Grammalecte  Check-in [8e5a2f5900]

// Grammar checker engine
/*jslint esversion: 6*/
/*global console,require,exports*/

"use strict";

${string}
${regex}
${map}


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/graphspell/helpers.js");
    var gc_options = require("resource://grammalecte/${lang}/gc_options.js");
    var gc_rules = require("resource://grammalecte/${lang}/gc_rules.js");
    var cregex = require("resource://grammalecte/${lang}/cregex.js");
    var text = require("resource://grammalecte/text.js");
    var echo = helpers.echo;
}
else if (typeof(console) !== "undefined") {
    var echo = function (o) { console.log(o); return true; };
}
else {
    var echo = function () { return true; }
}

function capitalizeArray (aArray) {
    // can’t map on user defined function??
    let aNew = [];
    for (let i = 0; i < aArray.length; i = i + 1) {
        aNew[i] = aArray[i].gl_toCapitalize();
    }

        try {
            [sNew, dErrors] = this._proofread(sText, sAlt, 0, true, dDA, dPriority, sCountry, bDebug, bContext);
            if (sNew) {
                sText = sNew;
            }
        }
        catch (e) {
            helpers.logerror(e);
        }

        // cleanup
        if (sText.includes(" ")) {
            sText = sText.replace(/ /g, ' '); // nbsp
        }
        if (sText.includes(" ")) {
            sText = sText.replace(/ /g, ' '); // snbsp
        }
        if (sText.includes("'")) {
            sText = sText.replace(/'/g, "’");
        }
        if (sText.includes("‑")) {
            sText = sText.replace(/‑/g, "-"); // nobreakdash
        }

        // parse sentence
        for (let [iStart, iEnd] of this._getSentenceBoundaries(sText)) {
            if (4 < (iEnd - iStart) < 2000) {
                dDA.clear();
                //helpers.echo(sText.slice(iStart, iEnd));
                try {
                    [, errs] = this._proofread(sText.slice(iStart, iEnd), sAlt.slice(iStart, iEnd), iStart, false, dDA, dPriority, sCountry, bDebug, bContext);
                    dErrors.gl_update(errs);
                }
                catch (e) {
                    helpers.logerror(e);
                }
            }
        }
        return Array.from(dErrors.values());
    },

    _zEndOfSentence: new RegExp ('([.?!:;…][ .?!… »”")]*|.$)', "g"),

        for (let [sOption, lRuleGroup] of this._getRules(bParagraph)) {
            if (!sOption || option(sOption)) {
                for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
                    if (!_aIgnoredRules.has(sRuleId)) {
                        while ((m = zRegex.gl_exec2(s, lGroups, lNegLookBefore)) !== null) {
                            bCondMemo = null;
                            /*if (bDebug) {
                                helpers.echo(">>>> Rule # " + sLineId + " - Text: " + s + " opt: "+ sOption);
                            }*/
                            for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) {
                            // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try {
                                    //helpers.echo(oEvalFunc[sFuncCond]);
                                    bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](s, sx, m, dDA, sCountry, bCondMemo));
                                    if (bCondMemo) {
                                        switch (cActionType) {
                                            case "-":
                                                // grammar error
                                                //helpers.echo("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source);
                                                nErrorStart = nOffset + m.start[eAct[0]];
                                                if (!dErrs.has(nErrorStart) || nPriority > dPriority.get(nErrorStart)) {
                                                    dErrs.set(nErrorStart, this._createError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bIdRule, sOption, bContext));
                                                    dPriority.set(nErrorStart, nPriority);
                                                }
                                                break;
                                            case "~":
                                                // text processor
                                                //helpers.echo("-> text processor by " + sLineId + "\nzRegex: " + zRegex.source);
                                                s = this._rewrite(s, sWhat, eAct[0], m, bUppercase);
                                                bChange = true;
                                                if (bDebug) {
                                                    helpers.echo("~ " + s + "  -- " + m[eAct[0]] + "  # " + sLineId);
                                                }
                                                break;
                                            case "=":
                                                // disambiguation
                                                //helpers.echo("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
                                                oEvalFunc[sWhat](s, m, dDA);
                                                if (bDebug) {
                                                    helpers.echo("= " + m[0] + "  # " + sLineId + "\nDA: " + dDA.gl_toString());
                                                }
                                                break;
                                            case ">":
                                                // we do nothing, this test is just a condition to apply all following actions
                                                break;
                                            default:
                                                helpers.echo("# error: unknown action at " + sLineId);
                                        }
                                    } else {
                                        if (cActionType == ">") {
                                            break;
                                        }
                                    }
                                }
                                catch (e) {
                                    helpers.echo(s);
                                    helpers.echo("# line id: " + sLineId + "\n# rule id: " + sRuleId);
                                    helpers.logerror(e);
                                }
                            }
                        }
                    }
                }
            }
        }

            if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) {
                sNew = sNew.gl_toCapitalize();
            }
        } else {
            sNew = sRepl.gl_expand(m);
            sNew = sNew + " ".repeat(ln-sNew.length);
        }
        //helpers.echo("\n"+s+"\nstart: "+m.start[iGroup]+" end:"+m.end[iGroup])
        return s.slice(0, m.start[iGroup]) + sNew + s.slice(m.end[iGroup]);
    },

