From: Senthil Kumaran <orsenthil@gmail.com>
Date: Fri, 15 Apr 2011 10:21:26 +0000 (+0800)
Subject: merge from 3.1
X-Git-Tag: v3.2.1b1~123
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=b4bd4af8c4adb03978803b5d94241a87e40bdaf9;p=python

merge from 3.1
---

b4bd4af8c4adb03978803b5d94241a87e40bdaf9
diff --cc Lib/test/test_urlparse.py
index 628b8ec04a,252eb138d0..c8d572cda1
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@@ -228,10 -197,13 +228,15 @@@ class UrlParseTestCase(unittest.TestCas
          #self.checkJoin(RFC1808_BASE, 'http:g', 'http:g')
          #self.checkJoin(RFC1808_BASE, 'http:', 'http:')
  
+     def test_RFC2368(self):
+         # Issue 11467: path that starts with a number is not parsed correctly
+         self.assertEqual(urllib.parse.urlparse('mailto:1337@example.org'),
+                 ('mailto', '', '1337@example.org', '', '', ''))
+ 
      def test_RFC2396(self):
          # cases from RFC 2396
 +
 +
          self.checkJoin(RFC2396_BASE, 'g:h', 'g:h')
          self.checkJoin(RFC2396_BASE, 'g', 'http://a/b/c/g')
          self.checkJoin(RFC2396_BASE, './g', 'http://a/b/c/g')
diff --cc Lib/urllib/parse.py
index 9a3e42ee78,a20a3d4156..45ae202d5c
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@@ -339,18 -183,20 +339,23 @@@ def urlsplit(url, scheme='', allow_frag
                  url, query = url.split('?', 1)
              v = SplitResult(scheme, netloc, url, query, fragment)
              _parse_cache[key] = v
 -            return v
 +            return _coerce_result(v)
-         if url.endswith(':') or not url[i+1].isdigit():
-             for c in url[:i]:
-                 if c not in scheme_chars:
-                     break
-             else:
+         for c in url[:i]:
+             if c not in scheme_chars:
+                 break
+         else:
+             try:
+                 # make sure "url" is not actually a port number (in which case
+                 # "scheme" is really part of the path
+                 _testportnum = int(url[i+1:])
+             except ValueError:
                  scheme, url = url[:i].lower(), url[i+1:]
+ 
      if url[:2] == '//':
          netloc, url = _splitnetloc(url, 2)
 +        if (('[' in netloc and ']' not in netloc) or
 +                (']' in netloc and '[' not in netloc)):
 +            raise ValueError("Invalid IPv6 URL")
      if allow_fragments and scheme in uses_fragment and '#' in url:
          url, fragment = url.split('#', 1)
      if scheme in uses_query and '?' in url: