File: url_pattern.cc

package info (click to toggle)
chromium 139.0.7258.127-1
  • links: PTS, VCS
  • area: main
  • in suites:
  • size: 6,122,068 kB
  • sloc: cpp: 35,100,771; ansic: 7,163,530; javascript: 4,103,002; python: 1,436,920; asm: 946,517; xml: 746,709; pascal: 187,653; perl: 88,691; sh: 88,436; objc: 79,953; sql: 51,488; cs: 44,583; fortran: 24,137; makefile: 22,147; tcl: 15,277; php: 13,980; yacc: 8,984; ruby: 7,485; awk: 3,720; lisp: 3,096; lex: 1,327; ada: 727; jsp: 228; sed: 36
file content (858 lines) | stat: -rw-r--r-- 26,110 bytes parent folder | download | duplicates (3)
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
// Copyright 2012 The Chromium Authors
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

#ifdef UNSAFE_BUFFERS_BUILD
// TODO(crbug.com/390223051): Remove C-library calls to fix the errors.
#pragma allow_unsafe_libc_calls
#endif

#include "extensions/common/url_pattern.h"

#include <stddef.h>

#include <array>
#include <ostream>
#include <string_view>

#include "base/containers/contains.h"
#include "base/strings/pattern.h"
#include "base/strings/strcat.h"
#include "base/strings/string_number_conversions.h"
#include "base/strings/string_split.h"
#include "base/strings/string_util.h"
#include "content/public/common/url_constants.h"
#include "extensions/common/constants.h"
#include "net/base/registry_controlled_domains/registry_controlled_domain.h"
#include "net/base/url_util.h"
#include "url/gurl.h"
#include "url/url_util.h"

const char URLPattern::kAllUrlsPattern[] = "<all_urls>";

namespace {

// TODO(aa): What about more obscure schemes like javascript: ?
// Note: keep this array in sync with kValidSchemeMasks.
constexpr std::array kValidSchemes = {
    url::kHttpScheme,          url::kHttpsScheme,
    url::kFileScheme,          url::kFtpScheme,
    content::kChromeUIScheme,  extensions::kExtensionScheme,
    url::kFileSystemScheme,    url::kWsScheme,
    url::kWssScheme,           url::kDataScheme,
    url::kUuidInPackageScheme,
};

constexpr std::array kValidSchemeMasks = {
    URLPattern::SCHEME_HTTP,
    URLPattern::SCHEME_HTTPS,
    URLPattern::SCHEME_FILE,
    URLPattern::SCHEME_FTP,
    URLPattern::SCHEME_CHROMEUI,
    URLPattern::SCHEME_EXTENSION,
    URLPattern::SCHEME_FILESYSTEM,
    URLPattern::SCHEME_WS,
    URLPattern::SCHEME_WSS,
    URLPattern::SCHEME_DATA,
    URLPattern::SCHEME_UUID_IN_PACKAGE,
};

static_assert(std::size(kValidSchemes) == std::size(kValidSchemeMasks),
              "must keep these arrays in sync");

const char kParseSuccess[] = "Success.";
const char kParseErrorMissingSchemeSeparator[] = "Missing scheme separator.";
const char kParseErrorInvalidScheme[] = "Invalid scheme.";
const char kParseErrorWrongSchemeType[] = "Wrong scheme type.";
const char kParseErrorEmptyHost[] = "Host can not be empty.";
const char kParseErrorInvalidHostWildcard[] = "Invalid host wildcard.";
const char kParseErrorEmptyPath[] = "Empty path.";
const char kParseErrorInvalidPort[] = "Invalid port.";
const char kParseErrorInvalidHost[] = "Invalid host.";

// Message explaining each URLPattern::ParseResult.
constexpr std::array kParseResultMessages = {
    kParseSuccess,
    kParseErrorMissingSchemeSeparator,
    kParseErrorInvalidScheme,
    kParseErrorWrongSchemeType,
    kParseErrorEmptyHost,
    kParseErrorInvalidHostWildcard,
    kParseErrorEmptyPath,
    kParseErrorInvalidPort,
    kParseErrorInvalidHost,
};

static_assert(static_cast<int>(URLPattern::ParseResult::kNumParseResults) ==
                  std::size(kParseResultMessages),
              "must add message for each parse result");

const char kPathSeparator[] = "/";

bool IsStandardScheme(std::string_view scheme) {
  // "*" gets the same treatment as a standard scheme.
  if (scheme == "*") {
    return true;
  }

  return url::IsStandard(scheme);
}

bool IsValidPortForScheme(std::string_view scheme, std::string_view port) {
  if (port == "*") {
    return true;
  }

