local u = mw.ustring.char
-- UTF-8 encoded strings for some commonly-used diacritics
local GRAVE = u(0x0300)
local ACUTE = u(0x0301)
local CIRC = u(0x0302)
local TILDE = u(0x0303)
local MACRON = u(0x0304)
local BREVE = u(0x0306)
local DOTABOVE = u(0x0307)
local DIAER = u(0x0308)
local CARON = u(0x030C)
local DGRAVE = u(0x030F)
local INVBREVE = u(0x0311)
local DOTBELOW = u(0x0323)
local RINGBELOW = u(0x0325)
local CEDILLA = u(0x0327)
local OGONEK = u(0x0328)
-- Puncuation to be used for standardChars field
local PUNCTUATION = ' \!\#\$\%\&\*\+\,\-\.\/\:\;\<\=\>\?\@\^\_\`\|\~\'\(\)'
local m = {}
m["aa"] = {
canonicalName = "Afar",
otherNames = {"Qafar"},
scripts = {"Latn"},
family = "cus",
}
m["ab"] = {
canonicalName = "Abkhaz",
otherNames = {"Abkhazian", "Abxazo"},
scripts = {"Cyrl", "Geor", "Latn"},
family = "cau-abz",
translit_module = "ab-translit",
override_translit = true,
entry_name = {
from = {GRAVE, ACUTE},
to = {}} ,
}
m["ae"] = {
canonicalName = "Avestan",
otherNames = {"Zend", "Old Bactrian"},
scripts = {"Avst", "Gujr"},
family = "ira-eas",
translit_module = "Avst-translit",
}
m["af"] = {
canonicalName = "Afrikaans",
scripts = {"Latn", "Arab"},
family = "gmw",
ancestors = {"nl"},
sort_key = {
from = {"[äáâà]", "[ëéêè]", "[ïíîì]", "[öóôò]", "[üúûù]", "[ÿýŷỳ]", "^-", "'"},
to = {"a" , "e" , "i" , "o" , "u" , "y" }} ,
}
m["ak"] = {
canonicalName = "Akan",
otherNames = {"Twi-Fante", "Twi", "Fante", "Fanti", "Asante", "Akuapem"},
scripts = {"Latn"},
family = "alv-kwa",
}
m["am"] = {
canonicalName = "Amharic",
scripts = {"Ethi"},
family = "sem-eth",
translit_module = "Ethi-translit",
}
m["an"] = {
canonicalName = "Aragonese",
scripts = {"Latn"},
family = "roa",
ancestors = {"roa-oan"},
}
m["ar"] = {
canonicalName = "Arabic",
otherNames = {"Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic"},
scripts = {"Arab", "Brai"},
family = "sem-arb",
-- alif waṣl to alif, remove diacritics
entry_name = {
from = {u(0x0671), u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652), u(0x0670), u(0x0640)},
to = {u(0x0627)}},
translit_module = "ar-translit",
}
m["as"] = {
canonicalName = "Assamese",
scripts = {"Beng"},
family = "inc",
ancestors = {"inc-mgd"},
}
m["av"] = {
canonicalName = "Avar",
otherNames = {"Avaric"},
scripts = {"Cyrl"},
family = "cau-nec",
ancestors = {"oav"},
translit_module = "av-translit",
override_translit = true,
entry_name = {
from = {GRAVE, ACUTE},
to = {}} ,
}
m["ay"] = {
canonicalName = "Aymara",
otherNames = {"Southern Aymara", "Central Aymara"},
scripts = {"Latn"},
family = "sai-aym",
}
m["az"] = {
canonicalName = "Azeri",
otherNames = {"Azerbaijani", "Azari", "Azeri Turkic", "Azerbaijani Turkic", "North Azerbaijani", "South Azerbaijani", "Afshar", "Afshari", "Afshar Azerbaijani", "Afchar", "Qashqa'i", "Qashqai", "Kashkay", "Sonqor"},
scripts = {"Latn", "Cyrl", "fa-Arab"},
family = "trk-ogz",
}
m["ba"] = {
canonicalName = "Bashkir",
scripts = {"Cyrl"},
family = "trk-kip",
translit_module = "ba-translit",
override_translit = true,
}
m["be"] = {
canonicalName = "Belaroushie",
otherNames = {"Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"},
scripts = {"Cyrl"},
family = "zle",
translit_module = "be-translit",
sort_key = {
from = {"Ё", "ё"},
to = {"Е" , "е"}},
entry_name = {
from = {"Ѐ", "ѐ", GRAVE, ACUTE},
to = {"Е", "е"}},
}
m["bg"] = {
canonicalName = "Bulgarie",
scripts = {"Cyrl"},
family = "zls",
translit_module = "bg-translit",
entry_name = {
from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE},
to = {"Е", "е", "И", "и"}},
}
m["bh"] = {
canonicalName = "Bihari",
scripts = {"Deva"},
family = "inc",
ancestors = {"inc-mgd"},
}
m["bi"] = {
canonicalName = "Bislama",
scripts = {"Latn"},
family = "crp",
ancestors = {"en"},
}
m["bm"] = {
canonicalName = "Bambara",
otherNames = {"Bamanankan"},
scripts = {"Latn"},
family = "dmn",
}
m["bn"] = {
canonicalName = "Bengali",
otherNames = {"Bangla"},
scripts = {"Beng"},
family = "inc",
ancestors = {"inc-mgd"},
translit_module = "bn-translit",
}
m["bo"] = {
canonicalName = "Tibetan",
otherNames = {"Ü", "Dbus", "Lhasa", "Lhasa Tibetan", "Amdo Tibetan", "Amdo", "Panang", "Khams", "Khams Tibetan", "Khamba", "Tseku", "Dolpo", "Humla", "Limi", "Lhomi", "Shing Saapa", "Mugom", "Mugu", "Nubri", "Walungge", "Gola", "Thudam", "Lowa", "Loke", "Mustang", "Tichurong"},
scripts = {"Tibt"},
family = "tbq",
ancestors = {"xct"},
translit_module = "bo-translit",
override_translit = true,
}
m["br"] = {
canonicalName = "Breton",
scripts = {"Latn"},
family = "cel-bry",
ancestors = {"xbm"},
}
m["ca"] = {
canonicalName = "Catalan",
otherNames = {"Valencian"},
scripts = {"Latn"},
family = "roa",
