Grammalecte  Check-in [a3687f4fd3]

Overview
Comment:Some change to javascript to work in node
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | graphspell | njs | nodejs
Files: files | file ages | folders
SHA3-256: a3687f4fd354247fe5fde6cd76eeaefc54bcc7b1383d4e0235e43e1016516858
User & Date: IllusionPerdu on 2018-10-10 09:19:04
Other Links: branch diff | manifest | tags
Context
2018-10-10
09:36
Minimal file to use in node check-in: b79bb889b9 user: IllusionPerdu tags: graphspell, njs, nodejs
09:19
Some change to javascript to work in node check-in: a3687f4fd3 user: IllusionPerdu tags: graphspell, njs, nodejs
2018-10-09
11:07
[graphspell][js] useless comments check-in: 4d2953e2f6 user: olr tags: trunk, graphspell
Changes
Hide Diffs Side-by-Side Diffs Ignore Whitespace Patch

Modified graphspell-js/char_player.js from [626d7d161b] to [27827e9132]. 

1
2
3



4
5
6
7
8
9
10

1
2
3
4
5
6
7
8
9
10
11
12
13




+
+
+








// list of similar chars
// useful for suggestion mechanism

/* jshint esversion:6 */
/* jslint esversion:6 */

${map}


var char_player = {

    _xTransCharsForSpelling: new Map([
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st']
︙
21
22
23
24
25
26
27
28

29
30
31
32
33
34
35

24
25
26
27
28
29
30

31
32
33
34
35
36
37
38








-
+








    _xTransCharsForSimplification: new Map([
        ['à', 'a'],  ['é', 'e'],  ['î', 'i'],  ['ô', 'o'],  ['û', 'u'],  ['ÿ', 'i'],  ['y', 'i'],
        ['â', 'a'],  ['è', 'e'],  ['ï', 'i'],  ['ö', 'o'],  ['ù', 'u'],  ['ŷ', 'i'],
        ['ä', 'a'],  ['ê', 'e'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'i'],
        ['á', 'a'],  ['ë', 'e'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'i'],
        ['ā', 'a'],  ['ē', 'e'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'i'],
        ['ç', 'c'],  ['ñ', 'n'],  ['k', 'q'],  ['w', 'v'],
        ['œ', 'oe'], ['æ', 'ae'], 
        ['œ', 'oe'], ['æ', 'ae'],
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st']
    ]),

    simplifyWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        sWord = [...sWord].map(c => this._xTransCharsForSimplification.gl_get(c, c)).join('');
︙
100
101
102
103
104
105
106
107

108
109
110
111
112
113
114

103
104
105
106
107
108
109

110
111
112
113
114
115
116
117








-
+








        ["Ë", "EeÉéÈèÊêËëĒēŒœ"],

        ["f", "fF"],
        ["F", "Ff"],

        ["g", "gGjJĵĴ"],
        ["G", "GgJjĴĵ"],
        

        ["h", "hH"],
        ["H", "Hh"],

        ["i", "iIîÎïÏyYíÍìÌīĪÿŸ"],
        ["I", "IiÎîÏïYyÍíÌìĪīŸÿ"],
        ["î", "iIîÎïÏyYíÍìÌīĪÿŸ"],
        ["Î", "IiÎîÏïYyÍíÌìĪīŸÿ"],
︙
378
379
380
381
382
383
384
385

386
387
388

389
390
391
392
393
394
395

381
382
383
384
385
386
387

388
389
390

391
392
393
394
395
396
397
398








-
+


-
+








    },

    // Other functions
    filterSugg: function (aSugg) {
        return aSugg.filter((sSugg) => { return !sSugg.endsWith("è") && !sSugg.endsWith("È"); });
    }

}
};


if (typeof(exports) !== 'undefined') {
if (typeof exports !== 'undefined') {
    exports._xTransCharsForSpelling = char_player._xTransCharsForSpelling;
    exports.spellingNormalization = char_player.spellingNormalization;
    exports._xTransCharsForSimplification = char_player._xTransCharsForSimplification;
    exports.simplifyWord = char_player.simplifyWord;
    exports.aVowel = char_player.aVowel;
    exports.aConsonant = char_player.aConsonant;
    exports.aDouble = char_player.aDouble;
︙

Modified graphspell-js/dawg.js from [d94e6b7163] to [56edbc7aa3]. 

