summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBarney Gale <barney.gale@gmail.com>2024-01-30 19:52:53 (GMT)
committerGitHub <noreply@github.com>2024-01-30 19:52:53 (GMT)
commitfda7445ca50b892955fc31bd72a3615fef1d70c6 (patch)
tree37347a7623b016df6a24d390d0b4c7d6399baa9f
parent6de8aa31f39b3d8dbfba132e6649724eb07b8348 (diff)
downloadcpython-fda7445ca50b892955fc31bd72a3615fef1d70c6.zip
cpython-fda7445ca50b892955fc31bd72a3615fef1d70c6.tar.gz
cpython-fda7445ca50b892955fc31bd72a3615fef1d70c6.tar.bz2
GH-70303: Make `pathlib.Path.glob('**')` return both files and directories (#114684)
Return files and directories from `pathlib.Path.glob()` if the pattern ends with `**`. This is more compatible with `PurePath.full_match()` and with other glob implementations such as bash and `glob.glob()`. Users can add a trailing slash to match only directories. In my previous patch I added a `FutureWarning` with the intention of fixing this in Python 3.15. Upon further reflection I think this was an unnecessarily cautious remedy to a clear bug.
-rw-r--r--Doc/library/pathlib.rst5
-rw-r--r--Doc/whatsnew/3.13.rst10
-rw-r--r--Lib/pathlib/__init__.py8
-rw-r--r--Lib/test/test_pathlib/test_pathlib.py12
-rw-r--r--Lib/test/test_pathlib/test_pathlib_abc.py21
-rw-r--r--Misc/NEWS.d/next/Library/2024-01-28-18-38-18.gh-issue-70303._Lt_pj.rst2
6 files changed, 35 insertions, 23 deletions
diff --git a/Doc/library/pathlib.rst b/Doc/library/pathlib.rst
index f1aba79..f94b6fb 100644
--- a/Doc/library/pathlib.rst
+++ b/Doc/library/pathlib.rst
@@ -1038,9 +1038,8 @@ call fails (for example because the path doesn't exist).
The *follow_symlinks* parameter was added.
.. versionchanged:: 3.13
- Emits :exc:`FutureWarning` if the pattern ends with "``**``". In a
- future Python release, patterns with this ending will match both files
- and directories. Add a trailing slash to match only directories.
+ Return files and directories if *pattern* ends with "``**``". In
+ previous versions, only directories were returned.
.. versionchanged:: 3.13
The *pattern* parameter accepts a :term:`path-like object`.
diff --git a/Doc/whatsnew/3.13.rst b/Doc/whatsnew/3.13.rst
index fec1e55..b33203e 100644
--- a/Doc/whatsnew/3.13.rst
+++ b/Doc/whatsnew/3.13.rst
@@ -350,6 +350,11 @@ pathlib
(Contributed by Barney Gale in :gh:`77609` and :gh:`105793`, and
Kamil Turek in :gh:`107962`).
+* Return files and directories from :meth:`pathlib.Path.glob` and
+ :meth:`~pathlib.Path.rglob` when given a pattern that ends with "``**``". In
+ earlier versions, only directories were returned.
+ (Contributed by Barney Gale in :gh:`70303`).
+
pdb
---
@@ -1211,6 +1216,11 @@ Changes in the Python API
* :class:`mailbox.Maildir` now ignores files with a leading dot.
(Contributed by Zackery Spytz in :gh:`65559`.)
+* :meth:`pathlib.Path.glob` and :meth:`~pathlib.Path.rglob` now return both
+ files and directories if a pattern that ends with "``**``" is given, rather
+ than directories only. Users may add a trailing slash to match only
+ directories.
+
Build Changes
=============
diff --git a/Lib/pathlib/__init__.py b/Lib/pathlib/__init__.py
index cc159ed..4447f98 100644
--- a/Lib/pathlib/__init__.py
+++ b/Lib/pathlib/__init__.py
@@ -465,14 +465,6 @@ class PurePath(_abc.PurePathBase):
elif pattern[-1] in (self.pathmod.sep, self.pathmod.altsep):
# GH-65238: pathlib doesn't preserve trailing slash. Add it back.
parts.append('')
- elif parts[-1] == '**':
- # GH-70303: '**' only matches directories. Add trailing slash.
- warnings.warn(
- "Pattern ending '**' will match files and directories in a "
- "future Python release. Add a trailing slash to match only "
- "directories and remove this warning.",
- FutureWarning, 4)
- parts.append('')
parts.reverse()
return parts
diff --git a/Lib/test/test_pathlib/test_pathlib.py b/Lib/test/test_pathlib/test_pathlib.py
index a8cc30e..3bee9b8 100644
--- a/Lib/test/test_pathlib/test_pathlib.py
+++ b/Lib/test/test_pathlib/test_pathlib.py
@@ -1258,18 +1258,6 @@ class PathTest(test_pathlib_abc.DummyPathTest, PurePathTest):
with set_recursion_limit(recursion_limit):
list(base.glob('**/'))
- def test_glob_recursive_no_trailing_slash(self):
- P = self.cls
- p = P(self.base)
- with self.assertWarns(FutureWarning):
- p.glob('**')
- with self.assertWarns(FutureWarning):
- p.glob('*/**')
- with self.assertWarns(FutureWarning):
- p.rglob('**')
- with self.assertWarns(FutureWarning):
- p.rglob('*/**')
-
def test_glob_pathlike(self):
P = self.cls
p = P(self.base)
diff --git a/Lib/test/test_pathlib/test_pathlib_abc.py b/Lib/test/test_pathlib/test_pathlib_abc.py
index 18a612f..0e12182 100644
--- a/Lib/test/test_pathlib/test_pathlib_abc.py
+++ b/Lib/test/test_pathlib/test_pathlib_abc.py
@@ -1765,16 +1765,26 @@ class DummyPathTest(DummyPurePathTest):
_check(p, "*/fileB", ["dirB/fileB", "linkB/fileB"])
_check(p, "*/", ["dirA/", "dirB/", "dirC/", "dirE/", "linkB/"])
_check(p, "dir*/*/..", ["dirC/dirD/..", "dirA/linkC/..", "dirB/linkD/.."])
