971 lines
28 KiB
JavaScript
971 lines
28 KiB
JavaScript
|
module.exports = Tokenizer;
|
||
|
|
||
|
var decodeCodePoint = require("entities/lib/decode_codepoint.js");
|
||
|
var entityMap = require("entities/maps/entities.json");
|
||
|
var legacyMap = require("entities/maps/legacy.json");
|
||
|
var xmlMap = require("entities/maps/xml.json");
|
||
|
|
||
|
var i = 0;
|
||
|
|
||
|
var TEXT = i++;
|
||
|
var BEFORE_TAG_NAME = i++; //after <
|
||
|
var IN_TAG_NAME = i++;
|
||
|
var IN_SELF_CLOSING_TAG = i++;
|
||
|
var BEFORE_CLOSING_TAG_NAME = i++;
|
||
|
var IN_CLOSING_TAG_NAME = i++;
|
||
|
var AFTER_CLOSING_TAG_NAME = i++;
|
||
|
|
||
|
//attributes
|
||
|
var BEFORE_ATTRIBUTE_NAME = i++;
|
||
|
var IN_ATTRIBUTE_NAME = i++;
|
||
|
var AFTER_ATTRIBUTE_NAME = i++;
|
||
|
var BEFORE_ATTRIBUTE_VALUE = i++;
|
||
|
var IN_ATTRIBUTE_VALUE_DQ = i++; // "
|
||
|
var IN_ATTRIBUTE_VALUE_SQ = i++; // '
|
||
|
var IN_ATTRIBUTE_VALUE_NQ = i++;
|
||
|
|
||
|
//declarations
|
||
|
var BEFORE_DECLARATION = i++; // !
|
||
|
var IN_DECLARATION = i++;
|
||
|
|
||
|
//processing instructions
|
||
|
var IN_PROCESSING_INSTRUCTION = i++; // ?
|
||
|
|
||
|
//comments
|
||
|
var BEFORE_COMMENT = i++;
|
||
|
var IN_COMMENT = i++;
|
||
|
var AFTER_COMMENT_1 = i++;
|
||
|
var AFTER_COMMENT_2 = i++;
|
||
|
|
||
|
//cdata
|
||
|
var BEFORE_CDATA_1 = i++; // [
|
||
|
var BEFORE_CDATA_2 = i++; // C
|
||
|
var BEFORE_CDATA_3 = i++; // D
|
||
|
var BEFORE_CDATA_4 = i++; // A
|
||
|
var BEFORE_CDATA_5 = i++; // T
|
||
|
var BEFORE_CDATA_6 = i++; // A
|
||
|
var IN_CDATA = i++; // [
|
||
|
var AFTER_CDATA_1 = i++; // ]
|
||
|
var AFTER_CDATA_2 = i++; // ]
|
||
|
|
||
|
//special tags
|
||
|
var BEFORE_SPECIAL = i++; //S
|
||
|
var BEFORE_SPECIAL_END = i++; //S
|
||
|
|
||
|
var BEFORE_SCRIPT_1 = i++; //C
|
||
|
var BEFORE_SCRIPT_2 = i++; //R
|
||
|
var BEFORE_SCRIPT_3 = i++; //I
|
||
|
var BEFORE_SCRIPT_4 = i++; //P
|
||
|
var BEFORE_SCRIPT_5 = i++; //T
|
||
|
var AFTER_SCRIPT_1 = i++; //C
|
||
|
var AFTER_SCRIPT_2 = i++; //R
|
||
|
var AFTER_SCRIPT_3 = i++; //I
|
||
|
var AFTER_SCRIPT_4 = i++; //P
|
||
|
var AFTER_SCRIPT_5 = i++; //T
|
||
|
|
||
|
var BEFORE_STYLE_1 = i++; //T
|
||
|
var BEFORE_STYLE_2 = i++; //Y
|
||
|
var BEFORE_STYLE_3 = i++; //L
|
||
|
var BEFORE_STYLE_4 = i++; //E
|
||
|
var AFTER_STYLE_1 = i++; //T
|
||
|
var AFTER_STYLE_2 = i++; //Y
|
||
|
var AFTER_STYLE_3 = i++; //L
|
||
|
var AFTER_STYLE_4 = i++; //E
|
||
|
|
||
|
var BEFORE_ENTITY = i++; //&
|
||
|
var BEFORE_NUMERIC_ENTITY = i++; //#
|
||
|
var IN_NAMED_ENTITY = i++;
|
||
|
var IN_NUMERIC_ENTITY = i++;
|
||
|
var IN_HEX_ENTITY = i++; //X
|
||
|
|
||
|
var j = 0;
|
||
|
|
||
|
var SPECIAL_NONE = j++;
|
||
|
var SPECIAL_SCRIPT = j++;
|
||
|
var SPECIAL_STYLE = j++;
|
||
|
|
||
|
function whitespace(c) {
|
||
|
return c === " " || c === "\n" || c === "\t" || c === "\f" || c === "\r";
|
||
|
}
|
||
|
|
||
|
function ifElseState(upper, SUCCESS, FAILURE) {
|
||
|
var lower = upper.toLowerCase();
|
||
|
|
||
|
if (upper === lower) {
|
||
|
return function(c) {
|
||
|
if (c === lower) {
|
||
|
this._state = SUCCESS;
|
||
|
} else {
|
||
|
this._state = FAILURE;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
} else {
|
||
|
return function(c) {
|
||
|
if (c === lower || c === upper) {
|
||
|
this._state = SUCCESS;
|
||
|
} else {
|
||
|
this._state = FAILURE;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
}
|
||
|
}
|
||
|
|
||
|
function consumeSpecialNameChar(upper, NEXT_STATE) {
|
||
|
var lower = upper.toLowerCase();
|
||
|
|
||
|
return function(c) {
|
||
|
if (c === lower || c === upper) {
|
||
|
this._state = NEXT_STATE;
|
||
|
} else {
|
||
|
this._state = IN_TAG_NAME;
|
||
|
this._index--; //consume the token again
|
||
|
}
|
||
|
};
|
||
|
}
|
||
|
|
||
|
function Tokenizer(options, cbs) {
|
||
|
this._state = TEXT;
|
||
|
this._buffer = "";
|
||
|
this._sectionStart = 0;
|
||
|
this._index = 0;
|
||
|
this._bufferOffset = 0; //chars removed from _buffer
|
||
|
this._baseState = TEXT;
|
||
|
this._special = SPECIAL_NONE;
|
||
|
this._cbs = cbs;
|
||
|
this._running = true;
|
||
|
this._ended = false;
|
||
|
this._xmlMode = !!(options && options.xmlMode);
|
||
|
this._decodeEntities = !!(options && options.decodeEntities);
|
||
|
}
|
||
|
|
||
|
Tokenizer.prototype._stateText = function(c) {
|
||
|
if (c === "<") {
|
||
|
if (this._index > this._sectionStart) {
|
||
|
this._cbs.ontext(this._getSection());
|
||
|
}
|
||
|
this._state = BEFORE_TAG_NAME;
|
||
|
this._sectionStart = this._index;
|
||
|
} else if (
|
||
|
this._decodeEntities &&
|
||
|
this._special === SPECIAL_NONE &&
|
||
|
c === "&"
|
||
|
) {
|
||
|
if (this._index > this._sectionStart) {
|
||
|
this._cbs.ontext(this._getSection());
|
||
|
}
|
||
|
this._baseState = TEXT;
|
||
|
this._state = BEFORE_ENTITY;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeTagName = function(c) {
|
||
|
if (c === "/") {
|
||
|
this._state = BEFORE_CLOSING_TAG_NAME;
|
||
|
} else if (c === "<") {
|
||
|
this._cbs.ontext(this._getSection());
|
||
|
this._sectionStart = this._index;
|
||
|
} else if (c === ">" || this._special !== SPECIAL_NONE || whitespace(c)) {
|
||
|
this._state = TEXT;
|
||
|
} else if (c === "!") {
|
||
|
this._state = BEFORE_DECLARATION;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else if (c === "?") {
|
||
|
this._state = IN_PROCESSING_INSTRUCTION;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else {
|
||
|
this._state =
|
||
|
!this._xmlMode && (c === "s" || c === "S")
|
||
|
? BEFORE_SPECIAL
|
||
|
: IN_TAG_NAME;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInTagName = function(c) {
|
||
|
if (c === "/" || c === ">" || whitespace(c)) {
|
||
|
this._emitToken("onopentagname");
|
||
|
this._state = BEFORE_ATTRIBUTE_NAME;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeCloseingTagName = function(c) {
|
||
|
if (whitespace(c));
|
||
|
else if (c === ">") {
|
||
|
this._state = TEXT;
|
||
|
} else if (this._special !== SPECIAL_NONE) {
|
||
|
if (c === "s" || c === "S") {
|
||
|
this._state = BEFORE_SPECIAL_END;
|
||
|
} else {
|
||
|
this._state = TEXT;
|
||
|
this._index--;
|
||
|
}
|
||
|
} else {
|
||
|
this._state = IN_CLOSING_TAG_NAME;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInCloseingTagName = function(c) {
|
||
|
if (c === ">" || whitespace(c)) {
|
||
|
this._emitToken("onclosetag");
|
||
|
this._state = AFTER_CLOSING_TAG_NAME;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterCloseingTagName = function(c) {
|
||
|
//skip everything until ">"
|
||
|
if (c === ">") {
|
||
|
this._state = TEXT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeAttributeName = function(c) {
|
||
|
if (c === ">") {
|
||
|
this._cbs.onopentagend();
|
||
|
this._state = TEXT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else if (c === "/") {
|
||
|
this._state = IN_SELF_CLOSING_TAG;
|
||
|
} else if (!whitespace(c)) {
|
||
|
this._state = IN_ATTRIBUTE_NAME;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInSelfClosingTag = function(c) {
|
||
|
if (c === ">") {
|
||
|
this._cbs.onselfclosingtag();
|
||
|
this._state = TEXT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else if (!whitespace(c)) {
|
||
|
this._state = BEFORE_ATTRIBUTE_NAME;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInAttributeName = function(c) {
|
||
|
if (c === "=" || c === "/" || c === ">" || whitespace(c)) {
|
||
|
this._cbs.onattribname(this._getSection());
|
||
|
this._sectionStart = -1;
|
||
|
this._state = AFTER_ATTRIBUTE_NAME;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterAttributeName = function(c) {
