มอดูล:languages/data2

จาก วิกิพจนานุกรม พจนานุกรมเสรี
ไปยังการนำทาง ไปยังการค้นหา
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 DOUBLEINVBREVE = u(0x0361)

-- Puncuation to be used for standardChars field
local PUNCTUATION = ' !#$%&*+,-./:;<=>?@^_`|~\'()'

local Cyrl = {"Cyrl"}
local Latn = {"Latn"}
local LatnArab = {"Latn", "Arab"}

local m = {}

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

m["ab"] = {
	"อับฮาเซีย",
	"Q5111",
	"cau-abz",
	aliases = {"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-cen",
	aliases = {"เซนด์", "แบกเตรียเก่า", "Avestan", "Zend", "Old Bactrian"},
	scripts = {"Avst", "Gujr"},
	translit_module = "Avst-translit",
	--wikipedia_article = "Avestan",
}

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

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

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

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

m["ar"] = {
	"อาหรับ",
	"Q13955",
	"sem-arb",
	-- FIXME, some of the following are varieties but it's not clear which ones
	otherNames = {"อาหรับมาตรฐานใหม่", "อาหรับมาตรฐาน", "อาหรับวรรณกรรม", "อาหรับคลาสสิก", "Arabic", "Modern Standard Arabic", "Standard Arabic", "Literary Arabic", "Classical Arabic"},
	scripts = {"Arab", "Brai"},
	-- replace alif waṣl with alif
	-- remove tatweel and diacritics: fathatan, dammatan, kasratan, fatha,
	-- damma, kasra, shadda, sukun, superscript (dagger) alef
	entry_name = {
		from = {u(0x0671), u(0x0640), "[" .. u(0x064B) .. "-" .. u(0x0652) .. "]", u(0x0670)},
		to   = {u(0x0627)}},
	translit_module = "ar-translit",
	standardChars = "ء-غف-ْٰٱ" .. PUNCTUATION .. "٠-٩،؛؟٫٬ـ",
}

m["as"] = {
	"อัสสัม",
	"Q29401",
	"inc",
	aliases = {"Assamese", "Asamiya"},
	scripts = {"as-Beng"},
	ancestors = {"inc-mas"},
	translit_module = "Beng-translit",
}

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

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

m["az"] = {
	"อาเซอร์ไบจาน",
	"Q9292",
	"trk-ogz",
	aliases = {"อาเซอรี", "อาซารี", "เติร์กแบบอาเซอรี", "เติร์กแบบอาเซอร์ไบจาน", "Azerbaijani", "Azeri", "Azari", "Azeri Turkic", "Azerbaijani Turkic"},
	varieties = {
		{"อาเซอร์ไบจานเหนือ", "North Azerbaijani"},
		{"อาเซอร์ไบจานใต้", "South Azerbaijani"},
		{"Afshar", "Afshari", "Afshar Azerbaijani", "Afchar"},
		{"Qashqa'i", "Qashqai", "Kashkay"},
		"Sonqor"},
	scripts = {"Latn", "Cyrl", "fa-Arab"},
	ancestors = {"trk-oat"},
}

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

m["be"] = {
	"เบลารุส",
	"Q9091",
	"zle",
	aliases = {"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",
	aliases = {"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",
	aliases = {"Bihari"},
	scripts = {"Deva"},
	ancestors = {"inc-mgd"},
	translit_module = "Deva-translit",
}

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

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

m["bn"] = {
	"เบงกอล",
	"Q9610",
	"inc",
	aliases = {"เบงกาลี", "บังลา", "Bengali", "Bangla"},
	scripts = {"Beng", "Newa"},
	ancestors = {"inc-mbn"},
	translit_module = "Beng-translit",
}

m["bo"] = {
	"ทิเบต",
	"Q34271",
	"sit-tib",
	aliases = {"Tibetan"},
	varieties = {
		{"Amdo Tibetan", "Amdo"},
		"Dolpo",
		{"Khams", "Khams Tibetan"}, "Khamba",
		"Gola",
		"Humla",
		"Limi", {"Lhasa", "Lhasa Tibetan"}, "Lhomi", "Loke", "Lowa",
		"Mugom", "Mugu", "Mustang",
		"Nubri",
		"Panang",
		"Shing Saapa",
		"Thudam", "Tichurong", "Tseku",
		{"Ü", "Dbus"},
		"Walungge"}, -- and "Gyalsumdo", "Lower Manang"? "Kyirong"?
	scripts = {"Tibt"}, -- sometimes Deva?
	ancestors = {"xct"},
	translit_module = "Tibt-translit",
	override_translit = true,
}

