Lib/test/test_urlparse.py

   1 #! /usr/bin/env python
   2
   3 from test import test_support
   4 import unittest
   5 import urlparse
   6
   7 RFC1808_BASE = "http://a/b/c/d;p?q#f"
   8 RFC2396_BASE = "http://a/b/c/d;p?q"
   9 RFC3986_BASE = 'http://a/b/c/d;p?q'
  10
  11 # A list of test cases.  Each test case is a a two-tuple that contains
  12 # a string with the query and a dictionary with the expected result.
  13
  14 parse_qsl_test_cases = [
  15     ("", []),
  16     ("&", []),
  17     ("&&", []),
  18     ("=", [('', '')]),
  19     ("=a", [('', 'a')]),
  20     ("a", [('a', '')]),
  21     ("a=", [('a', '')]),
  22     ("a=", [('a', '')]),
  23     ("&a=b", [('a', 'b')]),
  24     ("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]),
  25     ("a=1&a=2", [('a', '1'), ('a', '2')]),
  26 ]
  27
  28 class UrlParseTestCase(unittest.TestCase):
  29
  30     def checkRoundtrips(self, url, parsed, split):
  31         result = urlparse.urlparse(url)
  32         self.assertEqual(result, parsed)
  33         t = (result.scheme, result.netloc, result.path,
  34              result.params, result.query, result.fragment)
  35         self.assertEqual(t, parsed)
  36         # put it back together and it should be the same
  37         result2 = urlparse.urlunparse(result)
  38         self.assertEqual(result2, url)
  39         self.assertEqual(result2, result.geturl())
  40
  41         # the result of geturl() is a fixpoint; we can always parse it
  42         # again to get the same result:
  43         result3 = urlparse.urlparse(result.geturl())
  44         self.assertEqual(result3.geturl(), result.geturl())
  45         self.assertEqual(result3,          result)
  46         self.assertEqual(result3.scheme,   result.scheme)
  47         self.assertEqual(result3.netloc,   result.netloc)
  48         self.assertEqual(result3.path,     result.path)
  49         self.assertEqual(result3.params,   result.params)
  50         self.assertEqual(result3.query,    result.query)
  51         self.assertEqual(result3.fragment, result.fragment)
  52         self.assertEqual(result3.username, result.username)
  53         self.assertEqual(result3.password, result.password)
  54         self.assertEqual(result3.hostname, result.hostname)
  55         self.assertEqual(result3.port,     result.port)
  56
  57         # check the roundtrip using urlsplit() as well
  58         result = urlparse.urlsplit(url)
  59         self.assertEqual(result, split)
  60         t = (result.scheme, result.netloc, result.path,
  61              result.query, result.fragment)
  62         self.assertEqual(t, split)
  63         result2 = urlparse.urlunsplit(result)
  64         self.assertEqual(result2, url)
  65         self.assertEqual(result2, result.geturl())
  66
  67         # check the fixpoint property of re-parsing the result of geturl()
  68         result3 = urlparse.urlsplit(result.geturl())
  69         self.assertEqual(result3.geturl(), result.geturl())
  70         self.assertEqual(result3,          result)
  71         self.assertEqual(result3.scheme,   result.scheme)
  72         self.assertEqual(result3.netloc,   result.netloc)
  73         self.assertEqual(result3.path,     result.path)
  74         self.assertEqual(result3.query,    result.query)
  75         self.assertEqual(result3.fragment, result.fragment)
  76         self.assertEqual(result3.username, result.username)
  77         self.assertEqual(result3.password, result.password)
  78         self.assertEqual(result3.hostname, result.hostname)
  79         self.assertEqual(result3.port,     result.port)
  80
  81     def test_qsl(self):
  82         for orig, expect in parse_qsl_test_cases:
  83             result = urlparse.parse_qsl(orig, keep_blank_values=True)
  84             self.assertEqual(result, expect, "Error parsing %s" % repr(orig))
  85
  86     def test_roundtrips(self):
  87         testcases = [
  88             ('file:///tmp/junk.txt',
  89              ('file', '', '/tmp/junk.txt', '', '', ''),
  90              ('file', '', '/tmp/junk.txt', '', '')),
  91             ('imap://mail.python.org/mbox1',
  92              ('imap', 'mail.python.org', '/mbox1', '', '', ''),
  93              ('imap', 'mail.python.org', '/mbox1', '', '')),
  94             ('mms://wms.sys.hinet.net/cts/Drama/09006251100.asf',
  95              ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf',
  96               '', '', ''),
  97              ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf',
  98               '', '')),
  99             ('nfs://server/path/to/file.txt',
 100              ('nfs', 'server', '/path/to/file.txt',  '', '', ''),
 101              ('nfs', 'server', '/path/to/file.txt', '', '')),
 102             ('svn+ssh://svn.zope.org/repos/main/ZConfig/trunk/',
 103              ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/',
 104               '', '', ''),
 105              ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/',
 106               '', '')),
 107             ('git+ssh://git@github.com/user/project.git',
 108             ('git+ssh', 'git@github.com','/user/project.git',
 109              '','',''),
 110             ('git+ssh', 'git@github.com','/user/project.git',
 111              '', ''))
 112             ]
 113         for url, parsed, split in testcases:
 114             self.checkRoundtrips(url, parsed, split)
 115
 116     def test_http_roundtrips(self):
 117         # urlparse.urlsplit treats 'http:' as an optimized special case,
 118         # so we test both 'http:' and 'https:' in all the following.
