FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

[3.10] gh-67693: Fix urlunparse() and urlunsplit() for URIs with path starting with multiple slashes and no authority (GH-113563) by serhiy-storchaka · Pull Request #119026 · python/cpython · GitHub

/ cpython Public

[3.10] gh-67693: Fix urlunparse() and urlunsplit() for URIs with path starting with multiple slashes and no authority (GH-113563) #119026

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

Merged
ambv merged 1 commit into from
Sep 4, 2024
+70 −4
Conversation 0 Commits 1 Checks 0 Files changed 3
Merged

[3.10] gh-67693: Fix urlunparse() and urlunsplit() for URIs with path starting with multiple slashes and no authority (GH-113563) #119026

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension .py  (2) .rst  (1) All 2 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
70 changes: 67 additions & 3 deletions Lib/test/test_urlparse.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -70,15 +70,17 @@

class UrlParseTestCase(unittest.TestCase):

def checkRoundtrips(self, url, parsed, split):
def checkRoundtrips(self, url, parsed, split, url2=None):
if url2 is None:
url2 = url
result = urllib.parse.urlparse(url)
self.assertEqual(result, parsed)
t = (result.scheme, result.netloc, result.path,
result.params, result.query, result.fragment)
self.assertEqual(t, parsed)
# put it back together and it should be the same
result2 = urllib.parse.urlunparse(result)
self.assertEqual(result2, url)
self.assertEqual(result2, url2)
self.assertEqual(result2, result.geturl())

# the result of geturl() is a fixpoint; we can always parse it
Expand All @@ -104,7 +106,7 @@ def checkRoundtrips(self, url, parsed, split):
result.query, result.fragment)
self.assertEqual(t, split)
result2 = urllib.parse.urlunsplit(result)
self.assertEqual(result2, url)
self.assertEqual(result2, url2)
self.assertEqual(result2, result.geturl())

# check the fixpoint property of re-parsing the result of geturl()
Expand Down Expand Up @@ -142,9 +144,39 @@ def test_qs(self):

def test_roundtrips(self):
str_cases = [
('path/to/file',
('', '', 'path/to/file', '', '', ''),
('', '', 'path/to/file', '', '')),
('/path/to/file',
('', '', '/path/to/file', '', '', ''),
('', '', '/path/to/file', '', '')),
('//path/to/file',
('', 'path', '/to/file', '', '', ''),
('', 'path', '/to/file', '', '')),
('////path/to/file',
('', '', '//path/to/file', '', '', ''),
('', '', '//path/to/file', '', '')),
('scheme:path/to/file',
('scheme', '', 'path/to/file', '', '', ''),
('scheme', '', 'path/to/file', '', '')),
('scheme:/path/to/file',
('scheme', '', '/path/to/file', '', '', ''),
('scheme', '', '/path/to/file', '', '')),
('scheme://path/to/file',
('scheme', 'path', '/to/file', '', '', ''),
('scheme', 'path', '/to/file', '', '')),
('scheme:////path/to/file',
('scheme', '', '//path/to/file', '', '', ''),
('scheme', '', '//path/to/file', '', '')),
('file:///tmp/junk.txt',
('file', '', '/tmp/junk.txt', '', '', ''),
('file', '', '/tmp/junk.txt', '', '')),
('file:////tmp/junk.txt',
('file', '', '//tmp/junk.txt', '', '', ''),
('file', '', '//tmp/junk.txt', '', '')),
('file://///tmp/junk.txt',
('file', '', '///tmp/junk.txt', '', '', ''),
('file', '', '///tmp/junk.txt', '', '')),
('imap://mail.python.org/mbox1',
('imap', 'mail.python.org', '/mbox1', '', '', ''),
('imap', 'mail.python.org', '/mbox1', '', '')),
Expand Down Expand Up @@ -175,6 +207,38 @@ def _encode(t):
for url, parsed, split in str_cases + bytes_cases:
self.checkRoundtrips(url, parsed, split)

def test_roundtrips_normalization(self):
str_cases = [
('///path/to/file',
'/path/to/file',
('', '', '/path/to/file', '', '', ''),
('', '', '/path/to/file', '', '')),
('scheme:///path/to/file',
'scheme:/path/to/file',
('scheme', '', '/path/to/file', '', '', ''),
('scheme', '', '/path/to/file', '', '')),
('file:/tmp/junk.txt',
'file:///tmp/junk.txt',
('file', '', '/tmp/junk.txt', '', '', ''),
('file', '', '/tmp/junk.txt', '', '')),
('http:/tmp/junk.txt',
'http:///tmp/junk.txt',
('http', '', '/tmp/junk.txt', '', '', ''),
('http', '', '/tmp/junk.txt', '', '')),
('https:/tmp/junk.txt',
'https:///tmp/junk.txt',
('https', '', '/tmp/junk.txt', '', '', ''),
('https', '', '/tmp/junk.txt', '', '')),
]
def _encode(t):
return (t[0].encode('ascii'),
t[1].encode('ascii'),
tuple(x.encode('ascii') for x in t[2]),
tuple(x.encode('ascii') for x in t[3]))
bytes_cases = [_encode(x) for x in str_cases]
for url, url2, parsed, split in str_cases + bytes_cases:
self.checkRoundtrips(url, parsed, split, url2)

def test_http_roundtrips(self):
# urllib.parse.urlsplit treats 'http:' as an optimized special case,
# so we test both 'http:' and 'https:' in all the following.
Expand Down
2 changes: 1 addition & 1 deletion Lib/urllib/parse.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -521,7 +521,7 @@ def urlunsplit(components):
empty query; the RFC states that these are equivalent)."""
scheme, netloc, url, query, fragment, _coerce_result = (
_coerce_args(*components))
if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
if netloc or (scheme and scheme in uses_netloc) or url[:2] == '//':
if url and url[:1] != '/': url = '/' + url
url = '//' + (netloc or '') + url
if scheme:
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Library/2019-08-27-01-16-50.gh-issue-67693.4NIAiy.rst
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Fix :func:`urllib.parse.urlunparse` and :func:`urllib.parse.urlunsplit` for URIs with path starting with multiple slashes and no authority.
Based on patch by Ashwin Ramaswami.
Back | FazBrowse Home | New Git URL