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.

diff --git a/Lib/test/test_urllib2.py b/Lib/test/test_urllib2.py
index 30aa8f2ac026b3c46e676a4e424783472fab73ae..0ab6367fd51cc45cb782079f0a9b872740192994 100644 (file)
--- a/Lib/test/test_urllib2.py
+++ b/Lib/test/test_urllib2.py
@@ -770,6 +770,34 @@ class HandlerTests(unittest.TestCase):
             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()

diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
index c050ed85c295608d907cc797bf13e1d2fbb1c3d8..428be4acef67350f233c770c66b4897217914f12 100644 (file)
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -231,6 +231,9 @@ class Request:
         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 @@ class AbstractHTTPHandler(BaseHandler):
                 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):