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
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
579
580
581
582
583
584
|
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
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
579
580
581
582
583
584
585
586
587
588
589
|
-
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
+
-
-
-
-
+
-
-
-
-
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
-
+
|
}
if (bDebug) {
console.log("UPDATE:");
console.log(this.asString());
}
}
* _getNextPointers (self, dToken, dGraph, dPointer, bDebug=false) {
* _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("¬", 1);
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>")) {
for (let sRegex in dNode["<re_morph>"]) {
if (!sRegex.includes("¬")) {
// no anti-pattern
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("¬", 1);
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
let lMorph = dToken._get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]));
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("¬", 1);
if (sNegPattern == "*") {
// all morphologies must match with <sPattern>
if (sPattern) {
let lMorph = dToken.gl_get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]));
if (lMorph.length > 0 && lMorph.every(sMorph => (sMorph.search(sPattern) !== -1))) {
} else {
let lMorph = dToken.gl_get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]));
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("tags") && dNode.hasOwnProperty("<tags>")) {
for (let sTag in dToken["tags"]) {
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 (!bTokenFound && dPointer.hasOwnProperty("bKeep")) {
yield dPointer;
}
// JUMP
// Warning! Recurssion!
if (dNode.hasOwnPropertys("<>")) {
let dPointer2 = { "iNode1": iNode1, "dNode": dGraph[dNode["<>"]], "bKeep": True };
yield* this._getNextPointers(dToken, dGraph, dPointer2, bDebug);
}
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);
}
}
parseGraph (dGraph, sCountry="${country_default}", dOptions=null, bShowRuleId=false, bDebug=false, bContext=false) {
// parse graph with tokens from the text and execute actions encountered
let lPointer = [];
let bTagAndRewrite = false;
try {
for (let [iToken, dToken] in this.lToken.entries()) {
if (bDebug) {
console.log("TOKEN: " + dToken["sValue"]);
}
// 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) {
for (let [iToken, dToken] of this.lToken.entries()) {
if (bDebug) {
console.log("TOKEN: " + dToken["sValue"]);
}
// 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 bDebug:
// console.log("+", dPointer);
if (dPointer["dNode"].hasOwnProperty("<rules>")) {
let bChange = this._executeActions(dGraph, dPointer["dNode"]["<rules>"], dPointer["iNode1"]-1, iToken, dOpt, sCountry, bShowRuleId, bDebug, bContext);
if (bChange) {
bTagAndRewrite = true;
}
}
}
for (let sRuleId in dGraph[nextNodeKey]) {
for (let sRuleId of dGraph[nextNodeKey]) {
try {
if (bDebug) {
console.log(" >TRY: " + sRuleId);
}
let [sOption, sFuncCond, cActionType, sWhat, ...eAct] = gc_rules_graph.dRule[sRuleId];
// Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ]
// TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ]
|
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
|
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
|
-
+
-
+
-
+
-
+
-
+
-
-
-
+
+
+
-
+
-
+
|
if (bShowRuleId) {
sMessage += " ## " + sLineId + " # " + sRuleId;
}
//
return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext);
}
_createErrorFromTokens (self, sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) {
_createErrorFromTokens (sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) {
// suggestions
let lSugg = [];
if (sSugg.startsWith("=")) {
sSugg = oEvalFunc[sSugg.slice(1)](self.lToken, nTokenOffset, nLastToken);
sSugg = oEvalFunc[sSugg.slice(1)](this.lToken, nTokenOffset, nLastToken);
lSugg = (sSugg) ? sSugg.split("|") : [];
} else if (sSugg == "_") {
lSugg = [];
} else {
lSugg = self._expand(sSugg, nTokenOffset, nLastToken).split("|");
lSugg = this._expand(sSugg, nTokenOffset, nLastToken).split("|");
}
if (bCaseSvty && lSugg.length > 0 && self.lToken[iFirstToken]["sValue"].slice(0,1).isupper()) {
if (bCaseSvty && lSugg.length > 0 && this.lToken[iFirstToken]["sValue"].slice(0,1).isupper()) {
lSugg = capitalizeArray(lSugg);
}
// Message
let sMessage = (sMsg.startsWith("=")) ? oEvalFunc[sMsg.slice(1)](self.lToken, nTokenOffset, nLastToken) : self._expand(sMsg, nTokenOffset, nLastToken);
let sMessage = (sMsg.startsWith("=")) ? oEvalFunc[sMsg.slice(1)](this.lToken, nTokenOffset, nLastToken) : this._expand(sMsg, nTokenOffset, nLastToken);
if (bShowRuleId) {
sMessage += " ## " + sLineId + " # " + sRuleId;
}
//
return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext);
}
_createError (nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) {
let oErr = {
"nStart": nStart,
"nEnd": nEnd,
"sLineId": sLineId,
"sRuleId": sRuleId,
"sType": sOption || "notype",
"sMessage": sMessage,
"aSuggestions": lSugg,
"URL": sURL
}
if (bContext) {
oErr['sUnderlined'] = self.sText0.slice(nStart, nEnd);
oErr['sBefore'] = self.sText0.slice(Math.max(0,nStart-80), nStart);
oErr['sAfter'] = self.sText0.slice(nEnd, nEnd+80);
oErr['sUnderlined'] = this.sText0.slice(nStart, nEnd);
oErr['sBefore'] = this.sText0.slice(Math.max(0,nStart-80), nStart);
oErr['sAfter'] = this.sText0.slice(nEnd, nEnd+80);
}
return oErr;
}
_expand (sText, nTokenOffset, nLastToken) {
let m;
while ((m = /\\(-?[0-9]+)/.exec(sText)) !== null) {
if (m[1].slice(0,1) == "-") {
sText = sText.replace(m[0], self.lToken[nLastToken+parseInt(m[1],10)+1]["sValue"]);
sText = sText.replace(m[0], this.lToken[nLastToken+parseInt(m[1],10)+1]["sValue"]);
} else {
sText = sText.replace(m[0], self.lToken[nTokenOffset+parseInt(m[1],10)]["sValue"]);
sText = sText.replace(m[0], this.lToken[nTokenOffset+parseInt(m[1],10)]["sValue"]);
}
}
return sText;
}
rewriteText (sText, sRepl, iGroup, m, bUppercase) {
// text processor: write sRepl in sText at iGroup position"
|