2102 lines
62 KiB
JavaScript
2102 lines
62 KiB
JavaScript
'use strict';
|
|
|
|
var Preprocessor = require('./preprocessor'),
|
|
locationInfoMixin = require('../location_info/tokenizer_mixin'),
|
|
UNICODE = require('../common/unicode'),
|
|
NAMED_ENTITY_TRIE = require('./named_entity_trie');
|
|
|
|
//Aliases
|
|
var $ = UNICODE.CODE_POINTS,
|
|
$$ = UNICODE.CODE_POINT_SEQUENCES;
|
|
|
|
//Replacement code points for numeric entities
|
|
var NUMERIC_ENTITY_REPLACEMENTS = {
|
|
0x00: 0xFFFD, 0x0D: 0x000D, 0x80: 0x20AC, 0x81: 0x0081, 0x82: 0x201A, 0x83: 0x0192, 0x84: 0x201E,
|
|
0x85: 0x2026, 0x86: 0x2020, 0x87: 0x2021, 0x88: 0x02C6, 0x89: 0x2030, 0x8A: 0x0160, 0x8B: 0x2039,
|
|
0x8C: 0x0152, 0x8D: 0x008D, 0x8E: 0x017D, 0x8F: 0x008F, 0x90: 0x0090, 0x91: 0x2018, 0x92: 0x2019,
|
|
0x93: 0x201C, 0x94: 0x201D, 0x95: 0x2022, 0x96: 0x2013, 0x97: 0x2014, 0x98: 0x02DC, 0x99: 0x2122,
|
|
0x9A: 0x0161, 0x9B: 0x203A, 0x9C: 0x0153, 0x9D: 0x009D, 0x9E: 0x017E, 0x9F: 0x0178
|
|
};
|
|
|
|
//States
|
|
var DATA_STATE = 'DATA_STATE',
|
|
CHARACTER_REFERENCE_IN_DATA_STATE = 'CHARACTER_REFERENCE_IN_DATA_STATE',
|
|
RCDATA_STATE = 'RCDATA_STATE',
|
|
CHARACTER_REFERENCE_IN_RCDATA_STATE = 'CHARACTER_REFERENCE_IN_RCDATA_STATE',
|
|
RAWTEXT_STATE = 'RAWTEXT_STATE',
|
|
SCRIPT_DATA_STATE = 'SCRIPT_DATA_STATE',
|
|
PLAINTEXT_STATE = 'PLAINTEXT_STATE',
|
|
TAG_OPEN_STATE = 'TAG_OPEN_STATE',
|
|
END_TAG_OPEN_STATE = 'END_TAG_OPEN_STATE',
|
|
TAG_NAME_STATE = 'TAG_NAME_STATE',
|
|
RCDATA_LESS_THAN_SIGN_STATE = 'RCDATA_LESS_THAN_SIGN_STATE',
|
|
RCDATA_END_TAG_OPEN_STATE = 'RCDATA_END_TAG_OPEN_STATE',
|
|
RCDATA_END_TAG_NAME_STATE = 'RCDATA_END_TAG_NAME_STATE',
|
|
RAWTEXT_LESS_THAN_SIGN_STATE = 'RAWTEXT_LESS_THAN_SIGN_STATE',
|
|
RAWTEXT_END_TAG_OPEN_STATE = 'RAWTEXT_END_TAG_OPEN_STATE',
|
|
RAWTEXT_END_TAG_NAME_STATE = 'RAWTEXT_END_TAG_NAME_STATE',
|
|
SCRIPT_DATA_LESS_THAN_SIGN_STATE = 'SCRIPT_DATA_LESS_THAN_SIGN_STATE',
|
|
SCRIPT_DATA_END_TAG_OPEN_STATE = 'SCRIPT_DATA_END_TAG_OPEN_STATE',
|
|
SCRIPT_DATA_END_TAG_NAME_STATE = 'SCRIPT_DATA_END_TAG_NAME_STATE',
|
|
SCRIPT_DATA_ESCAPE_START_STATE = 'SCRIPT_DATA_ESCAPE_START_STATE',
|
|
SCRIPT_DATA_ESCAPE_START_DASH_STATE = 'SCRIPT_DATA_ESCAPE_START_DASH_STATE',
|
|
SCRIPT_DATA_ESCAPED_STATE = 'SCRIPT_DATA_ESCAPED_STATE',
|
|
SCRIPT_DATA_ESCAPED_DASH_STATE = 'SCRIPT_DATA_ESCAPED_DASH_STATE',
|
|
SCRIPT_DATA_ESCAPED_DASH_DASH_STATE = 'SCRIPT_DATA_ESCAPED_DASH_DASH_STATE',
|
|
SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN_STATE = 'SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN_STATE',
|
|
SCRIPT_DATA_ESCAPED_END_TAG_OPEN_STATE = 'SCRIPT_DATA_ESCAPED_END_TAG_OPEN_STATE',
|
|
SCRIPT_DATA_ESCAPED_END_TAG_NAME_STATE = 'SCRIPT_DATA_ESCAPED_END_TAG_NAME_STATE',
|
|
SCRIPT_DATA_DOUBLE_ESCAPE_START_STATE = 'SCRIPT_DATA_DOUBLE_ESCAPE_START_STATE',
|
|
SCRIPT_DATA_DOUBLE_ESCAPED_STATE = 'SCRIPT_DATA_DOUBLE_ESCAPED_STATE',
|
|
SCRIPT_DATA_DOUBLE_ESCAPED_DASH_STATE = 'SCRIPT_DATA_DOUBLE_ESCAPED_DASH_STATE',
|
|
SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH_STATE = 'SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH_STATE',
|
|
SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN_STATE = 'SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN_STATE',
|
|
SCRIPT_DATA_DOUBLE_ESCAPE_END_STATE = 'SCRIPT_DATA_DOUBLE_ESCAPE_END_STATE',
|
|
BEFORE_ATTRIBUTE_NAME_STATE = 'BEFORE_ATTRIBUTE_NAME_STATE',
|
|
ATTRIBUTE_NAME_STATE = 'ATTRIBUTE_NAME_STATE',
|
|
AFTER_ATTRIBUTE_NAME_STATE = 'AFTER_ATTRIBUTE_NAME_STATE',
|
|
BEFORE_ATTRIBUTE_VALUE_STATE = 'BEFORE_ATTRIBUTE_VALUE_STATE',
|
|
ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE = 'ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE',
|
|
ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE = 'ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE',
|
|
ATTRIBUTE_VALUE_UNQUOTED_STATE = 'ATTRIBUTE_VALUE_UNQUOTED_STATE',
|
|
CHARACTER_REFERENCE_IN_ATTRIBUTE_VALUE_STATE = 'CHARACTER_REFERENCE_IN_ATTRIBUTE_VALUE_STATE',
|
|
AFTER_ATTRIBUTE_VALUE_QUOTED_STATE = 'AFTER_ATTRIBUTE_VALUE_QUOTED_STATE',
|
|
SELF_CLOSING_START_TAG_STATE = 'SELF_CLOSING_START_TAG_STATE',
|
|
BOGUS_COMMENT_STATE = 'BOGUS_COMMENT_STATE',
|
|
BOGUS_COMMENT_STATE_CONTINUATION = 'BOGUS_COMMENT_STATE_CONTINUATION',
|
|
MARKUP_DECLARATION_OPEN_STATE = 'MARKUP_DECLARATION_OPEN_STATE',
|
|
COMMENT_START_STATE = 'COMMENT_START_STATE',
|
|
COMMENT_START_DASH_STATE = 'COMMENT_START_DASH_STATE',
|
|
COMMENT_STATE = 'COMMENT_STATE',
|
|
COMMENT_END_DASH_STATE = 'COMMENT_END_DASH_STATE',
|
|
COMMENT_END_STATE = 'COMMENT_END_STATE',
|
|
COMMENT_END_BANG_STATE = 'COMMENT_END_BANG_STATE',
|
|
DOCTYPE_STATE = 'DOCTYPE_STATE',
|
|
DOCTYPE_NAME_STATE = 'DOCTYPE_NAME_STATE',
|
|
AFTER_DOCTYPE_NAME_STATE = 'AFTER_DOCTYPE_NAME_STATE',
|
|
BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE = 'BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE',
|
|
DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE = 'DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE',
|
|
DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE = 'DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE',
|
|
BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS_STATE = 'BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS_STATE',
|
|
BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE = 'BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE',
|
|
DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE = 'DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE',
|
|
DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE = 'DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE',
|
|
AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE = 'AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE',
|
|
BOGUS_DOCTYPE_STATE = 'BOGUS_DOCTYPE_STATE',
|
|
CDATA_SECTION_STATE = 'CDATA_SECTION_STATE';
|
|
|
|
//Utils
|
|
|
|
//OPTIMIZATION: these utility functions should not be moved out of this module. V8 Crankshaft will not inline
|
|
//this functions if they will be situated in another module due to context switch.
