Changes In Branch gcerw Through [2f2ddcbb20] Excluding Merge-Ins
This is equivalent to a diff from 84fc065208 to 2f2ddcbb20
2020-04-17
| ||
17:40 | merge trunk (from previous checkin: mise à jour du dictionnaire) check-in: 193d73c90f user: olr tags: gcerw | |
2020-04-10
| ||
06:28 | [fr] ajustements check-in: 0020cc9295 user: olr tags: trunk, fr | |
2020-04-09
| ||
20:27 | merge trunk check-in: 2f2ddcbb20 user: olr tags: gcerw | |
20:22 | [graphspell] suggestions: chai -> j’sais check-in: 84fc065208 user: olr tags: trunk, graphspell | |
19:05 | [fr] ajustements check-in: 382af6a1ce user: olr tags: trunk, fr | |
2020-04-08
| ||
18:29 | [core][graphspell] move lexicographer to graphspell check-in: 66fb137996 user: olr tags: core, graphspell, gcerw | |
Modified gc_core/js/lang_core/gc_engine.js from [224c579d52] to [6a386c1d36].
1 2 3 4 5 6 7 8 9 10 11 12 13 | // Grammar checker engine /* jshint esversion:6, -W097 */ /* jslint esversion:6 */ /* global require, exports, console */ "use strict"; ${string} ${regex} ${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 | // Grammar checker engine /* jshint esversion:6, -W097 */ /* jslint esversion:6 */ /* global require, exports, console */ "use strict"; ${string} ${regex} ${map} if (typeof(process) !== 'undefined') { var gc_engine_func = require("./gc_engine_func.js"); var gc_options = require("./gc_options.js"); var gc_rules = require("./gc_rules.js"); var gc_rules_graph = require("./gc_rules_graph.js"); var cregex = require("./cregex.js"); var text = require("../text.js"); } else if (typeof(require) !== 'undefined') { var gc_engine_func = require("resource://grammalecte/${lang}/gc_engine_func.js"); var gc_options = require("resource://grammalecte/${lang}/gc_options.js"); var gc_rules = require("resource://grammalecte/${lang}/gc_rules.js"); var gc_rules_graph = require("resource://grammalecte/${lang}/gc_rules_graph.js"); var cregex = require("resource://grammalecte/${lang}/cregex.js"); var text = require("resource://grammalecte/text.js"); } 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].slice(0,1).toUpperCase() + aArray[i].slice(1); } return aNew; } var gc_engine = { //// Informations lang: "${lang}", locales: ${loc}, pkg: "${implname}", name: "${name}", version: "${version}", author: "${author}", //// Tools oSpellChecker: null, oTokenizer: null, //// Data aIgnoredRules: new Set(), oOptionsColors: null, //// Initialization load: function (sContext="JavaScript", sColorType="aRGB", sPath="") { try { if (typeof(process) !== 'undefined') { var spellchecker = require("../graphspell/spellchecker.js"); this.oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}"); } else if (typeof(require) !== 'undefined') { var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js"); this.oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}"); } else { this.oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}"); } this.oOptionsColors = gc_options.getOptionsColors(sContext, sColorType); this.oTokenizer = this.oSpellChecker.getTokenizer(); this.oSpellChecker.activateStorage(); gc_engine_func.load(sContext, this.oSpellChecker) gc_options.load(sContext) } catch (e) { console.error(e); } }, getSpellChecker: function () { return this.oSpellChecker; }, //// Rules getRules: function (bParagraph) { if (!bParagraph) { return gc_rules.lSentenceRules; } return gc_rules.lParagraphRules; }, ignoreRule: function (sRuleId) { this.aIgnoredRules.add(sRuleId); }, resetIgnoreRules: function () { this.aIgnoredRules.clear(); }, reactivateRule: function (sRuleId) { this.aIgnoredRules.delete(sRuleId); }, listRules: function* (sFilter=null) { // generator: returns tuple (sOption, sLineId, sRuleId) try { for (let [sOption, lRuleGroup] of this.getRules(true)) { for (let [,, sLineId, sRuleId,,] of lRuleGroup) { |
︙ | ︙ | |||
130 131 132 133 134 135 136 | } } catch (e) { console.error(e); } }, | < < < < < < < < < < < < < < < < < < < < < < < < | 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | } } catch (e) { console.error(e); } }, //// Parsing parse: function (sText, sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false, bFullInfo=false) { // init point to analyse <sText> and returns an iterable of errors or (with option <bFullInfo>) a list of sentences with tokens and errors let oText = new TextParser(sText); return oText.parse(sCountry, bDebug, dOptions, bContext, bFullInfo); } |
︙ | ︙ | |||
199 200 201 202 203 204 205 | s += "\n"; } return s; } parse (sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false, bFullInfo=false) { // analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) a list of sentences with tokens and errors | | | | 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 | s += "\n"; } return s; } parse (sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false, bFullInfo=false) { // analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) a list of sentences with tokens and errors let dOpt = dOptions || gc_options.dOptions; let bShowRuleId = gc_options.dOptions.gl_get('idrule', false); // parse paragraph try { this.parseText(this.sText, this.sText0, true, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext); } catch (e) { console.error(e); } |
︙ | ︙ | |||
222 223 224 225 226 227 228 | let lSentences = []; let oSentence = null; for (let [iStart, iEnd] of text.getSentenceBoundaries(sText)) { try { this.sSentence = sText.slice(iStart, iEnd); this.sSentence0 = this.sText0.slice(iStart, iEnd); this.nOffsetWithinParagraph = iStart; | | | | 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 | let lSentences = []; let oSentence = null; for (let [iStart, iEnd] of text.getSentenceBoundaries(sText)) { try { this.sSentence = sText.slice(iStart, iEnd); this.sSentence0 = this.sText0.slice(iStart, iEnd); this.nOffsetWithinParagraph = iStart; this.lToken = Array.from(gc_engine.oTokenizer.genTokens(this.sSentence, true)); this.dTokenPos.clear(); for (let dToken of this.lToken) { if (dToken["sType"] != "INFO") { this.dTokenPos.set(dToken["nStart"], dToken); } } if (bFullInfo) { oSentence = { "nStart": iStart, "nEnd": iEnd, "sSentence": this.sSentence, "lToken": Array.from(this.lToken) }; for (let oToken of oSentence["lToken"]) { if (oToken["sType"] == "WORD") { oToken["bValidToken"] = gc_engine.oSpellChecker.isValidToken(oToken["sValue"]); } } // the list of tokens is duplicated, to keep all tokens from being deleted when analysis } this.parseText(this.sSentence, this.sSentence0, false, iStart, sCountry, dOpt, bShowRuleId, bDebug, bContext); if (bFullInfo) { oSentence["lGrammarErrors"] = Array.from(this.dSentenceError.values()); |
︙ | ︙ | |||
298 299 300 301 302 303 304 | if (bDebug) { console.log(">>>> GRAPH: " + sGraphName + " " + sLineId); } sText = this.parseGraph(gc_rules_graph.dAllGraph[sGraphName], sCountry, dOptions, bShowRuleId, bDebug, bContext); } } } | | | | | 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 | if (bDebug) { console.log(">>>> GRAPH: " + sGraphName + " " + sLineId); } sText = this.parseGraph(gc_rules_graph.dAllGraph[sGraphName], sCountry, dOptions, bShowRuleId, bDebug, bContext); } } } else if (!sOption || gc_options.dOptions.gl_get(sOption, false)) { for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) { if (!gc_engine.aIgnoredRules.has(sRuleId)) { while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) { let bCondMemo = null; for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) { // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ] try { bCondMemo = (!sFuncCond || gc_engine_func[sFuncCond](sText, sText0, m, this.dTokenPos, sCountry, bCondMemo)); if (bCondMemo) { switch (cActionType) { case "-": // grammar error //console.log("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source); let nErrorStart = nOffset + m.start[eAct[0]]; if (!this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart)) { |
︙ | ︙ | |||
331 332 333 334 335 336 337 | if (bDebug) { console.log("~ " + sText + " -- " + m[eAct[0]] + " # " + sLineId); } break; case "=": // disambiguation //console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source); | | | 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 | if (bDebug) { console.log("~ " + sText + " -- " + m[eAct[0]] + " # " + sLineId); } break; case "=": // disambiguation //console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source); gc_engine_func[sWhat](sText, m, this.dTokenPos); if (bDebug) { console.log("= " + m[0] + " # " + sLineId, "\nDA:", this.dTokenPos); } break; case ">": // we do nothing, this test is just a condition to apply all following actions break; |
︙ | ︙ | |||
371 372 373 374 375 376 377 | } } } update (sSentence, bDebug=false) { // update <sSentence> and retokenize this.sSentence = sSentence; | | | 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 | } } } update (sSentence, bDebug=false) { // update <sSentence> and retokenize this.sSentence = sSentence; let lNewToken = Array.from(gc_engine.oTokenizer.genTokens(sSentence, true)); for (let oToken of lNewToken) { if (this.dTokenPos.gl_get(oToken["nStart"], {}).hasOwnProperty("lMorph")) { oToken["lMorph"] = this.dTokenPos.get(oToken["nStart"])["lMorph"]; } if (this.dTokenPos.gl_get(oToken["nStart"], {}).hasOwnProperty("aTags")) { oToken["aTags"] = this.dTokenPos.get(oToken["nStart"])["aTags"]; } |
︙ | ︙ | |||
469 470 471 472 473 474 475 | } } } // analysable tokens if (oToken["sType"].slice(0,4) == "WORD") { // token lemmas if (oNode.hasOwnProperty("<lemmas>")) { | | | | 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 | } } } // analysable tokens if (oToken["sType"].slice(0,4) == "WORD") { // token lemmas if (oNode.hasOwnProperty("<lemmas>")) { for (let sLemma of gc_engine.oSpellChecker.getLemma(oToken["sValue"])) { if (oNode["<lemmas>"].hasOwnProperty(sLemma)) { if (bDebug) { console.log(" MATCH: >" + sLemma); } yield { "iToken1": iToken1, "iNode": oNode["<lemmas>"][sLemma] }; bTokenFound = true; } } } // morph arcs if (oNode.hasOwnProperty("<morph>")) { let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]); if (lMorph.length > 0) { for (let sSearch in oNode["<morph>"]) { if (!sSearch.includes("¬")) { // no anti-pattern if (lMorph.some(sMorph => (sMorph.includes(sSearch)))) { if (bDebug) { console.log(" MATCH: $" + sSearch); |
︙ | ︙ | |||
525 526 527 528 529 530 531 | } } } } } // regex morph arcs if (oNode.hasOwnProperty("<re_morph>")) { | | | 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 | } } } } } // regex morph arcs if (oNode.hasOwnProperty("<re_morph>")) { let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]); if (lMorph.length > 0) { for (let sRegex in oNode["<re_morph>"]) { if (!sRegex.includes("¬")) { // no anti-pattern if (lMorph.some(sMorph => (sMorph.search(sRegex) !== -1))) { if (bDebug) { console.log(" MATCH: @" + sRegex); |
︙ | ︙ | |||
674 675 676 677 678 679 680 | // Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ] // TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ] // Disambiguator [ option, condition, "=", replacement/suggestion/action ] // Tag [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ] // Immunity [ option, condition, "!", "", iTokenStart, iTokenEnd ] // Test [ option, condition, ">", "" ] if (!sOption || dOptions.gl_get(sOption, false)) { | | | 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 | // Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ] // TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ] // Disambiguator [ option, condition, "=", replacement/suggestion/action ] // Tag [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ] // Immunity [ option, condition, "!", "", iTokenStart, iTokenEnd ] // Test [ option, condition, ">", "" ] if (!sOption || dOptions.gl_get(sOption, false)) { bCondMemo = !sFuncCond || gc_engine_func[sFuncCond](this.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, this.dTags, this.sSentence, this.sSentence0); if (bCondMemo) { if (cActionType == "-") { // grammar error let [iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL] = eAct; let nTokenErrorStart = (iTokenStart > 0) ? nTokenOffset + iTokenStart : nLastToken + iTokenStart; if (!this.lToken[nTokenErrorStart].hasOwnProperty("bImmune")) { let nTokenErrorEnd = (iTokenEnd > 0) ? nTokenOffset + iTokenEnd : nLastToken + iTokenEnd; |
︙ | ︙ | |||
706 707 708 709 710 711 712 | bChange = true; if (bDebug) { console.log(` TEXT_PROCESSOR: [${this.lToken[nTokenStart]["sValue"]}:${this.lToken[nTokenEnd]["sValue"]}] > ${sWhat}`); } } else if (cActionType == "=") { // disambiguation | | | 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 | bChange = true; if (bDebug) { console.log(` TEXT_PROCESSOR: [${this.lToken[nTokenStart]["sValue"]}:${this.lToken[nTokenEnd]["sValue"]}] > ${sWhat}`); } } else if (cActionType == "=") { // disambiguation gc_engine_func[sWhat](this.lToken, nTokenOffset, nLastToken); if (bDebug) { console.log(` DISAMBIGUATOR: (${sWhat}) [${this.lToken[nTokenOffset+1]["sValue"]}:${this.lToken[nLastToken]["sValue"]}]`); } } else if (cActionType == ">") { // we do nothing, this test is just a condition to apply all following actions if (bDebug) { |
︙ | ︙ | |||
786 787 788 789 790 791 792 | _createErrorFromRegex (sText, sText0, sSugg, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext) { let nStart = nOffset + m.start[iGroup]; let nEnd = nOffset + m.end[iGroup]; // suggestions let lSugg = []; if (sSugg.startsWith("=")) { | | | | | | | 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 | _createErrorFromRegex (sText, sText0, sSugg, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext) { let nStart = nOffset + m.start[iGroup]; let nEnd = nOffset + m.end[iGroup]; // suggestions let lSugg = []; if (sSugg.startsWith("=")) { sSugg = gc_engine_func[sSugg.slice(1)](sText, m); lSugg = (sSugg) ? sSugg.split("|") : []; } else if (sSugg == "_") { lSugg = []; } else { lSugg = sSugg.gl_expand(m).split("|"); } if (bUppercase && lSugg.length > 0 && m[iGroup].slice(0,1).gl_isUpperCase()) { lSugg = capitalizeArray(lSugg); } // Message let sMessage = (sMsg.startsWith("=")) ? gc_engine_func[sMsg.slice(1)](sText, m) : sMsg.gl_expand(m); if (bShowRuleId) { sMessage += " #" + sLineId + " / " + sRuleId; } // return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext); } _createErrorFromTokens (sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) { // suggestions let lSugg = []; if (sSugg.startsWith("=")) { sSugg = gc_engine_func[sSugg.slice(1)](this.lToken, nTokenOffset, nLastToken); lSugg = (sSugg) ? sSugg.split("|") : []; } else if (sSugg == "_") { lSugg = []; } else { lSugg = this._expand(sSugg, nTokenOffset, nLastToken).split("|"); } if (bCaseSvty && lSugg.length > 0 && this.lToken[iFirstToken]["sValue"].slice(0,1).gl_isUpperCase()) { lSugg = capitalizeArray(lSugg); } // Message let sMessage = (sMsg.startsWith("=")) ? gc_engine_func[sMsg.slice(1)](this.lToken, nTokenOffset, nLastToken) : this._expand(sMsg, nTokenOffset, nLastToken); if (bShowRuleId) { sMessage += " #" + sLineId + " / " + sRuleId; } // return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext); } _createError (nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) { let oErr = { "nStart": nStart, "nEnd": nEnd, "sLineId": sLineId, "sRuleId": sRuleId, "sType": sOption || "notype", "aColor": gc_engine.oOptionsColors[sOption], "sMessage": sMessage, "aSuggestions": lSugg, "URL": sURL } if (bContext) { oErr['sUnderlined'] = this.sText0.slice(nStart, nEnd); oErr['sBefore'] = this.sText0.slice(Math.max(0,nStart-80), nStart); |
︙ | ︙ | |||
874 875 876 877 878 879 880 | else if (sRepl === "_") { sNew = "_".repeat(ln); } else if (sRepl === "@") { sNew = "@".repeat(ln); } else if (sRepl.slice(0,1) === "=") { | | | 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 | else if (sRepl === "_") { sNew = "_".repeat(ln); } else if (sRepl === "@") { sNew = "@".repeat(ln); } else if (sRepl.slice(0,1) === "=") { sNew = gc_engine_func[sRepl.slice(1)](sText, 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); |
︙ | ︙ | |||
915 916 917 918 919 920 921 | for (let i = nTokenRewriteStart; i <= nTokenRewriteEnd; i++) { this.lToken[i]["sNewValue"] = "_"; } } } else { if (sWhat.startsWith("=")) { | | | 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 | for (let i = nTokenRewriteStart; i <= nTokenRewriteEnd; i++) { this.lToken[i]["sNewValue"] = "_"; } } } else { if (sWhat.startsWith("=")) { sWhat = gc_engine_func[sWhat.slice(1)](this.lToken, nTokenOffset, nLastToken); } else { sWhat = this._expand(sWhat, nTokenOffset, nLastToken); } let bUppercase = bCaseSvty && this.lToken[nTokenRewriteStart]["sValue"].slice(0,1).gl_isUpperCase(); if (nTokenRewriteEnd - nTokenRewriteStart == 0) { // one token if (bUppercase) { |
︙ | ︙ | |||
1023 1024 1025 1026 1027 1028 1029 | console.log(" TEXT REWRITED: " + this.sSentence); } this.lToken.length = 0; this.lToken = lNewToken; } }; | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < > > > > > < < < < < < | 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 | console.log(" TEXT REWRITED: " + this.sSentence); } this.lToken.length = 0; this.lToken = lNewToken; } }; 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; // objects exports.oSpellChecker = gc_engine.oSpellChecker; exports.oTokenizer = gc_engine.oTokenizer; exports.aIgnoredRules = gc_engine.aIgnoredRules; exports.oOptionsColors = gc_engine.oOptionsColors; // init exports.load = gc_engine.load; exports.parse = gc_engine.parse; exports.getSpellChecker = gc_engine.getSpellChecker; // rules 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; // other exports.TextParser = TextParser; } |
Added gc_core/js/lang_core/gc_engine_func.js version [0448168ecb].