  // Only accept non-wildcard ports if the scheme uses ports.
  if (url::DefaultPortForScheme(scheme) == url::PORT_UNSPECIFIED) {
    return false;
  }

  int parsed_port = url::PORT_UNSPECIFIED;
  if (!base::StringToInt(port, &parsed_port)) {
    return false;
  }
  return (parsed_port >= 0) && (parsed_port < 65536);
}

// Returns |path| with the trailing wildcard stripped if one existed.
//
// The functions that rely on this (OverlapsWith and Contains) are only
// called for the patterns inside URLPatternSet. In those cases, we know that
// the path will have only a single wildcard at the end. This makes figuring
// out overlap much easier. It seems like there is probably a computer-sciency
// way to solve the general case, but we don't need that yet.
std::string_view StripTrailingWildcard(std::string_view path) {
  if (base::EndsWith(path, "*")) {
    path.remove_suffix(1);
  }
  return path;
}

// Removes trailing dot from |host_piece| if any.
std::string_view CanonicalizeHostForMatching(std::string_view host_piece) {
  if (base::EndsWith(host_piece, ".")) {
    host_piece.remove_suffix(1);
  }
  return host_piece;
}

}  // namespace

// static
bool URLPattern::IsValidSchemeForExtensions(std::string_view scheme) {
  for (auto* valid_scheme : kValidSchemes) {
    if (scheme == valid_scheme) {
      return true;
    }
  }
  return false;
}

// static
int URLPattern::GetValidSchemeMaskForExtensions() {
  int result = 0;
  for (int valid_scheme_mask : kValidSchemeMasks) {
    result |= valid_scheme_mask;
  }
  return result;
}

URLPattern::URLPattern()
    : valid_schemes_(SCHEME_NONE),
      match_all_urls_(false),
      match_subdomains_(false),
      port_("*") {}

URLPattern::URLPattern(int valid_schemes)
    : valid_schemes_(valid_schemes),
      match_all_urls_(false),
      match_subdomains_(false),
      port_("*") {}

URLPattern::URLPattern(int valid_schemes, std::string_view pattern)
    // Strict error checking is used, because this constructor is only
    // appropriate when we know |pattern| is valid.
    : valid_schemes_(valid_schemes),
      match_all_urls_(false),
      match_subdomains_(false),
      port_("*") {
  ParseResult result = Parse(pattern);
  DCHECK_EQ(ParseResult::kSuccess, result)
      << "Parsing unexpectedly failed for pattern: " << pattern << ": "
      << GetParseResultString(result);
}

URLPattern::URLPattern(const URLPattern& other) = default;

URLPattern::URLPattern(URLPattern&& other) = default;

URLPattern::~URLPattern() = default;

URLPattern& URLPattern::operator=(const URLPattern& other) = default;

URLPattern& URLPattern::operator=(URLPattern&& other) = default;

std::ostream& operator<<(std::ostream& out, const URLPattern& url_pattern) {
  return out << '"' << url_pattern.GetAsString() << '"';
}

URLPattern::ParseResult URLPattern::Parse(std::string_view pattern) {
  spec_.clear();
  SetMatchAllURLs(false);
  SetMatchSubdomains(false);
  SetPort("*");

  // Special case pattern to match every valid URL.
  if (pattern == kAllUrlsPattern) {
    SetMatchAllURLs(true);
    return ParseResult::kSuccess;
  }

  // Parse out the scheme.
  size_t scheme_end_pos = pattern.find(url::kStandardSchemeSeparator);
  bool has_standard_scheme_separator = true;

