Grammalecte  Check-in [622ce25bcf]

Overview
Comment:[core][js] ge engine: new engine (code conversion from Python [draft])
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | rg
Files: files | file ages | folders
SHA3-256: 622ce25bcf8f9701143469a3fc1504d660730a7508bd5834ce1dc7cbeb803f5a
User & Date: olr on 2018-09-10 08:20:45
Other Links: branch diff | manifest | tags
Context
2018-09-10
08:57
[core] gc engine: built functions and exports check-in: 2b29190468 user: olr tags: core, rg
08:20
[core][js] ge engine: new engine (code conversion from Python [draft]) check-in: 622ce25bcf user: olr tags: core, rg
08:19
[core] gc engine: remove useless function call check-in: 00475b3f6b user: olr tags: core, rg
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Modified gc_core/js/lang_core/gc_engine.js from [12095116ac] to [8c2bd41fd9]. 

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

// Grammar checker engine
/*jslint esversion: 6*/
/*global console,require,exports*/

"use strict";

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


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/graphspell/helpers.js");
    var gc_options = require("resource://grammalecte/${lang}/gc_options.js");
    var gc_rules = require("resource://grammalecte/${lang}/gc_rules.js");
    var cregex = require("resource://grammalecte/${lang}/cregex.js");
    var text = require("resource://grammalecte/text.js");
    var echo = helpers.echo;
}
else if (typeof(console) !== "undefined") {
    var echo = function (o) { console.log(o); return true; };
}
else {
    var echo = function () { return true; }
}

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].gl_toCapitalize();
    }
    return aNew;
}


// data
let _sAppContext = "";                                  // what software is running
let _dOptions = null;


let _aIgnoredRules = new Set();
let _oSpellChecker = null;


var gc_engine = {

    //// Informations

    lang: "${lang}",
    locales: ${loc},
    pkg: "${implname}",
    name: "${name}",
    version: "${version}",
    author: "${author}",

    //// Parsing

    parse: function (sText, sCountry="${country_default}", bDebug=false, bContext=false) {
        // analyses the paragraph sText and returns list of errors
        let dErrors;
        let errs;
        let sAlt = sText;
        let dDA = new Map();        // Disamnbiguator
        let dPriority = new Map();  // Key = position; value = priority
        let sNew = "";

        // parse paragraph
        try {
            [sNew, dErrors] = this._proofread(sText, sAlt, 0, true, dDA, dPriority, sCountry, bDebug, bContext);
            if (sNew) {
                sText = sNew;
            }
        }
        catch (e) {
            helpers.logerror(e);
        }

        // cleanup
        if (sText.includes(" ")) {
            sText = sText.replace(/ /g, ' '); // nbsp
        }
        if (sText.includes(" ")) {
            sText = sText.replace(/ /g, ' '); // snbsp
        }
        if (sText.includes("'")) {
            sText = sText.replace(/'/g, "’");
        }
        if (sText.includes("‑")) {
            sText = sText.replace(/‑/g, "-"); // nobreakdash
        }

        // parse sentence
        for (let [iStart, iEnd] of this._getSentenceBoundaries(sText)) {
            if (4 < (iEnd - iStart) < 2000) {
                dDA.clear();
                //helpers.echo(sText.slice(iStart, iEnd));
                try {
                    [, errs] = this._proofread(sText.slice(iStart, iEnd), sAlt.slice(iStart, iEnd), iStart, false, dDA, dPriority, sCountry, bDebug, bContext);
                    dErrors.gl_update(errs);
                }
                catch (e) {
                    helpers.logerror(e);
                }
            }
        }
        return Array.from(dErrors.values());
    },

    _zEndOfSentence: new RegExp ('([.?!:;…][ .?!… »”")]*|.$)', "g"),
    _zBeginOfParagraph: new RegExp ("^[-  –—.,;?!…]*", "ig"),
    _zEndOfParagraph: new RegExp ("[-  .,;?!…–—]*$", "ig"),

    _getSentenceBoundaries: function* (sText) {
        let mBeginOfSentence = this._zBeginOfParagraph.exec(sText);
        let iStart = this._zBeginOfParagraph.lastIndex;
        let m;
        while ((m = this._zEndOfSentence.exec(sText)) !== null) {
            yield [iStart, this._zEndOfSentence.lastIndex];
            iStart = this._zEndOfSentence.lastIndex;


        }
    },


    _proofread: function (s, sx, nOffset, bParagraph, dDA, dPriority, sCountry, bDebug, bContext) {


        let dErrs = new Map();
        let bChange = false;
        let bIdRule = option('idrule');
        let m;
        let bCondMemo;
        let nErrorStart;

        for (let [sOption, lRuleGroup] of this._getRules(bParagraph)) {
            if (!sOption || option(sOption)) {
                for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
                    if (!_aIgnoredRules.has(sRuleId)) {
                        while ((m = zRegex.gl_exec2(s, lGroups, lNegLookBefore)) !== null) {
                            bCondMemo = null;
                            /*if (bDebug) {
                                helpers.echo(">>>> Rule # " + sLineId + " - Text: " + s + " opt: "+ sOption);
                            }*/
                            for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) {
                            // action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try {
                                    //helpers.echo(oEvalFunc[sFuncCond]);
                                    bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](s, sx, m, dDA, sCountry, bCondMemo));
                                    if (bCondMemo) {
                                        switch (cActionType) {
                                            case "-":
                                                // grammar error
                                                //helpers.echo("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source);
                                                nErrorStart = nOffset + m.start[eAct[0]];
                                                if (!dErrs.has(nErrorStart) || nPriority > dPriority.get(nErrorStart)) {
                                                    dErrs.set(nErrorStart, this._createError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bIdRule, sOption, bContext));
                                                    dPriority.set(nErrorStart, nPriority);
                                                }
                                                break;
                                            case "~":
                                                // text processor
                                                //helpers.echo("-> text processor by " + sLineId + "\nzRegex: " + zRegex.source);
                                                s = this._rewrite(s, sWhat, eAct[0], m, bUppercase);
                                                bChange = true;
                                                if (bDebug) {
                                                    helpers.echo("~ " + s + "  -- " + m[eAct[0]] + "  # " + sLineId);
                                                }
                                                break;
                                            case "=":
                                                // disambiguation
                                                //helpers.echo("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
                                                oEvalFunc[sWhat](s, m, dDA);
                                                if (bDebug) {
                                                    helpers.echo("= " + m[0] + "  # " + sLineId + "\nDA: " + dDA.gl_toString());
                                                }
                                                break;
                                            case ">":
                                                // we do nothing, this test is just a condition to apply all following actions
                                                break;
                                            default:
                                                helpers.echo("# error: unknown action at " + sLineId);
                                        }
                                    } else {
                                        if (cActionType == ">") {
                                            break;
                                        }
                                    }
                                }
                                catch (e) {
                                    helpers.echo(s);
                                    helpers.echo("# line id: " + sLineId + "\n# rule id: " + sRuleId);
                                    helpers.logerror(e);
                                }
                            }
                        }
                    }
                }
            }
        }
        if (bChange) {
            return [s, dErrs];
        }
        return [false, dErrs];
    },

