@delali/narsil 0.1.15 → 0.2.0
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.
- package/NOTICE +54 -0
- package/README.md +38 -982
- package/dist/adapters/filesystem.mjs +1 -1
- package/dist/adapters/indexeddb.mjs +1 -1
- package/dist/{chunk-WISGW24C.mjs → chunk-AUMKFYTG.mjs} +1 -1
- package/dist/{chunk-HRABJLPB.mjs → chunk-BKAI2WXI.mjs} +1 -0
- package/dist/chunk-GHJWC2E5.mjs +9 -0
- package/dist/chunk-KH3YGMVT.mjs +15 -0
- package/dist/{chunk-ALB35PRQ.mjs → chunk-M2EDG55Y.mjs} +8 -0
- package/dist/{chunk-HMO6OMZ3.mjs → chunk-S6IAXOBA.mjs} +1073 -506
- package/dist/chunk-TGP5M5R7.mjs +880 -0
- package/dist/chunk-U2BKYEC7.mjs +254 -0
- package/dist/{chunk-MEW7HD75.mjs → chunk-XAKNSWIK.mjs} +2543 -1154
- package/dist/{config-CojEPOgS.d.ts → config-P27AtSn4.d.ts} +28 -7
- package/dist/direct-executor-2FV3MEDD.mjs +5 -0
- package/dist/distribution/coordinator/etcd.d.ts +2 -2
- package/dist/distribution/coordinator/etcd.mjs +2 -2
- package/dist/distribution/coordinator/in-memory.d.ts +2 -2
- package/dist/distribution.d.ts +10 -4
- package/dist/distribution.mjs +1875 -1772
- package/dist/embeddings/openai.mjs +1 -1
- package/dist/index.browser.mjs +4566 -1783
- package/dist/index.d.ts +14 -5
- package/dist/index.mjs +6 -5
- package/dist/{language-ONQ3iVDf.d.ts → language-CmJBHf1j.d.ts} +4 -1
- package/dist/languages/albanian.d.ts +5 -0
- package/dist/languages/albanian.mjs +103 -0
- package/dist/languages/amharic.d.ts +5 -0
- package/dist/languages/amharic.mjs +240 -0
- package/dist/languages/arabic.d.ts +1 -1
- package/dist/languages/arabic.mjs +939 -154
- package/dist/languages/armenian.d.ts +1 -1
- package/dist/languages/armenian.mjs +275 -243
- package/dist/languages/azerbaijani.d.ts +5 -0
- package/dist/languages/azerbaijani.mjs +152 -0
- package/dist/languages/bambara.d.ts +5 -0
- package/dist/languages/bambara.mjs +60 -0
- package/dist/languages/basque.d.ts +5 -0
- package/dist/languages/basque.mjs +726 -0
- package/dist/languages/belarusian.d.ts +5 -0
- package/dist/languages/belarusian.mjs +100 -0
- package/dist/languages/bengali.d.ts +5 -0
- package/dist/languages/bengali.mjs +128 -0
- package/dist/languages/bosnian.d.ts +5 -0
- package/dist/languages/bosnian.mjs +197 -0
- package/dist/languages/breton.d.ts +5 -0
- package/dist/languages/breton.mjs +96 -0
- package/dist/languages/bulgarian.d.ts +1 -1
- package/dist/languages/bulgarian.mjs +11 -2
- package/dist/languages/burmese.d.ts +5 -0
- package/dist/languages/burmese.mjs +57 -0
- package/dist/languages/catalan.d.ts +5 -0
- package/dist/languages/catalan.mjs +987 -0
- package/dist/languages/chinese.d.ts +1 -1
- package/dist/languages/chinese.mjs +4 -3
- package/dist/languages/croatian.d.ts +5 -0
- package/dist/languages/croatian.mjs +191 -0
- package/dist/languages/czech.d.ts +5 -0
- package/dist/languages/czech.mjs +628 -0
- package/dist/languages/dagbani.d.ts +1 -1
- package/dist/languages/dagbani.mjs +11 -2
- package/dist/languages/danish.d.ts +1 -1
- package/dist/languages/danish.mjs +215 -110
- package/dist/languages/dutch.d.ts +1 -1
- package/dist/languages/dutch.mjs +1248 -163
- package/dist/languages/english.d.ts +1 -1
- package/dist/languages/english.mjs +2 -1
- package/dist/languages/esperanto.d.ts +5 -0
- package/dist/languages/esperanto.mjs +689 -0
- package/dist/languages/estonian.d.ts +5 -0
- package/dist/languages/estonian.mjs +2160 -0
- package/dist/languages/ewe.d.ts +1 -1
- package/dist/languages/ewe.mjs +11 -2