|
||
|
if (c === "=") {
|
||
|
this._state = BEFORE_ATTRIBUTE_VALUE;
|
||
|
} else if (c === "/" || c === ">") {
|
||
|
this._cbs.onattribend();
|
||
|
this._state = BEFORE_ATTRIBUTE_NAME;
|
||
|
this._index--;
|
||
|
} else if (!whitespace(c)) {
|
||
|
this._cbs.onattribend();
|
||
|
this._state = IN_ATTRIBUTE_NAME;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeAttributeValue = function(c) {
|
||
|
if (c === '"') {
|
||
|
this._state = IN_ATTRIBUTE_VALUE_DQ;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else if (c === "'") {
|
||
|
this._state = IN_ATTRIBUTE_VALUE_SQ;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else if (!whitespace(c)) {
|
||
|
this._state = IN_ATTRIBUTE_VALUE_NQ;
|
||
|
this._sectionStart = this._index;
|
||
|
this._index--; //reconsume token
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInAttributeValueDoubleQuotes = function(c) {
|
||
|
if (c === '"') {
|
||
|
this._emitToken("onattribdata");
|
||
|
this._cbs.onattribend();
|
||
|
this._state = BEFORE_ATTRIBUTE_NAME;
|
||
|
} else if (this._decodeEntities && c === "&") {
|
||
|
this._emitToken("onattribdata");
|
||
|
this._baseState = this._state;
|
||
|
this._state = BEFORE_ENTITY;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInAttributeValueSingleQuotes = function(c) {
|
||
|
if (c === "'") {
|
||
|
this._emitToken("onattribdata");
|
||
|
this._cbs.onattribend();
|
||
|
this._state = BEFORE_ATTRIBUTE_NAME;
|
||
|
} else if (this._decodeEntities && c === "&") {
|
||
|
this._emitToken("onattribdata");
|
||
|
this._baseState = this._state;
|
||
|
this._state = BEFORE_ENTITY;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInAttributeValueNoQuotes = function(c) {
|
||
|
if (whitespace(c) || c === ">") {
|
||
|
this._emitToken("onattribdata");
|
||
|
this._cbs.onattribend();
|
||
|
this._state = BEFORE_ATTRIBUTE_NAME;
|
||
|
this._index--;
|
||
|
} else if (this._decodeEntities && c === "&") {
|
||
|
this._emitToken("onattribdata");
|
||
|
this._baseState = this._state;
|
||
|
this._state = BEFORE_ENTITY;
|
||
|
this._sectionStart = this._index;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeDeclaration = function(c) {
|
||
|
this._state =
|
||
|
c === "["
|
||
|
? BEFORE_CDATA_1
|
||
|
: c === "-"
|
||
|
? BEFORE_COMMENT
|
||
|
: IN_DECLARATION;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInDeclaration = function(c) {
|
||
|
if (c === ">") {
|
||
|
this._cbs.ondeclaration(this._getSection());
|
||
|
this._state = TEXT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInProcessingInstruction = function(c) {
|
||
|
if (c === ">") {
|
||
|
this._cbs.onprocessinginstruction(this._getSection());
|
||
|
this._state = TEXT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeComment = function(c) {
|
||
|
if (c === "-") {
|
||
|
this._state = IN_COMMENT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else {
|
||
|
this._state = IN_DECLARATION;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInComment = function(c) {
|
||
|
if (c === "-") this._state = AFTER_COMMENT_1;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterComment1 = function(c) {
|
||
|
if (c === "-") {
|
||
|
this._state = AFTER_COMMENT_2;
|
||
|
} else {
|
||
|
this._state = IN_COMMENT;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterComment2 = function(c) {
|
||
|
if (c === ">") {
|
||
|
//remove 2 trailing chars
|
||
|
this._cbs.oncomment(
|
||
|
this._buffer.substring(this._sectionStart, this._index - 2)
|
||
|
);
|
||
|
this._state = TEXT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else if (c !== "-") {
|
||
|
this._state = IN_COMMENT;
|
||
|
}
|
||
|
// else: stay in AFTER_COMMENT_2 (`--->`)
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeCdata1 = ifElseState(
