Overview
Comment: | [fx][fr][js] tokeniseur --> lexicographe |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | fr | fx | kill_innerHTML |
Files: | files | file ages | folders |
SHA3-256: |
b4cf00a4c806dc5001284479150bc600 |
User & Date: | olr on 2017-07-13 06:50:45 |
Original Comment: | [fr][js] tokeniseur --> lexicographe |
Other Links: | branch diff | manifest | tags |
Context
2017-07-13
| ||
06:54 | [fr][js] fausse manœuvre (commit accidentel) check-in: af7332c066 user: olr tags: fr, kill_innerHTML | |
06:50 | [fx][fr][js] tokeniseur --> lexicographe check-in: b4cf00a4c8 user: olr tags: fr, fx, kill_innerHTML | |
2017-07-12
| ||
11:03 | [fr][js] màj: lexicographe, tokenizer check-in: 074cb33c80 user: olr tags: fr, kill_innerHTML | |
Changes
Modified gc_core/js/helpers.js from [6c4ecd114f] to [262e2563f7].
︙ | ︙ | |||
28 29 30 31 32 33 34 35 36 37 38 39 40 41 | if (funcOutput !== null) { funcOutput(sMsg); } else { console.error(sMsg); } } // load ressources in workers (suggested by Mozilla extensions reviewers) // for more options have a look here: https://gist.github.com/Noitidart/ec1e6b9a593ec7e3efed // if not in workers, use sdk/data.load() instead function loadFile (spf) { try { let xRequest; | > > > > > > > > > | 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | if (funcOutput !== null) { funcOutput(sMsg); } else { console.error(sMsg); } } function inspect (o) { let sMsg = "__inspect__: " + typeof o; for (let sParam in o) { sMsg += "\n" + sParam + ": " + o.sParam; } sMsg += "\n" + JSON.stringify(o) + "\n__end__"; echo(sMsg); } // load ressources in workers (suggested by Mozilla extensions reviewers) // for more options have a look here: https://gist.github.com/Noitidart/ec1e6b9a593ec7e3efed // if not in workers, use sdk/data.load() instead function loadFile (spf) { try { let xRequest; |
︙ | ︙ | |||
76 77 78 79 80 81 82 83 84 85 86 | let obj = {}; for (let [k, v] of m) { obj[k] = v; } return obj; } exports.echo = echo; exports.logerror = logerror; exports.objectToMap = objectToMap; exports.mapToObject = mapToObject; | > > < | 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | let obj = {}; for (let [k, v] of m) { obj[k] = v; } return obj; } exports.setLogOutput = setLogOutput; exports.echo = echo; exports.logerror = logerror; exports.inspect = inspect; exports.objectToMap = objectToMap; exports.mapToObject = mapToObject; exports.loadFile = loadFile; |
Modified gc_lang/fr/modules-js/lexicographe.js from [98b82a04c2] to [461116409d].
︙ | ︙ | |||
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 | ["s'en", " (se) pronom personnel objet + (en) pronom adverbial"] ]); const _dSeparator = new Map ([ ['.', "point"], ['·', "point médian"], ['…', "points de suspension"], [';', "point-virgule"], [',', "virgule"], ['?', "point d’interrogation"], ['!', "point d’exclamation"], ['(', "parenthèse ouvrante"], [')', "parenthèse fermante"], ['[', "crochet ouvrante"], [']', "crochet fermante"], ['{', "accolade ouvrante"], ['}', "accolade fermante"], ['—', "tiret cadratin"], ['–', "tiret demi-cadratin"], ['«', "guillemet ouvrant (chevrons)"], ['»', "guillemet fermant (chevrons)"], ['“', "guillemet ouvrant double"], ['”', "guillemet fermant double"], ['‘', "guillemet ouvrant"], ['’', "guillemet fermant"], ]); class Lexicographe { constructor (oDict) { this.oDict = oDict; this._zElidedPrefix = new RegExp ("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i"); this._zCompoundWord = new RegExp ("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$", "i"); this._zTag = new RegExp ("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*][^:;/]*", "g"); }; getInfoForToken (oToken) { // Token: .sType, .sValue, .nStart, .nEnd let m = null; try { helpers.echo(oToken); switch (oToken.sType) { case 'SEPARATOR': | > > > > > > > > > | | | | | | | | | | > > | 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 | ["s'en", " (se) pronom personnel objet + (en) pronom adverbial"] ]); const _dSeparator = new Map ([ ['.', "point"], ['·', "point médian"], ['…', "points de suspension"], [':', "deux-points"], [';', "point-virgule"], [',', "virgule"], ['?', "point d’interrogation"], ['!', "point d’exclamation"], ['(', "parenthèse ouvrante"], [')', "parenthèse fermante"], ['[', "crochet ouvrante"], [']', "crochet fermante"], ['{', "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"], ['/', "signe de la division"], ['+', "signe de l’addition"], ['*', "signe de la multiplication"], ['=', "signe de l’égalité"], ['<', "inférieur à"], ['>', "supérieur à"], ]); class Lexicographe { constructor (oDict) { this.oDict = oDict; this._zElidedPrefix = new RegExp ("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i"); this._zCompoundWord = new RegExp ("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$", "i"); this._zTag = new RegExp ("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*][^:;/]*", "g"); }; getInfoForToken (oToken) { // Token: .sType, .sValue, .nStart, .nEnd // return a list [type, token_string, values] let m = null; try { helpers.echo(oToken); switch (oToken.sType) { case 'SEPARATOR': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dSeparator._get(oToken.sValue, "caractère indéterminé")] }; break; case 'NUM': return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["nombre"] }; break; case 'LINK': return { sType: oToken.sType, sValue: oToken.sValue.slice(0,40)+"…", aLabel: ["hyperlien"] }; break; case 'ELPFX': let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase(); return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dPFX._get(sTemp, "préfixe élidé inconnu")] }; break; case 'WORD': if (oToken.sValue._count("-") > 4) { return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] }; } else if (this.oDict.isValidToken(oToken.sValue)) { let lMorph = this.oDict.getMorph(oToken.sValue); let aElem = [ for (s of lMorph) if (s.includes(":")) this._formatTags(s) ]; return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem}; } else if (m = this._zCompoundWord.exec(oToken.sValue)) { // mots composés let lMorph = this.oDict.getMorph(m[1]); let aElem = [ for (s of lMorph) if (s.includes(":")) this._formatTags(s) ]; aElem.push("-" + m[2] + ": " + this._formatSuffix(m[2].toLowerCase())); return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem }; } else { return { sType: "UNKNOWN", sValue: oToken.sValue, aLabel: ["inconnu du dictionnaire"] }; } break; } } catch (e) { helpers.logerror(e); } return null; }; getHTMLForText (sText) { // deprecated sText = sText.replace(/[.,.?!:;…\/()\[\]“”«»"„{}–—#+*<>%=\n]/g, " ").replace(/\s+/g, " "); let iStart = 0; let iEnd = 0; let sHtml = '<div class="paragraph">\n'; while ((iEnd = sText.indexOf(" ", iStart)) !== -1) { sHtml += this.getHTMLForToken(sText.slice(iStart, iEnd)); iStart = iEnd + 1; } sHtml += this.getHTMLForToken(sText.slice(iStart)); return sHtml + '</div>\n'; }; getHTMLForToken (sWord) { // deprecated try { if (!sWord) { return ""; } if (sWord._count("-") > 4) { return '<p><b class="mbok">' + sWord + "</b> <s>:</s> élément complexe indéterminé</p>\n"; } |
︙ | ︙ |
Modified gc_lang/fr/xpi/data/lxg_panel.css from [beaf75f9d5] to [3d666aa76c].
︙ | ︙ | |||
38 39 40 41 42 43 44 45 46 47 48 | padding: 5px 50px; background-color: hsla(0, 0%, 75%, 1); color: hsla(0, 0%, 96%, 1); border-radius: 5px; text-align: center; font-size: 20px; } #wordlist ul { margin: 0 0 5px 40px; } #wordlist b { | > > > | > > > | > > > > > > | > > > | | | 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 | padding: 5px 50px; background-color: hsla(0, 0%, 75%, 1); color: hsla(0, 0%, 96%, 1); border-radius: 5px; text-align: center; font-size: 20px; } #wordlist .token { margin: 8px; } #wordlist ul { margin: 0 0 5px 40px; } #wordlist b { background-color: hsla(150, 10%, 50%, 1); color: hsla(0, 0%, 96%, 1); padding: 2px 5px; border-radius: 2px; text-decoration: none; } #wordlist b.WORD { background-color: hsla(150, 50%, 50%, 1); } #wordlist b.ELPFX { background-color: hsla(150, 30%, 50%, 1); } #wordlist b.UNKNOWN { background-color: hsla(0, 50%, 50%, 1); } #wordlist b.NUM { background-color: hsla(180, 50%, 50%, 1); } #wordlist b.COMPLEX { background-color: hsla(60, 50%, 50%, 1); } #wordlist b.SEPARATOR { background-color: hsla(210, 50%, 50%, 1); } #wordlist b.LINK { background-color: hsla(270, 50%, 50%, 1); } #wordlist s { color: hsla(0, 0%, 60%, 1); text-decoration: none; } #wordlist .textline { text-decoration: bold; |
︙ | ︙ |
Modified gc_lang/fr/xpi/data/lxg_panel.js from [8999221c88] to [4bd6c52064].
︙ | ︙ | |||
23 24 25 26 27 28 29 | // Conjugueur document.getElementById('conjugueur').addEventListener("click", function (event) { self.port.emit('openConjugueur'); }); */ self.port.on("addSeparator", function (sText) { | < < | < < > | > > | < < < > | 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | // Conjugueur document.getElementById('conjugueur').addEventListener("click", function (event) { self.port.emit('openConjugueur'); }); */ self.port.on("addSeparator", function (sText) { addSeparator(sText); }); self.port.on("addParagraphElems", function (sJSON) { addParagraphElems(sJSON); }); self.port.on("addMessage", function (sClass, sText) { addMessage(sClass, sText); }); self.port.on("clear", function (sHtml) { document.getElementById("wordlist").textContent = ""; }); self.port.on("startWaitIcon", function() { |
︙ | ︙ | |||
63 64 65 66 67 68 69 70 71 72 73 74 75 76 | self.port.emit("resize", xElem.id, 10); } } }, false ); // display selection function displayClasses () { setHidden("ok", document.getElementById("ok").checked); setHidden("mbok", document.getElementById("mbok").checked); setHidden("nb", document.getElementById("nb").checked); | > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 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 | self.port.emit("resize", xElem.id, 10); } } }, false ); /* Actions */ function addSeparator (sText) { if (document.getElementById("wordlist").textContent !== "") { let xElem = document.createElement("p"); xElem.className = "separator"; xElem.textContent = sText; document.getElementById("wordlist").appendChild(xElem); } } function addMessage (sClass, sText) { let xNode = document.createElement("p"); xNode.className = sClass; xNode.textContent = sText; document.getElementById("wordlist").appendChild(xNode); } function addParagraphElems (sJSON) { try { let xNodeDiv = document.createElement("div"); xNodeDiv.className = "paragraph"; let lElem = JSON.parse(sJSON); for (let oToken of lElem) { xNodeDiv.appendChild(createTokenNode(oToken)); } document.getElementById("wordlist").appendChild(xNodeDiv); } catch (e) { console.error("\n" + e.fileName + "\n" + e.name + "\nline: " + e.lineNumber + "\n" + e.message); console.error(sJSON); } } function createTokenNode (oToken) { let xTokenNode = document.createElement("div"); xTokenNode.className = "token " + oToken.sType; let xTokenValue = document.createElement("b"); xTokenValue.className = oToken.sType; xTokenValue.textContent = oToken.sValue; xTokenNode.appendChild(xTokenValue); let xSep = document.createElement("s"); xSep.textContent = " : "; xTokenNode.appendChild(xSep); if (oToken.aLabel.length === 1) { xTokenNode.appendChild(document.createTextNode(oToken.aLabel[0])); } else { let xTokenList = document.createElement("ul"); for (let sLabel of oToken.aLabel) { let xTokenLine = document.createElement("li"); xTokenLine.textContent = sLabel; xTokenList.appendChild(xTokenLine); } xTokenNode.appendChild(xTokenList); } return xTokenNode; } // display selection function displayClasses () { setHidden("ok", document.getElementById("ok").checked); setHidden("mbok", document.getElementById("mbok").checked); setHidden("nb", document.getElementById("nb").checked); |
︙ | ︙ |
Modified gc_lang/fr/xpi/gce_worker.js from [31c05a3116] to [69edc307b9].
︙ | ︙ | |||
143 144 145 146 147 148 149 | gce.setOptions(dMemoOptions); return sAllRes; } // Lexicographer | < < < < < < < | 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | gce.setOptions(dMemoOptions); return sAllRes; } // Lexicographer function getListOfElements (sText) { try { let aElem = []; let aRes = null; for (let oToken of oTokenizer.genTokens(sText)) { aRes = oLxg.getInfoForToken(oToken); if (aRes) { aElem = aElem.concat(aRes); } } return JSON.stringify(aElem); } catch (e) { helpers.logerror(e); |
︙ | ︙ |
Modified gc_lang/fr/xpi/ui.js from [d81c939773] to [60cc552c6c].
︙ | ︙ | |||
567 568 569 570 571 572 573 | xLxgPanel.port.emit("addSeparator", _("separator")); loadGrammarChecker(); let nParagraph = 0; // non empty paragraphs let sRes = ""; try { for (let sParagraph of text.getParagraph(sText)) { if (sParagraph.trim() !== "") { | | | | | | 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 | xLxgPanel.port.emit("addSeparator", _("separator")); loadGrammarChecker(); let nParagraph = 0; // non empty paragraphs let sRes = ""; try { for (let sParagraph of text.getParagraph(sText)) { if (sParagraph.trim() !== "") { sRes = await xGCEWorker.post('getListOfElements', [sParagraph]); xLxgPanel.port.emit("addParagraphElems", sRes); nParagraph += 1; } } xLxgPanel.port.emit("addMessage", 'message', _("numberOfParagraphs") + " " + nParagraph); } catch (e) { xLxgPanel.port.emit("addMessage", 'bug', e.message); } xLxgPanel.port.emit("stopWaitIcon"); } /* Conjugueur |
︙ | ︙ |