@cognica-io/uqa-darwin-arm64 0.2.2 → 0.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,515 @@
1
+ {
2
+ "format": "uqa-nori-neutral",
3
+ "format_version": 1,
4
+ "byte_order": "big",
5
+ "exporter_sha256": "176880e8983ea3ce7b9e3996a535329133242ee9e1758370c9fa20ad63bac57c",
6
+ "reference": {
7
+ "lucene_version": "10.5.1",
8
+ "lucene_commit": "64ce863a2bea79c69c19c4d56268c26710ff0ff9",
9
+ "docker_image": "eclipse-temurin@sha256:3b0a98dfbdf1067c20a7854cec159551777d2ee1381bc76cd4bd0719f543b148",
10
+ "runtime": {
11
+ "java_version": "21.0.10",
12
+ "java_runtime_version": "21.0.10+7-LTS",
13
+ "java_vendor": "Eclipse Adoptium"
14
+ },
15
+ "jars": [
16
+ {
17
+ "artifact": "lucene-core",
18
+ "url": "https://repo.maven.apache.org/maven2/org/apache/lucene/lucene-core/10.5.1/lucene-core-10.5.1.jar",
19
+ "bytes": 4744152,
20
+ "sha256": "2b4912cc792f462e8e7b350f7c958f538ee7ec42da4cf4b65902fb9d546bba53"
21
+ },
22
+ {
23
+ "artifact": "lucene-analysis-common",
24
+ "url": "https://repo.maven.apache.org/maven2/org/apache/lucene/lucene-analysis-common/10.5.1/lucene-analysis-common-10.5.1.jar",
25
+ "bytes": 1757025,
26
+ "sha256": "f710afd91a820987a48f3a215e076715b9237b324cf5458281109ef0d2a17b73"
27
+ },
28
+ {
29
+ "artifact": "lucene-analysis-nori",
30
+ "url": "https://repo.maven.apache.org/maven2/org/apache/lucene/lucene-analysis-nori/10.5.1/lucene-analysis-nori-10.5.1.jar",
31
+ "bytes": 7824879,
32
+ "sha256": "d186e323dca89700256d63925ac1fd6d3a410c84ec78603697aaf923e4e4df53"
33
+ }
34
+ ],
35
+ "dictionary_source": {
36
+ "name": "mecab-ko-dic-2.1.1-20180720",
37
+ "url": "https://s3.amazonaws.com/lucene-testdata/mecab/mecab-ko-dic-2.1.1-20180720.tar.gz",
38
+ "sha256": "fd62d3d6d8fa85145528065fabad4d7cb20f6b2201e71be4081a4e9701a5b330",
39
+ "license_file": "COPYING",
40
+ "license": "Apache-2.0",
41
+ "lucene_normalize_entries": false
42
+ },
43
+ "dictionary_resources": [
44
+ {
45
+ "path": "org/apache/lucene/analysis/ko/dict/CharacterDefinition.dat",
46
+ "bytes": 65564,
47
+ "sha256": "5ed2303b58a61819dd256f295b6cd52f869b6a15479255242133f7556c090b20"
48
+ },
49
+ {
50
+ "path": "org/apache/lucene/analysis/ko/dict/ConnectionCosts.dat",
51
+ "bytes": 11231986,
52
+ "sha256": "90902b01157c383a196c7e9798dc4bec5e6aae88d17ef83c73217312d633945e"
53
+ },
54
+ {
55
+ "path": "org/apache/lucene/analysis/ko/dict/TokenInfoDictionary$buffer.dat",
56
+ "bytes": 7288372,
57
+ "sha256": "73af46066a8d8138590b20c3941ee0c6cfe8b15d81ad8167d2565804128cca8b"
58
+ },
59
+ {
60
+ "path": "org/apache/lucene/analysis/ko/dict/TokenInfoDictionary$fst.dat",
61
+ "bytes": 5632475,
62
