 from pyramid.authentication import CallbackAuthenticationPolicy
16 from pyramid.interfaces import IAuthenticationPolicy, IAuthorizationPolicy
17 from pyramid.security import Denied
18 from pyramid.threadlocal import get_current_request
19 from zope.interface import implementer
20
21 from warehouse.cache.http import add_vary_callback
22 from warehouse.macaroons.interfaces import IMacaroonService
23 from warehouse.macaroons.services import InvalidMacaroon
24
25
26 def _extract_basic_macaroon(auth):
27 """
28 A helper function for extracting a macaroon from a
29 HTTP Basic Authentication-style header.
30
31 Returns None if the header doesn't contain a structurally
32 valid macaroon, or the candidate (not yet verified) macaroon
33 in a serialized form.
34 """
35 try:
36 authorization = base64.b64decode(auth).decode()
37 auth_method, _, auth = authorization.partition(":")
38 except ValueError:
39 return None
40
41 # TODO: Remove @token as an acceptable token username (GH-6345)
42 if auth_method != "@token" and auth_method != "__token__":
43 return None
44
45 return auth
46
47
48 def _extract_http_macaroon(request):
49 """
50 A helper function for the extraction of HTTP Macaroon from a given request.
51 Returns either a None if no macaroon could be found, or the string
52 that represents our serialized macaroon.
53 """
54 authorization = request.headers.get("Authorization")
55 if not authorization:
56 return None
57
58 try:
59 auth_method, auth = authorization.split(" ", 1)
60 except ValueError:
61 return None
62
63 if auth_method.lower() == "basic":
64 return _extract_basic_macaroon(auth)
65 elif auth_method.lower() == "token":
66 return auth
67
68 return None
69
70
71 @implementer(IAuthenticationPolicy)
72 class MacaroonAuthenticationPolicy(CallbackAuthenticationPolicy):
73 def __init__(self, callback=None):
74 self.callback = callback
75
76 def unauthenticated_userid(self, request):
77 # If we're calling into this API on a request, then we want to register
78 # a callback which will ensure that the response varies based on the
79 # Authorization header.
80 request.add_response_callback(add_vary_callback("Authorization"))
81
82 # We need to extract our Macaroon from the request.
83 macaroon = _extract_http_macaroon(request)
84 if macaroon is None:
85 return None
86
87 # Check to see if our Macaroon exists in the database, and if so
88 # fetch the user that is associated with it.
89 macaroon_service = request.find_service(IMacaroonService, context=None)
90 userid = macaroon_service.find_userid(macaroon)
91 if userid is not None:
92 return str(userid)
93
94 def remember(self, request, userid, **kw):
95 # This is a NO-OP because our Macaroon header policy doesn't allow
96 # the ability for authentication to "remember" the user id. This
97 # assumes it has been configured in clients somewhere out of band.
98 return []
99
100 def forget(self, request):
101 # This is a NO-OP because our Macaroon header policy doesn't allow
102 # the ability for authentication to "forget" the user id. This
103 # assumes it has been configured in clients somewhere out of band.
104 return []
105
106
107 @implementer(IAuthorizationPolicy)
108 class MacaroonAuthorizationPolicy:
109 def __init__(self, policy):
110 self.policy = policy
111
112 def permits(self, context, principals, permission):
113 # The Pyramid API doesn't let us access the request here, so we have to pull it
114 # out of the thread local instead.
115 # TODO: Work with Pyramid devs to figure out if there is a better way to support
116 # the worklow we are using here or not.
117 request = get_current_request()
118
119 # Our request could possibly be a None, if there isn't an active request, in
120 # that case we're going to always deny, because without a request, we can't
121 # determine if this request is authorized or not.
122 if request is None:
123 return Denied("There was no active request.")
124
125 # Re-extract our Macaroon from the request, it sucks to have to do this work
126 # twice, but I believe it is inevitable unless we pass the Macaroon back as
127 # a principal-- which doesn't seem to be the right fit for it.
128 macaroon = _extract_http_macaroon(request)
129
130 # This logic will only happen on requests that are being authenticated with
131 # Macaroons. Any other request will just fall back to the standard Authorization
132 # policy.
