มอดูล:languages/data2

จาก วิกิพจนานุกรม พจนานุกรมเสรี
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 Cyrl = {"Cyrl"}
local Latn = {"Latn"}

local m = {}

m["aa"] = {
	"อาฟาร์",
	"Q27811",
	"cus",
	otherNames = {"กาฟาร์", "Afar", "Qafar"},
	scripts = Latn,
}

m["ab"] = {
	"อับฮาเซีย",
	"Q5111",
	"cau-abz",
	otherNames = {"อับฮัซ", "Abkhaz", "Abkhazian", "Abxazo"},
	scripts = {"Cyrl", "Geor", "Latn"},
	translit_module = "ab-translit",
	override_translit = true,
	entry_name = {
		from = {GRAVE, ACUTE},
		to   = {}} ,
}

m["ae"] = {
	"อเวสตะ",
	"Q29572",
	"ira-eas",
	otherNames = {"เซนด์", "แบกเตรียเก่า", "Avestan", "Zend", "Old Bactrian"},
	scripts = {"Avst", "Gujr"},
	translit_module = "Avst-translit",
}

m["af"] = {
	"แอฟริคานส์",
	"Q14196",
	"gmw",
	otherNames = {"Afrikaans"},
	scripts = {"Latn", "Arab"},
	ancestors = {"nl"},
	sort_key = {
		from = {"[äáâà]", "[ëéêè]", "[ïíîì]", "[öóôò]", "[üúûù]", "[ÿýŷỳ]", "^-", "'"},
		to   = {"a"	 , "e"	, "i"	, "o"	, "u"  , "y" }} ,
}

m["ak"] = {
	"อาคัน",
	"Q28026",
	"alv-kwa",
	otherNames = {"Akan", "Twi-Fante", "Twi", "Fante", "Fanti", "Asante", "Akuapem"},
	scripts = Latn,
}

m["am"] = {
	"อัมฮารา",
	"Q28244",
	"sem-eth",
	otherNames = {"Amharic"},
	scripts = {"Ethi"},
	translit_module = "Ethi-translit",
}

m["an"] = {
	"อารากอน",
	"Q8765",
	"roa",
	otherNames = {"Aragonese"},
	scripts = Latn,
	ancestors = {"roa-oan"},
}

m["ar"] = {
	"อาหรับ",
	"Q13955",
	"sem-arb",
	otherNames = {"อาหรับมาตรฐานใหม่", "อาหรับมาตรฐาน", "อาหรับวรรณกรรม", "อาหรับคลาสสิก", "Arabic", "Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic"},
	scripts = {"Arab", "Brai"},
	-- 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",
	standardChars = "ء-غف-ْٰٱ" .. PUNCTUATION .. "٠-٩،؛؟٫٬ـ",
}

m["as"] = {
	"อัสสัม",
	"Q29401",
	"inc",
	otherNames = {"Assamese"},
	scripts = {"Beng"},
	ancestors = {"inc-mgd"},
	translit_module = "Beng-translit",
}

m["av"] = {
	"อะวาร์",
	"Q29561",
	"cau-nec",
	otherNames = {"Avar", "Avaric"},
	scripts = Cyrl,
	ancestors = {"oav"},
	translit_module = "av-translit",
	override_translit = true,
	entry_name = {
		from = {GRAVE, ACUTE},
		to   = {}} ,
	wikipedia_article = "Avestan",
}

m["ay"] = {
	"ไอย์มารา",
	"Q4627",
	"sai-aym",
	otherNames = {"ไอย์มาราใต้", "ไอย์มารากลาง", "Aymara", "Southern Aymara", "Central Aymara"},
	scripts = Latn,
}

m["az"] = {
	"อาเซอร์ไบจาน",
	"Q9292",
	"trk-ogz",
	otherNames = {"อาเซอรี", "อาเซอร์ไบจานเติร์ก", "อาเซอรีเติร์ก", "อาเซอร์ไบจานเหนือ", "อาเซอร์ไบจานใต้", "Azeri", "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"},
}

m["ba"] = {
	"บัชคีร์",
	"Q13389",
	"trk-kip",
	otherNames = {"Bashkir"},
	scripts = Cyrl,
	translit_module = "ba-translit",
	override_translit = true,
}

m["be"] = {
	"เบลารุส",
	"Q9091",
	"zle",
	otherNames = {"รัสเซียขาว", "Belarusian", "Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"},
	scripts = Cyrl,
	ancestors = {"orv"},
	translit_module = "be-translit-Thai",
	sort_key = {
		from = {"Ё", "ё"},
		to   = {"Е" , "е"}},
	entry_name = {
		from = {"Ѐ", "ѐ", GRAVE, ACUTE},
		to   = {"Е", "е"}},
}

m["bg"] = {
	"บัลแกเรีย",
	"Q7918",
	"zls",
	otherNames = {"Bulgarian"},
	scripts = Cyrl,
	ancestors = {"cu"},
	translit_module = "bg-translit",
	entry_name = {
		from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE},
		to   = {"Е", "е", "И", "и"}},
}

m["bh"] = {
	"พิหาร",
	"Q135305",
	"inc",
	otherNames = {"Bihari"},
	scripts = {"Deva"},
	ancestors = {"inc-mgd"},
	translit_module = "Deva-translit",
}

m["bi"] = {
	"บิสลามา",
	"Q35452",
	"crp",
	otherNames = {"Bislama"},
	scripts = Latn,
	ancestors = {"en"},
}

m["bm"] = {
	"บัมบารา",
	"Q33243",
	"dmn",
	otherNames = {"Bambara", "Bamanankan"},
	scripts = Latn,
}

m["bn"] = {
	"เบงกาลี",
	"Q9610",
	"inc",
	otherNames = {"บังคลา", "Bengali", "Bangla"},
	scripts = {"Beng", "Newa"},
	ancestors = {"inc-mgd"},
	translit_module = "Beng-translit",
}

m["bo"] = {
	"ทิเบต",
	"Q34271",
	"tbq",
	otherNames = {"Tibetan", "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"}, -- and "Gyalsumdo", "Lower Manang"? "Kyirong"?
	scripts = {"Tibt"}, -- sometimes Deva?
	ancestors = {"xct"},
	translit_module = "Tibt-translit",
	override_translit = true,
}

m["br"] = {
	"เบรอตง",
	"Q12107",
	"cel-bry",
	otherNames = {"Breton"},
	scripts = Latn,
	ancestors = {"xbm"},
}

m["ca"] = {
	"คาตาลัน",
	"Q7026",
	"roa",
	otherNames = {"วาเลนเซีย", "Catalan", "Valencian"},
	scripts = Latn,
	ancestors = {"roa-oca"},
	sort_key = {
		from = {"à", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "l·l"},
		to   = {"a", "e"   , "i"   , "o"   , "u"   , "c", "ll" }} ,
}

m["ce"] = {
	"เชเชน",
	"Q33350",
	"cau-nkh",
	otherNames = {"Chechen"},
	scripts = Cyrl,
	translit_module = "ce-translit",
	override_translit = true,
	entry_name = {
		from = {MACRON},
		to   = {}},
}

m["ch"] = {
	"ชามอร์โร",
	"Q33262",
	"poz-sus",
	otherNames = {"Chamorro", "Chamoru"},
	scripts = Latn,
}

m["co"] = {
	"คอร์ซิกา",
	"Q33111",
	"roa",
	otherNames = {"Corsican", "Corsu"},
	scripts = Latn,
}

m["cr"] = {
	"ครี",
	"Q33390",
	"alg",
	otherNames = {"Cree"},
	scripts = {"Cans", "Latn"},
	translit_module = "cr-translit",
}

m["cs"] = {
	"เช็ก",
	"Q9056",
	"zlw",
	otherNames = {"Czech"},
	scripts = Latn,
	ancestors = {"zlw-ocs"},
	sort_key = {
		from = {"á", "é", "í", "ó", "[úů]", "ý"},
		to   = {"a", "e", "i", "o", "u"   , "y"}} ,
}

m["cu"] = {
	"สลาโวนิกคริสตจักรเก่า",
	"Q35499",
	"zls",
	otherNames = {"สลาวิกคริสตจักรเก่า", "Old Church Slavonic", "Old Church Slavic"},
	scripts = {"Cyrs", "Glag"},
	translit_module = "Cyrs-Glag-translit",
	entry_name = {
		from = {u(0x0484)}, -- kamora
		to   = {}},
	sort_key = {
		from = {"оу", "є"},
		to   = {"у" , "е"}} ,
}

m["cv"] = {
	"ชูวัช",
	"Q33348",
	"trk-ogr",
	otherNames = {"Chuvash"},
	scripts = Cyrl,
	translit_module = "cv-translit",
	override_translit = true,
}

m["cy"] = {
	"เวลส์",
	"Q9309",
	"cel-bry",
	otherNames = {"Welsh"},
	scripts = Latn,
	ancestors = {"wlm"},
	sort_key = {
		from = {"[âáàä]", "ch", "dd", "[êéèë]", "ff", "ngh", "[îíìï]", "ll", "[ôóòö]", "ph", "rh", "th", "[ûúùü]", "[ŵẃẁẅ]", "[ŷýỳÿ]", "'"},
		to   = {"a"	    , "c~", "d~", "e"	  , "f~", "g~h", "i"	  , "l~", "o"	  , "p~", "r~", "t~", "u"	  , "w"     , "y"	       }} ,
	standardChars = "A-IL-PR-UWYa-il-pr-uwy0-9ÂâÊêÎîÔôÛûŴŵŶŷ" .. PUNCTUATION,
}

m["da"] = {
	"เดนมาร์ก",
	"Q9035",
	"gmq",
	otherNames = {"เดนิช", "Danish"},
	scripts = Latn,
	ancestors = {"gmq-oda"},
}

m["de"] = {
	"เยอรมัน",
	"Q188",
	"gmw",
	otherNames = {"เยอรมันสูง", "เยอรมันสูงใหม่", "German", "High German", "New High German", "Deutsch"},
	scripts = {"Latn", "Latf"},
	ancestors = {"gmh"},
	sort_key = {
		from = {"[äàáâå]", "[ëèéê]", "[ïìíî]", "[öòóô]", "[üùúû]", "ß" },
		to   = {"a"	  , "e"	 , "i"	 , "o"	 , "u"	 , "ss"}} ,
	standardChars = "A-Za-z0-9ÄäÖöÜüß" .. PUNCTUATION,
}

m["dv"] = {
	"ดิเวฮิ",
	"Q32656",
	"inc",
	otherNames = {"มัลดีฟส์", "มาห์ล", "Dhivehi", "Divehi", "Mahal", "Mahl", "Maldivian"},
	scripts = {"Thaa"},
	ancestors = {"pmh"},	-- or Helu?
	translit_module = "Thaa-translit",
	override_translit = true,
}

m["dz"] = {
	"ซองคา",
	"Q33081",
	"tbq",
	otherNames = {"Dzongkha"},
	scripts = {"Tibt"},
	ancestors = {"xct"},
	translit_module = "Tibt-translit",
	override_translit = true,
}

m["ee"] = {
	"เอเว",
	"Q30005",
	"alv-von",
	otherNames = {"Ewe"},
	scripts = Latn,
}

m["el"] = {
	"กรีก",
	"Q9129",
	"grk",
	otherNames = {"กรีกใหม่", "Greek", "Modern Greek", "Neo-Hellenic"},
	scripts = {"Grek", "Brai"},
	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"}} ,
	standardChars = "ͺ;΄-ώϜϝ" .. PUNCTUATION .. "ἀ-῾",
}

m["en"] = {
	"อังกฤษ",
	"Q1860",
	"gmw",
	otherNames = {"อังกฤษใหม่", "English", "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 of subsumed dialects which once had codes
	scripts = {"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion
	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"] = {
	"เอสเปรันโต",
	"Q143",
	"art",
	otherNames = {"Esperanto"},
	scripts = Latn,
	translit_module = "eo-translit",
	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"] = {
	"สเปน",
	"Q1321",
	"roa",
	otherNames = {"คาสตีล", "Spanish", "Castilian", "Amazonian Spanish", "Amazonic Spanish", "Loreto-Ucayali Spanish"},
	scripts = {"Latn", "Brai"},
	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"] = {
	"เอสโตเนีย",
	"Q9072",
	"fiu-fin",
	otherNames = {"Estonian"},
	scripts = Latn,
}

m["eu"] = {
	"บาสก์",
	"Q8752",
	"euq",
	otherNames = {"Basque", "Euskara"},
	scripts = Latn,
}

m["fa"] = {
	"เปอร์เซีย",
	"Q9168",
	"ira-wes",
	otherNames = {"ฟาร์ซี", "เปอร์เซียใหม่", "Persian", "Farsi", "New Persian", "Modern Persian", "Western Persian", "Iranian Persian", "Eastern Persian", "Dari", "Aimaq", "Aimak", "Aymaq", "Eimak"},
	scripts = {"fa-Arab"},
	ancestors = {"pal"}, -- "ira-mid"
	entry_name = {
		from = {u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)},
		to   = {}} ,
}

