Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(159)

Issues Search
    My Issues | Starred     Open | Closed | All

Side by Side Diff: Source/core/html/parser/HTMLMetaCharsetParser.cpp

Issue 74513003: Moved text decoding to the parser thread (Closed) Base URL: https://chromium.googlesource.com/chromium/blink.git@parserthread_step25
Patch Set: Removed AtomicString from HTMLMetaCharsetParser Created 7 years ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch
« Source/core/html/parser/HTMLIdentifier.h ('K') | « Source/core/html/parser/HTMLMetaCharsetParser.h ('k') | Source/core/html/parser/HTMLPreloadScanner.cpp » ('j') | Source/core/html/parser/HTMLTokenizer.h » ('J')
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
1 /* 1 /*
2 * Copyright (C) 2010 Google Inc. All Rights Reserved. 2 * Copyright (C) 2010 Google Inc. All Rights Reserved.
3 * 3 *
4 * Redistribution and use in source and binary forms, with or without 4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions 5 * modification, are permitted provided that the following conditions
6 * are met: 6 * are met:
7 * 1. Redistributions of source code must retain the above copyright 7 * 1. Redistributions of source code must retain the above copyright
8 * notice, this list of conditions and the following disclaimer. 8 * notice, this list of conditions and the following disclaimer.
9 * 2. Redistributions in binary form must reproduce the above copyright 9 * 2. Redistributions in binary form must reproduce the above copyright
10 * notice, this list of conditions and the following disclaimer in the 10 * notice, this list of conditions and the following disclaimer in the
(...skipping 88 matching lines...) Expand 10 before | Expand all | Expand 10 after
99 } 99 }
100 100
101 return ""; 101 return "";
102 } 102 }
103 103
104 bool HTMLMetaCharsetParser::processMeta() 104 bool HTMLMetaCharsetParser::processMeta()
105 { 105 {
106 const HTMLToken::AttributeList& tokenAttributes = m_token.attributes(); 106 const HTMLToken::AttributeList& tokenAttributes = m_token.attributes();
107 AttributeList attributes; 107 AttributeList attributes;
108 for (HTMLToken::AttributeList::const_iterator iter = tokenAttributes.begin() ; iter != tokenAttributes.end(); ++iter) { 108 for (HTMLToken::AttributeList::const_iterator iter = tokenAttributes.begin() ; iter != tokenAttributes.end(); ++iter) {
109 String attributeName = StringImpl::create8BitIfPossible(iter->name); 109 HTMLIdentifier attributeName(iter->name, Likely8Bit);
110 String attributeValue = StringImpl::create8BitIfPossible(iter->value); 110 String attributeValue = StringImpl::create8BitIfPossible(iter->value);
111 attributes.append(std::make_pair(attributeName, attributeValue)); 111 attributes.append(std::make_pair(attributeName, attributeValue));
112 } 112 }
113 113
114 m_encoding = encodingFromMetaAttributes(attributes); 114 m_encoding = encodingFromMetaAttributes(attributes);
115 return m_encoding.isValid(); 115 return m_encoding.isValid();
116 } 116 }
117 117
118 WTF::TextEncoding HTMLMetaCharsetParser::encodingFromMetaAttributes(const Attrib uteList& attributes) 118 WTF::TextEncoding HTMLMetaCharsetParser::encodingFromMetaAttributes(const Attrib uteList& attributes)
119 { 119 {
120 bool gotPragma = false; 120 bool gotPragma = false;
121 Mode mode = None; 121 Mode mode = None;
122 String charset; 122 String charset;
123 123
124 for (AttributeList::const_iterator iter = attributes.begin(); iter != attrib utes.end(); ++iter) { 124 for (AttributeList::const_iterator iter = attributes.begin(); iter != attrib utes.end(); ++iter) {
125 const AtomicString& attributeName = iter->first; 125 const HTMLIdentifier& attributeName = iter->first;
126 const String& attributeValue = iter->second; 126 const String& attributeValue = iter->second;
127 127
