Grammalecte  Check-in [891500b92a]

Overview
Comment:[graphspell][fx] lexicographer update: same code for Python and JavaScript (remove deprecated code)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fx | graphspell | salxg
Files: files | file ages | folders
SHA3-256: 891500b92a4b12944293c70593356b6c0f48a8d5e62c5692133e56c6fcc7de35
User & Date: olr on 2020-09-10 13:15:03
Other Links: branch diff | manifest | tags
Context
2020-09-10
15:30
[core][graphspell][fx][cli] new lexicographer check-in: 4fdd6a9337 user: olr tags: trunk, cli, core, fx, graphspell
13:15
[graphspell][fx] lexicographer update: same code for Python and JavaScript (remove deprecated code) Closed-Leaf check-in: 891500b92a user: olr tags: fx, graphspell, salxg
12:17
[core][graphspell][fx][cli] lexicographer: update check-in: e0ce6b10d7 user: olr tags: cli, core, fx, graphspell, salxg
Changes
Hide Diffs Side-by-Side Diffs Ignore Whitespace Patch

Modified gc_lang/fr/webext/gce_worker.js from [e86439bcff] to [879c183120].

︙
240
241
242
243
244
245
246




247

248
249
250
251
252
253
254

240
241
242
243
244
245
246
247
248
249
250

251
252
253
254
255
256
257
258








+
+
+
+
-
+









function getListOfTokens (sText, oInfo={}) {
    // lexicographer
    try {
        sText = sText.replace(/­/g, "").normalize("NFC");
        for (let sParagraph of text.getParagraph(sText)) {
            if (sParagraph.trim() !== "") {
                let lTokens = [ ...oTokenizer.genTokens(sParagraph) ];
                for (let oToken of lTokens) {
                    oSpellChecker.setLabelsOnToken(oToken);
                }
                postMessage(createResponse("getListOfTokens", { sParagraph: sParagraph, lTokens: lexgraph_fr.getListOfTokens(sParagraph, true) }, oInfo, false));
                postMessage(createResponse("getListOfTokens", { sParagraph: sParagraph, lTokens: lTokens }, oInfo, false));
            }
        }
        postMessage(createResponse("getListOfTokens", null, oInfo, true));
    }
    catch (e) {
        console.error(e);
        postMessage(createResponse("getListOfTokens", createErrorResult(e, "no tokens"), oInfo, true, true));
︙

Modified graphspell-js/lexgraph_fr.js from [841b4146b0] to [816b039883].

︙
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

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








-
-
-
-



-
+


-
-
-
-
-
-
-





-
+








            ['>', "supérieur à"],
            ['⩽', "inférieur ou égal à"],
            ['⩾', "supérieur ou égal à"],
            ['%', "signe de pourcentage"],
            ['‰', "signe pour mille"],
        ]),

    oSpellChecker: null,
    oTokenizer: null,
    oLocGraph: null,

    _zPartDemForm: new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-(là|ci)$", "i"),
    _aPartDemExceptList: new Set(["celui", "celle", "ceux", "celles", "de", "jusque", "par", "marie-couche-toi"]),
    _zInterroVerb: new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)(-(?:t-(?:ie?l|elle|on)|je|tu|ie?ls?|elles?|on|[nv]ous))$", "i"),
    _zImperatifVerb: new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)(-(?:l(?:es?|a)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts][’'](?:y|en)|les?|la|[mt]oi|leur|lui))$", "i"),
    _zImperatifVerb: new RegExp("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)(-(?:l(?:es?|a)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts]['’ʼ‘‛´`′‵՚ꞌꞋ](?:y|en)|les?|la|[mt]oi|leur|lui))$", "i"),
    _zTag: new RegExp("[:;/][a-zA-Z0-9ÑÂĴĈŔÔṼŴ!][^:;/]*", "g"),


    load: function (oSpellChecker, oTokenizer, oLocGraph) {
        this.oSpellChecker = oSpellChecker;
        this.oTokenizer = oTokenizer;
        this.oLocGraph = JSON.parse(oLocGraph);
    },

    split: function (sWord) {
        // returns an arry of strings (prefix, trimed_word, suffix)
        let sPrefix = "";
        let sSuffix = "";
        // préfixe élidé
        let m = /^([ldmtsnjcç]|lorsqu|presqu|jusqu|puisqu|quoiqu|quelqu|qu)[’'‘`ʼ]([a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st-]+)/i.exec(sWord);
        let m = /^([ldmtsnjcç]|lorsqu|presqu|jusqu|puisqu|quoiqu|quelqu|qu)['’ʼ‘‛´`′‵՚ꞌꞋ]([a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st-]+)/i.exec(sWord);
        if (m) {
            sPrefix = m[1] + "’";
            sWord = m[2];
        }
        // mots composés
        m = /^([a-zA-Zà-öÀ-Ö0-9_ø-ÿØ-ßĀ-ʯfi-st]+)(-(?:(?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts]’(?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous|ce))$/i.exec(sWord);
        if (m) {
︙
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
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
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
778
779
780
781
782