  // Some urls also use ':' alone as the scheme separator.
  if (scheme_end_pos == std::string_view::npos) {
    scheme_end_pos = pattern.find(':');
    has_standard_scheme_separator = false;
  }

  if (scheme_end_pos == std::string_view::npos) {
    return ParseResult::kMissingSchemeSeparator;
  }

  if (!SetScheme(pattern.substr(0, scheme_end_pos))) {
    return ParseResult::kInvalidScheme;
  }

  bool standard_scheme = IsStandardScheme(scheme_);
  if (standard_scheme != has_standard_scheme_separator) {
    return ParseResult::kWrongSchemeSeparator;
  }

  // Advance past the scheme separator.
  scheme_end_pos +=
      (standard_scheme ? strlen(url::kStandardSchemeSeparator) : 1);
  if (scheme_end_pos >= pattern.size()) {
    return ParseResult::kEmptyHost;
  }

  // Parse out the host and path.
  size_t host_start_pos = scheme_end_pos;
  size_t path_start_pos = 0;

  if (!standard_scheme) {
    path_start_pos = host_start_pos;
  } else if (scheme_ == url::kFileScheme) {
    size_t host_end_pos = pattern.find(kPathSeparator, host_start_pos);
    if (host_end_pos == std::string_view::npos) {
      // Allow hostname omission.
      // e.g. file://* is interpreted as file:///*,
      // file://foo* is interpreted as file:///foo*.
      path_start_pos = host_start_pos - 1;
    } else {
      // Ignore hostname if scheme is file://.
      // e.g. file://localhost/foo is equal to file:///foo.
      path_start_pos = host_end_pos;
    }
  } else {
    size_t host_end_pos = pattern.find(kPathSeparator, host_start_pos);

    // Host is required.
    if (host_start_pos == host_end_pos) {
      return ParseResult::kEmptyHost;
    }

    if (host_end_pos == std::string_view::npos) {
      return ParseResult::kEmptyPath;
    }

    std::string_view host_and_port =
        pattern.substr(host_start_pos, host_end_pos - host_start_pos);

    size_t port_separator_pos = std::string_view::npos;
    if (host_and_port[0] != '[') {
      // Not IPv6 (either IPv4 or just a normal address).
      port_separator_pos = host_and_port.find(':');
    } else {  // IPv6.
      size_t ipv6_host_end_pos = host_and_port.find(']');
      if (ipv6_host_end_pos == std::string_view::npos) {
        return ParseResult::kInvalidHost;
      }
      if (ipv6_host_end_pos == 1) {
        return ParseResult::kEmptyHost;
      }

      if (ipv6_host_end_pos < host_and_port.length() - 1) {
        // The host isn't the only component. Check for a port. This would
        // require a ':' to follow the closing ']' from the host.
        if (host_and_port[ipv6_host_end_pos + 1] != ':') {
          return ParseResult::kInvalidHost;
        }

        port_separator_pos = ipv6_host_end_pos + 1;
      }
    }

    if (port_separator_pos != std::string_view::npos &&
        !SetPort(host_and_port.substr(port_separator_pos + 1))) {
      return ParseResult::kInvalidPort;
    }

    // Note: this substr() will be the entire string if the port position
    // wasn't found.
    std::string_view host_piece = host_and_port.substr(0, port_separator_pos);

    if (host_piece.empty()) {
      return ParseResult::kEmptyHost;
    }

    if (host_piece == "*") {
      match_subdomains_ = true;
      host_piece = std::string_view();
    } else if (base::StartsWith(host_piece, "*.")) {
      if (host_piece.length() == 2) {
        // We don't allow just '*.' as a host.
        return ParseResult::kEmptyHost;
      }
      match_subdomains_ = true;
      host_piece = host_piece.substr(2);
    }

    host_ = std::string(host_piece);

    path_start_pos = host_end_pos;
  }

  SetPath(pattern.substr(path_start_pos));

  // No other '*' can occur in the host, though. This isn't necessary, but is
  // done as a convenience to developers who might otherwise be confused and
  // think '*' works as a glob in the host.
  if (base::Contains(host_, '*')) {
    return ParseResult::kInvalidHostWildcard;
  }

  if (!host_.empty()) {
    // If |host_| is present (i.e., isn't a wildcard), we need to canonicalize
    // it.
    url::CanonHostInfo host_info;
    host_ = net::CanonicalizeHost(host_, &host_info);
    // net::CanonicalizeHost() returns an empty string on failure.
    if (host_.empty()) {
      return ParseResult::kInvalidHost;
    }
  }