    _createError: function (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bIdRule, sOption, bContext) {
        let oErr = {};
        oErr["nStart"] = nOffset + m.start[iGroup];
        oErr["nEnd"] = nOffset + m.end[iGroup];
        oErr["sLineId"] = sLineId;
        oErr["sRuleId"] = sRuleId;
        oErr["sType"] = (sOption) ? sOption : "notype";
        // suggestions
        if (sRepl.slice(0,1) === "=") {
            let sugg = oEvalFunc[sRepl.slice(1)](s, m);
            if (sugg) {
                if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) {
                    oErr["aSuggestions"] = capitalizeArray(sugg.split("|"));
                } else {
                    oErr["aSuggestions"] = sugg.split("|");
                }
            } else {
                oErr["aSuggestions"] = [];
            }
        } else if (sRepl == "_") {
            oErr["aSuggestions"] = [];
        } else {
            if (bUppercase && m[iGroup].slice(0,1).gl_isUpperCase()) {
                oErr["aSuggestions"] = capitalizeArray(sRepl.gl_expand(m).split("|"));
            } else {
                oErr["aSuggestions"] = sRepl.gl_expand(m).split("|");
            }
        }
        // Message
        let sMessage = "";
        if (sMsg.slice(0,1) === "=") {
            sMessage = oEvalFunc[sMsg.slice(1)](s, m);
        } else {
            sMessage = sMsg.gl_expand(m);
        }
        if (bIdRule) {
            sMessage += " ##" + sLineId + " #" + sRuleId;
        }
        oErr["sMessage"] = sMessage;
        // URL
        oErr["URL"] = sURL || "";
        // Context
        if (bContext) {
            oErr["sUnderlined"] = sx.slice(m.start[iGroup], m.end[iGroup]);
            oErr["sBefore"] = sx.slice(Math.max(0, m.start[iGroup]-80), m.start[iGroup]);
            oErr["sAfter"] = sx.slice(m.end[iGroup], m.end[iGroup]+80);
        }
        return oErr;
    },

    _rewrite: function (s, sRepl, iGroup, m, bUppercase) {
        // text processor: write sRepl in s at iGroup position"
        let ln = m.end[iGroup] - m.start[iGroup];
        let sNew = "";
        if (sRepl === "*") {
            sNew = " ".repeat(ln);
        } else if (sRepl === ">" || sRepl === "_" || sRepl === "~") {
            sNew = sRepl + " ".repeat(ln-1);
        } else if (sRepl === "@") {
            sNew = "@".repeat(ln);
        } else if (sRepl.slice(0,1) === "=") {
            sNew = oEvalFunc[sRepl.slice(1)](s, 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);
        }
        //helpers.echo("\n"+s+"\nstart: "+m.start[iGroup]+" end:"+m.end[iGroup])
        return s.slice(0, m.start[iGroup]) + sNew + s.slice(m.end[iGroup]);
    },

    // Actions on rules

    ignoreRule: function (sRuleId) {
        _aIgnoredRules.add(sRuleId);
    },

    resetIgnoreRules: function () {
        _aIgnoredRules.clear();
    },

    reactivateRule: function (sRuleId) {
        _aIgnoredRules.delete(sRuleId);
    },

    listRules: function* (sFilter=null) {
        // generator: returns tuple (sOption, sLineId, sRuleId)
        try {
            for (let [sOption, lRuleGroup] of this._getRules(true)) {
                for (let [,, sLineId, sRuleId,,] of lRuleGroup) {
                    if (!sFilter || sRuleId.test(sFilter)) {
                        yield [sOption, sLineId, sRuleId];
                    }
                }
            }
            for (let [sOption, lRuleGroup] of this._getRules(false)) {
                for (let [,, sLineId, sRuleId,,] of lRuleGroup) {
                    if (!sFilter || sRuleId.test(sFilter)) {
                        yield [sOption, sLineId, sRuleId];
                    }
                }
            }
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    _getRules: function (bParagraph) {
        if (!bParagraph) {
            return gc_rules.lSentenceRules;
        }
        return gc_rules.lParagraphRules;
    },

    //// Initialization

    load: function (sContext="JavaScript", sPath="") {
        try {
            if (typeof(require) !== 'undefined') {
                var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
                _oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            } else {
                _oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
            _oSpellChecker.activateStorage();
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    getSpellChecker: function () {
        return _oSpellChecker;
    },

    //// Options

    setOption: function (sOpt, bVal) {
        if (_dOptions.has(sOpt)) {
            _dOptions.set(sOpt, bVal);













<




<

<
<
|
<
<
<














>
>

|













|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<

|
<
<
|
|
<
<
>
>
|
<
>
|
|
>
>
|
<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
<
|
<
<
<
<
<
|
<
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
<
<


<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
|
<
<
<
<
<
<
|
<
<
<
<
|
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|

<
<
















|






|








|

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








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

// Grammar checker engine
/*jslint esversion: 6*/
/*global console,require,exports*/

"use strict";

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


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

    var gc_options = require("resource://grammalecte/${lang}/gc_options.js");
    var gc_rules = require("resource://grammalecte/${lang}/gc_rules.js");
    var cregex = require("resource://grammalecte/${lang}/cregex.js");
    var text = require("resource://grammalecte/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].gl_toCapitalize();
    }
    return aNew;
}


// data
let _sAppContext = "";                                  // what software is running
let _dOptions = null;
let _oSpellChecker = null;
let _oTokenizer = null;
let _aIgnoredRules = new Set();



var gc_engine = {

    //// Informations

    lang: "${lang}",
    locales: ${loc},
    pkg: "${implname}",
    name: "${name}",
    version: "${version}",
    author: "${author}",

    //// Initialization
























































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


        try {
            if (typeof(require) !== 'undefined') {


                var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
                _oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            } else {

                _oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
            _oTokenizer = _oSpellChecker.getTokenizer();
            _oSpellChecker.activateStorage();





        }















        catch (e) {

            console.error(e);





        }








    },
















    getSpellChecker: function () {
















        return _oSpellChecker;


    },








    //// Rules



























    getRules: function (bParagraph) {






        if (!bParagraph) {




            return gc_rules.lSentenceRules;

        }





















        return gc_rules.lParagraphRules;
    },



    ignoreRule: function (sRuleId) {
        _aIgnoredRules.add(sRuleId);
    },

    resetIgnoreRules: function () {
        _aIgnoredRules.clear();
    },

    reactivateRule: function (sRuleId) {
        _aIgnoredRules.delete(sRuleId);
    },

    listRules: function* (sFilter=null) {
        // generator: returns tuple (sOption, sLineId, sRuleId)
        try {
            for (let [sOption, lRuleGroup] of this.getRules(true)) {
                for (let [,, sLineId, sRuleId,,] of lRuleGroup) {
                    if (!sFilter || sRuleId.test(sFilter)) {
                        yield [sOption, sLineId, sRuleId];
                    }
                }
            }
            for (let [sOption, lRuleGroup] of this.getRules(false)) {
                for (let [,, sLineId, sRuleId,,] of lRuleGroup) {
                    if (!sFilter || sRuleId.test(sFilter)) {
                        yield [sOption, sLineId, sRuleId];
                    }
                }
            }
        }
        catch (e) {
            console.error(e);
        }






