133 if macaroon is not None:
134 macaroon_service = request.find_service(IMacaroonService, context=None)
135
136 try:
137 macaroon_service.verify(macaroon, context, principals, permission)
138 except InvalidMacaroon as exc:
139 return Denied(f"The supplied token was invalid: {str(exc)!r}")
140
141 # If our Macaroon is verified, then we'll pass this request to our underlying
142 # Authorization policy, so it can handle its own authorization logic on
143 # the prinicpal.
144 return self.policy.permits(context, principals, permission)
145
146 def principals_allowed_by_permission(self, context, permission):
147 # We just dispatch this, because Macaroons don't restrict what principals are
148 # allowed by a particular permission, they just restrict specific requests
149 # to not have that permission.
150 return self.policy.principals_allowed_by_permission(context, permission)
151
[end of warehouse/macaroons/auth_policy.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/warehouse/macaroons/auth_policy.py b/warehouse/macaroons/auth_policy.py
--- a/warehouse/macaroons/auth_policy.py
+++ b/warehouse/macaroons/auth_policy.py
@@ -38,8 +38,7 @@
except ValueError:
return None
- # TODO: Remove @token as an acceptable token username (GH-6345)
- if auth_method != "@token" and auth_method != "__token__":
+ if auth_method != "__token__":
return None
return auth
diff --git a/warehouse/macaroons/services.py b/warehouse/macaroons/services.py
--- a/warehouse/macaroons/services.py
+++ b/warehouse/macaroons/services.py
@@ -43,12 +43,8 @@
if prefixed_macaroon is None:
return None
- prefix, split, raw_macaroon = prefixed_macaroon.partition("-")
- # TODO: Remove ':' as an acceptable delimiter for tokens (GH-6345)
- if prefix != "pypi" or not split:
- prefix, _, raw_macaroon = prefixed_macaroon.partition(":")
-
- if prefix != "pypi":
+ prefix, _, raw_macaroon = prefixed_macaroon.partition("-")
+ if prefix != "pypi" or not raw_macaroon:
return None
return raw_macaroon
| {"golden_diff": "diff --git a/warehouse/macaroons/auth_policy.py b/warehouse/macaroons/auth_policy.py\n--- a/warehouse/macaroons/auth_policy.py\n+++ b/warehouse/macaroons/auth_policy.py\n@@ -38,8 +38,7 @@\n except ValueError:\n return None\n \n- # TODO: Remove @token as an acceptable token username (GH-6345)\n- if auth_method != \"@token\" and auth_method != \"__token__\":\n+ if auth_method != \"__token__\":\n return None\n \n return auth\ndiff --git a/warehouse/macaroons/services.py b/warehouse/macaroons/services.py\n--- a/warehouse/macaroons/services.py\n+++ b/warehouse/macaroons/services.py\n@@ -43,12 +43,8 @@\n if prefixed_macaroon is None:\n return None\n \n- prefix, split, raw_macaroon = prefixed_macaroon.partition(\"-\")\n- # TODO: Remove ':' as an acceptable delimiter for tokens (GH-6345)\n- if prefix != \"pypi\" or not split:\n- prefix, _, raw_macaroon = prefixed_macaroon.partition(\":\")\n-\n- if prefix != \"pypi\":\n+ prefix, _, raw_macaroon = prefixed_macaroon.partition(\"-\")\n+ if prefix != \"pypi\" or not raw_macaroon:\n return None\n \n return raw_macaroon\n", "issue": "API tokens: Remove @token and pypi: cases\nAt some point in the future (perhaps at the end of the API token beta?), support for `@token` as a token username and `pypi:` as a token prefix should end in favor of `__token__` and `pypi-`, respectively.\r\n\r\nSee #6287, #6342.\r\n\r\ncc @brainwane @di @ewdurbin @dstufft \r\n\r\n\n", "before_files": [{"content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport datetime\nimport json\nimport uuid\n\nimport pymacaroons\n\nfrom pymacaroons.exceptions import MacaroonDeserializationException\nfrom sqlalchemy.orm import joinedload\nfrom sqlalchemy.orm.exc import NoResultFound\nfrom zope.interface import implementer\n\nfrom warehouse.accounts.models import User\nfrom warehouse.macaroons.caveats import InvalidMacaroon, Verifier\nfrom warehouse.macaroons.interfaces import IMacaroonService\nfrom warehouse.macaroons.models import Macaroon\n\n\n@implementer(IMacaroonService)\nclass DatabaseMacaroonService:\n def __init__(self, db_session):\n self.db = db_session\n\n def _extract_raw_macaroon(self, prefixed_macaroon):\n \"\"\"\n Returns the base64-encoded macaroon component of a PyPI macaroon,\n dropping the prefix.