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
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
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
572
573
574
575
576
|
console.log(this.asString());
}
}
* _getNextPointers (dToken, dGraph, dPointer, bDebug=false) {
// generator: return nodes where <dToken> “values” match <dNode> arcs
try {
let dNode = dPointer["dNode"];
let iNode1 = dPointer["iNode1"];
let bTokenFound = false;
// token value
if (dNode.hasOwnProperty(dToken["sValue"])) {
if (bDebug) {
console.log(" MATCH: " + dToken["sValue"]);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode[dToken["sValue"]]] };
bTokenFound = true;
}
if (dToken["sValue"].slice(0,2).gl_isTitle()) { // we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
let sValue = dToken["sValue"].toLowerCase();
if (dNode.hasOwnProperty(sValue)) {
if (bDebug) {
console.log(" MATCH: " + sValue);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode[sValue]] };
bTokenFound = true;
}
}
else if (dToken["sValue"].gl_isUpperCase()) {
let sValue = dToken["sValue"].toLowerCase();
if (dNode.hasOwnProperty(sValue)) {
if (bDebug) {
console.log(" MATCH: " + sValue);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode[sValue]] };
bTokenFound = true;
}
sValue = dToken["sValue"].gl_toCapitalize();
if (dNode.hasOwnProperty(sValue)) {
if (bDebug) {
console.log(" MATCH: " + sValue);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode[sValue]] };
bTokenFound = true;
}
}
// regex value arcs
if (dToken["sType"] != "INFO" && dToken["sType"] != "PUNC" && dToken["sType"] != "SIGN") {
if (dNode.hasOwnProperty("<re_value>")) {
for (let sRegex in dNode["<re_value>"]) {
if (!sRegex.includes("¬")) {
// no anti-pattern
if (dToken["sValue"].search(sRegex) !== -1) {
if (bDebug) {
console.log(" MATCH: ~" + sRegex);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_value>"][sRegex]] };
bTokenFound = true;
}
} else {
// there is an anti-pattern
let [sPattern, sNegPattern] = sRegex.split("¬", 2);
if (sNegPattern && dToken["sValue"].search(sNegPattern) !== -1) {
continue;
}
if (!sPattern || dToken["sValue"].search(sPattern) !== -1) {
if (bDebug) {
console.log(" MATCH: ~" + sRegex);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_value>"][sRegex]] };
bTokenFound = true;
}
}
}
}
}
// analysable tokens
if (dToken["sType"].slice(0,4) == "WORD") {
// token lemmas
if (dNode.hasOwnProperty("<lemmas>")) {
for (let sLemma of _oSpellChecker.getLemma(dToken["sValue"])) {
if (dNode["<lemmas>"].hasOwnProperty(sLemma)) {
if (bDebug) {
console.log(" MATCH: >" + sLemma);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<lemmas>"][sLemma]] };
bTokenFound = true;
}
}
}
// regex morph arcs
if (dNode.hasOwnProperty("<re_morph>")) {
let lMorph = (dToken.hasOwnProperty("lMorph")) ? dToken["lMorph"] : _oSpellChecker.getMorph(dToken["sValue"]);
for (let sRegex in dNode["<re_morph>"]) {
if (!sRegex.includes("¬")) {
// no anti-pattern
if (lMorph.some(sMorph => (sMorph.search(sRegex) !== -1))) {
if (bDebug) {
console.log(" MATCH: @" + sRegex);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] };
bTokenFound = true;
}
} else {
// there is an anti-pattern
let [sPattern, sNegPattern] = sRegex.split("¬", 2);
if (sNegPattern == "*") {
// all morphologies must match with <sPattern>
if (sPattern) {
if (lMorph.length > 0 && lMorph.every(sMorph => (sMorph.search(sPattern) !== -1))) {
if (bDebug) {
console.log(" MATCH: @" + sRegex);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] };
bTokenFound = true;
}
}
} else {
if (sNegPattern && lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) {
continue;
}
if (!sPattern || lMorph.some(sMorph => (sMorph.search(sPattern) !== -1))) {
if (bDebug) {
console.log(" MATCH: @" + sRegex);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] };
bTokenFound = true;
}
}
}
}
}
}
// token tags
if (dToken.hasOwnProperty("aTags") && dNode.hasOwnProperty("<tags>")) {
for (let sTag of dToken["aTags"]) {
if (dNode["<tags>"].hasOwnProperty(sTag)) {
if (bDebug) {
console.log(" MATCH: /" + sTag);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<tags>"][sTag]] };
bTokenFound = true;
}
}
}
// meta arc (for token type)
if (dNode.hasOwnProperty("<meta>")) {
for (let sMeta in dNode["<meta>"]) {
// no regex here, we just search if <dNode["sType"]> exists within <sMeta>
if (sMeta == "*" || dToken["sType"] == sMeta) {
if (bDebug) {
console.log(" MATCH: *" + sMeta);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<meta>"][sMeta]] };
bTokenFound = true;
}
else if (sMeta.includes("¬")) {
if (!sMeta.includes(dToken["sType"])) {
if (bDebug) {
console.log(" MATCH: *" + sMeta);
}
yield { "iNode1": iNode1, "dNode": dGraph[dNode["<meta>"][sMeta]] };
bTokenFound = true;
}
}
}
}
if (!bTokenFound && dPointer.hasOwnProperty("bKeep")) {
yield dPointer;
}
// JUMP
// Warning! Recurssion!
if (dNode.hasOwnProperty("<>")) {
let dPointer2 = { "iNode1": iNode1, "dNode": dGraph[dNode["<>"]], "bKeep": true };
yield* this._getNextPointers(dToken, dGraph, dPointer2, bDebug);
}
}
catch (e) {
console.error(e);
}
}
|
|
|
|
|
|
|
|
|
|
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>
|
|
|
|
|
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
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
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
572
573
574
575
576
577
578
|
console.log(this.asString());
}
}
* _getNextPointers (dToken, dGraph, dPointer, bDebug=false) {
// generator: return nodes where <dToken> “values” match <dNode> arcs
try {
let dNode = dGraph[dPointer["iNode"]];
let iToken1 = dPointer["iToken1"];
let bTokenFound = false;
// token value
if (dNode.hasOwnProperty(dToken["sValue"])) {
if (bDebug) {
console.log(" MATCH: " + dToken["sValue"]);
}
yield { "iToken1": iToken1, "iNode": dNode[dToken["sValue"]] };
bTokenFound = true;
}
if (dToken["sValue"].slice(0,2).gl_isTitle()) { // we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
let sValue = dToken["sValue"].toLowerCase();
if (dNode.hasOwnProperty(sValue)) {
if (bDebug) {
console.log(" MATCH: " + sValue);
}
yield { "iToken1": iToken1, "iNode": dNode[sValue] };
bTokenFound = true;
}
}
else if (dToken["sValue"].gl_isUpperCase()) {
let sValue = dToken["sValue"].toLowerCase();
if (dNode.hasOwnProperty(sValue)) {
if (bDebug) {
console.log(" MATCH: " + sValue);
}
yield { "iToken1": iToken1, "iNode": dNode[sValue] };
bTokenFound = true;
}
sValue = dToken["sValue"].gl_toCapitalize();
if (dNode.hasOwnProperty(sValue)) {
if (bDebug) {
console.log(" MATCH: " + sValue);
}
yield { "iToken1": iToken1, "iNode": dNode[sValue] };
bTokenFound = true;
}
}
// regex value arcs
if (dToken["sType"] != "INFO" && dToken["sType"] != "PUNC" && dToken["sType"] != "SIGN") {
if (dNode.hasOwnProperty("<re_value>")) {
for (let sRegex in dNode["<re_value>"]) {
if (!sRegex.includes("¬")) {
// no anti-pattern
if (dToken["sValue"].search(sRegex) !== -1) {
if (bDebug) {
console.log(" MATCH: ~" + sRegex);
}
yield { "iToken1": iToken1, "iNode": dNode["<re_value>"][sRegex] };
bTokenFound = true;
}
} else {
// there is an anti-pattern
let [sPattern, sNegPattern] = sRegex.split("¬", 2);
if (sNegPattern && dToken["sValue"].search(sNegPattern) !== -1) {
continue;
}
if (!sPattern || dToken["sValue"].search(sPattern) !== -1) {
if (bDebug) {
console.log(" MATCH: ~" + sRegex);
}
yield { "iToken1": iToken1, "iNode": dNode["<re_value>"][sRegex] };
bTokenFound = true;
}
}
}
}
}
// analysable tokens
if (dToken["sType"].slice(0,4) == "WORD") {
// token lemmas
if (dNode.hasOwnProperty("<lemmas>")) {
for (let sLemma of _oSpellChecker.getLemma(dToken["sValue"])) {
if (dNode["<lemmas>"].hasOwnProperty(sLemma)) {
if (bDebug) {
console.log(" MATCH: >" + sLemma);
}
yield { "iToken1": iToken1, "iNode": dNode["<lemmas>"][sLemma] };
bTokenFound = true;
}
}
}
// regex morph arcs
if (dNode.hasOwnProperty("<re_morph>")) {
let lMorph = (dToken.hasOwnProperty("lMorph")) ? dToken["lMorph"] : _oSpellChecker.getMorph(dToken["sValue"]);
if (lMorph.length > 0) {
for (let sRegex in dNode["<re_morph>"]) {
if (!sRegex.includes("¬")) {
// no anti-pattern
if (lMorph.some(sMorph => (sMorph.search(sRegex) !== -1))) {
if (bDebug) {
console.log(" MATCH: @" + sRegex);
}
yield { "iToken1": iToken1, "iNode": dNode["<re_morph>"][sRegex] };
bTokenFound = true;
}