m["ff"] = {
	"ฟูลา",
	"Q33454",
	"alv-sng",
	otherNames = {"Fula", "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", "Adlm"},
}

m["fi"] = {
	"ฟินแลนด์",
	"Q1412",
	"fiu-fin",
	otherNames = {"ฟินนิช", "ซูโอมี", "Finnish", "Suomi", "Botnian"},
	scripts = Latn,
	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"] = {
	"ฟิจิ",
	"Q33295",
	"poz-occ",
	otherNames = {"Fijian"},
	scripts = Latn,
}

m["fo"] = {
	"แฟโร",
	"Q25258",
	"gmq",
	otherNames = {"Faroese"},
	scripts = Latn,
	ancestors = {"non"},
}

m["fr"] = {
	"ฝรั่งเศส",
	"Q150",
	"roa-oil",
	otherNames = {"ฝรั่งเศสใหม่", "French", "Modern French"},
	scripts = {"Latn", "Brai"},
	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"] = {
	"ฟรีเชียตะวันตก",
	"Q27175",
	"gmw-fri",
	otherNames = {"ฟรีเชีย", "West Frisian", "Western Frisian", "Frisian"},
	scripts = Latn,
	ancestors = {"ofs"},
}

m["ga"] = {
	"ไอริช",
	"Q9142",
	"cel-gae",
	otherNames = {"ไอร์แลนด์", "แกลิกแบบไอร์แลนด์", "Irish", "Irish Gaelic"},
	scripts = Latn,
	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"}} ,
	standardChars = "A-IL-PR-Ua-il-pr-u0-9ÁáÉéÍíÓóÚú" .. PUNCTUATION,
}

m["gd"] = {
	"แกลิกแบบสกอตแลนด์",
	"Q9314",
	"cel-gae",
	otherNames = {"Scottish Gaelic", "Gàidhlig", "Highland Gaelic", "Scots Gaelic", "Scottish"},
	scripts = Latn,
	ancestors = {"mga"},
	sort_key = {
		from = {"[áà]", "[éè]", "[íì]", "[óò]", "[úù]", "[ýỳ]"},
		to   = {"a"   , "e"   , "i"   , "o"   , "u"   , "y"   }} ,
	standardChars = "A-IL-PR-Ua-il-pr-u0-9ÀàÈèÌìÒòÙù" .. PUNCTUATION,
}

m["gl"] = {
	"กาลิเซีย",
	"Q9307",
	"roa",
	otherNames = {"Galician"},
	scripts = Latn,
	ancestors = {"roa-opt"},
	sort_key = {
		from = {"á", "é", "í", "ó", "ú"},
		to   = {"a", "e", "i", "o", "u"}} ,
}

m["gn"] = {
	"กัวรานี",
	"Q35876",
	"tup-gua",
	otherNames = {"Guaraní"},
	scripts = Latn,
}

m["gu"] = {
	"คุชราต",
	"Q5137",
	"inc",
	otherNames = {"Gujarati"},
	scripts = {"Gujr"},
	ancestors = {"inc-ogu"},
	translit_module = "Gujr-translit",
}

m["gv"] = {
	"แมงซ์",
	"Q12175",
	"cel-gae",
	otherNames = {"แกลิกแบบเกาะแมน", "Manx", "Manx Gaelic"},
	scripts = Latn,
	ancestors = {"mga"},
	sort_key = {
		from = {"ç", "-"},
		to   = {"c"}} ,
	standardChars = "A-WYÇa-wyç0-9" .. PUNCTUATION,
}

m["ha"] = {
	"เฮาซา",
	"Q56475",
	"cdc-wst",
	otherNames = {"Hausa"},
	scripts = {"Latn", "Arab"},
    sort_key = {
		from = {"ɓ",   "ɗ",   "ƙ",  "'y", "ƴ",  "'" },
		to   = {"b~" , "d~"	, "k~", "y~", "y~", ""  }},
    entry_name = {
		from = {"R̃", "r̃", "À", "à", "È", "è", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Î", "î", "Ô", "ô", "Û", "û", "Ā", "ā", "Ē", "ē", "Ī", "ī", "Ō", "ō", "Ū", "ū", "Á", "á", "É", "é", "Í", "í", "Ó", "ó", "Ú", "ú", "Ā̀", "ā̀", "Ḕ", "ḕ", "Ī̀", "ī̀", "Ṑ", "ṑ", "Ū̀", "ū̀", GRAVE, ACUTE},
		to   = {"R", "r", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "I", "i", "O", "o", "U", "u"}},
}

m["he"] = {
	"ฮีบรู",
	"Q9288",
	"sem-can",
	otherNames = {"อิฟริท", "Hebrew", "Ivrit"},
	scripts = {"Hebr", "Phnx", "Brai"},
	translit_module = "he-translit",
	entry_name = {
		from = {"[" .. u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. "]"},
		to   = {}} ,
}

m["hi"] = {
	"ฮินดี",
	"Q1568",
	"inc",
	otherNames = {"Hindi", "Hindavi", "Khariboli", "Khari Boli", "Manak Hindi"},
	scripts = {"Deva", "Kthi", "Newa"},
	ancestors = {"inc-ohi"},
	translit_module = "Deva-translit",
}

m["ho"] = {
	"ฮีรีโมตู",
	"Q33617",
	"crp",
	otherNames = {"Hiri Motu", "Pidgin Motu", "Police Motu"},
	scripts = Latn,
	ancestors = {"meu"},
}

m["ht"] = {
	"ไฮติครีโอล",
	"Q33491",
	"crp",
	otherNames = {"ไฮติ", "ครีโอล", "Haitian Creole", "Creole", "Haitian", "Kreyòl"},
	scripts = Latn,
}

m["hu"] = {
	"ฮังการี",
	"Q9067",
	"urj-ugr",
	otherNames = {"มอยอร์", "Hungarian", "Magyar"},
	scripts = {"Latn", "Hung"},
	ancestors = {"ohu"},
	sort_key = {
		from = {"á", "é", "í", "ó", "ú", "ő", "ű"},
		to   = {"a", "e", "i", "o", "u", "ö", "ü"}} ,
}

m["hy"] = {
	"อาร์มีเนีย",
	"Q8785",
	"hyx",
	otherNames = {"อาร์มีเนียใหม่", "อาร์มีเนียตะวันออก", "อาร์มีเนียตะวันตก", "Armenian", "Modern Armenian", "Eastern Armenian", "Western Armenian"},
	scripts = {"Armn", "Brai"},
	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"] = {
	"เฮเรโร",
	"Q33315",
	"bnt",
	otherNames = {"Herero"},
	scripts = Latn,
}

