| 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 |
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
30x
2022x
240x
84x
1x
83x
2x
35x
1x
34x
2x
1x
1x
34x
1x
33x
2x
1x
1x
2x
1x
1x
10x
1x
9x
2x
1x
1x
2x
1x
1x
2x
22x
2x
2x
2x
2x
2x
2x
2x
2x
2x
2x
2x
2x
2x
2x
9x
4x
166x
49x
1x
11x
2x
14x
3x
3x
2x
11x
1x
2x
1x
9x
3x
3x
3x
3x
3x
3x
3x
6x
3x
3x
3x
3x
3x
3x
9x
3x
1246x
774x
1x
99x
1x
103x
1x
1x
1x
93x
1x
1x
1x
71x
1x
1x
1x
1x
1x
1x
1x
1x
1x
1x
1x
1x
1x
1x
83x
1x
30x
30x
| /*
* Copyright (c) AXA Shared Services Spain S.A.
*
* Permission is hereby granted, free of charge, to any person obtaining
* a copy of this software and associated documentation files (the
* "Software"), to deal in the Software without restriction, including
* without limitation the rights to use, copy, modify, merge, publish,
* distribute, sublicense, and/or sell copies of the Software, and to
* permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
* LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
* OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
* WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
const ArabicStemmer = require('./stemmers/arabic-stemmer');
const ArmenianStemmer = require('./stemmers/armenian-stemmer');
const BasqueStemmer = require('./stemmers/basque-stemmer');
const CatalanStemmer = require('./stemmers/catalan-stemmer');
const CzechStemmer = require('./stemmers/czech-stemmer');
const ChineseStemmer = require('./stemmers/chinese-stemmer');
const ChineseTokenizer = require('./tokenizers/chinese-tokenizer');
const DanishStemmer = require('./stemmers/danish-stemmer');
const DutchStemmer = require('./stemmers/dutch-stemmer');
const EnglishStemmer = require('./stemmers/english-stemmer');
const FinnishStemmer = require('./stemmers/finnish-stemmer');
const FrenchStemmer = require('./stemmers/french-stemmer');
const GermanStemmer = require('./stemmers/german-stemmer');
const HungarianStemmer = require('./stemmers/hungarian-stemmer');
const IrishStemmer = require('./stemmers/irish-stemmer');
const ItalianStemmer = require('./stemmers/italian-stemmer');
const NorwegianStemmer = require('./stemmers/norwegian-stemmer');
const PortugueseStemmer = require('./stemmers/portuguese-stemmer');
const PunctTokenizer = require('./tokenizers/punct-tokenizer');
const RomanianStemmer = require('./stemmers/romanian-stemmer');
const RussianStemmer = require('./stemmers/russian-stemmer');
const SloveneStemmer = require('./stemmers/slovene-stemmer');
const SpanishStemmer = require('./stemmers/spanish-stemmer');
const SwedishStemmer = require('./stemmers/swedish-stemmer');
const TamilStemmer = require('./stemmers/tamil-stemmer');
const TurkishStemmer = require('./stemmers/turkish-stemmer');
const PorterStemmer = require('./stemmers/natural/porter-stemmer');
const PorterStemmerEs = require('./stemmers/natural/porter-stemmer-es');
const PorterStemmerFa = require('./stemmers/natural/porter-stemmer-fa');
const PorterStemmerFr = require('./stemmers/natural/porter-stemmer-fr');
const PorterStemmerRu = require('./stemmers/natural/porter-stemmer-ru');
const PorterStemmerIt = require('./stemmers/natural/porter-stemmer-it');
const PorterStemmerNo = require('./stemmers/natural/porter-stemmer-no');
const PorterStemmerPt = require('./stemmers/natural/porter-stemmer-pt');
const PorterStemmerSv = require('./stemmers/natural/porter-stemmer-sv');
const PorterStemmerNl = require('./stemmers/natural/porter-stemmer-nl');
const StemmerJa = require('./stemmers/natural/stemmer-ja');
const StemmerId = require('./stemmers/natural/indonesian/stemmer_id');
const {
AggressiveTokenizer,
AggressiveTokenizerFa,
AggressiveTokenizerFr,
AggressiveTokenizerRu,
AggressiveTokenizerEs,
AggressiveTokenizerId,
AggressiveTokenizerIt,
AggressiveTokenizerNl,
AggressiveTokenizerNo,
AggressiveTokenizerPt,
AggressiveTokenizerPl,
AggressiveTokenizerSv,
TokenizerJa,
} = require('./tokenizers');
class NlpUtil {
/**
* Given a locale, get the 2 character one.
* @param {String} locale Locale of the language.
* @returns {String} Locale in 2 character length.
