mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-10 03:49:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

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

Browse source
This commit is contained in:
Senthil Kumaran 2010-08-04 04:45:31 +00:00
parent 75a292e5be
commit 0b5019fe23
3 changed files with 44 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

18
Doc/library/urlparse.rst
View file

@ -58,6 +58,24 @@ The :mod:`urlparse` module defines the following functions:
>>> o.geturl() >>> o.geturl()
'http://www.cwi.nl:80/%7Eguido/Python.html' 'http://www.cwi.nl:80/%7Eguido/Python.html'
If the scheme value is not specified, urlparse following the syntax
specifications from RFC 1808, expects the netloc value to start with '//',
Otherwise, it is not possible to distinguish between net_loc and path
component and would classify the indistinguishable component as path as in
a relative url.
>>> from urlparse import urlparse
>>> urlparse('//www.cwi.nl:80/%7Eguido/Python.html')
ParseResult(scheme='', netloc='www.cwi.nl:80', path='/%7Eguido/Python.html',
params='', query='', fragment='')
>>> urlparse('www.cwi.nl:80/%7Eguido/Python.html')
ParseResult(scheme='', netloc='', path='www.cwi.nl:80/%7Eguido/Python.html',
params='', query='', fragment='')
>>> urlparse('help/Python.html')
ParseResult(scheme='', netloc='', path='help/Python.html', params='',
query='', fragment='')
If the *scheme* argument is specified, it gives the default addressing If the *scheme* argument is specified, it gives the default addressing
scheme, to be used only if the URL does not specify one. The default value for scheme, to be used only if the URL does not specify one. The default value for
this argument is the empty string. this argument is the empty string.

20
Lib/test/test_urlparse.py
View file

@ -478,6 +478,26 @@ class UrlParseTestCase(unittest.TestCase):
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"), self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"),
('x-newscheme','foo.com','/stuff','','','')) ('x-newscheme','foo.com','/stuff','','',''))
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(urlparse.urlparse("path"),
('','','path','','',''))
self.assertEqual(urlparse.urlparse("//www.python.org:80"),
('','www.python.org:80','','','',''))
self.assertEqual(urlparse.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(urlparse.urlparse("path:80"),
('','','path:80','','',''))
self.assertEqual(urlparse.urlparse("http:"),('http','','','','',''))
self.assertEqual(urlparse.urlparse("https:"),('https','','','','',''))
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
def test_main(): def test_main():

11
Lib/urlparse.py
View file

@ -187,11 +187,12 @@ def urlsplit(url, scheme='', allow_fragments=True):
v = SplitResult(scheme, netloc, url, query, fragment) v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v _parse_cache[key] = v
return v return v
for c in url[:i]: if url.endswith(':') or not url[i+1].isdigit():
if c not in scheme_chars: for c in url[:i]:
break if c not in scheme_chars:
else: break
scheme, url = url[:i].lower(), url[i+1:] else:
scheme, url = url[:i].lower(), url[i+1:]
if url[:2] == '//': if url[:2] == '//':
netloc, url = _splitnetloc(url, 2) netloc, url = _splitnetloc(url, 2)