Grammalecte  Check-in [1975bd1394]

Overview
Comment:[core][js] code clarification: separate specific inner functions from gc engine core
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | core
Files: files | file ages | folders
SHA3-256: 1975bd13944a5a19bdfb760e3a1a8f93a363d53dd253b042a012cd5cc98b1d05
User & Date: olr on 2020-08-19 15:53:49
Other Links: manifest | tags
Context
2020-08-19
15:57
[graphspell][js] remove importation dirt... check-in: 48d2a67a6a user: olr tags: trunk, graphspell
15:53
[core][js] code clarification: separate specific inner functions from gc engine core check-in: 1975bd1394 user: olr tags: trunk, core
15:11
[core][py] code clarification: separate specific inner functions from gc engine core check-in: 0b126eb254 user: olr tags: trunk, core
Changes

Modified gc_core/js/lang_core/gc_engine.js from [a87347cf36] to [1328582cce].

1
2
3
4
5
6
7

8
9
10
11
12
13
14
15


16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
// Grammar checker engine

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console */

"use strict";


${string}
${regex}
${map}


if (typeof(process) !== 'undefined') {
    // NodeJS


    var gc_options = require("./gc_options.js");
    var gc_rules = require("./gc_rules.js");
    var gc_rules_graph = require("./gc_rules_graph.js");
    var cregex = require("./cregex.js");
    var text = require("../text.js");
}


function capitalizeArray (aArray) {
    // can’t map on user defined function??
    let aNew = [];
    for (let i = 0; i < aArray.length; i = i + 1) {
        aNew[i] = aArray[i].slice(0,1).toUpperCase() + aArray[i].slice(1);
    }
    return aNew;
}

function echo (x) {
    console.log(x);
    return true;
}

var _sAppContext = "";

var gc_engine = {

    //// Informations

    lang: "${lang}",
    locales: ${loc},







>








>
>

















<
<
<
<
<
<







1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35






36
37
38
39
40
41
42
// Grammar checker engine

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console */

"use strict";


${string}
${regex}
${map}


if (typeof(process) !== 'undefined') {
    // NodeJS
    var spellchecker = require("../graphspell/spellchecker.js");
    var gc_functions = require("./gc_functions.js");
    var gc_options = require("./gc_options.js");
    var gc_rules = require("./gc_rules.js");
    var gc_rules_graph = require("./gc_rules_graph.js");
    var cregex = require("./cregex.js");
    var text = require("../text.js");
}


function capitalizeArray (aArray) {
    // can’t map on user defined function??
    let aNew = [];
    for (let i = 0; i < aArray.length; i = i + 1) {
        aNew[i] = aArray[i].slice(0,1).toUpperCase() + aArray[i].slice(1);
    }
    return aNew;
}








var gc_engine = {

    //// Informations

    lang: "${lang}",
    locales: ${loc},
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71

72
73
74
75
76
77
78
    aIgnoredRules: new Set(),
    oOptionsColors: null,

    //// Initialization

    load: function (sContext="JavaScript", sColorType="aRGB", sPath="") {
        try {
            _sAppContext = sContext;
            if (typeof(process) !== 'undefined') {
                var spellchecker = require("../graphspell/spellchecker.js");
                this.oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            } else {
                this.oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            }
            this.oSpellChecker.activateStorage();
            this.oTokenizer = this.oSpellChecker.getTokenizer();

            gc_options.load(sContext)
            this.oOptionsColors = gc_options.getOptionsColors(sContext, sColorType);
        }
        catch (e) {
            console.error(e);
        }
    },







<

<






>







53
54
55
56
57
58
59

60

61
62
63
64
65
66
67
68
69
70
71
72
73
74
    aIgnoredRules: new Set(),
    oOptionsColors: null,

    //// Initialization

    load: function (sContext="JavaScript", sColorType="aRGB", sPath="") {
        try {

            if (typeof(process) !== 'undefined') {

                this.oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            } else {
                this.oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            }
            this.oSpellChecker.activateStorage();
            this.oTokenizer = this.oSpellChecker.getTokenizer();
            gc_functions.load(sContext, this.oSpellChecker);
            gc_options.load(sContext)
            this.oOptionsColors = gc_options.getOptionsColors(sContext, sColorType);
        }
        catch (e) {
            console.error(e);
        }
    },
298
299
300
301
302
303
304

305
306
307
308
309
310
311
312
                for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
                    if (!gc_engine.aIgnoredRules.has(sRuleId)) {
                        while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) {
                            let bCondMemo = null;
                            for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) {
                                // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try {

                                    bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](sText, sText0, m, this.dTokenPos, sCountry, bCondMemo));
                                    if (bCondMemo) {
                                        switch (cActionType) {
                                            case "-":
                                                // grammar error
                                                //console.log("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source);
                                                let nErrorStart = nOffset + m.start[eAct[0]];
                                                if (!this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart)) {