ancestors = {"roa-oca"},
sort_key = {
from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"},
to = {"a", "e" , "i" , "o" , "u" , "c", "ll" }} ,
}
m["ce"] = {
canonicalName = "Chechen",
scripts = {"Cyrl"},
family = "cau-nkh",
translit_module = "ce-translit",
override_translit = true,
entry_name = {
from = {MACRON},
to = {}},
}
m["ch"] = {
canonicalName = "Chamorro",
otherNames = {"Chamoru"},
scripts = {"Latn"},
family = "poz-sus",
}
m["co"] = {
canonicalName = "Corsican",
otherNames = {"Corsu"},
scripts = {"Latn"},
family = "roa",
}
m["cr"] = {
canonicalName = "Cree",
scripts = {"Cans", "Latn"},
family = "alg",
translit_module = "cr-translit",
}
m["cs"] = {
canonicalName = "Czech",
scripts = {"Latn"},
family = "zlw",
ancestors = {"zlw-ocs"},
sort_key = {
from = {"á", "é", "í", "ó", "[úů]", "ý"},
to = {"a", "e", "i", "o", "u" , "y"}} ,
}
m["cu"] = {
canonicalName = "Auld Kirk Slavonic",
otherNames = {"Auld Kirk Slavic"},
scripts = {"Cyrs", "Glag"},
family = "zls",
translit_module = "Cyrs-Glag-translit",
entry_name = {
from = {u(0x0484)}, -- kamora
to = {}},
sort_key = {
from = {"оу", "є"},
to = {"у" , "е"}} ,
}
m["cv"] = {
canonicalName = "Chuvash",
scripts = {"Cyrl"},
family = "trk-ogr",
translit_module = "cv-translit",
override_translit = true,
}
m["cy"] = {
canonicalName = "Welsh",
scripts = {"Latn"},
family = "cel-bry",
ancestors = {"wlm"},
sort_key = {
from = {"[âáàä]", "[êéèë]", "[îíìï]", "[ôóòö]", "[ûúùü]", "[ŵẃẁẅ]", "[ŷýỳÿ]", "'"},
to = {"a" , "e" , "i" , "o" , "u" , "w" , "y" }} ,
}
m["da"] = {
canonicalName = "Dens",
scripts = {"Latn"},
family = "gmq",
ancestors = {"gmq-oda"},
}
m["de"] = {
canonicalName = "German",
otherNames = {"High German", "New High German", "Deutsch"},
scripts = {"Latn", "Latf"},
family = "gmw",
ancestors = {"gmh"},
sort_key = {
from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" },
to = {"a" , "e" , "i" , "o" , "u" , "ss"}} ,
}
m["dv"] = {
canonicalName = "Dhivehi",
otherNames = {"Divehi", "Mahal", "Mahl", "Maldivian"},
scripts = {"Thaa"},
family = "inc",
ancestors = {"pmh"},
translit_module = "dv-translit",
override_translit = true,
}
m["dz"] = {
canonicalName = "Dzongkha",
scripts = {"Tibt"},
family = "tbq",
ancestors = {"xct"},
translit_module = "bo-translit",
override_translit = true,
}
m["ee"] = {
canonicalName = "Ewe",
scripts = {"Latn"},
family = "alv-von",
}
m["el"] = {
canonicalName = "Greek",
otherNames = {"Modern Greek", "Neo-Hellenic"},
scripts = {"Grek", "Brai"},
family = "grk",
ancestors = {"grc"},
translit_module = "el-translit",
override_translit = true,
sort_key = { -- Keep this synchronized with grc, cpg, pnt
from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧ]", "ῥ", "ς"},
to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}} ,
}
m["en"] = {
canonicalName = "Inglis",
otherNames = {"Modren Inglis", "New Inglis", "Hawaiian Creole Inglis", "Hawai'ian Creole Inglis", "Hawaiian Creole", "Hawai'ian Creole", "Polari", "Yinglish"}, -- all but the first three are names of subsumed dialects which once had codes
scripts = {"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion
family = "gmw",
ancestors = {"enm"},
sort_key = {
from = {"[äàáâåā]", "[ëèéêē]", "[ïìíîī]", "[öòóôō]", "[üùúûū]", "æ" , "œ" , "[çč]", "ñ", "'"},
to = {"a" , "e" , "i" , "o" , "u" , "ae", "oe", "c" , "n"}},
wikimedia_codes = {"en", "simple"},
standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF)
}
m["eo"] = {
canonicalName = "Esperanto",
scripts = {"Latn"},
family = "art",
sort_key = {
from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ĉ]", "[ĝ]", "[ĥ]", "[ĵ]", "[ŝ]", "[ŭ]"},
to = {"a" , "e" , "i" , "o" , "u", "cĉ", "gĉ", "hĉ", "jĉ", "sĉ", "uĉ"}} ,
}
m["es"] = {
canonicalName = "Spainish",
otherNames = {"Castilian", "Amazonian Spainish", "Amazonic Spainish", "Loreto-Ucayali Spainish", "Spainish"},
scripts = {"Latn", "Brai"},
family = "roa",
ancestors = {"osp"},
sort_key = {
from = {"á", "é", "í", "ó", "[úü]", "ç", "ñ"},
to = {"a", "e", "i", "o", "u" , "c", "n"}},
standardChars = "A-VXYZa-vxyz0-9ÁáÉéÍíÓóÚúÑñ¿¡" .. PUNCTUATION
}
m["et"] = {
canonicalName = "Estonie",
scripts = {"Latn"},
family = "fiu-fin",
}
m["eu"] = {
canonicalName = "Basque",
otherNames = {"Euskara"},
scripts = {"Latn"},
family = "euq",
}
m["fa"] = {
canonicalName = "Persie",
otherNames = {"Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari", "Aimaq", "Aimak", "Aymaq", "Eimak"},
scripts = {"fa-Arab"},
family = "ira-wes",
ancestors = {"pal"}, -- "ira-mid"
entry_name = {
from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)},
to = {}} ,
}
m["ff"] = {
canonicalName = "Fula",
