Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1"""
2APIs exposing metadata from third-party Python packages.
4This codebase is shared between importlib.metadata in the stdlib
5and importlib_metadata in PyPI. See
6https://github.com/python/importlib_metadata/wiki/Development-Methodology
7for more detail.
8"""
10from __future__ import annotations
12import abc
13import collections
14import email
15import functools
16import itertools
17import operator
18import os
19import pathlib
20import posixpath
21import re
22import sys
23import textwrap
24import types
25from collections.abc import Iterable, Mapping
26from contextlib import suppress
27from importlib import import_module
28from importlib.abc import MetaPathFinder
29from itertools import starmap
30from typing import Any
32from . import _meta
33from ._collections import FreezableDefaultDict, Pair
34from ._compat import (
35 NullFinder,
36 install,
37)
38from ._functools import method_cache, pass_none
39from ._itertools import always_iterable, bucket, unique_everseen
40from ._meta import PackageMetadata, SimplePath
41from ._typing import md_none
42from .compat import py39, py311
44__all__ = [
45 'Distribution',
46 'DistributionFinder',
47 'PackageMetadata',
48 'PackageNotFoundError',
49 'SimplePath',
50 'distribution',
51 'distributions',
52 'entry_points',
53 'files',
54 'metadata',
55 'packages_distributions',
56 'requires',
57 'version',
58]
61class PackageNotFoundError(ModuleNotFoundError):
62 """The package was not found."""
64 def __str__(self) -> str:
65 return f"No package metadata was found for {self.name}"
67 @property
68 def name(self) -> str: # type: ignore[override] # make readonly
69 (name,) = self.args
70 return name
73class Sectioned:
74 """
75 A simple entry point config parser for performance
77 >>> for item in Sectioned.read(Sectioned._sample):
78 ... print(item)
79 Pair(name='sec1', value='# comments ignored')
80 Pair(name='sec1', value='a = 1')
81 Pair(name='sec1', value='b = 2')
82 Pair(name='sec2', value='a = 2')
84 >>> res = Sectioned.section_pairs(Sectioned._sample)
85 >>> item = next(res)
86 >>> item.name
87 'sec1'
88 >>> item.value
89 Pair(name='a', value='1')
90 >>> item = next(res)
91 >>> item.value
92 Pair(name='b', value='2')
93 >>> item = next(res)
94 >>> item.name
95 'sec2'
96 >>> item.value
97 Pair(name='a', value='2')
98 >>> list(res)
99 []
100 """
102 _sample = textwrap.dedent(
103 """
104 [sec1]
105 # comments ignored
106 a = 1
107 b = 2
109 [sec2]
110 a = 2
111 """
112 ).lstrip()
114 @classmethod
115 def section_pairs(cls, text):
116 return (
117 section._replace(value=Pair.parse(section.value))
118 for section in cls.read(text, filter_=cls.valid)
119 if section.name is not None
120 )
122 @staticmethod
123 def read(text, filter_=None):
124 lines = filter(filter_, map(str.strip, text.splitlines()))
125 name = None
126 for value in lines:
127 section_match = value.startswith('[') and value.endswith(']')
128 if section_match:
129 name = value.strip('[]')
130 continue
131 yield Pair(name, value)
133 @staticmethod
134 def valid(line: str):
135 return line and not line.startswith('#')
138class _EntryPointMatch(types.SimpleNamespace):
139 module: str
140 attr: str
141 extras: str
144class EntryPoint:
145 """An entry point as defined by Python packaging conventions.
147 See `the packaging docs on entry points
148 <https://packaging.python.org/specifications/entry-points/>`_
149 for more information.
151 >>> ep = EntryPoint(
152 ... name=None, group=None, value='package.module:attr [extra1, extra2]')
153 >>> ep.module
154 'package.module'
155 >>> ep.attr
156 'attr'
157 >>> ep.extras
158 ['extra1', 'extra2']
160 If the value package or module are not valid identifiers, a
161 ValueError is raised on access.
163 >>> EntryPoint(name=None, group=None, value='invalid-name').module
164 Traceback (most recent call last):
165 ...
166 ValueError: ('Invalid object reference...invalid-name...
167 >>> EntryPoint(name=None, group=None, value='invalid-name').attr
168 Traceback (most recent call last):
169 ...
