From d17ebdba4a4443a523c0344440d37d472ed82b5a Mon Sep 17 00:00:00 2001
From: Senthil Kumaran <orsenthil@gmail.com>
Date: Mon, 22 Nov 2010 04:53:57 +0000
Subject: Merged revisions 86676 via svnmerge from
 svn+ssh://pythondev@svn.python.org/python/branches/py3k

........
  r86676 | senthil.kumaran | 2010-11-22 12:48:26 +0800 (Mon, 22 Nov 2010) | 4 lines

  Fix Issue4493 - urllib2 adds '/' to the path component of url, when it does not
  starts with one. This behavior is exhibited by browser and other clients.
........
---
 Lib/test/test_urllib2.py | 19 +++++++++++++++++++
 Lib/urllib/parse.py      |  7 ++++++-
 Lib/urllib/request.py    |  2 +-
 Misc/NEWS                |  3 +++
 4 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/Lib/test/test_urllib2.py b/Lib/test/test_urllib2.py
index 38cf607..94bbc00 100644
--- a/Lib/test/test_urllib2.py
+++ b/Lib/test/test_urllib2.py
@@ -849,6 +849,25 @@ class HandlerTests(unittest.TestCase):
             p_ds_req = h.do_request_(ds_req)
             self.assertEqual(p_ds_req.unredirected_hdrs["Host"],"example.com")
 
+    def test_fixpath_in_weirdurls(self):
+        # Issue4493: urllib2 to supply '/' when to urls where path does not
+        # start with'/'
+
+        h = urllib.request.AbstractHTTPHandler()
+        o = h.parent = MockOpener()
+
+        weird_url = 'http://www.python.org?getspam'
+        req = Request(weird_url)
+        newreq = h.do_request_(req)
+        self.assertEqual(newreq.host,'www.python.org')
+        self.assertEqual(newreq.selector,'/?getspam')
+
+        url_without_path = 'http://www.python.org'
+        req = Request(url_without_path)
+        newreq = h.do_request_(req)
+        self.assertEqual(newreq.host,'www.python.org')
+        self.assertEqual(newreq.selector,'')
+
 
     def test_errors(self):
         h = urllib.request.HTTPErrorProcessor()
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index b437d6f..cfd47f9 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -688,7 +688,12 @@ def splithost(url):
         _hostprog = re.compile('^//([^/?]*)(.*)$')
 
     match = _hostprog.match(url)
-    if match: return match.group(1, 2)
+    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
 
 _userprog = None
diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
index 5a67c0b..7edfa1b 100644
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -105,7 +105,7 @@ from urllib.response import addinfourl, addclosehook
 # check for SSL
 try:
     import ssl
-except:
+except ImportError:
     _have_ssl = False
 else:
     _have_ssl = True
diff --git a/Misc/NEWS b/Misc/NEWS
index 53b18d6..77341a2 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -16,6 +16,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #4493: urllib2 adds '/' in front of path components which does not
+  start with '/. Common behavior exhibited by browsers and other clients.
+
 - Issue #6378: idle.bat now runs with the appropriate Python version rather than
   the system default. Patch by Sridhar Ratnakumar.
 
-- 
cgit v0.12