otherNames = {"Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulani", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code
scripts = {"Latn"},
family = "alv-sng",
}
m["fi"] = {
canonicalName = "Finnish",
otherNames = {"Suomi", "Botnian"},
scripts = {"Latn"},
family = "fiu-fin",
entry_name = {
from = {"ˣ"}, -- Used to indicate gemination of the next consonant
to = {}},
sort_key = {
from = {"[áàâã]", "[éèêẽ]", "[íìîĩ]", "[óòôõ]", "[úùûũ]", "[ýỳŷüű]", "[øõő]", "æ" , "œ" , "[čç]", "š", "ž", "ß" , "[':]"},
to = {"a" , "e" , "i" , "o" , "u" , "y" , "ö" , "ae", "oe", "c" , "s", "z", "ss"}} ,
}
m["fj"] = {
canonicalName = "Fijian",
scripts = {"Latn"},
family = "poz-occ",
}
m["fo"] = {
canonicalName = "Faroese",
scripts = {"Latn"},
family = "gmq",
ancestors = {"non"},
}
m["fr"] = {
canonicalName = "French",
otherNames = {"Modren French"},
scripts = {"Latn", "Brai"},
family = "roa-oil",
ancestors = {"frm"},
sort_key = {
from = {"[áàâä]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "æ" , "œ" , "'"},
to = {"a" , "e" , "i" , "o" , "u" , "y" , "c", "ae", "oe"}},
standardChars = "A-Za-z0-9ÀÂÇÉÈÊËÎÏÔŒÛÙÜàâçéèêëîïôœûùü«»" .. PUNCTUATION
}
m["fy"] = {
canonicalName = "Wast Frisian",
otherNames = {"Wastren Frisian", "Frisian"},
scripts = {"Latn"},
family = "gmw-fri",
ancestors = {"ofs"},
}
m["ga"] = {
canonicalName = "Erse",
otherNames = {"Erse Gaelic"},
scripts = {"Latn"},
family = "cel-gae",
ancestors = {"mga"},
sort_key = {
from = {"á", "é", "í", "ó", "ú", "ý", "ḃ" , "ċ" , "ḋ" , "ḟ" , "ġ" , "ṁ" , "ṗ" , "ṡ" , "ṫ" },
to = {"a", "e", "i", "o", "u", "y", "bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}} ,
}
m["gd"] = {
canonicalName = "Scots Gaelic",
otherNames = {"Gàidhlig", "Hieland Gaelic", "Scots Gaelic"},
scripts = {"Latn"},
family = "cel-gae",
ancestors = {"mga"},
sort_key = {
from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"},
to = {"a" , "e" , "i" , "o" , "u" , "y" }} ,
}
m["gl"] = {
canonicalName = "Galician",
scripts = {"Latn"},
family = "roa",
ancestors = {"roa-opt"},
sort_key = {
from = {"á", "é", "í", "ó", "ú"},
to = {"a", "e", "i", "o", "u"}} ,
}
m["gn"] = {
canonicalName = "Guaraní",
scripts = {"Latn"},
family = "tup-gua",
}
m["gu"] = {
canonicalName = "Gujarati",
scripts = {"Gujr"},
family = "inc",
ancestors = {"inc-ogu"},
translit_module = "gu-translit",
}
m["gv"] = {
canonicalName = "Manx",
otherNames = {"Manx Gaelic"},
scripts = {"Latn"},
family = "cel-gae",
ancestors = {"mga"},
sort_key = {
from = {"ç", "-"},
to = {"c"}} ,
}
m["ha"] = {
canonicalName = "Hausa",
scripts = {"Latn", "Arab"},
family = "cdc-wst",
}
m["he"] = {
canonicalName = "Ebreu",
otherNames = {"Ivrit"},
scripts = {"Hebr", "Phnx", "Brai"},
family = "sem-can",
entry_name = {
from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"},
to = {}} ,
}
m["hi"] = {
canonicalName = "Hindi",
otherNames = {"Braj", "Brij Bhasha", "Braj Bhasha", "Braj Bhāshā", "Braj Bhakha", "Dehaati Zabaan"},
scripts = {"Deva", "Guru"}, -- Guru for the subsumed variety Braj
family = "inc",
ancestors = {"inc-ohi"},
translit_module = "hi-translit",
}
m["ho"] = {
canonicalName = "Hiri Motu",
otherNames = {"Pidgin Motu", "Police Motu"},
scripts = {"Latn"},
family = "crp",
ancestors = {"meu"},
}
m["ht"] = {
canonicalName = "Haitian Creole",
otherNames = {"Creole", "Haitian", "Kreyòl"},
scripts = {"Latn"},
family = "crp",
}
m["hu"] = {
canonicalName = "Hungarian",
otherNames = {"Magyar"},
scripts = {"Latn", "Hung"},
family = "urj-ugr",
ancestors = {"ohu"},
sort_key = {
from = {"á", "é", "í", "ó", "ú", "ő", "ű"},
to = {"a", "e", "i", "o", "u", "ö", "ü"}} ,
}
m["hy"] = {
canonicalName = "Armenian",
otherNames = {"Modern Armenian", "Eastern Armenian", "Western Armenian"},
scripts = {"Armn", "Brai"},
family = "hyx",
ancestors = {"axm"},
translit_module = "Armn-translit",
override_translit = true,
sort_key = {
from = {"ու", "և", "եւ"},
to = {"ւ", "եվ", "եվ"}},
entry_name = {
from = {"՞", "՜", "՛", "՟", "և", "<sup>յ</sup>", "<sup>ի</sup>"},
to = {"", "", "", "", "եւ", "յ", "ի"}} ,
}
m["hz"] = {
canonicalName = "Herero",
scripts = {"Latn"},
family = "bnt",
}
m["ia"] = {
canonicalName = "Interlingua",
scripts = {"Latn"},
family = "art",
}
m["id"] = {
canonicalName = "Indonesian",
scripts = {"Latn"},
family = "poz-mly",
ancestors = {"ms"},
}
m["ie"] = {
canonicalName = "Interlingue",
otherNames = {"Occidental"},
scripts = {"Latn"},
family = "art",
}
m["ig"] = {
canonicalName = "Igbo",
scripts = {"Latn"},
family = "nic-bco",
}
m["ii"] = {
canonicalName = "Sichuan Yi",
otherNames = {"Nuosu", "Nosu", "Northern Yi", "Liangshan Yi"},
scripts = {"Yiii"},
family = "tbq-lol",
}
m["ik"] = {
canonicalName = "Inupiak",
otherNames = {"Inupiaq", "Iñupiaq", "Inupiatun"},