1
2
3
4
5
6
7
8
9
10




11
12
13
14
15




16
17
18
19
20
21
22
23
24

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











+
+
+
+


-
-
-
+
+
+
+

-








// JavaScript

// FSA DICTIONARY BUILDER
//
// by Olivier R.
// License: MPL 2
//
// This tool encodes lexicon into an indexable binary dictionary
// Input files MUST be encoded in UTF-8.

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console, helpers */

"use strict";


if (typeof(require) !== 'undefined') {
    var str_transform = require("resource://grammalecte/graphspell/str_transform.js");
if(typeof process !== 'undefined') {
    var str_transform = require('./str_transform.js');
} else if (typeof require !== 'undefined') {
    var str_transform = require('resource://grammalecte/graphspell/str_transform.js');
}


${map}


class DAWG {
    /*  DIRECT ACYCLIC WORD GRAPH
        This code is inspired from Steve Hanov’s DAWG, 2011. (http://stevehanov.ca/blog/index.php?id=115)
︙
96
97
98
99
100
101
102
103

104
105
106
107
108
109
110

100
101
102
103
104
105
106

107
108
109
110
111
112
113
114








-
+








        let lWord = [];
        for (let [sFlex, iAff, iTag] of lEntry) {
            let lTemp = [];
            for (let c of sFlex) {
                lTemp.push(dChar.get(c));
            }
            lTemp.push(iAff+nChar);
            lTemp.push(iTag+nChar+nAff)
            lTemp.push(iTag+nChar+nAff);
            lWord.push(lTemp);
        }
        lEntry.length = 0; // clear the array

        // Dictionary of arc values occurrency, to sort arcs of each node
        let lKeyVal = [];
        for (let c of dChar.keys()) { lKeyVal.push([dChar.get(c), dCharOccur.get(c)]); }
︙
426
427
428
429
430
431
432
433

434
435
436
437
438
439
440

430
431
432
433
434
435
436

437
438
439
440
441
442
443
444








-
+








        this.nNextId += 1;
        return this.nNextId-1;
    },

    reset: function () {
        this.nNextId = 0;
    }
}
};


class DawgNode {

    constructor () {
        this.i = oNodeCounter.getId();
        this.final = false;
︙
540
541
542
543
544
545
546
547

548
549
550
551
552
553
554

544
545
546
547
548
549
550

551
552
553
554
555
556
557
558








-
+








    convValueToHexString (nVal, nByte) {
        // nVal: value to convert, nByte: number of bytes
        let sHexVal = nVal.toString(16); // conversion to hexadecimal string
        //console.log(`value: ${nVal} in ${nByte} bytes`);
        if (sHexVal.length < (nByte*2)) {
            return "0".repeat((nByte*2) - sHexVal.length) + sHexVal;
        } else if (sHexVal.length == (nByte*2)) {
            return sHexVal
            return sHexVal;
        } else {
            throw "Conversion to byte string: value bigger than allowed.";
        }
    }
}
︙

Modified graphspell-js/helpers.js from [6ccb02c60d] to [2ed0ee7e88]. 

