[Python-checkins] python/dist/src/Lib urlparse.py,1.46,1.47

Sun Jan 9 16:29:12 CET 2005

Update of /cvsroot/python/python/dist/src/Lib
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv28840
Modified Files:
	urlparse.py 
Log Message:
Patch #712317: In URLs such as http://www.example.com?query=spam, treat '?' as
a delimiter. Previously, the 'network location' (<authority> in RFC 2396) would
become 'www.example.com?query=spam', while RFC 2396 does not allow a '?' in
<authority>. See bug #548176 for further discussion.
Index: urlparse.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/urlparse.py,v
retrieving revision 1.46
retrieving revision 1.47
diff -u -d -r1.46 -r1.47

--- urlparse.py	31 Dec 2004 19:15:26 -0000	1.46
+++ urlparse.py	9 Jan 2005 15:29:10 -0000	1.47
@@ -63,6 +63,15 @@
 i = url.find(';')
 return url[:i], url[i+1:]
 
+def _splitnetloc(url, start=0):
+ for c in '/?#': # the order is important!
+ delim = url.find(c, start)
+ if delim >= 0:
+ break
+ else:
+ delim = len(url)
+ return url[start:delim], url[delim:]
+
 def urlsplit(url, scheme='', allow_fragments=1):
 """Parse a URL into 5 components:
 <scheme>://<netloc>/<path>?<query>#<fragment>
@@ -82,13 +91,7 @@
 scheme = url[:i].lower()
 url = url[i+1:]
 if url[:2] == '//':
- i = url.find('/', 2)
- if i < 0:
- i = url.find('#')
- if i < 0:
- i = len(url)
- netloc = url[2:i]
- url = url[i:]
+ netloc, url = _splitnetloc(url, 2)
 if allow_fragments and '#' in url:
 url, fragment = url.split('#', 1)
 if '?' in url:
@@ -101,12 +104,8 @@
 break
 else:
 scheme, url = url[:i].lower(), url[i+1:]
- if scheme in uses_netloc:
- if url[:2] == '//':
- i = url.find('/', 2)
- if i < 0:
- i = len(url)
- netloc, url = url[2:i], url[i:]
+ if scheme in uses_netloc and url[:2] == '//':
+ netloc, url = _splitnetloc(url, 2)
 if allow_fragments and scheme in uses_fragment and '#' in url:
 url, fragment = url.split('#', 1)
 if scheme in uses_query and '?' in url:
