From 7ff61f51b6f75315291419269295a8ac3933397b Mon Sep 17 00:00:00 2001 From: Barney Gale Date: Wed, 29 May 2024 21:51:04 +0100 Subject: [PATCH] GH-119169: Implement `pathlib.Path.walk()` using `os.walk()` (#119573) For silly reasons, pathlib's generic implementation of `walk()` currently resides in `glob._Globber`. This commit moves it into `pathlib._abc.PathBase.walk()` where it really belongs, and makes `pathlib.Path.walk()` call `os.walk()`. --- Lib/glob.py | 37 ------------------------------------- Lib/pathlib/_abc.py | 32 +++++++++++++++++++++++++++++++- Lib/pathlib/_local.py | 4 +++- 3 files changed, 34 insertions(+), 39 deletions(-) diff --git a/Lib/glob.py b/Lib/glob.py index 920f79ad7e1fe5..fbb1d35aab71fa 100644 --- a/Lib/glob.py +++ b/Lib/glob.py @@ -519,43 +519,6 @@ def select_exists(self, path, exists=False): elif self.lexists(path): yield path - @classmethod - def walk(cls, root, top_down, on_error, follow_symlinks): - """Walk the directory tree from the given root, similar to os.walk(). - """ - paths = [root] - while paths: - path = paths.pop() - if isinstance(path, tuple): - yield path - continue - try: - with cls.scandir(path) as scandir_it: - dirnames = [] - filenames = [] - if not top_down: - paths.append((path, dirnames, filenames)) - for entry in scandir_it: - name = entry.name - try: - if entry.is_dir(follow_symlinks=follow_symlinks): - if not top_down: - paths.append(cls.parse_entry(entry)) - dirnames.append(name) - else: - filenames.append(name) - except OSError: - filenames.append(name) - except OSError as error: - if on_error is not None: - on_error(error) - else: - if top_down: - yield path, dirnames, filenames - if dirnames: - prefix = cls.add_slash(path) - paths += [cls.concat_path(prefix, d) for d in reversed(dirnames)] - class _StringGlobber(_Globber): lexists = staticmethod(os.path.lexists) diff --git a/Lib/pathlib/_abc.py b/Lib/pathlib/_abc.py index 6b5d9fc2a0c560..d7471b6927331d 100644 --- a/Lib/pathlib/_abc.py +++ b/Lib/pathlib/_abc.py @@ -621,7 +621,37 @@ def rglob(self, pattern, *, case_sensitive=None, recurse_symlinks=True): def walk(self, top_down=True, on_error=None, follow_symlinks=False): """Walk the directory tree from this directory, similar to os.walk().""" - return self._globber.walk(self, top_down, on_error, follow_symlinks) + paths = [self] + while paths: + path = paths.pop() + if isinstance(path, tuple): + yield path + continue + dirnames = [] + filenames = [] + if not top_down: + paths.append((path, dirnames, filenames)) + try: + for child in path.iterdir(): + try: + if child.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) + if not top_down: + while not isinstance(paths.pop(), tuple): + pass + continue + if top_down: + yield path, dirnames, filenames + paths += [path.joinpath(d) for d in reversed(dirnames)] def absolute(self): """Return an absolute version of this path diff --git a/Lib/pathlib/_local.py b/Lib/pathlib/_local.py index 49d9f813c54c23..473fd525768b50 100644 --- a/Lib/pathlib/_local.py +++ b/Lib/pathlib/_local.py @@ -672,7 +672,9 @@ 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) root_dir = str(self) - results = self._globber.walk(root_dir, top_down, on_error, follow_symlinks) + if not follow_symlinks: + follow_symlinks = os._walk_symlinks_as_files + results = os.walk(root_dir, top_down, on_error, follow_symlinks) for path_str, dirnames, filenames in results: if root_dir == '.': path_str = path_str[2:]