\n\n Returns None if the macaroon is None, has no prefix, or has the\n wrong prefix.\n \"\"\"\n if prefixed_macaroon is None:\n return None\n\n prefix, split, raw_macaroon = prefixed_macaroon.partition(\"-\")\n # TODO: Remove ':' as an acceptable delimiter for tokens (GH-6345)\n if prefix != \"pypi\" or not split:\n prefix, _, raw_macaroon = prefixed_macaroon.partition(\":\")\n\n if prefix != \"pypi\":\n return None\n\n return raw_macaroon\n\n def find_macaroon(self, macaroon_id):\n \"\"\"\n Returns a macaroon model from the DB by its identifier.\n Returns None if no macaroon has the given ID.\n \"\"\"\n try:\n dm = (\n self.db.query(Macaroon)\n .options(joinedload(\"user\"))\n .filter(Macaroon.id == uuid.UUID(macaroon_id))\n .one()\n )\n except NoResultFound:\n return None\n\n return dm\n\n def find_userid(self, raw_macaroon):\n \"\"\"\n Returns the id of the user associated with the given raw (serialized)\n macaroon.\n \"\"\"\n raw_macaroon = self._extract_raw_macaroon(raw_macaroon)\n if raw_macaroon is None:\n return None\n\n try:\n m = pymacaroons.Macaroon.deserialize(raw_macaroon)\n except MacaroonDeserializationException:\n return None\n\n dm = self.find_macaroon(m.identifier.decode())\n\n if dm is None:\n return None\n\n return dm.user.id\n\n def verify(self, raw_macaroon, context, principals, permission):\n \"\"\"\n Returns True if the given raw (serialized) macaroon is\n valid for the context, principals, and requested permission.\n\n Raises InvalidMacaroon if the macaroon is not valid.\n \"\"\"\n raw_macaroon = self._extract_raw_macaroon(raw_macaroon)\n if raw_macaroon is None:\n raise InvalidMacaroon(\"malformed or nonexistent macaroon\")\n\n try:\n m = pymacaroons.Macaroon.deserialize(raw_macaroon)\n except MacaroonDeserializationException:\n raise InvalidMacaroon(\"malformed macaroon\")\n\n dm = self.find_macaroon(m.identifier.decode())\n\n if dm is None:\n raise InvalidMacaroon(\"deleted or nonexistent macaroon\")\n\n verifier = Verifier(m, context, principals, permission)\n if verifier.verify(dm.key):\n dm.last_used = datetime.datetime.now()\n return True\n\n raise InvalidMacaroon(\"invalid macaroon\")\n\n def create_macaroon(self, location, user_id, description, caveats):\n \"\"\"\n Returns a tuple of a new raw (serialized) macaroon and its DB model.\n The description provided is not embedded into the macaroon, only stored\n in the DB model.\n \"\"\"\n user = self.db.query(User).filter(User.id == user_id).one()\n\n dm = Macaroon(user=user, description=description, caveats=caveats)\n self.db.add(dm)\n self.db.flush()\n\n m = pymacaroons.Macaroon(\n location=location,\n identifier=str(dm.id),\n key=dm.key,\n version=pymacaroons.MACAROON_V2,\n )\n m.add_first_party_caveat(json.dumps(caveats))\n serialized_macaroon = f\"pypi-{m.serialize()}\"\n return serialized_macaroon, dm\n\n def delete_macaroon(self, macaroon_id):\n \"\"\"\n Deletes a macaroon from the DB by its identifier.\n \"\"\"\n dm = self.find_macaroon(macaroon_id)\n self.db.delete(dm)\n self.db.flush()\n\n def get_macaroon_by_description(self, user_id, description):\n \"\"\"\n Returns a macaroon model from the DB with the given description,\n if one exists for the given user.\n\n Returns None if the user doesn't have a macaroon with this description.\n \"\"\"\n try:\n dm = (\n self.db.query(Macaroon)\n .options(joinedload(\"user\"))\n .filter(Macaroon.description == description)\n .filter(Macaroon.user_id == user_id)\n .one()\n )\n except NoResultFound:\n return None\n\n return dm\n\n\ndef database_macaroon_factory(context, request):\n return DatabaseMacaroonService(request.db)\n", "path": "warehouse/macaroons/services.py"}, {"content": "# Licensed under the Apache License, Version 2.0 (the \"License\");\n# you may not use this file except in compliance with the License.