GH-125413: Add pathlib.Path.info attribute (#127730)

Add `pathlib.Path.info` attribute, which stores an object implementing the `pathlib.types.PathInfo` protocol (also new). The object supports querying the file type and internally caching `os.stat()` results. Path objects generated by `Path.iterdir()` are initialised with status information from `os.DirEntry` objects, which is gleaned from scanning the parent directory.

The `PathInfo` protocol has four methods: `exists()`, `is_dir()`, `is_file()` and `is_symlink()`.

Author: barneygale

Doc/library/pathlib.rst

@@ -1177,6 +1177,38 @@ Querying file type and status
    .. versionadded:: 3.5
 
 
+.. attribute:: Path.info
+
+   A :class:`~pathlib.types.PathInfo` object that supports querying file type
+   information. The object exposes methods that cache their results, which can
+   help reduce the number of system calls needed when switching on file type.
+   For example::
+
+      >>> p = Path('src')
+      >>> if p.info.is_symlink():
+      ...     print('symlink')
+      ... elif p.info.is_dir():
+      ...     print('directory')
+      ... elif p.info.exists():
+      ...     print('something else')
+      ... else:
+      ...     print('not found')
+      ...
+      directory
+
+   If the path was generated from :meth:`Path.iterdir` then this attribute is
+   initialized with some information about the file type gleaned from scanning
+   the parent directory. Merely accessing :attr:`Path.info` does not perform
+   any filesystem queries.
+
+   To fetch up-to-date information, it's best to call :meth:`Path.is_dir`,
+   :meth:`~Path.is_file` and :meth:`~Path.is_symlink` rather than methods of
+   this attribute. There is no way to reset the cache; instead you can create
+   a new path object with an empty info cache via ``p = Path(p)``.
+
+   .. versionadded:: 3.14
+
+
 Reading and writing files
 ^^^^^^^^^^^^^^^^^^^^^^^^^
 
@@ -1903,3 +1935,56 @@ Below is a table mapping various :mod:`os` functions to their corresponding
 .. [4] :func:`os.walk` always follows symlinks when categorizing paths into
    *dirnames* and *filenames*, whereas :meth:`Path.walk` categorizes all
    symlinks into *filenames* when *follow_symlinks* is false (the default.)
+
+
+Protocols
+---------
+
+.. module:: pathlib.types
+   :synopsis: pathlib types for static type checking
+
+
+The :mod:`pathlib.types` module provides types for static type checking.
+
+.. versionadded:: 3.14
+
+
+.. class:: PathInfo()
+
+   A :class:`typing.Protocol` describing the
+   :attr:`Path.info <pathlib.Path.info>` attribute. Implementations may
+   return cached results from their methods.
+
+   .. method:: exists(*, follow_symlinks=True)
+
+      Return ``True`` if the path is an existing file or directory, or any
+      other kind of file; return ``False`` if the path doesn't exist.
+
+      If *follow_symlinks* is ``False``, return ``True`` for symlinks without
+      checking if their targets exist.
+
+   .. method:: is_dir(*, follow_symlinks=True)
+
+      Return ``True`` if the path is a directory, or a symbolic link pointing
+      to a directory; return ``False`` if the path is (or points to) any other
+      kind of file, or if it doesn't exist.
+
+      If *follow_symlinks* is ``False``, return ``True`` only if the path
+      is a directory (without following symlinks); return ``False`` if the
+      path is any other kind of file, or if it doesn't exist.
+
+   .. method:: is_file(*, follow_symlinks=True)
+
+      Return ``True`` if the path is a file, or a symbolic link pointing to
+      a file; return ``False`` if the path is (or points to) a directory or
+      other non-file, or if it doesn't exist.
+
+      If *follow_symlinks* is ``False``, return ``True`` only if the path
+      is a file (without following symlinks); return ``False`` if the path
+      is a directory or other other non-file, or if it doesn't exist.
+
+   .. method:: is_symlink()
+
+      Return ``True`` if the path is a symbolic link (even if broken); return
+      ``False`` if the path is a directory or any kind of file, or if it
+      doesn't exist.

Doc/whatsnew/3.14.rst

@@ -617,6 +617,15 @@ pathlib
 
   (Contributed by Barney Gale in :gh:`73991`.)
 
