Spaces:
Running on Zero
Running on Zero
Daryl Lim Claude Sonnet 4.6 commited on
Commit ·
09577a5
1
Parent(s): bfb1fb7
fix: add name spacing correction to generation script
Browse filesAdd fix_name_spacing() to scripts/generate_langmap.py that uses regex to
restore spaces lost during PDF word extraction (e.g. MandarinChinese →
Mandarin Chinese, Tonga(TongaIslands) → Tonga (Tonga Islands)). Apply it
in parse_table9() after extracting each language name, then regenerate
langmap/langid_mapping.py — all 418 names now have correct spacing.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- langmap/langid_mapping.py +88 -88
- scripts/generate_langmap.py +18 -0
langmap/langid_mapping.py
CHANGED
|
@@ -14,9 +14,9 @@ langid_to_language = {
|
|
| 14 |
"<2am>": {"name": "Amharic", "region": "Africa"},
|
| 15 |
"<2bm>": {"name": "Bambara", "region": "Africa"},
|
| 16 |
"<2bci>": {"name": "Baoulé", "region": "Africa"},
|
| 17 |
-
"<2bas>": {"name": "Basa(Cameroon)", "region": "Africa"},
|
| 18 |
"<2bim>": {"name": "Bimoba", "region": "Africa"},
|
| 19 |
-
"<2bqc>": {"name": "Boko(Benin)", "region": "Africa"},
|
| 20 |
"<2bus>": {"name": "Bokobaru", "region": "Africa"},
|
| 21 |
"<2bum>": {"name": "Bulu", "region": "Africa"},
|
| 22 |
"<2ny>": {"name": "Chichewa", "region": "Africa"},
|
|
@@ -42,15 +42,15 @@ langid_to_language = {
|
|
| 42 |
"<2kbp>": {"name": "Kabiyè", "region": "Africa"},
|
| 43 |
"<2kmb>": {"name": "Kimbundu", "region": "Africa"},
|
| 44 |
"<2rw>": {"name": "Kinyarwanda", "region": "Africa"},
|
| 45 |
-
"<2ktu>": {"name": "Kituba(DRC)", "region": "Africa"},
|
| 46 |
"<2kg>": {"name": "Kongo", "region": "Africa"},
|
| 47 |
"<2kri>": {"name": "Krio", "region": "Africa"},
|
| 48 |
"<2kj>": {"name": "Kuanyama", "region": "Africa"},
|
| 49 |
-
"<2laj>": {"name": "Lango(Uganda)", "region": "Africa"},
|
| 50 |
"<2ln>": {"name": "Lingala", "region": "Africa"},
|
| 51 |
"<2lu>": {"name": "Luba-Katanga", "region": "Africa"},
|
| 52 |
"<2lg>": {"name": "Luganda", "region": "Africa"},
|
| 53 |
-
"<2ffm>": {"name": "
|
| 54 |
"<2mgh>": {"name": "Makhuwa-Meetto", "region": "Africa"},
|
| 55 |
"<2mg>": {"name": "Malagasy", "region": "Africa"},
|
| 56 |
"<2mas>": {"name": "Masai", "region": "Africa"},
|
|
@@ -69,13 +69,13 @@ langid_to_language = {
|
|
| 69 |
"<2st>": {"name": "Sesotho", "region": "Africa"},
|
| 70 |
"<2sn>": {"name": "Shona", "region": "Africa"},
|
| 71 |
"<2so>": {"name": "Somali", "region": "Africa"},
|
| 72 |
-
"<2nr>": {"name": "
|
| 73 |
-
"<2spp>": {"name": "
|
| 74 |
"<2sus>": {"name": "Susu", "region": "Africa"},
|
| 75 |
"<2sw>": {"name": "Swahili", "region": "Africa"},
|
| 76 |
"<2ss>": {"name": "Swati", "region": "Africa"},
|
| 77 |
-
"<2ber>": {"name": "Tamazight(Tfng)", "region": "Africa"},
|
| 78 |
-
"<2tdx>": {"name": "Tandroy-
|
| 79 |
"<2teo>": {"name": "Teso", "region": "Africa"},
|
| 80 |
"<2tll>": {"name": "Tetela", "region": "Africa"},
|
| 81 |
"<2ti>": {"name": "Tigrinya", "region": "Africa"},
|
|
@@ -95,44 +95,44 @@ langid_to_language = {
|
|
| 95 |
"<2agr>": {"name": "Aguaruna", "region": "Americas"},
|
| 96 |
"<2cni>": {"name": "Asháninka", "region": "Americas"},
|
| 97 |
"<2kwi>": {"name": "Awa-Cuaiquer", "region": "Americas"},
|
| 98 |
-
"<2quy>": {"name": "
|
| 99 |
"<2ay>": {"name": "Aymara", "region": "Americas"},
|
| 100 |
-
"<2bzj>": {"name": "
|
| 101 |
-
"<2qvc>": {"name": "
|
| 102 |
-
"<2qxr>": {"name": "
|
| 103 |
-
"<2maz>": {"name": "
|
| 104 |
"<2chr>": {"name": "Cherokee", "region": "Americas"},
|
| 105 |
"<2ctu>": {"name": "Chol", "region": "Americas"},
|
| 106 |
"<2cac>": {"name": "Chuj", "region": "Americas"},
|
| 107 |
-
"<2gui>": {"name": "E.
|
| 108 |
-
"<2nhe>": {"name": "E.
|
| 109 |
-
"<2djk>": {"name": "E.
|
| 110 |
"<2sja>": {"name": "Epena", "region": "Americas"},
|
| 111 |
"<2cab>": {"name": "Garifuna", "region": "Americas"},
|
| 112 |
"<2guh>": {"name": "Guahibo", "region": "Americas"},
|
| 113 |
"<2gn>": {"name": "Guarani", "region": "Americas"},
|
| 114 |
-
"<2amu>": {"name": "
|
| 115 |
-
"<2ngu>": {"name": "
|
| 116 |
-
"<2gyn>": {"name": "
|
| 117 |
-
"<2ht>": {"name": "
|
| 118 |
"<2haw>": {"name": "Hawaiian", "region": "Americas"},
|
| 119 |
-
"<2qub>": {"name": "
|
| 120 |
"<2hus>": {"name": "Huastec", "region": "Americas"},
|
| 121 |
-
"<2qvi>": {"name": "
|
| 122 |
"<2inb>": {"name": "Inga", "region": "Americas"},
|
| 123 |
"<2iu>": {"name": "Inuktitut", "region": "Americas"},
|
| 124 |
-
"<2jam>": {"name": "
|
| 125 |
"<2kl>": {"name": "Kalaallisut", "region": "Americas"},
|
| 126 |
"<2cak>": {"name": "Kaqchikel", "region": "Americas"},
|
| 127 |
"<2kek>": {"name": "Kekchí", "region": "Americas"},
|
| 128 |
"<2tlh>": {"name": "Klingon", "region": "Americas"},
|
| 129 |
"<2quc>": {"name": "K’iche’", "region": "Americas"},
|
| 130 |
-
"<2quf>": {"name": "
|
| 131 |
"<2mam>": {"name": "Mam", "region": "Americas"},
|
| 132 |
"<2arn>": {"name": "Mapudungun", "region": "Americas"},
|
| 133 |
"<2miq>": {"name": "Mískito", "region": "Americas"},
|
| 134 |
-
"<2emp>": {"name": "N.Emberá", "region": "Americas"},
|
| 135 |
-
"<2qvz>": {"name": "N.
|
| 136 |
"<2nv>": {"name": "Navajo", "region": "Americas"},
|
| 137 |
"<2gym>": {"name": "Ngäbere", "region": "Americas"},
|
| 138 |
"<2zxx>": {"name": "Noise", "region": "Americas"},
|
|
@@ -140,30 +140,30 @@ langid_to_language = {
|
|
| 140 |
"<2pap>": {"name": "Papiamento", "region": "Americas"},
|
| 141 |
"<2jac>": {"name": "Popti’", "region": "Americas"},
|
| 142 |
"<2qu>": {"name": "Quechua", "region": "Americas"},
|
| 143 |
-
"<2otq>": {"name": "
|
| 144 |
-
"<2rcf>": {"name": "
|
| 145 |
-
"<2quh>": {"name": "S.
|
| 146 |
-
"<2qup>": {"name": "S.
|
| 147 |
-
"<2cuk>": {"name": "
|
| 148 |
"<2srm>": {"name": "Saramaccan", "region": "Americas"},
|
| 149 |
-
"<2crs>": {"name": "
|
| 150 |
"<2shp>": {"name": "Shipibo-Conibo", "region": "Americas"},
|
| 151 |
"<2jiv>": {"name": "Shuar", "region": "Americas"},
|
| 152 |
-
"<2srn>": {"name": "
|
| 153 |
-
"<2acf>": {"name": "
|
| 154 |
"<2tca>": {"name": "Ticuna", "region": "Americas"},
|
| 155 |
"<2toj>": {"name": "Tojolabal", "region": "Americas"},
|
| 156 |
"<2tzh>": {"name": "Tzeltal", "region": "Americas"},
|
| 157 |
"<2tzo>": {"name": "Tzotzil", "region": "Americas"},
|
| 158 |
"<2tzj>": {"name": "Tz’utujil", "region": "Americas"},
|
| 159 |
-
"<2knj>": {"name": "W.Kanjobal", "region": "Americas"},
|
| 160 |
"<2guc>": {"name": "Wayuu", "region": "Americas"},
|
| 161 |
-
"<2noa>": {"name": "
|
| 162 |
"<2yua>": {"name": "Yucateco", "region": "Americas"},
|
| 163 |
"<2zap>": {"name": "Zapotec", "region": "Americas"},
|
| 164 |
"<2az>": {"name": "Azerbaijani", "region": "Central Asia"},
|
| 165 |
"<2ba>": {"name": "Bashkir", "region": "Central Asia"},
|
| 166 |
-
"<2kaa-Latn>": {"name": "Kara-Kalpak(Latn)", "region": "Central Asia"},
|
| 167 |
"<2kk>": {"name": "Kazakh", "region": "Central Asia"},
|
| 168 |
"<2ky>": {"name": "Kyrghyz", "region": "Central Asia"},
|
| 169 |
"<2tg>": {"name": "Tajik", "region": "Central Asia"},
|
|
@@ -173,14 +173,14 @@ langid_to_language = {
|
|
| 173 |
"<2dz>": {"name": "Dzongkha", "region": "East Asia"},
|
| 174 |
"<2ja>": {"name": "Japanese", "region": "East Asia"},
|
| 175 |
"<2ko>": {"name": "Korean", "region": "East Asia"},
|
| 176 |
-
"<2zh>": {"name": "
|
| 177 |
"<2mn>": {"name": "Mongolian", "region": "East Asia"},
|
| 178 |
"<2bo>": {"name": "Tibetan", "region": "East Asia"},
|
| 179 |
"<2sah>": {"name": "Yakut", "region": "East Asia"},
|
| 180 |
"<2za>": {"name": "Zhuang", "region": "East Asia"},
|
| 181 |
"<2ady>": {"name": "Adyghe", "region": "Europe"},
|
| 182 |
"<2sq>": {"name": "Albanian", "region": "Europe"},
|
| 183 |
-
"<2grc>": {"name": "
|
| 184 |
"<2hy>": {"name": "Armenian", "region": "Europe"},
|
| 185 |
"<2frp>": {"name": "Arpitan", "region": "Europe"},
|
| 186 |
"<2av>": {"name": "Avar", "region": "Europe"},
|
|
@@ -190,13 +190,13 @@ langid_to_language = {
|
|
| 190 |
"<2br>": {"name": "Breton", "region": "Europe"},
|
| 191 |
"<2bg>": {"name": "Bulgarian", "region": "Europe"},
|
| 192 |
"<2bua>": {"name": "Buryat", "region": "Europe"},
|
| 193 |
-
"<2rmc>": {"name": "
|
| 194 |
"<2ca>": {"name": "Catalan", "region": "Europe"},
|
| 195 |
"<2ce>": {"name": "Chechen", "region": "Europe"},
|
| 196 |
"<2cv>": {"name": "Chuvash", "region": "Europe"},
|
| 197 |
"<2kw>": {"name": "Cornish", "region": "Europe"},
|
| 198 |
"<2co>": {"name": "Corsican", "region": "Europe"},
|
| 199 |
-
"<2crh>": {"name": "
|
| 200 |
"<2hr>": {"name": "Croatian", "region": "Europe"},
|
| 201 |
"<2cs>": {"name": "Czech", "region": "Europe"},
|
| 202 |
"<2da>": {"name": "Danish", "region": "Europe"},
|
|
@@ -213,7 +213,7 @@ langid_to_language = {
|
|
| 213 |
"<2ka>": {"name": "Georgian", "region": "Europe"},
|
| 214 |
"<2de>": {"name": "German", "region": "Europe"},
|
| 215 |
"<2el>": {"name": "Greek", "region": "Europe"},
|
| 216 |
-
"<2mrj>": {"name": "
|
| 217 |
"<2hu>": {"name": "Hungarian", "region": "Europe"},
|
| 218 |
"<2is>": {"name": "Icelandic", "region": "Europe"},
|
| 219 |
"<2ga>": {"name": "Irish", "region": "Europe"},
|
|
@@ -234,13 +234,13 @@ langid_to_language = {
|
|
| 234 |
"<2mk>": {"name": "Macedonian", "region": "Europe"},
|
| 235 |
"<2mt>": {"name": "Maltese", "region": "Europe"},
|
| 236 |
"<2gv>": {"name": "Manx", "region": "Europe"},
|
| 237 |
-
"<2chm>": {"name": "
|
| 238 |
"<2mdf>": {"name": "Moksha", "region": "Europe"},
|
| 239 |
-
"<2se>": {"name": "N.Sami", "region": "Europe"},
|
| 240 |
"<2nog>": {"name": "Nogai", "region": "Europe"},
|
| 241 |
"<2no>": {"name": "Norwegian", "region": "Europe"},
|
| 242 |
"<2oc>": {"name": "Occitan", "region": "Europe"},
|
| 243 |
-
"<2ang>": {"name": "
|
| 244 |
"<2os>": {"name": "Ossetian", "region": "Europe"},
|
| 245 |
"<2pl>": {"name": "Polish", "region": "Europe"},
|
| 246 |
"<2pt>": {"name": "Portuguese", "region": "Europe"},
|
|
@@ -248,35 +248,35 @@ langid_to_language = {
|
|
| 248 |
"<2ro>": {"name": "Romanian", "region": "Europe"},
|
| 249 |
"<2rm>": {"name": "Romansh", "region": "Europe"},
|
| 250 |
"<2ru>": {"name": "Russian", "region": "Europe"},
|
| 251 |
-
"<2alt>": {"name": "S.Altai", "region": "Europe"},
|
| 252 |
"<2stq>": {"name": "Saterfriesisch", "region": "Europe"},
|
| 253 |
-
"<2gd>": {"name": "
|
| 254 |
"<2sr>": {"name": "Serbian", "region": "Europe"},
|
| 255 |
"<2sk>": {"name": "Slovak", "region": "Europe"},
|
| 256 |
"<2sl>": {"name": "Slovenian", "region": "Europe"},
|
| 257 |
"<2es>": {"name": "Spanish", "region": "Europe"},
|
| 258 |
"<2sv>": {"name": "Swedish", "region": "Europe"},
|
| 259 |
-
"<2gsw>": {"name": "
|
| 260 |
"<2tab>": {"name": "Tabassaran", "region": "Europe"},
|
| 261 |
"<2tt>": {"name": "Tatar", "region": "Europe"},
|
| 262 |
"<2tyv>": {"name": "Tuvinian", "region": "Europe"},
|
| 263 |
"<2udm>": {"name": "Udmurt", "region": "Europe"},
|
| 264 |
"<2uk>": {"name": "Ukrainian", "region": "Europe"},
|
| 265 |
"<2vec>": {"name": "Venetian", "region": "Europe"},
|
| 266 |
-
"<2fy>": {"name": "W.Frisian", "region": "Europe"},
|
| 267 |
"<2wa>": {"name": "Walloon", "region": "Europe"},
|
| 268 |
"<2cy>": {"name": "Welsh", "region": "Europe"},
|
| 269 |
"<2ar>": {"name": "Arabic", "region": "Middle East & North Africa"},
|
| 270 |
-
"<2bgp>": {"name": "E.Baluchi", "region": "Middle East & North Africa"},
|
| 271 |
"<2mey>": {"name": "Hassaniyya", "region": "Middle East & North Africa"},
|
| 272 |
"<2he>": {"name": "Hebrew", "region": "Middle East & North Africa"},
|
| 273 |
"<2ks>": {"name": "Kashmiri", "region": "Middle East & North Africa"},
|
| 274 |
-
"<2ku>": {"name": "Kurdish(Kurmanji)", "region": "Middle East & North Africa"},
|
| 275 |
-
"<2ckb>": {"name": "Kurdish(Sorani)", "region": "Middle East & North Africa"},
|
| 276 |
-
"<2lrc>": {"name": "N.Luri", "region": "Middle East & North Africa"},
|
| 277 |
"<2ps>": {"name": "Pashto", "region": "Middle East & North Africa"},
|
| 278 |
"<2fa>": {"name": "Persian", "region": "Middle East & North Africa"},
|
| 279 |
-
"<2luz>": {"name": "S.Luri", "region": "Middle East & North Africa"},
|
| 280 |
"<2skr>": {"name": "Saraiki", "region": "Middle East & North Africa"},
|
| 281 |
"<2sd>": {"name": "Sindhi", "region": "Middle East & North Africa"},
|
| 282 |
"<2syr>": {"name": "Syriac", "region": "Middle East & North Africa"},
|
|
@@ -293,10 +293,10 @@ langid_to_language = {
|
|
| 293 |
"<2chk>": {"name": "Chuukese", "region": "Oceania"},
|
| 294 |
"<2mps>": {"name": "Dadibi", "region": "Oceania"},
|
| 295 |
"<2enq>": {"name": "Enga", "region": "Oceania"},
|
| 296 |
-
"<2hif>": {"name": "
|
| 297 |
"<2fj>": {"name": "Fijian", "region": "Oceania"},
|
| 298 |
"<2gil>": {"name": "Gilbertese", "region": "Oceania"},
|
| 299 |
-
"<2ho>": {"name": "
|
| 300 |
"<2hui>": {"name": "Huli", "region": "Oceania"},
|
| 301 |
"<2kos>": {"name": "Kosraean", "region": "Oceania"},
|
| 302 |
"<2ksd>": {"name": "Kuanua", "region": "Oceania"},
|
|
@@ -311,7 +311,7 @@ langid_to_language = {
|
|
| 311 |
"<2hvn>": {"name": "Sabu", "region": "Oceania"},
|
| 312 |
"<2sm>": {"name": "Samoan", "region": "Oceania"},
|
| 313 |
"<2twu>": {"name": "Termanu", "region": "Oceania"},
|
| 314 |
-
"<2to>": {"name": "Tonga(
|
| 315 |
"<2tvl>": {"name": "Tuvalu", "region": "Oceania"},
|
| 316 |
"<2ubu>": {"name": "Umbu-Ungu", "region": "Oceania"},
|
| 317 |
"<2yap>": {"name": "Yapese", "region": "Oceania"},
|
|
@@ -319,29 +319,29 @@ langid_to_language = {
|
|
| 319 |
"<2awa>": {"name": "Awadhi", "region": "South Asia"},
|
| 320 |
"<2bn>": {"name": "Bengali", "region": "South Asia"},
|
| 321 |
"<2bho>": {"name": "Bhojpuri", "region": "South Asia"},
|
| 322 |
-
"<2brx>": {"name": "Bodo(India)", "region": "South Asia"},
|
| 323 |
"<2hne>": {"name": "Chhattisgarhi", "region": "South Asia"},
|
| 324 |
"<2dv>": {"name": "Dhivehi", "region": "South Asia"},
|
| 325 |
-
"<2taj>": {"name": "E.Tamang", "region": "South Asia"},
|
| 326 |
"<2gbm>": {"name": "Garhwali", "region": "South Asia"},
|
| 327 |
-
"<2gom>": {"name": "
|
| 328 |
"<2gu>": {"name": "Gujarati", "region": "South Asia"},
|
| 329 |
"<2hi>": {"name": "Hindi", "region": "South Asia"},
|
| 330 |
"<2bjj>": {"name": "Kanauji", "region": "South Asia"},
|
| 331 |
"<2kn>": {"name": "Kannada", "region": "South Asia"},
|
| 332 |
"<2kha>": {"name": "Khasi", "region": "South Asia"},
|
| 333 |
-
"<2trp>": {"name": "
|
| 334 |
"<2mag>": {"name": "Magahi", "region": "South Asia"},
|
| 335 |
"<2mai>": {"name": "Maithili", "region": "South Asia"},
|
| 336 |
"<2ml>": {"name": "Malayalam", "region": "South Asia"},
|
| 337 |
"<2mr>": {"name": "Marathi", "region": "South Asia"},
|
| 338 |
-
"<2mni>": {"name": "Meiteilon(Manipuri)", "region": "South Asia"},
|
| 339 |
"<2mtr>": {"name": "Mewari", "region": "South Asia"},
|
| 340 |
"<2lus>": {"name": "Mizo", "region": "South Asia"},
|
| 341 |
"<2ne>": {"name": "Nepali", "region": "South Asia"},
|
| 342 |
"<2new>": {"name": "Newari", "region": "South Asia"},
|
| 343 |
"<2noe>": {"name": "Nimadi", "region": "South Asia"},
|
| 344 |
-
"<2or>": {"name": "Odia(Oriya)", "region": "South Asia"},
|
| 345 |
"<2pa>": {"name": "Punjabi", "region": "South Asia"},
|
| 346 |
"<2raj>": {"name": "Rajasthani", "region": "South Asia"},
|
| 347 |
"<2sa>": {"name": "Sanskrit", "region": "South Asia"},
|
|
@@ -354,67 +354,67 @@ langid_to_language = {
|
|
| 354 |
"<2te>": {"name": "Telugu", "region": "South Asia"},
|
| 355 |
"<2tcy>": {"name": "Tulu", "region": "South Asia"},
|
| 356 |
"<2ace>": {"name": "Achinese", "region": "Southeast Asia"},
|
| 357 |
-
"<2msm>": {"name": "
|
| 358 |
"<2ahk>": {"name": "Akha", "region": "Southeast Asia"},
|
| 359 |
"<2ban>": {"name": "Balinese", "region": "Southeast Asia"},
|
| 360 |
"<2bgz>": {"name": "Banggai", "region": "Southeast Asia"},
|
| 361 |
-
"<2akb>": {"name": "
|
| 362 |
-
"<2btx>": {"name": "
|
| 363 |
-
"<2bts>": {"name": "
|
| 364 |
-
"<2bbc>": {"name": "
|
| 365 |
"<2bew>": {"name": "Betawi", "region": "Southeast Asia"},
|
| 366 |
-
"<2jvn>": {"name": "
|
| 367 |
"<2ceb>": {"name": "Cebuano", "region": "Southeast Asia"},
|
| 368 |
-
"<2bik>": {"name": "
|
| 369 |
-
"<2mel>": {"name": "
|
| 370 |
"<2cbk>": {"name": "Chavacano", "region": "Southeast Asia"},
|
| 371 |
-
"<2bru>": {"name": "E.Bru", "region": "Southeast Asia"},
|
| 372 |
-
"<2cfm>": {"name": "
|
| 373 |
"<2fil>": {"name": "Filipino", "region": "Southeast Asia"},
|
| 374 |
"<2gor>": {"name": "Gorontalo", "region": "Southeast Asia"},
|
| 375 |
-
"<2cnh>": {"name": "
|
| 376 |
"<2hil>": {"name": "Hiligaynon", "region": "Southeast Asia"},
|
| 377 |
"<2hmn>": {"name": "Hmong", "region": "Southeast Asia"},
|
| 378 |
"<2iba>": {"name": "Iban", "region": "Southeast Asia"},
|
| 379 |
"<2ilo>": {"name": "Ilocano", "region": "Southeast Asia"},
|
| 380 |
"<2id>": {"name": "Indonesian", "region": "Southeast Asia"},
|
| 381 |
-
"<2ium>": {"name": "
|
| 382 |
-
"<2jax>": {"name": "
|
| 383 |
"<2jv>": {"name": "Javanese", "region": "Southeast Asia"},
|
| 384 |
"<2kac>": {"name": "Kachin", "region": "Southeast Asia"},
|
| 385 |
-
"<2dtp>": {"name": "
|
| 386 |
-
"<2meo>": {"name": "
|
| 387 |
"<2ify>": {"name": "Keley-IKallahan", "region": "Southeast Asia"},
|
| 388 |
"<2km>": {"name": "Khmer", "region": "Southeast Asia"},
|
| 389 |
"<2kjg>": {"name": "Khmu", "region": "Southeast Asia"},
|
| 390 |
"<2krj>": {"name": "Kinaray-A", "region": "Southeast Asia"},
|
| 391 |
-
"<2mkn>": {"name": "
|
| 392 |
"<2lhu>": {"name": "Lahu", "region": "Southeast Asia"},
|
| 393 |
"<2lo>": {"name": "Lao", "region": "Southeast Asia"},
|
| 394 |
"<2mad>": {"name": "Madurese", "region": "Southeast Asia"},
|
| 395 |
"<2mak>": {"name": "Makasar", "region": "Southeast Asia"},
|
| 396 |
"<2ms>": {"name": "Malay", "region": "Southeast Asia"},
|
| 397 |
-
"<2xmm>": {"name": "
|
| 398 |
"<2mqy>": {"name": "Manggarai", "region": "Southeast Asia"},
|
| 399 |
"<2mrw>": {"name": "Maranao", "region": "Southeast Asia"},
|
| 400 |
"<2msb>": {"name": "Masbatenyo", "region": "Southeast Asia"},
|
| 401 |
-
"<2mbt>": {"name": "
|
| 402 |
"<2min>": {"name": "Minangkabau", "region": "Southeast Asia"},
|
| 403 |
"<2mnw>": {"name": "Mon", "region": "Southeast Asia"},
|
| 404 |
-
"<2my>": {"name": "Myanmar(Burmese)", "region": "Southeast Asia"},
|
| 405 |
"<2nij>": {"name": "Ngaju", "region": "Southeast Asia"},
|
| 406 |
"<2nia>": {"name": "Nias", "region": "Southeast Asia"},
|
| 407 |
-
"<2nut>": {"name": "Nung(
|
| 408 |
-
"<2pck>": {"name": "
|
| 409 |
"<2pam>": {"name": "Pampanga", "region": "Southeast Asia"},
|
| 410 |
"<2pag>": {"name": "Pangasinan", "region": "Southeast Asia"},
|
| 411 |
"<2prk>": {"name": "Parauk", "region": "Southeast Asia"},
|
| 412 |
"<2rki>": {"name": "Rakhine", "region": "Southeast Asia"},
|
| 413 |
-
"<2msi>": {"name": "
|
| 414 |
"<2sxn>": {"name": "Sangir", "region": "Southeast Asia"},
|
| 415 |
"<2shn>": {"name": "Shan", "region": "Southeast Asia"},
|
| 416 |
"<2su>": {"name": "Sundanese", "region": "Southeast Asia"},
|
| 417 |
-
"<2ksw>": {"name": "S’
|
| 418 |
"<2tsg>": {"name": "Tausug", "region": "Southeast Asia"},
|
| 419 |
"<2tet>": {"name": "Tetum", "region": "Southeast Asia"},
|
| 420 |
"<2th>": {"name": "Thai", "region": "Southeast Asia"},
|
|
@@ -422,5 +422,5 @@ langid_to_language = {
|
|
| 422 |
"<2tyz>": {"name": "Tày", "region": "Southeast Asia"},
|
| 423 |
"<2ppk>": {"name": "Uma", "region": "Southeast Asia"},
|
| 424 |
"<2vi>": {"name": "Vietnamese", "region": "Southeast Asia"},
|
| 425 |
-
"<2war>": {"name": "Waray(Philippines)", "region": "Southeast Asia"},
|
| 426 |
}
|
|
|
|
| 14 |
"<2am>": {"name": "Amharic", "region": "Africa"},
|
| 15 |
"<2bm>": {"name": "Bambara", "region": "Africa"},
|
| 16 |
"<2bci>": {"name": "Baoulé", "region": "Africa"},
|
| 17 |
+
"<2bas>": {"name": "Basa (Cameroon)", "region": "Africa"},
|
| 18 |
"<2bim>": {"name": "Bimoba", "region": "Africa"},
|
| 19 |
+
"<2bqc>": {"name": "Boko (Benin)", "region": "Africa"},
|
| 20 |
"<2bus>": {"name": "Bokobaru", "region": "Africa"},
|
| 21 |
"<2bum>": {"name": "Bulu", "region": "Africa"},
|
| 22 |
"<2ny>": {"name": "Chichewa", "region": "Africa"},
|
|
|
|
| 42 |
"<2kbp>": {"name": "Kabiyè", "region": "Africa"},
|
| 43 |
"<2kmb>": {"name": "Kimbundu", "region": "Africa"},
|
| 44 |
"<2rw>": {"name": "Kinyarwanda", "region": "Africa"},
|
| 45 |
+
"<2ktu>": {"name": "Kituba (DRC)", "region": "Africa"},
|
| 46 |
"<2kg>": {"name": "Kongo", "region": "Africa"},
|
| 47 |
"<2kri>": {"name": "Krio", "region": "Africa"},
|
| 48 |
"<2kj>": {"name": "Kuanyama", "region": "Africa"},
|
| 49 |
+
"<2laj>": {"name": "Lango (Uganda)", "region": "Africa"},
|
| 50 |
"<2ln>": {"name": "Lingala", "region": "Africa"},
|
| 51 |
"<2lu>": {"name": "Luba-Katanga", "region": "Africa"},
|
| 52 |
"<2lg>": {"name": "Luganda", "region": "Africa"},
|
| 53 |
+
"<2ffm>": {"name": "Maasina Fulfulde", "region": "Africa"},
|
| 54 |
"<2mgh>": {"name": "Makhuwa-Meetto", "region": "Africa"},
|
| 55 |
"<2mg>": {"name": "Malagasy", "region": "Africa"},
|
| 56 |
"<2mas>": {"name": "Masai", "region": "Africa"},
|
|
|
|
| 69 |
"<2st>": {"name": "Sesotho", "region": "Africa"},
|
| 70 |
"<2sn>": {"name": "Shona", "region": "Africa"},
|
| 71 |
"<2so>": {"name": "Somali", "region": "Africa"},
|
| 72 |
+
"<2nr>": {"name": "South Ndebele", "region": "Africa"},
|
| 73 |
+
"<2spp>": {"name": "Supyire Senoufo", "region": "Africa"},
|
| 74 |
"<2sus>": {"name": "Susu", "region": "Africa"},
|
| 75 |
"<2sw>": {"name": "Swahili", "region": "Africa"},
|
| 76 |
"<2ss>": {"name": "Swati", "region": "Africa"},
|
| 77 |
+
"<2ber>": {"name": "Tamazight (Tfng)", "region": "Africa"},
|
| 78 |
+
"<2tdx>": {"name": "Tandroy-Mahafaly Malagasy", "region": "Africa"},
|
| 79 |
"<2teo>": {"name": "Teso", "region": "Africa"},
|
| 80 |
"<2tll>": {"name": "Tetela", "region": "Africa"},
|
| 81 |
"<2ti>": {"name": "Tigrinya", "region": "Africa"},
|
|
|
|
| 95 |
"<2agr>": {"name": "Aguaruna", "region": "Americas"},
|
| 96 |
"<2cni>": {"name": "Asháninka", "region": "Americas"},
|
| 97 |
"<2kwi>": {"name": "Awa-Cuaiquer", "region": "Americas"},
|
| 98 |
+
"<2quy>": {"name": "Ayacucho Quechua", "region": "Americas"},
|
| 99 |
"<2ay>": {"name": "Aymara", "region": "Americas"},
|
| 100 |
+
"<2bzj>": {"name": "Belize Kriol English", "region": "Americas"},
|
| 101 |
+
"<2qvc>": {"name": "Cajamarca Quechua", "region": "Americas"},
|
| 102 |
+
"<2qxr>": {"name": "Cañar H. Quichua", "region": "Americas"},
|
| 103 |
+
"<2maz>": {"name": "Central Mazahua", "region": "Americas"},
|
| 104 |
"<2chr>": {"name": "Cherokee", "region": "Americas"},
|
| 105 |
"<2ctu>": {"name": "Chol", "region": "Americas"},
|
| 106 |
"<2cac>": {"name": "Chuj", "region": "Americas"},
|
| 107 |
+
"<2gui>": {"name": "E. Bolivian Guaraní", "region": "Americas"},
|
| 108 |
+
"<2nhe>": {"name": "E. Huasteca Nahuatl", "region": "Americas"},
|
| 109 |
+
"<2djk>": {"name": "E. Maroon Creole", "region": "Americas"},
|
| 110 |
"<2sja>": {"name": "Epena", "region": "Americas"},
|
| 111 |
"<2cab>": {"name": "Garifuna", "region": "Americas"},
|
| 112 |
"<2guh>": {"name": "Guahibo", "region": "Americas"},
|
| 113 |
"<2gn>": {"name": "Guarani", "region": "Americas"},
|
| 114 |
+
"<2amu>": {"name": "Guerrero Amuzgo", "region": "Americas"},
|
| 115 |
+
"<2ngu>": {"name": "Guerrero Nahuatl", "region": "Americas"},
|
| 116 |
+
"<2gyn>": {"name": "Guyanese Creole English", "region": "Americas"},
|
| 117 |
+
"<2ht>": {"name": "Haitian Creole", "region": "Americas"},
|
| 118 |
"<2haw>": {"name": "Hawaiian", "region": "Americas"},
|
| 119 |
+
"<2qub>": {"name": "Huallaga Huánuco Quechua", "region": "Americas"},
|
| 120 |
"<2hus>": {"name": "Huastec", "region": "Americas"},
|
| 121 |
+
"<2qvi>": {"name": "Imbabura H. Quichua", "region": "Americas"},
|
| 122 |
"<2inb>": {"name": "Inga", "region": "Americas"},
|
| 123 |
"<2iu>": {"name": "Inuktitut", "region": "Americas"},
|
| 124 |
+
"<2jam>": {"name": "Jamaican Creole English", "region": "Americas"},
|
| 125 |
"<2kl>": {"name": "Kalaallisut", "region": "Americas"},
|
| 126 |
"<2cak>": {"name": "Kaqchikel", "region": "Americas"},
|
| 127 |
"<2kek>": {"name": "Kekchí", "region": "Americas"},
|
| 128 |
"<2tlh>": {"name": "Klingon", "region": "Americas"},
|
| 129 |
"<2quc>": {"name": "K’iche’", "region": "Americas"},
|
| 130 |
+
"<2quf>": {"name": "Lambayeque Quechua", "region": "Americas"},
|
| 131 |
"<2mam>": {"name": "Mam", "region": "Americas"},
|
| 132 |
"<2arn>": {"name": "Mapudungun", "region": "Americas"},
|
| 133 |
"<2miq>": {"name": "Mískito", "region": "Americas"},
|
| 134 |
+
"<2emp>": {"name": "N. Emberá", "region": "Americas"},
|
| 135 |
+
"<2qvz>": {"name": "N. Pastaza Quichua", "region": "Americas"},
|
| 136 |
"<2nv>": {"name": "Navajo", "region": "Americas"},
|
| 137 |
"<2gym>": {"name": "Ngäbere", "region": "Americas"},
|
| 138 |
"<2zxx>": {"name": "Noise", "region": "Americas"},
|
|
|
|
| 140 |
"<2pap>": {"name": "Papiamento", "region": "Americas"},
|
| 141 |
"<2jac>": {"name": "Popti’", "region": "Americas"},
|
| 142 |
"<2qu>": {"name": "Quechua", "region": "Americas"},
|
| 143 |
+
"<2otq>": {"name": "Querétaro Otomi", "region": "Americas"},
|
| 144 |
+
"<2rcf>": {"name": "Réunion Creole French", "region": "Americas"},
|
| 145 |
+
"<2quh>": {"name": "S. Bolivian Quechua", "region": "Americas"},
|
| 146 |
+
"<2qup>": {"name": "S. Pastaza Quechua", "region": "Americas"},
|
| 147 |
+
"<2cuk>": {"name": "San Blas Kuna", "region": "Americas"},
|
| 148 |
"<2srm>": {"name": "Saramaccan", "region": "Americas"},
|
| 149 |
+
"<2crs>": {"name": "Seselwa Creole French", "region": "Americas"},
|
| 150 |
"<2shp>": {"name": "Shipibo-Conibo", "region": "Americas"},
|
| 151 |
"<2jiv>": {"name": "Shuar", "region": "Americas"},
|
| 152 |
+
"<2srn>": {"name": "Sranan Tongo", "region": "Americas"},
|
| 153 |
+
"<2acf>": {"name": "St Lucian Creole French", "region": "Americas"},
|
| 154 |
"<2tca>": {"name": "Ticuna", "region": "Americas"},
|
| 155 |
"<2toj>": {"name": "Tojolabal", "region": "Americas"},
|
| 156 |
"<2tzh>": {"name": "Tzeltal", "region": "Americas"},
|
| 157 |
"<2tzo>": {"name": "Tzotzil", "region": "Americas"},
|
| 158 |
"<2tzj>": {"name": "Tz’utujil", "region": "Americas"},
|
| 159 |
+
"<2knj>": {"name": "W. Kanjobal", "region": "Americas"},
|
| 160 |
"<2guc>": {"name": "Wayuu", "region": "Americas"},
|
| 161 |
+
"<2noa>": {"name": "Woun Meu", "region": "Americas"},
|
| 162 |
"<2yua>": {"name": "Yucateco", "region": "Americas"},
|
| 163 |
"<2zap>": {"name": "Zapotec", "region": "Americas"},
|
| 164 |
"<2az>": {"name": "Azerbaijani", "region": "Central Asia"},
|
| 165 |
"<2ba>": {"name": "Bashkir", "region": "Central Asia"},
|
| 166 |
+
"<2kaa-Latn>": {"name": "Kara-Kalpak (Latn)", "region": "Central Asia"},
|
| 167 |
"<2kk>": {"name": "Kazakh", "region": "Central Asia"},
|
| 168 |
"<2ky>": {"name": "Kyrghyz", "region": "Central Asia"},
|
| 169 |
"<2tg>": {"name": "Tajik", "region": "Central Asia"},
|
|
|
|
| 173 |
"<2dz>": {"name": "Dzongkha", "region": "East Asia"},
|
| 174 |
"<2ja>": {"name": "Japanese", "region": "East Asia"},
|
| 175 |
"<2ko>": {"name": "Korean", "region": "East Asia"},
|
| 176 |
+
"<2zh>": {"name": "Mandarin Chinese", "region": "East Asia"},
|
| 177 |
"<2mn>": {"name": "Mongolian", "region": "East Asia"},
|
| 178 |
"<2bo>": {"name": "Tibetan", "region": "East Asia"},
|
| 179 |
"<2sah>": {"name": "Yakut", "region": "East Asia"},
|
| 180 |
"<2za>": {"name": "Zhuang", "region": "East Asia"},
|
| 181 |
"<2ady>": {"name": "Adyghe", "region": "Europe"},
|
| 182 |
"<2sq>": {"name": "Albanian", "region": "Europe"},
|
| 183 |
+
"<2grc>": {"name": "Ancient Greek", "region": "Europe"},
|
| 184 |
"<2hy>": {"name": "Armenian", "region": "Europe"},
|
| 185 |
"<2frp>": {"name": "Arpitan", "region": "Europe"},
|
| 186 |
"<2av>": {"name": "Avar", "region": "Europe"},
|
|
|
|
| 190 |
"<2br>": {"name": "Breton", "region": "Europe"},
|
| 191 |
"<2bg>": {"name": "Bulgarian", "region": "Europe"},
|
| 192 |
"<2bua>": {"name": "Buryat", "region": "Europe"},
|
| 193 |
+
"<2rmc>": {"name": "Carpathian Romani", "region": "Europe"},
|
| 194 |
"<2ca>": {"name": "Catalan", "region": "Europe"},
|
| 195 |
"<2ce>": {"name": "Chechen", "region": "Europe"},
|
| 196 |
"<2cv>": {"name": "Chuvash", "region": "Europe"},
|
| 197 |
"<2kw>": {"name": "Cornish", "region": "Europe"},
|
| 198 |
"<2co>": {"name": "Corsican", "region": "Europe"},
|
| 199 |
+
"<2crh>": {"name": "Crimean Tatar", "region": "Europe"},
|
| 200 |
"<2hr>": {"name": "Croatian", "region": "Europe"},
|
| 201 |
"<2cs>": {"name": "Czech", "region": "Europe"},
|
| 202 |
"<2da>": {"name": "Danish", "region": "Europe"},
|
|
|
|
| 213 |
"<2ka>": {"name": "Georgian", "region": "Europe"},
|
| 214 |
"<2de>": {"name": "German", "region": "Europe"},
|
| 215 |
"<2el>": {"name": "Greek", "region": "Europe"},
|
| 216 |
+
"<2mrj>": {"name": "Hill Mari", "region": "Europe"},
|
| 217 |
"<2hu>": {"name": "Hungarian", "region": "Europe"},
|
| 218 |
"<2is>": {"name": "Icelandic", "region": "Europe"},
|
| 219 |
"<2ga>": {"name": "Irish", "region": "Europe"},
|
|
|
|
| 234 |
"<2mk>": {"name": "Macedonian", "region": "Europe"},
|
| 235 |
"<2mt>": {"name": "Maltese", "region": "Europe"},
|
| 236 |
"<2gv>": {"name": "Manx", "region": "Europe"},
|
| 237 |
+
"<2chm>": {"name": "Meadow Mari", "region": "Europe"},
|
| 238 |
"<2mdf>": {"name": "Moksha", "region": "Europe"},
|
| 239 |
+
"<2se>": {"name": "N. Sami", "region": "Europe"},
|
| 240 |
"<2nog>": {"name": "Nogai", "region": "Europe"},
|
| 241 |
"<2no>": {"name": "Norwegian", "region": "Europe"},
|
| 242 |
"<2oc>": {"name": "Occitan", "region": "Europe"},
|
| 243 |
+
"<2ang>": {"name": "Old English", "region": "Europe"},
|
| 244 |
"<2os>": {"name": "Ossetian", "region": "Europe"},
|
| 245 |
"<2pl>": {"name": "Polish", "region": "Europe"},
|
| 246 |
"<2pt>": {"name": "Portuguese", "region": "Europe"},
|
|
|
|
| 248 |
"<2ro>": {"name": "Romanian", "region": "Europe"},
|
| 249 |
"<2rm>": {"name": "Romansh", "region": "Europe"},
|
| 250 |
"<2ru>": {"name": "Russian", "region": "Europe"},
|
| 251 |
+
"<2alt>": {"name": "S. Altai", "region": "Europe"},
|
| 252 |
"<2stq>": {"name": "Saterfriesisch", "region": "Europe"},
|
| 253 |
+
"<2gd>": {"name": "Scottish Gaelic", "region": "Europe"},
|
| 254 |
"<2sr>": {"name": "Serbian", "region": "Europe"},
|
| 255 |
"<2sk>": {"name": "Slovak", "region": "Europe"},
|
| 256 |
"<2sl>": {"name": "Slovenian", "region": "Europe"},
|
| 257 |
"<2es>": {"name": "Spanish", "region": "Europe"},
|
| 258 |
"<2sv>": {"name": "Swedish", "region": "Europe"},
|
| 259 |
+
"<2gsw>": {"name": "Swiss German", "region": "Europe"},
|
| 260 |
"<2tab>": {"name": "Tabassaran", "region": "Europe"},
|
| 261 |
"<2tt>": {"name": "Tatar", "region": "Europe"},
|
| 262 |
"<2tyv>": {"name": "Tuvinian", "region": "Europe"},
|
| 263 |
"<2udm>": {"name": "Udmurt", "region": "Europe"},
|
| 264 |
"<2uk>": {"name": "Ukrainian", "region": "Europe"},
|
| 265 |
"<2vec>": {"name": "Venetian", "region": "Europe"},
|
| 266 |
+
"<2fy>": {"name": "W. Frisian", "region": "Europe"},
|
| 267 |
"<2wa>": {"name": "Walloon", "region": "Europe"},
|
| 268 |
"<2cy>": {"name": "Welsh", "region": "Europe"},
|
| 269 |
"<2ar>": {"name": "Arabic", "region": "Middle East & North Africa"},
|
| 270 |
+
"<2bgp>": {"name": "E. Baluchi", "region": "Middle East & North Africa"},
|
| 271 |
"<2mey>": {"name": "Hassaniyya", "region": "Middle East & North Africa"},
|
| 272 |
"<2he>": {"name": "Hebrew", "region": "Middle East & North Africa"},
|
| 273 |
"<2ks>": {"name": "Kashmiri", "region": "Middle East & North Africa"},
|
| 274 |
+
"<2ku>": {"name": "Kurdish (Kurmanji)", "region": "Middle East & North Africa"},
|
| 275 |
+
"<2ckb>": {"name": "Kurdish (Sorani)", "region": "Middle East & North Africa"},
|
| 276 |
+
"<2lrc>": {"name": "N. Luri", "region": "Middle East & North Africa"},
|
| 277 |
"<2ps>": {"name": "Pashto", "region": "Middle East & North Africa"},
|
| 278 |
"<2fa>": {"name": "Persian", "region": "Middle East & North Africa"},
|
| 279 |
+
"<2luz>": {"name": "S. Luri", "region": "Middle East & North Africa"},
|
| 280 |
"<2skr>": {"name": "Saraiki", "region": "Middle East & North Africa"},
|
| 281 |
"<2sd>": {"name": "Sindhi", "region": "Middle East & North Africa"},
|
| 282 |
"<2syr>": {"name": "Syriac", "region": "Middle East & North Africa"},
|
|
|
|
| 293 |
"<2chk>": {"name": "Chuukese", "region": "Oceania"},
|
| 294 |
"<2mps>": {"name": "Dadibi", "region": "Oceania"},
|
| 295 |
"<2enq>": {"name": "Enga", "region": "Oceania"},
|
| 296 |
+
"<2hif>": {"name": "Fiji Hindi", "region": "Oceania"},
|
| 297 |
"<2fj>": {"name": "Fijian", "region": "Oceania"},
|
| 298 |
"<2gil>": {"name": "Gilbertese", "region": "Oceania"},
|
| 299 |
+
"<2ho>": {"name": "Hiri Motu", "region": "Oceania"},
|
| 300 |
"<2hui>": {"name": "Huli", "region": "Oceania"},
|
| 301 |
"<2kos>": {"name": "Kosraean", "region": "Oceania"},
|
| 302 |
"<2ksd>": {"name": "Kuanua", "region": "Oceania"},
|
|
|
|
| 311 |
"<2hvn>": {"name": "Sabu", "region": "Oceania"},
|
| 312 |
"<2sm>": {"name": "Samoan", "region": "Oceania"},
|
| 313 |
"<2twu>": {"name": "Termanu", "region": "Oceania"},
|
| 314 |
+
"<2to>": {"name": "Tonga (Tonga Islands)", "region": "Oceania"},
|
| 315 |
"<2tvl>": {"name": "Tuvalu", "region": "Oceania"},
|
| 316 |
"<2ubu>": {"name": "Umbu-Ungu", "region": "Oceania"},
|
| 317 |
"<2yap>": {"name": "Yapese", "region": "Oceania"},
|
|
|
|
| 319 |
"<2awa>": {"name": "Awadhi", "region": "South Asia"},
|
| 320 |
"<2bn>": {"name": "Bengali", "region": "South Asia"},
|
| 321 |
"<2bho>": {"name": "Bhojpuri", "region": "South Asia"},
|
| 322 |
+
"<2brx>": {"name": "Bodo (India)", "region": "South Asia"},
|
| 323 |
"<2hne>": {"name": "Chhattisgarhi", "region": "South Asia"},
|
| 324 |
"<2dv>": {"name": "Dhivehi", "region": "South Asia"},
|
| 325 |
+
"<2taj>": {"name": "E. Tamang", "region": "South Asia"},
|
| 326 |
"<2gbm>": {"name": "Garhwali", "region": "South Asia"},
|
| 327 |
+
"<2gom>": {"name": "Goan Konkani", "region": "South Asia"},
|
| 328 |
"<2gu>": {"name": "Gujarati", "region": "South Asia"},
|
| 329 |
"<2hi>": {"name": "Hindi", "region": "South Asia"},
|
| 330 |
"<2bjj>": {"name": "Kanauji", "region": "South Asia"},
|
| 331 |
"<2kn>": {"name": "Kannada", "region": "South Asia"},
|
| 332 |
"<2kha>": {"name": "Khasi", "region": "South Asia"},
|
| 333 |
+
"<2trp>": {"name": "Kok Borok", "region": "South Asia"},
|
| 334 |
"<2mag>": {"name": "Magahi", "region": "South Asia"},
|
| 335 |
"<2mai>": {"name": "Maithili", "region": "South Asia"},
|
| 336 |
"<2ml>": {"name": "Malayalam", "region": "South Asia"},
|
| 337 |
"<2mr>": {"name": "Marathi", "region": "South Asia"},
|
| 338 |
+
"<2mni>": {"name": "Meiteilon (Manipuri)", "region": "South Asia"},
|
| 339 |
"<2mtr>": {"name": "Mewari", "region": "South Asia"},
|
| 340 |
"<2lus>": {"name": "Mizo", "region": "South Asia"},
|
| 341 |
"<2ne>": {"name": "Nepali", "region": "South Asia"},
|
| 342 |
"<2new>": {"name": "Newari", "region": "South Asia"},
|
| 343 |
"<2noe>": {"name": "Nimadi", "region": "South Asia"},
|
| 344 |
+
"<2or>": {"name": "Odia (Oriya)", "region": "South Asia"},
|
| 345 |
"<2pa>": {"name": "Punjabi", "region": "South Asia"},
|
| 346 |
"<2raj>": {"name": "Rajasthani", "region": "South Asia"},
|
| 347 |
"<2sa>": {"name": "Sanskrit", "region": "South Asia"},
|
|
|
|
| 354 |
"<2te>": {"name": "Telugu", "region": "South Asia"},
|
| 355 |
"<2tcy>": {"name": "Tulu", "region": "South Asia"},
|
| 356 |
"<2ace>": {"name": "Achinese", "region": "Southeast Asia"},
|
| 357 |
+
"<2msm>": {"name": "Agusan Manobo", "region": "Southeast Asia"},
|
| 358 |
"<2ahk>": {"name": "Akha", "region": "Southeast Asia"},
|
| 359 |
"<2ban>": {"name": "Balinese", "region": "Southeast Asia"},
|
| 360 |
"<2bgz>": {"name": "Banggai", "region": "Southeast Asia"},
|
| 361 |
+
"<2akb>": {"name": "Batak Angkola", "region": "Southeast Asia"},
|
| 362 |
+
"<2btx>": {"name": "Batak Karo", "region": "Southeast Asia"},
|
| 363 |
+
"<2bts>": {"name": "Batak Simalungun", "region": "Southeast Asia"},
|
| 364 |
+
"<2bbc>": {"name": "Batak Toba", "region": "Southeast Asia"},
|
| 365 |
"<2bew>": {"name": "Betawi", "region": "Southeast Asia"},
|
| 366 |
+
"<2jvn>": {"name": "Caribbean Javanese", "region": "Southeast Asia"},
|
| 367 |
"<2ceb>": {"name": "Cebuano", "region": "Southeast Asia"},
|
| 368 |
+
"<2bik>": {"name": "Central Bikol", "region": "Southeast Asia"},
|
| 369 |
+
"<2mel>": {"name": "Central Melanau", "region": "Southeast Asia"},
|
| 370 |
"<2cbk>": {"name": "Chavacano", "region": "Southeast Asia"},
|
| 371 |
+
"<2bru>": {"name": "E. Bru", "region": "Southeast Asia"},
|
| 372 |
+
"<2cfm>": {"name": "Falam Chin", "region": "Southeast Asia"},
|
| 373 |
"<2fil>": {"name": "Filipino", "region": "Southeast Asia"},
|
| 374 |
"<2gor>": {"name": "Gorontalo", "region": "Southeast Asia"},
|
| 375 |
+
"<2cnh>": {"name": "Hakha Chin", "region": "Southeast Asia"},
|
| 376 |
"<2hil>": {"name": "Hiligaynon", "region": "Southeast Asia"},
|
| 377 |
"<2hmn>": {"name": "Hmong", "region": "Southeast Asia"},
|
| 378 |
"<2iba>": {"name": "Iban", "region": "Southeast Asia"},
|
| 379 |
"<2ilo>": {"name": "Ilocano", "region": "Southeast Asia"},
|
| 380 |
"<2id>": {"name": "Indonesian", "region": "Southeast Asia"},
|
| 381 |
+
"<2ium>": {"name": "Iu Mien", "region": "Southeast Asia"},
|
| 382 |
+
"<2jax>": {"name": "Jambi Malay", "region": "Southeast Asia"},
|
| 383 |
"<2jv>": {"name": "Javanese", "region": "Southeast Asia"},
|
| 384 |
"<2kac>": {"name": "Kachin", "region": "Southeast Asia"},
|
| 385 |
+
"<2dtp>": {"name": "Kadazan Dusun", "region": "Southeast Asia"},
|
| 386 |
+
"<2meo>": {"name": "Kedah Malay", "region": "Southeast Asia"},
|
| 387 |
"<2ify>": {"name": "Keley-IKallahan", "region": "Southeast Asia"},
|
| 388 |
"<2km>": {"name": "Khmer", "region": "Southeast Asia"},
|
| 389 |
"<2kjg>": {"name": "Khmu", "region": "Southeast Asia"},
|
| 390 |
"<2krj>": {"name": "Kinaray-A", "region": "Southeast Asia"},
|
| 391 |
+
"<2mkn>": {"name": "Kupang Malay", "region": "Southeast Asia"},
|
| 392 |
"<2lhu>": {"name": "Lahu", "region": "Southeast Asia"},
|
| 393 |
"<2lo>": {"name": "Lao", "region": "Southeast Asia"},
|
| 394 |
"<2mad>": {"name": "Madurese", "region": "Southeast Asia"},
|
| 395 |
"<2mak>": {"name": "Makasar", "region": "Southeast Asia"},
|
| 396 |
"<2ms>": {"name": "Malay", "region": "Southeast Asia"},
|
| 397 |
+
"<2xmm>": {"name": "Manado Malay", "region": "Southeast Asia"},
|
| 398 |
"<2mqy>": {"name": "Manggarai", "region": "Southeast Asia"},
|
| 399 |
"<2mrw>": {"name": "Maranao", "region": "Southeast Asia"},
|
| 400 |
"<2msb>": {"name": "Masbatenyo", "region": "Southeast Asia"},
|
| 401 |
+
"<2mbt>": {"name": "Matigsalug Manobo", "region": "Southeast Asia"},
|
| 402 |
"<2min>": {"name": "Minangkabau", "region": "Southeast Asia"},
|
| 403 |
"<2mnw>": {"name": "Mon", "region": "Southeast Asia"},
|
| 404 |
+
"<2my>": {"name": "Myanmar (Burmese)", "region": "Southeast Asia"},
|
| 405 |
"<2nij>": {"name": "Ngaju", "region": "Southeast Asia"},
|
| 406 |
"<2nia>": {"name": "Nias", "region": "Southeast Asia"},
|
| 407 |
+
"<2nut>": {"name": "Nung (Viet Nam)", "region": "Southeast Asia"},
|
| 408 |
+
"<2pck>": {"name": "Paite Chin", "region": "Southeast Asia"},
|
| 409 |
"<2pam>": {"name": "Pampanga", "region": "Southeast Asia"},
|
| 410 |
"<2pag>": {"name": "Pangasinan", "region": "Southeast Asia"},
|
| 411 |
"<2prk>": {"name": "Parauk", "region": "Southeast Asia"},
|
| 412 |
"<2rki>": {"name": "Rakhine", "region": "Southeast Asia"},
|
| 413 |
+
"<2msi>": {"name": "Sabah Malay", "region": "Southeast Asia"},
|
| 414 |
"<2sxn>": {"name": "Sangir", "region": "Southeast Asia"},
|
| 415 |
"<2shn>": {"name": "Shan", "region": "Southeast Asia"},
|
| 416 |
"<2su>": {"name": "Sundanese", "region": "Southeast Asia"},
|
| 417 |
+
"<2ksw>": {"name": "S’gaw Karen", "region": "Southeast Asia"},
|
| 418 |
"<2tsg>": {"name": "Tausug", "region": "Southeast Asia"},
|
| 419 |
"<2tet>": {"name": "Tetum", "region": "Southeast Asia"},
|
| 420 |
"<2th>": {"name": "Thai", "region": "Southeast Asia"},
|
|
|
|
| 422 |
"<2tyz>": {"name": "Tày", "region": "Southeast Asia"},
|
| 423 |
"<2ppk>": {"name": "Uma", "region": "Southeast Asia"},
|
| 424 |
"<2vi>": {"name": "Vietnamese", "region": "Southeast Asia"},
|
| 425 |
+
"<2war>": {"name": "Waray (Philippines)", "region": "Southeast Asia"},
|
| 426 |
}
|
scripts/generate_langmap.py
CHANGED
|
@@ -417,6 +417,23 @@ LANGUAGE_OVERRIDES: dict[str, str] = {
|
|
| 417 |
}
|
| 418 |
|
| 419 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 420 |
def parse_table9(pdf_path: str) -> list[dict[str, str]]:
|
| 421 |
"""Parse Table 9 from the MADLAD-400 paper using word-based extraction.
|
| 422 |
|
|
@@ -455,6 +472,7 @@ def parse_table9(pdf_path: str) -> list[dict[str, str]]:
|
|
| 455 |
data_ws = [w for w in data_col if abs(w["top"] - bcp_top) <= ROW_TOLERANCE]
|
| 456 |
|
| 457 |
name = " ".join(w["text"] for w in sorted(name_ws, key=lambda w: w["x0"]))
|
|
|
|
| 458 |
script = " ".join(w["text"] for w in sorted(script_ws, key=lambda w: w["x0"]))
|
| 459 |
data_texts = [w["text"] for w in sorted(data_ws, key=lambda w: w["x0"])]
|
| 460 |
|
|
|
|
| 417 |
}
|
| 418 |
|
| 419 |
|
| 420 |
+
def fix_name_spacing(name: str) -> str:
|
| 421 |
+
"""Insert spaces lost during PDF word extraction.
|
| 422 |
+
|
| 423 |
+
PDF word extraction sometimes concatenates adjacent words when they appear
|
| 424 |
+
close together on the page. This function restores spaces before uppercase
|
| 425 |
+
letters that follow lowercase letters, before opening parentheses, and after
|
| 426 |
+
periods followed by uppercase letters.
|
| 427 |
+
"""
|
| 428 |
+
# Insert space before uppercase letter following a lowercase/accented lowercase letter
|
| 429 |
+
name = re.sub(r"([a-zà-öø-ÿ])([A-Z])", r"\1 \2", name)
|
| 430 |
+
# Insert space before opening parenthesis following a word character
|
| 431 |
+
name = re.sub(r"(\w)\(", r"\1 (", name)
|
| 432 |
+
# Insert space after period followed by uppercase letter
|
| 433 |
+
name = re.sub(r"\.([A-Z])", r". \1", name)
|
| 434 |
+
return name
|
| 435 |
+
|
| 436 |
+
|
| 437 |
def parse_table9(pdf_path: str) -> list[dict[str, str]]:
|
| 438 |
"""Parse Table 9 from the MADLAD-400 paper using word-based extraction.
|
| 439 |
|
|
|
|
| 472 |
data_ws = [w for w in data_col if abs(w["top"] - bcp_top) <= ROW_TOLERANCE]
|
| 473 |
|
| 474 |
name = " ".join(w["text"] for w in sorted(name_ws, key=lambda w: w["x0"]))
|
| 475 |
+
name = fix_name_spacing(name)
|
| 476 |
script = " ".join(w["text"] for w in sorted(script_ws, key=lambda w: w["x0"]))
|
| 477 |
data_texts = [w["text"] for w in sorted(data_ws, key=lambda w: w["x0"])]
|
| 478 |
|