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


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

-

+
+
-
-
+
+




















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









// HELPERS

/* jshint esversion:6, -W097 */
/*jslint esversion: 6*/
/*global console,require,exports,XMLHttpRequest*/
/* jslint esversion:6 */
/* global require, exports, console, XMLHttpRequest */

"use strict";


var helpers = {

    inspect: function (o) {
        let sMsg = "__inspect__: " + typeof o;
        for (let sParam in o) {
            sMsg += "\n" + sParam + ": " + o.sParam;
        }
        sMsg += "\n" + JSON.stringify(o) + "\n__end__";
        console.log(sMsg);
    },

    loadFile: function (spf) {
        // load ressources in workers (suggested by Mozilla extensions reviewers)
        // for more options have a look here: https://gist.github.com/Noitidart/ec1e6b9a593ec7e3efed
        // if not in workers, use sdk/data.load() instead
        try {
            if(typeof process !== 'undefined' && typeof require !== 'undefined') {
                //console.log('loadFile(disque): ' + spf);
                let fs = require('fs');
                return fs.readFileSync(spf, 'utf8');
            } else {
            console.log("loadFile: " + spf);
            let xRequest;
            xRequest = new XMLHttpRequest();
            xRequest.open('GET', spf, false); // 3rd arg is false for synchronous, sync is acceptable in workers
            xRequest.overrideMimeType('text/json');
            xRequest.send();
            return xRequest.responseText;
                //console.log('loadFile: ' + spf);
                let xRequest;
                xRequest = new XMLHttpRequest();
                xRequest.open('GET', spf, false); // 3rd arg is false for synchronous, sync is acceptable in workers
                xRequest.overrideMimeType('text/json');
                xRequest.send();
                return xRequest.responseText;
            }
        }
        catch (e) {
            console.error(e);
            return null;
        }
    },
︙
57
58
59
60
61
62
63
64

65
66
67
68
69

64
65
66
67
68
69
70

71
72
73
74
75
76








-
+






            obj[k] = v;
        }
        return obj;
    }
};


if (typeof(exports) !== 'undefined') {
if (typeof exports !== 'undefined') {
    exports.inspect = helpers.inspect;
    exports.loadFile = helpers.loadFile;
    exports.objectToMap = helpers.objectToMap;
    exports.mapToObject = helpers.mapToObject;
}

Modified graphspell-js/ibdawg.js from [26e5034903] to [ad47fc175d]. 

1
2
3





4
5
6
7
8
9
10
11








12
13
14
15
16
17
18
19
20




1
2
3
4
5
6
7
8





9
10
11
12
13
14
15
16
17

18
19
20
21
22
23
24

-
-
-
+
+
+
+
+



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

-








//// IBDAWG
/*jslint esversion: 6*/
/*global console,require,exports*/
// IBDAWG

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console*/

"use strict";


if (typeof(require) !== 'undefined') {
    var str_transform = require("resource://grammalecte/graphspell/str_transform.js");
    var helpers = require("resource://grammalecte/graphspell/helpers.js");
    var char_player = require("resource://grammalecte/graphspell/char_player.js");
if(typeof process !== 'undefined') {
    var str_transform = require('./str_transform.js');
    var helpers = require('./helpers.js');
    var char_player = require('./char_player.js');
} else if (typeof require !== 'undefined') {
    var str_transform = require('resource://grammalecte/graphspell/str_transform.js');
    var helpers = require('resource://grammalecte/graphspell/helpers.js');
    var char_player = require('resource://grammalecte/graphspell/char_player.js');
}


// Don’t remove <string>. Necessary in TB.
${string}
${map}
${set}
︙
219
220
221
222
223
224
225
226

227
228
229
230
231
232
233

223
224
225
226
227
228
229

230
231
232
233
234
235
236
237








-
+








            "l2grams": this.l2grams
        };
        return oJSON;
    }

    isValidToken (sToken) {
        // checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)
        sToken = char_player.spellingNormalization(sToken)
        sToken = char_player.spellingNormalization(sToken);
        if (this.isValid(sToken)) {
            return true;
        }
        if (sToken.includes("-")) {
            if (sToken.gl_count("-") > 4) {
                return true;
            }
︙
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