scripts = {"Latn"},
family = "esx-inu",
}
m["io"] = {
canonicalName = "Ido",
scripts = {"Latn"},
family = "art",
}
m["is"] = {
canonicalName = "Icelandic",
scripts = {"Latn"},
family = "gmq",
ancestors = {"non"},
}
m["it"] = {
canonicalName = "Italian",
scripts = {"Latn"},
family = "roa",
sort_key = {
from = {"[àáâäå]", "[èéêë]", "[ìíîï]", "[òóôö]", "[ùúûü]"},
to = {"a" , "e" , "i" , "o" , "u" }} ,
}
m["iu"] = {
canonicalName = "Inuktitut",
otherNames = {"Eastern Canadian Inuktitut", "Eastern Canadian Inuit", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun", "Inuinnaq", "Inuinnaqtun", "Inuvialuk", "Inuvialuktun", "Nunavimmiutit", "Nunatsiavummiut", "Aivilimmiut", "Natsilingmiut", "Kivallirmiut", "Siglit", "Siglitun"},
scripts = {"Cans", "Latn"},
family = "esx-inu",
translit_module = "iu-translit",
override_translit = true,
}
m["ja"] = {
canonicalName = "Japanese",
otherNames = {"Modern Japanese", "Nipponese", "Nihongo"},
scripts = {"Jpan", "Latn", "Hira", "Brai"},
family = "jpx",
ancestors = {"ojp"},
--[[
sort_key = {
from = {"[ぁァア]", "[ぃィイ]", "[ぅゔゥウヴ]", "[ぇェエ]", "[ぉォオ]", "[がゕカガヵ]", "[ぎキギ]", "[ぐクグㇰ]", "[げゖケゲヶ]", "[ごコゴ]", "[ざサザ]", "[じシジㇱ]", "[ずスズㇲ]", "[ぜセゼ]", "[ぞソゾ]", "[だタダ]", "[ぢチヂ]", "[っづッツヅ]", "[でテデ]", "[どトドㇳ]", "ナ", "ニ", "[ヌㇴ]", "ネ", "ノ", "[ばぱハバパㇵ]", "[びぴヒビピㇶ]", "[ぶぷフブプㇷ]", "[べぺヘベペㇸ]", "[ぼぽホボポㇹ]", "マ", "ミ", "[ムㇺ]", "メ", "モ", "[ゃャヤ]", "[ゅュユ]", "[ょョヨ]", "[ラㇻ]", "[リㇼ]", "[ルㇽ]", "[レㇾ]", "[ロㇿ]", "[ゎヮワヷ]", "[ヰヸ]", "[ヱヹ]", "[ヲヺ]", "ン", "[゙゚゛゜ゝゞ・ヽヾ]", "𛀀"},
to = {"あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ", "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の", "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "ゐ", "ゑ", "を", "ん", "", "え"}},
]]
}
m["jv"] = {
canonicalName = "Javanese",
scripts = {"Latn", "Java"},
family = "poz-sus",
translit_module = "jv-translit",
ancestors = {"kaw"},
link_tr = true,
}
m["ka"] = {
canonicalName = "Georgian",
otherNames = {"Kartvelian", "Judeo-Georgian", "Kivruli", "Gruzinic"},
scripts = {"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian
family = "ccs-gzn",
ancestors = {"oge"},
translit_module = "Geor-translit",
override_translit = true,
entry_name = {
from = {"̂"},
to = {""}},
}
m["kg"] = {
canonicalName = "Kongo",
otherNames = {"Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"},
scripts = {"Latn"},
family = "bnt",
}
m["ki"] = {
canonicalName = "Kikuyu",
otherNames = {"Gikuyu", "Gĩkũyũ"},
scripts = {"Latn"},
family = "bnt",
}
m["kj"] = {
canonicalName = "Kwanyama",
otherNames = {"Kuanyama", "Oshikwanyama"},
scripts = {"Latn"},
family = "bnt",
}
m["kk"] = {
canonicalName = "Kazakh",
scripts = {"Cyrl", "Latn", "Arab", "kk-Arab"},
family = "trk-kip",
translit_module = "kk-translit",
override_translit = true,
}
m["kl"] = {
canonicalName = "Greenlandic",
otherNames = {"Kalaallisut"},
scripts = {"Latn"},
family = "esx-inu",
}
m["km"] = {
canonicalName = "Khmer",
otherNames = {"Cambodian"},
scripts = {"Khmr"},
family = "mkh",
ancestors = {"mkh-mkm"},
translit_module = "km-translit",
}
m["kn"] = {
canonicalName = "Kannada",
scripts = {"Knda"},
family = "dra",
translit_module = "kn-translit",
}
m["ko"] = {
canonicalName = "Korean",
otherNames = {"Modern Korean"},
scripts = {"Kore", "Brai"},
family = "qfa-kor",
ancestors = {"okm"},
translit_module = "ko-translit",
}
m["kr"] = {
canonicalName = "Kanuri",
otherNames = {"Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"},
scripts = {"Latn"},
family = "ssa-sah",
}
m["ks"] = {
canonicalName = "Kashmiri",
scripts = {"ks-Arab", "Deva"},
family = "inc-dar",
}
m["ku"] = {
canonicalName = "Kurdish",
scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"},
family = "ira-wes",
}
-- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT
m["kw"] = {
canonicalName = "Cornish",
scripts = {"Latn"},
family = "cel-bry",
ancestors = {"cnx"},
}
m["ky"] = {
canonicalName = "Kyrgyz",
otherNames = {"Kirghiz", "Kirgiz"},
scripts = {"Cyrl", "Latn", "Arab"},
family = "trk-kip",
translit_module = "ky-translit",
override_translit = true,
}
m["la"] = {
canonicalName = "Laitin",
scripts = {"Latn"},
family = "itc",
ancestors = {"itc-ola"},
entry_name = {
from = {"[ĀĂ]", "[āă]", "[ĒĔ]", "[ēĕë]", "[ĪĬÏ]", "[īĭï]", "[ŌŎ]", "[ōŏ]", "[ŪŬÜ]", "[ūŭü]", "Ȳ", "ȳ", MACRON, BREVE, DIAER},
to = {"A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "Y", "y"}},
}
m["lb"] = {
canonicalName = "Luxembourgish",
scripts = {"Latn"},
family = "gmw",
ancestors = {"gmh"},
}
m["lg"] = {
canonicalName = "Luganda",
otherNames = {"Ganda", "Oluganda"},
scripts = {"Latn"},
family = "bnt",
entry_name = {
from = {"á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ", "â", "Â", "ê", "Ê", "î", "Î", "ô", "Ô", "û", "Û" },
