Загрузить файлы в «venv/Lib/site-packages/pip/_internal/utils»

This commit is contained in:
2026-07-02 19:10:53 +00:00
parent c2a6b91c8a
commit 1da26aa27a
5 changed files with 567 additions and 0 deletions

View File

@@ -0,0 +1,88 @@
from __future__ import annotations
import itertools
import os
import shutil
import sys
from pip._internal.cli.main import main
from pip._internal.utils.compat import WINDOWS
_EXECUTABLE_NAMES = [
"pip",
f"pip{sys.version_info.major}",
f"pip{sys.version_info.major}.{sys.version_info.minor}",
]
if WINDOWS:
_allowed_extensions = {"", ".exe"}
_EXECUTABLE_NAMES = [
"".join(parts)
for parts in itertools.product(_EXECUTABLE_NAMES, _allowed_extensions)
]
def _wrapper(args: list[str] | None = None) -> int:
"""Central wrapper for all old entrypoints.
Historically pip has had several entrypoints defined. Because of issues
arising from PATH, sys.path, multiple Pythons, their interactions, and most
of them having a pip installed, users suffer every time an entrypoint gets
moved.
To alleviate this pain, and provide a mechanism for warning users and
directing them to an appropriate place for help, we now define all of
our old entrypoints as wrappers for the current one.
"""
sys.stderr.write(
"WARNING: pip is being invoked by an old script wrapper. This will "
"fail in a future version of pip.\n"
"Please see https://github.com/pypa/pip/issues/5599 for advice on "
"fixing the underlying issue.\n"
"To avoid this problem you can invoke Python with '-m pip' instead of "
"running pip directly.\n"
)
return main(args)
def get_best_invocation_for_this_pip() -> str:
"""Try to figure out the best way to invoke pip in the current environment."""
binary_directory = "Scripts" if WINDOWS else "bin"
binary_prefix = os.path.join(sys.prefix, binary_directory)
# Try to use pip[X[.Y]] names, if those executables for this environment are
# the first on PATH with that name.
path_parts = os.path.normcase(os.environ.get("PATH", "")).split(os.pathsep)
exe_are_in_PATH = os.path.normcase(binary_prefix) in path_parts
if exe_are_in_PATH:
for exe_name in _EXECUTABLE_NAMES:
found_executable = shutil.which(exe_name)
binary_executable = os.path.join(binary_prefix, exe_name)
if (
found_executable
and os.path.exists(binary_executable)
and os.path.samefile(
found_executable,
binary_executable,
)
):
return exe_name
# Use the `-m` invocation, if there's no "nice" invocation.
return f"{get_best_invocation_for_this_python()} -m pip"
def get_best_invocation_for_this_python() -> str:
"""Try to figure out the best way to invoke the current Python."""
exe = sys.executable
exe_name = os.path.basename(exe)
# Try to use the basename, if it's the first executable.
found_executable = shutil.which(exe_name)
# Virtual environments often symlink to their parent Python binaries, but we don't
# want to treat the Python binaries as equivalent when the environment's Python is
# not on PATH (not activated). Thus, we don't follow symlinks.
if found_executable and os.path.samestat(os.lstat(found_executable), os.lstat(exe)):
return exe_name
# Use the full executable name, because we couldn't find something simpler.
return exe

View File

@@ -0,0 +1,203 @@
from __future__ import annotations
import fnmatch
import os
import os.path
import random
import sys
from collections.abc import Generator
from contextlib import contextmanager
from pathlib import Path
from tempfile import NamedTemporaryFile
from typing import Any, BinaryIO, Callable, cast
from pip._internal.utils.compat import get_path_uid
from pip._internal.utils.misc import format_size
from pip._internal.utils.retry import retry
def check_path_owner(path: str) -> bool:
# If we don't have a way to check the effective uid of this process, then
# we'll just assume that we own the directory.
if sys.platform == "win32" or not hasattr(os, "geteuid"):
return True
assert os.path.isabs(path)
previous = None
while path != previous:
if os.path.lexists(path):
# Check if path is writable by current user.
if os.geteuid() == 0:
# Special handling for root user in order to handle properly
# cases where users use sudo without -H flag.
try:
path_uid = get_path_uid(path)
except OSError:
return False
return path_uid == 0
else:
return os.access(path, os.W_OK)
else:
previous, path = path, os.path.dirname(path)
return False # assume we don't own the path
@contextmanager
def adjacent_tmp_file(path: str, **kwargs: Any) -> Generator[BinaryIO, None, None]:
"""Return a file-like object pointing to a tmp file next to path.
The file is created securely and is ensured to be written to disk
after the context reaches its end.
kwargs will be passed to tempfile.NamedTemporaryFile to control
the way the temporary file will be opened.
"""
with NamedTemporaryFile(
delete=False,
dir=os.path.dirname(path),
prefix=os.path.basename(path),
suffix=".tmp",
**kwargs,
) as f:
result = cast(BinaryIO, f)
try:
yield result
finally:
result.flush()
os.fsync(result.fileno())
replace = retry(stop_after_delay=1, wait=0.25)(os.replace)
# test_writable_dir and _test_writable_dir_win are copied from Flit,
# with the author's agreement to also place them under pip's license.
def test_writable_dir(path: str) -> bool:
"""Check if a directory is writable.
Uses os.access() on POSIX, tries creating files on Windows.
"""
# If the directory doesn't exist, find the closest parent that does.
while not os.path.isdir(path):
parent = os.path.dirname(path)
if parent == path:
break # Should never get here, but infinite loops are bad
path = parent
if os.name == "posix":
return os.access(path, os.W_OK)
return _test_writable_dir_win(path)
def _test_writable_dir_win(path: str) -> bool:
# os.access doesn't work on Windows: http://bugs.python.org/issue2528
# and we can't use tempfile: http://bugs.python.org/issue22107
basename = "accesstest_deleteme_fishfingers_custard_"
alphabet = "abcdefghijklmnopqrstuvwxyz0123456789"
for _ in range(10):
name = basename + "".join(random.choice(alphabet) for _ in range(6))
file = os.path.join(path, name)
try:
fd = os.open(file, os.O_RDWR | os.O_CREAT | os.O_EXCL)
except FileExistsError:
pass
except PermissionError:
# This could be because there's a directory with the same name.
# But it's highly unlikely there's a directory called that,
# so we'll assume it's because the parent dir is not writable.
# This could as well be because the parent dir is not readable,
# due to non-privileged user access.
return False
else:
os.close(fd)
os.unlink(file)
return True
# This should never be reached
raise OSError("Unexpected condition testing for writable directory")
def find_files(path: str, pattern: str) -> list[str]:
"""Returns a list of absolute paths of files beneath path, recursively,
with filenames which match the UNIX-style shell glob pattern."""
result: list[str] = []
for root, _, files in os.walk(path):
matches = fnmatch.filter(files, pattern)
result.extend(os.path.join(root, f) for f in matches)
return result
def file_size(path: str) -> int | float:
# If it's a symlink, return 0.
if os.path.islink(path):
return 0
return os.path.getsize(path)
def format_file_size(path: str) -> str:
return format_size(file_size(path))
def directory_size(path: str) -> int | float:
size = 0.0
for root, _dirs, files in os.walk(path):
for filename in files:
file_path = os.path.join(root, filename)
size += file_size(file_path)
return size
def format_directory_size(path: str) -> str:
return format_size(directory_size(path))
def copy_directory_permissions(directory: str, target_file: BinaryIO) -> None:
mode = (
os.stat(directory).st_mode & 0o666 # select read/write permissions of directory
| 0o600 # set owner read/write permissions
)
# Change permissions only if there is no risk of following a symlink.
if os.chmod in os.supports_fd:
os.chmod(target_file.fileno(), mode)
elif os.chmod in os.supports_follow_symlinks:
os.chmod(target_file.name, mode, follow_symlinks=False)
def _subdirs_without_generic(
path: str, predicate: Callable[[str, list[str]], bool]
) -> Generator[Path]:
"""Yields every subdirectory of +path+ that has no files matching the
predicate under it."""
directories = []
excluded = set()
for root_str, _, filenames in os.walk(Path(path).resolve()):
root = Path(root_str)
if predicate(root_str, filenames):
# This directory should be excluded, so exclude it and all of its
# parent directories.
# The last item in root.parents is ".", so we ignore it.
#
# Wrapping this in `list()` is only needed for Python 3.9.
excluded.update(list(root.parents)[:-1])
excluded.add(root)
directories.append(root)
for d in sorted(directories, reverse=True):
if d not in excluded:
yield d
def subdirs_without_files(path: str) -> Generator[Path]:
"""Yields every subdirectory of +path+ that has no files under it."""
return _subdirs_without_generic(path, lambda root, filenames: len(filenames) > 0)
def subdirs_without_wheels(path: str) -> Generator[Path]:
"""Yields every subdirectory of +path+ that has no .whl files under it."""
return _subdirs_without_generic(
path, lambda root, filenames: any(x.endswith(".whl") for x in filenames)
)

View File

@@ -0,0 +1,24 @@
"""Filetype information."""
from pip._internal.utils.misc import splitext
WHEEL_EXTENSION = ".whl"
BZ2_EXTENSIONS: tuple[str, ...] = (".tar.bz2", ".tbz")
XZ_EXTENSIONS: tuple[str, ...] = (
".tar.xz",
".txz",
".tlz",
".tar.lz",
".tar.lzma",
)
ZIP_EXTENSIONS: tuple[str, ...] = (".zip", WHEEL_EXTENSION)
TAR_EXTENSIONS: tuple[str, ...] = (".tar.gz", ".tgz", ".tar")
ARCHIVE_EXTENSIONS = ZIP_EXTENSIONS + BZ2_EXTENSIONS + TAR_EXTENSIONS + XZ_EXTENSIONS
def is_archive_file(name: str) -> bool:
"""Return True if `name` is a considered as an archive file."""
ext = splitext(name)[1].lower()
if ext in ARCHIVE_EXTENSIONS:
return True
return False

View File

@@ -0,0 +1,102 @@
from __future__ import annotations
import os
import sys
def glibc_version_string() -> str | None:
"Returns glibc version string, or None if not using glibc."
return glibc_version_string_confstr() or glibc_version_string_ctypes()
def glibc_version_string_confstr() -> str | None:
"Primary implementation of glibc_version_string using os.confstr."
# os.confstr is quite a bit faster than ctypes.DLL. It's also less likely
# to be broken or missing. This strategy is used in the standard library
# platform module:
# https://github.com/python/cpython/blob/fcf1d003bf4f0100c9d0921ff3d70e1127ca1b71/Lib/platform.py#L175-L183
if sys.platform == "win32":
return None
try:
gnu_libc_version = os.confstr("CS_GNU_LIBC_VERSION")
if gnu_libc_version is None:
return None
# os.confstr("CS_GNU_LIBC_VERSION") returns a string like "glibc 2.17":
_, version = gnu_libc_version.split()
except (AttributeError, OSError, ValueError):
# os.confstr() or CS_GNU_LIBC_VERSION not available (or a bad value)...
return None
return version
def glibc_version_string_ctypes() -> str | None:
"Fallback implementation of glibc_version_string using ctypes."
try:
import ctypes
except ImportError:
return None
# ctypes.CDLL(None) internally calls dlopen(NULL), and as the dlopen
# manpage says, "If filename is NULL, then the returned handle is for the
# main program". This way we can let the linker do the work to figure out
# which libc our process is actually using.
#
# We must also handle the special case where the executable is not a
# dynamically linked executable. This can occur when using musl libc,
# for example. In this situation, dlopen() will error, leading to an
# OSError. Interestingly, at least in the case of musl, there is no
# errno set on the OSError. The single string argument used to construct
# OSError comes from libc itself and is therefore not portable to
# hard code here. In any case, failure to call dlopen() means we
# can't proceed, so we bail on our attempt.
try:
process_namespace = ctypes.CDLL(None)
except OSError:
return None
try:
gnu_get_libc_version = process_namespace.gnu_get_libc_version
except AttributeError:
# Symbol doesn't exist -> therefore, we are not linked to
# glibc.
return None
# Call gnu_get_libc_version, which returns a string like "2.5"
gnu_get_libc_version.restype = ctypes.c_char_p
version_str: str = gnu_get_libc_version()
# py2 / py3 compatibility:
if not isinstance(version_str, str):
version_str = version_str.decode("ascii")
return version_str
# platform.libc_ver regularly returns completely nonsensical glibc
# versions. E.g. on my computer, platform says:
#
# ~$ python2.7 -c 'import platform; print(platform.libc_ver())'
# ('glibc', '2.7')
# ~$ python3.5 -c 'import platform; print(platform.libc_ver())'
# ('glibc', '2.9')
#
# But the truth is:
#
# ~$ ldd --version
# ldd (Debian GLIBC 2.22-11) 2.22
#
# This is unfortunate, because it means that the linehaul data on libc
# versions that was generated by pip 8.1.2 and earlier is useless and
# misleading. Solution: instead of using platform, use our code that actually
# works.
def libc_ver() -> tuple[str, str]:
"""Try to determine the glibc version
Returns a tuple of strings (lib, version) which default to empty strings
in case the lookup fails.
"""
glibc_version = glibc_version_string()
if glibc_version is None:
return ("", "")
else:
return ("glibc", glibc_version)