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








-
+












-
-
+
+












-
+

-
-
+








            }
        }
        return Boolean(this._convBytesToInteger(this.byDic.slice(iAddr, iAddr+this.nBytesArc)) & this._finalNodeMask);
    }

    getMorph (sWord) {
        // retrieves morphologies list, different casing allowed
        sWord = char_player.spellingNormalization(sWord)
        sWord = char_player.spellingNormalization(sWord);
        let l = this.morph(sWord);
        if (sWord[0].gl_isUpperCase()) {
            l.push(...this.morph(sWord.toLowerCase()));
            if (sWord.gl_isUpperCase() && sWord.length > 1) {
                l.push(...this.morph(sWord.gl_toCapitalize()));
            }
        }
        return l;
    }

    suggest (sWord, nSuggLimit=10) {
        // returns a array of suggestions for <sWord>
        //const t0 = Date.now();
        sWord = char_player.spellingNormalization(sWord)
	//console.time("Suggestions for " + sWord + ");
        sWord = char_player.spellingNormalization(sWord);
        let sPfx = "";
        let sSfx = "";
        [sPfx, sWord, sSfx] = char_player.cut(sWord);
        let nMaxSwitch = Math.max(Math.floor(sWord.length / 3), 1);
        let nMaxDel = Math.floor(sWord.length / 5);
        let nMaxHardRepl = Math.max(Math.floor((sWord.length - 5) / 4), 1);
        let nMaxJump = Math.max(Math.floor(sWord.length / 4), 1);
        let oSuggResult = new SuggResult(sWord);
        this._suggest(oSuggResult, sWord, nMaxSwitch, nMaxDel, nMaxHardRepl, nMaxJump);
        let aSugg = oSuggResult.getSuggestions(nSuggLimit);
        if (sSfx || sPfx) {
            // we add what we removed
            return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx } );
            return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx; } );
        }
        //const t1 = Date.now();
        //console.log("Suggestions for " + sWord + " in " + ((t1-t0)/1000).toString() + " s");
	//console.timeEnd("Suggestions for " + sWord + ");
        return aSugg;
    }

    _suggest (oSuggResult, sRemain, nMaxSwitch=0, nMaxDel=0, nMaxHardRepl=0, nMaxJump=0, nDist=0, nDeep=0, iAddr=0, sNewWord="", bAvoidLoop=false) {
        // returns a set of suggestions
        // recursive function
        if (sRemain == "") {
︙
587
588
589
590
591
592
593
594

595
596
597
598
599
600
601

590
591
592
593
594
595
596

597
598
599
600
601
602
603
604








-
+








                }
                iAddr = iEndArcAddr + this.nBytesNodeAddress;
            }
        }
    }

    * _getArcs1 (iAddr) {
        "generator: return all arcs at <iAddr> as tuples of (nVal, iAddr)"
        // generator: return all arcs at <iAddr> as tuples of (nVal, iAddr)
        while (true) {
            let iEndArcAddr = iAddr+this.nBytesArc;
            let nRawArc = this._convBytesToInteger(this.byDic.slice(iAddr, iEndArcAddr));
            yield [nRawArc & this._arcMask, this._convBytesToInteger(this.byDic.slice(iEndArcAddr, iEndArcAddr+this.nBytesNodeAddress))];
            if (nRawArc & this._lastArcMask) {
                break;
            }
︙
628
629
630
631
632
633
634
635

636
637

631
632
633
634
635
636
637

638
639
640








-
+




    _lookupArcNode3 (nVal, iAddr) {
        // to do
    }
}


if (typeof(exports) !== 'undefined') {
if (typeof exports !== 'undefined') {
    exports.IBDAWG = IBDAWG;
}

Modified graphspell-js/spellchecker.js from [b26374afa0] to [6b69161b99]. 

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

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











+
+
+



-
-
-
-
+
+
+
+
+
+

-








// Spellchecker
// Wrapper for the IBDAWG class.
// Useful to check several dictionaries at once.

// To avoid iterating over a pile of dictionaries, it is assumed that 3 are enough:
// - the main dictionary, bundled with the package
// - the extended dictionary
// - the community dictionary, added by an organization
// - the personal dictionary, created by the user for its own convenience

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global require, exports, console, IBDAWG, Tokenizer */

"use strict";


if (typeof(require) !== 'undefined') {
    var ibdawg = require("resource://grammalecte/graphspell/ibdawg.js");
    var tokenizer = require("resource://grammalecte/graphspell/tokenizer.js");
if(typeof process !== 'undefined') {
    var ibdawg = require('./ibdawg.js');
    var tokenizer = require('./tokenizer.js');
} else if (typeof require !== 'undefined') {
    var ibdawg = require('resource://grammalecte/graphspell/ibdawg.js');
    var tokenizer = require('resource://grammalecte/graphspell/tokenizer.js');
}


${map}


const dDefaultDictionaries = new Map([
    ["fr", "fr-allvars.json"],
    ["en", "en.json"]
︙
62
63
64
65
66
67
68
69

70
71
72
73
74
75
76

66
67
68
69
70
71
72

73
74
75
76
77
78
79
80








-
+








            }
        }
        catch (e) {
            let sfDictionary = (typeof(dictionary) == "string") ? dictionary : dictionary.sLangName + "/" + dictionary.sFileName;
            if (bNecessary) {
                throw "Error: <" + sfDictionary + "> not loaded. " + e.message;
            }
            console.log("Error: <" + sfDictionary + "> not loaded.")
            console.log("Error: <" + sfDictionary + "> not loaded.");
            console.log(e.message);
            return null;
        }
    }

    loadTokenizer () {
        if (typeof(tokenizer) !== 'undefined') {
︙
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

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








-
+
















-
+








        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (this.oMainDic.isValid(sWord)) {
            return true;
        }
        if (this.bExtendedDic && this.oExtendedDic.isValid(sWord)) {
            return true;
        }
        if (this.bCommunityDic && this.oCommunityDic.isValid(sToken)) {
        if (this.bCommunityDic && this.oCommunityDic.isValid(sWord)) {
            return true;
        }
        if (this.bPersonalDic && this.oPersonalDic.isValid(sWord)) {
            return true;
        }
        return false;
    }

    lookup (sWord) {
        // checks if sWord is in dictionary as is (strict verification)
        if (this.oMainDic.lookup(sWord)) {
            return true;
        }
        if (this.bExtendedDic && this.oExtendedDic.lookup(sWord)) {
            return true;
        }
        if (this.bCommunityDic && this.oCommunityDic.lookup(sToken)) {
        if (this.bCommunityDic && this.oCommunityDic.lookup(sWord)) {
            return true;
        }
        if (this.bPersonalDic && this.oPersonalDic.lookup(sWord)) {
            return true;
        }
        return false;
    }
︙
269
270
271
272
273
274
275
276

277
278
279
280
281
282
283

273
274
275
276
277
278
279

280
281
282
283
284
285
286
287








-
+








        if (this.bPersonalDic) {
            yield this.oPersonalDic.suggest(sWord, nSuggLimit);
        }
    }

    * select (sFlexPattern="", sTagsPattern="") {
        // generator: returns all entries which flexion fits <sFlexPattern> and morphology fits <sTagsPattern>
        yield* this.oMainDic.select(sFlexPattern, sTagsPattern)
        yield* this.oMainDic.select(sFlexPattern, sTagsPattern);
        if (this.bExtendedDic) {
            yield* this.oExtendedDic.select(sFlexPattern, sTagsPattern);
        }
        if (this.bCommunityDic) {
            yield* this.oCommunityDic.select(sFlexPattern, sTagsPattern);
        }
        if (this.bPersonalDic) {
︙
297
298
299
300
301
302
303
304

305
306

301
302
303
304
305
306
307

308
309
310








-
+



        if (this.bPersonalDic) {
            lResult.push(...this.oPersonalDic.getSimilarEntries(sWord, nSuggLimit));
        }
        return lResult;
    }
}

if (typeof(exports) !== 'undefined') {
if (typeof exports !== 'undefined') {
    exports.SpellChecker = SpellChecker;
}

Modified graphspell-js/str_transform.js from [63ae767339] to [2ff1a56a97]. 