544
545
546
547
548
549
550
















































































































































































































551
552
553
554
555
556
557
558
559
560
561
562
563








-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-














                    oToken["aLabels"] = ["token de nature inconnue"];
            }
        } catch (e) {
            console.error(e);
        }
    },

    getInfoForToken: function (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a object {sType, sValue, aLabels}
        let m = null;
        try {
            switch (oToken.sType) {
                case 'PUNC':
                case 'SIGN':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: [this.dValues.gl_get(oToken.sValue, "caractère indéterminé")]
                    };
                    break;
                case 'NUM':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["nombre"]
                    };
                    break;
                case 'LINK':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabels: ["hyperlien"]
                    };
                    break;
                case 'TAG':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["étiquette (hashtag)"]
                    };
                    break;
                case 'HTML':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabels: ["balise HTML"]
                    };
                    break;
                case 'PSEUDOHTML':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["balise pseudo-HTML"]
                    };
                    break;
                case 'HTMLENTITY':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["entité caractère XML/HTML"]
                    };
                    break;
                case 'HOUR':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["heure"]
                    };
                    break;
                case 'WORD_ELIDED':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: [this.dValues.gl_get(oToken.sValue.toLowerCase(), "préfixe élidé inconnu")]
                    };
                    break;
                case 'WORD_ORDINAL':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["nombre ordinal"]
                    };
                    break;
                case 'FOLDERUNIX':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabels: ["dossier UNIX (et dérivés)"]
                    };
                    break;
                case 'FOLDERWIN':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabels: ["dossier Windows"]
                    };
                    break;
                case 'WORD_ACRONYM':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["Sigle ou acronyme"]
                    };
                    break;
                case 'WORD':
                    if (oToken.sValue.gl_count("-") > 4) {
                        return {
                            sType: "COMPLEX",
                            sValue: oToken.sValue,
                            aLabels: ["élément complexe indéterminé"]
                        };
                    } else if (m = this._zPartDemForm.exec(oToken.sValue)) {
                        // mots avec particules démonstratives
                        if (this._aPartDemExceptList.has(m[1].toLowerCase())) {
                            return {
                                sType: "WORD",
                                sValue: oToken.sValue,
                                aLabels: this._getMorph(oToken.sValue)
                            };
                        }
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabels: ["mot avec particule démonstrative"],
                            lSubTokens: [
                                { sType: oToken.sType, sValue: m[1], aLabels: this._getMorph(m[1]) },
                                { sType: oToken.sType, sValue: m[2], aLabels: [ this._formatSuffix(m[2]) ] }
                            ]
                        };
                    } else if (m = this._zImperatifVerb.exec(oToken.sValue)) {
                        // formes interrogatives
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabels: ["forme verbale impérative"],
                            lSubTokens: [
                                { sType: oToken.sType, sValue: m[1], aLabels: this._getMorph(m[1]) },
                                { sType: oToken.sType, sValue: m[2], aLabels: [ this._formatSuffix(m[2]) ] }
                            ]
                        };
                    } else if (m = this._zInterroVerb.exec(oToken.sValue)) {
                        // formes interrogatives
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabels: ["forme verbale interrogative"],
                            lSubTokens: [
                                { sType: oToken.sType, sValue: m[1], aLabels: this._getMorph(m[1]) },
                                { sType: oToken.sType, sValue: m[2], aLabels: [ this._formatSuffix(m[2]) ] }
                            ]
                        };
                    } else if (this.oSpellChecker.isValidToken(oToken.sValue)) {
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabels: this._getMorph(oToken.sValue)
                        };
                    } else {
                        return {
                            sType: "UNKNOWN_WORD",
                            sValue: oToken.sValue,
                            aLabels: ["mot inconnu du dictionnaire"]
                        };
                    }
                    break;
                default:
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabels: ["token inconnu"]
                    }
            }
        } catch (e) {
            console.error(e);
        }
        return null;
    },

