More code review fixes for Path.walk

python · miss-islington · Jul 22, 2022 · May 8, 2022 · May 9, 2022 · May 9, 2022
commit 4509797b2b1e774953216893c2c17cfea821585e
@@ -961,9 +961,7 @@ call fails (for example because the path doesn't exist).
    Note that the names in the lists contain no path components. To get a full
    path (which begins with *self*) to a file or directory in *dirpath*, do
    ``dirpath / name``. Whether or not the lists are sorted depends on the file
-   system. If a file or a directory is removed from or added to the *dirpath*
-   during the generation of *dirnames* and *filenames*, it is uncertain whether
-   the new entry will appear in the generated lists.
+   system.
 
    If optional argument *top_down* is ``True`` or not specified, the triple for a
    directory is generated before the triples for any of its subdirectories

@@ -1311,84 +1311,11 @@ def expanduser(self):
         return self
 
     def walk(self, top_down=True, on_error=None, follow_symlinks=False):
-        """Generate a top-down directory tree from this directory
-
-        For each directory in the directory tree rooted at self (including
-        self but excluding '.' and '..'), yields a 3-tuple
-
-        dirpath, dirnames, filenames
-
-        dirpath is the Path to the directory. dirnames is a list of
-        the names of the subdirectories in dirpath (excluding '.' and '..').
-        filenames is a list of the names of the non-directory files in dirpath.
-        Note that the names in the lists are just names, with no path components.
-        To get a full path (which begins with top) to a file or directory in
-        dirpath, do dirpath / name.
-
-        If optional arg 'top_down' is true or not specified, the triple for a
-        directory is generated before the triples for any of its subdirectories
-        (directories are generated top down).  If top_down is false, the triple
-        for a directory is generated after the triples for all of its
-        subdirectories (directories are generated bottom up).
-
-        When top_down is True, the caller can modify the dirnames list in-place
-        (e.g., via del or slice assignment), and walk will only recurse
-        into the subdirectories whose names remain in dirnames; this
-        can be used to prune the search, or to impose a specific order of
-        visiting. Modifying dirnames when
-        top_down is False has no effect on the behavior of Path.walk(), since the
-        directories in dirnames have already been generated by the time dirnames
-        itself is generated. No matter the value of top_down, the list of
-        subdirectories is retrieved before the tuples for the directory and its
-        subdirectories are generated.
-
-        By default errors from Path._scandir() call are ignored.  If
-        optional arg 'on_error' is specified, it should be a callable; it
-        will be called with one argument, an OSError instance.  It can
-        report the error to continue with the walk, or raise the exception
-        to abort the walk.  Note that the filename is available as the
-        filename attribute of the exception object.
-
-        By default, Path.walk does not follow symbolic links to subdirectories
-        on systems that support them.  In order to get this functionality, set
-        the optional argument 'follow_symlinks' to true. Unlike os.walk,
-        Path.walk only adds symbolic links to dirnames if follow_symlinks=True. 
-
-        Caution: if self is a relative Path, don't change the
-        current working directory between resumptions of walk. walk never
-        changes the current directory, and assumes that the caller doesn't
-        either.
-
-        Caution: Unlike os.walk, Path.walk assumes the directories have not
-        been modified between its resumptions. I.e. If a directory from
-        dirnames has been replaced with a symlink and follow_symlinks=False,
-        walk will still try to descend into it. To prevent such behavior,
-        remove directories from dirnames if they have been modified and you
-        do not want Path.walk to descend into them anymore.
-
-        Example:
-
-        from pathlib import Path
-        for root, dirs, files in Path().walk(on_error=print):
-            print(
-                root,
-                "consumes",
-                sum((root / file).stat().st_size for file in files),
-                "bytes in",
-                len(files),
-                "non-directory files"
-            )
-            # don't visit __pycache__ directories
-            if '__pycache__' in dirs:
-                dirs.remove('__pycache__')
-        """
+        """Generate a top-down directory tree from this directory, similar to os.walk()"""
         sys.audit("pathlib.Path.walk", self, on_error, follow_symlinks)
         return self._walk(top_down, on_error, follow_symlinks)
 
     def _walk(self, top_down, on_error, follow_symlinks):
-        dirnames = []
-        filenames = []
-
         # We may not have read permission for self, in which case we can't
         # get a list of the files the directory contains. os.walk
         # always suppressed the exception then, rather than blow up for a
@@ -1402,6 +1329,8 @@ def _walk(self, top_down, on_error, follow_symlinks):
             return
 
         with scandir_it:
+            dirnames = []
+            filenames = []
             for entry in scandir_it:
                 try:
                     is_dir = entry.is_dir(follow_symlinks=follow_symlinks)