Issue #11467: Fix urlparse behavior when handling urls which contains scheme...

Issue #11467: Fix urlparse behavior when handling urls which contains scheme specific part only digits.

Lib/test/test_urlparse.py

@@ -197,6 +197,11 @@ class UrlParseTestCase(unittest.TestCase):
         #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')

Lib/urllib/parse.py

@@ -184,12 +184,17 @@ def urlsplit(url, scheme='', allow_fragments=True):
             v = SplitResult(scheme, netloc, url, query, fragment)
             _parse_cache[key] = v
             return v
-        if url.endswith(':') or not url[i+1].isdigit():
         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 allow_fragments and scheme in uses_fragment and '#' in url:

Misc/NEWS

@@ -51,6 +51,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #11467: Fix urlparse behavior when handling urls which contains scheme 
+  specific part only digits. Patch by Santoso Wijaya.
+
 - Issue #11474: Fix the bug with url2pathname() handling of '/C|/' on Windows.
   Patch by Santoso Wijaya.