languages/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 /**
  25  * These determine things like interwikis, language selectors, and so on.
  26  * Safe to change without running scripts on the respective sites.
  27  *
  28  * \xE2\x80\x8E is the left-to-right marker and
  29  * \xE2\x80\x8F is the right-to-left marker.
  30  * They are required for ensuring the correct display of brackets in
  31  * mixed rtl/ltr environment.
  32  *
  33  * Some writing systems require some line-height fixes. This includes
  34  * most Indic scripts, like Devanagari.
  35  * If you are adding support for such a language, add it also to
  36  * the relevant section in skins/common/shared.css.
  37  *
  38  * @ingroup Language
  39  */
  40 /* private */ $coreLanguageNames = array(
  41         'aa' => 'Qafár af',    # Afar
  42         'ab' => 'Аҧсшәа', # Abkhaz
  43         'ace' => 'Acèh',       # Aceh
  44         'af' => 'Afrikaans',    # Afrikaans
  45         'ak' => 'Akan',         # Akan
  46         'aln' => 'Gegë',       # Gheg Albanian
  47         'als' => 'Alemannisch', # Alemannic -- not a valid code, for compatibility. See gsw.
  48         'am' => 'አማርኛ', # Amharic
  49         'an' => 'aragonés',    # Aragonese
  50         'ang' => 'Ænglisc',    # Old English (Bug 23283)
  51         'anp' => 'अङ्गिका',       # Angika
  52         'ar' => 'العربية',       # Arabic
  53         'arc' => 'ܐܪܡܝܐ',  # Aramaic
  54         'arn' => 'mapudungun',  # Mapuche, Mapudungu, Araucanian (Araucano)
  55         'ary' => 'Maġribi',    # Moroccan Spoken Arabic
  56         'arz' => 'مصرى',    # Egyptian Spoken Arabic
  57         'as' => 'অসমীয়া',        # Assamese
  58         'ast' => 'asturianu',   # Asturian
  59         'av' => 'авар',     # Avar
  60         'avk' => 'Kotava', # Kotava
  61         'ay' => 'Aymar aru',    # Aymara
  62         'az' => 'azərbaycanca',        # Azerbaijani
  63         'azb' => 'تورکجه',        # South Azerbaijani
  64         'ba' => 'башҡортса',   # Bashkir
  65         'bar' => 'Boarisch',    # Bavarian (Austro-Bavarian and South Tyrolean)
  66         'bat-smg' => 'žemaitėška', # Samogitian (deprecated code, 'sgs' in ISO 693-3 since 2010-06-30 )
  67         'bbc' => 'Batak Toba', # Batak Toba (falls back to bbc-latn)
  68         'bbc-latn' => 'Batak Toba', # Batak Toba
  69         'bcc' => 'بلوچی مکرانی', # Southern Balochi
  70         'bcl' => 'Bikol Central', # Bikol: Central Bicolano language
  71         'be' => 'беларуская', #  Belarusian normative
  72         'be-tarask' => "беларуская (тарашкевіца)\xE2\x80\x8E",     # Belarusian in Taraskievica orthography
  73         'be-x-old' => "беларуская (тарашкевіца)\xE2\x80\x8E",      # Belarusian in Taraskievica orthography; compat link
  74         'bg' => 'български',   # Bulgarian
  75         'bh' => 'भोजपुरी',        # Bihari macro language. Falls back to Bhojpuri (bho). The name actually says "Bhojpuri".