\n# You may obtain a copy of the License at\n#\n# http://www.apache.org/licenses/LICENSE-2.0\n#\n# Unless required by applicable law or agreed to in writing, software\n# distributed under the License is distributed on an \"AS IS\" BASIS,\n# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n# See the License for the specific language governing permissions and\n# limitations under the License.\n\nimport base64\n\nfrom pyramid.authentication import CallbackAuthenticationPolicy\nfrom pyramid.interfaces import IAuthenticationPolicy, IAuthorizationPolicy\nfrom pyramid.security import Denied\nfrom pyramid.threadlocal import get_current_request\nfrom zope.interface import implementer\n\nfrom warehouse.cache.http import add_vary_callback\nfrom warehouse.macaroons.interfaces import IMacaroonService\nfrom warehouse.macaroons.services import InvalidMacaroon\n\n\ndef _extract_basic_macaroon(auth):\n \"\"\"\n A helper function for extracting a macaroon from a\n HTTP Basic Authentication-style header.\n\n Returns None if the header doesn't contain a structurally\n valid macaroon, or the candidate (not yet verified) macaroon\n in a serialized form.\n \"\"\"\n try:\n authorization = base64.b64decode(auth).decode()\n auth_method, _, auth = authorization.partition(\":\")\n except ValueError:\n return None\n\n # TODO: Remove @token as an acceptable token username (GH-6345)\n if auth_method != \"@token\" and auth_method != \"__token__\":\n return None\n\n return auth\n\n\ndef _extract_http_macaroon(request):\n \"\"\"\n A helper function for the extraction of HTTP Macaroon from a given request.\n Returns either a None if no macaroon could be found, or the string\n that represents our serialized macaroon.\n \"\"\"\n authorization = request.headers.get(\"Authorization\")\n if not authorization:\n return None\n\n try:\n auth_method, auth = authorization.split(\" \", 1)\n except ValueError:\n return None\n\n if auth_method.lower() == \"basic\":\n return _extract_basic_macaroon(auth)\n elif auth_method.lower() == \"token\":\n return auth\n\n return None\n\n\n@implementer(IAuthenticationPolicy)\nclass MacaroonAuthenticationPolicy(CallbackAuthenticationPolicy):\n def __init__(self, callback=None):\n self.callback = callback\n\n def unauthenticated_userid(self, request):\n # If we're calling into this API on a request, then we want to register\n # a callback which will ensure that the response varies based on the\n # Authorization header.\n request.add_response_callback(add_vary_callback(\"Authorization\"))\n\n # We need to extract our Macaroon from the request.\n macaroon = _extract_http_macaroon(request)\n if macaroon is None:\n return None\n\n # Check to see if our Macaroon exists in the database, and if so\n # fetch the user that is associated with it.\n macaroon_service = request.find_service(IMacaroonService, context=None)\n userid = macaroon_service.find_userid(macaroon)\n if userid is not None:\n return str(userid)\n\n def remember(self, request, userid, **kw):\n # This is a NO-OP because our Macaroon header policy doesn't allow\n # the ability for authentication to \"remember\" the user id. This\n # assumes it has been configured in clients somewhere out of band.\n return []\n\n def forget(self, request):\n # This is a NO-OP because our Macaroon header policy doesn't allow\n # the ability for authentication to \"forget\" the user id. This\n # assumes it has been configured in clients somewhere out of band.\n return []\n\n\n@implementer(IAuthorizationPolicy)\nclass MacaroonAuthorizationPolicy:\n def __init__(self, policy):\n self.policy = policy\n\n def permits(self, context, principals, permission):\n # The Pyramid API doesn't let us access the request here, so we have to pull it\n # out of the thread local instead.