Comment: | [core][js] change name of new functions for built-in objects |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk | core |
Files: | files | file ages | folders |
SHA3-256: |
5e196b8b64fc05db64504f9101acead3 |
User & Date: | olr on 2017-07-26 17:48:10 |
Other Links: | manifest | tags |
2017-07-26
| ||
17:50 | [fr] regex pour aller check-in: 918c1a03f0 user: olr tags: trunk, fr | |
17:48 | [core][js] change name of new functions for built-in objects check-in: 5e196b8b64 user: olr tags: trunk, core | |
13:11 | [fr] regex pour aller check-in: 49ea76c727 user: olr tags: trunk, fr | |
Modified compile_rules.py from [9f6ed3c641] to [c1af58c8e6].
︙ | ︙ | |||
77 78 79 80 81 82 83 | # methods sCode = sCode.replace(".__len__()", ".length") sCode = sCode.replace(".endswith", ".endsWith") sCode = sCode.replace(".find", ".indexOf") sCode = sCode.replace(".startswith", ".startsWith") sCode = sCode.replace(".lower", ".toLowerCase") sCode = sCode.replace(".upper", ".toUpperCase") | | | | | | | | | | 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | # methods sCode = sCode.replace(".__len__()", ".length") sCode = sCode.replace(".endswith", ".endsWith") sCode = sCode.replace(".find", ".indexOf") sCode = sCode.replace(".startswith", ".startsWith") sCode = sCode.replace(".lower", ".toLowerCase") sCode = sCode.replace(".upper", ".toUpperCase") sCode = sCode.replace(".isdigit", ".gl_isDigit") sCode = sCode.replace(".isupper", ".gl_isUpperCase") sCode = sCode.replace(".islower", ".gl_isLowerCase") sCode = sCode.replace(".istitle", ".gl_isTitle") sCode = sCode.replace(".capitalize", ".gl_toCapitalize") sCode = sCode.replace(".strip", ".gl_trim") sCode = sCode.replace(".lstrip", ".gl_trimLeft") sCode = sCode.replace(".rstrip", ".gl_trimRight") sCode = sCode.replace('.replace("."', ".replace(/\./g") sCode = sCode.replace('.replace("..."', ".replace(/\.\.\./g") sCode = re.sub('.replace\("([^"]+)" ?,', ".replace(/\\1/g,", sCode) # regex sCode = re.sub('re.search\("([^"]+)", *(m.group\(\\d\))\)', "(\\2.search(/\\1/) >= 0)", sCode) sCode = re.sub(".search\\(/\\(\\?i\\)([^/]+)/\\) >= 0\\)", ".search(/\\1/i) >= 0)", sCode) sCode = re.sub('(look\\(sx?[][.a-z:()]*), "\\(\\?i\\)([^"]+)"', "\\1, /\\2/i", sCode) |
︙ | ︙ |
Modified gc_core/js/ibdawg.js from [2d42754063] to [fca88c3e7c].
︙ | ︙ | |||
85 86 87 88 89 90 91 | 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("-")) { | | | | | | | 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 | 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 sWord = sWord.replace("’", "'"); } if (this.lookup(sWord)) { return true; } if (sWord.charAt(0).gl_isUpperCase()) { if (sWord.length > 1) { if (sWord.gl_isTitle()) { return !!this.lookup(sWord.toLowerCase()); } if (sWord.gl_isUpperCase()) { if (this.bOptNumSigle) { return true; } return !!(this.lookup(sWord.toLowerCase()) || this.lookup(sWord.gl_toCapitalize())); } return !!this.lookup(sWord.slice(0, 1).toLowerCase() + sWord.slice(1)); } else { return !!this.lookup(sWord.toLowerCase()); } } return false; |
︙ | ︙ | |||
152 153 154 155 156 157 158 | } 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); | | | | | 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | } 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 |
︙ | ︙ |
Modified gc_core/js/jsex_map.js from [181b814a6e] to [985754ee9e].
1 2 3 | // 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 | // 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 [bb46156b4b] to [cba83b3853].