- package/dist/languages/faroese.d.ts +5 -0
- package/dist/languages/faroese.mjs +93 -0
- package/dist/languages/fijian.d.ts +5 -0
- package/dist/languages/fijian.mjs +55 -0
- package/dist/languages/finnish.d.ts +1 -1
- package/dist/languages/finnish.mjs +528 -263
- package/dist/languages/french.d.ts +1 -1
- package/dist/languages/french.mjs +950 -437
- package/dist/languages/ga.d.ts +1 -1
- package/dist/languages/ga.mjs +2 -1
- package/dist/languages/galician.d.ts +5 -0
- package/dist/languages/galician.mjs +172 -0
- package/dist/languages/georgian.d.ts +5 -0
- package/dist/languages/georgian.mjs +91 -0
- package/dist/languages/german.d.ts +1 -1
- package/dist/languages/german.mjs +432 -162
- package/dist/languages/greek.d.ts +1 -1
- package/dist/languages/greek.mjs +1970 -281
- package/dist/languages/guarani.d.ts +5 -0
- package/dist/languages/guarani.mjs +132 -0
- package/dist/languages/gujarati.d.ts +5 -0
- package/dist/languages/gujarati.mjs +234 -0
- package/dist/languages/haitian-creole.d.ts +5 -0
- package/dist/languages/haitian-creole.mjs +106 -0
- package/dist/languages/hausa.d.ts +1 -1
- package/dist/languages/hausa.mjs +2 -1
- package/dist/languages/hawaiian.d.ts +5 -0
- package/dist/languages/hawaiian.mjs +69 -0
- package/dist/languages/hebrew.d.ts +5 -0
- package/dist/languages/hebrew.mjs +213 -0
- package/dist/languages/hindi.d.ts +1 -1
- package/dist/languages/hindi.mjs +175 -97
- package/dist/languages/hungarian.d.ts +1 -1
- package/dist/languages/hungarian.mjs +412 -326
- package/dist/languages/icelandic.d.ts +5 -0
- package/dist/languages/icelandic.mjs +161 -0
- package/dist/languages/igbo.d.ts +1 -1
- package/dist/languages/igbo.mjs +2 -1
- package/dist/languages/indonesian.d.ts +1 -1
- package/dist/languages/indonesian.mjs +329 -137
- package/dist/languages/irish.d.ts +1 -1
- package/dist/languages/irish.mjs +223 -139
- package/dist/languages/italian.d.ts +1 -1
- package/dist/languages/italian.mjs +703 -406
- package/dist/languages/japanese.d.ts +1 -1
- package/dist/languages/japanese.mjs +5 -108
- package/dist/languages/kannada.d.ts +5 -0
- package/dist/languages/kannada.mjs +94 -0
- package/dist/languages/kazakh.d.ts +5 -0
- package/dist/languages/kazakh.mjs +90 -0
- package/dist/languages/khmer.d.ts +5 -0
- package/dist/languages/khmer.mjs +181 -0
- package/dist/languages/kinyarwanda.d.ts +5 -0
- package/dist/languages/kinyarwanda.mjs +99 -0
- package/dist/languages/kirundi.d.ts +5 -0
- package/dist/languages/kirundi.mjs +92 -0
- package/dist/languages/korean.d.ts +5 -0
- package/dist/languages/korean.mjs +252 -0
- package/dist/languages/kurmanji.d.ts +5 -0
- package/dist/languages/kurmanji.mjs +50 -0
- package/dist/languages/kyrgyz.d.ts +5 -0
- package/dist/languages/kyrgyz.mjs +108 -0
- package/dist/languages/lao.d.ts +5 -0
- package/dist/languages/lao.mjs +63 -0
- package/dist/languages/latin.d.ts +5 -0
- package/dist/languages/latin.mjs +69 -0
- package/dist/languages/latvian.d.ts +5 -0
- package/dist/languages/latvian.mjs +173 -0
- package/dist/languages/lingala.d.ts +5 -0
- package/dist/languages/lingala.mjs +61 -0
- package/dist/languages/lithuanian.d.ts +5 -0
- package/dist/languages/lithuanian.mjs +571 -0
- package/dist/languages/luxembourgish.d.ts +5 -0
- package/dist/languages/luxembourgish.mjs +214 -0
- package/dist/languages/macedonian.d.ts +5 -0
- package/dist/languages/macedonian.mjs +808 -0
- package/dist/languages/malagasy.d.ts +5 -0
- package/dist/languages/malagasy.mjs +67 -0
