summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_urllib2net.py
diff options
context:
space:
mode:
authorJeremy Hylton <jeremy@alum.mit.edu>2004-08-07 17:40:50 (GMT)
committerJeremy Hylton <jeremy@alum.mit.edu>2004-08-07 17:40:50 (GMT)
commit5d9c3031c805ffb634688a6fcae0e7790688ce53 (patch)
tree43acb77a31e43498fe410844c30b83461fa66e4e /Lib/test/test_urllib2net.py
parent1baa2480215a2cd168e2fde10e640650c1807496 (diff)
downloadcpython-5d9c3031c805ffb634688a6fcae0e7790688ce53.zip
cpython-5d9c3031c805ffb634688a6fcae0e7790688ce53.tar.gz
cpython-5d9c3031c805ffb634688a6fcae0e7790688ce53.tar.bz2
Fix urllib2.urlopen() handling of chunked content encoding.
The change to use the newer httplib interface admitted the possibility that we'd get an HTTP/1.1 chunked response, but the code didn't handle it correctly. The raw socket object can't be pass to addinfourl(), because it would read the undecoded response. Instead, addinfourl() must call HTTPResponse.read(), which will handle the decoding. One extra wrinkle is that the HTTPReponse object can't be passed to addinfourl() either, because it doesn't implement readline() or readlines(). As a quick hack, use socket._fileobject(), which implements those methods on top of a read buffer. (suggested by mwh) Finally, add some tests based on test_urllibnet. Thanks to Andrew Sawyers for originally reporting the chunked problem.
Diffstat (limited to 'Lib/test/test_urllib2net.py')
-rw-r--r--Lib/test/test_urllib2net.py92
1 files changed, 92 insertions, 0 deletions
diff --git a/Lib/test/test_urllib2net.py b/Lib/test/test_urllib2net.py
new file mode 100644
index 0000000..3c23246
--- /dev/null
+++ b/Lib/test/test_urllib2net.py
@@ -0,0 +1,92 @@
+#!/usr/bin/env python
+
+import unittest
+from test import test_support
+
+import socket
+import urllib2
+import sys
+import os
+import mimetools
+
+class URLTimeoutTest(unittest.TestCase):
+
+ TIMEOUT = 10.0
+
+ def setUp(self):
+ socket.setdefaulttimeout(self.TIMEOUT)
+
+ def tearDown(self):
+ socket.setdefaulttimeout(None)
+
+ def testURLread(self):
+ f = urllib2.urlopen("http://www.python.org/")
+ x = f.read()
+
+class urlopenNetworkTests(unittest.TestCase):
+ """Tests urllib2.urlopen using the network.
+
+ These tests are not exhaustive. Assuming that testing using files does a
+ good job overall of some of the basic interface features. There are no
+ tests exercising the optional 'data' and 'proxies' arguments. No tests
+ for transparent redirection have been written.
+
+ setUp is not used for always constructing a connection to
+ http://www.python.org/ since there a few tests that don't use that address
+ and making a connection is expensive enough to warrant minimizing unneeded
+ connections.
+
+ """
+
+ def test_basic(self):
+ # Simple test expected to pass.
+ open_url = urllib2.urlopen("http://www.python.org/")
+ for attr in ("read", "close", "info", "geturl"):
+ self.assert_(hasattr(open_url, attr), "object returned from "
+ "urlopen lacks the %s attribute" % attr)
+ try:
+ self.assert_(open_url.read(), "calling 'read' failed")
+ finally:
+ open_url.close()
+
+ def test_info(self):
+ # Test 'info'.
+ open_url = urllib2.urlopen("http://www.python.org/")
+ try:
+ info_obj = open_url.info()
+ finally:
+ open_url.close()
+ self.assert_(isinstance(info_obj, mimetools.Message),
+ "object returned by 'info' is not an instance of "
+ "mimetools.Message")
+ self.assertEqual(info_obj.getsubtype(), "html")
+
+ def test_geturl(self):
+ # Make sure same URL as opened is returned by geturl.
+ URL = "http://www.python.org/"
+ open_url = urllib2.urlopen(URL)
+ try:
+ gotten_url = open_url.geturl()
+ finally:
+ open_url.close()
+ self.assertEqual(gotten_url, URL)
+
+ def test_bad_address(self):
+ # Make sure proper exception is raised when connecting to a bogus
+ # address.
+ self.assertRaises(IOError,
+ # SF patch 809915: In Sep 2003, VeriSign started
+ # highjacking invalid .com and .net addresses to
+ # boost traffic to their own site. This test
+ # started failing then. One hopes the .invalid
+ # domain will be spared to serve its defined
+ # purpose.
+ # urllib2.urlopen, "http://www.sadflkjsasadf.com/")
+ urllib2.urlopen, "http://www.python.invalid/")
+
+def test_main():
+ test_support.requires("network")
+ test_support.run_unittest(URLTimeoutTest, urlopenNetworkTests)
+
+if __name__ == "__main__":
+ test_main()