    },

    //// Options

    setOption: function (sOpt, bVal) {
        if (_dOptions.has(sOpt)) {
            _dOptions.set(sOpt, bVal);
︙︙
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


    getDefaultOptions: function () {
        return gc_options.getOptions(_sAppContext).gl_shallowCopy();
    },

    resetOptions: function () {
        _dOptions = gc_options.getOptions(_sAppContext).gl_shallowCopy();

    }





















































































































































































































































































































































































































































































































































































































































































































































































































};


//////// Common functions

function option (sOpt) {
    // return true if option sOpt is active
    return _dOptions.get(sOpt);
}

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

function morph (dDA, aWord, sPattern, bStrict=true, bNoWord=false) {
    // analyse a tuple (position, word), return true if sPattern in morphologies (disambiguation on)
    if (!aWord) {
        //helpers.echo("morph: noword, returns " + bNoWord);
        return bNoWord;
    }
    //helpers.echo("aWord: "+aWord.toString());
    let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _oSpellChecker.getMorph(aWord[1]);
    //helpers.echo("lMorph: "+lMorph.toString());
    if (lMorph.length === 0) {
        return false;
    }
    //helpers.echo("***");
    if (bStrict) {
        return lMorph.every(s  =>  (s.search(sPattern) !== -1));
    }
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}

function morphex (dDA, 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) {
        //helpers.echo("morph: noword, returns " + bNoWord);
        return bNoWord;
    }
    //helpers.echo("aWord: "+aWord.toString());
    let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _oSpellChecker.getMorph(aWord[1]);
    //helpers.echo("lMorph: "+lMorph.toString());
    if (lMorph.length === 0) {
        return false;
    }
    //helpers.echo("***");
    // check negative condition
    if (lMorph.some(s  =>  (s.search(sNegPattern) !== -1))) {
        return false;
    }
    // search sPattern
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}

function analyse (sWord, sPattern, bStrict=true) {
    // analyse a word, return true if sPattern in morphologies (disambiguation off)
    let lMorph = _oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0) {
        return false;
    }
    if (bStrict) {
        return lMorph.every(s  =>  (s.search(sPattern) !== -1));
    }
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}

function analysex (sWord, sPattern, sNegPattern) {
    // analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)
    let lMorph = _oSpellChecker.getMorph(sWord);
    if (lMorph.length === 0) {
        return false;
    }
    // check negative condition
    if (lMorph.some(s  =>  (s.search(sNegPattern) !== -1))) {
        return false;
    }
    // search sPattern
    return lMorph.some(s  =>  (s.search(sPattern) !== -1));
}


//// 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-ʯfi-st%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+)", "ig");
    let m = z.exec(s.slice(iStart));








>
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>










<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|








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
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
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
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
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940





941















































































942
943
944
945
946
947
948
949


    getDefaultOptions: function () {
        return gc_options.getOptions(_sAppContext).gl_shallowCopy();
    },

    resetOptions: function () {
        _dOptions = gc_options.getOptions(_sAppContext).gl_shallowCopy();
    },

    //// Parsing

    parse: function (sText, sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false) {
        let oText = new TextParser(sText);
        return oText.parse(sCountry, bDebug, dOptions, bContext);
    },

    _zEndOfSentence: new RegExp ('([.?!:;…][ .?!… »”")]*|.$)', "g"),
    _zBeginOfParagraph: new RegExp ("^[-  –—.,;?!…]*", "ig"),
    _zEndOfParagraph: new RegExp ("[-  .,;?!…–—]*$", "ig"),

    getSentenceBoundaries: function* (sText) {
        let mBeginOfSentence = this._zBeginOfParagraph.exec(sText);
        let iStart = this._zBeginOfParagraph.lastIndex;
        let m;
        while ((m = this._zEndOfSentence.exec(sText)) !== null) {
            yield [iStart, this._zEndOfSentence.lastIndex];
            iStart = this._zEndOfSentence.lastIndex;
        }
    }
};


class TextParser {

    constructor (sText) {
        this.sText = sText;
        this.sText0 = sText;
        this.sSentence = "";
        this.sSentence0 = "";
        this.nOffsetWithinParagraph = 0;
        this.lToken = [];
        this.dTokenPos = new Map();
        this.dTags = new Map();
        this.dError = new Map();
        this.dErrorPriority = new Map();  // Key = position; value = priority
    }

    asString () {
        let s = "===== TEXT =====\n"
        s += "sentence: " + this.sSentence0 + "\n";
        s += "now:      " + this.sSentence  + "\n";
        for (let dToken of this.lToken) {
            s += '#${dToken["i"]}\t${dToken["nStart"]}:{$dToken["nEnd"]}\t${dToken["sValue"]}\t${dToken["sType"]}';
            if (dToken.has("lMorph")) {
                s += "\t" + dToken["lMorph"].toString();
            }
            if (dToken.has("tags")) {
                s += "\t" + dToken["tags"].toString();
            }
            s += "\n";
        }
        return s;
    }

    parse (sText, sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false) {
        // analyses the paragraph sText and returns list of errors
        let dOpt = dOptions || gc_engine.dOptions;
        // parse paragraph
        try {
            this.parseText(this.sText, this.sText0, true, 0, sCountry, dOpt, bDebug, bContext);
        }
        catch (e) {
            console.error(e);
        }

        // cleanup
        if (this.sText.includes(" ")) {
            this.sText = this.sText.replace(/ /g, ' '); // nbsp
        }
        if (this.sText.includes(" ")) {
            this.sText = this.sText.replace(/ /g, ' '); // snbsp
        }
        if (this.sText.includes("'")) {
            this.sText = this.sText.replace(/'/g, "’");
        }
        if (this.sText.includes("‑")) {
            this.sText = this.sText.replace(/‑/g, "-"); // nobreakdash
        }

