@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
|
@@ -0,0 +1,67 @@
|
|
|
1
|
+
// src/languages/malagasy.ts
|
|
2
|
+
var stopWords = /* @__PURE__ */ new Set([
|
|
3
|
+
"aho",
|
|
4
|
+
"ahy",
|
|
5
|
+
"amin",
|
|
6
|
+
"anao",
|
|
7
|
+
"anay",
|
|
8
|
+
"antsika",
|
|
9
|
+
"any",
|
|
10
|
+
"ao",
|
|
11
|
+
"ary",
|
|
12
|
+
"avokoa",
|
|
13
|
+
"avy",
|
|
14
|
+
"azy",
|
|
15
|
+
"daholo",
|
|
16
|
+
"dia",
|
|
17
|
+
"efa",
|
|
18
|
+
"eto",
|
|
19
|
+
"fa",
|
|
20
|
+
"foana",
|
|
21
|
+
"ho",
|
|
22
|
+
"hoe",
|
|
23
|
+
"ianao",
|
|
24
|
+
"ianareo",
|
|
25
|
+
"ihany",
|
|
26
|
+
"ilay",
|
|
27
|
+
"indrindra",
|
|
28
|
+
"iny",
|
|
29
|
+
"io",
|
|
30
|
+
"ireo",
|
|
31
|
+
"isaky",
|
|
32
|
+
"isika",
|
|
33
|
+
"ity",
|
|
34
|
+
"izahay",
|
|
35
|
+
"izany",
|
|
36
|
+
"izao",
|
|
37
|
+
"izay",
|
|
38
|
+
"izy",
|
|
39
|
+
"ka",
|
|
40
|
+
"koa",
|
|
41
|
+
"mba",
|
|
42
|
+
"mbola",
|
|
43
|
+
"misy",
|
|
44
|
+
"na",
|
|
45
|
+
"no",
|
|
46
|
+
"noho",
|
|
47
|
+
"ny",
|
|
48
|
+
"raha",
|
|
49
|
+
"rehefa",
|
|
50
|
+
"samy",
|
|
51
|
+
"satria",
|
|
52
|
+
"sy",
|
|
53
|
+
"tahaka",
|
|
54
|
+
"tamin",
|
|
55
|
+
"toy",
|
|
56
|
+
"tsy",
|
|
57
|
+
"vao"
|
|
58
|
+
]);
|
|
59
|
+
var malagasy = {
|
|
60
|
+
name: "malagasy",
|
|
61
|
+
revision: "1",
|
|
62
|
+
stemmer: null,
|
|
63
|
+
stopWords,
|
|
64
|
+
tokenizer: { splitPattern: /[^\p{Script=Latin}0-9]+/giu }
|
|
65
|
+
};
|
|
66
|
+
|
|
67
|
+
export { malagasy };
|
|
@@ -0,0 +1,482 @@
|
|
|
1
|
+
// src/languages/malay.ts
|
|
2
|
+
var stopWords = /* @__PURE__ */ new Set([
|
|
3
|
+
"abdul",
|
|
4
|
+
"abdullah",
|
|
5
|
+
"acara",
|
|
6
|
+
"ada",
|
|
7
|
+
"adalah",
|
|
8
|
+
"ahmad",
|
|
9
|
+
"air",
|
|
10
|
+
"akan",
|
|
11
|
+
"akhbar",
|
|
12
|
+
"akhir",
|
|
13
|
+
"aktiviti",
|
|
14
|
+
"alam",
|
|
15
|
+
"amat",
|
|
16
|
+
"amerika",
|
|
17
|
+
"anak",
|
|
18
|
+
"anggota",
|
|
19
|
+
"antara",
|
|
20
|
+
"antarabangsa",
|
|
21
|
+
"apa",
|
|
22
|
+
"apabila",
|
|
23
|
+
"april",
|
|
24
|
+
"as",
|
|
25
|
+
"asas",
|
|
26
|
+
"asean",
|
|
27
|
+
"asia",
|
|
28
|
+
"asing",
|
|
29
|
+
"atas",
|
|
30
|
+
"atau",
|
|
31
|
+
"australia",
|
|
32
|
+
"awal",
|
|
33
|
+
"awam",
|
|
34
|
+
"bagaimanapun",
|
|
35
|
+
"bagi",
|
|
36
|
+
"bahagian",
|
|
37
|
+
"bahan",
|
|
38
|
+
"baharu",
|
|
39
|
+
"bahawa",
|
|
40
|
+
"baik",
|
|
41
|
+
"bandar",
|
|
42
|
+
"bank",
|
|
43
|
+
"banyak",
|
|
44
|
+
"barangan",
|
|
45
|
+
"baru",
|
|
46
|
+
"bawah",
|
|
47
|
+
"beberapa",
|
|
48
|
+
"bekas",
|
|
49
|
+
"beliau",
|
|
50
|
+
"belum",
|
|
51
|
+
"berada",
|
|
52
|
+
"berakhir",
|
|
53
|
+
"berbanding",
|
|
54
|
+
"berdasarkan",
|
|
55
|
+
"berharap",
|
|
56
|
+
"berikutan",
|
|
57
|
+
"berjaya",
|
|
58
|
+
"berjumlah",
|
|
59
|
+
"berkaitan",
|
|
60
|
+
"berkata",
|
|
61
|
+
"berkenaan",
|
|
62
|
+
"berlaku",
|
|
63
|
+
"bermula",
|
|
64
|
+
"bernama",
|
|
65
|
+
"bernilai",
|
|
66
|
+
"bersama",
|
|
67
|
+
"berubah",
|
|
68
|
+
"besar",
|
|
69
|
+
"bhd",
|
|
70
|
+
"bidang",
|
|
71
|
+
"bilion",
|
|
72
|
+
"bn",
|
|
73
|
+
"boleh",
|
|
74
|
+
"bukan",
|
|
75
|
+
"bulan",
|
|
76
|
+
"bursa",
|
|
77
|
+
"cadangan",
|
|
78
|
+
"china",
|
|
79
|
+
"dagangan",
|
|
80
|
+
"dalam",
|
|
81
|
+
"dan",
|
|
82
|
+
"dana",
|
|
83
|
+
"dapat",
|
|
84
|
+
"dari",
|
|
85
|
+
"daripada",
|
|
86
|
+
"dasar",
|
|
87
|
+
"datang",
|
|
88
|
+
"datuk",
|
|
89
|
+
"demikian",
|
|
90
|
+
"dengan",
|
|
91
|
+
"depan",
|
|
92
|
+
"derivatives",
|
|
93
|
+
"dewan",
|
|
94
|
+
"di",
|
|
95
|
+
"diadakan",
|
|
96
|
+
"dibuka",
|
|
97
|
+
"dicatatkan",
|
|
98
|
+
"dijangka",
|
|
99
|
+
"diniagakan",
|
|
100
|
+
"dis",
|
|
101
|
+
"disember",
|
|
102
|
+
"ditutup",
|
|
103
|
+
"dolar",
|
|
104
|
+
"dr",
|
|
105
|
+
"dua",
|
|
106
|
+
"dunia",
|
|
107
|
+
"ekonomi",
|
|
108
|
+
"eksekutif",
|
|
109
|
+
"eksport",
|
|
110
|
+
"empat",
|
|
111
|
+
"enam",
|
|
112
|
+
"faedah",
|
|
113
|
+
"feb",
|
|
114
|
+
"global",
|
|
115
|
+
"hadapan",
|
|
116
|
+
"hanya",
|
|
117
|
+
"harga",
|
|
118
|
+
"hari",
|
|
119
|
+
"hasil",
|
|
120
|
+
"hingga",
|
|
121
|
+
"hubungan",
|
|
122
|
+
"ia",
|
|
123
|
+
"iaitu",
|
|
124
|
+
"ialah",
|
|
125
|
+
"indeks",
|
|
126
|
+
"india",
|
|
127
|
+
"indonesia",
|
|
128
|
+
"industri",
|
|
129
|
+
"ini",
|
|
130
|
+
"islam",
|
|
131
|
+
"isnin",
|
|
132
|
+
"isu",
|
|
133
|
+
"itu",
|
|
134
|
+
"jabatan",
|
|
135
|
+
"jalan",
|
|
136
|
+
"jan",
|
|
137
|
+
"jawatan",
|
|
138
|
+
"jawatankuasa",
|
|
139
|
+
"jepun",
|
|
140
|
+
"jika",
|
|
141
|
+
"jualan",
|
|
142
|
+
"juga",
|
|
143
|
+
"julai",
|
|
144
|
+
"jumaat",
|
|
145
|
+
"jumlah",
|
|
146
|
+
"jun",
|
|
147
|
+
"juta",
|
|
148
|
+
"kadar",
|
|
149
|
+
"kalangan",
|
|
150
|
+
"kali",
|
|
151
|
+
"kami",
|
|
152
|
+
"kata",
|
|
153
|
+
"katanya",
|
|
154
|
+
"kaunter",
|
|
155
|
+
"kawasan",
|
|
156
|
+
"ke",
|
|
157
|
+
"keadaan",
|
|
158
|
+
"kecil",
|
|
159
|
+
"kedua",
|
|
160
|
+
"kedudukan",
|
|
161
|
+
"kekal",
|
|
162
|
+
"kementerian",
|
|
163
|
+
"kemudahan",
|
|
164
|
+
"kenaikan",
|
|
165
|
+
"kenyataan",
|
|
166
|
+
"kepada",
|
|
167
|
+
"kepentingan",
|
|
168
|
+
"keputusan",
|
|
169
|
+
"kerajaan",
|
|
170
|
+
"kerana",
|
|
171
|
+
"kereta",
|
|
172
|
+
"kerja",
|
|
173
|
+
"kerjasama",
|
|
174
|
+
"kes",
|
|
175
|
+
"keselamatan",
|
|
176
|
+
"keseluruhan",
|
|
177
|
+
"kesihatan",
|
|
178
|
+
"ketika",
|
|
179
|
+
"ketua",
|
|
180
|
+
"keuntungan",
|
|
181
|
+
"kewangan",
|
|
182
|
+
"khamis",
|
|
183
|
+
"kini",
|
|
184
|
+
"kita",
|
|
185
|
+
"klci",
|
|
186
|
+
"klibor",
|
|
187
|
+
"komposit",
|
|
188
|
+
"kontrak",
|
|
189
|
+
"kos",
|
|
190
|
+
"kuala",
|
|
191
|
+
"kuasa",
|
|
192
|
+
"kukuh",
|
|
193
|
+
"kumpulan",
|
|
194
|
+
"lagi",
|
|
195
|
+
"lain",
|
|
196
|
+
"langkah",
|
|
197
|
+
"laporan",
|
|
198
|
+
"lebih",
|
|
199
|
+
"lepas",
|
|
200
|
+
"lima",
|
|
201
|
+
"lot",
|
|
202
|
+
"luar",
|
|
203
|
+
"lumpur",
|
|
204
|
+
"mac",
|
|
205
|
+
"mahkamah",
|
|
206
|
+
"mahu",
|
|
207
|
+
"majlis",
|
|
208
|
+
"makanan",
|
|
209
|
+
"maklumat",
|
|
210
|
+
"malam",
|
|
211
|
+
"malaysia",
|
|
212
|
+
"mana",
|
|
213
|
+
"manakala",
|
|
214
|
+
"masa",
|
|
215
|
+
"masalah",
|
|
216
|
+
"masih",
|
|
217
|
+
"masyarakat",
|
|
218
|
+
"mata",
|
|
219
|
+
"media",
|
|
220
|
+
"mei",
|
|
221
|
+
"melalui",
|
|
222
|
+
"melihat",
|
|
223
|
+
"memandangkan",
|
|
224
|
+
"memastikan",
|
|
225
|
+
"membantu",
|
|
226
|
+
"membawa",
|
|
227
|
+
"memberi",
|
|
228
|
+
"memberikan",
|
|
229
|
+
"membolehkan",
|
|
230
|
+
"membuat",
|
|
231
|
+
"mempunyai",
|
|
232
|
+
"menambah",
|
|
233
|
+
