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
|
/*
* Copyright (C) 2010 Google 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 "HTMLMetaCharsetParser.h"
#include "HTMLNames.h"
#include "HTMLParserIdioms.h"
#include "HTMLParserOptions.h"
#include "HTMLTokenizer.h"
#include "TextCodec.h"
#include "TextEncodingRegistry.h"
#include <wtf/text/WTFString.h>
using namespace WTF;
namespace WebCore {
using namespace HTMLNames;
HTMLMetaCharsetParser::HTMLMetaCharsetParser()
: m_tokenizer(HTMLTokenizer::create(HTMLParserOptions(0)))
, m_assumedCodec(newTextCodec(Latin1Encoding()))
, m_inHeadSection(true)
, m_doneChecking(false)
{
}
HTMLMetaCharsetParser::~HTMLMetaCharsetParser()
{
}
static const char charsetString[] = "charset";
static const size_t charsetLength = sizeof("charset") - 1;
String HTMLMetaCharsetParser::extractCharset(const String& value)
{
size_t pos = 0;
unsigned length = value.length();
while (pos < length) {
pos = value.find(charsetString, pos, false);
if (pos == notFound)
break;
pos += charsetLength;
// Skip whitespace.
while (pos < length && value[pos] <= ' ')
++pos;
if (value[pos] != '=')
continue;
++pos;
while (pos < length && value[pos] <= ' ')
++pos;
char quoteMark = 0;
if (pos < length && (value[pos] == '"' || value[pos] == '\'')) {
quoteMark = static_cast<char>(value[pos++]);
ASSERT(!(quoteMark & 0x80));
}
if (pos == length)
break;
unsigned end = pos;
while (end < length && ((quoteMark && value[end] != quoteMark) || (!quoteMark && value[end] > ' ' && value[end] != '"' && value[end] != '\'' && value[end] != ';')))
++end;
if (quoteMark && (end == length))
break; // Close quote not found.
return value.substring(pos, end - pos);
}
return "";
}
bool HTMLMetaCharsetParser::processMeta()
{
const HTMLToken::AttributeList& tokenAttributes = m_token.attributes();
AttributeList attributes;
for (HTMLToken::AttributeList::const_iterator iter = tokenAttributes.begin(); iter != tokenAttributes.end(); ++iter) {
String attributeName = StringImpl::create8BitIfPossible(iter->name);
String attributeValue = StringImpl::create8BitIfPossible(iter->value);
attributes.append(std::make_pair(attributeName, attributeValue));
}
m_encoding = encodingFromMetaAttributes(attributes);
return m_encoding.isValid();
}
TextEncoding HTMLMetaCharsetParser::encodingFromMetaAttributes(const AttributeList& attributes)
{
bool gotPragma = false;
Mode mode = None;
String charset;
for (AttributeList::const_iterator iter = attributes.begin(); iter != attributes.end(); ++iter) {
const AtomicString& attributeName = iter->first;
const String& attributeValue = iter->second;
if (attributeName == http_equivAttr) {
if (equalIgnoringCase(attributeValue, "content-type"))
gotPragma = true;
} else if (charset.isEmpty()) {
if (attributeName == charsetAttr) {
charset = attributeValue;
mode = Charset;
} else if (attributeName == contentAttr) {
charset = extractCharset(attributeValue);
if (charset.length())
mode = Pragma;
}
}
}
if (mode == Charset || (mode == Pragma && gotPragma))
return TextEncoding(stripLeadingAndTrailingHTMLSpaces(charset));
return TextEncoding();
}
static const int bytesToCheckUnconditionally = 1024; // That many input bytes will be checked for meta charset even if <head> section is over.
bool HTMLMetaCharsetParser::checkForMetaCharset(const char* data, size_t length)
{
if (m_doneChecking)
return true;
ASSERT(!m_encoding.isValid());
// We still don't have an encoding, and are in the head.
// The following tags are allowed in <head>:
// SCRIPT|STYLE|META|LINK|OBJECT|TITLE|BASE
// We stop scanning when a tag that is not permitted in <head>
// is seen, rather when </head> is seen, because that more closely
// matches behavior in other browsers; more details in
// <http://bugs.webkit.org/show_bug.cgi?id=3590>.
// Additionally, we ignore things that looks like tags in <title>, <script>
// and <noscript>; see <http://bugs.webkit.org/show_bug.cgi?id=4560>,
// <http://bugs.webkit.org/show_bug.cgi?id=12165> and
// <http://bugs.webkit.org/show_bug.cgi?id=12389>.
// Since many sites have charset declarations after <body> or other tags
// that are disallowed in <head>, we don't bail out until we've checked at
// least bytesToCheckUnconditionally bytes of input.
m_input.append(SegmentedString(m_assumedCodec->decode(data, length)));
while (m_tokenizer->nextToken(m_input, m_token)) {
bool end = m_token.type() == HTMLToken::EndTag;
if (end || m_token.type() == HTMLToken::StartTag) {
AtomicString tagName(m_token.name());
if (!end) {
m_tokenizer->updateStateFor(tagName);
if (tagName == metaTag && processMeta()) {
m_doneChecking = true;
return true;
}
}
if (tagName != scriptTag && tagName != noscriptTag
&& tagName != styleTag && tagName != linkTag
&& tagName != metaTag && tagName != objectTag
&& tagName != titleTag && tagName != baseTag
&& (end || tagName != htmlTag) && (end || tagName != headTag)) {
m_inHeadSection = false;
}
}
if (!m_inHeadSection && m_input.numberOfCharactersConsumed() >= bytesToCheckUnconditionally) {
m_doneChecking = true;
return true;
}
m_token.clear();
}
return false;
}
}
|
