Grammalecte  Check-in [4f7bc2e814]

Overview
Comment:[fx] gestion des différentes sortes de mots composés du lexicographe
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fx | Lexicographe
Files: files | file ages | folders
SHA3-256: 4f7bc2e8145519b9a8cc224f400a90ed779993f85044c61d55280aeb2da82ca1
User & Date: olr on 2017-11-11 12:19:36
Other Links: branch diff | manifest | tags
Context
2017-11-12
13:22
[core][fx] tokenizer: +acronyms check-in: fa1205c098 user: olr tags: core, fx, Lexicographe
2017-11-11
12:19
[fx] gestion des différentes sortes de mots composés du lexicographe check-in: 4f7bc2e814 user: olr tags: fx, Lexicographe
2017-11-07
16:42
Permet d'isoler les sections ajoutées par script. check-in: cbaf0f2ddf user: IllusionPerdu tags: Lexicographe
Changes

Modified gc_lang/fr/modules-js/lexicographe.js from [e07c787a42] to [dcd48534e3].

226
227
228
229
230
231
232


233

234
235
236
237
238
239
240
class Lexicographe {

    constructor (oDict, oTokenizer, oLocGraph) {
        this.oDict = oDict;
        this.oTokenizer = oTokenizer;
        this.oLocGraph = JSON.parse(oLocGraph);



        this._zInterroVerb = 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-Z0-9ÑÂĴĈŔÔṼŴ!][^:;/]*", "g");
    }

    getInfoForToken (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a object {sType, sValue, aLabel}
        let m = null;







>
>
|
>







226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
class Lexicographe {

    constructor (oDict, oTokenizer, oLocGraph) {
        this.oDict = oDict;
        this.oTokenizer = oTokenizer;
        this.oLocGraph = JSON.parse(oLocGraph);

        this._zPartDemForm = new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-(là|ci)$", "i");
        this._aPartDemExceptList = new Set(["celui", "celle", "ceux", "celles", "de", "jusque", "par", "marie-couche-toi"]);
        this._zInterroVerb = new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-(t-(?:il|elle|on)|je|tu|ils?|elles?|on|[nv]ous)$", "i");
        this._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");
        this._zTag = new RegExp("[:;/][a-zA-Z0-9ÑÂĴĈŔÔṼŴ!][^:;/]*", "g");
    }

    getInfoForToken (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a object {sType, sValue, aLabel}
        let m = null;
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
                case 'WORD':
                    if (oToken.sValue.gl_count("-") > 4) {
                        return {
                            sType: "COMPLEX",
                            sValue: oToken.sValue,
                            aLabel: ["élément complexe indéterminé"]
                        };
                    } else if (m = this._zInterroVerb.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));

                        }


                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabel: ["forme verbale interrogative"],
                            aSubElem: [
                                { sType: oToken.sType, sValue: m[1],       aLabel: aElem },
                                { sType: oToken.sType, sValue: "-" + m[2], aLabel: [this._formatSuffix(m[2].toLowerCase())] }
                            ]
                        };
                    } 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.length > 0) ? aElem : ["mot composé indéterminé"]
                        };
                    } 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 += _dTag.get(m[0]);







|
|
>
>
>
>
|
>
>
>
>
>
>
|
>
>
>
>
>
|
>
>
>
>
>
>
|
>
|
>
>





|




<
<
<
<
<



|





|









>
>
>
>
>
>
>
>
>
>
>







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
                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.oDict.isValidToken(oToken.sValue)) {





                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabel: this._getMorph(oToken.sValue)
                        };
                    } else {
                        return {
                            sType: "UNKNOWN",
                            sValue: oToken.sValue,
                            aLabel: ["mot inconnu du dictionnaire"]
                        };
                    }
                    break;
            }
        } catch (e) {
            helpers.logerror(e);
        }
        return null;
    }

    _getMorph (sWord) {
        let aElem = [];
        for (let s of this.oDict.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 += _dTag.get(m[0]);