+ "sha256": "c07fec77418992d104b9c217661067743ada15282c167cac3d1dfdac90e12b8b"
63
+ },
64
+ {
65
+ "path": "org/apache/lucene/analysis/ko/dict/TokenInfoDictionary$posDict.dat",
66
+ "bytes": 2715,
67
+ "sha256": "12b227d6de87c7e980783ca7eed07074a69d57ef4cc0a0431221b04e3681385a"
68
+ },
69
+ {
70
+ "path": "org/apache/lucene/analysis/ko/dict/TokenInfoDictionary$targetMap.dat",
71
+ "bytes": 816309,
72
+ "sha256": "47aac565e59cb80a341199f9484d6abf128084e8b6b23e6c3d7b7a8d4263a590"
73
+ },
74
+ {
75
+ "path": "org/apache/lucene/analysis/ko/dict/UnknownDictionary$buffer.dat",
76
+ "bytes": 101,
77
+ "sha256": "2571f47d1e316d095d7727270538428e223da4e5c92990d0e4f8744cac739ade"
78
+ },
79
+ {
80
+ "path": "org/apache/lucene/analysis/ko/dict/UnknownDictionary$posDict.dat",
81
+ "bytes": 1826,
82
+ "sha256": "76cb39a78f503b5b202d5a418b0241e4f747096ccc39d13914a7c12fcd1ae678"
83
+ },
84
+ {
85
+ "path": "org/apache/lucene/analysis/ko/dict/UnknownDictionary$targetMap.dat",
86
+ "bytes": 36,
87
+ "sha256": "d5d9a3a0b35426c63b873f4b907fb9c3b51d8e6376c5ee9fbee00f960b569345"
88
+ }
89
+ ]
90
+ },
91
+ "model": {
92
+ "runtime": {
93
+ "java_version": "21.0.10",
94
+ "java_runtime_version": "21.0.10+7-LTS",
95
+ "java_vendor": "Eclipse Adoptium"
96
+ },
97
+ "surface_count": 774582,
98
+ "word_count": 816283,
99
+ "unknown_class_count": 14,
100
+ "unknown_word_count": 14,
101
+ "matrix_forward": 3822,
102
+ "matrix_backward": 2693,
103
+ "unicode_count": 1114112,
104
+ "character_count": 65536,
105
+ "pos_types": [
106
+ "MORPHEME",
107
+ "COMPOUND",
108
+ "INFLECT",
109
+ "PREANALYSIS"
110
+ ],
111
+ "pos_tags": [
112
+ {
113
+ "name": "EP",
114
+ "code": 100
115
+ },
116
+ {
117
+ "name": "EF",
118
+ "code": 101
119
+ },
120
+ {
121
+ "name": "EC",
122
+ "code": 102
123
+ },
124
+ {
125
+ "name": "ETN",
126
+ "code": 103
127
+ },
128
+ {
129
+ "name": "ETM",
130
+ "code": 104
131
+ },
132
+ {
133
+ "name": "IC",
134
+ "code": 110
135
+ },
136
+ {
137
+ "name": "JKS",
138
+ "code": 120
139
+ },
140
+ {
141
+ "name": "JKC",
142
+ "code": 121
143
+ },
144
+ {
145
+ "name": "JKG",
146
+ "code": 122
147
+ },
148
+ {
149
+ "name": "JKO",
150
+ "code": 123
151
+ },
152
+ {
153
+ "name": "JKB",
154
+ "code": 124
155
+ },
156
+ {
157
+ "name": "JKV",
158
+ "code": 125
159
+ },
160
+ {
161
+ "name": "JKQ",
162
+ "code": 126
163
+ },
164
+ {
165
+ "name": "JX",
166
+ "code": 127
167
+ },
168
+ {
169
+ "name": "JC",
170
+ "code": 128
171
+ },
172
+ {
173
+ "name": "MAG",
174
+ "code": 130
175
+ },
176
+ {
177
+ "name": "MAJ",
178
+ "code": 131
179
+ },
180
+ {
181
+ "name": "MM",
182
+ "code": 140
183
+ },
184
+ {
185
+ "name": "NNG",
186
+ "code": 150
187