m["br"] = {
	"เบรอตง",
	"Q12107",
	"cel-bry",
	aliases = {"Breton"},
	varieties = {{"Gwenedeg", "Vannetais"}, {"Kerneveg", "Cornouaillais"}, {"Leoneg", "Léonard"}, {"Tregerieg", "Trégorrois"}},
	scripts = Latn,
	ancestors = {"xbm"},
}

m["ca"] = {
	"คาตาลัน",
	"Q7026",
	"roa",
	aliases = {"Catalan"},
	-- don't list varieties here that are in [[Module:etymology languages/data]]
	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",
	aliases = {"Chechen"},
	scripts = Cyrl,
	translit_module = "ce-translit",
	override_translit = true,
	entry_name = {
		from = {MACRON},
		to   = {}},
}

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

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

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

m["cs"] = {
	"เช็ก",
	"Q9056",
	"zlw",
	aliases = {"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",
	aliases = {"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",
	aliases = {"Chuvash"},
	scripts = Cyrl,
	translit_module = "cv-translit",
	override_translit = true,
}

m["cy"] = {
	"เวลส์",
	"Q9309",
	"cel-bry",
	aliases = {"Welsh"},
	varieties = {"Cofi dialect", {"Dyfedeg", "Dyfed Welsh"}, {"Gwenhwyseg", "Gwent Welsh"}, {"Gwyndodeg", "Gwynedd Welsh"}, "North Wales Welsh", {"Powyseg", "Powys Welsh"}, "South Wales Welsh", "Patagonian 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",
	aliases = {"เดนิช", "Danish"},
	scripts = Latn,
	ancestors = {"gmq-oda"},
}

m["de"] = {
	"เยอรมัน",
	"Q188",
	"gmw",
	aliases = {"เยอรมันสูง", "เยอรมันสูงใหม่", "German", "High German", "New High German", "Deutsch"},
	varieties = {"Alsatian German", "American German",
		"Bavarian German", "Belgian German",
		"Central German",
		"DDR German",
		"East African German",
		"German German",
		"Hessian German",
		"Indiana German",
		"Liechtenstein German", "Lorraine German", "Luxembourgish German",
		"Namibian German", "Northern German",
		"Prussian German",
		"Silesia German", "South African German", "Southern German", "South Tyrolean German", "Switzerland German",
		"Texan German"},
	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"] = {
	"มัลดีฟส์",
	"Q32656",
	"inc",
	aliases = {"ดิเวฮิ", "Dhivehi", "Divehi", "Maldivian"},
	varieties = {{"มาห์ล", "Mahal", "Mahl"}},
	scripts = {"Thaa"},
	ancestors = {"elu-prk"},
	translit_module = "Thaa-translit",
	override_translit = true,
}

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

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

m["el"] = {
	"กรีก",
	"Q9129",
	"grk",
	aliases = {"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",
	aliases = {"อังกฤษใหม่", "English", "Modern English", "New English"},
	varieties = {{"Hawaiian Creole English", "Hawai'ian Creole English", "Hawaiian Creole", "Hawai'ian Creole"}, "Polari", "Yinglish"},
	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",
	aliases = {"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-ibe",
	aliases = {"คาสตีล", "Spanish", "Castilian"},
	varieties = {{"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",
	aliases = {"Estonian"},
	scripts = Latn,
}

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

m["fa"] = {
	"เปอร์เซีย",
	"Q9168",
	"ira-swi",
	aliases = {"ฟาร์ซี", "เปอร์เซียใหม่", "Persian", "Farsi", "New Persian", "Modern Persian"},
	varieties = {{"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-fwo",
	aliases = {"Fula", "Fulani"},
	varieties = {"Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code; Pular and Pulaar are distinct
	scripts = {"Latn", "Adlm"},
}

m["fi"] = {
	"ฟินแลนด์",
	"Q1412",
	"fiu-fin",
	aliases = {"ฟินนิช", "ซูโอมี", "Finnish", "Suomi"},
	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",
	aliases = {"Fijian"},
	scripts = Latn,
}