        // parse sentence
        for (let [iStart, iEnd] of gc_engine.getSentenceBoundaries(this.sText)) {
            try {
                this.sSentence = this.sText.slice(iStart, iEnd);
                this.sSentence0 = this.sText0.slice(iStart, iEnd);
                this.nOffsetWithinParagraph = iStart;
                this.lToken = Array.from(_oTokenizer.genTokens(this.sSentence, true));
                this.dTokenPos.clear();
                for (let dToken of this.lToken) {
                    if (dToken["sType"] != "INFO") {
                        this.dTokenPos.set(dToken["nStart"], dToken);
                    }
                }
                this.parseText(this.sSentence, this.sSentence0, false, iStart, sCountry, dOpt, bDebug, bContext);
            }
            catch (e) {
                console.error(e);
            }
        }
        return Array.from(this.dError.values());
    }

    parseText (sText, sText0, bParagraph, nOffset, sCountry, dOptions, bDebug, bContext) {
        let bChange = false;
        let bIdRule = option('idrule');

        for (let [sOption, lRuleGroup] of gc_engine.getRules(bParagraph)) {
            if (sOption == "@@@@") {
                // graph rules
                if (!bParagraph && bChange) {
                    this.update(sText, bDebug);
                    bChange = false;
                }
                for (let [sGraphName, sLineId] of lRuleGroup) {
                    if (!dOptions.has(sGraphName) || dOptions.get(sGraphName)) {
                        if (bDebug) {
                            console.log("\n>>>> GRAPH: " + sGraphName + " " + sLineId);
                        }
                        sText = this.parseGraph(gc_rules_graph.dAllGraph.get(sGraphName), sCountry, dOptions, bDebug, bContext);
                    }
                }
            }
            else if (!sOption || option(sOption)) {
                for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
                    if (!_aIgnoredRules.has(sRuleId)) {
                        while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) {
                            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, dDA, sCountry, bCondMemo));
                                    if (bCondMemo) {
                                        switch (cActionType) {
                                            case "-":
                                                // grammar error
                                                //console.log("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source);
                                                nErrorStart = nOffset + m.start[eAct[0]];
                                                if (!this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart)) {
                                                    this.dError.set(nErrorStart, this._createErrorFromRegex(sText, sText0, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bIdRule, sOption, bContext));
                                                    this.dErrorPriority.set(nErrorStart, nPriority);
                                                }
                                                break;
                                            case "~":
                                                // text processor
                                                //console.log("-> text processor by " + sLineId + "\nzRegex: " + zRegex.source);
                                                sText = this.rewriteText(sText, sWhat, eAct[0], m, bUppercase);
                                                bChange = true;
                                                if (bDebug) {
                                                    console.log("~ " + sText + "  -- " + m[eAct[0]] + "  # " + sLineId);
                                                }
                                                break;
                                            case "=":
                                                // disambiguation
                                                //console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
                                                oEvalFunc[sWhat](sText, m, dDA);
                                                if (bDebug) {
                                                    console.log("= " + m[0] + "  # " + sLineId + "\nDA: " + dDA.gl_toString());
                                                }
                                                break;
                                            case ">":
                                                // we do nothing, this test is just a condition to apply all following actions
                                                break;
                                            default:
                                                console.log("# error: unknown action at " + sLineId);
                                        }
                                    } else {
                                        if (cActionType == ">") {
                                            break;
                                        }
                                    }
                                }
                                catch (e) {
                                    console.log(s);
                                    console.log("# line id: " + sLineId + "\n# rule id: " + sRuleId);
                                    console.error(e);
                                }
                            }
                        }
                    }
                }
            }
        }
        if (bChange) {
            if (bParagraph) {
                this.sText = sText;
            } else {
                this.sSentence = sText
            }
        }
    }

    update (sSentence, bDebug=false) {
        // update <sSentence> and retokenize
        this.sSentence = sSentence;
        let lNewToken = Array.from(_oTokenizer.genTokens(sSentence, true));
        for (let dToken of lNewToken) {
            if (this.dTokenPos.gl_get(dToken["nStart"], {}).has("lMorph")) {
                dToken["lMorph"] = this.dTokenPos.gl_get(dToken["nStart"], {}).get("lMorph");
            }
            if (this.dTokenPos.gl_get(dToken["nStart"], {}).has("tags")) {
                dToken["tags"] = this.dTokenPos.gl_get(dToken["nStart"], {}).get("tags");
            }
        }
        this.lToken = lNewToken;
        this.dTokenPos.clear();
        for (let dToken of this.lToken) {
            if (dToken["sType"] != "INFO") {
                this.dTokenPos.set(dToken["nStart"], dToken);
            }
        }
        if (bDebug) {
            console.log("UPDATE:");
            console.log(this.asString());
        }
    }

