20222670105/node_modules/htmlparser2/lib/Tokenizer.js

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.QuoteType = void 0;
var decode_js_1 = require("entities/lib/decode.js");
var CharCodes;
(function (CharCodes) {
    CharCodes[CharCodes["Tab"] = 9] = "Tab";
    CharCodes[CharCodes["NewLine"] = 10] = "NewLine";
    CharCodes[CharCodes["FormFeed"] = 12] = "FormFeed";
    CharCodes[CharCodes["CarriageReturn"] = 13] = "CarriageReturn";
    CharCodes[CharCodes["Space"] = 32] = "Space";
    CharCodes[CharCodes["ExclamationMark"] = 33] = "ExclamationMark";
    CharCodes[CharCodes["Number"] = 35] = "Number";
    CharCodes[CharCodes["Amp"] = 38] = "Amp";
    CharCodes[CharCodes["SingleQuote"] = 39] = "SingleQuote";
    CharCodes[CharCodes["DoubleQuote"] = 34] = "DoubleQuote";
    CharCodes[CharCodes["Dash"] = 45] = "Dash";
    CharCodes[CharCodes["Slash"] = 47] = "Slash";
    CharCodes[CharCodes["Zero"] = 48] = "Zero";
    CharCodes[CharCodes["Nine"] = 57] = "Nine";
    CharCodes[CharCodes["Semi"] = 59] = "Semi";
    CharCodes[CharCodes["Lt"] = 60] = "Lt";
    CharCodes[CharCodes["Eq"] = 61] = "Eq";
    CharCodes[CharCodes["Gt"] = 62] = "Gt";
    CharCodes[CharCodes["Questionmark"] = 63] = "Questionmark";
    CharCodes[CharCodes["UpperA"] = 65] = "UpperA";
    CharCodes[CharCodes["LowerA"] = 97] = "LowerA";
    CharCodes[CharCodes["UpperF"] = 70] = "UpperF";
    CharCodes[CharCodes["LowerF"] = 102] = "LowerF";
    CharCodes[CharCodes["UpperZ"] = 90] = "UpperZ";
    CharCodes[CharCodes["LowerZ"] = 122] = "LowerZ";
    CharCodes[CharCodes["LowerX"] = 120] = "LowerX";
    CharCodes[CharCodes["OpeningSquareBracket"] = 91] = "OpeningSquareBracket";
})(CharCodes || (CharCodes = {}));
/** All the states the tokenizer can be in. */
var State;
(function (State) {
    State[State["Text"] = 1] = "Text";
    State[State["BeforeTagName"] = 2] = "BeforeTagName";
    State[State["InTagName"] = 3] = "InTagName";
    State[State["InSelfClosingTag"] = 4] = "InSelfClosingTag";
    State[State["BeforeClosingTagName"] = 5] = "BeforeClosingTagName";
    State[State["InClosingTagName"] = 6] = "InClosingTagName";
    State[State["AfterClosingTagName"] = 7] = "AfterClosingTagName";
    // Attributes
    State[State["BeforeAttributeName"] = 8] = "BeforeAttributeName";
    State[State["InAttributeName"] = 9] = "InAttributeName";
    State[State["AfterAttributeName"] = 10] = "AfterAttributeName";
    State[State["BeforeAttributeValue"] = 11] = "BeforeAttributeValue";
    State[State["InAttributeValueDq"] = 12] = "InAttributeValueDq";
    State[State["InAttributeValueSq"] = 13] = "InAttributeValueSq";
    State[State["InAttributeValueNq"] = 14] = "InAttributeValueNq";
    // Declarations
    State[State["BeforeDeclaration"] = 15] = "BeforeDeclaration";
    State[State["InDeclaration"] = 16] = "InDeclaration";
    // Processing instructions
    State[State["InProcessingInstruction"] = 17] = "InProcessingInstruction";
    // Comments & CDATA
    State[State["BeforeComment"] = 18] = "BeforeComment";
    State[State["CDATASequence"] = 19] = "CDATASequence";
    State[State["InSpecialComment"] = 20] = "InSpecialComment";
    State[State["InCommentLike"] = 21] = "InCommentLike";
    // Special tags
    State[State["BeforeSpecialS"] = 22] = "BeforeSpecialS";
    State[State["SpecialStartSequence"] = 23] = "SpecialStartSequence";
