Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(943)

Issues Search
    My Issues | Starred     Open | Closed | All

Unified 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: Rebase 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 side-by-side diff with in-line comments
Download patch
« no previous file with comments | « Source/core/html/parser/HTMLMetaCharsetParser.h ('k') | Source/core/html/parser/HTMLParserIdioms.h » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: Source/core/html/parser/HTMLMetaCharsetParser.cpp
diff --git a/Source/core/html/parser/HTMLMetaCharsetParser.cpp b/Source/core/html/parser/HTMLMetaCharsetParser.cpp
index 038c8a1e5fb7e896335332768fd9b0dea299b629..7947846a1690040a6e38f4847ec319995c9e0151 100644
--- a/Source/core/html/parser/HTMLMetaCharsetParser.cpp
+++ b/Source/core/html/parser/HTMLMetaCharsetParser.cpp
@@ -51,61 +51,12 @@ 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 == kNotFound)
- 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;
+ HTMLAttributeList attributes;
for (HTMLToken::AttributeList::const_iterator iter = tokenAttributes.begin(); iter != tokenAttributes.end(); ++iter) {
- String attributeName = StringImpl::create8BitIfPossible(iter->name);
+ String attributeName = attemptStaticStringCreation(iter->name, Likely8Bit);
String attributeValue = StringImpl::create8BitIfPossible(iter->value);
attributes.append(std::make_pair(attributeName, attributeValue));
}
@@ -114,37 +65,6 @@ bool HTMLMetaCharsetParser::processMeta()
return m_encoding.isValid();
}
-WTF::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 WTF::TextEncoding(stripLeadingAndTrailingHTMLSpaces(charset));
-
- return WTF::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)
@@ -177,20 +97,20 @@ bool HTMLMetaCharsetParser::checkForMetaCharset(const char* data, size_t 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());
+ String tagName = attemptStaticStringCreation(m_token.name(), Likely8Bit);
if (!end) {
m_tokenizer->updateStateFor(tagName);
- if (tagName == metaTag && processMeta()) {
+ if (threadSafeMatch(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)) {
+ if (!threadSafeMatch(tagName, scriptTag) && !threadSafeMatch(tagName, noscriptTag)
+ && !threadSafeMatch(tagName, styleTag) && !threadSafeMatch(tagName, linkTag)
+ && !threadSafeMatch(tagName, metaTag) && !threadSafeMatch(tagName, objectTag)
+ && !threadSafeMatch(tagName, titleTag) && !threadSafeMatch(tagName, baseTag)
+ && (end || !threadSafeMatch(tagName, htmlTag)) && (end || !threadSafeMatch(tagName, headTag))) {
m_inHeadSection = false;
}
}
« no previous file with comments | « Source/core/html/parser/HTMLMetaCharsetParser.h ('k') | Source/core/html/parser/HTMLParserIdioms.h » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698