|
|
//Always perform inlining check before modifying this functions ('node --trace-inlining').
|
|
function isWhitespace(cp) {
|
|
return cp === $.SPACE || cp === $.LINE_FEED || cp === $.TABULATION || cp === $.FORM_FEED;
|
|
}
|
|
|
|
function isAsciiDigit(cp) {
|
|
return cp >= $.DIGIT_0 && cp <= $.DIGIT_9;
|
|
}
|
|
|
|
function isAsciiUpper(cp) {
|
|
return cp >= $.LATIN_CAPITAL_A && cp <= $.LATIN_CAPITAL_Z;
|
|
}
|
|
|
|
function isAsciiLower(cp) {
|
|
return cp >= $.LATIN_SMALL_A && cp <= $.LATIN_SMALL_Z;
|
|
}
|
|
|
|
function isAsciiLetter(cp) {
|
|
return isAsciiLower(cp) || isAsciiUpper(cp);
|
|
}
|
|
|
|
function isAsciiAlphaNumeric(cp) {
|
|
return isAsciiLetter(cp) || isAsciiDigit(cp);
|
|
}
|
|
|
|
function isDigit(cp, isHex) {
|
|
return isAsciiDigit(cp) || isHex && (cp >= $.LATIN_CAPITAL_A && cp <= $.LATIN_CAPITAL_F ||
|
|
cp >= $.LATIN_SMALL_A && cp <= $.LATIN_SMALL_F);
|
|
}
|
|
|
|
function isReservedCodePoint(cp) {
|
|
return cp >= 0xD800 && cp <= 0xDFFF || cp > 0x10FFFF;
|
|
}
|
|
|
|
function toAsciiLowerCodePoint(cp) {
|
|
return cp + 0x0020;
|
|
}
|
|
|
|
//NOTE: String.fromCharCode() function can handle only characters from BMP subset.
|
|
//So, we need to workaround this manually.
|
|
//(see: https://developer.mozilla.org/en-US/docs/JavaScript/Reference/Global_Objects/String/fromCharCode#Getting_it_to_work_with_higher_values)
|
|
function toChar(cp) {
|
|
if (cp <= 0xFFFF)
|
|
return String.fromCharCode(cp);
|
|
|
|
cp -= 0x10000;
|
|
return String.fromCharCode(cp >>> 10 & 0x3FF | 0xD800) + String.fromCharCode(0xDC00 | cp & 0x3FF);
|
|
}
|
|
|
|
function toAsciiLowerChar(cp) {
|
|
return String.fromCharCode(toAsciiLowerCodePoint(cp));
|
|
}
|
|
|
|
//Tokenizer
|
|
var Tokenizer = module.exports = function (options) {
|
|
this.preprocessor = new Preprocessor();
|
|
|
|
this.tokenQueue = [];
|
|
|
|
this.allowCDATA = false;
|
|
|
|
this.state = DATA_STATE;
|
|
this.returnState = '';
|
|
|
|
this.tempBuff = [];
|
|
this.additionalAllowedCp = void 0;
|
|
this.lastStartTagName = '';
|
|
|
|
this.consumedAfterSnapshot = -1;
|
|
this.active = false;
|
|
|
|
this.currentCharacterToken = null;
|
|
this.currentToken = null;
|
|
this.currentAttr = null;
|
|
|
|
if (options && options.locationInfo)
|
|
locationInfoMixin.assign(this);
|
|
};
|
|
|
|
//Token types
|
|
Tokenizer.CHARACTER_TOKEN = 'CHARACTER_TOKEN';
|
|
Tokenizer.NULL_CHARACTER_TOKEN = 'NULL_CHARACTER_TOKEN';
|
|
Tokenizer.WHITESPACE_CHARACTER_TOKEN = 'WHITESPACE_CHARACTER_TOKEN';
|
|
Tokenizer.START_TAG_TOKEN = 'START_TAG_TOKEN';
|
|
Tokenizer.END_TAG_TOKEN = 'END_TAG_TOKEN';
|
|
Tokenizer.COMMENT_TOKEN = 'COMMENT_TOKEN';
|
|
Tokenizer.DOCTYPE_TOKEN = 'DOCTYPE_TOKEN';
|
|
Tokenizer.EOF_TOKEN = 'EOF_TOKEN';
|
|
Tokenizer.HIBERNATION_TOKEN = 'HIBERNATION_TOKEN';
|
|
|
|
//Tokenizer initial states for different modes
|
|
Tokenizer.MODE = Tokenizer.prototype.MODE = {
|
|
DATA: DATA_STATE,
|
|
RCDATA: RCDATA_STATE,
|
|
RAWTEXT: RAWTEXT_STATE,
|
|
SCRIPT_DATA: SCRIPT_DATA_STATE,
|
|
PLAINTEXT: PLAINTEXT_STATE
|
|
};
|
|
|
|
//Static
|
|
Tokenizer.getTokenAttr = function (token, attrName) {
|
|
for (var i = token.attrs.length - 1; i >= 0; i--) {
|
|
if (token.attrs[i].name === attrName)
|
|
return token.attrs[i].value;
|
|
}
|
|
|
|
return null;
|
|
};
|
|
|
|
//API
|
|
Tokenizer.prototype.getNextToken = function () {
|
|
while (!this.tokenQueue.length && this.active) {
|
|
this._hibernationSnapshot();
|
|
|
|
var cp = this._consume();
|
|
|
|
if (!this._ensureHibernation())
|
|
this[this.state](cp);
|
|
}
|
|
|
|
return this.tokenQueue.shift();
|
|
};
|
|
|
|
Tokenizer.prototype.write = function (chunk, isLastChunk) {
|
|
this.active = true;
|
|
this.preprocessor.write(chunk, isLastChunk);
|
|
};
|
|
|
|
Tokenizer.prototype.insertHtmlAtCurrentPos = function (chunk) {
|
|
this.active = true;
|
|
this.preprocessor.insertHtmlAtCurrentPos(chunk);
|
|
};
|
|
|
|
//Hibernation
|
|
Tokenizer.prototype._hibernationSnapshot = function () {
|
|
this.consumedAfterSnapshot = 0;
|
|
};
|
|
|
|
Tokenizer.prototype._ensureHibernation = function () {
|
|
if (this.preprocessor.endOfChunkHit) {
|
|
for (; this.consumedAfterSnapshot > 0; this.consumedAfterSnapshot--)
|
|
this.preprocessor.retreat();
|
|
|
|
this.active = false;
|
|
this.tokenQueue.push({type: Tokenizer.HIBERNATION_TOKEN});
|
|
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
};
|
|
|
|
|
|
//Consumption
|
|
Tokenizer.prototype._consume = function () {
|
|
this.consumedAfterSnapshot++;
|
|
return this.preprocessor.advance();
|
|
};
|
|
|
|
Tokenizer.prototype._unconsume = function () {
|
|
this.consumedAfterSnapshot--;
|
|
this.preprocessor.retreat();
|
|
};
|
|
|
|
Tokenizer.prototype._unconsumeSeveral = function (count) {
|
|
while (count--)
|
|
this._unconsume();
|
|
};
|
|
|
|
Tokenizer.prototype._reconsumeInState = function (state) {
|
|
this.state = state;
|
|
this._unconsume();
|
|
};
|
|
|
|
Tokenizer.prototype._consumeSubsequentIfMatch = function (pattern, startCp, caseSensitive) {
|
|
var consumedCount = 0,
|
|
isMatch = true,
|
|
patternLength = pattern.length,
|
|
patternPos = 0,
|
|
cp = startCp,
|
|
patternCp = void 0;
|
|
|
|
for (; patternPos < patternLength; patternPos++) {
|
|
if (patternPos > 0) {
|
|
cp = this._consume();
|
|
consumedCount++;
|
|
}
|
|
|
|
if (cp === $.EOF) {
|
|
isMatch = false;
|
|
break;
|
|
}
|
|
|
|
patternCp = pattern[patternPos];
|
|
|
|
if (cp !== patternCp && (caseSensitive || cp !== toAsciiLowerCodePoint(patternCp))) {
|
|
isMatch = false;
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (!isMatch)
|
|
this._unconsumeSeveral(consumedCount);
|
|
|
|
return isMatch;
|
|
};
|
|
|
|
//Lookahead
|
|
Tokenizer.prototype._lookahead = function () {
|
|
var cp = this._consume();
|
|
|
|
this._unconsume();
|
|
|
|
return cp;
|
|
};
|
|
|
|
//Temp buffer
|
|
Tokenizer.prototype.isTempBufferEqualToScriptString = function () {
|
|
if (this.tempBuff.length !== $$.SCRIPT_STRING.length)
|
|