>
|







294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
                for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
                    if (!gc_engine.aIgnoredRules.has(sRuleId)) {
                        while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) {
                            let bCondMemo = null;
                            for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) {
                                // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try {
                                    bCondMemo = (!sFuncCond || gc_functions[sFuncCond](sText, sText0, m, this.dTokenPos, sCountry, bCondMemo));
                                    //bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](sText, sText0, m, this.dTokenPos, sCountry, bCondMemo));
                                    if (bCondMemo) {
                                        switch (cActionType) {
                                            case "-":
                                                // grammar error
                                                //console.log("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source);
                                                let nErrorStart = nOffset + m.start[eAct[0]];
                                                if (!this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart)) {
323
324
325
326
327
328
329

330
331
332
333
334
335
336
337
                                                if (bDebug) {
                                                    console.log("~ " + sText + "  -- " + m[eAct[0]] + "  # " + sLineId);
                                                }
                                                break;
                                            case "=":
                                                // disambiguation
                                                //console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);

                                                oEvalFunc[sWhat](sText, m, this.dTokenPos);
                                                if (bDebug) {
                                                    console.log("= " + m[0] + "  # " + sLineId, "\nDA:", this.dTokenPos);
                                                }
                                                break;
                                            case ">":
                                                // we do nothing, this test is just a condition to apply all following actions
                                                break;







>
|







320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
                                                if (bDebug) {
                                                    console.log("~ " + sText + "  -- " + m[eAct[0]] + "  # " + sLineId);
                                                }
                                                break;
                                            case "=":
                                                // disambiguation
                                                //console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
                                                gc_functions[sWhat](sText, m, this.dTokenPos);
                                                //oEvalFunc[sWhat](sText, m, this.dTokenPos);
                                                if (bDebug) {
                                                    console.log("= " + m[0] + "  # " + sLineId, "\nDA:", this.dTokenPos);
                                                }
                                                break;
                                            case ">":
                                                // we do nothing, this test is just a condition to apply all following actions
                                                break;
666
667
668
669
670
671
672

673
674
675
676
677
678
679
680
                    // Suggestion    [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, iURL ]
                    // TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ]
                    // Disambiguator [ option, condition, "=", replacement/suggestion/action ]
                    // Tag           [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
                    // Immunity      [ option, condition, "!", "",                            iTokenStart, iTokenEnd ]
                    // Test          [ option, condition, ">", "" ]
                    if (!sOption || dOptions.gl_get(sOption, false)) {

                        bCondMemo = !sFuncCond || oEvalFunc[sFuncCond](this.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, this.dTags, this.sSentence, this.sSentence0);
                        if (bCondMemo) {
                            if (cActionType == "-") {
                                // grammar error
                                let [iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, iURL] = eAct;
                                let nTokenErrorStart = (iTokenStart > 0) ? nTokenOffset + iTokenStart : nLastToken + iTokenStart;
                                if (!this.lToken[nTokenErrorStart].hasOwnProperty("bImmune")) {
                                    let nTokenErrorEnd = (iTokenEnd > 0) ? nTokenOffset + iTokenEnd : nLastToken + iTokenEnd;







>
|







664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
                    // Suggestion    [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, iURL ]
                    // TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ]
                    // Disambiguator [ option, condition, "=", replacement/suggestion/action ]
                    // Tag           [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
                    // Immunity      [ option, condition, "!", "",                            iTokenStart, iTokenEnd ]
                    // Test          [ option, condition, ">", "" ]
                    if (!sOption || dOptions.gl_get(sOption, false)) {
                        bCondMemo = !sFuncCond || gc_functions[sFuncCond](this.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, this.dTags, this.sSentence, this.sSentence0);
                        //bCondMemo = !sFuncCond || oEvalFunc[sFuncCond](this.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, this.dTags, this.sSentence, this.sSentence0);
                        if (bCondMemo) {
                            if (cActionType == "-") {
                                // grammar error
                                let [iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, iURL] = eAct;
                                let nTokenErrorStart = (iTokenStart > 0) ? nTokenOffset + iTokenStart : nLastToken + iTokenStart;
                                if (!this.lToken[nTokenErrorStart].hasOwnProperty("bImmune")) {
                                    let nTokenErrorEnd = (iTokenEnd > 0) ? nTokenOffset + iTokenEnd : nLastToken + iTokenEnd;
699
700
701
702
703
704
705

706
707
708
709
710
711
712
713
                                bChange = true;
                                if (bDebug) {
                                    console.log(`    TEXT_PROCESSOR: [${this.lToken[nTokenStart]["sValue"]}:${this.lToken[nTokenEnd]["sValue"]}]  > ${sWhat}`);
                                }
                            }
                            else if (cActionType == "=") {
                                // disambiguation

                                oEvalFunc[sWhat](this.lToken, nTokenOffset, nLastToken);
                                if (bDebug) {
                                    console.log(`    DISAMBIGUATOR: (${sWhat})  [${this.lToken[nTokenOffset+1]["sValue"]}:${this.lToken[nLastToken]["sValue"]}]`);
                                }
                            }
                            else if (cActionType == ">") {
                                // we do nothing, this test is just a condition to apply all following actions
                                if (bDebug) {







>
|







698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
                                bChange = true;
                                if (bDebug) {
                                    console.log(`    TEXT_PROCESSOR: [${this.lToken[nTokenStart]["sValue"]}:${this.lToken[nTokenEnd]["sValue"]}]  > ${sWhat}`);
                                }
                            }
                            else if (cActionType == "=") {
                                // disambiguation
                                gc_functions[sWhat](this.lToken, nTokenOffset, nLastToken);
                                //oEvalFunc[sWhat](this.lToken, nTokenOffset, nLastToken);
                                if (bDebug) {
                                    console.log(`    DISAMBIGUATOR: (${sWhat})  [${this.lToken[nTokenOffset+1]["sValue"]}:${this.lToken[nLastToken]["sValue"]}]`);
                                }
                            }
                            else if (cActionType == ">") {
                                // we do nothing, this test is just a condition to apply all following actions
                                if (bDebug) {
781
782
783
784
785
786
787

788
789
790
791
792
793
794
795
796
797
798

799
800
801
802
803
804
805
806
807
808
809
810

811
812
813
814
815
816
817
818
819
820
821

822
823
824
825
826
827
828
829

    _createErrorFromRegex (sText, sText0, sSugg, nOffset, m, iGroup, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) {
        let nStart = nOffset + m.start[iGroup];
        let nEnd = nOffset + m.end[iGroup];
        // suggestions
        let lSugg = [];
        if (sSugg.startsWith("=")) {

            sSugg = oEvalFunc[sSugg.slice(1)](sText, m);
            lSugg = (sSugg) ? sSugg.split("|") : [];
        } else if (sSugg == "_") {
            lSugg = [];
        } else {
            lSugg = sSugg.gl_expand(m).split("|");
        }
        if (bCaseSvty && lSugg.length > 0 && m[iGroup].slice(0,1).gl_isUpperCase()) {
            lSugg = (m[iGroup].gl_isUpperCase()) ? lSugg.map((s) => s.toUpperCase()) : capitalizeArray(lSugg);
        }
        // Message

        let sMessage = (sMsg.startsWith("=")) ? oEvalFunc[sMsg.slice(1)](sText, m) : sMsg.gl_expand(m);
        if (bShowRuleId) {
            sMessage += "  #" + sLineId + " / " + sRuleId;
        }
        //
        return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, 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)](this.lToken, nTokenOffset, nLastToken);
            lSugg = (sSugg) ? sSugg.split("|") : [];
        } else if (sSugg == "_") {
            lSugg = [];
        } else {
            lSugg = this._expand(sSugg, nTokenOffset, nLastToken).split("|");
        }
        if (bCaseSvty && lSugg.length > 0 && this.lToken[iFirstToken]["sValue"].slice(0,1).gl_isUpperCase()) {
            lSugg = (this.sSentence.slice(nStart, nEnd).gl_isUpperCase()) ? lSugg.map((s) => s.toUpperCase()) : capitalizeArray(lSugg);
        }
        // Message

        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);
    }








>
|










>
|











>
|










>
|







781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833

    _createErrorFromRegex (sText, sText0, sSugg, nOffset, m, iGroup, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) {
        let nStart = nOffset + m.start[iGroup];
        let nEnd = nOffset + m.end[iGroup];
        // suggestions
        let lSugg = [];
        if (sSugg.startsWith("=")) {
            sSugg = gc_functions[sSugg.slice(1)](sText, m);
            //sSugg = oEvalFunc[sSugg.slice(1)](sText, m);
            lSugg = (sSugg) ? sSugg.split("|") : [];
        } else if (sSugg == "_") {
            lSugg = [];
        } else {
            lSugg = sSugg.gl_expand(m).split("|");
        }
        if (bCaseSvty && lSugg.length > 0 && m[iGroup].slice(0,1).gl_isUpperCase()) {
            lSugg = (m[iGroup].gl_isUpperCase()) ? lSugg.map((s) => s.toUpperCase()) : capitalizeArray(lSugg);
        }
        // Message
        let sMessage = (sMsg.startsWith("=")) ? gc_functions[sMsg.slice(1)](sText, m) : sMsg.gl_expand(m);
        //let sMessage = (sMsg.startsWith("=")) ? oEvalFunc[sMsg.slice(1)](sText, m) : sMsg.gl_expand(m);
        if (bShowRuleId) {
            sMessage += "  #" + sLineId + " / " + sRuleId;
        }
        //
        return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext);
    }

    _createErrorFromTokens (sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) {
        // suggestions
        let lSugg = [];
        if (sSugg.startsWith("=")) {
            sSugg = gc_functions[sSugg.slice(1)](this.lToken, nTokenOffset, nLastToken);
            //sSugg = oEvalFunc[sSugg.slice(1)](this.lToken, nTokenOffset, nLastToken);
            lSugg = (sSugg) ? sSugg.split("|") : [];
        } else if (sSugg == "_") {
            lSugg = [];
        } else {
            lSugg = this._expand(sSugg, nTokenOffset, nLastToken).split("|");
        }
        if (bCaseSvty && lSugg.length > 0 && this.lToken[iFirstToken]["sValue"].slice(0,1).gl_isUpperCase()) {
            lSugg = (this.sSentence.slice(nStart, nEnd).gl_isUpperCase()) ? lSugg.map((s) => s.toUpperCase()) : capitalizeArray(lSugg);
        }
        // Message
        let sMessage = (sMsg.startsWith("=")) ? gc_functions[sMsg.slice(1)](this.lToken, nTokenOffset, nLastToken) : this._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);
    }