} else {
// there is an anti-pattern
let [sPattern, sNegPattern] = sRegex.split("¬", 2);
if (sNegPattern == "*") {
// all morphologies must match with <sPattern>
if (sPattern) {
if (lMorph.every(sMorph => (sMorph.search(sPattern) !== -1))) {
if (bDebug) {
console.log(" MATCH: @" + sRegex);
}
yield { "iToken1": iToken1, "iNode": dNode["<re_morph>"][sRegex] };
bTokenFound = true;
}
}
} else {
if (sNegPattern && lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) {
continue;
}
if (!sPattern || lMorph.some(sMorph => (sMorph.search(sPattern) !== -1))) {
if (bDebug) {
console.log(" MATCH: @" + sRegex);
}
yield { "iToken1": iToken1, "iNode": dNode["<re_morph>"][sRegex] };
bTokenFound = true;
}
}
}
}
}
}
}
// token tags
if (dToken.hasOwnProperty("aTags") && dNode.hasOwnProperty("<tags>")) {
for (let sTag of dToken["aTags"]) {
if (dNode["<tags>"].hasOwnProperty(sTag)) {
if (bDebug) {
console.log(" MATCH: /" + sTag);
}
yield { "iToken1": iToken1, "iNode": dNode["<tags>"][sTag] };
bTokenFound = true;
}
}
}
// meta arc (for token type)
if (dNode.hasOwnProperty("<meta>")) {
for (let sMeta in dNode["<meta>"]) {
// no regex here, we just search if <dNode["sType"]> exists within <sMeta>
if (sMeta == "*" || dToken["sType"] == sMeta) {
if (bDebug) {
console.log(" MATCH: *" + sMeta);
}
yield { "iToken1": iToken1, "iNode": dNode["<meta>"][sMeta] };
bTokenFound = true;
}
else if (sMeta.includes("¬")) {
if (!sMeta.includes(dToken["sType"])) {
if (bDebug) {
console.log(" MATCH: *" + sMeta);
}
yield { "iToken1": iToken1, "iNode": dNode["<meta>"][sMeta] };
bTokenFound = true;
}
}
}
}
if (!bTokenFound && dPointer.hasOwnProperty("bKeep")) {
yield dPointer;
}
// JUMP
// Warning! Recurssion!
if (dNode.hasOwnProperty("<>")) {
let dPointer2 = { "iToken1": iToken1, "iNode": dNode["<>"], "bKeep": true };
yield* this._getNextPointers(dToken, dGraph, dPointer2, bDebug);
}
}
catch (e) {
console.error(e);
}
}
|
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
|
// check arcs for each existing pointer
let lNextPointer = [];
for (let dPointer of lPointer) {
lNextPointer.push(...this._getNextPointers(dToken, dGraph, dPointer, bDebug));
}
lPointer = lNextPointer;
// check arcs of first nodes
lPointer.push(...this._getNextPointers(dToken, dGraph, { "iNode1": iToken, "dNode": dGraph[0] }, bDebug));
// check if there is rules to check for each pointer
for (let dPointer of lPointer) {
if (dPointer["dNode"].hasOwnProperty("<rules>")) {
let bChange = this._executeActions(dGraph, dPointer["dNode"]["<rules>"], dPointer["iNode1"]-1, iToken, dOptions, sCountry, bShowRuleId, bDebug, bContext);
if (bChange) {
bTagAndRewrite = true;
}
}
}
}
} catch (e) {
|
|
|
|
|
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
|
// check arcs for each existing pointer
let lNextPointer = [];
for (let dPointer of lPointer) {
lNextPointer.push(...this._getNextPointers(dToken, dGraph, dPointer, bDebug));
}
lPointer = lNextPointer;
// check arcs of first nodes
lPointer.push(...this._getNextPointers(dToken, dGraph, { "iToken1": iToken, "iNode": 0 }, bDebug));
// check if there is rules to check for each pointer
for (let dPointer of lPointer) {
if (dGraph[dPointer["iNode"]].hasOwnProperty("<rules>")) {
let bChange = this._executeActions(dGraph, dGraph[dPointer["iNode"]]["<rules>"], dPointer["iToken1"]-1, iToken, dOptions, sCountry, bShowRuleId, bDebug, bContext);
if (bChange) {
bTagAndRewrite = true;
}
}
}
}
} catch (e) {
|