return false;
|
|
|
|
for (var i = 0; i < this.tempBuff.length; i++) {
|
|
if (this.tempBuff[i] !== $$.SCRIPT_STRING[i])
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
};
|
|
|
|
//Token creation
|
|
Tokenizer.prototype._createStartTagToken = function () {
|
|
this.currentToken = {
|
|
type: Tokenizer.START_TAG_TOKEN,
|
|
tagName: '',
|
|
selfClosing: false,
|
|
attrs: []
|
|
};
|
|
};
|
|
|
|
Tokenizer.prototype._createEndTagToken = function () {
|
|
this.currentToken = {
|
|
type: Tokenizer.END_TAG_TOKEN,
|
|
tagName: '',
|
|
attrs: []
|
|
};
|
|
};
|
|
|
|
Tokenizer.prototype._createCommentToken = function () {
|
|
this.currentToken = {
|
|
type: Tokenizer.COMMENT_TOKEN,
|
|
data: ''
|
|
};
|
|
};
|
|
|
|
Tokenizer.prototype._createDoctypeToken = function (initialName) {
|
|
this.currentToken = {
|
|
type: Tokenizer.DOCTYPE_TOKEN,
|
|
name: initialName,
|
|
forceQuirks: false,
|
|
publicId: null,
|
|
systemId: null
|
|
};
|
|
};
|
|
|
|
Tokenizer.prototype._createCharacterToken = function (type, ch) {
|
|
this.currentCharacterToken = {
|
|
type: type,
|
|
chars: ch
|
|
};
|
|
};
|
|
|
|
//Tag attributes
|
|
Tokenizer.prototype._createAttr = function (attrNameFirstCh) {
|
|
this.currentAttr = {
|
|
name: attrNameFirstCh,
|
|
value: ''
|
|
};
|
|
};
|
|
|
|
Tokenizer.prototype._isDuplicateAttr = function () {
|
|
return Tokenizer.getTokenAttr(this.currentToken, this.currentAttr.name) !== null;
|
|
};
|
|
|
|
Tokenizer.prototype._leaveAttrName = function (toState) {
|
|
this.state = toState;
|
|
|
|
if (!this._isDuplicateAttr())
|
|
this.currentToken.attrs.push(this.currentAttr);
|
|
};
|
|
|
|
Tokenizer.prototype._leaveAttrValue = function (toState) {
|
|
this.state = toState;
|
|
};
|
|
|
|
//Appropriate end tag token
|
|
//(see: http://www.whatwg.org/specs/web-apps/current-work/multipage/tokenization.html#appropriate-end-tag-token)
|
|
Tokenizer.prototype._isAppropriateEndTagToken = function () {
|
|
return this.lastStartTagName === this.currentToken.tagName;
|
|
};
|
|
|
|
//Token emission
|
|
Tokenizer.prototype._emitCurrentToken = function () {
|
|
this._emitCurrentCharacterToken();
|
|
|
|
//NOTE: store emited start tag's tagName to determine is the following end tag token is appropriate.
|
|
if (this.currentToken.type === Tokenizer.START_TAG_TOKEN)
|
|
this.lastStartTagName = this.currentToken.tagName;
|
|
|
|
this.tokenQueue.push(this.currentToken);
|
|
this.currentToken = null;
|
|
};
|
|
|
|
Tokenizer.prototype._emitCurrentCharacterToken = function () {
|
|
if (this.currentCharacterToken) {
|
|
this.tokenQueue.push(this.currentCharacterToken);
|
|
this.currentCharacterToken = null;
|
|
}
|
|
};
|
|
|
|
Tokenizer.prototype._emitEOFToken = function () {
|
|
this._emitCurrentCharacterToken();
|
|
this.tokenQueue.push({type: Tokenizer.EOF_TOKEN});
|
|
};
|
|
|
|
//Characters emission
|
|
|
|
//OPTIMIZATION: specification uses only one type of character tokens (one token per character).
|
|
//This causes a huge memory overhead and a lot of unnecessary parser loops. parse5 uses 3 groups of characters.
|
|
//If we have a sequence of characters that belong to the same group, parser can process it
|
|
//as a single solid character token.
|
|
//So, there are 3 types of character tokens in parse5:
|
|
//1)NULL_CHARACTER_TOKEN - \u0000-character sequences (e.g. '\u0000\u0000\u0000')
|
|
//2)WHITESPACE_CHARACTER_TOKEN - any whitespace/new-line character sequences (e.g. '\n \r\t \f')
|
|
//3)CHARACTER_TOKEN - any character sequence which don't belong to groups 1 and 2 (e.g. 'abcdef1234@@#$%^')
|
|
Tokenizer.prototype._appendCharToCurrentCharacterToken = function (type, ch) {
|
|
if (this.currentCharacterToken && this.currentCharacterToken.type !== type)
|
|
this._emitCurrentCharacterToken();
|
|
|
|
if (this.currentCharacterToken)
|
|
this.currentCharacterToken.chars += ch;
|
|
|
|
else
|
|
this._createCharacterToken(type, ch);
|
|
};
|
|
|
|
Tokenizer.prototype._emitCodePoint = function (cp) {
|
|
var type = Tokenizer.CHARACTER_TOKEN;
|
|
|
|
if (isWhitespace(cp))
|
|
type = Tokenizer.WHITESPACE_CHARACTER_TOKEN;
|
|
|
|
else if (cp === $.NULL)
|
|
type = Tokenizer.NULL_CHARACTER_TOKEN;
|
|
|
|
this._appendCharToCurrentCharacterToken(type, toChar(cp));
|
|
};
|
|
|
|
Tokenizer.prototype._emitSeveralCodePoints = function (codePoints) {
|
|
for (var i = 0; i < codePoints.length; i++)
|
|
this._emitCodePoint(codePoints[i]);
|
|
};
|
|
|
|
//NOTE: used then we emit character explicitly. This is always a non-whitespace and a non-null character.
|
|
//So we can avoid additional checks here.
|
|
Tokenizer.prototype._emitChar = function (ch) {
|
|
this._appendCharToCurrentCharacterToken(Tokenizer.CHARACTER_TOKEN, ch);
|
|
};
|
|
|
|
//Character reference tokenization
|
|
Tokenizer.prototype._consumeNumericEntity = function (isHex) {
|
|
var digits = '',
|
|
nextCp = void 0;
|
|
|
|
do {
|
|
digits += toChar(this._consume());
|
|
nextCp = this._lookahead();
|
|
} while (nextCp !== $.EOF && isDigit(nextCp, isHex));
|
|
|
|
if (this._lookahead() === $.SEMICOLON)
|
|
this._consume();
|
|
|
|
var referencedCp = parseInt(digits, isHex ? 16 : 10),
|
|
replacement = NUMERIC_ENTITY_REPLACEMENTS[referencedCp];
|
|
|
|
if (replacement)
|
|
return replacement;
|
|
|
|
if (isReservedCodePoint(referencedCp))
|
|
return $.REPLACEMENT_CHARACTER;
|
|
|
|
return referencedCp;
|
|
};
|
|
|
|
Tokenizer.prototype._consumeNamedEntity = function (startCp, inAttr) {
|
|
var referencedCodePoints = null,
|
|
entityCodePointsCount = 0,
|
|
cp = startCp,
|
|
leaf = NAMED_ENTITY_TRIE[cp],
|
|
consumedCount = 1,
|
|
semicolonTerminated = false;
|
|
|
|
for (; leaf && cp !== $.EOF; cp = this._consume(), consumedCount++, leaf = leaf.l && leaf.l[cp]) {
|
|
if (leaf.c) {
|
|
//NOTE: we have at least one named reference match. But we don't stop lookup at this point,
|
|
//because longer matches still can be found (e.g. '¬' and '∉') except the case
|
|
//then found match is terminated by semicolon.
