Index: gc_core/js/helpers.js ================================================================== --- gc_core/js/helpers.js +++ gc_core/js/helpers.js @@ -5,94 +5,94 @@ // 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; -function setLogOutput (func) { - funcOutput = func; -} - -function echo (obj) { - if (funcOutput !== null) { - funcOutput(obj); - } else { - console.log(obj); - } - return true; -} - -function logerror (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); - } -} - -function inspect (o) { - let sMsg = "__inspect__: " + typeof o; - for (let sParam in o) { - sMsg += "\n" + sParam + ": " + o.sParam; - } - sMsg += "\n" + JSON.stringify(o) + "\n__end__"; - echo(sMsg); -} - - -// 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 -function loadFile (spf) { - try { - let xRequest; - if (typeof XMLHttpRequest !== "undefined") { - xRequest = new XMLHttpRequest(); - } - else { - // JS bullshit again… necessary for Thunderbird - let { Cc, Ci } = require("chrome"); - xRequest = Cc["@mozilla.org/xmlextras/xmlhttprequest;1"].createInstance(); - xRequest.QueryInterface(Ci.nsIXMLHttpRequest); - } - xRequest.open('GET', spf, false); // 3rd arg is false for synchronous, sync is acceptable in workers - xRequest.send(); - return xRequest.responseText; - } - catch (e) { - logerror(e); - return null - } -} - - -// conversions -function objectToMap (obj) { - let m = new Map(); - for (let param in obj) { - //console.log(param + " " + obj[param]); - m.set(param, obj[param]); - } - return m; -} - -function mapToObject (m) { - let obj = {}; - for (let [k, v] of m) { - obj[k] = v; - } - return obj; -} +var helpers = { + + setLogOutput: function (func) { + funcOutput = func; + }, + + echo: function (obj) { + 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); + }, + + 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 { + let xRequest; + if (typeof XMLHttpRequest !== "undefined") { + xRequest = new XMLHttpRequest(); + } else { + // JS bullshit again… necessary for Thunderbird + let { Cc, Ci } = require("chrome"); + xRequest = Cc["@mozilla.org/xmlextras/xmlhttprequest;1"].createInstance(); + xRequest.QueryInterface(Ci.nsIXMLHttpRequest); + } + xRequest.open('GET', spf, false); // 3rd arg is false for synchronous, sync is acceptable in workers + xRequest.send(); + return xRequest.responseText; + } + catch (e) { + this.logerror(e); + return null; + } + }, + + // conversions + objectToMap: function (obj) { + let m = new Map(); + for (let param in obj) { + //console.log(param + " " + obj[param]); + m.set(param, obj[param]); + } + return m; + }, + + mapToObject: function (m) { + let obj = {}; + for (let [k, v] of m) { + obj[k] = v; + } + return obj; + } +}; if (typeof(exports) !== 'undefined') { - exports.setLogOutput = setLogOutput; - exports.echo = echo; - exports.logerror = logerror; - exports.inspect = inspect; - exports.loadFile = loadFile; - exports.objectToMap = objectToMap; - exports.mapToObject = mapToObject; + 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; } Index: gc_core/js/ibdawg.js ================================================================== --- gc_core/js/ibdawg.js +++ gc_core/js/ibdawg.js @@ -1,11 +1,14 @@ //// IBDAWG "use strict"; -const st = require("resource://grammalecte/str_transform.js"); -const helpers = require("resource://grammalecte/helpers.js"); + +if (typeof(require) !== 'undefined') { + var str_transform = require("resource://grammalecte/str_transform.js"); + var helpers = require("resource://grammalecte/helpers.js"); +} // String // Don’t remove. Necessary in TB. ${string} @@ -13,16 +16,15 @@ class IBDAWG { // INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH - constructor (sDicName) { + constructor (sDicName, sPath="") { try { - const dict = JSON.parse(helpers.loadFile("resource://grammalecte/_dictionaries/"+sDicName)); + let sURL = (sPath !== "") ? sPath + "/" + sDicName : "resource://grammalecte/_dictionaries/"+sDicName; + const dict = JSON.parse(helpers.loadFile(sURL)); Object.assign(this, dict); - //const dict = require("resource://grammalecte/"+sLang+"/dictionary.js"); - //Object.assign(this, dict.dictionary); } catch (e) { throw Error("# Error. File not found or not loadable.\n" + e.message + "\n"); } /* @@ -39,15 +41,15 @@ this.dChar = helpers.objectToMap(this.dChar); //this.byDic = new Uint8Array(this.byDic); // not quicker, even slower if (this.cStemming == "S") { - this.funcStemming = st.getStemFromSuffixCode; + this.funcStemming = str_transform.getStemFromSuffixCode; } else if (this.cStemming == "A") { - this.funcStemming = st.getStemFromAffixCode; + this.funcStemming = str_transform.getStemFromAffixCode; } else { - this.funcStemming = st.noStemming; + this.funcStemming = str_transform.noStemming; } // Configuring DAWG functions according to nVersion switch (this.nVersion) { case 1: @@ -72,18 +74,18 @@ throw ValueError("# Error: unknown code: " + this.nVersion); } //console.log(this.getInfo()); this.bOptNumSigle = true; this.bOptNumAtLast = false; - }; + } getInfo () { return ` Language: ${this.sLang} Version: ${this.nVersion} Stemming: ${this.cStemming}FX\n` + ` Arcs values: ${this.nArcVal} = ${this.nChar} characters, ${this.nAff} affixes, ${this.nTag} tags\n` + ` Dictionary: ${this.nEntries} entries, ${this.nNode} nodes, ${this.nArc} arcs\n` + ` Address size: ${this.nBytesNodeAddress} bytes, Arc size: ${this.nBytesArc} bytes\n`; - }; + } isValidToken (sToken) { // checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked) if (this.isValid(sToken)) { return true; @@ -93,11 +95,11 @@ return true; } return sToken.split("-").every(sWord => this.isValid(sWord)); } return false; - }; + } isValid (sWord) { // checks if sWord is valid (different casing tested if the first letter is a capital) if (!sWord) { return null; @@ -123,11 +125,11 @@ } else { return !!this.lookup(sWord.toLowerCase()); } } return false; - }; + } _convBytesToInteger (aBytes) { // Byte order = Big Endian (bigger first) let nVal = 0; let nWeight = (aBytes.length - 1) * 8; @@ -134,11 +136,11 @@ for (let n of aBytes) { nVal += n << nWeight; nWeight = nWeight - 8; } return nVal; - }; + } lookup (sWord) { // returns true if sWord in dictionary (strict verification) let iAddr = 0; for (let c of sWord) { @@ -149,11 +151,11 @@ if (iAddr === null) { return false; } } return Boolean(this._convBytesToInteger(this.byDic.slice(iAddr, iAddr+this.nBytesArc)) & this._finalNodeMask); - }; + } getMorph (sWord) { // retrieves morphologies list, different casing allowed let l = this.morph(sWord); if (sWord[0].gl_isUpperCase()) { @@ -161,15 +163,15 @@ if (sWord.gl_isUpperCase() && sWord.length > 1) { l = l.concat(this.morph(sWord.gl_toCapitalize())); } } return l; - }; + } // morph (sWord) { // is defined in constructor - // }; + // } // VERSION 1 _morph1 (sWord) { // returns morphologies of sWord let iAddr = 0; @@ -205,11 +207,11 @@ iAddr = iEndArcAddr + this.nBytesNodeAddress; } return l; } return []; - }; + } _stem1 (sWord) { // returns stems list of sWord let iAddr = 0; for (let c of sWord) { @@ -235,11 +237,11 @@ iAddr = iEndArcAddr + this.nBytesNodeAddress; } return l; } return []; - }; + } _lookupArcNode1 (nVal, iAddr) { // looks if nVal is an arc at the node at iAddr, if yes, returns address of next node else None while (true) { let iEndArcAddr = iAddr+this.nBytesArc; @@ -255,39 +257,39 @@ return null; } iAddr = iEndArcAddr + this.nBytesNodeAddress; } } - }; + } // VERSION 2 _morph2 (sWord) { // to do - }; + } _stem2 (sWord) { // to do - }; + } _lookupArcNode2 (nVal, iAddr) { // to do - }; + } // VERSION 3 _morph3 (sWord) { // to do - }; + } _stem3 (sWord) { // to do - }; + } _lookupArcNode3 (nVal, iAddr) { // to do - }; + } } if (typeof(exports) !== 'undefined') { exports.IBDAWG = IBDAWG; } Index: gc_core/js/jsex_map.js ================================================================== --- gc_core/js/jsex_map.js +++ gc_core/js/jsex_map.js @@ -6,42 +6,42 @@ let oNewMap = new Map(); for (let [key, val] of this.entries()) { oNewMap.set(key, val); } return oNewMap; - } + }; Map.prototype.gl_get = function (key, defaultValue) { let res = this.get(key); if (res !== undefined) { return res; } return defaultValue; - } + }; Map.prototype.gl_toString = function () { // Default .toString() gives nothing useful let sRes = "{ "; for (let [k, v] of this.entries()) { sRes += (typeof k === "string") ? '"' + k + '": ' : k.toString() + ": "; sRes += (typeof v === "string") ? '"' + v + '", ' : v.toString() + ", "; } - sRes = sRes.slice(0, -2) + " }" + sRes = sRes.slice(0, -2) + " }"; return sRes; - } + }; Map.prototype.gl_update = function (dDict) { for (let [k, v] of dDict.entries()) { this.set(k, v); } - } + }; Map.prototype.gl_updateOnlyExistingKeys = function (dDict) { for (let [k, v] of dDict.entries()) { if (this.has(k)){ this.set(k, v); } } - } + }; Map.prototype.grammalecte = true; } Index: gc_core/js/jsex_regex.js ================================================================== --- gc_core/js/jsex_regex.js +++ gc_core/js/jsex_regex.js @@ -40,23 +40,23 @@ // at the end of the pattern m.start.push(this.lastIndex - m[i].length); m.end.push(this.lastIndex); } else if (codePos === "w") { // word in the middle of the pattern - iPos = m[0].search("[ ’,()«»“”]"+m[i]+"[ ,’()«»“”]") + 1 + m.index + iPos = m[0].search("[ ’,()«»“”]"+m[i]+"[ ,’()«»“”]") + 1 + m.index; m.start.push(iPos); - m.end.push(iPos + m[i].length) + m.end.push(iPos + m[i].length); } else if (codePos === "*") { // anywhere iPos = m[0].indexOf(m[i]) + m.index; m.start.push(iPos); - m.end.push(iPos + m[i].length) + m.end.push(iPos + m[i].length); } else if (codePos === "**") { // anywhere after previous group iPos = m[0].indexOf(m[i], m.end[i-1]-m.index) + m.index; m.start.push(iPos); - m.end.push(iPos + m[i].length) + m.end.push(iPos + m[i].length); } else if (codePos.startsWith(">")) { // >x:_ // todo: look in substring x iPos = m[0].indexOf(m[i]) + m.index; m.start.push(iPos); @@ -81,9 +81,9 @@ } else { console.error(e); } } return m; - } + }; RegExp.prototype.grammalecte = true; } Index: gc_core/js/jsex_string.js ================================================================== --- gc_core/js/jsex_string.js +++ gc_core/js/jsex_string.js @@ -13,45 +13,45 @@ while ((iPos = this.indexOf(sSearch, iPos)) >= 0) { nOccur++; iPos += nStep; } return nOccur; - } + }; String.prototype.gl_isDigit = function () { return (this.search(/^[0-9⁰¹²³⁴⁵⁶⁷⁸⁹]+$/) !== -1); - } + }; String.prototype.gl_isLowerCase = function () { return (this.search(/^[a-zà-öø-ÿ0-9-]+$/) !== -1); - } + }; String.prototype.gl_isUpperCase = function () { return (this.search(/^[A-ZÀ-ÖØ-ߌ0-9-]+$/) !== -1); - } + }; String.prototype.gl_isTitle = function () { return (this.search(/^[A-ZÀ-ÖØ-ߌ][a-zà-öø-ÿ'’-]+$/) !== -1); - } + }; String.prototype.gl_toCapitalize = function () { return this.slice(0,1).toUpperCase() + this.slice(1).toLowerCase(); - } + }; String.prototype.gl_expand = function (oMatch) { let sNew = this; for (let i = 0; i < oMatch.length ; i++) { let z = new RegExp("\\\\"+parseInt(i), "g"); sNew = sNew.replace(z, oMatch[i]); } return sNew; - } + }; String.prototype.gl_trimRight = function (sChars) { let z = new RegExp("["+sChars+"]+$"); return this.replace(z, ""); - } + }; String.prototype.gl_trimLeft = function (sChars) { let z = new RegExp("^["+sChars+"]+"); return this.replace(z, ""); - } + }; String.prototype.gl_trim = function (sChars) { let z1 = new RegExp("^["+sChars+"]+"); let z2 = new RegExp("["+sChars+"]+$"); return this.replace(z1, "").replace(z2, ""); - } + }; String.prototype.grammalecte = true; } Index: gc_core/js/lang_core/gc_engine.js ================================================================== --- gc_core/js/lang_core/gc_engine.js +++ gc_core/js/lang_core/gc_engine.js @@ -1,11 +1,28 @@ // Grammar checker engine +"use strict"; + ${string} ${regex} ${map} + +if (typeof(require) !== 'undefined') { + var helpers = require("resource://grammalecte/helpers.js"); + var gc_options = require("resource://grammalecte/${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) { @@ -12,407 +29,411 @@ aNew[i] = aArray[i].gl_toCapitalize(); } return aNew; } -const ibdawg = require("resource://grammalecte/ibdawg.js"); -const helpers = require("resource://grammalecte/helpers.js"); -const gc_options = require("resource://grammalecte/${lang}/gc_options.js"); -const cr = require("resource://grammalecte/${lang}/cregex.js"); -const text = require("resource://grammalecte/text.js"); -const echo = require("resource://grammalecte/helpers.js").echo; - -const lang = "${lang}"; -const locales = ${loc}; -const pkg = "${implname}"; -const name = "${name}"; -const version = "${version}"; -const author = "${author}"; - -// commons regexes -const _zEndOfSentence = new RegExp ('([.?!:;…][ .?!… »”")]*|.$)', "g"); -const _zBeginOfParagraph = new RegExp ("^[-  –—.,;?!…]*", "ig"); -const _zEndOfParagraph = new RegExp ("[-  .,;?!…–—]*$", "ig"); - -// grammar rules and dictionary -//const _rules = require("./gc_rules.js"); -let _sContext = ""; // what software is running -const _rules = require("resource://grammalecte/${lang}/gc_rules.js"); + +// data +let _sAppContext = ""; // what software is running let _dOptions = null; let _aIgnoredRules = new Set(); let _oDict = null; -let _dAnalyses = new Map(); // cache for data from dictionary - - -///// Parsing - -function parse (sText, sCountry="${country_default}", bDebug=false, bContext=false) { - // analyses the paragraph sText and returns list of errors - let dErrors; - let errs; - let sAlt = sText; - let dDA = new Map(); // Disamnbiguator - let dPriority = new Map(); // Key = position; value = priority - let sNew = ""; - - // parse paragraph - try { - [sNew, dErrors] = _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 _getSentenceBoundaries(sText)) { - if (4 < (iEnd - iStart) < 2000) { - dDA.clear(); - //echo(sText.slice(iStart, iEnd)); - try { - [_, errs] = _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()); -} - -function* _getSentenceBoundaries (sText) { - let mBeginOfSentence = _zBeginOfParagraph.exec(sText) - let iStart = _zBeginOfParagraph.lastIndex; - let m; - while ((m = _zEndOfSentence.exec(sText)) !== null) { - yield [iStart, _zEndOfSentence.lastIndex]; - iStart = _zEndOfSentence.lastIndex; - } -} - -function _proofread (s, sx, nOffset, bParagraph, dDA, dPriority, sCountry, bDebug, bContext) { - let dErrs = new Map(); - let bChange = false; - let bIdRule = option('idrule'); - let m; - let bCondMemo; - let nErrorStart; - - for (let [sOption, lRuleGroup] of _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) { - 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 { - //echo(oEvalFunc[sFuncCond]); - bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](s, sx, m, dDA, sCountry, bCondMemo)) - if (bCondMemo) { - switch (cActionType) { - case "-": - // grammar error - //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, _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 - //echo("-> text processor by " + sLineId + "\nzRegex: " + zRegex.source); - s = _rewrite(s, sWhat, eAct[0], m, bUppercase); - bChange = true; - if (bDebug) { - echo("~ " + s + " -- " + m[eAct[0]] + " # " + sLineId); - } - break; - case "=": - // disambiguation - //echo("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source); - oEvalFunc[sWhat](s, m, dDA); - if (bDebug) { - 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: - echo("# error: unknown action at " + sLineId); - } - } else { - if (cActionType == ">") { - break; - } - } - } - catch (e) { - echo(s); - echo("# line id: " + sLineId + "\n# rule id: " + sRuleId); - helpers.logerror(e); +let _dAnalyses = new Map(); // cache for data from dictionary + + +var gc_engine = { + + //// Informations + + lang: "${lang}", + locales: ${loc}, + pkg: "${implname}", + name: "${name}", + version: "${version}", + author: "${author}", + + //// Parsing + + parse: function (sText, sCountry="${country_default}", bDebug=false, bContext=false) { + // analyses the paragraph sText and returns list of errors + let dErrors; + let errs; + let sAlt = sText; + let dDA = new Map(); // Disamnbiguator + let dPriority = new Map(); // Key = position; value = priority + let sNew = ""; + + // parse paragraph + 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 ('([.?!:;…][ .?!