\n # TODO: Work with Pyramid devs to figure out if there is a better way to support\n # the worklow we are using here or not.\n request = get_current_request()\n\n # Our request could possibly be a None, if there isn't an active request, in\n # that case we're going to always deny, because without a request, we can't\n # determine if this request is authorized or not.\n if request is None:\n return Denied(\"There was no active request.\")\n\n # Re-extract our Macaroon from the request, it sucks to have to do this work\n # twice, but I believe it is inevitable unless we pass the Macaroon back as\n # a principal-- which doesn't seem to be the right fit for it.\n macaroon = _extract_http_macaroon(request)\n\n # This logic will only happen on requests that are being authenticated with\n # Macaroons. Any other request will just fall back to the standard Authorization\n # policy.\n if macaroon is not None:\n macaroon_service = request.find_service(IMacaroonService, context=None)\n\n try:\n macaroon_service.verify(macaroon, context, principals, permission)\n except InvalidMacaroon as exc:\n return Denied(f\"The supplied token was invalid: {str(exc)!r}\")\n\n # If our Macaroon is verified, then we'll pass this request to our underlying\n # Authorization policy, so it can handle its own authorization logic on\n # the prinicpal.\n return self.policy.permits(context, principals, permission)\n\n def principals_allowed_by_permission(self, context, permission):\n # We just dispatch this, because Macaroons don't restrict what principals are\n # allowed by a particular permission, they just restrict specific requests\n # to not have that permission.\n return self.policy.principals_allowed_by_permission(context, permission)\n", "path": "warehouse/macaroons/auth_policy.py"}]} | 4,042 | 307 |
gh_patches_debug_35530 | rasdani/github-patches | git_diff | hylang__hy-2214 | You will be provided with a partial code base and an issue statement explaining a problem to resolve.
<issue>
curses and SIGWINCH do not work properly with Hy.
After importing curses under hy, curses is unable to detect the size of the terminal as it is resized.
This manifests as curses.LINES and curses.COLS not being updated, stdscr.getmaxyx not working and so on.
However, the workaround of launching the hy program from python with:
```
import hy
import curses
from main import main_event_loop
if __name__ == "__main__":
curses.wrapper(main_event_loop, ...)
```
allows curses to dynamically detect the size of the terminal.
I conclude therefore the problem is with the hy binary. My (limited) understanding acquired during tracking down the source of this problem is that curses uses the SIGWINCH signal, so perhaps that is a place to look.
Void linux x86 64bit, python 3.9.0
Freebsd 12.2, python 3.8.6
hy 0.19.0 (reported by pip) installed from git master branch via pip
</issue>
<code>
[start of hy/completer.py]
1 import contextlib
2 import os
3 import re
4 import sys
5 import builtins
6
7 import hy.macros
8 import hy.compiler
9
10
11 docomplete = True
12
13 try:
14 import readline
15 except AttributeError as e:
16 # https://github.com/pyreadline/pyreadline/issues/65
17 if "module 'collections' has no attribute 'Callable'" in str(e):
18 docomplete = False
19 else:
20 raise
21 except ImportError:
22 docomplete = False
23
24 if docomplete:
25 if sys.platform == 'darwin' and 'libedit' in readline.__doc__:
26 readline_bind = "bind ^I rl_complete"
27 else:
28 readline_bind = "tab: complete"
29
30
31 class Completer:
32
33 def __init__(self, namespace={}):
34 if not isinstance(namespace, dict):
35 raise TypeError('namespace must be a dictionary')
36 self.namespace = namespace
37 self.path = [builtins.__dict__,
38 namespace]
39
40 namespace.setdefault('__macros__', {})
41
42 self.path.append(namespace['__macros__'])
43
