Grammalecte  Diff

    let aNew = [];
    for (let i = 0; i < aArray.length; i = i + 1) {
        aNew[i] = aArray[i].slice(0,1).toUpperCase() + aArray[i].slice(1);
    }
    return aNew;
}


// data
let _sAppContext = "";                                  // what software is running
let _dOptions = null;
let _dOptionsColors = null;
let _oSpellChecker = null;
let _oTokenizer = null;
let _aIgnoredRules = new Set();


function echo (x) {
    console.log(x);
    return true;
}

var _sAppContext = "";

var gc_engine = {

    //// Informations

    lang: "${lang}",
    locales: ${loc},
    pkg: "${implname}",
    name: "${name}",
    version: "${version}",
    author: "${author}",

    //// Tools
    oSpellChecker: null,
    oTokenizer: null,

    //// Data
    aIgnoredRules: new Set(),
    oOptionsColors: null,

    //// Initialization

    load: function (sContext="JavaScript", sColorType="aRGB", sPath="") {
        try {
            _sAppContext = sContext;
            if(typeof(process) !== 'undefined') {
            if (typeof(process) !== 'undefined') {
                var spellchecker = require("../graphspell/spellchecker.js");
                _oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
                this.oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            } else if (typeof(require) !== 'undefined') {
                var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
                _oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            } else {
                _oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
                this.oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            }
            this.oSpellChecker.activateStorage();
            this.oTokenizer = this.oSpellChecker.getTokenizer();
            _sAppContext = sContext;
            gc_options.load(sContext)
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
            _dOptionsColors = gc_options.getOptionsColors(sContext, sColorType);
            this.oOptionsColors = gc_options.getOptionsColors(sContext, sColorType);
            _oTokenizer = _oSpellChecker.getTokenizer();
            _oSpellChecker.activateStorage();
        }
        catch (e) {
            console.error(e);
        }
    },

    getSpellChecker: function () {
        return _oSpellChecker;
        return this.oSpellChecker;
    },

    //// Rules

    getRules: function (bParagraph) {
        if (!bParagraph) {
            return gc_rules.lSentenceRules;
        }
        return gc_rules.lParagraphRules;
    },

    ignoreRule: function (sRuleId) {
        _aIgnoredRules.add(sRuleId);
        this.aIgnoredRules.add(sRuleId);
    },

    resetIgnoreRules: function () {
        _aIgnoredRules.clear();
        this.aIgnoredRules.clear();
    },

    reactivateRule: function (sRuleId) {
        _aIgnoredRules.delete(sRuleId);
        this.aIgnoredRules.delete(sRuleId);
    },

    listRules: function* (sFilter=null) {
        // generator: returns tuple (sOption, sLineId, sRuleId)
        try {
            for (let [sOption, lRuleGroup] of this.getRules(true)) {
                for (let [,, sLineId, sRuleId,,] of lRuleGroup) {

            console.error(e);
        }
    },

    //// Options

    setOption: function (sOpt, bVal) {
        if (_dOptions.has(sOpt)) {
            _dOptions.set(sOpt, bVal);
        gc_options.setOption(sOpt, bVal);
        }
    },

    setOptions: function (dOpt) {
        _dOptions.gl_updateOnlyExistingKeys(dOpt);
        gc_options.setOptions(dOpt);
    },

    getOptions: function () {
        return _dOptions;
        return gc_options.getOptions();
    },

    getDefaultOptions: function () {
        return gc_options.getOptions(_sAppContext).gl_shallowCopy();
        return gc_options.getDefaultOptions();
    },

    resetOptions: function () {
        _dOptions = gc_options.getOptions(_sAppContext).gl_shallowCopy();
        gc_options.resetOptions();
    },

    //// Parsing

    parse: function (sText, sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false, bFullInfo=false) {
        // init point to analyse <sText> and returns an iterable of errors or (with option <bFullInfo>) a list of sentences with tokens and errors
        let oText = new TextParser(sText);

            s += "\n";
        }
        return s;
    }

    parse (sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false, bFullInfo=false) {
        // analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) a list of sentences with tokens and errors
        let dOpt = dOptions || _dOptions;
        let dOpt = dOptions || gc_options.dOptions;
        let bShowRuleId = option('idrule');
        // parse paragraph
        try {
            this.parseText(this.sText, this.sText0, true, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext);
        }
        catch (e) {
            console.error(e);

        let lSentences = [];
        let oSentence = null;
        for (let [iStart, iEnd] of text.getSentenceBoundaries(sText)) {
            try {
                this.sSentence = sText.slice(iStart, iEnd);
                this.sSentence0 = this.sText0.slice(iStart, iEnd);
                this.nOffsetWithinParagraph = iStart;
                this.lToken = Array.from(_oTokenizer.genTokens(this.sSentence, true));
                this.lToken = Array.from(gc_engine.oTokenizer.genTokens(this.sSentence, true));
                this.dTokenPos.clear();
                for (let dToken of this.lToken) {
                    if (dToken["sType"] != "INFO") {
                        this.dTokenPos.set(dToken["nStart"], dToken);
                    }
                }
                if (bFullInfo) {
                    oSentence = { "nStart": iStart, "nEnd": iEnd, "sSentence": this.sSentence, "lToken": Array.from(this.lToken) };
                    for (let oToken of oSentence["lToken"]) {
                        if (oToken["sType"] == "WORD") {
                            oToken["bValidToken"] = _oSpellChecker.isValidToken(oToken["sValue"]);
                            oToken["bValidToken"] = gc_engine.oSpellChecker.isValidToken(oToken["sValue"]);
                        }
                    }
                    // the list of tokens is duplicated, to keep all tokens from being deleted when analysis
                }
                this.parseText(this.sSentence, this.sSentence0, false, iStart, sCountry, dOpt, bShowRuleId, bDebug, bContext);
                if (bFullInfo) {
                    oSentence["lGrammarErrors"] = Array.from(this.dSentenceError.values());

                        }
                        sText = this.parseGraph(gc_rules_graph.dAllGraph[sGraphName], sCountry, dOptions, bShowRuleId, bDebug, bContext);
                    }
                }
            }
            else if (!sOption || option(sOption)) {
                for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
                    if (!_aIgnoredRules.has(sRuleId)) {
                    if (!gc_engine.aIgnoredRules.has(sRuleId)) {
                        while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) {
                            let bCondMemo = null;
                            for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) {
                                // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try {
                                    bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](sText, sText0, m, this.dTokenPos, sCountry, bCondMemo));
                                    if (bCondMemo) {

            }
        }
    }

    update (sSentence, bDebug=false) {
        // update <sSentence> and retokenize
        this.sSentence = sSentence;
        let lNewToken = Array.from(_oTokenizer.genTokens(sSentence, true));
        let lNewToken = Array.from(gc_engine.oTokenizer.genTokens(sSentence, true));
        for (let oToken of lNewToken) {
            if (this.dTokenPos.gl_get(oToken["nStart"], {}).hasOwnProperty("lMorph")) {
                oToken["lMorph"] = this.dTokenPos.get(oToken["nStart"])["lMorph"];
            }
            if (this.dTokenPos.gl_get(oToken["nStart"], {}).hasOwnProperty("aTags")) {
                oToken["aTags"] = this.dTokenPos.get(oToken["nStart"])["aTags"];
            }

