@delali/narsil 0.1.14 → 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 -972
- 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 +12 -3
- package/dist/server.mjs +183 -64
- 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/languages/ewe.d.ts
CHANGED
package/dist/languages/ewe.mjs
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
1
|
+
import { withNormalisedSpellings } from '../chunk-GHJWC2E5.mjs';
|
|
2
|
+
|
|
1
3
|
// src/languages/ewe.ts
|
|
2
4
|
var stopWords = /* @__PURE__ */ new Set([
|
|
3
5
|
"nye",
|
|
@@ -71,12 +73,19 @@ var stopWords = /* @__PURE__ */ new Set([
|
|
|
71
73
|
"tsoa",
|
|
72
74
|
"hena"
|
|
73
75
|
]);
|
|
76
|
+
var ICELANDIC_ETH = /\u00F0/g;
|
|
77
|
+
var EWE_D = "\u0256";
|
|
78
|
+
function normalize(token) {
|
|
79
|
+
return token.replace(ICELANDIC_ETH, EWE_D);
|
|
80
|
+
}
|
|
74
81
|
var ewe = {
|
|
75
82
|
name: "ewe",
|
|
83
|
+
revision: "1",
|
|
76
84
|
stemmer: null,
|
|
77
|
-
stopWords,
|
|
85
|
+
stopWords: withNormalisedSpellings(stopWords, normalize),
|
|
86
|
+
normalizer: normalize,
|
|
78
87
|
tokenizer: {
|
|
79
|
-
splitPattern: /[^a-zA-
|
|
88
|
+
splitPattern: /[^a-zA-ZàáèéêìíòóùúãẽĩũɛɔɖƉðÐŋƐƆŊɣƔƒƑʋƲÀÁÈÉÊÌÍÒÓÙÚÃẼĨŨ0-9\p{M}]+/giu,
|
|
80
89
|
normalizeDiacritics: false,
|
|
81
90
|
minTokenLength: 1
|
|
82
91
|
}
|
|
@@ -0,0 +1,93 @@
|
|
|
1
|
+
// src/languages/faroese.ts
|
|
2
|
+
var stopWords = /* @__PURE__ */ new Set([
|
|
3
|
+
"\xE1",
|
|
4
|
+
"at",
|
|
5
|
+
"av",
|
|
6
|
+
"bara",
|
|
7
|
+
"eftir",
|
|
8
|
+
"eg",
|
|
9
|
+
"eisini",
|
|
10
|
+
"ella",
|
|
11
|
+
"er",
|
|
12
|
+
"fr\xE1",
|
|
13
|
+
"fyri",
|
|
14
|
+
"hann",
|
|
15
|
+
"hansara",
|
|
16
|
+
"har",
|
|
17
|
+
"hatta",
|
|
18
|
+
"hava",
|
|
19
|
+
"henda",
|
|
20
|
+
"hennara",
|
|
21
|
+
"henni",
|
|
22
|
+
"her",
|
|
23
|
+
"hesin",
|
|
24
|
+
"hetta",
|
|
25
|
+
"hevur",
|
|
26
|
+
"hon",
|
|
27
|
+
"honum",
|
|
28
|
+
"h\xF8vdu",
|
|
29
|
+
"hvar",
|
|
30
|
+
"hvat",
|
|
31
|
+
"hv\xED",
|
|
32
|
+
"hv\xF8r",
|
|
33
|
+
"hvussu",
|
|
34
|
+
"\xED",
|
|
35
|
+
"i\xF0",
|
|
36
|
+
"ikki",
|
|
37
|
+
"kann",
|
|
38
|
+
"kunnu",
|
|
39
|
+
"m\xE1",
|
|
40
|
+
"m\xE6r",
|
|
41
|
+
"meg",
|
|
42
|
+
"men",
|
|
43
|
+
"millum",
|