44 def attr_matches(self, text):
45 # Borrowed from IPython's completer
46 m = re.match(r"(\S+(\.[\w-]+)*)\.([\w-]*)$", text)
47
48 if m:
49 expr, attr = m.group(1, 3)
50 attr = attr.replace("-", "_")
51 expr = expr.replace("-", "_")
52 else:
53 return []
54
55 try:
56 obj = eval(expr, self.namespace)
57 words = dir(obj)
58 except Exception:
59 return []
60
61 n = len(attr)
62 matches = []
63 for w in words:
64 if w[:n] == attr:
65 matches.append("{}.{}".format(
66 expr.replace("_", "-"), w.replace("_", "-")))
67 return matches
68
69 def global_matches(self, text):
70 matches = []
71 for p in self.path:
72 for k in p.keys():
73 if isinstance(k, str):
74 k = k.replace("_", "-")
75 if k.startswith(text):
76 matches.append(k)
77 return matches
78
79 def complete(self, text, state):
80 if "." in text:
81 matches = self.attr_matches(text)
82 else:
83 matches = self.global_matches(text)
84 try:
85 return matches[state]
86 except IndexError:
87 return None
88
89
90 @contextlib.contextmanager
91 def completion(completer=None):
92 delims = "()[]{} "
93 if not completer:
94 completer = Completer()
95
96 if docomplete:
97 readline.set_completer(completer.complete)
98 readline.set_completer_delims(delims)
99
100 history = os.environ.get(
101 "HY_HISTORY", os.path.expanduser("~/.hy-history"))
102 readline.parse_and_bind("set blink-matching-paren on")
103
104 try:
105 readline.read_history_file(history)
106 except OSError:
107 pass
108
109 readline.parse_and_bind(readline_bind)
110
111 try:
112 yield
113 finally:
114 if docomplete:
115 try:
116 readline.write_history_file(history)
117 except OSError:
118 pass
119
[end of hy/completer.py]
</code>
I need you to solve this issue by generating a single patch file that I can apply directly to this repository using git apply. Please respond with a single patch file in the following format.
<patch>
diff --git a/file.py b/file.py
--- a/file.py
+++ b/file.py
@@ -1,27 +1,35 @@
def euclidean(a, b):
- while b:
- a, b = b, a % b
- return a
+ if b == 0:
+ return a
+ return euclidean(b, a % b)
def bresenham(x0, y0, x1, y1):
points = []
dx = abs(x1 - x0)
dy = abs(y1 - y0)
- sx = 1 if x0 < x1 else -1
- sy = 1 if y0 < y1 else -1
- err = dx - dy
+ x, y = x0, y0
+ sx = -1 if x0 > x1 else 1
+ sy = -1 if y0 > y1 else 1
- while True:
- points.append((x0, y0))
- if x0 == x1 and y0 == y1:
- break
- e2 = 2 * err
- if e2 > -dy:
- err -= dy
- x0 += sx
- if e2 < dx:
- err += dx
- y0 += sy
+ if dx > dy:
+ err = dx / 2.0
+ while x != x1:
+ points.append((x, y))
+ err -= dy
+ if err < 0:
+ y += sy
+ err += dx
+ x += sx
+ else:
+ err = dy / 2.0
+ while y != y1:
+ points.append((x, y))
+ err -= dx
+ if err < 0:
+ x += sx
+ err += dy
+ y += sy
+
+ points.append((x, y))
return points
</patch> | diff --git a/hy/completer.py b/hy/completer.py
--- a/hy/completer.py
+++ b/hy/completer.py
@@ -8,24 +8,19 @@
import hy.compiler
-docomplete = True
-
-try:
- import readline
-except AttributeError as e:
- # https://github.com/pyreadline/pyreadline/issues/65
- if "module 'collections' has no attribute 'Callable'" in str(e):
- docomplete = False
- else:
- raise
-except ImportError:
- docomplete = False
-
-if docomplete:
- if sys.platform == 'darwin' and 'libedit' in readline.__doc__:
- readline_bind = "bind ^I rl_complete"
- else:
- readline_bind = "tab: complete"
+# Lazily import `readline` to work around
+# https://bugs.python.org/issue2675#msg265564
+readline = None
+def init_readline():
+ global readline
+ try:
+ import readline
+ except AttributeError as e:
+ # https://github.com/pyreadline/pyreadline/issues/65
+ if "module 'collections' has no attribute 'Callable'" not in str(e):
+ raise
+ except ImportError:
+ pass
class Completer:
@@ -86,33 +81,42 @@
except IndexError:
return None
-
@contextlib.contextmanager
def completion(completer=None):
delims = "()[]{} "
+
+ init_readline()
+ if not readline:
+ # We have nothing to do. Act like a null context manager.