  // Null characters are not allowed in hosts.
  if (base::Contains(host_, '\0')) {
    return ParseResult::kInvalidHost;
  }

  return ParseResult::kSuccess;
}

void URLPattern::SetValidSchemes(int valid_schemes) {
  // TODO(devlin): Should we check that valid_schemes agrees with |scheme_|
  // here? Otherwise, valid_schemes_ and schemes_ may stop agreeing with each
  // other (e.g., in the case of `*://*/*`, where the scheme should only be
  // http or https).
  spec_.clear();
  valid_schemes_ = valid_schemes;
}

void URLPattern::SetHost(std::string_view host) {
  spec_.clear();
  host_ = host;
}

void URLPattern::SetMatchAllURLs(bool val) {
  spec_.clear();
  match_all_urls_ = val;

  if (val) {
    match_subdomains_ = true;
    scheme_ = "*";
    host_.clear();
    SetPath("/*");
  }
}

void URLPattern::SetMatchSubdomains(bool val) {
  spec_.clear();
  match_subdomains_ = val;
}

bool URLPattern::SetScheme(std::string_view scheme) {
  spec_.clear();
  scheme_ = scheme;
  if (scheme_ == "*") {
    valid_schemes_ &= (SCHEME_HTTP | SCHEME_HTTPS);
  } else if (!IsValidScheme(scheme_)) {
    return false;
  }
  return true;
}

bool URLPattern::IsValidScheme(std::string_view scheme) const {
  if (valid_schemes_ == SCHEME_ALL) {
    return true;
  }

  for (size_t i = 0; i < std::size(kValidSchemes); ++i) {
    if (scheme == kValidSchemes[i] && (valid_schemes_ & kValidSchemeMasks[i])) {
      return true;
    }
  }

  return false;
}

void URLPattern::SetPath(std::string_view path) {
  spec_.clear();
  path_ = path;
  path_escaped_ = path_;
  base::ReplaceSubstringsAfterOffset(&path_escaped_, 0, "\\", "\\\\");
  base::ReplaceSubstringsAfterOffset(&path_escaped_, 0, "?", "\\?");
}

bool URLPattern::SetPort(std::string_view port) {
  spec_.clear();
  if (IsValidPortForScheme(scheme_, port)) {
    port_ = port;
    return true;
  }
  return false;
}

bool URLPattern::MatchesURL(const GURL& test) const {
  // Invalid URLs can never match.
  if (!test.is_valid()) {
    return false;
  }

  const GURL* test_url = &test;
  bool has_inner_url = test.inner_url() != nullptr;

  if (has_inner_url) {
    if (!test.SchemeIsFileSystem()) {
      return false;  // The only nested URLs we handle are filesystem URLs.
    }
    test_url = test.inner_url();
  }

  // Ensure the scheme matches first, since <all_urls> may not match this URL if
  // the scheme is excluded.
  if (!MatchesScheme(test_url->scheme_piece())) {
    return false;
  }

  if (match_all_urls_) {
    return true;
  }

  // Unless |match_all_urls_| is true, the grammar only permits matching
  // URLs with nonempty paths.
  if (!test.has_path()) {
    return false;
  }

  std::string path_for_request = test.PathForRequest();
  if (has_inner_url) {
    path_for_request = base::StrCat({test_url->path_piece(), path_for_request});
  }

  return MatchesSecurityOriginHelper(*test_url) &&
         MatchesPath(path_for_request);
}

bool URLPattern::MatchesSecurityOrigin(const GURL& test) const {
  const GURL* test_url = &test;
  bool has_inner_url = test.inner_url() != nullptr;

  if (has_inner_url) {
    if (!test.SchemeIsFileSystem()) {
      return false;  // The only nested URLs we handle are filesystem URLs.
    }
    test_url = test.inner_url();
  }

