#! /usr/bin/env python from test import test_support import unittest import urlparse RFC1808_BASE = "http://a/b/c/d;p?q#f" RFC2396_BASE = "http://a/b/c/d;p?q" class UrlParseTestCase(unittest.TestCase): def checkRoundtrips(self, url, parsed, split): result = urlparse.urlparse(url) self.assertEqual(result, parsed) t = (result.scheme, result.netloc, result.path, result.params, result.query, result.fragment) self.assertEqual(t, parsed) # put it back together and it should be the same result2 = urlparse.urlunparse(result) self.assertEqual(result2, url) self.assertEqual(result2, result.geturl()) # the result of geturl() is a fixpoint; we can always parse it # again to get the same result: result3 = urlparse.urlparse(result.geturl()) self.assertEqual(result3.geturl(), result.geturl()) self.assertEqual(result3, result) self.assertEqual(result3.scheme, result.scheme) self.assertEqual(result3.netloc, result.netloc) self.assertEqual(result3.path, result.path) self.assertEqual(result3.params, result.params) self.assertEqual(result3.query, result.query) self.assertEqual(result3.fragment, result.fragment) self.assertEqual(result3.username, result.username) self.assertEqual(result3.password, result.password) self.assertEqual(result3.hostname, result.hostname) self.assertEqual(result3.port, result.port) # check the roundtrip using urlsplit() as well result = urlparse.urlsplit(url) self.assertEqual(result, split) t = (result.scheme, result.netloc, result.path, result.query, result.fragment) self.assertEqual(t, split) result2 = urlparse.urlunsplit(result) self.assertEqual(result2, url) self.assertEqual(result2, result.geturl()) # check the fixpoint property of re-parsing the result of geturl() result3 = urlparse.urlsplit(result.geturl()) self.assertEqual(result3.geturl(), result.geturl()) self.assertEqual(result3, result) self.assertEqual(result3.scheme, result.scheme) self.assertEqual(result3.netloc, result.netloc) self.assertEqual(result3.path, result.path) self.assertEqual(result3.query, result.query) self.assertEqual(result3.fragment, result.fragment) self.assertEqual(result3.username, result.username) self.assertEqual(result3.password, result.password) self.assertEqual(result3.hostname, result.hostname) self.assertEqual(result3.port, result.port) def test_roundtrips(self): testcases = [ ('file:///tmp/junk.txt', ('file', '', '/tmp/junk.txt', '', '', ''), ('file', '', '/tmp/junk.txt', '', '')), ('imap://mail.python.org/mbox1', ('imap', 'mail.python.org', '/mbox1', '', '', ''), ('imap', 'mail.python.org', '/mbox1', '', '')), ('mms://wms.sys.hinet.net/cts/Drama/09006251100.asf', ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf', '', '', ''), ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf', '', '')), ('svn+ssh://svn.zope.org/repos/main/ZConfig/trunk/', ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/', '', '', ''), ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/', '', '')) ] for url, parsed, split in testcases: self.checkRoundtrips(url, parsed, split) def test_http_roundtrips(self): # urlparse.urlsplit treats 'http:' as an optimized special case, # so we test both 'http:' and 'https:' in all the following. # Three cheers for white box knowledge! testcases = [ ('://www.python.org', ('www.python.org', '', '', '', ''), ('www.python.org', '', '', '')), ('://www.python.org#abc', ('www.python.org', '', '', '', 'abc'), ('www.python.org', '', '', 'abc')), ('://www.python.org?q=abc', ('www.python.org', '', '', 'q=abc', ''), ('www.python.org', '', 'q=abc', '')), ('://www.python.org/#abc', ('www.python.org', '/', '', '', 'abc'), ('www.python.org', '/', '', 'abc')), ('://a/b/c/d;p?q#f', ('a', '/b/c/d', 'p', 'q', 'f'), ('a', '/b/c/d;p', 'q', 'f')), ] for scheme in ('http', 'https'): for url, parsed, split in testcases: url = scheme + url parsed = (scheme,) + parsed split = (scheme,) + split self.checkRoundtrips(url, parsed, split) def checkJoin(self, base, relurl, expected): self.assertEqual(urlparse.urljoin(base, relurl), expected, (base, relurl, expected)) def test_unparse_parse(self): for u in ['Python', './Python']: self.assertEqual(urlparse.urlunsplit(urlparse.urlsplit(u)), u) self.assertEqual(urlparse.urlunparse(urlparse.urlparse(u)), u) def test_RFC1808(self): # "normal" cases from RFC 1808: self.checkJoin(RFC1808_BASE, 'g:h', 'g:h') self.checkJoin(RFC1808_BASE, 'g', 'http://a/b/c/g') self.checkJoin(RFC1808_BASE, './g', 'http://a/b/c/g') self.checkJoin(RFC1808_BASE, 'g/', 'http://a/b/c/g/') self.checkJoin(RFC1808_BASE, '/g', 'http://a/g') self.checkJoin(RFC1808_BASE, '//g', 'http://g') self.checkJoin(RFC1808_BASE, 'g?y', 'http://a/b/c/g?y') self.checkJoin(RFC1808_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x') self.checkJoin(RFC1808_BASE, '#s', 'http://a/b/c/d;p?q#s') self.checkJoin(RFC1808_BASE, 'g#s', 'http://a/b/c/g#s') self.checkJoin(RFC1808_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x') self.checkJoin(RFC1808_BASE, 'g?y#s', 'http://a/b/c/g?y#s') self.checkJoin(RFC1808_BASE, 'g;x', 'http://a/b/c/g;x') self.checkJoin(RFC1808_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s') self.checkJoin(RFC1808_BASE, '.', 'http://a/b/c/') self.checkJoin(RFC1808_BASE, './', 'http://a/b/c/') self.checkJoin(RFC1808_BASE, '..', 'http://a/b/') self.checkJoin(RFC1808_BASE, '../', 'http://a/b/') self.checkJoin(RFC1808_BASE, '../g', 'http://a/b/g') self.checkJoin(RFC1808_BASE, '../..', 'http://a/') self.checkJoin(RFC1808_BASE, '../../', 'http://a/') self.checkJoin(RFC1808_BASE, '../../g', 'http://a/g') # "abnormal" cases from RFC 1808: self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f') self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g') self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g') self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g') self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g') self.checkJoin(RFC1808_BASE, 'g.', 'http://a/b/c/g.') self.checkJoin(RFC1808_BASE, '.g', 'http://a/b/c/.g') self.checkJoin(RFC1808_BASE, 'g..', 'http://a/b/c/g..') self.checkJoin(RFC1808_BASE, '..g', 'http://a/b/c/..g') self.checkJoin(RFC1808_BASE, './../g', 'http://a/b/g') self.checkJoin(RFC1808_BASE, './g/.', 'http://a/b/c/g/') self.checkJoin(RFC1808_BASE, 'g/./h', 'http://a/b/c/g/h') self.checkJoin(RFC1808_BASE, 'g/../h', 'http://a/b/c/h') # RFC 1808 and RFC 1630 disagree on these (according to RFC 1808), # so we'll not actually run these tests (which expect 1808 behavior). #self.checkJoin(RFC1808_BASE, 'http:g', 'http:g') #self.checkJoin(RFC1808_BASE, 'http:', 'http:') def test_RFC2396(self): # cases from RFC 2396 self.checkJoin(RFC2396_BASE, '?y', 'http://a/b/c/?y') self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x') self.checkJoin(RFC2396_BASE, 'g:h', 'g:h') self.checkJoin(RFC2396_BASE, 'g', 'http://a/b/c/g') self.checkJoin(RFC2396_BASE, './g', 'http://a/b/c/g') self.checkJoin(RFC2396_BASE, 'g/', 'http://a/b/c/g/') self.checkJoin(RFC2396_BASE, '/g', 'http://a/g') self.checkJoin(RFC2396_BASE, '//g', 'http://g') self.checkJoin(RFC2396_BASE, 'g?y', 'http://a/b/c/g?y') self.checkJoin(RFC2396_BASE, '#s', 'http://a/b/c/d;p?q#s') self.checkJoin(RFC2396_BASE, 'g#s', 'http://a/b/c/g#s') self.checkJoin(RFC2396_BASE, 'g?y#s', 'http://a/b/c/g?y#s') self.checkJoin(RFC2396_BASE, 'g;x', 'http://a/b/c/g;x') self.checkJoin(RFC2396_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s') self.checkJoin(RFC2396_BASE, '.', 'http://a/b/c/') self.checkJoin(RFC2396_BASE, './', 'http://a/b/c/') self.checkJoin(RFC2396_BASE, '..', 'http://a/b/') self.checkJoin(RFC2396_BASE, '../', 'http://a/b/') self.checkJoin(RFC2396_BASE, '../g', 'http://a/b/g') self.checkJoin(RFC2396_BASE, '../..', 'http://a/') self.checkJoin(RFC2396_BASE, '../../', 'http://a/') self.checkJoin(RFC2396_BASE, '../../g', 'http://a/g') self.checkJoin(RFC2396_BASE, '', RFC2396_BASE) self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g') self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g') self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g') self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g') self.checkJoin(RFC2396_BASE, 'g.', 'http://a/b/c/g.') self.checkJoin(RFC2396_BASE, '.g', 'http://a/b/c/.g') self.checkJoin(RFC2396_BASE, 'g..', 'http://a/b/c/g..') self.checkJoin(RFC2396_BASE, '..g', 'http://a/b/c/..g') self.checkJoin(RFC2396_BASE, './../g', 'http://a/b/g') self.checkJoin(RFC2396_BASE, './g/.', 'http://a/b/c/g/') self.checkJoin(RFC2396_BASE, 'g/./h', 'http://a/b/c/g/h') self.checkJoin(RFC2396_BASE, 'g/../h', 'http://a/b/c/h') self.checkJoin(RFC2396_BASE, 'g;x=1/./y', 'http://a/b/c/g;x=1/y') self.checkJoin(RFC2396_BASE, 'g;x=1/../y', 'http://a/b/c/y') self.checkJoin(RFC2396_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x') self.checkJoin(RFC2396_BASE, 'g?y/../x', 'http://a/b/c/g?y/../x') self.checkJoin(RFC2396_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x') self.checkJoin(RFC2396_BASE, 'g#s/../x', 'http://a/b/c/g#s/../x') def test_urldefrag(self): for url, defrag, frag in [ ('http://python.org#frag', 'http://python.org', 'frag'), ('http://python.org', 'http://python.org', ''), ('http://python.org/#frag', 'http://python.org/', 'frag'), ('http://python.org/', 'http://python.org/', ''), ('http://python.org/?q#frag', 'http://python.org/?q', 'frag'), ('http://python.org/?q', 'http://python.org/?q', ''), ('http://python.org/p#frag', 'http://python.org/p', 'frag'), ('http://python.org/p?q', 'http://python.org/p?q', ''), (RFC1808_BASE, 'http://a/b/c/d;p?q', 'f'), (RFC2396_BASE, 'http://a/b/c/d;p?q', ''), ]: self.assertEqual(urlparse.urldefrag(url), (defrag, frag)) def test_urlsplit_attributes(self): url = "HTTP://WWW.PYTHON.ORG/doc/#frag" p = urlparse.urlsplit(url) self.assertEqual(p.scheme, "http") self.assertEqual(p.netloc, "WWW.PYTHON.ORG") self.assertEqual(p.path, "/doc/") self.assertEqual(p.query, "") self.assertEqual(p.fragment, "frag") self.assertEqual(p.username, None) self.assertEqual(p.password, None) self.assertEqual(p.hostname, "www.python.org") self.assertEqual(p.port, None) # geturl() won't return exactly the original URL in this case # since the scheme is always case-normalized #self.assertEqual(p.geturl(), url) url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag" p = urlparse.urlsplit(url) self.assertEqual(p.scheme, "http") self.assertEqual(p.netloc, "User:Pass@www.python.org:080") self.assertEqual(p.path, "/doc/") self.assertEqual(p.query, "query=yes") self.assertEqual(p.fragment, "frag") self.assertEqual(p.username, "User") self.assertEqual(p.password, "Pass") self.assertEqual(p.hostname, "www.python.org") self.assertEqual(p.port, 80) self.assertEqual(p.geturl(), url) def test_attributes_bad_port(self): """Check handling of non-integer ports.""" p = urlparse.urlsplit("http://www.example.net:foo") self.assertEqual(p.netloc, "www.example.net:foo") self.assertRaises(ValueError, lambda: p.port) p = urlparse.urlparse("http://www.example.net:foo") self.assertEqual(p.netloc, "www.example.net:foo") self.assertRaises(ValueError, lambda: p.port) def test_attributes_without_netloc(self): # This example is straight from RFC 3261. It looks like it # should allow the username, hostname, and port to be filled # in, but doesn't. Since it's a URI and doesn't use the # scheme://netloc syntax, the netloc and related attributes # should be left empty. uri = "sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15" p = urlparse.urlsplit(uri) self.assertEqual(p.netloc, "") self.assertEqual(p.username, None) self.assertEqual(p.password, None) self.assertEqual(p.hostname, None) self.assertEqual(p.port, None) self.assertEqual(p.geturl(), uri) p = urlparse.urlparse(uri) self.assertEqual(p.netloc, "") self.assertEqual(p.username, None) self.assertEqual(p.password, None) self.assertEqual(p.hostname, None) self.assertEqual(p.port, None) self.assertEqual(p.geturl(), uri) def test_caching(self): # Test case for bug #1313119 uri = "http://example.com/doc/" unicode_uri = unicode(uri) urlparse.urlparse(unicode_uri) p = urlparse.urlparse(uri) self.assertEqual(type(p.scheme), type(uri)) self.assertEqual(type(p.hostname), type(uri)) self.assertEqual(type(p.path), type(uri)) def test_main(): test_support.run_unittest(UrlParseTestCase) if __name__ == "__main__": test_main()