forked from Pissandshittium/pissandshittium
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathgurl_unittest.cc
1180 lines (1033 loc) · 42.9 KB
/
gurl_unittest.cc
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
// Copyright 2013 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "url/gurl.h"
#include <stddef.h>
#include "base/strings/string_number_conversions.h"
#include "base/strings/utf_string_conversions.h"
#include "testing/gtest/include/gtest/gtest.h"
#include "url/gurl_abstract_tests.h"
#include "url/origin.h"
#include "url/url_canon.h"
#include "url/url_test_utils.h"
namespace url {
namespace {
// Returns the canonicalized string for the given URL string for the
// GURLTest.Types test.
std::string TypesTestCase(const char* src) {
GURL gurl(src);
return gurl.possibly_invalid_spec();
}
} // namespace
// Different types of URLs should be handled differently, and handed off to
// different canonicalizers.
TEST(GURLTest, Types) {
// URLs with unknown schemes should be treated as path URLs, even when they
// have things like "://".
EXPECT_EQ("something:///HOSTNAME.com/",
TypesTestCase("something:///HOSTNAME.com/"));
// Conversely, URLs with known schemes should always trigger standard URL
// handling.
EXPECT_EQ("http://hostname.com/", TypesTestCase("http:HOSTNAME.com"));
EXPECT_EQ("http://hostname.com/", TypesTestCase("http:/HOSTNAME.com"));
EXPECT_EQ("http://hostname.com/", TypesTestCase("http://HOSTNAME.com"));
EXPECT_EQ("http://hostname.com/", TypesTestCase("http:///HOSTNAME.com"));
#ifdef WIN32
// URLs that look like Windows absolute path specs.
EXPECT_EQ("file:///C:/foo.txt", TypesTestCase("c:\\foo.txt"));
EXPECT_EQ("file:///Z:/foo.txt", TypesTestCase("Z|foo.txt"));
EXPECT_EQ("file://server/foo.txt", TypesTestCase("\\\\server\\foo.txt"));
EXPECT_EQ("file://server/foo.txt", TypesTestCase("//server/foo.txt"));
#endif
}
// Test the basic creation and querying of components in a GURL. We assume that
// the parser is already tested and works, so we are mostly interested if the
// object does the right thing with the results.
TEST(GURLTest, Components) {
GURL empty_url(u"");
EXPECT_TRUE(empty_url.is_empty());
EXPECT_FALSE(empty_url.is_valid());
GURL url(u"http://user:pass@google.com:99/foo;bar?q=a#ref");
EXPECT_FALSE(url.is_empty());
EXPECT_TRUE(url.is_valid());
EXPECT_TRUE(url.SchemeIs("http"));
EXPECT_FALSE(url.SchemeIsFile());
// This is the narrow version of the URL, which should match the wide input.
EXPECT_EQ("http://user:pass@google.com:99/foo;bar?q=a#ref", url.spec());
EXPECT_EQ("http", url.scheme());
EXPECT_EQ("user", url.username());
EXPECT_EQ("pass", url.password());
EXPECT_EQ("google.com", url.host());
EXPECT_EQ("99", url.port());
EXPECT_EQ(99, url.IntPort());
EXPECT_EQ("/foo;bar", url.path());
EXPECT_EQ("q=a", url.query());
EXPECT_EQ("ref", url.ref());
// Test parsing userinfo with special characters.
GURL url_special_pass("http://user:%40!$&'()*+,;=:@google.com:12345");
EXPECT_TRUE(url_special_pass.is_valid());
// GURL canonicalizes some delimiters.
EXPECT_EQ("%40!$&%27()*+,%3B%3D%3A", url_special_pass.password());
EXPECT_EQ("google.com", url_special_pass.host());
EXPECT_EQ("12345", url_special_pass.port());
}
TEST(GURLTest, Empty) {
GURL url;
EXPECT_FALSE(url.is_valid());
EXPECT_EQ("", url.spec());
EXPECT_EQ("", url.scheme());
EXPECT_EQ("", url.username());
EXPECT_EQ("", url.password());
EXPECT_EQ("", url.host());
EXPECT_EQ("", url.port());
EXPECT_EQ(PORT_UNSPECIFIED, url.IntPort());
EXPECT_EQ("", url.path());
EXPECT_EQ("", url.query());
EXPECT_EQ("", url.ref());
}
TEST(GURLTest, Copy) {
GURL url(u"http://user:pass@google.com:99/foo;bar?q=a#ref");
GURL url2(url);
EXPECT_TRUE(url2.is_valid());
EXPECT_EQ("http://user:pass@google.com:99/foo;bar?q=a#ref", url2.spec());
EXPECT_EQ("http", url2.scheme());
EXPECT_EQ("user", url2.username());
EXPECT_EQ("pass", url2.password());
EXPECT_EQ("google.com", url2.host());
EXPECT_EQ("99", url2.port());
EXPECT_EQ(99, url2.IntPort());
EXPECT_EQ("/foo;bar", url2.path());
EXPECT_EQ("q=a", url2.query());
EXPECT_EQ("ref", url2.ref());
// Copying of invalid URL should be invalid