1 2 3 | // regex | | | | 1 2 3 4 5 6 7 8 9 10 11 12 | // regex if (RegExp.prototype.grammalecte === undefined) { RegExp.prototype.gl_exec2 = function (sText, aGroupsPos, aNegLookBefore=null) { let m; while ((m = this.exec(sText)) !== null) { // we have to iterate over sText here too // because first match doesn’t imply it’s a valid match according to negative lookbefore assertions, // and even if first match is finally invalid, it doesn’t mean the following eligible matchs would be invalid too. if (aNegLookBefore !== null) { // check negative look before assertions |
︙ | ︙ | |||
72 73 74 75 76 77 78 | m.end.push(iPos + subm.length); } } } return m; } | | | 72 73 74 75 76 77 78 79 80 | m.end.push(iPos + subm.length); } } } return m; } RegExp.prototype.grammalecte = true; } |
Modified gc_core/js/jsex_string.js from [adf06fbda5] to [1e9c89a872].
1 2 3 | // String | | | | | | | | | | | | | | 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 | // String if (String.prototype.grammalecte === undefined) { String.prototype.gl_count = function (sSearch, bOverlapping) { // http://jsperf.com/string-ocurrence-split-vs-match/8 if (sSearch.length <= 0) { return this.length + 1; } let nOccur = 0; 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 [ee18ec83ee] to [fb021578af].
1 2 3 4 5 6 7 8 9 10 11 | // 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) { | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 | // Grammar checker engine ${string} ${regex} ${map} function capitalizeArray (aArray) { // can’t map on user defined function?? let aNew = []; for (let i = 0; i < aArray.length; i = i + 1) { aNew[i] = aArray[i].gl_toCapitalize(); } return aNew; } const ibdawg = require("resource://grammalecte/ibdawg.js"); const helpers = require("resource://grammalecte/helpers.js"); const gc_options = require("resource://grammalecte/${lang}/gc_options.js"); |
︙ | ︙ | |||
82 83 84 85 86 87 88 | // parse sentence for (let [iStart, iEnd] of _getSentenceBoundaries(sText)) { if (4 < (iEnd - iStart) < 2000) { dDA.clear(); //echo(sText.slice(iStart, iEnd)); try { [_, errs] = _proofread(sText.slice(iStart, iEnd), sAlt.slice(iStart, iEnd), iStart, false, dDA, dPriority, sCountry, bDebug, bContext); | | | 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 | // parse sentence for (let [iStart, iEnd] of _getSentenceBoundaries(sText)) { if (4 < (iEnd - iStart) < 2000) { dDA.clear(); //echo(sText.slice(iStart, iEnd)); try { [_, errs] = _proofread(sText.slice(iStart, iEnd), sAlt.slice(iStart, iEnd), iStart, false, dDA, dPriority, sCountry, bDebug, bContext); dErrors.gl_update(errs); } catch (e) { helpers.logerror(e); } } } return Array.from(dErrors.values()); |
︙ | ︙ | |||
114 115 116 117 118 119 120 | let bCondMemo; let nErrorStart; for (let [sOption, lRuleGroup] of _getRules(bParagraph)) { if (!sOption || option(sOption)) { for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) { if (!_aIgnoredRules.has(sRuleId)) { | | | 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 | let bCondMemo; let nErrorStart; for (let [sOption, lRuleGroup] of _getRules(bParagraph)) { if (!sOption || option(sOption)) { for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) { if (!_aIgnoredRules.has(sRuleId)) { while ((m = zRegex.gl_exec2(s, lGroups, lNegLookBefore)) !== null) { bCondMemo = null; /*if (bDebug) { echo(">>>> Rule # " + sLineId + " - Text: " + s + " opt: "+ sOption); }*/ for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) { // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ] try { |
︙ | ︙ | |||
149 150 151 152 153 154 155 | } break; case "=": // disambiguation //echo("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source); oEvalFunc[sWhat](s, m, dDA); if (bDebug) { | | | 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | } break; case "=": // disambiguation //echo("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source); oEvalFunc[sWhat](s, m, dDA); if (bDebug) { echo("= " + m[0] + " # " + sLineId + "\nDA: " + dDA.gl_toString()); } break; case ">": // we do nothing, this test is just a condition to apply all following actions break; default: echo("# error: unknown action at " + sLineId); |
︙ | ︙ | |||
192 193 194 195 196 197 198 | oErr["sLineId"] = sLineId; oErr["sRuleId"] = sRuleId; oErr["sType"] = (sOption) ? sOption : "notype"; // suggestions if (sRepl[0] === "=") { let sugg = oEvalFunc[sRepl.slice(1)](s, m); if (sugg) { | | | | | | | 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 | oErr["sLineId"] = sLineId; oErr["sRuleId"] = sRuleId; oErr["sType"] = (sOption) ? sOption : "notype"; // suggestions if (sRepl[0] === "=") { let sugg = oEvalFunc[sRepl.slice(1)](s, m); if (sugg) { if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) { oErr["aSuggestions"] = capitalizeArray(sugg.split("|")); } else { oErr["aSuggestions"] = sugg.split("|"); } } else { oErr["aSuggestions"] = []; } } else if (sRepl == "_") { oErr["aSuggestions"] = []; } else { if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) { oErr["aSuggestions"] = capitalizeArray(sRepl.gl_expand(m).split("|")); } else { oErr["aSuggestions"] = sRepl.gl_expand(m).split("|"); } } // Message if (sMsg[0] === "=") { sMessage = oEvalFunc[sMsg.slice(1)](s, m) } else { sMessage = sMsg.gl_expand(m); } if (bIdRule) { sMessage += " ##" + sLineId + " #" + sRuleId; } oErr["sMessage"] = sMessage; // URL oErr["URL"] = sURL || ""; |
︙ | ︙ | |||
243 244 245 246 247 248 249 | } 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); | | | | | 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 | } else if (sRepl === ">" || sRepl === "_" || sRepl === "~") { sNew = sRepl + " ".repeat(ln-1); } else if (sRepl === "@") { sNew = "@".repeat(ln); } else if (sRepl.slice(0,1) === "=") { sNew = oEvalFunc[sRepl.slice(1)](s, m); sNew = sNew + " ".repeat(ln-sNew.length); if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) { sNew = sNew.gl_toCapitalize(); } } else { sNew = sRepl.gl_expand(m); sNew = sNew + " ".repeat(ln-sNew.length); } //echo("\n"+s+"\nstart: "+m.start[iGroup]+" end:"+m.end[iGroup]) return s.slice(0, m.start[iGroup]) + sNew + s.slice(m.end[iGroup]); } function ignoreRule (sRuleId) { |
︙ | ︙ | |||
296 297 298 299 300 301 302 | //////// init function load (sContext="JavaScript") { try { _oDict = new ibdawg.IBDAWG("${dic_name}.json"); _sContext = sContext; | | | | | | 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 | //////// init function load (sContext="JavaScript") { try { _oDict = new ibdawg.IBDAWG("${dic_name}.json"); _sContext = sContext; _dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default } catch (e) { helpers.logerror(e); } } function setOption (sOpt, bVal) { if (_dOptions.has(sOpt)) { _dOptions.set(sOpt, bVal); } } function setOptions (dOpt) { _dOptions.gl_updateOnlyExistingKeys(dOpt); } function getOptions () { return _dOptions; } function getDefaultOptions () { return gc_options.getOptions(_sContext).gl_shallowCopy(); } function resetOptions () { _dOptions = gc_options.getOptions(_sContext).gl_shallowCopy(); } function getDictionary () { return _oDict; } function _getRules (bParagraph) { |
︙ | ︙ | |||
516 517 518 519 520 521 522 | helpers.logerror(e); } return false; } function look_chk1 (dDA, s, nOffset, zPattern, sPatternGroup1, sNegPatternGroup1=null) { // returns True if s has pattern zPattern and m.group(1) has pattern sPatternGroup1 | | | 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 | helpers.logerror(e); } return false; } function look_chk1 (dDA, s, nOffset, zPattern, sPatternGroup1, sNegPatternGroup1=null) { // returns True if s has pattern zPattern and m.group(1) has pattern sPatternGroup1 let m = zPattern.gl_exec2(s, null); if (!m) { return false; } try { let sWord = m[1]; let nPos = m.start[1] + nOffset; if (sNegPatternGroup1) { |
︙ | ︙ |
Modified gc_lang/fr/modules-js/conj.js from [82dfb400da] to [0ac007e97e].
︙ | ︙ | |||
378 379 380 381 382 383 384 | }; conjugue (sTemps, sWho, bPro, bNeg, bTpsCo, bInt, bFem) { if (!this.dConj.get(sTemps).get(sWho)) { return ""; } let sConj; | | | 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 | }; 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) ? _getConjWithTags(this.sVerbAux, this._tTagsAux, sTemps, sWho) : getConj("être", sTemps, sWho); } else { sConj = this.dConj.get(sTemps).get(sWho); } |
︙ | ︙ |
Modified gc_lang/fr/modules-js/gce_analyseur.js from [7588af7481] to [673094989d].
︙ | ︙ | |||
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 | 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 (cr.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 cr.mbNomNotAdj(_dAnalyses.gl_get(sWord2, "")) && cr.mbPpasNomNotAdj(_dAnalyses.gl_get(sWord1, "")); } function isAmbiguousNAV (sWord) { // words which are nom|adj and verb are ambiguous (except être and avoir) if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) { return false; } if (!cr.mbNomAdj(_dAnalyses.gl_get(sWord, "")) || sWord == "est") { return false; } if (cr.mbVconj(_dAnalyses.gl_get(sWord, "")) && !cr.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 (cr.checkConjVerb(a2, sReqMorphConj)) { // verb word2 is ok return false; } let a1 = _dAnalyses.gl_get(sWord1, null); if (!a1 || a1.length === 0) { return false; } if (cr.checkAgreement(a1, a2) && (cr.mbAdj(a2) || cr.mbAdj(a1))) { 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 (cr.checkConjVerb(a2, sReqMorphConj)) { // verb word2 is ok return false; } let a1 = _dAnalyses.gl_get(sWord1, null); if (!a1 || a1.length === 0) { return false; } if (cr.checkAgreement(a1, a2) && (cr.mbAdj(a2) || cr.mbAdjNb(a1))) { return false; } // now, we know there no agreement, and conjugation is also wrong if (cr.isNomAdj(a1)) { return true; } //if cr.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 cr.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))) { return true; } return false; } //// Syntagmes const _zEndOfNG1 = new RegExp ("^ *$|^ +(?:, +|)(?:n(?:’|e |o(?:u?s|tre) )|l(?:’|e(?:urs?|s|) |a )|j(?:’|e )|m(?:’|es? |a |on )|t(?:’|es? |a |u )|s(?:’|es? |a )|c(?:’|e(?:t|tte|s|) )|ç(?:a |’)|ils? |vo(?:u?s|tre) )"); const _zEndOfNG2 = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9_Ø-ßĀ-ʯ][a-zà-öA-Zø-ÿÀ-Ö0-9_Ø-ßĀ-ʯ-]+)"); const _zEndOfNG3 = new RegExp ("^ *, +([a-zà-öA-Zø-ÿÀ-Ö0-9_Ø-ßĀ-ʯ][a-zà-öA-Zø-ÿÀ-Ö0-9_Ø-ßĀ-ʯ-]+)"); function isEndOfNG (dDA, s, iOffset) { if (_zEndOfNG1.test(s)) { return true; } let m = _zEndOfNG2.gl_exec2(s, ["$"]); if (m && morphex(dDA, [iOffset+m.start[1], m[1]], ":[VR]", ":[NAQP]")) { return true; } m = _zEndOfNG3.gl_exec2(s, ["$"]); if (m && !morph(dDA, [iOffset+m.start[1], m[1]], ":[NA]", false)) { return true; } return false; } const _zNextIsNotCOD1 = new RegExp ("^ *,"); const _zNextIsNotCOD2 = new RegExp ("^ +(?:[mtsnj](e +|’)|[nv]ous |tu |ils? |elles? )"); const _zNextIsNotCOD3 = new RegExp ("^ +([a-zéèî][a-zà-öA-Zø-ÿÀ-ÖØ-ßĀ-ʯ-]+)"); function isNextNotCOD (dDA, s, iOffset) { if (_zNextIsNotCOD1.test(s) || _zNextIsNotCOD2.test(s)) { return true; } let m = _zNextIsNotCOD3.gl_exec2(s, ["$"]); if (m && morphex(dDA, [iOffset+m.start[1], m[1]], ":[123][sp]", ":[DM]")) { return true; } return false; } const _zNextIsVerb1 = new RegExp ("^ +[nmts](?:e |’)"); const _zNextIsVerb2 = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9_Ø-ßĀ-ʯ][a-zà-öA-Zø-ÿÀ-Ö0-9_Ø-ßĀ-ʯ-]+)"); function isNextVerb (dDA, s, iOffset) { if (_zNextIsVerb1.test(s)) { return true; } let m = _zNextIsVerb2.gl_exec2(s, ["$"]); if (m && morph(dDA, [iOffset+m.start[1], m[1]], ":[123][sp]", false)) { return true; } return false; } //// Exceptions const aREGULARPLURAL = new Set(["abricot", "amarante", "aubergine", "acajou", "anthracite", "brique", "caca", "café", "carotte", "cerise", "chataigne", "corail", "citron", "crème", "grave", "groseille", "jonquille", "marron", "olive", "pervenche", "prune", "sable"]); const aSHOULDBEVERB = new Set(["aller", "manger"]); |
Modified gc_lang/fr/modules-js/gce_suggestions.js from [4ab154433f] to [d46530bfae].
︙ | ︙ | |||
11 12 13 14 15 16 17 | // 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(); | | | 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | // 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)) { // 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"); |
︙ | ︙ | |||
161 162 163 164 165 166 167 | } else if (cMode == ":S") { lMode = _lSubjonctif; } else if (cMode.startsWith(":I") || cMode.startsWith(":S")) { lMode = [cMode]; } else { return ""; } | | | | 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | } else if (cMode == ":S") { lMode = _lSubjonctif; } else if (cMode.startsWith(":I") || cMode.startsWith(":S")) { lMode = [cMode]; } else { return ""; } let sWho = _dQuiEst.gl_get(sSuj.toLowerCase(), null); if (!sWho) { if (sSuj[0].gl_isLowerCase()) { // pas un pronom, ni un nom propre return ""; } sWho = ":3s"; } let aSugg = new Set(); for (let sStem of stem(sFlex)) { let tTags = conj._getTags(sStem); |
︙ | ︙ | |||
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 ""; } | | | 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | function suggPlur (sFlex, sWordToAgree=null) { // returns plural forms assuming sFlex is singular if (sWordToAgree) { if (!_dAnalyses.has(sWordToAgree) && !_storeMorphFromFSA(sWordToAgree)) { return ""; } let sGender = cr.getGender(_dAnalyses.gl_get(sWordToAgree, [])); if (sGender == ":m") { return suggMasPlur(sFlex); } else if (sGender == ":f") { return suggFemPlur(sFlex); } } let aSugg = new Set(); |
︙ | ︙ | |||
253 254 255 256 257 258 259 | return ""; } function suggMasSing (sFlex, bSuggSimil=false) { // returns masculine singular forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before let aSugg = new Set(); | | | 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 | return ""; } function suggMasSing (sFlex, bSuggSimil=false) { // returns masculine singular forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before 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 = cr.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { |
︙ | ︙ | |||
289 290 291 292 293 294 295 | return ""; } function suggMasPlur (sFlex, bSuggSimil=false) { // returns masculine plural forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before let aSugg = new Set(); | | | 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 | return ""; } function suggMasPlur (sFlex, bSuggSimil=false) { // returns masculine plural forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before 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 = cr.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { |
︙ | ︙ | |||
330 331 332 333 334 335 336 | } function suggFemSing (sFlex, bSuggSimil=false) { // returns feminine singular forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before let aSugg = new Set(); | | | 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 | } function suggFemSing (sFlex, bSuggSimil=false) { // returns feminine singular forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before 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 = cr.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { |
︙ | ︙ | |||
364 365 366 367 368 369 370 | return ""; } function suggFemPlur (sFlex, bSuggSimil=false) { // returns feminine plural forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before let aSugg = new Set(); | | | 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 | return ""; } function suggFemPlur (sFlex, bSuggSimil=false) { // returns feminine plural forms // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before 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 = cr.getLemmaOfMorph(sMorph); if (mfsp.isFemForm(sStem)) { |
︙ | ︙ | |||
