mirrors/cpython
0
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2024-12-13 20:05:53 +08:00
Code Issues Packages Projects Releases Wiki Activity
3ff069ebc6
cpython/Lib/test/test_urlparse.py
Ezio Melotti e130a52d8a Remove duplication.
2011-10-19 10:58:56 +03:00

805 lines
39 KiB
Python
Raw Blame History

#! /usr/bin/env python3
from test import support
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'
# 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')]),
(b"", []),
(b"&", []),
(b"&&", []),
(b"=", [(b'', b'')]),
(b"=a", [(b'', b'a')]),
(b"a", [(b'a', b'')]),
(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')]),
]
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_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/../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(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/../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):
str_cases = [
('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),
]
def _encode(t):
return t[0].encode('ascii'), t[1].encode('ascii'), t[2]
bytes_cases = [_encode(x) for x in str_cases]
for url, hostname, port in str_cases + bytes_cases:
urlparsed = urllib.parse.urlparse(url)
self.assertEqual((urlparsed.hostname, urlparsed.port) , (hostname, port))
str_cases = [
'http://::12.34.56.78]/',
'http://[::1/foo/',
'ftp://[::1/foo/bad]/bad',
'http://[::1/foo/bad]/bad',
'http://[::ffff:12.34.56.78']
bytes_cases = [x.encode('ascii') for x in str_cases]
for invalid_url in str_cases + bytes_cases:
self.assertRaises(ValueError, urllib.parse.urlparse, invalid_url)
def test_urldefrag(self):
str_cases = [
('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', ''),
]
def _encode(t):
return type(t)(x.encode('ascii') for x in t)
bytes_cases = [_encode(x) for x in str_cases]
for url, defrag, frag in str_cases + bytes_cases:
result = urllib.parse.urldefrag(url)
self.assertEqual(result.geturl(), url)
self.assertEqual(result, (defrag, frag))
self.assertEqual(result.url, defrag)
self.assertEqual(result.fragment, frag)
def test_urlsplit_attributes(self):
url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
p = urllib.parse.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
# We handle this by ignoring the first 4 characters of the URL
self.assertEqual(p.geturl()[4:], url[4:])
url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
p = urllib.parse.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)
# Addressing issue1698, which suggests Username can contain
# "@" characters. Though not RFC compliant, many ftp sites allow
# and request email addresses as usernames.
url = "http://User@example.com:Pass@www.python.org:080/doc/?query=yes#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "User@example.com: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@example.com")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# And check them all again, only with bytes this time
url = b"HTTP://WWW.PYTHON.ORG/doc/#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"WWW.PYTHON.ORG")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, None)
self.assertEqual(p.geturl()[4:], url[4:])
url = b"http://User:Pass@www.python.org:080/doc/?query=yes#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"User:Pass@www.python.org:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"User")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
url = b"http://User@example.com:Pass@www.python.org:080/doc/?query=yes#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"User@example.com:Pass@www.python.org:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"User@example.com")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"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 = urllib.parse.urlsplit("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urllib.parse.urlparse("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
# Once again, repeat ourselves to test bytes
p = urllib.parse.urlsplit(b"http://www.example.net:foo")
self.assertEqual(p.netloc, b"www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urllib.parse.urlparse(b"http://www.example.net:foo")
self.assertEqual(p.netloc, b"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 = urllib.parse.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 = urllib.parse.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)
# You guessed it, repeating the test with bytes input
uri = b"sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15"
p = urllib.parse.urlsplit(uri)
self.assertEqual(p.netloc, b"")
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 = urllib.parse.urlparse(uri)
self.assertEqual(p.netloc, b"")
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_noslash(self):
# Issue 1637: http://foo.com?query is legal
self.assertEqual(urllib.parse.urlparse("http://example.com?blahblah=/foo"),
('http', 'example.com', '', '', 'blahblah=/foo', ''))
self.assertEqual(urllib.parse.urlparse(b"http://example.com?blahblah=/foo"),
(b'http', b'example.com', b'', b'', b'blahblah=/foo', b''))
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(urllib.parse.urlparse("path"),
('','','path','','',''))
self.assertEqual(urllib.parse.urlparse("//www.python.org:80"),
('','www.python.org:80','','','',''))
self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
# Repeat for bytes input
self.assertEqual(urllib.parse.urlparse(b"path"),
(b'',b'',b'path',b'',b'',b''))
self.assertEqual(urllib.parse.urlparse(b"//www.python.org:80"),
(b'',b'www.python.org:80',b'',b'',b'',b''))
self.assertEqual(urllib.parse.urlparse(b"http://www.python.org:80"),
(b'http',b'www.python.org:80',b'',b'',b'',b''))
def test_portseparator(self):
# Issue 754016 makes changes for port separator ':' from scheme separator
self.assertEqual(urllib.parse.urlparse("path:80"),
('','','path:80','','',''))
self.assertEqual(urllib.parse.urlparse("http:"),('http','','','','',''))
self.assertEqual(urllib.parse.urlparse("https:"),('https','','','','',''))
self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
# As usual, need to check bytes input as well
self.assertEqual(urllib.parse.urlparse(b"path:80"),
(b'',b'',b'path:80',b'',b'',b''))
self.assertEqual(urllib.parse.urlparse(b"http:"),(b'http',b'',b'',b'',b'',b''))
self.assertEqual(urllib.parse.urlparse(b"https:"),(b'https',b'',b'',b'',b'',b''))
self.assertEqual(urllib.parse.urlparse(b"http://www.python.org:80"),
(b'http',b'www.python.org:80',b'',b'',b'',b''))
def test_usingsys(self):
# Issue 3314: sys module is used in the error
self.assertRaises(TypeError, urllib.parse.urlencode, "foo")
def test_anyscheme(self):
# Issue 7904: s3://foo.com/stuff has netloc "foo.com".
self.assertEqual(urllib.parse.urlparse("s3://foo.com/stuff"),
('s3', 'foo.com', '/stuff', '', '', ''))
self.assertEqual(urllib.parse.urlparse("x-newscheme://foo.com/stuff"),
('x-newscheme', 'foo.com', '/stuff', '', '', ''))
# And for bytes...
self.assertEqual(urllib.parse.urlparse(b"s3://foo.com/stuff"),
(b's3', b'foo.com', b'/stuff', b'', b'', b''))
self.assertEqual(urllib.parse.urlparse(b"x-newscheme://foo.com/stuff"),
(b'x-newscheme', b'foo.com', b'/stuff', b'', b'', b''))
def test_mixed_types_rejected(self):
# Several functions that process either strings or ASCII encoded bytes
# accept multiple arguments. Check they reject mixed type input
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlparse("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlparse(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlsplit("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlsplit(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlunparse(( b"http", "www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlunparse(("http", b"www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlunsplit((b"http", "www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urlunsplit(("http", b"www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urljoin("http://python.org", b"http://python.org")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib.parse.urljoin(b"http://python.org", "http://python.org")
def _check_result_type(self, str_type):
num_args = len(str_type._fields)
bytes_type = str_type._encoded_counterpart
self.assertIs(bytes_type._decoded_counterpart, str_type)
str_args = ('',) * num_args
bytes_args = (b'',) * num_args
str_result = str_type(*str_args)
bytes_result = bytes_type(*bytes_args)
encoding = 'ascii'
errors = 'strict'
self.assertEqual(str_result, str_args)
self.assertEqual(bytes_result.decode(), str_args)
self.assertEqual(bytes_result.decode(), str_result)
self.assertEqual(bytes_result.decode(encoding), str_args)
self.assertEqual(bytes_result.decode(encoding), str_result)
self.assertEqual(bytes_result.decode(encoding, errors), str_args)
self.assertEqual(bytes_result.decode(encoding, errors), str_result)
self.assertEqual(bytes_result, bytes_args)
self.assertEqual(str_result.encode(), bytes_args)
self.assertEqual(str_result.encode(), bytes_result)
self.assertEqual(str_result.encode(encoding), bytes_args)
self.assertEqual(str_result.encode(encoding), bytes_result)
self.assertEqual(str_result.encode(encoding, errors), bytes_args)
self.assertEqual(str_result.encode(encoding, errors), bytes_result)
def test_result_pairs(self):
# Check encoding and decoding between result pairs
result_types = [
urllib.parse.DefragResult,
urllib.parse.SplitResult,
urllib.parse.ParseResult,
]
for result_type in result_types:
self._check_result_type(result_type)
def test_parse_qs_encoding(self):
result = urllib.parse.parse_qs("key=\u0141%E9", encoding="latin-1")
self.assertEqual(result, {'key': ['\u0141\xE9']})
result = urllib.parse.parse_qs("key=\u0141%C3%A9", encoding="utf-8")
self.assertEqual(result, {'key': ['\u0141\xE9']})
result = urllib.parse.parse_qs("key=\u0141%C3%A9", encoding="ascii")
self.assertEqual(result, {'key': ['\u0141\ufffd\ufffd']})
result = urllib.parse.parse_qs("key=\u0141%E9-", encoding="ascii")
self.assertEqual(result, {'key': ['\u0141\ufffd-']})
result = urllib.parse.parse_qs("key=\u0141%E9-", encoding="ascii",
errors="ignore")
self.assertEqual(result, {'key': ['\u0141-']})
