Grammalecte  Check-in [b3d7cb93a1]

Overview
Comment:[fr] lexicographe: gestion des formes verbales interrogatives
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fr | Lexicographe
Files: files | file ages | folders
SHA3-256: b3d7cb93a15e3f1883bcafea8b84ce809c0834cf3ffc55f6b3770ff53b46bd2c
User & Date: olr on 2017-11-02 11:30:58
Other Links: branch diff | manifest | tags
Context
2017-11-03
18:40
[fx] lexicographe: affichage des locutions peu probables check-in: ddc5a860da user: olr tags: Lexicographe, fr
2017-11-02
11:30
[fr] lexicographe: gestion des formes verbales interrogatives check-in: b3d7cb93a1 user: olr tags: Lexicographe, fr
11:01
[fr] restructuration des données pour éviter la confusion avec le token <:> check-in: 685f9128f0 user: olr tags: Lexicographe, fr
Changes

Modified gc_lang/fr/modules-js/lexicographe.js from [5f1e1db445] to [ca1b924117].

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

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

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

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







|







 







|






<



|
>
>
>
>







226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
...
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
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;
................................................................................
                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));
                        }