  if (!MatchesScheme(test_url->scheme())) {
    return false;
  }

  if (match_all_urls_) {
    return true;
  }

  return MatchesSecurityOriginHelper(*test_url);
}

bool URLPattern::MatchesScheme(std::string_view test) const {
  if (!IsValidScheme(test)) {
    return false;
  }

  return scheme_ == "*" || test == scheme_;
}

bool URLPattern::MatchesHost(std::string_view host) const {
  // TODO(devlin): This is a bit sad. Parsing urls is expensive. However, it's
  // important that we do this conversion to a GURL in order to canonicalize the
  // host (the pattern's host_ already is canonicalized from Parse()). We can't
  // just do string comparison.
  return MatchesHost(GURL(base::StrCat(
      {url::kHttpScheme, url::kStandardSchemeSeparator, host, "/"})));
}

bool URLPattern::MatchesHost(const GURL& test) const {
  std::string_view test_host(CanonicalizeHostForMatching(test.host_piece()));
  const std::string_view pattern_host(CanonicalizeHostForMatching(host_));

  // If the hosts are exactly equal, we have a match.
  if (test_host == pattern_host) {
    return true;
  }

  // If we're matching subdomains, and we have no host in the match pattern,
  // that means that we're matching all hosts, which means we have a match no
  // matter what the test host is.
  if (match_subdomains_ && pattern_host.empty()) {
    return true;
  }

  // Otherwise, we can only match if our match pattern matches subdomains.
  if (!match_subdomains_) {
    return false;
  }

  // We don't do subdomain matching against IP addresses, so we can give up now
  // if the test host is an IP address.
  if (test.HostIsIPAddress()) {
    return false;
  }

  // Check if the test host is a subdomain of our host.
  if (test_host.length() <= (pattern_host.length() + 1)) {
    return false;
  }

  if (!base::EndsWith(test_host, pattern_host)) {
    return false;
  }

  return test_host[test_host.length() - pattern_host.length() - 1] == '.';
}

bool URLPattern::MatchesEffectiveTld(
    net::registry_controlled_domains::PrivateRegistryFilter private_filter,
    net::registry_controlled_domains::UnknownRegistryFilter unknown_filter)
    const {
  // Check if it matches all urls or is a pattern like http://*/*.
  if (match_all_urls_ || (match_subdomains_ && host_.empty())) {
    return true;
  }

  // If this doesn't even match subdomains, it can't possibly be a TLD wildcard.
  if (!match_subdomains_) {
    return false;
  }

  // If there was more than just a TLD in the host (e.g., *.foobar.com), it
  // doesn't match all hosts in an effective TLD.
  if (net::registry_controlled_domains::HostHasRegistryControlledDomain(
          host_, unknown_filter, private_filter)) {
    return false;
  }

  // At this point the host could either be just a TLD ("com") or some unknown
  // TLD-like string ("notatld"). To disambiguate between them construct a
  // fake URL, and check the registry.
  //
  // If we recognized this TLD, then this is a pattern like *.com, and it
  // matches an effective TLD.
  return net::registry_controlled_domains::HostHasRegistryControlledDomain(
      "notatld." + host_, unknown_filter, private_filter);
}

bool URLPattern::MatchesSingleOrigin() const {
  // Strictly speaking, the port is part of the origin, but in URLPattern it
  // defaults to *. It's not very interesting anyway, so leave it out.
  return !MatchesEffectiveTld() && scheme_ != "*" && !match_subdomains_;
}

bool URLPattern::MatchesPath(std::string_view test) const {
  // Make the behaviour of OverlapsWith consistent with MatchesURL, which is
  // need to match hosted apps on e.g. 'google.com' also run on 'google.com/'.
  // The below if is a no-copy way of doing (test + "/*" == path_escaped_).
  if (path_escaped_.length() == test.length() + 2 &&
      base::StartsWith(path_escaped_.c_str(), test) &&
      base::EndsWith(path_escaped_, "/*")) {
    return true;
  }

  return base::MatchPattern(test, path_escaped_);
}

const std::string& URLPattern::GetAsString() const {
  if (!spec_.empty()) {
    return spec_;
  }

