[Python-checkins] r83701 - in python/branches/py3k: Doc/library/urllib.parse.rst Lib/test/test_urlparse.py Lib/urllib/parse.py

[senthil.kumaran]

Author: senthil.kumaran
Date: Wed Aug  4 06:50:44 2010
New Revision: 83701

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



Modified:
   python/branches/py3k/Doc/library/urllib.parse.rst
   python/branches/py3k/Lib/test/test_urlparse.py
   python/branches/py3k/Lib/urllib/parse.py

Modified: python/branches/py3k/Doc/library/urllib.parse.rst
==============================================================================
--- python/branches/py3k/Doc/library/urllib.parse.rst	(original)
+++ python/branches/py3k/Doc/library/urllib.parse.rst	Wed Aug  4 06:50:44 2010
@@ -48,6 +48,23 @@
       >>> o.geturl()
       '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
    scheme, to be used only if the URL does not specify one.  The default value for
    this argument is the empty string.

Modified: python/branches/py3k/Lib/test/test_urlparse.py
==============================================================================
--- python/branches/py3k/Lib/test/test_urlparse.py	(original)
+++ python/branches/py3k/Lib/test/test_urlparse.py	Wed Aug  4 06:50:44 2010
@@ -461,6 +461,27 @@
         self.assertEqual(urllib.parse.urlparse("http://example.com?blahblah=/foo"),
                          ('http', 'example.com', '', '', 'blahblah=/foo', ''))
 
+    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(urllib.parse.urlparse("path"),
+                ('','','path','','',''))
+        self.assertEqual(urllib.parse.urlparse("//www.python.org:80"),
+                ('','www.python.org:80','','','',''))
+        self.assertEqual(urllib.parse.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(urllib.parse.urlparse("path:80"),
+                ('','','path:80','','',''))
+        self.assertEqual(urllib.parse.urlparse("http:"),('http','','','','',''))
+        self.assertEqual(urllib.parse.urlparse("https:"),('https','','','','',''))
+        self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
+                ('http','www.python.org:80','','','',''))
+
     def test_usingsys(self):
         # Issue 3314: sys module is used in the error
         self.assertRaises(TypeError, urllib.parse.urlencode, "foo")

Modified: python/branches/py3k/Lib/urllib/parse.py
==============================================================================
--- python/branches/py3k/Lib/urllib/parse.py	(original)
+++ python/branches/py3k/Lib/urllib/parse.py	Wed Aug  4 06:50:44 2010
@@ -192,11 +192,12 @@
             v = SplitResult(scheme, netloc, url, query, fragment)
             _parse_cache[key] = v
             return v
-        for c in url[:i]:
-            if c not in scheme_chars:
-                break
-        else:
-            scheme, url = url[:i].lower(), url[i+1:]
+        if url.endswith(':') or not url[i+1].isdigit():
+            for c in url[:i]:
+                if c not in scheme_chars:
+                    break
+            else:
+                scheme, url = url[:i].lower(), url[i+1:]
     if url[:2] == '//':
         netloc, url = _splitnetloc(url, 2)
         if (('[' in netloc and ']' not in netloc) or