View File

@@ -0,0 +1,150 @@
from __future__ import annotations
import hashlib
from collections.abc import Iterable
from typing import TYPE_CHECKING, BinaryIO, NoReturn
from pip._internal.exceptions import HashMismatch, HashMissing, InstallationError
from pip._internal.utils.misc import read_chunks
if TYPE_CHECKING:
from hashlib import _Hash
# The recommended hash algo of the moment. Change this whenever the state of
# the art changes; it won't hurt backward compatibility.
FAVORITE_HASH = "sha256"
# Names of hashlib algorithms allowed by the --hash option and ``pip hash``
# Currently, those are the ones at least as collision-resistant as sha256.
STRONG_HASHES = ["sha256", "sha384", "sha512"]
class Hashes:
"""A wrapper that builds multiple hashes at once and checks them against
known-good values
"""
def __init__(self, hashes: dict[str, list[str]] | None = None) -> None:
"""
:param hashes: A dict of algorithm names pointing to lists of allowed
hex digests
"""
allowed = {}
if hashes is not None:
for alg, keys in hashes.items():
# Make sure values are always sorted (to ease equality checks)
allowed[alg] = [k.lower() for k in sorted(keys)]
self._allowed = allowed
def __and__(self, other: Hashes) -> Hashes:
if not isinstance(other, Hashes):
return NotImplemented
# If either of the Hashes object is entirely empty (i.e. no hash
# specified at all), all hashes from the other object are allowed.
if not other:
return self
if not self:
return other
# Otherwise only hashes that present in both objects are allowed.
new = {}
for alg, values in other._allowed.items():
if alg not in self._allowed:
continue
new[alg] = [v for v in values if v in self._allowed[alg]]
return Hashes(new)
@property
def digest_count(self) -> int:
return sum(len(digests) for digests in self._allowed.values())
def is_hash_allowed(self, hash_name: str, hex_digest: str) -> bool:
"""Return whether the given hex digest is allowed."""
return hex_digest in self._allowed.get(hash_name, [])
def check_against_chunks(self, chunks: Iterable[bytes]) -> None:
"""Check good hashes against ones built from iterable of chunks of
data.
Raise HashMismatch if none match.
"""
gots = {}
for hash_name in self._allowed.keys():
try:
gots[hash_name] = hashlib.new(hash_name)
except (ValueError, TypeError):
raise InstallationError(f"Unknown hash name: {hash_name}")
for chunk in chunks:
for hash in gots.values():
hash.update(chunk)
for hash_name, got in gots.items():
if got.hexdigest() in self._allowed[hash_name]:
return
self._raise(gots)
def _raise(self, gots: dict[str, _Hash]) -> NoReturn:
raise HashMismatch(self._allowed, gots)
def check_against_file(self, file: BinaryIO) -> None:
"""Check good hashes against a file-like object
Raise HashMismatch if none match.
"""
return self.check_against_chunks(read_chunks(file))
def check_against_path(self, path: str) -> None:
with open(path, "rb") as file:
return self.check_against_file(file)
def has_one_of(self, hashes: dict[str, str]) -> bool:
"""Return whether any of the given hashes are allowed."""
for hash_name, hex_digest in hashes.items():
if self.is_hash_allowed(hash_name, hex_digest):
return True
return False
def __bool__(self) -> bool:
"""Return whether I know any known-good hashes."""
return bool(self._allowed)
def __eq__(self, other: object) -> bool:
if not isinstance(other, Hashes):
return NotImplemented
return self._allowed == other._allowed
def __hash__(self) -> int:
return hash(
",".join(
sorted(
":".join((alg, digest))
for alg, digest_list in self._allowed.items()
for digest in digest_list
)
)
)
class MissingHashes(Hashes):
"""A workalike for Hashes used when we're missing a hash for a requirement
It computes the actual hash of the requirement and raises a HashMissing
exception showing it to the user.
"""
def __init__(self) -> None:
"""Don't offer the ``hashes`` kwarg."""
# Pass our favorite hash in to generate a "gotten hash". With the
# empty list, it will never match, so an error will always raise.
super().__init__(hashes={FAVORITE_HASH: []})
def _raise(self, gots: dict[str, _Hash]) -> NoReturn:
raise HashMissing(gots[FAVORITE_HASH].hexdigest())