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

3 files changed, 44 insertions, 5 deletions

diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst
index add07a5..b915f29 100644
--- a/Doc/library/urllib.parse.rst
+++ b/Doc/library/urllib.parse.rst
@@ -48,6 +48,23 @@ The :mod:`urllib.parse` module defines the following functions:
       >>> 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.
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 69d65c1..e559142 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -461,6 +461,27 @@ class UrlParseTestCase(unittest.TestCase):
         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")
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 133b9d9..00f0e5b 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -192,11 +192,12 @@ 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)
         if (('[' in netloc and ']' not in netloc) or