File size: 8,725 Bytes
7885a28 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 |
from __future__ import annotations
import os
import pytest
from pandas.compat._optional import VERSIONS
from pandas import (
read_csv,
read_table,
)
import pandas._testing as tm
class BaseParser:
engine: str | None = None
low_memory = True
float_precision_choices: list[str | None] = []
def update_kwargs(self, kwargs):
kwargs = kwargs.copy()
kwargs.update({"engine": self.engine, "low_memory": self.low_memory})
return kwargs
def read_csv(self, *args, **kwargs):
kwargs = self.update_kwargs(kwargs)
return read_csv(*args, **kwargs)
def read_csv_check_warnings(
self,
warn_type: type[Warning],
warn_msg: str,
*args,
raise_on_extra_warnings=True,
check_stacklevel: bool = True,
**kwargs,
):
# We need to check the stacklevel here instead of in the tests
# since this is where read_csv is called and where the warning
# should point to.
kwargs = self.update_kwargs(kwargs)
with tm.assert_produces_warning(
warn_type,
match=warn_msg,
raise_on_extra_warnings=raise_on_extra_warnings,
check_stacklevel=check_stacklevel,
):
return read_csv(*args, **kwargs)
def read_table(self, *args, **kwargs):
kwargs = self.update_kwargs(kwargs)
return read_table(*args, **kwargs)
def read_table_check_warnings(
self,
warn_type: type[Warning],
warn_msg: str,
*args,
raise_on_extra_warnings=True,
**kwargs,
):
# We need to check the stacklevel here instead of in the tests
# since this is where read_table is called and where the warning
# should point to.
kwargs = self.update_kwargs(kwargs)
with tm.assert_produces_warning(
warn_type, match=warn_msg, raise_on_extra_warnings=raise_on_extra_warnings
):
return read_table(*args, **kwargs)
class CParser(BaseParser):
engine = "c"
float_precision_choices = [None, "high", "round_trip"]
class CParserHighMemory(CParser):
low_memory = False
class CParserLowMemory(CParser):
low_memory = True
class PythonParser(BaseParser):
engine = "python"
float_precision_choices = [None]
class PyArrowParser(BaseParser):
engine = "pyarrow"
float_precision_choices = [None]
@pytest.fixture
def csv_dir_path(datapath):
"""
The directory path to the data files needed for parser tests.
"""
return datapath("io", "parser", "data")
@pytest.fixture
def csv1(datapath):
"""
The path to the data file "test1.csv" needed for parser tests.
"""
return os.path.join(datapath("io", "data", "csv"), "test1.csv")
_cParserHighMemory = CParserHighMemory
_cParserLowMemory = CParserLowMemory
_pythonParser = PythonParser
_pyarrowParser = PyArrowParser
_py_parsers_only = [_pythonParser]
_c_parsers_only = [_cParserHighMemory, _cParserLowMemory]
_pyarrow_parsers_only = [pytest.param(_pyarrowParser, marks=pytest.mark.single_cpu)]
_all_parsers = [*_c_parsers_only, *_py_parsers_only, *_pyarrow_parsers_only]
_py_parser_ids = ["python"]
_c_parser_ids = ["c_high", "c_low"]
_pyarrow_parsers_ids = ["pyarrow"]
_all_parser_ids = [*_c_parser_ids, *_py_parser_ids, *_pyarrow_parsers_ids]
@pytest.fixture(params=_all_parsers, ids=_all_parser_ids)
def all_parsers(request):
"""
Fixture all of the CSV parsers.
"""
parser = request.param()
if parser.engine == "pyarrow":
pytest.importorskip("pyarrow", VERSIONS["pyarrow"])
# Try finding a way to disable threads all together
# for more stable CI runs
import pyarrow
pyarrow.set_cpu_count(1)
return parser
@pytest.fixture(params=_c_parsers_only, ids=_c_parser_ids)
def c_parser_only(request):
"""
Fixture all of the CSV parsers using the C engine.
"""
return request.param()
@pytest.fixture(params=_py_parsers_only, ids=_py_parser_ids)
def python_parser_only(request):
"""
Fixture all of the CSV parsers using the Python engine.
"""
return request.param()
@pytest.fixture(params=_pyarrow_parsers_only, ids=_pyarrow_parsers_ids)
def pyarrow_parser_only(request):
"""
Fixture all of the CSV parsers using the Pyarrow engine.