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

m["fr"] = {
	"ฝรั่งเศส",
	"Q150",
	"roa-oil",
	aliases = {"ฝรั่งเศสใหม่", "French", "Modern French"},
	varieties = {"African French", "Algerian French", "Alsatian French", "Antilles French", "Atlantic Canadian French",
		"Belgian French",
		"Congolese French",
		"European French",
		"French French",
		"Haitian French",
		"Ivorian French",
		"Lorraine French", "Louisiana French", "Luxembourgish French",
		"Malian French", "Marseille French", "Missourian French", "Moroccan French",
		"Newfoundland French", "North American French",
		"Picard French", "Provençal French‎",
		"Quebec French",
		"Réunion French", "Rwandan French",
		"Tunisian French",
		"West African 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",
	aliases = {"ฟรีเชีย", "West Frisian", "Western Frisian", "Frisian"},
	scripts = Latn,
	ancestors = {"ofs"},
	sort_key = {
		from = {"[àáâä]", "[èéêë]", "[ìíîïyỳýŷÿ]", "[òóôö]", "[ùúûü]", "æ", "[ /.-]"},
		to   = {"a"	 , "e"	, "i"	, "o"	, "u", "ae"}} ,
	standardChars = "A-PR-WYZa-pr-wyz0-9Ææâäàéêëèïìôöòúûüùỳ" .. PUNCTUATION,
}

m["ga"] = {
	"ไอริช",
	"Q9142",
	"cel-gae",
	aliases = {"ไอร์แลนด์", "แกลิกแบบไอร์แลนด์", "Irish Gaelic", "Gaelic"}, -- calling it simply "Gaelic" is rare in Ireland, but relatively common in the Irish diaspora
	varieties = {{"Cois Fharraige Irish", "Cois Fhairrge Irish"}, {"Connacht Irish", "Connaught Irish"}, "Cork Irish", "Donegal Irish", "Galway Irish", "Kerry Irish", "Mayo Irish", "Munster Irish", "Ulster Irish", "Waterford Irish", "West Muskerry Irish"},
	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",
	aliases = {"Scottish Gaelic", "Gaelic", "Gàidhlig", "Scots Gaelic", "Scottish"},
	varieties = {"Argyll Gaelic", "Arran Scottish Gaelic", {"Canadian Gaelic", "Canadian Scottish Gaelic", "Cape Breton Gaelic"}, "East Sutherland Gaelic", {"Galwegian Gaelic", "Gallovidian Gaelic", "Gallowegian Gaelic", "Galloway Gaelic"}, "Hebridean Gaelic", "Highland Gaelic"},
	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-ibe",
	aliases = {"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",
	aliases = {"Guaraní"},
	scripts = Latn,
}

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

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

m["ha"] = {
	"เฮาซา",
	"Q56475",
	"cdc-wst",
	aliases = {"Hausa"},
	scripts = LatnArab,
	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",
	aliases = {"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",
	aliases = {"Hindi"},
	-- FIXME, are the following varieties?
	otherNames = {"Hindavi", "Khariboli", "Khari Boli", "Manak Hindi"},
	scripts = {"Deva", "Kthi", "Newa"},
	ancestors = {"inc-ohi"},
	translit_module = "Deva-translit",
}

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

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

m["hu"] = {
	"ฮังการี",
	"Q9067",
	"urj-ugr",
	aliases = {"มอยอร์", "Hungarian", "Magyar"},
	scripts = {"Latn", "Hung"},
	ancestors = {"ohu"},
	sort_key = {
		from = {"á", "é", "í", "ó", "ú", "[öő]", "[üű]", "cs", "dzs", "gy", "ly", "ny", "zs"},
		to   = {"a", "e", "i", "o", "u", "o~", "u~", "c~", "dz~", "g~", "l~", "n~", "z~"},
	},
}

m["hy"] = {
	"อาร์มีเนีย",
	"Q8785",
	"hyx",
	aliases = {"อาร์มีเนียใหม่", "Armenian", "Modern Armenian"},
	varieties = {{"อาร์มีเนียตะวันออก", "Eastern Armenian"}, {"อาร์มีเนียตะวันตก", "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-swb",
	aliases = {"Herero"},
	scripts = Latn,
}

