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

specific part only digits. Patch by Santoso Wijaya.

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index c5764c59ca98104b58614ca19f306c77ba37dac4..996148592f3ea0d34d80a77ac8c795b5915c76fe 100644 (file)
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -196,10 +196,13 @@ 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(urlparse.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 --git a/Lib/urlparse.py b/Lib/urlparse.py
index a019a7b7a49e02e0e8d9f44d650d4047ae325dd8..e5528face6fcb6a1a0d4da02dd29865b81f9c871 100644 (file)
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -187,11 +187,15 @@ 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:
+        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] == '//':

diff --git a/Misc/NEWS b/Misc/NEWS
index 20fa4179249f97700d523537870cb22e0b652fc1..7510225f2310fa61890b2a60292ba797b97e45a5 100644 (file)
--- a/Misc/NEWS
+++ b/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.