… »”")]*|.$)', "g"), + _zBeginOfParagraph: new RegExp ("^[-  –—.,;?!…]*", "ig"), + _zEndOfParagraph: new RegExp ("[-  .,;?!…–—]*$", "ig"), + + _getSentenceBoundaries: function* (sText) { + let mBeginOfSentence = this._zBeginOfParagraph.exec(sText); + let iStart = this._zBeginOfParagraph.lastIndex; + let m; + while ((m = this._zEndOfSentence.exec(sText)) !== null) { + yield [iStart, this._zEndOfSentence.lastIndex]; + iStart = this._zEndOfSentence.lastIndex; + } + }, + + _proofread: function (s, sx, nOffset, bParagraph, dDA, dPriority, sCountry, bDebug, bContext) { + let dErrs = new Map(); + let bChange = false; + let bIdRule = option('idrule'); + let m; + let bCondMemo; + let nErrorStart; + + 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 (bChange) { - return [s, dErrs]; - } - return [false, dErrs]; -} - -function _createError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bIdRule, sOption, bContext) { - let oErr = {}; - oErr["nStart"] = nOffset + m.start[iGroup]; - oErr["nEnd"] = nOffset + m.end[iGroup]; - oErr["sLineId"] = sLineId; - oErr["sRuleId"] = sRuleId; - oErr["sType"] = (sOption) ? sOption : "notype"; - // suggestions - if (sRepl[0] === "=") { - let sugg = oEvalFunc[sRepl.slice(1)](s, m); - if (sugg) { - if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) { - oErr["aSuggestions"] = capitalizeArray(sugg.split("|")); - } else { - oErr["aSuggestions"] = sugg.split("|"); - } - } else { - oErr["aSuggestions"] = []; - } - } else if (sRepl == "_") { - oErr["aSuggestions"] = []; - } else { - if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) { - oErr["aSuggestions"] = capitalizeArray(sRepl.gl_expand(m).split("|")); - } else { - oErr["aSuggestions"] = sRepl.gl_expand(m).split("|"); - } - } - // Message - if (sMsg[0] === "=") { - sMessage = oEvalFunc[sMsg.slice(1)](s, m) - } else { - sMessage = sMsg.gl_expand(m); - } - if (bIdRule) { - sMessage += " ##" + sLineId + " #" + sRuleId; - } - oErr["sMessage"] = sMessage; - // URL - oErr["URL"] = sURL || ""; - // Context - if (bContext) { - oErr["sUnderlined"] = sx.slice(m.start[iGroup], m.end[iGroup]); - oErr["sBefore"] = sx.slice(Math.max(0, m.start[iGroup]-80), m.start[iGroup]); - oErr["sAfter"] = sx.slice(m.end[iGroup], m.end[iGroup]+80); - } - return oErr; -} - -function _rewrite (s, sRepl, iGroup, m, bUppercase) { - // text processor: write sRepl in s at iGroup position" - let ln = m.end[iGroup] - m.start[iGroup]; - let sNew = ""; - if (sRepl === "*") { - sNew = " ".repeat(ln); - } else if (sRepl === ">" || sRepl === "_" || sRepl === "~") { - sNew = sRepl + " ".repeat(ln-1); - } else if (sRepl === "@") { - sNew = "@".repeat(ln); - } else if (sRepl.slice(0,1) === "=") { - sNew = oEvalFunc[sRepl.slice(1)](s, m); - sNew = sNew + " ".repeat(ln-sNew.length); - 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); - } - //echo("\n"+s+"\nstart: "+m.start[iGroup]+" end:"+m.end[iGroup]) - return s.slice(0, m.start[iGroup]) + sNew + s.slice(m.end[iGroup]); -} - -function ignoreRule (sRuleId) { - _aIgnoredRules.add(sRuleId); -} - -function resetIgnoreRules () { - _aIgnoredRules.clear(); -} - -function reactivateRule (sRuleId) { - _aIgnoredRules.delete(sRuleId); -} - -function listRules (sFilter=null) { - // generator: returns tuple (sOption, sLineId, sRuleId) - try { - for ([sOption, lRuleGroup] of _getRules(true)) { - for ([_, _, sLineId, sRuleId, _, _] of lRuleGroup) { - if (!sFilter || sRuleId.test(sFilter)) { - yield [sOption, sLineId, sRuleId]; - } - } - } - for ([sOption, lRuleGroup] of _getRules(false)) { - for ([_, _, sLineId, sRuleId, _, _] of lRuleGroup) { - if (!sFilter || sRuleId.test(sFilter)) { - yield [sOption, sLineId, sRuleId]; - } - } - } - } - catch (e) { - helpers.logerror(e); - } -} - - -//////// init - -function load (sContext="JavaScript") { - try { - _oDict = new ibdawg.IBDAWG("${dic_name}.json"); - _sContext = sContext; - _dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default - } - catch (e) { - helpers.logerror(e); - } -} - -function setOption (sOpt, bVal) { - if (_dOptions.has(sOpt)) { - _dOptions.set(sOpt, bVal); - } -} - -function setOptions (dOpt) { - _dOptions.gl_updateOnlyExistingKeys(dOpt); -} - -function getOptions () { - return _dOptions; -} - -function getDefaultOptions () { - return gc_options.getOptions(_sContext).gl_shallowCopy(); -} - -function resetOptions () { - _dOptions = gc_options.getOptions(_sContext).gl_shallowCopy(); -} - -function getDictionary () { - return _oDict; -} - -function _getRules (bParagraph) { - if (!bParagraph) { - return _rules.lSentenceRules; - } - return _rules.lParagraphRules; -} - - - -//////// common functions + if (bChange) { + return [s, dErrs]; + } + return [false, dErrs]; + }, + + _createError: function (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bIdRule, sOption, bContext) { + let oErr = {}; + oErr["nStart"] = nOffset + m.start[iGroup]; + oErr["nEnd"] = nOffset + m.end[iGroup]; + oErr["sLineId"] = sLineId; + oErr["sRuleId"] = sRuleId; + oErr["sType"] = (sOption) ? sOption : "notype"; + // suggestions + if (sRepl.slice(0,1) === "=") { + let sugg = oEvalFunc[sRepl.slice(1)](s, m); + if (sugg) { + if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) { + oErr["aSuggestions"] = capitalizeArray(sugg.split("|")); + } else { + oErr["aSuggestions"] = sugg.split("|"); + } + } else { + oErr["aSuggestions"] = []; + } + } else if (sRepl == "_") { + oErr["aSuggestions"] = []; + } else { + if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) { + oErr["aSuggestions"] = capitalizeArray(sRepl.gl_expand(m).split("|")); + } else { + oErr["aSuggestions"] = sRepl.gl_expand(m).split("|"); + } + } + // Message + let sMessage = ""; + if (sMsg.slice(0,1) === "=") { + sMessage = oEvalFunc[sMsg.slice(1)](s, m); + } else { + sMessage = sMsg.gl_expand(m); + } + if (bIdRule) { + sMessage += " ##" + sLineId + " #" + sRuleId; + } + oErr["sMessage"] = sMessage; + // URL + oErr["URL"] = sURL || ""; + // Context + if (bContext) { + oErr["sUnderlined"] = sx.slice(m.start[iGroup], m.end[iGroup]); + oErr["sBefore"] = sx.slice(Math.max(0, m.start[iGroup]-80), m.start[iGroup]); + oErr["sAfter"] = sx.slice(m.end[iGroup], m.end[iGroup]+80); + } + return oErr; + }, + + _rewrite: function (s, sRepl, iGroup, m, bUppercase) { + // text processor: write sRepl in s at iGroup position" + let ln = m.end[iGroup] - m.start[iGroup]; + let sNew = ""; + if (sRepl === "*") { + sNew = " ".repeat(ln); + } else if (sRepl === ">" || sRepl === "_" || sRepl === "~") { + sNew = sRepl + " ".repeat(ln-1); + } else if (sRepl === "@") { + sNew = "@".repeat(ln); + } else if (sRepl.slice(0,1) === "=") { + sNew = oEvalFunc[sRepl.slice(1)](s, m); + sNew = sNew + " ".repeat(ln-sNew.length); + 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); + }, + + resetIgnoreRules: function () { + _aIgnoredRules.clear(); + }, + + reactivateRule: function (sRuleId) { + _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) { + if (!sFilter || sRuleId.test(sFilter)) { + yield [sOption, sLineId, sRuleId]; + } + } + } + for (let [sOption, lRuleGroup] of this._getRules(false)) { + for (let [,, sLineId, sRuleId,,] of lRuleGroup) { + if (!sFilter || sRuleId.test(sFilter)) { + yield [sOption, sLineId, sRuleId]; + } + } + } + } + catch (e) { + helpers.logerror(e); + } + }, + + _getRules: function (bParagraph) { + if (!bParagraph) { + return gc_rules.lSentenceRules; + } + return gc_rules.lParagraphRules; + }, + + //// Initialization + + load: function (sContext="JavaScript", sPath="") { + try { + if (typeof(require) !== 'undefined') { + var ibdawg = require("resource://grammalecte/ibdawg.js"); + _oDict = new ibdawg.IBDAWG("${dic_name}.json"); + } else { + _oDict = new IBDAWG("${dic_name}.json", sPath); + } + _sAppContext = sContext; + _dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default + } + catch (e) { + helpers.logerror(e); + } + }, + + getDictionary: function () { + return _oDict; + }, + + //// Options + + setOption: function (sOpt, bVal) { + if (_dOptions.has(sOpt)) { + _dOptions.set(sOpt, bVal); + } + }, + + setOptions: function (dOpt) { + _dOptions.gl_updateOnlyExistingKeys(dOpt); + }, + + getOptions: function () { + return _dOptions; + }, + + getDefaultOptions: function () { + return gc_options.getOptions(_sAppContext).gl_shallowCopy(); + }, + + resetOptions: function () { + _dOptions = gc_options.getOptions(_sAppContext).gl_shallowCopy(); + } +}; + + +//////// Common functions function option (sOpt) { // return true if option sOpt is active return _dOptions.get(sOpt); } function displayInfo (dDA, aWord) { // for debugging: info of word if (!aWord) { - echo("> nothing to find"); + helpers.echo("> nothing to find"); return true; } if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) { - echo("> not in FSA"); + helpers.echo("> not in FSA"); return true; } if (dDA.has(aWord[0])) { - echo("DA: " + dDA.get(aWord[0])); + helpers.echo("DA: " + dDA.get(aWord[0])); } - echo("FSA: " + _dAnalyses.get(aWord[1])); + helpers.echo("FSA: " + _dAnalyses.get(aWord[1])); return true; } function _storeMorphFromFSA (sWord) { // retrieves morphologies list from _oDict -> _dAnalyses - //echo("register: "+sWord + " " + _oDict.getMorph(sWord).toString()) + //helpers.echo("register: "+sWord + " " + _oDict.getMorph(sWord).toString()) _dAnalyses.set(sWord, _oDict.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) { - //echo("morph: noword, returns " + bNoWord); + //helpers.echo("morph: noword, returns " + bNoWord); return bNoWord; } - //echo("aWord: "+aWord.toString()); + //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]); - //echo("lMorph: "+lMorph.toString()); + //helpers.echo("lMorph: "+lMorph.toString()); if (lMorph.length === 0) { return false; } - //echo("***"); + //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) { - //echo("morph: noword, returns " + bNoWord); + //helpers.echo("morph: noword, returns " + bNoWord); return bNoWord; } - //echo("aWord: "+aWord.toString()); + //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]); - //echo("lMorph: "+lMorph.toString()); + //helpers.echo("lMorph: "+lMorph.toString()); if (lMorph.length === 0) { return false; } - //echo("***"); + //helpers.echo("***"); // check negative condition if (lMorph.some(s => (s.search(sNegPattern) !== -1))) { return false; } // search sPattern @@ -449,60 +470,56 @@ return []; } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return []; } - return [ for (s of _dAnalyses.get(sWord)) s.slice(1, s.indexOf(" ")) ]; + return _dAnalyses.get(sWord).map( s => s.slice(1, s.indexOf(" ")) ); } //// functions to get text outside pattern scope // warning: check compile_rules.py to understand how it works function nextword (s, iStart, n) { // get the nth word of the input string or empty string - let z = new RegExp("^( +[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+)", "i"); + let z = new RegExp("^(?: +[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+)", "ig"); let m = z.exec(s.slice(iStart)); if (!m) { return null; } - return [iStart + RegExp.lastIndex - m[2].length, m[2]]; + return [iStart + z.lastIndex - m[1].length, m[1]]; } function prevword (s, iEnd, n) { // get the (-)nth word of the input string or empty string - let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+) +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+ +){" + (n-1).toString() + "}$", "i"); + let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+ +){" + (n-1).toString() + "}$", "i"); let m = z.exec(s.slice(0, iEnd)); if (!m) { return null; } return [m.index, m[1]]; } -const _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*)", "i"); -const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*) +$", "i"); - function nextword1 (s, iStart) { // get next word (optimization) + let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*)", "ig"); let m = _zNextWord.exec(s.slice(iStart)); if (!m) { return null; } - return [iStart + RegExp.lastIndex - m[1].length, m[1]]; + return [iStart + _zNextWord.lastIndex - m[1].length, m[1]]; } + +const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*) +$", "i"); function prevword1 (s, iEnd) { // get previous word (optimization) - //echo("prev1, s:"+s); - //echo("prev1, s.slice(0, iEnd):"+s.slice(0, iEnd)); let m = _zPrevWord.exec(s.slice(0, iEnd)); - //echo("prev1, m:"+m); if (!m) { return null; } - //echo("prev1: " + m.index + " " + m[1]); return [m.index, m[1]]; } function look (s, zPattern, zNegPattern=null) { // seek zPattern in s (before/after/fulltext), if antipattern zNegPattern not in s @@ -549,16 +566,14 @@ return true; } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return true; } - //echo("morph: "+_dAnalyses.get(sWord).toString()); if (_dAnalyses.get(sWord).length === 1) { return true; } - let lSelect = [ for (sMorph of _dAnalyses.get(sWord)) if (sMorph.search(sPattern) !== -1) sMorph ]; - //echo("lSelect: "+lSelect.toString()); + let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) !== -1 ); if (lSelect.length > 0) { if (lSelect.length != _dAnalyses.get(sWord).length) { dDA.set(nPos, lSelect); } } else if (lDefault) { @@ -578,12 +593,11 @@ return true; } if (_dAnalyses.get(sWord).length === 1) { return true; } - let lSelect = [ for (sMorph of _dAnalyses.get(sWord)) if (sMorph.search(sPattern) === -1) sMorph ]; - //echo("lSelect: "+lSelect.toString()); + let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) === -1 ); if (lSelect.length > 0) { if (lSelect.length != _dAnalyses.get(sWord).length) { dDA.set(nPos, lSelect); } } else if (lDefault) { @@ -594,10 +608,11 @@ function define (dDA, nPos, lMorph) { dDA.set(nPos, lMorph); return true; } + //////// GRAMMAR CHECKER PLUGINS ${pluginsJS} @@ -605,20 +620,32 @@ ${callablesJS} if (typeof(exports) !