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

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

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

m["ig"] = {
	"อิกโบ",
	"Q33578",
	"alv-von",
	aliases = {"Igbo"},
	scripts = Latn,
}

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

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

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

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

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

m["iu"] = {
	"อินุกติตุต",
	"Q29921",
	"esx-inu",
	aliases = {"Inuktitut"},
	varieties = {
		"Aivilimmiut",
		{"Eastern Canadian Inuktitut", "Eastern Canadian Inuit"},
		{"Inuinnaq", "Inuinnaqtun"},
		{"Inuvialuktun", "Inuvialuk", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun"},
		"Kivallirmiut",
		"Natsilingmiut", "Nunavimmiutit", "Nunatsiavummiut",
		{"Siglitun", "Siglit"}},
	scripts = {"Cans", "Latn"},
	translit_module = "iu-translit",
	override_translit = true,
}

m["ja"] = {
	"ญี่ปุ่น",
	"Q5287",
	"jpx",
	aliases = {"ญี่ปุ่นใหม่", "Japanese", "Modern Japanese", "Nipponese", "Nihongo"},
	scripts = {"Jpan", "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",
	aliases = {"Javanese"},
	scripts = {"Latn", "Java"},
	translit_module = "translit-redirect",
	ancestors = {"kaw"},
	--link_tr = true,
}

m["ka"] = {
	"จอร์เจีย",
	"Q8108",
	"ccs-gzn",
	aliases = {"Georgian"},
	varieties = {{"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-kng",
	aliases = {"Kongo", "Kikongo"},
	varieties = {"Koongo", "Laari", "San Salvador Kongo", "Yombe"},
	scripts = Latn,
}

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

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

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

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

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

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

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

m["kr"] = {
	"Kanuri",
	"Q36094",
	"ssa-sah",
	varieties = {"Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"},
	scripts = LatnArab,
	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",
	aliases = {"กัศมีร์", "Kashmiri", "Koshur"},
	scripts = {"ks-Arab", "Deva", "Shrd", "Latn"},
	--translit_module = "translit-redirect",
	ancestors = {"inc-dar-pro"},
}

m["ku"] = {
	"เคิร์ด",
	"Q36368",
	"ira-nwi",
	aliases = {"Kurdish"},
	scripts = {"Latn", "ku-Arab", "Armn", "Cyrl"},
	--translit_module = "translit-redirect",
}

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

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

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

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

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

m["lg"] = {
	"ลูกันดา",
	"Q33368",
	"bnt",
	aliases = {"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",
	aliases = {"Limburgish", "Limburgan", "Limburgian", "Limburgic"},
	scripts = Latn,
	ancestors = {"dum"},
}

m["ln"] = {
	"Lingala",
	"Q36217",
	"bnt-bmo",
	aliases = {"Ngala"},
	scripts = Latn,
}

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

m["lt"] = {
	"ลิทัวเนีย",
	"Q9083",
	"bat",
	aliases = {"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-lub",
	scripts = Latn,
}

m["lv"] = {
	"ลัตเวีย",
	"Q9078",
	"bat",
	aliases = {"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",
	aliases = {"Malagasy"},
	varieties = {
		{"Antankarana", "Antankarana Malagasy"},
		{"Bara Malagasy", "Bara"}, {"Betsimisaraka Malagasy", "Betsimisaraka"}, {"Northern Betsimisaraka Malagasy", "Northern Betsimisaraka"}, {"Southern Betsimisaraka Malagasy", "Southern Betsimisaraka"}, {"Bushi", "Shibushi", "Kibushi"},
		{"Masikoro Malagasy", "Masikoro"},
		"Plateau Malagasy",
		"Sakalava",
		{"Tandroy Malagasy", "Tandroy"}, {"Tanosy", "Tanosy Malagasy"}, "Tesaka", {"Tsimihety", "Tsimihety Malagasy"}},
	scripts = Latn,
}

m["mh"] = {
	"มาร์แชลล์",
	"Q36280",
	"poz-mic",
	aliases = {"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",
	aliases = {"เมารี", "Maori", "Māori"},
	scripts = Latn,
}

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

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

m["mn"] = {
	"มองโกเลีย",
	"Q9246",
	"xgn",
	aliases = {"Mongolian"},
	varieties = {"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",
	aliases = {"Marathi"},
	scripts = {"Deva", "Modi"},
	ancestors = {"omr"},
	translit_module = "Deva-translit",
}

m["ms"] = {
	"มาเลย์",
	"Q9237",
	"poz-mly",
	aliases = {"มลายู", "มลายูมาตรฐาน", "Malay", "Malaysian", "Standard Malay"},
	scripts = {"Latn", "ms-Arab"},
}

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

m["my"] = {
	"พม่า",
	"Q9228",
	"tbq-brm",
	aliases = {"เมียนมา", "Burmese", "Myanmar"},
	varieties = {"Mandalay Burmese", "Myeik Burmese", "Palaw Burmese", {"Rangoon Burmese", "Yangon Burmese"}, "Yaw Burmese"},
	scripts = {"Mymr"},
	ancestors = {"obr"},
	translit_module = "my-translit",
	override_translit = true,
}

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

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

m["nd"] = {
	"Northern Ndebele",
	"Q35613",
	"bnt-ngu",
	aliases = {"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",
	aliases = {"Nepali", "Nepalese"},
	scripts = {"Deva", "Newa"},
	translit_module = "Deva-translit",
}

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

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

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

m["nr"] = {
	"Southern Ndebele",
	"Q36785",
	"bnt-ngu",
	aliases = {"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",
	aliases = {"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",
	aliases = {"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",
	aliases = {"Occitan"},
	-- don't list varieties here that are in [[Module:etymology languages/data]]
	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",
	aliases = {"Ojibwe", "Ojibway"},
	varieties = {{"Chippewa", "Ojibwemowin", "Southwestern Ojibwa"}},
	scripts = {"Cans", "Latn"},
}

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

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

m["os"] = {
	"ออสซีเซีย",
	"Q33968",
	"xsc",
	aliases = {"Ossetian", "Ossete", "Ossetic"},
	varieties = {"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",
	aliases = {"ปัญจาบี", "Punjabi", "Panjabi"},
	scripts = {"Guru", "pa-Arab"},
	ancestors = {"psu"},
	translit_module = "translit-redirect",
	entry_name = {
		from = {u(0x064B), u(0x064C), u(0x064D), u(0x064E), u(0x064F), u(0x0650), u(0x0651), u(0x0652)},
		to   = {}} ,
}

m["pi"] = {
	"บาลี",
	"Q36727",
	"inc-old",
	aliases = {"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", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)},
		to   = {"a", "i", "u", "d", "l", "m"   , "n"	, "t", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}} ,
	entry_name = {
		from = {u(0xFE00)},
		to   = {}},
}

m["pl"] = {
	"โปแลนด์",
	"Q809",
	"zlw-lch",
	aliases = {"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-pat",
	aliases = {"Pashto", "Pashtun", "Pushto", "Pashtu", "Afghani"},
	varieties = {{"พัชโตกลาง", "Central Pashto"}, {"พัชโตเหนือ", "Northern Pashto"}, {"พัชโตใต้", "Southern Pashto"}, {"Pukhto", "Pakhto", "Pakkhto"}},
	scripts = {"ps-Arab"},
	ancestors = {"ira-pat-pro"},
}

m["pt"] = {
	"โปรตุเกส",
	"Q5146",
	"roa-ibe",
	aliases = {"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",
	aliases = {"Quechua"},
	scripts = Latn,
}

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

m["ro"] = {
	"โรมาเนีย",
	"Q7913",
	"roa-eas",
	aliases = {"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",
	aliases = {"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",
	-- don't list varieties here that are in [[Module:etymology languages/data]]
	varieties = {{"Ha", "Giha"}, "Hangaza", "Vinza", "Shubi"}, -- Deleted "Subi", which normally refers to a different language
	scripts = Latn,
}

m["sa"] = {
	"สันสกฤต",
	"Q11059",
	"inc-old",
	aliases = {"Sanskrit"},
	scripts = {"Deva", "Bali", "as-Beng", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Java", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Mlym", "Mymr", "Newa", "Orya", "Saur", "Shrd", "Sidd", "Sinh", "Taml", "Telu", "Thai", "Tibt", "Tirh"},
	sort_key = {
		from = {"ā", "ī", "ū", "ḍ", "ḷ", "[ṁṃ]", "[ṇñṅ]", "ṭ", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)},
		to   = {"a", "i", "u", "d", "l", "m"   , "n"	, "t", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}} ,
	entry_name = {
		from = {u(0xFE00)},
		to   = {}},
	translit_module = "translit-redirect",
}

m["sc"] = {
	"ซาร์ดิเนีย",
	"Q33976",
	"roa",
	aliases = {"Sardinian"},
	-- don't list varieties here that are in [[Module:etymology languages/data]]
	scripts = Latn,
}

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

m["se"] = {
	"Northern Sami",
	"Q33947",
	"smi",
	aliases = {"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,
	ancestors = {"ngb"},
}

m["sh"] = {
	"เซอร์โบ-โครเอเชีย",
	"Q9301",
	"zls",
	aliases = {"Serbo-Croatian", "BCS", "Croato-Serbian", "Serbocroatian"},
	-- don't list varieties here that are in [[Module:etymology languages/data]]
	varieties = {{"บอสเนีย", "Bosnian"}, {"โครเอเชีย", "Croatian"}, {"มอนเตเนโกร", "Montenegrin"}, {"เซอร์เบีย", "Serbian"}, "Shtokavian"},
	scripts = {"Latn", "Cyrl", "Glag"},
	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",
	aliases = {"Sinhalese", "Singhalese", "Sinhala"},
	scripts = {"Sinh"},
	ancestors = {"elu-prk"},
	translit_module = "Sinh-translit",
	override_translit = true,
}

m["sk"] = {
	"สโลวัก",
	"Q9058",
	"zlw",
	aliases = {"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",
	aliases = {"สโลเวเนีย", "สโลวีน", "Slovene", "Slovenian"},
	scripts = Latn,
	entry_name = {
		from = {"[ÁÀÂĀȂȀ]", "[áàâāȃȁ]", "[ÉÈÊĒȆȄỆẸ]", "[éèêēȇȅệẹə]", "[ÍÌÎĪȊȈ]", "[íìîīȋȉ]", "[ÓÒÔŌȎȌỘỌ]", "[óòôōȏȍộọ]", "[ŔȒȐ]", "[ŕȓȑ]", "[ÚÙÛŪȖȔ]", "[úùûūȗȕ]", "ł", GRAVE, ACUTE, CIRC, MACRON, DGRAVE, INVBREVE, DOTBELOW},
		to   = {"A"       , "a"       , "E"         , "e"          , "I"       , "i"       , "O"         , "o"         , "R"    , "r"    , "U"       , "u"       , "l"},
	},
	sort_key = {
		from = {"č" , "š" , "ž" },
		to   = {"c²", "s²", "z²"},
	},
}

m["sm"] = {
	"ซามัว",
	"Q34011",
	"poz-pnp",
	aliases = {"Samoan"},
	scripts = Latn,
}

m["sn"] = {
	"Shona",
	"Q34004",
	"bnt",
	scripts = Latn,
	entry_name = {
		from = {ACUTE},
		to = {}} ,
}

m["so"] = {
	"โซมาลี",
	"Q13275",
	"cus",
	aliases = {"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",
	aliases = {"Albanian"},
	-- don't list varieties here that are in [[Module:etymology languages/data]]
	scripts = {"Latn", "Grek", "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",
	aliases = {"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-sts",
	aliases = {"โซโท", "Sotho", "Sesotho", "Southern Sesotho", "Southern Sotho"},
	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["su"] = {
	"ซุนดา",
	"Q34002",
	"poz-msa",
	aliases = {"Sundanese"},
	scripts = {"Latn", "Sund"},
	translit_module = "su-translit",
}

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

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

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

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

m["tg"] = {
	"ทาจิก",
	"Q9260",
	"ira-swi",
	aliases = {"ทาจิกิสถาน", "เปอร์เซียแบบทาจิก", "Tajik", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian", "Tajiki 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",
	aliases = {"สยาม", "ไทยกลาง", "Thai", "Siamese", "Central Thai"},
	scripts = {"Thai", "Brai"},
	--translit_module = "th-translit", !never use this line!
	sort_key = {
		from = {"[%pๆ]"},
		to   = {""}} ,
}

