HTMLMetaCharsetParser.cpp [plain text]
#include "config.h"
#include "HTMLMetaCharsetParser.h"
#include "HTMLNames.h"
#include "HTMLParserIdioms.h"
#include "TextEncodingRegistry.h"
namespace WebCore {
using namespace HTMLNames;
HTMLMetaCharsetParser::HTMLMetaCharsetParser()
: m_codec(newTextCodec(Latin1Encoding()))
{
}
static StringView extractCharset(const String& value)
{
unsigned length = value.length();
for (size_t pos = 0; pos < length; ) {
pos = value.find("charset", pos, false);
if (pos == notFound)
break;
static const size_t charsetLength = sizeof("charset") - 1;
pos += charsetLength;
while (pos < length && value[pos] <= ' ')
++pos;
if (value[pos] != '=')
continue;
++pos;
while (pos < length && value[pos] <= ' ')
++pos;
UChar quoteMark = 0;
if (pos < length && (value[pos] == '"' || value[pos] == '\''))
quoteMark = value[pos++];
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;
return StringView(value).substring(pos, end - pos);
}
return StringView();
}
bool HTMLMetaCharsetParser::processMeta(HTMLToken& token)
{
AttributeList attributes;
for (auto& attribute : token.attributes()) {
String attributeName = StringImpl::create8BitIfPossible(attribute.name);
String attributeValue = StringImpl::create8BitIfPossible(attribute.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;
enum { None, Charset, Pragma } mode = None;
StringView charset;
for (auto& attribute : attributes) {
const String& attributeName = attribute.first;
const String& attributeValue = attribute.second;
if (attributeName == http_equivAttr) {
if (equalLettersIgnoringASCIICase(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.toStringWithoutCopying()));
return TextEncoding();
}
bool HTMLMetaCharsetParser::checkForMetaCharset(const char* data, size_t length)
{
if (m_doneChecking)
return true;
ASSERT(!m_encoding.isValid());
constexpr int bytesToCheckUnconditionally = 1024;
m_input.append(m_codec->decode(data, length));
while (auto token = m_tokenizer.nextToken(m_input)) {
bool isEnd = token->type() == HTMLToken::EndTag;
if (isEnd || token->type() == HTMLToken::StartTag) {
AtomicString tagName(token->name());
if (!isEnd) {
m_tokenizer.updateStateFor(tagName);
if (tagName == metaTag && processMeta(*token)) {
m_doneChecking = true;
return true;
}
}
if (tagName != scriptTag && tagName != noscriptTag
&& tagName != styleTag && tagName != linkTag
&& tagName != metaTag && tagName != objectTag
&& tagName != titleTag && tagName != baseTag
&& (isEnd || tagName != htmlTag)
&& (isEnd || tagName != headTag)) {
m_inHeadSection = false;
}
}
if (!m_inHeadSection && m_input.numberOfCharactersConsumed() >= bytesToCheckUnconditionally) {
m_doneChecking = true;
return true;
}
}
return false;
}
}