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
|
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
|
-
+
+
+
-
+
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
-
+
-
-
+
+
+
-
-
-
+
+
+
+
-
-
-
-
-
+
+
+
+
+
-
+
-
+
-
+
-
+
|
// Grammar checker engine
/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console */
"use strict";
${string}
${regex}
${map}
if(typeof(process) !== 'undefined') {
if (typeof(process) !== 'undefined') {
var gc_engine_func = require("./gc_engine_func.js");
var gc_options = require("./gc_options.js");
var gc_rules = require("./gc_rules.js");
var gc_rules_graph = require("./gc_rules_graph.js");
var cregex = require("./cregex.js");
var text = require("../text.js");
}
} else if (typeof(require) !== 'undefined') {
// data
let _sAppContext = ""; // what software is running
let _dOptions = null;
let _dOptionsColors = null;
let _oSpellChecker = null;
let _oTokenizer = null;
let _aIgnoredRules = new Set();
function echo (x) {
console.log(x);
return true;
}
if(typeof(process) !== 'undefined') {
if (typeof(process) !== 'undefined') {
var spellchecker = require("../graphspell/spellchecker.js");
_oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
} else if (typeof(require) !== 'undefined') {
this.oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
}
else if (typeof(require) !== 'undefined') {
var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
_oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
} else {
_oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
this.oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
}
else {
this.oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
}
_sAppContext = sContext;
_dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default
_dOptionsColors = gc_options.getOptionsColors(sContext, sColorType);
_oTokenizer = _oSpellChecker.getTokenizer();
_oSpellChecker.activateStorage();
return _oSpellChecker;
return this.oSpellChecker;
},
//// Rules
getRules: function (bParagraph) {
if (!bParagraph) {
return gc_rules.lSentenceRules;
}
return gc_rules.lParagraphRules;
},
ignoreRule: function (sRuleId) {
_aIgnoredRules.add(sRuleId);
this.aIgnoredRules.add(sRuleId);
},
resetIgnoreRules: function () {
_aIgnoredRules.clear();
this.aIgnoredRules.clear();
},
reactivateRule: function (sRuleId) {
_aIgnoredRules.delete(sRuleId);
this.aIgnoredRules.delete(sRuleId);
},
listRules: function* (sFilter=null) {
// generator: returns tuple (sOption, sLineId, sRuleId)
try {
for (let [sOption, lRuleGroup] of this.getRules(true)) {
for (let [,, sLineId, sRuleId,,] of lRuleGroup) {
|
| ︙ | | |
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
|
128
129
130
131
132
133
134
135
136
137
138
139
140
141
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
|
}
}
catch (e) {
console.error(e);
}
},
//// Options
setOption: function (sOpt, bVal) {
if (_dOptions.has(sOpt)) {
_dOptions.set(sOpt, bVal);
}
},
setOptions: function (dOpt) {
_dOptions.gl_updateOnlyExistingKeys(dOpt);
},
getOptions: function () {
return _dOptions;
},
getDefaultOptions: function () {
return gc_options.getOptions(_sAppContext).gl_shallowCopy();
},
resetOptions: function () {
_dOptions = gc_options.getOptions(_sAppContext).gl_shallowCopy();
},
|
| ︙ | | |
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
|
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
|
-
-
+
+
|
s += "\n";
}
return s;
}
parse (sCountry="${country_default}", bDebug=false, dOptions=null, bContext=false, bFullInfo=false) {
// analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) a list of sentences with tokens and errors
let dOpt = dOptions || _dOptions;
let bShowRuleId = option('idrule');
let dOpt = dOptions || gc_options.dOptions;
let bShowRuleId = gc_options.dOptions.gl_get('idrule', false);
// parse paragraph
try {
this.parseText(this.sText, this.sText0, true, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext);
}
catch (e) {
console.error(e);
}
|
| ︙ | | |
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
|
