132
133
134
135
136
137
138
139
140
141
142
143
144
145
|
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
|
+
+
+
+
+
+
+
+
+
+
+
|
//// Lexicographer
var lexgraph_fr = {
dSugg: _dSugg,
// Préfixes et suffixes
aPfx1: new Set([
"anti", "archi", "contre", "hyper", "mé", "méta", "im", "in", "ir", "par", "proto",
"pseudo", "pré", "re", "ré", "sans", "sous", "supra", "sur", "ultra"
]),
aPfx2: new Set([
"belgo", "franco", "génito", "gynéco", "médico", "russo"
]),
// Étiquettes
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"]],
|
369
370
371
372
373
374
375
376
377
378
379
380
381
382
|
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
|
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
|
load: function (oSpellChecker, oTokenizer, oLocGraph) {
this.oSpellChecker = oSpellChecker;
this.oTokenizer = oTokenizer;
this.oLocGraph = JSON.parse(oLocGraph);
},
split: function (sWord) {
// returns an arry of strings (prefix, trimed_word, suffix)
let sPrefix = "";
let sSuffix = "";
// préfixe élidé
let m = /^([ldmtsnjcç]|lorsqu|presqu|jusqu|puisqu|quoiqu|quelqu|qu)[’'‘`ʼ]([a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st-]+)/i.exec(sWord);
if (m) {
sPrefix = m[1] + "’";
sWord = m[2];
}
// mots composés
m = /^([a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st-]+)(-(?:(?: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|ce))$/i.exec(sWord);
if (m) {
sWord = m[1];
sSuffix = m[2];
}
// split word in 3 parts: prefix, root, suffix
return [sPrefix, sWord, sSuffix];
},
getInfoForToken: function (oToken) {
// Token: .sType, .sValue, .nStart, .nEnd
// return a object {sType, sValue, aLabel}
let m = null;
try {
switch (oToken.sType) {
|