Merge branch 'master' into bugfix/94-bad-path

Author: jaraco

importlib_metadata/__init__.py

@@ -10,6 +10,7 @@
 import operator
 import functools
 import itertools
+import posixpath
 import collections
 
 from ._compat import (
@@ -23,7 +24,6 @@
     NotADirectoryError,
     PermissionError,
     pathlib,
-    PYPY_OPEN_BUG,
     ModuleNotFoundError,
     MetaPathFinder,
     email_message_from_string,
@@ -389,10 +389,6 @@ def path(self):
             """
             return vars(self).get('path', sys.path)
 
-        @property
-        def pattern(self):
-            return '.*' if self.name is None else re.escape(self.name)
-
     @abc.abstractmethod
     def find_distributions(self, context=Context()):
         """
@@ -404,6 +400,73 @@ def find_distributions(self, context=Context()):
         """
 
 
+class FastPath:
+    """
+    Micro-optimized class for searching a path for
+    children.
+    """
+
+    def __init__(self, root):
+        self.root = root
+
+    def joinpath(self, child):
+        return pathlib.Path(self.root, child)
+
+    def children(self):
+        with suppress(Exception):
+            return os.listdir(self.root or '')
+        with suppress(Exception):
+            return self.zip_children()
+        return []
+
+    def zip_children(self):
+        zip_path = zipp.Path(self.root)
+        names = zip_path.root.namelist()
+        self.joinpath = zip_path.joinpath
+
+        return (
+            posixpath.split(child)[0]
+            for child in names
+            )
+
+    def is_egg(self, search):
+        root_n_low = os.path.split(self.root)[1].lower()
+
+        return (
+            root_n_low == search.normalized + '.egg'
+            or root_n_low.startswith(search.prefix)
+            and root_n_low.endswith('.egg'))
+
+    def search(self, name):
+        for child in self.children():
+            n_low = child.lower()
+            if (n_low in name.exact_matches
+                    or n_low.startswith(name.prefix)
+                    and n_low.endswith(name.suffixes)
+                    # legacy case:
+                    or self.is_egg(name) and n_low == 'egg-info'):
+                yield self.joinpath(child)
+
+
+class Prepared:
+    """
+    A prepared search for metadata on a possibly-named package.
+    """
+    normalized = ''
+    prefix = ''
+    suffixes = '.dist-info', '.egg-info'
+    exact_matches = [''][:0]
+
+    def __init__(self, name):
+        self.name = name
+        if name is None:
+            return
+        self.normalized = name.lower().replace('-', '_')
+        self.prefix = self.normalized + '-'
+        self.exact_matches = [
+            self.normalized + suffix for suffix in self.suffixes]
+
+
 @install
 class MetadataPathFinder(NullFinder, DistributionFinder):
     """A degenerate finder for distribution packages on the file system.
@@ -421,45 +484,17 @@ def find_distributions(self, context=DistributionFinder.Context()):
         (or all names if ``None`` indicated) along the paths in the list
         of directories ``context.path``.
         """
-        found = self._search_paths(context.pattern, context.path)
+        found = self._search_paths(context.name, context.path)
         return map(PathDistribution, found)
 
     @classmethod
-    def _search_paths(cls, pattern, paths):
+    def _search_paths(cls, name, paths):
         """Find metadata directories in paths heuristically."""
         return itertools.chain.from_iterable(
-            cls._search_path(path, pattern)
-            for path in map(cls._switch_path, paths)
+            path.search(Prepared(name))
+            for path in map(FastPath, paths)
             )
 
-    @staticmethod
-    def _switch_path(path):
-        if not PYPY_OPEN_BUG or os.path.isfile(path):  # pragma: no branch
-            with suppress(Exception):
-                return zipp.Path(path)
-        return pathlib.Path(path)
-
-    @classmethod
-    def _matches_info(cls, normalized, item):
-        template = r'{pattern}(-.*)?\.(dist|egg)-info'
-        manifest = template.format(pattern=normalized)
-        return re.match(manifest, item.name, flags=re.IGNORECASE)
-
-    @classmethod
-    def _matches_legacy(cls, normalized, item):
-        template = r'{pattern}-.*\.egg[\\/]EGG-INFO'
-        manifest = template.format(pattern=normalized)
-        return re.search(manifest, str(item), flags=re.IGNORECASE)
-
-    @classmethod
-    def _search_path(cls, root, pattern):
-        if not root.is_dir():
-            return ()
-        normalized = pattern.replace('-', '_')
-        return (item for item in root.iterdir()
-                if cls._matches_info(normalized, item)
-                or cls._matches_legacy(normalized, item))
-
 
 class PathDistribution(Distribution):
     def __init__(self, path):

importlib_metadata/_compat.py

@@ -111,9 +111,6 @@ def py2_message_from_string(text):  # nocoverpy3
     email.message_from_string
     )
 
-# https://bitbucket.org/pypy/pypy/issues/3021/ioopen-directory-leaks-a-file-descriptor
-PYPY_OPEN_BUG = getattr(sys, 'pypy_version_info', (9, 9, 9))[:3] <= (7, 1, 1)
-
 
 class PyPy_repr:
     """

importlib_metadata/docs/changelog.rst

@@ -2,6 +2,13 @@
  importlib_metadata NEWS
 =========================
 
+v1.4.0
+======
+
+* Through careful optimization, ``distribution()`` is
+  3-4x faster. Thanks to Antony Lee for the
+  contribution. Closes #95.
+
 v1.3.0
 ======
 

importlib_metadata/docs/conf.py

@@ -166,6 +166,9 @@
 # Example configuration for intersphinx: refer to the Python standard library.
 intersphinx_mapping = {
     'python': ('https://docs.python.org/3', None),
+    'importlib_resources': (
+        'https://importlib-resources.readthedocs.io/en/latest/', None
+        ),
     }
 
 

importlib_metadata/docs/index.rst

@@ -3,15 +3,15 @@
 ===============================
 
 ``importlib_metadata`` is a library which provides an API for accessing an
-installed package's `metadata`_, such as its entry points or its top-level
+installed package's metadata (see :pep:`566`), such as its entry points or its top-level
 name.  This functionality intends to replace most uses of ``pkg_resources``
-`entry point API`_ and `metadata API`_.  Along with ``importlib.resources`` in
-`Python 3.7 and newer`_ (backported as `importlib_resources`_ for older
+`entry point API`_ and `metadata API`_.  Along with :mod:`importlib.resources` in
+Python 3.7 and newer (backported as :doc:`importlib_resources <importlib_resources:index>` for older
 versions of Python), this can eliminate the need to use the older and less
 efficient ``pkg_resources`` package.
 
 ``importlib_metadata`` is a backport of Python 3.8's standard library
-`importlib.metadata`_ module for Python 2.7, and 3.4 through 3.7.  Users of
+:doc:`importlib.metadata <library/importlib.metadata>` module for Python 2.7, and 3.4 through 3.7.  Users of
 Python 3.8 and beyond are encouraged to use the standard library module.
 When imported on Python 3.8 and later, ``importlib_metadata`` replaces the
 DistributionFinder behavior from the stdlib, but leaves the API in tact.
@@ -46,9 +46,5 @@ Indices and tables
 * :ref:`search`
 
 
-.. _`metadata`: https://www.python.org/dev/peps/pep-0566/
 .. _`entry point API`: https://setuptools.readthedocs.io/en/latest/pkg_resources.html#entry-points
 .. _`metadata API`: https://setuptools.readthedocs.io/en/latest/pkg_resources.html#metadata-api
-.. _`Python 3.7 and newer`: https://docs.python.org/3/library/importlib.html#module-importlib.resources
-.. _`importlib_resources`: https://importlib-resources.readthedocs.io/en/latest/index.html
-.. _`importlib.metadata`: https://docs.python.org/3/library/importlib.metadata.html

importlib_metadata/docs/using.rst

@@ -1,25 +1,25 @@
 .. _using:
 
-==========================
- Using importlib_metadata
-==========================
+=================================
+ Using :mod:`!importlib_metadata`
+=================================
 
 ``importlib_metadata`` is a library that provides for access to installed
 package metadata.  Built in part on Python's import system, this library
 intends to replace similar functionality in the `entry point
 API`_ and `metadata API`_ of ``pkg_resources``.  Along with
-``importlib.resources`` in `Python 3.7
-and newer`_ (backported as `importlib_resources`_ for older versions of
+:mod:`importlib.resources` in Python 3.7
+and newer (backported as :doc:`importlib_resources <importlib_resources:index>` for older versions of
 Python), this can eliminate the need to use the older and less efficient
 ``pkg_resources`` package.
 
 By "installed package" we generally mean a third-party package installed into
 Python's ``site-packages`` directory via tools such as `pip
 <https://pypi.org/project/pip/>`_.  Specifically,
 it means a package with either a discoverable ``dist-info`` or ``egg-info``
-directory, and metadata defined by `PEP 566`_ or its older specifications.
+directory, and metadata defined by :pep:`566` or its older specifications.
 By default, package metadata can live on the file system or in zip archives on
-``sys.path``.  Through an extension mechanism, the metadata can live almost
+:data:`sys.path`.  Through an extension mechanism, the metadata can live almost
 anywhere.
 
 
@@ -127,7 +127,7 @@ Distribution files
 You can also get the full set of files contained within a distribution.  The
 ``files()`` function takes a distribution package name and returns all of the
 files installed by this distribution.  Each file object returned is a
-``PackagePath``, a `pathlib.Path`_ derived object with additional ``dist``,
+``PackagePath``, a :class:`pathlib.Path` derived object with additional ``dist``,
 ``size``, and ``hash`` properties as indicated by the metadata.  For example::
 
     >>> util = [p for p in files('wheel') if 'util.py' in str(p)][0]
@@ -196,18 +196,18 @@ instance::
     >>> d.metadata['License']
     'MIT'
 
-The full set of available metadata is not described here.  See `PEP 566
-<https://www.python.org/dev/peps/pep-0566/>`_ for additional details.
+The full set of available metadata is not described here.  See :pep:`566`
+for additional details.
 
 
 Extending the search algorithm
 ==============================
 
-Because package metadata is not available through ``sys.path`` searches, or
+Because package metadata is not available through :data:`sys.path` searches, or
 package loaders directly, the metadata for a package is found through import
 system `finders`_.  To find a distribution package's metadata,
-``importlib_metadata`` queries the list of `meta path finders`_ on
-`sys.meta_path`_.
+``importlib.metadata`` queries the list of :term:`meta path finders <meta path finder>` on
+:data:`sys.meta_path`.
 
 By default ``importlib_metadata`` installs a finder for distribution packages
 found on the file system.  This finder doesn't actually find any *packages*,
@@ -217,7 +217,7 @@ The abstract class :py:class:`importlib.abc.MetaPathFinder` defines the
 interface expected of finders by Python's import system.
 ``importlib_metadata`` extends this protocol by looking for an optional
 ``find_distributions`` callable on the finders from
-``sys.meta_path`` and presents this extended interface as the
+:data:`sys.meta_path` and presents this extended interface as the
 ``DistributionFinder`` abstract base class, which defines this abstract
 method::
 
@@ -240,20 +240,13 @@ a custom finder, return instances of this derived ``Distribution`` in the
 
 .. _`entry point API`: https://setuptools.readthedocs.io/en/latest/pkg_resources.html#entry-points
 .. _`metadata API`: https://setuptools.readthedocs.io/en/latest/pkg_resources.html#metadata-api
-.. _`Python 3.7 and newer`: https://docs.python.org/3/library/importlib.html#module-importlib.resources
-.. _`importlib_resources`: https://importlib-resources.readthedocs.io/en/latest/index.html
-.. _`PEP 566`: https://www.python.org/dev/peps/pep-0566/
 .. _`finders`: https://docs.python.org/3/reference/import.html#finders-and-loaders
-.. _`meta path finders`: https://docs.python.org/3/glossary.html#term-meta-path-finder
-.. _`sys.meta_path`: https://docs.python.org/3/library/sys.html#sys.meta_path
-.. _`pathlib.Path`: https://docs.python.org/3/library/pathlib.html#pathlib.Path
 
 
 .. rubric:: Footnotes
 
 .. [#f1] Technically, the returned distribution metadata object is an
-         `email.message.Message
-         <https://docs.python.org/3/library/email.message.html#email.message.EmailMessage>`_
+         :class:`email.message.EmailMessage`
          instance, but this is an implementation detail, and not part of the
          stable API.  You should only use dictionary-like methods and syntax
          to access the metadata contents.