وحدة:languages/data2
يمكن إنشاء صفحة توثيق الوحدة في وحدة:languages/data2/شرح
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)
local CGJ = u(0x034F) -- combining grapheme joiner
local DOUBLEINVBREVE = u(0x0361)
-- Punctuation to be used for standardChars field
local PUNCTUATION = ' !#%&*+,-./:;<=>?@^_`|~\'()'
local m = {}
m["aa"] = {
canonicalName = "عفارية",
otherNames = {"Qafar"},
type = "عادي",
scripts = {"لاتيني"},
family = "cus",
}
m["ab"] = {
canonicalName = "أبخازية",
otherNames = {"Abkhazian", "Abxazo"},
type = "عادي",
scripts = {"كيريلي"},
family = "cau-nwc",
translit_module = "ab-translit",
entry_name = {
from = {GRAVE, ACUTE},
to = {}} ,
}
m["ae"] = {
canonicalName = "أفستية",
otherNames = {"Zend", "Old Bactrian"},
type = "عادي",
scripts = {"Avst", "Gujr"},
family = "ira",
translit_module = "Avst-translit",
}
m["af"] = {
canonicalName = "أفريكانية",
type = "عادي",
scripts = {"لاتيني", "عربي"},
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"},
type = "عادي",
scripts = {"لاتيني"},
family = "alv-kwa",
}
m["am"] = {
canonicalName = "أمهرية",
type = "عادي",
scripts = {"Ethi"},
family = "sem-eth",
translit_module = "Ethi-translit",
}
m["an"] = {
canonicalName = "أراغونية",
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
}
m["ar"] = {
canonicalName = "عربية",
otherNames = {"اللغة العربية الفصحى", "العربية المعيارية الحديثة", "اللغة العربية الأدبية", "اللغة العربية التراثية"},
type = "عادي",
scripts = {"عربية"},
family = "sem-arb",
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 = "آسامية",
type = "عادي",
scripts = {"Beng"},
family = "inc",
}
m["av"] = {
canonicalName = "أوارية",
otherNames = {"Avaric"},
type = "عادي",
scripts = {"كيريلي"},
family = "cau-nec",
translit_module = "av-translit",
}
m["ay"] = {
canonicalName = "أيمارا",
otherNames = {"Southern Aymara", "Central Aymara"},
type = "عادي",
scripts = {"لاتيني"},
family = "sai-aym",
}
m["az"] = {
canonicalName = "أذرية",
otherNames = {"Azerbaijani", "Azari", "Azeri Turkic", "Azerbaijani Turkic", "North Azerbaijani", "South Azerbaijani"},
type = "عادي",
scripts = {"لاتيني", "كيريلي", "fa-Arab"},
family = "trk",
}
m["ba"] = {
canonicalName = "باشقير",
type = "عادي",
scripts = {"كيريلي"},
family = "trk",
translit_module = "ba-translit",
}
m["be"] = {
canonicalName = "بيلاروسية",
otherNames = {"Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"},
type = "عادي",
scripts = {"كيريلي"},
family = "zle",
ancestors = {"orv"},
translit_module = "be-translit",
sort_key = {
from = {"Ё", "ё"},
to = {"Е" , "е"}},
entry_name = {
from = {GRAVE, ACUTE},
to = {}} ,
}
m["bg"] = {
canonicalName = "بلغارية",
type = "عادي",
scripts = {"كيريلي"},
family = "zls",
translit_module = "bg-translit",
entry_name = {
from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE},
to = {"Е", "е", "И", "и"}} ,
}
m["bh"] = {
canonicalName = "Bihari",
type = "عادي",
scripts = {"Deva"},
family = "inc",
}
m["bi"] = {
canonicalName = "بيسلامية",
type = "عادي",
scripts = {"لاتيني"},
family = "crp",
ancestors = {"en"},
}
m["bm"] = {
canonicalName = "بامبارية",
otherNames = {"Bamanankan"},
type = "عادي",
scripts = {"لاتيني"},
family = "dmn",
}
m["bn"] = {
canonicalName = "بنغالية",
otherNames = {"Bangla"},
type = "عادي",
scripts = {"Beng"},
family = "inc",
}
m["bo"] = {
canonicalName = "تبتية",
type = "عادي",
scripts = {"تبتي"},
family = "tbq",
translit_module = "bo-translit",
}
m["br"] = {
canonicalName = "بريتانية",
type = "عادي",
scripts = {"لاتيني"},