+ },
188
+ {
189
+ "name": "NNP",
190
+ "code": 151
191
+ },
192
+ {
193
+ "name": "NNB",
194
+ "code": 152
195
+ },
196
+ {
197
+ "name": "NNBC",
198
+ "code": 153
199
+ },
200
+ {
201
+ "name": "NP",
202
+ "code": 154
203
+ },
204
+ {
205
+ "name": "NR",
206
+ "code": 155
207
+ },
208
+ {
209
+ "name": "SF",
210
+ "code": 160
211
+ },
212
+ {
213
+ "name": "SH",
214
+ "code": 161
215
+ },
216
+ {
217
+ "name": "SL",
218
+ "code": 162
219
+ },
220
+ {
221
+ "name": "SN",
222
+ "code": 163
223
+ },
224
+ {
225
+ "name": "SP",
226
+ "code": 164
227
+ },
228
+ {
229
+ "name": "SSC",
230
+ "code": 165
231
+ },
232
+ {
233
+ "name": "SSO",
234
+ "code": 166
235
+ },
236
+ {
237
+ "name": "SC",
238
+ "code": 167
239
+ },
240
+ {
241
+ "name": "SY",
242
+ "code": 168
243
+ },
244
+ {
245
+ "name": "SE",
246
+ "code": 169
247
+ },
248
+ {
249
+ "name": "VA",
250
+ "code": 170
251
+ },
252
+ {
253
+ "name": "VCN",
254
+ "code": 171
255
+ },
256
+ {
257
+ "name": "VCP",
258
+ "code": 172
259
+ },
260
+ {
261
+ "name": "VV",
262
+ "code": 173
263
+ },
264
+ {
265
+ "name": "VX",
266
+ "code": 174
267
+ },
268
+ {
269
+ "name": "XPN",
270
+ "code": 181
271
+ },
272
+ {
273
+ "name": "XR",
274
+ "code": 182
275
+ },
276
+ {
277
+ "name": "XSA",
278
+ "code": 183
279
+ },
280
+ {
281
+ "name": "XSN",
282
+ "code": 184
283
+ },
284
+ {
285
+ "name": "XSV",
286
+ "code": 185
287
+ },
288
+ {
289
+ "name": "UNKNOWN",
290
+ "code": 999
291
+ },
292
+ {
293
+ "name": "UNA",
294
+ "code": -1
295
+ },
296
+ {
297
+ "name": "NA",
298
+ "code": -1
299
+ },
300
+ {
301
+ "name": "VSV",
302
+ "code": -1
303
+ }
304
+ ],
305
+ "character_classes": [
306
+ "NGRAM",
307
+ "DEFAULT",
308
+ "SPACE",
309
+ "SYMBOL",
310
+ "NUMERIC",
311
+ "ALPHA",
312
+ "CYRILLIC",
313
+ "GREEK",
314
+ "HIRAGANA",
315
+ "KATAKANA",
316
+ "KANJI",
317
+ "HANGUL",
318
+ "HANJA",
319
+ "HANJANUMERIC"
320
+ ],
321
+ "unicode_scripts": [
322
+ "COMMON",
323
+ "LATIN",
324
+ "GREEK",
325
+ "CYRILLIC",
326
+ "ARMENIAN",
327
+ "HEBREW",
328
+ "ARABIC",
329
+ "SYRIAC",
330
+ "THAANA",
331
+ "DEVANAGARI",
332
+ "BENGALI",
333
+ "GURMUKHI",
334
+ "GUJARATI",
335
+ "ORIYA",
336
+ "TAMIL",
337
+ "TELUGU",
338
+ "KANNADA",
339
+ "MALAYALAM",
340
+ "SINHALA",
341
+ "THAI",
342
+ "LAO",
343
+ "TIBETAN",
344
+ "MYANMAR",
345
+ "GEORGIAN",
346
+ "HANGUL",
347
+ "ETHIOPIC",
348
+ "CHEROKEE",
349
+ "CANADIAN_ABORIGINAL",
350
+ "OGHAM",
351
+ "RUNIC",
352
+ "KHMER",
353
+ "MONGOLIAN",
354
+ "HIRAGANA",
355
+ "KATAKANA",
356
+ "BOPOMOFO",
357
+ "HAN",
358
+ "YI",
359
+ "OLD_ITALIC",
360
+ "GOTHIC",
361
+ "DESERET",
362
+ "INHERITED",
363
+ "TAGALOG",
364
+ "HANUNOO",