|
||
|
"C",
|
||
|
BEFORE_CDATA_2,
|
||
|
IN_DECLARATION
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeCdata2 = ifElseState(
|
||
|
"D",
|
||
|
BEFORE_CDATA_3,
|
||
|
IN_DECLARATION
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeCdata3 = ifElseState(
|
||
|
"A",
|
||
|
BEFORE_CDATA_4,
|
||
|
IN_DECLARATION
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeCdata4 = ifElseState(
|
||
|
"T",
|
||
|
BEFORE_CDATA_5,
|
||
|
IN_DECLARATION
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeCdata5 = ifElseState(
|
||
|
"A",
|
||
|
BEFORE_CDATA_6,
|
||
|
IN_DECLARATION
|
||
|
);
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeCdata6 = function(c) {
|
||
|
if (c === "[") {
|
||
|
this._state = IN_CDATA;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else {
|
||
|
this._state = IN_DECLARATION;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInCdata = function(c) {
|
||
|
if (c === "]") this._state = AFTER_CDATA_1;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterCdata1 = function(c) {
|
||
|
if (c === "]") this._state = AFTER_CDATA_2;
|
||
|
else this._state = IN_CDATA;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterCdata2 = function(c) {
|
||
|
if (c === ">") {
|
||
|
//remove 2 trailing chars
|
||
|
this._cbs.oncdata(
|
||
|
this._buffer.substring(this._sectionStart, this._index - 2)
|
||
|
);
|
||
|
this._state = TEXT;
|
||
|
this._sectionStart = this._index + 1;
|
||
|
} else if (c !== "]") {
|
||
|
this._state = IN_CDATA;
|
||
|
}
|
||
|
//else: stay in AFTER_CDATA_2 (`]]]>`)
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeSpecial = function(c) {
|
||
|
if (c === "c" || c === "C") {
|
||
|
this._state = BEFORE_SCRIPT_1;
|
||
|
} else if (c === "t" || c === "T") {
|
||
|
this._state = BEFORE_STYLE_1;
|
||
|
} else {
|
||
|
this._state = IN_TAG_NAME;
|
||
|
this._index--; //consume the token again
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeSpecialEnd = function(c) {
|
||
|
if (this._special === SPECIAL_SCRIPT && (c === "c" || c === "C")) {
|
||
|
this._state = AFTER_SCRIPT_1;
|
||
|
} else if (this._special === SPECIAL_STYLE && (c === "t" || c === "T")) {
|
||
|
this._state = AFTER_STYLE_1;
|
||
|
} else this._state = TEXT;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeScript1 = consumeSpecialNameChar(
|
||
|
"R",
|
||
|
BEFORE_SCRIPT_2
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeScript2 = consumeSpecialNameChar(
|
||
|
"I",
|
||
|
BEFORE_SCRIPT_3
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeScript3 = consumeSpecialNameChar(
|
||
|
"P",
|
||
|
BEFORE_SCRIPT_4
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeScript4 = consumeSpecialNameChar(
|
||
|
"T",
|
||
|
BEFORE_SCRIPT_5
|
||
|
);
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeScript5 = function(c) {
|
||
|
if (c === "/" || c === ">" || whitespace(c)) {
|
||
|
this._special = SPECIAL_SCRIPT;
|
||
|
}
|
||
|
this._state = IN_TAG_NAME;
|
||
|
this._index--; //consume the token again
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterScript1 = ifElseState("R", AFTER_SCRIPT_2, TEXT);
|
||
|
Tokenizer.prototype._stateAfterScript2 = ifElseState("I", AFTER_SCRIPT_3, TEXT);
|
||
|
Tokenizer.prototype._stateAfterScript3 = ifElseState("P", AFTER_SCRIPT_4, TEXT);
|
||
|
Tokenizer.prototype._stateAfterScript4 = ifElseState("T", AFTER_SCRIPT_5, TEXT);
|
||
|
|
||
|
Tokenizer.prototype._stateAfterScript5 = function(c) {
|
||
|
if (c === ">" || whitespace(c)) {
|
||
|
this._special = SPECIAL_NONE;
|
||
|
this._state = IN_CLOSING_TAG_NAME;
|
||
|
this._sectionStart = this._index - 6;
|
||
|
this._index--; //reconsume the token
|
||
|
} else this._state = TEXT;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeStyle1 = consumeSpecialNameChar(
|
||
|
"Y",
