Grammalecte  Diff

Differences From Artifact [418e2031a5]:

To Artifact [53ea8f6dbf]:


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
590
591
592


593
594
595
596

597
598
599
600



601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619

620
621
622

623
624

625
626
627
628
629
630
631
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
590


591
592
593
594
595

596
597



598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618

619
620
621

622
623

624
625
626
627
628
629
630
631







-
-
+
+

-
-
+
+


-
+



-
+




-
+



-
+





-
+



-
+



-
+



-
+





-
-
+
+






-
+












-
+









-
+

-
+



-
+





-
+


-
+






-
+












-
+











-
+









-
+

-
+



-
+





-
-
-
+
+
+




-
+







-
+





-
-
+
+



-
-
-
+
+
+







-
+










-
-
+
+



-
+

-
-
-
+
+
+


















-
+


-
+

-
+







        }
        if (bDebug) {
            console.log("UPDATE:");
            console.log(this.asString());
        }
    }

    * _getNextPointers (dToken, dGraph, dPointer, bDebug=false) {
        // generator: return nodes where <dToken> “values” match <dNode> arcs
    * _getNextPointers (dToken, oGraph, oPointer, bDebug=false) {
        // generator: return nodes where <dToken> “values” match <oNode> arcs
        try {
            let dNode = dGraph[dPointer["iNode"]];
            let iToken1 = dPointer["iToken1"];
            let oNode = oGraph[oPointer["iNode"]];
            let iToken1 = oPointer["iToken1"];
            let bTokenFound = false;
            // token value
            if (dNode.hasOwnProperty(dToken["sValue"])) {
            if (oNode.hasOwnProperty(dToken["sValue"])) {
                if (bDebug) {
                    console.log("  MATCH: " + dToken["sValue"]);
                }
                yield { "iToken1": iToken1, "iNode": dNode[dToken["sValue"]] };
                yield { "iToken1": iToken1, "iNode": oNode[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 (oNode.hasOwnProperty(sValue)) {
                    if (bDebug) {
                        console.log("  MATCH: " + sValue);
                    }
                    yield { "iToken1": iToken1, "iNode": dNode[sValue] };
                    yield { "iToken1": iToken1, "iNode": oNode[sValue] };
                    bTokenFound = true;
                }
            }
            else if (dToken["sValue"].gl_isUpperCase()) {
                let sValue = dToken["sValue"].toLowerCase();
                if (dNode.hasOwnProperty(sValue)) {
                if (oNode.hasOwnProperty(sValue)) {
                    if (bDebug) {
                        console.log("  MATCH: " + sValue);
                    }
                    yield { "iToken1": iToken1, "iNode": dNode[sValue] };
                    yield { "iToken1": iToken1, "iNode": oNode[sValue] };
                    bTokenFound = true;
                }
                sValue = dToken["sValue"].gl_toCapitalize();
                if (dNode.hasOwnProperty(sValue)) {
                if (oNode.hasOwnProperty(sValue)) {
                    if (bDebug) {
                        console.log("  MATCH: " + sValue);
                    }
                    yield { "iToken1": iToken1, "iNode": dNode[sValue] };
                    yield { "iToken1": iToken1, "iNode": oNode[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 (oNode.hasOwnProperty("<re_value>")) {
                    for (let sRegex in oNode["<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] };
                                yield { "iToken1": iToken1, "iNode": oNode["<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] };
                                yield { "iToken1": iToken1, "iNode": oNode["<re_value>"][sRegex] };
                                bTokenFound = true;
                            }
                        }
                    }
                }
            }
            // analysable tokens
            if (dToken["sType"].slice(0,4) == "WORD") {
                // token lemmas
                if (dNode.hasOwnProperty("<lemmas>")) {
                if (oNode.hasOwnProperty("<lemmas>")) {
                    for (let sLemma of _oSpellChecker.getLemma(dToken["sValue"])) {
                        if (dNode["<lemmas>"].hasOwnProperty(sLemma)) {
                        if (oNode["<lemmas>"].hasOwnProperty(sLemma)) {
                            if (bDebug) {
                                console.log("  MATCH: >" + sLemma);
                            }
                            yield { "iToken1": iToken1, "iNode": dNode["<lemmas>"][sLemma] };
                            yield { "iToken1": iToken1, "iNode": oNode["<lemmas>"][sLemma] };
                            bTokenFound = true;
                        }
                    }
                }
                // regex morph arcs
                if (dNode.hasOwnProperty("<re_morph>")) {
                if (oNode.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>"]) {
                        for (let sRegex in oNode["<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] };
                                    yield { "iToken1": iToken1, "iNode": oNode["<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] };
                                            yield { "iToken1": iToken1, "iNode": oNode["<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] };
                                        yield { "iToken1": iToken1, "iNode": oNode["<re_morph>"][sRegex] };
                                        bTokenFound = true;
                                    }
                                }
                            }
                        }
                    }
                }
            }
            // token tags
            if (dToken.hasOwnProperty("aTags") && dNode.hasOwnProperty("<tags>")) {
            if (dToken.hasOwnProperty("aTags") && oNode.hasOwnProperty("<tags>")) {
                for (let sTag of dToken["aTags"]) {
                    if (dNode["<tags>"].hasOwnProperty(sTag)) {
                    if (oNode["<tags>"].hasOwnProperty(sTag)) {
                        if (bDebug) {
                            console.log("  MATCH: /" + sTag);
                        }
                        yield { "iToken1": iToken1, "iNode": dNode["<tags>"][sTag] };
                        yield { "iToken1": iToken1, "iNode": oNode["<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 (oNode.hasOwnProperty("<meta>")) {
                for (let sMeta in oNode["<meta>"]) {
                    // no regex here, we just search if <oNode["sType"]> exists within <sMeta>
                    if (sMeta == "*" || dToken["sType"] == sMeta) {
                        if (bDebug) {
                            console.log("  MATCH: *" + sMeta);
                        }
                        yield { "iToken1": iToken1, "iNode": dNode["<meta>"][sMeta] };
                        yield { "iToken1": iToken1, "iNode": oNode["<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] };
                            yield { "iToken1": iToken1, "iNode": oNode["<meta>"][sMeta] };
                            bTokenFound = true;
                        }
                    }
                }
            }
            if (!bTokenFound  &&  dPointer.hasOwnProperty("bKeep")) {
                yield dPointer;
            if (!bTokenFound  &&  oPointer.hasOwnProperty("bKeep")) {
                yield oPointer;
            }
            // JUMP
            // Warning! Recurssion!
            if (dNode.hasOwnProperty("<>")) {
                let dPointer2 = { "iToken1": iToken1, "iNode": dNode["<>"], "bKeep": true };
                yield* this._getNextPointers(dToken, dGraph, dPointer2, bDebug);
            if (oNode.hasOwnProperty("<>")) {
                let oPointer2 = { "iToken1": iToken1, "iNode": oNode["<>"], "bKeep": true };
                yield* this._getNextPointers(dToken, oGraph, oPointer2, bDebug);
            }
        }
        catch (e) {
            console.error(e);
        }
    }

