Grammalecte  Check-in [85d2c18b0e]

        this._zElidedPrefix = new RegExp("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i");
        this._zCompoundWord = new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$", "i");
        this._zTag = new RegExp("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*Ṽ][^:;/]*", "g");

    }

    getInfoForToken(oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a list [type, token_string, values]
        let m = null;
        try {
            switch (oToken.sType) {
                case 'SEPARATOR':
                    return {

            }
        } catch (e) {
            helpers.logerror(e);
        }
        return null;
    }

    _formatTags(sTags) {
        let sRes = "";
        sTags = sTags.replace(/V([0-3][ea]?)[itpqnmr_eaxz]+/, "V$1");
        let m;
        while ((m = this._zTag.exec(sTags)) !== null) {
            sRes += _dTAGS.get(m[0]);
            if (sRes.length > 100) {
                break;
            }
        }
        if (sRes.startsWith(" verbe") && !sRes.endsWith("infinitif")) {
            sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]";
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            helpers.echo(sRes);
            return sRes;
        }
        return sRes.gl_trimRight(",");
    }

    _formatSuffix(s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));
        }
        if (!s.includes("-")) {
            return _dAD.get(s.replace("’", "'"));
        }
        if (s.endsWith("ous")) {
            s += '2';
        }
        let nPos = s.indexOf("-");
        return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos + 1));
    }

    getListOfTokens(sText, bInfo = true) {
        let aElem = [];
        sText = sText.replace("'", "’").trim();
        if (sText !== "") {
            let aRes = null;
            for (let oToken of this.oTokenizer.genTokens(sText)) {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else if (oToken.sType !== "SPACE") {
                    aElem.push(oToken);
                }
            }
        }
        return aElem;
    }

    elpfxToword(sELPFX){
        return sELPFX.replace('’', 'e').toLowerCase();
    }

    getListOfTokensReduc(sText, bInfo = true) {
        let lstToken = this.getListOfTokens(sText, false);
        //console.log(lstToken);
        //console.log(this.oLocution);

        let id = 0;
        let aElem = [];
        let aRes = null;
        let isType = {'WORD':1,'ELPFX':1};
        do {
            let oToken = lstToken[id]
            let aLocution = this.oLocution[this.elpfxToword(oToken.sValue)];
            //console.log('Start cherche', oToken.sValue, aLocution);
            let stop = false;
            let start = id + 1;
            let lastTokenWord = '';
            let ok = false;


            let oLst = [];
            oLst.push(oToken);
            while (!stop && typeof aLocution !== "undefined") {
                if (start > lstToken.length){
                    break;
                }
                let typeToken = '';
                let nextToken = lstToken[start];
                //console.log(start, nextToken, aLocution);

                if ( typeof nextToken !== "undefined" ) {
                    aLocution = aLocution[this.elpfxToword(nextToken.sValue)];
                    typeToken = nextToken.sType;
                } else {
                    aLocution = "undefined";
                }

                if ( typeToken in isType && typeof aLocution !== "undefined") {
                    lastTokenWord = Object.keys(aLocution)[0];
                    start++;
                    oLst.push(nextToken);
                    //console.log( nextToken.sValue );
                } else if ( !(typeToken in isType) || typeof aLocution == "undefined") {
                    stop = true;
                    if ( lastTokenWord.substring(0, 1) == ':' ) {
                        ok = true;
                    }
                }
            };

            if ( ok ){
                let word = '';
                for (let oToken of oLst) {
                    word += oToken.sValue+' ';
                    //console.log('***',word);
                }
                id = id + oLst.length-1;
                let tmpToken = {
                    'nEnd':oLst[oLst.length-1].nEnd,
                    'nStart':oLst[0].nStart,
                    'sType':"LOC",
                    'sValue':word.replace('’ ','’').trim()
                };
                if (bInfo) {
                    let formatedTag = [];
                    for (let oToFormat of lastTokenWord.split('|') ){
                        formatedTag.push( this._formatTags(oToFormat).replace(/(\(él.\))/g,'').trim() );
                    }
                    aElem.push({
                        sType: tmpToken.sType,
                        sValue: tmpToken.sValue,
                        aLabel: formatedTag
                    });
                } else {
                    aElem.push(tmpToken);
                }
            } else {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else {
                    aElem.push(oToken);
                }
            }
            id++;
        } while (id < lstToken.length);
        return aElem;
    }
}


if (typeof (exports) !== 'undefined') {
    exports.Lexicographe = Lexicographe;
}