+ yield
+ return
+
if not completer:
completer = Completer()
- if docomplete:
- readline.set_completer(completer.complete)
- readline.set_completer_delims(delims)
+ if sys.platform == 'darwin' and 'libedit' in readline.__doc__:
+ readline_bind = "bind ^I rl_complete"
+ else:
+ readline_bind = "tab: complete"
- history = os.environ.get(
- "HY_HISTORY", os.path.expanduser("~/.hy-history"))
- readline.parse_and_bind("set blink-matching-paren on")
+ readline.set_completer(completer.complete)
+ readline.set_completer_delims(delims)
- try:
- readline.read_history_file(history)
- except OSError:
- pass
+ history = os.environ.get(
+ "HY_HISTORY", os.path.expanduser("~/.hy-history"))
+ readline.parse_and_bind("set blink-matching-paren on")
- readline.parse_and_bind(readline_bind)
+ try:
+ readline.read_history_file(history)
+ except OSError:
+ pass
+
+ readline.parse_and_bind(readline_bind)
try:
yield
finally:
- if docomplete:
- try:
- readline.write_history_file(history)
- except OSError:
- pass
+ try:
+ readline.write_history_file(history)
+ except OSError:
+ pass
| {"golden_diff": "diff --git a/hy/completer.py b/hy/completer.py\n--- a/hy/completer.py\n+++ b/hy/completer.py\n@@ -8,24 +8,19 @@\n import hy.compiler\n \n \n-docomplete = True\n-\n-try:\n- import readline\n-except AttributeError as e:\n- # https://github.com/pyreadline/pyreadline/issues/65\n- if \"module 'collections' has no attribute 'Callable'\" in str(e):\n- docomplete = False\n- else:\n- raise\n-except ImportError:\n- docomplete = False\n-\n-if docomplete:\n- if sys.platform == 'darwin' and 'libedit' in readline.__doc__:\n- readline_bind = \"bind ^I rl_complete\"\n- else:\n- readline_bind = \"tab: complete\"\n+# Lazily import `readline` to work around\n+# https://bugs.python.org/issue2675#msg265564\n+readline = None\n+def init_readline():\n+ global readline\n+ try:\n+ import readline\n+ except AttributeError as e:\n+ # https://github.com/pyreadline/pyreadline/issues/65\n+ if \"module 'collections' has no attribute 'Callable'\" not in str(e):\n+ raise\n+ except ImportError:\n+ pass\n \n \n class Completer:\n@@ -86,33 +81,42 @@\n except IndexError:\n return None\n \n-\n @contextlib.contextmanager\n def completion(completer=None):\n delims = \"()[]{} \"\n+\n+ init_readline()\n+ if not readline:\n+ # We have nothing to do. Act like a null context manager.\n+ yield\n+ return\n+\n if not completer:\n completer = Completer()\n \n- if docomplete:\n- readline.set_completer(completer.complete)\n- readline.set_completer_delims(delims)\n+ if sys.platform == 'darwin' and 'libedit' in readline.__doc__:\n+ readline_bind = \"bind ^I rl_complete\"\n+ else:\n+ readline_bind = \"tab: complete\"\n \n- history = os.environ.get(\n- \"HY_HISTORY\", os.path.expanduser(\"~/.hy-history\"))\n- readline.parse_and_bind(\"set blink-matching-paren on\")\n+ readline.set_completer(completer.complete)\n+ readline.set_completer_delims(delims)\n \n- try:\n- readline.read_history_file(history)\n- except OSError:\n- pass\n+ history = os.environ.get(\n+ \"HY_HISTORY\", os.path.expanduser(\"~/.hy-history\"))\n+ readline.parse_and_bind(\"set blink-matching-paren on\")\n \n- readline.parse_and_bind(readline_bind)\n+ try:\n+ readline.read_history_file(history)\n+ except OSError:\n+ pass\n+\n+ readline.parse_and_bind(readline_bind)\n \n try:\n yield\n finally:\n- if docomplete:\n- try:\n- readline.write_history_file(history)\n- except OSError:\n- pass\n+ try:\n+ readline.write_history_file(history)\n+ except OSError:\n+ pass\n", "issue": "curses and SIGWINCH do not work properly with Hy.