m["ia"] = {
	"อินเทอร์ลิงกวา",
	"Q35934",
	"art",
	otherNames = {"Interlingua"},
	scripts = Latn,
}

m["id"] = {
	"อินโดนีเซีย",
	"Q9240",
	"poz-mly",
	otherNames = {"Indonesian"},
	scripts = Latn,
	ancestors = {"ms"},
}

m["ie"] = {
	"Interlingue",
	"Q35850",
	"art",
	otherNames = {"Occidental"},
	scripts = Latn,
}

m["ig"] = {
	"อิกโบ",
	"Q33578",
	"nic-bco",
	otherNames = {"Igbo"},
	scripts = Latn,
}

m["ii"] = {
	"Sichuan Yi",
	"Q34235",
	"tbq-lol",
	otherNames = {"Nuosu", "Nosu", "Northern Yi", "Liangshan Yi"},
	scripts = {"Yiii"},
	--translit_module = "ii-translit",
}

m["ik"] = {
	"Inupiak",
	"Q27183",
	"esx-inu",
	otherNames = {"Inupiaq", "Iñupiaq", "Inupiatun"},
	scripts = Latn,
}

m["io"] = {
	"อิดอ",
	"Q35224",
	"art",
	otherNames = {"Ido"},
	scripts = Latn,
}

m["is"] = {
	"ไอซ์แลนด์",
	"Q294",
	"gmq",
	otherNames = {"Icelandic"},
	scripts = Latn,
	ancestors = {"non"},
}

m["it"] = {
	"อิตาลี",
	"Q652",
	"roa",
	otherNames = {"อิตาเลียน", "Italian"},
	scripts = Latn,
	sort_key = {
		from = {"[àáâäå]", "[èéêë]", "[ìíîï]", "[òóôö]", "[ùúûü]"},
		to   = {"a"	  , "e"	 , "i"	 , "o"	 , "u"	 }} ,
}

m["iu"] = {
	"อินุกติตุต",
	"Q29921",
	"esx-inu",
	otherNames = {"Inuktitut", "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"},
	translit_module = "iu-translit",
	override_translit = true,
}

m["ja"] = {
	"ญี่ปุ่น",
	"Q5287",
	"jpx",
	otherNames = {"ญี่ปุ่นใหม่", "Japanese", "Modern Japanese", "Nipponese", "Nihongo"},
	scripts = {"Jpan", "Latn", "Hira", "Brai"},
	ancestors = {"ojp"},
	--[=[
	-- Handled by jsort function in [[Module:ja]].
	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"] = {
	"ชวา",
	"Q33549",
	"poz-sus",
	otherNames = {"Javanese"},
	scripts = {"Latn", "Java"},
	translit_module = "Java-translit",
	ancestors = {"kaw"},
	--link_tr = true,
}

m["ka"] = {
	"จอร์เจีย",
	"Q8108",
	"ccs-gzn",
	otherNames = {"Georgian", "Kartvelian", "Judeo-Georgian", "Kivruli", "Gruzinic"},
	scripts = {"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian
	ancestors = {"oge"},
	translit_module = "Geor-translit",
	override_translit = true,
	entry_name = {
		from = {"̂"},
		to   = {""}},
}

m["kg"] = {
	"คองโก",
	"Q33702",
	"bnt",
	otherNames = {"Kongo", "Kikongo", "Koongo", "Laari", "San Salvador Kongo", "Yombe"},
	scripts = Latn,
}

m["ki"] = {
	"Kikuyu",
	"Q33587",
	"bnt",
	otherNames = {"Gikuyu", "Gĩkũyũ"},
	scripts = Latn,
}

m["kj"] = {
	"Kwanyama",
	"Q1405077",
	"bnt",
	otherNames = {"Kuanyama", "Oshikwanyama"},
	scripts = Latn,
}

m["kk"] = {
	"คาซัค",
	"Q9252",
	"trk-kip",
	otherNames = {"คาซัคสถาน", "Kazakh"},
	scripts = {"Cyrl", "Latn", "kk-Arab"},
	translit_module = "kk-translit",
	override_translit = true,
}

m["kl"] = {
	"กรีนแลนด์",
	"Q25355",
	"esx-inu",
	otherNames = {"กะลาลลิซุต", "Greenlandic", "Kalaallisut"},
	scripts = Latn,
}

m["km"] = {
	"เขมร",
	"Q9205",
	"mkh",
	otherNames = {"กัมพูชา", "Khmer", "Cambodian"},
	scripts = {"Khmr"},
	ancestors = {"mkh-mkm"},
	translit_module = "Khmr-translit",
}

m["kn"] = {
	"กันนาดา",
	"Q33673",
	"dra",
	otherNames = {"Kannada"},
	scripts = {"Knda"},
	ancestors = {"dra-mkn"},
	translit_module = "Knda-translit",
}

m["ko"] = {
	"เกาหลี",
	"Q9176",
	"qfa-kor",
	otherNames = {"เกาหลีใหม่", "Korean", "Modern Korean"},
	scripts = {"Kore", "Hani", "Brai"},
	ancestors = {"okm"},
	translit_module = "ko-translit",
}

m["kr"] = {
	"Kanuri",
	"Q36094",
	"ssa-sah",
	otherNames = {"Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"},
	scripts = {"Latn", "Arab"},
	sort_key = {
		from = {"ny", "ǝ", "sh"},
		to   = {"n~", "e~", "s~"}} , -- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically
	entry_name = {
		from = {"À", "à", "È", "è", "Ǝ̀", "ǝ̀", "Ì", "ì", "Ò", "ò", "Ù", "ù", "Â", "â", "Ê", "ê", "Ǝ̂", "ǝ̂", "Î", "î", "Ô", "ô", "Û", "û", "Ă", "ă", "Ĕ", "ĕ", "Ǝ̆", "ǝ̆", "Ĭ", "ĭ", "Ŏ", "ŏ", "Ŭ", "ŭ", "Á", "á", "É", "é", "Ǝ́", "ǝ́", "Í", "í", "Ó", "ó", "Ú", "ú", GRAVE, ACUTE},
		to   = {"A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u", "A", "a", "E", "e", "Ǝ", "ǝ", "I", "i", "O", "o", "U", "u"}},
}

m["ks"] = {
	"แคชเมียร์",
	"Q33552",
	"inc-dar",
	otherNames = {"กัศมีร์", "Kashmiri"},
	scripts = {"ks-Arab", "Deva"},
}

m["ku"] = {
	"เคิร์ด",
	"Q36368",
	"ira-wes",
	otherNames = {"Kurdish"},
	scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"},
}

-- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT

m["kw"] = {
	"คอร์นวอลล์",
	"Q25289",
	"cel-bry",
	otherNames = {"คอร์นิช", "Cornish"},
	scripts = Latn,
	ancestors = {"cnx"},
}

m["ky"] = {
	"คีร์กีซ",
	"Q9255",
	"trk-kip",
	otherNames = {"คีร์กีซสถาน", "Kyrgyz", "Kirghiz", "Kirgiz"},
	scripts = {"Cyrl", "Latn", "Arab"},
	translit_module = "ky-translit",
	override_translit = true,
}

m["la"] = {
	"ละติน",
	"Q397",
	"itc",
	otherNames = {"ลาติน", "Latin"},
	scripts = Latn,
	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"}},
	standardChars = "A-Za-zÆ挜Ā-ăĒ-ĕĪ-ĭŌ-ŏŪ-ŭȲȳ" .. MACRON .. BREVE .. PUNCTUATION,
}

m["lb"] = {
	"ลักเซมเบิร์ก",
	"Q9051",
	"gmw",
	otherNames = {"Luxembourgish"},
	scripts = Latn,
	ancestors = {"gmh"},
}

m["lg"] = {
	"ลูกันดา",
	"Q33368",
	"bnt",
	otherNames = {"Luganda", "Ganda", "Oluganda"},
	scripts = Latn,
	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"] = {
	"ลิมเบิร์ก",
	"Q102172",
	"gmw",
	otherNames = {"Limburgish", "Limburgan", "Limburgian", "Limburgic"},
	scripts = Latn,
	ancestors = {"dum"},
}

m["ln"] = {
	"Lingala",
	"Q36217",
	"bnt",
	otherNames = {"Ngala"},
	scripts = Latn,
}

m["lo"] = {
	"ลาว",
	"Q9211",
	"tai-swe",
	otherNames = {"Lao", "Laotian"},
	scripts = {"Laoo"},
	translit_module = "Laoo-translit",
	sort_key = {
		from = {"ຼ", "ຽ", "ໜ", "ໝ"},
		to   = {"ລ", "ຍ", "ຫນ", "ຫມ"}},
}

m["lt"] = {
	"ลิทัวเนีย",
	"Q9083",
	"bat",
	otherNames = {"Lithuanian"},
	scripts = Latn,
	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"] = {
	"Luba-Katanga",
	"Q36157",
	"bnt",
	scripts = Latn,
}

m["lv"] = {
	"ลัตเวีย",
	"Q9078",
	"bat",
	otherNames = {"Latvian", "Lettish", "Lett"},
	scripts = Latn,
	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"] = {
	"มาลากาซี",
	"Q7930",
	"poz-bre",
	otherNames = {"Malagasy", "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"},
	scripts = Latn,
}

m["mh"] = {
	"มาร์แชล",
	"Q36280",
	"poz-mic",
	otherNames = {"Marshallese"},
	scripts = Latn,
	sort_key = {
		from = {"ā" , "ļ" , "m̧" , "ņ" , "n̄"  , "o̧" , "ō"  , "ū" },
		to   = {"a~", "l~", "m~", "n~", "n~~", "o~", "o~~", "u~"}} ,
}

m["mi"] = {
	"มาวรี",
	"Q36451",
	"poz-pep",
	otherNames = {"เมารี", "Maori", "Māori"},
	scripts = Latn,
}

m["mk"] = {
	"มาซิโดเนีย",
	"Q9296",
	"zls",
	otherNames = {"Macedonian"},
	scripts = Cyrl,
	--translit_module = "mk-translit",
	entry_name = {
		from = {ACUTE},
		to   = {}},
}

m["ml"] = {
	"มาลายาลัม",
	"Q36236",
	"dra",
	otherNames = {"Malayalam"},
	scripts = {"Mlym"},
	translit_module = "Mlym-translit",
	override_translit = true,
}

m["mn"] = {
	"มองโกเลีย",
	"Q9246",
	"xgn",
	otherNames = {"Mongolian", "Khalkha Mongolian"},
	scripts = {"Cyrl", "Mong", "Soyo", "Zanb"}, -- entries in Soyo or Zanb might require prior discussion
	ancestors = {"cmg"},
	translit_module = "mn-translit",
	override_translit = true,
}

-- "mo" IS TREATED AS "ro", SEE WT:LT

m["mr"] = {
	"มราฐี",
	"Q1571",
	"inc",
	otherNames = {"Marathi"},
	scripts = {"Deva", "Modi"},
	ancestors = {"omr"},
	translit_module = "Deva-translit",
}

m["ms"] = {
	"มาเลย์",
	"Q9237",
	"poz-mly",
	otherNames = {"มลายู", "มลายูมาตรฐาน", "Malay", "Malaysian", "Standard Malay", "Orang Seletar", "Orang Kanaq", "Jakun", "Temuan"},
	scripts = {"Latn", "ms-Arab"},
}

m["mt"] = {
	"มอลตา",
	"Q9166",
	"sem-arb",
	otherNames = {"Maltese"},
	scripts = Latn,
	ancestors = {"sqr"},
}

m["my"] = {
	"พม่า",
	"Q9228",
	"tbq-brm",
	otherNames = {"เมียนมา", "Burmese", "Myanmar"},
	scripts = {"Mymr"},
	ancestors = {"obr"},
	translit_module = "Mymr-translit",
	override_translit = true,
}

m["na"] = {
	"นาอูรู",
	"Q13307",
	"poz-mic",
	otherNames = {"Nauruan", "Nauru"},
	scripts = Latn,
}

m["nb"] = {
	"บุ๊กมอล",
	"Q25167",
	"gmq",
	otherNames = {"Norwegian Bokmål", "Bokmål"},
	scripts = Latn,
	ancestors = {"gmq-mno"},
	wikimedia_codes = {"no"},
}

m["nd"] = {
	"Northern Ndebele",
	"Q35613",
	"bnt-ngu",
	otherNames = {"North Ndebele"},
	scripts = Latn,
	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"] = {
	"เนปาล",
	"Q33823",
	"inc-pah",
	otherNames = {"Nepali", "Nepalese"},
	scripts = {"Deva", "Newa"},
	translit_module = "Deva-translit",
	ancestors = {"psu"},
}

m["ng"] = {
	"Ndonga",
	"Q33900",
	"bnt",
	scripts = Latn,
}

m["nl"] = {
	"ดัตช์",
	"Q7411",
	"gmw",
	otherNames = {"เนเธอร์แลนด์", "เฟลมิช", "Dutch", "Netherlandic", "Flemish"},
	scripts = Latn,
	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"] = {
	"นือนอสก์",
	"Q25164",
	"gmq",
	otherNames = {"Norwegian Nynorsk", "New Norwegian", "Nynorsk"},
	scripts = Latn,
	ancestors = {"gmq-mno"},
}

