Changes In Branch webext2 Through [d0f7053d0f] Excluding Merge-Ins
This is equivalent to a diff from 6af1e457f4 to d0f7053d0f
2017-08-06
| ||
13:27 | [build] don’t use Firefox nightly for Addon-SDK tests -> developper edition check-in: 97544c27f2 user: olr tags: build, webext2 | |
12:22 | [core][fr][js] merge webext2_fix: code cleaning + bug fixes + remove Array comprehensions (for compatibility) check-in: d0f7053d0f user: olr tags: fr, core, webext2 | |
12:14 | [core][js] set echo as console.log if no require available check-in: 7cc552ce5a user: olr tags: core, webext2_fix | |
2017-08-05
| ||
16:01 | [fx] test with Nightly again check-in: 578863e008 user: olr tags: fx, webext2 | |
2017-08-01
| ||
09:50 | [core][py] variable renaming check-in: 1b98af1338 user: olr tags: trunk, core | |
2017-07-31
| ||
15:31 | [core][js] helpers as object check-in: 1140b979f8 user: olr tags: core, webext2 | |
07:52 | [core][js] text: remove useless functions check-in: 6af1e457f4 user: olr tags: trunk, core | |
07:44 | [core][js][fr] JavaScript sucks: avoid weird and unpredictable behavior, infinite loop and similar crazyness -> stable number of groups in regex check-in: 20ec5b88a4 user: olr tags: trunk, core, warning | |
Modified gc_core/js/helpers.js from [da0905c944] to [8fee48eb89].
1 2 3 4 5 6 7 8 9 | // HELPERS "use strict"; // In Firefox, there is no console.log in PromiseWorker, but there is worker.log. // In Thunderbird, you can’t access to console directly. So it’s required to pass a log function. let funcOutput = null; | > > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | < | | | | < | | | | | | | | | | | | | | | < | | | | | | | | | | | | | | | | > | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | // HELPERS "use strict"; // In Firefox, there is no console.log in PromiseWorker, but there is worker.log. // In Thunderbird, you can’t access to console directly. So it’s required to pass a log function. let funcOutput = null; var helpers = { setLogOutput: function (func) { 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 = 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; } |
Modified gc_core/js/ibdawg.js from [e748c8288e] to [cdddd20c84].
1 2 3 4 | //// IBDAWG "use strict"; | > > | | > | > | < < | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | //// IBDAWG "use strict"; 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} class IBDAWG { // INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH constructor (sDicName, sPath="") { try { let sURL = (sPath !== "") ? sPath + "/" + sDicName : "resource://grammalecte/_dictionaries/"+sDicName; const dict = JSON.parse(helpers.loadFile(sURL)); Object.assign(this, dict); } catch (e) { throw Error("# Error. File not found or not loadable.\n" + e.message + "\n"); } /* Properties: sName, nVersion, sHeader, lArcVal, nArcVal, byDic, sLang, nChar, nBytesArc, nBytesNodeAddress, nEntries, nNode, nArc, nAff, cStemming, nTag, dChar, _arcMask, _finalNodeMask, _lastArcMask, _addrBitMask, nBytesOffset, */ if (!this.sHeader.startsWith("/pyfsa/")) { throw TypeError("# Error. Not a pyfsa binary dictionary. Header: " + this.sHeader); } if (!(this.nVersion == "1" || this.nVersion == "2" || this.nVersion == "3")) { throw RangeError("# Error. Unknown dictionary version: " + this.nVersion); } this.dChar = helpers.objectToMap(this.dChar); //this.byDic = new Uint8Array(this.byDic); // not quicker, even slower if (this.cStemming == "S") { this.funcStemming = str_transform.getStemFromSuffixCode; } else if (this.cStemming == "A") { this.funcStemming = str_transform.getStemFromAffixCode; } else { this.funcStemming = str_transform.noStemming; } // Configuring DAWG functions according to nVersion switch (this.nVersion) { case 1: this.morph = this._morph1; this.stem = this._stem1; |
︙ | ︙ | |||
70 71 72 73 74 75 76 | break; default: throw ValueError("# Error: unknown code: " + this.nVersion); } //console.log(this.getInfo()); this.bOptNumSigle = true; this.bOptNumAtLast = false; | < > < > < > | 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 | break; default: 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; } if (sToken.includes("-")) { if (sToken.gl_count("-") > 4) { 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; } if (sWord.includes("’")) { // ugly hack |
︙ | ︙ | |||
121 122 123 124 125 126 127 | } return !!this.lookup(sWord.slice(0, 1).toLowerCase() + sWord.slice(1)); } else { return !!this.lookup(sWord.toLowerCase()); } } return false; | < > < > < > < > | | 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | } return !!this.lookup(sWord.slice(0, 1).toLowerCase() + sWord.slice(1)); } 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; 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) { if (!this.dChar.has(c)) { return false; } iAddr = this._lookupArcNode(this.dChar.get(c), iAddr); 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()) { l = l.concat(this.morph(sWord.toLowerCase())); 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; for (let c of sWord) { if (!this.dChar.has(c)) { |
︙ | ︙ | |||
203 204 205 206 207 208 209 | } } iAddr = iEndArcAddr + this.nBytesNodeAddress; } return l; } return []; | < > | 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | } } iAddr = iEndArcAddr + this.nBytesNodeAddress; } return l; } return []; } _stem1 (sWord) { // returns stems list of sWord let iAddr = 0; for (let c of sWord) { if (!this.dChar.has(c)) { return []; |
︙ | ︙ | |||
233 234 235 236 237 238 239 | l.push(this.funcStemming(sWord, this.lArcVal[nArc])); } iAddr = iEndArcAddr + this.nBytesNodeAddress; } return l; } return []; | < > < > < > < > < > < > < > < > | 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | l.push(this.funcStemming(sWord, this.lArcVal[nArc])); } 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; let nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr)); if (nVal == (nRawArc & this._arcMask)) { // the value we are looking for // we return the address of the next node return this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress)); } else { // value not found if (nRawArc & this._lastArcMask) { 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; } |
Modified gc_core/js/jsex_map.js from [985754ee9e] to [ca76af0666].