GURL invalid;
GURL invalid2(invalid);
EXPECT_FALSE(invalid2.is_valid());
EXPECT_EQ("", invalid2.spec());
EXPECT_EQ("", invalid2.scheme());
EXPECT_EQ("", invalid2.username());
EXPECT_EQ("", invalid2.password());
EXPECT_EQ("", invalid2.host());
EXPECT_EQ("", invalid2.port());
EXPECT_EQ(PORT_UNSPECIFIED, invalid2.IntPort());
EXPECT_EQ("", invalid2.path());
EXPECT_EQ("", invalid2.query());
EXPECT_EQ("", invalid2.ref());
}
TEST(GURLTest, Assign) {
GURL url(u"http://user:pass@google.com:99/foo;bar?q=a#ref");
GURL url2;
url2 = url;
EXPECT_TRUE(url2.is_valid());
EXPECT_EQ("http://user:pass@google.com:99/foo;bar?q=a#ref", url2.spec());
EXPECT_EQ("http", url2.scheme());
EXPECT_EQ("user", url2.username());
EXPECT_EQ("pass", url2.password());
EXPECT_EQ("google.com", url2.host());
EXPECT_EQ("99", url2.port());
EXPECT_EQ(99, url2.IntPort());
EXPECT_EQ("/foo;bar", url2.path());
EXPECT_EQ("q=a", url2.query());
EXPECT_EQ("ref", url2.ref());
// Assignment of invalid URL should be invalid
GURL invalid;
GURL invalid2;
invalid2 = invalid;
EXPECT_FALSE(invalid2.is_valid());
EXPECT_EQ("", invalid2.spec());
EXPECT_EQ("", invalid2.scheme());
EXPECT_EQ("", invalid2.username());
EXPECT_EQ("", invalid2.password());
EXPECT_EQ("", invalid2.host());
EXPECT_EQ("", invalid2.port());
EXPECT_EQ(PORT_UNSPECIFIED, invalid2.IntPort());
EXPECT_EQ("", invalid2.path());
EXPECT_EQ("", invalid2.query());
EXPECT_EQ("", invalid2.ref());
}
// This is a regression test for http://crbug.com/309975.
TEST(GURLTest, SelfAssign) {
GURL a("filesystem:http://example.com/temporary/");
// This should not crash.
a = *&a; // The *& defeats Clang's -Wself-assign warning.
}
TEST(GURLTest, CopyFileSystem) {
GURL url(u"filesystem:https://user:pass@google.com:99/t/foo;bar?q=a#ref");
GURL url2(url);
EXPECT_TRUE(url2.is_valid());
EXPECT_EQ("filesystem:https://google.com:99/t/foo;bar?q=a#ref", url2.spec());
EXPECT_EQ("filesystem", url2.scheme());
EXPECT_EQ("", url2.username());
EXPECT_EQ("", url2.password());
EXPECT_EQ("", url2.host());
EXPECT_EQ("", url2.port());
EXPECT_EQ(PORT_UNSPECIFIED, url2.IntPort());
EXPECT_EQ("/foo;bar", url2.path());
EXPECT_EQ("q=a", url2.query());
EXPECT_EQ("ref", url2.ref());
const GURL* inner = url2.inner_url();
ASSERT_TRUE(inner);
EXPECT_EQ("https", inner->scheme());
EXPECT_EQ("", inner->username());
EXPECT_EQ("", inner->password());
EXPECT_EQ("google.com", inner->host());
EXPECT_EQ("99", inner->port());
EXPECT_EQ(99, inner->IntPort());
EXPECT_EQ("/t", inner->path());
EXPECT_EQ("", inner->query());
EXPECT_EQ("", inner->ref());
}
TEST(GURLTest, IsValid) {
const char* valid_cases[] = {
"http://google.com",
"unknown://google.com",
"http://user:pass@google.com",
"http://google.com:12345",
"http://google.com:0", // 0 is a valid port
"http://google.com/path",
"http://google.com//path",
"http://google.com?k=v#fragment",
"http://user:pass@google.com:12345/path?k=v#fragment",
"http:/path",
"http:path",
};
for (size_t i = 0; i < std::size(valid_cases); i++) {
EXPECT_TRUE(GURL(valid_cases[i]).is_valid())
<< "Case: " << valid_cases[i];
}
const char* invalid_cases[] = {
"http://?k=v",
"http:://google.com",
"http//google.com",
"http://google.com:12three45",
"file://server:123", // file: URLs cannot have a port
"file://server:0",
"://google.com",
"path",
};
for (size_t i = 0; i < std::size(invalid_cases); i++) {
EXPECT_FALSE(GURL(invalid_cases[i]).is_valid())
<< "Case: " << invalid_cases[i];
}
}
TEST(GURLTest, ExtraSlashesBeforeAuthority) {
// According to RFC3986, the hierarchical part for URI with an authority
// must use only two slashes; GURL intentionally just ignores extra slashes
// if there are more than 2, and parses the following part as an authority.
GURL url("http:///host");
EXPECT_EQ("host", url.host());
EXPECT_EQ("/", url.path());
}
// Given invalid URLs, we should still get most of the components.
TEST(GURLTest, ComponentGettersWorkEvenForInvalidURL) {
constexpr struct InvalidURLTestExpectations {
const char* url;
const char* spec;
const char* scheme;
const char* host;
const char* port;
const char* path;
// Extend as needed...
