languages/data/Names.php

   1 <?php
   2 /**
   3  * Language names.
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Language
  22  */
  23
  24 namespace MediaWiki\Languages\Data;
  25
  26 /**
  27  * Language names in their own languages (language autonyms).
  28  *
  29  * These determine things like interwikis, language selectors, and so on.
  30  * Safe to change without running scripts on the respective sites.
  31  *
  32  * \xE2\x80\x8E is the left-to-right marker and
  33  * \xE2\x80\x8F is the right-to-left marker.
  34  * They are required for ensuring the correct display of brackets in
  35  * mixed rtl/ltr environment.
  36  *
  37  * Some writing systems require some line-height fixes. This includes
  38  * most Indic scripts, like Devanagari.
  39  * If you are adding support for such a language, add it also to
  40  * the relevant section in shared.css.
  41  *
  42  * Do not use this class directly. Use Language::fetchLanguageNames(), which
  43  * includes support for the CLDR extension.
  44  *
  45  * @ingroup Language
  46  */
  47 class Names {
  48         public static $names = [
  49                 'aa' => 'Qafár af', # Afar
  50                 'ab' => 'Аҧсшәа', # Abkhaz
  51                 'ace' => 'Acèh', # Aceh
  52                 'ady' => 'адыгабзэ', # Adyghe
  53                 'ady-cyrl' => 'адыгабзэ', # Adyghe
  54                 'aeb' => 'تونسي/Tûnsî', # Tunisian Arabic (multiple scripts - defaults to Arabic)
  55                 'aeb-arab' => 'تونسي', # Tunisian Arabic (Arabic Script)
  56                 'aeb-latn' => 'Tûnsî', # Tunisian Arabic (Latin Script)
  57                 'af' => 'Afrikaans', # Afrikaans
  58                 'ak' => 'Akan', # Akan
  59                 'aln' => 'Gegë', # Gheg Albanian
  60                 'als' => 'Alemannisch', # Alemannic -- not a valid code, for compatibility. See gsw.
  61                 'am' => 'አማርኛ', # Amharic
  62                 'an' => 'aragonés', # Aragonese
  63                 'ang' => 'Ænglisc', # Old English, bug 23283
  64                 'anp' => 'अङ्गिका', # Angika
  65                 'ar' => 'العربية', # Arabic
  66                 'arc' => 'ܐܪܡܝܐ', # Aramaic
  67                 'arn' => 'mapudungun', # Mapuche, Mapudungu, Araucanian (Araucano)
  68                 'arq' => 'جازايرية', # Algerian Spoken Arabic
  69                 'ary' => 'Maġribi', # Moroccan Spoken Arabic
  70                 'arz' => 'مصرى', # Egyptian Spoken Arabic
  71                 'as' => 'অসমীয়া', # Assamese
  72                 'ase' => 'American sign language', # American sign language
  73                 'ast' => 'asturianu', # Asturian
  74                 'av' => 'авар', # Avar
  75                 'avk' => 'Kotava', # Kotava
  76                 'awa' => 'अवधी', # Awadhi
  77                 'ay' => 'Aymar aru', # Aymara
  78                 'az' => 'azərbaycanca', # Azerbaijani
  79                 'azb' => 'تۆرکجه', # South Azerbaijani
  80                 'ba' => 'башҡортса', # Bashkir
  81                 'ban' => 'Basa Bali', # Balinese
  82                 'bar' => 'Boarisch', # Bavarian (Austro-Bavarian and South Tyrolean)
  83                 'bat-smg' => 'žemaitėška', # Samogitian (deprecated code, 'sgs' in ISO 693-3 since 2010-06-30 )
  84                 'bbc' => 'Batak Toba', # Batak Toba (falls back to bbc-latn)
  85                 'bbc-latn' => 'Batak Toba', # Batak Toba
  86                 'bcc' => 'جهلسری بلوچی', # Southern Balochi
  87                 'bcl' => 'Bikol Central', # Bikol: Central Bicolano language
  88                 'be' => 'беларуская', # Belarusian normative
  89                 'be-tarask' => "беларуская (тарашкевіца)\xE2\x80\x8E", # Belarusian in Taraskievica orthography
  90                 'be-x-old' => "беларуская (тарашкевіца)\xE2\x80\x8E", # (be-tarask compat)
  91                 'bg' => 'български', # Bulgarian
  92                 'bgn' => 'روچ کپتین بلوچی', # Western Balochi
  93                 'bh' => 'भोजपुरी', # Bihari macro language. Falls back to Bhojpuri (bho)
  94                 'bho' => 'भोजपुरी', # Bhojpuri
  95                 'bi' => 'Bislama', # Bislama
  96                 'bjn' => 'Bahasa Banjar', # Banjarese
  97                 'bm' => 'bamanankan', # Bambara
  98                 'bn' => 'বাংলা', # Bengali
  99                 'bo' => 'བོད་ཡིག', # Tibetan
 100                 'bpy' => 'বিষ্ণুপ্রিয়া মণিপুরী', # Bishnupriya Manipuri
 101                 'bqi' => 'بختیاری', # Bakthiari
 102                 'br' => 'brezhoneg', # Breton
 103                 'brh' => 'Bráhuí', # Brahui
 104                 'bs' => 'bosanski', # Bosnian
 105                 'bto' => 'Iriga Bicolano', # Rinconada Bikol
 106                 'bug' => 'ᨅᨔ ᨕᨘᨁᨗ', # Buginese
 107                 'bxr' => 'буряад', # Buryat (Russia)
 108                 'ca' => 'català', # Catalan
 109                 'cbk-zam' => 'Chavacano de Zamboanga', # Zamboanga Chavacano
 110                 'cdo' => 'Mìng-dĕ̤ng-ngṳ̄', # Min Dong
 111                 'ce' => 'нохчийн', # Chechen
 112                 'ceb' => 'Cebuano', # Cebuano
 113                 'ch' => 'Chamoru', # Chamorro
 114                 'cho' => 'Choctaw', # Choctaw
 115                 'chr' => 'ᏣᎳᎩ', # Cherokee
 116                 'chy' => 'Tsetsêhestâhese', # Cheyenne
 117                 'ckb' => 'کوردیی ناوەندی', # Central Kurdish
 118                 'co' => 'corsu', # Corsican
 119                 'cps' => 'Capiceño', # Capiznon
 120                 'cr' => 'Nēhiyawēwin / ᓀᐦᐃᔭᐍᐏᐣ', # Cree
 121                 'crh' => 'qırımtatarca', # Crimean Tatar (multiple scripts - defaults to Latin)
 122                 'crh-latn' => "qırımtatarca (Latin)\xE2\x80\x8E", # Crimean Tatar (Latin)
 123                 'crh-cyrl' => "къырымтатарджа (Кирилл)\xE2\x80\x8E", # Crimean Tatar (Cyrillic)
 124                 'cs' => 'čeština', # Czech
 125                 'csb' => 'kaszëbsczi', # Cassubian
 126                 'cu' => 'словѣньскъ / ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ', # Old Church Slavonic (ancient language)
 127                 'cv' => 'Чӑвашла', # Chuvash
 128                 'cy' => 'Cymraeg', # Welsh
 129                 'da' => 'dansk', # Danish
 130                 'de' => 'Deutsch', # German ("Du")
 131                 'de-at' => 'Österreichisches Deutsch', # Austrian German
 132                 'de-ch' => 'Schweizer Hochdeutsch', # Swiss Standard German
 133                 'de-formal' => "Deutsch (Sie-Form)\xE2\x80\x8E", # German - formal address ("Sie")
 134                 'diq' => 'Zazaki', # Zazaki
 135                 'dsb' => 'dolnoserbski', # Lower Sorbian
 136                 'dtp' => 'Dusun Bundu-liwan', # Central Dusun
 137                 'dty' => 'डोटेली', # Doteli
 138                 'dv' => 'ދިވެހިބަސް', # Dhivehi
 139                 'dz' => 'ཇོང་ཁ', # Dzongkha (Bhutan)
 140                 'ee' => 'eʋegbe', # Éwé
 141                 'egl' => 'Emiliàn', # Emilian
 142                 'el' => 'Ελληνικά', # Greek
 143                 'eml' => 'emiliàn e rumagnòl', # Emiliano-Romagnolo / Sammarinese
 144                 'en' => 'English', # English
 145                 'en-ca' => 'Canadian English', # Canadian English
 146                 'en-gb' => 'British English', # British English
 147                 'eo' => 'Esperanto', # Esperanto
 148                 'es' => 'español', # Spanish
 149                 'et' => 'eesti', # Estonian
 150                 'eu' => 'euskara', # Basque
 151                 'ext' => 'estremeñu', # Extremaduran
 152                 'fa' => 'فارسی', # Persian
 153                 'ff' => 'Fulfulde', # Fulfulde, Maasina
 154                 'fi' => 'suomi', # Finnish
 155                 'fit' => 'meänkieli', # Tornedalen Finnish
 156                 'fiu-vro' => 'Võro', # Võro (deprecated code, 'vro' in ISO 639-3 since 2009-01-16)
 157                 'fj' => 'Na Vosa Vakaviti', # Fijian
 158                 'fo' => 'føroyskt', # Faroese
 159                 'fr' => 'français', # French
 160                 'frc' => 'français cadien', # Cajun French
 161                 'frp' => 'arpetan', # Franco-Provençal/Arpitan
 162                 'frr' => 'Nordfriisk', # North Frisian
 163                 'fur' => 'furlan', # Friulian
 164                 'fy' => 'Frysk', # Frisian
 165                 'ga' => 'Gaeilge', # Irish
 166                 'gag' => 'Gagauz', # Gagauz
 167                 'gan' => '贛語', # Gan (multiple scripts - defaults to Traditional)
 168                 'gan-hans' => "赣语（简体）\xE2\x80\x8E", # Gan (Simplified Han)
 169                 'gan-hant' => "贛語（繁體）\xE2\x80\x8E", # Gan (Traditional Han)
 170                 'gd' => 'Gàidhlig', # Scots Gaelic
 171                 'gl' => 'galego', # Galician
 172                 'glk' => 'گیلکی', # Gilaki
 173                 'gn' => 'Avañe\'ẽ', # Guaraní, Paraguayan
 174                 'gom' => 'गोंयची कोंकणी / Gõychi Konknni', # Goan Konkani
 175                 'gom-deva' => 'गोंयची कोंकणी', # Goan Konkani (Devanagari script)
 176                 'gom-latn' => 'Gõychi Konknni', # Goan Konkani (Latin script)
 177                 'gor' => 'Bahasa Hulontalo', # Gorontalo
 178                 'got' => '𐌲𐌿𐍄𐌹𐍃𐌺', # Gothic
 179                 'grc' => 'Ἀρχαία ἑλληνικὴ', # Ancient Greek
 180                 'gsw' => 'Alemannisch', # Alemannic
 181                 'gu' => 'ગુજરાતી', # Gujarati
 182                 'gv' => 'Gaelg', # Manx
 183                 'ha' => 'Hausa', # Hausa
 184                 'hak' => '客家語/Hak-kâ-ngî', # Hakka
 185                 'haw' => 'Hawaiʻi', # Hawaiian
 186                 'he' => 'עברית', # Hebrew
 187                 'hi' => 'हिन्दी', # Hindi
 188                 'hif' => 'Fiji Hindi', # Fijian Hindi (multiple scripts - defaults to Latin)
 189                 'hif-latn' => 'Fiji Hindi', # Fiji Hindi (latin)
 190                 'hil' => 'Ilonggo', # Hiligaynon
 191                 'ho' => 'Hiri Motu', # Hiri Motu
 192                 'hr' => 'hrvatski', # Croatian
 193                 'hrx' => 'Hunsrik', # Riograndenser Hunsrückisch
 194                 'hsb' => 'hornjoserbsce', # Upper Sorbian
 195                 'ht' => 'Kreyòl ayisyen', # Haitian Creole French
 196                 'hu' => 'magyar', # Hungarian
 197                 'hy' => 'Հայերեն', # Armenian
 198                 'hz' => 'Otsiherero', # Herero
 199                 'ia' => 'interlingua', # Interlingua (IALA)
 200                 'id' => 'Bahasa Indonesia', # Indonesian
 201                 'ie' => 'Interlingue', # Interlingue (Occidental)
 202                 'ig' => 'Igbo', # Igbo
 203                 'ii' => 'ꆇꉙ', # Sichuan Yi
 204                 'ik' => 'Iñupiak', # Inupiak (Inupiatun, Northwest Alaska / Inupiatun, North Alaskan)
 205                 'ike-cans' => 'ᐃᓄᒃᑎᑐᑦ', # Inuktitut, Eastern Canadian (Unified Canadian Aboriginal Syllabics)
 206                 'ike-latn' => 'inuktitut', # Inuktitut, Eastern Canadian (Latin script)
 207                 'ilo' => 'Ilokano', # Ilokano
 208                 'inh' => 'ГӀалгӀай', # Ingush
 209                 'io' => 'Ido', # Ido
 210                 'is' => 'íslenska', # Icelandic
 211                 'it' => 'italiano', # Italian
 212                 'iu' => 'ᐃᓄᒃᑎᑐᑦ/inuktitut', # Inuktitut (macro language, see ike/ikt, falls back to ike-cans)
 213                 'ja' => '日本語', # Japanese
 214                 'jam' => 'Patois', # Jamaican Creole English
 215                 'jbo' => 'la .lojban.', # Lojban
 216                 'jut' => 'jysk', # Jutish / Jutlandic
 217                 'jv' => 'Basa Jawa', # Javanese
 218                 'ka' => 'ქართული', # Georgian
 219                 'kaa' => 'Qaraqalpaqsha', # Karakalpak
 220                 'kab' => 'Taqbaylit', # Kabyle
 221                 'kbd' => 'Адыгэбзэ', # Kabardian
 222                 'kbd-cyrl' => 'Адыгэбзэ', # Kabardian (Cyrillic)
 223                 'kg' => 'Kongo', # Kongo, (FIXME!) should probaly be KiKongo or KiKoongo
 224                 'khw' => 'کھوار', # Khowar
 225                 'ki' => 'Gĩkũyũ', # Gikuyu
 226                 'kiu' => 'Kırmancki', # Kirmanjki
 227                 'kj' => 'Kwanyama', # Kwanyama
 228                 'kk' => 'қазақша', # Kazakh (multiple scripts - defaults to Cyrillic)
 229                 'kk-arab' => "قازاقشا (تٴوتە)\xE2\x80\x8F", # Kazakh Arabic
 230                 'kk-cyrl' => "қазақша (кирил)\xE2\x80\x8E", # Kazakh Cyrillic
 231                 'kk-latn' => "qazaqşa (latın)\xE2\x80\x8E", # Kazakh Latin
 232                 'kk-cn' => "قازاقشا (جۇنگو)\xE2\x80\x8F", # Kazakh (China)
 233                 'kk-kz' => "қазақша (Қазақстан)\xE2\x80\x8E", # Kazakh (Kazakhstan)
 234                 'kk-tr' => "qazaqşa (Türkïya)\xE2\x80\x8E", # Kazakh (Turkey)
 235                 'kl' => 'kalaallisut', # Inuktitut, Greenlandic/Greenlandic/Kalaallisut (kal)
 236                 'km' => 'ភាសាខ្មែរ', # Khmer, Central
 237                 'kn' => 'ಕನ್ನಡ', # Kannada
 238                 'ko' => '한국어', # Korean
 239                 'ko-kp' => '한국어 (조선)', # Korean (DPRK)
 240                 'koi' => 'Перем Коми', # Komi-Permyak
 241                 'kr' => 'Kanuri', # Kanuri, Central
 242                 'krc' => 'къарачай-малкъар', # Karachay-Balkar
 243                 'kri' => 'Krio', # Krio
 244                 'krj' => 'Kinaray-a', # Kinaray-a
 245                 'krl' => 'karjal', # Karelian
 246                 'ks' => 'कॉशुर / کٲشُر', # Kashmiri (multiple scripts - defaults to Perso-Arabic)
 247                 'ks-arab' => 'کٲشُر', # Kashmiri (Perso-Arabic script)
 248                 'ks-deva' => 'कॉशुर', # Kashmiri (Devanagari script)
 249                 'ksh' => 'Ripoarisch', # Ripuarian
 250                 'ku' => 'Kurdî', # Kurdish (multiple scripts - defaults to Latin)
 251                 'ku-latn' => "Kurdî (latînî)\xE2\x80\x8E", # Northern Kurdish (Latin script)
 252                 'ku-arab' => "كوردي (عەرەبی)\xE2\x80\x8F", # Northern Kurdish (Arabic script) (falls back to ckb)
 253                 'kv' => 'коми', # Komi-Zyrian (Cyrillic is common script but also written in Latin script)
 254                 'kw' => 'kernowek', # Cornish
 255                 'ky' => 'Кыргызча', # Kirghiz
 256                 'la' => 'Latina', # Latin
 257                 'lad' => 'Ladino', # Ladino
 258                 'lb' => 'Lëtzebuergesch', # Luxemburguish
 259                 'lbe' => 'лакку', # Lak
 260                 'lez' => 'лезги', # Lezgi
 261                 'lfn' => 'Lingua Franca Nova', # Lingua Franca Nova
 262                 'lg' => 'Luganda', # Ganda
 263                 'li' => 'Limburgs', # Limburgian
 264                 'lij' => 'Ligure', # Ligurian
 265                 'liv' => 'Līvõ kēļ', # Livonian
 266                 'lki' => 'لەکی‎', # Laki
 267                 'lmo' => 'lumbaart', # Lombard
 268                 'ln' => 'lingála', # Lingala
 269                 'lo' => 'ລາວ', # Laotian
 270                 'lrc' => 'لۊری شومالی', # Northern Luri
 271                 'loz' => 'Silozi', # Lozi
 272                 'lt' => 'lietuvių', # Lithuanian
 273                 'ltg' => 'latgaļu', # Latgalian
 274                 'lus' => 'Mizo ţawng', # Mizo/Lushai
 275                 'luz' => 'لئری دوٙمینی', # Southern Luri
 276                 'lv' => 'latviešu', # Latvian
 277                 'lzh' => '文言', # Literary Chinese, bug 8217
 278                 'lzz' => 'Lazuri', # Laz
 279                 'mai' => 'मैथिली', # Maithili
 280                 'map-bms' => 'Basa Banyumasan', # Banyumasan
 281                 'mdf' => 'мокшень', # Moksha
 282                 'mg' => 'Malagasy', # Malagasy
 283                 'mh' => 'Ebon', # Marshallese
 284                 'mhr' => 'олык марий', # Eastern Mari
 285                 'mi' => 'Māori', # Maori
 286                 'min' => 'Baso Minangkabau', # Minangkabau
 287                 'mk' => 'македонски', # Macedonian
 288                 'ml' => 'മലയാളം', # Malayalam
 289                 'mn' => 'монгол', # Halh Mongolian (Cyrillic) (ISO 639-3: khk)
 290                 'mo' => 'молдовеняскэ', # Moldovan, deprecated
 291                 'mr' => 'मराठी', # Marathi
 292                 'mrj' => 'кырык мары', # Hill Mari
 293                 'ms' => 'Bahasa Melayu', # Malay
 294                 'mt' => 'Malti', # Maltese
 295                 'mus' => 'Mvskoke', # Muskogee/Creek
 296                 'mwl' => 'Mirandés', # Mirandese
 297                 'my' => 'မြန်မာဘာသာ', # Burmese
 298                 'myv' => 'эрзянь', # Erzya
 299                 'mzn' => 'مازِرونی', # Mazanderani
 300                 'na' => 'Dorerin Naoero', # Nauruan
 301                 'nah' => 'Nāhuatl', # Nahuatl (not in ISO 639-3)
 302                 'nan' => 'Bân-lâm-gú', # Min-nan, bug 8217
 303                 'nap' => 'Napulitano', # Neapolitan, bug 43793
 304                 'nb' => 'norsk bokmål', # Norwegian (Bokmal)
 305                 'nds' => 'Plattdüütsch', # Low German ''or'' Low Saxon
 306                 'nds-nl' => 'Nedersaksies', # aka Nedersaksisch: Dutch Low Saxon
 307                 'ne' => 'नेपाली', # Nepali
 308                 'new' => 'नेपाल भाषा', # Newar / Nepal Bhasha
 309                 'ng' => 'Oshiwambo', # Ndonga
 310                 'niu' => 'Niuē', # Niuean
 311                 'nl' => 'Nederlands', # Dutch
 312                 'nl-informal' => "Nederlands (informeel)\xE2\x80\x8E", # Dutch (informal address ("je"))
 313                 'nn' => 'norsk nynorsk', # Norwegian (Nynorsk)
 314                 'no' => 'norsk bokmål', # Norwegian (falls back to nb).
 315                 'nov' => 'Novial', # Novial
 316                 'nrm' => 'Nouormand', # Norman
 317                 'nso' => 'Sesotho sa Leboa', # Northern Sotho
 318                 'nv' => 'Diné bizaad', # Navajo
 319                 'ny' => 'Chi-Chewa', # Chichewa
 320                 'oc' => 'occitan', # Occitan
 321                 'olo' => 'Livvinkarjala', # Livvi-Karelian
 322                 'om' => 'Oromoo', # Oromo
 323                 'or' => 'ଓଡ଼ିଆ', # Oriya
 324                 'os' => 'Ирон', # Ossetic, bug 29091
 325                 'pa' => 'ਪੰਜਾਬੀ', # Eastern Punjabi (Gurmukhi script) (pan)
 326                 'pag' => 'Pangasinan', # Pangasinan
 327                 'pam' => 'Kapampangan', # Pampanga
 328                 'pap' => 'Papiamentu', # Papiamentu
 329                 'pcd' => 'Picard', # Picard
 330                 'pdc' => 'Deitsch', # Pennsylvania German
 331                 'pdt' => 'Plautdietsch', # Plautdietsch/Mennonite Low German
 332                 'pfl' => 'Pälzisch', # Palatinate German
 333                 'pi' => 'पालि', # Pali
 334                 'pih' => 'Norfuk / Pitkern', # Norfuk/Pitcairn/Norfolk
 335                 'pl' => 'polski', # Polish
 336                 'pms' => 'Piemontèis', # Piedmontese
 337                 'pnb' => 'پنجابی', # Western Punjabi
 338                 'pnt' => 'Ποντιακά', # Pontic/Pontic Greek
 339                 'prg' => 'Prūsiskan', # Prussian
 340                 'ps' => 'پښتو', # Pashto
 341                 'pt' => 'português', # Portuguese
 342                 'pt-br' => 'português do Brasil', # Brazilian Portuguese
 343                 'qu' => 'Runa Simi', # Southern Quechua
 344                 'qug' => 'Runa shimi', # Kichwa/Northern Quechua (temporarily used until Kichwa has its own)
 345                 'rgn' => 'Rumagnôl', # Romagnol
 346                 'rif' => 'Tarifit', # Tarifit
 347                 'rm' => 'rumantsch', # Raeto-Romance
 348                 'rmy' => 'Romani', # Vlax Romany
 349                 'rn' => 'Kirundi', # Rundi/Kirundi/Urundi
 350                 'ro' => 'română', # Romanian
 351                 'roa-rup' => 'armãneashti', # Aromanian (deprecated code, 'rup' exists in ISO 693-3)
 352                 'roa-tara' => 'tarandíne', # Tarantino
 353                 'ru' => 'русский', # Russian
 354                 'rue' => 'русиньскый', # Rusyn
 355                 'rup' => 'armãneashti', # Aromanian
 356                 'ruq' => 'Vlăheşte', # Megleno-Romanian (multiple scripts - defaults to Latin)
 357                 'ruq-cyrl' => 'Влахесте', # Megleno-Romanian (Cyrillic script)
 358                 # 'ruq-grek' => 'Βλαεστε', # Megleno-Romanian (Greek script)
 359                 'ruq-latn' => 'Vlăheşte', # Megleno-Romanian (Latin script)
 360                 'rw' => 'Kinyarwanda', # Kinyarwanda, should possibly be Kinyarwandi
 361                 'sa' => 'संस्कृतम्', # Sanskrit
 362                 'sah' => 'саха тыла', # Sakha
 363                 'sat' => 'Santali', # Santali
 364                 'sc' => 'sardu', # Sardinian
 365                 'scn' => 'sicilianu', # Sicilian
 366                 'sco' => 'Scots', # Scots
 367                 'sd' => 'سنڌي', # Sindhi
 368                 'sdc' => 'Sassaresu', # Sassarese
 369                 'sdh' => 'کوردی خوارگ', # Southern Kurdish
 370                 'se' => 'sámegiella', # Northern Sami
 371                 'sei' => 'Cmique Itom', # Seri
 372                 'ses' => 'Koyraboro Senni', # Koyraboro Senni
 373                 'sg' => 'Sängö', # Sango/Sangho
 374                 'sgs' => 'žemaitėška', # Samogitian
 375                 'sh' => 'srpskohrvatski / српскохрватски', # Serbocroatian
 376                 'shi' => 'Tašlḥiyt/ⵜⴰⵛⵍⵃⵉⵜ', # Tachelhit (multiple scripts - defaults to Latin)
 377                 'shi-tfng' => 'ⵜⴰⵛⵍⵃⵉⵜ', # Tachelhit (Tifinagh script)
 378                 'shi-latn' => 'Tašlḥiyt', # Tachelhit (Latin script)
 379                 'shn' => 'ၽႃႇသႃႇတႆး ', # Shan
 380                 'si' => 'සිංහල', # Sinhalese
 381                 'simple' => 'Simple English', # Simple English
 382                 'sk' => 'slovenčina', # Slovak
 383                 'sl' => 'slovenščina', # Slovenian
 384                 'sli' => 'Schläsch', # Lower Selisian
 385                 'sm' => 'Gagana Samoa', # Samoan
 386                 'sma' => 'Åarjelsaemien', # Southern Sami
 387                 'sn' => 'chiShona', # Shona
 388                 'so' => 'Soomaaliga', # Somali
 389                 'sq' => 'shqip', # Albanian
 390                 'sr' => 'српски / srpski', # Serbian (multiple scripts - defaults to Cyrillic)
 391                 'sr-ec' => "српски (ћирилица)\xE2\x80\x8E", # Serbian Cyrillic ekavian
 392                 'sr-el' => "srpski (latinica)\xE2\x80\x8E", # Serbian Latin ekavian
 393                 'srn' => 'Sranantongo', # Sranan Tongo
 394                 'ss' => 'SiSwati', # Swati
 395                 'st' => 'Sesotho', # Southern Sotho
 396                 'stq' => 'Seeltersk', # Saterland Frisian
 397                 'su' => 'Basa Sunda', # Sundanese
 398                 'sv' => 'svenska', # Swedish
 399                 'sw' => 'Kiswahili', # Swahili
 400                 'szl' => 'ślůnski', # Silesian
 401                 'ta' => 'தமிழ்', # Tamil
 402                 'tcy' => 'ತುಳು', # Tulu
 403                 'te' => 'తెలుగు', # Telugu
 404                 'tet' => 'tetun', # Tetun
 405                 'tg' => 'тоҷикӣ', # Tajiki (falls back to tg-cyrl)
 406                 'tg-cyrl' => 'тоҷикӣ', # Tajiki (Cyrllic script) (default)
 407                 'tg-latn' => 'tojikī', # Tajiki (Latin script)
 408                 'th' => 'ไทย', # Thai
 409                 'ti' => 'ትግርኛ', # Tigrinya
 410                 'tk' => 'Türkmençe', # Turkmen
 411                 'tl' => 'Tagalog', # Tagalog
 412                 'tly' => 'толышә зывон', # Talysh
 413                 'tn' => 'Setswana', # Setswana
 414                 'to' => 'lea faka-Tonga', # Tonga (Tonga Islands)
 415                 'tokipona' => 'Toki Pona', # Toki Pona
 416                 'tpi' => 'Tok Pisin', # Tok Pisin
 417                 'tr' => 'Türkçe', # Turkish
 418                 'tru' => 'Ṫuroyo', # Turoyo
 419                 'ts' => 'Xitsonga', # Tsonga
 420                 'tt' => 'татарча/tatarça', # Tatar (multiple scripts - defaults to Cyrillic)
 421                 'tt-cyrl' => 'татарча', # Tatar (Cyrillic script) (default)
 422                 'tt-latn' => 'tatarça', # Tatar (Latin script)
 423                 'tum' => 'chiTumbuka', # Tumbuka
 424                 'tw' => 'Twi', # Twi, (FIXME!)
 425                 'ty' => 'reo tahiti', # Tahitian
 426                 'tyv' => 'тыва дыл', # Tyvan
 427                 'tzm' => 'ⵜⴰⵎⴰⵣⵉⵖⵜ', # Tamazight
 428                 'udm' => 'удмурт', # Udmurt
 429                 'ug' => 'ئۇيغۇرچە / Uyghurche', # Uyghur (multiple scripts - defaults to Arabic)
 430                 'ug-arab' => 'ئۇيغۇرچە', # Uyghur (Arabic script) (default)
 431                 'ug-latn' => 'Uyghurche', # Uyghur (Latin script)
 432                 'uk' => 'українська', # Ukrainian
 433                 'ur' => 'اردو', # Urdu
 434                 'uz' => 'oʻzbekcha/ўзбекча', # Uzbek (multiple scripts - defaults to Latin)
 435                 'uz-cyrl' => 'ўзбекча', # Uzbek Cyrillic
 436                 'uz-latn' => 'oʻzbekcha', # Uzbek Latin (default)
 437                 've' => 'Tshivenda', # Venda
 438                 'vec' => 'vèneto', # Venetian
 439                 'vep' => 'vepsän kel’', # Veps
 440                 'vi' => 'Tiếng Việt', # Vietnamese
 441                 'vls' => 'West-Vlams', # West Flemish
 442                 'vmf' => 'Mainfränkisch', # Upper Franconian, Main-Franconian
 443                 'vo' => 'Volapük', # Volapük
 444                 'vot' => 'Vaďďa', # Vod/Votian
 445                 'vro' => 'Võro', # Võro
 446                 'wa' => 'walon', # Walloon
 447                 'war' => 'Winaray', # Waray-Waray
 448                 'wo' => 'Wolof', # Wolof
 449                 'wuu' => '吴语', # Wu Chinese
 450                 'xal' => 'хальмг', # Kalmyk-Oirat
 451                 'xh' => 'isiXhosa', # Xhosan
 452                 'xmf' => 'მარგალური', # Mingrelian
 453                 'yi' => 'ייִדיש', # Yiddish
 454                 'yo' => 'Yorùbá', # Yoruba
 455                 'yue' => '粵語', # Cantonese
 456                 'za' => 'Vahcuengh', # Zhuang
 457                 'zea' => 'Zeêuws', # Zeeuws/Zeaws
 458                 'zh' => '中文', # (Zhōng Wén) - Chinese
 459                 'zh-classical' => '文言', # Classical Chinese/Literary Chinese -- (see bug 8217)
 460                 'zh-cn' => "中文（中国大陆）\xE2\x80\x8E", # Chinese (PRC)
 461                 'zh-hans' => "中文（简体）\xE2\x80\x8E", # Mandarin Chinese (Simplified Chinese script) (cmn-hans)
 462                 'zh-hant' => "中文（繁體）\xE2\x80\x8E", # Mandarin Chinese (Traditional Chinese script) (cmn-hant)
 463                 'zh-hk' => "中文（香港）\xE2\x80\x8E", # Chinese (Hong Kong)
 464                 'zh-min-nan' => 'Bân-lâm-gú', # Min-nan -- (see bug 8217)
 465                 'zh-mo' => "中文（澳門）\xE2\x80\x8E", # Chinese (Macau)
 466                 'zh-my' => "中文（马来西亚）\xE2\x80\x8E", # Chinese (Malaysia)
 467                 'zh-sg' => "中文（新加坡）\xE2\x80\x8E", # Chinese (Singapore)
 468                 'zh-tw' => "中文（台灣）\xE2\x80\x8E", # Chinese (Taiwan)
 469                 'zh-yue' => '粵語', # Cantonese -- (see bug 8217)
 470                 'zu' => 'isiZulu' # Zulu
 471         ];
 472 }