Grammalecte  Check-in [a3687f4fd3]

// list of similar chars
// useful for suggestion mechanism

/* jshint esversion:6 */
/* jslint esversion:6 */

${map}


var char_player = {

    _xTransCharsForSpelling: new Map([
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st']

    _xTransCharsForSimplification: new Map([
        ['à', 'a'],  ['é', 'e'],  ['î', 'i'],  ['ô', 'o'],  ['û', 'u'],  ['ÿ', 'i'],  ['y', 'i'],
        ['â', 'a'],  ['è', 'e'],  ['ï', 'i'],  ['ö', 'o'],  ['ù', 'u'],  ['ŷ', 'i'],
        ['ä', 'a'],  ['ê', 'e'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'i'],
        ['á', 'a'],  ['ë', 'e'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'i'],
        ['ā', 'a'],  ['ē', 'e'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'i'],
        ['ç', 'c'],  ['ñ', 'n'],  ['k', 'q'],  ['w', 'v'],
        ['œ', 'oe'], ['æ', 'ae'],
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st']
    ]),

    simplifyWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        sWord = [...sWord].map(c => this._xTransCharsForSimplification.gl_get(c, c)).join('');

        ["Ë", "EeÉéÈèÊêËëĒēŒœ"],

        ["f", "fF"],
        ["F", "Ff"],

        ["g", "gGjJĵĴ"],
        ["G", "GgJjĴĵ"],

        ["h", "hH"],
        ["H", "Hh"],

        ["i", "iIîÎïÏyYíÍìÌīĪÿŸ"],
        ["I", "IiÎîÏïYyÍíÌìĪīŸÿ"],
        ["î", "iIîÎïÏyYíÍìÌīĪÿŸ"],
        ["Î", "IiÎîÏïYyÍíÌìĪīŸÿ"],

    },

    // Other functions
    filterSugg: function (aSugg) {
        return aSugg.filter((sSugg) => { return !sSugg.endsWith("è") && !sSugg.endsWith("È"); });
    }

};


if (typeof exports !== 'undefined') {
    exports._xTransCharsForSpelling = char_player._xTransCharsForSpelling;
    exports.spellingNormalization = char_player.spellingNormalization;
    exports._xTransCharsForSimplification = char_player._xTransCharsForSimplification;
    exports.simplifyWord = char_player.simplifyWord;
    exports.aVowel = char_player.aVowel;
    exports.aConsonant = char_player.aConsonant;
    exports.aDouble = char_player.aDouble;

// JavaScript

// FSA DICTIONARY BUILDER
//
// by Olivier R.
// License: MPL 2
//
// This tool encodes lexicon into an indexable binary dictionary
// Input files MUST be encoded in UTF-8.

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console, helpers */

"use strict";

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


${map}


class DAWG {
    /*  DIRECT ACYCLIC WORD GRAPH
        This code is inspired from Steve Hanov’s DAWG, 2011. (http://stevehanov.ca/blog/index.php?id=115)

        let lWord = [];
        for (let [sFlex, iAff, iTag] of lEntry) {
            let lTemp = [];
            for (let c of sFlex) {
                lTemp.push(dChar.get(c));
            }
            lTemp.push(iAff+nChar);
            lTemp.push(iTag+nChar+nAff);
            lWord.push(lTemp);
        }
        lEntry.length = 0; // clear the array

        // Dictionary of arc values occurrency, to sort arcs of each node
        let lKeyVal = [];
        for (let c of dChar.keys()) { lKeyVal.push([dChar.get(c), dCharOccur.get(c)]); }

        this.nNextId += 1;
        return this.nNextId-1;
    },

    reset: function () {
        this.nNextId = 0;
    }
};


class DawgNode {

    constructor () {
        this.i = oNodeCounter.getId();
        this.final = false;

    convValueToHexString (nVal, nByte) {
        // nVal: value to convert, nByte: number of bytes
        let sHexVal = nVal.toString(16); // conversion to hexadecimal string
        //console.log(`value: ${nVal} in ${nByte} bytes`);
        if (sHexVal.length < (nByte*2)) {
            return "0".repeat((nByte*2) - sHexVal.length) + sHexVal;
        } else if (sHexVal.length == (nByte*2)) {
            return sHexVal;
        } else {
            throw "Conversion to byte string: value bigger than allowed.";
        }
    }
}

// HELPERS

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console, XMLHttpRequest */

"use strict";


var helpers = {

    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__";
        console.log(sMsg);
    },

    loadFile: function (spf) {
        // load ressources in workers (suggested by Mozilla extensions reviewers)
        // for more options have a look here: https://gist.github.com/Noitidart/ec1e6b9a593ec7e3efed
        // if not in workers, use sdk/data.load() instead
        try {
            if(typeof process !== 'undefined' && typeof require !== 'undefined') {
                //console.log('loadFile(disque): ' + spf);
                let fs = require('fs');
                return fs.readFileSync(spf, 'utf8');
            } else {
                //console.log('loadFile: ' + spf);
                let xRequest;
                xRequest = new XMLHttpRequest();
                xRequest.open('GET', spf, false); // 3rd arg is false for synchronous, sync is acceptable in workers
                xRequest.overrideMimeType('text/json');
                xRequest.send();
                return xRequest.responseText;
            }
        }
        catch (e) {
            console.error(e);
            return null;
        }
    },

            obj[k] = v;
        }
        return obj;
    }
};


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

// IBDAWG

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console*/

"use strict";

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


// Don’t remove <string>. Necessary in TB.
${string}
${map}
${set}

            "l2grams": this.l2grams
        };
        return oJSON;
    }

    isValidToken (sToken) {
        // checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)
        sToken = char_player.spellingNormalization(sToken);
        if (this.isValid(sToken)) {
            return true;
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }

            }
        }
        return Boolean(this._convBytesToInteger(this.byDic.slice(iAddr, iAddr+this.nBytesArc)) & this._finalNodeMask);
    }

    getMorph (sWord) {
        // retrieves morphologies list, different casing allowed
        sWord = char_player.spellingNormalization(sWord);
        let l = this.morph(sWord);
        if (sWord[0].gl_isUpperCase()) {
            l.push(...this.morph(sWord.toLowerCase()));
            if (sWord.gl_isUpperCase() && sWord.length > 1) {
                l.push(...this.morph(sWord.gl_toCapitalize()));
            }
        }
        return l;
    }

    suggest (sWord, nSuggLimit=10) {
        // returns a array of suggestions for <sWord>
	//console.time("Suggestions for " + sWord + ");
        sWord = char_player.spellingNormalization(sWord);
        let sPfx = "";
        let sSfx = "";
        [sPfx, sWord, sSfx] = char_player.cut(sWord);
        let nMaxSwitch = Math.max(Math.floor(sWord.length / 3), 1);
        let nMaxDel = Math.floor(sWord.length / 5);
        let nMaxHardRepl = Math.max(Math.floor((sWord.length - 5) / 4), 1);
        let nMaxJump = Math.max(Math.floor(sWord.length / 4), 1);
        let oSuggResult = new SuggResult(sWord);
        this._suggest(oSuggResult, sWord, nMaxSwitch, nMaxDel, nMaxHardRepl, nMaxJump);
        let aSugg = oSuggResult.getSuggestions(nSuggLimit);
        if (sSfx || sPfx) {
            // we add what we removed
            return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx; } );
        }

	//console.timeEnd("Suggestions for " + sWord + ");
        return aSugg;
    }

    _suggest (oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=false) {
        // returns a set of suggestions
        // recursive function
        if (sRemain == "") {

                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
        }
    }

    * _getArcs1 (iAddr) {
        // generator: return all arcs at <iAddr> as tuples of (nVal, iAddr)
        while (true) {
            let iEndArcAddr = iAddr+this.nBytesArc;
            let nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
            yield [nRawArc & this._arcMask, this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress))];
            if (nRawArc & this._lastArcMask) {
                break;
            }

    _lookupArcNode3 (nVal, iAddr) {
        // to do
    }
}


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

// Spellchecker
// Wrapper for the IBDAWG class.
// Useful to check several dictionaries at once.

// To avoid iterating over a pile of dictionaries, it is assumed that 3 are enough:
// - the main dictionary, bundled with the package
// - the extended dictionary
// - the community dictionary, added by an organization
// - the personal dictionary, created by the user for its own convenience

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console, IBDAWG, Tokenizer */

"use strict";

if(typeof process !== 'undefined') {
    var ibdawg = require('./ibdawg.js');
    var tokenizer = require('./tokenizer.js');
} else if (typeof require !== 'undefined') {
    var ibdawg = require('resource://grammalecte/graphspell/ibdawg.js');
    var tokenizer = require('resource://grammalecte/graphspell/tokenizer.js');
}