|
|
referencedCodePoints = leaf.c;
|
|
entityCodePointsCount = consumedCount;
|
|
|
|
if (cp === $.SEMICOLON) {
|
|
semicolonTerminated = true;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (referencedCodePoints) {
|
|
if (!semicolonTerminated) {
|
|
//NOTE: unconsume excess (e.g. 'it' in '¬it')
|
|
this._unconsumeSeveral(consumedCount - entityCodePointsCount);
|
|
|
|
//NOTE: If the character reference is being consumed as part of an attribute and the next character
|
|
//is either a U+003D EQUALS SIGN character (=) or an alphanumeric ASCII character, then, for historical
|
|
//reasons, all the characters that were matched after the U+0026 AMPERSAND character (&) must be
|
|
//unconsumed, and nothing is returned.
|
|
//However, if this next character is in fact a U+003D EQUALS SIGN character (=), then this is a
|
|
//parse error, because some legacy user agents will misinterpret the markup in those cases.
|
|
//(see: http://www.whatwg.org/specs/web-apps/current-work/multipage/tokenization.html#tokenizing-character-references)
|
|
if (inAttr) {
|
|
var nextCp = this._lookahead();
|
|
|
|
if (nextCp === $.EQUALS_SIGN || isAsciiAlphaNumeric(nextCp)) {
|
|
this._unconsumeSeveral(entityCodePointsCount);
|
|
return null;
|
|
}
|
|
}
|
|
}
|
|
|
|
return referencedCodePoints;
|
|
}
|
|
|
|
this._unconsumeSeveral(consumedCount);
|
|
|
|
return null;
|
|
};
|
|
|
|
Tokenizer.prototype._consumeCharacterReference = function (startCp, inAttr) {
|
|
if (isWhitespace(startCp) || startCp === $.GREATER_THAN_SIGN ||
|
|
startCp === $.AMPERSAND || startCp === this.additionalAllowedCp || startCp === $.EOF) {
|
|
//NOTE: not a character reference. No characters are consumed, and nothing is returned.
|
|
this._unconsume();
|
|
return null;
|
|
}
|
|
|
|
if (startCp === $.NUMBER_SIGN) {
|
|
//NOTE: we have a numeric entity candidate, now we should determine if it's hex or decimal
|
|
var isHex = false,
|
|
nextCp = this._lookahead();
|
|
|
|
if (nextCp === $.LATIN_SMALL_X || nextCp === $.LATIN_CAPITAL_X) {
|
|
this._consume();
|
|
isHex = true;
|
|
}
|
|
|
|
nextCp = this._lookahead();
|
|
|
|
//NOTE: if we have at least one digit this is a numeric entity for sure, so we consume it
|
|
if (nextCp !== $.EOF && isDigit(nextCp, isHex))
|
|
return [this._consumeNumericEntity(isHex)];
|
|
|
|
//NOTE: otherwise this is a bogus number entity and a parse error. Unconsume the number sign
|
|
//and the 'x'-character if appropriate.
|
|
this._unconsumeSeveral(isHex ? 2 : 1);
|
|
return null;
|
|
}
|
|
|
|
return this._consumeNamedEntity(startCp, inAttr);
|
|
};
|
|
|
|
//State machine
|
|
var _ = Tokenizer.prototype;
|
|
|
|
//12.2.4.1 Data state
|
|
//------------------------------------------------------------------
|
|
_[DATA_STATE] = function dataState(cp) {
|
|
this.preprocessor.dropParsedChunk();
|
|
|
|
if (cp === $.AMPERSAND)
|
|
this.state = CHARACTER_REFERENCE_IN_DATA_STATE;
|
|
|
|
else if (cp === $.LESS_THAN_SIGN)
|
|
this.state = TAG_OPEN_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this._emitCodePoint(cp);
|
|
|
|
else if (cp === $.EOF)
|
|
this._emitEOFToken();
|
|
|
|
else
|
|
this._emitCodePoint(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.2 Character reference in data state
|
|
//------------------------------------------------------------------
|
|
_[CHARACTER_REFERENCE_IN_DATA_STATE] = function characterReferenceInDataState(cp) {
|
|
this.additionalAllowedCp = void 0;
|
|
|
|
var referencedCodePoints = this._consumeCharacterReference(cp, false);
|
|
|
|
if (!this._ensureHibernation()) {
|
|
if (referencedCodePoints)
|
|
this._emitSeveralCodePoints(referencedCodePoints);
|
|
|
|
else
|
|
this._emitChar('&');
|
|
|
|
this.state = DATA_STATE;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.3 RCDATA state
|
|
//------------------------------------------------------------------
|
|
_[RCDATA_STATE] = function rcdataState(cp) {
|
|
this.preprocessor.dropParsedChunk();
|
|
|
|
if (cp === $.AMPERSAND)
|
|
this.state = CHARACTER_REFERENCE_IN_RCDATA_STATE;
|
|
|
|
else if (cp === $.LESS_THAN_SIGN)
|
|
this.state = RCDATA_LESS_THAN_SIGN_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
|
|
else if (cp === $.EOF)
|
|
this._emitEOFToken();
|
|
|
|
else
|
|
this._emitCodePoint(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.4 Character reference in RCDATA state
|
|
//------------------------------------------------------------------
|
|
_[CHARACTER_REFERENCE_IN_RCDATA_STATE] = function characterReferenceInRcdataState(cp) {
|
|
this.additionalAllowedCp = void 0;
|
|
|
|
var referencedCodePoints = this._consumeCharacterReference(cp, false);
|
|
|
|
if (!this._ensureHibernation()) {
|
|
if (referencedCodePoints)
|
|
this._emitSeveralCodePoints(referencedCodePoints);
|
|
|
|
else
|
|
this._emitChar('&');
|
|
|
|
this.state = RCDATA_STATE;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.5 RAWTEXT state
|
|
//------------------------------------------------------------------
|
|
_[RAWTEXT_STATE] = function rawtextState(cp) {
|
|
this.preprocessor.dropParsedChunk();
|
|
|
|
if (cp === $.LESS_THAN_SIGN)
|
|
this.state = RAWTEXT_LESS_THAN_SIGN_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
|
|
else if (cp === $.EOF)
|
|
this._emitEOFToken();
|
|
|
|
else
|
|
this._emitCodePoint(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.6 Script data state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_STATE] = function scriptDataState(cp) {
|
|
this.preprocessor.dropParsedChunk();
|
|
|
|
if (cp === $.LESS_THAN_SIGN)
|
|
this.state = SCRIPT_DATA_LESS_THAN_SIGN_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
|
|
else if (cp === $.EOF)
|
|
this._emitEOFToken();
|
|
|
|
else
|
|
this._emitCodePoint(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.7 PLAINTEXT state
|
|
//------------------------------------------------------------------
|
|
_[PLAINTEXT_STATE] = function plaintextState(cp) {
|
|
this.preprocessor.dropParsedChunk();
|
|
|
|
if (cp === $.NULL)
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
|
|
else if (cp === $.EOF)
|
|
this._emitEOFToken();
|
|
|
|
else
|
|
this._emitCodePoint(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.8 Tag open state
|
|
//------------------------------------------------------------------
|
|
_[TAG_OPEN_STATE] = function tagOpenState(cp) {
|
|
if (cp === $.EXCLAMATION_MARK)
|
|
this.state = MARKUP_DECLARATION_OPEN_STATE;
|
|
|
|
else if (cp === $.SOLIDUS)
|
|
this.state = END_TAG_OPEN_STATE;
|
|
|
|
else if (isAsciiLetter(cp)) {
|
|
this._createStartTagToken();
|
|
this._reconsumeInState(TAG_NAME_STATE);
|
|
}
|
|
|
|
else if (cp === $.QUESTION_MARK)
|
|
this._reconsumeInState(BOGUS_COMMENT_STATE);
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.9 End tag open state
|
|
//------------------------------------------------------------------
|
|
_[END_TAG_OPEN_STATE] = function endTagOpenState(cp) {
|
|
if (isAsciiLetter(cp)) {
|
|
this._createEndTagToken();
|
|
this._reconsumeInState(TAG_NAME_STATE);
|
|
}
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN)
|
|
this.state = DATA_STATE;
|
|
|
|
else if (cp === $.EOF) {
|
|
this._reconsumeInState(DATA_STATE);
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
}
|
|
|
|
else
|
|
this._reconsumeInState(BOGUS_COMMENT_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.10 Tag name state
|
|
//------------------------------------------------------------------
|
|
_[TAG_NAME_STATE] = function tagNameState(cp) {
|
|
if (isWhitespace(cp))
|
|
this.state = BEFORE_ATTRIBUTE_NAME_STATE;
|
|
|
|
else if (cp === $.SOLIDUS)
|
|
this.state = SELF_CLOSING_START_TAG_STATE;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (isAsciiUpper(cp))
|
|
this.currentToken.tagName += toAsciiLowerChar(cp);
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentToken.tagName += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this.currentToken.tagName += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.11 RCDATA less-than sign state
|
|
//------------------------------------------------------------------
|
|
_[RCDATA_LESS_THAN_SIGN_STATE] = function rcdataLessThanSignState(cp) {
|
|
if (cp === $.SOLIDUS) {
|
|
this.tempBuff = [];
|
|
this.state = RCDATA_END_TAG_OPEN_STATE;
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._reconsumeInState(RCDATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.12 RCDATA end tag open state
|
|
