lib-python.2.7.test.test_urlparse.py Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of jython Show documentation
Show all versions of jython Show documentation
Jython is an implementation of the high-level, dynamic, object-oriented
language Python written in 100% Pure Java, and seamlessly integrated with
the Java platform. It thus allows you to run Python on any Java platform.
#! /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"
RFC3986_BASE = 'http://a/b/c/d;p?q'
SIMPLE_BASE = 'http://a/b/c/d'
# A list of test cases. Each test case is a two-tuple that contains
# a string with the query and a dictionary with the expected result.
parse_qsl_test_cases = [
("", []),
("&", []),
("&&", []),
("=", [('', '')]),
("=a", [('', 'a')]),
("a", [('a', '')]),
("a=", [('a', '')]),
("a=", [('a', '')]),
("&a=b", [('a', 'b')]),
("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]),
("a=1&a=2", [('a', '1'), ('a', '2')]),
]
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_qsl(self):
for orig, expect in parse_qsl_test_cases:
result = urlparse.parse_qsl(orig, keep_blank_values=True)
self.assertEqual(result, expect, "Error parsing %r" % orig)
expect_without_blanks = [v for v in expect if len(v[1])]
result = urlparse.parse_qsl(orig, keep_blank_values=False)
self.assertEqual(result, expect_without_blanks,
"Error parsing %r" % orig)
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',
'', '')),
('nfs://server/path/to/file.txt',
('nfs', 'server', '/path/to/file.txt', '', '', ''),
('nfs', 'server', '/path/to/file.txt', '', '')),
('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/',
'', '')),
('git+ssh://[email protected]/user/project.git',
('git+ssh', '[email protected]','/user/project.git',
'','',''),
('git+ssh', '[email protected]','/user/project.git',
'', ''))
]
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','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]:
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_RFC2368(self):
# Issue 11467: path that starts with a number is not parsed correctly
self.assertEqual(urlparse.urlparse('mailto:[email protected]'),
('mailto', '', '[email protected]', '', '', ''))
def test_RFC2396(self):
# cases from RFC 2396
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_RFC3986(self):
# Test cases from RFC3986
self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x')
self.checkJoin(RFC3986_BASE, 'g:h','g:h')
self.checkJoin(RFC3986_BASE, 'g','http://a/b/c/g')
self.checkJoin(RFC3986_BASE, './g','http://a/b/c/g')
self.checkJoin(RFC3986_BASE, 'g/','http://a/b/c/g/')
self.checkJoin(RFC3986_BASE, '/g','http://a/g')
self.checkJoin(RFC3986_BASE, '//g','http://g')
self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
self.checkJoin(RFC3986_BASE, 'g?y','http://a/b/c/g?y')
self.checkJoin(RFC3986_BASE, '#s','http://a/b/c/d;p?q#s')
self.checkJoin(RFC3986_BASE, 'g#s','http://a/b/c/g#s')
self.checkJoin(RFC3986_BASE, 'g?y#s','http://a/b/c/g?y#s')
self.checkJoin(RFC3986_BASE, ';x','http://a/b/c/;x')
self.checkJoin(RFC3986_BASE, 'g;x','http://a/b/c/g;x')
self.checkJoin(RFC3986_BASE, 'g;x?y#s','http://a/b/c/g;x?y#s')
self.checkJoin(RFC3986_BASE, '','http://a/b/c/d;p?q')
self.checkJoin(RFC3986_BASE, '.','http://a/b/c/')
self.checkJoin(RFC3986_BASE, './','http://a/b/c/')
self.checkJoin(RFC3986_BASE, '..','http://a/b/')
self.checkJoin(RFC3986_BASE, '../','http://a/b/')
self.checkJoin(RFC3986_BASE, '../g','http://a/b/g')
self.checkJoin(RFC3986_BASE, '../..','http://a/')
self.checkJoin(RFC3986_BASE, '../../','http://a/')
self.checkJoin(RFC3986_BASE, '../../g','http://a/g')
#Abnormal Examples
# The 'abnormal scenarios' are incompatible with RFC2986 parsing
# Tests are here for reference.
#self.checkJoin(RFC3986_BASE, '../../../g','http://a/g')
#self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g')
#self.checkJoin(RFC3986_BASE, '/./g','http://a/g')
#self.checkJoin(RFC3986_BASE, '/../g','http://a/g')
self.checkJoin(RFC3986_BASE, 'g.','http://a/b/c/g.')