== 'undefined') { - exports.load = load; - exports.parse = parse; - exports.lang = lang; - exports.version = version; - exports.getDictionary = getDictionary; - exports.setOption = setOption; - exports.setOptions = setOptions; - exports.getOptions = getOptions; - exports.getDefaultOptions = getDefaultOptions; - exports.resetOptions = resetOptions; - exports.ignoreRule = ignoreRule; - exports.reactivateRule = reactivateRule; - exports.resetIgnoreRules = resetIgnoreRules; - exports.listRules = listRules; + exports.lang = gc_engine.lang; + exports.locales = gc_engine.locales; + exports.pkg = gc_engine.pkg; + exports.name = gc_engine.name; + exports.version = gc_engine.version; + exports.author = gc_engine.author; + exports.parse = gc_engine.parse; + exports._zEndOfSentence = gc_engine._zEndOfSentence; + exports._zBeginOfParagraph = gc_engine._zBeginOfParagraph; + exports._zEndOfParagraph = gc_engine._zEndOfParagraph; + exports._getSentenceBoundaries = gc_engine._getSentenceBoundaries; + exports._proofread = gc_engine._proofread; + exports._createError = gc_engine._createError; + exports._rewrite = gc_engine._rewrite; + exports.ignoreRule = gc_engine.ignoreRule; + exports.resetIgnoreRules = gc_engine.resetIgnoreRules; + exports.reactivateRule = gc_engine.reactivateRule; + exports.listRules = gc_engine.listRules; + exports._getRules = gc_engine._getRules; + exports.load = gc_engine.load; + exports.getDictionary = gc_engine.getDictionary; + exports.setOption = gc_engine.setOption; + exports.setOptions = gc_engine.setOptions; + exports.getOptions = gc_engine.getOptions; + exports.getDefaultOptions = gc_engine.getDefaultOptions; + exports.resetOptions = gc_engine.resetOptions; } Index: gc_core/js/lang_core/gc_options.js ================================================================== --- gc_core/js/lang_core/gc_options.js +++ gc_core/js/lang_core/gc_options.js @@ -1,27 +1,31 @@ // Options for Grammalecte ${map} -function getOptions (sContext="JavaScript") { - if (dOpt.hasOwnProperty(sContext)) { - return dOpt[sContext]; - } - return dOpt["JavaScript"]; -} - -const lStructOpt = ${lStructOpt}; - -const dOpt = { - "JavaScript": new Map (${dOptJavaScript}), - "Firefox": new Map (${dOptFirefox}), - "Thunderbird": new Map (${dOptThunderbird}), -} - -const dOptLabel = ${dOptLabel}; + +var gc_options = { + getOptions: function (sContext="JavaScript") { + if (this.dOpt.hasOwnProperty(sContext)) { + return this.dOpt[sContext]; + } + return this.dOpt["JavaScript"]; + }, + + lStructOpt: ${lStructOpt}, + + dOpt: { + "JavaScript": new Map (${dOptJavaScript}), + "Firefox": new Map (${dOptFirefox}), + "Thunderbird": new Map (${dOptThunderbird}), + }, + + dOptLabel: ${dOptLabel} +} if (typeof(exports) !== 'undefined') { - exports.getOptions = getOptions; - exports.lStructOpt = lStructOpt; - exports.dOptLabel = dOptLabel; + exports.getOptions = gc_options.getOptions; + exports.lStructOpt = gc_options.lStructOpt; + exports.dOpt = gc_options.dOpt; + exports.dOptLabel = gc_options.dOptLabel; } Index: gc_core/js/lang_core/gc_rules.js ================================================================== --- gc_core/js/lang_core/gc_rules.js +++ gc_core/js/lang_core/gc_rules.js @@ -2,14 +2,16 @@ "use strict"; ${string} ${regex} -const lParagraphRules = ${paragraph_rules_JS}; +var gc_rules = { + lParagraphRules: ${paragraph_rules_JS}, -const lSentenceRules = ${sentence_rules_JS}; + lSentenceRules: ${sentence_rules_JS} +} if (typeof(exports) !== 'undefined') { - exports.lParagraphRules = lParagraphRules; - exports.lSentenceRules = lSentenceRules; + exports.lParagraphRules = gc_rules.lParagraphRules; + exports.lSentenceRules = gc_rules.lSentenceRules; } Index: gc_core/js/str_transform.js ================================================================== --- gc_core/js/str_transform.js +++ gc_core/js/str_transform.js @@ -1,60 +1,32 @@ //// STRING TRANSFORMATION -var dSimilarChars = new Map ([ - ["a", "aàâáä"], - ["à", "aàâáä"], - ["â", "aàâáä"], - ["á", "aàâáä"], - ["ä", "aàâáä"], - ["c", "cç"], - ["ç", "cç"], - ["e", "eéêèë"], - ["é", "eéêèë"], - ["ê", "eéêèë"], - ["è", "eéêèë"], - ["ë", "eéêèë"], - ["i", "iîïíì"], - ["î", "iîïíì"], - ["ï", "iîïíì"], - ["í", "iîïíì"], - ["ì", "iîïíì"], - ["o", "oôóòö"], - ["ô", "oôóòö"], - ["ó", "oôóòö"], - ["ò", "oôóòö"], - ["ö", "oôóòö"], - ["u", "uûùüú"], - ["û", "uûùüú"], - ["ù", "uûùüú"], - ["ü", "uûùüú"], - ["ú", "uûùüú"] -]); - // Note: 48 is the ASCII code for "0" -// Suffix only -function getStemFromSuffixCode (sFlex, sSfxCode) { - if (sSfxCode == "0") { - return sFlex; - } - return sSfxCode[0] == '0' ? sFlex + sSfxCode.slice(1) : sFlex.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1); -} - -// Prefix and suffix -function getStemFromAffixCode (sFlex, sAffCode) { - if (sAffCode == "0") { - return sFlex; - } - if (!sAffCode.includes("/")) { - return "# error #"; - } - var [sPfxCode, sSfxCode] = sAffCode.split('/'); - sFlex = sPfxCode.slice(1) + sFlex.slice(sPfxCode.charCodeAt(0)-48); - return sSfxCode[0] == '0' ? sFlex + sSfxCode.slice(1) : sFlex.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1); -} +var str_transform = { + getStemFromSuffixCode: function (sFlex, sSfxCode) { + // Suffix only + if (sSfxCode == "0") { + return sFlex; + } + return sSfxCode[0] == '0' ? sFlex + sSfxCode.slice(1) : sFlex.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1); + }, + + getStemFromAffixCode: function (sFlex, sAffCode) { + // Prefix and suffix + if (sAffCode == "0") { + return sFlex; + } + if (!sAffCode.includes("/")) { + return "# error #"; + } + let [sPfxCode, sSfxCode] = sAffCode.split('/'); + sFlex = sPfxCode.slice(1) + sFlex.slice(sPfxCode.charCodeAt(0)-48); + return sSfxCode[0] == '0' ? sFlex + sSfxCode.slice(1) : sFlex.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1); + } +}; if (typeof(exports) !== 'undefined') { - exports.getStemFromSuffixCode = getStemFromSuffixCode; - exports.getStemFromAffixCode = getStemFromAffixCode; + exports.getStemFromSuffixCode = str_transform.getStemFromSuffixCode; + exports.getStemFromAffixCode = str_transform.getStemFromAffixCode; } Index: gc_core/js/tests.js ================================================================== --- gc_core/js/tests.js +++ gc_core/js/tests.js @@ -1,26 +1,29 @@ // JavaScript "use strict"; -const helpers = require("resource://grammalecte/helpers.js"); +if (typeof(require) !== 'undefined') { + var helpers = require("resource://grammalecte/helpers.js"); +} class TestGrammarChecking { - constructor (gce) { + constructor (gce, spfTests="") { this.gce = gce; + this.spfTests = spfTests; this._aRuleTested = new Set(); - }; + } * testParse (bDebug=false) { const t0 = Date.now(); - const aData = JSON.parse(helpers.loadFile("resource://grammalecte/"+this.gce.lang+"/tests_data.json")).aData; - //const aData = require("resource://grammalecte/"+this.gce.lang+"/tests_data.js").aData; - let nInvalid = 0 - let nTotal = 0 + let sURL = (this.spfTests !== "") ? this.spfTests : "resource://grammalecte/"+this.gce.lang+"/tests_data.json"; + const aData = JSON.parse(helpers.loadFile(sURL)).aData; + let nInvalid = 0; + let nTotal = 0; let sErrorText; let sSugg; let sExpectedErrors; let sTextToCheck; let sFoundErrors; @@ -59,11 +62,11 @@ "\n# Line num: " + sLineNum + "\n> to check: " + sTextToCheck + "\n expected: " + sExpectedErrors + "\n found: " + sFoundErrors + "\n errors: \n" + sListErr; - nInvalid = nInvalid + 1 + nInvalid = nInvalid + 1; } nTotal = nTotal + 1; } i = i + 1; if (i % 1000 === 0) { @@ -76,11 +79,11 @@ helpers.logerror(e); } if (bShowUntested) { i = 0; - for (let [sOpt, sLineId, sRuleId] of gce.listRules()) { + for (let [sOpt, sLineId, sRuleId] of this.gce.listRules()) { if (!this._aRuleTested.has(sLineId) && !/^[0-9]+[sp]$|^[pd]_/.test(sRuleId)) { sUntestedRules += sRuleId + ", "; i += 1; } } @@ -90,11 +93,11 @@ } const t1 = Date.now(); yield "Tests parse finished in " + ((t1-t0)/1000).toString() + " s\nTotal errors: " + nInvalid.toString() + " / " + nTotal.toString(); - }; + } _getExpectedErrors (sLine) { try { let sRes = " ".repeat(sLine.length); let z = /\{\{.+?\}\}/g; @@ -116,19 +119,19 @@ } catch (e) { helpers.logerror(e); } return " ".repeat(sLine.length); - }; + } _getFoundErrors (sLine, bDebug, sOption) { try { let aErrs = []; if (sOption) { - gce.setOption(sOption, true); + this.gce.setOption(sOption, true); aErrs = this.gce.parse(sLine, "FR", bDebug); - gce.setOption(sOption, false); + this.gce.setOption(sOption, false); } else { aErrs = this.gce.parse(sLine, "FR", bDebug); } let sRes = " ".repeat(sLine.length); let sListErr = ""; @@ -141,13 +144,13 @@ } catch (e) { helpers.logerror(e); } return [" ".repeat(sLine.length), ""]; - }; + } } if (typeof(exports) !== 'undefined') { exports.TestGrammarChecking = TestGrammarChecking; } Index: gc_core/js/text.js ================================================================== --- gc_core/js/text.js +++ gc_core/js/text.js @@ -1,64 +1,69 @@ // JavaScript "use strict"; -const helpers = require("resource://grammalecte/helpers.js"); - - -function* getParagraph (sText) { - // generator: returns paragraphs of text - let iStart = 0; - let iEnd = 0; - sText = sText.replace("\r", ""); - while ((iEnd = sText.indexOf("\n", iStart)) !== -1) { - yield sText.slice(iStart, iEnd); - iStart = iEnd + 1; - } - yield sText.slice(iStart); -} - -function* wrap (sText, nWidth=80) { - // generator: returns text line by line - while (sText) { - if (sText.length >= nWidth) { - let nEnd = sText.lastIndexOf(" ", nWidth) + 1; - if (nEnd > 0) { - yield sText.slice(0, nEnd); - sText = sText.slice(nEnd); - } else { - yield sText.slice(0, nWidth); - sText = sText.slice(nWidth); - } - } else { - break; - } - } - yield sText; -} - -function getReadableError (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"]; - } - return sResult; - } - catch (e) { - helpers.logerror(e); - return "\n# Error. Data: " + oErr.toString(); - } -} + +if (typeof(exports) !== 'undefined') { + var helpers = require("resource://grammalecte/helpers.js"); +} + + +var text = { + getParagraph: function* (sText) { + // generator: returns paragraphs of text + let iStart = 0; + let iEnd = 0; + sText = sText.replace("\r", ""); + while ((iEnd = sText.indexOf("\n", iStart)) !== -1) { + yield sText.slice(iStart, iEnd); + iStart = iEnd + 1; + } + yield sText.slice(iStart); + }, + + wrap: function* (sText, nWidth=80) { + // generator: returns text line by line + while (sText) { + if (sText.length >= nWidth) { + let nEnd = sText.lastIndexOf(" ", nWidth) + 1; + if (nEnd > 0) { + yield sText.slice(0, nEnd); + sText = sText.slice(nEnd); + } else { + yield sText.slice(0, nWidth); + sText = sText.slice(nWidth); + } + } else { + break; + } + } + 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"]; + } + return sResult; + } + catch (e) { + helpers.logerror(e); + return "\n# Error. Data: " + oErr.toString(); + } + } +}; if (typeof(exports) !== 'undefined') { - exports.getParagraph = getParagraph; - exports.wrap = wrap; - exports.getReadableError = getReadableError; + exports.getParagraph = text.getParagraph; + exports.wrap = text.wrap; + exports.getReadableError = text.getReadableError; } Index: gc_core/js/tokenizer.js ================================================================== --- gc_core/js/tokenizer.js +++ gc_core/js/tokenizer.js @@ -1,13 +1,17 @@ // JavaScript // Very simple tokenizer "use strict"; -const helpers = require("resource://grammalecte/helpers.js"); + +if (typeof(exports) !== 'undefined') { + var helpers = require("resource://grammalecte/helpers.js"); +} + -const aPatterns = { +const aTkzPatterns = { // All regexps must start with ^. "default": [ [/^[   \t]+/, 'SPACE'], [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'], @@ -33,22 +37,22 @@ [/^\d\d?[hm]\d\d\b/, 'HOUR'], [/^\d+(?:er|nd|e|de|ième|ème|eme)s?\b/, 'ORDINAL'], [/^-?\d+(?:[.,]\d+|)/, 'NUM'], [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+)*/, 'WORD'] ] -} +}; class Tokenizer { constructor (sLang) { this.sLang = sLang; - if (!aPatterns.hasOwnProperty(sLang)) { + if (!aTkzPatterns.hasOwnProperty(sLang)) { this.sLang = "default"; } - this.aRules = aPatterns[this.sLang]; - }; + this.aRules = aTkzPatterns[this.sLang]; + } * genTokens (sText) { let m; let i = 0; while (sText) { @@ -72,11 +76,11 @@ } } i += nCut; sText = sText.slice(nCut); } - }; + } getSpellingErrors (sText, oDict) { let aSpellErr = []; for (let oToken of this.genTokens(sText)) { if (oToken.sType === 'WORD' && !oDict.isValidToken(oToken.sValue)) { Index: gc_core/py/lang_core/gc_engine.py ================================================================== --- gc_core/py/lang_core/gc_engine.py +++ gc_core/py/lang_core/gc_engine.py @@ -472,19 +472,19 @@ # warning: check compile_rules.py to understand how it works def nextword (s, iStart, n): "get the nth word of the input string or empty string" - m = re.match("( +[\\w%-]+){" + str(n-1) + "} +([\\w%-]+)", s[iStart:]) + m = re.match("(?: +[\\w%-]+){" + str(n-1) + "} +([\\w%-]+)", s[iStart:]) if not m: return None - return (iStart+m.start(2), m.group(2)) + return (iStart+m.start(1), m.group(1)) def prevword (s, iEnd, n): "get the (-)nth word of the input string or empty string" - m = re.search("([\\w%-]+) +([\\w%-]+ +){" + str(n-1) + "}$", s[:iEnd]) + m = re.search("([\\w%-]+) +(?:[\\w%-]+ +){" + str(n-1) + "}$", s[:iEnd]) if not m: return None return (m.start(1), m.group(1)) Index: gc_lang/fr/config.ini ================================================================== --- gc_lang/fr/config.ini +++ gc_lang/fr/config.ini @@ -30,11 +30,11 @@ # Firefox fx_identifier = French-GC@grammalecte.net fx_name = Grammalecte [fr] fx_standard_path = C:\Program Files\Mozilla Firefox\firefox.exe -fx_beta_path = C:\Program Files\Mozilla Firefox Beta\firefox.exe +fx_dev_path = C:\Program Files\Firefox Developer Edition\firefox.exe fx_nightly_path = C:\Program Files (x86)\Nightly\firefox.exe # Thunderbird tb_identifier = French-GC-TB@grammalecte.net Index: gc_lang/fr/modules-js/conj.js ================================================================== --- gc_lang/fr/modules-js/conj.js +++ gc_lang/fr/modules-js/conj.js @@ -4,187 +4,175 @@ "use strict"; ${map} -let helpers = null; // module not loaded in Firefox content script - -let _oData = {}; -let _lVtyp = null; -let _lTags = null; -let _dPatternConj = {}; -let _dVerb = {}; - - -if (typeof(exports) !== 'undefined') { - // used within Grammalecte library - helpers = require("resource://grammalecte/helpers.js"); - _oData = JSON.parse(helpers.loadFile("resource://grammalecte/fr/conj_data.json")); - _lVtyp = _oData.lVtyp; - _lTags = _oData.lTags; - _dPatternConj = _oData.dPatternConj; - _dVerb = _oData.dVerb; -} else { - // used within Firefox content script (conjugation panel). - // can’t load JSON from here, so we do it in ui.js and send it here. - self.port.on("provideConjData", function (sData) { - _oData = JSON.parse(sData); - _lVtyp = _oData.lVtyp; - _lTags = _oData.lTags; - _dPatternConj = _oData.dPatternConj; - _dVerb = _oData.dVerb; - }); -} - - -const _zStartVoy = new RegExp("^[aeéiouœê]"); -const _zNeedTeuph = new RegExp("[tdc]$"); - -const _dProSuj = new Map ([ [":1s", "je"], [":1ś", "je"], [":2s", "tu"], [":3s", "il"], [":1p", "nous"], [":2p", "vous"], [":3p", "ils"] ]); -const _dProObj = new Map ([ [":1s", "me "], [":1ś", "me "], [":2s", "te "], [":3s", "se "], [":1p", "nous "], [":2p", "vous "], [":3p", "se "] ]); -const _dProObjEl = new Map ([ [":1s", "m’"], [":1ś", "m’"], [":2s", "t’"], [":3s", "s’"], [":1p", "nous "], [":2p", "vous "], [":3p", "s’"] ]); -const _dImpePro = new Map ([ [":2s", "-toi"], [":1p", "-nous"], [":2p", "-vous"] ]); -const _dImpeProNeg = new Map ([ [":2s", "ne te "], [":1p", "ne nous "], [":2p", "ne vous "] ]); -const _dImpeProEn = new Map ([ [":2s", "-t’en"], [":1p", "-nous-en"], [":2p", "-vous-en"] ]); -const _dImpeProNegEn = new Map ([ [":2s", "ne t’en "], [":1p", "ne nous en "], [":2p", "ne vous en "] ]); - -const _dGroup = new Map ([ ["0", "auxiliaire"], ["1", "1ᵉʳ groupe"], ["2", "2ᵉ groupe"], ["3", "3ᵉ groupe"] ]); - -const _dTenseIdx = new Map ([ [":PQ", 0], [":Ip", 1], [":Iq", 2], [":Is", 3], [":If", 4], [":K", 5], [":Sp", 6], [":Sq", 7], [":E", 8] ]); - - -function isVerb (sVerb) { - return _dVerb.hasOwnProperty(sVerb); -} - -function getConj (sVerb, sTense, sWho) { - // returns conjugation (can be an empty string) - if (!_dVerb.hasOwnProperty(sVerb)) { - return null; - } - if (!_dPatternConj[sTense][_lTags[_dVerb[sVerb][1]][_dTenseIdx.get(sTense)]].hasOwnProperty(sWho)) { - return ""; - } - return _modifyStringWithSuffixCode(sVerb, _dPatternConj[sTense][_lTags[_dVerb[sVerb][1]][_dTenseIdx.get(sTense)]][sWho]); -} - -function hasConj (sVerb, sTense, sWho) { - // returns false if no conjugation (also if empty) else true - if (!_dVerb.hasOwnProperty(sVerb)) { - return false; - } - if (_dPatternConj[sTense][_lTags[_dVerb[sVerb][1]][_dTenseIdx.get(sTense)]].hasOwnProperty(sWho) - && _dPatternConj[sTense][_lTags[_dVerb[sVerb][1]][_dTenseIdx.get(sTense)]][sWho]) { - return true; - } - return false; -} - -function getVtyp (sVerb) { - // returns raw informations about sVerb - if (!