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
|
["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':
return [oToken.sType, oToken.sValue, _dSeparator._get(oToken.sValue, "caractère indéterminé")];
break;
case 'NUM':
return [oToken.sType, oToken.sValue, "nombre"];
break;
case 'LINK':
return [oToken.sType, oToken.sValue.slice(0,40)+"…", "hyperlien"];
break;
case 'ELPFX':
sTemp = oToken.sValue.replace("’", "'").replace("`", "'").toLowerCase();
return [oToken.sType, oToken.sValue, _dPFX._get(sTemp, "préfixe élidé inconnu")];
break;
case 'WORD':
if (oToken.sValue._count("-") > 4) {
return ["COMPLEX", oToken.sValue, "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 [ oToken.sType, oToken.sValue, [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 [ oToken.sType, oToken.sValue, [aElem] ];
}
else {
return ["INCONNU", oToken.sValue, "inconnu du dictionnaire"];
}
break;
}
}
catch (e) {
helpers.logerror(e);
}
return null
};
getHTMLForText (sText) {
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) {
try {
if (!sWord) {
return "";
}
if (sWord._count("-") > 4) {
return '<p><b class="mbok">' + sWord + "</b> <s>:</s> élément complexe indéterminé</p>\n";
}
|
>
>
>
>
>
>
>
>
>
|
|
|
|
|
|
|
|
|
|
>
>
|
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";
}
|