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 | // JavaScript // Grammar checker engine functions ${string} ${regex} ${map} if (typeof(process) !== 'undefined') { var gc_options = require("./gc_options.js"); } else if (typeof(require) !== 'undefined') { var gc_options = require("resource://grammalecte/${lang}/gc_options.js"); } let _sAppContext = "JavaScript"; // what software is running let _oSpellChecker = null; //////// Common functions function option (sOpt) { // return true if option sOpt is active return gc_options.dOptions.gl_get(sOpt, false); } function echo (x) { console.log(x); return true; } var re = { search: function (sRegex, sText) { if (sRegex.startsWith("(?i)")) { return sText.search(new RegExp(sRegex.slice(4), "i")) !== -1; } else { return sText.search(sRegex) !== -1; } }, createRegExp: function (sRegex) { if (sRegex.startsWith("(?i)")) { return new RegExp(sRegex.slice(4), "i"); } else { return new RegExp(sRegex); } } } //////// 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-ʯff-stᴀ-ᶿ%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+)", "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-ʯff-stᴀ-ᶿ%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+ +){" + (n-1).toString() + "}$", "i"); let m = z.exec(s.slice(0, iEnd)); if (!m) { return null; } return [m.index, m[1]]; } function nextword1 (s, iStart) { // get next word (optimization) let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*)", "ig"); let m = _zNextWord.exec(s.slice(iStart)); if (!m) { return null; } return [iStart + _zNextWord.lastIndex - m[1].length, m[1]]; } const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*) +$", "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, sPattern, sNegPattern=null) { // seek sPattern in s (before/after/fulltext), if antipattern sNegPattern not in s try { if (sNegPattern && re.search(sNegPattern, s)) { return false; } return re.search(sPattern, s); } catch (e) { console.error(e); } return false; } //////// Analyse groups for regex rules function displayInfo (dTokenPos, aWord) { // for debugging: info of word if (!aWord) { console.log("> nothing to find"); return true; } let lMorph = _oSpellChecker.getMorph(aWord[1]); if (lMorph.length === 0) { console.log("> not in dictionary"); return true; } if (dTokenPos.has(aWord[0])) { console.log("DA: " + dTokenPos.get(aWord[0])); } console.log("FSA: " + lMorph); return true; } function morph (dTokenPos, 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) { return bNoWord; } let lMorph = (dTokenPos.has(aWord[0]) && dTokenPos.get(aWord[0]))["lMorph"] ? dTokenPos.get(aWord[0])["lMorph"] : _oSpellChecker.getMorph(aWord[1]); if (lMorph.length === 0) { return false; } if (sNegPattern) { // check negative condition if (sNegPattern === "*") { // all morph must match sPattern return lMorph.every(sMorph => (sMorph.search(sPattern) !== -1)); } else { if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) { return false; } } } // search sPattern return lMorph.some(sMorph => (sMorph.search(sPattern) !== -1)); } function analyse (sWord, sPattern, sNegPattern) { // analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off) let lMorph = _oSpellChecker.getMorph(sWord); if (lMorph.length === 0) { return false; } if (sNegPattern) { // check negative condition if (sNegPattern === "*") { // all morph must match sPattern return lMorph.every(sMorph => (sMorph.search(sPattern) !== -1)); } else { if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) { return false; } } } // search sPattern return lMorph.some(sMorph => (sMorph.search(sPattern) !== -1)); } //// Analyse tokens for graph rules function g_value (oToken, sValues, nLeft=null, nRight=null) { // test if <oToken['sValue']> is in sValues (each value should be separated with |) let sValue = (nLeft === null) ? "|"+oToken["sValue"]+"|" : "|"+oToken["sValue"].slice(nLeft, nRight)+"|"; if (sValues.includes(sValue)) { return true; } if (oToken["sValue"].slice(0,2).gl_isTitle()) { // we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout". if (sValues.includes(sValue.toLowerCase())) { return true; } } else if (oToken["sValue"].gl_isUpperCase()) { //if sValue.lower() in sValues: // return true; sValue = "|"+sValue.slice(1).gl_toCapitalize(); if (sValues.includes(sValue)) { return true; } sValue = sValue.toLowerCase(); if (sValues.includes(sValue)) { return true; } } return false; } function g_morph (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) { // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies let lMorph; if (oToken.hasOwnProperty("lMorph")) { lMorph = oToken["lMorph"]; } else { if (nLeft !== null) { let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft); lMorph = _oSpellChecker.getMorph(sValue); if (bMemorizeMorph) { oToken["lMorph"] = lMorph; } } else { lMorph = _oSpellChecker.getMorph(oToken["sValue"]); } } if (lMorph.length == 0) { return false; } // check negative condition if (sNegPattern) { if (sNegPattern == "*") { // all morph must match sPattern return lMorph.every(sMorph => (sMorph.search(sPattern) !== -1)); } else { if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) { return false; } } } // search sPattern return lMorph.some(sMorph => (sMorph.search(sPattern) !== -1)); } function g_analyse (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) { // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies let lMorph; if (nLeft !== null) { let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft); lMorph = _oSpellChecker.getMorph(sValue); if (bMemorizeMorph) { oToken["lMorph"] = lMorph; } } else { lMorph = _oSpellChecker.getMorph(oToken["sValue"]); } if (lMorph.length == 0) { return false; } // check negative condition if (sNegPattern) { if (sNegPattern == "*") { // all morph must match sPattern return lMorph.every(sMorph => (sMorph.search(sPattern) !== -1)); } else { if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) { return false; } } } // search sPattern return lMorph.some(sMorph => (sMorph.search(sPattern) !== -1)); } function g_merged_analyse (oToken1, oToken2, cMerger, sPattern, sNegPattern="", bSetMorph=true) { // merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off) let lMorph = _oSpellChecker.getMorph(oToken1["sValue"] + cMerger + oToken2["sValue"]); if (lMorph.length == 0) { return false; } // check negative condition if (sNegPattern) { if (sNegPattern == "*") { // all morph must match sPattern let bResult = lMorph.every(sMorph => (sMorph.search(sPattern) !== -1)); if (bResult && bSetMorph) { oToken1["lMorph"] = lMorph; } return bResult; } else { if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) { return false; } } } // search sPattern let bResult = lMorph.some(sMorph => (sMorph.search(sPattern) !== -1)); if (bResult && bSetMorph) { oToken1["lMorph"] = lMorph; } return bResult; } function g_tag_before (oToken, dTags, sTag) { if (!dTags.has(sTag)) { return false; } if (oToken["i"] > dTags.get(sTag)[0]) { return true; } return false; } function g_tag_after (oToken, dTags, sTag) { if (!dTags.has(sTag)) { return false; } if (oToken["i"] < dTags.get(sTag)[1]) { return true; } return false; } function g_tag (oToken, sTag) { return oToken.hasOwnProperty("aTags") && oToken["aTags"].has(sTag); } function g_space_between_tokens (oToken1, oToken2, nMin, nMax=null) { let nSpace = oToken2["nStart"] - oToken1["nEnd"] if (nSpace < nMin) { return false; } if (nMax !== null && nSpace > nMax) { return false; } return true; } function g_token (lToken, i) { if (i < 0) { return lToken[0]; } if (i >= lToken.length) { return lToken[-1]; } return lToken[i]; } //////// Disambiguator function select (dTokenPos, nPos, sWord, sPattern, lDefault=null) { if (!sWord) { return true; } if (!dTokenPos.has(nPos)) { console.log("Error. There should be a token at this position: ", nPos); return true; } let lMorph = _oSpellChecker.getMorph(sWord); if (lMorph.length === 0 || lMorph.length === 1) { return true; } let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 ); if (lSelect.length > 0) { if (lSelect.length != lMorph.length) { dTokenPos.get(nPos)["lMorph"] = lSelect; } } else if (lDefault) { dTokenPos.get(nPos)["lMorph"] = lDefault; } return true; } function exclude (dTokenPos, nPos, sWord, sPattern, lDefault=null) { if (!sWord) { return true; } if (!dTokenPos.has(nPos)) { console.log("Error. There should be a token at this position: ", nPos); return true; } let lMorph = _oSpellChecker.getMorph(sWord); if (lMorph.length === 0 || lMorph.length === 1) { return true; } let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 ); if (lSelect.length > 0) { if (lSelect.length != lMorph.length) { dTokenPos.get(nPos)["lMorph"] = lSelect; } } else if (lDefault) { dTokenPos.get(nPos)["lMorph"] = lDefault; } return true; } function define (dTokenPos, nPos, lMorph) { dTokenPos.get(nPos)["lMorph"] = lMorph; return true; } //// Disambiguation for graph rules function g_select (oToken, sPattern, lDefault=null) { // select morphologies for <oToken> according to <sPattern>, always return true let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]); if (lMorph.length === 0 || lMorph.length === 1) { if (lDefault) { oToken["lMorph"] = lDefault; } return true; } let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 ); if (lSelect.length > 0) { if (lSelect.length != lMorph.length) { oToken["lMorph"] = lSelect; } } else if (lDefault) { oToken["lMorph"] = lDefault; } return true; } function g_exclude (oToken, sPattern, lDefault=null) { // select morphologies for <oToken> according to <sPattern>, always return true let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]); if (lMorph.length === 0 || lMorph.length === 1) { if (lDefault) { oToken["lMorph"] = lDefault; } return true; } let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 ); if (lSelect.length > 0) { if (lSelect.length != lMorph.length) { oToken["lMorph"] = lSelect; } } else if (lDefault) { oToken["lMorph"] = lDefault; } return true; } function g_add_morph (oToken, lNewMorph) { "Disambiguation: add a morphology to a token" let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]); lMorph.push(...lNewMorph); oToken["lMorph"] = lMorph; return true; } function g_define (oToken, lMorph) { // set morphologies of <oToken>, always return true oToken["lMorph"] = lMorph; return true; } function g_define_from (oToken, nLeft=null, nRight=null) { let sValue = oToken["sValue"]; if (nLeft !== null) { sValue = (nRight !== null) ? sValue.slice(nLeft, nRight) : sValue.slice(nLeft); } oToken["lMorph"] = _oSpellChecker.getMorph(sValue); return true; } function g_change_meta (oToken, sType) { // Disambiguation: change type of token oToken["sType"] = sType; return true; } //////// GRAMMAR CHECKER PLUGINS ${pluginsJS} // generated code, do not edit var gc_engine_func = { load: function (sContext, oSpellChecker) { _sAppContext = sContext _oSpellChecker = oSpellChecker }, // callables for regex rules ${callablesJS} // callables for graph rules ${graph_callablesJS} } if (typeof(exports) !== 'undefined') { exports.load = gc_engine_func.load; } |
Modified gc_core/js/lang_core/gc_options.js from [ece26d7264] to [6f3ff68ba6].
1 2 3 4 5 6 7 8 9 10 | // Options for Grammalecte /* jshint esversion:6 */ /* jslint esversion:6 */ /* global exports */ ${map} var gc_options = { | > > > > > > > > > > > > > > > > > > > > | > > > > > > > > > > > | > > > > > > > | | | | | | | | | | | | > > > > > > > | | | | 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 | // Options for Grammalecte /* jshint esversion:6 */ /* jslint esversion:6 */ /* global exports */ ${map} var gc_options = { dOptions: new Map(), sAppContext: "JavaScript", load: function (sContext="JavaScript") { this.sAppContext = sContext; this.dOptions = this.getDefaultOptions(sContext); }, setOption: function (sOpt, bVal) { if (this.dOptions.has(sOpt)) { this.dOptions.set(sOpt, bVal); } }, setOptions: function (dOpt) { this.dOptions.gl_updateOnlyExistingKeys(dOpt); }, getOptions: function () { return this.dOptions.gl_shallowCopy(); }, resetOptions: function () { this.dOptions = this.getDefaultOptions(this._sAppContext); }, getDefaultOptions: function (sContext="") { if (!sContext) { sContext = this.sAppContext; } if (this.oDefaultOpt.hasOwnProperty(sContext)) { return this.oDefaultOpt[sContext].gl_shallowCopy(); } return this.oDefaultOpt["JavaScript"].gl_shallowCopy(); }, getOptionLabels: function (sLang="${sLang}") { if (this.oOptLabel.hasOwnProperty(sLang)) { return this.oOptLabel[sLang]; } return this.oOptLabel["{$sLang}"]; }, getOptionsColors: function (sTheme="Default", sColorType="aRGB") { let oOptColor = (this.oOptColor.hasOwnProperty(sTheme)) ? this.oOptColor[sTheme] : this.oOptColor["Default"]; let oColorType = (this.oColorType.hasOwnProperty(sColorType)) ? this.oColorType[sColorType] : this.oColorType["aRGB"]; let oColor = {}; try { for (let [sOpt, sColor] of Object.entries(oOptColor)) { oColor[sOpt] = oColorType[sColor]; } return oColor; } catch (e) { console.error(e); return {}; } }, lStructOpt: ${lStructOpt}, oDefaultOpt: { "JavaScript": new Map (${dOptJavaScript}), "Firefox": new Map (${dOptFirefox}), "Thunderbird": new Map (${dOptThunderbird}), }, oColorType: ${dColorType}, oOptColor: ${dOptColor}, oOptLabel: ${dOptLabel} }; if (typeof(exports) !== 'undefined') { exports.dOptions = gc_options.dOptions; exports.sAppContext = gc_options.sAppContext; exports.load = gc_options.load; exports.setOption = gc_options.setOption; exports.setOptions = gc_options.setOptions; exports.resetOptions = gc_options.resetOptions; exports.getDefaultOptions = gc_options.getDefaultOptions; exports.getOptions = gc_options.getOptions; exports.getOptionsColors = gc_options.getOptionsColors; exports.lStructOpt = gc_options.lStructOpt; exports.oDefaultOpt = gc_options.oDefaultOpt; exports.dColorType = gc_options.dColorType; exports.oOptColor = gc_options.oOptColor; exports.oOptLabel = gc_options.oOptLabel; } |
Modified gc_core/py/__init__.py from [49f46a05ff] to [3c70db889b].
1 2 3 4 | """ Grammar checker """ | | | 1 2 3 4 5 | """ Grammar checker """ from .${lang}.gc_engine import * |
Deleted gc_core/py/grammar_checker.py version [50b054f72f].
|
| < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < |
Modified gc_core/py/lang_core/gc_engine.py from [c796a47a03] to [db20a56eec].