  if (match_all_urls_) {
    spec_ = kAllUrlsPattern;
    return spec_;
  }

  bool standard_scheme = IsStandardScheme(scheme_);

  std::string spec = scheme_ +
      (standard_scheme ? url::kStandardSchemeSeparator : ":");

  if (scheme_ != url::kFileScheme && standard_scheme) {
    if (match_subdomains_) {
      spec += "*";
      if (!host_.empty()) {
        spec += ".";
      }
    }

    if (!host_.empty()) {
      spec += host_;
    }

    if (port_ != "*") {
      spec += ":";
      spec += port_;
    }
  }

  if (!path_.empty()) {
    spec += path_;
  }

  spec_ = std::move(spec);
  return spec_;
}

bool URLPattern::OverlapsWith(const URLPattern& other) const {
  if (match_all_urls() || other.match_all_urls()) {
    return true;
  }
  return (MatchesAnyScheme(other.GetExplicitSchemes()) ||
          other.MatchesAnyScheme(GetExplicitSchemes()))
      && (MatchesHost(other.host()) || other.MatchesHost(host()))
      && (MatchesPortPattern(other.port()) || other.MatchesPortPattern(port()))
      && (MatchesPath(StripTrailingWildcard(other.path())) ||
          other.MatchesPath(StripTrailingWildcard(path())));
}

bool URLPattern::Contains(const URLPattern& other) const {
  // Important: it's not enough to just check match_all_urls(); we also need to
  // make sure that the schemes in this pattern are a superset of those in
  // |other|.
  if (match_all_urls() &&
      (valid_schemes_ & other.valid_schemes_) == other.valid_schemes_) {
    return true;
  }

  return MatchesAllSchemes(other.GetExplicitSchemes()) &&
         MatchesHost(other.host()) &&
         (!other.match_subdomains_ || match_subdomains_) &&
         MatchesPortPattern(other.port()) &&
         MatchesPath(StripTrailingWildcard(other.path()));
}

std::optional<URLPattern> URLPattern::CreateIntersection(
    const URLPattern& other) const {
  // Easy case: Schemes don't overlap. Return nullopt.
  int intersection_schemes = URLPattern::SCHEME_NONE;
  if (valid_schemes_ == URLPattern::SCHEME_ALL) {
    intersection_schemes = other.valid_schemes_;
  } else if (other.valid_schemes_ == URLPattern::SCHEME_ALL) {
    intersection_schemes = valid_schemes_;
  } else {
    intersection_schemes = valid_schemes_ & other.valid_schemes_;
  }

  if (intersection_schemes == URLPattern::SCHEME_NONE) {
    return std::nullopt;
  }

  {
    // In a few cases, we can (mostly) return a copy of one of the patterns.
    // This can happen when either:
    // - The URLPattern's are identical (possibly excluding valid_schemes_)
    // - One of the patterns has match_all_urls() equal to true.
    // NOTE(devlin): Theoretically, we could use Contains() instead of
    // match_all_urls() here. However, Contains() strips the trailing wildcard
    // from the path, which could yield the incorrect result.
    const URLPattern* copy_source = nullptr;
    if (*this == other || other.match_all_urls()) {
      copy_source = this;
    } else if (match_all_urls()) {
      copy_source = &other;
    }

    if (copy_source) {
      // NOTE: equality checks don't take into account valid_schemes_, and
      // schemes can be different in the case of match_all_urls() as well, so
      // we can't always just return *copy_source.
      if (intersection_schemes == copy_source->valid_schemes_) {
        return *copy_source;
      }
      URLPattern result(intersection_schemes);
      ParseResult parse_result = result.Parse(copy_source->GetAsString());
      CHECK_EQ(ParseResult::kSuccess, parse_result);
      return result;
    }
  }

  // No more easy cases. Go through component by component to find the patterns
  // that intersect.

