Spaces:
Sleeping
Sleeping
File size: 8,285 Bytes
f7c08b1 |
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 |
from __future__ import annotations
import ipaddress
import os
import re
import typing
from urllib.request import getproxies
from ._types import PrimitiveData
if typing.TYPE_CHECKING: # pragma: no cover
from ._urls import URL
def primitive_value_to_str(value: PrimitiveData) -> str:
"""
Coerce a primitive data type into a string value.
Note that we prefer JSON-style 'true'/'false' for boolean values here.
"""
if value is True:
return "true"
elif value is False:
return "false"
elif value is None:
return ""
return str(value)
def get_environment_proxies() -> dict[str, str | None]:
"""Gets proxy information from the environment"""
# urllib.request.getproxies() falls back on System
# Registry and Config for proxies on Windows and macOS.
# We don't want to propagate non-HTTP proxies into
# our configuration such as 'TRAVIS_APT_PROXY'.
proxy_info = getproxies()
mounts: dict[str, str | None] = {}
for scheme in ("http", "https", "all"):
if proxy_info.get(scheme):
hostname = proxy_info[scheme]
mounts[f"{scheme}://"] = (
hostname if "://" in hostname else f"http://{hostname}"
)
no_proxy_hosts = [host.strip() for host in proxy_info.get("no", "").split(",")]
for hostname in no_proxy_hosts:
# See https://curl.haxx.se/libcurl/c/CURLOPT_NOPROXY.html for details
# on how names in `NO_PROXY` are handled.
if hostname == "*":
# If NO_PROXY=* is used or if "*" occurs as any one of the comma
# separated hostnames, then we should just bypass any information
# from HTTP_PROXY, HTTPS_PROXY, ALL_PROXY, and always ignore
# proxies.
return {}
elif hostname:
# NO_PROXY=.google.com is marked as "all://*.google.com,
# which disables "www.google.com" but not "google.com"
# NO_PROXY=google.com is marked as "all://*google.com,
# which disables "www.google.com" and "google.com".
# (But not "wwwgoogle.com")
# NO_PROXY can include domains, IPv6, IPv4 addresses and "localhost"
# NO_PROXY=example.com,::1,localhost,192.168.0.0/16
if "://" in hostname:
mounts[hostname] = None
elif is_ipv4_hostname(hostname):
mounts[f"all://{hostname}"] = None
elif is_ipv6_hostname(hostname):
mounts[f"all://[{hostname}]"] = None
elif hostname.lower() == "localhost":
mounts[f"all://{hostname}"] = None
else:
mounts[f"all://*{hostname}"] = None
return mounts
def to_bytes(value: str | bytes, encoding: str = "utf-8") -> bytes:
return value.encode(encoding) if isinstance(value, str) else value
def to_str(value: str | bytes, encoding: str = "utf-8") -> str:
return value if isinstance(value, str) else value.decode(encoding)
def to_bytes_or_str(value: str, match_type_of: typing.AnyStr) -> typing.AnyStr:
return value if isinstance(match_type_of, str) else value.encode()
def unquote(value: str) -> str:
return value[1:-1] if value[0] == value[-1] == '"' else value
def peek_filelike_length(stream: typing.Any) -> int | None:
"""
Given a file-like stream object, return its length in number of bytes
without reading it into memory.
"""
try:
# Is it an actual file?
fd = stream.fileno()
# Yup, seems to be an actual file.
length = os.fstat(fd).st_size
except (AttributeError, OSError):
# No... Maybe it's something that supports random access, like `io.BytesIO`?
try:
# Assuming so, go to end of stream to figure out its length,
# then put it back in place.
offset = stream.tell()
length = stream.seek(0, os.SEEK_END)
stream.seek(offset)
except (AttributeError, OSError):
# Not even that? Sorry, we're doomed...
return None
return length
class URLPattern:
"""
A utility class currently used for making lookups against proxy keys...
# Wildcard matching...
>>> pattern = URLPattern("all://")
>>> pattern.matches(httpx.URL("http://example.com"))
True
# Witch scheme matching...
>>> pattern = URLPattern("https://")
>>> pattern.matches(httpx.URL("https://example.com"))
True
>>> pattern.matches(httpx.URL("http://example.com"))
False
# With domain matching...
>>> pattern = URLPattern("https://example.com")
>>> pattern.matches(httpx.URL("https://example.com"))
True
>>> pattern.matches(httpx.URL("http://example.com"))
False
>>> pattern.matches(httpx.URL("https://other.com"))
False
# Wildcard scheme, with domain matching...
>>> pattern = URLPattern("all://example.com")
>>> pattern.matches(httpx.URL("https://example.com"))
True
>>> pattern.matches(httpx.URL("http://example.com"))
True
>>> pattern.matches(httpx.URL("https://other.com"))
False
# With port matching...
>>> pattern = URLPattern("https://example.com:1234")
>>> pattern.matches(httpx.URL("https://example.com:1234"))
True
>>> pattern.matches(httpx.URL("https://example.com"))
False
"""
def __init__(self, pattern: str) -> None:
from ._urls import URL
if pattern and ":" not in pattern:
raise ValueError(
f"Proxy keys should use proper URL forms rather "
f"than plain scheme strings. "
f'Instead of "{pattern}", use "{pattern}://"'
)
url = URL(pattern)
self.pattern = pattern
self.scheme = "" if url.scheme == "all" else url.scheme
self.host = "" if url.host == "*" else url.host
self.port = url.port
if not url.host or url.host == "*":
self.host_regex: typing.Pattern[str] | None = None
elif url.host.startswith("*."):
# *.example.com should match "www.example.com", but not "example.com"
domain = re.escape(url.host[2:])
self.host_regex = re.compile(f"^.+\\.{domain}$")
elif url.host.startswith("*"):
# *example.com should match "www.example.com" and "example.com"
domain = re.escape(url.host[1:])
self.host_regex = re.compile(f"^(.+\\.)?{domain}$")
else:
# example.com should match "example.com" but not "www.example.com"
domain = re.escape(url.host)
self.host_regex = re.compile(f"^{domain}$")
def matches(self, other: URL) -> bool:
if self.scheme and self.scheme != other.scheme:
return False
if (
self.host
and self.host_regex is not None
and not self.host_regex.match(other.host)
):
return False
if self.port is not None and self.port != other.port:
return False
return True
@property
def priority(self) -> tuple[int, int, int]:
"""
The priority allows URLPattern instances to be sortable, so that
we can match from most specific to least specific.
"""
# URLs with a port should take priority over URLs without a port.
port_priority = 0 if self.port is not None else 1
# Longer hostnames should match first.
host_priority = -len(self.host)
# Longer schemes should match first.
scheme_priority = -len(self.scheme)
return (port_priority, host_priority, scheme_priority)
def __hash__(self) -> int:
return hash(self.pattern)
def __lt__(self, other: URLPattern) -> bool:
return self.priority < other.priority
def __eq__(self, other: typing.Any) -> bool:
return isinstance(other, URLPattern) and self.pattern == other.pattern
def is_ipv4_hostname(hostname: str) -> bool:
try:
ipaddress.IPv4Address(hostname.split("/")[0])
except Exception:
return False
return True
def is_ipv6_hostname(hostname: str) -> bool:
try:
ipaddress.IPv6Address(hostname.split("/")[0])
except Exception:
return False
return True
|