    // Actions on rules

    ignoreRule: function (sRuleId) {
        _aIgnoredRules.add(sRuleId);

                    if (!sFilter || sRuleId.test(sFilter)) {
                        yield [sOption, sLineId, sRuleId];
                    }
                }
            }
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    _getRules: function (bParagraph) {
        if (!bParagraph) {
            return gc_rules.lSentenceRules;
        }

            } else {
                _oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    getSpellChecker: function () {
        return _oSpellChecker;
    },

    // return true if option sOpt is active
    return _dOptions.get(sOpt);
}

function displayInfo (dDA, aWord) {
    // for debugging: info of word
    if (!aWord) {
        helpers.echo("> nothing to find");
        return true;
    }
    if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
        helpers.echo("> not in FSA");
        return true;
    }
    if (dDA.has(aWord[0])) {
        helpers.echo("DA: " + dDA.get(aWord[0]));
    }
    helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
    return true;
}

function _storeMorphFromFSA (sWord) {
    // retrieves morphologies list from _oSpellChecker -> _dAnalyses
    //helpers.echo("register: "+sWord + " " + _oSpellChecker.getMorph(sWord).toString())
    _dAnalyses.set(sWord, _oSpellChecker.getMorph(sWord));
    return !!_dAnalyses.get(sWord);
}

function morph (dDA, aWord, sPattern, bStrict=true, bNoWord=false) {
    // analyse a tuple (position, word), return true if sPattern in morphologies (disambiguation on)
    if (!aWord) {
        //helpers.echo("morph: noword, returns " + bNoWord);
        return bNoWord;
    }
    //helpers.echo("aWord: "+aWord.toString());
    if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
        return false;
    }
    let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]);
    //helpers.echo("lMorph: "+lMorph.toString());
    if (lMorph.length === 0) {
        return false;
    }
    //helpers.echo("***");
    if (bStrict) {
        return lMorph.every(s  =>  (s.search(sPattern) !== -1));
    }
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}

function morphex (dDA, 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) {
        //helpers.echo("morph: noword, returns " + bNoWord);
        return bNoWord;
    }
    //helpers.echo("aWord: "+aWord.toString());
    if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
        return false;
    }
    let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]);
    //helpers.echo("lMorph: "+lMorph.toString());
    if (lMorph.length === 0) {
        return false;
    }
    //helpers.echo("***");
    // check negative condition
    if (lMorph.some(s  =>  (s.search(sNegPattern) !== -1))) {
        return false;
    }
    // search sPattern
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}

    try {
        if (zNegPattern && zNegPattern.test(s)) {
            return false;
        }
        return zPattern.test(s);
    }
    catch (e) {
        helpers.logerror(e);
    }
    return false;
}

function look_chk1 (dDA, s, nOffset, zPattern, sPatternGroup1, sNegPatternGroup1=null) {
    // returns True if s has pattern zPattern and m.group(1) has pattern sPatternGroup1
    let m = zPattern.gl_exec2(s, null);
    if (!m) {
        return false;
    }
    try {
        let sWord = m[1];
        let nPos = m.start[1] + nOffset;
        if (sNegPatternGroup1) {
            return morphex(dDA, [nPos, sWord], sPatternGroup1, sNegPatternGroup1);
        } 
        return morph(dDA, [nPos, sWord], sPatternGroup1, false);
    }
    catch (e) {
        helpers.logerror(e);
        return false;
    }
}


//////// Disambiguator

                if (i % 1000 === 0) {
                    yield i.toString();
                }
            }
            bShowUntested = true;
        }
        catch (e) {
            helpers.logerror(e);
        }

        if (bShowUntested) {
            i = 0;
            for (let [sOpt, sLineId, sRuleId] of this.gce.listRules()) {
                if (!this._aRuleTested.has(sLineId) && !/^[0-9]+[sp]$|^[pd]_/.test(sRuleId)) {
                    sUntestedRules += sRuleId + ", ";

                    console.log("\ninfinite loop?\nline:"+sLine+"\nm: "+ m.toString());
                    break;
                }
            }
            return sRes;
        }
        catch (e) {
            helpers.logerror(e);
        }
        return " ".repeat(sLine.length);
    }

    _getFoundErrors (sLine, bDebug, sOption) {
        try {
            let aErrs = [];

                sRes = sRes.slice(0, dErr["nStart"]) + "~".repeat(dErr["nEnd"] - dErr["nStart"]) + sRes.slice(dErr["nEnd"]);
                sListErr += "    * {" + dErr['sLineId'] + " / " + dErr['sRuleId'] + "}  at  " + dErr['nStart'] + ":" + dErr['nEnd'] + "\n";
                this._aRuleTested.add(dErr["sLineId"]);
            }
            return [sRes, sListErr];
        }
        catch (e) {
            helpers.logerror(e);
        }
        return [" ".repeat(sLine.length), ""];
    }

}


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

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

"use strict";


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

            }
            if (oErr["URL"] !== "") {
                sResult += "\n  > URL: " + oErr["URL"];
            }
            return sResult;
        }
        catch (e) {
            helpers.logerror(e);
            return "\n# Error. Data: " + oErr.toString();
        }
    }
};


if (typeof(exports) !== 'undefined') {
    exports.getParagraph = text.getParagraph;
    exports.wrap = text.wrap;
    exports.getReadableError = text.getReadableError;
}

        let m = /NF[  -]?(C|E|P|Q|S|X|Z|EN(?:[  -]ISO|))[  -]?([0-9]+(?:[\/‑-][0-9]+|))/i.exec(s);
        if (!m) {
            return "";
        }
        return "NF " + m[1].toUpperCase().replace(/ /g, " ").replace(/-/g, " ") + " " + m[2].replace(/\//g, "‑").replace(/-/g, "‑");
    }
    catch (e) {
        helpers.logerror(e);
        return "# erreur #";
    }
}

function undoLigature (c) {
    if (c == "fi") {
        return "fi";

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

"use strict";

${string}
${map}


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

const _dTag = new Map([
    [':N', [" nom,", "Nom"]],
    [':A', [" adjectif,", "Adjectif"]],
    [':M1', [" prénom,", "Prénom"]],
    [':M2', [" patronyme,", "Patronyme, matronyme, nom de famille…"]],
    [':MP', [" nom propre,", "Nom propre"]],
    [':W', [" adverbe,", "Adverbe"]],

    [':O2', [" 2ᵉ pers.,", "Pronom : 2ᵉ personne"]],
    [':O3', [" 3ᵉ pers.,", "Pronom : 3ᵉ personne"]],
    [':C', [" conjonction,", "Conjonction"]],
    [':Ĉ', [" conjonction (él.),", "Conjonction (élément)"]],
    [':Cc', [" conjonction de coordination,", "Conjonction de coordination"]],
    [':Cs', [" conjonction de subordination,", "Conjonction de subordination"]],
    [':Ĉs', [" conjonction de subordination (él.),", "Conjonction de subordination (élément)"]],
    
    [':Ñ', [" locution nominale (él.),", "Locution nominale (élément)"]],
    [':Â', [" locution adjectivale (él.),", "Locution adjectivale (élément)"]],
    [':Ṽ', [" locution verbale (él.),", "Locution verbale (élément)"]],
    [':Ŵ', [" locution adverbiale (él.),", "Locution adverbiale (élément)"]],
    [':Ŕ', [" locution prépositive (él.),", "Locution prépositive (élément)"]],
    [':Ĵ', [" locution interjective (él.),", "Locution interjective (élément)"]],

                            sValue: oToken.sValue,
                            aLabel: ["mot inconnu du dictionnaire"]
                        };
                    }
                    break;
            }
        } catch (e) {
            helpers.logerror(e);
        }
        return null;
    }

    _getMorph (sWord) {
        let aElem = [];
        for (let s of this.oSpellChecker.getMorph(sWord)) {

        try {
            gce = require("resource://grammalecte/fr/gc_engine.js");
            helpers = require("resource://grammalecte/graphspell/helpers.js");
            text = require("resource://grammalecte/text.js");
            tkz = require("resource://grammalecte/graphspell/tokenizer.js");
            //lxg = require("resource://grammalecte/fr/lexicographe.js");
            oTokenizer = new tkz.Tokenizer("fr");
            //helpers.setLogOutput(worker.log);
            gce.load(sContext);
            oSpellChecker = gce.getSpellChecker();
            if (sGCOptions !== "") {
                gce.setOptions(helpers.objectToMap(JSON.parse(sGCOptions)));
            }
            // we always retrieve options from the gce, for setOptions filters obsolete options
            return gce.getOptions().gl_toString();

            console.log("[Worker] Already initialized…")
        }
        // we always retrieve options from the gc_engine, for setOptions filters obsolete options
        dOptions = helpers.mapToObject(gc_engine.getOptions());
        postMessage(createResponse("init", dOptions, dInfo, true));
    }
    catch (e) {
        helpers.logerror(e);
        postMessage(createResponse("init", createErrorResult(e, "init failed"), dInfo, true, true));
    }
}


function parse (sText, sCountry, bDebug, bContext, dInfo={}) {
    sText = sText.replace(/­/g, "").normalize("NFC");