} expectations[] = {
{
"http:google.com:foo",
"http://google.com:foo/",
"http",
"google.com",
"foo",
"/",
},
{
"https:google.com:foo",
"https://google.com:foo/",
"https",
"google.com",
"foo",
"/",
},
};
for (const auto& e : expectations) {
const GURL url(e.url);
EXPECT_FALSE(url.is_valid());
EXPECT_EQ(e.spec, url.possibly_invalid_spec());
EXPECT_EQ(e.scheme, url.scheme());
EXPECT_EQ("", url.username());
EXPECT_EQ("", url.password());
EXPECT_EQ(e.host, url.host());
EXPECT_EQ(e.port, url.port());
EXPECT_EQ(PORT_INVALID, url.IntPort());
EXPECT_EQ(e.path, url.path());
EXPECT_EQ("", url.query());
EXPECT_EQ("", url.ref());
}
}
TEST(GURLTest, Resolve) {
// The tricky cases for relative URL resolving are tested in the
// canonicalizer unit test. Here, we just test that the GURL integration
// works properly.
struct ResolveCase {
const char* base;
const char* relative;
bool expected_valid;
const char* expected;
} resolve_cases[] = {
{"http://www.google.com/", "foo.html", true,
"http://www.google.com/foo.html"},
{"http://www.google.com/foo/", "bar", true,
"http://www.google.com/foo/bar"},
{"http://www.google.com/foo/", "/bar", true, "http://www.google.com/bar"},
{"http://www.google.com/foo", "bar", true, "http://www.google.com/bar"},
{"http://www.google.com/", "http://images.google.com/foo.html", true,
"http://images.google.com/foo.html"},
{"http://www.google.com/", "http://images.\tgoogle.\ncom/\rfoo.html",
true, "http://images.google.com/foo.html"},
{"http://www.google.com/blah/bloo?c#d", "../../../hello/./world.html?a#b",
true, "http://www.google.com/hello/world.html?a#b"},
{"http://www.google.com/foo#bar", "#com", true,
"http://www.google.com/foo#com"},
{"http://www.google.com/", "Https:images.google.com", true,
"https://images.google.com/"},
// A non-standard base can be replaced with a standard absolute URL.
{"data:blahblah", "http://google.com/", true, "http://google.com/"},
{"data:blahblah", "http:google.com", true, "http://google.com/"},
{"data:blahblah", "https:google.com", true, "https://google.com/"},
// Filesystem URLs have different paths to test.
{"filesystem:http://www.google.com/type/", "foo.html", true,
"filesystem:http://www.google.com/type/foo.html"},
{"filesystem:http://www.google.com/type/", "../foo.html", true,
"filesystem:http://www.google.com/type/foo.html"},
// https://crbug.com/530123 - scheme validation (e.g. are "10.0.0.7:"
// or "x1:" valid schemes) when deciding if |relative| is an absolute url.
{"file:///some/dir/ip-relative.html", "10.0.0.7:8080/foo.html", true,
"file:///some/dir/10.0.0.7:8080/foo.html"},
{"file:///some/dir/", "1://host", true, "file:///some/dir/1://host"},
{"file:///some/dir/", "x1://host", true, "x1://host"},
{"file:///some/dir/", "X1://host", true, "x1://host"},
{"file:///some/dir/", "x.://host", true, "x.://host"},
{"file:///some/dir/", "x+://host", true, "x+://host"},
{"file:///some/dir/", "x-://host", true, "x-://host"},
{"file:///some/dir/", "x!://host", true, "file:///some/dir/x!://host"},
{"file:///some/dir/", "://host", true, "file:///some/dir/://host"},
};
for (size_t i = 0; i < std::size(resolve_cases); i++) {
// 8-bit code path.
GURL input(resolve_cases[i].base);
GURL output = input.Resolve(resolve_cases[i].relative);
EXPECT_EQ(resolve_cases[i].expected_valid, output.is_valid()) << i;
EXPECT_EQ(resolve_cases[i].expected, output.spec()) << i;
EXPECT_EQ(output.SchemeIsFileSystem(), output.inner_url() != NULL);
// Wide code path.