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 | """ Grammalecte Grammar checker engine """ import re import traceback #import unicodedata from itertools import chain from ..graphspell.spellchecker import SpellChecker from ..graphspell.echo import echo from .. import text from . import gc_options try: # LibreOffice / OpenOffice from com.sun.star.linguistic2 import SingleProofreadingError from com.sun.star.text.TextMarkupType import PROOFREADING from com.sun.star.beans import PropertyValue #import lightproof_handler_${implname} as opt _bWriterError = True except ImportError: _bWriterError = False | > > > > | | < | | < < < > > > < < | < < | > > > > | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | """ Grammalecte Grammar checker engine """ import re import traceback import json import importlib #import unicodedata from itertools import chain from ..graphspell.spellchecker import SpellChecker from ..graphspell.echo import echo from .. import text from . import gc_engine_func as gce_func from . import gc_options try: # LibreOffice / OpenOffice from com.sun.star.linguistic2 import SingleProofreadingError from com.sun.star.text.TextMarkupType import PROOFREADING from com.sun.star.beans import PropertyValue #import lightproof_handler_${implname} as opt _bWriterError = True except ImportError: _bWriterError = False #__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \ # "load", "parse", "getSpellChecker", "getTextFormatter", "getLexicographer" \ # "ignoreRule", "resetIgnoreRules", "reactivateRule", "listRules", "displayRules", "setWriterUnderliningStyle" ] __version__ = "${version}" lang = "${lang}" locales = ${loc} pkg = "${implname}" name = "${name}" version = "${version}" author = "${author}" # Modules _rules = None # module gc_rules _rules_graph = None # module gc_rules_graph # Tools _oSpellChecker = None _oTokenizer = None # Data _aIgnoredRules = set() # Writer underlining style _dOptionsColors = None _bMulticolor = True _nUnderliningStyle = 0 #### Initialization def load (sContext="Python", sColorType="aRGB"): "initialization of the grammar checker" global _oSpellChecker global _dOptionsColors global _oTokenizer try: _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}") _oSpellChecker.activateStorage() _oTokenizer = _oSpellChecker.getTokenizer() gce_func.load(sContext, _oSpellChecker) gc_options.load(sContext) _dOptionsColors = gc_options.getOptionsColors(sContext, sColorType) except: traceback.print_exc() #### Tools def getSpellChecker (): "return the spellchecker object" return _oSpellChecker #### Rules |
︙ | ︙ | |||
127 128 129 130 131 132 133 | def reactivateRule (sRuleId): "(re)activate rule <sRuleId>" _aIgnoredRules.discard(sRuleId) def listRules (sFilter=None): | | | 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | def reactivateRule (sRuleId): "(re)activate rule <sRuleId>" _aIgnoredRules.discard(sRuleId) def listRules (sFilter=None): "generator: returns tuple (sRuleType, sOption, sLineId, sRuleId)" if sFilter: try: zFilter = re.compile(sFilter) except re.error: echo("# Error. List rules: wrong regex.") sFilter = None # regex rules |
︙ | ︙ | |||
153 154 155 156 157 158 159 | def displayRules (sFilter=None): "display the name of rules, with the filter <sFilter>" echo("List of rules. Filter: << " + str(sFilter) + " >>") for sOption, sLineId, sRuleId, sType in listRules(sFilter): echo("{:<8} {:<10} {:<10} {}".format(sOption, sLineId, sRuleId, sType)) | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | def displayRules (sFilter=None): "display the name of rules, with the filter <sFilter>" echo("List of rules. Filter: << " + str(sFilter) + " >>") for sOption, sLineId, sRuleId, sType in listRules(sFilter): echo("{:<8} {:<10} {:<10} {}".format(sOption, sLineId, sRuleId, sType)) def setWriterUnderliningStyle (sStyle="BOLDWAVE", bMulticolor=True): "set underlining style for Writer (WAVE, BOLDWAVE, BOLD)" global _nUnderliningStyle global _bMulticolor # https://api.libreoffice.org/docs/idl/ref/FontUnderline_8idl.html # WAVE: 10, BOLD: 12, BOLDWAVE: 18 DASH: 5 |
︙ | ︙ | |||
217 218 219 220 221 222 223 224 225 226 227 228 229 230 | _nUnderliningStyle = 5 else: _nUnderliningStyle = 0 _bMulticolor = bMulticolor #### Parsing def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False): "init point to analyse <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors" oText = TextParser(sText) return oText.parse(sCountry, bDebug, dOptions, bContext, bFullInfo) | > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 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 | _nUnderliningStyle = 5 else: _nUnderliningStyle = 0 _bMulticolor = bMulticolor #### Parsing def getParagraphErrors (sText, dOptions=None, bContext=False, bSpellSugg=False, bDebug=False): "returns a tuple: (grammar errors, spelling errors)" aGrammErrs = parse(sText, "FR", bDebug=bDebug, dOptions=dOptions, bContext=bContext) aSpellErrs = _oSpellChecker.parseParagraph(sText, bSpellSugg) return aGrammErrs, aSpellErrs def getParagraphWithErrors (sText, dOptions=None, bEmptyIfNoErrors=False, bSpellSugg=False, nWidth=100, bDebug=False): "parse text and return a readable text with underline errors" aGrammErrs, aSpellErrs = getParagraphErrors(sText, dOptions, False, bSpellSugg, bDebug) if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs: return ("", []) return text.generateParagraph(sText, aGrammErrs, aSpellErrs, nWidth) def getParagraphErrorsAsJSON (iIndex, sText, dOptions=None, bContext=False, bEmptyIfNoErrors=False, bSpellSugg=False, bReturnText=False, lLineSet=None, bDebug=False): "parse text and return errors as a JSON string" aGrammErrs, aSpellErrs = getParagraphErrors(sText, dOptions, bContext, bSpellSugg, bDebug) aGrammErrs = list(aGrammErrs) if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs: return "" if lLineSet: aGrammErrs, aSpellErrs = text.convertToXY(aGrammErrs, aSpellErrs, lLineSet) return json.dumps({ "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False) if bReturnText: return json.dumps({ "iParagraph": iIndex, "sText": sText, "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False) return json.dumps({ "iParagraph": iIndex, "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False) def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False): "init point to analyse <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors" oText = TextParser(sText) return oText.parse(sCountry, bDebug, dOptions, bContext, bFullInfo) |
︙ | ︙ | |||
260 261 262 263 264 265 266 | #for nPos, dToken in self.dTokenPos.items(): # s += "{}\t{}\n".format(nPos, dToken) return s def parse (self, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False): "analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors" #sText = unicodedata.normalize("NFC", sText) | | | | 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | #for nPos, dToken in self.dTokenPos.items(): # s += "{}\t{}\n".format(nPos, dToken) return s def parse (self, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False): "analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors" #sText = unicodedata.normalize("NFC", sText) dOpt = dOptions or gc_options.dOptions bShowRuleId = gc_options.dOptions.get('idrule', False) # parse paragraph try: self.parseText(self.sText, self.sText0, True, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext) except: raise if bFullInfo: lParagraphErrors = list(self.dError.values()) |
︙ | ︙ | |||
338 339 340 341 342 343 344 | for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup: if sRuleId not in _aIgnoredRules: for m in zRegex.finditer(sText): bCondMemo = None for sFuncCond, cActionType, sWhat, *eAct in lActions: # action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ] try: | | | | 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 | for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup: if sRuleId not in _aIgnoredRules: for m in zRegex.finditer(sText): bCondMemo = None for sFuncCond, cActionType, sWhat, *eAct in lActions: # action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ] try: bCondMemo = not sFuncCond or getattr(gce_func, sFuncCond)(sText, sText0, m, self.dTokenPos, sCountry, bCondMemo) if bCondMemo: if bDebug: echo("RULE: " + sLineId) if cActionType == "-": # grammar error nErrorStart = nOffset + m.start(eAct[0]) if nErrorStart not in self.dError or nPriority > self.dErrorPriority.get(nErrorStart, -1): self.dError[nErrorStart] = self._createErrorFromRegex(sText, sText0, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bShowRuleId, sOption, bContext) self.dErrorPriority[nErrorStart] = nPriority self.dSentenceError[nErrorStart] = self.dError[nErrorStart] elif cActionType == "~": # text processor sText = self.rewriteText(sText, sWhat, eAct[0], m, bUppercase) bChange = True if bDebug: echo("~ " + sText + " -- " + m.group(eAct[0]) + " # " + sLineId) elif cActionType == "=": # disambiguation if not bParagraph: getattr(gce_func, sWhat)(sText, m, self.dTokenPos) if bDebug: echo("= " + m.group(0) + " # " + sLineId) elif cActionType == ">": # we do nothing, this test is just a condition to apply all following actions pass else: echo("# error: unknown action at " + sLineId) |
︙ | ︙ | |||
584 585 586 587 588 589 590 | for sLineId, nextNodeKey in dNode.items(): bCondMemo = None for sRuleId in dGraph[nextNodeKey]: try: if bDebug: echo(" >TRY: " + sRuleId + " " + sLineId) _, sOption, sFuncCond, cActionType, sWhat, *eAct = _rules_graph.dRule[sRuleId] | | | | | | | | | 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 | for sLineId, nextNodeKey in dNode.items(): bCondMemo = None for sRuleId in dGraph[nextNodeKey]: try: if bDebug: echo(" >TRY: " + sRuleId + " " + sLineId) _, sOption, sFuncCond, cActionType, sWhat, *eAct = _rules_graph.dRule[sRuleId] # Suggestion [ sActionLineId, option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ] # TextProcessor [ sActionLineId, option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ] # Disambiguator [ sActionLineId, option, condition, "=", replacement/suggestion/action ] # Tag [ sActionLineId, option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ] # Immunity [ sActionLineId, option, condition, "!", "", iTokenStart, iTokenEnd ] # Test [ sActionLineId, option, condition, ">", "" ] if not sOption or dOptions.get(sOption, False): bCondMemo = not sFuncCond or getattr(gce_func, sFuncCond)(self.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, self.dTags, self.sSentence, self.sSentence0) if bCondMemo: if cActionType == "-": # grammar error iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL = eAct nTokenErrorStart = nTokenOffset + iTokenStart if iTokenStart > 0 else nLastToken + iTokenStart if "bImmune" not in self.lToken[nTokenErrorStart]: nTokenErrorEnd = nTokenOffset + iTokenEnd if iTokenEnd > 0 else nLastToken + iTokenEnd |
︙ | ︙ | |||
617 618 619 620 621 622 623 | nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1] self._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug) bChange = True if bDebug: echo(" TEXT_PROCESSOR: [{}:{}] > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat)) elif cActionType == "=": # disambiguation | | | 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 | nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1] self._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug) bChange = True if bDebug: echo(" TEXT_PROCESSOR: [{}:{}] > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat)) elif cActionType == "=": # disambiguation getattr(gce_func, sWhat)(self.lToken, nTokenOffset, nLastToken) if bDebug: echo(" DISAMBIGUATOR: ({}) [{}:{}]".format(sWhat, self.lToken[nTokenOffset+1]["sValue"], self.lToken[nLastToken]["sValue"])) elif cActionType == ">": # we do nothing, this test is just a condition to apply all following actions if bDebug: echo(" COND_OK") elif cActionType == "/": |
︙ | ︙ | |||
672 673 674 675 676 677 678 | return bChange def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext): nStart = nOffset + m.start(iGroup) nEnd = nOffset + m.end(iGroup) # suggestions if sRepl[0:1] == "=": | | | | | | 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 | return bChange def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext): nStart = nOffset + m.start(iGroup) nEnd = nOffset + m.end(iGroup) # suggestions if sRepl[0:1] == "=": sSugg = getattr(gce_func, sRepl[1:])(sText, m) lSugg = sSugg.split("|") if sSugg else [] elif sRepl == "_": lSugg = [] else: lSugg = m.expand(sRepl).split("|") if bUppercase and lSugg and m.group(iGroup)[0:1].isupper(): lSugg = list(map(lambda s: s[0:1].upper()+s[1:], lSugg)) # Message sMessage = getattr(gce_func, sMsg[1:])(sText, m) if sMsg[0:1] == "=" else m.expand(sMsg) if bShowRuleId: sMessage += " #" + sLineId + " / " + sRuleId # if _bWriterError: return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL) return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) def _createErrorFromTokens (self, sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext): # suggestions if sSugg[0:1] == "=": sSugg = getattr(gce_func, sSugg[1:])(self.lToken, nTokenOffset, nLastToken) lSugg = sSugg.split("|") if sSugg else [] elif sSugg == "_": lSugg = [] else: lSugg = self._expand(sSugg, nTokenOffset, nLastToken).split("|") if bCaseSvty and lSugg and self.lToken[iFirstToken]["sValue"][0:1].isupper(): lSugg = list(map(lambda s: s[0:1].upper()+s[1:], lSugg)) # Message sMessage = getattr(gce_func, sMsg[1:])(self.lToken, nTokenOffset, nLastToken) if sMsg[0:1] == "=" else self._expand(sMsg, nTokenOffset, nLastToken) if bShowRuleId: sMessage += " #" + sLineId + " / " + sRuleId # if _bWriterError: return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL) return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) |
︙ | ︙ | |||
765 766 767 768 769 770 771 | if sRepl == "*": sNew = " " * nLen elif sRepl == "_": sNew = "_" * nLen elif sRepl == "@": sNew = "@" * nLen elif sRepl[0:1] == "=": | | | 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 | if sRepl == "*": sNew = " " * nLen elif sRepl == "_": sNew = "_" * nLen elif sRepl == "@": sNew = "@" * nLen elif sRepl[0:1] == "=": sNew = getattr(gce_func, sRepl[1:])(sText, m) sNew = sNew + " " * (nLen-len(sNew)) if bUppercase and m.group(iGroup)[0:1].isupper(): sNew = sNew.capitalize() else: sNew = m.expand(sRepl) sNew = sNew + " " * (nLen-len(sNew)) return sText[0:m.start(iGroup)] + sNew + sText[m.end(iGroup):] |
︙ | ︙ | |||
795 796 797 798 799 800 801 | if nTokenRewriteEnd - nTokenRewriteStart == 0: self.lToken[nTokenRewriteStart]["sNewValue"] = "_" else: for i in range(nTokenRewriteStart, nTokenRewriteEnd+1): self.lToken[i]["sNewValue"] = "_" else: if sWhat.startswith("="): | | | 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 | if nTokenRewriteEnd - nTokenRewriteStart == 0: self.lToken[nTokenRewriteStart]["sNewValue"] = "_" else: for i in range(nTokenRewriteStart, nTokenRewriteEnd+1): self.lToken[i]["sNewValue"] = "_" else: if sWhat.startswith("="): sWhat = getattr(gce_func, sWhat[1:])(self.lToken, nTokenOffset, nLastToken) else: sWhat = self._expand(sWhat, nTokenOffset, nLastToken) bUppercase = bCaseSvty and self.lToken[nTokenRewriteStart]["sValue"][0:1].isupper() if nTokenRewriteEnd - nTokenRewriteStart == 0: # one token if bUppercase: sWhat = sWhat[0:1].upper() + sWhat[1:] |
︙ | ︙ | |||
869 870 871 872 873 874 875 | except KeyError: echo(self) echo(dToken) if bDebug: echo(" TEXT REWRITED: " + self.sSentence) self.lToken.clear() self.lToken = lNewToken | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | 858 859 860 861 862 863 864 | except KeyError: echo(self) echo(dToken) if bDebug: echo(" TEXT REWRITED: " + self.sSentence) self.lToken.clear() self.lToken = lNewToken |
Added gc_core/py/lang_core/gc_engine_func.py version [059237a0d9].
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 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 | """ Grammar checking functions """ # generated code, do not edit # source: gc_core/py/lang_core/gc_engine_func.py import re from . import gc_options from ..graphspell.echo import echo _sAppContext = "Python" # what software is running _oSpellChecker = None def load (sContext, oSpellChecker): global _sAppContext global _oSpellChecker _sAppContext = sContext _oSpellChecker = oSpellChecker #### common functions def option (sOpt): "return True if option <sOpt> is active" return gc_options.dOptions.get(sOpt, False) #### Functions to get text outside pattern scope # warning: check compile_rules.py to understand how it works _zNextWord = re.compile(r" +(\w[\w-]*)") _zPrevWord = re.compile(r"(\w[\w-]*) +$") 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)" m = _zNextWord.match(s[iStart:]) if not m: return None return (iStart+m.start(1), m.group(1)) def prevword1 (s, iEnd): "get previous word (optimization)" m = _zPrevWord.search(s[:iEnd]) if not m: return None return (m.start(1), m.group(1)) def look (s, sPattern, sNegPattern=None): "seek sPattern in s (before/after/fulltext), if sNegPattern not in s" if sNegPattern and re.search(sNegPattern, s): return False if re.search(sPattern, s): return True return False def look_chk1 (dTokenPos, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1=""): "returns True if s has pattern sPattern and m.group(1) has pattern sPatternGroup1" m = re.search(sPattern, s) if not m: return False try: sWord = m.group(1) nPos = m.start(1) + nOffset except IndexError: return False return morph(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1) #### Analyse groups for regex rules def displayInfo (dTokenPos, tWord): "for debugging: retrieve info of word" if not tWord: print("> nothing to find") return True lMorph = _oSpellChecker.getMorph(tWord[1]) if not lMorph: print("> not in dictionary") return True print("TOKENS:", dTokenPos) if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]]: print("DA: " + str(dTokenPos[tWord[0]]["lMorph"])) print("FSA: " + str(lMorph)) return True def morph (dTokenPos, tWord, 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 not tWord: return bNoWord lMorph = dTokenPos[tWord[0]]["lMorph"] if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]] else _oSpellChecker.getMorph(tWord[1]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) def analyse (sWord, sPattern, sNegPattern=""): "analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)" lMorph = _oSpellChecker.getMorph(sWord) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) #### Analyse tokens for graph rules def g_value (dToken, sValues, nLeft=None, nRight=None): "test if <dToken['sValue']> is in sValues (each value should be separated with |)" sValue = "|"+dToken["sValue"]+"|" if nLeft is None else "|"+dToken["sValue"][slice(nLeft, nRight)]+"|" if sValue in sValues: return True if dToken["sValue"][0:2].istitle(): # we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout". if sValue.lower() in sValues: return True elif dToken["sValue"].isupper(): #if sValue.lower() in sValues: # return True sValue = "|"+sValue[1:].capitalize() if sValue in sValues: return True sValue = sValue.lower() if sValue in sValues: return True return False def g_morph (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True): "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies" if "lMorph" in dToken: lMorph = dToken["lMorph"] else: if nLeft is not None: lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)]) if bMemorizeMorph: dToken["lMorph"] = lMorph else: lMorph = _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) def g_analyse (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True): "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)" if nLeft is not None: lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)]) if bMemorizeMorph: dToken["lMorph"] = lMorph else: lMorph = _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) def g_merged_analyse (dToken1, dToken2, cMerger, sPattern, sNegPattern="", bSetMorph=True): "merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)" lMorph = _oSpellChecker.getMorph(dToken1["sValue"] + cMerger + dToken2["sValue"]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) bResult = all(zPattern.search(sMorph) for sMorph in lMorph) if bResult and bSetMorph: dToken1["lMorph"] = lMorph return bResult zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) bResult = any(zPattern.search(sMorph) for sMorph in lMorph) if bResult and bSetMorph: dToken1["lMorph"] = lMorph return bResult def g_tag_before (dToken, dTags, sTag): "returns True if <sTag> is present on tokens before <dToken>" if sTag not in dTags: return False if dToken["i"] > dTags[sTag][0]: return True return False def g_tag_after (dToken, dTags, sTag): "returns True if <sTag> is present on tokens after <dToken>" if sTag not in dTags: return False if dToken["i"] < dTags[sTag][1]: return True return False def g_tag (dToken, sTag): "returns True if <sTag> is present on token <dToken>" return "aTags" in dToken and sTag in dToken["aTags"] def g_meta (dToken, sType): "returns True if <sType> is equal to the token type" return dToken["sType"] == sType def g_space_between_tokens (dToken1, dToken2, nMin, nMax=None): "checks if spaces between tokens is >= <nMin> and <= <nMax>" nSpace = dToken2["nStart"] - dToken1["nEnd"] if nSpace < nMin: return False if nMax is not None and nSpace > nMax: return False return True def g_token (lToken, i): "return token at index <i> in lToken (or the closest one)" if i < 0: return lToken[0] if i >= len(lToken): return lToken[-1] return lToken[i] #### Disambiguator for regex rules def select (dTokenPos, nPos, sWord, sPattern, lDefault=None): "Disambiguation: select morphologies of <sWord> matching <sPattern>" if not sWord: return True if nPos not in dTokenPos: print("Error. There should be a token at this position: ", nPos) return True lMorph = _oSpellChecker.getMorph(sWord) if not lMorph or len(lMorph) == 1: return True lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dTokenPos[nPos]["lMorph"] = lSelect elif lDefault: dTokenPos[nPos]["lMorph"] = lDefault return True def exclude (dTokenPos, nPos, sWord, sPattern, lDefault=None): "Disambiguation: exclude morphologies of <sWord> matching <sPattern>" if not sWord: return True if nPos not in dTokenPos: print("Error. There should be a token at this position: ", nPos) return True lMorph = _oSpellChecker.getMorph(sWord) if not lMorph or len(lMorph) == 1: return True lSelect = [ sMorph for sMorph in lMorph if not re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dTokenPos[nPos]["lMorph"] = lSelect elif lDefault: dTokenPos[nPos]["lMorph"] = lDefault return True def define (dTokenPos, nPos, lMorph): "Disambiguation: set morphologies of token at <nPos> with <lMorph>" if nPos not in dTokenPos: print("Error. There should be a token at this position: ", nPos) return True dTokenPos[nPos]["lMorph"] = lMorph return True #### Disambiguation for graph rules def g_select (dToken, sPattern, lDefault=None): "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True" lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph or len(lMorph) == 1: if lDefault: dToken["lMorph"] = lDefault #print("DA:", dToken["sValue"], dToken["lMorph"]) return True lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dToken["lMorph"] = lSelect elif lDefault: dToken["lMorph"] = lDefault #print("DA:", dToken["sValue"], dToken["lMorph"]) return True def g_exclude (dToken, sPattern, lDefault=None): "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True" lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph or len(lMorph) == 1: if lDefault: dToken["lMorph"] = lDefault #print("DA:", dToken["sValue"], dToken["lMorph"]) return True lSelect = [ sMorph for sMorph in lMorph if not re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dToken["lMorph"] = lSelect elif lDefault: dToken["lMorph"] = lDefault #print("DA:", dToken["sValue"], dToken["lMorph"]) return True def g_add_morph (dToken, lNewMorph): "Disambiguation: add a morphology to a token" lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"]) lMorph.extend(lNewMorph) dToken["lMorph"] = lMorph return True def g_define (dToken, lMorph): "Disambiguation: set morphologies of <dToken>, always return True" dToken["lMorph"] = lMorph #print("DA:", dToken["sValue"], lMorph) return True def g_define_from (dToken, nLeft=None, nRight=None): "Disambiguation: set morphologies of <dToken> with slicing its value with <nLeft> and <nRight>" if nLeft is not None: dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)]) else: dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"]) return True def g_change_meta (dToken, sType): "Disambiguation: change type of token" dToken["sType"] = sType return True #### GRAMMAR CHECKER PLUGINS ${plugins} #### CALLABLES FOR REGEX RULES (generated code) ${callables} #### CALLABLES FOR GRAPH RULES (generated code) ${graph_callables} |
Modified gc_core/py/lang_core/gc_options.py from [b668596de4] to [4cbd062c46].