"menarik",
|
|
234
|
+
"menawarkan",
|
|
235
|
+
"mencapai",
|
|
236
|
+
"mencatatkan",
|
|
237
|
+
"mendapat",
|
|
238
|
+
"mendapatkan",
|
|
239
|
+
"menerima",
|
|
240
|
+
"menerusi",
|
|
241
|
+
"mengadakan",
|
|
242
|
+
"mengambil",
|
|
243
|
+
"mengenai",
|
|
244
|
+
"menggalakkan",
|
|
245
|
+
"menggunakan",
|
|
246
|
+
"mengikut",
|
|
247
|
+
"mengumumkan",
|
|
248
|
+
"mengurangkan",
|
|
249
|
+
"meningkat",
|
|
250
|
+
"meningkatkan",
|
|
251
|
+
"menjadi",
|
|
252
|
+
"menjelang",
|
|
253
|
+
"menokok",
|
|
254
|
+
"menteri",
|
|
255
|
+
"menunjukkan",
|
|
256
|
+
"menurut",
|
|
257
|
+
"menyaksikan",
|
|
258
|
+
"menyediakan",
|
|
259
|
+
"mereka",
|
|
260
|
+
"merosot",
|
|
261
|
+
"merupakan",
|
|
262
|
+
"mesyuarat",
|
|
263
|
+
"minat",
|
|
264
|
+
"minggu",
|
|
265
|
+
"minyak",
|
|
266
|
+
"modal",
|
|
267
|
+
"mohd",
|
|
268
|
+
"mudah",
|
|
269
|
+
"mungkin",
|
|
270
|
+
"naik",
|
|
271
|
+
"najib",
|
|
272
|
+
"nasional",
|
|
273
|
+
"negara",
|
|
274
|
+
"negeri",
|
|
275
|
+
"niaga",
|
|
276
|
+
"nilai",
|
|
277
|
+
"nov",
|
|
278
|
+
"ogos",
|
|
279
|
+
"okt",
|
|
280
|
+
"oleh",
|
|
281
|
+
"operasi",
|
|
282
|
+
"orang",
|
|
283
|
+
"pada",
|
|
284
|
+
"pagi",
|
|
285
|
+
"paling",
|
|
286
|
+
"pameran",
|
|
287
|
+
"papan",
|
|
288
|
+
"para",
|
|
289
|
+
"paras",
|
|
290
|
+
"parlimen",
|
|
291
|
+
"parti",
|
|
292
|
+
"pasaran",
|
|
293
|
+
"pasukan",
|
|
294
|
+
"pegawai",
|
|
295
|
+
"pejabat",
|
|
296
|
+
"pekerja",
|
|
297
|
+
"pelabur",
|
|
298
|
+
"pelaburan",
|
|
299
|
+
"pelancongan",
|
|
300
|
+
"pelanggan",
|
|
301
|
+
"pelbagai",
|
|
302
|
+
"peluang",
|
|
303
|
+
"pembangunan",
|
|
304
|
+
"pemberita",
|
|
305
|
+
"pembinaan",
|
|
306
|
+
"pemimpin",
|
|
307
|
+
"pendapatan",
|
|
308
|
+
"pendidikan",
|
|
309
|
+
"penduduk",
|
|
310
|
+
"penerbangan",
|
|
311
|
+
"pengarah",
|
|
312
|
+
"pengeluaran",
|
|
313
|
+
"pengerusi",
|
|
314
|
+
"pengguna",
|
|
315
|
+
"pengurusan",
|
|
316
|
+
"peniaga",
|
|
317
|
+
"peningkatan",
|
|
318
|
+
"penting",
|
|
319
|
+
"peratus",
|
|
320
|
+
"perdagangan",
|
|
321
|
+
"perdana",
|
|
322
|
+
"peringkat",
|
|
323
|
+
"perjanjian",
|
|
324
|
+
"perkara",
|
|
325
|
+
"perkhidmatan",
|
|
326
|
+
"perladangan",
|
|
327
|
+
"perlu",
|
|
328
|
+
"permintaan",
|
|
329
|
+
"perniagaan",
|
|
330
|
+
"persekutuan",
|
|
331
|
+
"persidangan",
|
|
332
|
+
"pertama",
|
|
333
|
+
"pertubuhan",
|
|
334
|
+
"pertumbuhan",
|
|
335
|
+
"perusahaan",
|
|
336
|
+
"peserta",
|
|
337
|
+
"petang",
|
|
338
|
+
"pihak",
|
|
339
|
+
"pilihan",
|
|
340
|
+
"pinjaman",
|
|
341
|
+
"polis",
|
|
342
|
+
"politik",
|
|
343
|
+
"presiden",
|
|
344
|
+
"prestasi",
|
|
345
|
+
"produk",
|
|
346
|
+
"program",
|
|
347
|
+
"projek",
|
|
348
|
+
"proses",
|
|
349
|
+
"proton",
|
|
350
|
+
"pukul",
|
|
351
|
+
"pula",
|
|
352
|
+
"pusat",
|
|
353
|
+
"rabu",
|
|
354
|
+
"rakan",
|
|
355
|
+
"rakyat",
|
|
356
|
+
"ramai",
|
|
357
|
+
"rantau",
|
|
358
|
+
"raya",
|
|
359
|
+
"rendah",
|
|
360
|
+
"ringgit",
|
|
361
|
+
"rumah",
|
|
362
|
+
"sabah",
|
|
363
|
+
"sahaja",
|
|
364
|
+
"saham",
|
|
365
|
+
"sama",
|
|
366
|
+
"sarawak",
|
|
367
|
+
"satu",
|
|
368
|
+
"sawit",
|
|
369
|
+
"saya",
|
|
370
|
+
"sdn",
|
|
371
|
+
"sebagai",
|
|
372
|
+
"sebahagian",
|
|
373
|
+
"sebanyak",
|
|
374
|
+
"sebarang",
|
|
375
|
+
"sebelum",
|
|
376
|
+
"sebelumnya",
|
|
377
|
+
"sebuah",
|
|
378
|
+
"secara",
|
|
379
|
+
"sedang",
|
|
380
|
+
"segi",
|
|
381
|
+
"sehingga",
|
|
382
|
+
"sejak",
|
|
383
|
+
"sekarang",
|
|
384
|
+
"sektor",
|
|
385
|
+
"sekuriti",
|
|
386
|
+
"selain",
|
|
387
|
+
"selama",
|
|
388
|
+
"selasa",
|
|
389
|
+
"selatan",
|
|
390
|
+
"selepas",
|
|
391
|
+
"seluruh",
|
|
392
|
+
"semakin",
|
|
393
|
+
"semalam",
|
|
394
|
+
"semasa",
|
|
395
|
+
"sementara",
|
|
396
|
+
"semua",
|
|
397
|
+
"semula",
|
|
398
|
+
"sen",
|
|
399
|
+
"sendiri",
|
|
400
|
+
"seorang",
|
|
401
|
+
"sepanjang",
|
|
402
|
+
"seperti",
|
|
403
|
+
"sept",
|
|
404
|
+
"september",
|
|
405
|
+
"serantau",
|
|
406
|
+
"seri",
|
|
407
|
+
"serta",
|
|
408
|
+
"sesi",
|
|
409
|
+
"setiap",
|
|
410
|
+
"setiausaha",
|
|
411
|
+
"sidang",
|
|
412
|
+
"singapura",
|
|
413
|
+
"sini",
|
|
414
|
+
"sistem",
|
|
415
|
+
"sokongan",
|
|
416
|
+
"sri",
|
|
417
|
+
"sudah",
|
|
418
|
+
"sukan",
|
|
419
|
+
"suku",
|
|
420
|
+
"sumber",
|
|
421
|
+
"supaya",
|
|
422
|
+
"susut",
|
|
423
|
+
"syarikat",
|
|
424
|
+
"syed",
|
|
425
|
+
"tahap",
|
|
426
|
+
"tahun",
|
|
427
|
+
"tan",
|
|
428
|
+
"tanah",
|
|
429
|
+
"tanpa",
|
|
430
|
+
"tawaran",
|
|
431
|
+
"teknologi",
|
|
432
|
+
"telah",
|
|
433
|
+
"tempat",
|
|
434
|
+
"tempatan",
|
|
435
|
+
"tempoh",
|
|
436
|
+
"tenaga",
|
|
437
|
+
"tengah",
|
|
438
|
+
"tentang",
|
|
439
|
+
"terbaik",
|
|
440
|
+
"terbang",
|
|
441
|
+
"terbesar",
|
|
442
|
+
"terbuka",
|
|
443
|
+
"terdapat",
|
|
444
|
+
"terhadap",
|
|
445
|
+
"termasuk",
|
|
446
|
+
"tersebut",
|
|
447
|
+
"terus",
|
|
448
|
+
"tetapi",
|
|
449
|
+
"thailand",
|
|
450
|
+
"tiada",
|
|
451
|
+
"tidak",
|
|
452
|
+
"tiga",
|
|
453
|
+
"timbalan",
|
|
454
|
+
"timur",
|
|
455
|
+
"tindakan",
|
|
456
|
+
"tinggi",
|
|
457
|
+
"tun",
|
|
458
|
+
"tunai",
|
|
459
|
+
"turun",
|
|
460
|
+
"turut",
|
|
461
|
+
"umno",
|
|
462
|
+
"unit",
|
|
463
|
+
"untuk",
|
|
464
|
+
"untung",
|
|
465
|
+
"urus",
|
|
466
|
+
"usaha",
|
|
467
|
+
"utama",
|
|
468
|
+
"walaupun",
|
|
469
|
+
"wang",
|
|
470
|
+
"wanita",
|
|
471
|
+
"wilayah",
|
|
472
|
+
"yang"
|
|
473
|
+
]);
|
|
474
|
+
var malay = {
|
|
475
|
+
name: "malay",
|
|
476
|
+
revision: "1",
|
|
477
|
+
stemmer: null,
|
|
478
|
+
stopWords,
|
|
479
|
+
tokenizer: { splitPattern: /[^a-z0-9]+/gi }
|
|
480
|
+
};
|
|
481
|
+
|
|
482
|
+
export { malay };
|
|
@@ -0,0 +1,122 @@
|
|
|
1
|
+
import { withNormalisedSpellings } from '../chunk-GHJWC2E5.mjs';
|
|
2
|
+
|
|
3
|
+
// src/languages/malayalam.ts
|
|
4
|
+
var stopWords = /* @__PURE__ */ new Set([
|
|
5
|
+
"\u0D05\u0D19\u0D4D\u0D19\u0D28\u0D46",
|
|
6
|
+
"\u0D05\u0D24\u0D3F\u0D28\u0D3E\u0D7D",
|
|
7
|
+
"\u0D05\u0D24\u0D3F\u0D28\u0D4D",
|
|
8
|
+
"\u0D05\u0D24\u0D3F\u0D28\u0D4D\u0D31\u0D46",
|
|
9
|
+
"\u0D05\u0D24\u0D3F\u0D7D",
|
|
10
|
+
"\u0D05\u0D24\u0D41\u0D02",
|
|
11
|
+
"\u0D05\u0D24\u0D41\u0D15\u0D4A\u0D23\u0D4D\u0D1F\u0D4D",
|
|
12
|
+
"\u0D05\u0D24\u0D4D",
|
|
13
|
+
"\u0D05\u0D28\u0D4D\u0D28\u0D47\u0D30\u0D02",
|
|
14
|
+
"\u0D05\u0D28\u0D4D\u0D28\u0D4D",
|
|
15
|
+
"\u0D05\u0D2A\u0D4D\u0D2A\u0D4B\u0D7E",
|
|
16
|
+
"\u0D05\u0D32\u0D4D\u0D32",
|
|
17
|
+
"\u0D05\u0D32\u0D4D\u0D32\u0D46\u0D19\u0D4D\u0D15\u0D3F\u0D7D",