to = {"a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U",}},
sort_key = {
from = {"ŋ"},
to = {"n"}}
}
m["li"] = {
canonicalName = "Limburgish",
otherNames = {"Limburgan", "Limburgian", "Limburgic"},
scripts = {"Latn"},
family = "gmw",
ancestors = {"dum"},
}
m["ln"] = {
canonicalName = "Lingala",
otherNames = {"Ngala"},
scripts = {"Latn"},
family = "bnt",
}
m["lo"] = {
canonicalName = "Lao",
otherNames = {"Laotian"},
scripts = {"Laoo"},
family = "tai-swe",
translit_module = "lo-translit",
sort_key = {
from = {"ຼ", "ຽ", "ໜ", "ໝ", "([ເແໂໃໄ])([ກ-ຮ])"},
to = {"ລ", "ຍ", "ຫນ", "ຫມ", "%2%1"}},
}
m["lt"] = {
canonicalName = "Lithuanian",
scripts = {"Latn"},
family = "bat",
ancestors = {"olt"},
entry_name = {
from = {"[áãà]", "[ÁÃÀ]", "[éẽè]", "[ÉẼÈ]", "[íĩì]", "[ÍĨÌ]", "[ýỹ]", "[ÝỸ]", "ñ", "[óõò]", "[ÓÕÒ]", "[úũù]", "[ÚŨÙ]", ACUTE, GRAVE, TILDE},
to = {"a", "A", "e", "E", "i", "I", "y", "Y", "n", "o", "O", "u", "U"}} ,
}
m["lu"] = {
canonicalName = "Luba-Katanga",
scripts = {"Latn"},
family = "bnt",
}
m["lv"] = {
canonicalName = "Latvian",
otherNames = {"Lettish", "Lett"},
scripts = {"Latn"},
family = "bat",
entry_name = {
-- This attempts to convert vowels with tone marks to vowels either with
-- or without macrons. Specifically, there should be no macrons if the
-- vowel is part of a diphthong (including resonant diphthongs such
-- pìrksts -> pirksts not #pīrksts). What we do is first convert the
-- vowel + tone mark to a vowel + tilde in a decomposed fashion,
-- then remove the tilde in diphthongs, then convert the remaining
-- vowel + tilde sequences to macroned vowels, then delete any other
-- tilde. We leave already-macroned vowels alone: Both e.g. ar and ār
-- occur before consonants. FIXME: This still might not be sufficient.
from = {"Ȩ", "ȩ", "[ÂÃÀ]", "[âãà]", "[ÊẼÈ]", "[êẽè]", "[ÎĨÌ]", "[îĩì]", "[ÔÕÒ]", "[ôõò]", "[ÛŨÙ]", "[ûũù]", "[ÑǸ]", "[ñǹ]", "[" .. CIRC .. TILDE ..GRAVE .."]", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .. "?([^aAeEiIoOuUāĀēĒīĪūŪ])", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .."?$", "([iI])" .. TILDE .. "?([eE])" .. TILDE .. "?", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "U" .. TILDE, "u" .. TILDE, TILDE},
to = {"E", "e", "A" .. TILDE, "a" .. TILDE, "E" .. TILDE, "e" .. TILDE, "I" .. TILDE, "i" .. TILDE, "O", "o", "U" .. TILDE, "u" .. TILDE, "N", "n", TILDE, "%1%2%3", "%1%2", "%1%2", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ū", "ū", ""}},
}
m["mg"] = {
canonicalName = "Malagasy",
otherNames = {"Betsimisaraka Malagasy", "Betsimisaraka", "Northern Betsimisaraka Malagasy", "Northern Betsimisaraka", "Southern Betsimisaraka Malagasy", "Southern Betsimisaraka", "Bara Malagasy", "Bara", "Masikoro Malagasy", "Masikoro", "Antankarana", "Antankarana Malagasy", "Plateau Malagasy", "Sakalava", "Tandroy Malagasy", "Tandroy", "Tanosy", "Tanosy Malagasy", "Tesaka", "Tsimihety", "Tsimihety Malagasy", "Bushi", "Shibushi", "Kibushi", "Sakalava"},
scripts = {"Latn"},
family = "poz-bre",
}
m["mh"] = {
canonicalName = "Marshallese",
scripts = {"Latn"},
family = "poz-mic",
sort_key = {
from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄" , "o̧" , "ō" , "ū" },
to = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} ,
}
m["mi"] = {
canonicalName = "Maori",
otherNames = {"Māori"},
scripts = {"Latn"},
family = "poz-pol",
}
m["mk"] = {
canonicalName = "Macedonian",
scripts = {"Cyrl"},
family = "zls",
translit_module = "mk-translit",
entry_name = {
from = {ACUTE},
to = {}},
}
m["ml"] = {
canonicalName = "Malayalam",
scripts = {"Mlym"},
family = "dra",
translit_module = "ml-translit",
override_translit = true,
}
m["mn"] = {
canonicalName = "Mongolian",
otherNames = {"Khalkha Mongolian"},
scripts = {"Cyrl", "Mong", "Soyo", "Zanb"}, -- entries in Soyo or Zanb might require prior discussion
family = "xgn",
ancestors = {"cmg"},
translit_module = "mn-translit",
override_translit = true,
}
-- "mo" IS TREATED AS "ro", SEE WT:LT
m["mr"] = {
canonicalName = "Marathi",
scripts = {"Deva", "Modi"},
family = "inc",
ancestors = {"omr"},
translit_module = "hi-translit",
}
m["ms"] = {
canonicalName = "Malay",
otherNames = {"Malaysian", "Standard Malay", "Orang Seletar", "Orang Kanaq", "Jakun", "Temuan"},
scripts = {"Latn", "Arab"},
family = "poz-mly",
}
m["mt"] = {
canonicalName = "Maltese",
scripts = {"Latn"},
family = "sem-arb",
ancestors = {"sqr"},
}
m["my"] = {
canonicalName = "Burmese",
otherNames = {"Myanmar"},
scripts = {"Mymr"},
family = "tbq-brm",
ancestors = {"obr"},
translit_module = "my-translit",
override_translit = true,
}
m["na"] = {
canonicalName = "Nauruan",
otherNames = {"Nauru"},
scripts = {"Latn"},
family = "poz-mic",
}
m["nb"] = {
canonicalName = "Norse Bokmål",
otherNames = {"Bokmål"},
scripts = {"Latn"},
family = "gmq",
ancestors = {"gmq-mno"},
wikimedia_codes = {"no"},
}
m["nd"] = {
canonicalName = "Northren Ndebele",
otherNames = {"North Ndebele"},
scripts = {"Latn"},
family = "bnt-ngu",
entry_name = {
from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON},
to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }},
}
m["ne"] = {
canonicalName = "Nepali",
otherNames = {"Nepalese"},
scripts = {"Deva"},
family = "inc",
translit_module = "ne-translit",
}
m["ng"] = {
canonicalName = "Ndonga",
scripts = {"Latn"},
family = "bnt",
}
m["nl"] = {
canonicalName = "Dutch",
otherNames = {"Netherlandic", "Flemish"},
scripts = {"Latn"},
family = "gmw",
ancestors = {"dum"},
sort_key = {
from = {"[äáâå]", "[ëéê]", "[ïíî]", "[öóô]", "[üúû]", "ç", "ñ", "^-"},
to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} ,
standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF),
}
m["nn"] = {
canonicalName = "Norse Nynorsk",
otherNames = {"New Norse", "Nynorsk"},
scripts = {"Latn"},
family = "gmq",
ancestors = {"gmq-mno"},
}
m["no"] = {
canonicalName = "Norse",
scripts = {"Latn"},
family = "gmq",
ancestors = {"gmq-mno"},
}
m["nr"] = {
canonicalName = "Southern Ndebele",
otherNames = {"South Ndebele"},
scripts = {"Latn"},
family = "bnt-ngu",
entry_name = {
from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON},
to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }},
}
m["nv"] = {
canonicalName = "Navajo",
otherNames = {"Navaho", "Diné bizaad"},
scripts = {"nv-Latn"},
family = "apa",
sort_key = {
from = {"[áą]", "[éę]", "[íį]", "[óǫ]", "ń", "^n([djlt])", "ł" , "[ʼ’']", ACUTE},
to = {"a" , "e" , "i" , "o" , "n", "ni%1" , "l"}}, -- the copyright sign is used to guarantee that ł will always be sorted after all other words with l
}
m["ny"] = {
canonicalName = "Chichewa",
otherNames = {"Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"},
scripts = {"Latn"},
family = "bnt",
entry_name = {
from = {"ŵ", "Ŵ", "á", "Á", "é", "É", "í", "Í", "ó", "Ó", "ú", "Ú", "ń", "Ń", "ḿ", "Ḿ" },
to = {"w", "W", "a", "A", "e", "E", "i", "I", "o", "O", "u", "U", "n", "N", "m", "M"}},
sort_key = {
from = {"ng'"},
to = {"ng"}}
}
m["oc"] = {
canonicalName = "Occitan",
otherNames = {"Provençal", "Auvergnat", "Auvernhat", "Gascon", "Languedocien", "Lengadocian", "Shuadit", "Chouhadite", "Chouhadit", "Chouadite", "Chouadit", "Shuhadit", "Judeo-Provençal", "Judeo-Provencal", "Judeo-Comtadin"},
scripts = {"Latn", "Hebr"},
family = "roa",
ancestors = {"pro"},
sort_key = {
from = {"[àá]", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "([lns])·h"},
to = {"a" , "e" , "i" , "o" , "u" , "c", "%1h" }} ,
}
m["oj"] = {
canonicalName = "Ojibwe",
otherNames = {"Chippewa", "Ojibway", "Ojibwemowin", "Southwestern Ojibwa"},
scripts = {"Cans", "Latn"},
family = "alg",
}
m["om"] = {
canonicalName = "Oromo",
otherNames = {"Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"},
scripts = {"Latn", "Ethi"},
family = "cus",
}
m["or"] = {
canonicalName = "Oriya",
otherNames = {"Odia", "Oorya"},
scripts = {"Orya"},
family = "inc",
ancestors = {"inc-mgd"},
}
m["os"] = {
canonicalName = "Ossetian",
otherNames = {"Ossete", "Ossetic", "Digor", "Iron"},
scripts = {"Cyrl", "Geor", "Latn"},
family = "ira",
translit_module = "os-translit",
override_translit = true,
ancestors = {"oos"},
entry_name = {
from = {GRAVE, ACUTE},
to = {}} ,
}
m["pa"] = {
canonicalName = "Punjabi",
otherNames = {"Panjabi"},
scripts = {"Guru", "Arab", "Deva"},
family = "inc",
ancestors = {"psu"},
translit_module = "translit-redirect",
}
m["pi"] = {
canonicalName = "Pali",
scripts = {"Latn", "Deva", "Beng", "Sinh", "Mymr", "Thai", "Lana", "Khmr"}, -- holds Laoo, not enough glyphes to render
family = "inc",
ancestors = {"bh"},
sort_key = {
from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "[ṇñṅ]", "ṭ"},
to = {"a", "i", "u", "d", "l", "m" , "n" , "t"}} ,
}
m["pl"] = {
canonicalName = "Pols",
scripts = {"Latn"},
family = "zlw",
ancestors = {"zlw-opl"},
sort_key = {
from = {"[Ąą]", "[Ćć]", "[Ęę]", "[Łł]", "[Ńń]", "[Óó]", "[Śś]", "[Żż]", "[Źź]"},
to = {
"a" .. u(0x10FFFF),
"c" .. u(0x10FFFF),
"e" .. u(0x10FFFF),
"l" .. u(0x10FFFF),
"n" .. u(0x10FFFF),
"o" .. u(0x10FFFF),
"s" .. u(0x10FFFF),
"z" .. u(0x10FFFF),
"z" .. u(0x10FFFE)}} ,
}
m["ps"] = {
canonicalName = "Pashto",
otherNames = {"Pashtun", "Pushto", "Pashtu", "Central Pashto", "Northern Pashto", "Southern Pashto", "Pukhto", "Pakhto", "Pakkhto", "Afghani"},
scripts = {"ps-Arab"},
family = "ira-eas",
}
m["pt"] = {
canonicalName = "Portuguese",