+* Add :attr:`pathlib.Path.info` attribute, which stores an object
+  implementing the :class:`pathlib.types.PathInfo` protocol (also new). The
+  object supports querying the file type and internally caching
+  :func:`~os.stat` results. Path objects generated by
+  :meth:`~pathlib.Path.iterdir` are initialized with file type information
+  gleaned from scanning the parent directory.
+
+  (Contributed by Barney Gale in :gh:`125413`.)
+
 
 pdb
 ---

Lib/glob.py

@@ -348,7 +348,7 @@ def lexists(path):
 
     @staticmethod
     def scandir(path):
-        """Implements os.scandir().
+        """Like os.scandir(), but generates (entry, name, path) tuples.
         """
         raise NotImplementedError
 
@@ -425,23 +425,18 @@ def wildcard_selector(self, part, parts):
 
         def select_wildcard(path, exists=False):
             try:
-                # We must close the scandir() object before proceeding to
-                # avoid exhausting file descriptors when globbing deep trees.
-                with self.scandir(path) as scandir_it:
-                    entries = list(scandir_it)
+                entries = self.scandir(path)
             except OSError:
                 pass
             else:
-                prefix = self.add_slash(path)
-                for entry in entries:
-                    if match is None or match(entry.name):
+                for entry, entry_name, entry_path in entries:
+                    if match is None or match(entry_name):
                         if dir_only:
                             try:
                                 if not entry.is_dir():
                                     continue
                             except OSError:
                                 continue
-                        entry_path = self.concat_path(prefix, entry.name)
                         if dir_only:
                             yield from select_next(entry_path, exists=True)
                         else:
@@ -483,15 +478,11 @@ def select_recursive(path, exists=False):
         def select_recursive_step(stack, match_pos):
             path = stack.pop()
             try:
-                # We must close the scandir() object before proceeding to
-                # avoid exhausting file descriptors when globbing deep trees.
-                with self.scandir(path) as scandir_it:
-                    entries = list(scandir_it)
+                entries = self.scandir(path)
             except OSError:
                 pass
             else:
-                prefix = self.add_slash(path)
-                for entry in entries:
+                for entry, _entry_name, entry_path in entries:
                     is_dir = False
                     try:
                         if entry.is_dir(follow_symlinks=follow_symlinks):
@@ -500,7 +491,6 @@ def select_recursive_step(stack, match_pos):
                         pass
 
                     if is_dir or not dir_only:
-                        entry_path = self.concat_path(prefix, entry.name)
                         if match is None or match(str(entry_path), match_pos):
                             if dir_only:
                                 yield from select_next(entry_path, exists=True)
@@ -528,9 +518,16 @@ class _StringGlobber(_GlobberBase):
     """Provides shell-style pattern matching and globbing for string paths.
     """
     lexists = staticmethod(os.path.lexists)
-    scandir = staticmethod(os.scandir)
     concat_path = operator.add
 
+    @staticmethod
+    def scandir(path):
+        # We must close the scandir() object before proceeding to
+        # avoid exhausting file descriptors when globbing deep trees.
+        with os.scandir(path) as scandir_it:
+            entries = list(scandir_it)
+        return ((entry, entry.name, entry.path) for entry in entries)
+
     if os.name == 'nt':
         @staticmethod
         def add_slash(pathname):
@@ -544,3 +541,19 @@ def add_slash(pathname):
             if not pathname or pathname[-1] == '/':
                 return pathname
             return f'{pathname}/'
+
+
+class _PathGlobber(_GlobberBase):
+    """Provides shell-style pattern matching and globbing for pathlib paths.
+    """
+
+    lexists = operator.methodcaller('exists', follow_symlinks=False)
+    add_slash = operator.methodcaller('joinpath', '')
+
+    @staticmethod
+    def scandir(path):
+        return ((child.info, child.name, child) for child in path.iterdir())
+
+    @staticmethod
+    def concat_path(path, text):
+        return path.with_segments(str(path) + text)

Lib/pathlib/_abc.py

@@ -13,10 +13,9 @@
 
 import functools
 import io
-import operator
 import posixpath
 from errno import EINVAL
-from glob import _GlobberBase, _no_recurse_symlinks
+from glob import _PathGlobber, _no_recurse_symlinks
 from pathlib._os import copyfileobj
 
 
@@ -76,21 +75,6 @@ def magic_open(path, mode='r', buffering=-1, encoding=None, errors=None,
     raise TypeError(f"{cls.__name__} can't be opened with mode {mode!r}")
 
 
-class PathGlobber(_GlobberBase):
-    """
-    Class providing shell-style globbing for path objects.
-    """
-
-    lexists = operator.methodcaller('exists', follow_symlinks=False)
-    add_slash = operator.methodcaller('joinpath', '')
-    scandir = operator.methodcaller('_scandir')
-
-    @staticmethod
-    def concat_path(path, text):
-        """Appends text to the given path."""
-        return path.with_segments(str(path) + text)
-
-
 class CopyReader:
     """
     Class that implements the "read" part of copying between path objects.
@@ -367,7 +351,7 @@ def full_match(self, pattern, *, case_sensitive=None):
             pattern = self.with_segments(pattern)
         if case_sensitive is None:
             case_sensitive = _is_case_sensitive(self.parser)
-        globber = PathGlobber(pattern.parser.sep, case_sensitive, recursive=True)
+        globber = _PathGlobber(pattern.parser.sep, case_sensitive, recursive=True)
         match = globber.compile(str(pattern))
         return match(str(self)) is not None
 
@@ -388,33 +372,45 @@ class ReadablePath(JoinablePath):
     """
     __slots__ = ()
 
+    @property
+    def info(self):
+        """
+        A PathInfo object that exposes the file type and other file attributes
+        of this path.
+        """
+        raise NotImplementedError
+
     def exists(self, *, follow_symlinks=True):
         """
         Whether this path exists.
 
         This method normally follows symlinks; to check whether a symlink exists,
         add the argument follow_symlinks=False.
         """
-        raise NotImplementedError
+        info = self.joinpath().info
+        return info.exists(follow_symlinks=follow_symlinks)
 
     def is_dir(self, *, follow_symlinks=True):
         """
         Whether this path is a directory.
         """
-        raise NotImplementedError
+        info = self.joinpath().info
+        return info.is_dir(follow_symlinks=follow_symlinks)
 
     def is_file(self, *, follow_symlinks=True):
         """
         Whether this path is a regular file (also True for symlinks pointing
         to regular files).
         """
-        raise NotImplementedError
+        info = self.joinpath().info
+        return info.is_file(follow_symlinks=follow_symlinks)
 
     def is_symlink(self):
         """
         Whether this path is a symbolic link.
         """
-        raise NotImplementedError
+        info = self.joinpath().info
+        return info.is_symlink()
 
     def __open_rb__(self, buffering=-1):
         """
@@ -437,15 +433,6 @@ def read_text(self, encoding=None, errors=None, newline=None):
         with magic_open(self, mode='r', encoding=encoding, errors=errors, newline=newline) as f:
             return f.read()
 
-    def _scandir(self):
-        """Yield os.DirEntry-like objects of the directory contents.
-
-        The children are yielded in arbitrary order, and the
-        special entries '.' and '..' are not included.
-        """
-        import contextlib
-        return contextlib.nullcontext(self.iterdir())
-
     def iterdir(self):
         """Yield path objects of the directory contents.
 
@@ -471,7 +458,7 @@ def glob(self, pattern, *, case_sensitive=None, recurse_symlinks=True):
         else:
             case_pedantic = True
         recursive = True if recurse_symlinks else _no_recurse_symlinks
-        globber = PathGlobber(self.parser.sep, case_sensitive, case_pedantic, recursive)
+        globber = _PathGlobber(self.parser.sep, case_sensitive, case_pedantic, recursive)
         select = globber.selector(parts)
         return select(self)
 
@@ -498,18 +485,16 @@ def walk(self, top_down=True, on_error=None, follow_symlinks=False):
             if not top_down:
                 paths.append((path, dirnames, filenames))
             try:
-                with path._scandir() as entries:
-                    for entry in entries:
-                        name = entry.name
-                        try:
-                            if entry.is_dir(follow_symlinks=follow_symlinks):
-                                if not top_down:
-                                    paths.append(path.joinpath(name))
-                                dirnames.append(name)
-                            else:
-                                filenames.append(name)
-                        except OSError:
-                            filenames.append(name)
+                for child in path.iterdir():
+                    try:
+                        if child.info.is_dir(follow_symlinks=follow_symlinks):
+                            if not top_down:
+                                paths.append(child)
+                            dirnames.append(child.name)
+                        else:
+                            filenames.append(child.name)
+                    except OSError:
+                        filenames.append(child.name)
             except OSError as error:
                 if on_error is not None:
                     on_error(error)