self.checkJoin(RFC3986_BASE, '.g','http://a/b/c/.g')
self.checkJoin(RFC3986_BASE, 'g..','http://a/b/c/g..')
self.checkJoin(RFC3986_BASE, '..g','http://a/b/c/..g')
self.checkJoin(RFC3986_BASE, './../g','http://a/b/g')
self.checkJoin(RFC3986_BASE, './g/.','http://a/b/c/g/')
self.checkJoin(RFC3986_BASE, 'g/./h','http://a/b/c/g/h')
self.checkJoin(RFC3986_BASE, 'g/../h','http://a/b/c/h')
self.checkJoin(RFC3986_BASE, 'g;x=1/./y','http://a/b/c/g;x=1/y')
self.checkJoin(RFC3986_BASE, 'g;x=1/../y','http://a/b/c/y')
self.checkJoin(RFC3986_BASE, 'g?y/./x','http://a/b/c/g?y/./x')
self.checkJoin(RFC3986_BASE, 'g?y/../x','http://a/b/c/g?y/../x')
self.checkJoin(RFC3986_BASE, 'g#s/./x','http://a/b/c/g#s/./x')
self.checkJoin(RFC3986_BASE, 'g#s/../x','http://a/b/c/g#s/../x')
#self.checkJoin(RFC3986_BASE, 'http:g','http:g') # strict parser
self.checkJoin(RFC3986_BASE, 'http:g','http://a/b/c/g') # relaxed parser
# Test for issue9721
self.checkJoin('http://a/b/c/de', ';x','http://a/b/c/;x')
def test_urljoins(self):
self.checkJoin(SIMPLE_BASE, 'g:h','g:h')
self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g')
self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d')
self.checkJoin(SIMPLE_BASE, 'g','http://a/b/c/g')
self.checkJoin(SIMPLE_BASE, './g','http://a/b/c/g')
self.checkJoin(SIMPLE_BASE, 'g/','http://a/b/c/g/')
self.checkJoin(SIMPLE_BASE, '/g','http://a/g')
self.checkJoin(SIMPLE_BASE, '//g','http://g')
self.checkJoin(SIMPLE_BASE, '?y','http://a/b/c/d?y')
self.checkJoin(SIMPLE_BASE, 'g?y','http://a/b/c/g?y')
self.checkJoin(SIMPLE_BASE, 'g?y/./x','http://a/b/c/g?y/./x')
self.checkJoin(SIMPLE_BASE, '.','http://a/b/c/')
self.checkJoin(SIMPLE_BASE, './','http://a/b/c/')
self.checkJoin(SIMPLE_BASE, '..','http://a/b/')
self.checkJoin(SIMPLE_BASE, '../','http://a/b/')
self.checkJoin(SIMPLE_BASE, '../g','http://a/b/g')
self.checkJoin(SIMPLE_BASE, '../..','http://a/')
self.checkJoin(SIMPLE_BASE, '../../g','http://a/g')
self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g')
self.checkJoin(SIMPLE_BASE, './../g','http://a/b/g')
self.checkJoin(SIMPLE_BASE, './g/.','http://a/b/c/g/')
self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g')
self.checkJoin(SIMPLE_BASE, 'g/./h','http://a/b/c/g/h')
self.checkJoin(SIMPLE_BASE, 'g/../h','http://a/b/c/h')
self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g')
self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d')
self.checkJoin(SIMPLE_BASE, 'http:?y','http://a/b/c/d?y')
self.checkJoin(SIMPLE_BASE, 'http:g?y','http://a/b/c/g?y')
self.checkJoin(SIMPLE_BASE, 'http:g?y/./x','http://a/b/c/g?y/./x')
self.checkJoin('http:///', '..','http:///')
self.checkJoin('', 'http://a/b/c/g?y/./x','http://a/b/c/g?y/./x')
self.checkJoin('', 'http://a/./g', 'http://a/./g')
self.checkJoin('svn://pathtorepo/dir1','dir2','svn://pathtorepo/dir2')
self.checkJoin('svn+ssh://pathtorepo/dir1','dir2','svn+ssh://pathtorepo/dir2')
def test_RFC2732(self):
for url, hostname, port in [
('http://Test.python.org:5432/foo/', 'test.python.org', 5432),
('http://12.34.56.78:5432/foo/', '12.34.56.78', 5432),
('http://[::1]:5432/foo/', '::1', 5432),
('http://[dead:beef::1]:5432/foo/', 'dead:beef::1', 5432),
('http://[dead:beef::]:5432/foo/', 'dead:beef::', 5432),
('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]:5432/foo/',
'dead:beef:cafe:5417:affe:8fa3:deaf:feed', 5432),
('http://[::12.34.56.78]:5432/foo/', '::12.34.56.78', 5432),
('http://[::ffff:12.34.56.78]:5432/foo/',
'::ffff:12.34.56.78', 5432),
('http://Test.python.org/foo/', 'test.python.org', None),
('http://12.34.56.78/foo/', '12.34.56.78', None),
('http://[::1]/foo/', '::1', None),
('http://[dead:beef::1]/foo/', 'dead:beef::1', None),
('http://[dead:beef::]/foo/', 'dead:beef::', None),
('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]/foo/',
'dead:beef:cafe:5417:affe:8fa3:deaf:feed', None),
('http://[::12.34.56.78]/foo/', '::12.34.56.78', None),
('http://[::ffff:12.34.56.78]/foo/',
'::ffff:12.34.56.78', None),
]:
urlparsed = urlparse.urlparse(url)