family = "cel-bry",
ancestors = {"xbm"},
}
m["ca"] = {
canonicalName = "كتالونية",
otherNames = {"Valencian"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
sort_key = {
from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"},
to = {"a", "e" , "i" , "o" , "u" , "c", "ll" }} ,
}
m["ce"] = {
canonicalName = "شيشانية",
type = "عادي",
scripts = {"كيريلي"},
family = "cau-nec",
translit_module = "ce-translit",
}
m["ch"] = {
canonicalName = "Chamorro",
otherNames = {"Chamoru"},
type = "عادي",
scripts = {"لاتيني"},
family = "poz-sus",
}
m["co"] = {
canonicalName = "كورسية",
otherNames = {"Corsu"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
}
m["cr"] = {
canonicalName = "كرية",
type = "عادي",
scripts = {"Cans", "لاتيني"},
family = "alg",
}
m["cs"] = {
canonicalName = "تشيكية",
type = "عادي",
scripts = {"لاتيني"},
family = "zlw",
sort_key = {
from = {"á", "é", "í", "ó", "[úů]", "ý"},
to = {"a", "e", "i", "o", "u" , "y"}} ,
}
m["cu"] = {
canonicalName = "Old Church Slavonic",
otherNames = {"Old Church Slavic"},
type = "عادي",
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 = "تشوفاش",
type = "عادي",
scripts = {"كيريلي"},
family = "trk",
translit_module = "cv-translit",
}
m["cy"] = {
canonicalName = "ويلزية",
type = "عادي",
scripts = {"لاتيني"},
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 = "دنماركية",
type = "عادي",
scripts = {"لاتيني"},
family = "gmq",
}
m["de"] = {
canonicalName = "ألمانية",
otherNames = {"High German", "New High German", "Deutsch"}, -- the last name is indeed also used in English
type = "عادي",
scripts = {"لاتيني", "Latf"},
family = "gmw",
ancestors = {"gmh"},
sort_key = {
from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" },
to = {"a" , "e" , "i" , "o" , "u" , "ss"}} ,
}
m["dv"] = {
canonicalName = "ديفهي",
otherNames = {"Divehi", "Mahal", "Mahl", "Maldivian"},
type = "عادي",
scripts = {"Thaa"},
family = "inc",
translit_module = "dv-translit",
}
m["dz"] = {
canonicalName = "Dzongkha",
type = "عادي",
scripts = {"تبتي"},
family = "tbq",
translit_module = "bo-translit",
}
m["ee"] = {
canonicalName = "Ewe",
type = "عادي",
scripts = {"لاتيني"},
family = "alv",
}
m["el"] = {
canonicalName = "يونانية",
otherNames = {"Modern Greek", "Neo-Hellenic"},
type = "عادي",
scripts = {"Grek"},
family = "grk",
translit_module = "el-translit",
sort_key = { -- Keep this synchronized with grc, cpg
from = {"[ᾳάᾴὰᾲᾶᾷἀᾀἄᾄἂᾂἆᾆἁᾁἅᾅἃᾃἇᾇ]", "[έὲἐἔἒἑἕἓ]", "[ῃήῄὴῂῆῇἠᾐἤᾔἢᾒἦᾖἡᾑἥᾕἣᾓἧᾗ]", "[ίὶῖἰἴἲἶἱἵἳἷϊΐῒῗ]", "[όὸὀὄὂὁὅὃ]", "[ύὺῦὐὔὒὖὑὕὓὗϋΰῢῧ]", "[ῳώῴὼῲῶῷὠᾠὤᾤὢᾢὦᾦὡᾡὥᾥὣᾣὧᾧ]", "ῥ", "ς"},
to = {"α" , "ε" , "η" , "ι" , "ο" , "υ" , "ω" , "ρ", "σ"}} ,
}
m["en"] = {
canonicalName = "إنجليزية",
otherNames = {"Modern English", "New English", "Hawaiian Creole English", "Hawai'ian Creole English", "Hawaiian Creole", "Hawai'ian Creole", "Polari", "Yinglish"}, -- all but the first three are names and alt names of subsumed dialects which once had ISO codes
type = "عادي",
scripts = {"لاتيني", "Shaw", "Dsrt"}, -- last two are rare but probably attested; entries in them might require community approval, but it's good for the script codes not to be orphans
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"},
}
m["eo"] = {
canonicalName = "Esperanto",
type = "عادي",
scripts = {"لاتيني"},
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 = "إسبانية",
otherNames = {"Castilian"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
sort_key = {
from = {"á", "é", "í", "ó", "[úü]", "ç", "ñ"},