170 ValueError: ('Invalid object reference...invalid-name...
171 >>> EntryPoint(name=None, group=None, value='invalid-name').extras
172 Traceback (most recent call last):
173 ...
174 ValueError: ('Invalid object reference...invalid-name...
176 The same thing happens on construction.
178 >>> EntryPoint(name=None, group=None, value='invalid-name')
179 Traceback (most recent call last):
180 ...
181 ValueError: ('Invalid object reference...invalid-name...
183 """
185 pattern = re.compile(
186 r'(?P<module>[\w.]+)\s*'
187 r'(:\s*(?P<attr>[\w.]+)\s*)?'
188 r'((?P<extras>\[.*\])\s*)?$'
189 )
190 """
191 A regular expression describing the syntax for an entry point,
192 which might look like:
194 - module
195 - package.module
196 - package.module:attribute
197 - package.module:object.attribute
198 - package.module:attr [extra1, extra2]
200 Other combinations are possible as well.
202 The expression is lenient about whitespace around the ':',
203 following the attr, and following any extras.
204 """
206 name: str
207 value: str
208 group: str
210 dist: Distribution | None = None
212 def __init__(self, name: str, value: str, group: str) -> None:
213 vars(self).update(name=name, value=value, group=group)
214 self.module
216 def load(self) -> Any:
217 """Load the entry point from its definition. If only a module
218 is indicated by the value, return that module. Otherwise,
219 return the named object.
220 """
221 module = import_module(self.module)
222 attrs = filter(None, (self.attr or '').split('.'))
223 return functools.reduce(getattr, attrs, module)
225 @property
226 def module(self) -> str:
227 return self._match.module
229 @property
230 def attr(self) -> str:
231 return self._match.attr
233 @property
234 def extras(self) -> list[str]:
235 return re.findall(r'\w+', self._match.extras or '')
237 @functools.cached_property
238 def _match(self) -> _EntryPointMatch:
239 match = self.pattern.match(self.value)
240 if not match:
241 raise ValueError(
242 'Invalid object reference. '
243 'See https://packaging.python.org'
244 '/en/latest/specifications/entry-points/#data-model',
245 self.value,
246 )
247 return _EntryPointMatch(**match.groupdict())
249 def _for(self, dist):
250 vars(self).update(dist=dist)
251 return self
253 def matches(self, **params):
254 """
255 EntryPoint matches the given parameters.
257 >>> ep = EntryPoint(group='foo', name='bar', value='bing:bong [extra1, extra2]')
258 >>> ep.matches(group='foo')
259 True
260 >>> ep.matches(name='bar', value='bing:bong [extra1, extra2]')
261 True
262 >>> ep.matches(group='foo', name='other')
263 False
264 >>> ep.matches()
265 True
266 >>> ep.matches(extras=['extra1', 'extra2'])
267 True
268 >>> ep.matches(module='bing')
269 True
270 >>> ep.matches(attr='bong')
271 True
272 """
273 self._disallow_dist(params)
274 attrs = (getattr(self, param) for param in params)
275 return all(map(operator.eq, params.values(), attrs))
277 @staticmethod
278 def _disallow_dist(params):
279 """
280 Querying by dist is not allowed (dist objects are not comparable).
281 >>> EntryPoint(name='fan', value='fav', group='fag').matches(dist='foo')
282 Traceback (most recent call last):
283 ...
284 ValueError: "dist" is not suitable for matching...
285 """
286 if "dist" in params:
287 raise ValueError(
288 '"dist" is not suitable for matching. '
289 "Instead, use Distribution.entry_points.select() on a "
290 "located distribution."
291 )
293 def _key(self):
294 return self.name, self.value, self.group
296 def __lt__(self, other):
297 return self._key() < other._key()
299 def __eq__(self, other):
300 return self._key() == other._key()
302 def __setattr__(self, name, value):
303 raise AttributeError("EntryPoint objects are immutable.")
305 def __repr__(self):
306 return (
307 f'EntryPoint(name={self.name!r}, value={self.value!r}, '
308 f'group={self.group!r})'
309 )
311 def __hash__(self) -> int:
312 return hash(self._key())
315class EntryPoints(tuple):
316 """
317 An immutable collection of selectable EntryPoint objects.
318 """
320 __slots__ = ()
322 def __getitem__(self, name: str) -> EntryPoint: # type: ignore[override] # Work with str instead of int
323 """
324 Get the EntryPoint in self matching name.
325 """
326 try:
327 return next(iter(self.select(name=name)))
328 except StopIteration:
329 raise KeyError(name)
331 def __repr__(self):
332 """
333 Repr with classname and tuple constructor to
334 signal that we deviate from regular tuple behavior.