- package/dist/languages/malay.d.ts +5 -0
- package/dist/languages/malay.mjs +482 -0
- package/dist/languages/malayalam.d.ts +5 -0
- package/dist/languages/malayalam.mjs +122 -0
- package/dist/languages/maltese.d.ts +5 -0
- package/dist/languages/maltese.mjs +139 -0
- package/dist/languages/maori.d.ts +5 -0
- package/dist/languages/maori.mjs +79 -0
- package/dist/languages/marathi.d.ts +5 -0
- package/dist/languages/marathi.mjs +111 -0
- package/dist/languages/nepali.d.ts +1 -1
- package/dist/languages/nepali.mjs +209 -99
- package/dist/languages/norwegian.d.ts +1 -1
- package/dist/languages/norwegian.mjs +218 -85
- package/dist/languages/oromo.d.ts +5 -0
- package/dist/languages/oromo.mjs +78 -0
- package/dist/languages/persian.d.ts +5 -0
- package/dist/languages/persian.mjs +710 -0
- package/dist/languages/polish.d.ts +5 -0
- package/dist/languages/polish.mjs +614 -0
- package/dist/languages/portuguese.d.ts +1 -1
- package/dist/languages/portuguese.mjs +613 -380
- package/dist/languages/punjabi.d.ts +5 -0
- package/dist/languages/punjabi.mjs +197 -0
- package/dist/languages/romanian.d.ts +1 -1
- package/dist/languages/romanian.mjs +561 -382
- package/dist/languages/russian.d.ts +1 -1
- package/dist/languages/russian.mjs +373 -244
- package/dist/languages/samoan.d.ts +5 -0
- package/dist/languages/samoan.mjs +63 -0
- package/dist/languages/sanskrit.d.ts +1 -1
- package/dist/languages/sanskrit.mjs +2 -2
- package/dist/languages/scottish-gaelic.d.ts +5 -0
- package/dist/languages/scottish-gaelic.mjs +370 -0
- package/dist/languages/serbian.d.ts +1 -1
- package/dist/languages/serbian.mjs +3635 -155
- package/dist/languages/shona.d.ts +5 -0
- package/dist/languages/shona.mjs +91 -0
- package/dist/languages/sinhala.d.ts +5 -0
- package/dist/languages/sinhala.mjs +182 -0
- package/dist/languages/slovak.d.ts +5 -0
- package/dist/languages/slovak.mjs +430 -0
- package/dist/languages/slovenian.d.ts +1 -1
- package/dist/languages/slovenian.mjs +11 -2
- package/dist/languages/sorani.d.ts +5 -0
- package/dist/languages/sorani.mjs +156 -0
- package/dist/languages/spanish.d.ts +1 -1
- package/dist/languages/spanish.mjs +676 -374
- package/dist/languages/swahili.d.ts +1 -1
- package/dist/languages/swahili.mjs +2 -1
- package/dist/languages/swedish.d.ts +1 -1
- package/dist/languages/swedish.mjs +237 -95
- package/dist/languages/tagalog.d.ts +5 -0
- package/dist/languages/tagalog.mjs +159 -0
- package/dist/languages/tamil.d.ts +1 -1
- package/dist/languages/tamil.mjs +836 -64
- package/dist/languages/tatar.d.ts +5 -0
- package/dist/languages/tatar.mjs +1017 -0
- package/dist/languages/telugu.d.ts +5 -0
- package/dist/languages/telugu.mjs +62 -0
- package/dist/languages/thai.d.ts +5 -0
- package/dist/languages/thai.mjs +65 -0
- package/dist/languages/tibetan.d.ts +5 -0
- package/dist/languages/tibetan.mjs +119 -0
- package/dist/languages/tigrinya.d.ts +5 -0
- package/dist/languages/tigrinya.mjs +194 -0
- package/dist/languages/tongan.d.ts +5 -0
- package/dist/languages/tongan.mjs +56 -0
- package/dist/languages/turkish.d.ts +1 -1
- package/dist/languages/turkish.mjs +1246 -393
- package/dist/languages/twi.d.ts +1 -1
- package/dist/languages/twi.mjs +13 -2
- package/dist/languages/ukrainian.d.ts +1 -1
- package/dist/languages/ukrainian.mjs +125 -47
- package/dist/languages/urdu.d.ts +5 -0
- package/dist/languages/urdu.mjs +528 -0
- package/dist/languages/vietnamese.d.ts +5 -0
- package/dist/languages/vietnamese.mjs +277 -0