1 2 3 4 5 6 7 8 9 10 | // Map if (Map.prototype.grammalecte === undefined) { Map.prototype.gl_shallowCopy = function () { let oNewMap = new Map(); for (let [key, val] of this.entries()) { oNewMap.set(key, val); } return oNewMap; | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 | // Map if (Map.prototype.grammalecte === undefined) { Map.prototype.gl_shallowCopy = function () { 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) + " }"; 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; } |
Modified gc_core/js/jsex_regex.js from [b8b02d05dd] to [8feeee694f].
︙ | ︙ | |||
38 39 40 41 42 43 44 | m.end.push(m.index + codePos + m[i].length); } else if (codePos === "$") { // 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 | | | | | | 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | m.end.push(m.index + codePos + m[i].length); } else if (codePos === "$") { // at the end of the pattern m.start.push(this.lastIndex - m[i].length); m.end.push(this.lastIndex); } else if (codePos === "w") { // word in the middle of the pattern iPos = m[0].search("[ ’,()«»“”]"+m[i]+"[ ,’()«»“”]") + 1 + m.index; m.start.push(iPos); m.end.push(iPos + m[i].length); } else if (codePos === "*") { // anywhere iPos = m[0].indexOf(m[i]) + m.index; m.start.push(iPos); m.end.push(iPos + m[i].length); } else if (codePos === "**") { // anywhere after previous group iPos = m[0].indexOf(m[i], m.end[i-1]-m.index) + m.index; m.start.push(iPos); m.end.push(iPos + m[i].length); } else if (codePos.startsWith(">")) { // >x:_ // todo: look in substring x iPos = m[0].indexOf(m[i]) + m.index; m.start.push(iPos); m.end.push(iPos + m[i].length); } else { |
︙ | ︙ | |||
79 80 81 82 83 84 85 | if (typeof(helpers) !== "undefined") { helpers.logerror(e); } else { console.error(e); } } return m; | | | 79 80 81 82 83 84 85 86 87 88 89 | if (typeof(helpers) !== "undefined") { helpers.logerror(e); } else { console.error(e); } } return m; }; RegExp.prototype.grammalecte = true; } |
Modified gc_core/js/jsex_string.js from [1e9c89a872] to [86533aa4da].
︙ | ︙ | |||
11 12 13 14 15 16 17 | let iPos = 0; let nStep = (bOverlapping) ? 1 : sSearch.length; while ((iPos = this.indexOf(sSearch, iPos)) >= 0) { nOccur++; iPos += nStep; } return nOccur; | | | | | | | | | | | | 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | let iPos = 0; let nStep = (bOverlapping) ? 1 : sSearch.length; while ((iPos = this.indexOf(sSearch, iPos)) >= 0) { nOccur++; iPos += nStep; } return nOccur; }; String.prototype.gl_isDigit = function () { return (this.search(/^[0-9⁰¹²³⁴⁵⁶⁷⁸⁹]+$/) !== -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; } |
Modified gc_core/js/lang_core/gc_engine.js from [ce3013cd59] to [46602d3f85].
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 | // Grammar checker engine ${string} ${regex} ${map} function capitalizeArray (aArray) { // can’t map on user defined function?? let aNew = []; for (let i = 0; i < aArray.length; i = i + 1) { aNew[i] = aArray[i].gl_toCapitalize(); } return aNew; } | > > > > > > > > > > > > > > > > > < < < < < < < < < < < < | < < < < < < < | < | > > > > > > > > > > > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > | > > > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > < | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > | > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > | > > > | > > | | | > > | > > > | | | | | | | | < | | | > | | > | < < < | | | | | | | | | | | | < < | < | | | | | | | | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 | // 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) { aNew[i] = aArray[i].gl_toCapitalize(); } return aNew; } // 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 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]; }, _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) { helpers.echo("> nothing to find"); return true; } if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) { helpers.echo("> not in FSA"); return true; } if (dDA.has(aWord[0])) { helpers.echo("DA: " + dDA.get(aWord[0])); } helpers.echo("FSA: " + _dAnalyses.get(aWord[1])); return true; } function _storeMorphFromFSA (sWord) { // retrieves morphologies list from _oDict -> _dAnalyses //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) { //helpers.echo("morph: noword, returns " + bNoWord); return bNoWord; } //helpers.echo("aWord: "+aWord.toString()); if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) { return false; } let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]); //helpers.echo("lMorph: "+lMorph.toString()); if (lMorph.length === 0) { return false; } //helpers.echo("***"); if (bStrict) { return lMorph.every(s => (s.search(sPattern) !== -1)); } return lMorph.some(s => (s.search(sPattern) !== -1)); } function morphex (dDA, aWord, sPattern, sNegPattern, bNoWord=false) { // analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on) if (!aWord) { //helpers.echo("morph: noword, returns " + bNoWord); return bNoWord; } //helpers.echo("aWord: "+aWord.toString()); if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) { return false; } let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]); //helpers.echo("lMorph: "+lMorph.toString()); if (lMorph.length === 0) { return false; } //helpers.echo("***"); // check negative condition if (lMorph.some(s => (s.search(sNegPattern) !== -1))) { return false; } // search sPattern return lMorph.some(s => (s.search(sPattern) !== -1)); } |
︙ | ︙ | |||
447 448 449 450 451 452 453 | // returns a list of sWord's stems if (!sWord) { return []; } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return []; } | | | | | < < < > | > > < < < < | 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 | // returns a list of sWord's stems if (!sWord) { return []; } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return []; } 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%_-]+)", "ig"); let m = z.exec(s.slice(iStart)); if (!m) { return null; } 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() + "}$", "i"); let m = z.exec(s.slice(0, iEnd)); if (!m) { return null; } return [m.index, m[1]]; } function nextword1 (s, iStart) { // get next word (optimization) let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*)", "ig"); let m = _zNextWord.exec(s.slice(iStart)); if (!m) { return null; } return [iStart + _zNextWord.lastIndex - m[1].length, m[1]]; } const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*) +$", "i"); function prevword1 (s, iEnd) { // get previous word (optimization) let m = _zPrevWord.exec(s.slice(0, iEnd)); if (!m) { return null; } return [m.index, m[1]]; } function look (s, zPattern, zNegPattern=null) { // seek zPattern in s (before/after/fulltext), if antipattern zNegPattern not in s try { if (zNegPattern && zNegPattern.test(s)) { |