|
||
|
BEFORE_STYLE_2
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeStyle2 = consumeSpecialNameChar(
|
||
|
"L",
|
||
|
BEFORE_STYLE_3
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeStyle3 = consumeSpecialNameChar(
|
||
|
"E",
|
||
|
BEFORE_STYLE_4
|
||
|
);
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeStyle4 = function(c) {
|
||
|
if (c === "/" || c === ">" || whitespace(c)) {
|
||
|
this._special = SPECIAL_STYLE;
|
||
|
}
|
||
|
this._state = IN_TAG_NAME;
|
||
|
this._index--; //consume the token again
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateAfterStyle1 = ifElseState("Y", AFTER_STYLE_2, TEXT);
|
||
|
Tokenizer.prototype._stateAfterStyle2 = ifElseState("L", AFTER_STYLE_3, TEXT);
|
||
|
Tokenizer.prototype._stateAfterStyle3 = ifElseState("E", AFTER_STYLE_4, TEXT);
|
||
|
|
||
|
Tokenizer.prototype._stateAfterStyle4 = function(c) {
|
||
|
if (c === ">" || whitespace(c)) {
|
||
|
this._special = SPECIAL_NONE;
|
||
|
this._state = IN_CLOSING_TAG_NAME;
|
||
|
this._sectionStart = this._index - 5;
|
||
|
this._index--; //reconsume the token
|
||
|
} else this._state = TEXT;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateBeforeEntity = ifElseState(
|
||
|
"#",
|
||
|
BEFORE_NUMERIC_ENTITY,
|
||
|
IN_NAMED_ENTITY
|
||
|
);
|
||
|
Tokenizer.prototype._stateBeforeNumericEntity = ifElseState(
|
||
|
"X",
|
||
|
IN_HEX_ENTITY,
|
||
|
IN_NUMERIC_ENTITY
|
||
|
);
|
||
|
|
||
|
//for entities terminated with a semicolon
|
||
|
Tokenizer.prototype._parseNamedEntityStrict = function() {
|
||
|
//offset = 1
|
||
|
if (this._sectionStart + 1 < this._index) {
|
||
|
var entity = this._buffer.substring(
|
||
|
this._sectionStart + 1,
|
||
|
this._index
|
||
|
),
|
||
|
map = this._xmlMode ? xmlMap : entityMap;
|
||
|
|
||
|
if (map.hasOwnProperty(entity)) {
|
||
|
this._emitPartial(map[entity]);
|
||
|
this._sectionStart = this._index + 1;
|
||
|
}
|
||
|
}
|
||
|
};
|
||
|
|
||
|
//parses legacy entities (without trailing semicolon)
|
||
|
Tokenizer.prototype._parseLegacyEntity = function() {
|
||
|
var start = this._sectionStart + 1,
|
||
|
limit = this._index - start;
|
||
|
|
||
|
if (limit > 6) limit = 6; //the max length of legacy entities is 6
|
||
|
|
||
|
while (limit >= 2) {
|
||
|
//the min length of legacy entities is 2
|
||
|
var entity = this._buffer.substr(start, limit);
|
||
|
|
||
|
if (legacyMap.hasOwnProperty(entity)) {
|
||
|
this._emitPartial(legacyMap[entity]);
|
||
|
this._sectionStart += limit + 1;
|
||
|
return;
|
||
|
} else {
|
||
|
limit--;
|
||
|
}
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInNamedEntity = function(c) {
|
||
|
if (c === ";") {
|
||
|
this._parseNamedEntityStrict();
|
||
|
if (this._sectionStart + 1 < this._index && !this._xmlMode) {
|
||
|
this._parseLegacyEntity();
|
||
|
}
|
||
|
this._state = this._baseState;
|
||
|
} else if (
|
||
|
(c < "a" || c > "z") &&
|
||
|
(c < "A" || c > "Z") &&
|
||
|
(c < "0" || c > "9")
|
||
|
) {
|
||
|
if (this._xmlMode);
|
||
|
else if (this._sectionStart + 1 === this._index);
|
||
|
else if (this._baseState !== TEXT) {
|
||
|
if (c !== "=") {
|
||
|
this._parseNamedEntityStrict();
|
||
|
}
|
||
|
} else {
|
||
|
this._parseLegacyEntity();
|
||
|
}
|
||
|
|
||
|
this._state = this._baseState;
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._decodeNumericEntity = function(offset, base) {
|
||
|
var sectionStart = this._sectionStart + offset;
|
||
|
|
||
|
if (sectionStart !== this._index) {
|
||
|
//parse entity
|
||
|
var entity = this._buffer.substring(sectionStart, this._index);
|
||
|
var parsed = parseInt(entity, base);
|
||
|
|
||
|
this._emitPartial(decodeCodePoint(parsed));
|
||
|
this._sectionStart = this._index;
|
||
|
} else {
|
||
|
this._sectionStart--;
|
||
|
}
|
||
|
|
||