def test_parse_qsl_encoding(self):
result = urllib.parse.parse_qsl("key=\u0141%E9", encoding="latin-1")
self.assertEqual(result, [('key', '\u0141\xE9')])
result = urllib.parse.parse_qsl("key=\u0141%C3%A9", encoding="utf-8")
self.assertEqual(result, [('key', '\u0141\xE9')])
result = urllib.parse.parse_qsl("key=\u0141%C3%A9", encoding="ascii")
self.assertEqual(result, [('key', '\u0141\ufffd\ufffd')])
result = urllib.parse.parse_qsl("key=\u0141%E9-", encoding="ascii")
self.assertEqual(result, [('key', '\u0141\ufffd-')])
result = urllib.parse.parse_qsl("key=\u0141%E9-", encoding="ascii",
errors="ignore")
self.assertEqual(result, [('key', '\u0141-')])
def test_splitnport(self):
# Normal cases are exercised by other tests; ensure that we also
# catch cases with no port specified. (testcase ensuring coverage)
result = urllib.parse.splitnport('parrot:88')
self.assertEqual(result, ('parrot', 88))
result = urllib.parse.splitnport('parrot')
self.assertEqual(result, ('parrot', -1))
result = urllib.parse.splitnport('parrot', 55)
self.assertEqual(result, ('parrot', 55))
result = urllib.parse.splitnport('parrot:')
self.assertEqual(result, ('parrot', None))
def test_splitquery(self):
# Normal cases are exercised by other tests; ensure that we also
# catch cases with no port specified (testcase ensuring coverage)
result = urllib.parse.splitquery('http://python.org/fake?foo=bar')
self.assertEqual(result, ('http://python.org/fake', 'foo=bar'))
result = urllib.parse.splitquery('http://python.org/fake?foo=bar?')
self.assertEqual(result, ('http://python.org/fake?foo=bar', ''))
result = urllib.parse.splitquery('http://python.org/fake')
self.assertEqual(result, ('http://python.org/fake', None))
def test_splitvalue(self):
# Normal cases are exercised by other tests; test pathological cases
# with no key/value pairs. (testcase ensuring coverage)
result = urllib.parse.splitvalue('foo=bar')
self.assertEqual(result, ('foo', 'bar'))
result = urllib.parse.splitvalue('foo=')
self.assertEqual(result, ('foo', ''))
result = urllib.parse.splitvalue('foobar')
self.assertEqual(result, ('foobar', None))
def test_to_bytes(self):
result = urllib.parse.to_bytes('http://www.python.org')
self.assertEqual(result, 'http://www.python.org')
self.assertRaises(UnicodeError, urllib.parse.to_bytes,
'http://www.python.org/medi\u00e6val')
def test_urlencode_sequences(self):
# Other tests incidentally urlencode things; test non-covered cases:
# Sequence and object values.
result = urllib.parse.urlencode({'a': [1, 2], 'b': (3, 4, 5)}, True)
self.assertEqual(result, 'a=1&a=2&b=3&b=4&b=5')
class Trivial:
def __str__(self):
return 'trivial'
result = urllib.parse.urlencode({'a': Trivial()}, True)
self.assertEqual(result, 'a=trivial')
def test_quote_from_bytes(self):
self.assertRaises(TypeError, urllib.parse.quote_from_bytes, 'foo')
result = urllib.parse.quote_from_bytes(b'archaeological arcana')
self.assertEqual(result, 'archaeological%20arcana')
result = urllib.parse.quote_from_bytes(b'')
self.assertEqual(result, '')
def test_unquote_to_bytes(self):
result = urllib.parse.unquote_to_bytes('abc%20def')
self.assertEqual(result, b'abc def')
result = urllib.parse.unquote_to_bytes('')
self.assertEqual(result, b'')
def test_quote_errors(self):
self.assertRaises(TypeError, urllib.parse.quote, b'foo',
encoding='utf-8')
self.assertRaises(TypeError, urllib.parse.quote, b'foo', errors='strict')
def test_main():
support.run_unittest(UrlParseTestCase)
if __name__ == "__main__":
test_main()
Reference in New Issue View Git Blame Copy Permalink