Grammalecte  Diff

Differences From Artifact [cfbfcc7fa9]:

To Artifact [a348883011]:


195
196
197
198
199
200
201
202

203
204
205
206
207
208
209
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 {
            switch (oToken.sType) {







<
>







195
196
197
198
199
200
201

202
203
204
205
206
207
208
209
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 {
            switch (oToken.sType) {
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
                    break;
                case 'WORD': 
                    if (oToken.sValue.gl_count("-") > 4) {
                        return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] };
                    }
                    else if (this.oDict.isValidToken(oToken.sValue)) {
                        let lMorph = this.oDict.getMorph(oToken.sValue);
                        let aElem = [ for (s of lMorph) if (s.includes(":")) this._formatTags(s) ];



                        return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem};
                    }
                    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;
    };


    _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 += _dTAGS.get(m[0]);
            if (sRes.length > 100) {
                break;
            }
        }
        if (sRes.startsWith(" verbe") && !sRes.endsWith("infinitif")) {
            sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]";
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            helpers.echo(sRes);
            return sRes;
        }
        return sRes.gl_trimRight(",");
    };


    _formatSuffix (s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));
        }
        if (!s.includes("-")) {
            return _dAD.get(s.replace("’", "'"));
        }
        if (s.endsWith("ous")) {
            s += '2';
        }
        let nPos = s.indexOf("-");
        return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos+1));
    };

}


if (typeof(exports) !== 'undefined') {
    exports.Lexicographe = Lexicographe;
}







|
>
>
>





|
>
>
>













<
>




















<
>













<
>






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
                    break;
                case 'WORD': 
                    if (oToken.sValue.gl_count("-") > 4) {
                        return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] };
                    }
                    else if (this.oDict.isValidToken(oToken.sValue)) {
                        let lMorph = this.oDict.getMorph(oToken.sValue);
                        let aElem = [];
                        for (let s of lMorph){
                            if (s.includes(":"))  aElem.push( 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 (let s of lMorph){
                            if (s.includes(":"))  aElem.push( 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;

    }

    _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 += _dTAGS.get(m[0]);
            if (sRes.length > 100) {
                break;
            }
        }
        if (sRes.startsWith(" verbe") && !sRes.endsWith("infinitif")) {
            sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]";
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            helpers.echo(sRes);
            return sRes;
        }
        return sRes.gl_trimRight(",");

    }

    _formatSuffix (s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));
        }
        if (!s.includes("-")) {
            return _dAD.get(s.replace("’", "'"));
        }
        if (s.endsWith("ous")) {
            s += '2';
        }
        let nPos = s.indexOf("-");
        return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos+1));

    }
}


if (typeof(exports) !== 'undefined') {
    exports.Lexicographe = Lexicographe;
}