m["no"] = {
	"นอร์เวย์",
	"Q9043",
	"gmq",
	otherNames = {"Norwegian"},
	scripts = Latn,
	ancestors = {"gmq-mno"},
}

m["nr"] = {
	"Southern Ndebele",
	"Q36785",
	"bnt-ngu",
	otherNames = {"South Ndebele"},
	scripts = Latn,
	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"] = {
	"นาวาโฮ",
	"Q13310",
	"apa",
	otherNames = {"Navajo", "Navaho", "Diné bizaad"},
	scripts = {"nv-Latn"},
	sort_key = {
		from = {"[áą]", "[éę]", "[íį]", "[óǫ]", "ń", "^n([djlt])", "ł" , "[ʼ’']", ACUTE},
		to   = {"a"   , "e"   , "i"   , "o"   , "n", "ni%1"	  , "l~"}}, -- the tilde is used to guarantee that ł will always be sorted after all other words with l
}

m["ny"] = {
	"เชวา",
	"Q33273",
	"bnt",
	otherNames = {"ชิเชวา", "Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"},
	scripts = Latn,
	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"] = {
	"อ็อกซิตัน",
	"Q14185",
	"roa",
	otherNames = {"พรอว็องส์", "Occitan", "Provençal", "Auvergnat", "Auvernhat", "Gascon", "Languedocien", "Lengadocian", "Shuadit", "Chouhadite", "Chouhadit", "Chouadite", "Chouadit", "Shuhadit", "Judeo-Provençal", "Judeo-Provencal", "Judeo-Comtadin"},
	scripts = {"Latn", "Hebr"},
	ancestors = {"pro"},
	sort_key = {
		from = {"[àá]", "[èé]", "[íï]", "[òó]", "[úü]", "ç", "([lns])·h"},
		to   = {"a"   , "e"   , "i"   , "o"   , "u"   , "c", "%1h"	  }} ,
}

m["oj"] = {
	"โอจิบเว",
	"Q33875",
	"alg",
	otherNames = {"Ojibwe", "Chippewa", "Ojibway", "Ojibwemowin", "Southwestern Ojibwa"},
	scripts = {"Cans", "Latn"},
}

m["om"] = {
	"ออโรโม",
	"Q33864",
	"cus",
	otherNames = {"Oromo", "Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"},
	scripts = {"Latn", "Ethi"},
}

m["or"] = {
	"โอริยา",
	"Q33810",
	"inc",
	otherNames = {"โอเดีย", "Oriya", "Odia", "Oorya"},
	scripts = {"Orya"},
	ancestors = {"inc-mgd"},
	translit_module = "Orya-translit",
}

m["os"] = {
	"ออสซีเซีย",
	"Q33968",
	"ira-eas",
	otherNames = {"Ossetian", "Ossete", "Ossetic", "Digor", "Iron"},
	scripts = {"Cyrl", "Geor", "Latn"},
	ancestors = {"oos"},
	translit_module = "os-translit",
	override_translit = true,
	entry_name = {
		from = {GRAVE, ACUTE},
		to   = {}} ,
}

m["pa"] = {
	"ปัญจาบ",
	"Q58635",
	"inc",
	otherNames = {"ปัญจาบี", "Punjabi", "Panjabi"},
	scripts = {"Guru", "Arab", "Deva"},
	ancestors = {"psu"},
	translit_module = "translit-redirect",
}

m["pi"] = {
	"บาลี",
	"Q36727",
	"inc",
	otherNames = {"บาฬี", "ปาลิ", "ปาลี", "ปาฬิ", "ปาฬี", "Pali"},
	scripts = {"Thai", "Brah", "Deva", "Beng", "Sinh", "Mymr", "Lana", "Laoo", "Khmr", "Latn"},
	ancestors = {"sa"},
	translit_module = "translit-redirect",
	sort_key = {
		from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "[ṇñṅ]", "ṭ", u(0xFE00)},
		to   = {"a", "i", "u", "d", "l", "m"   , "n"	, "t"}} ,
	entry_name = {
		from = {u(0xFE00)},
		to   = {}},
}

m["pl"] = {
	"โปแลนด์",
	"Q809",
	"zlw",
	otherNames = {"โปลิช", "Polish"},
	scripts = Latn,
	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"] = {
	"พัชโต",
	"Q58680",
	"ira-eas",
	otherNames = {"พัชโตกลาง", "พัชโตเหนือ", "พัชโตใต้", "Pashto", "Pashtun", "Pushto", "Pashtu", "Central Pashto", "Northern Pashto", "Southern Pashto", "Pukhto", "Pakhto", "Pakkhto", "Afghani"},
	scripts = {"ps-Arab"},
}

m["pt"] = {
	"โปรตุเกส",
	"Q5146",
	"roa",
	otherNames = {"โปรตุเกสใหม่", "Portuguese", "Modern Portuguese"},
	scripts = {"Latn", "Brai"},
	ancestors = {"roa-opt"},
	sort_key = {
		from = {"[àãáâä]", "[èẽéêë]", "[ìĩíï]", "[òóôõö]", "[üúùũ]", "ç", "ñ"},
		to   = {"a"	  , "e"	  , "i"	 , "o"	  , "u"	 , "c", "n"}} ,
}

m["qu"] = {
	"เกชัว",
	"Q5218",
	"qwe",
	otherNames = {"Quechua"},
	scripts = Latn,
}

m["rm"] = {
	"Romansch",
	"Q13199",
	"roa-rhe",
	otherNames = {"Romansh", "Rumantsch", "Romanche"},
	scripts = Latn,
}

m["ro"] = {
	"โรมาเนีย",
	"Q7913",
	"roa-eas",
	otherNames = {"รูมาเนีย", "Romanian", "Daco-Romanian", "Roumanian", "Rumanian"},
	scripts = {"Latn", "Cyrl"},
	sort_key = {
        from = {"ă" , "â"  , "î" , "ș" , "ț" },
        to   = {"a~", "a~~", "i~", "s~", "t~"}},
}

m["ru"] = {
	"รัสเซีย",
	"Q7737",
	"zle",
	otherNames = {"Russian"},
	scripts = {"Cyrl", "Brai"},
	translit_module = "ru-translit-Thai",
	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"] = {
	"Rwanda-Rundi",
	"Q33573",
	"bnt",
	otherNames = {"Rwanda", "Kinyarwanda", "Rundi", "Kirundi", "Ha", "Giha", "Hangaza", "Vinza", "Shubi", "Subi"},
	scripts = Latn,
}