+ _check(p, "dir*/**", [
+ "dirA", "dirA/linkC", "dirA/linkC/fileB", "dirA/linkC/linkD", "dirA/linkC/linkD/fileB",
+ "dirB", "dirB/fileB", "dirB/linkD", "dirB/linkD/fileB",
+ "dirC", "dirC/fileC", "dirC/dirD", "dirC/dirD/fileD", "dirC/novel.txt",
+ "dirE"])
_check(p, "dir*/**/", ["dirA/", "dirA/linkC/", "dirA/linkC/linkD/", "dirB/", "dirB/linkD/",
"dirC/", "dirC/dirD/", "dirE/"])
_check(p, "dir*/**/..", ["dirA/..", "dirA/linkC/..", "dirB/..",
"dirB/linkD/..", "dirA/linkC/linkD/..",
"dirC/..", "dirC/dirD/..", "dirE/.."])
+ _check(p, "dir*/*/**", [
+ "dirA/linkC", "dirA/linkC/linkD", "dirA/linkC/fileB", "dirA/linkC/linkD/fileB",
+ "dirB/linkD", "dirB/linkD/fileB",
+ "dirC/dirD", "dirC/dirD/fileD"])
_check(p, "dir*/*/**/", ["dirA/linkC/", "dirA/linkC/linkD/", "dirB/linkD/", "dirC/dirD/"])
_check(p, "dir*/*/**/..", ["dirA/linkC/..", "dirA/linkC/linkD/..",
"dirB/linkD/..", "dirC/dirD/.."])
_check(p, "dir*/**/fileC", ["dirC/fileC"])
_check(p, "dir*/*/../dirD/**/", ["dirC/dirD/../dirD/"])
+ _check(p, "*/dirD/**", ["dirC/dirD", "dirC/dirD/fileD"])
_check(p, "*/dirD/**/", ["dirC/dirD/"])
@needs_symlinks
@@ -1791,12 +1801,20 @@ class DummyPathTest(DummyPurePathTest):
_check(p, "*/fileB", ["dirB/fileB"])
_check(p, "*/", ["dirA/", "dirB/", "dirC/", "dirE/"])
_check(p, "dir*/*/..", ["dirC/dirD/.."])
+ _check(p, "dir*/**", [
+ "dirA", "dirA/linkC",
+ "dirB", "dirB/fileB", "dirB/linkD",
+ "dirC", "dirC/fileC", "dirC/dirD", "dirC/dirD/fileD", "dirC/novel.txt",
+ "dirE"])
_check(p, "dir*/**/", ["dirA/", "dirB/", "dirC/", "dirC/dirD/", "dirE/"])
_check(p, "dir*/**/..", ["dirA/..", "dirB/..", "dirC/..", "dirC/dirD/..", "dirE/.."])
+ _check(p, "dir*/*/**", ["dirC/dirD", "dirC/dirD/fileD"])
_check(p, "dir*/*/**/", ["dirC/dirD/"])
_check(p, "dir*/*/**/..", ["dirC/dirD/.."])
_check(p, "dir*/**/fileC", ["dirC/fileC"])
+ _check(p, "dir*/*/../dirD/**", ["dirC/dirD/../dirD", "dirC/dirD/../dirD/fileD"])
_check(p, "dir*/*/../dirD/**/", ["dirC/dirD/../dirD/"])
+ _check(p, "*/dirD/**", ["dirC/dirD", "dirC/dirD/fileD"])
_check(p, "*/dirD/**/", ["dirC/dirD/"])
def test_rglob_common(self):
@@ -1833,10 +1851,13 @@ class DummyPathTest(DummyPurePathTest):
"dirC/dirD", "dirC/dirD/fileD"])
_check(p.rglob("file*"), ["dirC/fileC", "dirC/dirD/fileD"])
_check(p.rglob("**/file*"), ["dirC/fileC", "dirC/dirD/fileD"])
+ _check(p.rglob("dir*/**"), ["dirC/dirD", "dirC/dirD/fileD"])
_check(p.rglob("dir*/**/"), ["dirC/dirD/"])
_check(p.rglob("*/*"), ["dirC/dirD/fileD"])
_check(p.rglob("*/"), ["dirC/dirD/"])
_check(p.rglob(""), ["dirC/", "dirC/dirD/"])
+ _check(p.rglob("**"), [
+ "dirC", "dirC/fileC", "dirC/dirD", "dirC/dirD/fileD", "dirC/novel.txt"])
_check(p.rglob("**/"), ["dirC/", "dirC/dirD/"])
# gh-91616, a re module regression
_check(p.rglob("*.txt"), ["dirC/novel.txt"])
diff --git a/Misc/NEWS.d/next/Library/2024-01-28-18-38-18.gh-issue-70303._Lt_pj.rst b/Misc/NEWS.d/next/Library/2024-01-28-18-38-18.gh-issue-70303._Lt_pj.rst
new file mode 100644
index 0000000..dedda24
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-01-28-18-38-18.gh-issue-70303._Lt_pj.rst
@@ -0,0 +1,2 @@
+Return both files and directories from :meth:`pathlib.Path.glob` if a
+pattern ends with "``**``". Previously only directories were returned.