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

diff --git a/Doc/library/urlparse.rst b/Doc/library/urlparse.rst
index 1f580230fb3276e0b6350c15701da248da044d32..c3eb559d1d507ad20672af51cd6b04c2ec1d0a5a 100644 (file)
--- a/Doc/library/urlparse.rst
+++ b/Doc/library/urlparse.rst
@@ -58,6 +58,24 @@ The :mod:`urlparse` 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 80e4d91193d110264df8f4ce2c9b5fab82b8c08b..82440176f42beddedffe888123ebee84d2e51021 100644 (file)
--- 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 6261b24e78e3f5214655d4067973ba216989ca7d..99ebe6ad334f842b4d04e59e3e69ec15fd810ebd 100644 (file)
--- 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)