//------------------------------------------------------------------
|
|
_[RCDATA_END_TAG_OPEN_STATE] = function rcdataEndTagOpenState(cp) {
|
|
if (isAsciiLetter(cp)) {
|
|
this._createEndTagToken();
|
|
this._reconsumeInState(RCDATA_END_TAG_NAME_STATE);
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._reconsumeInState(RCDATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.13 RCDATA end tag name state
|
|
//------------------------------------------------------------------
|
|
_[RCDATA_END_TAG_NAME_STATE] = function rcdataEndTagNameState(cp) {
|
|
if (isAsciiUpper(cp)) {
|
|
this.currentToken.tagName += toAsciiLowerChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else if (isAsciiLower(cp)) {
|
|
this.currentToken.tagName += toChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else {
|
|
if (this._isAppropriateEndTagToken()) {
|
|
if (isWhitespace(cp)) {
|
|
this.state = BEFORE_ATTRIBUTE_NAME_STATE;
|
|
return;
|
|
}
|
|
|
|
if (cp === $.SOLIDUS) {
|
|
this.state = SELF_CLOSING_START_TAG_STATE;
|
|
return;
|
|
}
|
|
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
return;
|
|
}
|
|
}
|
|
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._emitSeveralCodePoints(this.tempBuff);
|
|
this._reconsumeInState(RCDATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.14 RAWTEXT less-than sign state
|
|
//------------------------------------------------------------------
|
|
_[RAWTEXT_LESS_THAN_SIGN_STATE] = function rawtextLessThanSignState(cp) {
|
|
if (cp === $.SOLIDUS) {
|
|
this.tempBuff = [];
|
|
this.state = RAWTEXT_END_TAG_OPEN_STATE;
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._reconsumeInState(RAWTEXT_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.15 RAWTEXT end tag open state
|
|
//------------------------------------------------------------------
|
|
_[RAWTEXT_END_TAG_OPEN_STATE] = function rawtextEndTagOpenState(cp) {
|
|
if (isAsciiLetter(cp)) {
|
|
this._createEndTagToken();
|
|
this._reconsumeInState(RAWTEXT_END_TAG_NAME_STATE);
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._reconsumeInState(RAWTEXT_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.16 RAWTEXT end tag name state
|
|
//------------------------------------------------------------------
|
|
_[RAWTEXT_END_TAG_NAME_STATE] = function rawtextEndTagNameState(cp) {
|
|
if (isAsciiUpper(cp)) {
|
|
this.currentToken.tagName += toAsciiLowerChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else if (isAsciiLower(cp)) {
|
|
this.currentToken.tagName += toChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else {
|
|
if (this._isAppropriateEndTagToken()) {
|
|
if (isWhitespace(cp)) {
|
|
this.state = BEFORE_ATTRIBUTE_NAME_STATE;
|
|
return;
|
|
}
|
|
|
|
if (cp === $.SOLIDUS) {
|
|
this.state = SELF_CLOSING_START_TAG_STATE;
|
|
return;
|
|
}
|
|
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
return;
|
|
}
|
|
}
|
|
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._emitSeveralCodePoints(this.tempBuff);
|
|
this._reconsumeInState(RAWTEXT_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.17 Script data less-than sign state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_LESS_THAN_SIGN_STATE] = function scriptDataLessThanSignState(cp) {
|
|
if (cp === $.SOLIDUS) {
|
|
this.tempBuff = [];
|
|
this.state = SCRIPT_DATA_END_TAG_OPEN_STATE;
|
|
}
|
|
|
|
else if (cp === $.EXCLAMATION_MARK) {
|
|
this.state = SCRIPT_DATA_ESCAPE_START_STATE;
|
|
this._emitChar('<');
|
|
this._emitChar('!');
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._reconsumeInState(SCRIPT_DATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.18 Script data end tag open state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_END_TAG_OPEN_STATE] = function scriptDataEndTagOpenState(cp) {
|
|
if (isAsciiLetter(cp)) {
|
|
this._createEndTagToken();
|
|
this._reconsumeInState(SCRIPT_DATA_END_TAG_NAME_STATE);
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._reconsumeInState(SCRIPT_DATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.19 Script data end tag name state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_END_TAG_NAME_STATE] = function scriptDataEndTagNameState(cp) {
|
|
if (isAsciiUpper(cp)) {
|
|
this.currentToken.tagName += toAsciiLowerChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else if (isAsciiLower(cp)) {
|
|
this.currentToken.tagName += toChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else {
|
|
if (this._isAppropriateEndTagToken()) {
|
|
if (isWhitespace(cp)) {
|
|
this.state = BEFORE_ATTRIBUTE_NAME_STATE;
|
|
return;
|
|
}
|
|
|
|
else if (cp === $.SOLIDUS) {
|
|
this.state = SELF_CLOSING_START_TAG_STATE;
|
|
return;
|
|
}
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
return;
|
|
}
|
|
}
|
|
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._emitSeveralCodePoints(this.tempBuff);
|
|
this._reconsumeInState(SCRIPT_DATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.20 Script data escape start state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPE_START_STATE] = function scriptDataEscapeStartState(cp) {
|
|
if (cp === $.HYPHEN_MINUS) {
|
|
this.state = SCRIPT_DATA_ESCAPE_START_DASH_STATE;
|
|
this._emitChar('-');
|
|
}
|
|
|
|
else
|
|
this._reconsumeInState(SCRIPT_DATA_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.21 Script data escape start dash state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPE_START_DASH_STATE] = function scriptDataEscapeStartDashState(cp) {
|
|
if (cp === $.HYPHEN_MINUS) {
|
|
this.state = SCRIPT_DATA_ESCAPED_DASH_DASH_STATE;
|
|
this._emitChar('-');
|
|
}
|
|
|
|
else
|
|
this._reconsumeInState(SCRIPT_DATA_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.22 Script data escaped state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPED_STATE] = function scriptDataEscapedState(cp) {
|
|
if (cp === $.HYPHEN_MINUS) {
|
|
this.state = SCRIPT_DATA_ESCAPED_DASH_STATE;
|
|
this._emitChar('-');
|
|
}
|
|
|
|
else if (cp === $.LESS_THAN_SIGN)
|
|
this.state = SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this._emitCodePoint(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.23 Script data escaped dash state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPED_DASH_STATE] = function scriptDataEscapedDashState(cp) {
|
|
if (cp === $.HYPHEN_MINUS) {
|
|
this.state = SCRIPT_DATA_ESCAPED_DASH_DASH_STATE;
|
|
this._emitChar('-');
|
|
}
|
|
|
|
else if (cp === $.LESS_THAN_SIGN)
|
|
this.state = SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN_STATE;
|
|
|
|
else if (cp === $.NULL) {
|
|
this.state = SCRIPT_DATA_ESCAPED_STATE;
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
}
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else {
|
|
this.state = SCRIPT_DATA_ESCAPED_STATE;
|
|
this._emitCodePoint(cp);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.24 Script data escaped dash dash state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPED_DASH_DASH_STATE] = function scriptDataEscapedDashDashState(cp) {
|
|
if (cp === $.HYPHEN_MINUS)
|
|
this._emitChar('-');
|
|
|
|
else if (cp === $.LESS_THAN_SIGN)
|
|
this.state = SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN_STATE;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = SCRIPT_DATA_STATE;
|
|
this._emitChar('>');
|
|
}
|
|
|
|
else if (cp === $.NULL) {
|
|
this.state = SCRIPT_DATA_ESCAPED_STATE;
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
}
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else {
|
|
this.state = SCRIPT_DATA_ESCAPED_STATE;
|
|
this._emitCodePoint(cp);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.25 Script data escaped less-than sign state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN_STATE] = function scriptDataEscapedLessThanSignState(cp) {
|
|
if (cp === $.SOLIDUS) {
|
|
this.tempBuff = [];
|
|
this.state = SCRIPT_DATA_ESCAPED_END_TAG_OPEN_STATE;
|
|
}
|
|
|
|
else if (isAsciiLetter(cp)) {
|
|
this.tempBuff = [];
|
|
this._emitChar('<');
|
|
this._reconsumeInState(SCRIPT_DATA_DOUBLE_ESCAPE_START_STATE);
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._reconsumeInState(SCRIPT_DATA_ESCAPED_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.26 Script data escaped end tag open state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPED_END_TAG_OPEN_STATE] = function scriptDataEscapedEndTagOpenState(cp) {
|
|
if (isAsciiLetter(cp)) {
|
|
this._createEndTagToken();
|
|
this._reconsumeInState(SCRIPT_DATA_ESCAPED_END_TAG_NAME_STATE);
