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
|
// Copyright (c) 2012 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "extensions/common/url_pattern.h"
#include "base/strings/string_number_conversions.h"
#include "base/strings/string_piece.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 "url/gurl.h"
#include "url/url_util.h"
const char URLPattern::kAllUrlsPattern[] = "<all_urls>";
namespace {
// TODO(aa): What about more obscure schemes like data: and javascript: ?
// Note: keep this array in sync with kValidSchemeMasks.
const char* kValidSchemes[] = {
content::kHttpScheme,
content::kHttpsScheme,
content::kFileScheme,
content::kFtpScheme,
content::kChromeUIScheme,
extensions::kExtensionScheme,
content::kFileSystemScheme,
};
const int kValidSchemeMasks[] = {
URLPattern::SCHEME_HTTP,
URLPattern::SCHEME_HTTPS,
URLPattern::SCHEME_FILE,
URLPattern::SCHEME_FTP,
URLPattern::SCHEME_CHROMEUI,
URLPattern::SCHEME_EXTENSION,
URLPattern::SCHEME_FILESYSTEM,
};
COMPILE_ASSERT(arraysize(kValidSchemes) == arraysize(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.";
// Message explaining each URLPattern::ParseResult.
const char* const kParseResultMessages[] = {
kParseSuccess,
kParseErrorMissingSchemeSeparator,
kParseErrorInvalidScheme,
kParseErrorWrongSchemeType,
kParseErrorEmptyHost,
kParseErrorInvalidHostWildcard,
kParseErrorEmptyPath,
kParseErrorInvalidPort,
};
COMPILE_ASSERT(URLPattern::NUM_PARSE_RESULTS == arraysize(kParseResultMessages),
must_add_message_for_each_parse_result);
const char kPathSeparator[] = "/";
bool IsStandardScheme(const std::string& scheme) {
// "*" gets the same treatment as a standard scheme.
if (scheme == "*")
return true;
return url::IsStandard(scheme.c_str(),
url::Component(0, static_cast<int>(scheme.length())));
}
bool IsValidPortForScheme(const std::string& scheme, const std::string& port) {
if (port == "*")
return true;
// Only accept non-wildcard ports if the scheme uses ports.
if (url::DefaultPortForScheme(scheme.c_str(), scheme.length()) ==
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 StripTrailingWildcard(const std::string& path) {
size_t wildcard_index = path.find('*');
size_t path_last = path.size() - 1;
DCHECK(wildcard_index == std::string::npos || wildcard_index == path_last);
return wildcard_index == path_last ? path.substr(0, path_last) : path;
}
} // namespace
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, const std::string& 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);
if (PARSE_SUCCESS != result)
NOTREACHED() << "URLPattern invalid: " << pattern << " result " << result;
}
URLPattern::~URLPattern() {
}
bool URLPattern::operator<(const URLPattern& other) const {
return GetAsString() < other.GetAsString();
}
bool URLPattern::operator>(const URLPattern& other) const {
return GetAsString() > other.GetAsString();
}
bool URLPattern::operator==(const URLPattern& other) const {
return GetAsString() == other.GetAsString();
}
URLPattern::ParseResult URLPattern::Parse(const std::string& pattern) {
spec_.clear();
SetMatchAllURLs(false);
SetMatchSubdomains(false);
SetPort("*");
// Special case pattern to match every valid URL.
if (pattern == kAllUrlsPattern) {
SetMatchAllURLs(true);
return PARSE_SUCCESS;
}
// Parse out the scheme.
size_t scheme_end_pos = pattern.find(content::kStandardSchemeSeparator);
bool has_standard_scheme_separator = true;
// Some urls also use ':' alone as the scheme separator.
if (scheme_end_pos == std::string::npos) {
scheme_end_pos = pattern.find(':');
has_standard_scheme_separator = false;
}
if (scheme_end_pos == std::string::npos)
return PARSE_ERROR_MISSING_SCHEME_SEPARATOR;
if (!SetScheme(pattern.substr(0, scheme_end_pos)))
return PARSE_ERROR_INVALID_SCHEME;
bool standard_scheme = IsStandardScheme(scheme_);
if (standard_scheme != has_standard_scheme_separator)
return PARSE_ERROR_WRONG_SCHEME_SEPARATOR;
// Advance past the scheme separator.
scheme_end_pos +=
(standard_scheme ? strlen(content::kStandardSchemeSeparator) : 1);
if (scheme_end_pos >= pattern.size())
return PARSE_ERROR_EMPTY_HOST;
// 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_ == content::kFileScheme) {
size_t host_end_pos = pattern.find(kPathSeparator, host_start_pos);
if (host_end_pos == std::string::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 PARSE_ERROR_EMPTY_HOST;
if (host_end_pos == std::string::npos)
return PARSE_ERROR_EMPTY_PATH;
host_ = pattern.substr(host_start_pos, host_end_pos - host_start_pos);
// The first component can optionally be '*' to match all subdomains.