    _getNextPointers (self, dToken, dGraph, dPointer, bDebug=false) {
        // generator: return nodes where <dToken> “values” match <dNode> arcs
        let dNode = dPointer["dNode"];
        let iNode1 = dPointer["iNode1"];
        let bTokenFound = false;
        // token value
        if (dNode.hasOwnProperty(dToken["sValue"])) {
            if (bDebug) {
                console.log("  MATCH: " + dToken["sValue"]);
            }
            yield { "iNode1": iNode1, "dNode": dGraph[dNode[dToken["sValue"]]] };
            bTokenFound = true;
        }
        if (dToken["sValue"].slice(0,2).gl_isTitle()) { // we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
            let sValue = dToken["sValue"].toLowerCase();
            if (dNode.hasOwnProperty(sValue)) {
                if (bDebug) {
                    console.log("  MATCH: " + sValue);
                }
                yield { "iNode1": iNode1, "dNode": dGraph[dNode[sValue]] };
                bTokenFound = true;
            }
        }
        else if (dToken["sValue"].gl_isUpperCase()) {
            let sValue = dToken["sValue"].toLowerCase();
            if (dNode.hasOwnProperty(sValue)) {
                if (bDebug) {
                    console.log("  MATCH: " + sValue);
                }
                yield { "iNode1": iNode1, "dNode": dGraph[dNode[sValue]] };
                bTokenFound = true;
            }
            sValue = dToken["sValue"].gl_toCapitalize();
            if (dNode.hasOwnProperty(sValue)) {
                if (bDebug) {
                    console.log("  MATCH: " + sValue);
                }
                yield { "iNode1": iNode1, "dNode": dGraph[dNode[sValue]] };
                bTokenFound = true;
            }
        }
        // regex value arcs
        if (dToken["sType"] != "INFO"  &&  dToken["sType"] != "PUNC"  &&  dToken["sType"] != "SIGN") {
            if (dNode.hasOwnProperty("<re_value>")) {
                for (let sRegex in dNode["<re_value>"]) {
                    if (!sRegex.includes("¬")) {
                        // no anti-pattern
                        if (dToken["sValue"].search(sRegex) !== -1):
                            if (bDebug) {
                                console.log("  MATCH: ~" + sRegex);
                            }
                            yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_value>"][sRegex]] };
                            bTokenFound = true;
                    } else {
                        // there is an anti-pattern
                        let [sPattern, sNegPattern] = sRegex.split("¬", 1);
                        if (sNegPattern && dToken["sValue"].search(sNegPattern) !== -1) {
                            continue;
                        }
                        if (!sPattern || dToken["sValue"].search(sPattern) !== -1) {
                            if (bDebug) {
                                console.log("  MATCH: ~" + sRegex);
                            }
                            yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_value>"][sRegex]] };
                            bTokenFound = true;
                        }
                    }
                }
            }
        }
        // analysable tokens
        if (dToken["sType"].slice(0,4) == "WORD") {
            // token lemmas
            if (dNode.hasOwnProperty("<lemmas>")) {
                for (let sLemma of _oSpellChecker.getLemma(dToken["sValue"])) {
                    if (dNode["<lemmas>"].hasOwnProperty(sLemma)) {
                        if (bDebug) {
                            console.log("  MATCH: >" + sLemma);
                        }
                        yield { "iNode1": iNode1, "dNode": dGraph[dNode["<lemmas>"][sLemma]] };
                        bTokenFound = true;
                    }
                }
            }
            // regex morph arcs
            if (dNode.hasOwnProperty("<re_morph>")) {
                for (let sRegex in dNode["<re_morph>"]) {
                    if (!sRegex.includes("¬")) {
                        // no anti-pattern
                        let lMorph = dToken._get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]));
                        if (lMorph.some(sMorph  =>  (sMorph.search(sRegex) !== -1))) {
                            if (bDebug) {
                                console.log("  MATCH: @" + sRegex);
                            }
                            yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] };
                            bTokenFound = true;
                        }
                    } else {
                        // there is an anti-pattern
                        let [sPattern, sNegPattern] = sRegex.split("¬", 1);
                        if (sNegPattern == "*") {
                            // all morphologies must match with <sPattern>
                            if (sPattern) {
                                let lMorph = dToken.gl_get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]));
                                if (lMorph.length > 0  &&  lMorph.every(sMorph  =>  (sMorph.search(sPattern) !== -1))) {
                                    if (bDebug) {
                                        console.log("  MATCH: @" + sRegex);
                                    }
                                    yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] };
                                    bTokenFound = true;
                                }
                            }
                        } else {
                            let lMorph = dToken.gl_get("lMorph", _oSpellChecker.getMorph(dToken["sValue"]));
                            if (sNegPattern  &&  lMorph.some(sMorph  =>  (sMorph.search(sNegPattern) !== -1))) {
                                continue;
                            }
                            if (!sPattern  ||  lMorph.some(sMorph  =>  (sMorph.search(sPattern) !== -1))) {
                                if (bDebug) {
                                    console.log("  MATCH: @" + sRegex);
                                }
                                yield { "iNode1": iNode1, "dNode": dGraph[dNode["<re_morph>"][sRegex]] };
                                bTokenFound = true;
                            }
                        }
                    }
                }
            }
        }
        // token tags
        if (dToken.hasOwnProperty("tags") && dNode.hasOwnProperty("<tags>")) {
            for (dToken["tags"].has(sTag)) {
                if (dNode["<tags>"].hasOwnProperty(sTag)) {
                    if (bDebug) {
                        console.log("  MATCH: /" + sTag);
                    }
                    yield { "iNode1": iNode1, "dNode": dGraph[dNode["<tags>"][sTag]] };
                    bTokenFound = true;
                }
            }
        }
        // meta arc (for token type)
        if (dNode.hasOwnProperty("<meta>")) {
            for (let sMeta in dNode["<meta>"]) {
                // no regex here, we just search if <dNode["sType"]> exists within <sMeta>
                if (sMeta == "*" or dToken["sType"] == sMeta) {
                    if (bDebug) {
                        console.log("  MATCH: *" + sMeta);
                    }
                    yield { "iNode1": iNode1, "dNode": dGraph[dNode["<meta>"][sMeta]] };
                    bTokenFound = true;
                }
                else if (sMeta.includes("¬")) {
                    if (!sMeta.includes(dToken["sType"])) {
                        if (bDebug) {
                            console.log("  MATCH: *" + sMeta);
                        }
                        yield { "iNode1": iNode1, "dNode": dGraph[dNode["<meta>"][sMeta]] };
                        bTokenFound = true;
                    }
                }
            }
        }
        if (!bTokenFound  &&  dPointer.hasOwnProperty("bKeep")) {
            yield dPointer;
        }
        // JUMP
        // Warning! Recurssion!
        if (dNode.has("<>")) {
            let dPointer2 = { "iNode1": iNode1, "dNode": dGraph[dNode["<>"]], "bKeep": True };
            yield* this._getNextPointers(dToken, dGraph, dPointer2, bDebug);
        }
    }

    parseGraph (dGraph, sCountry="${country_default}", dOptions=null, bShowRuleId=false, bDebug=false, bContext=false) {
        // parse graph with tokens from the text and execute actions encountered
        let lPointer = [];
        let bTagAndRewrite = false;
        for let [iToken, dToken] in this.lToken.entries():
            if (bDebug) {
                console.log("TOKEN: " + dToken["sValue"]);
            }
            // check arcs for each existing pointer
            let lNextPointer = [];
            for (let dPointer of lPointer) {
                lNextPointer.push(...this._getNextPointers(dToken, dGraph, dPointer, bDebug));
            }
            lPointer = lNextPointer;
            // check arcs of first nodes
            lPointer.push(...this._getNextPointers(dToken, dGraph, { "iNode1": iToken, "dNode": dGraph[0] }, bDebug));
            // check if there is rules to check for each pointer
            for (let dPointer of lPointer) {
                //if bDebug:
                //    console.log("+", dPointer);
                if ("<rules>" in dPointer["dNode"]) {
                    let bChange = this._executeActions(dGraph, dPointer["dNode"]["<rules>"], dPointer["iNode1"]-1, iToken, dOpt, sCountry, bShowRuleId, bDebug, bContext);
                    if (bChange) {
                        bTagAndRewrite = true;
                    }
                }
            }
        if (bTagAndRewrite) {
            this.rewriteFromTags(bDebug);
        }
        if (bDebug) {
            console.log(this);
        }
        return this.sSentence;
    }