128 if (attributeName == http_equivAttr) { 128 if (threadSafeMatch(attributeName, http_equivAttr)) {
129 if (equalIgnoringCase(attributeValue, "content-type")) 129 if (equalIgnoringCase(attributeValue, "content-type"))
130 gotPragma = true; 130 gotPragma = true;
131 } else if (charset.isEmpty()) { 131 } else if (charset.isEmpty()) {
132 if (attributeName == charsetAttr) { 132 if (threadSafeMatch(attributeName, charsetAttr)) {
133 charset = attributeValue; 133 charset = attributeValue;
134 mode = Charset; 134 mode = Charset;
135 } else if (attributeName == contentAttr) { 135 } else if (threadSafeMatch(attributeName, contentAttr)) {
136 charset = extractCharset(attributeValue); 136 charset = extractCharset(attributeValue);
137 if (charset.length()) 137 if (charset.length())
138 mode = Pragma; 138 mode = Pragma;
139 } 139 }
140 } 140 }
141 } 141 }
142 142
143 if (mode == Charset || (mode == Pragma && gotPragma)) 143 if (mode == Charset || (mode == Pragma && gotPragma))
144 return WTF::TextEncoding(stripLeadingAndTrailingHTMLSpaces(charset)); 144 return WTF::TextEncoding(stripLeadingAndTrailingHTMLSpaces(charset));
145 145
(...skipping 25 matching lines...) Expand all
171 171
172 // Since many sites have charset declarations after <body> or other tags 172 // Since many sites have charset declarations after <body> or other tags
173 // that are disallowed in <head>, we don't bail out until we've checked at 173 // that are disallowed in <head>, we don't bail out until we've checked at
174 // least bytesToCheckUnconditionally bytes of input. 174 // least bytesToCheckUnconditionally bytes of input.
175 175
176 m_input.append(SegmentedString(m_assumedCodec->decode(data, length))); 176 m_input.append(SegmentedString(m_assumedCodec->decode(data, length)));
177 177
178 while (m_tokenizer->nextToken(m_input, m_token)) { 178 while (m_tokenizer->nextToken(m_input, m_token)) {
179 bool end = m_token.type() == HTMLToken::EndTag; 179 bool end = m_token.type() == HTMLToken::EndTag;
180 if (end || m_token.type() == HTMLToken::StartTag) { 180 if (end || m_token.type() == HTMLToken::StartTag) {
181 AtomicString tagName(m_token.name()); 181 HTMLIdentifier tagName(m_token.name(), Likely8Bit);
182 if (!end) { 182 if (!end) {
183 m_tokenizer->updateStateFor(tagName); 183 m_tokenizer->updateStateFor(tagName);
184 if (tagName == metaTag && processMeta()) { 184 if (tagName == metaTag && processMeta()) {
185 m_doneChecking = true; 185 m_doneChecking = true;
186 return true; 186 return true;
187 } 187 }
188 } 188 }
189 189
190 if (tagName != scriptTag && tagName != noscriptTag 190 if (tagName != scriptTag && tagName != noscriptTag
191 && tagName != styleTag && tagName != linkTag 191 && tagName != styleTag && tagName != linkTag
192 && tagName != metaTag && tagName != objectTag 192 && tagName != metaTag && tagName != objectTag
193 && tagName != titleTag && tagName != baseTag 193 && tagName != titleTag && tagName != baseTag
194 && (end || tagName != htmlTag) && (end || tagName != headTag)) { 194 && (end || tagName != htmlTag) && (end || tagName != headTag)) {
195 m_inHeadSection = false; 195 m_inHeadSection = false;
196 } 196 }
197 } 197 }
198 198
199 if (!m_inHeadSection && m_input.numberOfCharactersConsumed() >= bytesToC heckUnconditionally) { 199 if (!m_inHeadSection && m_input.numberOfCharactersConsumed() >= bytesToC heckUnconditionally) {
200 m_doneChecking = true; 200 m_doneChecking = true;
201 return true; 201 return true;
202 } 202 }
203 203
204 m_token.clear(); 204 m_token.clear();
205 } 205 }
206 206
207 return false; 207 return false;
208 } 208 }
209 209
210 } 210 }
OLDNEW
« Source/core/html/parser/HTMLIdentifier.h ('K') | « Source/core/html/parser/HTMLMetaCharsetParser.h ('k') | Source/core/html/parser/HTMLPreloadScanner.cpp » ('j') | Source/core/html/parser/HTMLTokenizer.h » ('J')

Powered by Google App Engine
This is Rietveld 408576698