_dVerb.hasOwnProperty(sVerb)) { - return null; - } - return _lVtyp[_dVerb[sVerb][0]]; -} - -function getSimil (sWord, sMorph, sFilter=null) { - if (!sMorph.includes(":V")) { - return new Set(); - } - let sInfi = sMorph.slice(1, sMorph.indexOf(" ")); - let tTags = _getTags(sInfi); - let aSugg = new Set(); - if (sMorph.includes(":Q") || sMorph.includes(":Y")) { - // we suggest conjugated forms - if (sMorph.includes(":V1")) { - aSugg.add(sInfi); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Ip", ":3s")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Ip", ":2p")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Iq", ":1s")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Iq", ":3s")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Iq", ":3p")); - } else if (sMorph.includes(":V2")) { - aSugg.add(_getConjWithTags(sInfi, tTags, ":Ip", ":1s")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Ip", ":3s")); - } else if (sMorph.includes(":V3")) { - aSugg.add(_getConjWithTags(sInfi, tTags, ":Ip", ":1s")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Ip", ":3s")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Is", ":1s")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":Is", ":3s")); - } else if (isMorph.includes(":V0a")) { - aSugg.add("eus"); - aSugg.add("eut"); - } else { - aSugg.add("étais"); - aSugg.add("était"); - } - aSugg.delete(""); - } else { - // we suggest past participles - aSugg.add(_getConjWithTags(sInfi, tTags, ":PQ", ":Q1")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":PQ", ":Q2")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":PQ", ":Q3")); - aSugg.add(_getConjWithTags(sInfi, tTags, ":PQ", ":Q4")); - aSugg.delete(""); - // if there is only one past participle (epi inv), unreliable. - if (aSugg.size === 1) { - aSugg.clear(); - } - if (sMorph.includes(":V1")) { - aSugg.add(sInfi); - } - } - return aSugg; -} - - -function _getTags (sVerb) { - // returns tuple of tags (usable with functions _getConjWithTags and _hasConjWithTags) - if (!_dVerb.hasOwnProperty(sVerb)) { - return null; - } - return _lTags[_dVerb[sVerb][1]]; -} - -function _getConjWithTags (sVerb, tTags, sTense, sWho) { - // returns conjugation (can be an empty string) - if (!_dPatternConj[sTense][tTags[_dTenseIdx.get(sTense)]].hasOwnProperty(sWho)) { - return ""; - } - return _modifyStringWithSuffixCode(sVerb, _dPatternConj[sTense][tTags[_dTenseIdx.get(sTense)]][sWho]); -} - -function _hasConjWithTags (tTags, sTense, sWho) { - // returns false if no conjugation (also if empty) else true - if (_dPatternConj[sTense][tTags[_dTenseIdx.get(sTense)]].hasOwnProperty(sWho) - && _dPatternConj[sTense][tTags[_dTenseIdx.get(sTense)]][sWho]) { - return true; - } - return false; -} - -function _modifyStringWithSuffixCode (sWord, sSfx) { - // returns sWord modified by sSfx - if (sSfx === "") { - return ""; - } - if (sSfx === "0") { - return sWord; - } - try { - if (sSfx[0] !== '0') { - return sWord.slice(0, -(sSfx.charCodeAt(0)-48)) + sSfx.slice(1); // 48 is the ASCII code for "0" - } else { - return sWord + sSfx.slice(1); - } - } - catch (e) { - console.log(e); - return "## erreur, code : " + sSfx + " ##"; - } -} +var conj = { + _lVtyp: [], + _lTags: [], + _dPatternConj: {}, + _dVerb: {}, + + init: function (sJSONData) { + try { + let _oData = JSON.parse(sJSONData); + this._lVtyp = _oData.lVtyp; + this._lTags = _oData.lTags; + this._dPatternConj = _oData.dPatternConj; + this._dVerb = _oData.dVerb; + } + catch (e) { + console.error(e); + } + }, + + _zStartVoy: new RegExp("^[aeéiouœê]"), + _zNeedTeuph: new RegExp("[tdc]$"), + + _dProSuj: new Map ([ [":1s", "je"], [":1ś", "je"], [":2s", "tu"], [":3s", "il"], [":1p", "nous"], [":2p", "vous"], [":3p", "ils"] ]), + _dProObj: new Map ([ [":1s", "me "], [":1ś", "me "], [":2s", "te "], [":3s", "se "], [":1p", "nous "], [":2p", "vous "], [":3p", "se "] ]), + _dProObjEl: new Map ([ [":1s", "m’"], [":1ś", "m’"], [":2s", "t’"], [":3s", "s’"], [":1p", "nous "], [":2p", "vous "], [":3p", "s’"] ]), + _dImpePro: new Map ([ [":2s", "-toi"], [":1p", "-nous"], [":2p", "-vous"] ]), + _dImpeProNeg: new Map ([ [":2s", "ne te "], [":1p", "ne nous "], [":2p", "ne vous "] ]), + _dImpeProEn: new Map ([ [":2s", "-t’en"], [":1p", "-nous-en"], [":2p", "-vous-en"] ]), + _dImpeProNegEn: new Map ([ [":2s", "ne t’en "], [":1p", "ne nous en "], [":2p", "ne vous en "] ]), + + _dGroup: new Map ([ ["0", "auxiliaire"], ["1", "1ᵉʳ groupe"], ["2", "2ᵉ groupe"], ["3", "3ᵉ groupe"] ]), + + _dTenseIdx: new Map ([ [":PQ", 0], [":Ip", 1], [":Iq", 2], [":Is", 3], [":If", 4], [":K", 5], [":Sp", 6], [":Sq", 7], [":E", 8] ]), + + isVerb: function (sVerb) { + return this._dVerb.hasOwnProperty(sVerb); + }, + + getConj: function (sVerb, sTense, sWho) { + // returns conjugation (can be an empty string) + if (!this._dVerb.hasOwnProperty(sVerb)) { + return null; + } + if (!this._dPatternConj[sTense][this._lTags[this._dVerb[sVerb][1]][this._dTenseIdx.get(sTense)]].hasOwnProperty(sWho)) { + return ""; + } + return this._modifyStringWithSuffixCode(sVerb, this._dPatternConj[sTense][this._lTags[this._dVerb[sVerb][1]][this._dTenseIdx.get(sTense)]][sWho]); + }, + + hasConj: function (sVerb, sTense, sWho) { + // returns false if no conjugation (also if empty) else true + if (!this._dVerb.hasOwnProperty(sVerb)) { + return false; + } + if (this._dPatternConj[sTense][this._lTags[this._dVerb[sVerb][1]][this._dTenseIdx.get(sTense)]].hasOwnProperty(sWho) + && this._dPatternConj[sTense][this._lTags[this._dVerb[sVerb][1]][this._dTenseIdx.get(sTense)]][sWho]) { + return true; + } + return false; + }, + + getVtyp: function (sVerb) { + // returns raw informations about sVerb + if (!this._dVerb.hasOwnProperty(sVerb)) { + return null; + } + return this._lVtyp[this._dVerb[sVerb][0]]; + }, + + getSimil: function (sWord, sMorph, sFilter=null) { + if (!sMorph.includes(":V")) { + return new Set(); + } + let sInfi = sMorph.slice(1, sMorph.indexOf(" ")); + let tTags = this._getTags(sInfi); + let aSugg = new Set(); + if (sMorph.includes(":Q") || sMorph.includes(":Y")) { + // we suggest conjugated forms + if (sMorph.includes(":V1")) { + aSugg.add(sInfi); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Ip", ":3s")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Ip", ":2p")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Iq", ":1s")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Iq", ":3s")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Iq", ":3p")); + } else if (sMorph.includes(":V2")) { + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Ip", ":1s")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Ip", ":3s")); + } else if (sMorph.includes(":V3")) { + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Ip", ":1s")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Ip", ":3s")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Is", ":1s")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":Is", ":3s")); + } else if (sMorph.includes(":V0a")) { + aSugg.add("eus"); + aSugg.add("eut"); + } else { + aSugg.add("étais"); + aSugg.add("était"); + } + aSugg.delete(""); + } else { + // we suggest past participles + aSugg.add(this._getConjWithTags(sInfi, tTags, ":PQ", ":Q1")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":PQ", ":Q2")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":PQ", ":Q3")); + aSugg.add(this._getConjWithTags(sInfi, tTags, ":PQ", ":Q4")); + aSugg.delete(""); + // if there is only one past participle (epi inv), unreliable. + if (aSugg.size === 1) { + aSugg.clear(); + } + if (sMorph.includes(":V1")) { + aSugg.add(sInfi); + } + } + return aSugg; + }, + + _getTags: function (sVerb) { + // returns tuple of tags (usable with functions _getConjWithTags and _hasConjWithTags) + if (!this._dVerb.hasOwnProperty(sVerb)) { + return null; + } + return this._lTags[this._dVerb[sVerb][1]]; + }, + + _getConjWithTags: function (sVerb, tTags, sTense, sWho) { + // returns conjugation (can be an empty string) + if (!this._dPatternConj[sTense][tTags[this._dTenseIdx.get(sTense)]].hasOwnProperty(sWho)) { + return ""; + } + return this._modifyStringWithSuffixCode(sVerb, this._dPatternConj[sTense][tTags[this._dTenseIdx.get(sTense)]][sWho]); + }, + + _hasConjWithTags: function (tTags, sTense, sWho) { + // returns false if no conjugation (also if empty) else true + if (this._dPatternConj[sTense][tTags[this._dTenseIdx.get(sTense)]].hasOwnProperty(sWho) + && this._dPatternConj[sTense][tTags[this._dTenseIdx.get(sTense)]][sWho]) { + return true; + } + return false; + }, + + _modifyStringWithSuffixCode: function (sWord, sSfx) { + // returns sWord modified by sSfx + if (sSfx === "") { + return ""; + } + if (sSfx === "0") { + return sWord; + } + try { + if (sSfx[0] !== '0') { + return sWord.slice(0, -(sSfx.charCodeAt(0)-48)) + sSfx.slice(1); // 48 is the ASCII code for "0" + } else { + return sWord + sSfx.slice(1); + } + } + catch (e) { + console.log(e); + return "## erreur, code : " + sSfx + " ##"; + } + } +}; class Verb { constructor (sVerb) { @@ -191,107 +179,107 @@ if (typeof sVerb !== "string" || sVerb === "") { throw new TypeError ("The value should be a non-empty string"); } this.sVerb = sVerb; this.sVerbAux = ""; - this._sRawInfo = getVtyp(this.sVerb); + this._sRawInfo = conj.getVtyp(this.sVerb); this.sInfo = this._readableInfo(this._sRawInfo); - this._tTags = _getTags(sVerb); - this._tTagsAux = _getTags(this.sVerbAux); + this._tTags = conj._getTags(sVerb); + this._tTagsAux = conj._getTags(this.sVerbAux); this.bProWithEn = (this._sRawInfo[5] === "e"); this.dConj = new Map ([ [":Y", new Map ([ ["label", "Infinitif"], [":Y", sVerb] ])], [":PQ", new Map ([ ["label", "Participes passés et présent"], - [":Q1", _getConjWithTags(sVerb, this._tTags, ":PQ", ":Q1")], - [":Q2", _getConjWithTags(sVerb, this._tTags, ":PQ", ":Q2")], - [":Q3", _getConjWithTags(sVerb, this._tTags, ":PQ", ":Q3")], - [":Q4", _getConjWithTags(sVerb, this._tTags, ":PQ", ":Q4")], - [":P", _getConjWithTags(sVerb, this._tTags, ":PQ", ":P")] + [":Q1", conj._getConjWithTags(sVerb, this._tTags, ":PQ", ":Q1")], + [":Q2", conj._getConjWithTags(sVerb, this._tTags, ":PQ", ":Q2")], + [":Q3", conj._getConjWithTags(sVerb, this._tTags, ":PQ", ":Q3")], + [":Q4", conj._getConjWithTags(sVerb, this._tTags, ":PQ", ":Q4")], + [":P", conj._getConjWithTags(sVerb, this._tTags, ":PQ", ":P")] ])], [":Ip", new Map ([ ["label", "Présent"], - [":1s", _getConjWithTags(sVerb, this._tTags, ":Ip", ":1s")], - [":1ś", _getConjWithTags(sVerb, this._tTags, ":Ip", ":1ś")], - [":2s", _getConjWithTags(sVerb, this._tTags, ":Ip", ":2s")], - [":3s", _getConjWithTags(sVerb, this._tTags, ":Ip", ":3s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":Ip", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":Ip", ":2p")], - [":3p", _getConjWithTags(sVerb, this._tTags, ":Ip", ":3p")] + [":1s", conj._getConjWithTags(sVerb, this._tTags, ":Ip", ":1s")], + [":1ś", conj._getConjWithTags(sVerb, this._tTags, ":Ip", ":1ś")], + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":Ip", ":2s")], + [":3s", conj._getConjWithTags(sVerb, this._tTags, ":Ip", ":3s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":Ip", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":Ip", ":2p")], + [":3p", conj._getConjWithTags(sVerb, this._tTags, ":Ip", ":3p")] ])], [":Iq", new Map ([ ["label", "Imparfait"], - [":1s", _getConjWithTags(sVerb, this._tTags, ":Iq", ":1s")], - [":2s", _getConjWithTags(sVerb, this._tTags, ":Iq", ":2s")], - [":3s", _getConjWithTags(sVerb, this._tTags, ":Iq", ":3s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":Iq", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":Iq", ":2p")], - [":3p", _getConjWithTags(sVerb, this._tTags, ":Iq", ":3p")] + [":1s", conj._getConjWithTags(sVerb, this._tTags, ":Iq", ":1s")], + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":Iq", ":2s")], + [":3s", conj._getConjWithTags(sVerb, this._tTags, ":Iq", ":3s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":Iq", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":Iq", ":2p")], + [":3p", conj._getConjWithTags(sVerb, this._tTags, ":Iq", ":3p")] ])], [":Is", new Map ([ ["label", "Passé simple"], - [":1s", _getConjWithTags(sVerb, this._tTags, ":Is", ":1s")], - [":2s", _getConjWithTags(sVerb, this._tTags, ":Is", ":2s")], - [":3s", _getConjWithTags(sVerb, this._tTags, ":Is", ":3s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":Is", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":Is", ":2p")], - [":3p", _getConjWithTags(sVerb, this._tTags, ":Is", ":3p")] + [":1s", conj._getConjWithTags(sVerb, this._tTags, ":Is", ":1s")], + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":Is", ":2s")], + [":3s", conj._getConjWithTags(sVerb, this._tTags, ":Is", ":3s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":Is", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":Is", ":2p")], + [":3p", conj._getConjWithTags(sVerb, this._tTags, ":Is", ":3p")] ])], [":If", new Map ([ ["label", "Futur"], - [":1s", _getConjWithTags(sVerb, this._tTags, ":If", ":1s")], - [":2s", _getConjWithTags(sVerb, this._tTags, ":If", ":2s")], - [":3s", _getConjWithTags(sVerb, this._tTags, ":If", ":3s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":If", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":If", ":2p")], - [":3p", _getConjWithTags(sVerb, this._tTags, ":If", ":3p")] + [":1s", conj._getConjWithTags(sVerb, this._tTags, ":If", ":1s")], + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":If", ":2s")], + [":3s", conj._getConjWithTags(sVerb, this._tTags, ":If", ":3s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":If", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":If", ":2p")], + [":3p", conj._getConjWithTags(sVerb, this._tTags, ":If", ":3p")] ])], [":Sp", new Map ([ ["label", "Présent subjonctif"], - [":1s", _getConjWithTags(sVerb, this._tTags, ":Sp", ":1s")], - [":1ś", _getConjWithTags(sVerb, this._tTags, ":Sp", ":1ś")], - [":2s", _getConjWithTags(sVerb, this._tTags, ":Sp", ":2s")], - [":3s", _getConjWithTags(sVerb, this._tTags, ":Sp", ":3s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":Sp", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":Sp", ":2p")], - [":3p", _getConjWithTags(sVerb, this._tTags, ":Sp", ":3p")] + [":1s", conj._getConjWithTags(sVerb, this._tTags, ":Sp", ":1s")], + [":1ś", conj._getConjWithTags(sVerb, this._tTags, ":Sp", ":1ś")], + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":Sp", ":2s")], + [":3s", conj._getConjWithTags(sVerb, this._tTags, ":Sp", ":3s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":Sp", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":Sp", ":2p")], + [":3p", conj._getConjWithTags(sVerb, this._tTags, ":Sp", ":3p")] ])], [":Sq", new Map ([ ["label", "Imparfait subjonctif"], - [":1s", _getConjWithTags(sVerb, this._tTags, ":Sq", ":1s")], - [":1ś", _getConjWithTags(sVerb, this._tTags, ":Sq", ":1ś")], - [":2s", _getConjWithTags(sVerb, this._tTags, ":Sq", ":2s")], - [":3s", _getConjWithTags(sVerb, this._tTags, ":Sq", ":3s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":Sq", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":Sq", ":2p")], - [":3p", _getConjWithTags(sVerb, this._tTags, ":Sq", ":3p")] + [":1s", conj._getConjWithTags(sVerb, this._tTags, ":Sq", ":1s")], + [":1ś", conj._getConjWithTags(sVerb, this._tTags, ":Sq", ":1ś")], + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":Sq", ":2s")], + [":3s", conj._getConjWithTags(sVerb, this._tTags, ":Sq", ":3s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":Sq", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":Sq", ":2p")], + [":3p", conj._getConjWithTags(sVerb, this._tTags, ":Sq", ":3p")] ])], [":K", new