|
|
18
|
+
"\u0D05\u0D35\u0D7B",
|
|
19
|
+
"\u0D05\u0D35\u0D28\u0D4D\u0D31\u0D46",
|
|
20
|
+
"\u0D05\u0D35\u0D30\u0D41\u0D1F\u0D46",
|
|
21
|
+
"\u0D05\u0D35\u0D7C",
|
|
22
|
+
"\u0D05\u0D35\u0D33\u0D41\u0D1F\u0D46",
|
|
23
|
+
"\u0D05\u0D35\u0D7E",
|
|
24
|
+
"\u0D05\u0D35\u0D3F\u0D1F\u0D46",
|
|
25
|
+
"\u0D06",
|
|
26
|
+
"\u0D06\u0D15\u0D41\u0D02",
|
|
27
|
+
"\u0D06\u0D15\u0D41\u0D28\u0D4D\u0D28\u0D41",
|
|
28
|
+
"\u0D06\u0D23\u0D4D",
|
|
29
|
+
"\u0D06\u0D2F",
|
|
30
|
+
"\u0D06\u0D2F\u0D3F",
|
|
31
|
+
"\u0D06\u0D2F\u0D3F\u0D30\u0D41\u0D28\u0D4D\u0D28\u0D41",
|
|
32
|
+
"\u0D06\u0D30\u0D4D",
|
|
33
|
+
"\u0D07\u0D19\u0D4D\u0D19\u0D28\u0D46",
|
|
34
|
+
"\u0D07\u0D24\u0D3F\u0D28\u0D4D",
|
|
35
|
+
"\u0D07\u0D24\u0D3F\u0D28\u0D4D\u0D31\u0D46",
|
|
36
|
+
"\u0D07\u0D24\u0D3F\u0D7D",
|
|
37
|
+
"\u0D07\u0D24\u0D41\u0D02",
|
|
38
|
+
"\u0D07\u0D24\u0D4D",
|
|
39
|
+
"\u0D07\u0D28\u0D3F",
|
|
40
|
+
"\u0D07\u0D28\u0D4D\u0D28\u0D4D",
|
|
41
|
+
"\u0D07\u0D2A\u0D4D\u0D2A\u0D4B\u0D7E",
|
|
42
|
+
"\u0D07\u0D32\u0D4D\u0D32",
|
|
43
|
+
"\u0D07\u0D35\u0D7C",
|
|
44
|
+
"\u0D07\u0D35\u0D3F\u0D1F\u0D46",
|
|
45
|
+
"\u0D08",
|
|
46
|
+
"\u0D09\u0D23\u0D4D\u0D1F\u0D4D",
|
|
47
|
+
"\u0D09\u0D33\u0D4D\u0D33",
|
|
48
|
+
"\u0D0E\u0D19\u0D4D\u0D15\u0D3F\u0D32\u0D41\u0D02",
|
|
49
|
+
"\u0D0E\u0D19\u0D4D\u0D15\u0D3F\u0D7D",
|
|
50
|
+
"\u0D0E\u0D19\u0D4D\u0D19\u0D28\u0D46",
|
|
51
|
+
"\u0D0E\u0D28\u0D4D\u0D24\u0D4D",
|
|
52
|
+
"\u0D0E\u0D28\u0D4D\u0D28",
|
|
53
|
+
"\u0D0E\u0D28\u0D4D\u0D28\u0D3E\u0D7D",
|
|
54
|
+
"\u0D0E\u0D28\u0D4D\u0D28\u0D3F\u0D35",
|
|
55
|
+
"\u0D0E\u0D28\u0D4D\u0D28\u0D41",
|
|
56
|
+
"\u0D0E\u0D28\u0D4D\u0D28\u0D41\u0D02",
|
|
57
|
+
"\u0D0E\u0D28\u0D4D\u0D28\u0D4D",
|
|
58
|
+
"\u0D0E\u0D28\u0D4D\u0D31\u0D46",
|
|
59
|
+
"\u0D0E\u0D2A\u0D4D\u0D2A\u0D4B\u0D7E",
|
|
60
|
+
"\u0D0E\u0D32\u0D4D\u0D32\u0D3E",
|
|
61
|
+
"\u0D0E\u0D35\u0D3F\u0D1F\u0D46",
|
|
62
|
+
"\u0D0F\u0D24\u0D4D",
|
|
63
|
+
"\u0D0F\u0D31\u0D4D\u0D31\u0D35\u0D41\u0D02",
|
|
64
|
+
"\u0D12\u0D2A\u0D4D\u0D2A\u0D02",
|
|
65
|
+
"\u0D12\u0D30\u0D41",
|
|
66
|
+
"\u0D13\u0D30\u0D4B",
|
|
67
|
+
"\u0D15\u0D34\u0D3F\u0D2F\u0D41\u0D02",
|
|
68
|
+
"\u0D15\u0D42\u0D1F\u0D3E\u0D24\u0D46",