to = {"a", "e", "i", "o", "u" , "c", "n"}} ,
}
m["et"] = {
canonicalName = "إستونية",
type = "عادي",
scripts = {"لاتيني"},
family = "fiu-fin",
ancestors = {"fiu-fin-pro"},
}
m["eu"] = {
canonicalName = "بشكنشية",
otherNames = {"Euskara"},
type = "عادي",
scripts = {"لاتيني"},
family = "euq",
}
m["fa"] = {
canonicalName = "فارسية",
otherNames = {"Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari"},
type = "عادي",
scripts = {"fa-Arab"},
family = "ira",
entry_name = {
from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)},
to = {}} ,
}
m["ff"] = {
canonicalName = "فولانية",
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
type = "عادي",
scripts = {"لاتيني"},
family = "alv-sng",
}
m["fi"] = {
canonicalName = "فنلندية",
otherNames = {"Suomi"},
type = "عادي",
scripts = {"لاتيني"},
family = "fiu-fin",
ancestors = {"fiu-fin-pro"},
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 = "فيجية",
type = "عادي",
scripts = {"لاتيني"},
family = "poz-occ",
}
m["fo"] = {
canonicalName = "فاروية",
type = "عادي",
scripts = {"لاتيني"},
family = "gmq",
}
m["fr"] = {
canonicalName = "فرنسية",
otherNames = {"Modern French"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
ancestors = {"frm"},
sort_key = {
from = {"[áàâä]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "æ" , "œ" , "'"},
to = {"a" , "e" , "i" , "o" , "u" , "y" , "c", "ae", "oe"}} ,
}
m["fy"] = {
canonicalName = "فريزية غربية",
otherNames = {"Western Frisian", "Frisian"},
type = "عادي",
scripts = {"لاتيني"},
family = "gmw-fri",
}
m["ga"] = {
canonicalName = "أيرلندية",
otherNames = {"Irish Gaelic"},
type = "عادي",
scripts = {"لاتيني"},
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 = "Scottish Gaelic",
otherNames = {"Gàidhlig", "Highland Gaelic", "Scots Gaelic", "Scottish"},
type = "عادي",
scripts = {"لاتيني"},
family = "cel-gae",
ancestors = {"mga"},
sort_key = {
from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"},
to = {"a" , "e" , "i" , "o" , "u" , "y" }} ,
}
m["gl"] = {
canonicalName = "غاليسية",
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
}
m["gn"] = {
canonicalName = "Guaraní",
type = "عادي",
scripts = {"لاتيني"},
family = "tup",
}
m["gu"] = {
canonicalName = "غوجاراتية",
type = "عادي",
scripts = {"Gujr"},
family = "inc",
}
m["gv"] = {
canonicalName = "مانكس",
otherNames = {"Manx Gaelic"},
type = "عادي",
scripts = {"لاتيني"},
family = "cel-gae",
ancestors = {"mga"},
sort_key = {
from = {"ç", "-"},
to = {"c"}} ,
}
m["ha"] = {
canonicalName = "هوسية",
type = "عادي",
scripts = {"لاتيني", "عربي"},
family = "cdc-wst",
}
m["he"] = {
canonicalName = "عبرية",
otherNames = {"Ivrit"},
type = "عادي",
scripts = {"Hebr"},
family = "sem-can",
entry_name = {
from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"},
to = {}} ,
}
m["hi"] = {
canonicalName = "هندية",
type = "عادي",
scripts = {"Deva"},
family = "inc",
translit_module = "hi-translit",
}
m["ho"] = {
canonicalName = "Hiri Motu",
otherNames = {"Pidgin Motu", "Police Motu"},
type = "عادي",
scripts = {"لاتيني"},
family = "crp",
ancestors = {"meu"},
}
m["ht"] = {
canonicalName = "كريولية هايتية",
otherNames = {"Creole", "Haitian", "Kreyòl"},
type = "عادي",
scripts = {"لاتيني"},
family = "crp",
}
m["hu"] = {
canonicalName = "مجرية",
otherNames = {"Magyar"},
type = "عادي",
scripts = {"لاتيني"},
family = "fiu-ugr",
sort_key = {
from = {"á", "é", "í", "ó", "ú", "ő", "ű"},
to = {"a", "e", "i", "o", "u", "ö", "ü"}} ,
}
m["hy"] = {
canonicalName = "أرمنية",
otherNames = {"Modern Armenian", "Eastern Armenian", "Western Armenian"},
type = "عادي",
scripts = {"Armn"},
family = "hyx",
translit_module = "Armn-translit",
sort_key = {
from = {"ու", "և", "եւ"},
to = {"ւ", "եվ", "եվ"}},
entry_name = {
from = {"՞", "՜", "՛", "՟", "և", "<sup>յ</sup>", "<sup>ի</sup>", "ՙ", "̈", "յ̵", GRAVE},
to = {"", "", "", "", "եւ", "յ", "ի", "", "", "յ"}} ,
}
m["hz"] = {
canonicalName = "Herero",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["ia"] = {
canonicalName = "إنترلنغوا",
type = "عادي",
scripts = {"لاتيني"},
family = "art",
}
m["id"] = {
canonicalName = "إندونيسية",
type = "عادي",
scripts = {"لاتيني"},
family = "poz-mly",
}
m["ie"] = {
canonicalName = "Interlingue",
otherNames = {"Occidental"},
type = "عادي",
scripts = {"لاتيني"},
family = "art",
}
m["ig"] = {
canonicalName = "Igbo",
type = "عادي",
scripts = {"لاتيني"},
family = "nic-bco",
}
m["ii"] = {
canonicalName = "Sichuan Yi",
type = "عادي",
scripts = {"Yiii"},
family = "tbq",
}
m["ik"] = {
canonicalName = "Inupiak",
otherNames = {"Inupiaq", "Iñupiaq", "Inupiatun"},
type = "عادي",
scripts = {"لاتيني"},
family = "esx-inu",
}
m["io"] = {
canonicalName = "إيدو",
type = "عادي",
scripts = {"لاتيني"},
family = "art",
}
m["is"] = {
canonicalName = "آيسلندية",
type = "عادي",
scripts = {"لاتيني"},
family = "gmq",
ancestors = {"non"},
}
m["it"] = {
canonicalName = "إيطالية",
type = "عادي",
scripts = {"لاتيني"},
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"},
type = "عادي",
scripts = {"Cans", "لاتيني"},
family = "esx-inu",
translit_module = "iu-translit",
}
m["ja"] = {
canonicalName = "يابانية",
otherNames = {"Modern Japanese", "Nipponese", "Nihongo"},
type = "عادي",
scripts = {"Jpan", "لاتيني", "Hira"},
family = "jpx",
}
m["jv"] = {
canonicalName = "جاوية",
type = "عادي",
scripts = {"لاتيني", "Java"},
family = "poz-sus",
}
m["ka"] = {
canonicalName = "جورجية",
otherNames = {"Kartvelian"},
type = "عادي",
scripts = {"Geor", "Geok"},
family = "ccs",
translit_module = "Geor-translit",
entry_name = {
from = {"̂"},
to = {""}},
}
m["kg"] = {
canonicalName = "Kongo",
otherNames = {"Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["ki"] = {
canonicalName = "Kikuyu",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["kj"] = {
canonicalName = "Kwanyama",
otherNames = {"Kuanyama", "Oshikwanyama"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["kk"] = {
canonicalName = "قازاقية",
type = "عادي",
scripts = {"كيريلي", "لاتيني", "عربي", "kk-Arab"},
family = "trk",
translit_module = "kk-translit",
}
m["kl"] = {
canonicalName = "جرينلاندية",
otherNames = {"Kalaallisut"},
type = "عادي",
scripts = {"لاتيني"},
family = "esx-inu",
}
m["km"] = {
canonicalName = "خميرية",
otherNames = {"Cambodian"},
type = "عادي",
scripts = {"Khmr"},
family = "mkh",
translit_module = "km-translit",
}
m["kn"] = {
canonicalName = "كنادية",
type = "عادي",
scripts = {"Knda"},
family = "dra",
translit_module = "kn-translit",
}
m["ko"] = {
canonicalName = "كورية",
otherNames = {"Modern Korean"},
type = "عادي",
scripts = {"Kore"},
family = "qfa-kor",
translit_module = "ko-translit",
}
m["kr"] = {
canonicalName = "كانورية",
otherNames = {"Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"},
type = "عادي",
scripts = {"لاتيني"},
family = "ssa",
}
m["ks"] = {
canonicalName = "كشميرية",
type = "عادي",
scripts = {"ks-Arab", "Deva"},
family = "iir-dar",
}
m["ku"] = {
canonicalName = "كردية",
type = "عادي",
scripts = {"لاتيني", "ku-Arab"},
family = "ira",
}
m["kw"] = {
canonicalName = "كورنية",
