Grammalecte  Diff

    },

    //// Parsing

    parse: function (sText, sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false) {
        let oText = new TextParser(sText);
        return oText.parse(sCountry, bDebug, dOptions, bContext);
    },

    _zEndOfSentence: new RegExp ('([.?!:;…][   .?!…»«“”"‘’)–—]+(?=[A-ZÉÈÎÔ])|.$)', "g"),
    _zBeginOfParagraph: new RegExp ("^[-  –—.,;?!…]*", "ig"),
    _zEndOfParagraph: new RegExp ("[-  .,;?!…–—]*$", "ig"),

    getSentenceBoundaries: function* (sText) {
        let mBeginOfSentence = this._zBeginOfParagraph.exec(sText);
        let iStart = this._zBeginOfParagraph.lastIndex;
        let m;
        while ((m = this._zEndOfSentence.exec(sText)) !== null) {
            yield [iStart, this._zEndOfSentence.lastIndex];
            iStart = this._zEndOfSentence.lastIndex;
        }
    }
};


class TextParser {

    constructor (sText) {

            this.sText = this.sText.replace(/‑/g, "-"); // nobreakdash
        }
        if (this.sText.includes("@@")) {
            this.sText = this.sText.replace(/@@+/g, "");
        }

        // parse sentence
        for (let [iStart, iEnd] of gc_engine.getSentenceBoundaries(this.sText)) {
            try {
                this.sSentence = this.sText.slice(iStart, iEnd);
                this.sSentence0 = this.sText0.slice(iStart, iEnd);
                this.nOffsetWithinParagraph = iStart;
                this.lToken = Array.from(_oTokenizer.genTokens(this.sSentence, true));
                this.dTokenPos.clear();
                for (let dToken of this.lToken) {