                    }
                }
            }
            // analysable tokens
            if (oToken["sType"].slice(0,4) == "WORD") {
                // token lemmas
                if (oNode.hasOwnProperty("<lemmas>")) {
                    for (let sLemma of _oSpellChecker.getLemma(oToken["sValue"])) {
                    for (let sLemma of gc_engine.oSpellChecker.getLemma(oToken["sValue"])) {
                        if (oNode["<lemmas>"].hasOwnProperty(sLemma)) {
                            if (bDebug) {
                                console.log("  MATCH: >" + sLemma);
                            }
                            yield { "iToken1": iToken1, "iNode": oNode["<lemmas>"][sLemma] };
                            bTokenFound = true;
                        }
                    }
                }
                // morph arcs
                if (oNode.hasOwnProperty("<morph>")) {
                    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
                    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
                    if (lMorph.length > 0) {
                        for (let sSearch in oNode["<morph>"]) {
                            if (!sSearch.includes("¬")) {
                                // no anti-pattern
                                if (lMorph.some(sMorph  =>  (sMorph.includes(sSearch)))) {
                                    if (bDebug) {
                                        console.log("  MATCH: $" + sSearch);

                                }
                            }
                        }
                    }
                }
                // regex morph arcs
                if (oNode.hasOwnProperty("<re_morph>")) {
                    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
                    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
                    if (lMorph.length > 0) {
                        for (let sRegex in oNode["<re_morph>"]) {
                            if (!sRegex.includes("¬")) {
                                // no anti-pattern
                                if (lMorph.some(sMorph  =>  (sMorph.search(sRegex) !== -1))) {
                                    if (bDebug) {
                                        console.log("  MATCH: @" + sRegex);

    _createError (nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) {
        let oErr = {
            "nStart": nStart,
            "nEnd": nEnd,
            "sLineId": sLineId,
            "sRuleId": sRuleId,
            "sType": sOption || "notype",
            "aColor": _dOptionsColors[sOption],
            "aColor": gc_engine.oOptionsColors[sOption],
            "sMessage": sMessage,
            "aSuggestions": lSugg,
            "URL": sURL
        }
        if (bContext) {
            oErr['sUnderlined'] = this.sText0.slice(nStart, nEnd);
            oErr['sBefore'] = this.sText0.slice(Math.max(0,nStart-80), nStart);

};


//////// Common functions

function option (sOpt) {
    // return true if option sOpt is active
    return _dOptions.get(sOpt);
    return gc_options.dOptions.gl_get(sOpt, false);
}

var re = {
    search: function (sRegex, sText) {
        if (sRegex.startsWith("(?i)")) {
            return sText.search(new RegExp(sRegex.slice(4), "i")) !== -1;
        } else {

function displayInfo (dTokenPos, aWord) {
    // for debugging: info of word
    if (!aWord) {
        console.log("> nothing to find");
        return true;
    }
    let lMorph = _oSpellChecker.getMorph(aWord[1]);
    let lMorph = gc_engine.oSpellChecker.getMorph(aWord[1]);
    if (lMorph.length === 0) {
        console.log("> not in dictionary");
        return true;
    }
    if (dTokenPos.has(aWord[0])) {
        console.log("DA: " + dTokenPos.get(aWord[0]));
    }
    console.log("FSA: " + lMorph);
    return true;
}

function morph (dTokenPos, aWord, sPattern, sNegPattern, bNoWord=false) {
    // analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
    if (!aWord) {
        return bNoWord;
    }
    let lMorph = (dTokenPos.has(aWord[0])  &&  dTokenPos.get(aWord[0]))["lMorph"] ? dTokenPos.get(aWord[0])["lMorph"] : _oSpellChecker.getMorph(aWord[1]);
    let lMorph = (dTokenPos.has(aWord[0])  &&  dTokenPos.get(aWord[0]))["lMorph"] ? dTokenPos.get(aWord[0])["lMorph"] : gc_engine.oSpellChecker.getMorph(aWord[1]);
    if (lMorph.length === 0) {
        return false;
    }
    if (sNegPattern) {
        // check negative condition
        if (sNegPattern === "*") {
            // all morph must match sPattern