"""
return request.param()
def _get_all_parser_float_precision_combinations():
"""
Return all allowable parser and float precision
combinations and corresponding ids.
"""
params = []
ids = []
for parser, parser_id in zip(_all_parsers, _all_parser_ids):
if hasattr(parser, "values"):
# Wrapped in pytest.param, get the actual parser back
parser = parser.values[0]
for precision in parser.float_precision_choices:
# Re-wrap in pytest.param for pyarrow
mark = pytest.mark.single_cpu if parser.engine == "pyarrow" else ()
param = pytest.param((parser(), precision), marks=mark)
params.append(param)
ids.append(f"{parser_id}-{precision}")
return {"params": params, "ids": ids}
@pytest.fixture(
params=_get_all_parser_float_precision_combinations()["params"],
ids=_get_all_parser_float_precision_combinations()["ids"],
)
def all_parsers_all_precisions(request):
"""
Fixture for all allowable combinations of parser
and float precision
"""
return request.param
_utf_values = [8, 16, 32]
_encoding_seps = ["", "-", "_"]
_encoding_prefixes = ["utf", "UTF"]
_encoding_fmts = [
f"{prefix}{sep}{{0}}" for sep in _encoding_seps for prefix in _encoding_prefixes
]
@pytest.fixture(params=_utf_values)
def utf_value(request):
"""
Fixture for all possible integer values for a UTF encoding.
"""
return request.param
@pytest.fixture(params=_encoding_fmts)
def encoding_fmt(request):
"""
Fixture for all possible string formats of a UTF encoding.
"""
return request.param
@pytest.fixture(
params=[
("-1,0", -1.0),
("-1,2e0", -1.2),
("-1e0", -1.0),
("+1e0", 1.0),
("+1e+0", 1.0),
("+1e-1", 0.1),
("+,1e1", 1.0),
("+1,e0", 1.0),
("-,1e1", -1.0),
("-1,e0", -1.0),
("0,1", 0.1),
("1,", 1.0),
(",1", 0.1),
("-,1", -0.1),
("1_,", 1.0),
("1_234,56", 1234.56),
("1_234,56e0", 1234.56),
# negative cases; must not parse as float
("_", "_"),
("-_", "-_"),
("-_1", "-_1"),
("-_1e0", "-_1e0"),
("_1", "_1"),
("_1,", "_1,"),
("_1,_", "_1,_"),
("_1e0", "_1e0"),
("1,2e_1", "1,2e_1"),
("1,2e1_0", "1,2e1_0"),
("1,_2", "1,_2"),
(",1__2", ",1__2"),
(",1e", ",1e"),
("-,1e", "-,1e"),
("1_000,000_000", "1_000,000_000"),
("1,e1_2", "1,e1_2"),
("e11,2", "e11,2"),
("1e11,2", "1e11,2"),
("1,2,2", "1,2,2"),
("1,2_1", "1,2_1"),
("1,2e-10e1", "1,2e-10e1"),
("--1,2", "--1,2"),
("1a_2,1", "1a_2,1"),
("1,2E-1", 0.12),
("1,2E1", 12.0),
]
)
def numeric_decimal(request):
"""
Fixture for all numeric formats which should get recognized. The first entry
represents the value to read while the second represents the expected result.
"""
return request.param
@pytest.fixture
def pyarrow_xfail(request):
"""
Fixture that xfails a test if the engine is pyarrow.
Use if failure is do to unsupported keywords or inconsistent results.
"""
if "all_parsers" in request.fixturenames:
parser = request.getfixturevalue("all_parsers")
elif "all_parsers_all_precisions" in request.fixturenames:
# Return value is tuple of (engine, precision)
parser = request.getfixturevalue("all_parsers_all_precisions")[0]
else:
return
if parser.engine == "pyarrow":
mark = pytest.mark.xfail(reason="pyarrow doesn't support this.")
request.applymarker(mark)
@pytest.fixture
def pyarrow_skip(request):
"""
Fixture that skips a test if the engine is pyarrow.
Use if failure is do a parsing failure from pyarrow.csv.read_csv
"""
if "all_parsers" in request.fixturenames:
parser = request.getfixturevalue("all_parsers")
elif "all_parsers_all_precisions" in request.fixturenames:
# Return value is tuple of (engine, precision)
parser = request.getfixturevalue("all_parsers_all_precisions")[0]
else:
return
if parser.engine == "pyarrow":
pytest.skip(reason="https://github.com/apache/arrow/issues/38676")
|