Grammalecte  Diff

Differences From Artifact [908b008d84]:

To Artifact [a71cf52ea3]:


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
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

+
+
+
+





+
+
+
+
+
+
+
+
+
+
+
+
+
+
+





-
+




-
-
-
-
-
-

-
-
-
-
-
-
-
+
-
-
-
-
-
+
-
-
-
-
+


-
+


+
+
+
+
+
+
+
+
+
+
+
-
+

-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+

-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+

-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+

-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+

-
-
-
-
-
-
-
+
+
+
+
+
+
+

-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+






-
-
-
-
-
-
+
+
+
+
+

-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

-
-
-
+
+
+

-
-
-
+
+
+

-
-
-
+
+
+

-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

-
+

-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

-
+
-
-
-
-
-
+
-
-
-
+

-
-
-
-
+
+
+
+
+
+
-
-
-
+

-
-
-
+
+
+

-
-
-
+
+
+

-
+
-
-
-
+
+
-
-
-
+
+
+
+
+


-
+









-
+



-
+



-
+

-
+





-
+







-
+


-
+




-
+



-
+









-
+


-
+




-
+



-
+







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

"use strict";

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


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/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]._toCapitalize();
        aNew[i] = aArray[i].gl_toCapitalize();
    }
    return aNew;
}

const ibdawg = require("resource://grammalecte/ibdawg.js");
const helpers = require("resource://grammalecte/helpers.js");
const gc_options = require("resource://grammalecte/${lang}/gc_options.js");
const cr = require("resource://grammalecte/${lang}/cregex.js");
const text = require("resource://grammalecte/text.js");
const echo = require("resource://grammalecte/helpers.js").echo;

const lang = "${lang}";
const locales = ${loc};
const pkg = "${implname}";
const name = "${name}";
const version = "${version}";
const author = "${author}";

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

let _sAppContext = "";                                  // what software is running
// grammar rules and dictionary
//const _rules = require("./gc_rules.js");
const _rules = require("resource://grammalecte/${lang}/gc_rules.js");
let _dOptions = gc_options.dOpt._shallowCopy();     // duplication necessary, to be able to reset to default
let _dOptions = null;
let _aIgnoredRules = new Set();
let _oDict = null;
let _dAnalyses = new Map();                        // cache for data from dictionary
let _dAnalyses = new Map();                             // cache for data from dictionary


var gc_engine = {

    //// Informations

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

///// Parsing
    //// Parsing

function parse (sText, sCountry="${country_default}", bDebug=false, bContext=false) {
    // analyses the paragraph sText and returns list of errors
    let dErrors;
    let errs;
    let sAlt = sText;
    let dDA = new Map();        // Disamnbiguator
    let dPriority = new Map();  // Key = position; value = priority
    let sNew = "";
    parse: function (sText, sCountry="${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] = _proofread(sText, sAlt, 0, true, dDA, dPriority, sCountry, bDebug, bContext);
        if (sNew) {
            sText = sNew;
        }
    }
    catch (e) {
        helpers.logerror(e);
    }
        // 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
    }
        // 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 _getSentenceBoundaries(sText)) {
        if (4 < (iEnd - iStart) < 2000) {
            dDA.clear();
            //echo(sText.slice(iStart, iEnd));
            try {
                [_, errs] = _proofread(sText.slice(iStart, iEnd), sAlt.slice(iStart, iEnd), iStart, false, dDA, dPriority, sCountry, bDebug, bContext);
                dErrors._update(errs);
            }
            catch (e) {
                helpers.logerror(e);
            }
        }
    }
    return Array.from(dErrors.values());
}
        // 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"),