335 """
336 return '%s(%r)' % (self.__class__.__name__, tuple(self))
338 def select(self, **params) -> EntryPoints:
339 """
340 Select entry points from self that match the
341 given parameters (typically group and/or name).
342 """
343 return EntryPoints(ep for ep in self if py39.ep_matches(ep, **params))
345 @property
346 def names(self) -> set[str]:
347 """
348 Return the set of all names of all entry points.
349 """
350 return {ep.name for ep in self}
352 @property
353 def groups(self) -> set[str]:
354 """
355 Return the set of all groups of all entry points.
356 """
357 return {ep.group for ep in self}
359 @classmethod
360 def _from_text_for(cls, text, dist):
361 return cls(ep._for(dist) for ep in cls._from_text(text))
363 @staticmethod
364 def _from_text(text):
365 return (
366 EntryPoint(name=item.value.name, value=item.value.value, group=item.name)
367 for item in Sectioned.section_pairs(text or '')
368 )
371class PackagePath(pathlib.PurePosixPath):
372 """A reference to a path in a package"""
374 hash: FileHash | None
375 size: int
376 dist: Distribution
378 def read_text(self, encoding: str = 'utf-8') -> str:
379 return self.locate().read_text(encoding=encoding)
381 def read_binary(self) -> bytes:
382 return self.locate().read_bytes()
384 def locate(self) -> SimplePath:
385 """Return a path-like object for this path"""
386 return self.dist.locate_file(self)
389class FileHash:
390 def __init__(self, spec: str) -> None:
391 self.mode, _, self.value = spec.partition('=')
393 def __repr__(self) -> str:
394 return f'<FileHash mode: {self.mode} value: {self.value}>'
397class Distribution(metaclass=abc.ABCMeta):
398 """
399 An abstract Python distribution package.
401 Custom providers may derive from this class and define
402 the abstract methods to provide a concrete implementation
403 for their environment. Some providers may opt to override
404 the default implementation of some properties to bypass
405 the file-reading mechanism.
406 """
408 @abc.abstractmethod
409 def read_text(self, filename) -> str | None:
410 """Attempt to load metadata file given by the name.
412 Python distribution metadata is organized by blobs of text
413 typically represented as "files" in the metadata directory
414 (e.g. package-1.0.dist-info). These files include things
415 like:
417 - METADATA: The distribution metadata including fields
418 like Name and Version and Description.
419 - entry_points.txt: A series of entry points as defined in
420 `the entry points spec <https://packaging.python.org/en/latest/specifications/entry-points/#file-format>`_.
421 - RECORD: A record of files according to
422 `this recording spec <https://packaging.python.org/en/latest/specifications/recording-installed-packages/#the-record-file>`_.
424 A package may provide any set of files, including those
425 not listed here or none at all.
427 :param filename: The name of the file in the distribution info.
428 :return: The text if found, otherwise None.
429 """
431 @abc.abstractmethod
432 def locate_file(self, path: str | os.PathLike[str]) -> SimplePath:
433 """
434 Given a path to a file in this distribution, return a SimplePath
435 to it.
437 This method is used by callers of ``Distribution.files()`` to
438 locate files within the distribution. If it's possible for a
439 Distribution to represent files in the distribution as
440 ``SimplePath`` objects, it should implement this method
441 to resolve such objects.
443 Some Distribution providers may elect not to resolve SimplePath
444 objects within the distribution by raising a
445 NotImplementedError, but consumers of such a Distribution would
446 be unable to invoke ``Distribution.files()``.
447 """
449 @classmethod
450 def from_name(cls, name: str) -> Distribution:
451 """Return the Distribution for the given package name.
453 :param name: The name of the distribution package to search for.
454 :return: The Distribution instance (or subclass thereof) for the named
455 package, if found.
456 :raises PackageNotFoundError: When the named package's distribution
457 metadata cannot be found.
458 :raises ValueError: When an invalid value is supplied for name.
459 """
460 if not name:
461 raise ValueError("A distribution name is required.")
462 try:
463 return next(iter(cls._prefer_valid(cls.discover(name=name))))
464 except StopIteration:
465 raise PackageNotFoundError(name)
467 @classmethod
468 def discover(
469 cls, *, context: DistributionFinder.Context | None = None, **kwargs
470 ) -> Iterable[Distribution]:
471 """Return an iterable of Distribution objects for all packages.
473 Pass a ``context`` or pass keyword arguments for constructing
474 a context.
476 :context: A ``DistributionFinder.Context`` object.
477 :return: Iterable of Distribution objects for packages matching
478 the context.
479 """
480 if context and kwargs:
481 raise ValueError("cannot accept context and kwargs")
482 context = context or DistributionFinder.Context(**kwargs)
483 return itertools.chain.from_iterable(
484 resolver(context) for resolver in cls._discover_resolvers()
485 )
487 @staticmethod
488 def _prefer_valid(dists: Iterable[Distribution]) -> Iterable[Distribution]:
489 """
490 Prefer (move to the front) distributions that have metadata.
492 Ref python/importlib_resources#489.
493 """
494 buckets = bucket(dists, lambda dist: bool(dist.metadata))
495 return itertools.chain(buckets[True], buckets[False])
497 @staticmethod
498 def at(path: str | os.PathLike[str]) -> Distribution:
499 """Return a Distribution for the indicated metadata path.
501 :param path: a string or path-like object
502 :return: a concrete Distribution instance for the path
503 """
504 return PathDistribution(pathlib.Path(path))
506 @staticmethod
507 def _discover_resolvers():
508 """Search the meta_path for resolvers (MetadataPathFinders)."""
509 declared = (
510 getattr(finder, 'find_distributions', None) for finder in sys.meta_path
511 )
512 return filter(None, declared)
514 @property
515 def metadata(self) -> _meta.PackageMetadata | None:
516 """Return the parsed metadata for this Distribution.
518 The returned object will have keys that name the various bits of
519 metadata per the
520 `Core metadata specifications <https://packaging.python.org/en/latest/specifications/core-metadata/#core-metadata>`_.
522 Custom providers may provide the METADATA file or override this
523 property.
524 """
526 text = (
527 self.read_text('METADATA')
528 or self.read_text('PKG-INFO')
529 # This last clause is here to support old egg-info files. Its
530 # effect is to just end up using the PathDistribution's self._path
531 # (which points to the egg-info file) attribute unchanged.
532 or self.read_text('')
533 )
534 return self._assemble_message(text)
536 @staticmethod
537 @pass_none
538 def _assemble_message(text: str) -> _meta.PackageMetadata:
539 # deferred for performance (python/cpython#109829)
540 from . import _adapters
542 return _adapters.Message(email.message_from_string(text))
544 @property
545 def name(self) -> str:
546 """Return the 'Name' metadata for the distribution package."""
547 return md_none(self.metadata)['Name']
549 @property
550 def _normalized_name(self):
551 """Return a normalized version of the name."""
552 return Prepared.normalize(self.name)
554 @property
555 def version(self) -> str:
556 """Return the 'Version' metadata for the distribution package."""
557 return md_none(self.metadata)['Version']
559 @property
560 def entry_points(self) -> EntryPoints:
561 """
562 Return EntryPoints for this distribution.
564 Custom providers may provide the ``entry_points.txt`` file
565 or override this property.
566 """
567 return EntryPoints._from_text_for(self.read_text('entry_points.txt'), self)
569 @property
570 def files(self) -> list[PackagePath] | None:
571 """Files in this distribution.
573 :return: List of PackagePath for this distribution or None
575 Result is `None` if the metadata file that enumerates files
576 (i.e. RECORD for dist-info, or installed-files.txt or
577 SOURCES.txt for egg-info) is missing.
578 Result may be empty if the metadata exists but is empty.
580 Custom providers are recommended to provide a "RECORD" file (in
581 ``read_text``) or override this property to allow for callers to be
582 able to resolve filenames provided by the package.
