Skip to content

[2.7] bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812) #13815

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
merged 2 commits into from
Jun 4, 2019
Merged

[2.7] bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812) #13815

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b02410c
bpo-36742: Corrects fix to handle decomposition in usernames
zooba Jun 4, 2019
07392c7
Replace accidentally removed u prefixes
zooba Jun 4, 2019
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
13 changes: 7 additions & 6 deletions Lib/test/test_urlparse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -648,12 +648,13 @@ def test_urlsplit_normalization(self):
urlparse.urlsplit(u'http://\u30d5\u309a\ufe1380')

for scheme in [u"http", u"https", u"ftp"]:
for c in denorm_chars:
url = u"{}://netloc{}false.netloc/path".format(scheme, c)
if test_support.verbose:
print "Checking %r" % url
with self.assertRaises(ValueError):
urlparse.urlsplit(url)
for netloc in [u"netloc{}false.netloc", u"n{}user@netloc"]:
for c in denorm_chars:
url = u"{}://{}/path".format(scheme, netloc.format(c))
if test_support.verbose:
print "Checking %r" % url
with self.assertRaises(ValueError):
urlparse.urlsplit(url)

def test_main():
test_support.run_unittest(UrlParseTestCase)
Expand Down
12 changes: 6 additions & 6 deletions Lib/urlparse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,17 +171,17 @@ def _checknetloc(netloc):
# looking for characters like \u2100 that expand to 'a/c'
# IDNA uses NFKC equivalence, so normalize for this check
import unicodedata
n = netloc.rpartition('@')[2] # ignore anything to the left of '@'
n = n.replace(':', '') # ignore characters already included
n = n.replace('#', '') # but not the surrounding text
n = n.replace('?', '')
n = netloc.replace(u'@', u'') # ignore characters already included
n = n.replace(u':', u'') # but not the surrounding text
n = n.replace(u'#', u'')
n = n.replace(u'?', u'')
netloc2 = unicodedata.normalize('NFKC', n)
if n == netloc2:
return
for c in '/?#@:':
if c in netloc2:
raise ValueError("netloc '" + netloc + "' contains invalid " +
"characters under NFKC normalization")
raise ValueError(u"netloc '" + netloc + u"' contains invalid " +
u"characters under NFKC normalization")

def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components:
Expand Down