GURL inputw(base::UTF8ToUTF16(resolve_cases[i].base));
GURL outputw =
input.Resolve(base::UTF8ToUTF16(resolve_cases[i].relative));
EXPECT_EQ(resolve_cases[i].expected_valid, outputw.is_valid()) << i;
EXPECT_EQ(resolve_cases[i].expected, outputw.spec()) << i;
EXPECT_EQ(outputw.SchemeIsFileSystem(), outputw.inner_url() != NULL);
}
}
TEST(GURLTest, GetOrigin) {
struct TestCase {
const char* input;
const char* expected;
} cases[] = {
{"http://www.google.com", "http://www.google.com/"},
{"javascript:window.alert(\"hello,world\");", ""},
{"http://user:pass@www.google.com:21/blah#baz",
"http://www.google.com:21/"},
{"http://user@www.google.com", "http://www.google.com/"},
{"http://:pass@www.google.com", "http://www.google.com/"},
{"http://:@www.google.com", "http://www.google.com/"},
{"filesystem:http://www.google.com/temp/foo?q#b",
"http://www.google.com/"},
{"filesystem:http://user:pass@google.com:21/blah#baz",
"http://google.com:21/"},
{"blob:null/guid-goes-here", ""},
{"blob:http://origin/guid-goes-here", "" /* should be http://origin/ */},
};
for (size_t i = 0; i < std::size(cases); i++) {
GURL url(cases[i].input);
GURL origin = url.DeprecatedGetOriginAsURL();
EXPECT_EQ(cases[i].expected, origin.spec());
}
}
TEST(GURLTest, GetAsReferrer) {
struct TestCase {
const char* input;
const char* expected;
} cases[] = {
{"http://www.google.com", "http://www.google.com/"},
{"http://user:pass@www.google.com:21/blah#baz", "http://www.google.com:21/blah"},
{"http://user@www.google.com", "http://www.google.com/"},
{"http://:pass@www.google.com", "http://www.google.com/"},
{"http://:@www.google.com", "http://www.google.com/"},
{"http://www.google.com/temp/foo?q#b", "http://www.google.com/temp/foo?q"},
{"not a url", ""},
{"unknown-scheme://foo.html", ""},
{"file:///tmp/test.html", ""},
{"https://www.google.com", "https://www.google.com/"},
};
for (size_t i = 0; i < std::size(cases); i++) {
GURL url(cases[i].input);
GURL origin = url.GetAsReferrer();
EXPECT_EQ(cases[i].expected, origin.spec());
}
}
TEST(GURLTest, GetWithEmptyPath) {
struct TestCase {
const char* input;
const char* expected;
} cases[] = {
{"http://www.google.com", "http://www.google.com/"},
{"javascript:window.alert(\"hello, world\");", ""},
{"http://www.google.com/foo/bar.html?baz=22", "http://www.google.com/"},
{"filesystem:http://www.google.com/temporary/bar.html?baz=22", "filesystem:http://www.google.com/temporary/"},
{"filesystem:file:///temporary/bar.html?baz=22", "filesystem:file:///temporary/"},
};
for (size_t i = 0; i < std::size(cases); i++) {
GURL url(cases[i].input);
GURL empty_path = url.GetWithEmptyPath();
EXPECT_EQ(cases[i].expected, empty_path.spec());
}
}
TEST(GURLTest, GetWithoutFilename) {
struct TestCase {
const char* input;
const char* expected;
} cases[] = {
// Common Standard URLs.
{"https://www.google.com", "https://www.google.com/"},
{"https://www.google.com/", "https://www.google.com/"},
{"https://www.google.com/maps.htm", "https://www.google.com/"},
{"https://www.google.com/maps/", "https://www.google.com/maps/"},
{"https://www.google.com/index.html", "https://www.google.com/"},
{"https://www.google.com/index.html?q=maps", "https://www.google.com/"},
{"https://www.google.com/index.html#maps/", "https://www.google.com/"},
{"https://foo:bar@www.google.com/maps.htm", "https://foo:bar@www.google.com/"},
{"https://www.google.com/maps/au/index.html", "https://www.google.com/maps/au/"},
{"https://www.google.com/maps/au/north", "https://www.google.com/maps/au/"},
{"https://www.google.com/maps/au/north/", "https://www.google.com/maps/au/north/"},
{"https://www.google.com/maps/au/index.html?q=maps#fragment/", "https://www.google.com/maps/au/"},
{"http://www.google.com:8000/maps/au/index.html?q=maps#fragment/", "http://www.google.com:8000/maps/au/"},
{"https://www.google.com/maps/au/north/?q=maps#fragment", "https://www.google.com/maps/au/north/"},
{"https://www.google.com/maps/au/north?q=maps#fragment", "https://www.google.com/maps/au/"},
// Less common standard URLs.
{"filesystem:http://www.google.com/temporary/bar.html?baz=22", "filesystem:http://www.google.com/temporary/"},
{"file:///temporary/bar.html?baz=22","file:///temporary/"},
{"ftp://foo/test/index.html", "ftp://foo/test/"},
{"gopher://foo/test/index.html", "gopher://foo/test/"},
{"ws://foo/test/index.html", "ws://foo/test/"},
// Non-standard, hierarchical URLs.
{"chrome://foo/bar.html", "chrome://foo/"},
{"httpa://foo/test/index.html", "httpa://foo/test/"},
// Non-standard, non-hierarchical URLs.
{"blob:https://foo.bar/test/index.html", ""},
{"about:blank", ""},
{"data:foobar", ""},
{"scheme:opaque_data", ""},
// Invalid URLs.
{"foobar", ""},
};
for (size_t i = 0; i < std::size(cases); i++) {
GURL url(cases[i].input);
GURL without_filename = url.GetWithoutFilename();
EXPECT_EQ(cases[i].expected, without_filename.spec()) << i;
}
}
TEST(GURLTest, GetWithoutRef) {
struct TestCase {
const char* input;
const char* expected;
} cases[] = {
// Common Standard URLs.