869
870
871
872
873
874
875

876
877
878
879
880
881
882
883
        else if (sRepl === "_") {
            sNew = "_".repeat(ln);
        }
        else if (sRepl === "@") {
            sNew = "@".repeat(ln);
        }
        else if (sRepl.slice(0,1) === "=") {

            sNew = oEvalFunc[sRepl.slice(1)](sText, m);
            sNew = sNew + " ".repeat(ln-sNew.length);
            if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) {
                sNew = sNew.gl_toCapitalize();
            }
        } else {
            sNew = sRepl.gl_expand(m);
            sNew = sNew + " ".repeat(ln-sNew.length);







>
|







873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
        else if (sRepl === "_") {
            sNew = "_".repeat(ln);
        }
        else if (sRepl === "@") {
            sNew = "@".repeat(ln);
        }
        else if (sRepl.slice(0,1) === "=") {
            sNew = gc_functions[sRepl.slice(1)](sText, m);
            //sNew = oEvalFunc[sRepl.slice(1)](sText, m);
            sNew = sNew + " ".repeat(ln-sNew.length);
            if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) {
                sNew = sNew.gl_toCapitalize();
            }
        } else {
            sNew = sRepl.gl_expand(m);
            sNew = sNew + " ".repeat(ln-sNew.length);
910
911
912
913
914
915
916

917
918
919
920
921
922
923
924
                for (let i = nTokenRewriteStart;  i <= nTokenRewriteEnd;  i++) {
                    this.lToken[i]["sNewValue"] = "_";
                }
            }
        }
        else {
            if (sWhat.startsWith("=")) {

                sWhat = oEvalFunc[sWhat.slice(1)](this.lToken, nTokenOffset, nLastToken);
            } else {
                sWhat = this._expand(sWhat, nTokenOffset, nLastToken);
            }
            let bUppercase = bCaseSvty && this.lToken[nTokenRewriteStart]["sValue"].slice(0,1).gl_isUpperCase();
            if (nTokenRewriteEnd - nTokenRewriteStart == 0) {
                // one token
                if (bUppercase) {







>
|







915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
                for (let i = nTokenRewriteStart;  i <= nTokenRewriteEnd;  i++) {
                    this.lToken[i]["sNewValue"] = "_";
                }
            }
        }
        else {
            if (sWhat.startsWith("=")) {
                sWhat = gc_functions[sWhat.slice(1)](this.lToken, nTokenOffset, nLastToken);
                //sWhat = oEvalFunc[sWhat.slice(1)](this.lToken, nTokenOffset, nLastToken);
            } else {
                sWhat = this._expand(sWhat, nTokenOffset, nLastToken);
            }
            let bUppercase = bCaseSvty && this.lToken[nTokenRewriteStart]["sValue"].slice(0,1).gl_isUpperCase();
            if (nTokenRewriteEnd - nTokenRewriteStart == 0) {
                // one token
                if (bUppercase) {
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
            console.log("  TEXT REWRITED: " + this.sSentence);
        }
        this.lToken.length = 0;
        this.lToken = lNewToken;
    }
};


//////// Common functions

function option (sOpt) {
    // return true if option sOpt is active
    return gc_options.dOptions.gl_get(sOpt, false);
}

var re = {
    search: function (sRegex, sText) {
        if (sRegex.startsWith("(?i)")) {
            return sText.search(new RegExp(sRegex.slice(4), "i")) !== -1;
        } else {
            return sText.search(sRegex) !== -1;
        }
    },

    createRegExp: function (sRegex) {
        if (sRegex.startsWith("(?i)")) {
            return new RegExp(sRegex.slice(4), "i");
        } else {
            return new RegExp(sRegex);
        }
    }
}


//////// functions to get text outside pattern scope

// warning: check compile_rules.py to understand how it works

function nextword (s, iStart, n) {
    // get the nth word of the input string or empty string
    let z = new RegExp("^(?: +[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+)", "ig");
    let m = z.exec(s.slice(iStart));
    if (!m) {
        return null;
    }
    return [iStart + z.lastIndex - m[1].length, m[1]];
}

function prevword (s, iEnd, n) {
    // get the (-)nth word of the input string or empty string
    let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+ +){" + (n-1).toString() + "}$", "i");
    let m = z.exec(s.slice(0, iEnd));
    if (!m) {
        return null;
    }
    return [m.index, m[1]];
}

function nextword1 (s, iStart) {
    // get next word (optimization)
    let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*)", "ig");
    let m = _zNextWord.exec(s.slice(iStart));
    if (!m) {
        return null;
    }
    return [iStart + _zNextWord.lastIndex - m[1].length, m[1]];
}

const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*) +$", "i");

function prevword1 (s, iEnd) {
    // get previous word (optimization)
    let m = _zPrevWord.exec(s.slice(0, iEnd));
    if (!m) {
        return null;
    }
    return [m.index, m[1]];
}

function look (s, sPattern, sNegPattern=null) {
    // seek sPattern in s (before/after/fulltext), if antipattern sNegPattern not in s
    try {
        if (sNegPattern && re.search(sNegPattern, s)) {
            return false;
        }
        return re.search(sPattern, s);
    }
    catch (e) {
        console.error(e);
    }
    return false;
}


