Mirror
/
cpython
mirror of https://github.com/python/cpython
4
1
Fork 0
Code Issues Releases Wiki Activity

Issue2987 - Added additional Invalid URL and changed the Invalid URL checking code for better.

This commit is contained in:
Senthil Kumaran 2010-04-20 20:37:59 +00:00
parent c166b4021f
commit 241a04371b
2 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Lib/test/test_urlparse.py
View File

@ -272,6 +272,7 @@ class UrlParseTestCase(unittest.TestCase):
for invalid_url in [ for invalid_url in [
'http://::12.34.56.78]/', 'http://::12.34.56.78]/',
'http://[::1/foo/', 'http://[::1/foo/',
'http://[::1/foo/bad]/bad',
'http://[::ffff:12.34.56.78']: 'http://[::ffff:12.34.56.78']:
self.assertRaises(ValueError, lambda : urlparse.urlparse(invalid_url).hostname) self.assertRaises(ValueError, lambda : urlparse.urlparse(invalid_url).hostname)
self.assertRaises(ValueError, lambda : urlparse.urlparse(invalid_url)) self.assertRaises(ValueError, lambda : urlparse.urlparse(invalid_url))

14
Lib/urlparse.py
View File

@ -90,8 +90,6 @@ class ResultMixin(object):
netloc = self.netloc.split('@')[-1] netloc = self.netloc.split('@')[-1]
if '[' in netloc and ']' in netloc: if '[' in netloc and ']' in netloc:
return netloc.split(']')[0][1:].lower() return netloc.split(']')[0][1:].lower()
elif '[' in netloc or ']' in netloc:
raise ValueError("Invalid IPv6 hostname")
elif ':' in netloc: elif ':' in netloc:
return netloc.split(':')[0].lower() return netloc.split(':')[0].lower()
elif netloc == '': elif netloc == '':
@ -151,10 +149,6 @@ def _splitparams(url):
def _splitnetloc(url, start=0): def _splitnetloc(url, start=0):
delim = len(url) # position of end of domain part of url, default is end delim = len(url) # position of end of domain part of url, default is end
if '[' in url: # check for invalid IPv6 URL
if not ']' in url: raise ValueError("Invalid IPv6 URL")
elif ']' in url:
if not '[' in url: raise ValueError("Invalid IPv6 URL")
for c in '/?#': # look for delimiters; the order is NOT important for c in '/?#': # look for delimiters; the order is NOT important
wdelim = url.find(c, start) # find first of this delim wdelim = url.find(c, start) # find first of this delim
if wdelim >= 0: # if found if wdelim >= 0: # if found
@ -182,6 +176,10 @@ def urlsplit(url, scheme='', allow_fragments=True):
url = url[i+1:] url = url[i+1:]
if url[:2] == '//': if url[:2] == '//':
netloc, url = _splitnetloc(url, 2) netloc, url = _splitnetloc(url, 2)
if '[' in netloc :
if not ']' in netloc: raise ValueError("Invalid IPv6 URL")
if ']' in netloc:
if not '[' in netloc: raise ValueError("Invalid IPv6 URL")
if allow_fragments and '#' in url: if allow_fragments and '#' in url:
url, fragment = url.split('#', 1) url, fragment = url.split('#', 1)
if '?' in url: if '?' in url:
@ -197,6 +195,10 @@ def urlsplit(url, scheme='', allow_fragments=True):
if url[:2] == '//': if url[:2] == '//':
netloc, url = _splitnetloc(url, 2) netloc, url = _splitnetloc(url, 2)
if '[' in netloc:
if not ']' in netloc: raise ValueError("Invalid IPv6 URL")
if ']' in netloc:
if not '[' in netloc: raise ValueError("Invalid IPv6 URL")
if allow_fragments and scheme in uses_fragment and '#' in url: if allow_fragments and scheme in uses_fragment and '#' in url:
url, fragment = url.split('#', 1) url, fragment = url.split('#', 1)
if scheme in uses_query and '?' in url: if scheme in uses_query and '?' in url: