/usr/lib/python3/dist-packages/hyperlink/test/test_url.py is in python3-hyperlink 17.3.1-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 | # -*- coding: utf-8 -*-
# Copyright (c) Twisted Matrix Laboratories.
# See LICENSE for details.
from __future__ import unicode_literals
import socket
from .common import HyperlinkTestCase
from .. import URL, URLParseError
# automatically import the py27 windows implementation when appropriate
from .. import _url
from .._url import inet_pton, SCHEME_PORT_MAP, parse_host
unicode = type(u'')
BASIC_URL = "http://www.foo.com/a/nice/path/?zot=23&zut"
# Examples from RFC 3986 section 5.4, Reference Resolution Examples
relativeLinkBaseForRFC3986 = 'http://a/b/c/d;p?q'
relativeLinkTestsForRFC3986 = [
# "Normal"
# ('g:h', 'g:h'), # can't click on a scheme-having url without an abs path
('g', 'http://a/b/c/g'),
('./g', 'http://a/b/c/g'),
('g/', 'http://a/b/c/g/'),
('/g', 'http://a/g'),
('//g', 'http://g'),
('?y', 'http://a/b/c/d;p?y'),
('g?y', 'http://a/b/c/g?y'),
('#s', 'http://a/b/c/d;p?q#s'),
('g#s', 'http://a/b/c/g#s'),
('g?y#s', 'http://a/b/c/g?y#s'),
(';x', 'http://a/b/c/;x'),
('g;x', 'http://a/b/c/g;x'),
('g;x?y#s', 'http://a/b/c/g;x?y#s'),
('', 'http://a/b/c/d;p?q'),
('.', 'http://a/b/c/'),
('./', 'http://a/b/c/'),
('..', 'http://a/b/'),
('../', 'http://a/b/'),
('../g', 'http://a/b/g'),
('../..', 'http://a/'),
('../../', 'http://a/'),
('../../g', 'http://a/g'),
# Abnormal examples
# ".." cannot be used to change the authority component of a URI.
('../../../g', 'http://a/g'),
('../../../../g', 'http://a/g'),
# Only include "." and ".." when they are only part of a larger segment,
# not by themselves.
('/./g', 'http://a/g'),
('/../g', 'http://a/g'),
('g.', 'http://a/b/c/g.'),
('.g', 'http://a/b/c/.g'),
('g..', 'http://a/b/c/g..'),
('..g', 'http://a/b/c/..g'),
# Unnecessary or nonsensical forms of "." and "..".
('./../g', 'http://a/b/g'),
('./g/.', 'http://a/b/c/g/'),
('g/./h', 'http://a/b/c/g/h'),
('g/../h', 'http://a/b/c/h'),
('g;x=1/./y', 'http://a/b/c/g;x=1/y'),
('g;x=1/../y', 'http://a/b/c/y'),
# Separating the reference's query and fragment components from the path.
('g?y/./x', 'http://a/b/c/g?y/./x'),
('g?y/../x', 'http://a/b/c/g?y/../x'),
('g#s/./x', 'http://a/b/c/g#s/./x'),
('g#s/../x', 'http://a/b/c/g#s/../x')
]
ROUNDTRIP_TESTS = (
"http://localhost",
"http://localhost/",
"http://127.0.0.1/",
"http://[::127.0.0.1]/",
"http://[::1]/",
"http://localhost/foo",
"http://localhost/foo/",
"http://localhost/foo!!bar/",
"http://localhost/foo%20bar/",
"http://localhost/foo%2Fbar/",
"http://localhost/foo?n",
"http://localhost/foo?n=v",
"http://localhost/foo?n=/a/b",
"http://example.com/foo!@$bar?b!@z=123",
"http://localhost/asd?a=asd%20sdf/345",
"http://(%2525)/(%2525)?(%2525)&(%2525)=(%2525)#(%2525)",
"http://(%C3%A9)/(%C3%A9)?(%C3%A9)&(%C3%A9)=(%C3%A9)#(%C3%A9)",
"?sslrootcert=/Users/glyph/Downloads/rds-ca-2015-root.pem&sslmode=verify",
# from boltons.urlutils' tests
'http://googlewebsite.com/e-shops.aspx',
'http://example.com:8080/search?q=123&business=Nothing%20Special',
'http://hatnote.com:9000/?arg=1&arg=2&arg=3',
'https://xn--bcher-kva.ch',
'http://xn--ggbla1c4e.xn--ngbc5azd/',
'http://tools.ietf.org/html/rfc3986#section-3.4',
# 'http://wiki:pedia@hatnote.com',
'ftp://ftp.rfc-editor.org/in-notes/tar/RFCs0001-0500.tar.gz',
'http://[1080:0:0:0:8:800:200C:417A]/index.html',
'ssh://192.0.2.16:2222/',
'https://[::101.45.75.219]:80/?hi=bye',
'ldap://[::192.9.5.5]/dc=example,dc=com??sub?(sn=Jensen)',
'mailto:me@example.com?to=me@example.com&body=hi%20http://wikipedia.org',
'news:alt.rec.motorcycle',
'tel:+1-800-867-5309',
'urn:oasis:member:A00024:x',
('magnet:?xt=urn:btih:1a42b9e04e122b97a5254e3df77ab3c4b7da725f&dn=Puppy%'
'20Linux%20precise-5.7.1.iso&tr=udp://tracker.openbittorrent.com:80&'
'tr=udp://tracker.publicbt.com:80&tr=udp://tracker.istole.it:6969&'
'tr=udp://tracker.ccc.de:80&tr=udp://open.demonii.com:1337'),
# percent-encoded delimiters in percent-encodable fields
'https://%3A@example.com/', # colon in username
'https://%40@example.com/', # at sign in username
'https://%2f@example.com/', # slash in username
'https://a:%3a@example.com/', # colon in password
'https://a:%40@example.com/', # at sign in password
'https://a:%2f@example.com/', # slash in password
'https://a:%3f@example.com/', # question mark in password
'https://example.com/%2F/', # slash in path
'https://example.com/%3F/', # question mark in path
'https://example.com/%23/', # hash in path
'https://example.com/?%23=b', # hash in query param name
'https://example.com/?%3D=b', # equals in query param name
'https://example.com/?%26=b', # ampersand in query param name
'https://example.com/?a=%23', # hash in query param value
'https://example.com/?a=%26', # ampersand in query param value
'https://example.com/?a=%3D', # equals in query param value
# double-encoded percent sign in all percent-encodable positions:
"http://(%2525):(%2525)@example.com/(%2525)/?(%2525)=(%2525)#(%2525)",
# colon in first part of schemeless relative url
'first_seg_rel_path__colon%3Anotok/second_seg__colon%3Aok',
)
class TestURL(HyperlinkTestCase):
"""
Tests for L{URL}.
"""
def assertUnicoded(self, u):
"""
The given L{URL}'s components should be L{unicode}.
@param u: The L{URL} to test.
"""
self.assertTrue(isinstance(u.scheme, unicode) or u.scheme is None,
repr(u))
self.assertTrue(isinstance(u.host, unicode) or u.host is None,
repr(u))
for seg in u.path:
self.assertEqual(type(seg), unicode, repr(u))
for (k, v) in u.query:
self.assertEqual(type(seg), unicode, repr(u))
self.assertTrue(v is None or isinstance(v, unicode), repr(u))
self.assertEqual(type(u.fragment), unicode, repr(u))
def assertURL(self, u, scheme, host, path, query,
fragment, port, userinfo=''):
"""
The given L{URL} should have the given components.
@param u: The actual L{URL} to examine.
@param scheme: The expected scheme.
@param host: The expected host.
@param path: The expected path.
@param query: The expected query.
@param fragment: The expected fragment.
@param port: The expected port.
@param userinfo: The expected userinfo.
"""
actual = (u.scheme, u.host, u.path, u.query,
u.fragment, u.port, u.userinfo)
expected = (scheme, host, tuple(path), tuple(query),
fragment, port, u.userinfo)
self.assertEqual(actual, expected)
def test_initDefaults(self):
"""
L{URL} should have appropriate default values.
"""
def check(u):
self.assertUnicoded(u)
self.assertURL(u, 'http', '', [], [], '', 80, '')
check(URL('http', ''))
check(URL('http', '', [], []))
check(URL('http', '', [], [], ''))
def test_init(self):
"""
L{URL} should accept L{unicode} parameters.
"""
u = URL('s', 'h', ['p'], [('k', 'v'), ('k', None)], 'f')
self.assertUnicoded(u)
self.assertURL(u, 's', 'h', ['p'], [('k', 'v'), ('k', None)],
'f', None)
self.assertURL(URL('http', '\xe0', ['\xe9'],
[('\u03bb', '\u03c0')], '\u22a5'),
'http', '\xe0', ['\xe9'],
[('\u03bb', '\u03c0')], '\u22a5', 80)
def test_initPercent(self):
"""
L{URL} should accept (and not interpret) percent characters.
"""
u = URL('s', '%68', ['%70'], [('%6B', '%76'), ('%6B', None)],
'%66')
self.assertUnicoded(u)
self.assertURL(u,
's', '%68', ['%70'],
[('%6B', '%76'), ('%6B', None)],
'%66', None)
def test_repr(self):
"""
L{URL.__repr__} will display the canonical form of the URL, wrapped in
a L{URL.from_text} invocation, so that it is C{eval}-able but still easy
to read.
"""
self.assertEqual(
repr(URL(scheme='http', host='foo', path=['bar'],
query=[('baz', None), ('k', 'v')],
fragment='frob')),
"URL.from_text(%s)" % (repr(u"http://foo/bar?baz&k=v#frob"),)
)
def test_from_text(self):
"""
Round-tripping L{URL.from_text} with C{str} results in an equivalent
URL.
"""
urlpath = URL.from_text(BASIC_URL)
self.assertEqual(BASIC_URL, urlpath.to_text())
def test_roundtrip(self):
"""
L{URL.to_text} should invert L{URL.from_text}.
"""
for test in ROUNDTRIP_TESTS:
result = URL.from_text(test).to_text(with_password=True)
self.assertEqual(test, result)
def test_roundtrip_double_iri(self):
for test in ROUNDTRIP_TESTS:
url = URL.from_text(test)
iri = url.to_iri()
double_iri = iri.to_iri()
assert iri == double_iri
iri_text = iri.to_text(with_password=True)
double_iri_text = double_iri.to_text(with_password=True)
assert iri_text == double_iri_text
return
def test_equality(self):
"""
Two URLs decoded using L{URL.from_text} will be equal (C{==}) if they
decoded same URL string, and unequal (C{!=}) if they decoded different
strings.
"""
urlpath = URL.from_text(BASIC_URL)
self.assertEqual(urlpath, URL.from_text(BASIC_URL))
self.assertNotEqual(
urlpath,
URL.from_text('ftp://www.anotherinvaliddomain.com/'
'foo/bar/baz/?zot=21&zut')
)
def test_fragmentEquality(self):
"""
An URL created with the empty string for a fragment compares equal
to an URL created with an unspecified fragment.
"""
self.assertEqual(URL(fragment=''), URL())
self.assertEqual(URL.from_text(u"http://localhost/#"),
URL.from_text(u"http://localhost/"))
def test_child(self):
"""
L{URL.child} appends a new path segment, but does not affect the query
or fragment.
"""
urlpath = URL.from_text(BASIC_URL)
self.assertEqual("http://www.foo.com/a/nice/path/gong?zot=23&zut",
urlpath.child('gong').to_text())
self.assertEqual("http://www.foo.com/a/nice/path/gong%2F?zot=23&zut",
urlpath.child('gong/').to_text())
self.assertEqual(
"http://www.foo.com/a/nice/path/gong%2Fdouble?zot=23&zut",
urlpath.child('gong/double').to_text()
)
self.assertEqual(
"http://www.foo.com/a/nice/path/gong%2Fdouble%2F?zot=23&zut",
urlpath.child('gong/double/').to_text()
)
def test_multiChild(self):
"""
L{URL.child} receives multiple segments as C{*args} and appends each in
turn.
"""
url = URL.from_text('http://example.com/a/b')
self.assertEqual(url.child('c', 'd', 'e').to_text(),
'http://example.com/a/b/c/d/e')
def test_childInitRoot(self):
"""
L{URL.child} of a L{URL} without a path produces a L{URL} with a single
path segment.
"""
childURL = URL(host=u"www.foo.com").child(u"c")
self.assertTrue(childURL.rooted)
self.assertEqual("http://www.foo.com/c", childURL.to_text())
def test_sibling(self):
"""
L{URL.sibling} of a L{URL} replaces the last path segment, but does not
affect the query or fragment.
"""
urlpath = URL.from_text(BASIC_URL)
self.assertEqual(
"http://www.foo.com/a/nice/path/sister?zot=23&zut",
urlpath.sibling('sister').to_text()
)
# Use an url without trailing '/' to check child removal.
url_text = "http://www.foo.com/a/nice/path?zot=23&zut"
urlpath = URL.from_text(url_text)
self.assertEqual(
"http://www.foo.com/a/nice/sister?zot=23&zut",
urlpath.sibling('sister').to_text()
)
def test_click(self):
"""
L{URL.click} interprets the given string as a relative URI-reference
and returns a new L{URL} interpreting C{self} as the base absolute URI.
"""
urlpath = URL.from_text(BASIC_URL)
# A null uri should be valid (return here).
self.assertEqual("http://www.foo.com/a/nice/path/?zot=23&zut",
urlpath.click("").to_text())
# A simple relative path remove the query.
self.assertEqual("http://www.foo.com/a/nice/path/click",
urlpath.click("click").to_text())
# An absolute path replace path and query.
self.assertEqual("http://www.foo.com/click",
urlpath.click("/click").to_text())
# Replace just the query.
self.assertEqual("http://www.foo.com/a/nice/path/?burp",
urlpath.click("?burp").to_text())
# One full url to another should not generate '//' between authority.
# and path
self.assertTrue("//foobar" not in
urlpath.click('http://www.foo.com/foobar').to_text())
# From a url with no query clicking a url with a query, the query
# should be handled properly.
u = URL.from_text('http://www.foo.com/me/noquery')
self.assertEqual('http://www.foo.com/me/17?spam=158',
u.click('/me/17?spam=158').to_text())
# Check that everything from the path onward is removed when the click
# link has no path.
u = URL.from_text('http://localhost/foo?abc=def')
self.assertEqual(u.click('http://www.python.org').to_text(),
'http://www.python.org')
# https://twistedmatrix.com/trac/ticket/8184
u = URL.from_text('http://hatnote.com/a/b/../c/./d/e/..')
res = 'http://hatnote.com/a/c/d/'
self.assertEqual(u.click('').to_text(), res)
# test click default arg is same as empty string above
self.assertEqual(u.click().to_text(), res)
# test click on a URL instance
u = URL.fromText('http://localhost/foo/?abc=def')
u2 = URL.from_text('bar')
u3 = u.click(u2)
self.assertEqual(u3.to_text(), 'http://localhost/foo/bar')
def test_clickRFC3986(self):
"""
L{URL.click} should correctly resolve the examples in RFC 3986.
"""
base = URL.from_text(relativeLinkBaseForRFC3986)
for (ref, expected) in relativeLinkTestsForRFC3986:
self.assertEqual(base.click(ref).to_text(), expected)
def test_clickSchemeRelPath(self):
"""
L{URL.click} should not accept schemes with relative paths.
"""
base = URL.from_text(relativeLinkBaseForRFC3986)
self.assertRaises(NotImplementedError, base.click, 'g:h')
self.assertRaises(NotImplementedError, base.click, 'http:h')
def test_cloneUnchanged(self):
"""
Verify that L{URL.replace} doesn't change any of the arguments it
is passed.
"""
urlpath = URL.from_text('https://x:1/y?z=1#A')
self.assertEqual(urlpath.replace(urlpath.scheme,
urlpath.host,
urlpath.path,
urlpath.query,
urlpath.fragment,
urlpath.port),
urlpath)
self.assertEqual(urlpath.replace(), urlpath)
def test_clickCollapse(self):
"""
L{URL.click} collapses C{.} and C{..} according to RFC 3986 section
5.2.4.
"""
tests = [
['http://localhost/', '.', 'http://localhost/'],
['http://localhost/', '..', 'http://localhost/'],
['http://localhost/a/b/c', '.', 'http://localhost/a/b/'],
['http://localhost/a/b/c', '..', 'http://localhost/a/'],
['http://localhost/a/b/c', './d/e', 'http://localhost/a/b/d/e'],
['http://localhost/a/b/c', '../d/e', 'http://localhost/a/d/e'],
['http://localhost/a/b/c', '/./d/e', 'http://localhost/d/e'],
['http://localhost/a/b/c', '/../d/e', 'http://localhost/d/e'],
['http://localhost/a/b/c/', '../../d/e/',
'http://localhost/a/d/e/'],
['http://localhost/a/./c', '../d/e', 'http://localhost/d/e'],
['http://localhost/a/./c/', '../d/e', 'http://localhost/a/d/e'],
['http://localhost/a/b/c/d', './e/../f/../g',
'http://localhost/a/b/c/g'],
['http://localhost/a/b/c', 'd//e', 'http://localhost/a/b/d//e'],
]
for start, click, expected in tests:
actual = URL.from_text(start).click(click).to_text()
self.assertEqual(
actual,
expected,
"{start}.click({click}) => {actual} not {expected}".format(
start=start,
click=repr(click),
actual=actual,
expected=expected,
)
)
def test_queryAdd(self):
"""
L{URL.add} adds query parameters.
"""
self.assertEqual(
"http://www.foo.com/a/nice/path/?foo=bar",
URL.from_text("http://www.foo.com/a/nice/path/")
.add(u"foo", u"bar").to_text())
self.assertEqual(
"http://www.foo.com/?foo=bar",
URL(host=u"www.foo.com").add(u"foo", u"bar")
.to_text())
urlpath = URL.from_text(BASIC_URL)
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot=23&zut&burp",
urlpath.add(u"burp").to_text())
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot=23&zut&burp=xxx",
urlpath.add(u"burp", u"xxx").to_text())
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot=23&zut&burp=xxx&zing",
urlpath.add(u"burp", u"xxx").add(u"zing").to_text())
# Note the inversion!
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot=23&zut&zing&burp=xxx",
urlpath.add(u"zing").add(u"burp", u"xxx").to_text())
# Note the two values for the same name.
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot=23&zut&burp=xxx&zot=32",
urlpath.add(u"burp", u"xxx").add(u"zot", '32')
.to_text())
def test_querySet(self):
"""
L{URL.set} replaces query parameters by name.
"""
urlpath = URL.from_text(BASIC_URL)
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot=32&zut",
urlpath.set(u"zot", '32').to_text())
# Replace name without value with name/value and vice-versa.
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot&zut=itworked",
urlpath.set(u"zot").set(u"zut", u"itworked").to_text()
)
# Q: what happens when the query has two values and we replace?
# A: we replace both values with a single one
self.assertEqual(
"http://www.foo.com/a/nice/path/?zot=32&zut",
urlpath.add(u"zot", u"xxx").set(u"zot", '32').to_text()
)
def test_queryRemove(self):
"""
L{URL.remove} removes all instances of a query parameter.
"""
url = URL.from_text(u"https://example.com/a/b/?foo=1&bar=2&foo=3")
self.assertEqual(
url.remove(u"foo"),
URL.from_text(u"https://example.com/a/b/?bar=2")
)
def test_parseEqualSignInParamValue(self):
"""
Every C{=}-sign after the first in a query parameter is simply included
in the value of the parameter.
"""
u = URL.from_text('http://localhost/?=x=x=x')
self.assertEqual(u.get(''), ['x=x=x'])
self.assertEqual(u.to_text(), 'http://localhost/?=x%3Dx%3Dx')
u = URL.from_text('http://localhost/?foo=x=x=x&bar=y')
self.assertEqual(u.query, (('foo', 'x=x=x'), ('bar', 'y')))
self.assertEqual(u.to_text(), 'http://localhost/?foo=x%3Dx%3Dx&bar=y')
def test_empty(self):
"""
An empty L{URL} should serialize as the empty string.
"""
self.assertEqual(URL().to_text(), '')
def test_justQueryText(self):
"""
An L{URL} with query text should serialize as just query text.
"""
u = URL(query=[(u"hello", u"world")])
self.assertEqual(u.to_text(), '?hello=world')
def test_identicalEqual(self):
"""
L{URL} compares equal to itself.
"""
u = URL.from_text('http://localhost/')
self.assertEqual(u, u)
def test_similarEqual(self):
"""
URLs with equivalent components should compare equal.
"""
u1 = URL.from_text('http://u@localhost:8080/p/a/t/h?q=p#f')
u2 = URL.from_text('http://u@localhost:8080/p/a/t/h?q=p#f')
self.assertEqual(u1, u2)
def test_differentNotEqual(self):
"""
L{URL}s that refer to different resources are both unequal (C{!=}) and
also not equal (not C{==}).
"""
u1 = URL.from_text('http://localhost/a')
u2 = URL.from_text('http://localhost/b')
self.assertFalse(u1 == u2, "%r != %r" % (u1, u2))
self.assertNotEqual(u1, u2)
def test_otherTypesNotEqual(self):
"""
L{URL} is not equal (C{==}) to other types.
"""
u = URL.from_text('http://localhost/')
self.assertFalse(u == 42, "URL must not equal a number.")
self.assertFalse(u == object(), "URL must not equal an object.")
self.assertNotEqual(u, 42)
self.assertNotEqual(u, object())
def test_identicalNotUnequal(self):
"""
Identical L{URL}s are not unequal (C{!=}) to each other.