*/
static getTruncatedLocale(locale) {
return locale ? locale.substr(0, 2).toLowerCase() : undefined;
}
static getStemmer(locale) {
switch (locale) {
case 'en': // English
if (NlpUtil.useAlternative[locale]) {
return new EnglishStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmer;
case 'fa': // Farsi
return PorterStemmerFa;
case 'fr': // French
if (NlpUtil.useAlternative[locale]) {
return new FrenchStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerFr; // French
case 'ru': // Russian
if (NlpUtil.useAlternative[locale]) {
return new RussianStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerRu;
case 'es': // Spanish
if (NlpUtil.useAlternative[locale]) {
return new SpanishStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerEs;
case 'it': // Italian
if (NlpUtil.useAlternative[locale]) {
return new ItalianStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerIt;
case 'no': // Norwegian
if (NlpUtil.useAlternative[locale]) {
return new NorwegianStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerNo;
case 'pt': // Portuguese
if (NlpUtil.useAlternative[locale]) {
return new PortugueseStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerPt;
case 'sv': // Swedish
if (NlpUtil.useAlternative[locale]) {
return new SwedishStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerSv;
case 'nl': // Dutch
if (NlpUtil.useAlternative[locale]) {
return new DutchStemmer(NlpUtil.getTokenizer(locale));
}
return PorterStemmerNl;
case 'id':
return StemmerId; // Indonesian
case 'ja':
return new StemmerJa(); // Japanese
case 'ar':
return new ArabicStemmer(NlpUtil.getTokenizer(locale)); // Arabic
case 'hy':
return new ArmenianStemmer(NlpUtil.getTokenizer(locale)); // Armenian
case 'eu':
return new BasqueStemmer(NlpUtil.getTokenizer(locale)); // Basque
case 'ca':
return new CatalanStemmer(NlpUtil.getTokenizer(locale)); // Catalan
case 'cs':
return new CzechStemmer(NlpUtil.getTokenizer(locale)); // Czech
case 'da':
return new DanishStemmer(NlpUtil.getTokenizer(locale)); // Danish
case 'fi':
return new FinnishStemmer(NlpUtil.getTokenizer(locale)); // Finnish
case 'de':
return new GermanStemmer(NlpUtil.getTokenizer(locale)); // German
case 'hu':
return new HungarianStemmer(NlpUtil.getTokenizer(locale)); // Hungarian
case 'ga':
return new IrishStemmer(NlpUtil.getTokenizer(locale)); // Irish
case 'ro':
return new RomanianStemmer(NlpUtil.getTokenizer(locale)); // Romanian
case 'sl':
return new SloveneStemmer(NlpUtil.getTokenizer(locale)); // Slovene
case 'ta':
return new TamilStemmer(NlpUtil.getTokenizer(locale)); // Tamil
case 'tr':
return new TurkishStemmer(NlpUtil.getTokenizer(locale)); // Turkish
case 'zh':
return new ChineseStemmer(); // Chinese
default:
return PorterStemmer;
}
}
static getTokenizer(locale) {
switch (locale) {
case 'en':
return new AggressiveTokenizer(); // English
case 'fa':
return new AggressiveTokenizerFa(); // Farsi
case 'fr':
return new AggressiveTokenizerFr(); // French
case 'ru':
return new AggressiveTokenizerRu(); // Russian
case 'es':
return new AggressiveTokenizerEs(); // Spanish
case 'it':
return new AggressiveTokenizerIt(); // Italian
case 'nl':
return new AggressiveTokenizerNl(); // Dutch
case 'no':
return new AggressiveTokenizerNo(); // Norwegian
case 'pt':
return new AggressiveTokenizerPt(); // Portuguese
case 'pl':
return new AggressiveTokenizerPl(); // Polish
case 'sv':
return new AggressiveTokenizerSv(); // Swedish
case 'id':
return new AggressiveTokenizerId(); // Indonesian
case 'ja':
return new TokenizerJa(); // Japanese
case 'ar':
return new PunctTokenizer(); // Arabic
case 'hy':
return new PunctTokenizer(); // Armenian
case 'eu':
return new PunctTokenizer(); // Basque
case 'ca':
return new PunctTokenizer(); // Catalan
case 'cs':
return new PunctTokenizer(); // Czech
case 'da':
return new PunctTokenizer(); // Danish
case 'fi':
return new PunctTokenizer(); // Finnish
case 'de':
return new PunctTokenizer(); // German
case 'hu':
return new PunctTokenizer(); // Hungarian
case 'ga':
return new PunctTokenizer(); // Irish
case 'ro':
return new PunctTokenizer(); // Romanian
case 'sl':
return new PunctTokenizer(); // Slovene
case 'ta':
return new PunctTokenizer(); // Tamil
case 'tr':
return new PunctTokenizer(); // Turkish
case 'zh':
return new ChineseTokenizer(); // Chinese
default:
return new PunctTokenizer();
}
}
static getCulture(locale) {
switch (locale) {
case 'en':
return 'en-us'; // English
case 'fa':
return 'fa-ir'; // Farsi
case 'fr':
return 'fr-fr'; // French
case 'ru':
return 'ru-ru'; // Russian
case 'es':
return 'es-es'; // Spanish
case 'it':
return 'it-it'; // Italian
case 'nl':
return 'nl-nl'; // Dutch
case 'no':
return 'no-no'; // Norwegian
case 'pt':
return 'pt-br'; // Portuguese
case 'pl':
return 'pl-pl'; // Polish
case 'sv':
return 'sv-se'; // Swedish
case 'id':
return 'id-id'; // Indonesian
case 'ja':
return 'ja-jp'; // Japanese
case 'ar':
return 'ar-ae'; // Arabic
case 'hy':
return 'hy-am'; // Armenian
case 'eu':
return 'eu-es'; // Basque
case 'ca':
return 'ca-es'; // Catalan
case 'cs':
return 'cs-cz'; // Czech
case 'da':
return 'da-dk'; // Danish
case 'fi':
return 'fi-fi'; // Finnish
case 'de':
return 'de-de'; // German
case 'hu':
return 'hu-hu'; // Hungarian
case 'ga':
return 'ga-ie'; // Irish
case 'ro':
return 'ro-ro'; // Romanian
case 'sl':
return 'sl-sl'; // Slovene
case 'ta':
return 'ta-in'; // Tamil
case 'tr':
return 'tr-tr'; // Turkish
case 'zh':
return 'zh-cn'; // Chinese
default:
return 'en-us';
}
}
}
NlpUtil.useAlternative = {
en: false,
fa: false,
fr: false,
ru: false,
es: false,
it: false,
nl: false,
no: false,
pt: false,
pl: false,
sv: false,
id: false,
ja: false,
ca: false,
da: false,
fi: false,
de: false,
hu: false,
ro: false,
tr: false,
};
module.exports = NlpUtil;
|