            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));
    }
}

// HELPERS
/*jslint esversion: 6*/
/*global console,require,exports,XMLHttpRequest*/

"use strict";

// In Firefox, there is no console.log in PromiseWorker, but there is worker.log.
// In Thunderbird, you can’t access to console directly. So it’s required to pass a log function.
let funcOutput = null;

var helpers = {

    setLogOutput: function (func) {
        // probably obsolete now, as console.log seems to work everywhere (at last!)
        funcOutput = func;
    },

    echo: function (obj) {
        // probably obsolete now, as console.log seems to work everywhere (at last!)
        if (funcOutput !== null) {
            funcOutput(obj);
        } else {
            console.log(obj);
        }
        return true;
    },

    logerror: function (e, bStack=false) {
        let sMsg = "\n" + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message;
        if (bStack) {
            sMsg += "\n--- Stack ---\n" + e.stack;
        }
        if (funcOutput !== null) {
            funcOutput(sMsg);
        } else {
            console.error(sMsg);
        }
    },

    inspect: function (o) {
        let sMsg = "__inspect__: " + typeof o;
        for (let sParam in o) {
            sMsg += "\n" + sParam + ": " + o.sParam;
        }
        sMsg += "\n" + JSON.stringify(o) + "\n__end__";
        this.echo(sMsg);

        }
        return obj;
    }
};


if (typeof(exports) !== 'undefined') {
    exports.setLogOutput = helpers.setLogOutput;
    exports.echo = helpers.echo;
    exports.logerror = helpers.logerror;
    exports.inspect = helpers.inspect;
    exports.loadFile = helpers.loadFile;
    exports.objectToMap = helpers.objectToMap;
    exports.mapToObject = helpers.mapToObject;
}

                        matrix[i][j] = Math.min(matrix[i][j], matrix[i-2][j-2] + nCost);  // Transposition
                    }
                }
            }
            return matrix[nLen1][nLen2];
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    distanceDamerauLevenshtein: function (s1, s2) {
        // distance of Damerau-Levenshtein between <s1> and <s2>
        // https://fr.wikipedia.org/wiki/Distance_de_Damerau-Levenshtein
        try {

                    matrix[i+1][j+1] = Math.min(matrix[i+1][j+1], matrix[i1] ? matrix[i1][j1] + (i-i1-1) + 1 + (j-j1-1) : Infinity);
                }
                sd[s1[i-1]] = i;
            }
            return matrix[nLen1+1][nLen2+1];
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    showDistance (s1, s2) {
        console.log(`Distance: ${s1} / ${s2} = ${this.distanceDamerauLevenshtein(s1, s2)})`);
    },

    changeWordWithSuffixCode: function (sWord, sSfxCode) {
        if (sSfxCode == "0") {
            return sWord;
        }
        return sSfxCode[0] == '0' ? sWord + sSfxCode.slice(1) : sWord.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
    },
    
    // Prefix and suffix
    defineAffixCode: function (sFlex, sStem) {
        /*
            UNTESTED!
            Returns a string defining how to get stem from flexion. Examples:
                "0" if stem = flexion
                "stem" if no common substring
                "n(pfx)/m(sfx)"
            with n and m: chars with numeric meaning, "0" = 0, "1" = 1, ... ":" = 10, etc. (See ASCII table.) Says how many letters to strip from flexion.
                pfx [optional]: string to add before the flexion 
                sfx [optional]: string to add after the flexion
        */
        if (sFlex == sStem) {
            return "0";
        }
        // is stem a substring of flexion?
        let n = sFlex.indexOf(sStem);

// JavaScript
// Very simple tokenizer
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";


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


const aTkzPatterns = {
    // All regexps must start with ^.
    "default":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERUNIX'],

                            yield { "sType": sType, "sValue": m[0], "nStart": i, "nEnd": i + m[0].length }
                        }
                        nCut = m[0].length;
                        break;
                    }
                }
                catch (e) {
                    helpers.logerror(e);
                }
            }
            i += nCut;
            sText = sText.slice(nCut);
        }
    }
}


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

                        m.start.push(iPos);
                        m.end.push(iPos + subm.length);
                    }
                }
            }
        }
        catch (e) {
            if (typeof(helpers) !== "undefined") {
                helpers.logerror(e);
            } else {
                console.error(e);
            }
        }
        return m;
    };

    RegExp.prototype.grammalecte = true;
}