ilusha/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython synced 2026-09-29 12:10:30 +03:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix Issue754016 - urlparse goes wrong with IP:port without scheme

Browse source
This commit is contained in:
Senthil Kumaran 2010-08-04 04:50:44 +00:00
parent 4aa0d4d2d0
commit 84c7d9f87b
3 changed files with 44 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

21
Lib/test/test_urlparse.py
View file

@ -461,6 +461,27 @@ class UrlParseTestCase(unittest.TestCase):
self.assertEqual(urllib.parse.urlparse("http://example.com?blahblah=/foo"),
('http', 'example.com', '', '', 'blahblah=/foo', ''))
def test_withoutscheme(self):
# Test urlparse without scheme
# Issue 754016: urlparse goes wrong with IP:port without scheme
# RFC 1808 specifies that netloc should start with //, urlparse expects
# the same, otherwise it classifies the portion of url as path.
self.assertEqual(urllib.parse.urlparse("path"),
('','','path','','',''))
self.assertEqual(urllib.parse.urlparse("//www.python.org:80"),
('','www.python.org:80','','','',''))
self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
def test_portseparator(self):
# Issue 754016 makes changes for port separator ':' from scheme separator
self.assertEqual(urllib.parse.urlparse("path:80"),
('','','path:80','','',''))
self.assertEqual(urllib.parse.urlparse("http:"),('http','','','','',''))
self.assertEqual(urllib.parse.urlparse("https:"),('https','','','','',''))
self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
def test_usingsys(self):
# Issue 3314: sys module is used in the error
self.assertRaises(TypeError, urllib.parse.urlencode, "foo")

11
Lib/urllib/parse.py
View file

@ -192,11 +192,12 @@ def urlsplit(url, scheme='', allow_fragments=True):
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
return v
for c in url[:i]:
if c not in scheme_chars:
break
else:
scheme, url = url[:i].lower(), url[i+1:]
if url.endswith(':') or not url[i+1].isdigit():
for c in url[:i]:
if c not in scheme_chars:
break
else:
scheme, url = url[:i].lower(), url[i+1:]
if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or