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
|
/*
* Copyright (C) 2009, 2010 Apple Inc. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include "config.h"
#include "UserContentURLPattern.h"
#include "URL.h"
#include <wtf/NeverDestroyed.h>
#include <wtf/StdLibExtras.h>
namespace WebCore {
bool UserContentURLPattern::matchesPatterns(const URL& url, const Vector<String>& whitelist, const Vector<String>& blacklist)
{
// In order for a URL to be a match it has to be present in the whitelist and not present in the blacklist.
// If there is no whitelist at all, then all URLs are assumed to be in the whitelist.
bool matchesWhitelist = whitelist.isEmpty();
if (!matchesWhitelist) {
for (auto& entry : whitelist) {
UserContentURLPattern contentPattern(entry);
if (contentPattern.matches(url)) {
matchesWhitelist = true;
break;
}
}
}
bool matchesBlacklist = false;
if (!blacklist.isEmpty()) {
for (auto& entry : blacklist) {
UserContentURLPattern contentPattern(entry);
if (contentPattern.matches(url)) {
matchesBlacklist = true;
break;
}
}
}
return matchesWhitelist && !matchesBlacklist;
}
bool UserContentURLPattern::parse(const String& pattern)
{
static NeverDestroyed<const String> schemeSeparator(ASCIILiteral("://"));
size_t schemeEndPos = pattern.find(schemeSeparator);
if (schemeEndPos == notFound)
return false;
m_scheme = pattern.left(schemeEndPos);
unsigned hostStartPos = schemeEndPos + schemeSeparator.get().length();
if (hostStartPos >= pattern.length())
return false;
int pathStartPos = 0;
if (equalLettersIgnoringASCIICase(m_scheme, "file"))
pathStartPos = hostStartPos;
else {
size_t hostEndPos = pattern.find('/', hostStartPos);
if (hostEndPos == notFound)
return false;
m_host = pattern.substring(hostStartPos, hostEndPos - hostStartPos);
m_matchSubdomains = false;
if (m_host == "*") {
// The pattern can be just '*', which means match all domains.
m_host = "";
m_matchSubdomains = true;
} else if (m_host.startsWith("*.")) {
// The first component can be '*', which means to match all subdomains.
m_host = m_host.substring(2); // Length of "*."
m_matchSubdomains = true;
}
// No other '*' can occur in the host.
if (m_host.find('*') != notFound)
return false;
pathStartPos = hostEndPos;
}
m_path = pattern.right(pattern.length() - pathStartPos);
return true;
}
bool UserContentURLPattern::matches(const URL& test) const
{
if (m_invalid)
return false;
if (!equalIgnoringASCIICase(test.protocol(), m_scheme))
return false;
if (!equalLettersIgnoringASCIICase(m_scheme, "file") && !matchesHost(test))
return false;
return matchesPath(test);
}
bool UserContentURLPattern::matchesHost(const URL& test) const
{
const String& host = test.host();
if (equalIgnoringASCIICase(host, m_host))
return true;
if (!m_matchSubdomains)
return false;
// If we're matching subdomains, and we have no host, that means the pattern
// was <scheme>://*/<whatever>, so we match anything.
if (!m_host.length())
return true;
// Check if the domain is a subdomain of our host.
if (!host.endsWith(m_host, false))
return false;
ASSERT(host.length() > m_host.length());
// Check that the character before the suffix is a period.
return host[host.length() - m_host.length() - 1] == '.';
}
struct MatchTester
{
const String m_pattern;
unsigned m_patternIndex;
const String m_test;
unsigned m_testIndex;
MatchTester(const String& pattern, const String& test)
: m_pattern(pattern)
, m_patternIndex(0)
, m_test(test)
, m_testIndex(0)
{
}
bool testStringFinished() const { return m_testIndex >= m_test.length(); }
bool patternStringFinished() const { return m_patternIndex >= m_pattern.length(); }
void eatWildcard()
{
while (!patternStringFinished()) {
if (m_pattern[m_patternIndex] != '*')
return;
m_patternIndex++;
}
}
void eatSameChars()
{
while (!patternStringFinished() && !testStringFinished()) {
if (m_pattern[m_patternIndex] == '*')
return;
if (m_pattern[m_patternIndex] != m_test[m_testIndex])
return;
m_patternIndex++;
m_testIndex++;
}
}
bool test()
{
// Eat all the matching chars.
eatSameChars();
// If the string is finished, then the pattern must be empty too, or contains
// only wildcards.
if (testStringFinished()) {
eatWildcard();
if (patternStringFinished())
return true;
return false;
}
// Pattern is empty but not string, this is not a match.
if (patternStringFinished())
return false;
// If we don't encounter a *, then we're hosed.
if (m_pattern[m_patternIndex] != '*')
return false;
while (!testStringFinished()) {
MatchTester nextMatch(*this);
nextMatch.m_patternIndex++;
if (nextMatch.test())
return true;
m_testIndex++;
}
// We reached the end of the string. Let's see if the pattern contains only
// wildcards.
eatWildcard();
return patternStringFinished();
}
};
bool UserContentURLPattern::matchesPath(const URL& test) const
{
MatchTester match(m_path, test.path());
return match.test();
}
} // namespace WebCore
|