//////// Analyse groups for regex rules

function displayInfo (dTokenPos, aWord) {
    // for debugging: info of word
    if (!aWord) {
        console.log("> nothing to find");
        return true;
    }
    let lMorph = gc_engine.oSpellChecker.getMorph(aWord[1]);
    if (lMorph.length === 0) {
        console.log("> not in dictionary");
        return true;
    }
    if (dTokenPos.has(aWord[0])) {
        console.log("DA: " + dTokenPos.get(aWord[0]));
    }
    console.log("FSA: " + lMorph);
    return true;
}

function morph (dTokenPos, aWord, sPattern, sNegPattern, bNoWord=false) {
    // analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
    if (!aWord) {
        return bNoWord;
    }
    let lMorph = (dTokenPos.has(aWord[0])  &&  dTokenPos.get(aWord[0]))["lMorph"] ? dTokenPos.get(aWord[0])["lMorph"] : gc_engine.oSpellChecker.getMorph(aWord[1]);
    if (lMorph.length === 0) {
        return false;
    }
    if (sNegPattern) {
        // check negative condition
        if (sNegPattern === "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function analyse (sWord, sPattern, sNegPattern) {
    // analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0) {
        return false;
    }
    if (sNegPattern) {
        // check negative condition
        if (sNegPattern === "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}


//// Analyse tokens for graph rules

function g_value (oToken, sValues, nLeft=null, nRight=null) {
    // test if <oToken['sValue']> is in sValues (each value should be separated with |)
    let sValue = (nLeft === null) ? "|"+oToken["sValue"]+"|" : "|"+oToken["sValue"].slice(nLeft, nRight)+"|";
    if (sValues.includes(sValue)) {
        return true;
    }
    if (oToken["sValue"].slice(0,2).gl_isTitle()) { // we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
        if (sValues.includes(sValue.toLowerCase())) {
            return true;
        }
    }
    else if (oToken["sValue"].gl_isUpperCase()) {
        //if sValue.lower() in sValues:
        //    return true;
        sValue = "|"+sValue.slice(1).gl_toCapitalize();
        if (sValues.includes(sValue)) {
            return true;
        }
        sValue = sValue.toLowerCase();
        if (sValues.includes(sValue)) {
            return true;
        }
    }
    return false;
}

function g_morph (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
    // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
    let lMorph;
    if (oToken.hasOwnProperty("lMorph")) {
        lMorph = oToken["lMorph"];
    }
    else {
        if (nLeft !== null) {
            let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
            lMorph = gc_engine.oSpellChecker.getMorph(sValue);
            if (bMemorizeMorph) {
                oToken["lMorph"] = lMorph;
            }
        } else {
            lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
        }
    }
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function g_analyse (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
    // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
    let lMorph;
    if (nLeft !== null) {
        let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
        lMorph = gc_engine.oSpellChecker.getMorph(sValue);
        if (bMemorizeMorph) {
            oToken["lMorph"] = lMorph;
        }
    } else {
        lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    }
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function g_merged_analyse (oToken1, oToken2, cMerger, sPattern, sNegPattern="", bSetMorph=true) {
    // merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)
    let lMorph = gc_engine.oSpellChecker.getMorph(oToken1["sValue"] + cMerger + oToken2["sValue"]);
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            let bResult = lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
            if (bResult && bSetMorph) {
                oToken1["lMorph"] = lMorph;
            }
            return bResult;
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    let bResult = lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
    if (bResult && bSetMorph) {
        oToken1["lMorph"] = lMorph;
    }
    return bResult;
}

function g_tag_before (oToken, dTags, sTag) {
    if (!dTags.has(sTag)) {
        return false;
    }
    if (oToken["i"] > dTags.get(sTag)[0]) {
        return true;
    }
    return false;
}

function g_tag_after (oToken, dTags, sTag) {
    if (!dTags.has(sTag)) {
        return false;
    }
    if (oToken["i"] < dTags.get(sTag)[1]) {
        return true;
    }
    return false;
}

function g_tag (oToken, sTag) {
    return oToken.hasOwnProperty("aTags") && oToken["aTags"].has(sTag);
}

function g_space_between_tokens (oToken1, oToken2, nMin, nMax=null) {
    let nSpace = oToken2["nStart"] - oToken1["nEnd"]
    if (nSpace < nMin) {
        return false;
    }
    if (nMax !== null && nSpace > nMax) {
        return false;
    }
    return true;
}

function g_token (lToken, i) {
    if (i < 0) {
        return lToken[0];
    }
    if (i >= lToken.length) {
        return lToken[lToken.length-1];
    }
    return lToken[i];
}


//////// Disambiguator

function select (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (!dTokenPos.has(nPos)) {
        console.log("Error. There should be a token at this position: ", nPos);
        return true;
    }
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0  ||  lMorph.length === 1) {
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            dTokenPos.get(nPos)["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        dTokenPos.get(nPos)["lMorph"] = lDefault;
    }
    return true;
}

function exclude (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (!dTokenPos.has(nPos)) {
        console.log("Error. There should be a token at this position: ", nPos);
        return true;
    }
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0  ||  lMorph.length === 1) {
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            dTokenPos.get(nPos)["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        dTokenPos.get(nPos)["lMorph"] = lDefault;
    }
    return true;
}

function define (dTokenPos, nPos, sMorphs) {
    dTokenPos.get(nPos)["lMorph"] = sMorphs.split("|");
    return true;
}


//// Disambiguation for graph rules

function g_select (oToken, sPattern, lDefault=null) {
    // select morphologies for <oToken> according to <sPattern>, always return true
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    if (lMorph.length === 0  || lMorph.length === 1) {
        if (lDefault) {
            oToken["lMorph"] = lDefault;
        }
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            oToken["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        oToken["lMorph"] = lDefault;
    }
    return true;
}

function g_exclude (oToken, sPattern, lDefault=null) {
    // select morphologies for <oToken> according to <sPattern>, always return true
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    if (lMorph.length === 0  || lMorph.length === 1) {
        if (lDefault) {
            oToken["lMorph"] = lDefault;
        }
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            oToken["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        oToken["lMorph"] = lDefault;
    }
    return true;
}

function g_add_morph (oToken, sNewMorph) {
    // Disambiguation: add a morphology to a token
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    lMorph.push(...sNewMorph.split("|"));
    oToken["lMorph"] = lMorph;
    return true;
}

function g_rewrite (oToken, sToReplace, sReplace) {
    // Disambiguation: rewrite morphologies
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    oToken["lMorph"] = lMorph.map(s => s.replace(sToReplace, sReplace));
    return true;
}

function g_define (oToken, sMorphs) {
    // set morphologies of <oToken>, always return true
    oToken["lMorph"] = sMorphs.split("|");
    return true;
}

function g_define_from (oToken, nLeft=null, nRight=null) {
    let sValue = oToken["sValue"];
    if (nLeft !== null) {
        sValue = (nRight !== null) ? sValue.slice(nLeft, nRight) : sValue.slice(nLeft);
    }
    oToken["lMorph"] = gc_engine.oSpellChecker.getMorph(sValue);
    return true;
}

function g_change_meta (oToken, sType) {
    // Disambiguation: change type of token
    oToken["sType"] = sType;
    return true;
}



//////// GRAMMAR CHECKER PLUGINS

${pluginsJS}


// generated code, do not edit
const oEvalFunc = {
    // callables for regex rules
${callablesJS}

    // callables for graph rules
${graph_callablesJS}
}


if (typeof(exports) !== 'undefined') {
    exports.lang = gc_engine.lang;
    exports.locales = gc_engine.locales;
    exports.pkg = gc_engine.pkg;
    exports.name = gc_engine.name;
    exports.version = gc_engine.version;







<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







1024
1025
1026
1027
1028
1029
1030


























































































































































































































































































































































































































































































1031
1032
1033
1034
1035
1036
1037
            console.log("  TEXT REWRITED: " + this.sSentence);
        }
        this.lToken.length = 0;
        this.lToken = lNewToken;
    }
};




























































































































































































































































































































































































































































































if (typeof(exports) !== 'undefined') {
    exports.lang = gc_engine.lang;
    exports.locales = gc_engine.locales;
    exports.pkg = gc_engine.pkg;
    exports.name = gc_engine.name;
    exports.version = gc_engine.version;

Added gc_core/js/lang_core/gc_functions.js version [9add95291e].



















































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
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
// JavaScript
// Grammar checker engine functions

${string}
${regex}
${map}


if (typeof(process) !== 'undefined') {
    var gc_options = require("./gc_options.js");
}


let _sAppContext = "JavaScript";        // what software is running
let _oSpellChecker = null;


//////// Common functions

function option (sOpt) {
    // return true if option sOpt is active
    return gc_options.dOptions.gl_get(sOpt, false);
}

function echo (x) {
    console.log(x);
    return true;
}

var re = {
    search: function (sRegex, sText) {
        if (sRegex.startsWith("(?i)")) {
            return sText.search(new RegExp(sRegex.slice(4), "i")) !== -1;
        } else {
            return sText.search(sRegex) !== -1;
        }
    },

    createRegExp: function (sRegex) {
        if (sRegex.startsWith("(?i)")) {
            return new RegExp(sRegex.slice(4), "i");
        } else {
            return new RegExp(sRegex);
        }
    }
}


//////// functions to get text outside pattern scope

// warning: check compile_rules.py to understand how it works

function nextword (s, iStart, n) {
    // get the nth word of the input string or empty string
    let z = new RegExp("^(?: +[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+)", "ig");
    let m = z.exec(s.slice(iStart));
    if (!m) {
        return null;
    }
    return [iStart + z.lastIndex - m[1].length, m[1]];
}

function prevword (s, iEnd, n) {
    // get the (-)nth word of the input string or empty string
    let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+ +){" + (n-1).toString() + "}$", "i");
    let m = z.exec(s.slice(0, iEnd));
    if (!m) {
        return null;
    }
    return [m.index, m[1]];
}

function nextword1 (s, iStart) {
    // get next word (optimization)
    let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*)", "ig");
    let m = _zNextWord.exec(s.slice(iStart));
    if (!m) {
        return null;
    }
    return [iStart + _zNextWord.lastIndex - m[1].length, m[1]];
}

const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*) +$", "i");

function prevword1 (s, iEnd) {
    // get previous word (optimization)
    let m = _zPrevWord.exec(s.slice(0, iEnd));
    if (!m) {
        return null;
    }
    return [m.index, m[1]];
}

function look (s, sPattern, sNegPattern=null) {
    // seek sPattern in s (before/after/fulltext), if antipattern sNegPattern not in s
    try {
        if (sNegPattern && re.search(sNegPattern, s)) {
            return false;
        }
        return re.search(sPattern, s);
    }
    catch (e) {
        console.error(e);
    }
    return false;
}