{"https://www.google.com/index.html",
"https://www.google.com/index.html"},
{"https://www.google.com/index.html#maps/",
"https://www.google.com/index.html"},
{"https://foo:bar@www.google.com/maps.htm",
"https://foo:bar@www.google.com/maps.htm"},
{"https://foo:bar@www.google.com/maps.htm#fragment",
"https://foo:bar@www.google.com/maps.htm"},
{"https://www.google.com/maps/au/index.html?q=maps",
"https://www.google.com/maps/au/index.html?q=maps"},
{"https://www.google.com/maps/au/index.html?q=maps#fragment/",
"https://www.google.com/maps/au/index.html?q=maps"},
{"http://www.google.com:8000/maps/au/index.html?q=maps",
"http://www.google.com:8000/maps/au/index.html?q=maps"},
{"http://www.google.com:8000/maps/au/index.html?q=maps#fragment/",
"http://www.google.com:8000/maps/au/index.html?q=maps"},
{"https://www.google.com/maps/au/north/?q=maps",
"https://www.google.com/maps/au/north/?q=maps"},
{"https://www.google.com/maps/au/north?q=maps#fragment",
"https://www.google.com/maps/au/north?q=maps"},
// Less common standard URLs.
{"filesystem:http://www.google.com/temporary/bar.html?baz=22",
"filesystem:http://www.google.com/temporary/bar.html?baz=22"},
{"file:///temporary/bar.html?baz=22#fragment",
"file:///temporary/bar.html?baz=22"},
{"ftp://foo/test/index.html", "ftp://foo/test/index.html"},
{"ftp://foo/test/index.html#fragment", "ftp://foo/test/index.html"},
{"gopher://foo/test/index.html", "gopher://foo/test/index.html"},
{"gopher://foo/test/index.html#fragment", "gopher://foo/test/index.html"},
{"ws://foo/test/index.html", "ws://foo/test/index.html"},
{"ws://foo/test/index.html#fragment", "ws://foo/test/index.html"},
// Non-standard, hierarchical URLs.
{"chrome://foo/bar.html", "chrome://foo/bar.html"},
{"chrome://foo/bar.html#fragment", "chrome://foo/bar.html"},
{"httpa://foo/test/index.html", "httpa://foo/test/index.html"},
{"httpa://foo/test/index.html#fragment", "httpa://foo/test/index.html"},
// Non-standard, non-hierarchical URLs.
{"blob:https://foo.bar/test/index.html",
"blob:https://foo.bar/test/index.html"},
{"blob:https://foo.bar/test/index.html#fragment",
"blob:https://foo.bar/test/index.html"},
{"about:blank", "about:blank"},
{"about:blank#ref", "about:blank"},
{"data:foobar", "data:foobar"},
{"scheme:opaque_data", "scheme:opaque_data"},
// Invalid URLs.
{"foobar", ""},
};
for (size_t i = 0; i < std::size(cases); i++) {
GURL url(cases[i].input);
GURL without_ref = url.GetWithoutRef();
EXPECT_EQ(cases[i].expected, without_ref.spec());
}
}
TEST(GURLTest, Replacements) {
// The URL canonicalizer replacement test will handle most of these case.
// The most important thing to do here is to check that the proper
// canonicalizer gets called based on the scheme of the input.
struct ReplaceCase {
using ApplyReplacementsFunc = GURL(const GURL&);
const char* base;
ApplyReplacementsFunc* apply_replacements;
const char* expected;
} replace_cases[] = {
{.base = "http://www.google.com/foo/bar.html?foo#bar",
.apply_replacements =
+[](const GURL& url) {
GURL::Replacements replacements;
replacements.SetPathStr("/");
replacements.ClearQuery();
replacements.ClearRef();
return url.ReplaceComponents(replacements);
},
.expected = "http://www.google.com/"},
{.base = "http://www.google.com/foo/bar.html?foo#bar",
.apply_replacements =
+[](const GURL& url) {
GURL::Replacements replacements;
replacements.SetSchemeStr("javascript");
replacements.ClearUsername();
replacements.ClearPassword();
replacements.ClearHost();
replacements.ClearPort();
replacements.SetPathStr("window.open('foo');");
replacements.ClearQuery();
replacements.ClearRef();
return url.ReplaceComponents(replacements);
},
.expected = "javascript:window.open('foo');"},
{.base = "file:///C:/foo/bar.txt",
.apply_replacements =
+[](const GURL& url) {
GURL::Replacements replacements;
replacements.SetSchemeStr("http");
replacements.SetHostStr("www.google.com");
replacements.SetPortStr("99");
replacements.SetPathStr("/foo");
replacements.SetQueryStr("search");
replacements.SetRefStr("ref");
return url.ReplaceComponents(replacements);
},
.expected = "http://www.google.com:99/foo?search#ref"},
#ifdef WIN32
{.base = "http://www.google.com/foo/bar.html?foo#bar",
.apply_replacements =
+[](const GURL& url) {
GURL::Replacements replacements;
replacements.SetSchemeStr("file");
replacements.ClearUsername();
replacements.ClearPassword();
replacements.ClearHost();
replacements.ClearPort();
replacements.SetPathStr("c:\\");
replacements.ClearQuery();
replacements.ClearRef();
return url.ReplaceComponents(replacements);
},
.expected = "file:///C:/"},
#endif
{.base = "filesystem:http://www.google.com/foo/bar.html?foo#bar",
.apply_replacements =
+[](const GURL& url) {
GURL::Replacements replacements;
replacements.SetPathStr("/");
replacements.ClearQuery();
replacements.ClearRef();
return url.ReplaceComponents(replacements);
},
.expected = "filesystem:http://www.google.com/foo/"},
// Lengthen the URL instead of shortening it, to test creation of
// inner_url.