  76         'bho' => 'भोजपुरी',       # Bhojpuri
  77         'bi' => 'Bislama',              # Bislama
  78         'bjn' => 'Bahasa Banjar',       # Banjarese
  79         'bm' => 'bamanankan',   # Bambara
  80         'bn' => 'বাংলা',      # Bengali
  81         'bo' => 'བོད་ཡིག',        # Tibetan
  82         'bpy' => 'বিষ্ণুপ্রিয়া মণিপুরী',       # Bishnupriya Manipuri
  83         'bqi' => 'بختياري',      # Bakthiari
  84         'br' => 'brezhoneg',    # Breton
  85         'brh' => 'Bráhuí',    # Brahui
  86         'bs' => 'bosanski',             # Bosnian
  87         'bug' => 'ᨅᨔ ᨕᨘᨁᨗ', # Buginese
  88         'bxr' => 'буряад',        # Buryat (Russia)
  89         'ca' => 'català',      # Catalan
  90         'cbk-zam' => 'Chavacano de Zamboanga',  # Zamboanga Chavacano
  91         'cdo' => 'Mìng-dĕ̤ng-ngṳ̄',       # Min Dong
  92         'ce' => 'нохчийн',       # Chechen
  93         'ceb' => 'Cebuano',     # Cebuano
  94         'ch' => 'Chamoru',              # Chamorro
  95         'cho' => 'Choctaw',             # Choctaw
  96         'chr' => 'ᏣᎳᎩ', # Cherokee
  97         'chy' => 'Tsetsêhestâhese',   # Cheyenne
  98         'ckb' => 'کوردی',  # Sorani. The name actually says "Kurdi" (Kurdish).
  99         'co' => 'corsu',                # Corsican
 100         'cps' => 'Capiceño', # Capiznon
 101         'cr' => 'Nēhiyawēwin / ᓀᐦᐃᔭᐍᐏᐣ',                # Cree
 102         'crh' => 'qırımtatarca',   # Crimean Tatar (multiple scripts - defaults to Latin)
 103         'crh-latn' => "qırımtatarca (Latin)\xE2\x80\x8E",       # Crimean Tatar (Latin)
 104         'crh-cyrl' => "къырымтатарджа (Кирилл)\xE2\x80\x8E",       # Crimean Tatar (Cyrillic)
 105         'cs' => 'česky',       # Czech
 106         'csb' => 'kaszëbsczi', # Cassubian
 107         'cu' => 'словѣ́ньскъ / ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ',      # Old Church Slavonic (ancient language)
 108         'cv' => 'Чӑвашла',       # Chuvash
 109         'cy' => 'Cymraeg',              # Welsh
 110         'da' => 'dansk',                # Danish
 111         'de' => 'Deutsch',              # German ("Du")
 112         'de-at' => 'Österreichisches Deutsch',         # Austrian German
 113         'de-ch' => 'Schweizer Hochdeutsch',             # Swiss Standard German
 114         'de-formal' => "Deutsch (Sie-Form)\xE2\x80\x8E",                # German - formal address ("Sie")
 115         'diq' => 'Zazaki',              # Zazaki
 116         'dsb' => 'dolnoserbski', # Lower Sorbian
 117         'dtp' => 'Dusun Bundu-liwan', # Central Dusun
 118         'dv' => 'ދިވެހިބަސް',         # Dhivehi
 119         'dz' => 'ཇོང་ཁ',              # Dzongkha (Bhutan)
 120         'ee' => 'eʋegbe',      # Éwé
 121         'egl' => 'Emiliàn',    # Emilian
 122         'el' => 'Ελληνικά',     # Greek
 123         'eml' => 'emiliàn e rumagnòl',        # Emiliano-Romagnolo / Sammarinese
 124         'en' => 'English',              # English
 125         'en-ca' => 'Canadian English',  # Canadian English
 126         'en-gb' => 'British English',   # British English
 127         'eo' => 'Esperanto',    # Esperanto
 128         'es' => 'español',     # Spanish