self.assertEqual((urlparsed.hostname, urlparsed.port) , (hostname, port))
for invalid_url in [
'http://::12.34.56.78]/',
'http://[::1/foo/',
'ftp://[::1/foo/bad]/bad',
'http://[::1/foo/bad]/bad',
'http://[::ffff:12.34.56.78']:
self.assertRaises(ValueError, urlparse.urlparse, invalid_url)
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:[email protected]:080/doc/?query=yes#frag"
p = urlparse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "User:[email protected]: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)
# Addressing issue1698, which suggests Username can contain
# "@" characters. Though not RFC compliant, many ftp sites allow
# and request email addresses as usernames.
url = "http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = urlparse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "[email protected]:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "[email protected]")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Verify an illegal port of value greater than 65535 is set as None
url = "http://www.python.org:65536"
p = urlparse.urlsplit(url)
self.assertEqual(p.port, None)
def test_issue14072(self):
p1 = urlparse.urlsplit('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urlparse.urlsplit('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
# Assert for urlparse
p1 = urlparse.urlparse('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urlparse.urlparse('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
def test_telurl_params(self):
p1 = urlparse.urlparse('tel:123-4;phone-context=+1-650-516')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '123-4')
self.assertEqual(p1.params, 'phone-context=+1-650-516')
p1 = urlparse.urlparse('tel:+1-201-555-0123')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+1-201-555-0123')
self.assertEqual(p1.params, '')
p1 = urlparse.urlparse('tel:7042;phone-context=example.com')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '7042')
self.assertEqual(p1.params, 'phone-context=example.com')
p1 = urlparse.urlparse('tel:863-1234;phone-context=+1-914-555')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '863-1234')
self.assertEqual(p1.params, 'phone-context=+1-914-555')
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:[email protected];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_noslash(self):
# Issue 1637: http://foo.com?query is legal
self.assertEqual(urlparse.urlparse("http://example.com?blahblah=/foo"),
('http', 'example.com', '', '', 'blahblah=/foo', ''))
def test_anyscheme(self):
# Issue 7904: s3://foo.com/stuff has netloc "foo.com".
self.assertEqual(urlparse.urlparse("s3://foo.com/stuff"),
('s3','foo.com','/stuff','','',''))
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"),
('x-newscheme','foo.com','/stuff','','',''))
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query#fragment"),
('x-newscheme','foo.com','/stuff','','query','fragment'))
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query"),
('x-newscheme','foo.com','/stuff','','query',''))
def test_withoutscheme(self):
# Test urlparse without scheme
# Issue 754016: urlparse goes wrong with IP:port without scheme
# RFC 1808 specifies that netloc should start with //, urlparse expects
# the same, otherwise it classifies the portion of url as path.
self.assertEqual(urlparse.urlparse("path"),
('','','path','','',''))
self.assertEqual(urlparse.urlparse("//www.python.org:80"),
('','www.python.org:80','','','',''))
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
def test_portseparator(self):
# Issue 754016 makes changes for port separator ':' from scheme separator
self.assertEqual(urlparse.urlparse("path:80"),
('','','path:80','','',''))
self.assertEqual(urlparse.urlparse("http:"),('http','','','','',''))
self.assertEqual(urlparse.urlparse("https:"),('https','','','','',''))
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
def test_main():
test_support.run_unittest(UrlParseTestCase)
if __name__ == "__main__":
test_main()