|
|
69
|
+
"\u0D15\u0D42\u0D1F\u0D3F",
|
|
70
|
+
"\u0D15\u0D42\u0D1F\u0D46",
|
|
71
|
+
"\u0D1A\u0D3F\u0D32",
|
|
72
|
+
"\u0D1E\u0D19\u0D4D\u0D19\u0D7E",
|
|
73
|
+
"\u0D1E\u0D3E\u0D7B",
|
|
74
|
+
"\u0D24\u0D28\u0D4D\u0D28\u0D46",
|
|
75
|
+
"\u0D24\u0D28\u0D4D\u0D31\u0D46",
|
|
76
|
+
"\u0D24\u0D3E\u0D7B",
|
|
77
|
+
"\u0D28\u0D2E\u0D4D\u0D2E\u0D41\u0D1F\u0D46",
|
|
78
|
+
"\u0D28\u0D3E\u0D02",
|
|
79
|
+
"\u0D28\u0D3F\u0D19\u0D4D\u0D19\u0D7E",
|
|
80
|
+
"\u0D28\u0D3F\u0D28\u0D4D\u0D31\u0D46",
|
|
81
|
+
"\u0D28\u0D40",
|
|
82
|
+
"\u0D2A\u0D15\u0D4D\u0D37\u0D47",
|
|
83
|
+
"\u0D2A\u0D32",
|
|
84
|
+
"\u0D2A\u0D3F\u0D28\u0D4D\u0D28\u0D46",
|
|
85
|
+
"\u0D2A\u0D4B\u0D32\u0D41\u0D02",
|
|
86
|
+
"\u0D2A\u0D4B\u0D32\u0D46",
|
|
87
|
+
"\u0D2E\u0D31\u0D4D\u0D31\u0D41",
|
|
88
|
+
"\u0D2E\u0D31\u0D4D\u0D31\u0D4D",
|
|
89
|
+
"\u0D2E\u0D3E\u0D24\u0D4D\u0D30\u0D02",
|
|
90
|
+
"\u0D2E\u0D41\u0D24\u0D7D",
|
|
91
|
+
"\u0D35\u0D30\u0D46",
|
|
92
|
+
"\u0D35\u0D33\u0D30\u0D46",
|
|
93
|
+
"\u0D35\u0D47\u0D23\u0D02",
|
|
94
|
+
"\u0D35\u0D47\u0D23\u0D4D\u0D1F\u0D3F",
|
|
95
|
+
"\u0D36\u0D47\u0D37\u0D02"
|
|
96
|
+
]);
|
|
97
|
+
var CHILLU_BY_BASE = /* @__PURE__ */ new Map([
|
|
98
|
+
["\u0D23", "\u0D7A"],
|
|
99
|
+
["\u0D28", "\u0D7B"],
|
|
100
|
+
["\u0D30", "\u0D7C"],
|
|
101
|
+
["\u0D32", "\u0D7D"],
|
|
102
|
+
["\u0D33", "\u0D7E"],
|
|
103
|
+
["\u0D15", "\u0D7F"]
|
|
104
|
+
]);
|
|
105
|
+
var JOINED_CHILLU = /([\u0D23\u0D28\u0D30\u0D32\u0D33\u0D15])\u0D4D\u200D/g;
|
|
106
|
+
var ZERO_WIDTH_JOINERS = /[\u200c\u200d]/g;
|
|
107
|
+
function foldChillu(_match, base) {
|
|
108
|
+
return CHILLU_BY_BASE.get(base) ?? base;
|
|
109
|
+
}
|
|
110
|
+
function normalize(token) {
|
|
111
|
+
return token.replace(JOINED_CHILLU, foldChillu).replace(ZERO_WIDTH_JOINERS, "");
|
|
112
|
+
}
|
|
113
|
+
var malayalam = {
|
|
114
|
+
name: "malayalam",
|
|
115
|
+
revision: "1",
|
|
116
|
+
stemmer: null,
|
|
117
|
+
stopWords: withNormalisedSpellings(stopWords, normalize),
|
|
118
|
+
normalizer: normalize,
|
|
119
|
+
tokenizer: { splitPattern: /[^\u0d00-\u0d7f\u200c\u200da-z0-9]+/gi }
|
|
120
|
+
};
|
|
121
|
+
|
|
122
|
+
export { malayalam };
|