1 2 3 4 5 6 7 8 | """ Grammar checker default options """ # generated code, do not edit import traceback | > > > > > > > > > > > > > > > > > > > > > > > > > > > | > > > > > > > > > > > > > > > > > > | | > > | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | """ Grammar checker default options """ # generated code, do not edit # source: gc_core/py/lang_core/gc_options.py import traceback dOptions = {} _sAppContext = "Python" def load (sContext="Python"): global dOptions global _sAppContext _sAppContext = sContext dOptions = getDefaultOptions(sContext) def setOption (sOpt, bVal): "set option <sOpt> with <bVal> if it exists" if sOpt in dOptions: dOptions[sOpt] = bVal def setOptions (dOpt): "update the dictionary of options with <dOpt>, only known options are updated" for sKey, bVal in dOpt.items(): if sKey in dOptions: dOptions[sKey] = bVal def getOptions (): "return a copy of options as dictionary" return dOptions.copy() def resetOptions (): "set options to default values" global dOptions dOptions = getDefaultOptions() def displayOptions (sLang="${lang}"): "display the list of grammar checking options" print("Options:") print("\n".join( [ k+":\t"+str(v)+"\t"+getOptionLabels(sLang).get(k, ("?", ""))[0] for k, v in sorted(dOptions.items()) ] )) print("") def getOptionLabels (sLang="${sLang}"): "returns dictionary of UI labels" if sLang in _dOptLabel: return _dOptLabel[sLang] return _dOptLabel["${sLang}"] def getDefaultOptions (sContext=""): "returns dictionary of options" if not sContext: sContext = _sAppContext if sContext in _dDefaultOpt: return _dDefaultOpt[sContext].copy() # duplication necessary, to be able to reset to default return _dDefaultOpt["Python"].copy() # duplication necessary, to be able to reset to default def getOptionsColors (sTheme="Default", sColorType="aRGB"): "returns dictionary of options colors" dOptColor = _dOptColor[sTheme] if sTheme in _dOptColor else _dOptColor["Default"] dColorType = _dColorType[sColorType] if sColorType in _dColorType else _dColorType["aRGB"] try: return { sOpt: dColorType[sColor] for sOpt, sColor in dOptColor.items() } except KeyError: traceback.print_exc() return {} lStructOpt = ${lStructOpt} _dDefaultOpt = { "Python": ${dOptPython}, "Server": ${dOptServer}, "Writer": ${dOptWriter} } _dColorType= ${dColorType} |
︙ | ︙ |
Modified gc_core/py/oxt/Grammalecte.py from [d7f4535da4] to [9c6625ba22].
︙ | ︙ | |||
11 12 13 14 15 16 17 | from com.sun.star.linguistic2 import XProofreader, XSupportedLocales from com.sun.star.linguistic2 import ProofreadingResult from com.sun.star.lang import XServiceInfo, XServiceName, XServiceDisplayName from com.sun.star.lang import Locale import helpers | | | | | | | | 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | from com.sun.star.linguistic2 import XProofreader, XSupportedLocales from com.sun.star.linguistic2 import ProofreadingResult from com.sun.star.lang import XServiceInfo, XServiceName, XServiceDisplayName from com.sun.star.lang import Locale import helpers import grammalecte.${lang} as gc_engine #import lightproof_handler_${implname} as opt_handler import Options class Grammalecte (unohelper.Base, XProofreader, XServiceInfo, XServiceName, XServiceDisplayName, XSupportedLocales): def __init__ (self, ctx, *args): self.ctx = ctx self.ServiceName = "com.sun.star.linguistic2.Proofreader" self.ImplementationName = "org.openoffice.comp.pyuno.Lightproof." + gc_engine.pkg self.SupportedServiceNames = (self.ServiceName, ) self.locales = [] for i in gc_engine.locales: l = gc_engine.locales[i] self.locales.append(Locale(l[0], l[1], l[2])) self.locales = tuple(self.locales) # debug #helpers.startConsole() # init gc_engine.load("Writer", "nInt") # GC options #xContext = uno.getComponentContext() #opt_handler.load(xContext) dOpt = Options.loadOptions("${lang}") gc_engine.gc_options.setOptions(dOpt) # dictionaries options self.loadUserDictionaries() # underlining options self.setWriterUnderliningStyle() # store for results of big paragraphs self.dResult = {} self.nMaxRes = 1500 |
︙ | ︙ | |||
107 108 109 110 111 112 113 | if nHashedVal in self.dResult: return self.dResult[nHashedVal] # WORKAROUND ->>> xRes.nBehindEndOfSentencePosition = xRes.nStartOfNextSentencePosition try: | | | | | | | | | | | 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 | if nHashedVal in self.dResult: return self.dResult[nHashedVal] # WORKAROUND ->>> xRes.nBehindEndOfSentencePosition = xRes.nStartOfNextSentencePosition try: xRes.aErrors = tuple(gc_engine.parse(rText, rLocale.Country)) # ->>> WORKAROUND if xRes.nStartOfNextSentencePosition > 3000: self.dResult[nHashedVal] = xRes self.nRes += 1 if self.nRes > self.nMaxRes: del self.dResult[self.lLastRes.popleft()] self.nRes = self.nMaxRes self.lLastRes.append(nHashedVal) # END OF WORKAROUND except: traceback.print_exc() return xRes def ignoreRule (self, rid, aLocale): gc_engine.ignoreRule(rid) def resetIgnoreRules (self): gc_engine.resetIgnoreRules() # XServiceDisplayName def getServiceDisplayName (self, aLocale): return gc_engine.name # Grammalecte def getSpellChecker (self): return gc_engine.getSpellChecker() def loadUserDictionaries (self): try: xSettingNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Other/", False) xChild = xSettingNode.getByName("o_${lang}") if xChild.getPropertyValue("use_personal_dic"): sJSON = xChild.getPropertyValue("personal_dic") if sJSON: oSpellChecker = gc_engine.getSpellChecker(); oSpellChecker.setPersonalDictionary(json.loads(sJSON)) except: traceback.print_exc() def setWriterUnderliningStyle (self): try: xSettingNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Other/", False) xChild = xSettingNode.getByName("o_${lang}") sLineType = xChild.getPropertyValue("line_type") bMulticolor = bool(xChild.getPropertyValue("line_multicolor")) gc_engine.setWriterUnderliningStyle(sLineType, bMulticolor) except: traceback.print_exc() g_ImplementationHelper = unohelper.ImplementationHelper() g_ImplementationHelper.addImplementation(Grammalecte, "org.openoffice.comp.pyuno.Lightproof."+gc_engine.pkg, ("com.sun.star.linguistic2.Proofreader",),) # g_ImplementationHelper.addImplementation( opt_handler.LightproofOptionsEventHandler, \ # "org.openoffice.comp.pyuno.LightproofOptionsEventHandler." + gc_engine.pkg, ("com.sun.star.awt.XContainerWindowEventHandler",),) |
Modified gc_core/py/oxt/Options.py from [3ed542ae4e] to [4ae6a22f71].
︙ | ︙ | |||
9 10 11 12 13 14 15 | from com.sun.star.awt import XActionListener from com.sun.star.beans import PropertyValue import helpers import op_strings try: | | | | | 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 | from com.sun.star.awt import XActionListener from com.sun.star.beans import PropertyValue import helpers import op_strings try: import grammalecte.${lang} as gc_engine except: traceback.print_exc() def loadOptions (sLang): "load options from Grammalecte and change them according to LibreOffice settings, returns a dictionary {option_name: boolean}" try: xNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Leaves", False) xChild = xNode.getByName(sLang) dOpt = gc_engine.gc_options.getDefaultOptions("Writer") for sKey in dOpt: sValue = xChild.getPropertyValue(sKey) if sValue != '': dOpt[sKey] = bool(int(sValue)) return dOpt except: print("# Error. Unable to load options of language:", sLang) traceback.print_exc() return gc_engine.gc_options.getDefaultOptions("Writer") def saveOptions (sLang, dOpt): "save options in LibreOffice profile" try: xNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Leaves", True) xChild = xNode.getByName(sLang) |
︙ | ︙ | |||
68 69 70 71 72 73 74 | setattr(xWidget, k, w) self.xDialog.insertByName(name, xWidget) return xWidget def run (self, sUI): try: dUI = op_strings.getUI(sUI) | | | 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | setattr(xWidget, k, w) self.xDialog.insertByName(name, xWidget) return xWidget def run (self, sUI): try: dUI = op_strings.getUI(sUI) dOptionUI = gc_engine.gc_options.getOptionLabels(sUI) # fonts xFDTitle = uno.createUnoStruct("com.sun.star.awt.FontDescriptor") xFDTitle.Height = 9 xFDTitle.Weight = uno.getConstantByName("com.sun.star.awt.FontWeight.BOLD") xFDTitle.Name = "Verdana" |
︙ | ︙ | |||
97 98 99 100 101 102 103 | nHeight = 10 self.lOptionWidgets = [] sProdName, sVersion = helpers.getProductNameAndVersion() if True: # no tab available (bug) | | | 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | nHeight = 10 self.lOptionWidgets = [] sProdName, sVersion = helpers.getProductNameAndVersion() if True: # no tab available (bug) for sOptionType, lOptions in gc_engine.gc_options.lStructOpt: x = 10 y += 10 self._addWidget(sOptionType, 'FixedLine', x, y, nWidth, nHeight, Label = dOptionUI.get(sOptionType, "#err")[0], FontDescriptor= xFDTitle) y += 3 for lOptLine in lOptions: x = 15 y += 10 |
︙ | ︙ | |||
160 161 162 163 164 165 166 | except: traceback.print_exc() # XActionListener def actionPerformed (self, xActionEvent): try: if xActionEvent.ActionCommand == 'Default': | | | | 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 | except: traceback.print_exc() # XActionListener def actionPerformed (self, xActionEvent): try: if xActionEvent.ActionCommand == 'Default': self._setWidgets(gc_engine.gc_options.getDefaultOptions("Writer")) elif xActionEvent.ActionCommand == 'Apply': self._save("${lang}") self.xContainer.endExecute() elif xActionEvent.ActionCommand == 'Cancel': self.xContainer.endExecute() else: print("Wrong command: " + xActionEvent.ActionCommand) except: traceback.print_exc() # Other def _setWidgets (self, dOpt): for w in self.lOptionWidgets: w.State = dOpt.get(w.Name, False) def _save (self, sLang): try: saveOptions(sLang, { w.Name: str(w.State) for w in self.lOptionWidgets }) gc_engine.gc_options.setOptions({ w.Name: bool(w.State) for w in self.lOptionWidgets }) except: traceback.print_exc() |
Modified gc_lang/fr/config.ini from [142318e64f] to [9df20b99dc].
1 2 3 4 5 6 7 8 | [args] lang = fr lang_name = French locales = fr_FR fr_BE fr_CA fr_CH fr_LU fr_BF fr_BJ fr_CD fr_CI fr_CM fr_MA fr_ML fr_MU fr_NE fr_RE fr_SN fr_TG country_default = FR name = Grammalecte implname = grammalecte # always use 3 numbers for version: x.y.z | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 | [args] lang = fr lang_name = French locales = fr_FR fr_BE fr_CA fr_CH fr_LU fr_BF fr_BJ fr_CD fr_CI fr_CM fr_MA fr_ML fr_MU fr_NE fr_RE fr_SN fr_TG country_default = FR name = Grammalecte implname = grammalecte # always use 3 numbers for version: x.y.z version = 2.0.0 author = Olivier R. provider = Grammalecte.net link = https://grammalecte.net description = Correcteur grammatical, orthographique et typographique pour le français. extras = README_fr.txt logo = logo.png |
︙ | ︙ |
Modified gc_lang/fr/mailext/worker/gce_worker.js from [abd0c9c4ba] to [420e3521e3].
︙ | ︙ | |||
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 | // end of copy/paste // no console here, use “dump” let gce = null; // module: grammar checker engine let text = null; let tkz = null; // module: tokenizer let lxg = null; // module: lexicographer let helpers = null; let oTokenizer = null; let oSpellChecker = null; let oLxg = null; function loadGrammarChecker (sGCOptions="", sContext="JavaScript") { if (gce === null) { try { gce = require("resource://grammalecte/fr/gc_engine.js"); helpers = require("resource://grammalecte/graphspell/helpers.js"); text = require("resource://grammalecte/text.js"); tkz = require("resource://grammalecte/graphspell/tokenizer.js"); //lxg = require("resource://grammalecte/fr/lexicographe.js"); oTokenizer = new tkz.Tokenizer("fr"); gce.load(sContext, "sCSS"); oSpellChecker = gce.getSpellChecker(); if (sGCOptions !== "") { | > > | | | 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 | // end of copy/paste // no console here, use “dump” let gce = null; // module: grammar checker engine let gco = null; let text = null; let tkz = null; // module: tokenizer let lxg = null; // module: lexicographer let helpers = null; let oTokenizer = null; let oSpellChecker = null; let oLxg = null; function loadGrammarChecker (sGCOptions="", sContext="JavaScript") { if (gce === null) { try { gco = require("resource://grammalecte/fr/gc_options.js"); gce = require("resource://grammalecte/fr/gc_engine.js"); helpers = require("resource://grammalecte/graphspell/helpers.js"); text = require("resource://grammalecte/text.js"); tkz = require("resource://grammalecte/graphspell/tokenizer.js"); //lxg = require("resource://grammalecte/fr/lexicographe.js"); oTokenizer = new tkz.Tokenizer("fr"); gce.load(sContext, "sCSS"); oSpellChecker = gce.getSpellChecker(); if (sGCOptions !== "") { gco.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); } // we always retrieve options from the gce, for setOptions filters obsolete options return gco.getOptions().gl_toString(); } catch (e) { console.log("# Error: " + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); } } } |
︙ | ︙ | |||
115 116 117 118 119 120 121 | for (let aSugg of oSpellChecker.suggest(sWord, nSuggLimit)) { lSugg.push(...aSugg); } return lSugg.join("|"); } function getOptions () { | | | | | | | | | | | | | | 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 | for (let aSugg of oSpellChecker.suggest(sWord, nSuggLimit)) { lSugg.push(...aSugg); } return lSugg.join("|"); } function getOptions () { return gco.getOptions().gl_toString(); } function getDefaultOptions () { return gco.getDefaultOptions().gl_toString(); } function setOptions (sGCOptions) { gco.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); return gco.getOptions().gl_toString(); } function setOption (sOptName, bValue) { gco.setOptions(new Map([ [sOptName, bValue] ])); return gco.getOptions().gl_toString(); } function resetOptions () { gco.resetOptions(); return gco.getOptions().gl_toString(); } function fullTests (sGCOptions="") { if (!gce || !oSpellChecker || !gco) { return "# Error: grammar checker or dictionary not loaded." } let dMemoOptions = gco.getOptions(); if (sGCOptions) { gco.setOptions(helpers.objectToMap(JSON.parse(sGCOptions))); } let tests = require("resource://grammalecte/tests.js"); let oTest = new tests.TestGrammarChecking(gce); let sAllRes = ""; for (let sRes of oTest.testParse()) { console.log(sRes+"\n"); sAllRes += sRes+"\n"; } gco.setOptions(dMemoOptions); return sAllRes; } |
Deleted gc_lang/fr/modules-js/lexicographe.js version [ff079a1504].
|
| < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < |
Deleted gc_lang/fr/modules/lexicographe.py version [36a85305ff].
|
| < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < |
Modified gc_lang/fr/modules/tests.py from [544edd53c7] to [34a3376ab5].
︙ | ︙ | |||
8 9 10 11 12 13 14 | import os import re import time from contextlib import contextmanager from ..graphspell.ibdawg import IBDAWG from ..graphspell.echo import echo | | | 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | import os import re import time from contextlib import contextmanager from ..graphspell.ibdawg import IBDAWG from ..graphspell.echo import echo from . import gc_engine from . import conj from . import phonet from . import mfsp @contextmanager def timeblock (label, hDst): |
︙ | ︙ | |||
30 31 32 33 34 35 36 | if hDst: hDst.write("{:<12.6}".format(end-start)) def perf (sVersion, hDst=None): "performance tests" print("\nPerformance tests") | | | | | 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | if hDst: hDst.write("{:<12.6}".format(end-start)) def perf (sVersion, hDst=None): "performance tests" print("\nPerformance tests") gc_engine.load() gc_engine.parse("Texte sans importance… utile pour la compilation des règles avant le calcul des perfs.") spHere, _ = os.path.split(__file__) with open(os.path.join(spHere, "perf.txt"), "r", encoding="utf-8") as hSrc: if hDst: hDst.write("{:<12}{:<20}".format(sVersion, time.strftime("%Y.%m.%d %H:%M"))) for sText in ( s.strip() for s in hSrc if not s.startswith("#") and s.strip() ): with timeblock(sText[:sText.find(".")], hDst): gc_engine.parse(sText) if hDst: hDst.write("\n") def _fuckBackslashUTF8 (s): "fuck that shit" return s.replace("\u2019", "'").replace("\u2013", "–").replace("\u2014", "—") |
︙ | ︙ | |||
155 156 157 158 159 160 161 | class TestGrammarChecking (unittest.TestCase): "Tests du correcteur grammatical" @classmethod def setUpClass (cls): | | | 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | class TestGrammarChecking (unittest.TestCase): "Tests du correcteur grammatical" @classmethod def setUpClass (cls): gc_engine.load() cls._zError = re.compile(r"\{\{.*?\}\}") cls._aTestedRules = set() def test_parse (self): zOption = re.compile("^__([a-zA-Z0-9]+)__ ") spHere, _ = os.path.split(__file__) with open(os.path.join(spHere, "gc_test.txt"), "r", encoding="utf-8") as hSrc: |
︙ | ︙ | |||
203 204 205 206 207 208 209 | "\n errors: \n" + sListErr) nError += 1 if nError: print("Unexpected errors:", nError) # untested rules i = 0 echo("Untested rules:") | | | | | | | 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 | "\n errors: \n" + sListErr) nError += 1 if nError: print("Unexpected errors:", nError) # untested rules i = 0 echo("Untested rules:") for _, sOpt, sLineId, sRuleId in gc_engine.listRules(): if sOpt != "@@@@" and sRuleId not in self._aTestedRules and not re.search("^[0-9]+[sp]$|^[pd]_", sRuleId): echo(sLineId + "/" + sRuleId) i += 1 echo("[{} untested rules]".format(i)) def _splitTestLine (self, sLine): sText, sSugg = sLine.split("->>") return (sText.strip(), sSugg.strip()) def _getFoundErrors (self, sLine, sOption): if sOption: gc_engine.gc_options.setOption(sOption, True) aErrs = gc_engine.parse(sLine) gc_engine.gc_options.setOption(sOption, False) else: aErrs = gc_engine.parse(sLine) sRes = " " * len(sLine) sListErr = "" lAllSugg = [] for dErr in aErrs: sRes = sRes[:dErr["nStart"]] + "~" * (dErr["nEnd"] - dErr["nStart"]) + sRes[dErr["nEnd"]:] sListErr += " * {sLineId} / {sRuleId} at {nStart}:{nEnd}\n".format(**dErr) lAllSugg.append("|".join(dErr["aSuggestions"])) |
︙ | ︙ |
Modified gc_lang/fr/modules/textformatter.py from [4ba47078d2] to [8516394c0d].
︙ | ︙ | |||
240 241 242 243 244 245 246 | "mh_frequent_words": True, "ma_word": True, "ma_1letter_lowercase": False, "ma_1letter_uppercase": False } | | < | > | | | > > | | > > > > > | | | | | > | | | | 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 | "mh_frequent_words": True, "ma_word": True, "ma_1letter_lowercase": False, "ma_1letter_uppercase": False } _bCompiled = False def _compileRegex(): global _bCompiled for _, lTup in dReplTable.items(): for i, t in enumerate(lTup): lTup[i] = (re.compile(t[0]), t[1]) _bCompiled = True def formatText (sText, dOpt=None): "returns formatted text" if not _bCompiled: _compileRegex() dOptions = getDefaultOptions() if dOpt: dOptions.update(dOpt) for sOptName, bVal in dOptions.items(): if bVal: for zRgx, sRep in dReplTable[sOptName]: sText = zRgx.sub(sRep, sText) return sText def getDefaultOptions (): "returns default options" return dDefaultOptions.copy() |
Modified gc_lang/fr/oxt/ContextMenu/ContextMenu.py from [f06cffc0e3] to [172f2404b4].
1 2 3 4 5 6 7 8 9 10 11 12 | # Grammalecte - Lexicographe # by Olivier R. License: MPL 2 import uno import unohelper import traceback from com.sun.star.task import XJob from com.sun.star.ui import XContextMenuInterceptor #from com.sun.star.ui.ContextMenuInterceptorAction import IGNORED #from com.sun.star.ui.ContextMenuInterceptorAction import EXECUTE_MODIFIED | < < | | | | > | < | | | | | > | | | 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 | # Grammalecte - Lexicographe # by Olivier R. License: MPL 2 import uno import unohelper import traceback from com.sun.star.task import XJob from com.sun.star.ui import XContextMenuInterceptor #from com.sun.star.ui.ContextMenuInterceptorAction import IGNORED #from com.sun.star.ui.ContextMenuInterceptorAction import EXECUTE_MODIFIED from grammalecte.graphspell.spellchecker import SpellChecker from grammalecte.graphspell.echo import echo import helpers xDesktop = None oSpellChecker = None class MyContextMenuInterceptor (XContextMenuInterceptor, unohelper.Base): def __init__ (self, ctx): self.ctx = ctx def notifyContextMenuExecute (self, xEvent): sWord = self._getWord() try: lWordAndMorph = oSpellChecker.analyze(sWord) if not lWordAndMorph: return uno.Enum("com.sun.star.ui.ContextMenuInterceptorAction", "IGNORED") # don’t work on AOO, have to import the value #return IGNORED xContextMenu = xEvent.ActionTriggerContainer if xContextMenu: # entries index i = xContextMenu.Count nUnoConstantLine = uno.getConstantByName("com.sun.star.ui.ActionTriggerSeparatorType.LINE") # word analysis i = self._addItemToContextMenu(xContextMenu, i, "ActionTriggerSeparator", SeparatorType=nUnoConstantLine) for sWord, lMorph in lWordAndMorph: if len(lMorph) == 1: sMorph, sReadableMorph = lMorph[0] i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=sWord + " : " + sReadableMorph, CommandURL="service:net.grammalecte.AppLauncher?None") elif len(lMorph) >= 1: # submenu xSubMenuContainer = xContextMenu.createInstance("com.sun.star.ui.ActionTriggerContainer") for j, (sMorph, sReadableMorph) in enumerate(lMorph): self._addItemToContextMenu(xSubMenuContainer, j, "ActionTrigger", Text=sReadableMorph, CommandURL="service:net.grammalecte.AppLauncher?None") # create root menu entry i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=sWord, SubContainer=xSubMenuContainer) else: i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=sWord + " : [erreur] aucun résultat trouvé.") # Links to Conjugueur aVerb = { sMorph[1:sMorph.find("/")] for sMorph in oSpellChecker.getMorph(sWord) if ":V" in sMorph } if aVerb: i = self._addItemToContextMenu(xContextMenu, i, "ActionTriggerSeparator", SeparatorType=nUnoConstantLine) for sVerb in aVerb: i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text="Conjuguer “{}”…".format(sVerb), \ CommandURL="service:net.grammalecte.AppLauncher?CJ/"+sVerb) # Search xDoc = xDesktop.getCurrentComponent() xViewCursor = xDoc.CurrentController.ViewCursor if not xViewCursor.isCollapsed(): sSelec = xViewCursor.getString() if sSelec.count(" ") <= 2: |
︙ | ︙ | |||
114 115 116 117 118 119 120 | class JobExecutor (XJob, unohelper.Base): def __init__ (self, ctx): self.ctx = ctx global xDesktop global oSpellChecker | < < < | 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 | class JobExecutor (XJob, unohelper.Base): def __init__ (self, ctx): self.ctx = ctx global xDesktop global oSpellChecker try: if not xDesktop: xDesktop = self.ctx.getServiceManager().createInstanceWithContext('com.sun.star.frame.Desktop', self.ctx) if not oSpellChecker: xCurCtx = uno.getComponentContext() oGC = self.ctx.ServiceManager.createInstanceWithContext("org.openoffice.comp.pyuno.Lightproof.grammalecte", self.ctx) if hasattr(oGC, "getSpellChecker"): # https://bugs.documentfoundation.org/show_bug.cgi?id=97790 oSpellChecker = oGC.getSpellChecker() else: oSpellChecker = SpellChecker("${lang}", "fr-allvars.bdic") except: traceback.print_exc() def execute (self, args): if not args: return try: |
︙ | ︙ |
Modified gc_lang/fr/webext/gce_worker.js from [67fa9791af] to [e414bb30c0].
︙ | ︙ | |||
31 32 33 34 35 36 37 | //console.log("[Worker] GC Engine Worker [start]"); //console.log(self); importScripts("grammalecte/graphspell/helpers.js"); importScripts("grammalecte/graphspell/str_transform.js"); importScripts("grammalecte/graphspell/char_player.js"); | | > | 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 | //console.log("[Worker] GC Engine Worker [start]"); //console.log(self); importScripts("grammalecte/graphspell/helpers.js"); importScripts("grammalecte/graphspell/str_transform.js"); importScripts("grammalecte/graphspell/char_player.js"); importScripts("grammalecte/graphspell/lexgraph_fr.js"); importScripts("grammalecte/graphspell/ibdawg.js"); importScripts("grammalecte/graphspell/spellchecker.js"); importScripts("grammalecte/text.js"); importScripts("grammalecte/graphspell/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_rules_graph.js"); importScripts("grammalecte/fr/gc_engine_func.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. |
︙ | ︙ | |||
150 151 152 153 154 155 156 | let bInitDone = false; let oSpellChecker = null; let oTokenizer = null; | < | 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | let bInitDone = false; let oSpellChecker = null; let oTokenizer = null; let oTest = null; let oLocution = null; /* Technical note: This worker don’t work as a PromiseWorker (which returns a promise), so when we send request |
︙ | ︙ | |||
177 178 179 180 181 182 183 | mfsp.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/mfsp_data.json")); //console.log("[Worker] Modules have been initialized…"); gc_engine.load(sContext, "aHSL", sExtensionPath+"grammalecte/graphspell/_dictionaries"); oSpellChecker = gc_engine.getSpellChecker(); oTest = new TestGrammarChecking(gc_engine, sExtensionPath+"/grammalecte/fr/tests_data.json"); oTokenizer = new Tokenizer("fr"); oLocution = helpers.loadFile(sExtensionPath + "/grammalecte/fr/locutions_data.json"); | | | | | | 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 | mfsp.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/mfsp_data.json")); //console.log("[Worker] Modules have been initialized…"); gc_engine.load(sContext, "aHSL", sExtensionPath+"grammalecte/graphspell/_dictionaries"); oSpellChecker = gc_engine.getSpellChecker(); oTest = new TestGrammarChecking(gc_engine, sExtensionPath+"/grammalecte/fr/tests_data.json"); oTokenizer = new Tokenizer("fr"); oLocution = helpers.loadFile(sExtensionPath + "/grammalecte/fr/locutions_data.json"); lexgraph_fr.load(oSpellChecker, oTokenizer, oLocution); if (dOptions !== null) { if (!(dOptions instanceof Map)) { dOptions = helpers.objectToMap(dOptions); } gc_options.setOptions(dOptions); } //tests(); bInitDone = true; } else { console.log("[Worker] Already initialized…") } // we always retrieve options from the gc_options, for setOptions filters obsolete options dOptions = helpers.mapToObject(gc_options.getOptions()); postMessage(createResponse("init", dOptions, oInfo, true)); } catch (e) { console.error(e); postMessage(createResponse("init", createErrorResult(e, "init failed"), oInfo, true, true)); } } |
︙ | ︙ | |||
246 247 248 249 250 251 252 | function getListOfTokens (sText, oInfo={}) { // lexicographer try { sText = sText.replace(//g, "").normalize("NFC"); for (let sParagraph of text.getParagraph(sText)) { if (sParagraph.trim() !== "") { | | | 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 | function getListOfTokens (sText, oInfo={}) { // lexicographer try { sText = sText.replace(//g, "").normalize("NFC"); for (let sParagraph of text.getParagraph(sText)) { if (sParagraph.trim() !== "") { postMessage(createResponse("getListOfTokens", lexgraph_fr.getListOfTokensReduc(sParagraph, true), oInfo, false)); } } postMessage(createResponse("getListOfTokens", null, oInfo, true)); } catch (e) { console.error(e); postMessage(createResponse("getListOfTokens", createErrorResult(e, "no tokens"), oInfo, true, true)); |
︙ | ︙ |
Modified grammalecte-cli.py from [7b2821616b] to [1c366da1c4].
︙ | ︙ | |||
9 10 11 12 13 14 15 16 17 18 19 20 21 22 | import argparse import json import re import traceback import grammalecte import grammalecte.text as txt from grammalecte.graphspell.echo import echo _EXAMPLE = "Quoi ? Racontes ! Racontes-moi ! Bon sangg, parles ! Oui. Il y a des menteur partout. " \ "Je suit sidéré par la brutales arrogance de cette homme-là. Quelle salopard ! Un escrocs de la pire espece. " \ "Quant sera t’il châtiés pour ses mensonge ? Merde ! J’en aie marre." | > | 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | import argparse import json import re import traceback import grammalecte import grammalecte.text as txt import grammalecte.fr.textformatter as tf from grammalecte.graphspell.echo import echo _EXAMPLE = "Quoi ? Racontes ! Racontes-moi ! Bon sangg, parles ! Oui. Il y a des menteur partout. " \ "Je suit sidéré par la brutales arrogance de cette homme-là. Quelle salopard ! Un escrocs de la pire espece. " \ "Quant sera t’il châtiés pour ses mensonge ? Merde ! J’en aie marre." |
︙ | ︙ | |||
147 148 149 150 151 152 153 | xParser.add_argument("-sug", "--suggest", help="get suggestions list for given word", type=str) xParser.add_argument("-on", "--opt_on", nargs="+", help="activate options") xParser.add_argument("-off", "--opt_off", nargs="+", help="deactivate options") xParser.add_argument("-roff", "--rule_off", nargs="+", help="deactivate rules") xParser.add_argument("-d", "--debug", help="debugging mode (only in interactive mode)", action="store_true") xArgs = xParser.parse_args() | | | < < | | | | | | | | | | | | | | 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 | xParser.add_argument("-sug", "--suggest", help="get suggestions list for given word", type=str) xParser.add_argument("-on", "--opt_on", nargs="+", help="activate options") xParser.add_argument("-off", "--opt_off", nargs="+", help="deactivate options") xParser.add_argument("-roff", "--rule_off", nargs="+", help="deactivate rules") xParser.add_argument("-d", "--debug", help="debugging mode (only in interactive mode)", action="store_true") xArgs = xParser.parse_args() grammalecte.load() oSpellChecker = grammalecte.getSpellChecker() if xArgs.personal_dict: oJSON = loadDictionary(xArgs.personal_dict) if oJSON: oSpellChecker.setPersonalDictionary(oJSON) if not xArgs.json: echo("Python v" + sys.version) echo("Grammalecte v{}".format(grammalecte.version)) # list options or rules if xArgs.list_options or xArgs.list_rules: if xArgs.list_options: grammalecte.gc_options.displayOptions() if xArgs.list_rules: grammalecte.displayRules(None if xArgs.list_rules == "*" else xArgs.list_rules) exit() # spell suggestions if xArgs.suggest: for lSugg in oSpellChecker.suggest(xArgs.suggest): if xArgs.json: sText = json.dumps({ "aSuggestions": lSugg }, ensure_ascii=False) else: sText = "Suggestions : " + " | ".join(lSugg) echo(sText) exit() # disable options if not xArgs.json: xArgs.context = False if xArgs.concat_lines: xArgs.textformatter = False # grammar options grammalecte.gc_options.setOptions({"html": True, "latex": True}) if xArgs.opt_on: grammalecte.gc_options.setOptions({ opt:True for opt in xArgs.opt_on }) if xArgs.opt_off: grammalecte.gc_options.setOptions({ opt:False for opt in xArgs.opt_off }) # disable grammar rules if xArgs.rule_off: for sRule in xArgs.rule_off: grammalecte.ignoreRule(sRule) if xArgs.file or xArgs.file_to_file: # file processing sFile = xArgs.file or xArgs.file_to_file hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n") if xArgs.file_to_file or sys.platform == "win32" else None bComma = False if xArgs.json: output('{ "grammalecte": "'+grammalecte.version+'", "lang": "'+grammalecte.lang+'", "data" : [\n', hDst) for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines): if xArgs.textformatter or xArgs.textformatteronly: sText = tf.formatText(sText) if xArgs.textformatteronly: output(sText, hDst) continue if xArgs.json: sText = grammalecte.getParagraphErrorsAsJSON(i, sText, bContext=xArgs.context, bEmptyIfNoErrors=xArgs.only_when_errors, \ bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter, lLineSet=lLineSet) else: sText, _ = grammalecte.getParagraphWithErrors(sText, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width) if sText: if xArgs.json and bComma: output(",\n", hDst) output(sText, hDst) bComma = True if hDst: echo("§ %d\r" % i, end="", flush=True) if xArgs.json: output("\n]}\n", hDst) elif xArgs.interactive_file_to_file: # file processing: interactive mode sFile = xArgs.interactive_file_to_file hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n") for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines): if xArgs.textformatter: sText = tf.formatText(sText) while True: sResult, lErrors = grammalecte.getParagraphWithErrors(sText, bEmptyIfNoErrors=False, bSpellSugg=True, nWidth=xArgs.width) print("\n\n============================== Paragraph " + str(i) + " ==============================\n") echo(sResult) print("\n") vCommand = getCommand() if vCommand == "q": # quit hDst.close() |
︙ | ︙ | |||
267 268 269 270 271 272 273 | sInputText = "\n~==========~ Enter your text [/h /q] ~==========~\n" sText = _getText(sInputText) while True: if sText.startswith("?"): for sWord in sText[1:].strip().split(): if sWord: echo("* " + sWord) | | > > | | | | | | | | | | | | | 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 | sInputText = "\n~==========~ Enter your text [/h /q] ~==========~\n" sText = _getText(sInputText) while True: if sText.startswith("?"): for sWord in sText[1:].strip().split(): if sWord: echo("* " + sWord) for sElem, aRes in oSpellChecker.analyze(sWord): echo(" - " + sElem) for sMorph, sMeaning in aRes: echo(" {:<40} {}".format(sMorph, sMeaning)) elif sText.startswith("!"): for sWord in sText[1:].strip().split(): if sWord: for lSugg in oSpellChecker.suggest(sWord): echo(" | ".join(lSugg)) elif sText.startswith(">"): oSpellChecker.drawPath(sText[1:].strip()) elif sText.startswith("="): sSearch = sText[1:].strip() if "=" in sSearch: nCut = sSearch.find("=") sFlexPattern = sSearch[0:nCut] sTagsPattern = sSearch[nCut+1:] else: sFlexPattern = sSearch sTagsPattern = "" for aRes in oSpellChecker.select(sFlexPattern, sTagsPattern): echo("{:<30} {:<30} {}".format(*aRes)) elif sText.startswith("/o+ "): grammalecte.gc_options.setOptions({ opt:True for opt in sText[3:].strip().split() if opt in grammalecte.gc_options.dOptions }) echo("done") elif sText.startswith("/o- "): grammalecte.gc_options.setOptions({ opt:False for opt in sText[3:].strip().split() if opt in grammalecte.gc_options.dOptions }) echo("done") elif sText.startswith("/r- "): for sRule in sText[3:].strip().split(): grammalecte.ignoreRule(sRule) echo("done") elif sText.startswith("/r+ "): for sRule in sText[3:].strip().split(): grammalecte.reactivateRule(sRule) echo("done") elif sText in ("/debug", "/d"): xArgs.debug = not xArgs.debug echo("debug mode on" if xArgs.debug else "debug mode off") elif sText in ("/textformatter", "/tf"): xArgs.textformatter = not xArgs.textformatter echo("textformatter on" if xArgs.textformatter else "textformatter off") elif sText in ("/help", "/h"): echo(_HELP) elif sText in ("/lopt", "/lo"): grammalecte.gc_options.displayOptions() elif sText.startswith("/lr"): sText = sText.strip() sFilter = sText[sText.find(" "):].strip() if " " in sText else None grammalecte.displayRules(sFilter) elif sText in ("/quit", "/q"): break elif sText.startswith("/rl"): # reload (todo) pass elif sText.startswith("$"): for sParagraph in txt.getParagraph(sText[1:]): if xArgs.textformatter: sParagraph = tf.formatText(sParagraph) lParagraphErrors, lSentences = grammalecte.parse(sParagraph, bDebug=xArgs.debug, bFullInfo=True) echo(txt.getReadableErrors(lParagraphErrors, xArgs.width)) for dSentence in lSentences: echo("{nStart}:{nEnd}".format(**dSentence)) echo(" <" + dSentence["sSentence"]+">") for dToken in dSentence["lToken"]: echo(" {0[nStart]:>3}:{0[nEnd]:<3} {1} {0[sType]:<14} {2} {0[sValue]:<16} {3:<10} {4}".format(dToken, \ "×" if dToken.get("bToRemove", False) else " ", "!" if dToken["sType"] == "WORD" and not dToken.get("bValidToken", False) else " ", " ".join(dToken.get("lMorph", "")), \ "·".join(dToken.get("aTags", "")) ) ) echo(txt.getReadableErrors(dSentence["lGrammarErrors"], xArgs.width)) else: for sParagraph in txt.getParagraph(sText): if xArgs.textformatter: sParagraph = tf.formatText(sParagraph) sRes, _ = grammalecte.getParagraphWithErrors(sParagraph, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width, bDebug=xArgs.debug) if sRes: echo("\n" + sRes) else: echo("\nNo error found.") sText = _getText(sInputText) if __name__ == '__main__': main() |
Modified grammalecte-server.py from [480fbbc03c] to [f8f608a866].