 119         # Three cheers for white box knowledge!
 120         testcases = [
 121             ('://www.python.org',
 122              ('www.python.org', '', '', '', ''),
 123              ('www.python.org', '', '', '')),
 124             ('://www.python.org#abc',
 125              ('www.python.org', '', '', '', 'abc'),
 126              ('www.python.org', '', '', 'abc')),
 127             ('://www.python.org?q=abc',
 128              ('www.python.org', '', '', 'q=abc', ''),
 129              ('www.python.org', '', 'q=abc', '')),
 130             ('://www.python.org/#abc',
 131              ('www.python.org', '/', '', '', 'abc'),
 132              ('www.python.org', '/', '', 'abc')),
 133             ('://a/b/c/d;p?q#f',
 134              ('a', '/b/c/d', 'p', 'q', 'f'),
 135              ('a', '/b/c/d;p', 'q', 'f')),
 136             ]
 137         for scheme in ('http', 'https'):
 138             for url, parsed, split in testcases:
 139                 url = scheme + url
 140                 parsed = (scheme,) + parsed
 141                 split = (scheme,) + split
 142                 self.checkRoundtrips(url, parsed, split)
 143
 144     def checkJoin(self, base, relurl, expected):
 145         self.assertEqual(urlparse.urljoin(base, relurl), expected,
 146                          (base, relurl, expected))
 147
 148     def test_unparse_parse(self):
 149         for u in ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]:
 150             self.assertEqual(urlparse.urlunsplit(urlparse.urlsplit(u)), u)
 151             self.assertEqual(urlparse.urlunparse(urlparse.urlparse(u)), u)
 152
 153     def test_RFC1808(self):
 154         # "normal" cases from RFC 1808:
 155         self.checkJoin(RFC1808_BASE, 'g:h', 'g:h')
 156         self.checkJoin(RFC1808_BASE, 'g', 'http://a/b/c/g')
 157         self.checkJoin(RFC1808_BASE, './g', 'http://a/b/c/g')
 158         self.checkJoin(RFC1808_BASE, 'g/', 'http://a/b/c/g/')
 159         self.checkJoin(RFC1808_BASE, '/g', 'http://a/g')
 160         self.checkJoin(RFC1808_BASE, '//g', 'http://g')
 161         self.checkJoin(RFC1808_BASE, 'g?y', 'http://a/b/c/g?y')
 162         self.checkJoin(RFC1808_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x')
 163         self.checkJoin(RFC1808_BASE, '#s', 'http://a/b/c/d;p?q#s')
 164         self.checkJoin(RFC1808_BASE, 'g#s', 'http://a/b/c/g#s')
 165         self.checkJoin(RFC1808_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x')
 166         self.checkJoin(RFC1808_BASE, 'g?y#s', 'http://a/b/c/g?y#s')
 167         self.checkJoin(RFC1808_BASE, 'g;x', 'http://a/b/c/g;x')
 168         self.checkJoin(RFC1808_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s')
 169         self.checkJoin(RFC1808_BASE, '.', 'http://a/b/c/')
 170         self.checkJoin(RFC1808_BASE, './', 'http://a/b/c/')
 171         self.checkJoin(RFC1808_BASE, '..', 'http://a/b/')
 172         self.checkJoin(RFC1808_BASE, '../', 'http://a/b/')
 173         self.checkJoin(RFC1808_BASE, '../g', 'http://a/b/g')
 174         self.checkJoin(RFC1808_BASE, '../..', 'http://a/')
 175         self.checkJoin(RFC1808_BASE, '../../', 'http://a/')
 176         self.checkJoin(RFC1808_BASE, '../../g', 'http://a/g')
 177
 178         # "abnormal" cases from RFC 1808:
 179         self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f')
 180         self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g')
 181         self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g')
 182         self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g')
 183         self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g')
 184         self.checkJoin(RFC1808_BASE, 'g.', 'http://a/b/c/g.')
 185         self.checkJoin(RFC1808_BASE, '.g', 'http://a/b/c/.g')
 186         self.checkJoin(RFC1808_BASE, 'g..', 'http://a/b/c/g..')
 187         self.checkJoin(RFC1808_BASE, '..g', 'http://a/b/c/..g')
 188         self.checkJoin(RFC1808_BASE, './../g', 'http://a/b/g')
 189         self.checkJoin(RFC1808_BASE, './g/.', 'http://a/b/c/g/')
 190         self.checkJoin(RFC1808_BASE, 'g/./h', 'http://a/b/c/g/h')
 191         self.checkJoin(RFC1808_BASE, 'g/../h', 'http://a/b/c/h')
 192
 193         # RFC 1808 and RFC 1630 disagree on these (according to RFC 1808),
 194         # so we'll not actually run these tests (which expect 1808 behavior).
 195         #self.checkJoin(RFC1808_BASE, 'http:g', 'http:g')
 196         #self.checkJoin(RFC1808_BASE, 'http:', 'http:')
 197
 198     def test_RFC2396(self):
 199         # cases from RFC 2396
 200
 201
 202         self.checkJoin(RFC2396_BASE, 'g:h', 'g:h')
 203         self.checkJoin(RFC2396_BASE, 'g', 'http://a/b/c/g')
 204         self.checkJoin(RFC2396_BASE, './g', 'http://a/b/c/g')
 205         self.checkJoin(RFC2396_BASE, 'g/', 'http://a/b/c/g/')
 206         self.checkJoin(RFC2396_BASE, '/g', 'http://a/g')
 207         self.checkJoin(RFC2396_BASE, '//g', 'http://g')
 208         self.checkJoin(RFC2396_BASE, 'g?y', 'http://a/b/c/g?y')
 209         self.checkJoin(RFC2396_BASE, '#s', 'http://a/b/c/d;p?q#s')
 210         self.checkJoin(RFC2396_BASE, 'g#s', 'http://a/b/c/g#s')
 211         self.checkJoin(RFC2396_BASE, 'g?y#s', 'http://a/b/c/g?y#s')
 212         self.checkJoin(RFC2396_BASE, 'g;x', 'http://a/b/c/g;x')
 213         self.checkJoin(RFC2396_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s')
 214         self.checkJoin(RFC2396_BASE, '.', 'http://a/b/c/')
 215         self.checkJoin(RFC2396_BASE, './', 'http://a/b/c/')
 216         self.checkJoin(RFC2396_BASE, '..', 'http://a/b/')
 217         self.checkJoin(RFC2396_BASE, '../', 'http://a/b/')
 218         self.checkJoin(RFC2396_BASE, '../g', 'http://a/b/g')
 219         self.checkJoin(RFC2396_BASE, '../..', 'http://a/')
 220         self.checkJoin(RFC2396_BASE, '../../', 'http://a/')
 221         self.checkJoin(RFC2396_BASE, '../../g', 'http://a/g')
 222         self.checkJoin(RFC2396_BASE, '', RFC2396_BASE)
 223         self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g')
 224         self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g')
 225         self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g')
 226         self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g')
 227         self.checkJoin(RFC2396_BASE, 'g.', 'http://a/b/c/g.')
 228         self.checkJoin(RFC2396_BASE, '.g', 'http://a/b/c/.g')
 229         self.checkJoin(RFC2396_BASE, 'g..', 'http://a/b/c/g..')