    _executeActions (dGraph, dNode, nTokenOffset, nLastToken, dOptions, sCountry, bShowRuleId, bDebug, bContext) {
        // execute actions found in the DARG
        let bChange = false;
        for (let [sLineId, nextNodeKey] of Object.entries(dNode)) {
            let bCondMemo = null;
            for sRuleId in dGraph[nextNodeKey]:
                try {
                    if (bDebug) {
                        console.log("   >TRY: " + sRuleId);
                    }
                    let [sOption, sFuncCond, cActionType, sWhat, ...eAct] = gc_rules_graph.dRule[sRuleId];
                    // Suggestion    [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ]
                    // TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ]
                    // 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, sURL] = eAct;
                                let nTokenErrorStart = (iTokenStart > 0) ? nTokenOffset + iTokenStart : nLastToken + iTokenStart;
                                if (this.lToken[nTokenErrorStart].hasOwnProperty("bImmune")) {
                                    let nTokenErrorEnd = (iTokenEnd > 0) ? nTokenOffset + iTokenEnd : nLastToken + iTokenEnd;
                                    let nErrorStart = this.nOffsetWithinParagraph + ((cStartLimit == "<") ? this.lToken[nTokenErrorStart]["nStart"] : this.lToken[nTokenErrorStart]["nEnd"]);
                                    let nErrorEnd = this.nOffsetWithinParagraph + ((cEndLimit == ">") ? this.lToken[nTokenErrorEnd]["nEnd"] : this.lToken[nTokenErrorEnd]["nStart"]);
                                    if (this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart, -1)) {
                                        this.dError[nErrorStart] = this._createErrorFromTokens(sWhat, nTokenOffset, nLastToken, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, bCaseSvty, sMessage, sURL, bShowRuleId, sOption, bContext);
                                        this.dErrorPriority[nErrorStart] = nPriority;
                                        if (bDebug) {
                                            console.log("    NEW_ERROR:  {}  {}:  {}".format(sRuleId, sLineId, this.dError[nErrorStart]));
                                        }
                                    }
                                }
                            }
                            else if (cActionType == "~") {
                                // text processor
                                let nTokenStart = (eAct[0] > 0) ? nTokenOffset + eAct[0] : nLastToken + eAct[0];
                                let nTokenEnd = (eAct[1] > 0) ? nTokenOffset + eAct[1] : nLastToken + eAct[1];
                                this._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug);
                                bChange = true;
                                if (bDebug) {
                                    console.log("    TEXT_PROCESSOR:  " + sRuleId + " " + sLineId);
                                    console.log("       " + this.lToken[nTokenStart]["sValue"] + " : " + this.lToken[nTokenEnd]["sValue"] + "  > ", sWhat);
                                }
                            }
                            else if (cActionType == "=") {
                                // disambiguation
                                oEvalFunc[sWhat](this.lToken, nTokenOffset, nLastToken);
                                if (bDebug) {
                                    console.log("    DISAMBIGUATOR:  {} {} ({})  {}:{}".format(sRuleId, sLineId, 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) {
                                    console.log("    COND_OK:  " + sRuleId + " " + sLineId);
                                }
                            }
                            else if (cActionType == "/") {
                                // Tag
                                let nTokenStart = (eAct[0] > 0) ? nTokenOffset + eAct[0] : nLastToken + eAct[0];
                                let nTokenEnd = (eAct[1] > 0) ? nTokenOffset + eAct[1] : nLastToken + eAct[1];
                                for (let i = nTokenStart; i <= nTokenEnd; i++) {
                                    if (this.lToken[i].hasOwnProperty("tags")) {
                                        this.lToken[i]["tags"].add(...sWhat.split("|"))
                                    } else {
                                        this.lToken[i]["tags"] = new Set(sWhat.split("|"));
                                    }
                                }
                                if (bDebug) {
                                    console.log("    TAG:  " + sRuleId + " " + sLineId);
                                    console.log("       " + sWhat + " > " + this.lToken[nTokenStart]["sValue"] + " : " + this.lToken[nTokenEnd]["sValue"]);
                                }
                                if (!this.dTags.has(sWhat)) {
                                    this.dTags.set(sWhat, [nTokenStart, nTokenStart]);
                                } else {
                                    this.dTags.set(sWhat, [min(nTokenStart, this.dTags.get(sWhat)[0], max(nTokenEnd, this.dTags.get(sWhat)[1]]);
                                }
                            }
                            else if (cActionType == "%") {
                                // immunity
                                if (bDebug) {
                                    console.log("    IMMUNITY:\n      " + _rules_graph.dRule[sRuleId]);;
                                }
                                nTokenStart = (eAct[0] > 0) ? nTokenOffset + eAct[0] : else nLastToken + eAct[0];
                                nTokenEnd = (eAct[1] > 0) ? nTokenOffset + eAct[1] : else nLastToken + eAct[1];
                                if (nTokenEnd - nTokenStart == 0) {
                                    this.lToken[nTokenStart]["bImmune"] = True
                                    let nErrorStart = this.nOffsetWithinParagraph + this.lToken[nTokenStart]["nStart"];
                                    if (nErrorStart in this.dError) {
                                        this.dError.delete(nErrorStart);
                                    }
                                } else {
                                    for (let i = nTokenStart;  i <= nTokenEnd;  i++) {
                                        this.lToken[i]["bImmune"] = true;
                                        let nErrorStart = this.nOffsetWithinParagraph + this.lToken[i]["nStart"];
                                        if (nErrorStart in this.dError) {
                                            this.dError.delete(nErrorStart);
                                        }
                                    }
                                }
                            } else {
                                console.log("# error: unknown action at " + sLineId);
                            }
                        }
                        else if (cActionType == ">") {
                            if (bDebug) {
                                console.log("    COND_BREAK:  " + sRuleId + " " + sLineId);
                            }
                            break;
                        }
                    }
                }
                catch (e) {
                    console.log("Error: ", sLineId, sRuleId, this.sSentence);
                    console.error(e);
                }
        }
        return bChange;
    }

    _createErrorFromRegex (sText, sText0, sSugg, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, 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 (bUppercase && lSugg.length > 0 && m[iGroup].slice(0,1).gl_isUpperCase()) {
            lSugg = 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 (self, sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) {
        // suggestions
        let lSugg = [];
        if (sSugg.startsWith("=")) {
            sSugg = oEvalFunc[sSugg.slice(1)](self.lToken, nTokenOffset, nLastToken);
            lSugg = (sSugg) ? sSugg.split("|") : [];
        } else if (sSugg == "_") {
            lSugg = [];
        } else {
            lSugg = self._expand(sSugg, nTokenOffset, nLastToken).split("|");
        }
        if (bCaseSvty && lSugg.length > 0 && self.lToken[iFirstToken]["sValue"].slice(0,1).isupper()) {
            lSugg = capitalizeArray(lSugg);
        }
        // Message
        let sMessage = (sMsg.startsWith("=")) ? oEvalFunc[sMsg.slice(1)](self.lToken, nTokenOffset, nLastToken) : self._expand(sMsg, nTokenOffset, nLastToken);
        if (bShowRuleId) {
            sMessage += " ## " + sLineId + " # " + sRuleId;
        }
        //
        return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext);
    }

    _createError (nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) {
        oErr = {
            "nStart": nStart,
            "nEnd": nEnd,
            "sLineId": sLineId,
            "sRuleId": sRuleId,
            "sType": sOption  if sOption  else "notype",
            "sMessage": sMessage,
            "aSuggestions": lSugg,
            "URL": sURL
        }
        if (bContext) {
            oErr['sUnderlined'] = self.sText0.slice(nStart, nEnd);
            oErr['sBefore'] = self.sText0.slice(Math.max(0,nStart-80), nStart);
            oErr['sAfter'] = self.sText0.slice(nEnd, nEnd+80);
        }
        return oErr;
    }

    _expand (sText, nTokenOffset, nLastToken) {
        let m;
        while ((m = /\\(-?[0-9]+)/.exec(sText)) !== null) {
            if (m[1][0:1] == "-") {
                sText = sText.replace(m[0], self.lToken[nLastToken+parseInt(m[1],10)+1]["sValue"]);
            } else {
                sText = sText.replace(m[0], self.lToken[nTokenOffset+parseInt(m[1],10)]["sValue"]);
            }
        }
        return sText;
    }

    rewriteText (sText, sRepl, iGroup, m, bUppercase) {
        // text processor: write sRepl in sText at iGroup position"
        let ln = m.end[iGroup] - m.start[iGroup];
        let sNew = "";
        if (sRepl === "*") {
            sNew = " ".repeat(ln);
        } else if (sRepl === ">" || sRepl === "_" || sRepl === "~") {
            sNew = sRepl + " ".repeat(ln-1);
        } 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);
        }
        //console.log("\n"+sText+"\nstart: "+m.start[iGroup]+" end:"+m.end[iGroup])
        return sText.slice(0, m.start[iGroup]) + sNew + sText.slice(m.end[iGroup]);
    }