//////// Analyse groups for regex rules

function displayInfo (dTokenPos, aWord) {
    // for debugging: info of word
    if (!aWord) {
        console.log("> nothing to find");
        return true;
    }
    let lMorph = gc_engine.oSpellChecker.getMorph(aWord[1]);
    if (lMorph.length === 0) {
        console.log("> not in dictionary");
        return true;
    }
    if (dTokenPos.has(aWord[0])) {
        console.log("DA: " + dTokenPos.get(aWord[0]));
    }
    console.log("FSA: " + lMorph);
    return true;
}

function morph (dTokenPos, aWord, sPattern, sNegPattern, bNoWord=false) {
    // analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
    if (!aWord) {
        return bNoWord;
    }
    let lMorph = (dTokenPos.has(aWord[0])  &&  dTokenPos.get(aWord[0]))["lMorph"] ? dTokenPos.get(aWord[0])["lMorph"] : gc_engine.oSpellChecker.getMorph(aWord[1]);
    if (lMorph.length === 0) {
        return false;
    }
    if (sNegPattern) {
        // check negative condition
        if (sNegPattern === "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function analyse (sWord, sPattern, sNegPattern) {
    // analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0) {
        return false;
    }
    if (sNegPattern) {
        // check negative condition
        if (sNegPattern === "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}


//// Analyse tokens for graph rules

function g_value (oToken, sValues, nLeft=null, nRight=null) {
    // test if <oToken['sValue']> is in sValues (each value should be separated with |)
    let sValue = (nLeft === null) ? "|"+oToken["sValue"]+"|" : "|"+oToken["sValue"].slice(nLeft, nRight)+"|";
    if (sValues.includes(sValue)) {
        return true;
    }
    if (oToken["sValue"].slice(0,2).gl_isTitle()) { // we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
        if (sValues.includes(sValue.toLowerCase())) {
            return true;
        }
    }
    else if (oToken["sValue"].gl_isUpperCase()) {
        //if sValue.lower() in sValues:
        //    return true;
        sValue = "|"+sValue.slice(1).gl_toCapitalize();
        if (sValues.includes(sValue)) {
            return true;
        }
        sValue = sValue.toLowerCase();
        if (sValues.includes(sValue)) {
            return true;
        }
    }
    return false;
}

function g_morph (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
    // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
    let lMorph;
    if (oToken.hasOwnProperty("lMorph")) {
        lMorph = oToken["lMorph"];
    }
    else {
        if (nLeft !== null) {
            let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
            lMorph = gc_engine.oSpellChecker.getMorph(sValue);
            if (bMemorizeMorph) {
                oToken["lMorph"] = lMorph;
            }
        } else {
            lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
        }
    }
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function g_analyse (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
    // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
    let lMorph;
    if (nLeft !== null) {
        let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
        lMorph = gc_engine.oSpellChecker.getMorph(sValue);
        if (bMemorizeMorph) {
            oToken["lMorph"] = lMorph;
        }
    } else {
        lMorph = gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    }
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            return lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    return lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
}

function g_merged_analyse (oToken1, oToken2, cMerger, sPattern, sNegPattern="", bSetMorph=true) {
    // merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)
    let lMorph = gc_engine.oSpellChecker.getMorph(oToken1["sValue"] + cMerger + oToken2["sValue"]);
    if (lMorph.length == 0) {
        return false;
    }
    // check negative condition
    if (sNegPattern) {
        if (sNegPattern == "*") {
            // all morph must match sPattern
            let bResult = lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1));
            if (bResult && bSetMorph) {
                oToken1["lMorph"] = lMorph;
            }
            return bResult;
        }
        else {
            if (lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                return false;
            }
        }
    }
    // search sPattern
    let bResult = lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1));
    if (bResult && bSetMorph) {
        oToken1["lMorph"] = lMorph;
    }
    return bResult;
}

function g_tag_before (oToken, dTags, sTag) {
    if (!dTags.has(sTag)) {
        return false;
    }
    if (oToken["i"] > dTags.get(sTag)[0]) {
        return true;
    }
    return false;
}

function g_tag_after (oToken, dTags, sTag) {
    if (!dTags.has(sTag)) {
        return false;
    }
    if (oToken["i"] < dTags.get(sTag)[1]) {
        return true;
    }
    return false;
}

function g_tag (oToken, sTag) {
    return oToken.hasOwnProperty("aTags") && oToken["aTags"].has(sTag);
}

function g_space_between_tokens (oToken1, oToken2, nMin, nMax=null) {
    let nSpace = oToken2["nStart"] - oToken1["nEnd"]
    if (nSpace < nMin) {
        return false;
    }
    if (nMax !== null && nSpace > nMax) {
        return false;
    }
    return true;
}

function g_token (lToken, i) {
    if (i < 0) {
        return lToken[0];
    }
    if (i >= lToken.length) {
        return lToken[lToken.length-1];
    }
    return lToken[i];
}


