GH-73435: Implement recursive wildcards in `pathlib.PurePath.match()` (#101398)

`PurePath.match()` now handles the `**` wildcard as in `Path.glob()`, i.e. it matches any number of path segments.

We now compile a `re.Pattern` object for the entire pattern. This is made more difficult by `fnmatch` not treating directory separators as special when evaluating wildcards (`*`, `?`, etc), and so we arrange the path parts onto separate *lines* in a string, and ensure we don't set `re.DOTALL`.

Co-authored-by: Hugo van Kemenade <hugovk@users.noreply.github.com>
Co-authored-by: Alex Waygood <Alex.Waygood@Gmail.com>

1 files changed, 23 insertions, 1 deletions

diff --git a/Lib/test/test_pathlib.py b/Lib/test/test_pathlib.py
index 4391d685d3c..076ace3d930 100644
--- a/Lib/test/test_pathlib.py
+++ b/Lib/test/test_pathlib.py
@@ -310,8 +310,30 @@ class _BasePurePathTest(object):
         self.assertFalse(P('/ab.py').match('/a/*.py'))
         self.assertFalse(P('/a/b/c.py').match('/a/*.py'))
         # Multi-part glob-style pattern.
-        self.assertFalse(P('/a/b/c.py').match('/**/*.py'))
+        self.assertTrue(P('a').match('**'))
+        self.assertTrue(P('c.py').match('**'))
+        self.assertTrue(P('a/b/c.py').match('**'))
+        self.assertTrue(P('/a/b/c.py').match('**'))
+        self.assertTrue(P('/a/b/c.py').match('/**'))
+        self.assertTrue(P('/a/b/c.py').match('**/'))
+        self.assertTrue(P('/a/b/c.py').match('/a/**'))
+        self.assertTrue(P('/a/b/c.py').match('**/*.py'))
+        self.assertTrue(P('/a/b/c.py').match('/**/*.py'))
         self.assertTrue(P('/a/b/c.py').match('/a/**/*.py'))
+        self.assertTrue(P('/a/b/c.py').match('/a/b/**/*.py'))
+        self.assertTrue(P('/a/b/c.py').match('/**/**/**/**/*.py'))
+        self.assertFalse(P('c.py').match('**/a.py'))
+        self.assertFalse(P('c.py').match('c/**'))
+        self.assertFalse(P('a/b/c.py').match('**/a'))
+        self.assertFalse(P('a/b/c.py').match('**/a/b'))
+        self.assertFalse(P('a/b/c.py').match('**/a/b/c'))
+        self.assertFalse(P('a/b/c.py').match('**/a/b/c.'))
+        self.assertFalse(P('a/b/c.py').match('**/a/b/c./**'))
+        self.assertFalse(P('a/b/c.py').match('**/a/b/c./**'))
+        self.assertFalse(P('a/b/c.py').match('/a/b/c.py/**'))
+        self.assertFalse(P('a/b/c.py').match('/**/a/b/c.py'))
+        self.assertRaises(ValueError, P('a').match, '**a/b/c')
+        self.assertRaises(ValueError, P('a').match, 'a/b/c**')
         # Case-sensitive flag
         self.assertFalse(P('A.py').match('a.PY', case_sensitive=True))
         self.assertTrue(P('A.py').match('a.PY', case_sensitive=False))