|
this._state = this._baseState;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInNumericEntity = function(c) {
|
||
|
if (c === ";") {
|
||
|
this._decodeNumericEntity(2, 10);
|
||
|
this._sectionStart++;
|
||
|
} else if (c < "0" || c > "9") {
|
||
|
if (!this._xmlMode) {
|
||
|
this._decodeNumericEntity(2, 10);
|
||
|
} else {
|
||
|
this._state = this._baseState;
|
||
|
}
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._stateInHexEntity = function(c) {
|
||
|
if (c === ";") {
|
||
|
this._decodeNumericEntity(3, 16);
|
||
|
this._sectionStart++;
|
||
|
} else if (
|
||
|
(c < "a" || c > "f") &&
|
||
|
(c < "A" || c > "F") &&
|
||
|
(c < "0" || c > "9")
|
||
|
) {
|
||
|
if (!this._xmlMode) {
|
||
|
this._decodeNumericEntity(3, 16);
|
||
|
} else {
|
||
|
this._state = this._baseState;
|
||
|
}
|
||
|
this._index--;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._cleanup = function() {
|
||
|
if (this._sectionStart < 0) {
|
||
|
this._buffer = "";
|
||
|
this._bufferOffset += this._index;
|
||
|
this._index = 0;
|
||
|
} else if (this._running) {
|
||
|
if (this._state === TEXT) {
|
||
|
if (this._sectionStart !== this._index) {
|
||
|
this._cbs.ontext(this._buffer.substr(this._sectionStart));
|
||
|
}
|
||
|
this._buffer = "";
|
||
|
this._bufferOffset += this._index;
|
||
|
this._index = 0;
|
||
|
} else if (this._sectionStart === this._index) {
|
||
|
//the section just started
|
||
|
this._buffer = "";
|
||
|
this._bufferOffset += this._index;
|
||
|
this._index = 0;
|
||
|
} else {
|
||
|
//remove everything unnecessary
|
||
|
this._buffer = this._buffer.substr(this._sectionStart);
|
||
|
this._index -= this._sectionStart;
|
||
|
this._bufferOffset += this._sectionStart;
|
||
|
}
|
||
|
|
||
|
this._sectionStart = 0;
|
||
|
}
|
||
|
};
|
||
|
|
||
|
//TODO make events conditional
|
||
|
Tokenizer.prototype.write = function(chunk) {
|
||
|
if (this._ended) this._cbs.onerror(Error(".write() after done!"));
|
||
|
|
||
|
this._buffer += chunk;
|
||
|
this._parse();
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._parse = function() {
|
||
|
while (this._index < this._buffer.length && this._running) {
|
||
|
var c = this._buffer.charAt(this._index);
|
||
|
if (this._state === TEXT) {
|
||
|
this._stateText(c);
|
||
|
} else if (this._state === BEFORE_TAG_NAME) {
|
||
|
this._stateBeforeTagName(c);
|
||
|
} else if (this._state === IN_TAG_NAME) {
|
||
|
this._stateInTagName(c);
|
||
|
} else if (this._state === BEFORE_CLOSING_TAG_NAME) {
|
||
|
this._stateBeforeCloseingTagName(c);
|
||
|
} else if (this._state === IN_CLOSING_TAG_NAME) {
|
||
|
this._stateInCloseingTagName(c);
|
||
|
} else if (this._state === AFTER_CLOSING_TAG_NAME) {
|
||
|
this._stateAfterCloseingTagName(c);
|
||
|
} else if (this._state === IN_SELF_CLOSING_TAG) {
|
||
|
this._stateInSelfClosingTag(c);
|
||
|
} else if (this._state === BEFORE_ATTRIBUTE_NAME) {
|
||
|
|
||
|
/*
|
||
|
* attributes
|
||
|
*/
|
||
|
this._stateBeforeAttributeName(c);
|
||
|
} else if (this._state === IN_ATTRIBUTE_NAME) {
|
||
|
this._stateInAttributeName(c);
|
||
|
} else if (this._state === AFTER_ATTRIBUTE_NAME) {
|
||
|
this._stateAfterAttributeName(c);
|
||
|
} else if (this._state === BEFORE_ATTRIBUTE_VALUE) {
|
||
|
this._stateBeforeAttributeValue(c);
|
||
|
} else if (this._state === IN_ATTRIBUTE_VALUE_DQ) {
|
||
|
this._stateInAttributeValueDoubleQuotes(c);
|
||
|
} else if (this._state === IN_ATTRIBUTE_VALUE_SQ) {
|
||
|
this._stateInAttributeValueSingleQuotes(c);
|
||
|
} else if (this._state === IN_ATTRIBUTE_VALUE_NQ) {
|
||
|
this._stateInAttributeValueNoQuotes(c);
|
||
|
} else if (this._state === BEFORE_DECLARATION) {
|
||
|
|
||
|
/*
|
||
|
* declarations
|
||
|
*/
|
||
|
this._stateBeforeDeclaration(c);
|
||
|