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

function _proofread (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;
    _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 _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._exec2(s, lGroups, lNegLookBefore)) !== null) {
                        bCondMemo = null;
                        /*if (bDebug) {
                            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 {
                                //echo(oEvalFunc[sFuncCond]);
                                bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](s, sx, m, dDA, sCountry, bCondMemo))
                                if (bCondMemo) {
                                    switch (cActionType) {
                                        case "-":
                                            // grammar error
                                            //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, _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
                                            //echo("-> text processor by " + sLineId + "\nzRegex: " + zRegex.source);
                                            s = _rewrite(s, sWhat, eAct[0], m, bUppercase);
                                            bChange = true;
                                            if (bDebug) {
                                                echo("~ " + s + "  -- " + m[eAct[0]] + "  # " + sLineId);
                                            }
                                            break;
                                        case "=":
                                            // disambiguation
                                            //echo("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
                                            oEvalFunc[sWhat](s, m, dDA);
                                            if (bDebug) {
                                                echo("= " + m[0] + "  # " + sLineId + "\nDA: " + dDA._toString());
                                            }
                                            break;
                                        case ">":
                                            // we do nothing, this test is just a condition to apply all following actions
                                            break;
                                        default:
                                            echo("# error: unknown action at " + sLineId);
                                    }
                                } else {
                                    if (cActionType == ">") {
                                        break;
                                    }
                                }
                            }
                            catch (e) {
                                echo(s);
                                echo("# line id: " + sLineId + "\n# rule id: " + sRuleId);
                                helpers.logerror(e);
        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];
}
        if (bChange) {
            return [s, dErrs];
        }
        return [false, dErrs];
    },

function _createError (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[0] === "=") {
        let sugg = oEvalFunc[sRepl.slice(1)](s, m);
        if (sugg) {
            if (bUppercase && m[iGroup].slice(0,1)._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)._isUpperCase()) {
            oErr["aSuggestions"] = capitalizeArray(sRepl._expand(m).split("|"));
        } else {
            oErr["aSuggestions"] = sRepl._expand(m).split("|");
        }
    }
    // Message
    if (sMsg[0] === "=") {
        sMessage = oEvalFunc[sMsg.slice(1)](s, m)
    } else {
        sMessage = sMsg._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;
}
    _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;
    },

function _rewrite (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)._isUpperCase()) {
            sNew = sNew._toCapitalize();
        }
    } else {
        sNew = sRepl._expand(m);
        sNew = sNew + " ".repeat(ln-sNew.length);
    }
    //echo("\n"+s+"\nstart: "+m.start[iGroup]+" end:"+m.end[iGroup])
    return s.slice(0, m.start[iGroup]) + sNew + s.slice(m.end[iGroup]);
}
    _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

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

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

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

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

    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;
    },

//////// init
    //// Initialization

function load () {
    try {
        _oDict = new ibdawg.IBDAWG("${js_binary_dic}");
    }
    catch (e) {
        helpers.logerror(e);
    }
}
    load: function (sContext="JavaScript", sPath="") {
        try {
            if (typeof(require) !== 'undefined') {
                var ibdawg = require("resource://grammalecte/ibdawg.js");
                _oDict = new ibdawg.IBDAWG("${dic_name}.json");
            } else {
                _oDict = new IBDAWG("${dic_name}.json", sPath);
            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

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

        return _oDict;
function setOptions (dOpt) {
    _dOptions._updateOnlyExistingKeys(dOpt);
}
    },

function getOptions () {
    return _dOptions;
}

    //// Options

    setOption: function (sOpt, bVal) {
        if (_dOptions.has(sOpt)) {
            _dOptions.set(sOpt, bVal);
        }
function getDefaultOptions () {
    return gc_options.dOpt._shallowCopy();
}
    },

function resetOptions () {
    _dOptions = gc_options.dOpt._shallowCopy();
}
    setOptions: function (dOpt) {
        _dOptions.gl_updateOnlyExistingKeys(dOpt);
    },

function getDictionary () {
    return _oDict;
}
    getOptions: function () {
        return _dOptions;
    },

function _getRules (bParagraph) {
    getDefaultOptions: function () {
    if (!bParagraph) {
        return _rules.lSentenceRules;
    }
        return gc_options.getOptions(_sAppContext).gl_shallowCopy();
    },
    return _rules.lParagraphRules;
}


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


//////// common functions
//////// 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) {
        echo("> nothing to find");
        helpers.echo("> nothing to find");
        return true;
    }
    if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
        echo("> not in FSA");
        helpers.echo("> not in FSA");
        return true;
    }
    if (dDA.has(aWord[0])) {
        echo("DA: " + dDA.get(aWord[0]));
        helpers.echo("DA: " + dDA.get(aWord[0]));
    }
    echo("FSA: " + _dAnalyses.get(aWord[1]));
    helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
    return true;
}

function _storeMorphFromFSA (sWord) {
    // retrieves morphologies list from _oDict -> _dAnalyses
    //echo("register: "+sWord + " " + _oDict.getMorph(sWord).toString())
    //helpers.echo("register: "+sWord + " " + _oDict.getMorph(sWord).toString())
    _dAnalyses.set(sWord, _oDict.getMorph(sWord));
    return !!_dAnalyses.get(sWord);
}