m["sa"] = {
	"สันสกฤต",
	"Q11059",
	"inc",
	otherNames = {"Sanskrit"},
	scripts = {"Deva", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Mlym", "Mymr", "Newa", "Orya", "Shrd", "Sinh", "Taml", "Telu", "Thai", "Tibt"},
	sort_key = {
		from = {u(0xFE00)},
		to   = {}} ,
	entry_name = {
		from = {u(0xFE00)},
		to   = {}},
	translit_module = "translit-redirect",
}

m["sc"] = {
	"ซาร์ดิเนีย",
	"Q33976",
	"roa",
	otherNames = {"Sardinian", "Campidanese", "Campidanese Sardinian", "Logudorese", "Logudorese Sardinian", "Nuorese", "Nuorese Sardinian"},
	scripts = Latn,
}

m["sd"] = {
	"สินธี",
	"Q33997",
	"inc",
	otherNames = {"Sindhi"},
	scripts = {"sd-Arab", "Deva", "Sind", "Khoj"},
	ancestors = {"psu"},
}

m["se"] = {
	"Northern Sami",
	"Q33947",
	"smi",
	otherNames = {"North Sami", "Northern Saami", "North Saami"},
	scripts = Latn,
	entry_name = {
		from = {"ạ", "[ēẹ]", "ī", "[ōọ]", "ū", "ˈ"},
		to   = {"a", "e"   , "i", "o"   , "u"} },
	sort_key = {
		from = {"á" , "č" , "đ" , "ŋ" , "š" , "ŧ" , "ž" },
		to   = {"a²", "c²", "d²", "n²", "s²", "t²", "z²"} },
	standardChars = "A-PR-VZa-pr-vz0-9ÁáČčĐđŊŋŠšŦŧŽž" .. PUNCTUATION,
}

m["sg"] = {
	"Sango",
	"Q33954",
	"crp",
	scripts = Latn,
}

m["sh"] = {
	"เซอร์โบ-โครเอเชีย",
	"Q9301",
	"zls",
	otherNames = {"บอสเนีย", "โครเอเชีย", "มอนเตเนโกร", "เซอร์เบีย", "Serbo-Croatian", "BCS", "Croato-Serbian", "Serbocroatian", "Bosnian", "Croatian", "Montenegrin", "Serbian"},
	scripts = {"Latn", "Cyrl"},
	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"] = {
	"สิงหล",
	"Q13267",
	"inc",
	otherNames = {"Sinhalese", "Singhalese", "Sinhala"},
	scripts = {"Sinh"},
	ancestors = {"elu-prk"},
	translit_module = "Sinh-translit",
	override_translit = true,
}

m["sk"] = {
	"สโลวัก",
	"Q9058",
	"zlw",
	otherNames = {"Slovak"},
	scripts = Latn,
	sort_key = {
		from = {"[áä]", "é", "í", "[óô]", "ú", "ý", "ŕ", "ĺ", "[" .. DIAER .. ACUTE .. CIRC .. "]"},
		to   = {"a"   , "e", "i", "o"   , "u", "y", "r", "l", ""}} ,
}

m["sl"] = {
	"สโลวีเนีย",
	"Q9063",
	"zls",
	otherNames = {"สโลเวเนีย", "สโลวีน", "Slovene", "Slovenian"},
	scripts = Latn,
	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"] = {
	"ซามัว",
	"Q34011",
	"poz-pnp",
	otherNames = {"Samoan"},
	scripts = Latn,
}

m["sn"] = {
	"Shona",
	"Q34004",
	"bnt",
	scripts = Latn,
}

m["so"] = {
	"โซมาลี",
	"Q13275",
	"cus",
	otherNames = {"Somali"},
	scripts = {"Latn", "Arab", "Osma"},
	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"] = {
	"แอลเบเนีย",
	"Q8748",
	"sqj",
	otherNames = {"Albanian"},
	scripts = {"Latn", "Elba"},
	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"] = {
	"Swazi",
	"Q34014",
	"bnt-ngu",
	otherNames = {"Swati"},
	scripts = Latn,
	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"] = {
	"ซูทู",
	"Q34340",
	"bnt",
	otherNames = {"โซโท", "Sotho", "Sesotho", "Southern Sesotho", "Southern Sotho"},
	scripts = Latn,
}

m["su"] = {
	"ซุนดา",
	"Q34002",
	"poz-msa",
	otherNames = {"Sundanese"},
	scripts = {"Latn", "Sund"},
	translit_module = "su-translit",
}

m["sv"] = {
	"สวีเดน",
	"Q9027",
	"gmq",
	otherNames = {"สวีดิช", "Swedish"},
	scripts = Latn,
	ancestors = {"gmq-osw"},
}

m["sw"] = {
	"สวาฮีลี",
	"Q7838",
	"bnt",
	otherNames = {"Swahili", "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"},
	sort_key = {
		from = {"ng'", "^-"},
		to   = {"ngz"}} ,
}

m["ta"] = {
	"ทมิฬ",
	"Q5885",
	"dra",
	otherNames = {"Tamil"},
	scripts = {"Taml"},
	ancestors = {"oty"},
	translit_module = "Taml-translit",
	override_translit = true,
}

m["te"] = {
	"เตลูกู",
	"Q8097",
	"dra",
	otherNames = {"Telugu"},
	scripts = {"Telu"},
	translit_module = "Telu-translit",
	override_translit = true,
}

m["tg"] = {
	"ทาจิก",
	"Q9260",
	"ira-wes",
	otherNames = {"ทาจิกิสถาน", "ทาจิกเปอร์เซีย", "Tajik", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian"},
	scripts = {"Cyrl", "fa-Arab", "Latn"},
	ancestors = {"pal"}, -- same as "fa", see WT:T:AFA
	translit_module = "tg-translit",
	override_translit = true,
	sort_key = {
		from = {"Ё", "ё"},
		to   = {"Е" , "е"}} ,
	entry_name = {
		from = {ACUTE},
		to   = {}} ,
}

m["th"] = {
	"ไทย",
	"Q9217",
	"tai-swe",
	otherNames = {"สยาม", "ไทยกลาง", "Thai", "Siamese", "Central Thai"},
	scripts = {"Thai", "Brai"},
	--translit_module = "th-translit", !never use this line!
	sort_key = {
		from = {"%p"},
		to   = {""}} ,
}

m["ti"] = {
	"ตึกรึญญา",
	"Q34124",
	"sem-eth",
	otherNames = {"ทิกรินยา", "ทิกรีนยา", "Tigrinya"},
	scripts = {"Ethi"},
	translit_module = "Ethi-translit",
}