Map ([ ["label", "Conditionnel"], - [":1s", _getConjWithTags(sVerb, this._tTags, ":K", ":1s")], - [":2s", _getConjWithTags(sVerb, this._tTags, ":K", ":2s")], - [":3s", _getConjWithTags(sVerb, this._tTags, ":K", ":3s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":K", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":K", ":2p")], - [":3p", _getConjWithTags(sVerb, this._tTags, ":K", ":3p")] + [":1s", conj._getConjWithTags(sVerb, this._tTags, ":K", ":1s")], + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":K", ":2s")], + [":3s", conj._getConjWithTags(sVerb, this._tTags, ":K", ":3s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":K", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":K", ":2p")], + [":3p", conj._getConjWithTags(sVerb, this._tTags, ":K", ":3p")] ])], [":E", new Map ([ ["label", "Impératif"], - [":2s", _getConjWithTags(sVerb, this._tTags, ":E", ":2s")], - [":1p", _getConjWithTags(sVerb, this._tTags, ":E", ":1p")], - [":2p", _getConjWithTags(sVerb, this._tTags, ":E", ":2p")] + [":2s", conj._getConjWithTags(sVerb, this._tTags, ":E", ":2s")], + [":1p", conj._getConjWithTags(sVerb, this._tTags, ":E", ":1p")], + [":2p", conj._getConjWithTags(sVerb, this._tTags, ":E", ":2p")] ])] ]); - }; + } _readableInfo () { // returns readable infos this.sVerbAux = (this._sRawInfo.slice(7,8) == "e") ? "être" : "avoir"; - let sGroup = _dGroup.get(this._sRawInfo[0]); + let sGroup = conj._dGroup.get(this._sRawInfo[0]); let sInfo = ""; if (this._sRawInfo.slice(3,4) == "t") { sInfo = "transitif"; } else if (this._sRawInfo.slice(4,5) == "n") { sInfo = "transitif indirect"; @@ -310,11 +298,11 @@ } if (sInfo === "") { sInfo = "# erreur - code : " + this._sRawInfo; } return sGroup + " · " + sInfo; - }; + } infinitif (bPro, bNeg, bTpsCo, bInt, bFem) { let sInfi; if (bTpsCo) { sInfi = (bPro) ? "être" : this.sVerbAux; @@ -323,11 +311,11 @@ } if (bPro) { if (this.bProWithEn) { sInfi = "s’en " + sInfi; } else { - sInfi = (_zStartVoy.test(sInfi)) ? "s’" + sInfi : "se " + sInfi; + sInfi = (conj._zStartVoy.test(sInfi)) ? "s’" + sInfi : "se " + sInfi; } } if (bNeg) { sInfi = "ne pas " + sInfi; } @@ -336,30 +324,30 @@ } if (bInt) { sInfi += " … ?"; } return sInfi; - }; + } participePasse (sWho) { return this.dConj.get(":PQ").get(sWho); - }; + } participePresent (bPro, bNeg, bTpsCo, bInt, bFem) { if (!this.dConj.get(":PQ").get(":P")) { return ""; } let sPartPre; if (bTpsCo) { - sPartPre = (!bPro) ? _getConjWithTags(this.sVerbAux, this._tTagsAux, ":PQ", ":P") : getConj("être", ":PQ", ":P"); + sPartPre = (!bPro) ? conj._getConjWithTags(this.sVerbAux, this._tTagsAux, ":PQ", ":P") : conj.getConj("être", ":PQ", ":P"); } else { sPartPre = this.dConj.get(":PQ").get(":P"); } if (sPartPre === "") { return ""; } - let bEli = _zStartVoy.test(sPartPre); + let bEli = conj._zStartVoy.test(sPartPre); if (bPro) { if (this.bProWithEn) { sPartPre = "s’en " + sPartPre; } else { sPartPre = (bEli) ? "s’" + sPartPre : "se " + sPartPre; @@ -373,11 +361,11 @@ } if (bInt) { sPartPre += " … ?"; } return sPartPre; - }; + } conjugue (sTemps, sWho, bPro, bNeg, bTpsCo, bInt, bFem) { if (!this.dConj.get(sTemps).get(sWho)) { return ""; } @@ -384,30 +372,30 @@ let sConj; if (!bTpsCo && bInt && sWho == ":1s" && this.dConj.get(sTemps).gl_get(":1ś", false)) { sWho = ":1ś"; } if (bTpsCo) { - sConj = (!bPro) ? _getConjWithTags(this.sVerbAux, this._tTagsAux, sTemps, sWho) : getConj("être", sTemps, sWho); + sConj = (!bPro) ? conj._getConjWithTags(this.sVerbAux, this._tTagsAux, sTemps, sWho) : conj.getConj("être", sTemps, sWho); } else { sConj = this.dConj.get(sTemps).get(sWho); } if (sConj === "") { return ""; } - let bEli = _zStartVoy.test(sConj); + let bEli = conj._zStartVoy.test(sConj); if (bPro) { if (!this.bProWithEn) { - sConj = (bEli) ? _dProObjEl.get(sWho) + sConj : _dProObj.get(sWho) + sConj; + sConj = (bEli) ? conj._dProObjEl.get(sWho) + sConj : conj._dProObj.get(sWho) + sConj; } else { - sConj = _dProObjEl.get(sWho) + "en " + sConj; + sConj = conj._dProObjEl.get(sWho) + "en " + sConj; } } if (bNeg) { sConj = (bEli && !bPro) ? "n’" + sConj : "ne " + sConj; } if (bInt) { - if (sWho == ":3s" && !_zNeedTeuph.test(sConj)) { + if (sWho == ":3s" && !conj._zNeedTeuph.test(sConj)) { sConj += "-t"; } sConj += "-" + this._getPronom(sWho, bFem); } else { if (sWho == ":1s" && bEli && !bNeg && !bPro) { @@ -424,11 +412,11 @@ } if (bInt) { sConj += " … ?"; } return sConj; - }; + } _getPronom (sWho, bFem) { if (sWho == ":3s") { if (this._sRawInfo[5] == "r") { return "on"; @@ -436,45 +424,45 @@ return "elle"; } } else if (sWho == ":3p" && bFem) { return "elles"; } - return _dProSuj.get(sWho); - }; + return conj._dProSuj.get(sWho); + } imperatif (sWho, bPro, bNeg, bTpsCo, bFem) { if (!this.dConj.get(":E").get(sWho)) { return ""; } let sImpe; if (bTpsCo) { - sImpe = (!bPro) ? _getConjWithTags(this.sVerbAux, this._tTagsAux, ":E", sWho) : getConj("être", ":E", sWho); + sImpe = (!bPro) ? conj._getConjWithTags(this.sVerbAux, this._tTagsAux, ":E", sWho) : conj.getConj("être", ":E", sWho); } else { sImpe = this.dConj.get(":E").get(sWho); } if (sImpe === "") { return ""; } - let bEli = _zStartVoy.test(sImpe); + let bEli = conj._zStartVoy.test(sImpe); if (bNeg) { if (bPro) { if (!this.bProWithEn) { - sImpe = (bEli && sWho == ":2s") ? "ne t’" + sImpe + " pas" : _dImpeProNeg.get(sWho) + sImpe + " pas"; + sImpe = (bEli && sWho == ":2s") ? "ne t’" + sImpe + " pas" : conj._dImpeProNeg.get(sWho) + sImpe + " pas"; } else { - sImpe = _dImpeProNegEn.get(sWho) + sImpe + " pas"; + sImpe = conj._dImpeProNegEn.get(sWho) + sImpe + " pas"; } } else { sImpe = (bEli) ? "n’" + sImpe + " pas" : "ne " + sImpe + " pas"; } } else if (bPro) { - sImpe = (this.bProWithEn) ? sImpe + _dImpeProEn.get(sWho) : sImpe + _dImpePro.get(sWho); + sImpe = (this.bProWithEn) ? sImpe + conj._dImpeProEn.get(sWho) : sImpe + conj._dImpePro.get(sWho); } if (bTpsCo) { return sImpe + " " + this._seekPpas(bPro, bFem, sWho.endsWith("p") || this._sRawInfo[5] == "r"); } return sImpe; - }; + } _seekPpas (bPro, bFem, bPlur) { if (!bPro && this.sVerbAux == "avoir") { return this.dConj.get(":PQ").get(":Q1"); } @@ -486,19 +474,53 @@ } return (this.dConj.get(":PQ").get(":Q4")) ? this.dConj.get(":PQ").get(":Q4") : this.dConj.get(":PQ").get(":Q1"); } } + +// Initialization +if (typeof(browser) !== 'undefined') { + // WebExtension (but not in Worker) + conj.init(helpers.loadFile(browser.extension.getURL("grammalecte/fr/conj_data.json"))); +} else if (typeof(require) !== 'undefined') { + // Add-on SDK and Thunderbird + let helpers = require("resource://grammalecte/helpers.js"); + conj.init(helpers.loadFile("resource://grammalecte/fr/conj_data.json")); +} else if (typeof(self) !== 'undefined' && typeof(self.port) !== 'undefined' && typeof(self.port.on) === "undefined") { + // used within Firefox content script (conjugation panel). + // can’t load JSON from here, so we do it in ui.js and send it here. + self.port.on("provideConjData", function (sJSONData) { + conj.init(sJSONData); + }); +} else { + console.log("Module conj non initialisé"); +} + if (typeof(exports) !== 'undefined') { - // Used for Grammalecte library. - // In content scripts, these variable are directly reachable + exports._lVtyp = conj._lVtyp; + exports._lTags = conj._lTags; + exports._dPatternConj = conj._dPatternConj; + exports._dVerb = conj._dVerb; + exports.init = conj.init; + exports._zStartVoy = conj._zStartVoy; + exports._zNeedTeuph = conj._zNeedTeuph; + exports._dProSuj = conj._dProSuj; + exports._dProObj = conj._dProObj; + exports._dProObjEl = conj._dProObjEl; + exports._dImpePro = conj._dImpePro; + exports._dImpeProNeg = conj._dImpeProNeg; + exports._dImpeProEn = conj._dImpeProEn; + exports._dImpeProNegEn = conj._dImpeProNegEn; + exports._dGroup = conj._dGroup; + exports._dTenseIdx = conj._dTenseIdx; + exports.isVerb = conj.isVerb; + exports.getConj = conj.getConj; + exports.hasConj = conj.hasConj; + exports.getVtyp = conj.getVtyp; + exports.getSimil = conj.getSimil; + exports._getTags = conj._getTags; + exports._getConjWithTags = conj._getConjWithTags; + exports._hasConjWithTags = conj._hasConjWithTags; + exports._modifyStringWithSuffixCode = conj._modifyStringWithSuffixCode; exports.Verb = Verb; - exports.isVerb = isVerb; - exports.getConj = getConj; - exports.hasConj = hasConj; - exports.getVtyp = getVtyp; - exports.getSimil = getSimil; - exports._getTags = _getTags; - exports._hasConjWithTags = _hasConjWithTags; - exports._getConjWithTags = _getConjWithTags; } Index: gc_lang/fr/modules-js/cregex.js ================================================================== --- gc_lang/fr/modules-js/cregex.js +++ gc_lang/fr/modules-js/cregex.js @@ -1,301 +1,348 @@ //// Grammalecte - Compiled regular expressions -///// Lemme -const zLemma = new RegExp("^>([a-zà-öø-ÿ0-9Ā-ʯ][a-zà-öø-ÿ0-9Ā-ʯ-]+)"); - -///// Masculin / féminin / singulier / pluriel -const zGender = new RegExp(":[mfe]"); -const zNumber = new RegExp(":[spi]"); - -///// Nom et adjectif -const zNA = new RegExp(":[NA]"); - -//// nombre -const zNAs = new RegExp(":[NA].*:s"); -const zNAp = new RegExp(":[NA].*:p"); -const zNAi = new RegExp(":[NA].*:i"); -const zNAsi = new RegExp(":[NA].*:[si]"); -const zNApi = new RegExp(":[NA].*:[pi]"); - -//// genre -const zNAm = new RegExp(":[NA].*:m"); -const zNAf = new RegExp(":[NA].*:f"); -const zNAe = new RegExp(":[NA].*:e"); -const zNAme = new RegExp(":[NA].*:[me]"); -const zNAfe = new RegExp(":[NA].*:[fe]"); - -//// nombre et genre -// singuilier -const zNAms = new RegExp(":[NA].*:m.*:s"); -const zNAfs = new RegExp(":[NA].*:f.*:s"); -const zNAes = new RegExp(":[NA].*:e.*:s"); -const zNAmes = new RegExp(":[NA].*:[me].*:s"); -const zNAfes = new RegExp(":[NA].*:[fe].*:s"); - -// singulier et invariable -const zNAmsi = new RegExp(":[NA].*:m.*:[si]"); -const zNAfsi = new RegExp(":[NA].*:f.*:[si]"); -const zNAesi = new RegExp(":[NA].*:e.*:[si]"); -const zNAmesi = new RegExp(":[NA].*:[me].*:[si]"); -const zNAfesi = new RegExp(":[NA].*:[fe].*:[si]"); - -// pluriel -const zNAmp = new RegExp(":[NA].*:m.*:p"); -const zNAfp = new RegExp(":[NA].*:f.*:p"); -const zNAep = new RegExp(":[NA].*:e.*:p"); -const zNAmep = new RegExp(":[NA].*:[me].*:p"); -const zNAfep = new RegExp(":[NA].*:[me].*:p"); - -// pluriel et invariable -const zNAmpi = new RegExp(":[NA].*:m.*:[pi]"); -const zNAfpi = new RegExp(":[NA].*:f.*:[pi]"); -const zNAepi = new RegExp(":[NA].*:e.*:[pi]"); -const zNAmepi = new RegExp(":[NA].*:[me].*:[pi]"); -const zNAfepi = new RegExp(":[NA].*:[fe].*:[pi]"); - -//// Divers -const zAD = new RegExp(":[AB]"); - -///// Verbe -const zVconj = new RegExp(":[123][sp]"); -const zVconj123 = new RegExp(":V[123].*:[123][sp]"); - -///// Nom | Adjectif | Verbe -const zNVconj = new RegExp(":(?:N|[123][sp])"); -const zNAVconj = new RegExp(":(?:N|A|[123][sp])"); - -///// Spécifique -const zNnotA = new RegExp(":N(?!:A)"); -const zPNnotA = new RegExp(":(?:N(?!:A)|Q)"); - -///// Noms propres -const zNP = new RegExp(":(?:M[12P]|T)"); -const zNPm = new RegExp(":(?:M[12P]|T):m"); -const zNPf = new RegExp(":(?:M[12P]|T):f"); -const zNPe = new RegExp(":(?:M[12P]|T):e"); - - -///// FONCTIONS - -function getLemmaOfMorph (sMorph) { - return zLemma.exec(sMorph)[1]; -} - -function checkAgreement (l1, l2) { - // check number agreement - if (!mbInv(l1) && !mbInv(l2)) { - if (mbSg(l1) && !mbSg(l2)) { - return false; - } - if (mbPl(l1) && !mbPl(l2)) { - return false; - } - } - // check gender agreement - if (mbEpi(l1) || mbEpi(l2)) { - return true; - } - if (mbMas(l1) && !mbMas(l2)) { - return false; - } - if (mbFem(l1) && !mbFem(l2)) { - return false; - } - return true; -} - -function checkConjVerb (lMorph, sReqConj) { - return lMorph.some(s => s.includes(sReqConj)); -} - -function getGender (lMorph) { - // returns gender of word (':m', ':f', ':e' or empty string). - let sGender = ""; - for (let sMorph of lMorph) { - let m = zGender.exec(sMorph); - if (m) { - if (!sGender) { - sGender = m[0]; - } else if (sGender != m[0]) { - return ":e"; - } - } - } - return sGender; -} - -function getNumber (lMorph) { - // returns number of word (':s', ':p', ':i' or empty string). - let sNumber = ""; - for (let sMorph of lMorph) { - let m = zNumber.exec(sWord); - if (m) { - if (!sNumber) { - sNumber = m[0]; - } else if (sNumber != m[0]) { - return ":i"; - } - } - } - return sNumber; -} - -// NOTE : isWhat (lMorph) returns true if lMorph contains nothing else than What -// mbWhat (lMorph) returns true if lMorph contains What at least once - -//// isXXX = it’s certain - -function isNom (lMorph) { - return lMorph.every(s => s.includes(":N")); -} - -function isNomNotAdj (lMorph) { - return lMorph.every(s => zNnotA.test(s)); -} - -function isAdj (lMorph) { - return lMorph.every(s => s.includes(":A")); -} - -function isNomAdj (lMorph) { - return lMorph.every(s => zNA.test(s)); -} - -function isNomVconj (lMorph) { - return lMorph.every(s => zNVconj.test(s)); -} - -function isInv (lMorph) { - return lMorph.every(s => s.includes(":i")); -} -function isSg (lMorph) { - return lMorph.every(s => s.includes(":s")); -} -function isPl (lMorph) { - return lMorph.every(s => s.includes(":p")); -} -function isEpi (lMorph) { - return lMorph.every(s => s.includes(":e")); -} -function isMas (lMorph) { - return lMorph.every(s => s.includes(":m")); -} -function isFem (lMorph) { - return lMorph.every(s => s.includes(":f")); -} - - -//// mbXXX = MAYBE XXX - -function mbNom (lMorph) { - return lMorph.some(s => s.includes(":N")); -} - -function mbAdj (lMorph) { - return lMorph.some(s => s.includes(":A")); -} - -function mbAdjNb (lMorph) { - return lMorph.some(s => zAD.test(s)); -} - -function mbNomAdj (lMorph) { - return lMorph.some(s => zNA.test(s)); -} - -function mbNomNotAdj (lMorph) { - let b = false; - for (let s of lMorph) { - if (s.includes(":A")) { - return false; - } - if (s.includes(":N")) { - b = true; - } - } - return b; -} - -function mbPpasNomNotAdj (lMorph) { - return lMorph.some(s => zPNnotA.test(s)); -} - -function mbVconj (lMorph) { - return lMorph.some(s => zVconj.test(s)); -} - -function mbVconj123 (lMorph) { - return lMorph.some(s => zVconj123.test(s)); -} - -function mbMG (lMorph) { - return lMorph.some(s => s.includes(":G")); -} - -function mbInv (lMorph) { - return lMorph.some(s => s.includes(":i")); -} -function mbSg (lMorph) { - return lMorph.some(s => s.includes(":s")); -} -function mbPl (lMorph) { - return lMorph.some(s => s.includes(":p")); -} -function mbEpi (lMorph) { - return lMorph.some(s => s.includes(":e")); -} -function mbMas (lMorph) { - return lMorph.some(s => s.includes(":m")); -} -function mbFem (lMorph) { - return lMorph.some(s => s.includes(":f")); -} - -function mbNpr (lMorph) { - return lMorph.some(s => zNP.test(s)); -} - -function mbNprMasNotFem (lMorph) { - if (lMorph.some(s => zNPf.test(s))) { - return false; - } - return lMorph.some(s => zNPm.test(s)); -} +var cregex = { + ///// Lemme + _zLemma: new RegExp(">([a-zà-öø-ÿ0-9Ā-ʯ][a-zà-öø-ÿ0-9Ā-ʯ-]+)"), + + ///// Masculin / féminin / singulier / pluriel + _zGender: new RegExp(":[mfe]"), + _zNumber: new RegExp(":[spi]"), + + ///// Nom et adjectif + _zNA: new RegExp(":[NA]"), + + //// nombre + _zNAs: new RegExp(":[NA].*:s"), + _zNAp: new RegExp(":[NA].*:p"), + _zNAi: new RegExp(":[NA].*:i"), + _zNAsi: new RegExp(":[NA].*:[si]"), + _zNApi: new RegExp(":[NA].*:[pi]"), + + //// genre + _zNAm: new RegExp(":[NA].*:m"), + _zNAf: new RegExp(":[NA].*:f"), + _zNAe: new RegExp(":[NA].*:e"), + _zNAme: new RegExp(":[NA].*:[me]"), + _zNAfe: new RegExp(":[NA].