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

2 files changed, 26 insertions, 5 deletions

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 80e4d91..8244017 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -478,6 +478,26 @@ class UrlParseTestCase(unittest.TestCase):
         self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"),
                          ('x-newscheme','foo.com','/stuff','','',''))
 
+    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(urlparse.urlparse("path"),
+                ('','','path','','',''))
+        self.assertEqual(urlparse.urlparse("//www.python.org:80"),
+                ('','www.python.org:80','','','',''))
+        self.assertEqual(urlparse.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(urlparse.urlparse("path:80"),
+                ('','','path:80','','',''))
+        self.assertEqual(urlparse.urlparse("http:"),('http','','','','',''))
+        self.assertEqual(urlparse.urlparse("https:"),('https','','','','',''))
+        self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
+                ('http','www.python.org:80','','','',''))
 
 
 def test_main():
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index 6261b24..99ebe6a 100644
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -187,11 +187,12 @@ def urlsplit(url, scheme='', allow_fragments=True):
             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)