Repository URL to install this package:
import sys
import unicodedata
import unittest
import urllib.parse
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'
# Each parse_qsl testcase is a two-tuple that contains
# a string with the query and a list with the expected result.
parse_qsl_test_cases = [
("", []),
("&", []),
("&&", []),
("=", [('', '')]),
("=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')]),
(b"", []),
(b"&", []),
(b"&&", []),
(b"=", [(b'', b'')]),
(b"=a", [(b'', b'a')]),
(b"a", [(b'a', b'')]),
(b"a=", [(b'a', b'')]),
(b"&a=b", [(b'a', b'b')]),
(b"a=a+b&b=b+c", [(b'a', b'a b'), (b'b', b'b c')]),
(b"a=1&a=2", [(b'a', b'1'), (b'a', b'2')]),
(";", []),
(";;", []),
(";a=b", [('a', 'b')]),
("a=a+b;b=b+c", [('a', 'a b'), ('b', 'b c')]),
("a=1;a=2", [('a', '1'), ('a', '2')]),
(b";", []),
(b";;", []),
(b";a=b", [(b'a', b'b')]),
(b"a=a+b;b=b+c", [(b'a', b'a b'), (b'b', b'b c')]),
(b"a=1;a=2", [(b'a', b'1'), (b'a', b'2')]),
]
# Each parse_qs testcase is a two-tuple that contains
# a string with the query and a dictionary with the expected result.
parse_qs_test_cases = [
("", {}),
("&", {}),
("&&", {}),
("=", {'': ['']}),
("=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', '2']}),
(b"", {}),
(b"&", {}),
(b"&&", {}),
(b"=", {b'': [b'']}),
(b"=a", {b'': [b'a']}),
(b"a", {b'a': [b'']}),
(b"a=", {b'a': [b'']}),
(b"&a=b", {b'a': [b'b']}),
(b"a=a+b&b=b+c", {b'a': [b'a b'], b'b': [b'b c']}),
(b"a=1&a=2", {b'a': [b'1', b'2']}),
(";", {}),
(";;", {}),
(";a=b", {'a': ['b']}),
("a=a+b;b=b+c", {'a': ['a b'], 'b': ['b c']}),
("a=1;a=2", {'a': ['1', '2']}),
(b";", {}),
(b";;", {}),
(b";a=b", {b'a': [b'b']}),
(b"a=a+b;b=b+c", {b'a': [b'a b'], b'b': [b'b c']}),
(b"a=1;a=2", {b'a': [b'1', b'2']}),
]
class UrlParseTestCase(unittest.TestCase):
def checkRoundtrips(self, url, parsed, split):
result = urllib.parse.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 = urllib.parse.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 = urllib.parse.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 = urllib.parse.urlsplit(url)
self.assertEqual(result, split)
t = (result.scheme, result.netloc, result.path,
result.query, result.fragment)
self.assertEqual(t, split)
result2 = urllib.parse.urlunsplit(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# check the fixpoint property of re-parsing the result of geturl()
result3 = urllib.parse.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 = urllib.parse.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 = urllib.parse.parse_qsl(orig, keep_blank_values=False)
self.assertEqual(result, expect_without_blanks,
"Error parsing %r" % orig)
def test_qs(self):
for orig, expect in parse_qs_test_cases:
result = urllib.parse.parse_qs(orig, keep_blank_values=True)
self.assertEqual(result, expect, "Error parsing %r" % orig)
expect_without_blanks = {v: expect[v]
for v in expect if len(expect[v][0])}
result = urllib.parse.parse_qs(orig, keep_blank_values=False)
self.assertEqual(result, expect_without_blanks,
"Error parsing %r" % orig)
def test_roundtrips(self):
str_cases = [
('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://git@github.com/user/project.git',
('git+ssh', 'git@github.com','/user/project.git',
'','',''),
('git+ssh', 'git@github.com','/user/project.git',
'', '')),
]
def _encode(t):
return (t[0].encode('ascii'),
tuple(x.encode('ascii') for x in t[1]),
tuple(x.encode('ascii') for x in t[2]))
bytes_cases = [_encode(x) for x in str_cases]
for url, parsed, split in str_cases + bytes_cases:
self.checkRoundtrips(url, parsed, split)
def test_http_roundtrips(self):
# urllib.parse.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!
str_cases = [
('://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')),
]
def _encode(t):
return (t[0].encode('ascii'),
tuple(x.encode('ascii') for x in t[1]),
tuple(x.encode('ascii') for x in t[2]))
bytes_cases = [_encode(x) for x in str_cases]
str_schemes = ('http', 'https')
bytes_schemes = (b'http', b'https')
str_tests = str_schemes, str_cases
bytes_tests = bytes_schemes, bytes_cases
for schemes, test_cases in (str_tests, bytes_tests):
for scheme in schemes:
for url, parsed, split in test_cases:
url = scheme + url
parsed = (scheme,) + parsed
split = (scheme,) + split
self.checkRoundtrips(url, parsed, split)
def checkJoin(self, base, relurl, expected):
str_components = (base, relurl, expected)
self.assertEqual(urllib.parse.urljoin(base, relurl), expected)
bytes_components = baseb, relurlb, expectedb = [
x.encode('ascii') for x in str_components]
self.assertEqual(urllib.parse.urljoin(baseb, relurlb), expectedb)
def test_unparse_parse(self):
str_cases = ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]
bytes_cases = [x.encode('ascii') for x in str_cases]
for u in str_cases + bytes_cases:
self.assertEqual(urllib.parse.urlunsplit(urllib.parse.urlsplit(u)), u)
self.assertEqual(urllib.parse.urlunparse(urllib.parse.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/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:')
# XXX: The following tests are no longer compatible with RFC3986
# 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')
def test_RFC2368(self):
# Issue 11467: path that starts with a number is not parsed correctly
self.assertEqual(urllib.parse.urlparse('mailto:1337@example.org'),
('mailto', '', '1337@example.org', '', '', ''))
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/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')
# XXX: The following tests are no longer compatible with RFC3986
# 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')
def test_RFC3986(self):
self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
self.checkJoin(RFC3986_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')
Loading ...