︙ | ︙ | |||
547 548 549 550 551 552 553 | } if (dDA.has(nPos)) { return true; } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return true; } | < | < | 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 | } if (dDA.has(nPos)) { return true; } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return true; } if (_dAnalyses.get(sWord).length === 1) { return true; } 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) { dDA.set(nPos, lDefaul); } |
︙ | ︙ | |||
576 577 578 579 580 581 582 | } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return true; } if (_dAnalyses.get(sWord).length === 1) { return true; } | | < > | > | | | > > > > > > > > > > > > > > > | | | | | | < < < < | 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 | } if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return true; } if (_dAnalyses.get(sWord).length === 1) { return true; } 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) { dDA.set(nPos, lDefault); } return true; } function define (dDA, nPos, lMorph) { dDA.set(nPos, lMorph); return true; } //////// GRAMMAR CHECKER PLUGINS ${pluginsJS} ${callablesJS} if (typeof(exports) !== 'undefined') { 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; } |
Modified gc_core/js/lang_core/gc_options.js from [6e45d077d4] to [ba36100a98].
1 2 3 4 | // Options for Grammalecte ${map} | > > | | | | | | | | | | | | | | > | | > | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 | // Options for Grammalecte ${map} 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 = gc_options.getOptions; exports.lStructOpt = gc_options.lStructOpt; exports.dOpt = gc_options.dOpt; exports.dOptLabel = gc_options.dOptLabel; } |
Modified gc_core/js/lang_core/gc_rules.js from [03bc540fb7] to [02fc1d6f94].
1 2 3 4 5 6 | // Grammar checker rules "use strict"; ${string} ${regex} | > | | > | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 | // Grammar checker rules "use strict"; ${string} ${regex} var gc_rules = { lParagraphRules: ${paragraph_rules_JS}, lSentenceRules: ${sentence_rules_JS} } if (typeof(exports) !== 'undefined') { exports.lParagraphRules = gc_rules.lParagraphRules; exports.lSentenceRules = gc_rules.lSentenceRules; } |
Modified gc_core/js/str_transform.js from [0fafeda9a5] to [3f33d76266].
1 2 | //// STRING TRANSFORMATION | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < > > | < | | | | | | > | < | | | | | | | | | | > | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | //// STRING TRANSFORMATION // Note: 48 is the ASCII code for "0" 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 = str_transform.getStemFromSuffixCode; exports.getStemFromAffixCode = str_transform.getStemFromAffixCode; } |
Modified gc_core/js/tests.js from [f2f737b523] to [abe05a3485].
1 2 3 4 5 | // JavaScript "use strict"; | > | > | > < > > | < | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 | // JavaScript "use strict"; if (typeof(require) !== 'undefined') { var helpers = require("resource://grammalecte/helpers.js"); } class TestGrammarChecking { constructor (gce, spfTests="") { this.gce = gce; this.spfTests = spfTests; this._aRuleTested = new Set(); } * testParse (bDebug=false) { const t0 = Date.now(); 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; let sListErr; let sLineNum; |
︙ | ︙ | |||
57 58 59 60 61 62 63 | if (sExpectedErrors !== sFoundErrors) { yield "\n" + i.toString() + "\n# Line num: " + sLineNum + "\n> to check: " + sTextToCheck + "\n expected: " + sExpectedErrors + "\n found: " + sFoundErrors + "\n errors: \n" + sListErr; | | | < > | 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | if (sExpectedErrors !== sFoundErrors) { yield "\n" + i.toString() + "\n# Line num: " + sLineNum + "\n> to check: " + sTextToCheck + "\n expected: " + sExpectedErrors + "\n found: " + sFoundErrors + "\n errors: \n" + sListErr; nInvalid = nInvalid + 1; } nTotal = nTotal + 1; } i = i + 1; if (i % 1000 === 0) { yield i.toString(); } } bShowUntested = true; } catch (e) { helpers.logerror(e); } if (bShowUntested) { i = 0; for (let [sOpt, sLineId, sRuleId] of this.gce.listRules()) { if (!this._aRuleTested.has(sLineId) && !/^[0-9]+[sp]$|^[pd]_/.test(sRuleId)) { sUntestedRules += sRuleId + ", "; i += 1; } } if (i > 0) { yield sUntestedRules + "\n[" + i.toString() + " untested rules]"; } } 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; let m; let i = 0; |
︙ | ︙ | |||
114 115 116 117 118 119 120 | } return sRes; } catch (e) { helpers.logerror(e); } return " ".repeat(sLine.length); | < > | | < > | 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 | } return sRes; } catch (e) { helpers.logerror(e); } return " ".repeat(sLine.length); } _getFoundErrors (sLine, bDebug, sOption) { try { let aErrs = []; if (sOption) { this.gce.setOption(sOption, true); aErrs = this.gce.parse(sLine, "FR", bDebug); this.gce.setOption(sOption, false); } else { aErrs = this.gce.parse(sLine, "FR", bDebug); } let sRes = " ".repeat(sLine.length); let sListErr = ""; for (let dErr of aErrs) { sRes = sRes.slice(0, dErr["nStart"]) + "~".repeat(dErr["nEnd"] - dErr["nStart"]) + sRes.slice(dErr["nEnd"]); sListErr += " * {" + dErr['sLineId'] + " / " + dErr['sRuleId'] + "} at " + dErr['nStart'] + ":" + dErr['nEnd'] + "\n"; this._aRuleTested.add(dErr["sLineId"]); } return [sRes, sListErr]; } catch (e) { helpers.logerror(e); } return [" ".repeat(sLine.length), ""]; } } if (typeof(exports) !== 'undefined') { exports.TestGrammarChecking = TestGrammarChecking; } |
Modified gc_core/js/text.js from [beffb97d58] to [46a1749c2b].
1 2 3 4 | // JavaScript "use strict"; | > > | | > > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | // JavaScript "use strict"; 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 = text.getParagraph; exports.wrap = text.wrap; exports.getReadableError = text.getReadableError; } |
Modified gc_core/js/tokenizer.js from [a6594366c3] to [fcd058bf6a].
1 2 3 4 5 | // JavaScript // Very simple tokenizer "use strict"; | > > | | > > | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 | // JavaScript // Very simple tokenizer "use strict"; if (typeof(exports) !== 'undefined') { var helpers = require("resource://grammalecte/helpers.js"); } const aTkzPatterns = { // All regexps must start with ^. "default": [ [/^[ \t]+/, 'SPACE'], [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'], [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.])[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'], [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'], |
︙ | ︙ | |||
31 32 33 34 35 36 37 | [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'], [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`]/i, 'ELPFX'], [/^\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'] ] | | | | < > | 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'], [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`]/i, 'ELPFX'], [/^\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 (!aTkzPatterns.hasOwnProperty(sLang)) { this.sLang = "default"; } this.aRules = aTkzPatterns[this.sLang]; } * genTokens (sText) { let m; let i = 0; while (sText) { let nCut = 1; for (let [zRegex, sType] of this.aRules) { |
︙ | ︙ | |||
70 71 72 73 74 75 76 | catch (e) { helpers.logerror(e); } } i += nCut; sText = sText.slice(nCut); } | < > | 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | catch (e) { helpers.logerror(e); } } 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)) { aSpellErr.push(oToken); } |
︙ | ︙ |
Modified gc_core/py/lang_core/gc_engine.py from [4742310603] to [27a1e1120d].
︙ | ︙ | |||
470 471 472 473 474 475 476 | ## functions to get text outside pattern scope # 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" | | | | | 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 | ## functions to get text outside pattern scope # 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:]) if not m: return None 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]) if not m: return None return (m.start(1), m.group(1)) def nextword1 (s, iStart): "get next word (optimization)" |
︙ | ︙ |
Modified gc_lang/fr/modules-js/conj.js from [4856ca7520] to [ab8249cda2].
1 2 3 4 5 6 7 8 | // Grammalecte - Conjugueur // License: GPL 3 "use strict"; ${map} | < | < | | | | | < < < < < < < < | < < < | | | | | < | > > | > | | | | | | | | | | | < | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | < | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | < > | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | // Grammalecte - Conjugueur // License: GPL 3 "use strict"; ${map} var conj = { _lVtyp: [], _lTags: [], _dPatternConj: {}, _dVerb: {}, init: function (sJSONData) { try { let _oData = JSON.parse(sJSONData); this._lVtyp = _oData.lVtyp; this._lTags = _oData.lTags; this._dPatternConj = _oData.dPatternConj; this._dVerb = _oData.dVerb; } catch (e) { console.error(e); } }, _zStartVoy: new RegExp("^[aeéiouœê]"), _zNeedTeuph: new RegExp("[tdc]$"), _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) { if (typeof sVerb !== "string" || sVerb === "") { throw new TypeError ("The value should be a non-empty string"); } this.sVerb = sVerb; this.sVerbAux = ""; this._sRawInfo = conj.getVtyp(this.sVerb); this.sInfo = this._readableInfo(this._sRawInfo); 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", 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", 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", 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", 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", 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", 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", 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", 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", 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 = 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"; } else if (this._sRawInfo.slice(2,3) == "i") { sInfo = "intransitif"; |
︙ | ︙ | |||
308 309 310 311 312 313 314 | if (this._sRawInfo.slice(6,7) == "m") { sInfo = sInfo + " impersonnel"; } if (sInfo === "") { sInfo = "# erreur - code : " + this._sRawInfo; } return sGroup + " · " + sInfo; | < > | < > < > | | < > | | | | | < > | < > | | | | | < > > | > > > > > > > > > > > > > > > | | > > > > > | > > > > > > > > > > > | | | | | | > | > | | 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 | if (this._sRawInfo.slice(6,7) == "m") { sInfo = sInfo + " impersonnel"; } 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; } else { sInfi = this.sVerb; } if (bPro) { if (this.bProWithEn) { sInfi = "s’en " + sInfi; } else { sInfi = (conj._zStartVoy.test(sInfi)) ? "s’" + sInfi : "se " + sInfi; } } if (bNeg) { sInfi = "ne pas " + sInfi; } if (bTpsCo) { sInfi += " " + this._seekPpas(bPro, bFem, (this._sRawInfo[5] == "r")); } 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) ? 