"""
u = URL.from_text('http://u@localhost:8080/p/a/t/h?q=p#f')
self.assertFalse(u != u, "%r == itself" % u)
def test_similarNotUnequal(self):
"""
Structurally similar L{URL}s are not unequal (C{!=}) to each other.
"""
u1 = URL.from_text('http://u@localhost:8080/p/a/t/h?q=p#f')
u2 = URL.from_text('http://u@localhost:8080/p/a/t/h?q=p#f')
self.assertFalse(u1 != u2, "%r == %r" % (u1, u2))
def test_differentUnequal(self):
"""
Structurally different L{URL}s are unequal (C{!=}) to each other.
"""
u1 = URL.from_text('http://localhost/a')
u2 = URL.from_text('http://localhost/b')
self.assertTrue(u1 != u2, "%r == %r" % (u1, u2))
def test_otherTypesUnequal(self):
"""
L{URL} is unequal (C{!=}) to other types.
"""
u = URL.from_text('http://localhost/')
self.assertTrue(u != 42, "URL must differ from a number.")
self.assertTrue(u != object(), "URL must be differ from an object.")
def test_asURI(self):
"""
L{URL.asURI} produces an URI which converts any URI unicode encoding
into pure US-ASCII and returns a new L{URL}.
"""
unicodey = ('http://\N{LATIN SMALL LETTER E WITH ACUTE}.com/'
'\N{LATIN SMALL LETTER E}\N{COMBINING ACUTE ACCENT}'
'?\N{LATIN SMALL LETTER A}\N{COMBINING ACUTE ACCENT}='
'\N{LATIN SMALL LETTER I}\N{COMBINING ACUTE ACCENT}'
'#\N{LATIN SMALL LETTER U}\N{COMBINING ACUTE ACCENT}')
iri = URL.from_text(unicodey)
uri = iri.asURI()
self.assertEqual(iri.host, '\N{LATIN SMALL LETTER E WITH ACUTE}.com')
self.assertEqual(iri.path[0],
'\N{LATIN SMALL LETTER E}\N{COMBINING ACUTE ACCENT}')
self.assertEqual(iri.to_text(), unicodey)
expectedURI = 'http://xn--9ca.com/%C3%A9?%C3%A1=%C3%AD#%C3%BA'
actualURI = uri.to_text()
self.assertEqual(actualURI, expectedURI,
'%r != %r' % (actualURI, expectedURI))
def test_asIRI(self):
"""
L{URL.asIRI} decodes any percent-encoded text in the URI, making it
more suitable for reading by humans, and returns a new L{URL}.
"""
asciiish = 'http://xn--9ca.com/%C3%A9?%C3%A1=%C3%AD#%C3%BA'
uri = URL.from_text(asciiish)
iri = uri.asIRI()
self.assertEqual(uri.host, 'xn--9ca.com')
self.assertEqual(uri.path[0], '%C3%A9')
self.assertEqual(uri.to_text(), asciiish)
expectedIRI = ('http://\N{LATIN SMALL LETTER E WITH ACUTE}.com/'
'\N{LATIN SMALL LETTER E WITH ACUTE}'
'?\N{LATIN SMALL LETTER A WITH ACUTE}='
'\N{LATIN SMALL LETTER I WITH ACUTE}'
'#\N{LATIN SMALL LETTER U WITH ACUTE}')
actualIRI = iri.to_text()
self.assertEqual(actualIRI, expectedIRI,
'%r != %r' % (actualIRI, expectedIRI))
def test_badUTF8AsIRI(self):
"""
Bad UTF-8 in a path segment, query parameter, or fragment results in
that portion of the URI remaining percent-encoded in the IRI.
"""
urlWithBinary = 'http://xn--9ca.com/%00%FF/%C3%A9'
uri = URL.from_text(urlWithBinary)
iri = uri.asIRI()
expectedIRI = ('http://\N{LATIN SMALL LETTER E WITH ACUTE}.com/'
'%00%FF/'
'\N{LATIN SMALL LETTER E WITH ACUTE}')
actualIRI = iri.to_text()
self.assertEqual(actualIRI, expectedIRI,
'%r != %r' % (actualIRI, expectedIRI))
def test_alreadyIRIAsIRI(self):
"""
A L{URL} composed of non-ASCII text will result in non-ASCII text.
"""
unicodey = ('http://\N{LATIN SMALL LETTER E WITH ACUTE}.com/'
'\N{LATIN SMALL LETTER E}\N{COMBINING ACUTE ACCENT}'
'?\N{LATIN SMALL LETTER A}\N{COMBINING ACUTE ACCENT}='
'\N{LATIN SMALL LETTER I}\N{COMBINING ACUTE ACCENT}'
'#\N{LATIN SMALL LETTER U}\N{COMBINING ACUTE ACCENT}')
iri = URL.from_text(unicodey)
alsoIRI = iri.asIRI()
self.assertEqual(alsoIRI.to_text(), unicodey)
def test_alreadyURIAsURI(self):
"""
A L{URL} composed of encoded text will remain encoded.
"""
expectedURI = 'http://xn--9ca.com/%C3%A9?%C3%A1=%C3%AD#%C3%BA'
uri = URL.from_text(expectedURI)
actualURI = uri.asURI().to_text()
self.assertEqual(actualURI, expectedURI)
def test_userinfo(self):
"""
L{URL.from_text} will parse the C{userinfo} portion of the URI
separately from the host and port.