 129         'et' => 'eesti',                # Estonian
 130         'eu' => 'euskara',              # Basque
 131         'ext' => 'estremeñu', # Extremaduran
 132         'fa' => 'فارسی',   # Persian
 133         'ff' => 'Fulfulde',             # Fulfulde, Maasina
 134         'fi' => 'suomi',                # Finnish
 135         'fit' => 'meänkieli', # Tornedalen Finnish
 136         'fiu-vro' => 'Võro',    # Võro (deprecated code, 'vro' in ISO 639-3 since 2009-01-16)
 137         'fj' => 'Na Vosa Vakaviti',     # Fijian
 138         'fo' => 'føroyskt',    # Faroese
 139         'fr' => 'français',    # French
 140         'frc' => 'français cadien', # Cajun French
 141         'frp' => 'arpetan',     # Franco-Provençal/Arpitan
 142         'frr' => 'Nordfriisk',  # North Frisian
 143         'fur' => 'furlan',              # Friulian
 144         'fy' => 'Frysk',                # Frisian
 145         'ga' => 'Gaeilge',              # Irish
 146         'gag' => 'Gagauz',              # Gagauz
 147         'gan' => '贛語',              # Gan (multiple scripts - defaults to Traditional)
 148         'gan-hans' => "赣语（简体）\xE2\x80\x8E", # Gan (Simplified Han)
 149         'gan-hant' => "贛語（繁體）\xE2\x80\x8E", # Gan (Traditional Han)
 150         'gd' => 'Gàidhlig',    # Scots Gaelic
 151         'gl' => 'galego',               # Galician
 152         'glk' => 'گیلکی',  # Gilaki
 153         'gn' => 'Avañe\'ẽ',  # Guaraní, Paraguayan
 154         'got' => '𐌲𐌿𐍄𐌹𐍃𐌺',    # Gothic
 155         'grc' => 'Ἀρχαία ἑλληνικὴ', # Ancient Greek
 156         'gsw' => 'Alemannisch', # Alemannic
 157         'gu' => 'ગુજરાતી',        # Gujarati
 158         'gv' => 'Gaelg',                # Manx
 159         'ha' => 'Hausa',        # Hausa
 160         'hak' => 'Hak-kâ-fa',  # Hakka
 161         'haw' => 'Hawai`i',             # Hawaiian
 162         'he' => 'עברית',   # Hebrew
 163         'hi' => 'हिन्दी',   # Hindi
 164         'hif' => 'Fiji Hindi',  # Fijian Hindi (multiple scripts - defaults to Latin)
 165         'hif-latn' => 'Fiji Hindi',     # Fiji Hindi (latin)
 166         'hil' => 'Ilonggo',     # Hiligaynon
 167         'ho' => 'Hiri Motu',    # Hiri Motu
 168         'hr' => 'hrvatski',             # Croatian
 169         'hsb' => 'hornjoserbsce',       # Upper Sorbian
 170         'ht' => 'Kreyòl ayisyen',              # Haitian Creole French
 171         'hu' => 'magyar',               # Hungarian
 172         'hy' => 'Հայերեն',       # Armenian
 173         'hz' => 'Otsiherero',   # Herero
 174         'ia' => 'interlingua',  # Interlingua (IALA)
 175         'id' => 'Bahasa Indonesia',     # Indonesian
 176         'ie' => 'Interlingue',  # Interlingue (Occidental)
 177         'ig' => 'Igbo',                 # Igbo
 178         'ii' => 'ꆇꉙ',       # Sichuan Yi
 179         'ik' => 'Iñupiak',     # Inupiak (Inupiatun, Northwest Alaska / Inupiatun, North Alaskan)
 180         'ike-cans' => 'ᐃᓄᒃᑎᑐᑦ',     # Inuktitut, Eastern Canadian/Eastern Canadian "Eskimo"/"Eastern Arctic Eskimo"/Inuit (Unified Canadian Aboriginal Syllabics)
 181         'ike-latn' => 'inuktitut',      # Inuktitut, Eastern Canadian (Latin script)
 182         'ilo' => 'Ilokano',     # Ilokano
 183         'inh' => 'ГӀалгӀай',    # Ingush
 184         'io' => 'Ido',                  # Ido
 185         'is' => 'íslenska',    # Icelandic
 186         'it' => 'italiano',             # Italian
 187         'iu' => 'ᐃᓄᒃᑎᑐᑦ/inuktitut', # Inuktitut (macro language - do no localise, see ike/ikt - falls back to ike-cans)
 188         'ja' => '日本語',    # Japanese
 189         'jam' => 'Patois',      # Jamaican Creole English
 190         'jbo' => 'Lojban',              # Lojban
 191         'jut' => 'jysk',        # Jutish / Jutlandic
 192         'jv' => 'Basa Jawa',    # Javanese
 193         'ka' => 'ქართული',        # Georgian
 194         'kaa' => 'Qaraqalpaqsha',       # Karakalpak
 195         'kab' => 'Taqbaylit',   # Kabyle
 196         'kbd' => 'Адыгэбзэ',    # Kabardian
 197         'kbd-cyrl' => 'Адыгэбзэ',       # Kabardian (Cyrillic)
 198         'kg' => 'Kongo',        # Kongo, (FIXME!) should probaly be KiKongo or KiKoongo
 199         'khw' => 'کھوار',  # Khowar
 200         'ki' => 'Gĩkũyũ',    # Gikuyu
 201         'kiu' => 'Kırmancki',  # Kirmanjki
 202         'kj' => 'Kwanyama',     # Kwanyama
 203         'kk' => 'қазақша',       # Kazakh (multiple scripts - defaults to Cyrillic)
 204         'kk-arab' => "قازاقشا (تٴوتە)\xE2\x80\x8F", # Kazakh Arabic
 205         'kk-cyrl' => "қазақша (кирил)\xE2\x80\x8E", # Kazakh Cyrillic
 206         'kk-latn' => "qazaqşa (latın)\xE2\x80\x8E",   # Kazakh Latin
 207         'kk-cn' => "قازاقشا (جۇنگو)\xE2\x80\x8F",   # Kazakh (China)
 208         'kk-kz' => "қазақша (Қазақстан)\xE2\x80\x8E",   # Kazakh (Kazakhstan)
 209         'kk-tr' => "qazaqşa (Türkïya)\xE2\x80\x8E",  # Kazakh (Turkey)
 210         'kl' => 'kalaallisut',  # Inuktitut, Greenlandic/Greenlandic/Kalaallisut (kal)
 211         'km' => 'ភាសាខ្មែរ',  # Khmer, Central
 212         'kn' => 'ಕನ್ನಡ',      # Kannada
 213         'ko' => '한국어',    # Korean
 214         'ko-kp' => '한국어 (조선)',        # Korean (DPRK)
 215         'koi' => 'Перем Коми', # Komi-Permyak
 216         'kr' => 'Kanuri',               # Kanuri, Central
 217         'krc' => 'къарачай-малкъар', # Karachay-Balkar
 218         'kri' => 'Krio', # Krio
 219         'krj' => 'Kinaray-a', # Kinaray-a
 220         'ks' => 'कॉशुर / کٲشُر', # Kashmiri (multiple scripts - defaults to Perso-Arabic)
 221         'ks-arab' => 'کٲشُر',      # Kashmiri (Perso-Arabic script)
 222         'ks-deva' => 'कॉशुर', # Kashmiri (Devanagari script)
 223         'ksh' => 'Ripoarisch',  # Ripuarian
 224         'ku' => 'Kurdî',       # Kurdish (multiple scripts - defaults to Latin)
 225         'ku-latn' => "Kurdî (latînî)\xE2\x80\x8E",   # Northern Kurdish (Latin script)
 226         'ku-arab' => "كوردي (عەرەبی)\xE2\x80\x8F",   # Northern Kurdish (Arabic script) (falls back to ckb)
 227         'kv' => 'коми',     # Komi-Zyrian (Cyrillic is common script but also written in Latin script)
 228         'kw' => 'kernowek',             # Cornish
 229         'ky' => 'Кыргызча',     # Kirghiz
 230         'la' => 'Latina',               # Latin
 231         'lad' => 'Ladino',      # Ladino
 232         'lb' => 'Lëtzebuergesch',      # Luxemburguish