- package/dist/languages/welsh.d.ts +5 -0
- package/dist/languages/welsh.mjs +446 -0
- package/dist/languages/wolof.d.ts +5 -0
- package/dist/languages/wolof.mjs +79 -0
- package/dist/languages/xhosa.d.ts +5 -0
- package/dist/languages/xhosa.mjs +95 -0
- package/dist/languages/yoruba.d.ts +1 -1
- package/dist/languages/yoruba.mjs +1 -0
- package/dist/languages/zulu.d.ts +1 -1
- package/dist/languages/zulu.mjs +2 -1
- package/dist/narsil-CMZRPDlQ.d.ts +159 -0
- package/dist/persistence/durability/checkpoint-worker.d.ts +13 -0
- package/dist/persistence/durability/checkpoint-worker.mjs +6 -5
- package/dist/{schema-DCgkO1j4.d.ts → schema-BnvLvjRp.d.ts} +5 -3
- package/dist/server.d.ts +4 -3
- package/dist/server.mjs +13 -2
- package/dist/{types-DHX6zGeD.d.ts → types-BRTcBgAp.d.ts} +1 -1
- package/dist/workers/entry.mjs +2 -2
- package/package.json +10 -3
- package/dist/chunk-TW6BXTOL.mjs +0 -338
- package/dist/direct-executor-E52FFGDE.mjs +0 -4
- package/dist/narsil-D-84Nvm4.d.ts +0 -72
package/dist/index.d.ts
CHANGED
|
@@ -1,8 +1,17 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
|
|
1
|
+
import { S as StopWordOverride, C as CustomTokenizer } from './schema-BnvLvjRp.js';
|
|
2
|
+
export { A as AnyDocument, B as BM25Params, E as EmbeddingFieldConfig, F as FieldType, I as IndexConfig, a as InsertOptions, P as PartitionConfig, b as SchemaDefinition, c as ScoringMode } from './schema-BnvLvjRp.js';
|
|
3
|
+
import { L as LanguageModule } from './language-CmJBHf1j.js';
|
|
4
|
+
export { T as TokenizerConfig } from './language-CmJBHf1j.js';
|
|
5
|
+
export { A as ArrayFilter, B as BatchResult, C as ComparisonFilter, D as DurabilityConfig, E as ErrorCode, a as ErrorCodes, F as FacetConfig, b as FacetResult, c as FilterExpression, G as GeoPolygonFilter, d as GeoRadiusFilter, e as GroupConfig, f as GroupReducer, g as GroupResult, H as HighlightConfig, h as HighlightMatch, i as Hit, j as HybridConfig, I as IndexContext, k as IndexInfo, l as IndexStats, m as InsertContext, M as MemoryStats, N as NarsilConfig, n as NarsilError, o as NarsilPlugin, P as PartitionContext, p as PartitionStatsResult, q as PreflightResult, r as PresenceFilter, s as ProcessMemoryReport, Q as QueryParams, t as QueryResult, R as RemoveContext, S as ScoreComponents, u as SearchContext, v as SearchMode, w as StringFilter, x as SuggestParams, y as SuggestResult, T as TermMatchPolicy, U as UpdateContext, V as VectorMaintenanceResult, z as VectorQueryConfig, W as WorkerConfig, J as WorkerContext } from './config-P27AtSn4.js';
|
|
6
|
+
export { N as Narsil, a as NarsilEventMap, c as createNarsil } from './narsil-CMZRPDlQ.js';
|
|
4
7
|
export { E as EmbeddingAdapter, I as InvalidationAdapter, a as InvalidationEvent, P as PartitionStatistics, b as PersistenceAdapter } from './adapters-Bo2JQg8b.js';
|
|
5
|
-
|
|
8
|
+
|
|
9
|
+
declare function registerTokenizer(name: string, tokenizer: CustomTokenizer): void;
|
|
10
|
+
declare function registerStopWords(name: string, stopWords: StopWordOverride): void;
|
|
11
|
+
declare function hasTokenizer(name: string): boolean;
|
|
12
|
+
declare function hasStopWords(name: string): boolean;
|
|
13
|
+
declare function getTokenizer(name: string): CustomTokenizer;
|
|
14
|
+
declare function getStopWords(name: string): StopWordOverride;
|
|
6
15
|
|
|
7
16
|
declare function configureNormalizationCache(maxSize: number): void;
|
|
8
17
|
declare function clearNormalizationCache(): void;