    parseGraph (dGraph, sCountry="${country_default}", dOptions=null, bShowRuleId=false, bDebug=false, bContext=false) {
    parseGraph (oGraph, sCountry="${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] 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));
                for (let oPointer of lPointer) {
                    lNextPointer.push(...this._getNextPointers(dToken, oGraph, oPointer, bDebug));
                }
                lPointer = lNextPointer;
                // check arcs of first nodes
                lPointer.push(...this._getNextPointers(dToken, dGraph, { "iToken1": iToken, "iNode": 0 }, bDebug));
                lPointer.push(...this._getNextPointers(dToken, oGraph, { "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);
                for (let oPointer of lPointer) {
                    if (oGraph[oPointer["iNode"]].hasOwnProperty("<rules>")) {
                        let bChange = this._executeActions(oGraph, oGraph[oPointer["iNode"]]["<rules>"], oPointer["iToken1"]-1, iToken, dOptions, sCountry, bShowRuleId, bDebug, bContext);
                        if (bChange) {
                            bTagAndRewrite = true;
                        }
                    }
                }
            }
        } catch (e) {
            console.error(e);
        }
        if (bTagAndRewrite) {
            this.rewriteFromTags(bDebug);
        }
        if (bDebug) {
            console.log(this.asString());
        }
        return this.sSentence;
    }

    _executeActions (dGraph, dNode, nTokenOffset, nLastToken, dOptions, sCountry, bShowRuleId, bDebug, bContext) {
    _executeActions (oGraph, oNode, nTokenOffset, nLastToken, dOptions, sCountry, bShowRuleId, bDebug, bContext) {
        // execute actions found in the DARG
        let bChange = false;
        for (let [sLineId, nextNodeKey] of Object.entries(dNode)) {
        for (let [sLineId, nextNodeKey] of Object.entries(oNode)) {
            let bCondMemo = null;
            for (let sRuleId of dGraph[nextNodeKey]) {
            for (let sRuleId of oGraph[nextNodeKey]) {
                try {
                    if (bDebug) {
                        console.log("   >TRY: " + sRuleId + " " + sLineId);
                    }
                    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 ]