def test_redirect(self):
from_url = "http://example.com/a.html"
to_url = "http://example.com/b.html"
h = HTTPRedirectHandler()
o = h.parent = MockOpener()
# ordinary redirect behaviour
for code in 301, 302, 303, 307, "refresh":
for data in None, "blah\nblah\n":
method = getattr(h, "http_error_%s" % code)
req = Request(from_url, data)
req.add_header("Nonsense", "viking=withhold")
req.add_unredirected_header("Spam", "spam")
req.origin_req_host = "example.com" # XXX
try:
method(req, MockFile(), code, "Blah",
MockHeaders({"location": to_url}))
except urllib2.HTTPError:
# 307 in response to POST requires user OK
self.assert_(code == 307 and data is not None)
self.assert_(o.req.get_full_url() == to_url)
try:
self.assert_(o.req.get_method() == "GET")
except AttributeError:
self.assert_(not o.req.has_data())
self.assert_(o.req.headers["Nonsense"] == "viking=withhold")
self.assert_(not o.req.headers.has_key("Spam"))
self.assert_(not o.req.unredirected_hdrs.has_key("Spam"))
# loop detection
def redirect(h, req, url=to_url):
h.http_error_302(req, MockFile(), 302, "Blah",
MockHeaders({"location": url}))
# Note that the *original* request shares the same record of
# redirections with the sub-requests caused by the redirections.
# detect infinite loop redirect of a URL to itself
req = Request(from_url)
req.origin_req_host = "example.com"
count = 0
try:
while 1:
redirect(h, req, "http://example.com/")
count = count + 1
except urllib2.HTTPError:
# don't stop until max_repeats, because cookies may introduce state
self.assert_(count == HTTPRedirectHandler.max_repeats)
# detect endless non-repeating chain of redirects
req = Request(from_url)
req.origin_req_host = "example.com"
count = 0
try:
while 1:
redirect(h, req, "http://example.com/%d" % count)
count = count + 1
except urllib2.HTTPError:
self.assert_(count == HTTPRedirectHandler.max_redirections)
def test_redirect(self):
from_url = "http://example.com/a.html"
to_url = "http://example.com/b.html"
h = HTTPRedirectHandler()
o = h.parent = MockOpener()
# ordinary redirect behaviour
for code in 301, 302, 303, 307, "refresh":
for data in None, "blah\nblah\n":
method = getattr(h, "http_error_%s" % code)
req = Request(from_url, data)
req.add_header("Nonsense", "viking=withhold")
req.add_unredirected_header("Spam", "spam")
req.origin_req_host = "example.com" # XXX
try:
method(req, MockFile(), code, "Blah",
MockHeaders({"location": to_url}))
except urllib2.HTTPError:
# 307 in response to POST requires user OK
self.assert_(code == 307 and data is not None)
self.assert_(o.req.get_full_url() == to_url)
try:
self.assert_(o.req.get_method() == "GET")
except AttributeError:
self.assert_(not o.req.has_data())
self.assert_(o.req.headers["Nonsense"] == "viking=withhold")
self.assert_(not o.req.headers.has_key("Spam"))
self.assert_(not o.req.unredirected_hdrs.has_key("Spam"))
# loop detection
def redirect(h, req, url=to_url):
h.http_error_302(req, MockFile(), 302, "Blah",
MockHeaders({"location": url}))
# Note that the *original* request shares the same record of
# redirections with the sub-requests caused by the redirections.
# detect infinite loop redirect of a URL to itself
req = Request(from_url)
req.origin_req_host = "example.com"
count = 0
try:
while 1:
redirect(h, req, "http://example.com/")
count = count + 1
except urllib2.HTTPError:
# don't stop until max_repeats, because cookies may introduce state
self.assert_(count == HTTPRedirectHandler.max_repeats)
# detect endless non-repeating chain of redirects
req = Request(from_url)
req.origin_req_host = "example.com"
count = 0
try:
while 1:
redirect(h, req, "http://example.com/%d" % count)
count = count + 1
except urllib2.HTTPError:
self.assert_(count == HTTPRedirectHandler.max_redirections)
def test_referer(self):
h = HTTPRefererProcessor()
o = h.parent = MockOpener()
# normal case
url = "http://example.com/"
req = Request(url)
r = MockResponse(200, "OK", {}, "", url)
newr = h.http_response(req, r)
self.assert_(r is newr)
self.assert_(h.referer == url)
newreq = h.http_request(req)
self.assert_(req is newreq)
self.assert_(req.unredirected_hdrs["Referer"] == url)
# don't clobber existing Referer
ref = "http://set.by.user.com/"
req.add_unredirected_header("Referer", ref)
newreq = h.http_request(req)
self.assert_(req is newreq)
self.assert_(req.unredirected_hdrs["Referer"] == ref)
def test_referer(self):
h = HTTPRefererProcessor()
o = h.parent = MockOpener()
# normal case
url = "http://example.com/"
req = Request(url)
r = MockResponse(200, "OK", {}, "", url)
newr = h.http_response(req, r)
self.assert_(r is newr)
self.assert_(h.referer == url)
newreq = h.http_request(req)
self.assert_(req is newreq)
self.assert_(req.unredirected_hdrs["Referer"] == url)
# don't clobber existing Referer
ref = "http://set.by.user.com/"
req.add_unredirected_header("Referer", ref)
newreq = h.http_request(req)
self.assert_(req is newreq)
self.assert_(req.unredirected_hdrs["Referer"] == ref)
def test_http(self):
h = 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.assert_(r.geturl() == url)
self.assert_(http.host == "example.com")
self.assert_(http.level == 0)
self.assert_(http.method == method)
self.assert_(http.selector == "/")
http.req_headers.sort()
self.assert_(http.req_headers == [
("Connection", "close"),
("Foo", "bar"), ("Spam", "eggs")])
self.assert_(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_(not req.unredirected_hdrs.has_key("Content-length"))
self.assert_(not req.unredirected_hdrs.has_key("Content-type"))
else: # POST
# No longer true, due to workarouhd for buggy httplib
# in Python versions < 2.4:
#self.assert_(req.unredirected_hdrs["Content-length"] == "0")
self.assert_(req.unredirected_hdrs["Content-type"] ==
"application/x-www-form-urlencoded")
# XXX the details of Host could be better tested
self.assert_(req.unredirected_hdrs["Host"] == "example.com")
self.assert_(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.assert_(req.unredirected_hdrs["Content-length"] == "foo")
self.assert_(req.unredirected_hdrs["Content-type"] == "bar")
self.assert_(req.unredirected_hdrs["Host"] == "baz")
self.assert_(req.unredirected_hdrs["Spam"] == "foo")
def test_http(self):
h = 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.assert_(r.geturl() == url)
self.assert_(http.host == "example.com")
self.assert_(http.level == 0)
self.assert_(http.method == method)
self.assert_(http.selector == "/")
http.req_headers.sort()
self.assert_(
http.req_headers == [("Connection",
"close"), ("Foo", "bar"), ("Spam",
"eggs")])
self.assert_(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_(
not req.unredirected_hdrs.has_key("Content-length"))
self.assert_(not req.unredirected_hdrs.has_key("Content-type"))
else: # POST
# No longer true, due to workarouhd for buggy httplib
# in Python versions < 2.4:
#self.assert_(req.unredirected_hdrs["Content-length"] == "0")
self.assert_(req.unredirected_hdrs["Content-type"] ==
"application/x-www-form-urlencoded")
# XXX the details of Host could be better tested
self.assert_(req.unredirected_hdrs["Host"] == "example.com")
self.assert_(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.assert_(req.unredirected_hdrs["Content-length"] == "foo")
self.assert_(req.unredirected_hdrs["Content-type"] == "bar")
self.assert_(req.unredirected_hdrs["Host"] == "baz")
self.assert_(req.unredirected_hdrs["Spam"] == "foo")