 230         self.checkJoin(RFC2396_BASE, '..g', 'http://a/b/c/..g')
 231         self.checkJoin(RFC2396_BASE, './../g', 'http://a/b/g')
 232         self.checkJoin(RFC2396_BASE, './g/.', 'http://a/b/c/g/')
 233         self.checkJoin(RFC2396_BASE, 'g/./h', 'http://a/b/c/g/h')
 234         self.checkJoin(RFC2396_BASE, 'g/../h', 'http://a/b/c/h')
 235         self.checkJoin(RFC2396_BASE, 'g;x=1/./y', 'http://a/b/c/g;x=1/y')
 236         self.checkJoin(RFC2396_BASE, 'g;x=1/../y', 'http://a/b/c/y')
 237         self.checkJoin(RFC2396_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x')
 238         self.checkJoin(RFC2396_BASE, 'g?y/../x', 'http://a/b/c/g?y/../x')
 239         self.checkJoin(RFC2396_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x')
 240         self.checkJoin(RFC2396_BASE, 'g#s/../x', 'http://a/b/c/g#s/../x')
 241
 242     def test_RFC3986(self):
 243         # Test cases from RFC3986
 244         self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
 245         self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x')
 246         self.checkJoin(RFC3986_BASE, 'g:h','g:h')
 247         self.checkJoin(RFC3986_BASE, 'g','http://a/b/c/g')
 248         self.checkJoin(RFC3986_BASE, './g','http://a/b/c/g')
 249         self.checkJoin(RFC3986_BASE, 'g/','http://a/b/c/g/')
 250         self.checkJoin(RFC3986_BASE, '/g','http://a/g')
 251         self.checkJoin(RFC3986_BASE, '//g','http://g')
 252         self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
 253         self.checkJoin(RFC3986_BASE, 'g?y','http://a/b/c/g?y')
 254         self.checkJoin(RFC3986_BASE, '#s','http://a/b/c/d;p?q#s')
 255         self.checkJoin(RFC3986_BASE, 'g#s','http://a/b/c/g#s')
 256         self.checkJoin(RFC3986_BASE, 'g?y#s','http://a/b/c/g?y#s')
 257         self.checkJoin(RFC3986_BASE, ';x','http://a/b/c/;x')
 258         self.checkJoin(RFC3986_BASE, 'g;x','http://a/b/c/g;x')
 259         self.checkJoin(RFC3986_BASE, 'g;x?y#s','http://a/b/c/g;x?y#s')
 260         self.checkJoin(RFC3986_BASE, '','http://a/b/c/d;p?q')
 261         self.checkJoin(RFC3986_BASE, '.','http://a/b/c/')
 262         self.checkJoin(RFC3986_BASE, './','http://a/b/c/')
 263         self.checkJoin(RFC3986_BASE, '..','http://a/b/')
 264         self.checkJoin(RFC3986_BASE, '../','http://a/b/')
 265         self.checkJoin(RFC3986_BASE, '../g','http://a/b/g')
 266         self.checkJoin(RFC3986_BASE, '../..','http://a/')
 267         self.checkJoin(RFC3986_BASE, '../../','http://a/')
 268         self.checkJoin(RFC3986_BASE, '../../g','http://a/g')
 269
 270         #Abnormal Examples
 271
 272         # The 'abnormal scenarios' are incompatible with RFC2986 parsing
 273         # Tests are here for reference.
 274
 275         #self.checkJoin(RFC3986_BASE, '../../../g','http://a/g')
 276         #self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g')
 277         #self.checkJoin(RFC3986_BASE, '/./g','http://a/g')
 278         #self.checkJoin(RFC3986_BASE, '/../g','http://a/g')
 279
 280         self.checkJoin(RFC3986_BASE, 'g.','http://a/b/c/g.')
 281         self.checkJoin(RFC3986_BASE, '.g','http://a/b/c/.g')
 282         self.checkJoin(RFC3986_BASE, 'g..','http://a/b/c/g..')
