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
|
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
|
+
-
-
-
-
-
-
-
+
-
-
-
-
-
-
-
-
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
-
+
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
+
+
+
-
-
-
+
+
+
-
-
-
+
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
-
+
-
-
-
-
+
+
+
+
-
-
-
+
+
+
+
-
-
-
-
+
-
-
-
+
+
+
-
-
-
+
+
+
-
-
-
+
+
+
-
-
+
+
-
-
-
-
+
|
}
return aNew;
}
const ibdawg = require("resource://grammalecte/ibdawg.js");
const helpers = require("resource://grammalecte/helpers.js");
const gc_options = require("resource://grammalecte/${lang}/gc_options.js");
const gc_rules = require("resource://grammalecte/${lang}/gc_rules.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 = "${author}";
// commons regexes
const _zEndOfSentence = new RegExp ('([.?!:;…][ .?!… »”")]*|.$)', "g");
const _zBeginOfParagraph = new RegExp ("^[- –—.,;?!…]*", "ig");
const _zEndOfParagraph = new RegExp ("[- .,;?!…–—]*$", "ig");
// grammar rules and dictionary
//const _rules = require("./gc_rules.js");
let _sContext = ""; // what software is running
const _rules = require("resource://grammalecte/${lang}/gc_rules.js");
let _dAnalyses = new Map(); // cache for data from dictionary
let _dAnalyses = new Map(); // cache for data from dictionary
const gc_engine = {
//// Informations
lang: "${lang}",
locales: ${loc},
pkg: "${implname}",
name: "${name}",
version: "${version}",
author: "${author}",
///// Parsing
function parse (sText, sCountry="${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.gl_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();
//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;
}
}
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;
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.gl_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.gl_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) {
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, 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
//echo("-> text processor by " + sLineId + "\nzRegex: " + zRegex.source);
s = this._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.gl_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);
}
}
}
}
}
}
}
}
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).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
if (sMsg[0] === "=") {
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).gl_isUpperCase()) {
sNew = sNew.gl_toCapitalize();
}
} else {
sNew = sRepl.gl_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]);
}
function ignoreRule (sRuleId) {
_aIgnoredRules.add(sRuleId);
}
function resetIgnoreRules () {
_aIgnoredRules.clear();
}
function reactivateRule (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);
}
}
//////// init
function load (sContext="JavaScript") {
try {
_oDict = new ibdawg.IBDAWG("${dic_name}.json");
_sContext = sContext;
_dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default
}
catch (e) {
helpers.logerror(e);
}
}
load: function (sContext="JavaScript") {
try {
_oDict = new ibdawg.IBDAWG("${dic_name}.json");
_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);
}
}
function setOptions (dOpt) {
_dOptions.gl_updateOnlyExistingKeys(dOpt);
}
function getOptions () {
return _dOptions;
}
function getDefaultOptions () {
return gc_options.getOptions(_sContext).gl_shallowCopy();
}
setOptions: function (dOpt) {
_dOptions.gl_updateOnlyExistingKeys(dOpt);
},
function resetOptions () {
_dOptions = gc_options.getOptions(_sContext).gl_shallowCopy();
}
function getDictionary () {
return _oDict;
}
getDefaultOptions: function () {
return gc_options.getOptions(_sAppContext).gl_shallowCopy();
},
function _getRules (bParagraph) {
if (!bParagraph) {
resetOptions: function () {
_dOptions = gc_options.getOptions(_sAppContext).gl_shallowCopy();
return _rules.lSentenceRules;
return _rules.lParagraphRules;
common functions
|