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
|
-
+
-
+
|
let lSentences = [];
let oSentence = null;
for (let [iStart, iEnd] of text.getSentenceBoundaries(sText)) {
try {
this.sSentence = sText.slice(iStart, iEnd);
this.sSentence0 = this.sText0.slice(iStart, iEnd);
this.nOffsetWithinParagraph = iStart;
this.lToken = Array.from(_oTokenizer.genTokens(this.sSentence, true));
this.lToken = Array.from(gc_engine.oTokenizer.genTokens(this.sSentence, true));
this.dTokenPos.clear();
for (let dToken of this.lToken) {
if (dToken["sType"] != "INFO") {
this.dTokenPos.set(dToken["nStart"], dToken);
}
}
if (bFullInfo) {
oSentence = { "nStart": iStart, "nEnd": iEnd, "sSentence": this.sSentence, "lToken": Array.from(this.lToken) };
for (let oToken of oSentence["lToken"]) {
if (oToken["sType"] == "WORD") {
oToken["bValidToken"] = _oSpellChecker.isValidToken(oToken["sValue"]);
oToken["bValidToken"] = gc_engine.oSpellChecker.isValidToken(oToken["sValue"]);
}
}
// the list of tokens is duplicated, to keep all tokens from being deleted when analysis
}
this.parseText(this.sSentence, this.sSentence0, false, iStart, sCountry, dOpt, bShowRuleId, bDebug, bContext);
if (bFullInfo) {
oSentence["lGrammarErrors"] = Array.from(this.dSentenceError.values());
|
| ︙ | | |
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
|
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
|
-
+
-
+
-
+
|
if (bDebug) {
console.log(">>>> GRAPH: " + sGraphName + " " + sLineId);
}
sText = this.parseGraph(gc_rules_graph.dAllGraph[sGraphName], sCountry, dOptions, bShowRuleId, bDebug, bContext);
}
}
}
else if (!sOption || option(sOption)) {
else if (!sOption || gc_options.dOptions.gl_get(sOption, false)) {
for (let [zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions, lGroups, lNegLookBefore] of lRuleGroup) {
if (!_aIgnoredRules.has(sRuleId)) {
if (!gc_engine.aIgnoredRules.has(sRuleId)) {
while ((m = zRegex.gl_exec2(sText, lGroups, lNegLookBefore)) !== null) {
let bCondMemo = null;
for (let [sFuncCond, cActionType, sWhat, ...eAct] of lActions) {
// action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
try {
bCondMemo = (!sFuncCond || oEvalFunc[sFuncCond](sText, sText0, m, this.dTokenPos, sCountry, bCondMemo));
bCondMemo = (!sFuncCond || gc_engine_func[sFuncCond](sText, sText0, m, this.dTokenPos, sCountry, bCondMemo));
if (bCondMemo) {
switch (cActionType) {
case "-":
// grammar error
//console.log("-> error detected in " + sLineId + "\nzRegex: " + zRegex.source);
let nErrorStart = nOffset + m.start[eAct[0]];
if (!this.dError.has(nErrorStart) || nPriority > this.dErrorPriority.get(nErrorStart)) {
|
| ︙ | | |
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
|
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
|
-
+
|
if (bDebug) {
console.log("~ " + sText + " -- " + m[eAct[0]] + " # " + sLineId);
}
break;
case "=":
// disambiguation
//console.log("-> disambiguation by " + sLineId + "\nzRegex: " + zRegex.source);
oEvalFunc[sWhat](sText, m, this.dTokenPos);
gc_engine_func[sWhat](sText, m, this.dTokenPos);
if (bDebug) {
console.log("= " + m[0] + " # " + sLineId, "\nDA:", this.dTokenPos);
}
break;
case ">":
// we do nothing, this test is just a condition to apply all following actions
break;
|
| ︙ | | |
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
|
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
|
-
+
|
}
}
}
update (sSentence, bDebug=false) {
// update <sSentence> and retokenize
this.sSentence = sSentence;
let lNewToken = Array.from(_oTokenizer.genTokens(sSentence, true));
let lNewToken = Array.from(gc_engine.oTokenizer.genTokens(sSentence, true));
for (let oToken of lNewToken) {
if (this.dTokenPos.gl_get(oToken["nStart"], {}).hasOwnProperty("lMorph")) {
oToken["lMorph"] = this.dTokenPos.get(oToken["nStart"])["lMorph"];
}
if (this.dTokenPos.gl_get(oToken["nStart"], {}).hasOwnProperty("aTags")) {
oToken["aTags"] = this.dTokenPos.get(oToken["nStart"])["aTags"];
}
|
| ︙ | | |
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
|
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