"""
url = URL.from_text(
'http://someuser:somepassword@example.com/some-segment@ignore'
)
self.assertEqual(url.authority(True),
'someuser:somepassword@example.com')
self.assertEqual(url.authority(False), 'someuser:@example.com')
self.assertEqual(url.userinfo, 'someuser:somepassword')
self.assertEqual(url.user, 'someuser')
self.assertEqual(url.to_text(),
'http://someuser:@example.com/some-segment@ignore')
self.assertEqual(
url.replace(userinfo=u"someuser").to_text(),
'http://someuser@example.com/some-segment@ignore'
)
def test_portText(self):
"""
L{URL.from_text} parses custom port numbers as integers.
"""
portURL = URL.from_text(u"http://www.example.com:8080/")
self.assertEqual(portURL.port, 8080)
self.assertEqual(portURL.to_text(), u"http://www.example.com:8080/")
def test_mailto(self):
"""
Although L{URL} instances are mainly for dealing with HTTP, other
schemes (such as C{mailto:}) should work as well. For example,
L{URL.from_text}/L{URL.to_text} round-trips cleanly for a C{mailto:} URL
representing an email address.
"""
self.assertEqual(URL.from_text(u"mailto:user@example.com").to_text(),
u"mailto:user@example.com")
def test_queryIterable(self):
"""
When a L{URL} is created with a C{query} argument, the C{query}
argument is converted into an N-tuple of 2-tuples.
"""
url = URL(query=[['alpha', 'beta']])
self.assertEqual(url.query, (('alpha', 'beta'),))
def test_pathIterable(self):
"""
When a L{URL} is created with a C{path} argument, the C{path} is
converted into a tuple.
"""
url = URL(path=['hello', 'world'])
self.assertEqual(url.path, ('hello', 'world'))
def test_invalidArguments(self):
"""
Passing an argument of the wrong type to any of the constructor
arguments of L{URL} will raise a descriptive L{TypeError}.
L{URL} typechecks very aggressively to ensure that its constitutent
parts are all properly immutable and to prevent confusing errors when
bad data crops up in a method call long after the code that called the
constructor is off the stack.
"""
class Unexpected(object):
def __str__(self):
return "wrong"
def __repr__(self):
return "<unexpected>"
defaultExpectation = "unicode" if bytes is str else "str"
def assertRaised(raised, expectation, name):
self.assertEqual(str(raised.exception),
"expected {0} for {1}, got {2}".format(
expectation,
name, "<unexpected>"))
def check(param, expectation=defaultExpectation):
with self.assertRaises(TypeError) as raised:
URL(**{param: Unexpected()})
assertRaised(raised, expectation, param)
check("scheme")
check("host")
check("fragment")
check("rooted", "bool")
check("userinfo")
check("port", "int or NoneType")
with self.assertRaises(TypeError) as raised:
URL(path=[Unexpected()])
assertRaised(raised, defaultExpectation, "path segment")
with self.assertRaises(TypeError) as raised:
URL(query=[(u"name", Unexpected())])
assertRaised(raised, defaultExpectation + " or NoneType",
"query parameter value")
with self.assertRaises(TypeError) as raised:
URL(query=[(Unexpected(), u"value")])
assertRaised(raised, defaultExpectation, "query parameter name")
# No custom error message for this one, just want to make sure
# non-2-tuples don't get through.
with self.assertRaises(TypeError):
URL(query=[Unexpected()])
with self.assertRaises(ValueError):
URL(query=[('k', 'v', 'vv')])
with self.assertRaises(ValueError):
URL(query=[('k',)])
url = URL.from_text("https://valid.example.com/")
with self.assertRaises(TypeError) as raised:
url.child(Unexpected())
assertRaised(raised, defaultExpectation, "path segment")
with self.assertRaises(TypeError) as raised:
url.sibling(Unexpected())
assertRaised(raised, defaultExpectation, "path segment")
with self.assertRaises(TypeError) as raised:
url.click(Unexpected())
assertRaised(raised, defaultExpectation, "relative URL")
def test_technicallyTextIsIterableBut(self):
"""
Technically, L{str} (or L{unicode}, as appropriate) is iterable, but
C{URL(path="foo")} resulting in C{URL.from_text("f/o/o")} is never what
you want.