otherNames = {"Modern Portuguese"},
scripts = {"Latn", "Brai"},
family = "roa",
ancestors = {"roa-opt"},
sort_key = {
from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"},
to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} ,
}
m["qu"] = {
canonicalName = "Quechua",
scripts = {"Latn"},
family = "qwe",
}
m["rm"] = {
canonicalName = "Romansch",
otherNames = {"Romansh", "Rumantsch", "Romanche"},
scripts = {"Latn"},
family = "roa",
}
m["ro"] = {
canonicalName = "Romanian",
otherNames = {"Daco-Romanian", "Roumanian", "Rumanian"},
scripts = {"Latn", "Cyrl"},
family = "roa",
sort_key = {
from = {"ă" , "â" , "î" , "ș" , "ț" },
to = {"a~", "a~~", "i~", "s~", "t~"}},
}
m["ru"] = {
canonicalName = "Russian",
scripts = {"Cyrl", "Brai"},
family = "zle",
translit_module = "ru-translit",
sort_key = {
from = {"ё"},
to = {"е" .. mw.ustring.char(0x10FFFF)}},
entry_name = {
from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE},
to = {"Е", "е", "И", "и"}},
standardChars = "ЁІА-яёі0-9—" .. PUNCTUATION,
}
m["rw"] = {
canonicalName = "Rwanda-Rundi",
otherNames = {"Rwanda", "Kinyarwanda", "Rundi", "Kirundi", "Ha", "Giha", "Hangaza", "Vinza", "Shubi", "Subi"},
scripts = {"Latn"},
family = "bnt",
}
m["sa"] = {
canonicalName = "Sanskrit",
scripts = {"Deva", "Beng", "Brah", "Gran", "Gujr", "Guru", "Khar", "Knda", "Mlym", "Mymr", "Orya", "Shrd", "Sinh", "Taml", "Telu", "Thai", "Tibt"},
family = "inc",
translit_module = "sa-translit",
}
m["sc"] = {
canonicalName = "Sardinian",
otherNames = {"Campidanese", "Campidanese Sardinian", "Logudorese", "Logudorese Sardinian", "Nuorese", "Nuorese Sardinian"},
scripts = {"Latn"},
family = "roa",
}
m["sd"] = {
canonicalName = "Sindhi",
scripts = {"sd-Arab", "Deva"},
family = "inc",
}
m["se"] = {
canonicalName = "Northern Sami",
otherNames = {"North Sami", "Northern Saami", "North Saami"},
scripts = {"Latn"},
family = "smi",
entry_name = {
from = {"([đflmnŋrsšŧv])'%1"},
to = {"%1%1"} },
}
m["sg"] = {
canonicalName = "Sango",
scripts = {"Latn"},
family = "crp",
}
m["sh"] = {
canonicalName = "Serbo-Croatian",
otherNames = {"BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"},
scripts = {"Latn", "Cyrl"},
family = "zls",
entry_name = {
from = {"[ȀÀȂÁĀÃ]", "[ȁàȃáāã]", "[ȄÈȆÉĒẼ]", "[ȅèȇéēẽ]", "[ȈÌȊÍĪĨ]", "[ȉìȋíīĩ]", "[ȌÒȎÓŌÕ]", "[ȍòȏóōõ]", "[ȐȒŔ]", "[ȑȓŕ]", "[ȔÙȖÚŪŨ]", "[ȕùȗúūũ]", "Ѐ", "ѐ", "[ӢЍ]", "[ӣѝ]", "[Ӯ]", "[ӯ]", GRAVE, ACUTE, DGRAVE, INVBREVE, MACRON, TILDE},
to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "Е", "е", "И" , "и", "У", "у" }},
wikimedia_codes = {"sh", "bs", "hr", "sr"},
}
m["si"] = {
canonicalName = "Sinhalese",
otherNames = {"Singhalese", "Sinhala"},
scripts = {"Sinh"},
family = "inc",
ancestors = {"pmh"},
translit_module = "si-translit",
override_translit = true,
}
m["sk"] = {
canonicalName = "Slovak",
scripts = {"Latn"},
family = "zlw",
sort_key = {
from = {"[áä]", "é", "í", "[óô]", "ú", "ý", "ŕ", "ĺ"},
to = {"a" , "e", "i", "o" , "u", "y", "r", "l"}} ,
}
m["sl"] = {
canonicalName = "Slovene",
otherNames = {"Slovenian"},
scripts = {"Latn"},
family = "zls",
entry_name = {
from = {"[ÁÀÂȂȀ]", "[áàâȃȁ]", "[ÉÈÊȆȄỆẸ]", "[éèêȇȅệẹə]", "[ÍÌÎȊȈ]", "[íìîȋȉ]", "[ÓÒÔȎȌỘỌ]", "[óòôȏȍộọ]", "[ŔȒȐ]", "[ŕȓȑ]", "[ÚÙÛȖȔ]", "[úùûȗȕ]", "ł", GRAVE, ACUTE, DGRAVE, INVBREVE, CIRC, DOTBELOW},
to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "R" , "r" , "U" , "u" , "l"}} ,
}
m["sm"] = {
canonicalName = "Samoan",
scripts = {"Latn"},
family = "poz-pol",
}
m["sn"] = {
canonicalName = "Shona",
scripts = {"Latn"},
family = "bnt",
}
m["so"] = {
canonicalName = "Somali",
scripts = {"Latn", "Arab", "Osma"},
family = "cus",
entry_name = {
from = {"[ÁÀÂ]", "[áàâ]", "[ÉÈÊ]", "[éèê]", "[ÍÌÎ]", "[íìî]", "[ÓÒÔ]", "[óòô]", "[ÚÙÛ]", "[úùû]", "[ÝỲ]", "[ýỳ]"},
to = {"A" , "a" , "E" , "e" , "I" , "i" , "O" , "o" , "U" , "u", "Y", "y"}} ,
}
m["sq"] = {
canonicalName = "Albanie",
scripts = {"Latn", "Elba"},
family = "sqj",
sort_key = {
from = { '[âãä]', '[ÂÃÄ]', '[êẽë]', '[ÊẼË]', 'ĩ', 'Ĩ', 'õ', 'Õ', 'ũ', 'Ũ', 'ỹ', 'Ỹ', 'ç', 'Ç' },
to = { 'a', 'A', 'e', 'E', 'i', 'I', 'o', 'O', 'u', 'U', 'y', 'Y', 'c', 'C' } } ,
}
m["ss"] = {
canonicalName = "Swazi",
otherNames = {"Swati"},
scripts = {"Latn"},
family = "bnt-ngu",
entry_name = {
from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON},
to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }},
}
m["st"] = {
canonicalName = "Sotho",
otherNames = {"Sesotho", "Southern Sesotho", "Southern Sotho"},
scripts = {"Latn"},
family = "bnt",
}
m["su"] = {
canonicalName = "Sundanese",
scripts = {"Latn", "Sund"},
family = "poz-msa",
translit_module = "su-translit",
}
m["sv"] = {
canonicalName = "Swadish",
scripts = {"Latn"},
family = "gmq",
ancestors = {"gmq-osw"},
}
m["sw"] = {
canonicalName = "Swahili",
otherNames = {"Settler Swahili", "KiSetla", "KiSettla", "Setla", "Settla", "Kitchen Swahili", "Kihindi", "Indian Swahili", "KiShamba", "Kishamba", "Field Swahili", "Kibabu", "Asian Swahili", "Kimanga", "Arab Swahili", "Kitvita", "Army Swahili"},
scripts = {"Latn", "Arab"},
family = "bnt",
sort_key = {
from = {"ng'", "^-"},
to = {"ngz"}} ,
}
m["ta"] = {
canonicalName = "Tamil",
scripts = {"Taml"},
family = "dra",
ancestors = {"oty"},
translit_module = "ta-translit",
override_translit = true,
}
m["te"] = {
canonicalName = "Telugu",
scripts = {"Telu"},
family = "dra",
translit_module = "te-translit",
override_translit = true,
}
m["tg"] = {
canonicalName = "Tajik",
otherNames = {"Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"},
scripts = {"Cyrl", "fa-Arab", "Latn"},
family = "ira-wes",
ancestors = {"fa"},
translit_module = "tg-translit",
override_translit = true,
sort_key = {
from = {"Ё", "ё"},
to = {"Е" , "е"}} ,
entry_name = {
from = {ACUTE},
to = {}} ,
}
m["th"] = {
canonicalName = "Thai",
scripts = {"Thai", "Brai"},
family = "tai-swe",
translit_module = "th-translit",
sort_key = {
from = {"%p", "([เแโใไ])([ก-ฮ])"},
to = {"", "%2%1"}},
}
m["ti"] = {
canonicalName = "Tigrinya",
scripts = {"Ethi"},
family = "sem-eth",
translit_module = "Ethi-translit",
}
m["tk"] = {
canonicalName = "Turkmen",
scripts = {"Latn", "Cyrl"},
family = "trk-ogz",
}
m["tl"] = {
canonicalName = "Tagalog",
scripts = {"Latn", "Tglg"},
family = "phi",
}
m["tn"] = {
canonicalName = "Tswana",
otherNames = {"Setswana"},
scripts = {"Latn"},
family = "bnt",
}
m["to"] = {
canonicalName = "Tongan",
scripts = {"Latn"},
family = "poz-pol",
}
m["tr"] = {
canonicalName = "Turkis",
scripts = {"Latn"},
family = "trk-ogz",
ancestors = {"ota"},
}
m["ts"] = {
canonicalName = "Tsonga",
scripts = {"Latn"},
family = "bnt",
}
m["tt"] = {
canonicalName = "Tatar",
scripts = {"Cyrl", "Latn", "Arab", "tt-Arab"},
family = "trk-kip",
translit_module = "tt-translit",
override_translit = true,
}
-- "tw" IS TREATED AS "ak", SEE WT:LT
m["ty"] = {
canonicalName = "Tahitian",
scripts = {"Latn"},
family = "poz-pol",
}
m["ug"] = {
canonicalName = "Uyghur",
otherNames = {"Uigur", "Uighur", "Uygur"},
scripts = {"ug-Arab", "Latn", "Cyrl"},
family = "trk",
ancestors = {"chg"},
translit_module = "ug-translit",
override_translit = true,
}
m["uk"] = {
canonicalName = "Ukrainian",
scripts = {"Cyrl"},
family = "zle",
translit_module = "uk-translit",
entry_name = {
from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE},
to = {"Е", "е", "И", "и"}},
}
m["ur"] = {
canonicalName = "Urdu",
scripts = {"ur-Arab"},
family = "inc",
ancestors = {"psu"},
entry_name = {
from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)},
to = {}} ,
}
m["uz"] = {
canonicalName = "Uzbek",
otherNames = {"Northern Uzbek", "Southern Uzbek"},
scripts = {"Latn", "Cyrl", "fa-Arab"},
family = "trk",
ancestors = {"chg"},
}
m["ve"] = {
canonicalName = "Venda",
scripts = {"Latn"},
family = "bnt",
}
m["vi"] = {
canonicalName = "Vietnamese",
otherNames = {"Annamese", "Annamite"},
scripts = {"Latn", "Hani"},
family = "mkh-vie",
ancestors = {"mkh-mvi"},
}
m["vo"] = {
canonicalName = "Volapük",
scripts = {"Latn"},
family = "art",
}
m["wa"] = {
canonicalName = "Walloon",
otherNames = {"Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"},
scripts = {"Latn"},
family = "roa-oil",
ancestors = {"fro"},
sort_key = {
from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"},
to = {"a" , "e" , "i" , "o" , "u" , "y" , "c"}} ,
}
m["wo"] = {
canonicalName = "Wolof",
otherNames = {"Gambian Wolof"}, -- the subsumed dialect 'wof'
scripts = {"Latn", "Arab"},
family = "alv-sng",
}
m["xh"] = {
canonicalName = "Xhosa",
scripts = {"Latn"},
family = "bnt-ngu",
entry_name = {
from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON},
to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }},
}
m["yi"] = {
canonicalName = "Yiddish",
scripts = {"Hebr"},
family = "gmw",
ancestors = {"gmh"},
translit_module = "yi-translit",
}
m["yo"] = {
canonicalName = "Yoruba",
scripts = {"Latn"},
family = "alv-von",
}
m["za"] = {
canonicalName = "Zhuang",
scripts = {"Latn", "Hani"},
family = "tai",
}
m["zh"] = {
canonicalName = "Chinese",
scripts = {"Hani", "Brai"},
family = "sit",
ancestors = {"ltc"},
}
m["zu"] = {
canonicalName = "Zulu",
otherNames = {"isiZulu"},
scripts = {"Latn"},
family = "bnt-ngu",
entry_name = {
from = {"[āàáâǎ]", "[ēèéêě]", "[īìíîǐ]", "[ōòóôǒ]", "[ūùúûǔ]", "ḿ", "[ǹńň]", MACRON, ACUTE, GRAVE, CIRC, CARON},
to = {"a" , "e" , "i" , "o" , "u" , "m", "n" }},
}
return m