} else if (this._state === IN_DECLARATION) {
|
||
|
this._stateInDeclaration(c);
|
||
|
} else if (this._state === IN_PROCESSING_INSTRUCTION) {
|
||
|
|
||
|
/*
|
||
|
* processing instructions
|
||
|
*/
|
||
|
this._stateInProcessingInstruction(c);
|
||
|
} else if (this._state === BEFORE_COMMENT) {
|
||
|
|
||
|
/*
|
||
|
* comments
|
||
|
*/
|
||
|
this._stateBeforeComment(c);
|
||
|
} else if (this._state === IN_COMMENT) {
|
||
|
this._stateInComment(c);
|
||
|
} else if (this._state === AFTER_COMMENT_1) {
|
||
|
this._stateAfterComment1(c);
|
||
|
} else if (this._state === AFTER_COMMENT_2) {
|
||
|
this._stateAfterComment2(c);
|
||
|
} else if (this._state === BEFORE_CDATA_1) {
|
||
|
|
||
|
/*
|
||
|
* cdata
|
||
|
*/
|
||
|
this._stateBeforeCdata1(c);
|
||
|
} else if (this._state === BEFORE_CDATA_2) {
|
||
|
this._stateBeforeCdata2(c);
|
||
|
} else if (this._state === BEFORE_CDATA_3) {
|
||
|
this._stateBeforeCdata3(c);
|
||
|
} else if (this._state === BEFORE_CDATA_4) {
|
||
|
this._stateBeforeCdata4(c);
|
||
|
} else if (this._state === BEFORE_CDATA_5) {
|
||
|
this._stateBeforeCdata5(c);
|
||
|
} else if (this._state === BEFORE_CDATA_6) {
|
||
|
this._stateBeforeCdata6(c);
|
||
|
} else if (this._state === IN_CDATA) {
|
||
|
this._stateInCdata(c);
|
||
|
} else if (this._state === AFTER_CDATA_1) {
|
||
|
this._stateAfterCdata1(c);
|
||
|
} else if (this._state === AFTER_CDATA_2) {
|
||
|
this._stateAfterCdata2(c);
|
||
|
} else if (this._state === BEFORE_SPECIAL) {
|
||
|
|
||
|
/*
|
||
|
* special tags
|
||
|
*/
|
||
|
this._stateBeforeSpecial(c);
|
||
|
} else if (this._state === BEFORE_SPECIAL_END) {
|
||
|
this._stateBeforeSpecialEnd(c);
|
||
|
} else if (this._state === BEFORE_SCRIPT_1) {
|
||
|
|
||
|
/*
|
||
|
* script
|
||
|
*/
|
||
|
this._stateBeforeScript1(c);
|
||
|
} else if (this._state === BEFORE_SCRIPT_2) {
|
||
|
this._stateBeforeScript2(c);
|
||
|
} else if (this._state === BEFORE_SCRIPT_3) {
|
||
|
this._stateBeforeScript3(c);
|
||
|
} else if (this._state === BEFORE_SCRIPT_4) {
|
||
|
this._stateBeforeScript4(c);
|
||
|
} else if (this._state === BEFORE_SCRIPT_5) {
|
||
|
this._stateBeforeScript5(c);
|
||
|
} else if (this._state === AFTER_SCRIPT_1) {
|
||
|
this._stateAfterScript1(c);
|
||
|
} else if (this._state === AFTER_SCRIPT_2) {
|
||
|
this._stateAfterScript2(c);
|
||
|
} else if (this._state === AFTER_SCRIPT_3) {
|
||
|
this._stateAfterScript3(c);
|
||
|
} else if (this._state === AFTER_SCRIPT_4) {
|
||
|
this._stateAfterScript4(c);
|
||
|
} else if (this._state === AFTER_SCRIPT_5) {
|
||
|
this._stateAfterScript5(c);
|
||
|
} else if (this._state === BEFORE_STYLE_1) {
|
||
|
|
||
|
/*
|
||
|
* style
|
||
|
*/
|
||
|
this._stateBeforeStyle1(c);
|
||
|
} else if (this._state === BEFORE_STYLE_2) {
|
||
|
this._stateBeforeStyle2(c);
|
||
|
} else if (this._state === BEFORE_STYLE_3) {
|
||
|
this._stateBeforeStyle3(c);
|
||
|
} else if (this._state === BEFORE_STYLE_4) {
|
||
|
this._stateBeforeStyle4(c);
|
||
|
} else if (this._state === AFTER_STYLE_1) {
|
||
|
this._stateAfterStyle1(c);
|
||
|
} else if (this._state === AFTER_STYLE_2) {
|
||
|
this._stateAfterStyle2(c);
|
||
|
} else if (this._state === AFTER_STYLE_3) {
|
||
|
this._stateAfterStyle3(c);
|
||
|
} else if (this._state === AFTER_STYLE_4) {
|
||
|
this._stateAfterStyle4(c);
|
||
|
} else if (this._state === BEFORE_ENTITY) {
|
||
|
|
||
|
/*
|
||
|
* entities
|
||
|
*/
|
||
|
this._stateBeforeEntity(c);
|
||
|
} else if (this._state === BEFORE_NUMERIC_ENTITY) {
|
||
|
this._stateBeforeNumericEntity(c);
|
||
|
} else if (this._state === IN_NAMED_ENTITY) {
|
||
|
this._stateInNamedEntity(c);
|
||
|
} else if (this._state === IN_NUMERIC_ENTITY) {
|
||
|
this._stateInNumericEntity(c);
|
||
|
} else if (this._state === IN_HEX_ENTITY) {
