GH-77609: Add follow_symlinks argument to `pathlib.Path.glob()` (GH-102616)

Add a keyword-only *follow_symlinks* parameter to `pathlib.Path.glob()` and`rglob()`.

When *follow_symlinks* is `None` (the default), these methods follow symlinks except when evaluating "`**`" wildcards. When set to true or false, symlinks are always or never followed, respectively.

1 files changed, 83 insertions, 0 deletions

diff --git a/Lib/test/test_pathlib.py b/Lib/test/test_pathlib.py
index 01615e2..4391d68 100644
--- a/Lib/test/test_pathlib.py
+++ b/Lib/test/test_pathlib.py
@@ -1863,6 +1863,35 @@ class _BasePathTest(object):
         _check(path, "dirb/file*", True, [])
         _check(path, "dirb/file*", False, ["dirB/fileB"])
 
+    @os_helper.skip_unless_symlink
+    def test_glob_follow_symlinks_common(self):
+        def _check(path, glob, expected):
+            actual = {path for path in path.glob(glob, follow_symlinks=True)
+                      if "linkD" not in path.parent.parts}  # exclude symlink loop.
+            self.assertEqual(actual, { P(BASE, q) for q in expected })
+        P = self.cls
+        p = P(BASE)
+        _check(p, "fileB", [])
+        _check(p, "dir*/file*", ["dirB/fileB", "dirC/fileC"])
+        _check(p, "*A", ["dirA", "fileA", "linkA"])
+        _check(p, "*B/*", ["dirB/fileB", "dirB/linkD", "linkB/fileB", "linkB/linkD"])
+        _check(p, "*/fileB", ["dirB/fileB", "linkB/fileB"])
+        _check(p, "*/", ["dirA", "dirB", "dirC", "dirE", "linkB"])
+
+    @os_helper.skip_unless_symlink
+    def test_glob_no_follow_symlinks_common(self):
+        def _check(path, glob, expected):
+            actual = {path for path in path.glob(glob, follow_symlinks=False)}
+            self.assertEqual(actual, { P(BASE, q) for q in expected })
+        P = self.cls
+        p = P(BASE)
+        _check(p, "fileB", [])
+        _check(p, "dir*/file*", ["dirB/fileB", "dirC/fileC"])
+        _check(p, "*A", ["dirA", "fileA", "linkA"])
+        _check(p, "*B/*", ["dirB/fileB", "dirB/linkD"])
+        _check(p, "*/fileB", ["dirB/fileB"])
+        _check(p, "*/", ["dirA", "dirB", "dirC", "dirE"])
+
     def test_rglob_common(self):
         def _check(glob, expected):
             self.assertEqual(sorted(glob), sorted(P(BASE, q) for q in expected))
@@ -1907,6 +1936,60 @@ class _BasePathTest(object):
         _check(p.rglob("*.*"), ["dirC/novel.txt"])
 
     @os_helper.skip_unless_symlink
+    def test_rglob_follow_symlinks_common(self):
+        def _check(path, glob, expected):
+            actual = {path for path in path.rglob(glob, follow_symlinks=True)
+                      if 'linkD' not in path.parent.parts}  # exclude symlink loop.
+            self.assertEqual(actual, { P(BASE, q) for q in expected })
+        P = self.cls
+        p = P(BASE)
+        _check(p, "fileB", ["dirB/fileB", "dirA/linkC/fileB", "linkB/fileB"])
+        _check(p, "*/fileA", [])
+        _check(p, "*/fileB", ["dirB/fileB", "dirA/linkC/fileB", "linkB/fileB"])
+        _check(p, "file*", ["fileA", "dirA/linkC/fileB", "dirB/fileB",
+                            "dirC/fileC", "dirC/dirD/fileD", "linkB/fileB"])
+        _check(p, "*/", ["dirA", "dirA/linkC", "dirA/linkC/linkD", "dirB", "dirB/linkD",
+                         "dirC", "dirC/dirD", "dirE", "linkB", "linkB/linkD"])
+        _check(p, "", ["", "dirA", "dirA/linkC", "dirA/linkC/linkD", "dirB", "dirB/linkD",
+                       "dirC", "dirE", "dirC/dirD", "linkB", "linkB/linkD"])
+
+        p = P(BASE, "dirC")
+        _check(p, "*", ["dirC/fileC", "dirC/novel.txt",
+                        "dirC/dirD", "dirC/dirD/fileD"])
+        _check(p, "file*", ["dirC/fileC", "dirC/dirD/fileD"])
+        _check(p, "*/*", ["dirC/dirD/fileD"])
+        _check(p, "*/", ["dirC/dirD"])
+        _check(p, "", ["dirC", "dirC/dirD"])
+        # gh-91616, a re module regression
+        _check(p, "*.txt", ["dirC/novel.txt"])
+        _check(p, "*.*", ["dirC/novel.txt"])
+
+    @os_helper.skip_unless_symlink
+    def test_rglob_no_follow_symlinks_common(self):
+        def _check(path, glob, expected):
+            actual = {path for path in path.rglob(glob, follow_symlinks=False)}
+            self.assertEqual(actual, { P(BASE, q) for q in expected })
+        P = self.cls
+        p = P(BASE)
+        _check(p, "fileB", ["dirB/fileB"])
+        _check(p, "*/fileA", [])
+        _check(p, "*/fileB", ["dirB/fileB"])
+        _check(p, "file*", ["fileA", "dirB/fileB", "dirC/fileC", "dirC/dirD/fileD", ])
+        _check(p, "*/", ["dirA", "dirB", "dirC", "dirC/dirD", "dirE"])
+        _check(p, "", ["", "dirA", "dirB", "dirC", "dirE", "dirC/dirD"])
+
+        p = P(BASE, "dirC")
+        _check(p, "*", ["dirC/fileC", "dirC/novel.txt",
+                        "dirC/dirD", "dirC/dirD/fileD"])
+        _check(p, "file*", ["dirC/fileC", "dirC/dirD/fileD"])
+        _check(p, "*/*", ["dirC/dirD/fileD"])
+        _check(p, "*/", ["dirC/dirD"])
+        _check(p, "", ["dirC", "dirC/dirD"])
+        # gh-91616, a re module regression
+        _check(p, "*.txt", ["dirC/novel.txt"])
+        _check(p, "*.*", ["dirC/novel.txt"])
+
+    @os_helper.skip_unless_symlink
     def test_rglob_symlink_loop(self):
         # Don't get fooled by symlink loops (Issue #26012).
         P = self.cls