    _getMorph (sWord) {
        let aElem = [];
        for (let s of this.oSpellChecker.getMorph(sWord)) {
            if (s.includes(":")) aElem.push(this.readableMorph(s));
        }
        if (aElem.length == 0) {
            aElem.push("mot inconnu du dictionnaire");
        }
        return aElem;
    },

    _formatSuffix (sSuffix) {
        sSuffix = sSuffix.replace(/['’ʼ‘‛´`′‵՚ꞌꞋ]/g, "’").toLowerCase();
        if (this.dValues.has(sSuffix)) {
            return this.dValues.get(sSuffix);
        }
        return " suffixe inconnu";
    },

    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;
    },


    // Other functions

    filterSugg: function (aSugg) {
        return aSugg.filter((sSugg) => { return !sSugg.endsWith("è") && !sSugg.endsWith("È"); });
    }
}



if (typeof(exports) !== 'undefined') {
    exports.lexgraph_fr = lexgraph_fr;
}

Modified graphspell/lexgraph_fr.py from [60d5043aa3] to [f36c3bc666]. 

1
2
3
4
5
6
7
8
9
10
11
12

13
14
15
16
17
18
19

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20













+








"""
Lexicographer for the French language
"""

# Note:
# This mode must contains at least:
#     <dSugg> : a dictionary for default suggestions.
#     <bLexicographer> : a boolean False
#       if the boolean is True, 4 functions are required:
#           split(sWord) -> returns a list of string (that will be analyzed)
#           analyze(sWord) -> returns a string with the meaning of word
#           readableMorph(sMorph) -> returns a string with the meaning of tags
#           setLabelsOnToken(dToken) -> adds readable information on token
#           filterSugg(aWord) -> returns a filtered list of suggestions


import re

#### Suggestions
︙
415
416
417
418
419
420
421
422

423
424
425
426
427
428
429

416
417
418
419
420
421
422

423
424
425
426
427
428
429
430








-
+








    if not sRes:
        return " [" + sMorph + "]: étiquettes inconnues"
    return sRes.rstrip(",")


_zPartDemForm = re.compile("([\\w]+)-(là|ci)$")
_zInterroVerb = re.compile("([\\w]+)(-(?:t-(?:ie?l|elle|on)|je|tu|ie?ls?|elles?|on|[nv]ous))$")
_zImperatifVerb = re.compile("([\\w]+)(-(?:l(?:es?|a)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts][’'](?:y|en)|les?|la|[mt]oi|leur|lui))$")
_zImperatifVerb = re.compile("([\\w]+)(-(?:l(?:es?|a)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts]['’ʼ‘‛´`′‵՚ꞌꞋ](?:y|en)|les?|la|[mt]oi|leur|lui))$")

def setLabelsOnToken (dToken):
    # Token: .sType, .sValue, .nStart, .nEnd, .lMorph
    try:
        if dToken["sType"] == "PUNC" or dToken["sType"] == "SIGN":
            dToken["aLabels"] = [_dValues.get(dToken["sValue"], "signe de ponctuation divers")]
        elif dToken["sType"] == 'NUM':
︙
437
438
439
440
441
442
443
444

445
446
447
448
449
450
451

438
439
440
441
442
443
444

445
446
447
448
449
450
451
452








-
+








        elif dToken["sType"] == 'PSEUDOHTML':
            dToken["aLabels"] = ["balise pseudo-HTML"]
        elif dToken["sType"] == 'HTMLENTITY':
            dToken["aLabels"] = ["entité caractère XML/HTML"]
        elif dToken["sType"] == 'HOUR':
            dToken["aLabels"] = ["heure"]
        elif dToken["sType"] == 'WORD_ELIDED':
            dToken["aLabels"] = [_dValues.get(dToken["sValue"], "préfixe élidé inconnu")]
            dToken["aLabels"] = [_dValues.get(dToken["sValue"].lower(), "préfixe élidé inconnu")]
        elif dToken["sType"] == 'WORD_ORDINAL':
            dToken["aLabels"] = ["nombre ordinal"]
        elif dToken["sType"] == 'FOLDERUNIX':
            dToken["aLabels"] = ["dossier UNIX (et dérivés)"]
        elif dToken["sType"] == 'FOLDERWIN':
            dToken["aLabels"] = ["dossier Windows"]
        elif dToken["sType"] == 'WORD_ACRONYM':
︙

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.007s