GH-127381: pathlib ABCs: remove case_sensitive argument (#131024)

Remove the *case_sensitive* argument from `_JoinablePath.full_match()` and
`_ReadablePath.glob()`. Using a non-native case sensitivity forces the use
of "case-pedantic" globbing, where we `iterdir()` even for non-wildcard
pattern segments. But it's hard to know when to enable this mode, as
case-sensitivity can vary by directory, so `_PathParser.normcase()` doesn't
always give the full picture. The `Path.glob()` implementation is forced to
make an educated guess, but we can avoid the issue in the ABCs by dropping
the *case_sensitive* argument.

(I probably shouldn't have added these arguments in `PurePath` and `Path`
in the first place!)

Also drop support for `_ReadablePath.glob(recurse_symlinks=False)`, which
makes recursive globbing much slower.
This commit is contained in:
Barney Gale 2025-03-10 17:50:48 +00:00 committed by GitHub
parent c3487c941d
commit 93fc3d34f9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 27 additions and 30 deletions

View file

@ -11,7 +11,7 @@ Protocols for supporting classes in pathlib.
from abc import ABC, abstractmethod
from glob import _PathGlobber, _no_recurse_symlinks
from glob import _PathGlobber
from pathlib import PurePath, Path
from pathlib._os import magic_open, ensure_distinct_paths, copy_file
from typing import Optional, Protocol, runtime_checkable
@ -216,15 +216,14 @@ class _JoinablePath(ABC):
parent = split(path)[0]
return tuple(parents)
def full_match(self, pattern, *, case_sensitive=None):
def full_match(self, pattern):
"""
Return True if this path matches the given glob-style pattern. The
pattern is matched against the entire path.
"""
if not hasattr(pattern, 'with_segments'):
pattern = self.with_segments(pattern)
if case_sensitive is None:
case_sensitive = self.parser.normcase('Aa') == 'Aa'
case_sensitive = self.parser.normcase('Aa') == 'Aa'
globber = _PathGlobber(pattern.parser.sep, case_sensitive, recursive=True)
match = globber.compile(str(pattern), altsep=pattern.parser.altsep)
return match(str(self)) is not None
@ -279,7 +278,7 @@ class _ReadablePath(_JoinablePath):
"""
raise NotImplementedError
def glob(self, pattern, *, case_sensitive=None, recurse_symlinks=True):
def glob(self, pattern, *, recurse_symlinks=True):
"""Iterate over this subtree and yield all existing files (of any
kind, including directories) matching the given relative pattern.
"""
@ -288,14 +287,10 @@ class _ReadablePath(_JoinablePath):
anchor, parts = _explode_path(pattern)
if anchor:
raise NotImplementedError("Non-relative patterns are unsupported")
case_sensitive_default = self.parser.normcase('Aa') == 'Aa'
if case_sensitive is None:
case_sensitive = case_sensitive_default
case_pedantic = False
else:
case_pedantic = case_sensitive_default != case_sensitive
recursive = True if recurse_symlinks else _no_recurse_symlinks
globber = _PathGlobber(self.parser.sep, case_sensitive, case_pedantic, recursive)
elif not recurse_symlinks:
raise NotImplementedError("recurse_symlinks=False is unsupported")
case_sensitive = self.parser.normcase('Aa') == 'Aa'
globber = _PathGlobber(self.parser.sep, case_sensitive, recursive=True)
select = globber.selector(parts)
return select(self.joinpath(''))

View file

@ -130,11 +130,6 @@ class JoinTestBase:
self.assertFalse(P('a/b/c.py').full_match('**/a/b/c./**'))
self.assertFalse(P('a/b/c.py').full_match('/a/b/c.py/**'))
self.assertFalse(P('a/b/c.py').full_match('/**/a/b/c.py'))
# Case-sensitive flag
self.assertFalse(P('A.py').full_match('a.PY', case_sensitive=True))
self.assertTrue(P('A.py').full_match('a.PY', case_sensitive=False))
self.assertFalse(P('c:/a/B.Py').full_match('C:/A/*.pY', case_sensitive=True))
self.assertTrue(P('/a/b/c.py').full_match('/A/*/*.Py', case_sensitive=False))
# Matching against empty path
self.assertFalse(P('').full_match('*'))
self.assertTrue(P('').full_match('**'))

View file

@ -433,6 +433,13 @@ class PurePathTest(test_pathlib_abc.JoinablePathTest):
with self.assertWarns(DeprecationWarning):
p.is_reserved()
def test_full_match_case_sensitive(self):
P = self.cls
self.assertFalse(P('A.py').full_match('a.PY', case_sensitive=True))
self.assertTrue(P('A.py').full_match('a.PY', case_sensitive=False))
self.assertFalse(P('c:/a/B.Py').full_match('C:/A/*.pY', case_sensitive=True))
self.assertTrue(P('/a/b/c.py').full_match('/A/*/*.Py', case_sensitive=False))
def test_match_empty(self):
P = self.cls
self.assertRaises(ValueError, P('a').match, '')
@ -2737,6 +2744,18 @@ class PathTest(test_pathlib_abc.RWPathTest, PurePathTest):
self.assertEqual(expect, set(p.glob(P(pattern))))
self.assertEqual(expect, set(p.glob(FakePath(pattern))))
def test_glob_case_sensitive(self):
P = self.cls
def _check(path, pattern, case_sensitive, expected):
actual = {str(q) for q in path.glob(pattern, case_sensitive=case_sensitive)}
expected = {str(P(self.base, q)) for q in expected}
self.assertEqual(actual, expected)
path = P(self.base)
_check(path, "DIRB/FILE*", True, [])
_check(path, "DIRB/FILE*", False, ["dirB/fileB"])
_check(path, "dirb/file*", True, [])
_check(path, "dirb/file*", False, ["dirB/fileB"])
@needs_symlinks
def test_glob_dot(self):
P = self.cls

View file

@ -709,18 +709,6 @@ class ReadablePathTest(JoinablePathTest):
p = P(self.base)
self.assertEqual(list(p.glob("")), [p.joinpath("")])
def test_glob_case_sensitive(self):
P = self.cls
def _check(path, pattern, case_sensitive, expected):
actual = {str(q) for q in path.glob(pattern, case_sensitive=case_sensitive)}
expected = {str(P(self.base, q)) for q in expected}
self.assertEqual(actual, expected)
path = P(self.base)
_check(path, "DIRB/FILE*", True, [])
_check(path, "DIRB/FILE*", False, ["dirB/fileB"])
_check(path, "dirb/file*", True, [])
_check(path, "dirb/file*", False, ["dirB/fileB"])
def test_info_exists(self):
p = self.cls(self.base)
self.assertTrue(p.info.exists())