| ︙ | | |
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
|
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
|
-
+
-
-
+
+
|
if (this.isValid(sToken)) {
return true;
}
if (sToken.includes("-")) {
if (sToken.gl_count("-") > 4) {
return true;
}
return sToken.split("-").every(sWord => this.isValid(sWord));
return sToken.split("-").every(sWord => this.isValid(sWord));
}
if (sToken.includes(".") || sToken.includes("·")) {
return true;
}
return false;
}
isValid (sWord) {
// checks if sWord is valid (different casing tested if the first letter is a capital)
if (!sWord) {
return null;
}
if (sWord.includes("’")) { // ugly hack
sWord = sWord.replace("’", "'");
if (sWord.includes("'")) { // ugly hack
sWord = sWord.replace("'", "’");
}
if (this.lookup(sWord)) {
return true;
}
if (sWord.charAt(0).gl_isUpperCase()) {
if (sWord.length > 1) {
if (sWord.gl_isTitle()) {
|
| ︙ | | |
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
|
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
|
-
+
|
if (!zTagsPattern || zTagsPattern.test(this.lArcVal[nMorphVal])) {
yield [sWord, sStem, this.lArcVal[nMorphVal]];
}
}
}
}
}
}
}
_morph1 (sWord) {
// returns morphologies of sWord
let iAddr = 0;
for (let c of sWord) {
if (!this.dChar.has(c)) {
return [];
|
| ︙ | | |
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
|
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
|
-
+
-
+
|
let l = [];
let nRawArc = 0;
while (!(nRawArc & this._lastArcMask)) {
let iEndArcAddr = iAddr + this.nBytesArc;
nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
let nArc = nRawArc & this._arcMask;
if (nArc > this.nChar) {
// This value is not a char, this is a stemming code
// This value is not a char, this is a stemming code
let sStem = ">" + this.funcStemming(sWord, this.lArcVal[nArc]);
// Now , we go to the next node and retrieve all following arcs values, all of them are tags
let iAddr2 = this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress));
let nRawArc2 = 0;
while (!(nRawArc2 & this._lastArcMask)) {
let iEndArcAddr2 = iAddr2 + this.nBytesArc;
nRawArc2 = this._convBytesToInteger(this.byDic.slice(iAddr2, iEndArcAddr2));
l.push(sStem + " " + this.lArcVal[nRawArc2 & this._arcMask]);
l.push(sStem + "/" + this.lArcVal[nRawArc2 & this._arcMask]);
iAddr2 = iEndArcAddr2+this.nBytesNodeAddress;
}
}
iAddr = iEndArcAddr + this.nBytesNodeAddress;
}
return l;
}
|
| ︙ | | |
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
|
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
|
-
+
-
+
|
let l = [];
let nRawArc = 0;
while (!(nRawArc & this._lastArcMask)) {
let iEndArcAddr = iAddr + this.nBytesArc;
nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
let nArc = nRawArc & this._arcMask;
if (nArc > this.nChar) {
// This value is not a char, this is a stemming code
// This value is not a char, this is a stemming code
l.push(this.funcStemming(sWord, this.lArcVal[nArc]));
}
iAddr = iEndArcAddr + this.nBytesNodeAddress;
}
return l;
}
return [];
}
_lookupArcNode1 (nVal, iAddr) {
// looks if nVal is an arc at the node at iAddr, if yes, returns address of next node else None
while (true) {
let iEndArcAddr = iAddr+this.nBytesArc;
let nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
if (nVal == (nRawArc & this._arcMask)) {
// the value we are looking for
// the value we are looking for
// we return the address of the next node
return this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress));
}
else {
// value not found
if (nRawArc & this._lastArcMask) {
return null;
|
| ︙ | | |