423 424 425 426 427 428 429 | return false; } function switchGender (sFlex, bPlur=null) { // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before let aSugg = new Set(); if (bPlur === null) { | | | | | | | 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 | return false; } function switchGender (sFlex, bPlur=null) { // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before let aSugg = new Set(); if (bPlur === null) { for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (sMorph.includes(":f")) { if (sMorph.includes(":s")) { aSugg.add(suggMasSing(sFlex)); } else if (sMorph.includes(":p")) { aSugg.add(suggMasPlur(sFlex)); } } else if (sMorph.includes(":m")) { if (sMorph.includes(":s")) { aSugg.add(suggFemSing(sFlex)); } else if (sMorph.includes(":p")) { aSugg.add(suggFemPlur(sFlex)); } else { aSugg.add(suggFemSing(sFlex)); aSugg.add(suggFemPlur(sFlex)); } } } } else if (bPlur) { for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (sMorph.includes(":f")) { aSugg.add(suggMasPlur(sFlex)); } else if (sMorph.includes(":m")) { aSugg.add(suggFemPlur(sFlex)); } } } else { for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { if (sMorph.includes(":f")) { aSugg.add(suggMasSing(sFlex)); } else if (sMorph.includes(":m")) { aSugg.add(suggFemSing(sFlex)); } } } if (aSugg.size > 0) { return Array.from(aSugg).join("|"); } return ""; } function switchPlural (sFlex) { let aSugg = new Set(); for (let sMorph of _dAnalyses.gl_get(sFlex, [])) { // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before if (sMorph.includes(":s")) { aSugg.add(suggPlur(sFlex)); } else if (sMorph.includes(":p")) { aSugg.add(suggSing(sFlex)); } } if (aSugg.size > 0) { return Array.from(aSugg).join("|"); } return ""; } function hasSimil (sWord, sPattern=null) { return phonet.hasSimil(sWord, sPattern); } function suggSimil (sWord, sPattern) { // return list of words phonetically similar to sWord and whom POS is matching sPattern let aSugg = phonet.selectSimil(sWord, sPattern); for (let sMorph of _dAnalyses.gl_get(sWord, [])) { for (let e of conj.getSimil(sWord, sMorph, sPattern)) { aSugg.add(e); } } if (aSugg.size > 0) { return Array.from(aSugg).join("|"); } |
︙ | ︙ | |||
509 510 511 512 513 514 515 | return "ce|cet"; } return "ce"; } function suggLesLa (sWord) { // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before | | | 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 | return "ce|cet"; } return "ce"; } function suggLesLa (sWord) { // we don’t check if word exists in _dAnalyses, for it is assumed it has been done before if (_dAnalyses.gl_get(sWord, []).some(s => s.includes(":p"))) { return "les|la"; } return "la"; } function formatNumber (s) { let nLen = s.length; |
︙ | ︙ |
Modified gc_lang/fr/modules-js/lexicographe.js from [673a7bbf6a] to [2702fb7f6b].
︙ | ︙ | |||
204 205 206 207 208 209 210 | getInfoForToken (oToken) { // Token: .sType, .sValue, .nStart, .nEnd // return a list [type, token_string, values] let m = null; try { switch (oToken.sType) { case 'SEPARATOR': | | | | | 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 | getInfoForToken (oToken) { // Token: .sType, .sValue, .nStart, .nEnd // return a list [type, token_string, values] let m = null; try { switch (oToken.sType) { case 'SEPARATOR': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dSeparator.gl_get(oToken.sValue, "caractère indéterminé")] }; break; case 'NUM': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["nombre"] }; break; case 'LINK': return { sType: oToken.sType, sValue: oToken.sValue.slice(0,40)+"…", aLabel: ["hyperlien"] }; break; case 'ELPFX': let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase(); return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dPFX.gl_get(sTemp, "préfixe élidé inconnu")] }; 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 (s of lMorph) if (s.includes(":")) this._formatTags(s) ]; return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem}; } |
︙ | ︙ | |||
262 263 264 265 266 267 268 | sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]"; } if (!sRes) { sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]"; helpers.echo(sRes); return sRes; } | | | 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | 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("-")) { |
︙ | ︙ |
Modified gc_lang/fr/modules-js/phonet.js from [7cb5eceb49] to [9c713cdc05].
