def test_http_doubleslash(self):
# Checks that the presence of an unnecessary double slash in a url doesn't break anything
# Previously, a double slash directly after the host could cause incorrect parsing of the url
h = urllib2.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_fixpath_in_weirdurls(self):
# Issue4493: urllib2 to supply '/' when to urls where path does not
# start with'/'
h = urllib2.AbstractHTTPHandler()
o = h.parent = MockOpener()
weird_url = 'http://www.python.org?getspam'
req = Request(weird_url)
newreq = h.do_request_(req)
self.assertEqual(newreq.get_host(),'www.python.org')
self.assertEqual(newreq.get_selector(),'/?getspam')
url_without_path = 'http://www.python.org'
req = Request(url_without_path)
newreq = h.do_request_(req)
self.assertEqual(newreq.get_host(),'www.python.org')
self.assertEqual(newreq.get_selector(),'')
def test_http(self):
class MockHTTPResponse:
def __init__(self, fp, msg, status, reason):
self.fp = fp
self.msg = msg
self.status = status
self.reason = reason
def read(self):
return ''
class MockHTTPClass:
def __init__(self):
self.req_headers = []
self.data = None
self.raise_on_endheaders = False
def __call__(self, host):
self.host = host
return self
def set_debuglevel(self, level):
self.level = level
def request(self, method, url, body=None, headers={}):
self.method = method
self.selector = url
self.req_headers += headers.items()
self.req_headers.sort()
if body:
self.data = body
if self.raise_on_endheaders:
import socket
raise socket.error()
def getresponse(self):
return MockHTTPResponse(MockFile(), {}, 200, "OK")
h = urllib2.AbstractHTTPHandler()
o = h.parent = MockOpener()
url = "http://example.com/"
for method, data in [("GET", None), ("POST", "blah")]:
req = Request(url, data, {"Foo": "bar"})
req.add_unredirected_header("Spam", "eggs")
http = MockHTTPClass()
r = h.do_open(http, req)
# result attributes
r.read
r.readline # wrapped MockFile methods
r.info
r.geturl # addinfourl methods
r.code, r.msg == 200, "OK" # added from MockHTTPClass.getreply()
hdrs = r.info()
hdrs.get
hdrs.has_key # r.info() gives dict from .getreply()
self.assertEqual(r.geturl(), url)
self.assertEqual(http.host, "example.com")
self.assertEqual(http.level, 0)
self.assertEqual(http.method, method)
self.assertEqual(http.selector, "/")
self.assertEqual(http.req_headers, [("Connection", "close"),
("Foo", "bar"),
("Spam", "eggs")])
self.assertEqual(http.data, data)
# check socket.error converted to URLError
http.raise_on_endheaders = True
self.assertRaises(urllib2.URLError, h.do_open, http, req)
# check adding of standard headers
o.addheaders = [("Spam", "eggs")]
for data in "", None: # POST, GET
req = Request("http://example.com/", data)
r = MockResponse(200, "OK", {}, "")
newreq = h.do_request_(req)
if data is None: # GET
self.assert_("Content-length" not in req.unredirected_hdrs)
self.assert_("Content-type" not in req.unredirected_hdrs)
else: # POST
self.assertEqual(req.unredirected_hdrs["Content-length"], "0")
self.assertEqual(req.unredirected_hdrs["Content-type"],
"application/x-www-form-urlencoded")
# XXX the details of Host could be better tested
self.assertEqual(req.unredirected_hdrs["Host"], "example.com")
self.assertEqual(req.unredirected_hdrs["Spam"], "eggs")
# don't clobber existing headers
req.add_unredirected_header("Content-length", "foo")
req.add_unredirected_header("Content-type", "bar")
req.add_unredirected_header("Host", "baz")
req.add_unredirected_header("Spam", "foo")
newreq = h.do_request_(req)
self.assertEqual(req.unredirected_hdrs["Content-length"], "foo")
self.assertEqual(req.unredirected_hdrs["Content-type"], "bar")
self.assertEqual(req.unredirected_hdrs["Host"], "baz")
self.assertEqual(req.unredirected_hdrs["Spam"], "foo")
def test_http(self):
h = urllib2.AbstractHTTPHandler()
o = h.parent = MockOpener()
url = "http://example.com/"
for method, data in [("GET", None), ("POST", "blah")]:
req = Request(url, data, {"Foo": "bar"})
req.timeout = None
req.add_unredirected_header("Spam", "eggs")
http = MockHTTPClass()
r = h.do_open(http, req)
# result attributes
r.read
r.readline # wrapped MockFile methods
r.info
r.geturl # addinfourl methods
r.code, r.msg == 200, "OK" # added from MockHTTPClass.getreply()
hdrs = r.info()
hdrs.get
hdrs.has_key # r.info() gives dict from .getreply()
self.assertEqual(r.geturl(), url)
self.assertEqual(http.host, "example.com")
self.assertEqual(http.level, 0)
self.assertEqual(http.method, method)
self.assertEqual(http.selector, "/")
self.assertEqual(http.req_headers, [("Connection", "close"),
("Foo", "bar"),
("Spam", "eggs")])
self.assertEqual(http.data, data)
# check socket.error converted to URLError
http.raise_on_endheaders = True
self.assertRaises(urllib2.URLError, h.do_open, http, req)
# check adding of standard headers
o.addheaders = [("Spam", "eggs")]
for data in "", None: # POST, GET
req = Request("http://example.com/", data)
r = MockResponse(200, "OK", {}, "")
newreq = h.do_request_(req)
if data is None: # GET
self.assert_("Content-length" not in req.unredirected_hdrs)
self.assert_("Content-type" not in req.unredirected_hdrs)
else: # POST
self.assertEqual(req.unredirected_hdrs["Content-length"], "0")
self.assertEqual(req.unredirected_hdrs["Content-type"],
"application/x-www-form-urlencoded")
# XXX the details of Host could be better tested
self.assertEqual(req.unredirected_hdrs["Host"], "example.com")
self.assertEqual(req.unredirected_hdrs["Spam"], "eggs")
# don't clobber existing headers
req.add_unredirected_header("Content-length", "foo")
req.add_unredirected_header("Content-type", "bar")
req.add_unredirected_header("Host", "baz")
req.add_unredirected_header("Spam", "foo")
newreq = h.do_request_(req)
self.assertEqual(req.unredirected_hdrs["Content-length"], "foo")
self.assertEqual(req.unredirected_hdrs["Content-type"], "bar")
self.assertEqual(req.unredirected_hdrs["Host"], "baz")
self.assertEqual(req.unredirected_hdrs["Spam"], "foo")