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

m["tk"] = {
	"เติร์กเมน",
	"Q9267",
	"trk-ogz",
	aliases = {"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", ""}},
	ancestors = {"trk-ogz-pro"},
}

m["tl"] = {
	"ตากาล็อก",
	"Q34057",
	"phi",
	aliases = {"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-sts",
	aliases = {"Tswana", "Setswana"},
	scripts = Latn,
}

m["to"] = {
	"ตองงา",
	"Q34094",
	"poz-pol",
	aliases = {"ตองกา", "Tongan"},
	scripts = Latn,
	sort_key = {
		from = {"ā", "ē", "ī", "ō", "ū", MACRON},
		to   = {"a", "e", "i", "o", "u", ""}},
	entry_name = {
		from = {"á", "é", "í", "ó", "ú", ACUTE},
		to   = {"a", "e", "i", "o", "u", ""}},
}

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

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

m["tt"] = {
	"ตาตาร์",
	"Q25285",
	"trk-kbu",
	aliases = {"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",
	aliases = {"Tahitian"},
	scripts = Latn,
}

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

m["uk"] = {
	"ยูเครน",
	"Q8798",
	"zle",
	aliases = {"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",
	aliases = {"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-kar",
	aliases = {"อุซเบกิสถาน", "Uzbek"},
	varieties = {{"อุซเบกเหนือ", "Norther Uzbek"}, {"อุซเบกใต้","Southern Uzbek"}},
	scripts = {"Latn", "Cyrl", "fa-Arab"},
	ancestors = {"chg"},
}

m["ve"] = {
	"เวนดา",
	"Q32704",
	"bnt-bso",
	aliases = {"Venda"},
	scripts = Latn,
}

m["vi"] = {
	"เวียดนาม",
	"Q9199",
	"mkh-vie",
	aliases = {"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",
	aliases = {"Volapük"},
	scripts = Latn,
}

m["wa"] = {
	"วัลลูน",
	"Q34219",
	"roa-oil",
	aliases = {"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-fwo",
	aliases = {"Wolof"},
	varieties = {"Gambian Wolof"}, -- the subsumed dialect 'wof'
	scripts = LatnArab,
}

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",
	aliases = {"Yiddish"},
	varieties = {"American Yiddish", "Daytshmerish Yiddish", "Mideastern Yiddish", "Galitzish",
		{"Northeastern Yiddish", "Litvish", "Lithuanian Yiddish"},
		{"Northwestern Yiddish", "Netherlandic Yiddish"},
		{"Polish Yiddish", "Poylish"},
		"South African Yiddish",
		{"Southeastern Yiddish", "Ukrainian Yiddish", "Ukrainish"},
		{"Southwestern Yiddish", "Judeo-Alsatian"},
		"Udmurtish"},
	scripts = {"Hebr"},
	ancestors = {"gmh"},
	sort_key = {
		from = {"[אַאָ]", "בּ", "[וֹוּ]", "יִ", "ײַ", "פֿ"},
		to = {"א", "ב", "ו", "י",	"יי", "פ"}} ,
	translit_module = "yi-translit",
}

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

m["za"] = {
	"จ้วง",
	"Q13216",
	"tai",
	aliases = {"Zhuang"},
	-- FIXME, are all of the following distinct?
	varieties = {
		"Chongzuo Zhuang",
		"Guibei Zhuang", "Guibian Zhuang",
		"Central Hongshuihe Zhuang", "Eastern Hongshuihe Zhuang",
		"Lianshan Zhuang", "Liujiang Zhuang", "Liuqian Zhuang",
		{"Min Zhuang", "Minz Zhuang"},
		"Nong Zhuang",
		"Qiubei Zhuang",
		"Shangsi Zhuang",
		{"Dai Zhuang", "Wenma", "Wenma Thu", "Wenma Zhuang"},
		"Yang Zhuang",
		{"Yongbei Zhuang", "Wuming Zhuang", "Standard Zhuang"},
		"Yongnan Zhuang", "Youjiang Zhuang",
		"Zuojiang Zhuang"},
	scripts = {"Latn", "Hani"},
	sort_key = {
		from = {"%p"},
		to   = {""}},
}

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

m["zu"] = {
	"ซูลู",
	"Q10179",
	"bnt-ngu",
	aliases = {"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