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 = conj._zStartVoy.test(sPartPre); if (bPro) { if (this.bProWithEn) { sPartPre = "s’en " + sPartPre; } else { sPartPre = (bEli) ? "s’" + sPartPre : "se " + sPartPre; } } if (bNeg) { sPartPre = (bEli && !bPro) ? "n’" + sPartPre + " pas" : "ne " + sPartPre + " pas"; } if (bTpsCo) { sPartPre += " " + this._seekPpas(bPro, bFem, this._sRawInfo[5] == "r"); } if (bInt) { sPartPre += " … ?"; } return sPartPre; } conjugue (sTemps, sWho, bPro, bNeg, bTpsCo, bInt, bFem) { if (!this.dConj.get(sTemps).get(sWho)) { return ""; } let sConj; if (!bTpsCo && bInt && sWho == ":1s" && this.dConj.get(sTemps).gl_get(":1ś", false)) { sWho = ":1ś"; } if (bTpsCo) { 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 = conj._zStartVoy.test(sConj); if (bPro) { if (!this.bProWithEn) { sConj = (bEli) ? conj._dProObjEl.get(sWho) + sConj : conj._dProObj.get(sWho) + sConj; } else { sConj = conj._dProObjEl.get(sWho) + "en " + sConj; } } if (bNeg) { sConj = (bEli && !bPro) ? "n’" + sConj : "ne " + sConj; } if (bInt) { if (sWho == ":3s" && !conj._zNeedTeuph.test(sConj)) { sConj += "-t"; } sConj += "-" + this._getPronom(sWho, bFem); } else { if (sWho == ":1s" && bEli && !bNeg && !bPro) { sConj = "j’" + sConj; } else { sConj = this._getPronom(sWho, bFem) + " " + sConj; } } if (bNeg) { sConj += " pas"; } if (bTpsCo) { sConj += " " + this._seekPpas(bPro, bFem, sWho.endsWith("p") || this._sRawInfo[5] == "r"); } if (bInt) { sConj += " … ?"; } return sConj; } _getPronom (sWho, bFem) { if (sWho == ":3s") { if (this._sRawInfo[5] == "r") { return "on"; } else if (bFem) { return "elle"; } } else if (sWho == ":3p" && bFem) { return "elles"; } 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) ? 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 = conj._zStartVoy.test(sImpe); if (bNeg) { if (bPro) { if (!this.bProWithEn) { sImpe = (bEli && sWho == ":2s") ? "ne t’" + sImpe + " pas" : conj._dImpeProNeg.get(sWho) + sImpe + " pas"; } else { sImpe = conj._dImpeProNegEn.get(sWho) + sImpe + " pas"; } } else { sImpe = (bEli) ? "n’" + sImpe + " pas" : "ne " + sImpe + " pas"; } } else if (bPro) { 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"); } if (!bFem) { return (bPlur && this.dConj.get(":PQ").get(":Q2")) ? this.dConj.get(":PQ").get(":Q2") : this.dConj.get(":PQ").get(":Q1"); } if (!bPlur) { return (this.dConj.get(":PQ").get(":Q3")) ? this.dConj.get(":PQ").get(":Q3") : this.dConj.get(":PQ").get(":Q1"); } 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') { 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; } |
Modified gc_lang/fr/modules-js/cregex.js from [266ea45a85] to [7faa9e5e5e].
1 2 3 | //// Grammalecte - Compiled regular expressions | > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > | > > | | | | | | | | | | | | | | > > > > > > > > > > > > > > > > > | > > > > > > > > > > > > > > > > > > > > > > > > > > | | | | | | | | | | | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 | //// Grammalecte - Compiled regular expressions 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._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; } |
Modified gc_lang/fr/modules-js/gce_analyseur.js from [673094989d] to [0ad6fe5843].
︙ | ︙ | |||
18 19 20 21 22 23 24 | return "vous"; } 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 | | | | | | | | | | | | | | | 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 | return "vous"; } 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 (cregex.mbNprMasNotFem(_dAnalyses.gl_get(s1, ""))) { return "ils"; } // si épicène, indéterminable, mais OSEF, le féminin l’emporte return "elles"; } return s1 + " et " + s2; } 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 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 (!cregex.mbNomAdj(_dAnalyses.gl_get(sWord, "")) || sWord == "est") { return false; } if (cregex.mbVconj(_dAnalyses.gl_get(sWord, "")) && !cregex.mbMG(_dAnalyses.gl_get(sWord, ""))) { return true; } return false; } function isAmbiguousAndWrong (sWord1, sWord2, sReqMorphNA, sReqMorphConj) { //// use it if sWord1 won’t be 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); if (!a2 || a2.length === 0) { return false; } 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 (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); if (!a2 || a2.length === 0) { return false; } 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 (cregex.checkAgreement(a1, a2) && (cregex.mbAdj(a2) || cregex.mbAdjNb(a1))) { return false; } // now, we know there no agreement, and conjugation is also wrong if (cregex.isNomAdj(a1)) { return 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); if (!a2 || a2.length === 0) { return true; } let a1 = _dAnalyses.gl_get(sWord1, null); if (!a1 || a1.length === 0) { return true; } return cregex.checkAgreement(a1, a2); } function mbUnit (s) { if (/[µ\/⁰¹²³⁴⁵⁶⁷⁸⁹Ωℓ·]/.test(s)) { return true; } if (s.length > 1 && s.length < 16 && s.slice(0, 1).gl_isLowerCase() && (!s.slice(1).gl_isLowerCase() || /[0-9]/.test(s))) { |
︙ | ︙ |
Modified gc_lang/fr/modules-js/gce_suggestions.js from [d46530bfae] to [db0ba9f8a1].