365
+ "BUHID",
366
+ "TAGBANWA",
367
+ "LIMBU",
368
+ "TAI_LE",
369
+ "LINEAR_B",
370
+ "UGARITIC",
371
+ "SHAVIAN",
372
+ "OSMANYA",
373
+ "CYPRIOT",
374
+ "BRAILLE",
375
+ "BUGINESE",
376
+ "COPTIC",
377
+ "NEW_TAI_LUE",
378
+ "GLAGOLITIC",
379
+ "TIFINAGH",
380
+ "SYLOTI_NAGRI",
381
+ "OLD_PERSIAN",
382
+ "KHAROSHTHI",
383
+ "BALINESE",
384
+ "CUNEIFORM",
385
+ "PHOENICIAN",
386
+ "PHAGS_PA",
387
+ "NKO",
388
+ "SUNDANESE",
389
+ "BATAK",
390
+ "LEPCHA",
391
+ "OL_CHIKI",
392
+ "VAI",
393
+ "SAURASHTRA",
394
+ "KAYAH_LI",
395
+ "REJANG",
396
+ "LYCIAN",
397
+ "CARIAN",
398
+ "LYDIAN",
399
+ "CHAM",
400
+ "TAI_THAM",
401
+ "TAI_VIET",
402
+ "AVESTAN",
403
+ "EGYPTIAN_HIEROGLYPHS",
404
+ "SAMARITAN",
405
+ "MANDAIC",
406
+ "LISU",
407
+ "BAMUM",
408
+ "JAVANESE",
409
+ "MEETEI_MAYEK",
410
+ "IMPERIAL_ARAMAIC",
411
+ "OLD_SOUTH_ARABIAN",
412
+ "INSCRIPTIONAL_PARTHIAN",
413
+ "INSCRIPTIONAL_PAHLAVI",
414
+ "OLD_TURKIC",
415
+ "BRAHMI",
416
+ "KAITHI",
417
+ "MEROITIC_HIEROGLYPHS",
418
+ "MEROITIC_CURSIVE",
419
+ "SORA_SOMPENG",
420
+ "CHAKMA",
421
+ "SHARADA",
422
+ "TAKRI",
423
+ "MIAO",
424
+ "CAUCASIAN_ALBANIAN",
425
+ "BASSA_VAH",
426
+ "DUPLOYAN",
427
+ "ELBASAN",
428
+ "GRANTHA",
429
+ "PAHAWH_HMONG",
430
+ "KHOJKI",
431
+ "LINEAR_A",
432
+ "MAHAJANI",
433
+ "MANICHAEAN",
434
+ "MENDE_KIKAKUI",
435
+ "MODI",
436
+ "MRO",
437
+ "OLD_NORTH_ARABIAN",
438
+ "NABATAEAN",
439
+ "PALMYRENE",
440
+ "PAU_CIN_HAU",
441
+ "OLD_PERMIC",
442
+ "PSALTER_PAHLAVI",
443
+ "SIDDHAM",
444
+ "KHUDAWADI",
445
+ "TIRHUTA",
446
+ "WARANG_CITI",
447
+ "AHOM",
448
+ "ANATOLIAN_HIEROGLYPHS",
449
+ "HATRAN",
450
+ "MULTANI",
451
+ "OLD_HUNGARIAN",
452
+ "SIGNWRITING",
453
+ "ADLAM",
454
+ "BHAIKSUKI",
455
+ "MARCHEN",
456
+ "NEWA",
457
+ "OSAGE",
458
+ "TANGUT",
459
+ "MASARAM_GONDI",
460
+ "NUSHU",
461
+ "SOYOMBO",
462
+ "ZANABAZAR_SQUARE",
463
+ "HANIFI_ROHINGYA",
464
+ "OLD_SOGDIAN",
465
+ "SOGDIAN",
466
+ "DOGRA",
467
+ "GUNJALA_GONDI",
468
+ "MAKASAR",
469
+ "MEDEFAIDRIN",
470
+ "ELYMAIC",
471
+ "NANDINAGARI",
472
+ "NYIAKENG_PUACHUE_HMONG",
473
+ "WANCHO",
474
+ "YEZIDI",
475
+ "CHORASMIAN",
476
+ "DIVES_AKURU",
477
+ "KHITAN_SMALL_SCRIPT",
478
+ "VITHKUQI",
479
+ "OLD_UYGHUR",
480
+ "CYPRO_MINOAN",
481
+ "TANGSA",
482
+ "TOTO",
483
+ "KAWI",
484
+ "NAG_MUNDARI",
485
+ "UNKNOWN"
486
+ ]
487
+ },
488
+ "files": [
489
+ {
490
+ "path": "lexicon.bin",
491
+ "bytes": 52951152,
492
+ "sha256": "6a58df4fce3e942548df9148781c529da00adee25b675f3097a04e2da149688b"
493
+ },
494
+ {
495
+ "path": "unknown.bin",
496
+ "bytes": 872,
497
+ "sha256": "e819484c9a88f9747eeb83b45be1a72640e497adb2685ed68f3e851d486cff67"
498
+ },
499
+ {
500
+ "path": "connection_costs.bin",
501
+ "bytes": 20585308,
502
+ "sha256": "3f4de9fbe07d5915096a8e199b93981c766317191e11921834cb0926574997eb"
503
+ },
504
+ {
505
+ "path": "characters.bin",
506
+ "bytes": 131102,
507
+ "sha256": "9014b27f52f1764285f732061b03372f2db0bc987d9ec8ebf90f3ce6d6c04778"
508
+ },
509
+ {
510
+ "path": "unicode.bin",
511
+ "bytes": 8912908,
512
+ "sha256": "cf7047a1256da56cfa12e4e681028c1a96eb716ffca98a617f062174117db8a1"
513
+ }
514
+ ]
515
+ }
@@ -0,0 +1,40 @@
1
+ {
2
+ "format": "uqa-nori-bundled-resource",
3
+ "format_version": 1,
4
+ "bundle_format_version": 1,
5
+ "dictionary_id": "ee85ee5796c706ea7288e44e64c7f58ba7bd22cea5683c1f4196c29a2435d74a",
6
+ "packer": "uqa-analysis pack_nori; bundle format 1",
7
+ "compression": "miniz_oxide 0.8.9; zlib level 9",
8
+ "files": [
9
+ {
10
+ "path": "data/nori.uqan",
11
+ "bytes": 9829534,
12
+ "sha256": "0d920523991ed60909972d85df630c65747ff5d49e1138e4998ca39f0079538d"
13
+ },
14
+ {
15
+ "path": "data/model_manifest.json",
16
+ "bytes": 11215,
17
+ "sha256": "4dcc735ed00862d2558d08af39256e933c6c59dd0b4fc13dd5f0a7d27977b699"
18
+ },
19
+ {
20
+ "path": "THIRD-PARTY/JDK-UNICODE.md",
21
+ "bytes": 9078,
22
+ "sha256": "6f72f10d166b2c2e8a395e03e734c5afc852b59aeca73ced124f6b9c96268d53"
23
+ },
24
+ {
25
+ "path": "THIRD-PARTY/LUCENE-LICENSE.txt",
26
+ "bytes": 26085,
27
+ "sha256": "a2521407b3209df7dcebfc12cd6d732b24bfa2fe44982ef613e269666482521d"
28
+ },
29
+ {
30
+ "path": "THIRD-PARTY/LUCENE-NOTICE.txt",
31
+ "bytes": 9782,
32
+ "sha256": "d3b82734d5e181509c4b6b832f5d3a90c8c6a34fc195272fc8957ccb9e8e20a8"
33
+ },
34
+ {
35
+ "path": "THIRD-PARTY/MECAB-COPYING.txt",
36
+ "bytes": 11357,
37
+ "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4"
38
+ }
39
+ ]
40
+ }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@cognica-io/uqa-darwin-arm64",
3
- "version": "0.2.2",
3
+ "version": "0.3.0",
4
4
  "description": "Node.js bindings for embedded UQA and local or Cloud HTTP SQL (aarch64-apple-darwin)",
5
5
  "license": "AGPL-3.0-only",
6
6
  "author": "Jaepil Jeong <jaepil@cognica.io>",
@@ -17,7 +17,14 @@
17
17
  "LICENSE",
18
18
  "LICENSING.md",
19
19
  "LICENSES/UQA-FOSS-EXCEPTION-1.0.txt",
20
- "LICENSES/UQA-NONCOMMERCIAL-EXCEPTION-1.0.txt"
20
+ "LICENSES/UQA-NONCOMMERCIAL-EXCEPTION-1.0.txt",
21
+ "THIRD-PARTY/JDK-UNICODE.md",
22
+ "THIRD-PARTY/LUCENE-LICENSE.txt",
23
+ "THIRD-PARTY/LUCENE-NOTICE.txt",
24
+ "THIRD-PARTY/MECAB-COPYING.txt",
25
+ "THIRD-PARTY/LUCENE-SOURCE.md",
26
+ "THIRD-PARTY/NORI-RESOURCE-MANIFEST.json",
27
+ "THIRD-PARTY/NORI-MODEL-MANIFEST.json"
21
28
  ],
22
29
  "os": [
23
30
  "darwin"
Binary file