    State[State["InSpecialTag"] = 24] = "InSpecialTag";
    State[State["BeforeEntity"] = 25] = "BeforeEntity";
    State[State["BeforeNumericEntity"] = 26] = "BeforeNumericEntity";
    State[State["InNamedEntity"] = 27] = "InNamedEntity";
    State[State["InNumericEntity"] = 28] = "InNumericEntity";
    State[State["InHexEntity"] = 29] = "InHexEntity";
})(State || (State = {}));
function isWhitespace(c) {
    return (c === CharCodes.Space ||
        c === CharCodes.NewLine ||
        c === CharCodes.Tab ||
        c === CharCodes.FormFeed ||
        c === CharCodes.CarriageReturn);
}
function isEndOfTagSection(c) {
    return c === CharCodes.Slash || c === CharCodes.Gt || isWhitespace(c);
}
function isNumber(c) {
    return c >= CharCodes.Zero && c <= CharCodes.Nine;
}
function isASCIIAlpha(c) {
    return ((c >= CharCodes.LowerA && c <= CharCodes.LowerZ) ||
        (c >= CharCodes.UpperA && c <= CharCodes.UpperZ));
}
function isHexDigit(c) {
    return ((c >= CharCodes.UpperA && c <= CharCodes.UpperF) ||
        (c >= CharCodes.LowerA && c <= CharCodes.LowerF));
}
var QuoteType;
(function (QuoteType) {
    QuoteType[QuoteType["NoValue"] = 0] = "NoValue";
    QuoteType[QuoteType["Unquoted"] = 1] = "Unquoted";
    QuoteType[QuoteType["Single"] = 2] = "Single";
    QuoteType[QuoteType["Double"] = 3] = "Double";
})(QuoteType = exports.QuoteType || (exports.QuoteType = {}));
/**
 * Sequences used to match longer strings.
 *
 * We don't have `Script`, `Style`, or `Title` here. Instead, we re-use the *End
 * sequences with an increased offset.
 */
var Sequences = {
    Cdata: new Uint8Array([0x43, 0x44, 0x41, 0x54, 0x41, 0x5b]),
    CdataEnd: new Uint8Array([0x5d, 0x5d, 0x3e]),
    CommentEnd: new Uint8Array([0x2d, 0x2d, 0x3e]),
    ScriptEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x63, 0x72, 0x69, 0x70, 0x74]),
    StyleEnd: new Uint8Array([0x3c, 0x2f, 0x73, 0x74, 0x79, 0x6c, 0x65]),
    TitleEnd: new Uint8Array([0x3c, 0x2f, 0x74, 0x69, 0x74, 0x6c, 0x65]), // `</title`
};
var Tokenizer = /** @class */ (function () {
    function Tokenizer(_a, cbs) {
        var _b = _a.xmlMode, xmlMode = _b === void 0 ? false : _b, _c = _a.decodeEntities, decodeEntities = _c === void 0 ? true : _c;
        this.cbs = cbs;
        /** The current state the tokenizer is in. */
        this.state = State.Text;
        /** The read buffer. */
        this.buffer = "";
        /** The beginning of the section that is currently being read. */
        this.sectionStart = 0;
        /** The index within the buffer that we are currently looking at. */
        this.index = 0;
        /** Some behavior, eg. when decoding entities, is done while we are in another state. This keeps track of the other state type. */
        this.baseState = State.Text;
        /** For special parsing behavior inside of script and style tags. */
        this.isSpecial = false;
        /** Indicates whether the tokenizer has been paused. */
        this.running = true;
        /** The offset of the current buffer. */
        this.offset = 0;
        this.currentSequence = undefined;
        this.sequenceIndex = 0;
        this.trieIndex = 0;
        this.trieCurrent = 0;
        /** For named entities, the index of the value. For numeric entities, the code point. */
        this.entityResult = 0;
        this.entityExcess = 0;
        this.xmlMode = xmlMode;
        this.decodeEntities = decodeEntities;
        this.entityTrie = xmlMode ? decode_js_1.xmlDecodeTree : decode_js_1.htmlDecodeTree;
    }
    Tokenizer.prototype.reset = function () {
        this.state = State.Text;
        this.buffer = "";
        this.sectionStart = 0;
        this.index = 0;
        this.baseState = State.Text;
        this.currentSequence = undefined;
        this.running = true;
        this.offset = 0;
    };
    Tokenizer.prototype.write = function (chunk) {
        this.offset += this.buffer.length;
        this.buffer = chunk;
        this.parse();
    };
    Tokenizer.prototype.end = function () {
        if (this.running)
            this.finish();
    };
    Tokenizer.prototype.pause = function () {
        this.running = false;
    };
    Tokenizer.prototype.resume = function () {
        this.running = true;
        if (this.index < this.buffer.length + this.offset) {
            this.parse();
        }
    };
    /**
     * The current index within all of the written data.
     */
    Tokenizer.prototype.getIndex = function () {
        return this.index;
    };
    /**
     * The start of the current section.
     */
    Tokenizer.prototype.getSectionStart = function () {
        return this.sectionStart;
    };
    Tokenizer.prototype.stateText = function (c) {
        if (c === CharCodes.Lt ||
            (!this.decodeEntities && this.fastForwardTo(CharCodes.Lt))) {
            if (this.index > this.sectionStart) {
                this.cbs.ontext(this.sectionStart, this.index);
            }
            this.state = State.BeforeTagName;
            this.sectionStart = this.index;
        }
        else if (this.decodeEntities && c === CharCodes.Amp) {
            this.state = State.BeforeEntity;
        }
    };
    Tokenizer.prototype.stateSpecialStartSequence = function (c) {
        var isEnd = this.sequenceIndex === this.currentSequence.length;
        var isMatch = isEnd
            ? // If we are at the end of the sequence, make sure the tag name has ended
                isEndOfTagSection(c)
            : // Otherwise, do a case-insensitive comparison
                (c | 0x20) === this.currentSequence[this.sequenceIndex];
        if (!isMatch) {
            this.isSpecial = false;
        }
        else if (!isEnd) {
            this.sequenceIndex++;
            return;
        }
        this.sequenceIndex = 0;
        this.state = State.InTagName;
        this.stateInTagName(c);
    };
    /** Look for an end tag. For <title> tags, also decode entities. */
    Tokenizer.prototype.stateInSpecialTag = function (c) {
        if (this.sequenceIndex === this.currentSequence.length) {
            if (c === CharCodes.Gt || isWhitespace(c)) {
                var endOfText = this.index - this.currentSequence.length;
                if (this.sectionStart < endOfText) {
                    // Spoof the index so that reported locations match up.
                    var actualIndex = this.index;
                    this.index = endOfText;
                    this.cbs.ontext(this.sectionStart, endOfText);
                    this.index = actualIndex;
                }
                this.isSpecial = false;
                this.sectionStart = endOfText + 2; // Skip over the `</`
                this.stateInClosingTagName(c);
                return; // We are done; skip the rest of the function.
            }
            this.sequenceIndex = 0;
        }
        if ((c | 0x20) === this.currentSequence[this.sequenceIndex]) {
            this.sequenceIndex += 1;
        }
        else if (this.sequenceIndex === 0) {
            if (this.currentSequence === Sequences.TitleEnd) {
                // We have to parse entities in <title> tags.
                if (this.decodeEntities && c === CharCodes.Amp) {
                    this.state = State.BeforeEntity;
                }
            }
            else if (this.fastForwardTo(CharCodes.Lt)) {
                // Outside of <title> tags, we can fast-forward.
                this.sequenceIndex = 1;
            }
        }
        else {
            // If we see a `<`, set the sequence index to 1; useful for eg. `<</script>`.
            this.sequenceIndex = Number(c === CharCodes.Lt);
        }
    };
    Tokenizer.prototype.stateCDATASequence = function (c) {
        if (c === Sequences.Cdata[this.sequenceIndex]) {
            if (++this.sequenceIndex === Sequences.Cdata.length) {
                this.state = State.InCommentLike;
                this.currentSequence = Sequences.CdataEnd;
                this.sequenceIndex = 0;
                this.sectionStart = this.index + 1;
            }
        }
        else {
            this.sequenceIndex = 0;
            this.state = State.InDeclaration;
            this.stateInDeclaration(c); // Reconsume the character
        }
    };
    /**
     * When we wait for one specific character, we can speed things up
     * by skipping through the buffer until we find it.
     *
     * @returns Whether the character was found.
     */
    Tokenizer.prototype.fastForwardTo = function (c) {
        while (++this.index < this.buffer.length + this.offset) {
            if (this.buffer.charCodeAt(this.index - this.offset) === c) {
                return true;
            }
        }
        /*
         * We increment the index at the end of the `parse` loop,
         * so set it to `buffer.length - 1` here.
         *
         * TODO: Refactor `parse` to increment index before calling states.
         */
        this.index = this.buffer.length + this.offset - 1;
        return false;
    };
    /**
     * Comments and CDATA end with `-->` and `]]>`.
     *
     * Their common qualities are:
     * - Their end sequences have a distinct character they start with.
     * - That character is then repeated, so we have to check multiple repeats.
     * - All characters but the start character of the sequence can be skipped.
     */
    Tokenizer.prototype.stateInCommentLike = function (c) {
        if (c === this.currentSequence[this.sequenceIndex]) {
            if (++this.sequenceIndex === this.currentSequence.length) {
                if (this.currentSequence === Sequences.CdataEnd) {
                    this.cbs.oncdata(this.sectionStart, this.index, 2);
                }
                else {
                    this.cbs.oncomment(this.sectionStart, this.index, 2);
                }
                this.sequenceIndex = 0;
                this.sectionStart = this.index + 1;
                this.state = State.Text;
            }
        }
        else if (this.sequenceIndex === 0) {
            // Fast-forward to the first character of the sequence
            if (this.fastForwardTo(this.currentSequence[0])) {
                this.sequenceIndex = 1;
            }
        }
        else if (c !== this.currentSequence[this.sequenceIndex - 1]) {
            // Allow long sequences, eg. --->, ]]]>
            this.sequenceIndex = 0;
        }
    };
    /**
     * HTML only allows ASCII alpha characters (a-z and A-Z) at the beginning of a tag name.
     *
     * XML allows a lot more characters here (@see https://www.w3.org/TR/REC-xml/#NT-NameStartChar).
     * We allow anything that wouldn't end the tag.
     */
    Tokenizer.prototype.isTagStartChar = function (c) {
        return this.xmlMode ? !isEndOfTagSection(c) : isASCIIAlpha(c);
    };
    Tokenizer.prototype.startSpecial = function (sequence, offset) {
        this.isSpecial = true;
        this.currentSequence = sequence;
        this.sequenceIndex = offset;
        this.state = State.SpecialStartSequence;
    };
    Tokenizer.prototype.stateBeforeTagName = function (c) {
        if (c === CharCodes.ExclamationMark) {
            this.state = State.BeforeDeclaration;
            this.sectionStart = this.index + 1;
        }
        else if (c === CharCodes.Questionmark) {
            this.state = State.InProcessingInstruction;
            this.sectionStart = this.index + 1;
        }
        else if (this.isTagStartChar(c)) {
            var lower = c | 0x20;
            this.sectionStart = this.index;
            if (!this.xmlM