Skip to content

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

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
serhiy-storchaka merged 10 commits into from
May 14, 2024
+70 −4
Merged

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

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
ff16c46
fix: always add double slash if scheme is in uses_netloc
epicfaace Aug 15, 2019
151e39c
📜🤖 Added by blurb_it.
blurb-it[bot] Aug 27, 2019
0e177fd
Update 2019-08-27-01-16-50.bpo-34276.4NIAiy.rst
epicfaace Aug 27, 2019
eea029d
Merge branch 'main' into urls
serhiy-storchaka Dec 29, 2023
cc9067b
Fix urlunparse() and urlunsplit() for URIs with path starting with mu…
serhiy-storchaka Dec 29, 2023
fb03e5f
Change issue number.
serhiy-storchaka Dec 29, 2023
26951a7
Merge branch 'main' into urls2
serhiy-storchaka Dec 29, 2023
7f495b0
Delete Misc/NEWS.d/next/Library/2023-12-29-16-31-31.gh-issue-67693.qi…
serhiy-storchaka May 13, 2024
f5ab0c1
Merge branch 'main' into urls2
serhiy-storchaka May 13, 2024
62957fe
Add few more tests.
serhiy-storchaka May 13, 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
Prev Previous commit
Add few more tests.
  • Loading branch information
@serhiy-storchaka
serhiy-storchaka committed May 13, 2024
commit 62957fe05a1b50ad980848d35a601cb2028a0b58
40 changes: 37 additions & 3 deletions Lib/test/test_urlparse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,15 +103,17 @@

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.assertSequenceEqual(result, parsed)
t = (result.scheme, result.netloc, result.path,
result.params, result.query, result.fragment)
self.assertSequenceEqual(t, parsed)
# put it back together and it should be the same
result2 = urllib.parse.urlunparse(result)
self.assertSequenceEqual(result2, url)
self.assertSequenceEqual(result2, url2)
self.assertSequenceEqual(result2, result.geturl())

# the result of geturl() is a fixpoint; we can always parse it
Expand All @@ -137,7 +139,7 @@ def checkRoundtrips(self, url, parsed, split):
result.query, result.fragment)
self.assertSequenceEqual(t, split)
result2 = urllib.parse.urlunsplit(result)
self.assertSequenceEqual(result2, url)
self.assertSequenceEqual(result2, url2)
self.assertSequenceEqual(result2, result.geturl())

# check the fixpoint property of re-parsing the result of geturl()
Expand Down Expand Up @@ -243,6 +245,38 @@ 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