type = "عادي",
scripts = {"لاتيني"},
family = "cel-bry",
ancestors = {"cnx"},
}
m["ky"] = {
canonicalName = "قرغيزية",
otherNames = {"Kirghiz", "Kirgiz"},
type = "عادي",
scripts = {"كيريلي", "لاتيني", "عربي"},
family = "trk",
translit_module = "ky-translit",
}
m["la"] = {
canonicalName = "لاتينية",
type = "عادي",
scripts = {"لاتيني"},
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 = "لوكسمبورغية",
type = "عادي",
scripts = {"لاتيني"},
family = "gmw",
ancestors = {"gmh"},
}
m["lg"] = {
canonicalName = "Luganda",
otherNames = {"Ganda"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["li"] = {
canonicalName = "ليمبورغية",
otherNames = {"Limburgan", "Limburgian", "Limburgic"},
type = "عادي",
scripts = {"لاتيني"},
family = "gmw",
ancestors = {"dum"},
}
m["ln"] = {
canonicalName = "لينغالا",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["lo"] = {
canonicalName = "لاو",
otherNames = {"Laotian"},
type = "عادي",
scripts = {"Laoo"},
family = "tai-swe",
translit_module = "lo-translit",
sort_key = {
from = {"[%pໆ]", "[່-ໍ]", "ຼ", "ຽ", "ໜ", "ໝ", "([ເແໂໃໄ])([ກ-ຮ])"},
to = {"", "", "ລ", "ຍ", "ຫນ", "ຫມ", "%2%1"}},
standardChars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. PUNCTUATION,
}
m["lt"] = {
canonicalName = "ليتوانية",
type = "عادي",
scripts = {"لاتيني"},
family = "bat",
entry_name = {
from = {"[áãà]", "[éẽè]", "[íĩì]", "[ýỹ]", "ñ", "[óõò]", "[úù]", ACUTE, GRAVE, TILDE},
to = {"a" , "e" , "i", "y" , "n", "o" , "u" }} ,
}
m["lu"] = {
canonicalName = "Luba-Katanga",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["lv"] = {
canonicalName = "لاتفية",
otherNames = {"Lettish", "Lett"},
type = "عادي",
scripts = {"لاتيني"},
family = "bat",
}
m["mg"] = {
canonicalName = "ملغاشية",
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"},
type = "عادي",
scripts = {"لاتيني"},
family = "poz-bre",
}
m["mh"] = {
canonicalName = "مارشالية",
type = "عادي",
scripts = {"لاتيني"},
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 = "ماورية",
otherNames = {"Māori"},
type = "عادي",
scripts = {"لاتيني"},
family = "poz-pol",
}
m["mk"] = {
canonicalName = "مقدونية",
type = "عادي",
scripts = {"كيريلي"},
family = "zls",
translit_module = "mk-translit",
entry_name = {
from = {ACUTE},
to = {}},
}
m["ml"] = {
canonicalName = "ماليالامية",
type = "عادي",
scripts = {"Mlym"},
family = "dra",
translit_module = "ml-translit",
}
m["mn"] = {
canonicalName = "منغولية",
otherNames = {"Khalkha Mongolian"},
type = "عادي",
scripts = {"كيريلي", "Mong"},
family = "xgn",
translit_module = "mn-translit",
}
m["mr"] = {
canonicalName = "مراثية",
type = "عادي",
scripts = {"Deva"},
family = "inc",
translit_module = "hi-translit",
}
m["ms"] = {
canonicalName = "ملايو",
type = "عادي",
scripts = {"لاتيني", "عربي"},
family = "poz-mly",
}
m["mt"] = {
canonicalName = "مالطية",
type = "عادي",
scripts = {"لاتيني"},
family = "sem-arb",
}
m["my"] = {
canonicalName = "بورمية",
otherNames = {"Myanmar"},
type = "عادي",
scripts = {"Mymr"},
family = "tbq-brm",
ancestors = {"obr"},
translit_module = "my-translit",
}
m["na"] = {
canonicalName = "ناورونية",
otherNames = {"Nauru"},
type = "عادي",
scripts = {"لاتيني"},
family = "poz-mic",
}
m["nb"] = {
canonicalName = "Norwegian Bokmål",
otherNames = {"Bokmål"},
type = "عادي",
scripts = {"لاتيني"},
family = "gmq",
wikimedia_codes = {"no"},
}
m["nd"] = {
canonicalName = "Northern Ndebele",
otherNames = {"North Ndebele"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["ne"] = {