 283         self.checkJoin(RFC3986_BASE, '..g','http://a/b/c/..g')
 284         self.checkJoin(RFC3986_BASE, './../g','http://a/b/g')
 285         self.checkJoin(RFC3986_BASE, './g/.','http://a/b/c/g/')
 286         self.checkJoin(RFC3986_BASE, 'g/./h','http://a/b/c/g/h')
 287         self.checkJoin(RFC3986_BASE, 'g/../h','http://a/b/c/h')
 288         self.checkJoin(RFC3986_BASE, 'g;x=1/./y','http://a/b/c/g;x=1/y')
 289         self.checkJoin(RFC3986_BASE, 'g;x=1/../y','http://a/b/c/y')
 290         self.checkJoin(RFC3986_BASE, 'g?y/./x','http://a/b/c/g?y/./x')
 291         self.checkJoin(RFC3986_BASE, 'g?y/../x','http://a/b/c/g?y/../x')
 292         self.checkJoin(RFC3986_BASE, 'g#s/./x','http://a/b/c/g#s/./x')
 293         self.checkJoin(RFC3986_BASE, 'g#s/../x','http://a/b/c/g#s/../x')
 294         #self.checkJoin(RFC3986_BASE, 'http:g','http:g') # strict parser
 295         self.checkJoin(RFC3986_BASE, 'http:g','http://a/b/c/g') # relaxed parser
 296
 297     def test_RFC2732(self):
 298         for url, hostname, port in [
 299             ('http://Test.python.org:5432/foo/', 'test.python.org', 5432),
 300             ('http://12.34.56.78:5432/foo/', '12.34.56.78', 5432),
 301             ('http://[::1]:5432/foo/', '::1', 5432),
 302             ('http://[dead:beef::1]:5432/foo/', 'dead:beef::1', 5432),
 303             ('http://[dead:beef::]:5432/foo/', 'dead:beef::', 5432),
 304             ('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]:5432/foo/',
 305              'dead:beef:cafe:5417:affe:8fa3:deaf:feed', 5432),
 306             ('http://[::12.34.56.78]:5432/foo/', '::12.34.56.78', 5432),
 307             ('http://[::ffff:12.34.56.78]:5432/foo/',
 308              '::ffff:12.34.56.78', 5432),
 309             ('http://Test.python.org/foo/', 'test.python.org', None),
 310             ('http://12.34.56.78/foo/', '12.34.56.78', None),
 311             ('http://[::1]/foo/', '::1', None),
 312             ('http://[dead:beef::1]/foo/', 'dead:beef::1', None),
 313             ('http://[dead:beef::]/foo/', 'dead:beef::', None),
 314             ('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]/foo/',
 315              'dead:beef:cafe:5417:affe:8fa3:deaf:feed', None),
 316             ('http://[::12.34.56.78]/foo/', '::12.34.56.78', None),
 317             ('http://[::ffff:12.34.56.78]/foo/',
 318              '::ffff:12.34.56.78', None),
 319             ]:
 320             urlparsed = urlparse.urlparse(url)
 321             self.assertEqual((urlparsed.hostname, urlparsed.port) , (hostname, port))
 322
 323         for invalid_url in [
 324                 'http://::12.34.56.78]/',
 325                 'http://[::1/foo/',
 326                 'ftp://[::1/foo/bad]/bad',
 327                 'http://[::1/foo/bad]/bad',
 328                 'http://[::ffff:12.34.56.78']:
 329             self.assertRaises(ValueError, urlparse.urlparse, invalid_url)
 330
 331     def test_urldefrag(self):
 332         for url, defrag, frag in [
 333             ('http://python.org#frag', 'http://python.org', 'frag'),
 334             ('http://python.org', 'http://python.org', ''),
 335             ('http://python.org/#frag', 'http://python.org/', 'frag'),
 336             ('http://python.org/', 'http://python.org/', ''),
 337             ('http://python.org/?q#frag', 'http://python.org/?q', 'frag'),
 338             ('http://python.org/?q', 'http://python.org/?q', ''),
 339             ('http://python.org/p#frag', 'http://python.org/p', 'frag'),
 340             ('http://python.org/p?q', 'http://python.org/p?q', ''),
 341             (RFC1808_BASE, 'http://a/b/c/d;p?q', 'f'),
 342             (RFC2396_BASE, 'http://a/b/c/d;p?q', ''),
 343             ]:
 344             self.assertEqual(urlparse.urldefrag(url), (defrag, frag))
 345
 346     def test_urlsplit_attributes(self):
 347         url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
 348         p = urlparse.urlsplit(url)
 349         self.assertEqual(p.scheme, "http")
 350         self.assertEqual(p.netloc, "WWW.PYTHON.ORG")
 351         self.assertEqual(p.path, "/doc/")
 352         self.assertEqual(p.query, "")
 353         self.assertEqual(p.fragment, "frag")
 354         self.assertEqual(p.username, None)
 355         self.assertEqual(p.password, None)
 356         self.assertEqual(p.hostname, "www.python.org")
 357         self.assertEqual(p.port, None)
 358         # geturl() won't return exactly the original URL in this case
 359         # since the scheme is always case-normalized
 360         #self.assertEqual(p.geturl(), url)
 361
 362         url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
 363         p = urlparse.urlsplit(url)
 364         self.assertEqual(p.scheme, "http")
 365         self.assertEqual(p.netloc, "User:Pass@www.python.org:080")
 366         self.assertEqual(p.path, "/doc/")
 367         self.assertEqual(p.query, "query=yes")
 368         self.assertEqual(p.fragment, "frag")
 369         self.assertEqual(p.username, "User")
 370         self.assertEqual(p.password, "Pass")
 371         self.assertEqual(p.hostname, "www.python.org")
 372         self.assertEqual(p.port, 80)
 373         self.assertEqual(p.geturl(), url)
 374
 375         # Addressing issue1698, which suggests Username can contain
 376         # "@" characters.  Though not RFC compliant, many ftp sites allow
 377         # and request email addresses as usernames.