1 2 | //// GRAMMAR CHECKING ENGINE PLUGIN: Suggestion mechanisms | > | | | > | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 | //// GRAMMAR CHECKING ENGINE PLUGIN: Suggestion mechanisms 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) { // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before let aSugg = new Set(); for (let sStem of stem(sFlex)) { let tTags = conj._getTags(sStem); 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)) !== 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"); aTense.add(":Is"); } else if (m[1] === ":P") { |
︙ | ︙ | |||
137 138 139 140 141 142 143 | if (aSugg.size > 0) { return Array.from(aSugg).join("|"); } return ""; } function suggVerbInfi (sFlex) { | | < | 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | if (aSugg.size > 0) { return Array.from(aSugg).join("|"); } return ""; } function suggVerbInfi (sFlex) { return stem(sFlex).filter(sStem => conj.isVerb(sStem)).join("|"); } const _dQuiEst = new Map ([ ["je", ":1s"], ["j’", ":1s"], ["j’en", ":1s"], ["j’y", ":1s"], ["tu", ":2s"], ["il", ":3s"], ["on", ":3s"], ["elle", ":3s"], ["nous", ":1p"], ["vous", ":2p"], ["ils", ":3p"], ["elles", ":3p"] |
︙ | ︙ | |||
193 194 195 196 197 198 199 | function suggPlur (sFlex, sWordToAgree=null) { // returns plural forms assuming sFlex is singular if (sWordToAgree) { if (!_dAnalyses.has(sWordToAgree) && !_storeMorphFromFSA(sWordToAgree)) { return ""; } | | | 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | function suggPlur (sFlex, sWordToAgree=null) { // returns plural forms assuming sFlex is singular if (sWordToAgree) { if (!_dAnalyses.has(sWordToAgree) && !_storeMorphFromFSA(sWordToAgree)) { return ""; } let sGender = cregex.getGender(_dAnalyses.gl_get(sWordToAgree, [])); if (sGender == ":m") { return suggMasPlur(sFlex); } else if (sGender == ":f") { return suggFemPlur(sFlex); } } let aSugg = new Set(); |
︙ | ︙ | |||
259 260 261 262 263 264 265 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":m") || sMorph.includes(":e")) { aSugg.add(suggSing(sFlex)); } else { | | | | 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":m") || sMorph.includes(":e")) { aSugg.add(suggSing(sFlex)); } else { let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { mfsp.getMasForm(sStem, false).forEach(function(x) { aSugg.add(x); }); } } } else { // a verb 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")); } } } |
︙ | ︙ | |||
295 296 297 298 299 300 301 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":m") || sMorph.includes(":e")) { aSugg.add(suggPlur(sFlex)); } else { | | | | 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":m") || sMorph.includes(":e")) { aSugg.add(suggPlur(sFlex)); } else { let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { mfsp.getMasForm(sStem, true).forEach(function(x) { aSugg.add(x); }); } } } else { // a verb 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 if (sSugg.endsWith("s")) { aSugg.add(sSugg); |
︙ | ︙ | |||
336 337 338 339 340 341 342 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":f") || sMorph.includes(":e")) { aSugg.add(suggSing(sFlex)); } else { | | | | 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":f") || sMorph.includes(":e")) { aSugg.add(suggSing(sFlex)); } else { let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { aSugg.add(sStem); } } } else { // a verb let sVerb = cregex.getLemmaOfMorph(sMorph); if (conj.hasConj(sVerb, ":PQ", ":Q3")) { aSugg.add(conj.getConj(sVerb, ":PQ", ":Q3")); } } } if (bSuggSimil) { for (let e of phonet.selectSimil(sFlex, ":f:[si]")) { |
︙ | ︙ | |||
370 371 372 373 374 375 376 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":f") || sMorph.includes(":e")) { aSugg.add(suggPlur(sFlex)); } else { | | | | 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 | let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (!sMorph.includes(":V")) { // not a verb if (sMorph.includes(":f") || sMorph.includes(":e")) { aSugg.add(suggPlur(sFlex)); } else { let sStem = cregex.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { aSugg.add(sStem+"s"); } } } else { // a verb let sVerb = cregex.getLemmaOfMorph(sMorph); if (conj.hasConj(sVerb, ":PQ", ":Q4")) { aSugg.add(conj.getConj(sVerb, ":PQ", ":Q4")); } } } if (bSuggSimil) { for (let e of phonet.selectSimil(sFlex, ":f:[pi]")) { |
︙ | ︙ |
Modified gc_lang/fr/modules-js/lexicographe.js from [5e8c9037a7] to [a348883011].