"""
with self.assertRaises(TypeError) as raised:
URL(path='foo')
self.assertEqual(
str(raised.exception),
"expected iterable of text for path, not: {0}"
.format(repr('foo'))
)
def test_netloc(self):
url = URL(scheme='https')
self.assertEqual(url.uses_netloc, True)
url = URL(scheme='git+https')
self.assertEqual(url.uses_netloc, True)
url = URL(scheme='mailto')
self.assertEqual(url.uses_netloc, False)
url = URL(scheme='ztp')
self.assertEqual(url.uses_netloc, None)
url = URL.from_text('ztp://test.com')
self.assertEqual(url.uses_netloc, True)
url = URL.from_text('ztp:test:com')
self.assertEqual(url.uses_netloc, False)
def test_ipv6_with_port(self):
t = 'https://[2001:0db8:85a3:0000:0000:8a2e:0370:7334]:80/'
url = URL.from_text(t)
assert url.host == '2001:0db8:85a3:0000:0000:8a2e:0370:7334'
assert url.port == 80
assert SCHEME_PORT_MAP[url.scheme] != url.port
def test_basic(self):
text = 'https://user:pass@example.com/path/to/here?k=v#nice'
url = URL.from_text(text)
assert url.scheme == 'https'
assert url.userinfo == 'user:pass'
assert url.host == 'example.com'
assert url.path == ('path', 'to', 'here')
assert url.fragment == 'nice'
text = 'https://user:pass@127.0.0.1/path/to/here?k=v#nice'
url = URL.from_text(text)
assert url.scheme == 'https'
assert url.userinfo == 'user:pass'
assert url.host == '127.0.0.1'
assert url.path == ('path', 'to', 'here')
text = 'https://user:pass@[::1]/path/to/here?k=v#nice'
url = URL.from_text(text)
assert url.scheme == 'https'
assert url.userinfo == 'user:pass'
assert url.host == '::1'
assert url.path == ('path', 'to', 'here')
def test_invalid_url(self):
self.assertRaises(URLParseError, URL.from_text, '#\n\n')
def test_invalid_authority_url(self):
self.assertRaises(URLParseError, URL.from_text, 'http://abc:\n\n/#')
def test_invalid_ipv6(self):
invalid_ipv6_ips = ['2001::0234:C1ab::A0:aabc:003F',
'2001::1::3F',
':',
'::::',
'::256.0.0.1']
for ip in invalid_ipv6_ips:
url_text = 'http://[' + ip + ']'
self.assertRaises(socket.error, inet_pton,
socket.AF_INET6, ip)
self.assertRaises(URLParseError, URL.from_text, url_text)
def test_invalid_port(self):
self.assertRaises(URLParseError, URL.from_text, 'ftp://portmouth:smash')
self.assertRaises(ValueError, URL.from_text,
'http://reader.googlewebsite.com:neverforget')
def test_idna(self):
u1 = URL.from_text('http://bücher.ch')
self.assertEquals(u1.host, 'bücher.ch')
self.assertEquals(u1.to_text(), 'http://bücher.ch')
self.assertEquals(u1.to_uri().to_text(), 'http://xn--bcher-kva.ch')
u2 = URL.from_text('https://xn--bcher-kva.ch')
self.assertEquals(u2.host, 'xn--bcher-kva.ch')
self.assertEquals(u2.to_text(), 'https://xn--bcher-kva.ch')
self.assertEquals(u2.to_iri().to_text(), u'https://bücher.ch')
def test_netloc_slashes(self):
# basic sanity checks
url = URL.from_text('mailto:mahmoud@hatnote.com')
self.assertEquals(url.scheme, 'mailto')
self.assertEquals(url.to_text(), 'mailto:mahmoud@hatnote.com')
url = URL.from_text('http://hatnote.com')
self.assertEquals(url.scheme, 'http')
self.assertEquals(url.to_text(), 'http://hatnote.com')
# test that unrecognized schemes stay consistent with '//'
url = URL.from_text('newscheme:a:b:c')
self.assertEquals(url.scheme, 'newscheme')
self.assertEquals(url.to_text(), 'newscheme:a:b:c')
url = URL.from_text('newerscheme://a/b/c')
self.assertEquals(url.scheme, 'newerscheme')
self.assertEquals(url.to_text(), 'newerscheme://a/b/c')
# test that reasonable guesses are made
url = URL.from_text('git+ftp://gitstub.biz/glyph/lefkowitz')
self.assertEquals(url.scheme, 'git+ftp')
self.assertEquals(url.to_text(),
'git+ftp://gitstub.biz/glyph/lefkowitz')
url = URL.from_text('what+mailto:freerealestate@enotuniq.org')
self.assertEquals(url.scheme, 'what+mailto')
self.assertEquals(url.to_text(),
'what+mailto:freerealestate@enotuniq.org')
url = URL(scheme='ztp', path=('x', 'y', 'z'), rooted=True)
self.assertEquals(url.to_text(), 'ztp:/x/y/z')
# also works when the input doesn't include '//'
url = URL(scheme='git+ftp', path=('x', 'y', 'z' ,''),
rooted=True, uses_netloc=True)
# broken bc urlunsplit
self.assertEquals(url.to_text(), 'git+ftp:///x/y/z/')
# really why would this ever come up but ok
url = URL.from_text('file:///path/to/heck')
url2 = url.replace(scheme='mailto')
self.assertEquals(url2.to_text(), 'mailto:/path/to/heck')
url_text = 'unregisteredscheme:///a/b/c'
url = URL.from_text(url_text)
no_netloc_url = url.replace(uses_netloc=False)
self.assertEquals(no_netloc_url.to_text(), 'unregisteredscheme:/a/b/c')
netloc_url = url.replace(uses_netloc=True)
self.assertEquals(netloc_url.to_text(), url_text)
return
def test_wrong_constructor(self):
with self.assertRaises(ValueError):
# whole URL not allowed
URL(BASIC_URL)
with self.assertRaises(ValueError):
# explicitly bad scheme not allowed
URL('HTTP_____more_like_imHoTTeP')
def test_encoded_userinfo(self):
url = URL.from_text('http://user:pass@example.com')
assert url.userinfo == 'user:pass'
