Skip to content

bpo-39799: Never return base's fragment from urllib.parse.urljoin #18710

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 6 commits into from
+6 −9
Closed

bpo-39799: Never return base's fragment from urllib.parse.urljoin #18710

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e4b230b
bpo-39799: Never return base's fragment from urllib.parse.urljoin
openandclose Feb 29, 2020
9cfe7c0
📜🤖 Added by blurb_it.
blurb-it[bot] Feb 29, 2020
40338d6
Add 3 edits suggested from @epicfaace
openandclose Mar 15, 2020
79f5a02
Merge branch 'main' into urljoin_no_base_fragment
serhiy-storchaka Nov 11, 2024
419fbe5
Fix new code and tests.
serhiy-storchaka Nov 12, 2024
744cab6
Remove duplicate tests.
serhiy-storchaka Nov 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions Lib/test/test_urlparse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -396,7 +396,6 @@ def test_RFC1808(self):
self.checkJoin(RFC1808_BASE, '../../g', 'http://a/g')

# "abnormal" cases from RFC 1808:
self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f')
self.checkJoin(RFC1808_BASE, 'g.', 'http://a/b/c/g.')
self.checkJoin(RFC1808_BASE, '.g', 'http://a/b/c/.g')
self.checkJoin(RFC1808_BASE, 'g..', 'http://a/b/c/g..')
Expand All @@ -412,6 +411,7 @@ def test_RFC1808(self):
#self.checkJoin(RFC1808_BASE, 'http:', 'http:')

# XXX: The following tests are no longer compatible with RFC3986
# self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f')
# self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g')
# self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g')
# self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g')
Expand Down Expand Up @@ -577,7 +577,7 @@ def test_urljoins(self):
self.checkJoin('a', 'b', 'b')

# Test with empty (but defined) components.
self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f')
self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q')
self.checkJoin(RFC1808_BASE, '#', 'http://a/b/c/d;p?q#', relroundtrip=False)
self.checkJoin(RFC1808_BASE, '#z', 'http://a/b/c/d;p?q#z')
self.checkJoin(RFC1808_BASE, '?', 'http://a/b/c/d;p?', relroundtrip=False)
Expand All @@ -588,7 +588,7 @@ def test_urljoins(self):
self.checkJoin(RFC1808_BASE, ';#z', 'http://a/b/c/;#z')
self.checkJoin(RFC1808_BASE, ';x', 'http://a/b/c/;x')
self.checkJoin(RFC1808_BASE, '/w', 'http://a/w')
self.checkJoin(RFC1808_BASE, '//', 'http://a/b/c/d;p?q#f')
self.checkJoin(RFC1808_BASE, '//', 'http://a/b/c/d;p?q')
self.checkJoin(RFC1808_BASE, '//#z', 'http://a/b/c/d;p?q#z')
self.checkJoin(RFC1808_BASE, '//?y', 'http://a/b/c/d;p?y')
self.checkJoin(RFC1808_BASE, '//;x', 'http://;x')
Expand All @@ -597,7 +597,7 @@ def test_urljoins(self):
# For backward compatibility with RFC1630, the scheme name is allowed
# to be present in a relative reference if it is the same as the base
# URI scheme.
self.checkJoin(RFC1808_BASE, 'http:', 'http://a/b/c/d;p?q#f')
self.checkJoin(RFC1808_BASE, 'http:', 'http://a/b/c/d;p?q')
self.checkJoin(RFC1808_BASE, 'http:#', 'http://a/b/c/d;p?q#', relroundtrip=False)
self.checkJoin(RFC1808_BASE, 'http:#z', 'http://a/b/c/d;p?q#z')
self.checkJoin(RFC1808_BASE, 'http:?', 'http://a/b/c/d;p?', relroundtrip=False)
Expand All @@ -608,7 +608,7 @@ def test_urljoins(self):
self.checkJoin(RFC1808_BASE, 'http:;#z', 'http://a/b/c/;#z')
self.checkJoin(RFC1808_BASE, 'http:;x', 'http://a/b/c/;x')
self.checkJoin(RFC1808_BASE, 'http:/w', 'http://a/w')
self.checkJoin(RFC1808_BASE, 'http://', 'http://a/b/c/d;p?q#f')
self.checkJoin(RFC1808_BASE, 'http://', 'http://a/b/c/d;p?q')
self.checkJoin(RFC1808_BASE, 'http://#z', 'http://a/b/c/d;p?q#z')
self.checkJoin(RFC1808_BASE, 'http://?y', 'http://a/b/c/d;p?y')
self.checkJoin(RFC1808_BASE, 'http://;x', 'http://;x')
Expand Down
4 changes: 0 additions & 4 deletions Lib/urllib/parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -566,8 +566,6 @@ def urljoin(base, url, allow_fragments=True):
interpretation of the latter."""
if not base:
return url
if not url:
return base

base, url, _coerce_result = _coerce_args(base, url)
bscheme, bnetloc, bpath, bquery, bfragment = \
Expand All @@ -589,8 +587,6 @@ def urljoin(base, url, allow_fragments=True):
path = bpath
if query is None:
query = bquery
if fragment is None:
fragment = bfragment
return _coerce_result(_urlunsplit(scheme, netloc, path,
query, fragment))

Expand Down
1 change: 1 addition & 0 deletions Misc/NEWS.d/next/Library/2020-02-29-20-44-36.bpo-39799.qTHOaP.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
The fragment of the base URI is now always discarded in :func:`urllib.parse.urljoin` in accordance to :rfc:`3986`.
Loading