 233         'lbe' => 'лакку',  # Lak
 234         'lez' => 'лезги',  # Lezgi
 235         'lfn' => 'Lingua Franca Nova',  # Lingua Franca Nova
 236         'lg' => 'Luganda',              # Ganda
 237         'li' => 'Limburgs',     # Limburgian
 238         'lij' => 'Ligure',      # Ligurian
 239         'liv' => 'Līvõ kēļ',        # Livonian
 240         'lmo' => 'lumbaart',    # Lombard
 241         'ln' => 'lingála',             # Lingala
 242         'lo' => 'ລາວ',    # Laotian
 243         'loz' => 'Silozi', # Lozi
 244         'lt' => 'lietuvių',    # Lithuanian
 245         'ltg' => 'latgaļu',    # Latgalian
 246         'lus' => 'Mizo ţawng', # Mizo/Lushai
 247         'lv' => 'latviešu',    # Latvian
 248         'lzh' => '文言',      # Literary Chinese -- (bug 8217) lzh instead of zh-classical, http://www.sil.org/iso639-3/codes.asp?order=639_3&letter=l
 249         'lzz' => 'Lazuri',      # Laz
 250         'mai' => 'मैथिली', # Maithili
 251         'map-bms' => 'Basa Banyumasan', # Banyumasan
 252         'mdf' => 'мокшень',              # Moksha
 253         'mg' => 'Malagasy',             # Malagasy
 254         'mh' => 'Ebon',                 # Marshallese
 255         'mhr' => 'олык марий', # Eastern Mari
 256         'mi' => 'Māori',       # Maori
 257         'min' => 'Baso Minangkabau',    # Minangkabau
 258         'mk' => 'македонски', # Macedonian
 259         'ml' => 'മലയാളം',   # Malayalam
 260         'mn' => 'монгол', # Halh Mongolian (Cyrillic) (ISO 639-3: khk)
 261         'mo' => 'молдовеняскэ',     # Moldovan, deprecated
 262         'mr' => 'मराठी',      # Marathi
 263         'mrj' => 'кырык мары', # Hill Mari
 264         'ms' => 'Bahasa Melayu',        # Malay
 265         'mt' => 'Malti',        # Maltese
 266         'mus' => 'Mvskoke',     # Muskogee/Creek
 267         'mwl' => 'Mirandés',   # Mirandese
 268         'my' => 'မြန်မာဘာသာ',               # Burmese
 269         'myv' => 'эрзянь',        # Erzya
 270         'mzn' => 'مازِرونی',            # Mazanderani
 271         'na' => 'Dorerin Naoero',               # Nauruan
 272         'nah' => 'Nāhuatl',            # Nahuatl, en:Wikipedia writes Nahuatlahtolli, while another form is Náhuatl
 273         'nan' => 'Bân-lâm-gú', # Min-nan -- (bug 8217) nan instead of zh-min-nan, http://www.sil.org/iso639-3/codes.asp?order=639_3&letter=n
 274         'nap' => 'Nnapulitano', # Neapolitan
 275         'nb' => "norsk bokmål",                # Norwegian (Bokmal)
 276         'nds' => 'Plattdüütsch',      # Low German ''or'' Low Saxon
 277         'nds-nl' => 'Nedersaksies',     # aka Nedersaksisch: Dutch Low Saxon
 278         'ne' => 'नेपाली',   # Nepali
 279         'new' => 'नेपाल भाषा',                # Newar / Nepal Bhasha
 280         'ng' => 'Oshiwambo',            # Ndonga
 281         'niu' => 'Niuē',       # Niuean
 282         'nl' => 'Nederlands',   # Dutch
 283         'nl-informal' => "Nederlands (informeel)\xE2\x80\x8E",  # Dutch (informal address ("je"))
 284         'nn' => "norsk nynorsk",        # Norwegian (Nynorsk)
 285         'no' => "norsk bokmål",                # Norwegian (falls back to nb).
 286         'nov' => 'Novial',              # Novial
 287         'nrm' => 'Nouormand',   # Norman
 288         'nso' => 'Sesotho sa Leboa',    # Northern Sotho
 289         'nv' => 'Diné bizaad', # Navajo
 290         'ny' => 'Chi-Chewa',    # Chichewa
 291         'oc' => 'occitan',              # Occitan
 292         'om' => 'Oromoo',               # Oromo
 293         'or' => 'ଓଡ଼ିଆ',              # Oriya
 294         'os' => 'Ирон', # Ossetic -- fixed per bug 29091
 295         'pa' => 'ਪੰਜਾਬੀ', # Eastern Punjabi (Gurmukhi script) (pan)
 296         'pag' => 'Pangasinan',  # Pangasinan
 297         'pam' => 'Kapampangan',   # Pampanga
 298         'pap' => 'Papiamentu',  # Papiamentu
 299         'pcd' => 'Picard',      # Picard
 300         'pdc' => 'Deitsch',     # Pennsylvania German
 301         'pdt' => 'Plautdietsch',        # Plautdietsch/Mennonite Low German
 302         'pfl' => 'Pälzisch',   # Palatinate German
 303         'pi' => 'पालि', # Pali
 304         'pih' => 'Norfuk / Pitkern', # Norfuk/Pitcairn/Norfolk
 305         'pl' => 'polski',               # Polish
 306         'pms' => 'Piemontèis', # Piedmontese
 307         'pnb' => 'پنجابی',        # Western Punjabi
 308         'pnt' => 'Ποντιακά',    # Pontic/Pontic Greek
 309         'prg' => 'Prūsiskan',  # Prussian
 310         'ps' => 'پښتو',     # Pashto, Northern/Paktu/Pakhtu/Pakhtoo/Afghan/Pakhto/Pashtu/Pushto/Yusufzai Pashto
 311         'pt' => 'português',   # Portuguese
 312         'pt-br' => 'português do Brasil',      # Brazilian Portuguese
 313         'qu' => 'Runa Simi',    # Southern Quechua
 314         'qug' => 'Runa shimi',  # Kichwa/Northern Quechua (one of the codes it covers; temporarily used until Kichwa has its own)
 315         'rgn' => 'Rumagnôl',   # Romagnol
 316         'rif' => 'Tarifit',     # Tarifit
 317         'rm' => 'rumantsch',    # Raeto-Romance
 318         'rmy' => 'Romani',      # Vlax Romany
 319         'rn' => 'Kirundi',              # Rundi/Kirundi/Urundi
 320         'ro' => 'română',     # Romanian
 321         'roa-rup' => 'Armãneashce', # Aromanian (deprecated code, 'rup' exists in ISO 693-3)
 322         'roa-tara' => 'tarandíne',     # Tarantino
 323         'ru' => 'русский',       # Russian
 324         'rue' => 'русиньскый',        # Rusyn
 325         'rup' => 'Armãneashce', # Aromanian
 326         'ruq' => 'Vlăheşte',  # Megleno-Romanian (multiple scripts - defaults to Latin)
 327         'ruq-cyrl' => 'Влахесте',       # Megleno-Romanian (Cyrillic script)
 328         # 'ruq-grek' => 'Βλαεστε',       # Megleno-Romanian (Greek script)
 329         'ruq-latn' => 'Vlăheşte',     # Megleno-Romanian (Latin script)
 330         'rw' => 'Kinyarwanda',  # Kinyarwanda, should possibly be Kinyarwandi
 331         'sa' => 'संस्कृतम्',  # Sanskrit
 332         'sah' => 'саха тыла', # Sakha
 333         'sat' => 'Santali',     # Santali
 334         'sc' => 'sardu',                # Sardinian
 335         'scn' => 'sicilianu',   # Sicilian
 336         'sco' => 'Scots',       # Scots
 337         'sd' => 'سنڌي',     # Sindhi
 338         'sdc' => 'Sassaresu',   # Sassarese
 339         'se' => 'sámegiella',  # Northern Sami
 340         'sei' => 'Cmique Itom', # Seri
 341         'sg' => 'Sängö',              # Sango/Sangho
 342         'sgs' => 'žemaitėška', # Samogitian
 343         'sh' => 'srpskohrvatski / српскохрватски', # Serbocroatian
 344         'shi' => 'Tašlḥiyt/ⵜⴰⵛⵍⵃⵉⵜ',    # Tachelhit (multiple scripts - defaults to Latin)
 345         'shi-tfng' => 'ⵜⴰⵛⵍⵃⵉⵜ',    # Tachelhit (Tifinagh script)
 346         'shi-latn' => 'Tašlḥiyt',    # Tachelhit (Latin script)
 347         'si' => 'සිංහල',      # Sinhalese
 348         'simple' => 'Simple English',   # Simple English
 349         'sk' => 'slovenčina',  # Slovak
 350         'sl' => 'slovenščina',        # Slovenian
 351         'sli' => 'Schläsch',   # Lower Selisian
 352         'sm' => 'Gagana Samoa', # Samoan
 353         'sma' => 'Åarjelsaemien',      # Southern Sami
 354         'sn' => 'chiShona',             # Shona
 355         'so' => 'Soomaaliga',   # Somali
 356         'sq' => 'shqip',                # Albanian
 357         'sr' => 'српски / srpski',        # Serbian (multiple scripts - defaults to Cyrillic)
 358         'sr-ec' => "српски (ћирилица)\xE2\x80\x8E",       # Serbian Cyrillic ekavian
 359         'sr-el' => "srpski (latinica)\xE2\x80\x8E",     # Serbian Latin ekavian
 360         'srn' => 'Sranantongo',         # Sranan Tongo
 361         'ss' => 'SiSwati',              # Swati
 362         'st' => 'Sesotho',              # Southern Sotho
 363         'stq' => 'Seeltersk',           # Saterland Frisian
 364         'su' => 'Basa Sunda',   # Sundanese
 365         'sv' => 'svenska',              # Swedish
 366         'sw' => 'Kiswahili',    # Swahili
 367         'szl' => 'ślůnski',   # Silesian
 368         'ta' => 'தமிழ்',      # Tamil
 369         'tcy' => 'ತುಳು', # Tulu
 370         'te' => 'తెలుగు',   # Telugu
 371         'tet' => 'tetun',       # Tetun
 372         'tg' => 'тоҷикӣ', # Tajiki (falls back to tg-cyrl)
 373         'tg-cyrl' => 'тоҷикӣ',    # Tajiki (Cyrllic script) (default)
 374         'tg-latn' => 'tojikī', # Tajiki (Latin script)
 375         'th' => 'ไทย',    # Thai
 376         'ti' => 'ትግርኛ',         # Tigrinya
 377         'tk' => 'Türkmençe',  # Turkmen
 378         'tl' => 'Tagalog',              # Tagalog
 379         'tly' => 'толышә зывон',     # Talysh
 380         'tn' => 'Setswana',             # Setswana
 381         'to' => 'lea faka-Tonga',               # Tonga (Tonga Islands)
 382         'tokipona' => 'Toki Pona',      # Toki Pona
 383         'tpi' => 'Tok Pisin',   # Tok Pisin
 384         'tr' => 'Türkçe',     # Turkish
 385         'tru' => 'Ṫuroyo', # Turoyo
 386         'ts' => 'Xitsonga',             # Tsonga
 387         'tt' => 'татарча/tatarça',      # Tatar (multiple scripts - defaults to Cyrillic)
 388         'tt-cyrl' => 'татарча',  # Tatar (Cyrillic script) (default)
 389         'tt-latn' => 'tatarça',        # Tatar (Latin script)
 390         'tum' => 'chiTumbuka',  # Tumbuka
 391         'tw' => 'Twi',                  # Twi, (FIXME!)
 392         'ty' => 'Reo Mā`ohi',  # Tahitian
 393         'tyv' => 'тыва дыл',     # Tyvan
 394         'udm' => 'удмурт',        # Udmurt
 395         'ug' => 'ئۇيغۇرچە / Uyghurche', # Uyghur (multiple scripts - defaults to Arabic)
 396         'ug-arab' => 'ئۇيغۇرچە', # Uyghur (Arabic script) (default)
 397         'ug-latn' => 'Uyghurche', # Uyghur (Latin script)
 398         'uk' => 'українська', # Ukrainian
 399         'ur' => 'اردو',     # Urdu
 400         'uz' => 'oʻzbekcha',   # Uzbek
 401         've' => 'Tshivenda',            # Venda
 402         'vec' => 'vèneto',     # Venetian
 403         'vep' => 'vepsän kel’',      # Veps
 404         'vi' => 'Tiếng Việt',       # Vietnamese
 405         'vls' => 'West-Vlams', # West Flemish
 406         'vmf' => 'Mainfränkisch', # Upper Franconian, Main-Franconian
 407         'vo' => 'Volapük',     # Volapük
 408         'vot' => 'Vaďďa',     # Vod/Votian
 409         'vro' => 'Võro',    # Võro
 410         'wa' => 'walon',                # Walloon
 411         'war' => 'Winaray', # Waray-Waray
 412         'wo' => 'Wolof',                # Wolof
 413         'wuu' => '吴语',              # Wu Chinese
 414         'xal' => 'хальмг',                # Kalmyk-Oirat (Kalmuk, Kalmuck, Kalmack, Qalmaq, Kalmytskii Jazyk, Khal:mag, Oirat, Volga Oirat, European Oirat, Western Mongolian)
 415         'xh' => 'isiXhosa',             # Xhosan
 416         'xmf' => 'მარგალური', # Mingrelian
 417         'yi' => 'ייִדיש', # Yiddish
 418         'yo' => 'Yorùbá',     # Yoruba
 419         'yue' => '粵語',      # Cantonese -- (bug 8217) yue instead of zh-yue, http://www.sil.org/iso639-3/codes.asp?order=639_3&letter=y
 420         'za' => 'Vahcuengh',    # Zhuang
 421         'zea' => 'Zeêuws',     # Zeeuws/Zeaws
 422         'zh' => '中文',                                               # (Zhōng Wén) - Chinese
 423         'zh-classical' => '文言',                     # Classical Chinese/Literary Chinese -- (see bug 8217)
 424         'zh-cn' => "中文（中国大陆）\xE2\x80\x8E",      # Chinese (PRC)
 425         'zh-hans' => "中文（简体）\xE2\x80\x8E",  # Mandarin Chinese (Simplified Chinese script) (cmn-hans)
 426         'zh-hant' => "中文（繁體）\xE2\x80\x8E",  # Mandarin Chinese (Traditional Chinese script) (cmn-hant)
 427         'zh-hk' => "中文（香港）\xE2\x80\x8E",    # Chinese (Hong Kong)
 428         'zh-min-nan' => 'Bân-lâm-gú',                                # Min-nan -- (see bug 8217)
 429         'zh-mo' => "中文（澳門）\xE2\x80\x8E",    # Chinese (Macau)
 430         'zh-my' => "中文（马来西亚）\xE2\x80\x8E",      # Chinese (Malaysia)
 431         'zh-sg' => "中文（新加坡）\xE2\x80\x8E", # Chinese (Singapore)
 432         'zh-tw' => "中文（台灣）\xE2\x80\x8E",    # Chinese (Taiwan)
 433         'zh-yue' => '粵語',                                   # Cantonese -- (see bug 8217)
 434         'zu' => 'isiZulu'               # Zulu
 435 );