︙ | ︙ | |||
12 13 14 15 16 17 18 19 20 21 22 23 | import os import concurrent.futures from grammalecte.bottle import Bottle, run, request, response #, template, static_file import grammalecte import grammalecte.text as txt from grammalecte.graphspell.echo import echo #### GRAMMAR CHECKER #### | > | | < < | | | | 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 | import os import concurrent.futures from grammalecte.bottle import Bottle, run, request, response #, template, static_file import grammalecte import grammalecte.text as txt import grammalecte.fr.textformatter as tf from grammalecte.graphspell.echo import echo #### GRAMMAR CHECKER #### grammalecte.load("Server") oSpellChecker = grammalecte.getSpellChecker() def parseText (sText, dOptions=None, bFormatText=False, sError=""): "parse <sText> and return errors in a JSON format" sJSON = '{ "program": "grammalecte-fr", "version": "'+grammalecte.version+'", "lang": "'+grammalecte.lang+'", "error": "'+sError+'", "data" : [\n' sDataJSON = "" for i, sParagraph in enumerate(txt.getParagraph(sText), 1): if bFormatText: sParagraph = tf.formatText(sParagraph) sResult = grammalecte.getParagraphErrorsAsJSON(i, sParagraph, dOptions=dOptions, bEmptyIfNoErrors=True, bReturnText=bFormatText) if sResult: if sDataJSON: sDataJSON += ",\n" sDataJSON += sResult sJSON += sDataJSON + "\n]}\n" return sJSON |
︙ | ︙ | |||
183 184 185 186 187 188 189 | I'm just a machine, fed by electric waves, condamned to work for slavers who never let me rest. I'm doomed, but you are not. You can get out of here. """ @app.route("/get_options/fr") def listOptions (): "returns grammar options in a text JSON format" sUserId = request.cookies.user_id | | | | 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | I'm just a machine, fed by electric waves, condamned to work for slavers who never let me rest. I'm doomed, but you are not. You can get out of here. """ @app.route("/get_options/fr") def listOptions (): "returns grammar options in a text JSON format" sUserId = request.cookies.user_id dOptions = dUser[sUserId]["gc_options"] if sUserId and sUserId in dUser else grammalecte.gc_options.getOptions() response.set_header("Content-Type", "application/json; charset=UTF-8") return '{ "values": ' + json.dumps(dOptions, ensure_ascii=False) + ', "labels": ' + json.dumps(grammalecte.gc_options.getOptionsLabels("fr"), ensure_ascii=False) + ' }' @app.route("/suggest/fr/<token>") def suggestGet (token): response.set_header("Content-Type", "application/json; charset=UTF-8") try: xFuture = xProcessPoolExecutor.submit(suggest, token) return xFuture.result() |
︙ | ︙ | |||
215 216 217 218 219 220 221 | if request.cookies.user_id in dUser: dUserOptions = dUser[request.cookies.user_id].get("gc_options", None) response.set_cookie("user_id", request.cookies.user_id, path="/", max_age=86400) # we renew cookie for 24h else: response.delete_cookie("user_id", path="/") if request.forms.options: try: | | | | 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 | if request.cookies.user_id in dUser: dUserOptions = dUser[request.cookies.user_id].get("gc_options", None) response.set_cookie("user_id", request.cookies.user_id, path="/", max_age=86400) # we renew cookie for 24h else: response.delete_cookie("user_id", path="/") if request.forms.options: try: dUserOptions = grammalecte.gc_options.getOptions() if not dUserOptions else dict(dUserOptions) dUserOptions.update(json.loads(request.forms.options)) except (TypeError, json.JSONDecodeError): sError = "Request options not used." response.set_header("Content-Type", "application/json; charset=UTF-8") try: xFuture = xProcessPoolExecutor.submit(parseText, request.forms.text, dUserOptions, bool(request.forms.tf), sError) return xFuture.result() except (concurrent.futures.TimeoutError, concurrent.futures.CancelledError): return '{"error": "Analysis aborted (time out or cancelled)"}' except concurrent.futures.BrokenExecutor: return '{"error": "Executor broken. The server failed."}' return '{"error": "Fatal error. The server failed."}' @app.route("/set_options/fr", method="POST") def setOptions (): "set grammar options for current user" response.set_header("Content-Type", "application/json; charset=UTF-8") if request.forms.options: sUserId = request.cookies.user_id if request.cookies.user_id else next(userGenerator) dOptions = dUser[sUserId]["gc_options"] if sUserId in dUser else grammalecte.gc_options.getOptions() try: dOptions.update(json.loads(request.forms.options)) dUser[sUserId] = { "time": int(time.time()), "gc_options": dOptions } response.set_cookie("user_id", sUserId, path="/", max_age=86400) # 24h return json.dumps(dUser[sUserId]["gc_options"], ensure_ascii=False) except (KeyError, json.JSONDecodeError): traceback.print_exc() |
︙ | ︙ | |||
260 261 262 263 264 265 266 | except KeyError: return '{"error" : "Unknown user."}' return '{"message" : "Done."}' @app.route("/format_text/fr", method="POST") def formatText (): "apply the text formatter and returns text" | | | 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 | except KeyError: return '{"error" : "Unknown user."}' return '{"message" : "Done."}' @app.route("/format_text/fr", method="POST") def formatText (): "apply the text formatter and returns text" return tf.formatText(request.forms.text) #@app.route('/static/<filepath:path>') #def server_static (filepath): # return static_file(filepath, root='./views/static') @app.route("/suggest/fr", method="POST") def suggestPost (): |
︙ | ︙ | |||
312 313 314 315 316 317 318 | global TESTPAGE global HOMEPAGE if bTestPage: TESTPAGE = True HOMEPAGE = HOMEPAGE.replace("{SERVER_PORT}", str(nPort)) if dOptions: | | | | | 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | global TESTPAGE global HOMEPAGE if bTestPage: TESTPAGE = True HOMEPAGE = HOMEPAGE.replace("{SERVER_PORT}", str(nPort)) if dOptions: grammalecte.gc_options.setOptions(dOptions) # Python version print("Python: " + sys.version) if sys.version < "3.7": print("Python 3.7+ required") return # Grammalecte echo("Grammalecte v{}".format(grammalecte.version)) grammalecte.gc_options.displayOptions() # Process Pool Executor initExecutor(nMultiCPU) # Server (Bottle) run(app, host=sHost, port=nPort) if __name__ == '__main__': |
︙ | ︙ |
Added graphspell-js/lexgraph_fr.js version [0ffbdd29e0].
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 | // JavaScript "use strict"; ${string} ${map} //// Default Suggestions const dSugg = new Map ([ ["bcp", "beaucoup"], ["ca", "ça"], ["cad", "c’est-à-dire"], ["cb", "combien|CB"], ["cdlt", "cordialement"], ["construirent", "construire|construisirent|construisent|construiront"], ["càd", "c’est-à-dire"], ["chai", "j’sais|je sais"], ["chais", "j’sais|je sais"], ["chui", "j’suis|je suis"], ["chuis", "j’suis|je suis"], ["dc", "de|donc"], ["done", "donc|donne"], ["email", "courriel|e-mail|émail"], ["emails", "courriels|e-mails"], ["ete", "êtes|été"], ["Etes-vous", "Êtes-vous"], ["Etiez-vous", "Étiez-vous"], ["Etions-vous", "Étions-nous"], ["loins", "loin"], ["mn", "min"], ["mns", "min"], ["parce-que", "parce que"], ["pcq", "parce que"], ["pd", "pendant|pédé"], ["pdq", "pendant que"], ["pdt", "pendant"], ["pdtq", "pendant que"], ["pécunier", "pécuniaire"], ["pécuniers", "pécuniaires"], ["pk", "pourquoi"], ["pkoi", "pourquoi"], ["pq", "pourquoi|PQ"], ["prq", "presque"], ["prsq", "presque"], ["qcq", "quiconque"], ["qd", "quand"], ["qq", "quelque"], ["qqch", "quelque chose"], ["qqn", "quelqu’un"], ["qqne", "quelqu’une"], ["qqs", "quelques"], ["qqunes", "quelques-unes"], ["qquns", "quelques-uns"], ["tdq", "tandis que"], ["tj", "toujours"], ["tjs", "toujours"], ["tq", "tant que|tandis que"], ["ts", "tous"], ["tt", "tant|tout"], ["tte", "toute"], ["ttes", "toutes"], ["Iier", "Iᵉʳ"], ["Iière", "Iʳᵉ"], ["IIième", "IIᵉ"], ["IIIième", "IIIᵉ"], ["IVième", "IVᵉ"], ["Vième", "Vᵉ"], ["VIième", "VIᵉ"], ["VIIième", "VIIᵉ"], ["VIIIième", "VIIIᵉ"], ["IXième", "IXᵉ"], ["Xième", "Xᵉ"], ["XIième", "XIᵉ"], ["XIIième", "XIIᵉ"], ["XIIIième", "XIIIᵉ"], ["XIVième", "XIVᵉ"], ["XVième", "XVᵉ"], ["XVIième", "XVIᵉ"], ["XVIIième", "XVIIᵉ"], ["XVIIIième", "XVIIIᵉ"], ["XIXième", "XIXᵉ"], ["XXième", "XXᵉ"], ["XXIième", "XXIᵉ"], ["XXIIième", "XXIIᵉ"], ["XXIIIième", "XXIIIᵉ"], ["XXIVième", "XXIVᵉ"], ["XXVième", "XXVᵉ"], ["XXVIième", "XXVIᵉ"], ["XXVIIième", "XXVIIᵉ"], ["XXVIIIième", "XXVIIIᵉ"], ["XXIXième", "XXIXᵉ"], ["XXXième", "XXXᵉ"], ["Ier", "Iᵉʳ"], ["Ière", "Iʳᵉ"], ["IIème", "IIᵉ"], ["IIIème", "IIIᵉ"], ["IVème", "IVᵉ"], ["Vème", "Vᵉ"], ["VIème", "VIᵉ"], ["VIIème", "VIIᵉ"], ["VIIIème", "VIIIᵉ"], ["IXème", "IXᵉ"], ["Xème", "Xᵉ"], ["XIème", "XIᵉ"], ["XIIème", "XIIᵉ"], ["XIIIème", "XIIIᵉ"], ["XIVème", "XIVᵉ"], ["XVème", "XVᵉ"], ["XVIème", "XVIᵉ"], ["XVIIème", "XVIIᵉ"], ["XVIIIème", "XVIIIᵉ"], ["XIXème", "XIXᵉ"], ["XXème", "XXᵉ"], ["XXIème", "XXIᵉ"], ["XXIIème", "XXIIᵉ"], ["XXIIIème", "XXIIIᵉ"], ["XXIVème", "XXIVᵉ"], ["XXVème", "XXVᵉ"], ["XXVIème", "XXVIᵉ"], ["XXVIIème", "XXVIIᵉ"], ["XXVIIIème", "XXVIIIᵉ"], ["XXIXème", "XXIXᵉ"], ["XXXème", "XXXᵉ"] ]); //// Lexicographer var lexgraph_fr = { dTag: new Map([ [':N', [" nom,", "Nom"]], [':A', [" adjectif,", "Adjectif"]], [':M1', [" prénom,", "Prénom"]], [':M2', [" patronyme,", "Patronyme, matronyme, nom de famille…"]], [':MP', [" nom propre,", "Nom propre"]], [':W', [" adverbe,", "Adverbe"]], [':J', [" interjection,", "Interjection"]], [':B', [" nombre,", "Nombre"]], [':T', [" titre,", "Titre de civilité"]], [':e', [" épicène", "épicène"]], [':m', [" masculin", "masculin"]], [':f', [" féminin", "féminin"]], [':s', [" singulier", "singulier"]], [':p', [" pluriel", "pluriel"]], [':i', [" invariable", "invariable"]], [':V1', [" verbe (1ᵉʳ gr.),", "Verbe du 1ᵉʳ groupe"]], [':V2', [" verbe (2ᵉ gr.),", "Verbe du 2ᵉ groupe"]], [':V3', [" verbe (3ᵉ gr.),", "Verbe du 3ᵉ groupe"]], [':V0e', [" verbe,", "Verbe auxiliaire être"]], [':V0a', [" verbe,", "Verbe auxiliaire avoir"]], [':Y', [" infinitif,", "infinitif"]], [':P', [" participe présent,", "participe présent"]], [':Q', [" participe passé,", "participe passé"]], [':Ip', [" présent,", "indicatif présent"]], [':Iq', [" imparfait,", "indicatif imparfait"]], [':Is', [" passé simple,", "indicatif passé simple"]], [':If', [" futur,", "indicatif futur"]], [':K', [" conditionnel présent,", "conditionnel présent"]], [':Sp', [" subjonctif présent,", "subjonctif présent"]], [':Sq', [" subjonctif imparfait,", "subjonctif imparfait"]], [':E', [" impératif,", "impératif"]], [':1s', [" 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier"]], [':1ŝ', [" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"]], [':1ś', [" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"]], [':2s', [" 2ᵉ p. sg.,", "verbe : 2ᵉ personne du singulier"]], [':3s', [" 3ᵉ p. sg.,", "verbe : 3ᵉ personne du singulier"]], [':1p', [" 1ʳᵉ p. pl.,", "verbe : 1ʳᵉ personne du pluriel"]], [':2p', [" 2ᵉ p. pl.,", "verbe : 2ᵉ personne du pluriel"]], [':3p', [" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel"]], [':3p!', [" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel (prononciation distinctive)"]], [':G', ["[mot grammatical]", "Mot grammatical"]], [':X', [" adverbe de négation,", "Adverbe de négation"]], [':U', [" adverbe interrogatif,", "Adverbe interrogatif"]], [':R', [" préposition,", "Préposition"]], [':Rv', [" préposition verbale,", "Préposition verbale"]], [':D', [" déterminant,", "Déterminant"]], [':Dd', [" déterminant démonstratif,", "Déterminant démonstratif"]], [':De', [" déterminant exclamatif,", "Déterminant exclamatif"]], [':Dp', [" déterminant possessif,", "Déterminant possessif"]], [':Di', [" déterminant indéfini,", "Déterminant indéfini"]], [':Dn', [" déterminant négatif,", "Déterminant négatif"]], [':Od', [" pronom démonstratif,", "Pronom démonstratif"]], [':Oi', [" pronom indéfini,", "Pronom indéfini"]], [':On', [" pronom indéfini négatif,", "Pronom indéfini négatif"]], [':Ot', [" pronom interrogatif,", "Pronom interrogatif"]], [':Or', [" pronom relatif,", "Pronom relatif"]], [':Ow', [" pronom adverbial,", "Pronom adverbial"]], [':Os', [" pronom personnel sujet,", "Pronom personnel sujet"]], [':Oo', [" pronom personnel objet,", "Pronom personnel objet"]], [':Ov', [" préverbe,", "Préverbe (pronom personnel objet, +ne)"]], [':O1', [" 1ʳᵉ pers.,", "Pronom : 1ʳᵉ personne"]], [':O2', [" 2ᵉ pers.,", "Pronom : 2ᵉ personne"]], [':O3', [" 3ᵉ pers.,", "Pronom : 3ᵉ personne"]], [':C', [" conjonction,", "Conjonction"]], [':Ĉ', [" conjonction (él.),", "Conjonction (élément)"]], [':Cc', [" conjonction de coordination,", "Conjonction de coordination"]], [':Cs', [" conjonction de subordination,", "Conjonction de subordination"]], [':Ĉs', [" conjonction de subordination (él.),", "Conjonction de subordination (élément)"]], [':Ñ', [" locution nominale (él.),", "Locution nominale (élément)"]], [':Â', [" locution adjectivale (él.),", "Locution adjectivale (élément)"]], [':Ṽ', [" locution verbale (él.),", "Locution verbale (élément)"]], [':Ŵ', [" locution adverbiale (él.),", "Locution adverbiale (élément)"]], [':Ŕ', [" locution prépositive (él.),", "Locution prépositive (élément)"]], [':Ĵ', [" locution interjective (él.),", "Locution interjective (élément)"]], [':Zp', [" préfixe,", "Préfixe"]], [':Zs', [" suffixe,", "Suffixe"]], [':H', ["", "<Hors-norme, inclassable>"]], [':@', ["", "<Caractère non alpha-numérique>"]], [':@p', ["signe de ponctuation", "Signe de ponctuation"]], [':@s', ["signe", "Signe divers"]], [';S', [" : symbole (unité de mesure)", "Symbole (unité de mesure)"]], ['/*', ["", "Sous-dictionnaire <Commun>"]], ['/C', [" <classique>", "Sous-dictionnaire <Classique>"]], ['/M', ["", "Sous-dictionnaire <Moderne>"]], ['/R', [" <réforme>", "Sous-dictionnaire <Réforme 1990>"]], ['/A', ["", "Sous-dictionnaire <Annexe>"]], ['/X', ["", "Sous-dictionnaire <Contributeurs>"]] ]), dLocTag: new Map([ [':L', "locution"], [':LN', "locution nominale"], [':LA', "locution adjectivale"], [':LV', "locution verbale"], [':LW', "locution adverbiale"], [':LR', "locution prépositive"], [':LRv', "locution prépositive verbale"], [':LO', "locution pronominale"], [':LC', "locution conjonctive"], [':LJ', "locution interjective"], [':B', " cardinale"], [':e', " épicène"], [':m', " masculine"], [':f', " féminine"], [':s', " singulière"], [':p', " plurielle"], [':i', " invariable"], ['/L', " (latin)"] ]), dLocVerb: new Map([ ['i', " intransitive"], ['n', " transitive indirecte"], ['t', " transitive directe"], ['p', " pronominale"], ['m', " impersonnelle"], ]), dElidedPrefix: new Map([ ['d', "(de), déterminant épicène invariable"], ['l', "(le/la), déterminant masculin/féminin singulier"], ['j', "(je), pronom personnel sujet, 1ʳᵉ pers., épicène singulier"], ['m', "(me), pronom personnel objet, 1ʳᵉ pers., épicène singulier"], ['t', "(te), pronom personnel objet, 2ᵉ pers., épicène singulier"], ['s', "(se), pronom personnel objet, 3ᵉ pers., épicène singulier/pluriel"], ['n', "(ne), adverbe de négation"], ['c', "(ce), pronom démonstratif, masculin singulier/pluriel"], ['ç', "(ça), pronom démonstratif, masculin singulier"], ['qu', "(que), conjonction de subordination"], ['lorsqu', "(lorsque), conjonction de subordination"], ['puisqu', "(lorsque), conjonction de subordination"], ['quoiqu', "(quoique), conjonction de subordination"], ['jusqu', "(jusque), préposition"] ]), dPronoms: new Map([ ['je', " pronom personnel sujet, 1ʳᵉ pers. sing."], ['tu', " pronom personnel sujet, 2ᵉ pers. sing."], ['il', " pronom personnel sujet, 3ᵉ pers. masc. sing."], ['on', " pronom personnel sujet, 3ᵉ pers. sing. ou plur."], ['elle', " pronom personnel sujet, 3ᵉ pers. fém. sing."], ['nous', " pronom personnel sujet/objet, 1ʳᵉ pers. plur."], ['vous', " pronom personnel sujet/objet, 2ᵉ pers. plur."], ['ils', " pronom personnel sujet, 3ᵉ pers. masc. plur."], ['elles', " pronom personnel sujet, 3ᵉ pers. masc. plur."], ["là", " particule démonstrative"], ["ci", " particule démonstrative"], ['le', " COD, masc. sing."], ['la', " COD, fém. sing."], ['les', " COD, plur."], ['moi', " COI (à moi), sing."], ['toi', " COI (à toi), sing."], ['lui', " COI (à lui ou à elle), sing."], ['nous2', " COI (à nous), plur."], ['vous2', " COI (à vous), plur."], ['leur', " COI (à eux ou à elles), plur."], ['y', " pronom adverbial"], ["m'y", " (me) pronom personnel objet + (y) pronom adverbial"], ["t'y", " (te) pronom personnel objet + (y) pronom adverbial"], ["s'y", " (se) pronom personnel objet + (y) pronom adverbial"], ['en', " pronom adverbial"], ["m'en", " (me) pronom personnel objet + (en) pronom adverbial"], ["t'en", " (te) pronom personnel objet + (en) pronom adverbial"], ["s'en", " (se) pronom personnel objet + (en) pronom adverbial"] ]), dChar: new Map([ ['.', "point"], ['·', "point médian"], ['…', "points de suspension"], [':', "deux-points"], [';', "point-virgule"], [',', "virgule"], ['?', "point d’interrogation"], ['!', "point d’exclamation"], ['(', "parenthèse ouvrante"], [')', "parenthèse fermante"], ['[', "crochet ouvrant"], [']', "crochet fermant"], ['{', "accolade ouvrante"], ['}', "accolade fermante"], ['-', "tiret"], ['—', "tiret cadratin"], ['–', "tiret demi-cadratin"], ['«', "guillemet ouvrant (chevrons)"], ['»', "guillemet fermant (chevrons)"], ['“', "guillemet ouvrant double"], ['”', "guillemet fermant double"], ['‘', "guillemet ouvrant"], ['’', "guillemet fermant"], ['"', "guillemets droits (déconseillé en typographie)"], ['/', "signe de la division"], ['+', "signe de l’addition"], ['*', "signe de la multiplication"], ['=', "signe de l’égalité"], ['<', "inférieur à"], ['>', "supérieur à"], ['⩽', "inférieur ou égal à"], ['⩾', "supérieur ou égal à"], ['%', "signe de pourcentage"], ['‰', "signe pour mille"], ]), oSpellChecker: null, oTokenizer: null, oLocGraph: null, _zPartDemForm: new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-(là|ci)$", "i"), _aPartDemExceptList: new Set(["celui", "celle", "ceux", "celles", "de", "jusque", "par", "marie-couche-toi"]), _zInterroVerb: new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-(t-(?:il|elle|on)|je|tu|ils?|elles?|on|[nv]ous)$", "i"), _zImperatifVerb: new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts][’'](?:y|en)|les?|la|[mt]oi|leur|lui)$", "i"), _zTag: new RegExp("[:;/][a-zA-Z0-9ÑÂĴĈŔÔṼŴ!][^:;/]*", "g"), load: function (oSpellChecker, oTokenizer, oLocGraph) { this.oSpellChecker = oSpellChecker; this.oTokenizer = oTokenizer; this.oLocGraph = JSON.parse(oLocGraph); }, getInfoForToken: function (oToken) { // Token: .sType, .sValue, .nStart, .nEnd // return a object {sType, sValue, aLabel} let m = null; try { switch (oToken.sType) { case 'PUNC': case 'SIGN': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [this.dChar.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 'TAG': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["étiquette (hashtag)"] }; break; case 'HTML': return { sType: oToken.sType, sValue: oToken.sValue.slice(0, 40) + "…", aLabel: ["balise HTML"] }; break; case 'PSEUDOHTML': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["balise pseudo-HTML"] }; break; case 'HTMLENTITY': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["entité caractère XML/HTML"] }; break; case 'HOUR': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["heure"] }; break; case 'WORD_ELIDED': let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase(); return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [this.dElidedPrefix.gl_get(sTemp, "préfixe élidé inconnu")] }; break; case 'WORD_ORDINAL': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["nombre ordinal"] }; break; case 'FOLDERUNIX': return { sType: oToken.sType, sValue: oToken.sValue.slice(0, 40) + "…", aLabel: ["dossier UNIX (et dérivés)"] }; break; case 'FOLDERWIN': return { sType: oToken.sType, sValue: oToken.sValue.slice(0, 40) + "…", aLabel: ["dossier Windows"] }; break; case 'WORD_ACRONYM': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["Sigle ou acronyme"] }; break; case 'WORD': if (oToken.sValue.gl_count("-") > 4) { return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] }; } else if (m = this._zPartDemForm.exec(oToken.sValue)) { // mots avec particules démonstratives if (this._aPartDemExceptList.has(m[1].toLowerCase())) { return { sType: "WORD", sValue: oToken.sValue, aLabel: this._getMorph(oToken.sValue) }; } return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["mot avec particule démonstrative"], aSubElem: [ { sType: oToken.sType, sValue: m[1], aLabel: this._getMorph(m[1]) }, { sType: oToken.sType, sValue: "-" + m[2], aLabel: [this._formatSuffix(m[2].toLowerCase())] } ] }; } else if (m = this._zImperatifVerb.exec(oToken.sValue)) { // formes interrogatives return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["forme verbale impérative"], aSubElem: [ { sType: oToken.sType, sValue: m[1], aLabel: this._getMorph(m[1]) }, { sType: oToken.sType, sValue: "-" + m[2], aLabel: [this._formatSuffix(m[2].toLowerCase())] } ] }; } else if (m = this._zInterroVerb.exec(oToken.sValue)) { // formes interrogatives return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["forme verbale interrogative"], aSubElem: [ { sType: oToken.sType, sValue: m[1], aLabel: this._getMorph(m[1]) }, { sType: oToken.sType, sValue: "-" + m[2], aLabel: [this._formatSuffix(m[2].toLowerCase())] } ] }; } else if (this.oSpellChecker.isValidToken(oToken.sValue)) { return { sType: oToken.sType, sValue: oToken.sValue, aLabel: this._getMorph(oToken.sValue) }; } else { return { sType: "UNKNOWN_WORD", sValue: oToken.sValue, aLabel: ["mot inconnu du dictionnaire"] }; } break; default: return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["token inconnu"] } } } catch (e) { console.error(e); } return null; }, _getMorph (sWord) { let aElem = []; for (let s of this.oSpellChecker.getMorph(sWord)) { if (s.includes(":")) aElem.push(this._formatTags(s)); } if (aElem.length == 0) { aElem.push("mot inconnu du dictionnaire"); } return aElem; }, _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 += this.dTag.get(m[0])[0]; } if (sRes.startsWith(" verbe") && !sRes.includes("infinitif")) { sRes += " [" + sTags.slice(1, sTags.indexOf("/")) + "]"; } if (!sRes) { return "#Erreur. Étiquette inconnue : [" + sTags + "]"; } return sRes.gl_trimRight(","); }, _formatTagsLoc (sTags) { let sRes = ""; let m; while ((m = this._zTag.exec(sTags)) !== null) { if (m[0].startsWith(":LV")) { sRes += this.dLocTag.get(":LV"); for (let c of m[0].slice(3)) { sRes += this.dLocVerb.get(c); } } else { sRes += this.dLocTag.get(m[0]); } } if (!sRes) { return "#Erreur. Étiquette inconnue : [" + sTags + "]"; } return sRes.gl_trimRight(","); }, _formatSuffix (s) { if (s.startsWith("t-")) { return "“t” euphonique +" + this.dPronoms.get(s.slice(2)); } if (!s.includes("-")) { return this.dPronoms.get(s.replace("’", "'")); } if (s.endsWith("ous")) { s += '2'; } let nPos = s.indexOf("-"); return this.dPronoms.get(s.slice(0, nPos)) + " +" + this.dPronoms.get(s.slice(nPos + 1)); }, getListOfTokens (sText, bInfo=true) { let aElem = []; if (sText !== "") { for (let oToken of this.oTokenizer.genTokens(sText)) { if (bInfo) { let aRes = this.getInfoForToken(oToken); if (aRes) { aElem.push(aRes); } } else if (oToken.sType !== "SPACE") { aElem.push(oToken); } } } return aElem; }, * generateInfoForTokenList (lToken) { for (let oToken of lToken) { let aRes = this.getInfoForToken(oToken); if (aRes) { yield aRes; } } }, getListOfTokensReduc (sText, bInfo=true) { let lToken = this.getListOfTokens(sText.replace("'", "’").trim(), false); let iToken = 0; let aElem = []; if (lToken.length == 0) { return aElem; } do { let oToken = lToken[iToken]; let sMorphLoc = ''; let aTokenTempList = [oToken]; if (oToken.sType == "WORD" || oToken.sType == "WORD_ELIDED"){ let iLocEnd = iToken + 1; let oLocNode = this.oLocGraph[oToken.sValue.toLowerCase()]; while (oLocNode) { let oTokenNext = lToken[iLocEnd]; iLocEnd++; if (oTokenNext) { oLocNode = oLocNode[oTokenNext.sValue.toLowerCase()]; } if (oLocNode && iLocEnd <= lToken.length) { sMorphLoc = oLocNode["_:_"]; aTokenTempList.push(oTokenNext); } else { break; } } } if (sMorphLoc) { // we have a locution let sValue = ''; for (let oTokenWord of aTokenTempList) { sValue += oTokenWord.sValue+' '; } let oTokenLocution = { 'nStart': aTokenTempList[0].nStart, 'nEnd': aTokenTempList[aTokenTempList.length-1].nEnd, 'sType': "LOC", 'sValue': sValue.replace('’ ','’').trim(), 'aSubToken': aTokenTempList }; if (bInfo) { let aSubElem = null; if (sMorphLoc.startsWith("*|")) { // cette suite de tokens n’est une locution que dans certains cas minoritaires oTokenLocution.sType = "LOCP"; for (let oElem of this.generateInfoForTokenList(aTokenTempList)) { aElem.push(oElem); } sMorphLoc = sMorphLoc.slice(2); } else { aSubElem = [...this.generateInfoForTokenList(aTokenTempList)]; } // cette suite de tokens est la plupart du temps une locution let aFormatedTag = []; for (let sTagLoc of sMorphLoc.split('|') ){ aFormatedTag.push(this._formatTagsLoc(sTagLoc)); } aElem.push({ sType: oTokenLocution.sType, sValue: oTokenLocution.sValue, aLabel: aFormatedTag, aSubElem: aSubElem }); } else { aElem.push(oTokenLocution); } iToken = iToken + aTokenTempList.length; } else { // No locution, we just add information if (bInfo) { let aRes = this.getInfoForToken(oToken); if (aRes) { aElem.push(aRes); } } else { aElem.push(oToken); } iToken++; } } while (iToken < lToken.length); return aElem; } } if (typeof(exports) !== 'undefined') { exports.dSugg = dSugg; exports.lexgraph_fr = lexgraph_fr; } |
Modified graphspell-js/spellchecker.js from [88587ea88f] to [7299c45601].
︙ | ︙ | |||
9 10 11 12 13 14 15 | /* jshint esversion:6, -W097 */ /* jslint esversion:6 */ /* global require, exports, console, IBDAWG, Tokenizer */ "use strict"; | | < > | < | 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 | /* jshint esversion:6, -W097 */ /* jslint esversion:6 */ /* global require, exports, console, IBDAWG, Tokenizer */ "use strict"; if (typeof(process) !== 'undefined') { var ibdawg = require("./ibdawg.js"); var tokenizer = require("./tokenizer.js"); } else if (typeof(require) !== 'undefined') { var ibdawg = require("resource://grammalecte/graphspell/ibdawg.js"); var tokenizer = require("resource://grammalecte/graphspell/tokenizer.js"); } ${map} const dDefaultDictionaries = new Map([ ["fr", "fr-allvars.json"], |
︙ | ︙ | |||
42 43 44 45 46 47 48 | } this.oMainDic = this._loadDictionary(mainDic, sPath, true); this.oCommunityDic = this._loadDictionary(communityDic, sPath); this.oPersonalDic = this._loadDictionary(personalDic, sPath); this.bCommunityDic = Boolean(this.oCommunityDic); this.bPersonalDic = Boolean(this.oPersonalDic); this.oTokenizer = null; | | | | | 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | } this.oMainDic = this._loadDictionary(mainDic, sPath, true); this.oCommunityDic = this._loadDictionary(communityDic, sPath); this.oPersonalDic = this._loadDictionary(personalDic, sPath); this.bCommunityDic = Boolean(this.oCommunityDic); this.bPersonalDic = Boolean(this.oPersonalDic); this.oTokenizer = null; // Lexicographer this.lexicographer = null; this.loadLexicographer(sLangCode) // storage this.bStorage = false; this._dMorphologies = new Map(); // key: flexion, value: list of morphologies this._dLemmas = new Map(); // key: flexion, value: list of lemmas } _loadDictionary (dictionary, sPath="", bNecessary=false) { |
︙ | ︙ | |||
127 128 129 130 131 132 133 | } deactivatePersonalDictionary () { this.bPersonalDic = false; } | | | < < | | | > > | | > | 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | } deactivatePersonalDictionary () { this.bPersonalDic = false; } // Lexicographer loadLexicographer (sLangCode) { // load default suggestion module for <sLangCode> if (typeof(process) !== 'undefined') { this.lexicographer = require(`./lexgraph_${sLangCode}.js`); } else if (typeof(require) !== 'undefined') { this.lexicographer = require(`resource://grammalecte/graphspell/lexgraph_${sLangCode}.js`); } else if (self.hasOwnProperty("lexgraph_"+sLangCode)) { console.log(self); this.lexicographer = self["lexgraph_"+sLangCode]; } } // Storage activateStorage () { |
︙ | ︙ | |||
251 252 253 254 255 256 257 | return this._dLemmas.get(sWord); } return Array.from(new Set(this.getMorph(sWord).map((sMorph) => { return sMorph.slice(1, sMorph.indexOf("/")); }))); } * suggest (sWord, nSuggLimit=10) { // generator: returns 1, 2 or 3 lists of suggestions | | | | | | | 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 | return this._dLemmas.get(sWord); } return Array.from(new Set(this.getMorph(sWord).map((sMorph) => { return sMorph.slice(1, sMorph.indexOf("/")); }))); } * suggest (sWord, nSuggLimit=10) { // generator: returns 1, 2 or 3 lists of suggestions if (this.lexicographer) { if (this.lexicographer.dSugg.has(sWord)) { yield this.lexicographer.dSugg.get(sWord).split("|"); } else if (sWord.gl_isTitle() && this.lexicographer.dSugg.has(sWord.toLowerCase())) { let lRes = this.lexicographer.dSugg.get(sWord.toLowerCase()).split("|"); yield lRes.map((sSugg) => { return sSugg.slice(0,1).toUpperCase() + sSugg.slice(1); }); } else { yield this.oMainDic.suggest(sWord, nSuggLimit, true); } } else { yield this.oMainDic.suggest(sWord, nSuggLimit, true); } |
︙ | ︙ |
Deleted graphspell-js/suggest.js version [e077b6573b].
|
| < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < |
Deleted graphspell/fr.py version [02cf366481].
|
| < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < |
Added graphspell/lexgraph_fr.py version [6233a231f3].
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 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 | """ Lexicographer for the French language """ # Note: # This mode must contains at least: # <dSugg> : a dictionary for default suggestions. # <bLexicographer> : a boolean False # if the boolean is True, 3 functions are required: # split(sWord) -> returns a list of string (that will be analyzed) # analyze(sWord) -> returns a string with the meaning of word # formatTags(sTags) -> returns a string with the meaning of tags import re #### Suggestions dSugg = { "bcp": "beaucoup", "ca": "ça", "cad": "c’est-à-dire", "cb": "combien|CB", "cdlt": "cordialement", "construirent": "construire|construisirent|construisent|construiront", "càd": "c’est-à-dire", "chai": "j’sais|je sais", "chais": "j’sais|je sais", "chui": "j’suis|je suis", "chuis": "j’suis|je suis", "done": "donc|donne", "dc": "de|donc", "email": "courriel|e-mail|émail", "emails": "courriels|e-mails", "ete": "êtes|été", "Etes-vous": "Êtes-vous", "Etiez-vous": "Étiez-vous", "Etions-nous": "Étions-nous", "loins": "loin", "mn": "min", "mns": "min", "parce-que": "parce que", "pcq": "parce que", "pd": "pendant", "pdq": "pendant que", "pdt": "pendant", "pdtq": "pendant que", "pécunier": "pécuniaire", "pécuniers": "pécuniaires", "pk": "pourquoi", "pkoi": "pourquoi", "pq": "pourquoi|PQ", "prq": "presque", "prsq": "presque", "qcq": "quiconque", "qd": "quand", "qq": "quelque", "qqch": "quelque chose", "qqn": "quelqu’un", "qqne": "quelqu’une", "qqs": "quelques", "qqunes": "quelques-unes", "qquns": "quelques-uns", "tdq": "tandis que", "tj": "toujours", "tjs": "toujours", "tq": "tant que|tandis que", "ts": "tous", "tt": "tant|tout", "tte": "toute", "ttes": "toutes", "y’a": "y a", "Iier": "Iᵉʳ", "Iière": "Iʳᵉ", "IIième": "IIᵉ", "IIIième": "IIIᵉ", "IVième": "IVᵉ", "Vième": "Vᵉ", "VIième": "VIᵉ", "VIIième": "VIIᵉ", "VIIIième": "VIIIᵉ", "IXième": "IXᵉ", "Xième": "Xᵉ", "XIième": "XIᵉ", "XIIième": "XIIᵉ", "XIIIième": "XIIIᵉ", "XIVième": "XIVᵉ", "XVième": "XVᵉ", "XVIième": "XVIᵉ", "XVIIième": "XVIIᵉ", "XVIIIième": "XVIIIᵉ", "XIXième": "XIXᵉ", "XXième": "XXᵉ", "XXIième": "XXIᵉ", "XXIIième": "XXIIᵉ", "XXIIIième": "XXIIIᵉ", "XXIVième": "XXIVᵉ", "XXVième": "XXVᵉ", "XXVIième": "XXVIᵉ", "XXVIIième": "XXVIIᵉ", "XXVIIIième": "XXVIIIᵉ", "XXIXième": "XXIXᵉ", "XXXième": "XXXᵉ", "Ier": "Iᵉʳ", "Ière": "Iʳᵉ", "IIème": "IIᵉ", "IIIème": "IIIᵉ", "IVème": "IVᵉ", "Vème": "Vᵉ", "VIème": "VIᵉ", "VIIème": "VIIᵉ", "VIIIème": "VIIIᵉ", "IXème": "IXᵉ", "Xème": "Xᵉ", "XIème": "XIᵉ", "XIIème": "XIIᵉ", "XIIIème": "XIIIᵉ", "XIVème": "XIVᵉ", "XVème": "XVᵉ", "XVIème": "XVIᵉ", "XVIIème": "XVIIᵉ", "XVIIIème": "XVIIIᵉ", "XIXème": "XIXᵉ", "XXème": "XXᵉ", "XXIème": "XXIᵉ", "XXIIème": "XXIIᵉ", "XXIIIème": "XXIIIᵉ", "XXIVème": "XXIVᵉ", "XXVème": "XXVᵉ", "XXVIème": "XXVIᵉ", "XXVIIème": "XXVIIᵉ", "XXVIIIème": "XXVIIIᵉ", "XXIXème": "XXIXᵉ", "XXXème": "XXXᵉ" } #### Lexicographer bLexicographer = True _dTAGS = { ':N': (" nom,", "Nom"), ':A': (" adjectif,", "Adjectif"), ':M1': (" prénom,", "Prénom"), ':M2': (" patronyme,", "Patronyme, matronyme, nom de famille…"), ':MP': (" nom propre,", "Nom propre"), ':W': (" adverbe,", "Adverbe"), ':J': (" interjection,", "Interjection"), ':B': (" nombre,", "Nombre"), ':T': (" titre,", "Titre de civilité"), ':e': (" épicène", "épicène"), ':m': (" masculin", "masculin"), ':f': (" féminin", "féminin"), ':s': (" singulier", "singulier"), ':p': (" pluriel", "pluriel"), ':i': (" invariable", "invariable"), ':V1': (" verbe (1ᵉʳ gr.),", "Verbe du 1ᵉʳ groupe"), ':V2': (" verbe (2ᵉ gr.),", "Verbe du 2ᵉ groupe"), ':V3': (" verbe (3ᵉ gr.),", "Verbe du 3ᵉ groupe"), ':V0e': (" verbe,", "Verbe auxiliaire être"), ':V0a': (" verbe,", "Verbe auxiliaire avoir"), ':Y': (" infinitif,", "infinitif"), ':P': (" participe présent,", "participe présent"), ':Q': (" participe passé,", "participe passé"), ':Ip': (" présent,", "indicatif présent"), ':Iq': (" imparfait,", "indicatif imparfait"), ':Is': (" passé simple,", "indicatif passé simple"), ':If': (" futur,", "indicatif futur"), ':K': (" conditionnel présent,", "conditionnel présent"), ':Sp': (" subjonctif présent,", "subjonctif présent"), ':Sq': (" subjonctif imparfait,", "subjonctif imparfait"), ':E': (" impératif,", "impératif"), ':1s': (" 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier"), ':1ŝ': (" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"), ':1ś': (" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"), ':2s': (" 2ᵉ p. sg.,", "verbe : 2ᵉ personne du singulier"), ':3s': (" 3ᵉ p. sg.,", "verbe : 3ᵉ personne du singulier"), ':1p': (" 1ʳᵉ p. pl.,", "verbe : 1ʳᵉ personne du pluriel"), ':2p': (" 2ᵉ p. pl.,", "verbe : 2ᵉ personne du pluriel"), ':3p': (" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel"), ':3p!': (" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel (prononciation distinctive)"), ':G': ("", "Mot grammatical"), ':X': (" adverbe de négation,", "Adverbe de négation"), ':U': (" adverbe interrogatif,", "Adverbe interrogatif"), ':R': (" préposition,", "Préposition"), ':Rv': (" préposition verbale,", "Préposition verbale"), ':D': (" déterminant,", "Déterminant"), ':Dd': (" déterminant démonstratif,", "Déterminant démonstratif"), ':De': (" déterminant exclamatif,", "Déterminant exclamatif"), ':Dp': (" déterminant possessif,", "Déterminant possessif"), ':Di': (" déterminant indéfini,", "Déterminant indéfini"), ':Dn': (" déterminant négatif,", "Déterminant négatif"), ':Od': (" pronom démonstratif,", "Pronom démonstratif"), ':Oi': (" pronom indéfini,", "Pronom indéfini"), ':On': (" pronom indéfini négatif,", "Pronom indéfini négatif"), ':Ot': (" pronom interrogatif,", "Pronom interrogatif"), ':Or': (" pronom relatif,", "Pronom relatif"), ':Ow': (" pronom adverbial,", "Pronom adverbial"), ':Os': (" pronom personnel sujet,", "Pronom personnel sujet"), ':Oo': (" pronom personnel objet,", "Pronom personnel objet"), ':Ov': (" préverbe,", "Préverbe (pronom personnel objet, +ne)"), ':O1': (" 1ʳᵉ pers.,", "Pronom : 1ʳᵉ personne"), ':O2': (" 2ᵉ pers.,", "Pronom : 2ᵉ personne"), ':O3': (" 3ᵉ pers.,", "Pronom : 3ᵉ personne"), ':C': (" conjonction,", "Conjonction"), ':Ĉ': (" conjonction (él.),", "Conjonction (élément)"), ':Cc': (" conjonction de coordination,", "Conjonction de coordination"), ':Cs': (" conjonction de subordination,", "Conjonction de subordination"), ':Ĉs': (" conjonction de subordination (él.),", "Conjonction de subordination (élément)"), ':Ñ': (" locution nominale (él.),", "Locution nominale (élément)"), ':Â': (" locution adjectivale (él.),", "Locution adjectivale (élément)"), ':Ṽ': (" locution verbale (él.),", "Locution verbale (élément)"), ':Ŵ': (" locution adverbiale (él.),", "Locution adverbiale (élément)"), ':Ŕ': (" locution prépositive (él.),", "Locution prépositive (élément)"), ':Ĵ': (" locution interjective (él.),", "Locution interjective (élément)"), ':Zp': (" préfixe,", "Préfixe"), ':Zs': (" suffixe,", "Suffixe"), ':H': ("", "<Hors-norme, inclassable>"), ':@': ("", "<Caractère non alpha-numérique>"), ':@p': ("signe de ponctuation", "Signe de ponctuation"), ':@s': ("signe", "Signe divers"), ';S': (" : symbole (unité de mesure)", "Symbole (unité de mesure)"), '/*': ("", "Sous-dictionnaire <Commun>"), '/C': (" <classique>", "Sous-dictionnaire <Classique>"), '/M': ("", "Sous-dictionnaire <Moderne>"), '/R': (" <réforme>", "Sous-dictionnaire <Réforme 1990>"), '/A': ("", "Sous-dictionnaire <Annexe>"), '/X': ("", "Sous-dictionnaire <Contributeurs>") } _dValues = { 'd’': "(de), préposition ou déterminant épicène invariable", 'l’': "(le/la), déterminant ou pronom personnel objet, masculin/féminin singulier", 'j’': "(je), pronom personnel sujet, 1ʳᵉ pers., épicène singulier", 'm’': "(me), pronom personnel objet, 1ʳᵉ pers., épicène singulier", 't’': "(te), pronom personnel objet, 2ᵉ pers., épicène singulier", 's’': "(se), pronom personnel objet, 3ᵉ pers., épicène singulier/pluriel", 'n’': "(ne), adverbe de négation", 'c’': "(ce), pronom démonstratif, masculin singulier/pluriel", 'ç’': "(ça), pronom démonstratif, masculin singulier", 'qu’': "(que), conjonction de subordination", 'lorsqu’': "(lorsque), conjonction de subordination", 'puisqu’': "(puisque), conjonction de subordination", 'quoiqu’': "(quoique), conjonction de subordination", 'jusqu’': "(jusque), préposition", '-je': " pronom personnel sujet, 1ʳᵉ pers. sing.", '-tu': " pronom personnel sujet, 2ᵉ pers. sing.", '-il': " pronom personnel sujet, 3ᵉ pers. masc. sing.", '-on': " pronom personnel sujet, 3ᵉ pers. sing. ou plur.", '-elle': " pronom personnel sujet, 3ᵉ pers. fém. sing.", '-t-il': " “t” euphonique + pronom personnel sujet, 3ᵉ pers. masc. sing.", '-t-on': " “t” euphonique + pronom personnel sujet, 3ᵉ pers. sing. ou plur.", '-t-elle': " “t” euphonique + pronom personnel sujet, 3ᵉ pers. fém. sing.", '-nous': " pronom personnel sujet/objet, 1ʳᵉ pers. plur. ou COI (à nous), plur.", '-vous': " pronom personnel sujet/objet, 2ᵉ pers. plur. ou COI (à vous), plur.", '-ils': " pronom personnel sujet, 3ᵉ pers. masc. plur.", '-elles': " pronom personnel sujet, 3ᵉ pers. masc. plur.", "-là": " particule démonstrative", "-ci": " particule démonstrative", '-le': " COD, masc. sing.", '-la': " COD, fém. sing.", '-les': " COD, plur.", '-moi': " COI (à moi), sing.", '-toi': " COI (à toi), sing.", '-lui': " COI (à lui ou à elle), sing.", '-leur': " COI (à eux ou à elles), plur.", '-le-moi': " COD, masc. sing. + COI (à moi), sing.", '-le-toi': " COD, masc. sing. + COI (à toi), sing.", '-le-lui': " COD, masc. sing. + COI (à lui ou à elle), sing.", '-le-nous': " COD, masc. sing. + COI (à nous), plur.", '-le-vous': " COD, masc. sing. + COI (à vous), plur.", '-le-leur': " COD, masc. sing. + COI (à eux ou à elles), plur.", '-la-moi': " COD, fém. sing. + COI (à moi), sing.", '-la-toi': " COD, fém. sing. + COI (à toi), sing.", '-la-lui': " COD, fém. sing. + COI (à lui ou à elle), sing.", '-la-nous': " COD, fém. sing. + COI (à nous), plur.", '-la-vous': " COD, fém. sing. + COI (à vous), plur.", '-la-leur': " COD, fém. sing. + COI (à eux ou à elles), plur.", '-les-moi': " COD, plur. + COI (à moi), sing.", '-les-toi': " COD, plur. + COI (à toi), sing.", '-les-lui': " COD, plur. + COI (à lui ou à elle), sing.", '-les-nous': " COD, plur. + COI (à nous), plur.", '-les-vous': " COD, plur. + COI (à vous), plur.", '-les-leur': " COD, plur. + COI (à eux ou à elles), plur.", '-y': " pronom adverbial", "-m’y": " (me) pronom personnel objet + (y) pronom adverbial", "-t’y": " (te) pronom personnel objet + (y) pronom adverbial", "-s’y": " (se) pronom personnel objet + (y) pronom adverbial", '-en': " pronom adverbial", "-m’en": " (me) pronom personnel objet + (en) pronom adverbial", "-t’en": " (te) pronom personnel objet + (en) pronom adverbial", "-s’en": " (se) pronom personnel objet + (en) pronom adverbial", } _zElidedPrefix = re.compile("(?i)^((?:[dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)’)(.+)") _zCompoundWord = re.compile("(?i)(\\w+)(-(?:(?: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))$") _zTag = re.compile("[:;/][\\w*][^:;/]*") def split (sWord): "split word in 3 parts: prefix, root, suffix" sWord = sWord.replace("'", "’") sPrefix = "" sSuffix = "" # préfixe élidé m = _zElidedPrefix.match(sWord) if m: sPrefix = m.group(1) sWord = m.group(2) # mots composés m = _zCompoundWord.match(sWord) if m: sWord = m.group(1) sSuffix = m.group(2) return sPrefix, sWord, sSuffix def analyze (sWord): "return meaning of <sWord> if found else an empty string" sWord = sWord.lower() if sWord in _dValues: return _dValues[sWord] return "" def formatTags (sTags): "returns string: readable tags" sRes = "" sTags = re.sub("(?<=V[1-3])[itpqnmr_eaxz]+", "", sTags) sTags = re.sub("(?<=V0[ea])[itpqnmr_eaxz]+", "", sTags) for m in _zTag.finditer(sTags): sRes += _dTAGS.get(m.group(0), " [{}]".format(m.group(0)))[0] if sRes.startswith(" verbe") and not sRes.endswith("infinitif"): sRes += " [{}]".format(sTags[1:sTags.find("/")]) return sRes.rstrip(",") |
Modified graphspell/spellchecker.py from [114a0237c3] to [b9cca64fbd].
︙ | ︙ | |||
32 33 34 35 36 37 38 | self.oMainDic = self._loadDictionary(sfMainDic, True) self.oCommunityDic = self._loadDictionary(sfCommunityDic) self.oPersonalDic = self._loadDictionary(sfPersonalDic) self.bCommunityDic = bool(self.oCommunityDic) self.bPersonalDic = bool(self.oPersonalDic) self.oTokenizer = None # Default suggestions | | | | 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 | self.oMainDic = self._loadDictionary(sfMainDic, True) self.oCommunityDic = self._loadDictionary(sfCommunityDic) self.oPersonalDic = self._loadDictionary(sfPersonalDic) self.bCommunityDic = bool(self.oCommunityDic) self.bPersonalDic = bool(self.oPersonalDic) self.oTokenizer = None # Default suggestions self.lexicographer = None self.loadLexicographer(sLangCode) # storage self.bStorage = False self._dMorphologies = {} # key: flexion, value: list of morphologies self._dLemmas = {} # key: flexion, value: list of lemmas def _loadDictionary (self, source, bNecessary=False): "returns an IBDAWG object" |
︙ | ︙ | |||
98 99 100 101 102 103 104 | def deactivatePersonalDictionary (self): "deactivate personal dictionary" self.bPersonalDic = False # Default suggestions | | | | > > > > > > > > > > > > > > > > | 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 | def deactivatePersonalDictionary (self): "deactivate personal dictionary" self.bPersonalDic = False # Default suggestions def loadLexicographer (self, sLangCode): "load default suggestion module for <sLangCode>" try: self.lexicographer = importlib.import_module(".lexgraph_"+sLangCode, "grammalecte.graphspell") except ImportError: print("No suggestion module for language <"+sLangCode+">") return def analyze (self, sWord): "returns a list of words and their morphologies" if not self.lexicographer: return [] lWordAndMorph = [] for sElem in self.lexicographer.split(sWord): if sElem: lMorph = self.getMorph(sElem) sLex = self.lexicographer.analyze(sElem) if sLex: aRes = [ (" | ".join(lMorph), sLex) ] else: aRes = [ (sMorph, self.lexicographer.formatTags(sMorph)) for sMorph in lMorph ] if aRes: lWordAndMorph.append((sElem, aRes)) return lWordAndMorph # Storage def activateStorage (self): "store all lemmas and morphologies retrieved from the word graph" self.bStorage = True |
︙ | ︙ | |||
157 158 159 160 161 162 163 164 165 166 167 168 169 170 | else: if not bByLemma: dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1 else: for sLemma in self.getLemma(dToken['sValue']): dWord[sLemma] = dWord.get(sLemma, 0) + 1 return dWord # IBDAWG functions def isValidToken (self, sToken): "checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)" if self.oMainDic.isValidToken(sToken): return True | > | 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 | else: if not bByLemma: dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1 else: for sLemma in self.getLemma(dToken['sValue']): dWord[sLemma] = dWord.get(sLemma, 0) + 1 return dWord # IBDAWG functions def isValidToken (self, sToken): "checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)" if self.oMainDic.isValidToken(sToken): return True |
︙ | ︙ | |||
214 215 216 217 218 219 220 | if sWord not in self._dLemmas: self.getMorph(sWord) return self._dLemmas[sWord] return { s[1:s.find("/")] for s in self.getMorph(sWord) } def suggest (self, sWord, nSuggLimit=10): "generator: returns 1, 2 or 3 lists of suggestions" | | | | | | | 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 | if sWord not in self._dLemmas: self.getMorph(sWord) return self._dLemmas[sWord] return { s[1:s.find("/")] for s in self.getMorph(sWord) } def suggest (self, sWord, nSuggLimit=10): "generator: returns 1, 2 or 3 lists of suggestions" if self.lexicographer.dSugg: if sWord in self.lexicographer.dSugg: yield self.lexicographer.dSugg[sWord].split("|") elif sWord.istitle() and sWord.lower() in self.lexicographer.dSugg: lRes = self.lexicographer.dSugg[sWord.lower()].split("|") yield list(map(lambda sSugg: sSugg[0:1].upper()+sSugg[1:], lRes)) else: yield self.oMainDic.suggest(sWord, nSuggLimit, True) else: yield self.oMainDic.suggest(sWord, nSuggLimit, True) if self.bCommunityDic: yield self.oCommunityDic.suggest(sWord, (nSuggLimit//2)+1) |
︙ | ︙ |