 378
 379         url = "http://User@example.com:Pass@www.python.org:080/doc/?query=yes#frag"
 380         p = urlparse.urlsplit(url)
 381         self.assertEqual(p.scheme, "http")
 382         self.assertEqual(p.netloc, "User@example.com:Pass@www.python.org:080")
 383         self.assertEqual(p.path, "/doc/")
 384         self.assertEqual(p.query, "query=yes")
 385         self.assertEqual(p.fragment, "frag")
 386         self.assertEqual(p.username, "User@example.com")
 387         self.assertEqual(p.password, "Pass")
 388         self.assertEqual(p.hostname, "www.python.org")
 389         self.assertEqual(p.port, 80)
 390         self.assertEqual(p.geturl(), url)
 391
 392
 393     def test_attributes_bad_port(self):
 394         """Check handling of non-integer ports."""
 395         p = urlparse.urlsplit("http://www.example.net:foo")
 396         self.assertEqual(p.netloc, "www.example.net:foo")
 397         self.assertRaises(ValueError, lambda: p.port)
 398
 399         p = urlparse.urlparse("http://www.example.net:foo")
 400         self.assertEqual(p.netloc, "www.example.net:foo")
 401         self.assertRaises(ValueError, lambda: p.port)
 402
 403     def test_attributes_without_netloc(self):
 404         # This example is straight from RFC 3261.  It looks like it
 405         # should allow the username, hostname, and port to be filled
 406         # in, but doesn't.  Since it's a URI and doesn't use the
 407         # scheme://netloc syntax, the netloc and related attributes
 408         # should be left empty.
 409         uri = "sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15"
 410         p = urlparse.urlsplit(uri)
 411         self.assertEqual(p.netloc, "")
 412         self.assertEqual(p.username, None)
 413         self.assertEqual(p.password, None)
 414         self.assertEqual(p.hostname, None)
 415         self.assertEqual(p.port, None)
 416         self.assertEqual(p.geturl(), uri)
 417
 418         p = urlparse.urlparse(uri)
 419         self.assertEqual(p.netloc, "")
 420         self.assertEqual(p.username, None)
 421         self.assertEqual(p.password, None)
 422         self.assertEqual(p.hostname, None)
 423         self.assertEqual(p.port, None)
 424         self.assertEqual(p.geturl(), uri)
 425
 426     def test_caching(self):
 427         # Test case for bug #1313119
 428         uri = "http://example.com/doc/"
 429         unicode_uri = unicode(uri)
 430
 431         urlparse.urlparse(unicode_uri)
 432         p = urlparse.urlparse(uri)
 433         self.assertEqual(type(p.scheme), type(uri))
 434         self.assertEqual(type(p.hostname), type(uri))
 435         self.assertEqual(type(p.path), type(uri))
 436
 437     def test_noslash(self):
 438         # Issue 1637: http://foo.com?query is legal
 439         self.assertEqual(urlparse.urlparse("http://example.com?blahblah=/foo"),
 440                          ('http', 'example.com', '', '', 'blahblah=/foo', ''))
 441
 442     def test_anyscheme(self):
 443         # Issue 7904: s3://foo.com/stuff has netloc "foo.com".
 444         self.assertEqual(urlparse.urlparse("s3://foo.com/stuff"),
 445                          ('s3','foo.com','/stuff','','',''))
 446         self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"),
 447                          ('x-newscheme','foo.com','/stuff','','',''))
 448
 449
 450
 451 def test_main():
 452     test_support.run_unittest(UrlParseTestCase)
 453
 454 if __name__ == "__main__":
 455     test_main()