//////// Disambiguator for regex rules

function select (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (!dTokenPos.has(nPos)) {
        console.log("Error. There should be a token at this position: ", nPos);
        return true;
    }
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0  ||  lMorph.length === 1) {
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            dTokenPos.get(nPos)["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        dTokenPos.get(nPos)["lMorph"] = lDefault;
    }
    return true;
}

function exclude (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (!dTokenPos.has(nPos)) {
        console.log("Error. There should be a token at this position: ", nPos);
        return true;
    }
    let lMorph = gc_engine.oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0  ||  lMorph.length === 1) {
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            dTokenPos.get(nPos)["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        dTokenPos.get(nPos)["lMorph"] = lDefault;
    }
    return true;
}

function define (dTokenPos, nPos, sMorphs) {
    dTokenPos.get(nPos)["lMorph"] = sMorphs.split("|");
    return true;
}


//// Disambiguation for graph rules

function g_select (oToken, sPattern, lDefault=null) {
    // select morphologies for <oToken> according to <sPattern>, always return true
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    if (lMorph.length === 0  || lMorph.length === 1) {
        if (lDefault) {
            oToken["lMorph"] = lDefault;
        }
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            oToken["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        oToken["lMorph"] = lDefault;
    }
    return true;
}

function g_exclude (oToken, sPattern, lDefault=null) {
    // select morphologies for <oToken> according to <sPattern>, always return true
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    if (lMorph.length === 0  || lMorph.length === 1) {
        if (lDefault) {
            oToken["lMorph"] = lDefault;
        }
        return true;
    }
    let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
    if (lSelect.length > 0) {
        if (lSelect.length != lMorph.length) {
            oToken["lMorph"] = lSelect;
        }
    } else if (lDefault) {
        oToken["lMorph"] = lDefault;
    }
    return true;
}

function g_add_morph (oToken, sNewMorph) {
    // Disambiguation: add a morphology to a token
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    lMorph.push(...sNewMorph.split("|"));
    oToken["lMorph"] = lMorph;
    return true;
}

function g_rewrite (oToken, sToReplace, sReplace) {
    // Disambiguation: rewrite morphologies
    let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
    oToken["lMorph"] = lMorph.map(s => s.replace(sToReplace, sReplace));
    return true;
}

function g_define (oToken, sMorphs) {
    // set morphologies of <oToken>, always return true
    oToken["lMorph"] = sMorphs.split("|");
    return true;
}

function g_define_from (oToken, nLeft=null, nRight=null) {
    let sValue = oToken["sValue"];
    if (nLeft !== null) {
        sValue = (nRight !== null) ? sValue.slice(nLeft, nRight) : sValue.slice(nLeft);
    }
    oToken["lMorph"] = gc_engine.oSpellChecker.getMorph(sValue);
    return true;
}

function g_change_meta (oToken, sType) {
    // Disambiguation: change type of token
    oToken["sType"] = sType;
    return true;
}



//////// GRAMMAR CHECKER PLUGINS

${pluginsJS}


// generated code, do not edit
var gc_functions = {

    load: function (sContext, oSpellChecker) {
        _sAppContext = sContext
        _oSpellChecker = oSpellChecker
    },

    // callables for regex rules
${callablesJS}

    // callables for graph rules
${graph_callablesJS}
}


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

Modified gc_lang/fr/webext/gce_worker.js from [c784b7c2c4] to [e351d5e6fd].

41
42
43
44
45
46
47

48
49
50
51
52
53
54
importScripts("grammalecte/text.js");
importScripts("grammalecte/graphspell/tokenizer.js");
importScripts("grammalecte/fr/conj.js");
importScripts("grammalecte/fr/mfsp.js");
importScripts("grammalecte/fr/phonet.js");
importScripts("grammalecte/fr/cregex.js");
importScripts("grammalecte/fr/gc_options.js");

importScripts("grammalecte/fr/gc_rules.js");
importScripts("grammalecte/fr/gc_rules_graph.js");
importScripts("grammalecte/fr/gc_engine.js");
importScripts("grammalecte/tests.js");
/*
    Warning.
    Initialization can’t be completed at startup of the worker,







>







41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
importScripts("grammalecte/text.js");
importScripts("grammalecte/graphspell/tokenizer.js");
importScripts("grammalecte/fr/conj.js");
importScripts("grammalecte/fr/mfsp.js");
importScripts("grammalecte/fr/phonet.js");
importScripts("grammalecte/fr/cregex.js");
importScripts("grammalecte/fr/gc_options.js");
importScripts("grammalecte/fr/gc_functions.js");
importScripts("grammalecte/fr/gc_rules.js");
importScripts("grammalecte/fr/gc_rules_graph.js");
importScripts("grammalecte/fr/gc_engine.js");
importScripts("grammalecte/tests.js");
/*
    Warning.
    Initialization can’t be completed at startup of the worker,