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







-
+









-
+




-
+




-
+







-
-
-


+




-
+

+
+



-
-

-



-



















-
+







    // returns a list of sWord's stems
    if (!sWord) {
        return [];
    }
    if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
        return [];
    }
    return [ for (s of _dAnalyses.get(sWord))  s.slice(1, s.indexOf(" ")) ];
    return _dAnalyses.get(sWord).map( s => s.slice(1, s.indexOf(" ")) );
}


//// 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%_-]+)", "i");
    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));
    if (!m) {
        return null;
    }
    return [iStart + RegExp.lastIndex - m[2].length, m[2]];
    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-ʯfi-st%_-]+) +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+ +){" + (n-1).toString() + "}$", "i");
    let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st%_-]+ +){" + (n-1).toString() + "}$", "i");
    let m = z.exec(s.slice(0, iEnd));
    if (!m) {
        return null;
    }
    return [m.index, m[1]];
}

const _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*)", "i");
const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯfi-st_-]*) +$", "i");

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

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

function prevword1 (s, iEnd) {
    // get previous word (optimization)
    //echo("prev1, s:"+s);
    //echo("prev1, s.slice(0, iEnd):"+s.slice(0, iEnd));
    let m = _zPrevWord.exec(s.slice(0, iEnd));
    //echo("prev1, m:"+m);
    if (!m) {
        return null;
    }
    //echo("prev1: " + m.index + " " + m[1]);
    return [m.index, m[1]];
}

function look (s, zPattern, zNegPattern=null) {
    // seek zPattern in s (before/after/fulltext), if antipattern zNegPattern not in s
    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._exec2(s, null);
    let m = zPattern.gl_exec2(s, null);
    if (!m) {
        return false;
    }
    try {
        let sWord = m[1];
        let nPos = m.start[1] + nOffset;
        if (sNegPatternGroup1) {
544
545
546
547
548
549
550
551
552
553
554
555

556
557
558
559
560
561
562
563
566
567
568
569
570
571
572

573
574
575

576

577
578
579
580
581
582
583







-



-
+
-







    }
    if (dDA.has(nPos)) {
        return true;
    }
    if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
        return true;
    }
    //echo("morph: "+_dAnalyses.get(sWord).toString());
    if (_dAnalyses.get(sWord).length === 1) {
        return true;
    }
    let lSelect = [ for (sMorph of _dAnalyses.get(sWord))  if (sMorph.search(sPattern) !== -1)  sMorph ];
    let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) !== -1 );
    //echo("lSelect: "+lSelect.toString());
    if (lSelect.length > 0) {
        if (lSelect.length != _dAnalyses.get(sWord).length) {
            dDA.set(nPos, lSelect);
        }
    } else if (lDefault) {
        dDA.set(nPos, lDefaul);
    }
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

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







-
+
-














+










-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
+
    }
    if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
        return true;
    }
    if (_dAnalyses.get(sWord).length === 1) {
        return true;
    }
    let lSelect = [ for (sMorph of _dAnalyses.get(sWord))  if (sMorph.search(sPattern) === -1)  sMorph ];
    let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) === -1 );
    //echo("lSelect: "+lSelect.toString());
    if (lSelect.length > 0) {
        if (lSelect.length != _dAnalyses.get(sWord).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}




exports.load = load;
exports.parse = parse;
exports.lang = lang;
exports.version = version;
exports.getDictionary = getDictionary;
exports.setOption = setOption;
exports.setOptions = setOptions;
exports.getOptions = getOptions;
exports.getDefaultOptions = getDefaultOptions;
exports.resetOptions = resetOptions;
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.getDictionary = gc_engine.getDictionary;
    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;
exports.ignoreRule = ignoreRule;
exports.reactivateRule = reactivateRule;
exports.resetIgnoreRules = resetIgnoreRules;
exports.listRules = listRules;
}