|
44
|
+
"m\xEDn",
|
|
45
|
+
"m\xEDni",
|
|
46
|
+
"m\xF3ti",
|
|
47
|
+
"n\xE6r",
|
|
48
|
+
"n\xFA",
|
|
49
|
+
"og",
|
|
50
|
+
"okkara",
|
|
51
|
+
"okkum",
|
|
52
|
+
"s\xE6r",
|
|
53
|
+
"seg",
|
|
54
|
+
"skal",
|
|
55
|
+
"skulu",
|
|
56
|
+
"so",
|
|
57
|
+
"sum",
|
|
58
|
+
"t\xE1",
|
|
59
|
+
"ta\xF0",
|
|
60
|
+
"t\xE6r",
|
|
61
|
+
"teg",
|
|
62
|
+
"teimum",
|
|
63
|
+
"teir",
|
|
64
|
+
"teirra",
|
|
65
|
+
"tey",
|
|
66
|
+
"t\xED",
|
|
67
|
+
"til",
|
|
68
|
+
"t\xEDn",
|
|
69
|
+
"tit",
|
|
70
|
+
"t\xFA",
|
|
71
|
+
"tykkara",
|
|
72
|
+
"tykkum",
|
|
73
|
+
"um",
|
|
74
|
+
"undir",
|
|
75
|
+
"uttan",
|
|
76
|
+
"var",
|
|
77
|
+
"vera",
|
|
78
|
+
"ver\xF0ur",
|
|
79
|
+
"vi\xF0",
|
|
80
|
+
"vil",
|
|
81
|
+
"vilja",
|
|
82
|
+
"vit",
|
|
83
|
+
"yvir"
|
|
84
|
+
]);
|
|
85
|
+
var faroese = {
|
|
86
|
+
name: "faroese",
|
|
87
|
+
revision: "1",
|
|
88
|
+
stemmer: null,
|
|
89
|
+
stopWords,
|
|
90
|
+
tokenizer: { splitPattern: /[^a-z0-9áðíóúýæø]+/gi }
|
|
91
|
+
};
|
|
92
|
+
|
|
93
|
+
export { faroese };
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
// src/languages/fijian.ts
|
|
2
|
+
var stopWords = /* @__PURE__ */ new Set([
|
|
3
|
+
"au",
|
|
4
|
+
"baleta",
|
|
5
|
+
"dua",
|
|
6
|
+
"e",
|
|
7
|
+
"ena",
|
|
8
|
+
"era",
|
|
9
|
+
"ga",
|
|
10
|
+
"ia",
|
|
11
|
+
"iko",
|
|
12
|
+
"ira",
|
|
13
|
+
"ka",
|
|
14
|
+
"ke",
|
|
15
|
+
"kece",
|
|
16
|
+
"kecega",
|
|
17
|
+
"keda",
|
|
18
|
+
"kei",
|
|
19
|
+
"keimami",
|
|
20
|
+
"kemuni",
|
|
21
|
+
"kena",
|
|
22
|
+
"ki",
|
|
23
|
+
"koya",
|
|
24
|
+
"mai",
|
|
25
|
+
"me",
|
|
26
|
+
"na",
|
|
27
|
+
"ni",
|
|
28
|
+
"nodra",
|
|
29
|
+
"nomu",
|
|
30
|
+
"nona",
|
|
31
|
+
"noqu",
|
|
32
|
+
"o",
|
|
33
|
+
"oqo",
|
|
34
|
+
"oya",
|
|
35
|
+
"rawa",
|
|
36
|
+
"sa",
|
|
37
|
+
"sara",
|
|
38
|
+
"se",
|
|
39
|
+
"sega",
|
|
40
|
+
"so",
|
|
41
|
+
"talega",
|
|
42
|
+
"tiko",
|
|
43
|
+
"tu",
|
|
44
|
+
"vei",
|
|
45
|
+
"yani"
|
|
46
|
+
]);
|
|
47
|
+
var fijian = {
|
|
48
|
+
name: "fijian",
|
|
49
|
+
revision: "1",
|
|
50
|
+
stemmer: null,
|
|
51
|
+
stopWords,
|
|
52
|
+
tokenizer: { splitPattern: /[^a-z0-9]+/gi }
|
|
53
|
+
};
|
|
54
|
+
|
|
55
|
+
export { fijian };
|