+13
-12
lines changedFilter options
+13
-12
lines changed Original file line number Diff line number Diff line change
@@ -648,12 +648,13 @@ def test_urlsplit_normalization(self):
648 648
urlparse.urlsplit(u'http://\u30d5\u309a\ufe1380')
649 649 650 650
for scheme in [u"http", u"https", u"ftp"]:
651 -
for c in denorm_chars:
652 -
url = u"{}://netloc{}false.netloc/path".format(scheme, c)
653 -
if test_support.verbose:
654 -
print "Checking %r" % url
655 -
with self.assertRaises(ValueError):
656 -
urlparse.urlsplit(url)
651 +
for netloc in [u"netloc{}false.netloc", u"n{}user@netloc"]:
652 +
for c in denorm_chars:
653 +
url = u"{}://{}/path".format(scheme, netloc.format(c))
654 +
if test_support.verbose:
655 +
print "Checking %r" % url
656 +
with self.assertRaises(ValueError):
657 +
urlparse.urlsplit(url)
657 658 658 659
def test_main():
659 660
test_support.run_unittest(UrlParseTestCase)
@@ -171,17 +171,17 @@ def _checknetloc(netloc):
171 171
# looking for characters like \u2100 that expand to 'a/c'
172 172
# IDNA uses NFKC equivalence, so normalize for this check
173 173
import unicodedata
174 -
n = netloc.rpartition('@')[2] # ignore anything to the left of '@'
175 -
n = n.replace(':', '') # ignore characters already included
176 -
n = n.replace('#', '') # but not the surrounding text
177 -
n = n.replace('?', '')
174 +
n = netloc.replace(u'@', u'') # ignore characters already included
175 +
n = n.replace(u':', u'') # but not the surrounding text
176 +
n = n.replace(u'#', u'')
177 +
n = n.replace(u'?', u'')
178 178
netloc2 = unicodedata.normalize('NFKC', n)
179 179
if n == netloc2:
180 180
return
181 181
for c in '/?#@:':
182 182
if c in netloc2:
183 -
raise ValueError("netloc '" + netloc + "' contains invalid " +
184 -
"characters under NFKC normalization")
183 +
raise ValueError(u"netloc '" + netloc + u"' contains invalid " +
184 +
u"characters under NFKC normalization")
185 185 186 186
def urlsplit(url, scheme='', allow_fragments=True):
187 187
"""Parse a URL into 5 components:
You can’t perform that action at this time.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4