1 | /* |
2 | * Copyright (C) 2010 Google Inc. All Rights Reserved. |
3 | * Copyright (C) 2015-2017 Apple Inc. All rights reserved. |
4 | * |
5 | * Redistribution and use in source and binary forms, with or without |
6 | * modification, are permitted provided that the following conditions |
7 | * are met: |
8 | * 1. Redistributions of source code must retain the above copyright |
9 | * notice, this list of conditions and the following disclaimer. |
10 | * 2. Redistributions in binary form must reproduce the above copyright |
11 | * notice, this list of conditions and the following disclaimer in the |
12 | * documentation and/or other materials provided with the distribution. |
13 | * |
14 | * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY |
15 | * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
16 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR |
17 | * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR |
18 | * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
19 | * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
20 | * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
21 | * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY |
22 | * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
23 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
24 | * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
25 | */ |
26 | |
27 | #include "config.h" |
28 | #include "HTMLMetaCharsetParser.h" |
29 | |
30 | #include "HTMLNames.h" |
31 | #include "HTMLParserIdioms.h" |
32 | #include "TextCodec.h" |
33 | #include "TextEncodingRegistry.h" |
34 | |
35 | namespace WebCore { |
36 | |
37 | using namespace HTMLNames; |
38 | |
39 | HTMLMetaCharsetParser::HTMLMetaCharsetParser() |
40 | : m_codec(newTextCodec(Latin1Encoding())) |
41 | { |
42 | } |
43 | |
44 | static StringView (const String& value) |
45 | { |
46 | unsigned length = value.length(); |
47 | for (size_t pos = 0; pos < length; ) { |
48 | pos = value.findIgnoringASCIICase("charset" , pos); |
49 | if (pos == notFound) |
50 | break; |
51 | |
52 | static const size_t charsetLength = sizeof("charset" ) - 1; |
53 | pos += charsetLength; |
54 | |
55 | // Skip whitespace. |
56 | while (pos < length && value[pos] <= ' ') |
57 | ++pos; |
58 | |
59 | if (value[pos] != '=') |
60 | continue; |
61 | |
62 | ++pos; |
63 | |
64 | while (pos < length && value[pos] <= ' ') |
65 | ++pos; |
66 | |
67 | UChar quoteMark = 0; |
68 | if (pos < length && (value[pos] == '"' || value[pos] == '\'')) |
69 | quoteMark = value[pos++]; |
70 | |
71 | if (pos == length) |
72 | break; |
73 | |
74 | unsigned end = pos; |
75 | while (end < length && ((quoteMark && value[end] != quoteMark) || (!quoteMark && value[end] > ' ' && value[end] != '"' && value[end] != '\'' && value[end] != ';'))) |
76 | ++end; |
77 | |
78 | if (quoteMark && (end == length)) |
79 | break; // Close quote not found. |
80 | |
81 | return StringView(value).substring(pos, end - pos); |
82 | } |
83 | return StringView(); |
84 | } |
85 | |
86 | bool HTMLMetaCharsetParser::processMeta(HTMLToken& token) |
87 | { |
88 | AttributeList attributes; |
89 | for (auto& attribute : token.attributes()) { |
90 | String attributeName = StringImpl::create8BitIfPossible(attribute.name); |
91 | String attributeValue = StringImpl::create8BitIfPossible(attribute.value); |
92 | attributes.append(std::make_pair(attributeName, attributeValue)); |
93 | } |
94 | |
95 | m_encoding = encodingFromMetaAttributes(attributes); |
96 | return m_encoding.isValid(); |
97 | } |
98 | |
99 | TextEncoding HTMLMetaCharsetParser::encodingFromMetaAttributes(const AttributeList& attributes) |
100 | { |
101 | bool gotPragma = false; |
102 | enum { None, Charset, Pragma } mode = None; |
103 | StringView charset; |
104 | |
105 | for (auto& attribute : attributes) { |
106 | const String& attributeName = attribute.first; |
107 | const String& attributeValue = attribute.second; |
108 | |
109 | if (attributeName == http_equivAttr) { |
110 | if (equalLettersIgnoringASCIICase(attributeValue, "content-type" )) |
111 | gotPragma = true; |
112 | } else if (charset.isEmpty()) { |
113 | if (attributeName == charsetAttr) { |
114 | charset = attributeValue; |
115 | mode = Charset; |
116 | } else if (attributeName == contentAttr) { |
117 | charset = extractCharset(attributeValue); |
118 | if (charset.length()) |
119 | mode = Pragma; |
120 | } |
121 | } |
122 | } |
123 | |
124 | if (mode == Charset || (mode == Pragma && gotPragma)) |
125 | return TextEncoding(stripLeadingAndTrailingHTMLSpaces(charset.toStringWithoutCopying())); |
126 | |
127 | return TextEncoding(); |
128 | } |
129 | |
130 | bool HTMLMetaCharsetParser::checkForMetaCharset(const char* data, size_t length) |
131 | { |
132 | if (m_doneChecking) |
133 | return true; |
134 | |
135 | ASSERT(!m_encoding.isValid()); |
136 | |
137 | // We still don't have an encoding, and are in the head. |
138 | // The following tags are allowed in <head>: |
139 | // SCRIPT|STYLE|META|LINK|OBJECT|TITLE|BASE |
140 | // |
141 | // We stop scanning when a tag that is not permitted in <head> |
142 | // is seen, rather when </head> is seen, because that more closely |
143 | // matches behavior in other browsers; more details in |
144 | // <http://bugs.webkit.org/show_bug.cgi?id=3590>. |
145 | // |
146 | // Additionally, we ignore things that looks like tags in <title>, <script> |
147 | // and <noscript>; see <http://bugs.webkit.org/show_bug.cgi?id=4560>, |
148 | // <http://bugs.webkit.org/show_bug.cgi?id=12165> and |
149 | // <http://bugs.webkit.org/show_bug.cgi?id=12389>. |
150 | // |
151 | // Since many sites have charset declarations after <body> or other tags |
152 | // that are disallowed in <head>, we don't bail out until we've checked at |
153 | // least bytesToCheckUnconditionally bytes of input. |
154 | |
155 | constexpr int bytesToCheckUnconditionally = 1024; |
156 | |
157 | bool ignoredSawErrorFlag; |
158 | m_input.append(m_codec->decode(data, length, false, false, ignoredSawErrorFlag)); |
159 | |
160 | while (auto token = m_tokenizer.nextToken(m_input)) { |
161 | bool isEnd = token->type() == HTMLToken::EndTag; |
162 | if (isEnd || token->type() == HTMLToken::StartTag) { |
163 | AtomicString tagName(token->name()); |
164 | if (!isEnd) { |
165 | m_tokenizer.updateStateFor(tagName); |
166 | if (tagName == metaTag && processMeta(*token)) { |
167 | m_doneChecking = true; |
168 | return true; |
169 | } |
170 | } |
171 | |
172 | if (tagName != scriptTag && tagName != noscriptTag |
173 | && tagName != styleTag && tagName != linkTag |
174 | && tagName != metaTag && tagName != objectTag |
175 | && tagName != titleTag && tagName != baseTag |
176 | && (isEnd || tagName != htmlTag) |
177 | && (isEnd || tagName != headTag)) { |
178 | m_inHeadSection = false; |
179 | } |
180 | } |
181 | |
182 | if (!m_inHeadSection && m_input.numberOfCharactersConsumed() >= bytesToCheckUnconditionally) { |
183 | m_doneChecking = true; |
184 | return true; |
185 | } |
186 | } |
187 | |
188 | return false; |
189 | } |
190 | |
191 | } |
192 | |