583 """
585 def make_file(name, hash=None, size_str=None):
586 result = PackagePath(name)
587 result.hash = FileHash(hash) if hash else None
588 result.size = int(size_str) if size_str else None
589 result.dist = self
590 return result
592 @pass_none
593 def make_files(lines):
594 # Delay csv import, since Distribution.files is not as widely used
595 # as other parts of importlib.metadata
596 import csv
598 return starmap(make_file, csv.reader(lines))
600 @pass_none
601 def skip_missing_files(package_paths):
602 return list(filter(lambda path: path.locate().exists(), package_paths))
604 return skip_missing_files(
605 make_files(
606 self._read_files_distinfo()
607 or self._read_files_egginfo_installed()
608 or self._read_files_egginfo_sources()
609 )
610 )
612 def _read_files_distinfo(self):
613 """
614 Read the lines of RECORD.
615 """
616 text = self.read_text('RECORD')
617 return text and text.splitlines()
619 def _read_files_egginfo_installed(self):
620 """
621 Read installed-files.txt and return lines in a similar
622 CSV-parsable format as RECORD: each file must be placed
623 relative to the site-packages directory and must also be
624 quoted (since file names can contain literal commas).
626 This file is written when the package is installed by pip,
627 but it might not be written for other installation methods.
628 Assume the file is accurate if it exists.
629 """
630 text = self.read_text('installed-files.txt')
631 # Prepend the .egg-info/ subdir to the lines in this file.
632 # But this subdir is only available from PathDistribution's
633 # self._path.
634 subdir = getattr(self, '_path', None)
635 if not text or not subdir:
636 return
638 paths = (
639 py311.relative_fix((subdir / name).resolve())
640 .relative_to(self.locate_file('').resolve(), walk_up=True)
641 .as_posix()
642 for name in text.splitlines()
643 )
644 return map('"{}"'.format, paths)
646 def _read_files_egginfo_sources(self):
647 """
648 Read SOURCES.txt and return lines in a similar CSV-parsable
649 format as RECORD: each file name must be quoted (since it
650 might contain literal commas).
652 Note that SOURCES.txt is not a reliable source for what
653 files are installed by a package. This file is generated
654 for a source archive, and the files that are present
655 there (e.g. setup.py) may not correctly reflect the files
656 that are present after the package has been installed.
657 """
658 text = self.read_text('SOURCES.txt')
659 return text and map('"{}"'.format, text.splitlines())
661 @property
662 def requires(self) -> list[str] | None:
663 """Generated requirements specified for this Distribution"""
664 reqs = self._read_dist_info_reqs() or self._read_egg_info_reqs()
665 return reqs and list(reqs)
667 def _read_dist_info_reqs(self):
668 return self.metadata.get_all('Requires-Dist')
670 def _read_egg_info_reqs(self):
671 source = self.read_text('requires.txt')
672 return pass_none(self._deps_from_requires_text)(source)
674 @classmethod
675 def _deps_from_requires_text(cls, source):
676 return cls._convert_egg_info_reqs_to_simple_reqs(Sectioned.read(source))
678 @staticmethod
679 def _convert_egg_info_reqs_to_simple_reqs(sections):
680 """
681 Historically, setuptools would solicit and store 'extra'
682 requirements, including those with environment markers,
683 in separate sections. More modern tools expect each
684 dependency to be defined separately, with any relevant
685 extras and environment markers attached directly to that
686 requirement. This method converts the former to the
687 latter. See _test_deps_from_requires_text for an example.
688 """
690 def make_condition(name):
691 return name and f'extra == "{name}"'
693 def quoted_marker(section):
694 section = section or ''
695 extra, sep, markers = section.partition(':')
696 if extra and markers:
697 markers = f'({markers})'
698 conditions = list(filter(None, [markers, make_condition(extra)]))
699 return '; ' + ' and '.join(conditions) if conditions else ''
701 def url_req_space(req):
702 """
703 PEP 508 requires a space between the url_spec and the quoted_marker.
704 Ref python/importlib_metadata#357.
705 """
706 # '@' is uniquely indicative of a url_req.
707 return ' ' * ('@' in req)
709 for section in sections:
710 space = url_req_space(section.value)
711 yield section.value + space + quoted_marker(section.name)
713 @property
714 def origin(self):
715 return self._load_json('direct_url.json')
717 def _load_json(self, filename):
718 # Deferred for performance (python/importlib_metadata#503)
719 import json
721 return pass_none(json.loads)(
722 self.read_text(filename),
723 object_hook=lambda data: types.SimpleNamespace(**data),
724 )
727class DistributionFinder(MetaPathFinder):
728 """
729 A MetaPathFinder capable of discovering installed distributions.
731 Custom providers should implement this interface in order to
732 supply metadata.
733 """
735 class Context:
736 """
737 Keyword arguments presented by the caller to
738 ``distributions()`` or ``Distribution.discover()``
739 to narrow the scope of a search for distributions
740 in all DistributionFinders.
