35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
|
// data
let _sAppContext = ""; // what software is running
let _dOptions = null;
let _aIgnoredRules = new Set();
let _oSpellChecker = null;
let _dAnalyses = new Map(); // cache for data from dictionary
|
<
|
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
// data
let _sAppContext = ""; // what software is running
let _dOptions = null;
let _aIgnoredRules = new Set();
let _oSpellChecker = null;
var gc_engine = {
//// Informations
lang: "${lang}",
|
325
326
327
328
329
330
331
332
333
334
335
336
337
338
|
var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
_oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
} else {
_oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
}
_sAppContext = sContext;
_dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default
}
catch (e) {
helpers.logerror(e);
}
},
getSpellChecker: function () {
|
>
|
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
|
var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
_oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
} else {
_oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
}
_sAppContext = sContext;
_dOptions = gc_options.getOptions(sContext).gl_shallowCopy(); // duplication necessary, to be able to reset to default
_oSpellChecker.activateStorage();
}
catch (e) {
helpers.logerror(e);
}
},
getSpellChecker: function () {
|
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
|
function displayInfo (dDA, aWord) {
// for debugging: info of word
if (!aWord) {
helpers.echo("> nothing to find");
return true;
}
if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
helpers.echo("> not in FSA");
return true;
}
if (dDA.has(aWord[0])) {
helpers.echo("DA: " + dDA.get(aWord[0]));
}
helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
return true;
}
function _storeMorphFromFSA (sWord) {
// retrieves morphologies list from _oSpellChecker -> _dAnalyses
//helpers.echo("register: "+sWord + " " + _oSpellChecker.getMorph(sWord).toString())
_dAnalyses.set(sWord, _oSpellChecker.getMorph(sWord));
return !!_dAnalyses.get(sWord);
}
if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
return false;
}
let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]);
if (!_dAnalyses.has(aWord[1]) && !_storeMorphFromFSA(aWord[1])) {
return false;
}
let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _dAnalyses.get(aWord[1]);
if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
return false;
}
if (bStrict) {
return _dAnalyses.get(sWord).every(s => (s.search(sPattern) !== -1));
}
return _dAnalyses.get(sWord).some(s => (s.search(sPattern) !== -1));
}
function analysex (sWord, sPattern, sNegPattern) {
// analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)
if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
return false;
}
// check negative condition
if (_dAnalyses.get(sWord).some(s => (s.search(sNegPattern) !== -1))) {
return false;
}
// search sPattern
return _dAnalyses.get(sWord).some(s => (s.search(sPattern) !== -1));
}
function stem (sWord) {
// returns a list of sWord's stems
if (!sWord) {
return [];
}
if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
return [];
}
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
|
|
>
|
|
<
<
<
<
<
<
<
<
<
<
|
<
<
<
|
|
>
|
|
|
>
|
|
<
<
<
<
<
<
<
<
<
<
<
|
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
|
function displayInfo (dDA, aWord) {
// for debugging: info of word
if (!aWord) {
helpers.echo("> nothing to find");
return true;
}
let lMorph = _oSpellChecker.getMorph(aWord[1]);
if (lMorph.length === 0) {
helpers.echo("> not in dictionary");
return true;
}
if (dDA.has(aWord[0])) {
helpers.echo("DA: " + dDA.get(aWord[0]));
}
helpers.echo("FSA: " + lMorph);
return true;
}
function morph (dDA, aWord, sPattern, bStrict=true, bNoWord=false) {
// analyse a tuple (position, word), return true if sPattern in morphologies (disambiguation on)
if (!aWord) {
//helpers.echo("morph: noword, returns " + bNoWord);
return bNoWord;
}
//helpers.echo("aWord: "+aWord.toString());
let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _oSpellChecker.getMorph(aWord[1]);
//helpers.echo("lMorph: "+lMorph.toString());
if (lMorph.length === 0) {
return false;
}
//helpers.echo("***");
if (bStrict) {
return lMorph.every(s => (s.search(sPattern) !== -1));
}
return lMorph.some(s => (s.search(sPattern) !== -1));
}
function morphex (dDA, aWord, sPattern, sNegPattern, bNoWord=false) {
// analyse a tuple (position, word), returns true if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)
if (!aWord) {
//helpers.echo("morph: noword, returns " + bNoWord);
return bNoWord;
}
//helpers.echo("aWord: "+aWord.toString());
let lMorph = dDA.has(aWord[0]) ? dDA.get(aWord[0]) : _oSpellChecker.getMorph(aWord[1]);
//helpers.echo("lMorph: "+lMorph.toString());
if (lMorph.length === 0) {
return false;
}
//helpers.echo("***");
// check negative condition
if (lMorph.some(s => (s.search(sNegPattern) !== -1))) {
return false;
}
// search sPattern
return lMorph.some(s => (s.search(sPattern) !== -1));
}
function analyse (sWord, sPattern, bStrict=true) {
// analyse a word, return true if sPattern in morphologies (disambiguation off)
let lMorph = _oSpellChecker.getMorph(sWord);
if (lMorph.length === 0) {
return false;
}
if (bStrict) {
return lMorph.every(s => (s.search(sPattern) !== -1));
}
return lMorph.some(s => (s.search(sPattern) !== -1));
}
function analysex (sWord, sPattern, sNegPattern) {
// analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)
let lMorph = _oSpellChecker.getMorph(sWord);
if (lMorph.length === 0) {
return false;
}
// check negative condition
if (lMorph.some(s => (s.search(sNegPattern) !== -1))) {
return false;
}
// search sPattern
return lMorph.some(s => (s.search(sPattern) !== -1));
}
//// functions to get text outside pattern scope
// warning: check compile_rules.py to understand how it works
|
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
|
function select (dDA, nPos, sWord, sPattern, lDefault=null) {
if (!sWord) {
return true;
}
if (dDA.has(nPos)) {
return true;
}
if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
return true;
}
if (_dAnalyses.get(sWord).length === 1) {
return true;
}
let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) !== -1 );
if (lSelect.length > 0) {
if (lSelect.length != _dAnalyses.get(sWord).length) {
dDA.set(nPos, lSelect);
}
} else if (lDefault) {
dDA.set(nPos, lDefaul);
}
return true;
}
function exclude (dDA, nPos, sWord, sPattern, lDefault=null) {
if (!sWord) {
return true;
}
if (dDA.has(nPos)) {
return true;
}
if (!_dAnalyses.has(sWord) && !_storeMorphFromFSA(sWord)) {
return true;
}
if (_dAnalyses.get(sWord).length === 1) {
return true;
}
let lSelect = _dAnalyses.get(sWord).filter( sMorph => sMorph.search(sPattern) === -1 );
if (lSelect.length > 0) {
if (lSelect.length != _dAnalyses.get(sWord).length) {
dDA.set(nPos, lSelect);
}
} else if (lDefault) {
dDA.set(nPos, lDefault);
}
return true;
}
|
|
<
<
|
|
|
|
|
<
<
|
|
|
|
|
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
|
function select (dDA, nPos, sWord, sPattern, lDefault=null) {
if (!sWord) {
return true;
}
if (dDA.has(nPos)) {
return true;
}
let lMorph = _oSpellChecker.getMorph(sWord);
if (lMorph.length === 0 || lMorph.length === 1) {
return false;
}
let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) !== -1 );
if (lSelect.length > 0) {
if (lSelect.length != lMorph.length) {
dDA.set(nPos, lSelect);
}
} else if (lDefault) {
dDA.set(nPos, lDefaul);
}
return true;
}
function exclude (dDA, nPos, sWord, sPattern, lDefault=null) {
if (!sWord) {
return true;
}
if (dDA.has(nPos)) {
return true;
}
let lMorph = _oSpellChecker.getMorph(sWord);
if (lMorph.length === 0 || lMorph.length === 1) {
return false;
}
let lSelect = lMorph.filter( sMorph => sMorph.search(sPattern) === -1 );
if (lSelect.length > 0) {
if (lSelect.length != lMorph.length) {
dDA.set(nPos, lSelect);
}
} else if (lDefault) {
dDA.set(nPos, lDefault);
}
return true;
}
|