|
|
@@ -16,4 +25,4 @@ declare function isSimdAvailable(): boolean;
|
|
|
16
25
|
|
|
17
26
|
declare const VERSION = "0.1.0";
|
|
18
27
|
|
|
19
|
-
export { LanguageModule, VERSION, clearNormalizationCache, configureNormalizationCache, getLanguage, getNormalizationCacheSize, isSimdAvailable, registerLanguage, resetNormalizationCache };
|
|
28
|
+
export { CustomTokenizer, LanguageModule, StopWordOverride, VERSION, clearNormalizationCache, configureNormalizationCache, getLanguage, getNormalizationCacheSize, getStopWords, getTokenizer, hasStopWords, hasTokenizer, isSimdAvailable, registerLanguage, registerStopWords, registerTokenizer, resetNormalizationCache };
|
package/dist/index.mjs
CHANGED
|
@@ -1,7 +1,8 @@
|
|
|
1
|
-
export { VERSION, createNarsil } from './chunk-
|
|
2
|
-
export { clearNormalizationCache, configureNormalizationCache, getLanguage, getNormalizationCacheSize, registerLanguage, resetNormalizationCache } from './chunk-
|
|
1
|
+
export { VERSION, createNarsil } from './chunk-XAKNSWIK.mjs';
|
|
2
|
+
export { clearNormalizationCache, configureNormalizationCache, getLanguage, getNormalizationCacheSize, getStopWords, getTokenizer, hasStopWords, hasTokenizer, registerLanguage, registerStopWords, registerTokenizer, resetNormalizationCache } from './chunk-S6IAXOBA.mjs';
|
|
3
|
+
import './chunk-TGP5M5R7.mjs';
|
|
3
4
|
export { isSimdAvailable } from './chunk-S7RJJMHI.mjs';
|
|
4
5
|
import './chunk-KMMJMDUA.mjs';
|
|
5
|
-
import './chunk-
|
|
6
|
-
export { ErrorCodes, NarsilError } from './chunk-
|
|
7
|
-
import './chunk-
|
|
6
|
+
import './chunk-U2BKYEC7.mjs';
|
|
7
|
+
export { ErrorCodes, NarsilError } from './chunk-M2EDG55Y.mjs';
|
|
8
|
+
import './chunk-BKAI2WXI.mjs';
|
|
@@ -1,7 +1,9 @@
|
|
|
1
1
|
interface LanguageModule {
|
|
2
2
|
name: string;
|
|
3
|
+
revision: string;
|
|
3
4
|
stemmer: ((token: string) => string) | null;
|
|
4
5
|
stopWords: Set<string>;
|
|
6
|
+
normalizer?: (token: string) => string;
|
|
5
7
|
tokenizer?: TokenizerConfig;
|
|
6
8
|
}
|
|
7
9
|
interface TokenizerConfig {
|
|
@@ -9,6 +11,7 @@ interface TokenizerConfig {
|
|
|
9
11
|
normalizeDiacritics?: boolean;
|
|
10
12
|
minTokenLength?: number;
|
|
11
13
|
stripPossessive?: boolean;
|
|
14
|
+
ngramSize?: number;
|
|
12
15
|
}
|
|
13
16
|
|
|
14
|
-
export type { LanguageModule as L };
|
|
17
|
+
export type { LanguageModule as L, TokenizerConfig as T };
|
|
@@ -0,0 +1,103 @@
|
|
|
1
|
+
// src/languages/albanian.ts
|
|
2
|
+
var stopWords = /* @__PURE__ */ new Set([
|
|
3
|
+
"ai",
|
|
4
|
+
"ajo",
|
|
5
|
+
"as",
|
|
6
|
+
"asnj\xEB",
|
|
7
|
+
"ata",
|
|
8
|
+
"atje",
|
|
9
|
+
"ato",
|
|
10
|
+
"aty",
|
|
11
|
+
"brenda",
|
|
12
|
+
"\xE7do",
|
|
13
|
+
"\xE7far\xEB",
|
|
14
|
+
"cila",
|
|
15
|
+
"cil\xEBt",
|
|
16
|
+
"cili",
|
|
17
|
+
"deri",
|
|
18
|
+
"dhe",
|
|
19
|
+
"disa",
|
|
20
|
+
"do",
|
|
21
|
+
"e",
|
|
22
|
+
"edhe",
|
|
23
|
+
"\xEBsht\xEB",
|
|
24
|
+
"gjat\xEB",
|
|
25
|
+
"gjithashtu",
|
|
26
|
+
"gjith\xEB",
|
|
27
|
+
"i",
|
|
28
|
+
"im",
|
|
29
|
+
"ime",
|
|
30
|
+
"ishte",
|
|
31
|
+
"jan\xEB",
|
|
32
|
+
"jasht\xEB",
|
|
33
|
+
"jon\xEB",
|
|
34
|
+
"jote",
|
|
35
|
+
"ju",
|
|
36
|
+
"juaj",
|
|
37
|
+
"ka",
|
|
38
|
+
"kam",
|
|
39
|
+
"kan\xEB",
|
|
40
|
+
"ke",
|
|
41
|
+
"kemi",
|
|
42
|
+
"keni",
|
|
43
|
+
"k\xEBta",
|
|
44
|
+
"k\xEBto",
|
|
45
|
+
"k\xEBtu",
|
|
46
|
+
"kjo",
|
|
47
|
+
"ku",
|
|
48
|
+
"kur",
|
|
49
|
+
"ky",
|
|
50
|
+