|
|
}
|
|
|
|
else {
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._reconsumeInState(SCRIPT_DATA_ESCAPED_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.27 Script data escaped end tag name state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_ESCAPED_END_TAG_NAME_STATE] = function scriptDataEscapedEndTagNameState(cp) {
|
|
if (isAsciiUpper(cp)) {
|
|
this.currentToken.tagName += toAsciiLowerChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else if (isAsciiLower(cp)) {
|
|
this.currentToken.tagName += toChar(cp);
|
|
this.tempBuff.push(cp);
|
|
}
|
|
|
|
else {
|
|
if (this._isAppropriateEndTagToken()) {
|
|
if (isWhitespace(cp)) {
|
|
this.state = BEFORE_ATTRIBUTE_NAME_STATE;
|
|
return;
|
|
}
|
|
|
|
if (cp === $.SOLIDUS) {
|
|
this.state = SELF_CLOSING_START_TAG_STATE;
|
|
return;
|
|
}
|
|
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
return;
|
|
}
|
|
}
|
|
|
|
this._emitChar('<');
|
|
this._emitChar('/');
|
|
this._emitSeveralCodePoints(this.tempBuff);
|
|
this._reconsumeInState(SCRIPT_DATA_ESCAPED_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.28 Script data double escape start state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_DOUBLE_ESCAPE_START_STATE] = function scriptDataDoubleEscapeStartState(cp) {
|
|
if (isWhitespace(cp) || cp === $.SOLIDUS || cp === $.GREATER_THAN_SIGN) {
|
|
this.state = this.isTempBufferEqualToScriptString() ? SCRIPT_DATA_DOUBLE_ESCAPED_STATE : SCRIPT_DATA_ESCAPED_STATE;
|
|
this._emitCodePoint(cp);
|
|
}
|
|
|
|
else if (isAsciiUpper(cp)) {
|
|
this.tempBuff.push(toAsciiLowerCodePoint(cp));
|
|
this._emitCodePoint(cp);
|
|
}
|
|
|
|
else if (isAsciiLower(cp)) {
|
|
this.tempBuff.push(cp);
|
|
this._emitCodePoint(cp);
|
|
}
|
|
|
|
else
|
|
this._reconsumeInState(SCRIPT_DATA_ESCAPED_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.29 Script data double escaped state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_DOUBLE_ESCAPED_STATE] = function scriptDataDoubleEscapedState(cp) {
|
|
if (cp === $.HYPHEN_MINUS) {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_DASH_STATE;
|
|
this._emitChar('-');
|
|
}
|
|
|
|
else if (cp === $.LESS_THAN_SIGN) {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN_STATE;
|
|
this._emitChar('<');
|
|
}
|
|
|
|
else if (cp === $.NULL)
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this._emitCodePoint(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.30 Script data double escaped dash state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_DOUBLE_ESCAPED_DASH_STATE] = function scriptDataDoubleEscapedDashState(cp) {
|
|
if (cp === $.HYPHEN_MINUS) {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH_STATE;
|
|
this._emitChar('-');
|
|
}
|
|
|
|
else if (cp === $.LESS_THAN_SIGN) {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN_STATE;
|
|
this._emitChar('<');
|
|
}
|
|
|
|
else if (cp === $.NULL) {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_STATE;
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
}
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_STATE;
|
|
this._emitCodePoint(cp);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.31 Script data double escaped dash dash state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH_STATE] = function scriptDataDoubleEscapedDashDashState(cp) {
|
|
if (cp === $.HYPHEN_MINUS)
|
|
this._emitChar('-');
|
|
|
|
else if (cp === $.LESS_THAN_SIGN) {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN_STATE;
|
|
this._emitChar('<');
|
|
}
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = SCRIPT_DATA_STATE;
|
|
this._emitChar('>');
|
|
}
|
|
|
|
else if (cp === $.NULL) {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_STATE;
|
|
this._emitChar(UNICODE.REPLACEMENT_CHARACTER);
|
|
}
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else {
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPED_STATE;
|
|
this._emitCodePoint(cp);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.32 Script data double escaped less-than sign state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN_STATE] = function scriptDataDoubleEscapedLessThanSignState(cp) {
|
|
if (cp === $.SOLIDUS) {
|
|
this.tempBuff = [];
|
|
this.state = SCRIPT_DATA_DOUBLE_ESCAPE_END_STATE;
|
|
this._emitChar('/');
|
|
}
|
|
|
|
else
|
|
this._reconsumeInState(SCRIPT_DATA_DOUBLE_ESCAPED_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.33 Script data double escape end state
|
|
//------------------------------------------------------------------
|
|
_[SCRIPT_DATA_DOUBLE_ESCAPE_END_STATE] = function scriptDataDoubleEscapeEndState(cp) {
|
|
if (isWhitespace(cp) || cp === $.SOLIDUS || cp === $.GREATER_THAN_SIGN) {
|
|
this.state = this.isTempBufferEqualToScriptString() ? SCRIPT_DATA_ESCAPED_STATE : SCRIPT_DATA_DOUBLE_ESCAPED_STATE;
|
|
|
|
this._emitCodePoint(cp);
|
|
}
|
|
|
|
else if (isAsciiUpper(cp)) {
|
|
this.tempBuff.push(toAsciiLowerCodePoint(cp));
|
|
this._emitCodePoint(cp);
|
|
}
|
|
|
|
else if (isAsciiLower(cp)) {
|
|
this.tempBuff.push(cp);
|
|
this._emitCodePoint(cp);
|
|
}
|
|
|
|
else
|
|
this._reconsumeInState(SCRIPT_DATA_DOUBLE_ESCAPED_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.34 Before attribute name state
|
|
//------------------------------------------------------------------
|
|
_[BEFORE_ATTRIBUTE_NAME_STATE] = function beforeAttributeNameState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.SOLIDUS || cp === $.GREATER_THAN_SIGN || cp === $.EOF)
|
|
this._reconsumeInState(AFTER_ATTRIBUTE_NAME_STATE);
|
|
|
|
else if (cp === $.EQUALS_SIGN) {
|
|
this._createAttr('=');
|
|
this.state = ATTRIBUTE_NAME_STATE;
|
|
}
|
|
|
|
else {
|
|
this._createAttr('');
|
|
this._reconsumeInState(ATTRIBUTE_NAME_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.35 Attribute name state
|
|
//------------------------------------------------------------------
|
|
_[ATTRIBUTE_NAME_STATE] = function attributeNameState(cp) {
|
|
if (isWhitespace(cp) || cp === $.SOLIDUS || cp === $.GREATER_THAN_SIGN || cp === $.EOF) {
|
|
this._leaveAttrName(AFTER_ATTRIBUTE_NAME_STATE);
|
|
this._unconsume();
|
|
}
|
|
|
|
else if (cp === $.EQUALS_SIGN)
|
|
this._leaveAttrName(BEFORE_ATTRIBUTE_VALUE_STATE);
|
|
|
|
else if (isAsciiUpper(cp))
|
|
this.currentAttr.name += toAsciiLowerChar(cp);
|
|
|
|
else if (cp === $.QUOTATION_MARK || cp === $.APOSTROPHE || cp === $.LESS_THAN_SIGN)
|
|
this.currentAttr.name += toChar(cp);
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentAttr.name += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else
|
|
this.currentAttr.name += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.36 After attribute name state
|
|
//------------------------------------------------------------------
|
|
_[AFTER_ATTRIBUTE_NAME_STATE] = function afterAttributeNameState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.SOLIDUS)
|
|
this.state = SELF_CLOSING_START_TAG_STATE;
|
|
|
|
else if (cp === $.EQUALS_SIGN)
|
|
this.state = BEFORE_ATTRIBUTE_VALUE_STATE;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else {
|
|
this._createAttr('');
|
|
this._reconsumeInState(ATTRIBUTE_NAME_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.37 Before attribute value state
|
|
//------------------------------------------------------------------
|
|
_[BEFORE_ATTRIBUTE_VALUE_STATE] = function beforeAttributeValueState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.QUOTATION_MARK)
|
|
this.state = ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE;
|
|
|
|
else if (cp === $.APOSTROPHE)
|
|
this.state = ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE;
|
|
|
|
else
|
|
this._reconsumeInState(ATTRIBUTE_VALUE_UNQUOTED_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.38 Attribute value (double-quoted) state
|
|
//------------------------------------------------------------------
|
|
_[ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE] = function attributeValueDoubleQuotedState(cp) {
|
|
if (cp === $.QUOTATION_MARK)
|
|
this.state = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE;
|
|
|
|
else if (cp === $.AMPERSAND) {
|
|
this.additionalAllowedCp = $.QUOTATION_MARK;
|
|
this.returnState = this.state;
|
|
this.state = CHARACTER_REFERENCE_IN_ATTRIBUTE_VALUE_STATE;
|
|
}
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentAttr.value += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this.currentAttr.value += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.39 Attribute value (single-quoted) state