︙ | ︙ | |||
14 15 16 17 18 19 20 | function hasSimil (sWord, sPattern=null) { // return True if there is list of words phonetically similar to sWord if (!sWord) { return false; } if (_dWord.has(sWord)) { if (sPattern) { | | | | | | | 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 | function hasSimil (sWord, sPattern=null) { // return True if there is list of words phonetically similar to sWord if (!sWord) { return false; } if (_dWord.has(sWord)) { if (sPattern) { return getSimil(sWord).some(sSimil => _dMorph.gl_get(sSimil, []).some(sMorph => sMorph.search(sPattern) >= 0)); } return true; } if (sWord.slice(0,1).gl_isUpperCase()) { sWord = sWord.toLowerCase(); if (_dWord.has(sWord)) { if (sPattern) { return getSimil(sWord).some(sSimil => _dMorph.gl_get(sSimil, []).some(sMorph => sMorph.search(sPattern) >= 0)); } return true; } } return false; } function getSimil (sWord) { // return list of words phonetically similar to sWord if (!sWord) { return []; } if (_dWord.has(sWord)) { return _lSet[_dWord.get(sWord)]; } if (sWord.slice(0,1).gl_isUpperCase()) { sWord = sWord.toLowerCase(); if (_dWord.has(sWord)) { return _lSet[_dWord.get(sWord)]; } } return []; } function selectSimil (sWord, sPattern) { // return list of words phonetically similar to sWord and whom POS is matching sPattern if (!sPattern) { return new Set(getSimil(sWord)); } let aSelect = new Set(); for (let sSimil of getSimil(sWord)) { for (let sMorph of _dMorph.gl_get(sSimil, [])) { if (sMorph.search(sPattern) >= 0) { aSelect.add(sSimil); } } } return aSelect; } exports.hasSimil = hasSimil; exports.getSimil = getSimil; exports.selectSimil = selectSimil; |
Modified gc_lang/fr/modules-js/textformatter.js from [fcd9e4b1a6] to [82caf6845e].
︙ | ︙ | |||
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 | ["etc", true], ["missing_hyphens", true], ["ma_word", true], ["ma_1letter_lowercase", false], ["ma_1letter_uppercase", false] ]); const dOptions = dDefaultOptions.gl_shallowCopy(); class TextFormatter { constructor () { this.sLang = "fr"; }; formatText (sText, dOpt=null) { if (dOpt !== null) { dOptions.gl_updateOnlyExistingKeys(dOpt); } for (let [sOptName, bVal] of dOptions) { if (bVal && oReplTable.has(sOptName)) { for (let [zRgx, sRep] of oReplTable[sOptName]) { sText = sText.replace(zRgx, sRep); } } |
︙ | ︙ |
Modified gc_lang/fr/xpi/gce_worker.js from [be41214f38] to [9e0a605cc0].
︙ | ︙ | |||
67 68 69 70 71 72 73 | gce.load(sContext); oDict = gce.getDictionary(); oLxg = new lxg.Lexicographe(oDict); if (sGCOptions !== "") { gce.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); } // we always retrieve options from the gce, for setOptions filters obsolete options | | | | | | | | 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 | gce.load(sContext); oDict = gce.getDictionary(); oLxg = new lxg.Lexicographe(oDict); if (sGCOptions !== "") { gce.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); } // we always retrieve options from the gce, for setOptions filters obsolete options return gce.getOptions().gl_toString(); } catch (e) { worker.log("# Error: " + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); } } } function parse (sText, sLang, bDebug, bContext) { let aGrammErr = gce.parse(sText, sLang, bDebug, bContext); return JSON.stringify(aGrammErr); } function parseAndSpellcheck (sText, sLang, bDebug, bContext) { let aGrammErr = gce.parse(sText, sLang, bDebug, bContext); let aSpellErr = oTokenizer.getSpellingErrors(sText, oDict); return JSON.stringify({ aGrammErr: aGrammErr, aSpellErr: aSpellErr }); } function getOptions () { return gce.getOptions().gl_toString(); } function getDefaultOptions () { return gce.getDefaultOptions().gl_toString(); } function setOptions (sGCOptions) { gce.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); return gce.getOptions().gl_toString(); } function setOption (sOptName, bValue) { gce.setOptions(new Map([ [sOptName, bValue] ])); return gce.getOptions().gl_toString(); } function resetOptions () { gce.resetOptions(); return gce.getOptions().gl_toString(); } function fullTests (sGCOptions="") { if (!gce || !oDict) { return "# Error: grammar checker or dictionary not loaded." } let dMemoOptions = gce.getOptions(); |
︙ | ︙ |