mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-31 14:07:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

GH-117586: Speed up pathlib.Path.walk() by working with strings (#117726)

Browse source 
Move `pathlib.Path.walk()` implementation into `glob._Globber`. The new
`glob._Globber.walk()` classmethod works with strings internally, which is
a little faster than generating `Path` objects and keeping them normalized.
The `pathlib.Path.walk()` method converts the strings back to path objects.

In the private pathlib ABCs, our existing subclass of `_Globber` ensures
that `PathBase` instances are used throughout.

Follow-up to #117589.
This commit is contained in:
Barney Gale 2024-04-11 01:26:53 +01:00 • committed by GitHub
parent 6258844c27
commit 0cc71bde00
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 52 additions and 71 deletions
Download patch file Download diff file Expand all files Collapse all files

20
Lib/pathlib/__init__.py
View file

@ -586,18 +586,6 @@ class Path(_abc.PathBase, PurePath):
"""
return (self._make_child_relpath(name) for name in os.listdir(self))
def _scandir(self):
return os.scandir(self)
def _make_child_direntry(self, entry):
# Transform an entry yielded from _scandir() into a path object.
path_str = entry.name if str(self) == '.' else entry.path
path = self.with_segments(path_str)
path._str = path_str
path._drv = self.drive
path._root = self.root
path._tail_cached = self._tail + [entry.name]
return path
def _make_child_relpath(self, name):
if not name:
@ -663,8 +651,12 @@ class Path(_abc.PathBase, PurePath):
def walk(self, top_down=True, on_error=None, follow_symlinks=False):
"""Walk the directory tree from this directory, similar to os.walk()."""
sys.audit("pathlib.Path.walk", self, on_error, follow_symlinks)
return _abc.PathBase.walk(
self, top_down=top_down, on_error=on_error, follow_symlinks=follow_symlinks)
root_dir = str(self)
results = self._globber.walk(root_dir, top_down, on_error, follow_symlinks)
for path_str, dirnames, filenames in results:
if root_dir == '.':
path_str = path_str[2:]
yield self._from_parsed_string(path_str), dirnames, filenames
def absolute(self):
"""Return an absolute version of this path