https://github.com/python/cpython/commit/80b2d60a51cfd824d025eb8b3ec500acce5c010c
commit: 80b2d60a51cfd824d025eb8b3ec500acce5c010c
branch: main
author: Barney Gale <[email protected]>
committer: barneygale <[email protected]>
date: 2025-07-21T17:33:20Z
summary:
GH-136874: `url2pathname()`: discard query and fragment components (#136875)
In `urllib.request.url2pathname()`, ignore any query or fragment components
in the given URL.
files:
A Misc/NEWS.d/next/Library/2025-07-20-16-02-00.gh-issue-136874.cLC3o1.rst
M Doc/library/urllib.request.rst
M Doc/whatsnew/3.14.rst
M Lib/test/test_urllib.py
M Lib/urllib/request.py
diff --git a/Doc/library/urllib.request.rst b/Doc/library/urllib.request.rst
index 1e716715fd9bed..e514b98fc5d553 100644
--- a/Doc/library/urllib.request.rst
+++ b/Doc/library/urllib.request.rst
@@ -210,6 +210,9 @@ The :mod:`urllib.request` module defines the following
functions:
Windows a UNC path is returned (as before), and on other platforms a
:exc:`~urllib.error.URLError` is raised.
+ .. versionchanged:: 3.14
+ The URL query and fragment components are discarded if present.
+
.. versionchanged:: 3.14
The *require_scheme* and *resolve_host* parameters were added.
diff --git a/Doc/whatsnew/3.14.rst b/Doc/whatsnew/3.14.rst
index 91f8ccc796794b..6bdf4aee709ad3 100644
--- a/Doc/whatsnew/3.14.rst
+++ b/Doc/whatsnew/3.14.rst
@@ -2192,6 +2192,7 @@ urllib
- Discard URL authority if it matches the local hostname.
- Discard URL authority if it resolves to a local IP address when the new
*resolve_host* argument is set to true.
+ - Discard URL query and fragment components.
- Raise :exc:`~urllib.error.URLError` if a URL authority isn't local,
except on Windows where we return a UNC path as before.
diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
index 1d889ae7cf458f..c30fb5e27eea8a 100644
--- a/Lib/test/test_urllib.py
+++ b/Lib/test/test_urllib.py
@@ -1526,6 +1526,14 @@ def test_url2pathname(self):
self.assertEqual(fn('////foo/bar'), f'{sep}{sep}foo{sep}bar')
self.assertEqual(fn('data:blah'), 'data:blah')
self.assertEqual(fn('data://blah'), f'data:{sep}{sep}blah')
+ self.assertEqual(fn('foo?bar'), 'foo')
+ self.assertEqual(fn('foo#bar'), 'foo')
+ self.assertEqual(fn('foo?bar=baz'), 'foo')
+ self.assertEqual(fn('foo?bar#baz'), 'foo')
+ self.assertEqual(fn('foo%3Fbar'), 'foo?bar')
+ self.assertEqual(fn('foo%23bar'), 'foo#bar')
+ self.assertEqual(fn('foo%3Fbar%3Dbaz'), 'foo?bar=baz')
+ self.assertEqual(fn('foo%3Fbar%23baz'), 'foo?bar#baz')
def test_url2pathname_require_scheme(self):
sep = os.path.sep
diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
index 41dc5d7b35dedb..c1c373d08815c1 100644
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -1654,11 +1654,11 @@ def url2pathname(url, *, require_scheme=False,
resolve_host=False):
The URL authority may be resolved with gethostbyname() if
*resolve_host* is set to true.
"""
- if require_scheme:
- scheme, url = _splittype(url)
- if scheme != 'file':
- raise URLError("URL is missing a 'file:' scheme")
- authority, url = _splithost(url)
+ if not require_scheme:
+ url = 'file:' + url
+ scheme, authority, url = urlsplit(url)[:3] # Discard query and fragment.
+ if scheme != 'file':
+ raise URLError("URL is missing a 'file:' scheme")
if os.name == 'nt':
if not _is_local_authority(authority, resolve_host):
# e.g. file://server/share/file.txt
diff --git
a/Misc/NEWS.d/next/Library/2025-07-20-16-02-00.gh-issue-136874.cLC3o1.rst
b/Misc/NEWS.d/next/Library/2025-07-20-16-02-00.gh-issue-136874.cLC3o1.rst
new file mode 100644
index 00000000000000..9a71eb8ef1ac8d
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2025-07-20-16-02-00.gh-issue-136874.cLC3o1.rst
@@ -0,0 +1 @@
+Discard URL query and fragment in :func:`urllib.request.url2pathname`.
_______________________________________________
Python-checkins mailing list -- [email protected]
To unsubscribe send an email to [email protected]
https://mail.python.org/mailman3//lists/python-checkins.python.org
Member address: [email protected]