{.base = "filesystem:http://www.google.com/foo/",
.apply_replacements =
+[](const GURL& url) {
GURL::Replacements replacements;
replacements.SetPathStr("bar.html");
replacements.SetQueryStr("foo");
replacements.SetRefStr("bar");
return url.ReplaceComponents(replacements);
},
.expected = "filesystem:http://www.google.com/foo/bar.html?foo#bar"},
};
for (const ReplaceCase& c : replace_cases) {
GURL output = c.apply_replacements(GURL(c.base));
EXPECT_EQ(c.expected, output.spec());
EXPECT_EQ(output.SchemeIsFileSystem(), output.inner_url() != NULL);
if (output.SchemeIsFileSystem()) {
// TODO(mmenke): inner_url()->spec() is currently the same as the spec()
// for the GURL itself. This should be fixed.
// See https://crbug.com/619596
EXPECT_EQ(c.expected, output.inner_url()->spec());
}
}
}
TEST(GURLTest, ClearFragmentOnDataUrl) {
// http://crbug.com/291747 - a data URL may legitimately have trailing
// whitespace in the spec after the ref is cleared. Test this does not trigger
// the Parsed importing validation DCHECK in GURL.
GURL url(" data: one # two ");
EXPECT_TRUE(url.is_valid());
// By default the trailing whitespace will have been stripped.
EXPECT_EQ("data: one #%20two", url.spec());
// Clear the URL's ref and observe the trailing whitespace.
GURL::Replacements repl;
repl.ClearRef();
GURL url_no_ref = url.ReplaceComponents(repl);
EXPECT_TRUE(url_no_ref.is_valid());
EXPECT_EQ("data: one ", url_no_ref.spec());
// Importing a parsed URL via this constructor overload will retain trailing
// whitespace.
GURL import_url(url_no_ref.spec(),
url_no_ref.parsed_for_possibly_invalid_spec(),
url_no_ref.is_valid());
EXPECT_TRUE(import_url.is_valid());
EXPECT_EQ(url_no_ref, import_url);
EXPECT_EQ("data: one ", import_url.spec());
EXPECT_EQ(" one ", import_url.path());
// For completeness, test that re-parsing the same URL rather than importing
// it trims the trailing whitespace.
GURL reparsed_url(url_no_ref.spec());
EXPECT_TRUE(reparsed_url.is_valid());
EXPECT_EQ("data: one", reparsed_url.spec());
}
TEST(GURLTest, PathForRequest) {
struct TestCase {
const char* input;
const char* expected;
const char* inner_expected;
} cases[] = {
{"http://www.google.com", "/", nullptr},
{"http://www.google.com/", "/", nullptr},
{"http://www.google.com/foo/bar.html?baz=22", "/foo/bar.html?baz=22",
nullptr},
{"http://www.google.com/foo/bar.html#ref", "/foo/bar.html", nullptr},
{"http://www.google.com/foo/bar.html?query#ref", "/foo/bar.html?query",
nullptr},
{"filesystem:http://www.google.com/temporary/foo/bar.html?query#ref",
"/foo/bar.html?query", "/temporary"},
{"filesystem:http://www.google.com/temporary/foo/bar.html?query",
"/foo/bar.html?query", "/temporary"},
};
for (size_t i = 0; i < std::size(cases); i++) {
GURL url(cases[i].input);
EXPECT_EQ(cases[i].expected, url.PathForRequest());
EXPECT_EQ(cases[i].expected, url.PathForRequestPiece());
EXPECT_EQ(cases[i].inner_expected == NULL, url.inner_url() == NULL);
if (url.inner_url() && cases[i].inner_expected) {
EXPECT_EQ(cases[i].inner_expected, url.inner_url()->PathForRequest());
EXPECT_EQ(cases[i].inner_expected,
url.inner_url()->PathForRequestPiece());
}
}
}
TEST(GURLTest, EffectiveIntPort) {
struct PortTest {
const char* spec;
int expected_int_port;
} port_tests[] = {
// http
{"http://www.google.com/", 80},
{"http://www.google.com:80/", 80},
{"http://www.google.com:443/", 443},
// https
{"https://www.google.com/", 443},
{"https://www.google.com:443/", 443},
{"https://www.google.com:80/", 80},
// ftp
{"ftp://www.google.com/", 21},
{"ftp://www.google.com:21/", 21},
{"ftp://www.google.com:80/", 80},
// file - no port
{"file://www.google.com/", PORT_UNSPECIFIED},
{"file://www.google.com:443/", PORT_UNSPECIFIED},
// data - no port
{"data:www.google.com:90", PORT_UNSPECIFIED},
{"data:www.google.com", PORT_UNSPECIFIED},
// filesystem - no port
{"filesystem:http://www.google.com:90/t/foo", PORT_UNSPECIFIED},
{"filesystem:file:///t/foo", PORT_UNSPECIFIED},
};
for (size_t i = 0; i < std::size(port_tests); i++) {
GURL url(port_tests[i].spec);
EXPECT_EQ(port_tests[i].expected_int_port, url.EffectiveIntPort());
}
}
TEST(GURLTest, IPAddress) {
struct IPTest {
const char* spec;
bool expected_ip;
} ip_tests[] = {
{"http://www.google.com/", false},
{"http://192.168.9.1/", true},
{"http://192.168.9.1.2/", false},
{"http://192.168.m.1/", false},
{"http://2001:db8::1/", false},
{"http://[2001:db8::1]/", true},
{"", false},
{"some random input!", false},
};
for (size_t i = 0; i < std::size(ip_tests); i++) {
GURL url(ip_tests[i].spec);
EXPECT_EQ(ip_tests[i].expected_ip, url.HostIsIPAddress());
}
}
TEST(GURLTest, HostNoBrackets) {
struct TestCase {
const char* input;
const char* expected_host;
const char* expected_plainhost;
} cases[] = {
{"http://www.google.com", "www.google.com", "www.google.com"},
{"http://[2001:db8::1]/", "[2001:db8::1]", "2001:db8::1"},
{"http://[::]/", "[::]", "::"},
// Don't require a valid URL, but don't crash either.
