[Python-checkins] cpython (2.7): Issue #11467: Fix urlparse behavior when handling urls which contains scheme

[senthil.kumaran]

http://hg.python.org/cpython/rev/7a693e283c68
changeset:   69365:7a693e283c68
branch:      2.7
parent:      69361:e1f0881d2cb4
user:        Senthil Kumaran <orsenthil at gmail.com>
date:        Fri Apr 15 18:07:33 2011 +0800
summary:
  Issue #11467: Fix urlparse behavior when handling urls which contains scheme
specific part only digits. Patch by Santoso Wijaya.

files:
  Lib/test/test_urlparse.py |   7 +++++--
  Lib/urlparse.py           |  14 +++++++++-----
  Misc/NEWS                 |   3 +++
  3 files changed, 17 insertions(+), 7 deletions(-)


diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -196,10 +196,13 @@
         #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 at example.org'),
+                ('mailto', '', '1337 at 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
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -187,11 +187,15 @@
             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
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -51,6 +51,9 @@
 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.
 

-- 
Repository URL: http://hg.python.org/cpython