  // Note: Alias the function type (rather than using auto) because
  // MatchesHost() is overloaded.
  using match_function_type = bool (URLPattern::*)(std::string_view) const;

  auto get_intersection = [this, &other](std::string_view own_str,
                                         std::string_view other_str,
                                         match_function_type match_function,
                                         std::string_view* out) {
    if ((this->*match_function)(other_str)) {
      *out = other_str;
      return true;
    }
    if ((other.*match_function)(own_str)) {
      *out = own_str;
      return true;
    }
    return false;
  };

  std::string_view scheme;
  std::string_view host;
  std::string_view port;
  std::string_view path;
  // If any pieces fail to overlap, then there is no intersection.
  if (!get_intersection(scheme_, other.scheme_, &URLPattern::MatchesScheme,
                        &scheme) ||
      !get_intersection(host_, other.host_, &URLPattern::MatchesHost, &host) ||
      !get_intersection(port_, other.port_, &URLPattern::MatchesPortPattern,
                        &port) ||
      !get_intersection(path_, other.path_, &URLPattern::MatchesPath, &path)) {
    return std::nullopt;
  }

  // Only match subdomains if both patterns match subdomains.
  std::string_view subdomains;
  if (match_subdomains_ && other.match_subdomains_) {
    // The host may be empty (e.g., in the case of *://*/* - in that case, only
    // append '*' instead of '*.'.
    subdomains = host.empty() ? "*" : "*.";
  }

  std::string_view scheme_separator =
      IsStandardScheme(scheme) ? url::kStandardSchemeSeparator : ":";

  std::string pattern_str = base::StrCat(
      {scheme, scheme_separator, subdomains, host, ":", port, path});

  URLPattern pattern(intersection_schemes);
  ParseResult result = pattern.Parse(pattern_str);
  // TODO(devlin): I don't think there's any way this should ever fail, but
  // use a CHECK() to flush any cases out. If nothing crops up, downgrade this
  // to a DCHECK in M72.
  CHECK_EQ(ParseResult::kSuccess, result);

  return pattern;
}

bool URLPattern::MatchesAnyScheme(
    const std::vector<std::string>& schemes) const {
  for (const auto& scheme : schemes) {
    if (MatchesScheme(scheme)) {
      return true;
    }
  }

  return false;
}

bool URLPattern::MatchesAllSchemes(
    const std::vector<std::string>& schemes) const {
  for (const auto& scheme : schemes) {
    if (!MatchesScheme(scheme)) {
      return false;
    }
  }

  return true;
}

bool URLPattern::MatchesSecurityOriginHelper(const GURL& test) const {
  // Ignore hostname if scheme is file://.
  if (scheme_ != url::kFileScheme && !MatchesHost(test)) {
    return false;
  }

  if (!MatchesPortPattern(base::NumberToString(test.EffectiveIntPort()))) {
    return false;
  }

  return true;
}

bool URLPattern::MatchesPortPattern(std::string_view port) const {
  return port_ == "*" || port_ == port;
}

std::vector<std::string> URLPattern::GetExplicitSchemes() const {
  std::vector<std::string> result;
  const bool is_wildcard_scheme = (scheme_ == "*");

  if (!is_wildcard_scheme && !match_all_urls_ && IsValidScheme(scheme_)) {
    result.push_back(scheme_);
    return result;
  }

  result.reserve(std::size(kValidSchemes));
  for (size_t i = 0; i < std::size(kValidSchemes); ++i) {
    const bool is_valid_scheme = (valid_schemes_ == SCHEME_ALL ||
                                  (valid_schemes_ & kValidSchemeMasks[i]));
    if (!is_valid_scheme) {
      continue;
    }

    const bool scheme_matches =
        (is_wildcard_scheme || kValidSchemes[i] == scheme_);
    if (scheme_matches) {
      result.push_back(kValidSchemes[i]);
    }
  }

  return result;
}

std::vector<URLPattern> URLPattern::ConvertToExplicitSchemes() const {
  std::vector<std::string> explicit_schemes = GetExplicitSchemes();
  std::vector<URLPattern> result;

  for (std::vector<std::string>::const_iterator i = explicit_schemes.begin();
       i != explicit_schemes.end(); ++i) {
    URLPattern temp = *this;
    temp.SetScheme(*i);
    temp.SetMatchAllURLs(false);
    result.push_back(temp);
  }

  return result;
}

// static
const char* URLPattern::GetParseResultString(
    URLPattern::ParseResult parse_result) {
  return kParseResultMessages[static_cast<int>(parse_result)];
}