[Python-checkins] bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812)
Steve Dower
webhook-mailer at python.org
Tue Jun 4 12:40:21 EDT 2019
https://github.com/python/cpython/commit/f61599b050c621386a3fc6bc480359e2d3bb93de
commit: f61599b050c621386a3fc6bc480359e2d3bb93de
branch: 2.7
author: Steve Dower <steve.dower at python.org>
committer: GitHub <noreply at github.com>
date: 2019-06-04T09:40:16-07:00
summary:
bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812)
files:
M Lib/test/test_urlparse.py
M Lib/urlparse.py
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 6fd1071bf7cd..857ed96d92fe 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -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 at 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)
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index f08e0fe58432..6834f3c1798b 100644
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -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:
More information about the Python-checkins
mailing list