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
|
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 = [];
if (sText !== "") {
for (let oToken of this.oTokenizer.genTokens(sText)) {
if (bInfo) {
let aRes = this.getInfoForToken(oToken);
if (aRes) {
aElem.push(aRes);
}
} else if (oToken.sType !== "SPACE") {
aElem.push(oToken);
}
}
}
return aElem;
}
getListOfTokensReduc (sText, bInfo = true) {
let aTokenList = this.getListOfTokens(sText.replace("'", "’").trim(), false);
let iKey = 0;
let aElem = [];
do {
let oToken = aTokenList[iKey];
let sMorphLoc = '';
let aTokenTempList = [oToken];
|
|
|
|
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
|
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 = [];
if (sText !== "") {
for (let oToken of this.oTokenizer.genTokens(sText)) {
if (bInfo) {
let aRes = this.getInfoForToken(oToken);
if (aRes) {
aElem.push(aRes);
}
} else if (oToken.sType !== "SPACE") {
aElem.push(oToken);
}
}
}
return aElem;
}
getListOfTokensReduc (sText, bInfo=true) {
let aTokenList = this.getListOfTokens(sText.replace("'", "’").trim(), false);
let iKey = 0;
let aElem = [];
do {
let oToken = aTokenList[iKey];
let sMorphLoc = '';
let aTokenTempList = [oToken];
|
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
|
}
if (sMorphLoc) {
let sWord = '';
for (let oTokenWord of aTokenTempList) {
sWord += oTokenWord.sValue+' ';
}
iKey = iKey + aTokenTempList.length-1;
'nEnd': aTokenTempList[aTokenTempList.length-1].nEnd,
}
iKey++;
|
<
<
>
>
<
|
>
|
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
|
}
if (sMorphLoc) {
let sWord = '';
for (let oTokenWord of aTokenTempList) {
sWord += oTokenWord.sValue+' ';
}
let oTokenLocution = {
'nStart': aTokenTempList[0].nStart,
'nEnd': aTokenTempList[aTokenTempList.length-1].nEnd,
'sType': "LOC",
'sValue': sWord.replace('’ ','’').trim()
};
if (bInfo) {
let aFormatedTag = [];
for (let sTagMulti of sMorphLoc.split('|') ){
aFormatedTag.push( this._formatTags(sTagMulti).replace(/( \(él.\))/g,'') );
}
aElem.push({
sType: oTokenLocution.sType,
sValue: oTokenLocution.sValue,
aLabel: aFormatedTag
});
} else {
aElem.push(oTokenLocution);
}
iKey = iKey + aTokenTempList.length;
} else {
if (bInfo) {
let 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;
}
|