|
|
//------------------------------------------------------------------
|
|
_[ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE] = function attributeValueSingleQuotedState(cp) {
|
|
if (cp === $.APOSTROPHE)
|
|
this.state = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE;
|
|
|
|
else if (cp === $.AMPERSAND) {
|
|
this.additionalAllowedCp = $.APOSTROPHE;
|
|
this.returnState = this.state;
|
|
this.state = CHARACTER_REFERENCE_IN_ATTRIBUTE_VALUE_STATE;
|
|
}
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentAttr.value += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this.currentAttr.value += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.40 Attribute value (unquoted) state
|
|
//------------------------------------------------------------------
|
|
_[ATTRIBUTE_VALUE_UNQUOTED_STATE] = function attributeValueUnquotedState(cp) {
|
|
if (isWhitespace(cp))
|
|
this._leaveAttrValue(BEFORE_ATTRIBUTE_NAME_STATE);
|
|
|
|
else if (cp === $.AMPERSAND) {
|
|
this.additionalAllowedCp = $.GREATER_THAN_SIGN;
|
|
this.returnState = this.state;
|
|
this.state = CHARACTER_REFERENCE_IN_ATTRIBUTE_VALUE_STATE;
|
|
}
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this._leaveAttrValue(DATA_STATE);
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentAttr.value += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.QUOTATION_MARK || cp === $.APOSTROPHE || cp === $.LESS_THAN_SIGN ||
|
|
cp === $.EQUALS_SIGN || cp === $.GRAVE_ACCENT)
|
|
this.currentAttr.value += toChar(cp);
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this.currentAttr.value += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.41 Character reference in attribute value state
|
|
//------------------------------------------------------------------
|
|
_[CHARACTER_REFERENCE_IN_ATTRIBUTE_VALUE_STATE] = function characterReferenceInAttributeValueState(cp) {
|
|
var referencedCodePoints = this._consumeCharacterReference(cp, true);
|
|
|
|
if (!this._ensureHibernation()) {
|
|
if (referencedCodePoints) {
|
|
for (var i = 0; i < referencedCodePoints.length; i++)
|
|
this.currentAttr.value += toChar(referencedCodePoints[i]);
|
|
}
|
|
else
|
|
this.currentAttr.value += '&';
|
|
|
|
this.state = this.returnState;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.42 After attribute value (quoted) state
|
|
//------------------------------------------------------------------
|
|
_[AFTER_ATTRIBUTE_VALUE_QUOTED_STATE] = function afterAttributeValueQuotedState(cp) {
|
|
if (isWhitespace(cp))
|
|
this._leaveAttrValue(BEFORE_ATTRIBUTE_NAME_STATE);
|
|
|
|
else if (cp === $.SOLIDUS)
|
|
this._leaveAttrValue(SELF_CLOSING_START_TAG_STATE);
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this._leaveAttrValue(DATA_STATE);
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this._reconsumeInState(BEFORE_ATTRIBUTE_NAME_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.43 Self-closing start tag state
|
|
//------------------------------------------------------------------
|
|
_[SELF_CLOSING_START_TAG_STATE] = function selfClosingStartTagState(cp) {
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this.currentToken.selfClosing = true;
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.EOF)
|
|
this._reconsumeInState(DATA_STATE);
|
|
|
|
else
|
|
this._reconsumeInState(BEFORE_ATTRIBUTE_NAME_STATE);
|
|
};
|
|
|
|
|
|
//12.2.4.44 Bogus comment state
|
|
//------------------------------------------------------------------
|
|
_[BOGUS_COMMENT_STATE] = function bogusCommentState() {
|
|
this._createCommentToken();
|
|
this._reconsumeInState(BOGUS_COMMENT_STATE_CONTINUATION);
|
|
};
|
|
|
|
//HACK: to support streaming and make BOGUS_COMMENT_STATE reentrant we've
|
|
//introduced BOGUS_COMMENT_STATE_CONTINUATION state which will not produce
|
|
//comment token on each call.
|
|
_[BOGUS_COMMENT_STATE_CONTINUATION] = function bogusCommentStateContinuation(cp) {
|
|
while (true) {
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
break;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._reconsumeInState(DATA_STATE);
|
|
break;
|
|
}
|
|
|
|
else {
|
|
this.currentToken.data += cp === $.NULL ? UNICODE.REPLACEMENT_CHARACTER : toChar(cp);
|
|
|
|
this._hibernationSnapshot();
|
|
cp = this._consume();
|
|
|
|
if (this._ensureHibernation())
|
|
return;
|
|
}
|
|
}
|
|
|
|
this._emitCurrentToken();
|
|
};
|
|
|
|
//12.2.4.45 Markup declaration open state
|
|
//------------------------------------------------------------------
|
|
_[MARKUP_DECLARATION_OPEN_STATE] = function markupDeclarationOpenState(cp) {
|
|
var dashDashMatch = this._consumeSubsequentIfMatch($$.DASH_DASH_STRING, cp, true),
|
|
doctypeMatch = !dashDashMatch && this._consumeSubsequentIfMatch($$.DOCTYPE_STRING, cp, false),
|
|
cdataMatch = !dashDashMatch && !doctypeMatch &&
|
|
this.allowCDATA &&
|
|
this._consumeSubsequentIfMatch($$.CDATA_START_STRING, cp, true);
|
|
|
|
if (!this._ensureHibernation()) {
|
|
if (dashDashMatch) {
|
|
this._createCommentToken();
|
|
this.state = COMMENT_START_STATE;
|
|
}
|
|
|
|
else if (doctypeMatch)
|
|
this.state = DOCTYPE_STATE;
|
|
|
|
else if (cdataMatch)
|
|
this.state = CDATA_SECTION_STATE;
|
|
|
|
else
|
|
this._reconsumeInState(BOGUS_COMMENT_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.46 Comment start state
|
|
//------------------------------------------------------------------
|
|
_[COMMENT_START_STATE] = function commentStartState(cp) {
|
|
if (cp === $.HYPHEN_MINUS)
|
|
this.state = COMMENT_START_DASH_STATE;
|
|
|
|
else if (cp === $.NULL) {
|
|
this.currentToken.data += UNICODE.REPLACEMENT_CHARACTER;
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else {
|
|
this.currentToken.data += toChar(cp);
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.47 Comment start dash state
|
|
//------------------------------------------------------------------
|
|
_[COMMENT_START_DASH_STATE] = function commentStartDashState(cp) {
|
|
if (cp === $.HYPHEN_MINUS)
|
|
this.state = COMMENT_END_STATE;
|
|
|
|
else if (cp === $.NULL) {
|
|
this.currentToken.data += '-';
|
|
this.currentToken.data += UNICODE.REPLACEMENT_CHARACTER;
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else {
|
|
this.currentToken.data += '-';
|
|
this.currentToken.data += toChar(cp);
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.48 Comment state
|
|
//------------------------------------------------------------------
|
|
_[COMMENT_STATE] = function commentState(cp) {
|
|
if (cp === $.HYPHEN_MINUS)
|
|
this.state = COMMENT_END_DASH_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentToken.data += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.EOF) {
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else
|
|
this.currentToken.data += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.49 Comment end dash state
|
|
//------------------------------------------------------------------
|
|
_[COMMENT_END_DASH_STATE] = function commentEndDashState(cp) {
|
|
if (cp === $.HYPHEN_MINUS)
|
|
this.state = COMMENT_END_STATE;
|
|
|
|
else if (cp === $.NULL) {
|
|
this.currentToken.data += '-';
|
|
this.currentToken.data += UNICODE.REPLACEMENT_CHARACTER;
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else {
|
|
this.currentToken.data += '-';
|
|
this.currentToken.data += toChar(cp);
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.50 Comment end state
|
|
//------------------------------------------------------------------
|
|
_[COMMENT_END_STATE] = function commentEndState(cp) {
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.EXCLAMATION_MARK)
|
|
this.state = COMMENT_END_BANG_STATE;
|
|
|
|
else if (cp === $.HYPHEN_MINUS)
|
|
this.currentToken.data += '-';
|
|
|
|
else if (cp === $.NULL) {
|
|
this.currentToken.data += '--';
|
|
this.currentToken.data += UNICODE.REPLACEMENT_CHARACTER;
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._reconsumeInState(DATA_STATE);
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else {
|
|
this.currentToken.data += '--';
|
|
this.currentToken.data += toChar(cp);
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.51 Comment end bang state
|
|
//------------------------------------------------------------------
|
|
_[COMMENT_END_BANG_STATE] = function commentEndBangState(cp) {
|
|
if (cp === $.HYPHEN_MINUS) {
|
|
this.currentToken.data += '--!';
|
|