canonicalName = "نيبالية",
otherNames = {"Nepalese"},
type = "عادي",
scripts = {"Deva"},
family = "inc",
translit_module = "sa-translit",
}
m["ng"] = {
canonicalName = "Ndonga",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["nl"] = {
canonicalName = "هولندية",
otherNames = {"Netherlandic", "Flemish"},
type = "عادي",
scripts = {"لاتيني"},
family = "gmw",
ancestors = {"dum"},
sort_key = {
from = {"[äáâå]", "[ëéê]", "[ïíî]", "[öóô]", "[üúû]", "ç", "ñ", "^-"},
to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} ,
}
m["nn"] = {
canonicalName = "نينوشك",
otherNames = {"New Norwegian", "Nynorsk"},
type = "عادي",
scripts = {"لاتيني"},
family = "gmq",
}
m["no"] = {
canonicalName = "نرويجية",
type = "عادي",
scripts = {"لاتيني"},
family = "gmq",
}
m["nr"] = {
canonicalName = "Southern Ndebele",
otherNames = {"South Ndebele"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["nv"] = {
canonicalName = "نافاجية",
type = "عادي",
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 = "شيشيوا",
otherNames = {"Chicheŵa", "Chinyanja", "Nyanja"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["oc"] = {
canonicalName = "قسطانية",
otherNames = {"Provençal", "Auvergnat", "Auvernhat", "Gascon", "Languedocien", "Lengadocian"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
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"},
type = "عادي",
scripts = {"Cans", "لاتيني"},
family = "alg",
}
m["om"] = {
canonicalName = "أورومو",
otherNames = {"Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"},
type = "عادي",
scripts = {"لاتيني", "Ethi"},
family = "cus",
}
m["or"] = {
canonicalName = "أوريا",
otherNames = {"Odia", "Oorya"},
type = "عادي",
scripts = {"Orya"},
family = "inc",
}
m["os"] = {
canonicalName = "أوسيتية",
otherNames = {"Ossete", "Ossetic", "Digor", "Iron"},
type = "عادي",
scripts = {"كيريلي", "Geor", "لاتيني"},
family = "ira",
translit_module = "os-translit",
entry_name = {
from = {GRAVE, ACUTE},
to = {}} ,
}
m["pa"] = {
canonicalName = "بنجابية",
otherNames = {"Panjabi"},
type = "عادي",
scripts = {"Guru", "عربي", "Deva"},
family = "inc",
}
m["pi"] = {
canonicalName = "بالي",
type = "عادي",
scripts = {"لاتيني", "Deva", "Sinh", "Mymr", "Khmr", "تايلندي"},
family = "inc",
sort_key = {
from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "[ṇñṅ]", "ṭ"},
to = {"a", "i", "u", "d", "l", "m" , "n" , "t"}} ,
}
m["pl"] = {
canonicalName = "بولندية",
type = "عادي",
scripts = {"لاتيني"},
family = "zlw",
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 = "بشتوية",
otherNames = {"Pashtun", "Pushto", "Pashtu", "Central Pashto", "Northern Pashto", "Southern Pashto", "Pukhto", "Pakhto", "Pakkhto", "Afghani"},
type = "عادي",
scripts = {"ps-Arab"},
family = "ira",
}
m["pt"] = {
canonicalName = "برتغالية",
otherNames = {"Modern Portuguese"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
sort_key = {
from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"},
to = {"a" , "e" , "i" , "o" , "u" , "c", "n"}} ,
}
m["qu"] = {
canonicalName = "كتشوا",
type = "عادي",
scripts = {"لاتيني"},
family = "qwe",
}
m["rm"] = {
canonicalName = "رومانشية",
otherNames = {"Romansh", "Rumantsch", "Romanche"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
}
m["rn"] = {
canonicalName = "Kirundi",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["ro"] = {
canonicalName = "رومانية",
otherNames = {"Daco-Romanian", "Roumanian", "Rumanian"},
type = "عادي",
scripts = {"لاتيني", "كيريلي"},
family = "roa",
}
m["ru"] = {
canonicalName = "روسية",
type = "عادي",
scripts = {"كيريلي"},
family = "zle",
ancestors = {"orv"},
translit_module = "ru-translit",
sort_key = {
from = {"ё"},
to = {"е" .. mw.ustring.char(0x10FFFF)}},
entry_name = {
from = {GRAVE, ACUTE},
to = {}} ,
}
m["rw"] = {
canonicalName = "Kinyarwanda",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["sa"] = {
canonicalName = "سنسكريتية",
type = "عادي",
scripts = {"Deva", "Beng", "Brah", "Gran", "Gujr", "Guru", "Khar", "Knda", "Mlym", "Mymr", "Orya", "Shrd", "Sinh", "تاميلي", "Telu", "تايلندي", "تبتي"},
family = "inc",
ancestors = {"inc-pro"},
translit_module = "sa-translit",
}
m["sc"] = {
canonicalName = "سردينية",
otherNames = {"Campidanese", "Logudorese", "Nuorese"},
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
}
m["sd"] = {
canonicalName = "سندية",
type = "عادي",
scripts = {"sd-Arab"},
family = "inc",
}
m["se"] = {
canonicalName = "سامي الشمالية",
otherNames = {"North Sami", "Northern Saami", "North Saami"},
type = "عادي",
scripts = {"لاتيني"},
family = "smi",
entry_name = {
from = {"([đflmnŋrsšŧv])'%1"},
to = {"%1%1"} },
}
m["sg"] = {
canonicalName = "Sango",
type = "عادي",
scripts = {"لاتيني"},
family = "crp",
}
m["sh"] = {
canonicalName = "صربية كرواتية",
otherNames = {"BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"},
type = "عادي",
scripts = {"لاتيني", "كيريلي"},
family = "zls",
entry_name = {
from = {"[ȀÀȂÁĀ]", "[ȁàȃáā]", "[ȄÈȆÉĒ]", "[ȅèȇéē]", "[ȈÌȊÍĪ]", "[ȉìȋíī]", "[ȌÒȎÓŌ]", "[ȍòȏóō]", "[ȐȒŔ]", "[ȑȓŕ]", "[ȔÙȖÚŪ]", "[ȕùȗúū]", "Ѐ", "ѐ", "[ӢЍ]", "[ӣѝ]", "[Ӯ]", "[ӯ]", GRAVE, ACUTE, DGRAVE, INVBREVE, MACRON},
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 = "سنهالية",
otherNames = {"Singhalese", "Sinhala"},
type = "عادي",
scripts = {"Sinh"},
family = "inc",
translit_module = "si-translit",
}
m["sk"] = {
canonicalName = "سلوفاكية",
type = "عادي",
scripts = {"لاتيني"},
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 = "سلوفينية",
otherNames = {"Slovenian"},
type = "عادي",
scripts = {"لاتيني"},
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 = "ساموية",
type = "عادي",
scripts = {"لاتيني"},
family = "poz-pol",
}
m["sn"] = {
canonicalName = "شونا",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["so"] = {
canonicalName = "صومالية",
type = "عادي",
scripts = {"لاتيني", "عربي", "عثماني (صومالي)"},
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 = "ألبانية",
type = "عادي",
scripts = {"لاتيني", "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"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["st"] = {
canonicalName = "Sotho",
otherNames = {"Sesotho", "Southern Sesotho", "Southern Sotho"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["su"] = {
canonicalName = "سوندية",
type = "عادي",
scripts = {"لاتيني", "Sund"},
family = "poz-msa",
}
m["sv"] = {
canonicalName = "سويدية",
type = "عادي",
scripts = {"لاتيني"},
family = "gmq",
ancestors = {"gmq-osw"},
}
m["sw"] = {
canonicalName = "سواحلية",
type = "عادي",
scripts = {"لاتيني", "عربي"},
family = "bnt",
sort_key = {
from = {"ng'", "^-"},
to = {"ngz"}} ,
}
m["ta"] = {
canonicalName = "تاميلية",
type = "عادي",
scripts = {"تاميلي"},
family = "dra",
translit_module = "ta-translit",
}
m["te"] = {
canonicalName = "تيلوغوية",
type = "عادي",
scripts = {"Telu"},
family = "dra",
translit_module = "te-translit",
}
m["tg"] = {
canonicalName = "طاجيكية",
otherNames = {"Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"},
type = "عادي",
scripts = {"كيريلي", "fa-Arab", "لاتيني"},
family = "ira",
translit_module = "tg-translit",
sort_key = {
from = {"Ё", "ё"},
to = {"Е" , "е"}} ,
}
m["th"] = {
canonicalName = "تايلندية",
type = "عادي",
scripts = {"تايلندي"},
family = "tai-swe",
sort_key = {
from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"},
to = {"", "", "%2%1"}},
}
m["ti"] = {
canonicalName = "تغرينية",
type = "عادي",
scripts = {"Ethi"},
family = "sem-eth",
translit_module = "Ethi-translit",
}
m["tk"] = {
canonicalName = "تركمانية",
type = "عادي",
scripts = {"لاتيني", "كيريلي"},
family = "trk",
}
m["tl"] = {
canonicalName = "تاغالوغية",
type = "عادي",
scripts = {"لاتيني", "Tglg"},
family = "phi",
}
m["tn"] = {
canonicalName = "تسوانية",
otherNames = {"Setswana"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["to"] = {
canonicalName = "تونغية",
type = "عادي",
scripts = {"لاتيني"},
family = "poz-pol",
}
m["tr"] = {
canonicalName = "تركية",
type = "عادي",
scripts = {"لاتيني"},
family = "trk",
}
m["ts"] = {
canonicalName = "Tsonga",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["tt"] = {
canonicalName = "تترية",
type = "عادي",
scripts = {"كيريلي", "لاتيني", "عربي", "tt-Arab"},
family = "trk",
translit_module = "tt-translit",
}
m["tw"] = {
canonicalName = "Twi",
type = "عادي",
scripts = {"لاتيني"},
family = "alv-kwa",
}
m["ty"] = {
canonicalName = "تاهيتية",
type = "عادي",
scripts = {"لاتيني"},
family = "poz-pol",
}
m["ug"] = {
canonicalName = "أويغورية",
otherNames = {"Uigur", "Uighur", "Uygur"},
type = "عادي",
scripts = {"ug-Arab", "لاتيني", "كيريلي"},
family = "trk",
translit_module = "ug-translit",
}
m["uk"] = {
canonicalName = "أوكرانية",
type = "عادي",
scripts = {"كيريلي"},
family = "zle",
ancestors = {"orv"},
translit_module = "uk-translit",
entry_name = {
from = {GRAVE, ACUTE},
to = {}} }
m["ur"] = {
canonicalName = "أردوية",
type = "عادي",
scripts = {"ur-Arab"},
family = "inc",
entry_name = {
from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)},
to = {}} ,
}
m["uz"] = {
canonicalName = "أوزبكية",
otherNames = {"Northern Uzbek", "Southern Uzbek"},
type = "عادي",
scripts = {"لاتيني", "كيريلي", "fa-Arab"},
family = "trk",
}
m["ve"] = {
canonicalName = "Venda",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["vi"] = {
canonicalName = "فيتنامية",
otherNames = {"Annamese", "Annamite"},
type = "عادي",
scripts = {"لاتيني", "Hani"},
family = "mkh-vie",
ancestors = {"mkh-vie-pro"},
}
m["vo"] = {
canonicalName = "فولابوك ",
type = "عادي",
scripts = {"لاتيني"},
family = "art",
}
m["wa"] = {
canonicalName = "والونية",
type = "عادي",
scripts = {"لاتيني"},
family = "roa",
sort_key = {
from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"},
to = {"a" , "e" , "i" , "o" , "u" , "y" , "c"}} ,
}
m["wo"] = {
canonicalName = "ولوفية",
type = "عادي",
scripts = {"لاتيني", "عربي"},
family = "alv-sng",
}
m["xh"] = {
canonicalName = "خوسية",
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
m["yi"] = {
canonicalName = "يديشية",
type = "عادي",
scripts = {"Hebr"},
family = "gmw",
ancestors = {"gmh"},
translit_module = "yi-translit",
}
m["yo"] = {
canonicalName = "يوربا",
type = "عادي",
scripts = {"لاتيني"},
family = "alv-von",
}
m["za"] = {
canonicalName = "Zhuang",
type = "عادي",
scripts = {"لاتيني", "Hani", "كيريلي"},
family = "tai",
}
m["zh"] = {
canonicalName = "صينية",
type = "عادي",
scripts = {"Hani"},
family = "sit",
}
m["zu"] = {
canonicalName = "زولوية",
otherNames = {"isiZulu"},
type = "عادي",
scripts = {"لاتيني"},
family = "bnt",
}
return m