|
-
+
-
+
|
}
}
}
// analysable tokens
if (oToken["sType"].slice(0,4) == "WORD") {
// token lemmas
if (oNode.hasOwnProperty("<lemmas>")) {
for (let sLemma of _oSpellChecker.getLemma(oToken["sValue"])) {
for (let sLemma of gc_engine.oSpellChecker.getLemma(oToken["sValue"])) {
if (oNode["<lemmas>"].hasOwnProperty(sLemma)) {
if (bDebug) {
console.log(" MATCH: >" + sLemma);
}
yield { "iToken1": iToken1, "iNode": oNode["<lemmas>"][sLemma] };
bTokenFound = true;
}
}
}
// morph arcs
if (oNode.hasOwnProperty("<morph>")) {
let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
if (lMorph.length > 0) {
for (let sSearch in oNode["<morph>"]) {
if (!sSearch.includes("¬")) {
// no anti-pattern
if (lMorph.some(sMorph => (sMorph.includes(sSearch)))) {
if (bDebug) {
console.log(" MATCH: $" + sSearch);
|
| ︙ | | |
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
|
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
|
-
+
|
}
}
}
}
}
// regex morph arcs
if (oNode.hasOwnProperty("<re_morph>")) {
let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : gc_engine.oSpellChecker.getMorph(oToken["sValue"]);
if (lMorph.length > 0) {
for (let sRegex in oNode["<re_morph>"]) {
if (!sRegex.includes("¬")) {
// no anti-pattern
if (lMorph.some(sMorph => (sMorph.search(sRegex) !== -1))) {
if (bDebug) {
console.log(" MATCH: @" + sRegex);
|
| ︙ | | |
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
|
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
|
-
+
|
// 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);
bCondMemo = !sFuncCond || gc_engine_func[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;
|
| ︙ | | |
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
|
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
|
-
+
|
bChange = true;
if (bDebug) {
console.log(` TEXT_PROCESSOR: [${this.lToken[nTokenStart]["sValue"]}:${this.lToken[nTokenEnd]["sValue"]}] > ${sWhat}`);
}
}
else if (cActionType == "=") {
// disambiguation
oEvalFunc[sWhat](this.lToken, nTokenOffset, nLastToken);
gc_engine_func[sWhat](this.lToken, nTokenOffset, nLastToken);
if (bDebug) {
console.log(` DISAMBIGUATOR: (${sWhat}) [${this.lToken[nTokenOffset+1]["sValue"]}:${this.lToken[nLastToken]["sValue"]}]`);
}
}
else if (cActionType == ">") {
// we do nothing, this test is just a condition to apply all following actions
if (bDebug) {
|
| ︙ | | |
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
|
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
|
-
+
-
+
-
+
-
+
-
+
|
_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);
sSugg = gc_engine_func[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);
let sMessage = (sMsg.startsWith("=")) ? gc_engine_func[sMsg.slice(1)](sText, m) : sMsg.gl_expand(m);
if (bShowRuleId) {
sMessage += " #" + sLineId + " / " + sRuleId;
}
//
return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext);
}
_createErrorFromTokens (sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext) {
// suggestions
let lSugg = [];
if (sSugg.startsWith("=")) {
sSugg = oEvalFunc[sSugg.slice(1)](this.lToken, nTokenOffset, nLastToken);
sSugg = gc_engine_func[sSugg.slice(1)](this.lToken, nTokenOffset, nLastToken);
lSugg = (sSugg) ? sSugg.split("|") : [];
} else if (sSugg == "_") {
lSugg = [];
} else {
lSugg = this._expand(sSugg, nTokenOffset, nLastToken).split("|");
}
if (bCaseSvty && lSugg.length > 0 && this.lToken[iFirstToken]["sValue"].slice(0,1).gl_isUpperCase()) {
lSugg = capitalizeArray(lSugg);
}
// Message
let sMessage = (sMsg.startsWith("=")) ? oEvalFunc[sMsg.slice(1)](this.lToken, nTokenOffset, nLastToken) : this._expand(sMsg, nTokenOffset, nLastToken);
let sMessage = (sMsg.startsWith("=")) ? gc_engine_func[sMsg.slice(1)](this.lToken, nTokenOffset, nLastToken) : this._expand(sMsg, nTokenOffset, nLastToken);
if (bShowRuleId) {
sMessage += " #" + sLineId + " / " + sRuleId;
}
//
return this._createError(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext);
}
_createError (nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) {
let oErr = {
"nStart": nStart,