\nAfter importing curses under hy, curses is unable to detect the size of the terminal as it is resized.\r\nThis manifests as curses.LINES and curses.COLS not being updated, stdscr.getmaxyx not working and so on.\r\n\r\nHowever, the workaround of launching the hy program from python with:\r\n```\r\nimport hy\r\nimport curses\r\nfrom main import main_event_loop\r\n\r\nif __name__ == \"__main__\":\r\n curses.wrapper(main_event_loop, ...)\r\n```\r\nallows curses to dynamically detect the size of the terminal.\r\n\r\nI conclude therefore the problem is with the hy binary. My (limited) understanding acquired during tracking down the source of this problem is that curses uses the SIGWINCH signal, so perhaps that is a place to look.\r\n\r\nVoid linux x86 64bit, python 3.9.0\r\nFreebsd 12.2, python 3.8.6\r\nhy 0.19.0 (reported by pip) installed from git master branch via pip\n", "before_files": [{"content": "import contextlib\nimport os\nimport re\nimport sys\nimport builtins\n\nimport hy.macros\nimport hy.compiler\n\n\ndocomplete = True\n\ntry:\n import readline\nexcept AttributeError as e:\n # https://github.com/pyreadline/pyreadline/issues/65\n if \"module 'collections' has no attribute 'Callable'\" in str(e):\n docomplete = False\n else:\n raise\nexcept ImportError:\n docomplete = False\n\nif docomplete:\n if sys.platform == 'darwin' and 'libedit' in readline.__doc__:\n readline_bind = \"bind ^I rl_complete\"\n else:\n readline_bind = \"tab: complete\"\n\n\nclass Completer:\n\n def __init__(self, namespace={}):\n if not isinstance(namespace, dict):\n raise TypeError('namespace must be a dictionary')\n self.namespace = namespace\n self.path = [builtins.__dict__,\n namespace]\n\n namespace.setdefault('__macros__', {})\n\n self.path.append(namespace['__macros__'])\n\n def attr_matches(self, text):\n # Borrowed from IPython's completer\n m = re.match(r\"(\\S+(\\.[\\w-]+)*)\\.([\\w-]*)$\", text)\n\n if m:\n expr, attr = m.group(1, 3)\n attr = attr.replace(\"-\", \"_\")\n expr = expr.replace(\"-\", \"_\")\n else:\n return []\n\n try:\n obj = eval(expr, self.namespace)\n words = dir(obj)\n except Exception:\n return []\n\n n = len(attr)\n matches = []\n for w in words:\n if w[:n] == attr:\n matches.append(\"{}.{}\".format(\n expr.replace(\"_\", \"-\"), w.replace(\"_\", \"-\")))\n return matches\n\n def global_matches(self, text):\n matches = []\n for p in self.path:\n for k in p.keys():\n if isinstance(k, str):\n k = k.replace(\"_\", \"-\")\n if k.startswith(text):\n matches.append(k)\n return matches\n\n def complete(self, text, state):\n if \".\" in text:\n matches = self.attr_matches(text)\n else:\n matches = self.global_matches(text)\n try:\n return matches[state]\n except IndexError:\n return None\n\n\[email protected]\ndef completion(completer=None):\n delims = \"()[]{} \"\n if not completer:\n completer = Completer()\n\n if docomplete:\n readline.set_completer(completer.complete)\n readline.set_completer_delims(delims)\n\n history = os.environ.get(\n \"HY_HISTORY\", os.path.expanduser(\"~/.hy-history\"))\n readline.parse_and_bind(\"set blink-matching-paren on\")\n\n try:\n readline.read_history_file(history)\n except OSError:\n pass\n\n readline.parse_and_bind(readline_bind)\n\n try:\n yield\n finally:\n if docomplete:\n try:\n readline.write_history_file(history)\n except OSError:\n pass\n", "path": "hy/completer.py"}]} | 1,658 | 709 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.