    _tagAndPrepareTokenForRewriting (sWhat, nTokenRewriteStart, nTokenRewriteEnd, nTokenOffset, nLastToken, bCaseSvty, bDebug) {
        // text processor: rewrite tokens between <nTokenRewriteStart> and <nTokenRewriteEnd> position
        if (bDebug) {
            console.log("     START: ${nTokenRewriteStart} - END: ${nTokenRewriteEnd}  ");
        }
        if (sWhat === "*") {
            // purge text
            if (nTokenRewriteEnd - nTokenRewriteStart == 0) {
                this.lToken[nTokenRewriteStart]["bToRemove"] = true;
            } else {
                for (let i = nTokenRewriteStart;  i <= nTokenRewriteEnd;  i++) {
                    this.lToken[i]["bToRemove"] = true;
                }
            }
        }
        else if (sWhat === "␣") {
            // merge tokens
            this.lToken[nTokenRewriteStart]["nMergeUntil"] = nTokenRewriteEnd;
        }
        else if (sWhat === "_") {
            // neutralized token
            if (nTokenRewriteEnd - nTokenRewriteStart == 0) {
                this.lToken[nTokenRewriteStart]["sNewValue"] = "_";
            } else {
                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).isupper();
            if (nTokenRewriteEnd - nTokenRewriteStart == 0) {
                // one token
                if (bUppercase) {
                    sWhat = sWhat.gl_toCapitalize();
                }
                this.lToken[nTokenRewriteStart]["sNewValue"] = sWhat;
            }
            else {
                // several tokens
                let lTokenValue = sWhat.split("|");
                if (lTokenValue.length != (nTokenRewriteEnd - nTokenRewriteStart + 1)) {
                    console.log("Error. Text processor: number of replacements != number of tokens.");
                    return;
                }
                let j = 0;
                for (let i = nTokenRewriteStart;  i <= nTokenRewriteEnd;  i++) {
                    let sValue = lTokenValue[j];
                    if (!sValue || sValue === "*") {
                        this.lToken[i]["bToRemove"] = true;
                    } else {
                        if (bUppercase) {
                            sValue = sValue.gl_toCapitalize();
                        }
                        this.lToken[i]["sNewValue"] = sValue;
                    }
                    j++;
                }
            }
        }
    }

    rewriteFromTags (self, bDebug=false) {
        // rewrite the sentence, modify tokens, purge the token list
        if (bDebug) {
            console.log("REWRITE");
        }
        let lNewToken = [];
        let nMergeUntil = 0;
        let dTokenMerger = null;
        for (let [iToken, dToken] in this.lToken.entries()) {
            let bKeepToken = true;
            if (dToken["sType"] != "INFO") {
                if (nMergeUntil && iToken <= nMergeUntil) {
                    dTokenMerger["sValue"] += " ".repeat(dToken["nStart"] - dTokenMerger["nEnd"]) + dToken["sValue"];
                    dTokenMerger["nEnd"] = dToken["nEnd"];
                    if (bDebug) {
                        console.log("  MERGED TOKEN: " + dTokenMerger["sValue"]);
                    }
                    bKeepToken = false;
                }
                if (dToken.hasOwnProperty("nMergeUntil")) {
                    if (iToken > nMergeUntil) { // this token is not already merged with a previous token
                        dTokenMerger = dToken;
                    }
                    if (dToken["nMergeUntil"] > nMergeUntil) {
                        nMergeUntil = dToken["nMergeUntil"];
                    }
                    delete dToken["nMergeUntil"];
                }
                else if (dToken.hasOwnProperty("bToRemove")) {
                    if (bDebug) {
                        console.log("  REMOVED: " + dToken["sValue"]);
                    }
                    this.sSentence = this.sSentence.slice(0, dToken["nStart"]) + " ".repeat(dToken["nEnd"] - dToken["nStart"]) + this.sSentence.slice(dToken["nEnd"]);
                    bKeepToken = false;
                }
            }
            //
            if (bKeepToken) {
                lNewToken.push(dToken);
                if (dToken.hasOwnProperty("sNewValue")) {
                    // rewrite token and sentence
                    if (bDebug) {
                        console.log(dToken["sValue"] + " -> " + dToken["sNewValue"]);
                    }
                    dToken["sRealValue"] = dToken["sValue"];
                    dToken["sValue"] = dToken["sNewValue"];
                    nDiffLen = len(dToken["sRealValue"]) - len(dToken["sNewValue"]);
                    sNewRepl = (nDiffLen >= 0) ? (dToken["sNewValue"] + " ".repeat(nDiffLen) : dToken["sNewValue"].slice(0, len(dToken["sRealValue"]));
                    this.sSentence = this.sSentence[:dToken["nStart"]] + sNewRepl + this.sSentence[dToken["nEnd"]:];
                    delete dToken["sNewValue"];
                }
            }
            else {
                try {
                    this.dTokenPos.delete(dToken["nStart"]);
                }
                catch (e) {
                    console.log(this.asString());
                    console.log(dToken);
                }
            }
        }
        if (bDebug) {
            console.log("  TEXT REWRITED: " + this.sSentence);
        }
        this.lToken.clear();
        this.lToken = lNewToken;
    }

};


//////// Common functions

function option (sOpt) {
    // return true if option sOpt is active
    return _dOptions.get(sOpt);
}






















































































//////// 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-ʯfi-st%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+)", "ig");
    let m = z.exec(s.slice(iStart));
︙︙
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

    try {
        if (zNegPattern && zNegPattern.test(s)) {
            return false;
        }
        return zPattern.test(s);
    }
    catch (e) {
        helpers.logerror(e);
    }
    return false;
}

function look_chk1 (dDA, s, nOffset, zPattern, sPatternGroup1, sNegPatternGroup1=null) {
    // returns True if s has pattern zPattern and m.group(1) has pattern sPatternGroup1
    let m = zPattern.gl_exec2(s, null);
    if (!m) {
        return false;
    }
    try {
        let sWord = m[1];
        let nPos = m.start[1] + nOffset;
        if (sNegPatternGroup1) {
            return morphex(dDA, [nPos, sWord], sPatternGroup1, sNegPatternGroup1);
        } 
        return morph(dDA, [nPos, sWord], sPatternGroup1, false);
    }
    catch (e) {
        helpers.logerror(e);

























































































































































































































        return false;
    }











}


//////// Disambiguator

function select (dDA, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (dDA.has(nPos)) {
        return true;
    }
    let lMorph = _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) {
            dDA.set(nPos, lSelect);
        }
    } else if (lDefault) {
        dDA.set(nPos, lDefaul);
    }
    return true;
}

function exclude (dDA, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (dDA.has(nPos)) {
        return true;
    }
    let lMorph = _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) {
            dDA.set(nPos, lSelect);
        }
    } else if (lDefault) {
        dDA.set(nPos, lDefault);
















