1 2 3 4 5 6 7 8 9 | // Grammalecte - Lexicographe // License: MPL 2 "use strict"; ${string} ${map} | > | < | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 | // Grammalecte - Lexicographe // License: MPL 2 "use strict"; ${string} ${map} if (typeof(exports) !== 'undefined') { var helpers = require("resource://grammalecte/helpers.js"); } const _dTAGS = new Map ([ [':G', "[mot grammatical]"], [':N', " nom,"], [':A', " adjectif,"], [':M1', " prénom,"], [':M2', " patronyme,"], |
︙ | ︙ | |||
195 196 197 198 199 200 201 | class Lexicographe { constructor (oDict) { this.oDict = oDict; this._zElidedPrefix = new RegExp ("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i"); this._zCompoundWord = new RegExp ("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$", "i"); this._zTag = new RegExp ("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*][^:;/]*", "g"); | < > | 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | class Lexicographe { 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; try { switch (oToken.sType) { |
︙ | ︙ | |||
222 223 224 225 226 227 228 | break; case 'WORD': if (oToken.sValue.gl_count("-") > 4) { return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] }; } else if (this.oDict.isValidToken(oToken.sValue)) { let lMorph = this.oDict.getMorph(oToken.sValue); | | > > > | > > > < > < > < > | 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 | break; case 'WORD': if (oToken.sValue.gl_count("-") > 4) { return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] }; } else if (this.oDict.isValidToken(oToken.sValue)) { let lMorph = this.oDict.getMorph(oToken.sValue); let aElem = []; for (let s of lMorph){ if (s.includes(":")) aElem.push( this._formatTags(s) ); } return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem}; } else if (m = this._zCompoundWord.exec(oToken.sValue)) { // mots composés let lMorph = this.oDict.getMorph(m[1]); let aElem = []; for (let s of lMorph){ if (s.includes(":")) aElem.push( this._formatTags(s) ); } aElem.push("-" + m[2] + ": " + this._formatSuffix(m[2].toLowerCase())); return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem }; } else { return { sType: "UNKNOWN", sValue: oToken.sValue, aLabel: ["inconnu du dictionnaire"] }; } break; } } catch (e) { helpers.logerror(e); } return null; } _formatTags (sTags) { let sRes = ""; sTags = sTags.replace(/V([0-3][ea]?)[itpqnmr_eaxz]+/, "V$1"); let m; while ((m = this._zTag.exec(sTags)) !== null) { sRes += _dTAGS.get(m[0]); if (sRes.length > 100) { break; } } if (sRes.startsWith(" verbe") && !sRes.endsWith("infinitif")) { sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]"; } if (!sRes) { sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]"; helpers.echo(sRes); return sRes; } return sRes.gl_trimRight(","); } _formatSuffix (s) { if (s.startsWith("t-")) { return "“t” euphonique +" + _dAD.get(s.slice(2)); } if (!s.includes("-")) { return _dAD.get(s.replace("’", "'")); } if (s.endsWith("ous")) { s += '2'; } let nPos = s.indexOf("-"); return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos+1)); } } if (typeof(exports) !== 'undefined') { exports.Lexicographe = Lexicographe; } |
Modified gc_lang/fr/modules-js/mfsp.js from [404b1b695d] to [5ce8b4f9f6].
1 2 3 4 | // Grammalecte "use strict"; | > > | < | | > | | | < | < | | > > > > > > > > | | > > | > | | | | | | | > > | | > > | | | | | | | | | > > | | > > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > > > > > > > > > > > > > > > > > > | | | | > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | // Grammalecte "use strict"; 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._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; } |
Modified gc_lang/fr/modules-js/phonet.js from [1d899a6d9f] to [742b1a34db].
1 2 | // Grammalecte - Suggestion phonétique | > | > | | > > > > > > | | | | > > | > | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | > > > > > > > > > > > > > > > > > | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | // Grammalecte - Suggestion phonétique 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._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; } |
Modified gc_lang/fr/modules-js/textformatter.js from [7314bcd9a1] to [c6e77daf98].
︙ | ︙ | |||
194 195 196 197 198 199 200 | [/^(qu|lorsqu|puisqu|quoiqu|presqu|jusqu|aujourd|entr|quelqu|prud) /ig, "$1’"] ], "ma_1letter_lowercase": [ [/[ ]([ldjnmtscç]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"] ], "ma_1letter_uppercase": [ [/[ ]([LDJNMTSCÇ]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"], [/^([LDJNMTSCÇ]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"] ] }; | | | 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | [/^(qu|lorsqu|puisqu|quoiqu|presqu|jusqu|aujourd|entr|quelqu|prud) /ig, "$1’"] ], "ma_1letter_lowercase": [ [/[ ]([ldjnmtscç]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"] ], "ma_1letter_uppercase": [ [/[ ]([LDJNMTSCÇ]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"], [/^([LDJNMTSCÇ]) (?=[aàeéêiîoôuyhAÀEÉÊIÎOÔUYH])/g, "$1’"] ] }; const dTFDefaultOptions = new Map ([ ["ts_units", true], ["start_of_paragraph", true], ["end_of_paragraph", true], ["between_words", true], ["before_punctuation", true], ["within_parenthesis", true], ["within_square_brackets", true], |
︙ | ︙ | |||
247 248 249 250 251 252 253 | ["etc", true], ["missing_hyphens", true], ["ma_word", true], ["ma_1letter_lowercase", false], ["ma_1letter_uppercase", false] ]); | | < > | | < | > | | 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 | ["etc", true], ["missing_hyphens", true], ["ma_word", true], ["ma_1letter_lowercase", false], ["ma_1letter_uppercase", false] ]); const dTFOptions = dTFDefaultOptions.gl_shallowCopy(); class TextFormatter { constructor () { this.sLang = "fr"; } formatText (sText, dOpt=null) { if (dOpt !== null) { dTFOptions.gl_updateOnlyExistingKeys(dOpt); } 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 dTFDefaultOptions; } } if (typeof(exports) !== 'undefined') { exports.TextFormatter = TextFormatter; exports.oReplTable = oReplTable; } |
Modified gc_lang/fr/modules/gce_suggestions.py from [948c38b1f8] to [e839f7efe5].