${map}


const dDefaultDictionaries = new Map([
    ["fr", "fr-allvars.json"],
    ["en", "en.json"]

            }
        }
        catch (e) {
            let sfDictionary = (typeof(dictionary) == "string") ? dictionary : dictionary.sLangName + "/" + dictionary.sFileName;
            if (bNecessary) {
                throw "Error: <" + sfDictionary + "> not loaded. " + e.message;
            }
            console.log("Error: <" + sfDictionary + "> not loaded.");
            console.log(e.message);
            return null;
        }
    }

    loadTokenizer () {
        if (typeof(tokenizer) !== 'undefined') {

        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (this.oMainDic.isValid(sWord)) {
            return true;
        }
        if (this.bExtendedDic && this.oExtendedDic.isValid(sWord)) {
            return true;
        }
        if (this.bCommunityDic && this.oCommunityDic.isValid(sWord)) {
            return true;
        }
        if (this.bPersonalDic && this.oPersonalDic.isValid(sWord)) {
            return true;
        }
        return false;
    }

    lookup (sWord) {
        // checks if sWord is in dictionary as is (strict verification)
        if (this.oMainDic.lookup(sWord)) {
            return true;
        }
        if (this.bExtendedDic && this.oExtendedDic.lookup(sWord)) {
            return true;
        }
        if (this.bCommunityDic && this.oCommunityDic.lookup(sWord)) {
            return true;
        }
        if (this.bPersonalDic && this.oPersonalDic.lookup(sWord)) {
            return true;
        }
        return false;
    }

        if (this.bPersonalDic) {
            yield this.oPersonalDic.suggest(sWord, nSuggLimit);
        }
    }

    * select (sFlexPattern="", sTagsPattern="") {
        // generator: returns all entries which flexion fits <sFlexPattern> and morphology fits <sTagsPattern>
        yield* this.oMainDic.select(sFlexPattern, sTagsPattern);
        if (this.bExtendedDic) {
            yield* this.oExtendedDic.select(sFlexPattern, sTagsPattern);
        }
        if (this.bCommunityDic) {
            yield* this.oCommunityDic.select(sFlexPattern, sTagsPattern);
        }
        if (this.bPersonalDic) {

        if (this.bPersonalDic) {
            lResult.push(...this.oPersonalDic.getSimilarEntries(sWord, nSuggLimit));
        }
        return lResult;
    }
}

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

// STRING TRANSFORMATION

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global exports, console */

"use strict";


// Note: 48 is the ASCII code for "0"

var str_transform = {

        let [sPfxCode, sSfxCode] = sAffCode.split('/');
        sWord = sPfxCode.slice(1) + sWord.slice(sPfxCode.charCodeAt(0)-48);
        return sSfxCode[0] == '0' ? sWord + sSfxCode.slice(1) : sWord.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
    }
};


if (typeof exports !== 'undefined') {
    exports.longestCommonSubstring = str_transform.longestCommonSubstring;
    exports.distanceDamerauLevenshtein = str_transform.distanceDamerauLevenshtein;
    exports.distanceDamerauLevenshtein2 = str_transform.distanceDamerauLevenshtein2;
    exports.showDistance = str_transform.showDistance;
    exports.changeWordWithSuffixCode = str_transform.changeWordWithSuffixCode;
    exports.changeWordWithAffixCode = str_transform.changeWordWithAffixCode;
    exports.defineAffixCode = str_transform.defineAffixCode;
    exports.defineSuffixCode = str_transform.defineSuffixCode;
}

// JavaScript
// Very simple tokenizer

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/*global require, exports, console*/

"use strict";


const aTkzPatterns = {
    // All regexps must start with ^.
    "default":

        while (sText) {
            let iCut = 1;
            for (let [zRegex, sType] of this.aRules) {
                if (sType !== "SPACE"  ||  bWithSpaces) {
                    try {
                        if ((m = zRegex.exec(sText)) !== null) {
                            iToken += 1;
                            yield { "i": iToken, "sType": sType, "sValue": m[0], "nStart": iNext, "nEnd": iNext + m[0].length };
                            iCut = m[0].length;
                            break;
                        }
                    }
                    catch (e) {
                        console.error(e);
                    }
                }
            }
            iNext += iCut;
            sText = sText.slice(iCut);
        }
        if (bStartEndToken) {
            yield { "i": iToken+1, "sType": "INFO", "sValue": "<end>", "nStart": iEnd, "nEnd": iEnd, "lMorph": ["<end>"] };
        }
    }
}


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