Grammalecte  Check-in [85d2c18b0e]

Overview
Comment:Renommage des variables pour se conformer au reste du code
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | Lexicographe
Files: files | file ages | folders
SHA3-256: 85d2c18b0ed858ae8ce8887bfd4c4dfe347232ef1450dffdaf14faa957849a29
User & Date: IllusionPerdu on 2017-10-29 23:33:31
Other Links: branch diff | manifest | tags
Context
2017-10-30
09:21
[fr] lexicographe: commentaire erroné check-in: b9365d6a6c user: olr tags: Lexicographe, fr
2017-10-29
23:33
Renommage des variables pour se conformer au reste du code check-in: 85d2c18b0e user: IllusionPerdu tags: Lexicographe
22:57
Ajout forme :Ô locution pronominales check-in: 937fa6cf25 user: IllusionPerdu tags: Lexicographe
Changes

Modified gc_lang/fr/modules-js/lexicographe.js from [a897840ed1] to [1cdb365c76].

205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
...
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
...
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
...
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
374


375
376
377
378

379
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
414

415
416
417
418
419
420

421
422
423

424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450

        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*Ṽ][^:;/]*", "g");

    }

    getInfoForToken(oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a list [type, token_string, values]
        let m = null;
        try {
            switch (oToken.sType) {
                case 'SEPARATOR':
                    return {
................................................................................
            }
        } 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;
................................................................................
            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));
    }

    getListOfTokens(sText, bInfo = true) {
        let aElem = [];
        sText = sText.replace("'", "’").trim();
        if (sText !== "") {
            let aRes = null;
            for (let oToken of this.oTokenizer.genTokens(sText)) {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
................................................................................
                    aElem.push(oToken);
                }
            }
        }
        return aElem;
    }

    elpfxToword(sELPFX){
        return sELPFX.replace('’', 'e').toLowerCase();
    }

    getListOfTokensReduc(sText, bInfo = true) {
        let lstToken = this.getListOfTokens(sText, false);
        //console.log(lstToken);
        //console.log(this.oLocution);

        let id = 0;
        let aElem = [];
        let aRes = null;
        let isType = {'WORD':1,'ELPFX':1};
        do {
            let oToken = lstToken[id]
            let aLocution = this.oLocution[this.elpfxToword(oToken.sValue)];
            //console.log('Start cherche', oToken.sValue, aLocution);
            let stop = false;
            let start = id + 1;
            let lastTokenWord = '';
            let ok = false;


            let oLst = [];
            oLst.push(oToken);
            while (!stop && typeof aLocution !== "undefined") {
                if (start > lstToken.length){

                    break;
                }

                let typeToken = '';
                let nextToken = lstToken[start];
                //console.log(start, nextToken, aLocution);

                if ( typeof nextToken !== "undefined" ) {
                    aLocution = aLocution[this.elpfxToword(nextToken.sValue)];
                    typeToken = nextToken.sType;

                } else {
                    aLocution = "undefined";
                }

                if ( typeToken in isType && typeof aLocution !== "undefined") {
                    lastTokenWord = Object.keys(aLocution)[0];
                    start++;
                    oLst.push(nextToken);
                    //console.log( nextToken.sValue );
                } else if ( !(typeToken in isType) || typeof aLocution == "undefined") {
                    stop = true;
                    if ( lastTokenWord.substring(0, 1) == ':' ) {
                        ok = true;
                    }
                }
            };

            if ( ok ){
                let word = '';
                for (let oToken of oLst) {
                    word += oToken.sValue+' ';
                    //console.log('***',word);
                }
                id = id + oLst.length-1;
                let tmpToken = {

                    'nEnd':oLst[oLst.length-1].nEnd,
                    'nStart':oLst[0].nStart,

                    'sType':"LOC",
                    'sValue':word.replace('’ ','’').trim()
                };
                if (bInfo) {
                    let formatedTag = [];
                    for (let oToFormat of lastTokenWord.split('|') ){

                        formatedTag.push( this._formatTags(oToFormat).replace(/(\(él.\))/g,'').trim() );
                    }
                    aElem.push({

                        sType: tmpToken.sType,
                        sValue: tmpToken.sValue,
                        aLabel: formatedTag
                    });
                } else {
                    aElem.push(tmpToken);
                }
            } else {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else {
                    aElem.push(oToken);
                }
            }
            id++;
        } while (id < lstToken.length);
        return aElem;
    }
}


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







|







 







|







 







|













|







 







|
|


|
|
<
<
<
|




|
|
<
|
<
<
|
>
>
|
|
|
<
>


>
|
<
<

|
|
<
>




|
|
|
|
<
|
|
|
|




|
|
|
|
<

|
<
>
|
<
>

|


|
<
>
|


>
|
<
|


|











|
|








205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
...
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
...
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
...
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

374
375
376
377
378


379
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
414
415
416
417
418

419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443

        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*Ṽ][^:;/]*", "g");

    }

    getInfoForToken (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a list [type, token_string, values]
        let m = null;
        try {
            switch (oToken.sType) {
                case 'SEPARATOR':
                    return {
................................................................................
            }
        } 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;
................................................................................
            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));
    }

    getListOfTokens (sText, bInfo = true) {
        let aElem = [];
        sText = sText.replace("'", "’").trim();
        if (sText !== "") {
            let aRes = null;
            for (let oToken of this.oTokenizer.genTokens(sText)) {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
................................................................................
                    aElem.push(oToken);
                }
            }
        }
        return aElem;
    }

    _unifyStr (sWord){
        return sWord.replace('’', 'e').toLowerCase();
    }

    getListOfTokensReduc (sText, bInfo = true) {
        let aTokenList = this.getListOfTokens(sText, false);



        let iKey = 0;
        let aElem = [];
        let aRes = null;
        let isType = {'WORD':1,'ELPFX':1};
        do {
            let oToken = aTokenList[iKey]
            let aLocution = this.oLocution[this._unifyStr(oToken.sValue)];

            let bStop = false;


            let bOk = false;
            let iKeyTree = iKey + 1;
            let sTokenTmpKey = '';
            let aTokenTempList = [];
            aTokenTempList.push(oToken);
            while (!bStop && typeof aLocution !== "undefined") {

                if (iKeyTree > aTokenList.length){
                    break;
                }
                let sTokenNextType = '';
                let oTokenNext = aTokenList[iKeyTree];



                if ( typeof oTokenNext !== "undefined" ) {
                    aLocution = aLocution[this._unifyStr(oTokenNext.sValue)];

                    sTokenNextType = oTokenNext.sType;
                } else {
                    aLocution = "undefined";
                }

                if ( sTokenNextType in isType && typeof aLocution !== "undefined") {
                    sTokenTmpKey = Object.keys(aLocution)[0];
                    iKeyTree++;
                    aTokenTempList.push(oTokenNext);

                } else if ( !(sTokenNextType in isType) || typeof aLocution == "undefined") {
                    bStop = true;
                    if ( sTokenTmpKey.substring(0, 1) == ':' ) {
                        bOk = true;
                    }
                }
            };

            if ( bOk ){
                let sWord = '';
                for (let oTokenWord of aTokenTempList) {
                    sWord += oTokenWord.sValue+' ';

                }
                iKey = iKey + aTokenTempList.length-1;

                let oTokenLocution = {
                    'nEnd':aTokenTempList[aTokenTempList.length-1].nEnd,

                    'niKeyTree':aTokenTempList[0].niKeyTree,
                    'sType':"LOC",
                    'sValue':sWord.replace('’ ','’').trim()
                };
                if (bInfo) {
                    let aFormatedTag = [];

                    for (let sTagMulti of sTokenTmpKey.split('|') ){
                        aFormatedTag.push( this._formatTags(sTagMulti).replace(/(\(él.\))/g,'').trim() );
                    }
                    aElem.push({
                        sType: oTokenLocution.sType,
                        sValue: oTokenLocution.sValue,

                        aLabel: aFormatedTag
                    });
                } else {
                    aElem.push(oTokenLocution);
                }
            } else {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else {
                    aElem.push(oToken);
                }
            }
            iKey++;
        } while (iKey < aTokenList.length);
        return aElem;
    }
}


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