︙ | ︙ | |||
11 12 13 14 15 16 17 | aSugg = set() for sStem in stem(sFlex): 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 | | | 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | aSugg = set() for sStem in stem(sFlex): 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): # 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") aTense.add(":Is") elif m.group(1) == ":P": |
︙ | ︙ |
Modified gc_lang/fr/tb/content/overlay.js from [31d038a91d] to [a6d0f601cc].
︙ | ︙ | |||
908 909 910 911 912 913 914 915 916 917 918 919 920 921 | oTextFormatter.resetProgressBar(); } }, false); window.addEventListener("load", function (xEvent) { oDictIgniter.init(); oGrammarChecker.loadGC(); }, false); window.addEventListener("compose-window-init", function (xEvent) { oGrammarChecker.loadUI(); oGrammarChecker.closePanel(); oGrammarChecker.clearPreview(); oTextFormatter.init(); | > | 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 | oTextFormatter.resetProgressBar(); } }, 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(); |
︙ | ︙ |
Added gc_lang/fr/webext/background.js version [03c66ef198].
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 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); |
Modified gc_lang/fr/webext/gce_worker.js from [8fda2777a3] to [2ab933f7e3].
1 2 3 | /* | > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | | < > | | | > > > > > > > > > > | > > | < > | < > > > > > > | < | < > > > > > > > > | | < < < < < < > > > | < | > | | | > | > | > > > > | < < | < < < < | | | | | > | | | < | | | | | | | | | | | | | > > | > > > > > > > > | | > | | | > | | < < | < | > | < > | | < < < | | < < < < < < < | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 | /* 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”. */ /* 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 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 () { postMessage(["options", gc_engine.getOptions().gl_toString()]); } function getDefaultOptions () { postMessage(["options", gc_engine.getDefaultOptions().gl_toString()]); } function setOptions (sGCOptions) { gc_engine.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); postMessage(["options", gc_engine.getOptions().gl_toString()]); } function setOption (sOptName, bValue) { gc_engine.setOptions(new Map([ [sOptName, bValue] ])); postMessage(["options", gc_engine.getOptions().gl_toString()]); } function resetOptions () { 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 getListOfTokens (sText) { try { let aElem = []; let aRes = null; for (let oToken of oTokenizer.genTokens(sText)) { aRes = oLxg.getInfoForToken(oToken); if (aRes) { aElem.push(aRes); } } postMessage(["tokens", aElem]); } catch (e) { helpers.logerror(e); postMessage(["error", e.message]); } } |
Modified gc_lang/fr/webext/manifest.json from [53ddc564c6] to [49413af971].
︙ | ︙ | |||
9 10 11 12 13 14 15 | "id": "French-GC@grammalecte.net", "strict_min_version": "54.0" } }, "author": "Olivier R.", "homepage_url": "https://grammalecte.net", | < | > > > | < > > | | 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 | "id": "French-GC@grammalecte.net", "strict_min_version": "54.0" } }, "author": "Olivier R.", "homepage_url": "https://grammalecte.net", "description": "Correcteur grammatical pour le français.", "icons": { "16": "img/logo-16.png", "32": "img/logo-32.png", "48": "img/logo-48.png", "64": "img/logo-64.png", "96": "img/logo-96.png" }, "browser_action": { "default_icon": "img/logo-32.png", "default_popup": "panel/main.html", "default_title": "Grammalecte [fr]", "browser_style": false }, "background": { "scripts": [ "background.js" ] }, "web_accessible_resources": [ "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" ] } |
Modified gc_lang/fr/xpi/data/conj_panel.js from [0a29bb81bd] to [eb75f474de].
︙ | ︙ | |||
67 68 69 70 71 72 73 | sVerb = sVerb.slice(2); } if (sVerb.endsWith("?")) { document.getElementById('oint').checked = true; sVerb = sVerb.slice(0,-1).trim(); } | | | 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | sVerb = sVerb.slice(2); } if (sVerb.endsWith("?")) { document.getElementById('oint').checked = true; sVerb = sVerb.slice(0,-1).trim(); } 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;"; document.getElementById('verb').value = ""; oVerb = new Verb(sVerb); |
︙ | ︙ |
Modified gc_lang/fr/xpi/gce_worker.js from [9e0a605cc0] to [32ac3727dc].
︙ | ︙ | |||
75 76 77 78 79 80 81 | } catch (e) { worker.log("# Error: " + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); } } } | | | | | | 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | } catch (e) { worker.log("# Error: " + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); } } } function parse (sText, sCountry, bDebug, bContext) { let aGrammErr = gce.parse(sText, sCountry, bDebug, bContext); return JSON.stringify(aGrammErr); } 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 () { return gce.getOptions().gl_toString(); } |
︙ | ︙ |
Modified make.py from [18d1b24a9f] to [e6482fde8c].
︙ | ︙ | |||
350 351 352 353 354 355 356 | # Firefox if xArgs.firefox: with helpers.cd("_build/xpi/"+sLang): os.system("jpm run -b nightly") if xArgs.web_ext: with helpers.cd("_build/webext/"+sLang): | | | 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 | # Firefox if xArgs.firefox: with helpers.cd("_build/xpi/"+sLang): os.system("jpm run -b nightly") if xArgs.web_ext: with helpers.cd("_build/webext/"+sLang): os.system(r'web-ext run --firefox="' + dVars['fx_nightly_path'] + '" --browser-console') # Thunderbird if xArgs.thunderbird: os.system("thunderbird -jsconsole -P debug") else: print("Folder not found: gc_lang/"+sLang) |
︙ | ︙ |