{"http://[]/", "[]", ""},
{"http://[x]/", "[x]", "x"},
{"http://[x/", "[x", "[x"},
{"http://x]/", "x]", "x]"},
{"http://[/", "[", "["},
{"http://]/", "]", "]"},
{"", "", ""},
};
for (size_t i = 0; i < std::size(cases); i++) {
GURL url(cases[i].input);
EXPECT_EQ(cases[i].expected_host, url.host());
EXPECT_EQ(cases[i].expected_plainhost, url.HostNoBrackets());
EXPECT_EQ(cases[i].expected_plainhost, url.HostNoBracketsPiece());
}
}
TEST(GURLTest, DomainIs) {
GURL url_1("http://google.com/foo");
EXPECT_TRUE(url_1.DomainIs("google.com"));
// Subdomain and port are ignored.
GURL url_2("http://www.google.com:99/foo");
EXPECT_TRUE(url_2.DomainIs("google.com"));
// Different top-level domain.
GURL url_3("http://www.google.com.cn/foo");
EXPECT_FALSE(url_3.DomainIs("google.com"));
// Different host name.
GURL url_4("http://www.iamnotgoogle.com/foo");
EXPECT_FALSE(url_4.DomainIs("google.com"));
// The input must be lower-cased otherwise DomainIs returns false.
GURL url_5("http://www.google.com/foo");
EXPECT_FALSE(url_5.DomainIs("Google.com"));
// If the URL is invalid, DomainIs returns false.
GURL invalid_url("google.com");
EXPECT_FALSE(invalid_url.is_valid());
EXPECT_FALSE(invalid_url.DomainIs("google.com"));
GURL url_with_escape_chars("https://www.,.test");
EXPECT_TRUE(url_with_escape_chars.is_valid());
EXPECT_EQ(url_with_escape_chars.host(), "www.%2C.test");
EXPECT_TRUE(url_with_escape_chars.DomainIs("%2C.test"));
}
TEST(GURLTest, DomainIsTerminatingDotBehavior) {
// If the host part ends with a dot, it matches input domains
// with or without a dot.
GURL url_with_dot("http://www.google.com./foo");
EXPECT_TRUE(url_with_dot.DomainIs("google.com"));
EXPECT_TRUE(url_with_dot.DomainIs("google.com."));
EXPECT_TRUE(url_with_dot.DomainIs(".com"));
EXPECT_TRUE(url_with_dot.DomainIs(".com."));
// But, if the host name doesn't end with a dot and the input
// domain does, then it's considered to not match.
GURL url_without_dot("http://google.com/foo");
EXPECT_FALSE(url_without_dot.DomainIs("google.com."));
// If the URL ends with two dots, it doesn't match.
GURL url_with_two_dots("http://www.google.com../foo");
EXPECT_FALSE(url_with_two_dots.DomainIs("google.com"));
}
TEST(GURLTest, DomainIsWithFilesystemScheme) {
GURL url_1("filesystem:http://www.google.com:99/foo/");
EXPECT_TRUE(url_1.DomainIs("google.com"));
GURL url_2("filesystem:http://www.iamnotgoogle.com/foo/");
EXPECT_FALSE(url_2.DomainIs("google.com"));
}
// Newlines should be stripped from inputs.
TEST(GURLTest, Newlines) {
// Constructor.
GURL url_1(" \t ht\ntp://\twww.goo\rgle.com/as\ndf \n ");
EXPECT_EQ("http://www.google.com/asdf", url_1.spec());
EXPECT_FALSE(
url_1.parsed_for_possibly_invalid_spec().potentially_dangling_markup);
// Relative path resolver.
GURL url_2 = url_1.Resolve(" \n /fo\to\r ");
EXPECT_EQ("http://www.google.com/foo", url_2.spec());
EXPECT_FALSE(
url_2.parsed_for_possibly_invalid_spec().potentially_dangling_markup);
// Constructor.
GURL url_3(" \t ht\ntp://\twww.goo\rgle.com/as\ndf< \n ");
EXPECT_EQ("http://www.google.com/asdf%3C", url_3.spec());
EXPECT_TRUE(
url_3.parsed_for_possibly_invalid_spec().potentially_dangling_markup);
// Relative path resolver.
GURL url_4 = url_1.Resolve(" \n /fo\to<\r ");
EXPECT_EQ("http://www.google.com/foo%3C", url_4.spec());
EXPECT_TRUE(
url_4.parsed_for_possibly_invalid_spec().potentially_dangling_markup);
// Note that newlines are NOT stripped from ReplaceComponents.
}
TEST(GURLTest, IsStandard) {
GURL a("http:foo/bar");
EXPECT_TRUE(a.IsStandard());
GURL b("foo:bar/baz");
EXPECT_FALSE(b.IsStandard());
GURL c("foo://bar/baz");
EXPECT_FALSE(c.IsStandard());
GURL d("cid:bar@baz");
EXPECT_FALSE(d.IsStandard());
}
TEST(GURLTest, SchemeIsHTTPOrHTTPS) {
EXPECT_TRUE(GURL("http://bar/").SchemeIsHTTPOrHTTPS());
EXPECT_TRUE(GURL("HTTPS://BAR").SchemeIsHTTPOrHTTPS());
EXPECT_FALSE(GURL("ftp://bar/").SchemeIsHTTPOrHTTPS());
}
TEST(GURLTest, SchemeIsWSOrWSS) {
EXPECT_TRUE(GURL("WS://BAR/").SchemeIsWSOrWSS());
EXPECT_TRUE(GURL("wss://bar/").SchemeIsWSOrWSS());
EXPECT_FALSE(GURL("http://bar/").SchemeIsWSOrWSS());
}
TEST(GURLTest, SchemeIsCryptographic) {
EXPECT_TRUE(GURL("https://foo.bar.com/").SchemeIsCryptographic());
EXPECT_TRUE(GURL("HTTPS://foo.bar.com/").SchemeIsCryptographic());
EXPECT_TRUE(GURL("HtTpS://foo.bar.com/").SchemeIsCryptographic());
EXPECT_TRUE(GURL("wss://foo.bar.com/").SchemeIsCryptographic());
EXPECT_TRUE(GURL("WSS://foo.bar.com/").SchemeIsCryptographic());
EXPECT_TRUE(GURL("WsS://foo.bar.com/").SchemeIsCryptographic());
EXPECT_FALSE(GURL("http://foo.bar.com/").SchemeIsCryptographic());
EXPECT_FALSE(GURL("ws://foo.bar.com/").SchemeIsCryptographic());
}
TEST(GURLTest, SchemeIsCryptographicStatic) {
EXPECT_TRUE(GURL::SchemeIsCryptographic("https"));
EXPECT_TRUE(GURL::SchemeIsCryptographic("wss"));
EXPECT_FALSE(GURL::SchemeIsCryptographic("http"));
EXPECT_FALSE(GURL::SchemeIsCryptographic("ws"));
EXPECT_FALSE(GURL::SchemeIsCryptographic("ftp"));
}
TEST(GURLTest, SchemeIsBlob) {
EXPECT_TRUE(GURL("BLOB://BAR/").SchemeIsBlob());
EXPECT_TRUE(GURL("blob://bar/").SchemeIsBlob());
EXPECT_FALSE(GURL("http://bar/").SchemeIsBlob());
}
TEST(GURLTest, SchemeIsLocal) {
EXPECT_TRUE(GURL("BLOB://BAR/").SchemeIsLocal());
EXPECT_TRUE(GURL("blob://bar/").SchemeIsLocal());
EXPECT_TRUE(GURL("DATA:TEXT/HTML,BAR").SchemeIsLocal());
EXPECT_TRUE(GURL("data:text/html,bar").SchemeIsLocal());
EXPECT_TRUE(GURL("ABOUT:BAR").SchemeIsLocal());
EXPECT_TRUE(GURL("about:bar").SchemeIsLocal());
EXPECT_TRUE(GURL("FILESYSTEM:HTTP://FOO.EXAMPLE/BAR").SchemeIsLocal());
EXPECT_TRUE(GURL("filesystem:http://foo.example/bar").SchemeIsLocal());
EXPECT_FALSE(GURL("http://bar/").SchemeIsLocal());
EXPECT_FALSE(GURL("file:///bar").SchemeIsLocal());
}
// Tests that the 'content' of the URL is properly extracted. This can be
// complex in cases such as multiple schemes (view-source:http:) or for
// javascript URLs. See GURL::GetContent for more details.
TEST(GURLTest, ContentForNonStandardURLs) {
struct TestCase {
const char* url;
const char* expected;
} cases[] = {
{"null", ""},
{"not-a-standard-scheme:this is arbitrary content",
"this is arbitrary content"},
// When there are multiple schemes, only the first is excluded from the
// content. Note also that for e.g. 'http://', the '//' is part of the
// content not the scheme.
{"view-source:http://example.com/path", "http://example.com/path"},
{"blob:http://example.com/GUID", "http://example.com/GUID"},
{"blob://http://example.com/GUID", "//http://example.com/GUID"},
{"blob:http://user:password@example.com/GUID",
"http://user:password@example.com/GUID"},
// The octothorpe character ('#') marks the end of the URL content, and
// the start of the fragment. It should not be included in the content.
{"http://www.example.com/GUID#ref", "www.example.com/GUID"},
{"http://me:secret@example.com/GUID/#ref", "me:secret@example.com/GUID/"},
{"data:text/html,Question?<div style=\"color: #bad\">idea</div>",
"text/html,Question?%3Cdiv%20style=%22color:%20"},
// TODO(mkwst): This seems like a bug. https://crbug.com/513600
{"filesystem:http://example.com/path", "/"},
// Javascript URLs include '#' symbols in their content.
{"javascript:#", "#"},