"nEnd": nEnd,
"sLineId": sLineId,
"sRuleId": sRuleId,
"sType": sOption || "notype",
"aColor": _dOptionsColors[sOption],
"aColor": gc_engine.oOptionsColors[sOption],
"sMessage": sMessage,
"aSuggestions": lSugg,
"URL": sURL
}
if (bContext) {
oErr['sUnderlined'] = this.sText0.slice(nStart, nEnd);
oErr['sBefore'] = this.sText0.slice(Math.max(0,nStart-80), nStart);
|
| ︙ | | |
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
|
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
|
-
+
|
else if (sRepl === "_") {
sNew = "_".repeat(ln);
}
else if (sRepl === "@") {
sNew = "@".repeat(ln);
}
else if (sRepl.slice(0,1) === "=") {
sNew = oEvalFunc[sRepl.slice(1)](sText, m);
sNew = gc_engine_func[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);
|
| ︙ | | |
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
|
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
|
-
+
|
for (let i = nTokenRewriteStart; i <= nTokenRewriteEnd; i++) {
this.lToken[i]["sNewValue"] = "_";
}
}
}
else {
if (sWhat.startsWith("=")) {
sWhat = oEvalFunc[sWhat.slice(1)](this.lToken, nTokenOffset, nLastToken);
sWhat = gc_engine_func[sWhat.slice(1)](this.lToken, nTokenOffset, nLastToken);
} else {
sWhat = this._expand(sWhat, nTokenOffset, nLastToken);
}
let bUppercase = bCaseSvty && this.lToken[nTokenRewriteStart]["sValue"].slice(0,1).gl_isUpperCase();
if (nTokenRewriteEnd - nTokenRewriteStart == 0) {
// one token
if (bUppercase) {
|
| ︙ | | |
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
|
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
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
-
-
-
-
-
-
|
console.log(" TEXT REWRITED: " + this.sSentence);
}
this.lToken.length = 0;
this.lToken = lNewToken;
}
};
//////// Common functions
function option (sOpt) {
// return true if option sOpt is active
return _dOptions.get(sOpt);
}
var re = {
search: function (sRegex, sText) {
if (sRegex.startsWith("(?i)")) {
return sText.search(new RegExp(sRegex.slice(4), "i")) !== -1;
} else {
return sText.search(sRegex) !== -1;
}
},
createRegExp: function (sRegex) {
if (sRegex.startsWith("(?i)")) {
return new RegExp(sRegex.slice(4), "i");
} else {
return new RegExp(sRegex);
}
}
}
//////// functions to get text outside pattern scope
// warning: check compile_rules.py to understand how it works
function nextword (s, iStart, n) {
// get the nth word of the input string or empty string
let z = new RegExp("^(?: +[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+){" + (n-1).toString() + "} +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+)", "ig");
let m = z.exec(s.slice(iStart));
if (!m) {
return null;
}
return [iStart + z.lastIndex - m[1].length, m[1]];
}
function prevword (s, iEnd, n) {
// get the (-)nth word of the input string or empty string
let z = new RegExp("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+) +(?:[a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ%_-]+ +){" + (n-1).toString() + "}$", "i");
let m = z.exec(s.slice(0, iEnd));
if (!m) {
return null;
}
return [m.index, m[1]];
}
function nextword1 (s, iStart) {
// get next word (optimization)
let _zNextWord = new RegExp ("^ +([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*)", "ig");
let m = _zNextWord.exec(s.slice(iStart));
if (!m) {
return null;
}
return [iStart + _zNextWord.lastIndex - m[1].length, m[1]];
}
const _zPrevWord = new RegExp ("([a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_][a-zà-öA-Zø-ÿÀ-Ö0-9Ø-ßĀ-ʯff-stᴀ-ᶿ_-]*) +$", "i");
function prevword1 (s, iEnd) {
// get previous word (optimization)
let m = _zPrevWord.exec(s.slice(0, iEnd));
if (!m) {
return null;
}
return [m.index, m[1]];
}
function look (s, sPattern, sNegPattern=null) {
// seek sPattern in s (before/after/fulltext), if antipattern sNegPattern not in s
try {
if (sNegPattern && re.search(sNegPattern, s)) {
return false;
}
return re.search(sPattern, s);
}
catch (e) {
console.error(e);
}
return false;
}
//////// Analyse groups for regex rules
function displayInfo (dTokenPos, aWord) {
// for debugging: info of word
if (!aWord) {
console.log("> nothing to find");
return true;
}
let lMorph = _oSpellChecker.getMorph(aWord[1]);
if (lMorph.length === 0) {
console.log("> not in dictionary");
return true;
}
if (dTokenPos.has(aWord[0])) {
console.log("DA: " + dTokenPos.get(aWord[0]));
}
console.log("FSA: " + lMorph);
return true;
}
function morph (dTokenPos, aWord, sPattern, sNegPattern, bNoWord=false) {
// analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
if (!aWord) {
return bNoWord;
}
let lMorph = (dTokenPos.has(aWord[0]) && dTokenPos.get(aWord[0]))["lMorph"] ? dTokenPos.get(aWord[0])["lMorph"] : _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 (oToken, sValues, nLeft=null, nRight=null) {
// test if <oToken['sValue']> is in sValues (each value should be separated with |)
let sValue = (nLeft === null) ? "|"+oToken["sValue"]+"|" : "|"+oToken["sValue"].slice(nLeft, nRight)+"|";
if (sValues.includes(sValue)) {
return true;
}
if (oToken["sValue"].slice(0,2).gl_isTitle()) { // we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
if (sValues.includes(sValue.toLowerCase())) {
return true;
}
}
else if (oToken["sValue"].gl_isUpperCase()) {
//if sValue.lower() in sValues:
// return true;
sValue = "|"+sValue.slice(1).gl_toCapitalize();
if (sValues.includes(sValue)) {
return true;
}
sValue = sValue.toLowerCase();
if (sValues.includes(sValue)) {
return true;
}
}
return false;
}
function g_morph (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
// analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
let lMorph;
if (oToken.hasOwnProperty("lMorph")) {
lMorph = oToken["lMorph"];
}
else {
if (nLeft !== null) {
let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
lMorph = _oSpellChecker.getMorph(sValue);
if (bMemorizeMorph) {
oToken["lMorph"] = lMorph;
}
} else {
lMorph = _oSpellChecker.getMorph(oToken["sValue"]);
}
}
if (lMorph.length == 0) {
return false;
}
// check negative condition
if (sNegPattern) {
if (sNegPattern == "*") {
// all morph must match sPattern
return lMorph.every(sMorph => (sMorph.search(sPattern) !== -1));
}
else {
if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) {
return false;
}
}
}
// search sPattern
return lMorph.some(sMorph => (sMorph.search(sPattern) !== -1));
}
function g_analyse (oToken, sPattern, sNegPattern="", nLeft=null, nRight=null, bMemorizeMorph=true) {
// analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies
let lMorph;
if (nLeft !== null) {
let sValue = (nRight !== null) ? oToken["sValue"].slice(nLeft, nRight) : oToken["sValue"].slice(nLeft);
lMorph = _oSpellChecker.getMorph(sValue);
if (bMemorizeMorph) {
oToken["lMorph"] = lMorph;
}
} else {
lMorph = _oSpellChecker.getMorph(oToken["sValue"]);
}
if (lMorph.length == 0) {
return false;
}
// check negative condition
if (sNegPattern) {
if (sNegPattern == "*") {
// all morph must match sPattern
return lMorph.every(sMorph => (sMorph.search(sPattern) !== -1));
}
else {
if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) {
return false;
}
}
}
// search sPattern
return lMorph.some(sMorph => (sMorph.search(sPattern) !== -1));
}
function g_merged_analyse (oToken1, oToken2, cMerger, sPattern, sNegPattern="", bSetMorph=true) {
// merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)
let lMorph = _oSpellChecker.getMorph(oToken1["sValue"] + cMerger + oToken2["sValue"]);
if (lMorph.length == 0) {
return false;
}
// check negative condition
if (sNegPattern) {
if (sNegPattern == "*") {
// all morph must match sPattern
let bResult = lMorph.every(sMorph => (sMorph.search(sPattern) !== -1));
if (bResult && bSetMorph) {
oToken1["lMorph"] = lMorph;
}
return bResult;
}
else {
if (lMorph.some(sMorph => (sMorph.search(sNegPattern) !== -1))) {
return false;
}
}
}
// search sPattern
let bResult = lMorph.some(sMorph => (sMorph.search(sPattern) !== -1));
if (bResult && bSetMorph) {
oToken1["lMorph"] = lMorph;
}
return bResult;
}
function g_tag_before (oToken, dTags, sTag) {
if (!dTags.has(sTag)) {
return false;
}
if (oToken["i"] > dTags.get(sTag)[0]) {
return true;
}
return false;
}
function g_tag_after (oToken, dTags, sTag) {
if (!dTags.has(sTag)) {
return false;
}
if (oToken["i"] < dTags.get(sTag)[1]) {
return true;
}
return false;
}
function g_tag (oToken, sTag) {
return oToken.hasOwnProperty("aTags") && oToken["aTags"].has(sTag);
}
function g_space_between_tokens (oToken1, oToken2, nMin, nMax=null) {
let nSpace = oToken2["nStart"] - oToken1["nEnd"]
if (nSpace < nMin) {
return false;
}
if (nMax !== null && nSpace > nMax) {
return false;
}
return true;
}
function g_token (lToken, i) {
if (i < 0) {
return lToken[0];
}
if (i >= lToken.length) {
return lToken[-1];
}
return lToken[i];
}
//////// Disambiguator
function select (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
if (!sWord) {
return true;
}
if (!dTokenPos.has(nPos)) {
console.log("Error. There should be a token at this position: ", nPos);
return true;
}
let lMorph = _oSpellChecker.getMorph(sWord);
if (lMorph.length === 0 || lMorph.length === 1) {
return true;
}
let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
if (lSelect.length > 0) {
if (lSelect.length != lMorph.length) {
dTokenPos.get(nPos)["lMorph"] = lSelect;
}
} else if (lDefault) {
dTokenPos.get(nPos)["lMorph"] = lDefault;
}
return true;
}
function exclude (dTokenPos, nPos, sWord, sPattern, lDefault=null) {
if (!sWord) {
return true;
}
if (!dTokenPos.has(nPos)) {
console.log("Error. There should be a token at this position: ", nPos);
return true;
}
let lMorph = _oSpellChecker.getMorph(sWord);
if (lMorph.length === 0 || lMorph.length === 1) {
return true;
}
let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
if (lSelect.length > 0) {
if (lSelect.length != lMorph.length) {
dTokenPos.get(nPos)["lMorph"] = lSelect;
}
} else if (lDefault) {
dTokenPos.get(nPos)["lMorph"] = lDefault;
}
return true;
}
function define (dTokenPos, nPos, lMorph) {
dTokenPos.get(nPos)["lMorph"] = lMorph;
return true;
}
//// Disambiguation for graph rules
function g_select (oToken, sPattern, lDefault=null) {
// select morphologies for <oToken> according to <sPattern>, always return true
let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
if (lMorph.length === 0 || lMorph.length === 1) {
if (lDefault) {
oToken["lMorph"] = lDefault;
}
return true;
}
let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
if (lSelect.length > 0) {
if (lSelect.length != lMorph.length) {
oToken["lMorph"] = lSelect;
}
} else if (lDefault) {
oToken["lMorph"] = lDefault;
}
return true;
}
function g_exclude (oToken, sPattern, lDefault=null) {
// select morphologies for <oToken> according to <sPattern>, always return true
let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
if (lMorph.length === 0 || lMorph.length === 1) {
if (lDefault) {
oToken["lMorph"] = lDefault;
}
return true;
}
let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
if (lSelect.length > 0) {
if (lSelect.length != lMorph.length) {
oToken["lMorph"] = lSelect;
}
} else if (lDefault) {
oToken["lMorph"] = lDefault;
}
return true;
}
function g_add_morph (oToken, lNewMorph) {
"Disambiguation: add a morphology to a token"
let lMorph = (oToken.hasOwnProperty("lMorph")) ? oToken["lMorph"] : _oSpellChecker.getMorph(oToken["sValue"]);
lMorph.push(...lNewMorph);
oToken["lMorph"] = lMorph;
return true;
}
function g_define (oToken, lMorph) {
// set morphologies of <oToken>, always return true
oToken["lMorph"] = lMorph;
return true;
}
function g_define_from (oToken, nLeft=null, nRight=null) {
let sValue = oToken["sValue"];
if (nLeft !== null) {
sValue = (nRight !== null) ? sValue.slice(nLeft, nRight) : sValue.slice(nLeft);
}
oToken["lMorph"] = _oSpellChecker.getMorph(sValue);
return true;
}
function g_change_meta (oToken, sType) {
// Disambiguation: change type of token
oToken["sType"] = sType;
return true;
}
//////// GRAMMAR CHECKER PLUGINS
${pluginsJS}
// generated code, do not edit
const oEvalFunc = {
// callables for regex rules
${callablesJS}
// callables for graph rules
${graph_callablesJS}
}
// options
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;
|