std::vector<std::string> host_components;
base::SplitString(host_, '.', &host_components);
if (host_components[0] == "*") {
match_subdomains_ = true;
host_components.erase(host_components.begin(),
host_components.begin() + 1);
}
host_ = JoinString(host_components, '.');
path_start_pos = host_end_pos;
}
SetPath(pattern.substr(path_start_pos));
size_t port_pos = host_.find(':');
if (port_pos != std::string::npos) {
if (!SetPort(host_.substr(port_pos + 1)))
return PARSE_ERROR_INVALID_PORT;
host_ = host_.substr(0, port_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 (host_.find('*') != std::string::npos)
return PARSE_ERROR_INVALID_HOST_WILDCARD;
return PARSE_SUCCESS;
}
void URLPattern::SetValidSchemes(int valid_schemes) {
spec_.clear();
valid_schemes_ = valid_schemes;
}
void URLPattern::SetHost(const std::string& 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(const std::string& scheme) {
spec_.clear();
scheme_ = scheme;
if (scheme_ == "*") {
valid_schemes_ &= (SCHEME_HTTP | SCHEME_HTTPS);
} else if (!IsValidScheme(scheme_)) {
return false;
}
return true;
}
bool URLPattern::IsValidScheme(const std::string& scheme) const {
if (valid_schemes_ == SCHEME_ALL)
return true;
for (size_t i = 0; i < arraysize(kValidSchemes); ++i) {
if (scheme == kValidSchemes[i] && (valid_schemes_ & kValidSchemeMasks[i]))
return true;
}
return false;
}
void URLPattern::SetPath(const std::string& path) {
spec_.clear();
path_ = path;
path_escaped_ = path_;
ReplaceSubstringsAfterOffset(&path_escaped_, 0, "\\", "\\\\");
ReplaceSubstringsAfterOffset(&path_escaped_, 0, "?", "\\?");
}
bool URLPattern::SetPort(const std::string& port) {
spec_.clear();
if (IsValidPortForScheme(scheme_, port)) {
port_ = port;
return true;
}
return false;
}
bool URLPattern::MatchesURL(const GURL& test) const {
const GURL* test_url = &test;
bool has_inner_url = test.inner_url() != NULL;
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;
std::string path_for_request = test.PathForRequest();
if (has_inner_url)
path_for_request = test_url->path() + 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() != NULL;
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(const std::string& test) const {
if (!IsValidScheme(test))
return false;
return scheme_ == "*" || test == scheme_;
}
bool URLPattern::MatchesHost(const std::string& host) const {
std::string test(content::kHttpScheme);
test += content::kStandardSchemeSeparator;
test += host;
test += "/";
return MatchesHost(GURL(test));
}
bool URLPattern::MatchesHost(const GURL& test) const {
// If the hosts are exactly equal, we have a match.
if (test.host() == 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_ && 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() <= (host_.length() + 1))
return false;
if (test.host().compare(test.host().length() - host_.length(),
host_.length(), host_) != 0)
return false;
return test.host()[test.host().length() - host_.length() - 1] == '.';
}
bool URLPattern::MatchesPath(const std::string& 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/'.
if (test + "/*" == path_escaped_)
return true;
return 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 ? content::kStandardSchemeSeparator : ":");
if (scheme_ != content::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_ = 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 {
if (match_all_urls())
return true;
return MatchesAllSchemes(other.GetExplicitSchemes())
&& MatchesHost(other.host())
&& MatchesPortPattern(other.port())
&& MatchesPath(StripTrailingWildcard(other.path()));
}
bool URLPattern::MatchesAnyScheme(
const std::vector<std::string>& schemes) const {
for (std::vector<std::string>::const_iterator i = schemes.begin();
i != schemes.end(); ++i) {
if (MatchesScheme(*i))
return true;
}
return false;
}
bool URLPattern::MatchesAllSchemes(
const std::vector<std::string>& schemes) const {
for (std::vector<std::string>::const_iterator i = schemes.begin();
i != schemes.end(); ++i) {
if (!MatchesScheme(*i))
return false;
}
return true;
}
bool URLPattern::MatchesSecurityOriginHelper(const GURL& test) const {
// Ignore hostname if scheme is file://.
if (scheme_ != content::kFileScheme && !MatchesHost(test))
return false;
if (!MatchesPortPattern(base::IntToString(test.EffectiveIntPort())))
return false;
return true;
}
bool URLPattern::MatchesPortPattern(const std::string& port) const {
return port_ == "*" || port_ == port;
}
std::vector<std::string> URLPattern::GetExplicitSchemes() const {
std::vector<std::string> result;
if (scheme_ != "*" && !match_all_urls_ && IsValidScheme(scheme_)) {
result.push_back(scheme_);
return result;
}
for (size_t i = 0; i < arraysize(kValidSchemes); ++i) {
if (MatchesScheme(kValidSchemes[i])) {
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[parse_result];
}
|