    }
    return true;
}

function define (dDA, nPos, lMorph) {




    dDA.set(nPos, lMorph);






    return true;
}


//////// GRAMMAR CHECKER PLUGINS

${pluginsJS}


${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;
    exports.author = gc_engine.author;
    exports.parse = gc_engine.parse;
    exports._zEndOfSentence = gc_engine._zEndOfSentence;
    exports._zBeginOfParagraph = gc_engine._zBeginOfParagraph;
    exports._zEndOfParagraph = gc_engine._zEndOfParagraph;
    exports._getSentenceBoundaries = gc_engine._getSentenceBoundaries;
    exports._proofread = gc_engine._proofread;
    exports._createError = gc_engine._createError;
    exports._rewrite = gc_engine._rewrite;
    exports.ignoreRule = gc_engine.ignoreRule;
    exports.resetIgnoreRules = gc_engine.resetIgnoreRules;
    exports.reactivateRule = gc_engine.reactivateRule;
    exports.listRules = gc_engine.listRules;
    exports._getRules = gc_engine._getRules;
    exports.load = gc_engine.load;
    exports.getSpellChecker = gc_engine.getSpellChecker;
    exports.setOption = gc_engine.setOption;
    exports.setOptions = gc_engine.setOptions;
    exports.getOptions = gc_engine.getOptions;
    exports.getDefaultOptions = gc_engine.getDefaultOptions;
    exports.resetOptions = gc_engine.resetOptions;
}








|















|



|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>


>
>
>
>
>
>
>
>
>
>
>





|



|









|


|




|



|









|


|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>




|
>
>
>
>
|
>
>
>
>
>
>











>
>
















|




|









989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
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

    try {
        if (zNegPattern && zNegPattern.test(s)) {
            return false;
        }
        return zPattern.test(s);
    }
    catch (e) {
        console.error(e);
    }
    return false;
}

function look_chk1 (dDA, s, nOffset, zPattern, sPatternGroup1, sNegPatternGroup1=null) {
    // returns True if s has pattern zPattern and m.group(1) has pattern sPatternGroup1
    let m = zPattern.gl_exec2(s, null);
    if (!m) {
        return false;
    }
    try {
        let sWord = m[1];
        let nPos = m.start[1] + nOffset;
        if (sNegPatternGroup1) {
            return morphex(dDA, [nPos, sWord], sPatternGroup1, sNegPatternGroup1);
        }
        return morph(dDA, [nPos, sWord], sPatternGroup1, false);
    }
    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 = _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])).has("lMorph") ? dTokenPos.get(aWord[0])["lMorph"] : _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 = _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 (dToken, sValues, nLeft=null, nRight=null) {
    // test if <dToken['sValue']> is in sValues (each value should be separated with |)
    let sValue = (nLeft === null) ? "|"+dToken["sValue"]+"|" : "|"+dToken["sValue"].slice(nLeft, nRight)+"|";
    if (sValues.includes(sValues)) {
        return 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".
        if (sValues.includes(sValue.toLowerCase())) {
            return true;
        }
    }
    else if (dToken["sValue"].gl_isUpperCase()) {
        //if sValue.lower() in sValues:
        //    return true;
        sValue = "|"+sValue[1:].gl_toCapitalize();
        if (sValues.includes(sValue)) {
            return true;
        }
    }
    return false;
}

function g_morph (dToken, 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 (dToken.hasOwnProperty("lMorph")) {
        lMorph = dToken["lMorph"];
    }
    else {
        if (nLeft !== null) {
            lMorph = _oSpellChecker.getMorph(dToken["sValue"].slice(nLeft, nRight));
            if (bMemorizeMorph) {
                dToken["lMorph"] = lMorph;
            }
        } else {
            lMorph = _oSpellChecker.getMorph(dToken["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 (dToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
    // analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
    if (nLeft !== null) {
        lMorph = _oSpellChecker.getMorph(dToken["sValue"].slice(nLeft, nRight));
        if (bMemorizeMorph) {
            dToken["lMorph"] = lMorph;
        }
    } else {
        lMorph = _oSpellChecker.getMorph(dToken["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 (dToken1, dToken2, cMerger, sPattern, sNegPattern="", bSetMorph=true) {
    // merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)
    let lMorph = _oSpellChecker.getMorph(dToken1["sValue"] + cMerger + dToken2["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) {
                dToken1["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) {
        dToken1["lMorph"] = lMorph;
    }
    return bResult;
}

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

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

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

function g_space_between_tokens (dToken1, dToken2, nMin, nMax=null) {
    let nSpace = dToken2["nStart"] - dToken1["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[-1];
    }
    return lToken[i];
}


//////// Disambiguator

function select (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (dTokenPos.has(nPos)) {
        return true;
    }
    let lMorph = _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.set(nPos, lSelect);
        }
    } else if (lDefault) {
        dTokenPos.set(nPos, lDefaul);
    }
    return true;
}

function exclude (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
    if (!sWord) {
        return true;
    }
    if (dTokenPos.has(nPos)) {
        return true;
    }
    let lMorph = _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.set(nPos, lSelect);
        }
    } else if (lDefault) {
        dTokenPos.set(nPos, lDefault);
    }
    return true;
}

function define (dTokenPos, nPos, lMorph) {
    dTokenPos.set(nPos, lMorph);
    return true;
}


//// Disambiguation for graph rules

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

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

function g_define (dToken, lMorph) {
    // set morphologies of <dToken>, always return true
    dToken["lMorph"] = lMorph;
    return true;
}

function g_define_from (dToken, nLeft=null, nRight=null) {
    if (nLeft !== null) {
        dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"].slice(nLeft, nRight));
    } else {
        dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"]);
    }
    return true;
}


//////// GRAMMAR CHECKER PLUGINS

${pluginsJS}


${callablesJS}


${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;
    exports.author = gc_engine.author;
    exports.parse = gc_engine.parse;
    exports._zEndOfSentence = gc_engine._zEndOfSentence;
    exports._zBeginOfParagraph = gc_engine._zBeginOfParagraph;
    exports._zEndOfParagraph = gc_engine._zEndOfParagraph;
    exports._getSentenceBoundaries = gc_engine._getSentenceBoundaries;
    exports._proofread = gc_engine._proofread;
    exports._createError = gc_engine._createError;
    exports.rewriteText = gc_engine.rewriteText;
    exports.ignoreRule = gc_engine.ignoreRule;
    exports.resetIgnoreRules = gc_engine.resetIgnoreRules;
    exports.reactivateRule = gc_engine.reactivateRule;
    exports.listRules = gc_engine.listRules;
    exports.getRules = gc_engine.getRules;
    exports.load = gc_engine.load;
    exports.getSpellChecker = gc_engine.getSpellChecker;
    exports.setOption = gc_engine.setOption;
    exports.setOptions = gc_engine.setOptions;
    exports.getOptions = gc_engine.getOptions;
    exports.getDefaultOptions = gc_engine.getDefaultOptions;
    exports.resetOptions = gc_engine.resetOptions;
}

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.008s