1
2





3
4
5
6
7
8
9



1
2
3
4
5
6
7
8
9
10
11
12

-
-
+
+
+
+
+








//// STRING TRANSFORMATION
/*jslint esversion: 6*/
// STRING TRANSFORMATION

/* jshint esversion:6, -W097 */
/* jslint esversion:6 */
/* global exports, console */

"use strict";


// Note: 48 is the ASCII code for "0"

var str_transform = {
︙
216
217
218
219
220
221
222
223

224
225
226
227
228
229
230
231
232

219
220
221
222
223
224
225

226
227
228
229
230
231
232
233
234
235








-
+










        let [sPfxCode, sSfxCode] = sAffCode.split('/');
        sWord = sPfxCode.slice(1) + sWord.slice(sPfxCode.charCodeAt(0)-48);
        return sSfxCode[0] == '0' ? sWord + sSfxCode.slice(1) : sWord.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
    }
};


if (typeof(exports) !== 'undefined') {
if (typeof exports !== 'undefined') {
    exports.longestCommonSubstring = str_transform.longestCommonSubstring;
    exports.distanceDamerauLevenshtein = str_transform.distanceDamerauLevenshtein;
    exports.distanceDamerauLevenshtein2 = str_transform.distanceDamerauLevenshtein2;
    exports.showDistance = str_transform.showDistance;
    exports.changeWordWithSuffixCode = str_transform.changeWordWithSuffixCode;
    exports.changeWordWithAffixCode = str_transform.changeWordWithAffixCode;
    exports.defineAffixCode = str_transform.defineAffixCode;
    exports.defineSuffixCode = str_transform.defineSuffixCode;
}

Modified graphspell-js/tokenizer.js from [88bacac87d] to [541689c69f]. 

1
2


3
4


5
6
7
8
9
10
11

1
2
3
4


5
6
7
8
9
10
11
12
13



+
+
-
-
+
+








// JavaScript
// Very simple tokenizer

/* jshint esversion:6, -W097 */
/*jslint esversion: 6*/
/*global require,exports*/
/* jslint esversion:6 */
/*global require, exports, console*/

"use strict";


const aTkzPatterns = {
    // All regexps must start with ^.
    "default":
︙
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

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








-
+



















-
+



        while (sText) {
            let iCut = 1;
            for (let [zRegex, sType] of this.aRules) {
                if (sType !== "SPACE"  ||  bWithSpaces) {
                    try {
                        if ((m = zRegex.exec(sText)) !== null) {
                            iToken += 1;
                            yield { "i": iToken, "sType": sType, "sValue": m[0], "nStart": iNext, "nEnd": iNext + m[0].length }
                            yield { "i": iToken, "sType": sType, "sValue": m[0], "nStart": iNext, "nEnd": iNext + m[0].length };
                            iCut = m[0].length;
                            break;
                        }
                    }
                    catch (e) {
                        console.error(e);
                    }
                }
            }
            iNext += iCut;
            sText = sText.slice(iCut);
        }
        if (bStartEndToken) {
            yield { "i": iToken+1, "sType": "INFO", "sValue": "<end>", "nStart": iEnd, "nEnd": iEnd, "lMorph": ["<end>"] };
        }
    }
}


if (typeof(exports) !== 'undefined') {
if (typeof exports !== 'undefined') {
    exports.Tokenizer = Tokenizer;
}

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.007s