[Python-3000-checkins] r65711 - in python/branches/py3k/Lib: test/test_urllib2.py urllib/request.py

[facundo.batista]

Author: facundo.batista
Date: Sat Aug 16 16:44:32 2008
New Revision: 65711

Log:

Issue #2776: fixed small issue when handling an URL with double slash
after a 302 response in the case of not going through a proxy.


Modified:
python/branches/py3k/Lib/test/test_urllib2.py
python/branches/py3k/Lib/urllib/request.py

Modified: python/branches/py3k/Lib/test/test_urllib2.py
==============================================================================
--- python/branches/py3k/Lib/test/test_urllib2.py (original)
+++ python/branches/py3k/Lib/test/test_urllib2.py Sat Aug 16 16:44:32 2008
@@ -770,6 +770,34 @@
self.assertEqual(req.unredirected_hdrs["Host"], "baz")
self.assertEqual(req.unredirected_hdrs["Spam"], "foo")

+ def test_http_doubleslash(self):
+ # Checks the presence of any unnecessary double slash in url does not
+ # break anything. Previously, a double slash directly after the host
+ # could could cause incorrect parsing.
+ h = urllib.request.AbstractHTTPHandler()
+ o = h.parent = MockOpener()
+
+ data = ""
+ ds_urls = [
+ "http://example.com/foo/bar/baz.html",
+ "http://example.com//foo/bar/baz.html",
+ "http://example.com/foo//bar/baz.html",
+ "http://example.com/foo/bar//baz.html"
+ ]
+
+ for ds_url in ds_urls:
+ ds_req = Request(ds_url, data)
+
+ # Check whether host is determined correctly if there is no proxy
+ np_ds_req = h.do_request_(ds_req)
+ self.assertEqual(np_ds_req.unredirected_hdrs["Host"],"example.com")
+
+ # Check whether host is determined correctly if there is a proxy
+ ds_req.set_proxy("someproxy:3128",None)
+ p_ds_req = h.do_request_(ds_req)
+ self.assertEqual(p_ds_req.unredirected_hdrs["Host"],"example.com")
+
+
def test_errors(self):
h = urllib.request.HTTPErrorProcessor()
o = h.parent = MockOpener()

Modified: python/branches/py3k/Lib/urllib/request.py
==============================================================================
--- python/branches/py3k/Lib/urllib/request.py (original)
+++ python/branches/py3k/Lib/urllib/request.py Sat Aug 16 16:44:32 2008
@@ -231,6 +231,9 @@
self.host, self.type = host, type
self.__r_host = self.__original

+ def has_proxy(self):
+ return self.__r_host == self.__original
+
def get_origin_req_host(self):
return self.origin_req_host

@@ -1010,10 +1013,12 @@
request.add_unredirected_header(
'Content-length', '%d' % len(data))

- scheme, sel = splittype(request.get_selector())
- sel_host, sel_path = splithost(sel)
+ sel_host = host
+ if request.has_proxy():
+ scheme, sel = splittype(request.get_selector())
+ sel_host, sel_path = splithost(sel)
if not request.has_header('Host'):
- request.add_unredirected_header('Host', sel_host or host)
+ request.add_unredirected_header('Host', sel_host)
for name, value in self.parent.addheaders:
name = name.capitalize()
if not request.has_header(name):