m["tk"] = {
	"เติร์กเมน",
	"Q9267",
	"trk-ogz",
	otherNames = {"เติร์กเมนิสถาน", "Turkmen"},
	scripts = {"Latn", "Cyrl"},
	entry_name = {
		from = {"ā", "ē", "ī", "ō", "ū", "ȳ", "ȫ", "ǖ", MACRON},
		to   = {"a", "e", "i", "o", "u", "y", "ö", "ü", ""}},
}

m["tl"] = {
	"ตากาล็อก",
	"Q34057",
	"phi",
	otherNames = {"Tagalog"},
	scripts = {"Latn", "Tglg"},
	entry_name = {
		from = {"[áàâ]", "[éèê]", "[íìî]", "[óòô]", "[úùû]", ACUTE, GRAVE, CIRC},
		to   = {"a"    , "e"    , "i"    , "o"    , "u"    }},
}

m["tn"] = {
	"สวานา",
	"Q34137",
	"bnt",
	otherNames = {"Tswana" ,"Setswana"},
	scripts = Latn,
}

m["to"] = {
	"ตองกา",
	"Q34094",
	"poz-pol",
	otherNames = {"Tongan"},
	scripts = Latn,
}

m["tr"] = {
	"ตุรกี",
	"Q256",
	"trk-ogz",
	otherNames = {"เติร์ก", "Turkish"},
	scripts = Latn,
	ancestors = {"ota"},
}

m["ts"] = {
	"Tsonga",
	"Q34327",
	"bnt",
	scripts = Latn,
}

m["tt"] = {
	"ตาตาร์",
	"Q25285",
	"trk-kip",
	otherNames = {"Tatar"},
	scripts = {"Cyrl", "Latn", "tt-Arab"},
	translit_module = "tt-translit",
	override_translit = true,
}

-- "tw" IS TREATED AS "ak", SEE WT:LT

m["ty"] = {
	"ตาฮีตี",
	"Q34128",
	"poz-pep",
	otherNames = {"Tahitian"},
	scripts = Latn,
}

m["ug"] = {
	"อุยกูร์",
	"Q13263",
	"trk",
	otherNames = {"Uyghur", "Uigur", "Uighur", "Uygur"},
	scripts = {"ug-Arab", "Latn", "Cyrl"},
	ancestors = {"chg"},
	translit_module = "ug-translit",
	override_translit = true,
}

m["uk"] = {
	"ยูเครน",
	"Q8798",
	"zle",
	otherNames = {"Ukrainian"},
	scripts = Cyrl,
	ancestors = {"orv"},
	translit_module = "uk-translit-Thai",
	entry_name = {
		from = {"Ѐ", "ѐ", "Ѝ", "ѝ", GRAVE, ACUTE},
		to   = {"Е", "е", "И", "и"}},
	standardChars = "ЄІЇА-ЩЫЬЮ-щыьюяєії" .. PUNCTUATION,
} 
m["ur"] = {
	"อูรดู",
	"Q1617",
	"inc",
	otherNames = {"Urdu"},
	scripts = {"ur-Arab"},
	ancestors = {"inc-sap"},
	entry_name = {
		from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)},
		to   = {}} ,
}

m["uz"] = {
	"อุซเบก",
	"Q9264",
	"trk",
	otherNames = {"อุซเบกิสถาน", "อุซเบกเหนือ", "อุซเบกใต้","Uzbek", "Northern Uzbek", "Southern Uzbek"},
	scripts = {"Latn", "Cyrl", "fa-Arab"},
	ancestors = {"chg"},
}

m["ve"] = {
	"เวนดา",
	"Q32704",
	"bnt",
	otherNames = {"Venda"},
	scripts = Latn,
}

m["vi"] = {
	"เวียดนาม",
	"Q9199",
	"mkh-vie",
	otherNames = {"ญวน", "อันนัม", "อนัม", "อนำ", "อานำ", "อานัม", "Vietnamese", "Annamese", "Annamite"},
	scripts = {"Latn", "Hani"},
	ancestors = {"mkh-mvi"},
	translit_module = "vi-translit",
	--sort_key = "vi-sortkey",
}

m["vo"] = {
	"โวลาปุก",
	"Q36986",
	"art",
	otherNames = {"Volapük"},
	scripts = Latn,
}

m["wa"] = {
	"วัลลูน",
	"Q34219",
	"roa-oil",
	otherNames = {"Walloon", "Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"},
	scripts = Latn,
	ancestors = {"fro"},
	sort_key = {
		from = {"[áàâäå]", "[éèêë]", "[íìîï]", "[óòôö]", "[úùûü]", "[ýỳŷÿ]", "ç", "'"},
		to   = {"a"	  , "e"	 , "i"	 , "o"	 , "u"	 , "y"	 , "c"}} ,
}

m["wo"] = {
	"โวลอฟ",
	"Q34257",
	"alv-sng",
	otherNames = {"Wolof", "Gambian Wolof"}, -- the subsumed dialect 'wof'
	scripts = {"Latn", "Arab"},
}

m["xh"] = {
	"Xhosa",
	"Q13218",
	"bnt-ngu",
	scripts = Latn,
	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"] = {
	"ยิดดิช",
	"Q8641",
	"gmw",
	otherNames = {"Yiddish"},
	scripts = {"Hebr"},
	ancestors = {"gmh"},
	--translit_module = "yi-translit",
}

m["yo"] = {
	"โยรูบา",
	"Q34311",
	"alv-von",
	otherNames = {"Yoruba"},
	scripts = Latn,
}

m["za"] = {
	"จ้วง",
	"Q13216",
	"tai",
	otherNames = {"จ้วงมาตรฐาน", "Zhuang", "Standard Zhuang", "Dai Zhuang", "Wenma Zhuang", "Wenma Thu", "Wenma", "Nong Zhuang", "Youjiang Zhuang", "Yongbei Zhuang", "Yang Zhuang", "Yongnan Zhuang", "Zuojiang Zhuang", "Central Hongshuihe Zhuang", "Eastern Hongshuihe Zhuang", "Guibei Zhuang", "Minz Zhuang", "Guibian Zhuang", "Liujiang Zhuang", "Lianshan Zhuang", "Liuqian Zhuang", "Qiubei Zhuang", "Chongzuo Zhuang", "Shangsi Zhuang"},
	scripts = {"Latn", "Hani"},
}

m["zh"] = {
	"จีน",
	"Q7850",
	"sit",
	otherNames = {"Chinese"},
	scripts = {"Hani", "Brai", "Nshu"},
	ancestors = {"ltc"},
	--sort_key = "zh-sortkey",
}

m["zu"] = {
	"ซูลู",
	"Q10179",
	"bnt-ngu",
	otherNames = {"อีซีซูลู", "Zulu", "isiZulu"},
	scripts = Latn,
	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