From 0176f765d46f7a86e7fa566c7f9fa5e4869ab88c Mon Sep 17 00:00:00 2001
From: "Nam T. Nguyen" <namnguyen@google.com>
Date: Sun, 28 May 2017 16:15:52 -0700
Subject: [PATCH] urllib: Simplify splithost by calling into urlparse.

The current regex based splitting produces a wrong result. For example::

  http://abc#@def

Web browsers parse that URL as ``http://abc/#@def``, that is, the host
is ``abc``, the path is ``/``, and the fragment is ``#@def``.
---
 Lib/test/test_urllib.py |  2 ++
 Lib/urllib.py           | 23 ++++++++---------------
 2 files changed, 10 insertions(+), 15 deletions(-)

diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
index 14de91e13dad19..0e14946a8b1e5f 100644
--- a/Lib/test/test_urllib.py
+++ b/Lib/test/test_urllib.py
@@ -878,6 +878,8 @@ def test_splithost(self):
                          ('www.example.org:80', ''))
         self.assertEqual(splithost('/foo/bar/baz.html'),
                          (None, '/foo/bar/baz.html'))
+        self.assertEqual(splithost('//127.0.0.1#@host.com'),
+                         ('127.0.0.1', '/#@host.com'))
 
     def test_splituser(self):
         splituser = urllib.splituser
diff --git a/Lib/urllib.py b/Lib/urllib.py
index c3c8ef4b600484..931fd51c807dcd 100644
--- a/Lib/urllib.py
+++ b/Lib/urllib.py
@@ -30,7 +30,7 @@
 import base64
 import re
 
-from urlparse import urljoin as basejoin
+from urlparse import urljoin as basejoin, urlparse, urlunparse
 
 __all__ = ["urlopen", "URLopener", "FancyURLopener", "urlretrieve",
            "urlcleanup", "quote", "quote_plus", "unquote", "unquote_plus",
@@ -1088,22 +1088,15 @@ def splittype(url):
         return scheme.lower(), url[len(scheme) + 1:]
     return None, url
 
-_hostprog = None
 def splithost(url):
     """splithost('//host[:port]/path') --> 'host[:port]', '/path'."""
-    global _hostprog
-    if _hostprog is None:
-        import re
-        _hostprog = re.compile('^//([^/?]*)(.*)$')
-
-    match = _hostprog.match(url)
-    if match:
-        host_port = match.group(1)
-        path = match.group(2)
-        if path and not path.startswith('/'):
-            path = '/' + path
-        return host_port, path
-    return None, url
+    fields = urlparse(url)
+    path = fields.path
+    rest = [fields.params, fields.query, fields.fragment]
+    if not path and any(rest):
+        path = '/'
+    return (None if fields.netloc == '' else fields.netloc,
+            urlunparse(['', '', path] + rest))
 
 _userprog = None
 def splituser(host):