*:[fe]"), + + //// nombre et genre + // singuilier + _zNAms: new RegExp(":[NA].*:m.*:s"), + _zNAfs: new RegExp(":[NA].*:f.*:s"), + _zNAes: new RegExp(":[NA].*:e.*:s"), + _zNAmes: new RegExp(":[NA].*:[me].*:s"), + _zNAfes: new RegExp(":[NA].*:[fe].*:s"), + + // singulier et invariable + _zNAmsi: new RegExp(":[NA].*:m.*:[si]"), + _zNAfsi: new RegExp(":[NA].*:f.*:[si]"), + _zNAesi: new RegExp(":[NA].*:e.*:[si]"), + _zNAmesi: new RegExp(":[NA].*:[me].*:[si]"), + _zNAfesi: new RegExp(":[NA].*:[fe].*:[si]"), + + // pluriel + _zNAmp: new RegExp(":[NA].*:m.*:p"), + _zNAfp: new RegExp(":[NA].*:f.*:p"), + _zNAep: new RegExp(":[NA].*:e.*:p"), + _zNAmep: new RegExp(":[NA].*:[me].*:p"), + _zNAfep: new RegExp(":[NA].*:[me].*:p"), + + // pluriel et invariable + _zNAmpi: new RegExp(":[NA].*:m.*:[pi]"), + _zNAfpi: new RegExp(":[NA].*:f.*:[pi]"), + _zNAepi: new RegExp(":[NA].*:e.*:[pi]"), + _zNAmepi: new RegExp(":[NA].*:[me].*:[pi]"), + _zNAfepi: new RegExp(":[NA].*:[fe].*:[pi]"), + + //// Divers + _zAD: new RegExp(":[AB]"), + + ///// Verbe + _zVconj: new RegExp(":[123][sp]"), + _zVconj123: new RegExp(":V[123].*:[123][sp]"), + + ///// Nom | Adjectif | Verbe + _zNVconj: new RegExp(":(?:N|[123][sp])"), + _zNAVconj: new RegExp(":(?:N|A|[123][sp])"), + + ///// Spécifique + _zNnotA: new RegExp(":N(?!:A)"), + _zPNnotA: new RegExp(":(?:N(?!:A)|Q)"), + + ///// Noms propres + _zNP: new RegExp(":(?:M[12P]|T)"), + _zNPm: new RegExp(":(?:M[12P]|T):m"), + _zNPf: new RegExp(":(?:M[12P]|T):f"), + _zNPe: new RegExp(":(?:M[12P]|T):e"), + + + ///// FONCTIONS + + getLemmaOfMorph: function (sMorph) { + return this._zLemma.exec(sMorph)[1]; + }, + + checkAgreement: function (l1, l2) { + // check number agreement + if (!this.mbInv(l1) && !this.mbInv(l2)) { + if (this.mbSg(l1) && !this.mbSg(l2)) { + return false; + } + if (this.mbPl(l1) && !this.mbPl(l2)) { + return false; + } + } + // check gender agreement + if (this.mbEpi(l1) || this.mbEpi(l2)) { + return true; + } + if (this.mbMas(l1) && !this.mbMas(l2)) { + return false; + } + if (this.mbFem(l1) && !this.mbFem(l2)) { + return false; + } + return true; + }, + + checkConjVerb: function (lMorph, sReqConj) { + return lMorph.some(s => s.includes(sReqConj)); + }, + + getGender: function (lMorph) { + // returns gender of word (':m', ':f', ':e' or empty string). + let sGender = ""; + for (let sMorph of lMorph) { + let m = this._zGender.exec(sMorph); + if (m) { + if (!sGender) { + sGender = m[0]; + } else if (sGender != m[0]) { + return ":e"; + } + } + } + return sGender; + }, + + getNumber: function (lMorph) { + // returns number of word (':s', ':p', ':i' or empty string). + let sNumber = ""; + for (let sMorph of lMorph) { + let m = this._zNumber.exec(sWord); + if (m) { + if (!sNumber) { + sNumber = m[0]; + } else if (sNumber != m[0]) { + return ":i"; + } + } + } + return sNumber; + }, + + // NOTE : isWhat (lMorph) returns true if lMorph contains nothing else than What + // mbWhat (lMorph) returns true if lMorph contains What at least once + + //// isXXX = it’s certain + + isNom: function (lMorph) { + return lMorph.every(s => s.includes(":N")); + }, + + isNomNotAdj: function (lMorph) { + return lMorph.every(s => this._zNnotA.test(s)); + }, + + isAdj: function (lMorph) { + return lMorph.every(s => s.includes(":A")); + }, + + isNomAdj: function (lMorph) { + return lMorph.every(s => this._zNA.test(s)); + }, + + isNomVconj: function (lMorph) { + return lMorph.every(s => this._zNVconj.test(s)); + }, + + isInv: function (lMorph) { + return lMorph.every(s => s.includes(":i")); + }, + isSg: function (lMorph) { + return lMorph.every(s => s.includes(":s")); + }, + isPl: function (lMorph) { + return lMorph.every(s => s.includes(":p")); + }, + isEpi: function (lMorph) { + return lMorph.every(s => s.includes(":e")); + }, + isMas: function (lMorph) { + return lMorph.every(s => s.includes(":m")); + }, + isFem: function (lMorph) { + return lMorph.every(s => s.includes(":f")); + }, + + + //// mbXXX = MAYBE XXX + + mbNom: function (lMorph) { + return lMorph.some(s => s.includes(":N")); + }, + + mbAdj: function (lMorph) { + return lMorph.some(s => s.includes(":A")); + }, + + mbAdjNb: function (lMorph) { + return lMorph.some(s => this._zAD.test(s)); + }, + + mbNomAdj: function (lMorph) { + return lMorph.some(s => this._zNA.test(s)); + }, + + mbNomNotAdj: function (lMorph) { + let b = false; + for (let s of lMorph) { + if (s.includes(":A")) { + return false; + } + if (s.includes(":N")) { + b = true; + } + } + return b; + }, + + mbPpasNomNotAdj: function (lMorph) { + return lMorph.some(s => this._zPNnotA.test(s)); + }, + + mbVconj: function (lMorph) { + return lMorph.some(s => this._zVconj.test(s)); + }, + + mbVconj123: function (lMorph) { + return lMorph.some(s => this._zVconj123.test(s)); + }, + + mbMG: function (lMorph) { + return lMorph.some(s => s.includes(":G")); + }, + + mbInv: function (lMorph) { + return lMorph.some(s => s.includes(":i")); + }, + mbSg: function (lMorph) { + return lMorph.some(s => s.includes(":s")); + }, + mbPl: function (lMorph) { + return lMorph.some(s => s.includes(":p")); + }, + mbEpi: function (lMorph) { + return lMorph.some(s => s.includes(":e")); + }, + mbMas: function (lMorph) { + return lMorph.some(s => s.includes(":m")); + }, + mbFem: function (lMorph) { + return lMorph.some(s => s.includes(":f")); + }, + + mbNpr: function (lMorph) { + return lMorph.some(s => this._zNP.test(s)); + }, + + mbNprMasNotFem: function (lMorph) { + if (lMorph.some(s => this._zNPf.test(s))) { + return false; + } + return lMorph.some(s => this._zNPm.test(s)); + } +}; if (typeof(exports) !== 'undefined') { - exports.getLemmaOfMorph = getLemmaOfMorph; - exports.checkAgreement = checkAgreement; - exports.checkConjVerb = checkConjVerb; - exports.getGender = getGender; - exports.getNumber = getNumber; - exports.isNom = isNom; - exports.isNomNotAdj = isNomNotAdj; - exports.isAdj = isAdj; - exports.isNomAdj = isNomAdj; - exports.isNomVconj = isNomVconj; - exports.isInv = isInv; - exports.isSg = isSg; - exports.isPl = isPl; - exports.isEpi = isEpi; - exports.isMas = isMas; - exports.isFem = isFem; - exports.mbNom = mbNom; - exports.mbAdj = mbAdj; - exports.mbAdjNb = mbAdjNb; - exports.mbNomAdj = mbNomAdj; - exports.mbNomNotAdj = mbNomNotAdj; - exports.mbPpasNomNotAdj = mbPpasNomNotAdj; - exports.mbVconj = mbVconj; - exports.mbVconj123 = mbVconj123; - exports.mbMG = mbMG; - exports.mbInv = mbInv; - exports.mbSg = mbSg; - exports.mbPl = mbPl; - exports.mbEpi = mbEpi; - exports.mbMas = mbMas; - exports.mbFem = mbFem; - exports.mbNpr = mbNpr; - exports.mbNprMasNotFem = mbNprMasNotFem; + exports._zLemma = cregex._zLemma; + exports._zGender = cregex._zGender; + exports._zNumber = cregex._zNumber; + exports._zNA = cregex._zNA; + exports._zNAs = cregex._zNAs; + exports._zNAp = cregex._zNAp; + exports._zNAi = cregex._zNAi; + exports._zNAsi = cregex._zNAsi; + exports._zNApi = cregex._zNApi; + exports._zNAm = cregex._zNAm; + exports._zNAf = cregex._zNAf; + exports._zNAe = cregex._zNAe; + exports._zNAme = cregex._zNAme; + exports._zNAfe = cregex._zNAfe; + exports._zNAms = cregex._zNAms; + exports._zNAfs = cregex._zNAfs; + exports._zNAes = cregex._zNAes; + exports._zNAmes = cregex._zNAmes; + exports._zNAfes = cregex._zNAfes; + exports._zNAmsi = cregex._zNAmsi; + exports._zNAfsi = cregex._zNAfsi; + exports._zNAesi = cregex._zNAesi; + exports._zNAmesi = cregex._zNAmesi; + exports._zNAfesi = cregex._zNAfesi; + exports._zNAmp = cregex._zNAmp; + exports._zNAfp = cregex._zNAfp; + exports._zNAep = cregex._zNAep; + exports._zNAmep = cregex._zNAmep; + exports._zNAfep = cregex._zNAfep; + exports._zNAmpi = cregex._zNAmpi; + exports._zNAfpi = cregex._zNAfpi; + exports._zNAepi = cregex._zNAepi; + exports._zNAmepi = cregex._zNAmepi; + exports._zNAfepi = cregex._zNAfepi; + exports._zAD = cregex._zAD; + exports._zVconj = cregex._zVconj; + exports._zVconj123 = cregex._zVconj123; + exports._zNVconj = cregex._zNVconj; + exports._zNAVconj = cregex._zNAVconj; + exports._zNnotA = cregex._zNnotA; + exports._zPNnotA = cregex._zPNnotA; + exports._zNP = cregex._zNP; + exports._zNPm = cregex._zNPm; + exports._zNPf = cregex._zNPf; + exports._zNPe = cregex._zNPe; + exports.getLemmaOfMorph = cregex.getLemmaOfMorph; + exports.checkAgreement = cregex.checkAgreement; + exports.checkConjVerb = cregex.checkConjVerb; + exports.getGender = cregex.getGender; + exports.getNumber = cregex.getNumber; + exports.isNom = cregex.isNom; + exports.isNomNotAdj = cregex.isNomNotAdj; + exports.isAdj = cregex.isAdj; + exports.isNomAdj = cregex.isNomAdj; + exports.isNomVconj = cregex.isNomVconj; + exports.isInv = cregex.isInv; + exports.isSg = cregex.isSg; + exports.isPl = cregex.isPl; + exports.isEpi = cregex.isEpi; + exports.isMas = cregex.isMas; + exports.isFem = cregex.isFem; + exports.mbNom = cregex.mbNom; + exports.mbAdj = cregex.mbAdj; + exports.mbAdjNb = cregex.mbAdjNb; + exports.mbNomAdj = cregex.mbNomAdj; + exports.mbNomNotAdj = cregex.mbNomNotAdj; + exports.mbPpasNomNotAdj = cregex.mbPpasNomNotAdj; + exports.mbVconj = cregex.mbVconj; + exports.mbVconj123 = cregex.mbVconj123; + exports.mbMG = cregex.mbMG; + exports.mbInv = cregex.mbInv; + exports.mbSg = cregex.mbSg; + exports.mbPl = cregex.mbPl; + exports.mbEpi = cregex.mbEpi; + exports.mbMas = cregex.mbMas; + exports.mbFem = cregex.mbFem; + exports.mbNpr = cregex.mbNpr; + exports.mbNprMasNotFem = cregex.mbNprMasNotFem; } Index: gc_lang/fr/modules-js/gce_analyseur.js ================================================================== --- gc_lang/fr/modules-js/gce_analyseur.js +++ gc_lang/fr/modules-js/gce_analyseur.js @@ -20,11 +20,11 @@ if (s2 == "eux") { return "ils"; } if (s2 == "elle" || s2 == "elles") { // We don’t check if word exists in _dAnalyses, for it is assumed it has been done before - if (cr.mbNprMasNotFem(_dAnalyses.gl_get(s1, ""))) { + if (cregex.mbNprMasNotFem(_dAnalyses.gl_get(s1, ""))) { return "ils"; } // si épicène, indéterminable, mais OSEF, le féminin l’emporte return "elles"; } @@ -32,22 +32,22 @@ } function apposition (sWord1, sWord2) { // returns true if nom + nom (no agreement required) // We don’t check if word exists in _dAnalyses, for it is assumed it has been done before - return cr.mbNomNotAdj(_dAnalyses.gl_get(sWord2, "")) && cr.mbPpasNomNotAdj(_dAnalyses.gl_get(sWord1, "")); + return cregex.mbNomNotAdj(_dAnalyses.gl_get(sWord2, "")) && cregex.mbPpasNomNotAdj(_dAnalyses.gl_get(sWord1, "")); } function isAmbiguousNAV (sWord) { // words which are nom|adj and verb are ambiguous (except être and avoir) if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return false; } - if (!cr.mbNomAdj(_dAnalyses.gl_get(sWord, "")) || sWord == "est") { + if (!cregex.mbNomAdj(_dAnalyses.gl_get(sWord, "")) || sWord == "est") { return false; } - if (cr.mbVconj(_dAnalyses.gl_get(sWord, "")) && !cr.mbMG(_dAnalyses.gl_get(sWord, ""))) { + if (cregex.mbVconj(_dAnalyses.gl_get(sWord, "")) && !cregex.mbMG(_dAnalyses.gl_get(sWord, ""))) { return true; } return false; } @@ -56,64 +56,64 @@ // We don’t check if word exists in _dAnalyses, for it is assumed it has been done before let a2 = _dAnalyses.gl_get(sWord2, null); if (!a2 || a2.length === 0) { return false; } - if (cr.checkConjVerb(a2, sReqMorphConj)) { + if (cregex.checkConjVerb(a2, sReqMorphConj)) { // verb word2 is ok return false; } let a1 = _dAnalyses.gl_get(sWord1, null); if (!a1 || a1.length === 0) { return false; } - if (cr.checkAgreement(a1, a2) && (cr.mbAdj(a2) || cr.mbAdj(a1))) { + if (cregex.checkAgreement(a1, a2) && (cregex.mbAdj(a2) || cregex.mbAdj(a1))) { return false; } return true; } function isVeryAmbiguousAndWrong (sWord1, sWord2, sReqMorphNA, sReqMorphConj, bLastHopeCond) { //// use it if sWord1 can be also a verb; word2 is assumed to be true via isAmbiguousNAV // We don’t check if word exists in _dAnalyses, for it is assumed it has been done before - let a2 = _dAnalyses.gl_get(sWord2, null) + let a2 = _dAnalyses.gl_get(sWord2, null); if (!a2 || a2.length === 0) { return false; } - if (cr.checkConjVerb(a2, sReqMorphConj)) { + if (cregex.checkConjVerb(a2, sReqMorphConj)) { // verb word2 is ok return false; } let a1 = _dAnalyses.gl_get(sWord1, null); if (!a1 || a1.length === 0) { return false; } - if (cr.checkAgreement(a1, a2) && (cr.mbAdj(a2) || cr.mbAdjNb(a1))) { + if (cregex.checkAgreement(a1, a2) && (cregex.mbAdj(a2) || cregex.mbAdjNb(a1))) { return false; } // now, we know there no agreement, and conjugation is also wrong - if (cr.isNomAdj(a1)) { + if (cregex.isNomAdj(a1)) { return true; } - //if cr.isNomAdjVerb(a1): # considered true + //if cregex.isNomAdjVerb(a1): # considered true if (bLastHopeCond) { return true; } return false; } function checkAgreement (sWord1, sWord2) { // We don’t check if word exists in _dAnalyses, for it is assumed it has been done before - let a2 = _dAnalyses.gl_get(sWord2, null) + let a2 = _dAnalyses.gl_get(sWord2, null); if (!a2 || a2.length === 0) { return true; } let a1 = _dAnalyses.gl_get(sWord1, null); if (!a1 || a1.length === 0) { return true; } - return cr.checkAgreement(a1, a2); + return cregex.checkAgreement(a1, a2); } function mbUnit (s) { if (/[µ\/⁰¹²³⁴⁵⁶⁷⁸⁹Ωℓ·]/.test(s)) { return true; Index: gc_lang/fr/modules-js/gce_suggestions.js ================================================================== --- gc_lang/fr/modules-js/gce_suggestions.js +++ gc_lang/fr/modules-js/gce_suggestions.js @@ -1,10 +1,12 @@ //// GRAMMAR CHECKING ENGINE PLUGIN: Suggestion mechanisms -const conj = require("resource://grammalecte/fr/conj.js"); -const mfsp = require("resource://grammalecte/fr/mfsp.js"); -const phonet = require("resource://grammalecte/fr/phonet.js"); +if (typeof(exports) !== 'undefined') { + var conj = require("resource://grammalecte/fr/conj.js"); + var mfsp = require("resource://grammalecte/fr/mfsp.js"); + var phonet = require("resource://grammalecte/fr/phonet.js"); +} //// verbs function suggVerb (sFlex, sWho, funcSugg2=null) { @@ -15,12 +17,12 @@ if (tTags) { // we get the tense let aTense = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { let m; - let zVerb = new RegExp (sStem+" .*?(:(?:Y|I[pqsf]|S[pq]|K))", "g"); - while (m = zVerb.exec(sMorph)) { + let zVerb = new RegExp (">"+sStem+" .*?(:(?:Y|I[pqsf]|S[pq]|K))", "g"); + while ((m = zVerb.exec(sMorph)) !== null) { // stem must be used in regex to prevent confusion between different verbs (e.g. sauras has 2 stems: savoir and saurer) if (m) { if (m[1] === ":Y") { aTense.add(":Ip"); aTense.add(":Iq"); @@ -139,12 +141,11 @@ } return ""; } function suggVerbInfi (sFlex) { - //return stem(sFlex).join("|"); - return [ for (sStem of stem(sFlex)) if (conj.isVerb(sStem)) sStem ].join("|"); + return stem(sFlex).filter(sStem => conj.isVerb(sStem)).join("|"); } const _dQuiEst = new Map ([ ["je", ":1s"], ["j’", ":1s"], ["j’en", ":1s"], ["j’y", ":1s"], @@ -195,11 +196,11 @@ // returns plural forms assuming sFlex is singular if (sWordToAgree) { if (!_dAnalyses.has(sWordToAgree) && !