url = url.replace(userinfo='us%20her:pass')
iri = url.to_iri()
assert iri.to_text(with_password=True) == 'http://us her:pass@example.com'
assert iri.to_text(with_password=False) == 'http://us her:@example.com'
assert iri.to_uri().to_text(with_password=True) == 'http://us%20her:pass@example.com'
def test_hash(self):
url_map = {}
url1 = URL.from_text('http://blog.hatnote.com/ask?utm_source=geocity')
assert hash(url1) == hash(url1) # sanity
url_map[url1] = 1
url2 = URL.from_text('http://blog.hatnote.com/ask')
url2 = url2.set('utm_source', 'geocity')
url_map[url2] = 2
assert len(url_map) == 1
assert list(url_map.values()) == [2]
assert hash(URL()) == hash(URL()) # slightly more sanity
def test_dir(self):
url = URL()
res = dir(url)
assert len(res) > 15
# twisted compat
assert 'fromText' not in res
assert 'asText' not in res
assert 'asURI' not in res
assert 'asIRI' not in res
def test_twisted_compat(self):
url = URL.fromText(u'http://example.com/a%20té%C3%A9st')
assert url.asText() == 'http://example.com/a%20té%C3%A9st'
assert url.asURI().asText() == 'http://example.com/a%20t%C3%A9%C3%A9st'
# TODO: assert url.asIRI().asText() == u'http://example.com/a%20téést'
def test_set_ordering(self):
# TODO
url = URL.from_text('http://example.com/?a=b&c')
url = url.set(u'x', u'x')
url = url.add(u'x', u'y')
assert url.to_text() == u'http://example.com/?a=b&x=x&c&x=y'
# Would expect:
# assert url.to_text() == u'http://example.com/?a=b&c&x=x&x=y'
def test_schemeless_path(self):
"See issue #4"
u1 = URL.from_text("urn%3Aietf%3Awg%3Aoauth%3A2.0%3Aoob")
u2 = URL.from_text(u1.to_text())
assert u1 == u2 # sanity testing roundtripping
u3 = URL.from_text(u1.to_iri().to_text())
assert u1 == u3
assert u2 == u3
# test that colons are ok past the first segment
u4 = URL.from_text("first-segment/urn%3Aietf%3Awg%3Aoauth%3A2.0%3Aoob")
u5 = u4.to_iri()
assert u5.to_text() == u'first-segment/urn:ietf:wg:oauth:2.0:oob'
u6 = URL.from_text(u5.to_text()).to_uri()
assert u5 == u6 # colons stay decoded bc they're not in the first seg
def test_emoji_domain(self):
"See issue #7, affecting only narrow builds (2.6-3.3)"
url = URL.from_text('https://xn--vi8hiv.ws')
iri = url.to_iri()
iri.to_text()
# as long as we don't get ValueErrors, we're good
def test_delim_in_param(self):
"Per issue #6 and #8"
self.assertRaises(ValueError, URL, scheme=u'http', host=u'a/c')
self.assertRaises(ValueError, URL, path=(u"?",))
self.assertRaises(ValueError, URL, path=(u"#",))
self.assertRaises(ValueError, URL, query=((u"&", "test")))
def test_empty_paths_eq(self):
u1 = URL.from_text('http://example.com/')
u2 = URL.from_text('http://example.com')
assert u1 == u2
u1 = URL.from_text('http://example.com')
u2 = URL.from_text('http://example.com')
assert u1 == u2
u1 = URL.from_text('http://example.com')
u2 = URL.from_text('http://example.com/')
assert u1 == u2
u1 = URL.from_text('http://example.com/')
u2 = URL.from_text('http://example.com/')
assert u1 == u2
def test_from_text_type(self):
assert URL.from_text(u'#ok').fragment == u'ok' # sanity
self.assertRaises(TypeError, URL.from_text, b'bytes://x.y.z')
self.assertRaises(TypeError, URL.from_text, object())
def test_from_text_bad_authority(self):
# bad ipv6 brackets
self.assertRaises(URLParseError, URL.from_text, 'http://[::1/')
self.assertRaises(URLParseError, URL.from_text, 'http://::1]/')
self.assertRaises(URLParseError, URL.from_text, 'http://[[::1]/')
self.assertRaises(URLParseError, URL.from_text, 'http://[::1]]/')
# empty port
self.assertRaises(URLParseError, URL.from_text, 'http://127.0.0.1:')
# non-integer port
self.assertRaises(URLParseError, URL.from_text, 'http://127.0.0.1:hi')
# extra port colon (makes for an invalid host)
self.assertRaises(URLParseError, URL.from_text, 'http://127.0.0.1::80')
def test_normalize(self):
url = URL.from_text('HTTP://Example.com/A%61/./../A%61?B%62=C%63#D%64')
assert url.get('Bb') == []
assert url.get('B%62') == ['C%63']
assert len(url.path) == 4
# test that most expected normalizations happen
norm_url = url.normalize()
assert norm_url.scheme == 'http'
assert norm_url.host == 'example.com'
assert norm_url.path == ('Aa',)
assert norm_url.get('Bb') == ['Cc']
assert norm_url.fragment == 'Dd'
assert norm_url.to_text() == 'http://example.com/Aa?Bb=Cc#Dd'
# test that flags work
noop_norm_url = url.normalize(scheme=False, host=False,
path=False, query=False, fragment=False)
assert noop_norm_url == url
# test that empty paths get at least one slash
slashless_url = URL.from_text('http://example.io')
slashful_url = slashless_url.normalize()
assert slashful_url.to_text() == 'http://example.io/'
# test case normalization for percent encoding
delimited_url = URL.from_text('/a%2fb/cd%3f?k%3d=v%23#test')
norm_delimited_url = delimited_url.normalize()
assert norm_delimited_url.to_text() == '/a%2Fb/cd%3F?k%3D=v%23#test'
# test invalid percent encoding during normalize
assert URL(path=('', '%te%sts')).normalize().to_text() == '/%te%sts'
|