this.state = COMMENT_END_DASH_STATE;
|
|
}
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else if (cp === $.NULL) {
|
|
this.currentToken.data += '--!';
|
|
this.currentToken.data += UNICODE.REPLACEMENT_CHARACTER;
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else {
|
|
this.currentToken.data += '--!';
|
|
this.currentToken.data += toChar(cp);
|
|
this.state = COMMENT_STATE;
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.52 DOCTYPE state
|
|
//------------------------------------------------------------------
|
|
_[DOCTYPE_STATE] = function doctypeState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this._createDoctypeToken(null);
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._createDoctypeToken(null);
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
else {
|
|
this._createDoctypeToken('');
|
|
this._reconsumeInState(DOCTYPE_NAME_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.54 DOCTYPE name state
|
|
//------------------------------------------------------------------
|
|
_[DOCTYPE_NAME_STATE] = function doctypeNameState(cp) {
|
|
if (isWhitespace(cp) || cp === $.GREATER_THAN_SIGN || cp === $.EOF)
|
|
this._reconsumeInState(AFTER_DOCTYPE_NAME_STATE);
|
|
|
|
else if (isAsciiUpper(cp))
|
|
this.currentToken.name += toAsciiLowerChar(cp);
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentToken.name += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else
|
|
this.currentToken.name += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.55 After DOCTYPE name state
|
|
//------------------------------------------------------------------
|
|
_[AFTER_DOCTYPE_NAME_STATE] = function afterDoctypeNameState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this.state = DATA_STATE;
|
|
this._emitCurrentToken();
|
|
}
|
|
|
|
else {
|
|
var publicMatch = this._consumeSubsequentIfMatch($$.PUBLIC_STRING, cp, false),
|
|
systemMatch = !publicMatch && this._consumeSubsequentIfMatch($$.SYSTEM_STRING, cp, false);
|
|
|
|
if (!this._ensureHibernation()) {
|
|
if (publicMatch)
|
|
this.state = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE;
|
|
|
|
else if (systemMatch)
|
|
this.state = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
|
|
|
|
else {
|
|
this.currentToken.forceQuirks = true;
|
|
this.state = BOGUS_DOCTYPE_STATE;
|
|
}
|
|
}
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.57 Before DOCTYPE public identifier state
|
|
//------------------------------------------------------------------
|
|
_[BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE] = function beforeDoctypePublicIdentifierState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.QUOTATION_MARK) {
|
|
this.currentToken.publicId = '';
|
|
this.state = DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE;
|
|
}
|
|
|
|
else if (cp === $.APOSTROPHE) {
|
|
this.currentToken.publicId = '';
|
|
this.state = DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE;
|
|
}
|
|
|
|
else {
|
|
this.currentToken.forceQuirks = true;
|
|
this._reconsumeInState(BOGUS_DOCTYPE_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.58 DOCTYPE public identifier (double-quoted) state
|
|
//------------------------------------------------------------------
|
|
_[DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE] = function doctypePublicIdentifierDoubleQuotedState(cp) {
|
|
if (cp === $.QUOTATION_MARK)
|
|
this.state = BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentToken.publicId += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else
|
|
this.currentToken.publicId += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.59 DOCTYPE public identifier (single-quoted) state
|
|
//------------------------------------------------------------------
|
|
_[DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE] = function doctypePublicIdentifierSingleQuotedState(cp) {
|
|
if (cp === $.APOSTROPHE)
|
|
this.state = BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS_STATE;
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentToken.publicId += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else
|
|
this.currentToken.publicId += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.61 Between DOCTYPE public and system identifiers state
|
|
//------------------------------------------------------------------
|
|
_[BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS_STATE] = function betweenDoctypePublicAndSystemIdentifiersState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.QUOTATION_MARK) {
|
|
this.currentToken.systemId = '';
|
|
this.state = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;
|
|
}
|
|
|
|
|
|
else if (cp === $.APOSTROPHE) {
|
|
this.currentToken.systemId = '';
|
|
this.state = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;
|
|
}
|
|
|
|
else {
|
|
this.currentToken.forceQuirks = true;
|
|
this._reconsumeInState(BOGUS_DOCTYPE_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.63 Before DOCTYPE system identifier state
|
|
//------------------------------------------------------------------
|
|
_[BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE] = function beforeDoctypeSystemIdentifierState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.QUOTATION_MARK) {
|
|
this.currentToken.systemId = '';
|
|
this.state = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;
|
|
}
|
|
|
|
else if (cp === $.APOSTROPHE) {
|
|
this.currentToken.systemId = '';
|
|
this.state = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;
|
|
}
|
|
|
|
else {
|
|
this.currentToken.forceQuirks = true;
|
|
this._reconsumeInState(BOGUS_DOCTYPE_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.64 DOCTYPE system identifier (double-quoted) state
|
|
//------------------------------------------------------------------
|
|
_[DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE] = function doctypeSystemIdentifierDoubleQuotedState(cp) {
|
|
if (cp === $.QUOTATION_MARK)
|
|
this.state = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentToken.systemId += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.EOF) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else
|
|
this.currentToken.systemId += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.65 DOCTYPE system identifier (single-quoted) state
|
|
//------------------------------------------------------------------
|
|
_[DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE] = function doctypeSystemIdentifierSingleQuotedState(cp) {
|
|
if (cp === $.APOSTROPHE)
|
|
this.state = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE;
|
|
|
|
else if (cp === $.GREATER_THAN_SIGN) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.NULL)
|
|
this.currentToken.systemId += UNICODE.REPLACEMENT_CHARACTER;
|
|
|
|
else if (cp === $.EOF) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else
|
|
this.currentToken.systemId += toChar(cp);
|
|
};
|
|
|
|
|
|
//12.2.4.66 After DOCTYPE system identifier state
|
|
//------------------------------------------------------------------
|
|
_[AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE] = function afterDoctypeSystemIdentifierState(cp) {
|
|
if (isWhitespace(cp))
|
|
return;
|
|
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this.currentToken.forceQuirks = true;
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
|
|
else
|
|
this.state = BOGUS_DOCTYPE_STATE;
|
|
};
|
|
|
|
|
|
//12.2.4.67 Bogus DOCTYPE state
|
|
//------------------------------------------------------------------
|
|
_[BOGUS_DOCTYPE_STATE] = function bogusDoctypeState(cp) {
|
|
if (cp === $.GREATER_THAN_SIGN) {
|
|
this._emitCurrentToken();
|
|
this.state = DATA_STATE;
|
|
}
|
|
|
|
else if (cp === $.EOF) {
|
|
this._emitCurrentToken();
|
|
this._reconsumeInState(DATA_STATE);
|
|
}
|
|
};
|
|
|
|
|
|
//12.2.4.68 CDATA section state
|
|
//------------------------------------------------------------------
|
|
_[CDATA_SECTION_STATE] = function cdataSectionState(cp) {
|
|
while (true) {
|
|
if (cp === $.EOF) {
|
|
this._reconsumeInState(DATA_STATE);
|
|
break;
|
|
}
|
|
|
|
else {
|
|
var cdataEndMatch = this._consumeSubsequentIfMatch($$.CDATA_END_STRING, cp, true);
|
|
|
|
if (this._ensureHibernation())
|
|
break;
|
|
|
|
if (cdataEndMatch) {
|
|
this.state = DATA_STATE;
|
|
break;
|
|
}
|
|
|
|
this._emitCodePoint(cp);
|
|
|
|
this._hibernationSnapshot();
|
|
cp = this._consume();
|
|
|
|
if (this._ensureHibernation())
|
|
break;
|
|
}
|
|
}
|
|
};
|