_storeMorphFromFSA(sWordToAgree)) { return ""; } - let sGender = cr.getGender(_dAnalyses.gl_get(sWordToAgree, [])); + let sGender = cregex.getGender(_dAnalyses.gl_get(sWordToAgree, [])); if (sGender == ":m") { return suggMasPlur(sFlex); } else if (sGender == ":f") { return suggFemPlur(sFlex); } @@ -261,18 +262,18 @@ if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":m") || sMorph.includes(":e")) { aSugg.add(suggSing(sFlex)); } else { - let sStem = cr.getLemmaOfMorph(sMorph); + let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { mfsp.getMasForm(sStem, false).forEach(function(x) { aSugg.add(x); }); } } } else { // a verb - let sVerb = cr.getLemmaOfMorph(sMorph); + let sVerb = cregex.getLemmaOfMorph(sMorph); if (conj.hasConj(sVerb, ":PQ", ":Q1") && conj.hasConj(sVerb, ":PQ", ":Q3")) { // We also check if the verb has a feminine form. // If not, we consider it’s better to not suggest the masculine one, as it can be considered invariable. aSugg.add(conj.getConj(sVerb, ":PQ", ":Q1")); } @@ -297,18 +298,18 @@ if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":m") || sMorph.includes(":e")) { aSugg.add(suggPlur(sFlex)); } else { - let sStem = cr.getLemmaOfMorph(sMorph); + let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { mfsp.getMasForm(sStem, true).forEach(function(x) { aSugg.add(x); }); } } } else { // a verb - let sVerb = cr.getLemmaOfMorph(sMorph); + let sVerb = cregex.getLemmaOfMorph(sMorph); if (conj.hasConj(sVerb, ":PQ", ":Q2")) { aSugg.add(conj.getConj(sVerb, ":PQ", ":Q2")); } else if (conj.hasConj(sVerb, ":PQ", ":Q1")) { let sSugg = conj.getConj(sVerb, ":PQ", ":Q1"); // it is necessary to filter these flexions, like “succédé” or “agi” that are not masculine plural @@ -338,18 +339,18 @@ if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":f") || sMorph.includes(":e")) { aSugg.add(suggSing(sFlex)); } else { - let sStem = cr.getLemmaOfMorph(sMorph); + let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { aSugg.add(sStem); } } } else { // a verb - let sVerb = cr.getLemmaOfMorph(sMorph); + let sVerb = cregex.getLemmaOfMorph(sMorph); if (conj.hasConj(sVerb, ":PQ", ":Q3")) { aSugg.add(conj.getConj(sVerb, ":PQ", ":Q3")); } } } @@ -372,18 +373,18 @@ if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":f") || sMorph.includes(":e")) { aSugg.add(suggPlur(sFlex)); } else { - let sStem = cr.getLemmaOfMorph(sMorph); + let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { aSugg.add(sStem+"s"); } } } else { // a verb - let sVerb = cr.getLemmaOfMorph(sMorph); + let sVerb = cregex.getLemmaOfMorph(sMorph); if (conj.hasConj(sVerb, ":PQ", ":Q4")) { aSugg.add(conj.getConj(sVerb, ":PQ", ":Q4")); } } } Index: gc_lang/fr/modules-js/lexicographe.js ================================================================== --- gc_lang/fr/modules-js/lexicographe.js +++ gc_lang/fr/modules-js/lexicographe.js @@ -5,13 +5,13 @@ ${string} ${map} -const helpers = require("resource://grammalecte/helpers.js"); -const tkz = require("resource://grammalecte/tokenizer.js"); - +if (typeof(exports) !== 'undefined') { + var helpers = require("resource://grammalecte/helpers.js"); +} const _dTAGS = new Map ([ [':G', "[mot grammatical]"], [':N', " nom,"], [':A', " adjectif,"], @@ -197,11 +197,11 @@ constructor (oDict) { this.oDict = oDict; this._zElidedPrefix = new RegExp ("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i"); this._zCompoundWord = new RegExp ("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$", "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; @@ -224,17 +224,23 @@ 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 (s of lMorph) if (s.includes(":")) this._formatTags(s) ]; + 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 (s of lMorph) if (s.includes(":")) this._formatTags(s) ]; + 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"] }; @@ -244,11 +250,11 @@ } catch (e) { helpers.logerror(e); } return null; - }; + } _formatTags (sTags) { let sRes = ""; sTags = sTags.replace(/V([0-3][ea]?)[itpqnmr_eaxz]+/, "V$1"); let m; @@ -265,11 +271,11 @@ 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)); } @@ -279,12 +285,12 @@ if (s.endsWith("ous")) { s += '2'; } let nPos = s.indexOf("-"); return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos+1)); - }; + } } if (typeof(exports) !== 'undefined') { exports.Lexicographe = Lexicographe; } Index: gc_lang/fr/modules-js/mfsp.js ================================================================== --- gc_lang/fr/modules-js/mfsp.js +++ gc_lang/fr/modules-js/mfsp.js @@ -1,87 +1,126 @@ // Grammalecte "use strict"; -const helpers = require("resource://grammalecte/helpers.js"); -const echo = helpers.echo; - -const oData = JSON.parse(helpers.loadFile("resource://grammalecte/fr/mfsp_data.json")); - -// list of affix codes -const _lTagMiscPlur = oData.lTagMiscPlur; -const _lTagMasForm = oData.lTagMasForm; - -// dictionary of words with uncommon plurals (-x, -ux, english, latin and italian plurals) and tags to generate them -const _dMiscPlur = helpers.objectToMap(oData.dMiscPlur); - -// dictionary of feminine forms and tags to generate masculine forms (singular and plural) -const _dMasForm = helpers.objectToMap(oData.dMasForm); - - - -function isFemForm (sWord) { - // returns True if sWord exists in _dMasForm - return _dMasForm.has(sWord); -} - -function getMasForm (sWord, bPlur) { - // returns masculine form with feminine form - if (_dMasForm.has(sWord)) { - return [ for (sTag of _whatSuffixCodes(sWord, bPlur)) _modifyStringWithSuffixCode(sWord, sTag) ]; - } - return []; -} - -function hasMiscPlural (sWord) { - // returns True if sWord exists in dMiscPlur - return _dMiscPlur.has(sWord); -} - -function getMiscPlural (sWord) { - // returns plural form with singular form - if (_dMiscPlur.has(sWord)) { - return [ for (sTag of _lTagMiscPlur[_dMiscPlur.get(sWord)].split("|")) _modifyStringWithSuffixCode(sWord, sTag) ]; - } - return []; -} - -function _whatSuffixCodes (sWord, bPlur) { - // necessary only for dMasFW - let sSfx = _lTagMasForm[_dMasForm.get(sWord)]; - if (sSfx.includes("/")) { - if (bPlur) { - return sSfx.slice(sSfx.indexOf("/")+1).split("|"); - } - return sSfx.slice(0, sSfx.indexOf("/")).split("|"); - } - return sSfx.split("|"); -} - -function _modifyStringWithSuffixCode (sWord, sSfx) { - // returns sWord modified by sSfx - if (!sWord) { - return ""; - } - if (sSfx === "0") { - return sWord; - } - try { - if (sSfx[0] !== '0') { - return sWord.slice(0, -(sSfx.charCodeAt(0)-48)) + sSfx.slice(1); // 48 is the ASCII code for "0" - } else { - return sWord + sSfx.slice(1); - } - } - catch (e) { - console.log(e); - return "## erreur, code : " + sSfx + " ##"; - } + +if (typeof(require) !== 'undefined') { + var helpers = require("resource://grammalecte/helpers.js"); +} + + +var mfsp = { + // list of affix codes + _lTagMiscPlur: [], + _lTagMasForm: [], + // dictionary of words with uncommon plurals (-x, -ux, english, latin and italian plurals) and tags to generate them + _dMiscPlur: new Map(), + // dictionary of feminine forms and tags to generate masculine forms (singular and plural) + _dMasForm: new Map(), + + init: function (sJSONData) { + try { + let _oData = JSON.parse(sJSONData); + this._lTagMiscPlur = _oData.lTagMiscPlur; + this._lTagMasForm = _oData.lTagMasForm; + this._dMiscPlur = helpers.objectToMap(_oData.dMiscPlur); + this._dMasForm = helpers.objectToMap(_oData.dMasForm); + } + catch (e) { + console.error(e); + } + }, + + isFemForm: function (sWord) { + // returns True if sWord exists in this._dMasForm + return this._dMasForm.has(sWord); + }, + + getMasForm: function (sWord, bPlur) { + // returns masculine form with feminine form + if (this._dMasForm.has(sWord)) { + let aMasForm = []; + for (let sTag of this._whatSuffixCode(sWord, bPlur)){ + aMasForm.push( this._modifyStringWithSuffixCode(sWord, sTag) ); + } + return aMasForm; + } + return []; + }, + + hasMiscPlural: function (sWord) { + // returns True if sWord exists in dMiscPlur + return this._dMiscPlur.has(sWord); + }, + + getMiscPlural: function (sWord) { + // returns plural form with singular form + if (this._dMiscPlur.has(sWord)) { + let aMiscPlural = []; + for (let sTag of this._lTagMiscPlur[this._dMiscPlur.get(sWord)].split("|")){ + aMiscPlural.push( this._modifyStringWithSuffixCode(sWord, sTag) ); + } + return aMiscPlural; + } + return []; + }, + + _whatSuffixCode: function (sWord, bPlur) { + // necessary only for dMasFW + let sSfx = this._lTagMasForm[this._dMasForm.get(sWord)]; + if (sSfx.includes("/")) { + if (bPlur) { + return sSfx.slice(sSfx.indexOf("/")+1).split("|"); + } + return sSfx.slice(0, sSfx.indexOf("/")).split("|"); + } + return sSfx.split("|"); + }, + + _modifyStringWithSuffixCode: function (sWord, sSfx) { + // returns sWord modified by sSfx + if (!sWord) { + return ""; + } + if (sSfx === "0") { + return sWord; + } + try { + if (sSfx[0] !== '0') { + return sWord.slice(0, -(sSfx.charCodeAt(0)-48)) + sSfx.slice(1); // 48 is the ASCII code for "0" + } else { + return sWord + sSfx.slice(1); + } + } + catch (e) { + console.log(e); + return "## erreur, code : " + sSfx + " ##"; + } + } +}; + + +// Initialization +if (typeof(browser) !== 'undefined') { + // WebExtension + mfsp.init(helpers.loadFile(browser.extension.getURL("grammalecte/fr/mfsp_data.json"))); +} else if (typeof(require) !== 'undefined') { + // Add-on SDK and Thunderbird + mfsp.init(helpers.loadFile("resource://grammalecte/fr/mfsp_data.json")); +} else { + console.log("Module mfsp non initialisé"); } if (typeof(exports) !== 'undefined') { - exports.isFemForm = isFemForm; - exports.getMasForm = getMasForm; - exports.hasMiscPlural = hasMiscPlural; - exports.getMiscPlural = getMiscPlural; + exports._lTagMiscPlur = mfsp._lTagMiscPlur; + exports._lTagMasForm = mfsp._lTagMasForm; + exports._dMiscPlur = mfsp._dMiscPlur; + exports._dMasForm = mfsp._dMasForm; + exports.init = mfsp.init; + exports.isFemForm = mfsp.isFemForm; + exports.getMasForm = mfsp.getMasForm; + exports.hasMiscPlural = mfsp.hasMiscPlural; + exports.getMiscPlural = mfsp.getMiscPlural; + exports._whatSuffixCode = mfsp._whatSuffixCode; + exports._modifyStringWithSuffixCode = mfsp._modifyStringWithSuffixCode; } Index: gc_lang/fr/modules-js/phonet.js ================================================================== --- gc_lang/fr/modules-js/phonet.js +++ gc_lang/fr/modules-js/phonet.js @@ -1,75 +1,103 @@ // Grammalecte - Suggestion phonétique -const helpers = require("resource://grammalecte/helpers.js"); -const echo = helpers.echo; - -const oData = JSON.parse(helpers.loadFile("resource://grammalecte/fr/phonet_data.json")); - -const _dWord = helpers.objectToMap(oData.dWord); -const _lSet = oData.lSet; -const _dMorph = helpers.objectToMap(oData.dMorph); - - - -function hasSimil (sWord, sPattern=null) { - // return True if there is list of words phonetically similar to sWord - if (!sWord) { - return false; - } - if (_dWord.has(sWord)) { - if (sPattern) { - return getSimil(sWord).some(sSimil => _dMorph.gl_get(sSimil, []).some(sMorph => sMorph.search(sPattern) >= 0)); - } - return true; - } - if (sWord.slice(0,1).gl_isUpperCase()) { - sWord = sWord.toLowerCase(); - if (_dWord.has(sWord)) { - if (sPattern) { - return getSimil(sWord).some(sSimil => _dMorph.gl_get(sSimil, []).some(sMorph => sMorph.search(sPattern) >= 0)); - } - return true; - } - } - return false; -} - -function getSimil (sWord) { - // return list of words phonetically similar to sWord - if (!sWord) { - return []; - } - if (_dWord.has(sWord)) { - return _lSet[_dWord.get(sWord)]; - } - if (sWord.slice(0,1).gl_isUpperCase()) { - sWord = sWord.toLowerCase(); - if (_dWord.has(sWord)) { - return _lSet[_dWord.get(sWord)]; - } - } - return []; -} - -function selectSimil (sWord, sPattern) { - // return list of words phonetically similar to sWord and whom POS is matching sPattern - if (!sPattern) { - return new Set(getSimil(sWord)); - } - let aSelect = new Set(); - for (let sSimil of getSimil(sWord)) { - for (let sMorph of _dMorph.gl_get(sSimil, [])) { - if (sMorph.search(sPattern) >= 0) { - aSelect.add(sSimil); - } - } - } - return aSelect; +if (typeof(require) !== 'undefined') { + var helpers = require("resource://grammalecte/helpers.js"); +} + + +var phonet = { + _dWord: new Map(), + _lSet: [], + _dMorph: new Map(), + + init: function (sJSONData) { + try { + let _oData = JSON.parse(sJSONData); + this._dWord = helpers.objectToMap(_oData.dWord); + this._lSet = _oData.lSet; + this._dMorph = helpers.objectToMap(_oData.dMorph); + } + catch (e) { + console.error(e); + } + }, + + hasSimil: function (sWord, sPattern=null) { + // return True if there is list of words phonetically similar to sWord + if (!sWord) { + return false; + } + if (this._dWord.has(sWord)) { + if (sPattern) { + return this.getSimil(sWord).some(sSimil => this._dMorph.gl_get(sSimil, []).some(sMorph => sMorph.search(sPattern) >= 0)); + } + return true; + } + if (sWord.slice(0,1).gl_isUpperCase()) { + sWord = sWord.toLowerCase(); + if (this._dWord.has(sWord)) { + if (sPattern) { + return this.getSimil(sWord).some(sSimil => this._dMorph.gl_get(sSimil, []).some(sMorph => sMorph.search(sPattern) >= 0)); + } + return true; + } + } + return false; + }, + + getSimil: function (sWord) { + // return list of words phonetically similar to sWord + if (!sWord) { + return []; + } + if (this._dWord.has(sWord)) { + return this._lSet[this._dWord.get(sWord)]; + } + if (sWord.slice(0,1).gl_isUpperCase()) { + sWord = sWord.toLowerCase(); + if (this._dWord.has(sWord)) { + return this._lSet[this._dWord.get(sWord)]; + } + } + return []; + }, + + selectSimil: function (sWord, sPattern) { + // return list of words phonetically similar to sWord and whom POS is matching sPattern + if (!sPattern) { + return new Set(this.getSimil(sWord)); + } + let aSelect = new Set(); + for (let sSimil of this.getSimil(sWord)) { + for (let sMorph of this._dMorph.gl_get(sSimil, [])) { + if (sMorph.search(sPattern) >= 0) { + aSelect.add(sSimil); + } + } + } + return aSelect; + } +}; + + +// Initialization +if (typeof(browser) !== 'undefined') { + // WebExtension + phonet.init(helpers.loadFile(browser.extension.getURL("grammalecte/fr/phonet_data.json"))); +} else if (typeof(require) !== 'undefined') { + // Add-on SDK and Thunderbird + phonet.init(helpers.loadFile("resource://grammalecte/fr/phonet_data.json")); +} else { + console.log("Module phonet non initialisé"); } if (typeof(exports) !== 'undefined') { - exports.hasSimil = hasSimil; - exports.getSimil = getSimil; - exports.selectSimil = selectSimil; + exports._dWord = phonet._dWord; + exports._lSet = phonet._lSet; + exports._dMorph = phonet._dMorph; + exports.init = phonet.init; + exports.hasSimil = phonet.hasSimil; + exports.getSimil = phonet.getSimil; + exports.selectSimil = phonet.selectSimil; } Index: gc_lang/fr/modules-js/textformatter.js ================================================================== --- gc_lang/fr/modules-js/textformatter.js +++ gc_lang/fr/modules-js/textformatter.js @@ -196,11 +196,11 @@ "ma_1letter_uppercase": [ [/[  ]([LDJNMTSCÇ]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"], [/^([LDJNMTSCÇ]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"] ] }; -const dDefaultOptions = new Map ([ +const dTFDefaultOptions = new Map ([ ["ts_units", true], ["start_of_paragraph", true], ["end_of_paragraph", true], ["between_words", true], ["before_punctuation", true], @@ -249,38 +249,38 @@ ["ma_word", true], ["ma_1letter_lowercase", false], ["ma_1letter_uppercase", false] ]); -const dOptions = dDefaultOptions.gl_shallowCopy(); +const dTFOptions = dTFDefaultOptions.gl_shallowCopy(); class TextFormatter { constructor () { this.sLang = "fr"; - }; + } formatText (sText, dOpt=null) { if (dOpt !== null) { - dOptions.gl_updateOnlyExistingKeys(dOpt); + dTFOptions.gl_updateOnlyExistingKeys(dOpt); } - for (let [sOptName, bVal] of dOptions) { + for (let [sOptName, bVal] of dTFOptions) { if (bVal && oReplTable.has(sOptName)) { for (let [zRgx, sRep] of oReplTable[sOptName]) { sText = sText.replace(zRgx, sRep); } } } return sText; - }; + } getDefaultOptions () { - return dDefaultOptions; + return dTFDefaultOptions; } } if (typeof(exports) !== 'undefined') { exports.TextFormatter = TextFormatter; exports.oReplTable = oReplTable; } Index: gc_lang/fr/modules/gce_suggestions.py ================================================================== --- gc_lang/fr/modules/gce_suggestions.py +++ gc_lang/fr/modules/gce_suggestions.py @@ -13,11 +13,11 @@ tTags = conj._getTags(sStem) if tTags: # we get the tense aTense = set() for sMorph in _dAnalyses.get(sFlex, []): # we don’t check if word exists in _dAnalyses, for it is assumed it has been done before - for m in re.finditer(sStem+" .