"lart",
|
|
51
|
+
"mbi",
|
|
52
|
+
"me",
|
|
53
|
+
"m\xEB",
|
|
54
|
+
"midis",
|
|
55
|
+
"mos",
|
|
56
|
+
"nd\xEBr",
|
|
57
|
+
"nd\xEBrmjet",
|
|
58
|
+
"ne",
|
|
59
|
+
"n\xEB",
|
|
60
|
+
"n\xEBn",
|
|
61
|
+
"nga",
|
|
62
|
+
"nj\xEB",
|
|
63
|
+
"nuk",
|
|
64
|
+
"ose",
|
|
65
|
+
"pa",
|
|
66
|
+
"pak",
|
|
67
|
+
"para",
|
|
68
|
+
"pas",
|
|
69
|
+
"pastaj",
|
|
70
|
+
"p\xEBr",
|
|
71
|
+
"por",
|
|
72
|
+
"posht\xEB",
|
|
73
|
+
"prej",
|
|
74
|
+
"q\xEB",
|
|
75
|
+
"sa",
|
|
76
|
+
"saj",
|
|
77
|
+
"shum\xEB",
|
|
78
|
+
"si",
|
|
79
|
+
"sipas",
|
|
80
|
+
"tani",
|
|
81
|
+
"te",
|
|
82
|
+
"t\xEB",
|
|
83
|
+
"tek",
|
|
84
|
+
"ti",
|
|
85
|
+
"tij",
|
|
86
|
+
"tjet\xEBr",
|
|
87
|
+
"tyre",
|
|
88
|
+
"u",
|
|
89
|
+
"un\xEB",
|
|
90
|
+
"vet\xEB",
|
|
91
|
+
"vet\xEBm",
|
|
92
|
+
"veten",
|
|
93
|
+
"yt"
|
|
94
|
+
]);
|
|
95
|
+
var albanian = {
|
|
96
|
+
name: "albanian",
|
|
97
|
+
revision: "1",
|
|
98
|
+
stemmer: null,
|
|
99
|
+
stopWords,
|
|
100
|
+
tokenizer: { splitPattern: /[^a-z0-9çë]+/gi }
|
|
101
|
+
};
|
|
102
|
+
|
|
103
|
+
export { albanian };
|
|
@@ -0,0 +1,240 @@
|
|
|
1
|
+
// src/languages/amharic.ts
|
|
2
|
+
var stopWords = /* @__PURE__ */ new Set([
|
|
3
|
+
"\u1201\u1208\u1271\u1295\u121D",
|
|
4
|
+
"\u1201\u1209",
|
|
5
|
+
"\u1201\u120D",
|
|
6
|
+
"\u1201\u1294\u1273",
|
|
7
|
+
"\u1206\u1290",
|
|
8
|
+
"\u1206\u1290\u12CD",
|
|
9
|
+
"\u1206\u1291",
|
|
10
|
+
"\u1206\u1296\u121D",
|
|
11
|
+
"\u1208\u1206\u1290",
|
|
12
|
+
"\u1208\u1206\u1290\u12CD",
|
|
13
|
+
"\u1208\u1206\u1291",
|
|
14
|
+
"\u1208\u120C\u120E\u127D",
|
|
15
|
+
"\u1208\u121B\u1293\u1278\u12CD\u121D",
|
|
16
|
+
"\u1208\u121B\u1295\u129B\u12CD\u121D",
|
|
17
|
+
"\u1208\u1290\u12DA\u1205",
|
|
18
|
+
"\u1208\u12A5\u12EB\u1295\u12F3\u1295\u12F1",
|
|
19
|
+
"\u1208\u12DA\u1201",
|
|
20
|
+
"\u1208\u12DA\u1205",
|
|
21
|
+
"\u120A\u1206\u1295",
|
|
22
|
+
"\u120B\u12ED",
|
|
23
|
+
"\u120C\u120B",
|
|
24
|
+
"\u120C\u120E\u127D",
|
|
25
|
+
"\u120D\u12E9",
|
|
26
|
+
"\u1218\u1206\u1291",
|
|
27
|
+
"\u1218\u1206\u1291\u1295",
|
|
28
|
+
"\u1218\u1206\u1293\u1278\u12CD",
|
|
29
|
+
"\u1218\u1206\u1293\u1278\u12CD\u1295",
|
|
30
|
+
"\u1218\u1206\u1295",
|
|
31
|
+
"\u121B\u1208\u1271",
|
|
32
|
+
"\u121B\u1208\u1275",
|
|
33
|
+
"\u121B\u1293\u1278\u12CD\u121D",
|
|
34
|
+
"\u121B\u1293\u1278\u12CD\u1295\u121D",
|
|
35
|
+
"\u121B\u1295",
|
|
36
|
+
"\u121B\u1295\u121D",
|
|
37
|
+
"\u121B\u1295\u129B\u12CD\u121D",
|
|
38
|
+
"\u121B\u12F5\u1228\u130D",
|
|
39
|
+
"\u121D\u1295\u130A\u12DC\u121D",
|
|
40
|
+
"\u122B\u1233\u127D\u1201\u1295",
|
|
41
|
+
"\u122B\u1235\u1205\u1295",
|
|
42
|
+
"\u122B\u1235\u123D\u1295",
|
|
43
|
+
"\u1230\u121E\u1291\u1295",
|
|
44
|
+
"\u1230\u12A3\u1275",
|
|
45
|
+
"\u1232\u1206\u1291",
|
|
46
|
+
"\u1232\u1206\u1295",
|
|
47
|
+
"\u1232\u1206\u1295\u1293",
|
|
48
|
+
"\u1232\u120D",
|
|
49
|
+
"\u1232\u1263\u120D",
|
|
50
|
+
"\u1232\u1296\u122D",
|
|
51
|
+
"\u1233\u1208",
|
|
52
|
+
"\u1233\u12ED\u1206\u1295",
|
|
53
|
+
"\u1235\u1208\u1206\u1290",
|
|
54
|
+
"\u1235\u1208\u121B\u1293\u1278\u12CD\u121D",
|
|
55
|
+
"\u1235\u1208\u12DA\u1201",
|
|
56
|
+
"\u1235\u121D",
|
|
57
|
+
"\u1236\u1235\u1270\u129B",
|
|
58
|
+
"\u1241\u1325\u122D",
|
|
59
|
+
"\u1260\u1201\u1294\u1273\u12CD",
|
|
60
|
+
"\u1260\u1206\u1290",
|
|
61
|
+
"\u1260\u1206\u1291",
|
|
62
|
+
"\u1260\u120B\u12ED",
|
|
63
|
+
"\u1260\u120C\u120B",
|
|
64
|
+
"\u1260\u120C\u120E\u127D",
|
|
65
|
+
"\u1260\u1219\u1209",
|
|
66
|
+
"\u1260\u1219\u1209\u121D",
|
|
67
|
+
"\u1260\u121A\u120D",
|
|
68
|
+
"\u1260\u121A\u127D\u1209",
|
|
69
|
+
"\u1260\u121A\u1308\u1263",
|
|
70
|
+
"\u1260\u121B\u1240\u12F5",
|
|
71
|
+
"\u1260\u121B\u1293\u1278\u12CD\u121D",
|
|
72
|
+
"\u1260\u122D\u12AB\u1273",
|
|
73
|
+
"\u1260\u1230\u121E\u1291",
|
|
74
|
+
"\u1260\u1235\u1270\u1240\u122D",
|
|
75
|
+
"\u1260\u1240\u122D",
|
|
76
|
+
"\u1260\u1270\u1208\u12ED",
|
|
77
|
+
"\u1260\u1270\u1208\u12ED\u121D",
|
|
78
|
+
"\u1260\u1270\u1218\u1208\u12A8\u1270",
|
|
79
|
+
"\u1260\u1270\u1218\u1233\u1233\u12ED",
|
|
80
|
+
"\u1260\u1273\u127D",
|
|
81
|
+
"\u1260\u128B\u120B",
|
|
82
|
+
"\u1260\u1290\u1231",
|
|
83
|
+
"\u1260\u1290\u12DA\u1201",
|
|
84
|
+
"\u1260\u1290\u12DA\u1205",
|
|
85
|
+
"\u1260\u12A5\u1290\u12DA\u1201",
|
|
86
|
+
"\u1260\u12A5\u1295\u12F0\u12DA\u1205",
|
|
87
|
+
"\u1260\u12A9\u120D",
|
|
88
|
+
"\u1260\u12CB\u1293",
|
|
89
|
+
"\u1260\u12CD\u1235\u1325",
|
|
90
|
+
"\u1260\u12DA\u1205",
|
|
91
|
+
"\u1260\u12DA\u1205\u121D",
|
|
92
|
+
"\u1260\u12DA\u1205\u1293",
|
|
93
|
+
"\u1262\u1206\u1295",
|
|
94
|
+
"\u1262\u1206\u1295\u121D",
|
|
95
|
+
"\u1262\u12EB\u1295\u1235",
|
|
96
|
+
"\u1263\u1209",
|
|
97
|
+
"\u1263\u1323\u121D",
|
|
98
|
+
"\u1265\u1208\u12CB\u120D",
|
|
99
|
+
"\u1265\u120E",
|
|
100
|
+
"\u1265\u127B",
|
|
101
|
+
"\u1265\u12D9",
|
|
102
|
+
"\u1266\u1273",
|
|
103
|
+
"\u1270\u1263\u1208",
|
|
104
|
+
"\u1270\u1265\u120E",
|
|
105
|
+
"\u1270\u12A8\u1293\u12C8\u1290",
|
|
106
|
+
"\u1270\u1308\u1208\u1338",
|
|
107
|
+
"\u1270\u1308\u120D\u133F\u120D",
|
|
108
|
+
"\u1270\u1328\u121B\u122A",
|
|
109
|
+
"\u1275\u1293\u1295\u1275",
|
|
110
|
+
"\u127D\u130D\u122D",
|
|
111
|
+
"\u128B\u120B",
|
|
112
|
+
"\u1290\u1260\u1228\u127D",
|
|
113
|
+
"\u1290\u1260\u1229",
|
|
114
|
+
"\u1290\u1260\u122D",
|
|
115
|
+
"\u1290\u12CD",
|
|
116
|
+
"\u1290\u1308\u122D",
|
|
117
|
+
"\u1290\u1308\u122E\u127D",
|
|
118
|
+
"\u1293",
|
|
119
|
+
"\u1293\u1275",
|
|
120
|
+
"\u1293\u1278\u12CD",
|
|
121
|
+
"\u12A0\u1201\u1295",
|
|
122
|
+
"\u12A0\u1208",
|
|
123
|
+
"\u12A0\u1209",
|
|
124
|
+
"\u12A0\u1233\u1230\u1260",
|
|
125
|
+
"\u12A0\u1233\u1235\u1260\u12CB\u120D",
|
|
126
|
+
"\u12A0\u1235\u1228\u12F5\u1270\u12CB\u120D",
|
|
127
|
+
"\u12A0\u1235\u1273\u12CD\u1230\u12CB\u120D",
|
|
128
|
+
"\u12A0\u1235\u1273\u12CD\u1240\u12CB\u120D",
|
|
129
|
+
"\u12A0\u1235\u1308\u1290\u12D8\u1261",
|
|
130
|
+
"\u12A0\u1235\u1308\u1295\u12DD\u1260\u12CB\u120D",
|
|
131
|
+
"\u12A0\u1235\u1348\u120B\u130A",
|
|
132
|
+
"\u12A0\u1265\u122B\u122D\u1270\u12CB\u120D",
|
|
133
|
+
"\u12A0\u1295\u1270",
|
|
134
|
+
"\u12A0\u1295\u127A",
|
|
135
|
+
"\u12A0\u1295\u12F0\u1206\u1290",
|
|
136
|
+
"\u12A0\u1295\u12F0\u129B",
|
|
137
|
+
"\u12A0\u1295\u12F1",
|
|
138
|
+
"\u12A0\u1295\u12F1\u1295",
|
|
139
|
+
"\u12A0\u1295\u12F2\u1275",
|
|
140
|
+
"\u12A0\u1295\u12F3\u1295\u12F5",
|
|
141
|
+
"\u12A0\u1295\u133B\u122D",
|
|
142
|
+
"\u12A5\u1235\u12A8",
|
|
143
|
+
"\u12A5\u1235\u12AA\u12F0\u122D\u1235",
|
|
144
|
+
"\u12A5\u1235\u12AB\u1201\u1295",
|
|
145
|
+
"\u12A5\u1263\u12AD\u1205",
|
|
146
|
+
"\u12A5\u1263\u12AD\u123D",
|
|
147
|
+
"\u12A5\u1290\u12DA\u1205",
|
|
148
|
+
"\u12A5\u1290\u12DA\u1205\u121D",
|
|
149
|
+
"\u12A5\u1290\u12DA\u1205\u1291",
|
|
150
|
+
"\u12A5\u1290\u12DA\u1205\u1295",
|
|
151
|
+
"\u12A5\u1290\u12F0\u1206\u1290",
|
|
152
|
+
"\u12A5\u1293\u1295\u1270",
|
|
153
|
+
"\u12A5\u1295\u12B3",
|
|
154
|
+
"\u12A5\u1295\u12B3\u1295",
|
|
155
|
+
"\u12A5\u1295\u12F0",
|
|
156
|
+
"\u12A5\u1295\u12F0\u1206\u1290\u1293",
|
|
157
|
+
"\u12A5\u1295\u12F0\u1270\u1293\u1308\u1229\u1275",
|
|
158
|
+
"\u12A5\u1295\u12F0\u1290\u12DA\u1205",
|
|
159
|
+
"\u12A5\u1295\u12F0\u1308\u1208\u1339\u1275",
|
|
160
|
+
"\u12A5\u1295\u12F0\u1308\u1293",
|
|
161
|
+
"\u12A5\u1295\u12F2\u1201\u121D",
|
|
162
|
+
"\u12A5\u1295\u12F2\u1205",
|
|
163
|
+
"\u12A5\u1295\u12F2\u1206\u1291",
|
|
164
|
+
"\u12A5\u1295\u12F2\u1206\u1295",
|
|
165
|
+
"\u12A5\u1295\u12F3\u1235\u1228\u12F1\u1275",
|
|
166
|
+
"\u12A5\u1295\u1302",
|
|
167
|
+
"\u12A5\u12DA\u1201",
|
|
168
|
+
"\u12A5\u1305\u130D",
|
|
169
|
+
"\u12A8\u1201\u1208\u1275",
|
|
170
|
+
"\u12A8\u1206\u1290",
|
|
171
|
+
"\u12A8\u1206\u1290\u12CD",
|
|
172
|
+
"\u12A8\u120C\u120B",
|
|
173
|
+
"\u12A8\u120C\u120E\u127D",
|
|
174
|
+
"\u12A8\u1290\u12DA\u1201",
|
|
175
|
+
"\u12A8\u12A0\u1235\u122D",
|
|
176
|
+
"\u12A8\u12A0\u1295\u12F3\u1295\u12F5",
|
|
177
|
+
"\u12A8\u12A0\u1295\u12F5",
|
|
178
|
+
"\u12A8\u12A5\u1290\u12DA\u1201",
|
|
179
|
+
"\u12A8\u12A5\u1290\u12DA\u1205",
|
|
180
|
+
"\u12A8\u12DA\u1205",
|
|
181
|
+
"\u12A8\u12DA\u1205\u121D",
|
|
182
|
+
"\u12A8\u12DA\u12EB",
|
|
183
|
+
"\u12AB\u120D\u1206\u1290",
|
|
184
|
+
"\u12C8\u122D",
|
|
185
|
+
"\u12C8\u1245\u1275",
|
|
186
|
+
"\u12C8\u12ED",
|
|
187
|
+
"\u12C8\u12ED\u121D",
|
|
188
|
+
"\u12C8\u12F0",
|
|
189
|
+
"\u12CD\u1235\u1325",
|
|
190
|
+
"\u12E8\u1206\u1290",
|
|
191
|
+
"\u12E8\u1206\u1290\u127D\u1295",
|
|
192
|
+
"\u12E8\u1206\u1290\u12CD",
|
|
193
|
+
"\u12E8\u1206\u1291\u1275",
|
|
194
|
+
"\u12E8\u1208\u12CD\u121D",
|
|
195
|
+
"\u12E8\u120C\u120B",
|
|
196
|
+
"\u12E8\u120C\u120B\u1278\u12CD\u1295",
|
|
197
|
+
"\u12E8\u120C\u120B\u12CD\u1295",
|
|
198
|
+
"\u12E8\u121A\u1206\u1291\u1275",
|
|
199
|
+
"\u12E8\u121A\u127D\u1208\u12CD\u1295",
|
|
200
|
+
"\u12E8\u121A\u1308\u129D",
|
|
201
|
+
"\u12E8\u121B\u1293\u1278\u12CD\u121D",
|
|
202
|
+
"\u12E8\u121B\u12EB\u1295\u1235",
|
|
203
|
+
"\u12E8\u121B\u12ED\u1260\u120D\u1325",
|
|
204
|
+
"\u12E8\u1270\u1208\u12EB\u12E8",
|
|
205
|
+
"\u12E8\u1270\u1208\u12EB\u12E9",
|
|
206
|
+
"\u12E8\u1290\u1260\u1228\u12CD\u1295",
|
|
207
|
+
"\u12E8\u1290\u1308\u1229",
|
|
208
|
+
"\u12E8\u1293\u1295\u1270",
|
|
209
|
+
"\u12E8\u12A0\u1295\u1240\u1339",
|
|
210
|
+
"\u12E8\u12DA\u1201",
|
|
211
|
+
"\u12E8\u12DA\u1205",
|
|
212
|
+
"\u12EB\u1208",
|
|
213
|
+
"\u12EB\u1209",
|
|
214
|
+
"\u12EB\u120B\u1278\u12CD",
|
|
215
|
+
"\u12EB\u120B\u1278\u12CD\u1295",
|
|
216
|
+
"\u12EB\u120D\u1206\u1290",
|
|
217
|
+
"\u12EB\u1295\u1270",
|
|
218
|
+
"\u12EB\u1295\u127A",
|
|
219
|
+
"\u12ED\u1205",
|
|
220
|
+
"\u12ED\u1205\u121D",
|
|
221
|
+
"\u12ED\u1205\u127D\u12CD",
|
|
222
|
+
"\u12ED\u1205\u1295",
|
|
223
|
+
"\u12ED\u1205\u1295\u1291",
|
|
224
|
+
"\u12ED\u1205\u1295\u1295\u121D",
|
|
225
|
+
"\u12ED\u1206\u1291\u1260\u1273\u120D",
|
|
226
|
+
"\u12ED\u1206\u1293\u1209",
|
|
227
|
+
"\u12ED\u12B8\u12CD",
|
|
228
|
+
"\u130A\u12DC\u1293",
|
|
229
|
+
"\u130B\u122D",
|
|
230
|
+
"\u130D\u1295"
|
|
231
|
+
]);
|
|
232
|
+
var amharic = {
|
|
233
|
+
name: "amharic",
|
|
234
|
+
revision: "1",
|
|
235
|
+
stemmer: null,
|
|
236
|
+
stopWords,
|
|
237
|
+
tokenizer: { splitPattern: /[^\u1200-\u135f\u1369-\u137ca-z0-9]+/gi }
|
|
238
|
+
};
|
|
239
|
+
|
|
240
|
+
export { amharic };
|