Grammalecte  Changes On Branch a6bed5e7d3e340d6

// JavaScript
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}


var text = {
    getParagraph: function* (sText, sSepParagraph = "\n") {
        // generator: returns paragraphs of text
        let iStart = 0;
        let iEnd = 0;
        sText = sText.replace("\r\n", "\n").replace("\r", "\n");
        while ((iEnd = sText.indexOf(sSepParagraph, iStart)) !== -1) {
            yield sText.slice(iStart, iEnd);
            iStart = iEnd + 1;
        }
        yield sText.slice(iStart);
    },

    wrap: function* (sText, nWidth=80) {

        }
        yield sText;
    },

    getReadableError: function (oErr) {
        // Returns an error oErr as a readable error
        try {
            let sResult = "\n* " + oErr['nStart'] + ":" + oErr['nEnd']
                        + "  # " + oErr['sLineId'] + "  # " + oErr['sRuleId'] + ":\n";
            sResult += "  " + oErr["sMessage"];
            if (oErr["aSuggestions"].length > 0) {
                sResult += "\n  > Suggestions : " + oErr["aSuggestions"].join(" | ");
            }
            if (oErr["URL"] !== "") {
                sResult += "\n  > URL: " + oErr["URL"];

                '    "dMasForm": ' +  json.dumps(dMasForm, ensure_ascii=False) + "\n}"
        open(sp+"/modules-js/mfsp_data.json", "w", encoding="utf-8", newline="\n").write(sCode)


def makePhonetTable (sp, bJS=False):
    print("> Correspondances phonétiques ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")

    try:
        oDict = ibdawg.IBDAWG("French.bdic")
    except:
        traceback.print_exc()
        return

    with open(sp+"/data/phonet_simil.txt", 'r', encoding='utf-8') as hSrc:

    with open(sp+"/data/locutions.txt", 'r', encoding='utf-8') as hSrc:
        dLocutions = {}
        for sLine in hSrc.readlines():
            if not sLine.startswith("#") and sLine.strip():
                lElem = sLine.strip().split()
                dCur = dLocutions
                for sWord in lElem:
                    if sWord not in dCur and not sWord.startswith(":"):
                        dCur[sWord] = {}
                    if sWord not in dCur and sWord.startswith(":"):
                        dCur[sWord] = ''
                    dCur = dCur[sWord]

    sCode = "# generated data (do not edit)\n\n" + \
            "dLocutions = " + str(dLocutions) + "\n"
    open(sp+"/modules/locutions_data.py", "w", encoding="utf-8", newline="\n").write(sCode)
    if bJS:
        open(sp+"/modules-js/locutions_data.json", "w", encoding="utf-8", newline="\n").write(json.dumps(dLocutions, ensure_ascii=False))

// Grammalecte - Lexicographe
// License: MPL 2
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";

${string}
${map}


if (typeof (require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}

const _dTAGS = new Map([
    [':G', "[mot grammatical]"],
    [':N', " nom,"],
    [':A', " adjectif,"],
    [':M1', " prénom,"],
    [':M2', " patronyme,"],
    [':MP', " nom propre,"],
    [':W', " adverbe,"],

    [':Oi', " pronom indéfini,"],
    [':On', " pronom indéfini négatif,"],
    [':Ot', " pronom interrogatif,"],
    [':Or', " pronom relatif,"],
    [':Ow', " pronom adverbial,"],
    [':Os', " pronom personnel sujet,"],
    [':Oo', " pronom personnel objet,"],
    [':C', " conjonction,"],

    [':Cc', " conjonction de coordination,"],
    [':Cs', " conjonction de subordination,"],


    [':Ĺ', " locution,"],
    [':Ĉ', " locution conjonctivale (él.),"],
    [':Ĉs', " locution conjonctivale de subordination (él.),"],
    [':Ŵ', " locution adverbiale (él.),"],
    [':Ñ', " locution nominale (él.),"],
    [':Â', " locution adjectivale (él.),"],
    [':Ṽ', " locution verbale (él.),"],
    [':Ŕ', " locution prépositive (él.),"],
    [':Ĵ', " locution interjective (él.),"],

    [':Zp', " préfixe,"],
    [':Zs', " suffixe,"],

    [':V1', " verbe (1ᵉʳ gr.),"],
    [':V2', " verbe (2ᵉ gr.),"],
    [':V3', " verbe (3ᵉ gr.),"],
    [':V0e', " verbe,"],
    [':V0a', " verbe,"],

    [':O1', " 1ʳᵉ pers.,"],
    [':O2', " 2ᵉ pers.,"],
    [':O3', " 3ᵉ pers.,"],

    [':e', " épicène"],
    [':m', " masculin"],
    [':f', " féminin"],
    [':s', " singulier"],
    [':p', " pluriel"],
    [':i', " invariable"],

    ['/C', " {classique}"],
    ['/M', ""],
    ['/R', " {réforme}"],
    ['/A', ""],
    ['/X', ""]
]);

const _dPFX = new Map([
    ['d', "(de), déterminant épicène invariable"],
    ['l', "(le/la), déterminant masculin/féminin singulier"],
    ['j', "(je), pronom personnel sujet, 1ʳᵉ pers., épicène singulier"],
    ['m', "(me), pronom personnel objet, 1ʳᵉ pers., épicène singulier"],
    ['t', "(te), pronom personnel objet, 2ᵉ pers., épicène singulier"],
    ['s', "(se), pronom personnel objet, 3ᵉ pers., épicène singulier/pluriel"],
    ['n', "(ne), adverbe de négation"],
    ['c', "(ce), pronom démonstratif, masculin singulier/pluriel"],
    ['ç', "(ça), pronom démonstratif, masculin singulier"],
    ['qu', "(que), conjonction de subordination"],
    ['lorsqu', "(lorsque), conjonction de subordination"],
    ['quoiqu', "(quoique), conjonction de subordination"],
    ['jusqu', "(jusque), préposition"]
]);

const _dAD = new Map([
    ['je', " pronom personnel sujet, 1ʳᵉ pers. sing."],
    ['tu', " pronom personnel sujet, 2ᵉ pers. sing."],
    ['il', " pronom personnel sujet, 3ᵉ pers. masc. sing."],
    ['on', " pronom personnel sujet, 3ᵉ pers. sing. ou plur."],
    ['elle', " pronom personnel sujet, 3ᵉ pers. fém. sing."],
    ['nous', " pronom personnel sujet/objet, 1ʳᵉ pers. plur."],
    ['vous', " pronom personnel sujet/objet, 2ᵉ pers. plur."],
    ['ils', " pronom personnel sujet, 3ᵉ pers. masc. plur."],
    ['elles', " pronom personnel sujet, 3ᵉ pers. masc. plur."],

    ["là", " particule démonstrative"],
    ["ci", " particule démonstrative"],

    ['le', " COD, masc. sing."],
    ['la', " COD, fém. sing."],
    ['les', " COD, plur."],

    ['moi', " COI (à moi), sing."],
    ['toi', " COI (à toi), sing."],
    ['lui', " COI (à lui ou à elle), sing."],
    ['nous2', " COI (à nous), plur."],
    ['vous2', " COI (à vous), plur."],
    ['leur', " COI (à eux ou à elles), plur."],

    ['y', " pronom adverbial"],
    ["m'y", " (me) pronom personnel objet + (y) pronom adverbial"],
    ["t'y", " (te) pronom personnel objet + (y) pronom adverbial"],
    ["s'y", " (se) pronom personnel objet + (y) pronom adverbial"],

    ['en', " pronom adverbial"],
    ["m'en", " (me) pronom personnel objet + (en) pronom adverbial"],
    ["t'en", " (te) pronom personnel objet + (en) pronom adverbial"],
    ["s'en", " (se) pronom personnel objet + (en) pronom adverbial"]
]);

const _dSeparator = new Map([
    ['.', "point"],
    ['·', "point médian"],
    ['…', "points de suspension"],
    [':', "deux-points"],
    [';', "point-virgule"],
    [',', "virgule"],
    ['?', "point d’interrogation"],

    ['<', "inférieur à"],
    ['>', "supérieur à"],
]);


class Lexicographe {

    constructor(oDict, oTokenizer, oLocution) {
        this.oDict = oDict;
        this.oTokenizer = oTokenizer;
        this.oLocution = JSON.parse(oLocution);

        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*][^:;/]*", "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 {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabel: [_dSeparator.gl_get(oToken.sValue, "caractère indéterminé")]
                    };
                    break;
                case 'NUM':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabel: ["nombre"]
                    };
                    break;
                case 'LINK':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabel: ["hyperlien"]
                    };
                    break;
                case 'ELPFX':
                    let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase();
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabel: [_dPFX.gl_get(sTemp, "préfixe élidé inconnu")]
                    };
                    break;
                case 'FOLDER':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabel: ["dossier"]
                    };
                    break;
                case 'WORD':
                    if (oToken.sValue.gl_count("-") > 4) {
                        return {
                            sType: "COMPLEX",
                            sValue: oToken.sValue,
                            aLabel: ["élément complexe indéterminé"]
                        };
                    } else if (this.oDict.isValidToken(oToken.sValue)) {
                        let lMorph = this.oDict.getMorph(oToken.sValue);
                        let aElem = [];
                        for (let s of lMorph) {
                            if (s.includes(":")) aElem.push(this._formatTags(s));
                        }
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabel: aElem
                        };
                    } else if (m = this._zCompoundWord.exec(oToken.sValue)) {
                        // mots composés
                        let lMorph = this.oDict.getMorph(m[1]);
                        let aElem = [];
                        for (let s of lMorph) {
                            if (s.includes(":")) aElem.push(this._formatTags(s));
                        }
                        aElem.push("-" + m[2] + ": " + this._formatSuffix(m[2].toLowerCase()));
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabel: aElem
                        };
                    } else {
                        return {
                            sType: "UNKNOWN",
                            sValue: oToken.sValue,
                            aLabel: ["inconnu du dictionnaire"]
                        };
                    }
                    break;
            }

        } 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');
    }

    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':"WORD",
                    'sValue':word.replace('’ ','’').trim()
                };
                if (bInfo) {
                    aElem.push({
                        sType: tmpToken.sType,
                        sValue: tmpToken.sValue,
                        aLabel: [this._formatTags(lastTokenWord).replace(/(\(él.\))/g,'').trim()]
                    });
                } 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;
}

let bInitDone = false;

let oDict = null;
let oTokenizer = null;
let oLxg = null;
let oTest = null;
let oLocution = null;


/*
    Technical note:
    This worker don’t work as a PromiseWorker (which returns a promise),  so when we send request
    to this worker, we can’t wait the return of the answer just after the request made.
    The answer is received by the background in another function (onmessage).

            conj.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/conj_data.json"));
            phonet.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/phonet_data.json"));
            mfsp.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/mfsp_data.json"));
            //console.log("[Worker] Modules have been initialized…");
            gc_engine.load(sContext, sExtensionPath+"grammalecte/_dictionaries");
            oDict = gc_engine.getDictionary();
            oTest = new TestGrammarChecking(gc_engine, sExtensionPath+"/grammalecte/fr/tests_data.json");
            oTokenizer = new Tokenizer("fr");

            oLocution =  helpers.loadFile(sExtensionPath + "/grammalecte/fr/locutions_data.json");

            oLxg = new Lexicographe(oDict, oTokenizer, oLocution);
            if (dOptions !== null) {
                gc_engine.setOptions(dOptions);
            }

            //tests();
            bInitDone = true;
        } else {
            console.log("[Worker] Already initialized…")
        }
        // we always retrieve options from the gc_engine, for setOptions filters obsolete options
        postMessage(createResponse("init", gc_engine.getOptions(), dInfo, true));

// Lexicographer

function getListOfTokens (sText, dInfo={}) {
    try {
        for (let sParagraph of text.getParagraph(sText)) {
            if (sParagraph.trim() !== "") {








                postMessage(createResponse("getListOfTokens", oLxg.getListOfTokensReduc(sParagraph, true), dInfo, false));
            }
        }
        postMessage(createResponse("getListOfTokens", null, dInfo, true));
    }
    catch (e) {
        helpers.logerror(e);
        postMessage(createResponse("getListOfTokens", createErrorResult(e, "no tokens"), dInfo, true, true));
    }
}