[Python-checkins] r59758 - in python/trunk: Lib/test/test_urlparse.py Lib/urlparse.py Misc/NEWS

[guido.van.rossum]

Author: guido.van.rossum
Date: Sat Jan  5 23:19:06 2008
New Revision: 59758

Modified:
   python/trunk/Lib/test/test_urlparse.py
   python/trunk/Lib/urlparse.py
   python/trunk/Misc/NEWS
Log:
Patch #1637: fix urlparse for URLs like 'http://x.com?arg=/foo'.
Fix by John Nagle.


Modified: python/trunk/Lib/test/test_urlparse.py
==============================================================================
--- python/trunk/Lib/test/test_urlparse.py	(original)
+++ python/trunk/Lib/test/test_urlparse.py	Sat Jan  5 23:19:06 2008
@@ -316,6 +316,11 @@
         self.assertEqual(type(p.hostname), type(uri))
         self.assertEqual(type(p.path), type(uri))
 
+    def test_noslash(self):
+        # Issue 1637: http://foo.com?query is legal
+        self.assertEqual(urlparse.urlparse("http://example.com?blahblah=/foo"),
+                         ('http', 'example.com', '', '', 'blahblah=/foo', ''))
+
 def test_main():
     test_support.run_unittest(UrlParseTestCase)
 

Modified: python/trunk/Lib/urlparse.py
==============================================================================
--- python/trunk/Lib/urlparse.py	(original)
+++ python/trunk/Lib/urlparse.py	Sat Jan  5 23:19:06 2008
@@ -169,13 +169,12 @@
     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:]
+    delim = len(url)   # position of end of domain part of url, default is end
+    for c in '/?#':    # look for delimiters; the order is NOT important
+        wdelim = url.find(c, start)        # find first of this delim
+        if wdelim >= 0:                    # if found
+            delim = min(delim, wdelim)     # use earliest delim position
+    return url[start:delim], url[delim:]   # return (domain, rest)
 
 def urlsplit(url, scheme='', allow_fragments=True):
     """Parse a URL into 5 components:

Modified: python/trunk/Misc/NEWS
==============================================================================
--- python/trunk/Misc/NEWS	(original)
+++ python/trunk/Misc/NEWS	Sat Jan  5 23:19:06 2008
@@ -342,6 +342,8 @@
 Library
 -------
 
+- Patch #1637: fix urlparse for URLs like 'http://x.com?arg=/foo'.
+
 - Patch #1698: allow '@' in username parsed by urlparse.py.
 
 - Issue #1735: TarFile.extractall() now correctly sets directory permissions