742 Each DistributionFinder may expect any parameters
743 and should attempt to honor the canonical
744 parameters defined below when appropriate.
746 This mechanism gives a custom provider a means to
747 solicit additional details from the caller beyond
748 "name" and "path" when searching distributions.
749 For example, imagine a provider that exposes suites
750 of packages in either a "public" or "private" ``realm``.
751 A caller may wish to query only for distributions in
752 a particular realm and could call
753 ``distributions(realm="private")`` to signal to the
754 custom provider to only include distributions from that
755 realm.
756 """
758 name = None
759 """
760 Specific name for which a distribution finder should match.
761 A name of ``None`` matches all distributions.
762 """
764 def __init__(self, **kwargs):
765 vars(self).update(kwargs)
767 @property
768 def path(self) -> list[str]:
769 """
770 The sequence of directory path that a distribution finder
771 should search.
773 Typically refers to Python installed package paths such as
774 "site-packages" directories and defaults to ``sys.path``.
775 """
776 return vars(self).get('path', sys.path)
778 @abc.abstractmethod
779 def find_distributions(self, context=Context()) -> Iterable[Distribution]:
780 """
781 Find distributions.
783 Return an iterable of all Distribution instances capable of
784 loading the metadata for packages matching the ``context``,
785 a DistributionFinder.Context instance.
786 """
789class FastPath:
790 """
791 Micro-optimized class for searching a root for children.
793 Root is a path on the file system that may contain metadata
794 directories either as natural directories or within a zip file.
796 >>> FastPath('').children()
797 ['...']
799 FastPath objects are cached and recycled for any given root.
801 >>> FastPath('foobar') is FastPath('foobar')
802 True
803 """
805 @functools.lru_cache() # type: ignore[misc]
806 def __new__(cls, root):
807 return super().__new__(cls)
809 def __init__(self, root):
810 self.root = root
812 def joinpath(self, child):
813 return pathlib.Path(self.root, child)
815 def children(self):
816 with suppress(Exception):
817 return os.listdir(self.root or '.')
818 with suppress(Exception):
819 return self.zip_children()
820 return []
822 def zip_children(self):
823 # deferred for performance (python/importlib_metadata#502)
824 from zipp.compat.overlay import zipfile
826 zip_path = zipfile.Path(self.root)
827 names = zip_path.root.namelist()
828 self.joinpath = zip_path.joinpath
830 return dict.fromkeys(child.split(posixpath.sep, 1)[0] for child in names)
832 def search(self, name):
833 return self.lookup(self.mtime).search(name)
835 @property
836 def mtime(self):
837 with suppress(OSError):
838 return os.stat(self.root).st_mtime
839 self.lookup.cache_clear()
841 @method_cache
842 def lookup(self, mtime):
843 return Lookup(self)
846class Lookup:
847 """
848 A micro-optimized class for searching a (fast) path for metadata.
849 """
851 def __init__(self, path: FastPath):
852 """
853 Calculate all of the children representing metadata.
855 From the children in the path, calculate early all of the
856 children that appear to represent metadata (infos) or legacy
857 metadata (eggs).
858 """
860 base = os.path.basename(path.root).lower()
861 base_is_egg = base.endswith(".egg")
862 self.infos = FreezableDefaultDict(list)
863 self.eggs = FreezableDefaultDict(list)
865 for child in path.children():
866 low = child.lower()
867 if low.endswith((".dist-info", ".egg-info")):
868 # rpartition is faster than splitext and suitable for this purpose.
869 name = low.rpartition(".")[0].partition("-")[0]
870 normalized = Prepared.normalize(name)
871 self.infos[normalized].append(path.joinpath(child))
872 elif base_is_egg and low == "egg-info":
873 name = base.rpartition(".")[0].partition("-")[0]
874 legacy_normalized = Prepared.legacy_normalize(name)
875 self.eggs[legacy_normalized].append(path.joinpath(child))
877 self.infos.freeze()
878 self.eggs.freeze()
880 def search(self, prepared: Prepared):
881 """
882 Yield all infos and eggs matching the Prepared query.
883 """
884 infos = (
885 self.infos[prepared.normalized]
886 if prepared
887 else itertools.chain.from_iterable(self.infos.values())
888 )
889 eggs = (
890 self.eggs[prepared.legacy_normalized]
891 if prepared
892 else itertools.chain.from_iterable(self.eggs.values())
893 )
894 return itertools.chain(infos, eggs)
897class Prepared:
898 """
899 A prepared search query for metadata on a possibly-named package.
901 Pre-calculates the normalization to prevent repeated operations.
903 >>> none = Prepared(None)
904 >>> none.normalized
905 >>> none.legacy_normalized
906 >>> bool(none)
907 False
908 >>> sample = Prepared('Sample__Pkg-name.foo')
909 >>> sample.normalized
910 'sample_pkg_name_foo'
911 >>> sample.legacy_normalized
912 'sample__pkg_name.foo'
913 >>> bool(sample)
914 True
915 """
917 normalized = None
918 legacy_normalized = None
920 def __init__(self, name: str | None):
921 self.name = name
922 if name is None:
923 return
924 self.normalized = self.normalize(name)
925 self.legacy_normalized = self.legacy_normalize(name)
927 @staticmethod
928 def normalize(name):
929 """
930 PEP 503 normalization plus dashes as underscores.
931 """
932 return re.sub(r"[-_.]+", "-", name).lower().replace('-', '_')
934 @staticmethod
935 def legacy_normalize(name):
936 """
937 Normalize the package name as found in the convention in
938 older packaging tools versions and specs.
939 """
940 return name.lower().replace('-', '_')
942 def __bool__(self):
943 return bool(self.name)
946@install
947class MetadataPathFinder(NullFinder, DistributionFinder):
948 """A degenerate finder for distribution packages on the file system.
950 This finder supplies only a find_distributions() method for versions
951 of Python that do not have a PathFinder find_distributions().
952 """
954 @classmethod
955 def find_distributions(
956 cls, context=DistributionFinder.Context()
957 ) -> Iterable[PathDistribution]:
958 """
959 Find distributions.
961 Return an iterable of all Distribution instances capable of
962 loading the metadata for packages matching ``context.name``
963 (or all names if ``None`` indicated) along the paths in the list
964 of directories ``context.path``.
965 """
966 found = cls._search_paths(context.name, context.path)
967 return map(PathDistribution, found)
969 @classmethod
970 def _search_paths(cls, name, paths):
971 """Find metadata directories in paths heuristically."""
972 prepared = Prepared(name)
973 return itertools.chain.from_iterable(
974 path.search(prepared) for path in map(FastPath, paths)
975 )
977 @classmethod
978 def invalidate_caches(cls) -> None:
979 FastPath.__new__.cache_clear()
982class PathDistribution(Distribution):
983 def __init__(self, path: SimplePath) -> None:
984 """Construct a distribution.
986 :param path: SimplePath indicating the metadata directory.
987 """
988 self._path = path
990 def read_text(self, filename: str | os.PathLike[str]) -> str | None:
991 with suppress(
992 FileNotFoundError,
993 IsADirectoryError,
994 KeyError,
995 NotADirectoryError,
996 PermissionError,
997 ):
998 return self._path.joinpath(filename).read_text(encoding='utf-8')
1000 return None
1002 read_text.__doc__ = Distribution.read_text.__doc__
1004 def locate_file(self, path: str | os.PathLike[str]) -> SimplePath:
1005 return self._path.parent / path
1007 @property
1008 def _normalized_name(self):
1009 """
1010 Performance optimization: where possible, resolve the
1011 normalized name from the file system path.
1012 """
1013 stem = os.path.basename(str(self._path))
1014 return (
1015 pass_none(Prepared.normalize)(self._name_from_stem(stem))
1016 or super()._normalized_name
1017 )
1019 @staticmethod
1020 def _name_from_stem(stem):
1021 """
1022 >>> PathDistribution._name_from_stem('foo-3.0.egg-info')
1023 'foo'
1024 >>> PathDistribution._name_from_stem('CherryPy-3.0.dist-info')
1025 'CherryPy'
1026 >>> PathDistribution._name_from_stem('face.egg-info')
1027 'face'
1028 >>> PathDistribution._name_from_stem('foo.bar')
1029 """
1030 filename, ext = os.path.splitext(stem)
1031 if ext not in ('.dist-info', '.egg-info'):
1032 return
1033 name, sep, rest = filename.partition('-')
1034 return name
1037def distribution(distribution_name: str) -> Distribution:
1038 """Get the ``Distribution`` instance for the named package.
1040 :param distribution_name: The name of the distribution package as a string.
1041 :return: A ``Distribution`` instance (or subclass thereof).
1042 """
1043 return Distribution.from_name(distribution_name)
1046def distributions(**kwargs) -> Iterable[Distribution]:
1047 """Get all ``Distribution`` instances in the current environment.
1049 :return: An iterable of ``Distribution`` instances.
1050 """
1051 return Distribution.discover(**kwargs)
1054def metadata(distribution_name: str) -> _meta.PackageMetadata | None:
1055 """Get the metadata for the named package.
1057 :param distribution_name: The name of the distribution package to query.
1058 :return: A PackageMetadata containing the parsed metadata.
1059 """
1060 return Distribution.from_name(distribution_name).metadata
1063def version(distribution_name: str) -> str:
1064 """Get the version string for the named package.
1066 :param distribution_name: The name of the distribution package to query.
1067 :return: The version string for the package as defined in the package's
1068 "Version" metadata key.
1069 """
1070 return distribution(distribution_name).version
1073_unique = functools.partial(
1074 unique_everseen,
1075 key=py39.normalized_name,
1076)
1077"""
1078Wrapper for ``distributions`` to return unique distributions by name.
1079"""
1082def entry_points(**params) -> EntryPoints:
1083 """Return EntryPoint objects for all installed packages.
1085 Pass selection parameters (group or name) to filter the
1086 result to entry points matching those properties (see
1087 EntryPoints.select()).
1089 :return: EntryPoints for all installed packages.
1090 """
1091 eps = itertools.chain.from_iterable(
1092 dist.entry_points for dist in _unique(distributions())
1093 )
1094 return EntryPoints(eps).select(**params)
1097def files(distribution_name: str) -> list[PackagePath] | None:
1098 """Return a list of files for the named package.
1100 :param distribution_name: The name of the distribution package to query.
1101 :return: List of files composing the distribution.
1102 """
1103 return distribution(distribution_name).files
1106def requires(distribution_name: str) -> list[str] | None:
1107 """
1108 Return a list of requirements for the named package.
1110 :return: An iterable of requirements, suitable for
1111 packaging.requirement.Requirement.
1112 """
1113 return distribution(distribution_name).requires
1116def packages_distributions() -> Mapping[str, list[str]]:
1117 """
1118 Return a mapping of top-level packages to their
1119 distributions.
1121 >>> import collections.abc
1122 >>> pkgs = packages_distributions()
1123 >>> all(isinstance(dist, collections.abc.Sequence) for dist in pkgs.values())
1124 True
1125 """
1126 pkg_to_dist = collections.defaultdict(list)
1127 for dist in distributions():
1128 for pkg in _top_level_declared(dist) or _top_level_inferred(dist):
1129 pkg_to_dist[pkg].append(md_none(dist.metadata)['Name'])
1130 return dict(pkg_to_dist)
1133def _top_level_declared(dist):
1134 return (dist.read_text('top_level.txt') or '').split()
1137def _topmost(name: PackagePath) -> str | None:
1138 """
1139 Return the top-most parent as long as there is a parent.
1140 """
1141 top, *rest = name.parts
1142 return top if rest else None
1145def _get_toplevel_name(name: PackagePath) -> str:
1146 """
1147 Infer a possibly importable module name from a name presumed on
1148 sys.path.
1150 >>> _get_toplevel_name(PackagePath('foo.py'))
1151 'foo'
1152 >>> _get_toplevel_name(PackagePath('foo'))
1153 'foo'
1154 >>> _get_toplevel_name(PackagePath('foo.pyc'))
1155 'foo'
1156 >>> _get_toplevel_name(PackagePath('foo/__init__.py'))
1157 'foo'
1158 >>> _get_toplevel_name(PackagePath('foo.pth'))
1159 'foo.pth'
1160 >>> _get_toplevel_name(PackagePath('foo.dist-info'))
1161 'foo.dist-info'
1162 """
1163 # Defer import of inspect for performance (python/cpython#118761)
1164 import inspect
1166 return _topmost(name) or inspect.getmodulename(name) or str(name)
1169def _top_level_inferred(dist):
1170 opt_names = set(map(_get_toplevel_name, always_iterable(dist.files)))
1172 def importable_name(name):
1173 return '.' not in name
1175 return filter(importable_name, opt_names)