#! /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 test_frags(self): for url, expected in [('http://www.python.org', ('http', 'www.python.org', '', '', '', '')), ('http://www.python.org#abc', ('http', 'www.python.org', '', '', '', 'abc')), ('http://www.python.org/#abc', ('http', 'www.python.org', '/', '', '', 'abc')), (RFC1808_BASE, ('http', 'a', '/b/c/d', 'p', 'q', 'f')), ('file:///tmp/junk.txt', ('file', '', '/tmp/junk.txt', '', '', '')), ]: result = urlparse.urlparse(url) self.assertEqual(result, expected) # put it back together and it should be the same result2 = urlparse.urlunparse(result) self.assertEqual(result2, url) def checkJoin(self, base, relurl, expected): self.assertEqual(urlparse.urljoin(base, relurl), expected) 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, '?y', 'http://a/b/c/d;p?y') 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, ';x', 'http://a/b/c/d;x') 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 ### urlparse.py as of v 1.32 fails on these two #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_main(): test_support.run_unittest(UrlParseTestCase) if __name__ == "__main__": test_main()