|
||
|
this._stateInHexEntity(c);
|
||
|
} else {
|
||
|
this._cbs.onerror(Error("unknown _state"), this._state);
|
||
|
}
|
||
|
|
||
|
this._index++;
|
||
|
}
|
||
|
|
||
|
this._cleanup();
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype.pause = function() {
|
||
|
this._running = false;
|
||
|
};
|
||
|
Tokenizer.prototype.resume = function() {
|
||
|
this._running = true;
|
||
|
|
||
|
if (this._index < this._buffer.length) {
|
||
|
this._parse();
|
||
|
}
|
||
|
if (this._ended) {
|
||
|
this._finish();
|
||
|
}
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype.end = function(chunk) {
|
||
|
if (this._ended) this._cbs.onerror(Error(".end() after done!"));
|
||
|
if (chunk) this.write(chunk);
|
||
|
|
||
|
this._ended = true;
|
||
|
|
||
|
if (this._running) this._finish();
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._finish = function() {
|
||
|
//if there is remaining data, emit it in a reasonable way
|
||
|
if (this._sectionStart < this._index) {
|
||
|
this._handleTrailingData();
|
||
|
}
|
||
|
|
||
|
this._cbs.onend();
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._handleTrailingData = function() {
|
||
|
var data = this._buffer.substr(this._sectionStart);
|
||
|
|
||
|
if (
|
||
|
this._state === IN_CDATA ||
|
||
|
this._state === AFTER_CDATA_1 ||
|
||
|
this._state === AFTER_CDATA_2
|
||
|
) {
|
||
|
this._cbs.oncdata(data);
|
||
|
} else if (
|
||
|
this._state === IN_COMMENT ||
|
||
|
this._state === AFTER_COMMENT_1 ||
|
||
|
this._state === AFTER_COMMENT_2
|
||
|
) {
|
||
|
this._cbs.oncomment(data);
|
||
|
} else if (this._state === IN_NAMED_ENTITY && !this._xmlMode) {
|
||
|
this._parseLegacyEntity();
|
||
|
if (this._sectionStart < this._index) {
|
||
|
this._state = this._baseState;
|
||
|
this._handleTrailingData();
|
||
|
}
|
||
|
} else if (this._state === IN_NUMERIC_ENTITY && !this._xmlMode) {
|
||
|
this._decodeNumericEntity(2, 10);
|
||
|
if (this._sectionStart < this._index) {
|
||
|
this._state = this._baseState;
|
||
|
this._handleTrailingData();
|
||
|
}
|
||
|
} else if (this._state === IN_HEX_ENTITY && !this._xmlMode) {
|
||
|
this._decodeNumericEntity(3, 16);
|
||
|
if (this._sectionStart < this._index) {
|
||
|
this._state = this._baseState;
|
||
|
this._handleTrailingData();
|
||
|
}
|
||
|
} else if (
|
||
|
this._state !== IN_TAG_NAME &&
|
||
|
this._state !== BEFORE_ATTRIBUTE_NAME &&
|
||
|
this._state !== BEFORE_ATTRIBUTE_VALUE &&
|
||
|
this._state !== AFTER_ATTRIBUTE_NAME &&
|
||
|
this._state !== IN_ATTRIBUTE_NAME &&
|
||
|
this._state !== IN_ATTRIBUTE_VALUE_SQ &&
|
||
|
this._state !== IN_ATTRIBUTE_VALUE_DQ &&
|
||
|
this._state !== IN_ATTRIBUTE_VALUE_NQ &&
|
||
|
this._state !== IN_CLOSING_TAG_NAME
|
||
|
) {
|
||
|
this._cbs.ontext(data);
|
||
|
}
|
||
|
//else, ignore remaining data
|
||
|
//TODO add a way to remove current tag
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype.reset = function() {
|
||
|
Tokenizer.call(
|
||
|
this,
|
||
|
{ xmlMode: this._xmlMode, decodeEntities: this._decodeEntities },
|
||
|
this._cbs
|
||
|
);
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype.getAbsoluteIndex = function() {
|
||
|
return this._bufferOffset + this._index;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._getSection = function() {
|
||
|
return this._buffer.substring(this._sectionStart, this._index);
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._emitToken = function(name) {
|
||
|
this._cbs[name](this._getSection());
|
||
|
this._sectionStart = -1;
|
||
|
};
|
||
|
|
||
|
Tokenizer.prototype._emitPartial = function(value) {
|
||
|
if (this._baseState !== TEXT) {
|
||
|
this._cbs.onattribdata(value); //TODO implement the new event
|
||
|
} else {
|
||
|
this._cbs.ontext(value);
|
||
|
}
|
||
|
};
|