    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function analyse (sWord, sPattern, sNegPattern) {
    // analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)
    let lMorph = _oSpellChecker.getMorph(sWord);
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0) {
        return false;
    }
    if (sNegPattern) {
        // check negative condition
        if (sNegPattern === "*") {
            // all morph must match sPattern

    let lMorph;
    if (oToken.hasOwnProperty("lMorph")) {
        lMorph = oToken["lMorph"];
    }
    else {
        if (nLeft !== null) {
            let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
            lMorph = _oSpellChecker.getMorph(sValue);
            lMorph = gc_engine.oSpellChecker.getMorph(sValue);
            if (bMemorizeMorph) {
                oToken["lMorph"] = lMorph;
            }
        } else {
            lMorph = _oSpellChecker.getMorph(oToken["sValue"]);
            lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
        }
    }
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {

}

function g_analyse (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
    // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
    let lMorph;
    if (nLeft !== null) {
        let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
        lMorph = _oSpellChecker.getMorph(sValue);
        lMorph = gc_engine.oSpellChecker.getMorph(sValue);
        if (bMemorizeMorph) {
            oToken["lMorph"] = lMorph;
        }
    } else {
        lMorph = _oSpellChecker.getMorph(oToken["sValue"]);
        lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    }
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {

    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function g_merged_analyse (oToken1, oToken2, cMerger, sPattern, sNegPattern="", bSetMorph=true) {
    // merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)
    let lMorph = _oSpellChecker.getMorph(oToken1["sValue"] + cMerger + oToken2["sValue"]);
    let lMorph = gc_engine.oSpellChecker.getMorph(oToken1["sValue"] + cMerger + oToken2["sValue"]);
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern

    if (!sWord) {
        return true;
    }
    if (!dTokenPos.has(nPos)) {
        console.log("Error. There should be a token at this position: ", nPos);
        return true;
    }
    let lMorph = _oSpellChecker.getMorph(sWord);
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0  ||  lMorph.length === 1) {
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            dTokenPos.get(nPos)["lMorph"] = lSelect;

    if (!sWord) {
        return true;
    }
    if (!dTokenPos.has(nPos)) {
        console.log("Error. There should be a token at this position: ", nPos);
        return true;
    }
    let lMorph = _oSpellChecker.getMorph(sWord);
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0  ||  lMorph.length === 1) {
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            dTokenPos.get(nPos)["lMorph"] = lSelect;

}


//// Disambiguation for graph rules

function g_select (oToken, sPattern, lDefault=null) {
    // select morphologies for <oToken> according to <sPattern>, always return true
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    if (lMorph.length === 0  || lMorph.length === 1) {
        if (lDefault) {
            oToken["lMorph"] = lDefault;
        }
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            oToken["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        oToken["lMorph"] = lDefault;
    }
    return true;
}

function g_exclude (oToken, sPattern, lDefault=null) {
    // select morphologies for <oToken> according to <sPattern>, always return true
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    if (lMorph.length === 0  || lMorph.length === 1) {
        if (lDefault) {
            oToken["lMorph"] = lDefault;
        }
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            oToken["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        oToken["lMorph"] = lDefault;
    }
    return true;
}

function g_add_morph (oToken, sNewMorph) {
    // Disambiguation: add a morphology to a token
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    lMorph.push(...sNewMorph.split("|"));
    oToken["lMorph"] = lMorph;
    return true;
}

function g_rewrite (oToken, sToReplace, sReplace) {
    // Disambiguation: rewrite morphologies
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    oToken["lMorph"] = lMorph.map(s => s.replace(sToReplace, sReplace));
    return true;
}

function g_define (oToken, sMorphs) {
    // set morphologies of <oToken>, always return true
    oToken["lMorph"] = sMorphs.split("|");
    return true;
}

function g_define_from (oToken, nLeft=null, nRight=null) {
    let sValue = oToken["sValue"];
    if (nLeft !== null) {
        sValue = (nRight !== null) ? sValue.slice(nLeft, nRight) : sValue.slice(nLeft);
    }
    oToken["lMorph"] = _oSpellChecker.getMorph(sValue);
    oToken["lMorph"] = gc_engine.oSpellChecker.getMorph(sValue);
    return true;
}

function g_change_meta (oToken, sType) {
    // Disambiguation: change type of token
    oToken["sType"] = sType;
    return true;