*?(:(?:Y|I[pqsf]|S[pq]|K|P))", sMorph): + for m in re.finditer(">"+sStem+" .*?(:(?:Y|I[pqsf]|S[pq]|K|P))", sMorph): # stem must be used in regex to prevent confusion between different verbs (e.g. sauras has 2 stems: savoir and saurer) if m: if m.group(1) == ":Y": aTense.add(":Ip") aTense.add(":Iq") Index: gc_lang/fr/tb/content/overlay.js ================================================================== --- gc_lang/fr/tb/content/overlay.js +++ gc_lang/fr/tb/content/overlay.js @@ -910,13 +910,14 @@ }, false); window.addEventListener("load", function (xEvent) { oDictIgniter.init(); oGrammarChecker.loadGC(); + //oGrammarChecker.fullTests(); }, false); window.addEventListener("compose-window-init", function (xEvent) { oGrammarChecker.loadUI(); oGrammarChecker.closePanel(); oGrammarChecker.clearPreview(); oTextFormatter.init(); }, true); ADDED gc_lang/fr/webext/background.js Index: gc_lang/fr/webext/background.js ================================================================== --- gc_lang/fr/webext/background.js +++ gc_lang/fr/webext/background.js @@ -0,0 +1,58 @@ +// Background + +"use strict"; + +let xGCEWorker = new Worker("gce_worker.js"); + +xGCEWorker.onmessage = function (e) { + switch (e.data[0]) { + case "grammar_errors": + console.log("GRAMMAR ERRORS"); + console.log(e.data[1].aGrammErr); + break; + case "spelling_and_grammar_errors": + console.log("SPELLING AND GRAMMAR ERRORS"); + console.log(e.data[1].aSpellErr); + console.log(e.data[1].aGrammErr); + break; + case "tests_results": + console.log("TESTS RESULTS"); + console.log(e.data[1]); + break; + case "options": + console.log("OPTIONS"); + console.log(e.data[1]); + break; + case "tokens": + console.log("TOKENS"); + console.log(e.data[1]); + break; + case "error": + console.log("ERROR"); + console.log(e.data[1]); + break; + default: + console.log("Unknown command: " + e.data[0]); + } +}; + +xGCEWorker.postMessage(["init", {sExtensionPath: browser.extension.getURL("."), sOptions: "", sContext: "Firefox"}]); + +xGCEWorker.postMessage(["parse", {sText: "J’en aie mare...", sCountry: "FR", bDebug: false, bContext: false}]); + +xGCEWorker.postMessage(["parseAndSpellcheck", {sText: "C’est terribles, ils va tout perdrre.", sCountry: "FR", bDebug: false, bContext: false}]); + +xGCEWorker.postMessage(["getListOfTokens", {sText: "J’en ai assez de ces âneries ! Merci bien. Ça suffira."}]); + +xGCEWorker.postMessage(["fullTests"]); + + +/* + Messages from the extension (not the Worker) +*/ +function handleMessage (oRequest, xSender, sendResponse) { + console.log(`[background] received: ${oRequest.content}`); + sendResponse({response: "response from background script"}); +} + +browser.runtime.onMessage.addListener(handleMessage); Index: gc_lang/fr/webext/gce_worker.js ================================================================== --- gc_lang/fr/webext/gce_worker.js +++ gc_lang/fr/webext/gce_worker.js @@ -1,139 +1,213 @@ +/* + WORKER: + https://developer.mozilla.org/en-US/docs/Web/API/Worker + https://developer.mozilla.org/en-US/docs/Web/API/DedicatedWorkerGlobalScope + + + JavaScript sucks. + No module available in WebExtension at the moment! :( + No require, no import/export. + + In Worker, we have importScripts() which imports everything in this scope. + + In order to use the same base of code with XUL-addon for Thunderbird and SDK-addon for Firefox, + all modules have been “objectified”. And while they are still imported via “require” + in the previous extensions, they are loaded as background scripts in WebExtension sharing + the same memory space… + + When JavaScript become a modern language, “deobjectify” the modules… + + ATM, import/export are not available by default: + — Chrome 60 – behind the Experimental Web Platform flag in chrome:flags. + — Firefox 54 – behind the dom.moduleScripts.enabled setting in about:config. + — Edge 15 – behind the Experimental JavaScript Features setting in about:flags. + + https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Statements/import + https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Statements/export +*/ + +"use strict"; + + +console.log("GC Engine Worker [start]"); +//console.log(self); + +importScripts("grammalecte/helpers.js"); +importScripts("grammalecte/str_transform.js"); +importScripts("grammalecte/ibdawg.js"); +importScripts("grammalecte/text.js"); +importScripts("grammalecte/tokenizer.js"); +importScripts("grammalecte/fr/conj.js"); +importScripts("grammalecte/fr/mfsp.js"); +importScripts("grammalecte/fr/phonet.js"); +importScripts("grammalecte/fr/cregex.js"); +importScripts("grammalecte/fr/gc_options.js"); +importScripts("grammalecte/fr/gc_rules.js"); +importScripts("grammalecte/fr/gc_engine.js"); +importScripts("grammalecte/fr/lexicographe.js"); +importScripts("grammalecte/tests.js"); +/* + Warning. + Initialization can’t be completed at startup of the worker, + for we need the path of the extension to load data stored in JSON files. + This path is retrieved in background.js and passed with the event “init”. +*/ /* -try { - console.log("BEFORE"); - //var myhelpers = require('./grammalecte/helpers.js'); - require(['./grammalecte/helpers.js'], function (foo) { - console.log("LOADING"); - echo("MODULE LOADED2"); - }); - console.log("AFTER"); -} -catch (e) { - console.log("\n" + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); - console.error(e); -}*/ - -echo("VA TE FAIRE FOUTRE"); - - - -let gce = null; // module: grammar checker engine -let text = null; -let tkz = null; // module: tokenizer -let lxg = null; // module: lexicographer -let helpers = null; - -let oTokenizer = null; + Message Event Object + https://developer.mozilla.org/en-US/docs/Web/API/MessageEvent +*/ +onmessage = function (e) { + let oParam = e.data[1]; + switch (e.data[0]) { + case "init": + loadGrammarChecker(oParam.sExtensionPath, oParam.sOptions, oParam.sContext); + break; + case "parse": + parse(oParam.sText, oParam.sCountry, oParam.bDebug, oParam.bContext); + break; + case "parseAndSpellcheck": + parseAndSpellcheck(oParam.sText, oParam.sCountry, oParam.bDebug, oParam.bContext); + break; + case "getOptions": + getOptions(); + break; + case "getDefaultOptions": + getDefaultOptions(); + break; + case "setOptions": + setOptions(oParam.sOptions); + break; + case "setOption": + setOption(oParam.sOptName, oParam.bValue); + break; + case "resetOptions": + resetOptions(); + break; + case "fullTests": + fullTests(); + break; + case "getListOfTokens": + getListOfTokens(oParam.sText); + break; + default: + console.log("Unknown command: " + e.data[0]); + } +} + + let oDict = null; -let oLxg = null; - -function loadGrammarChecker (sGCOptions="", sContext="JavaScript") { - if (gce === null) { - try { - gce = require("resource://grammalecte/fr/gc_engine.js"); - helpers = require("resource://grammalecte/helpers.js"); - text = require("resource://grammalecte/text.js"); - tkz = require("resource://grammalecte/tokenizer.js"); - lxg = require("resource://grammalecte/fr/lexicographe.js"); - oTokenizer = new tkz.Tokenizer("fr"); - helpers.setLogOutput(console.log); - gce.load(sContext); - oDict = gce.getDictionary(); - oLxg = new lxg.Lexicographe(oDict); - if (sGCOptions !== "") { - gce.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); - } - // we always retrieve options from the gce, for setOptions filters obsolete options - return gce.getOptions()._toString(); - } - catch (e) { - console.log("# Error: " + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); - } - } -} - -function parse (sText, sLang, bDebug, bContext) { - let aGrammErr = gce.parse(sText, sLang, bDebug, bContext); - return JSON.stringify(aGrammErr); -} - -function parseAndSpellcheck (sText, sLang, bDebug, bContext) { - let aGrammErr = gce.parse(sText, sLang, bDebug, bContext); - let aSpellErr = oTokenizer.getSpellingErrors(sText, oDict); - return JSON.stringify({ aGrammErr: aGrammErr, aSpellErr: aSpellErr }); +let oTokenizer = null; +let oLxg = null; +let oTest = null; + + +function loadGrammarChecker (sExtensionPath, sGCOptions="", sContext="JavaScript") { + try { + console.log("Loading… Extension path: " + sExtensionPath); + 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("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"); + oLxg = new Lexicographe(oDict); + if (sGCOptions !== "") { + gc_engine.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); + } + oTokenizer = new Tokenizer("fr"); + tests(); + // we always retrieve options from the gc_engine, for setOptions filters obsolete options + postMessage(["options", gc_engine.getOptions().gl_toString()]); + } + catch (e) { + console.error(e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); + postMessage(["error", e.message]); + } +} + +function parse (sText, sCountry, bDebug, bContext) { + let aGrammErr = gc_engine.parse(sText, sCountry, bDebug, bContext); + postMessage(["grammar_errors", {aGrammErr: aGrammErr}]); +} + +function parseAndSpellcheck (sText, sCountry, bDebug, bContext) { + let aGrammErr = gc_engine.parse(sText, sCountry, bDebug, bContext); + let aSpellErr = oTokenizer.getSpellingErrors(sText, oDict); + postMessage(["spelling_and_grammar_errors", {aGrammErr: aGrammErr, aSpellErr: aSpellErr}]); } function getOptions () { - return gce.getOptions()._toString(); + postMessage(["options", gc_engine.getOptions().gl_toString()]); } function getDefaultOptions () { - return gce.getDefaultOptions()._toString(); + postMessage(["options", gc_engine.getDefaultOptions().gl_toString()]); } function setOptions (sGCOptions) { - gce.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); - return gce.getOptions()._toString(); + gc_engine.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); + postMessage(["options", gc_engine.getOptions().gl_toString()]); } function setOption (sOptName, bValue) { - gce.setOptions(new Map([ [sOptName, bValue] ])); - return gce.getOptions()._toString(); + gc_engine.setOptions(new Map([ [sOptName, bValue] ])); + postMessage(["options", gc_engine.getOptions().gl_toString()]); } function resetOptions () { - gce.resetOptions(); - return gce.getOptions()._toString(); -} - -function fullTests (sGCOptions="") { - if (!gce || !oDict) { - return "# Error: grammar checker or dictionary not loaded." - } - let dMemoOptions = gce.getOptions(); - if (sGCOptions) { - gce.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); - } - let tests = require("resource://grammalecte/tests.js"); - let oTest = new tests.TestGrammarChecking(gce); - let sAllRes = ""; - for (let sRes of oTest.testParse()) { - dump(sRes+"\n"); - sAllRes += sRes+"\n"; - } - gce.setOptions(dMemoOptions); - return sAllRes; + gc_engine.resetOptions(); + postMessage(["options", gc_engine.getOptions().gl_toString()]); +} + +function tests () { + console.log(conj.getConj("devenir", ":E", ":2s")); + console.log(mfsp.getMasForm("emmerdeuse", true)); + console.log(mfsp.getMasForm("pointilleuse", false)); + console.log(phonet.getSimil("est")); + let aRes = gc_engine.parse("Je suit..."); + for (let oErr of aRes) { + console.log(text.getReadableError(oErr)); + } +} + +function fullTests (sGCOptions='{"nbsp":true, "esp":true, "unit":true, "num":true}') { + if (!gc_engine || !oDict) { + postMessage(["error", "# Error: grammar checker or dictionary not loaded."]); + return; + } + let dMemoOptions = gc_engine.getOptions(); + if (sGCOptions) { + gc_engine.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); + } + let sMsg = ""; + for (let sRes of oTest.testParse()) { + sMsg += sRes + "\n"; + console.log(sRes); + } + gc_engine.setOptions(dMemoOptions); + postMessage(["tests_results", sMsg]); } // Lexicographer -function getListOfElements (sText) { +function getListOfTokens (sText) { try { let aElem = []; let aRes = null; for (let oToken of oTokenizer.genTokens(sText)) { aRes = oLxg.getInfoForToken(oToken); if (aRes) { aElem.push(aRes); } } - return JSON.stringify(aElem); + postMessage(["tokens", aElem]); } catch (e) { helpers.logerror(e); - } - return JSON.stringify([]); -} - - -function handleMessage (oRequest, xSender, sendResponse) { - console.log(`[background] received: ${oRequest.content}`); - sendResponse({response: "response from background script"}); -} - -browser.runtime.onMessage.addListener(handleMessage); - - + postMessage(["error", e.message]); + } +} Index: gc_lang/fr/webext/manifest.json ================================================================== --- gc_lang/fr/webext/manifest.json +++ gc_lang/fr/webext/manifest.json @@ -11,11 +11,10 @@ } }, "author": "Olivier R.", "homepage_url": "https://grammalecte.net", - "offline_enabled": true, "description": "Correcteur grammatical pour le français.", "icons": { "16": "img/logo-16.png", "32": "img/logo-32.png", @@ -28,16 +27,20 @@ "default_popup": "panel/main.html", "default_title": "Grammalecte [fr]", "browser_style": false }, "background": { - "scripts": ["require.js", "grammalecte/helpers.js", "gce_worker.js"] + "scripts": [ + "background.js" + ] }, "web_accessible_resources": [ - "beasts/frog.jpg", - "beasts/turtle.jpg", - "beasts/snake.jpg" + "grammalecte/_dictionaries/French.json", + "grammalecte/fr/conj_data.json", + "grammalecte/fr/mfsp_data.json", + "grammalecte/fr/phonet_data.json", + "grammalecte/fr/tests_data.json" ], "permissions": [ "activeTab" ] } Index: gc_lang/fr/xpi/data/conj_panel.js ================================================================== --- gc_lang/fr/xpi/data/conj_panel.js +++ gc_lang/fr/xpi/data/conj_panel.js @@ -69,11 +69,11 @@ if (sVerb.endsWith("?")) { document.getElementById('oint').checked = true; sVerb = sVerb.slice(0,-1).trim(); } - if (!isVerb(sVerb)) { + if (!conj.isVerb(sVerb)) { document.getElementById('verb').style = "color: #BB4411;"; } else { self.port.emit("show"); document.getElementById('verb_title').textContent = sVerb; document.getElementById('verb').style = "color: #999999;"; Index: gc_lang/fr/xpi/gce_worker.js ================================================================== --- gc_lang/fr/xpi/gce_worker.js +++ gc_lang/fr/xpi/gce_worker.js @@ -77,17 +77,17 @@ worker.log("# Error: " + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); } } } -function parse (sText, sLang, bDebug, bContext) { - let aGrammErr = gce.parse(sText, sLang, bDebug, bContext); +function parse (sText, sCountry, bDebug, bContext) { + let aGrammErr = gce.parse(sText, sCountry, bDebug, bContext); return JSON.stringify(aGrammErr); } -function parseAndSpellcheck (sText, sLang, bDebug, bContext) { - let aGrammErr = gce.parse(sText, sLang, bDebug, bContext); +function parseAndSpellcheck (sText, sCountry, bDebug, bContext) { + let aGrammErr = gce.parse(sText, sCountry, bDebug, bContext); let aSpellErr = oTokenizer.getSpellingErrors(sText, oDict); return JSON.stringify({ aGrammErr: aGrammErr, aSpellErr: aSpellErr }); } function getOptions () { Index: make.py ================================================================== --- make.py +++ make.py @@ -348,15 +348,15 @@ tests.perf(sVersion, hDst) # Firefox if xArgs.firefox: with helpers.cd("_build/xpi/"+sLang): - os.system("jpm run -b nightly") + os.system('jpm run -b "' + dVars['fx_dev_path'] + '"') if xArgs.web_ext: with helpers.cd("_build/webext/"+sLang): - os.system(r'web-ext run --firefox="' + dVars['fx_beta_path'] + '" --browser-console') + os.system(r'web-ext run --firefox="' + dVars['fx_nightly_path'] + '" --browser-console') # Thunderbird if xArgs.thunderbird: os.system("thunderbird -jsconsole -P debug") else: