Wiktionary siwiktionary https://si.wiktionary.org/wiki/%E0%B7%80%E0%B7%92%E0%B6%9A%E0%B7%8A%E0%B7%82%E0%B6%B1%E0%B6%BB%E0%B7%92:%E0%B6%B8%E0%B7%94%E0%B6%BD%E0%B7%8A_%E0%B6%B4%E0%B7%92%E0%B6%A7%E0%B7%94%E0%B7%80 MediaWiki 1.46.0-wmf.23 case-sensitive මාධ්‍යය විශේෂ සාකච්ඡාව පරිශීලක පරිශීලක සාකච්ඡාව වික්ෂනරි වික්ෂනරි සාකච්ඡාව ගොනුව ගොනුව සාකච්ඡාව මාධ්‍යවිකි මාධ්‍යවිකි සාකච්ඡාව සැකිල්ල සැකිලි සාකච්ඡාව උදවු උදවු සාකච්ඡාව ප්‍රවර්ගය ප්‍රවර්ග සාකච්ඡාව TimedText TimedText talk Module Module talk Event Event talk 828 4981 231385 220417 2026-02-13T03:18:28Z en>Hazarasp 0 Merging Eastern and Western Gurung per [[WT:LTR#Merge Eastern Gurung [ggn] into Western Gurung [gvr] and rename it Gurung]] 231385 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["gaa"] = { "Ga", 33287, "alv-gda", "Latn", } m["gab"] = { "Gabri", 3441237, "cdc-est", "Latn", } m["gac"] = { "Mixed Great Andamanese", 56329630, "qfa-adn", "Latn", } m["gad"] = { -- not to be confused with gdk, gdg "Gaddang", 3438830, "phi", "Latn", } m["gae"] = { "Warekena", 1091095, "awd-nwk", "Latn", } m["gaf"] = { "Gende", 3100425, "ngf-gor", "Latn", } m["gag"] = { "Gagauz", 33457, "trk-ogz", "Latn, Cyrl", ancestors = "trk-oat", dotted_dotless_i = true, sort_key = { Latn = { from = { "i", -- Ensure "i" comes after "ı". "ä", "ç", "ê", "ı", "ö", "ş", "ţ", "ü" }, to = { "i" .. p[1], "a" .. p[1], "c" .. p[1], "e" .. p[1], "i", "o" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1] } }, }, } m["gah"] = { "Alekano", 3441595, "ngf-gah", "Latn", } m["gai"] = { "Borei", 6799756, "paa-ott", "Latn", } m["gaj"] = { "Gadsup", 5516467, "ngf-gau", "Latn", } m["gak"] = { "Gamkonora", 5520226, "paa-sah", "Latn", } m["gal"] = { "Galoli", 35322, "poz-tim", "Latn", } m["gam"] = { "Kandawo", 6361369, "ngf-jim", "Latn", } m["gan"] = { "Gan", 33475, "zhx", "Hants", ancestors = "ltc", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["gao"] = { "Gants", 5521529, "ngf-eso", "Latn", } m["gap"] = { "Gal", 5517742, "ngf-han", "Latn", } m["gaq"] = { "Gata'", 3501920, "mun", "Orya", } m["gar"] = { "Galeya", 5518509, "poz-ocw", "Latn", } m["gas"] = { "Adiwasi Garasia", 12953522, "inc-bhi", "Deva, Gujr", ancestors = "bhb", } m["gat"] = { "Kenati", 4219330, "ngf-kgo", "Latn", } m["gau"] = { "Kondekor", 12952433, "dra-pgd", "Telu", } m["gaw"] = { "Nobonob", 11732205, "ngf-han", "Latn", } m["gay"] = { "Gayo", 33286, "poz-nws", "Latn", } m["gbb"] = { "Kaytetye", 6380709, "aus-rnd", "Latn", } m["gbd"] = { "Karadjeri", 3913837, "aus-pam", "Latn", } m["gbe"] = { "Niksek", 56375, "paa-sep", "Latn", } m["gbf"] = { "Gaikundi", 5517032, "paa-nnd", "Latn", } m["gbg"] = { "Gbanziri", 35306, "nic-nkg", "Latn", } m["gbh"] = { "Defi Gbe", 12952446, "alv-gbe", "Latn", } m["gbi"] = { "Galela", 3094570, "paa-gto", "Latn", } m["gbj"] = { "Bodo Gadaba", 3347070, "mun", "Orya", } m["gbk"] = { "Gaddi", 17455500, "him", "Deva, Takr", translit = {Deva = "hi-translit"}, } m["gbl"] = { "Gamit", 2731717, "inc-bhi", "Deva, Gujr", } m["gbm"] = { "Garhwali", 33459, "inc-pah", "Deva", translit = "hi-translit", } m["gbn"] = { "Mo'da", 12755683, "csu-bbk", "Latn", } m["gbo"] = { "Northern Grebo", 11157042, "grb", "Latn", } m["gbp"] = { "Gbaya-Bossangoa", 11011295, "gba-wes", "Latn", } m["gbq"] = { "Gbaya-Bozoum", 4952879, "gba-wes", "Latn", } m["gbr"] = { "Gbagyi", 11015105, "alv-ngb", "Latn", } m["gbs"] = { "Gbesi Gbe", 12952448, "alv-pph", "Latn", } m["gbu"] = { "Gagadu", 35677, "aus-arn", "Latn", } m["gbv"] = { "Gbanu", 3914945, "gba-eas", "Latn", } m["gbw"] = { "Gabi", 5515391, "aus-pam", "Latn", } m["gbx"] = { "Eastern Xwla Gbe", 18379975, "alv-pph", "Latn", } m["gby"] = { "Gbari", 3915451, "alv-ngb", "Latn", } m["gcc"] = { "Mali", 6743338, "paa-bai", "Latn", } m["gcd"] = { "Ganggalida", 3913765, "aus-tnk", "Latn", } m["gce"] = { "Galice", 20711, "ath-pco", "Latn", } m["gcf"] = { "Antillean Creole", 3006280, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["gcl"] = { "Grenadian Creole English", 4252500, "crp", "Latn", ancestors = "en", } m["gcn"] = { "Gaina", 11732195, "ngf-gko", "Latn", } m["gcr"] = { "Guianese Creole", 1363072, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["gct"] = { "Colonia Tovar German", 1138351, "gmw-hgm", "Latn", ancestors = "gsw", } m["gdb"] = { "Ollari", 33906, "dra-pgd", "Orya, Telu", translit = { Telu = "te-translit" }, } m["gdc"] = { "Gugu Badhun", 10510360, "aus-pam", "Latn", } m["gdd"] = { "Gedaged", 35292, "poz-ocw", "Latn", } m["gde"] = { "Gude", 3441230, "cdc-cbm", "Latn", } m["gdf"] = { "Guduf-Gava", 3441350, "cdc-cbm", "Latn", } m["gdg"] = { -- not to be confused with gad, gdk "Ga'dang", 5515189, "phi", "Latn", } m["gdh"] = { "Gadjerawang", 3913817, "aus-jar", "Latn", } m["gdi"] = { "Gundi", 11137851, "nic-nkb", "Latn", } m["gdj"] = { "Kurtjar", 5619931, "aus-pmn", "Latn", } m["gdk"] = { -- not to be confused with gad, gdg "Gadang", 56256, "cdc-est", "Latn", } m["gdl"] = { "Dirasha", 56809, "cus-eas", "Ethi", } m["gdm"] = { "Laal", 33436, "qfa-dis", -- Chad; unclassified, isolate or grouped with Adamawa or Chadic languages "Latn", } m["gdn"] = { "Umanakaina", 7881084, "ngf-dag", "Latn", } m["gdo"] = { "Godoberi", 56515, "cau-and", "Cyrl", display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["gdq"] = { "Mehri", 13361, "sem-sar", "Arab, Latn", } m["gdr"] = { "Wipi", 8026711, "paa-etf", "Latn", } m["gds"] = { "Ghandruk Sign Language", 15971577, "sgn", } m["gdt"] = { "Kungardutyi", 6444517, "aus-kar", "Latn", } m["gdu"] = { "Gudu", 3441172, "cdc-cbm", "Latn", } m["gdx"] = { "Godwari", 3540922, "raj", "Deva", } m["gea"] = { "Geruma", 3438789, "cdc-wst", "Latn", } m["geb"] = { "Kire", 11129733, "paa-rub", "Latn", } m["gec"] = { "Gboloo Grebo", 11019342, "grb", "Latn", } m["ged"] = { "Gade", 3914459, "alv-nup", "Latn", } m["geg"] = { "Gengle", 3438345, "alv-mye", "Latn", ancestors = "kow", } m["geh"] = { "Hutterisch", 33385, "gmw-hgm", "Latn", ancestors = "bar", } m["gei"] = { "Gebe", 3100032, "poz-hce", "Latn", } m["gej"] = { "Gen", 33450, "alv-gbe", "Latn", } m["gek"] = { "Gerka", 3441277, "cdc-wst", "Latn", } m["gel"] = { "Fakkanci", 36627, "nic-knn", "Latn", } m["geq"] = { "Geme", 3915851, "znd", "Latn", } m["ges"] = { "Geser-Gorom", 5553579, "poz-cma", "Latn", } m["gev"] = { "Viya", 7937974, "bnt-tso", "Latn", } m["gew"] = { "Gera", 3438725, "cdc-wst", "Latn", } m["gex"] = { "Garre", 56618, "cus-som", "Latn", } m["gey"] = { "Enya", 5381452, "bnt-mbe", "Latn", } m["gez"] = { "Ge'ez", 35667, "sem-eth", "Ethi", translit = "Ethi-translit", } m["gfk"] = { "Patpatar", 3368846, "poz-ocw", "Latn", } m["gft"] = { "Gafat", 56910, "sem-eth", "Ethi, Latn", } m["gga"] = { "Gao", 3095228, "poz-ocw", "Latn", } m["ggb"] = { "Gbii", 3914390, "kro-wkr", "Latn", } m["ggd"] = { "Gugadj", 5615186, "aus-pmn", "Latn", } m["gge"] = { "Guragone", 5619801, "aus-arn", "Latn", } m["ggg"] = { "Gurgula", 5620032, "raj", "Arab", } m["ggk"] = { "Kungarakany", 6444516, "aus-arn", "Latn", } m["ggl"] = { "Ganglau", 5521140, "ngf-yag", "Latn", } m["ggt"] = { "Gitua", 3107865, "poz-ocw", "Latn", } m["ggu"] = { "Gban", 3913317, "dmn-nbe", "Latn", } m["ggw"] = { "Gogodala", 3512161, "ngf-gsu", "Latn", } m["gha"] = { "Ghadames", 56747, "ber", "Latn", -- and other scripts? } m["ghc"] = { "Classical Gaelic", 5128278, "cel-gae", "Latn, Latg", ancestors = "mga", } m["ghe"] = { "Southern Ghale", 12952453, "sit-tam", "Deva", } m["ghh"] = { "Northern Ghale", 22662104, "sit-tam", "Deva", } m["ghk"] = { "Geko Karen", 5530317, "kar", } m["ghl"] = { "Ghulfan", 16885737, "nub-hil", "Latn", -- and others? } m["ghn"] = { "Ghanongga", 3104772, "poz-ocw", "Latn", } m["gho"] = { "Ghomara", 35315, "ber", "Tfng, Latn", translit = {Tfng = "Tfng-translit"}, } m["ghr"] = { "Ghera", 22808992, "inc-hiw", } m["ghs"] = { "Guhu-Samane", 11732219, "ngf-gbi", "Latn", } m["ght"] = { "Kutang Ghale", 6448337, "sit-tam", "Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["gia"] = { "Kitja", 1284877, "aus-jar", "Latn", } m["gib"] = { "Gibanawa", 12953530, "crp", "Latn", ancestors = "ha", } m["gid"] = { "Gidar", 35265, "cdc-cbm", "Latn", } m["gie"] = { "Guébie", 63140714, "kro-did", "Latn", } m["gig"] = { "Goaria", 33269, "raj", "Arab", } m["gih"] = { "Githabul", 48987680, "aus-pam", "Latn", } m["gii"] = { "Girirra", 5564288, "cus-som", } m["gil"] = { "Gilbertese", 30898, "poz-mic", "Latn", } m["gim"] = { "Gimi (Papuan)", 11732209, "ngf-fgi", "Latn", } m["gin"] = { "Hinukh", 33283, "cau-wts", "Cyrl", translit = "gin-translit", display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["gip"] = { "Gimi (Austronesian)", 12952457, "poz-ocw", } m["giq"] = { "Green Gelao", 12953525, "gio", "Latn", } m["gir"] = { "Red Gelao", 3100264, "gio", } m["gis"] = { "North Giziga", 3515084, "cdc-cbm", } m["git"] = { "Gitxsan", 3107862, "nai-tsi", "Latn", } m["giu"] = { "Mulao", 11092831, "gio", } m["giw"] = { "White Gelao", 8843040, "gio", } m["gix"] = { "Gilima", 10977716, "nic-nkm", "Latn", } m["giy"] = { "Giyug", 5565906, } m["giz"] = { "South Giziga", 3502232, "cdc-cbm", } m["gji"] = { "Geji", 3914890, "cdc-wst", "Latn", } m["gjk"] = { "Kachi Koli", 12953646, "inc-wes", } m["gjm"] = { "Gunditjmara", 6448731, "aus-pam", "Latn", } m["gjn"] = { "Gonja", 35267, "alv-gng", "Latn", } m["gjr"] = { "Gurindji Kriol", 5620091, "qfa-mix", "Latn", ancestors = "gue, rop" } m["gju"] = { "Gojri", 3241731, "raj", "ur-Arab, Deva, Takr", strip_diacritics = { ["ur-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.smallv, from = {"ڵ", "ݩ"}, to = {"ل", "ن"} }, }, translit = {["ur-Arab"] = "ur-translit"}, } m["gka"] = { "Guya", 11732221, "ngf-war", "Latn", } m["gkd"] = { "Magi", 55621742, "ngf-ais", "Latn", } m["gke"] = { "Ndai", 6983667, "alv-mbm", } m["gkn"] = { "Gokana", 3075137, "nic-ogo", "Latn", } m["gko"] = { "Kok-Nar", 6426526, "aus-pmn", "Latn", } m["gkp"] = { "Guinea Kpelle", 11052867, "dmn-msw", "Latn, Kpel", ancestors = "kpe", } m["glc"] = { "Bon Gula", 289816, "alv-bua", } m["gld"] = { "Nanai", 13303, "tuw-nan", "Cyrl", translit = "gld-translit", strip_diacritics = {remove_diacritics = c.macron}, sort_key = { from = {"ё", "ӈ"}, to = {"е" .. p[1], "н" .. p[1]} }, } m["glh"] = { "Northwest Pashayi", 23713532, "inc-pas", "fa-Arab", } m["glj"] = { "Kulaal", 33360, "alv-bua", } m["glk"] = { "Gilaki", 33657, "ira-csp", "fa-Arab", } m["glo"] = { "Galambu", 2598797, "cdc-wst", "Latn", } m["glr"] = { "Glaro-Twabo", 3915313, "kro-wee", } m["glu"] = { "Gula", 5617176, "csu-bgr", "Latn", } m["glw"] = { "Glavda", 3441285, "cdc-cbm", "Latn", } m["gly"] = { "Gule", 3120736, "ssa-kom", } m["gma"] = { "Gambera", 10502327, "aus-wor", "Latn", } m["gmb"] = { "Gula'alaa", 3120733, "poz-sls", "Latn", } m["gmd"] = { "Mághdì", 3914475, "alv-bwj", } m["gmg"] = { "Magiyi", 16926155, "ngf-sog", "Latn", } m["gmh"] = { "Middle High German", 837985, "gmw-hgm", "Latn", strip_diacritics = { remove_diacritics = c.circ .. c.macron, from = {"Ë", "ë", "[ƷȤ]", "[ʒȥ]"}, to = {"E", "e", "Z", "z"} }, } m["gml"] = { "Middle Low German", 505674, "gmw-lgm", "Latn", strip_diacritics = {remove_diacritics = c.circ .. c.macron .. c.diaer}, } m["gmm"] = { "Gbaya-Mbodomo", 6799713, "gba-eas", "Latn", } m["gmn"] = { "Gimnime", 11016905, "alv-dur", "Latn", } m["gmr"] = { "Mirning", 6873793, "aus-pam", "Latn", } m["gmu"] = { "Gumalu", 5618027, "ngf-gum", "Latn", } m["gmv"] = { "Gamo", 16116386, "omv-nom", "Latn, Ethi", } m["gmx"] = { "Magoma", 16939552, "bnt-bki", } m["gmy"] = { "Mycenaean Greek", 668366, "grk", "Linb", translit = "Linb-translit", } m["gmz"] = { "Mgbo", 6826835, "alv-igb", ancestors = "izi", } m["gna"] = { "Kaansa", 56802, "nic-gur", } m["gnb"] = { "Gangte", 12952442, "tbq-kuk", } m["gnc"] = { "Guanche", 35762, "ber", } m["gnd"] = { "Zulgo-Gemzek", 56800, "cdc-cbm", "Latn", } m["gne"] = { "Ganang", 63163361, "nic-plc", ancestors = "izr", } m["gng"] = { "Ngangam", 35888, "nic-grm", } m["gnh"] = { "Lere", 3915319, "nic-jer", } m["gni"] = { "Gooniyandi", 2669219, "aus-bub", "Latn", } m["gnj"] = { "Ngen of Djonkro", 63170838, "dmn-nbe", "Latn", } m["gnk"] = { "ǁGana", 1975199, "khi-kal", "Latn", } m["gnl"] = { "Gangulu", 4916329, "aus-pam", "Latn", } m["gnm"] = { "Ginuman", 11732210, "ngf-dag", "Latn", } m["gnn"] = { "Gumatj", 10510745, "aus-yol", "Latn", } m["gnq"] = { "Gana", 5520523, "poz-san", "Latn", } m["gnr"] = { "Gureng Gureng", 5619998, "aus-pam", "Latn", } m["gnt"] = { "Guntai", 12952475, "paa-ton", "Latn", } m["gnu"] = { "Gnau", 3915810, "paa-trr", "Latn", } m["gnw"] = { "Western Bolivian Guarani", 3775037, "gn", "Latn", } m["gnz"] = { "Ganzi", 11137942, "nic-nkb", "Latn", } m["goa"] = { "Guro", 35251, "dmn-mda", "Latn", } m["gob"] = { "Playero", 3027923, "sai-guh", } m["goc"] = { "Gorakor", 12952463, "poz-ocw", "Latn", } m["god"] = { "Godié", 3914412, "kro-bet", } m["goe"] = { "Gongduk", 2669221, "sit", } m["gof"] = { "Gofa", 12631584, "omv-nom", "Latn, Ethi", } m["gog"] = { "Gogo", 3272630, "bnt-ruv", "Latn", } m["goh"] = { "Old High German", 35218, "gmw-hgm", "Latn, Runr", strip_diacritics = { remove_diacritics = c.circ .. c.macron .. c.diaer, from = {"[ƷȤ]", "[ʒȥ]"}, to = {"Z", "z"} }, translit = { Runr = "Runr-translit", }, } m["goi"] = { "Gobasi", 5575414, "ngf-est", "Latn", } m["goj"] = { "Gowlan", 12953532, "inc-sou", } -- gok is a spurious language, see [[w:Spurious languages]] m["gol"] = { "Gola", 35482, "alv", "Latn, Vaii", } m["gon"] = { "Gondi", 1775361, "dra-gon", "Telu, Gonm, Gong, Deva, Orya", translit = { Telu = "te-translit", Gong = "gon-Gong-translit", Gonm = "gon-Gonm-translit", }, } m["goo"] = { "Gone Dau", 3110470, "poz-pcc", "Latn", } m["gop"] = { "Yeretuar", 8052565, "poz-hce", "Latn", } m["goq"] = { "Gorap", 3110816, "crp", "Latn", ancestors = "ms", } m["gor"] = { "Gorontalo", 2501174, "phi", "Latn", } m["got"] = { "Gothic", 35722, "gme", "Goth, Runr, Latn", translit = {Goth = "Goth-translit"}, link_tr = true, strip_diacritics = {Latn = {remove_diacritics = c.macron}}, } m["gou"] = { "Gavar", 3441180, "cdc-cbm", } m["gov"] = { "Goo", 16927208, "dmn", "Latn", } m["gow"] = { "Gorwaa", 3437626, "cus-sou", "Latn", } m["gox"] = { "Gobu", 7194986, "bad-cnt", } m["goy"] = { "Goundo", 317636, "alv-kim", } m["goz"] = { "Gozarkhani", 5590235, "xme-ttc", ancestors = "xme-ttc-eas", } m["gpa"] = { "Gupa-Abawa", 3915352, "alv-ngb", "Latn", } m["gpn"] = { "Taiap", 56237, "qfa-dis", -- Papuan; isolate in Glottolog; relationship with Torricelli proposed by Usher "Latn", } m["gqa"] = { "Ga'anda", 56245, "cdc-cbm", "Latn", } m["gqi"] = { "Guiqiong", 3120647, "sit-qia", } m["gqn"] = { -- a variety of 'ter' "Kinikinao", 53386731, "awd", "Latn", } m["gqr"] = { "Gor", 759992, "csu-sar", "Latn", } m["gqu"] = { "Qau", 17284874, "gio", } m["gra"] = { "Rajput Garasia", 21041529, "inc-bhi", "Deva, Gujr", ancestors = "bhb", } m["grc"] = { "Ancient Greek", 35497, "grk", "Polyt, Cprt", translit = { Cprt = "Cprt-translit", }, override_translit = true, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Polyt = "ΑΆἈἉἊἋἌἍἎἏᾈᾉᾊᾋᾌᾍᾎᾏᾸᾹᾺᾼΒΓΔΕΈἘἙἚἛἜἝῈΖΗΉἨἩἪἫἬἭἮἯᾘᾙᾚᾛᾜᾝᾞᾟῊῌΘΙΊΪἸἹἺἻἼἽἾἿῘῙῚΚΛΜΝΞΟΌὈὉὊὋὌὍΠΡῬΡ̓ΣΤΥΎΫὙὛὝὟῨῩῪΦΧΨΩΏὨὩὪὫὬὭὮὯᾨᾩᾪᾫᾬᾭᾮᾯῸῺῼαάἀἁἂἃἄἅἆἇὰᾀᾁᾂᾃᾄᾅᾆᾇᾰᾱᾲᾳᾴᾶᾷβγδεέἐἑἒἓἔἕὲζηήἠἡἢἣἤἥἦἧὴᾐᾑᾒᾓᾔᾕᾖᾗῂῃῄῆῇθιίϊΐἰἱἲἳἴἵἶἷὶῐῑῒῖῗκλμνξοόὀὁὂὃὄὅὸπρῤῥςστυύϋΰὐὑὒὓὔὕὖὗὺῠῡῢῦῧφχψωώὠὡὢὣὤὥὦὧὼᾠᾡᾢᾣᾤᾥᾦᾧῲῳῴῶῷ·ͺ΄΅᾽᾿῀῁῍῎῏῝῞῟῭`´῾", Cprt = "𐠀𐠁𐠂𐠃𐠄𐠅𐠈𐠊𐠋𐠌𐠍𐠎𐠏𐠐𐠑𐠒𐠓𐠔𐠕𐠖𐠗𐠘𐠙𐠚𐠛𐠜𐠝𐠞𐠟𐠠𐠡𐠢𐠣𐠤𐠥𐠦𐠧𐠨𐠩𐠪𐠫𐠬𐠭𐠮𐠯𐠰𐠱𐠲𐠳𐠴𐠵𐠷𐠸𐠼𐠿", c.punc }, } m["grd"] = { "Guruntum", 3441272, "cdc-wst", "Latn", } m["grg"] = { "Madi", 6727664, "ngf-gmo", "Latn", } m["grh"] = { "Gbiri-Niragu", 3913936, "nic-kau", "Latn", } m["gri"] = { "Ghari", 3104782, "poz-sls", "Latn", } m["grj"] = { "Southern Grebo", 3914444, "grb", "Latn", } m["grm"] = { "Kota Marudu Talantang", 6433808, "poz-san", "Latn", } m["gro"] = { "Groma", 56551, "sit-tib", } m["grq"] = { "Gorovu", 56355, "paa-por", "Latn", } m["grs"] = { "Gresi", 5607612, "paa-nim", "Latn", } m["grt"] = { "Garo", 36137, "tbq-bdg", "Latn, Beng, Brai", } m["gru"] = { "Kistane", 13273, "sem-eth", "Latn, Ethi", } m["grv"] = { "Central Grebo", 18385114, "grb", "Latn", } m["grw"] = { "Gweda", 5623387, "poz-ocw", "Latn", } m["grx"] = { "Guriaso", 12631954, "qfa-unc", -- no consensus; may be Kwomtari per Baron (1983) and Usher (2020), but no connections accepted by -- Glottolog. "Latn", } m["gry"] = { "Barclayville Grebo", 11157342, "grb", "Latn", } m["grz"] = { "Guramalum", 3120935, "poz-ocw", "Latn", } m["gse"] = { "Ghanaian Sign Language", 35289, "sgn", "Latn", -- when documented } m["gsg"] = { "German Sign Language", 33282, "sgn-gsl", "Sgnw", } m["gsl"] = { "Gusilay", 35439, "alv-jol", "Latn", } m["gsm"] = { "Guatemalan Sign Language", 2886781, "sgn", "Latn", -- when documented } m["gsn"] = { "Gusan", 11732224, "ngf-era", "Latn", } m["gso"] = { "Southwest Gbaya", 4919322, "gba-sou", "Latn", } m["gsp"] = { "Wasembo", 7971402, "ngf-mad", -- placed in under Rai Coast by Glottolog (under Greater Yaganon) and Pawley-Hammarström "Latn", } m["gss"] = { "Greek Sign Language", 3565084, "sgn", } m["gsw"] = { "Alemannic German", 131339, "gmw-hgm", "Latn", wikimedia_codes = "als", ancestors = "gmh", } m["gta"] = { "Guató", 3027940, "qfa-dis", -- isolate or Macro-Jê "Latn", } m["gtu"] = { "Aghu Tharrnggala", 16825981, "aus-pmn", "Latn", } m["gua"] = { "Shiki", 3913946, "nic-jrn", "Latn", } m["gub"] = { "Guajajára", 7699720, "tup-gua", "Latn", } m["guc"] = { "Wayuu", 891085, "awd-taa", "Latn", } m["gud"] = { "Yocoboué Dida", 21074781, "kro-did", "Latn", } m["gue"] = { "Gurindji", 10511016, "aus-pam", "Latn", } m["guf"] = { "Gupapuyngu", 10511004, "aus-yol", "Latn", } m["gug"] = { "Paraguayan Guarani", 17478066, "gn", "Latn", wikimedia_codes = "gn", ancestors = "gn-cls", } m["guh"] = { "Guahibo", 2669193, "sai-guh", "Latn", } m["gui"] = { "Eastern Bolivian Guarani", 2963912, "gn", "Latn", } m["guk"] = { "Gumuz", 2396970, "ssa", "Latn, Ethi", } m["gul"] = { "Gullah", 33395, "crp", "Latn", ancestors = "en", } m["gum"] = { "Guambiano", 2744745, "sai-bar", "Latn", } m["gun"] = { "Mbya Guarani", 3915584, "gn", "Latn", } m["guo"] = { "Guayabero", 2980375, "sai-guh", "Latn", } m["gup"] = { "Gunwinggu", 1406574, "aus-gun", "Latn", } m["guq"] = { "Aché", 383701, "tup", "Latn", } m["gur"] = { "Farefare", 35331, "nic-mre", "Latn", } m["gus"] = { "Guinean Sign Language", 15983937, "sgn", "Latn", -- when documented } m["gut"] = { "Maléku Jaíka", 3915782, "cba", "Latn", } m["guu"] = { "Yanomamö", 8048928, "sai-ynm", "Latn", } m["guv"] = { "Gey", 11137816, "alv-sav", "Latn", } m["guw"] = { "Gun", 3111668, "alv-gbe", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron}, } m["gux"] = { "Gourmanchéma", 35474, "nic-grm", "Latn", } m["guz"] = { "Gusii", 33603, "bnt-lok", "Latn", } m["gva"] = { "Kaskihá", 3033534, "sai-mas", "Latn", } m["gvc"] = { "Guanano", 3566001, "sai-tuc", "Latn", } m["gve"] = { "Duwet", 5317647, "poz-ocw", "Latn", } m["gvf"] = { "Golin", 3110291, "ngf-sim", "Latn", } m["gvj"] = { "Guajá", 3915506, "tup", "Latn", } m["gvl"] = { "Gulay", 641737, "csu-sar", "Latn", } m["gvm"] = { "Gurmana", 3913363, "nic-shi", "Latn", } m["gvn"] = { "Kuku-Yalanji", 5621973, "aus-pam", "Latn", } m["gvo"] = { "Gavião do Jiparaná", 5528335, "tup", "Latn", } m["gvp"] = { "Pará Gavião", 3365443, "sai-nje", "Latn", } m["gvr"] = { "Gurung", 2392342, "sit-tam", "Gukh, Deva", } m["gvs"] = { "Gumawana", 5618041, "poz-ocw", "Latn", } m["gvy"] = { "Guyani", 10511230, "aus-pam", "Latn", } m["gwa"] = { "Mbato", 3914941, "alv-ptn", "Latn", } m["gwb"] = { "Gwa", 5623219, "nic-jrn", "Latn", } m["gwc"] = { "Kalami", 1675961, "inc-koh", "Arab", strip_diacritics = { ["Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ۂ", "ٱ"}, to = {"ہ", "ہ", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef .. u(0x065e) }, }, } m["gwd"] = { "Gawwada", 3032135, "cus-eas", "Latn, Ethi", } m["gwe"] = { "Gweno", 3358211, "bnt-chg", "Latn", } m["gwf"] = { "Gowro", 3812403, "inc-koh", "Arab", } m["gwg"] = { "Moo", 6907057, "alv-bwj", "Latn", } m["gwi"] = { "Gwich'in", 21057, "ath-nor", "Latn", } m["gwj"] = { "Gcwi", 12631978, "khi-kal", "Latn", } m["gwm"] = { "Awngthim", 4830109, "aus-pmn", "Latn", } m["gwn"] = { "Gwandara", 56521, "cdc-wst", "Latn", } m["gwr"] = { "Gwere", 5623559, "bnt-nyg", "Latn", } m["gwt"] = { "Gawar-Bati", 33894, "inc-kun", "Arab", } m["gwu"] = { "Guwamu", 10511225, "aus-pam", "Latn", } m["gww"] = { "Kwini", 10551249, "aus-wor", "Latn", } m["gwx"] = { "Gua", 35422, "alv-gng", "Latn", } m["gxx"] = { "Wè Southern", 19921582, "kro-wee", "Latn", } m["gya"] = { "Northwest Gbaya", 36594, "gba-wes", "Latn", } m["gyb"] = { "Garus", 5524492, "ngf-han", "Latn", } m["gyd"] = { "Kayardild", 3913770, "aus-tnk", "Latn", } m["gye"] = { "Gyem", 5624046, "nic-jer", "Latn", } m["gyf"] = { "Gungabula", 10510783, "aus-pam", "Latn", } m["gyg"] = { "Gbayi", 11137618, "nic-ngd", "Latn", } m["gyi"] = { "Gyele", 35434, "bnt-mnj", "Latn", } m["gyl"] = { "Gayil", 5528771, "omv-aro", "Latn", } m["gym"] = { "Ngäbere", 3915581, "cba", "Latn", } m["gyn"] = { "Guyanese Creole English", 3305477, "crp", "Latn", ancestors = "en", } m["gyo"] = { "Gyalsumdo", 53575940, "sit-kyk", } m["gyr"] = { "Guarayu", 3118779, "tup-gua", "Latn", } m["gyy"] = { "Gunya", 10511001, "aus-pam", "Latn", } m["gza"] = { "Ganza", 5521556, "omv-mao", "Latn", } m["gzn"] = { "Gane", 3095108, "poz-hce", "Latn", } return require("Module:languages").finalizeData(m, "language") o4h8upiez223ahia9apb68a5ls6lwwn 231386 231385 2026-04-14T07:49:37Z Lee 19 [[:en:Module:languages/data/3/g]] වෙතින් එක් සංශෝධනයක් 231385 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["gaa"] = { "Ga", 33287, "alv-gda", "Latn", } m["gab"] = { "Gabri", 3441237, "cdc-est", "Latn", } m["gac"] = { "Mixed Great Andamanese", 56329630, "qfa-adn", "Latn", } m["gad"] = { -- not to be confused with gdk, gdg "Gaddang", 3438830, "phi", "Latn", } m["gae"] = { "Warekena", 1091095, "awd-nwk", "Latn", } m["gaf"] = { "Gende", 3100425, "ngf-gor", "Latn", } m["gag"] = { "Gagauz", 33457, "trk-ogz", "Latn, Cyrl", ancestors = "trk-oat", dotted_dotless_i = true, sort_key = { Latn = { from = { "i", -- Ensure "i" comes after "ı". "ä", "ç", "ê", "ı", "ö", "ş", "ţ", "ü" }, to = { "i" .. p[1], "a" .. p[1], "c" .. p[1], "e" .. p[1], "i", "o" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1] } }, }, } m["gah"] = { "Alekano", 3441595, "ngf-gah", "Latn", } m["gai"] = { "Borei", 6799756, "paa-ott", "Latn", } m["gaj"] = { "Gadsup", 5516467, "ngf-gau", "Latn", } m["gak"] = { "Gamkonora", 5520226, "paa-sah", "Latn", } m["gal"] = { "Galoli", 35322, "poz-tim", "Latn", } m["gam"] = { "Kandawo", 6361369, "ngf-jim", "Latn", } m["gan"] = { "Gan", 33475, "zhx", "Hants", ancestors = "ltc", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["gao"] = { "Gants", 5521529, "ngf-eso", "Latn", } m["gap"] = { "Gal", 5517742, "ngf-han", "Latn", } m["gaq"] = { "Gata'", 3501920, "mun", "Orya", } m["gar"] = { "Galeya", 5518509, "poz-ocw", "Latn", } m["gas"] = { "Adiwasi Garasia", 12953522, "inc-bhi", "Deva, Gujr", ancestors = "bhb", } m["gat"] = { "Kenati", 4219330, "ngf-kgo", "Latn", } m["gau"] = { "Kondekor", 12952433, "dra-pgd", "Telu", } m["gaw"] = { "Nobonob", 11732205, "ngf-han", "Latn", } m["gay"] = { "Gayo", 33286, "poz-nws", "Latn", } m["gbb"] = { "Kaytetye", 6380709, "aus-rnd", "Latn", } m["gbd"] = { "Karadjeri", 3913837, "aus-pam", "Latn", } m["gbe"] = { "Niksek", 56375, "paa-sep", "Latn", } m["gbf"] = { "Gaikundi", 5517032, "paa-nnd", "Latn", } m["gbg"] = { "Gbanziri", 35306, "nic-nkg", "Latn", } m["gbh"] = { "Defi Gbe", 12952446, "alv-gbe", "Latn", } m["gbi"] = { "Galela", 3094570, "paa-gto", "Latn", } m["gbj"] = { "Bodo Gadaba", 3347070, "mun", "Orya", } m["gbk"] = { "Gaddi", 17455500, "him", "Deva, Takr", translit = {Deva = "hi-translit"}, } m["gbl"] = { "Gamit", 2731717, "inc-bhi", "Deva, Gujr", } m["gbm"] = { "Garhwali", 33459, "inc-pah", "Deva", translit = "hi-translit", } m["gbn"] = { "Mo'da", 12755683, "csu-bbk", "Latn", } m["gbo"] = { "Northern Grebo", 11157042, "grb", "Latn", } m["gbp"] = { "Gbaya-Bossangoa", 11011295, "gba-wes", "Latn", } m["gbq"] = { "Gbaya-Bozoum", 4952879, "gba-wes", "Latn", } m["gbr"] = { "Gbagyi", 11015105, "alv-ngb", "Latn", } m["gbs"] = { "Gbesi Gbe", 12952448, "alv-pph", "Latn", } m["gbu"] = { "Gagadu", 35677, "aus-arn", "Latn", } m["gbv"] = { "Gbanu", 3914945, "gba-eas", "Latn", } m["gbw"] = { "Gabi", 5515391, "aus-pam", "Latn", } m["gbx"] = { "Eastern Xwla Gbe", 18379975, "alv-pph", "Latn", } m["gby"] = { "Gbari", 3915451, "alv-ngb", "Latn", } m["gcc"] = { "Mali", 6743338, "paa-bai", "Latn", } m["gcd"] = { "Ganggalida", 3913765, "aus-tnk", "Latn", } m["gce"] = { "Galice", 20711, "ath-pco", "Latn", } m["gcf"] = { "Antillean Creole", 3006280, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["gcl"] = { "Grenadian Creole English", 4252500, "crp", "Latn", ancestors = "en", } m["gcn"] = { "Gaina", 11732195, "ngf-gko", "Latn", } m["gcr"] = { "Guianese Creole", 1363072, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["gct"] = { "Colonia Tovar German", 1138351, "gmw-hgm", "Latn", ancestors = "gsw", } m["gdb"] = { "Ollari", 33906, "dra-pgd", "Orya, Telu", translit = { Telu = "te-translit" }, } m["gdc"] = { "Gugu Badhun", 10510360, "aus-pam", "Latn", } m["gdd"] = { "Gedaged", 35292, "poz-ocw", "Latn", } m["gde"] = { "Gude", 3441230, "cdc-cbm", "Latn", } m["gdf"] = { "Guduf-Gava", 3441350, "cdc-cbm", "Latn", } m["gdg"] = { -- not to be confused with gad, gdk "Ga'dang", 5515189, "phi", "Latn", } m["gdh"] = { "Gadjerawang", 3913817, "aus-jar", "Latn", } m["gdi"] = { "Gundi", 11137851, "nic-nkb", "Latn", } m["gdj"] = { "Kurtjar", 5619931, "aus-pmn", "Latn", } m["gdk"] = { -- not to be confused with gad, gdg "Gadang", 56256, "cdc-est", "Latn", } m["gdl"] = { "Dirasha", 56809, "cus-eas", "Ethi", } m["gdm"] = { "Laal", 33436, "qfa-dis", -- Chad; unclassified, isolate or grouped with Adamawa or Chadic languages "Latn", } m["gdn"] = { "Umanakaina", 7881084, "ngf-dag", "Latn", } m["gdo"] = { "Godoberi", 56515, "cau-and", "Cyrl", display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["gdq"] = { "Mehri", 13361, "sem-sar", "Arab, Latn", } m["gdr"] = { "Wipi", 8026711, "paa-etf", "Latn", } m["gds"] = { "Ghandruk Sign Language", 15971577, "sgn", } m["gdt"] = { "Kungardutyi", 6444517, "aus-kar", "Latn", } m["gdu"] = { "Gudu", 3441172, "cdc-cbm", "Latn", } m["gdx"] = { "Godwari", 3540922, "raj", "Deva", } m["gea"] = { "Geruma", 3438789, "cdc-wst", "Latn", } m["geb"] = { "Kire", 11129733, "paa-rub", "Latn", } m["gec"] = { "Gboloo Grebo", 11019342, "grb", "Latn", } m["ged"] = { "Gade", 3914459, "alv-nup", "Latn", } m["geg"] = { "Gengle", 3438345, "alv-mye", "Latn", ancestors = "kow", } m["geh"] = { "Hutterisch", 33385, "gmw-hgm", "Latn", ancestors = "bar", } m["gei"] = { "Gebe", 3100032, "poz-hce", "Latn", } m["gej"] = { "Gen", 33450, "alv-gbe", "Latn", } m["gek"] = { "Gerka", 3441277, "cdc-wst", "Latn", } m["gel"] = { "Fakkanci", 36627, "nic-knn", "Latn", } m["geq"] = { "Geme", 3915851, "znd", "Latn", } m["ges"] = { "Geser-Gorom", 5553579, "poz-cma", "Latn", } m["gev"] = { "Viya", 7937974, "bnt-tso", "Latn", } m["gew"] = { "Gera", 3438725, "cdc-wst", "Latn", } m["gex"] = { "Garre", 56618, "cus-som", "Latn", } m["gey"] = { "Enya", 5381452, "bnt-mbe", "Latn", } m["gez"] = { "Ge'ez", 35667, "sem-eth", "Ethi", translit = "Ethi-translit", } m["gfk"] = { "Patpatar", 3368846, "poz-ocw", "Latn", } m["gft"] = { "Gafat", 56910, "sem-eth", "Ethi, Latn", } m["gga"] = { "Gao", 3095228, "poz-ocw", "Latn", } m["ggb"] = { "Gbii", 3914390, "kro-wkr", "Latn", } m["ggd"] = { "Gugadj", 5615186, "aus-pmn", "Latn", } m["gge"] = { "Guragone", 5619801, "aus-arn", "Latn", } m["ggg"] = { "Gurgula", 5620032, "raj", "Arab", } m["ggk"] = { "Kungarakany", 6444516, "aus-arn", "Latn", } m["ggl"] = { "Ganglau", 5521140, "ngf-yag", "Latn", } m["ggt"] = { "Gitua", 3107865, "poz-ocw", "Latn", } m["ggu"] = { "Gban", 3913317, "dmn-nbe", "Latn", } m["ggw"] = { "Gogodala", 3512161, "ngf-gsu", "Latn", } m["gha"] = { "Ghadames", 56747, "ber", "Latn", -- and other scripts? } m["ghc"] = { "Classical Gaelic", 5128278, "cel-gae", "Latn, Latg", ancestors = "mga", } m["ghe"] = { "Southern Ghale", 12952453, "sit-tam", "Deva", } m["ghh"] = { "Northern Ghale", 22662104, "sit-tam", "Deva", } m["ghk"] = { "Geko Karen", 5530317, "kar", } m["ghl"] = { "Ghulfan", 16885737, "nub-hil", "Latn", -- and others? } m["ghn"] = { "Ghanongga", 3104772, "poz-ocw", "Latn", } m["gho"] = { "Ghomara", 35315, "ber", "Tfng, Latn", translit = {Tfng = "Tfng-translit"}, } m["ghr"] = { "Ghera", 22808992, "inc-hiw", } m["ghs"] = { "Guhu-Samane", 11732219, "ngf-gbi", "Latn", } m["ght"] = { "Kutang Ghale", 6448337, "sit-tam", "Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["gia"] = { "Kitja", 1284877, "aus-jar", "Latn", } m["gib"] = { "Gibanawa", 12953530, "crp", "Latn", ancestors = "ha", } m["gid"] = { "Gidar", 35265, "cdc-cbm", "Latn", } m["gie"] = { "Guébie", 63140714, "kro-did", "Latn", } m["gig"] = { "Goaria", 33269, "raj", "Arab", } m["gih"] = { "Githabul", 48987680, "aus-pam", "Latn", } m["gii"] = { "Girirra", 5564288, "cus-som", } m["gil"] = { "Gilbertese", 30898, "poz-mic", "Latn", } m["gim"] = { "Gimi (Papuan)", 11732209, "ngf-fgi", "Latn", } m["gin"] = { "Hinukh", 33283, "cau-wts", "Cyrl", translit = "gin-translit", display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["gip"] = { "Gimi (Austronesian)", 12952457, "poz-ocw", } m["giq"] = { "Green Gelao", 12953525, "gio", "Latn", } m["gir"] = { "Red Gelao", 3100264, "gio", } m["gis"] = { "North Giziga", 3515084, "cdc-cbm", } m["git"] = { "Gitxsan", 3107862, "nai-tsi", "Latn", } m["giu"] = { "Mulao", 11092831, "gio", } m["giw"] = { "White Gelao", 8843040, "gio", } m["gix"] = { "Gilima", 10977716, "nic-nkm", "Latn", } m["giy"] = { "Giyug", 5565906, } m["giz"] = { "South Giziga", 3502232, "cdc-cbm", } m["gji"] = { "Geji", 3914890, "cdc-wst", "Latn", } m["gjk"] = { "Kachi Koli", 12953646, "inc-wes", } m["gjm"] = { "Gunditjmara", 6448731, "aus-pam", "Latn", } m["gjn"] = { "Gonja", 35267, "alv-gng", "Latn", } m["gjr"] = { "Gurindji Kriol", 5620091, "qfa-mix", "Latn", ancestors = "gue, rop" } m["gju"] = { "Gojri", 3241731, "raj", "ur-Arab, Deva, Takr", strip_diacritics = { ["ur-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.smallv, from = {"ڵ", "ݩ"}, to = {"ل", "ن"} }, }, translit = {["ur-Arab"] = "ur-translit"}, } m["gka"] = { "Guya", 11732221, "ngf-war", "Latn", } m["gkd"] = { "Magi", 55621742, "ngf-ais", "Latn", } m["gke"] = { "Ndai", 6983667, "alv-mbm", } m["gkn"] = { "Gokana", 3075137, "nic-ogo", "Latn", } m["gko"] = { "Kok-Nar", 6426526, "aus-pmn", "Latn", } m["gkp"] = { "Guinea Kpelle", 11052867, "dmn-msw", "Latn, Kpel", ancestors = "kpe", } m["glc"] = { "Bon Gula", 289816, "alv-bua", } m["gld"] = { "Nanai", 13303, "tuw-nan", "Cyrl", translit = "gld-translit", strip_diacritics = {remove_diacritics = c.macron}, sort_key = { from = {"ё", "ӈ"}, to = {"е" .. p[1], "н" .. p[1]} }, } m["glh"] = { "Northwest Pashayi", 23713532, "inc-pas", "fa-Arab", } m["glj"] = { "Kulaal", 33360, "alv-bua", } m["glk"] = { "Gilaki", 33657, "ira-csp", "fa-Arab", } m["glo"] = { "Galambu", 2598797, "cdc-wst", "Latn", } m["glr"] = { "Glaro-Twabo", 3915313, "kro-wee", } m["glu"] = { "Gula", 5617176, "csu-bgr", "Latn", } m["glw"] = { "Glavda", 3441285, "cdc-cbm", "Latn", } m["gly"] = { "Gule", 3120736, "ssa-kom", } m["gma"] = { "Gambera", 10502327, "aus-wor", "Latn", } m["gmb"] = { "Gula'alaa", 3120733, "poz-sls", "Latn", } m["gmd"] = { "Mághdì", 3914475, "alv-bwj", } m["gmg"] = { "Magiyi", 16926155, "ngf-sog", "Latn", } m["gmh"] = { "Middle High German", 837985, "gmw-hgm", "Latn", strip_diacritics = { remove_diacritics = c.circ .. c.macron, from = {"Ë", "ë", "[ƷȤ]", "[ʒȥ]"}, to = {"E", "e", "Z", "z"} }, } m["gml"] = { "Middle Low German", 505674, "gmw-lgm", "Latn", strip_diacritics = {remove_diacritics = c.circ .. c.macron .. c.diaer}, } m["gmm"] = { "Gbaya-Mbodomo", 6799713, "gba-eas", "Latn", } m["gmn"] = { "Gimnime", 11016905, "alv-dur", "Latn", } m["gmr"] = { "Mirning", 6873793, "aus-pam", "Latn", } m["gmu"] = { "Gumalu", 5618027, "ngf-gum", "Latn", } m["gmv"] = { "Gamo", 16116386, "omv-nom", "Latn, Ethi", } m["gmx"] = { "Magoma", 16939552, "bnt-bki", } m["gmy"] = { "Mycenaean Greek", 668366, "grk", "Linb", translit = "Linb-translit", } m["gmz"] = { "Mgbo", 6826835, "alv-igb", ancestors = "izi", } m["gna"] = { "Kaansa", 56802, "nic-gur", } m["gnb"] = { "Gangte", 12952442, "tbq-kuk", } m["gnc"] = { "Guanche", 35762, "ber", } m["gnd"] = { "Zulgo-Gemzek", 56800, "cdc-cbm", "Latn", } m["gne"] = { "Ganang", 63163361, "nic-plc", ancestors = "izr", } m["gng"] = { "Ngangam", 35888, "nic-grm", } m["gnh"] = { "Lere", 3915319, "nic-jer", } m["gni"] = { "Gooniyandi", 2669219, "aus-bub", "Latn", } m["gnj"] = { "Ngen of Djonkro", 63170838, "dmn-nbe", "Latn", } m["gnk"] = { "ǁGana", 1975199, "khi-kal", "Latn", } m["gnl"] = { "Gangulu", 4916329, "aus-pam", "Latn", } m["gnm"] = { "Ginuman", 11732210, "ngf-dag", "Latn", } m["gnn"] = { "Gumatj", 10510745, "aus-yol", "Latn", } m["gnq"] = { "Gana", 5520523, "poz-san", "Latn", } m["gnr"] = { "Gureng Gureng", 5619998, "aus-pam", "Latn", } m["gnt"] = { "Guntai", 12952475, "paa-ton", "Latn", } m["gnu"] = { "Gnau", 3915810, "paa-trr", "Latn", } m["gnw"] = { "Western Bolivian Guarani", 3775037, "gn", "Latn", } m["gnz"] = { "Ganzi", 11137942, "nic-nkb", "Latn", } m["goa"] = { "Guro", 35251, "dmn-mda", "Latn", } m["gob"] = { "Playero", 3027923, "sai-guh", } m["goc"] = { "Gorakor", 12952463, "poz-ocw", "Latn", } m["god"] = { "Godié", 3914412, "kro-bet", } m["goe"] = { "Gongduk", 2669221, "sit", } m["gof"] = { "Gofa", 12631584, "omv-nom", "Latn, Ethi", } m["gog"] = { "Gogo", 3272630, "bnt-ruv", "Latn", } m["goh"] = { "Old High German", 35218, "gmw-hgm", "Latn, Runr", strip_diacritics = { remove_diacritics = c.circ .. c.macron .. c.diaer, from = {"[ƷȤ]", "[ʒȥ]"}, to = {"Z", "z"} }, translit = { Runr = "Runr-translit", }, } m["goi"] = { "Gobasi", 5575414, "ngf-est", "Latn", } m["goj"] = { "Gowlan", 12953532, "inc-sou", } -- gok is a spurious language, see [[w:Spurious languages]] m["gol"] = { "Gola", 35482, "alv", "Latn, Vaii", } m["gon"] = { "Gondi", 1775361, "dra-gon", "Telu, Gonm, Gong, Deva, Orya", translit = { Telu = "te-translit", Gong = "gon-Gong-translit", Gonm = "gon-Gonm-translit", }, } m["goo"] = { "Gone Dau", 3110470, "poz-pcc", "Latn", } m["gop"] = { "Yeretuar", 8052565, "poz-hce", "Latn", } m["goq"] = { "Gorap", 3110816, "crp", "Latn", ancestors = "ms", } m["gor"] = { "Gorontalo", 2501174, "phi", "Latn", } m["got"] = { "Gothic", 35722, "gme", "Goth, Runr, Latn", translit = {Goth = "Goth-translit"}, link_tr = true, strip_diacritics = {Latn = {remove_diacritics = c.macron}}, } m["gou"] = { "Gavar", 3441180, "cdc-cbm", } m["gov"] = { "Goo", 16927208, "dmn", "Latn", } m["gow"] = { "Gorwaa", 3437626, "cus-sou", "Latn", } m["gox"] = { "Gobu", 7194986, "bad-cnt", } m["goy"] = { "Goundo", 317636, "alv-kim", } m["goz"] = { "Gozarkhani", 5590235, "xme-ttc", ancestors = "xme-ttc-eas", } m["gpa"] = { "Gupa-Abawa", 3915352, "alv-ngb", "Latn", } m["gpn"] = { "Taiap", 56237, "qfa-dis", -- Papuan; isolate in Glottolog; relationship with Torricelli proposed by Usher "Latn", } m["gqa"] = { "Ga'anda", 56245, "cdc-cbm", "Latn", } m["gqi"] = { "Guiqiong", 3120647, "sit-qia", } m["gqn"] = { -- a variety of 'ter' "Kinikinao", 53386731, "awd", "Latn", } m["gqr"] = { "Gor", 759992, "csu-sar", "Latn", } m["gqu"] = { "Qau", 17284874, "gio", } m["gra"] = { "Rajput Garasia", 21041529, "inc-bhi", "Deva, Gujr", ancestors = "bhb", } m["grc"] = { "Ancient Greek", 35497, "grk", "Polyt, Cprt", translit = { Cprt = "Cprt-translit", }, override_translit = true, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Polyt = "ΑΆἈἉἊἋἌἍἎἏᾈᾉᾊᾋᾌᾍᾎᾏᾸᾹᾺᾼΒΓΔΕΈἘἙἚἛἜἝῈΖΗΉἨἩἪἫἬἭἮἯᾘᾙᾚᾛᾜᾝᾞᾟῊῌΘΙΊΪἸἹἺἻἼἽἾἿῘῙῚΚΛΜΝΞΟΌὈὉὊὋὌὍΠΡῬΡ̓ΣΤΥΎΫὙὛὝὟῨῩῪΦΧΨΩΏὨὩὪὫὬὭὮὯᾨᾩᾪᾫᾬᾭᾮᾯῸῺῼαάἀἁἂἃἄἅἆἇὰᾀᾁᾂᾃᾄᾅᾆᾇᾰᾱᾲᾳᾴᾶᾷβγδεέἐἑἒἓἔἕὲζηήἠἡἢἣἤἥἦἧὴᾐᾑᾒᾓᾔᾕᾖᾗῂῃῄῆῇθιίϊΐἰἱἲἳἴἵἶἷὶῐῑῒῖῗκλμνξοόὀὁὂὃὄὅὸπρῤῥςστυύϋΰὐὑὒὓὔὕὖὗὺῠῡῢῦῧφχψωώὠὡὢὣὤὥὦὧὼᾠᾡᾢᾣᾤᾥᾦᾧῲῳῴῶῷ·ͺ΄΅᾽᾿῀῁῍῎῏῝῞῟῭`´῾", Cprt = "𐠀𐠁𐠂𐠃𐠄𐠅𐠈𐠊𐠋𐠌𐠍𐠎𐠏𐠐𐠑𐠒𐠓𐠔𐠕𐠖𐠗𐠘𐠙𐠚𐠛𐠜𐠝𐠞𐠟𐠠𐠡𐠢𐠣𐠤𐠥𐠦𐠧𐠨𐠩𐠪𐠫𐠬𐠭𐠮𐠯𐠰𐠱𐠲𐠳𐠴𐠵𐠷𐠸𐠼𐠿", c.punc }, } m["grd"] = { "Guruntum", 3441272, "cdc-wst", "Latn", } m["grg"] = { "Madi", 6727664, "ngf-gmo", "Latn", } m["grh"] = { "Gbiri-Niragu", 3913936, "nic-kau", "Latn", } m["gri"] = { "Ghari", 3104782, "poz-sls", "Latn", } m["grj"] = { "Southern Grebo", 3914444, "grb", "Latn", } m["grm"] = { "Kota Marudu Talantang", 6433808, "poz-san", "Latn", } m["gro"] = { "Groma", 56551, "sit-tib", } m["grq"] = { "Gorovu", 56355, "paa-por", "Latn", } m["grs"] = { "Gresi", 5607612, "paa-nim", "Latn", } m["grt"] = { "Garo", 36137, "tbq-bdg", "Latn, Beng, Brai", } m["gru"] = { "Kistane", 13273, "sem-eth", "Latn, Ethi", } m["grv"] = { "Central Grebo", 18385114, "grb", "Latn", } m["grw"] = { "Gweda", 5623387, "poz-ocw", "Latn", } m["grx"] = { "Guriaso", 12631954, "qfa-unc", -- no consensus; may be Kwomtari per Baron (1983) and Usher (2020), but no connections accepted by -- Glottolog. "Latn", } m["gry"] = { "Barclayville Grebo", 11157342, "grb", "Latn", } m["grz"] = { "Guramalum", 3120935, "poz-ocw", "Latn", } m["gse"] = { "Ghanaian Sign Language", 35289, "sgn", "Latn", -- when documented } m["gsg"] = { "German Sign Language", 33282, "sgn-gsl", "Sgnw", } m["gsl"] = { "Gusilay", 35439, "alv-jol", "Latn", } m["gsm"] = { "Guatemalan Sign Language", 2886781, "sgn", "Latn", -- when documented } m["gsn"] = { "Gusan", 11732224, "ngf-era", "Latn", } m["gso"] = { "Southwest Gbaya", 4919322, "gba-sou", "Latn", } m["gsp"] = { "Wasembo", 7971402, "ngf-mad", -- placed in under Rai Coast by Glottolog (under Greater Yaganon) and Pawley-Hammarström "Latn", } m["gss"] = { "Greek Sign Language", 3565084, "sgn", } m["gsw"] = { "Alemannic German", 131339, "gmw-hgm", "Latn", wikimedia_codes = "als", ancestors = "gmh", } m["gta"] = { "Guató", 3027940, "qfa-dis", -- isolate or Macro-Jê "Latn", } m["gtu"] = { "Aghu Tharrnggala", 16825981, "aus-pmn", "Latn", } m["gua"] = { "Shiki", 3913946, "nic-jrn", "Latn", } m["gub"] = { "Guajajára", 7699720, "tup-gua", "Latn", } m["guc"] = { "Wayuu", 891085, "awd-taa", "Latn", } m["gud"] = { "Yocoboué Dida", 21074781, "kro-did", "Latn", } m["gue"] = { "Gurindji", 10511016, "aus-pam", "Latn", } m["guf"] = { "Gupapuyngu", 10511004, "aus-yol", "Latn", } m["gug"] = { "Paraguayan Guarani", 17478066, "gn", "Latn", wikimedia_codes = "gn", ancestors = "gn-cls", } m["guh"] = { "Guahibo", 2669193, "sai-guh", "Latn", } m["gui"] = { "Eastern Bolivian Guarani", 2963912, "gn", "Latn", } m["guk"] = { "Gumuz", 2396970, "ssa", "Latn, Ethi", } m["gul"] = { "Gullah", 33395, "crp", "Latn", ancestors = "en", } m["gum"] = { "Guambiano", 2744745, "sai-bar", "Latn", } m["gun"] = { "Mbya Guarani", 3915584, "gn", "Latn", } m["guo"] = { "Guayabero", 2980375, "sai-guh", "Latn", } m["gup"] = { "Gunwinggu", 1406574, "aus-gun", "Latn", } m["guq"] = { "Aché", 383701, "tup", "Latn", } m["gur"] = { "Farefare", 35331, "nic-mre", "Latn", } m["gus"] = { "Guinean Sign Language", 15983937, "sgn", "Latn", -- when documented } m["gut"] = { "Maléku Jaíka", 3915782, "cba", "Latn", } m["guu"] = { "Yanomamö", 8048928, "sai-ynm", "Latn", } m["guv"] = { "Gey", 11137816, "alv-sav", "Latn", } m["guw"] = { "Gun", 3111668, "alv-gbe", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron}, } m["gux"] = { "Gourmanchéma", 35474, "nic-grm", "Latn", } m["guz"] = { "Gusii", 33603, "bnt-lok", "Latn", } m["gva"] = { "Kaskihá", 3033534, "sai-mas", "Latn", } m["gvc"] = { "Guanano", 3566001, "sai-tuc", "Latn", } m["gve"] = { "Duwet", 5317647, "poz-ocw", "Latn", } m["gvf"] = { "Golin", 3110291, "ngf-sim", "Latn", } m["gvj"] = { "Guajá", 3915506, "tup", "Latn", } m["gvl"] = { "Gulay", 641737, "csu-sar", "Latn", } m["gvm"] = { "Gurmana", 3913363, "nic-shi", "Latn", } m["gvn"] = { "Kuku-Yalanji", 5621973, "aus-pam", "Latn", } m["gvo"] = { "Gavião do Jiparaná", 5528335, "tup", "Latn", } m["gvp"] = { "Pará Gavião", 3365443, "sai-nje", "Latn", } m["gvr"] = { "Gurung", 2392342, "sit-tam", "Gukh, Deva", } m["gvs"] = { "Gumawana", 5618041, "poz-ocw", "Latn", } m["gvy"] = { "Guyani", 10511230, "aus-pam", "Latn", } m["gwa"] = { "Mbato", 3914941, "alv-ptn", "Latn", } m["gwb"] = { "Gwa", 5623219, "nic-jrn", "Latn", } m["gwc"] = { "Kalami", 1675961, "inc-koh", "Arab", strip_diacritics = { ["Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ۂ", "ٱ"}, to = {"ہ", "ہ", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef .. u(0x065e) }, }, } m["gwd"] = { "Gawwada", 3032135, "cus-eas", "Latn, Ethi", } m["gwe"] = { "Gweno", 3358211, "bnt-chg", "Latn", } m["gwf"] = { "Gowro", 3812403, "inc-koh", "Arab", } m["gwg"] = { "Moo", 6907057, "alv-bwj", "Latn", } m["gwi"] = { "Gwich'in", 21057, "ath-nor", "Latn", } m["gwj"] = { "Gcwi", 12631978, "khi-kal", "Latn", } m["gwm"] = { "Awngthim", 4830109, "aus-pmn", "Latn", } m["gwn"] = { "Gwandara", 56521, "cdc-wst", "Latn", } m["gwr"] = { "Gwere", 5623559, "bnt-nyg", "Latn", } m["gwt"] = { "Gawar-Bati", 33894, "inc-kun", "Arab", } m["gwu"] = { "Guwamu", 10511225, "aus-pam", "Latn", } m["gww"] = { "Kwini", 10551249, "aus-wor", "Latn", } m["gwx"] = { "Gua", 35422, "alv-gng", "Latn", } m["gxx"] = { "Wè Southern", 19921582, "kro-wee", "Latn", } m["gya"] = { "Northwest Gbaya", 36594, "gba-wes", "Latn", } m["gyb"] = { "Garus", 5524492, "ngf-han", "Latn", } m["gyd"] = { "Kayardild", 3913770, "aus-tnk", "Latn", } m["gye"] = { "Gyem", 5624046, "nic-jer", "Latn", } m["gyf"] = { "Gungabula", 10510783, "aus-pam", "Latn", } m["gyg"] = { "Gbayi", 11137618, "nic-ngd", "Latn", } m["gyi"] = { "Gyele", 35434, "bnt-mnj", "Latn", } m["gyl"] = { "Gayil", 5528771, "omv-aro", "Latn", } m["gym"] = { "Ngäbere", 3915581, "cba", "Latn", } m["gyn"] = { "Guyanese Creole English", 3305477, "crp", "Latn", ancestors = "en", } m["gyo"] = { "Gyalsumdo", 53575940, "sit-kyk", } m["gyr"] = { "Guarayu", 3118779, "tup-gua", "Latn", } m["gyy"] = { "Gunya", 10511001, "aus-pam", "Latn", } m["gza"] = { "Ganza", 5521556, "omv-mao", "Latn", } m["gzn"] = { "Gane", 3095108, "poz-hce", "Latn", } return require("Module:languages").finalizeData(m, "language") o4h8upiez223ahia9apb68a5ls6lwwn 231387 231386 2026-04-14T07:49:58Z Pinthura 2424 භාෂා නාම සිංහලට පරිවර්තනය 231387 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["gaa"] = { "Ga", 33287, "alv-gda", "Latn", } m["gab"] = { "Gabri", 3441237, "cdc-est", "Latn", } m["gac"] = { "Mixed Great Andamanese", 56329630, "qfa-adn", "Latn", } m["gad"] = { -- not to be confused with gdk, gdg "Gaddang", 3438830, "phi", "Latn", } m["gae"] = { "Warekena", 1091095, "awd-nwk", "Latn", } m["gaf"] = { "Gende", 3100425, "ngf-gor", "Latn", } m["gag"] = { "Gagauz", 33457, "trk-ogz", "Latn, Cyrl", ancestors = "trk-oat", dotted_dotless_i = true, sort_key = { Latn = { from = { "i", -- Ensure "i" comes after "ı". "ä", "ç", "ê", "ı", "ö", "ş", "ţ", "ü" }, to = { "i" .. p[1], "a" .. p[1], "c" .. p[1], "e" .. p[1], "i", "o" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1] } }, }, } m["gah"] = { "Alekano", 3441595, "ngf-gah", "Latn", } m["gai"] = { "Borei", 6799756, "paa-ott", "Latn", } m["gaj"] = { "Gadsup", 5516467, "ngf-gau", "Latn", } m["gak"] = { "Gamkonora", 5520226, "paa-sah", "Latn", } m["gal"] = { "Galoli", 35322, "poz-tim", "Latn", } m["gam"] = { "Kandawo", 6361369, "ngf-jim", "Latn", } m["gan"] = { "Gan", 33475, "zhx", "Hants", ancestors = "ltc", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["gao"] = { "Gants", 5521529, "ngf-eso", "Latn", } m["gap"] = { "Gal", 5517742, "ngf-han", "Latn", } m["gaq"] = { "Gata'", 3501920, "mun", "Orya", } m["gar"] = { "Galeya", 5518509, "poz-ocw", "Latn", } m["gas"] = { "Adiwasi Garasia", 12953522, "inc-bhi", "Deva, Gujr", ancestors = "bhb", } m["gat"] = { "Kenati", 4219330, "ngf-kgo", "Latn", } m["gau"] = { "Kondekor", 12952433, "dra-pgd", "Telu", } m["gaw"] = { "Nobonob", 11732205, "ngf-han", "Latn", } m["gay"] = { "Gayo", 33286, "poz-nws", "Latn", } m["gbb"] = { "Kaytetye", 6380709, "aus-rnd", "Latn", } m["gbd"] = { "Karadjeri", 3913837, "aus-pam", "Latn", } m["gbe"] = { "Niksek", 56375, "paa-sep", "Latn", } m["gbf"] = { "Gaikundi", 5517032, "paa-nnd", "Latn", } m["gbg"] = { "Gbanziri", 35306, "nic-nkg", "Latn", } m["gbh"] = { "Defi Gbe", 12952446, "alv-gbe", "Latn", } m["gbi"] = { "Galela", 3094570, "paa-gto", "Latn", } m["gbj"] = { "Bodo Gadaba", 3347070, "mun", "Orya", } m["gbk"] = { "Gaddi", 17455500, "him", "Deva, Takr", translit = {Deva = "hi-translit"}, } m["gbl"] = { "Gamit", 2731717, "inc-bhi", "Deva, Gujr", } m["gbm"] = { "Garhwali", 33459, "inc-pah", "Deva", translit = "hi-translit", } m["gbn"] = { "Mo'da", 12755683, "csu-bbk", "Latn", } m["gbo"] = { "Northern Grebo", 11157042, "grb", "Latn", } m["gbp"] = { "Gbaya-Bossangoa", 11011295, "gba-wes", "Latn", } m["gbq"] = { "Gbaya-Bozoum", 4952879, "gba-wes", "Latn", } m["gbr"] = { "Gbagyi", 11015105, "alv-ngb", "Latn", } m["gbs"] = { "Gbesi Gbe", 12952448, "alv-pph", "Latn", } m["gbu"] = { "Gagadu", 35677, "aus-arn", "Latn", } m["gbv"] = { "Gbanu", 3914945, "gba-eas", "Latn", } m["gbw"] = { "Gabi", 5515391, "aus-pam", "Latn", } m["gbx"] = { "Eastern Xwla Gbe", 18379975, "alv-pph", "Latn", } m["gby"] = { "Gbari", 3915451, "alv-ngb", "Latn", } m["gcc"] = { "Mali", 6743338, "paa-bai", "Latn", } m["gcd"] = { "Ganggalida", 3913765, "aus-tnk", "Latn", } m["gce"] = { "Galice", 20711, "ath-pco", "Latn", } m["gcf"] = { "Antillean Creole", 3006280, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["gcl"] = { "Grenadian Creole English", 4252500, "crp", "Latn", ancestors = "en", } m["gcn"] = { "Gaina", 11732195, "ngf-gko", "Latn", } m["gcr"] = { "Guianese Creole", 1363072, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["gct"] = { "Colonia Tovar German", 1138351, "gmw-hgm", "Latn", ancestors = "gsw", } m["gdb"] = { "Ollari", 33906, "dra-pgd", "Orya, Telu", translit = { Telu = "te-translit" }, } m["gdc"] = { "Gugu Badhun", 10510360, "aus-pam", "Latn", } m["gdd"] = { "Gedaged", 35292, "poz-ocw", "Latn", } m["gde"] = { "Gude", 3441230, "cdc-cbm", "Latn", } m["gdf"] = { "Guduf-Gava", 3441350, "cdc-cbm", "Latn", } m["gdg"] = { -- not to be confused with gad, gdk "Ga'dang", 5515189, "phi", "Latn", } m["gdh"] = { "Gadjerawang", 3913817, "aus-jar", "Latn", } m["gdi"] = { "Gundi", 11137851, "nic-nkb", "Latn", } m["gdj"] = { "Kurtjar", 5619931, "aus-pmn", "Latn", } m["gdk"] = { -- not to be confused with gad, gdg "Gadang", 56256, "cdc-est", "Latn", } m["gdl"] = { "Dirasha", 56809, "cus-eas", "Ethi", } m["gdm"] = { "Laal", 33436, "qfa-dis", -- Chad; unclassified, isolate or grouped with Adamawa or Chadic languages "Latn", } m["gdn"] = { "Umanakaina", 7881084, "ngf-dag", "Latn", } m["gdo"] = { "Godoberi", 56515, "cau-and", "Cyrl", display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["gdq"] = { "Mehri", 13361, "sem-sar", "Arab, Latn", } m["gdr"] = { "Wipi", 8026711, "paa-etf", "Latn", } m["gds"] = { "Ghandruk Sign Language", 15971577, "sgn", } m["gdt"] = { "Kungardutyi", 6444517, "aus-kar", "Latn", } m["gdu"] = { "Gudu", 3441172, "cdc-cbm", "Latn", } m["gdx"] = { "Godwari", 3540922, "raj", "Deva", } m["gea"] = { "Geruma", 3438789, "cdc-wst", "Latn", } m["geb"] = { "Kire", 11129733, "paa-rub", "Latn", } m["gec"] = { "Gboloo Grebo", 11019342, "grb", "Latn", } m["ged"] = { "Gade", 3914459, "alv-nup", "Latn", } m["geg"] = { "Gengle", 3438345, "alv-mye", "Latn", ancestors = "kow", } m["geh"] = { "Hutterisch", 33385, "gmw-hgm", "Latn", ancestors = "bar", } m["gei"] = { "Gebe", 3100032, "poz-hce", "Latn", } m["gej"] = { "Gen", 33450, "alv-gbe", "Latn", } m["gek"] = { "Gerka", 3441277, "cdc-wst", "Latn", } m["gel"] = { "Fakkanci", 36627, "nic-knn", "Latn", } m["geq"] = { "Geme", 3915851, "znd", "Latn", } m["ges"] = { "Geser-Gorom", 5553579, "poz-cma", "Latn", } m["gev"] = { "Viya", 7937974, "bnt-tso", "Latn", } m["gew"] = { "Gera", 3438725, "cdc-wst", "Latn", } m["gex"] = { "Garre", 56618, "cus-som", "Latn", } m["gey"] = { "Enya", 5381452, "bnt-mbe", "Latn", } m["gez"] = { "Ge'ez", 35667, "sem-eth", "Ethi", translit = "Ethi-translit", } m["gfk"] = { "Patpatar", 3368846, "poz-ocw", "Latn", } m["gft"] = { "Gafat", 56910, "sem-eth", "Ethi, Latn", } m["gga"] = { "Gao", 3095228, "poz-ocw", "Latn", } m["ggb"] = { "Gbii", 3914390, "kro-wkr", "Latn", } m["ggd"] = { "Gugadj", 5615186, "aus-pmn", "Latn", } m["gge"] = { "Guragone", 5619801, "aus-arn", "Latn", } m["ggg"] = { "Gurgula", 5620032, "raj", "Arab", } m["ggk"] = { "Kungarakany", 6444516, "aus-arn", "Latn", } m["ggl"] = { "Ganglau", 5521140, "ngf-yag", "Latn", } m["ggt"] = { "Gitua", 3107865, "poz-ocw", "Latn", } m["ggu"] = { "Gban", 3913317, "dmn-nbe", "Latn", } m["ggw"] = { "Gogodala", 3512161, "ngf-gsu", "Latn", } m["gha"] = { "Ghadames", 56747, "ber", "Latn", -- and other scripts? } m["ghc"] = { "Classical Gaelic", 5128278, "cel-gae", "Latn, Latg", ancestors = "mga", } m["ghe"] = { "Southern Ghale", 12952453, "sit-tam", "Deva", } m["ghh"] = { "Northern Ghale", 22662104, "sit-tam", "Deva", } m["ghk"] = { "Geko Karen", 5530317, "kar", } m["ghl"] = { "Ghulfan", 16885737, "nub-hil", "Latn", -- and others? } m["ghn"] = { "Ghanongga", 3104772, "poz-ocw", "Latn", } m["gho"] = { "Ghomara", 35315, "ber", "Tfng, Latn", translit = {Tfng = "Tfng-translit"}, } m["ghr"] = { "Ghera", 22808992, "inc-hiw", } m["ghs"] = { "Guhu-Samane", 11732219, "ngf-gbi", "Latn", } m["ght"] = { "Kutang Ghale", 6448337, "sit-tam", "Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["gia"] = { "Kitja", 1284877, "aus-jar", "Latn", } m["gib"] = { "Gibanawa", 12953530, "crp", "Latn", ancestors = "ha", } m["gid"] = { "Gidar", 35265, "cdc-cbm", "Latn", } m["gie"] = { "Guébie", 63140714, "kro-did", "Latn", } m["gig"] = { "Goaria", 33269, "raj", "Arab", } m["gih"] = { "Githabul", 48987680, "aus-pam", "Latn", } m["gii"] = { "Girirra", 5564288, "cus-som", } m["gil"] = { "Gilbertese", 30898, "poz-mic", "Latn", } m["gim"] = { "Gimi (Papuan)", 11732209, "ngf-fgi", "Latn", } m["gin"] = { "Hinukh", 33283, "cau-wts", "Cyrl", translit = "gin-translit", display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["gip"] = { "Gimi (Austronesian)", 12952457, "poz-ocw", } m["giq"] = { "Green Gelao", 12953525, "gio", "Latn", } m["gir"] = { "Red Gelao", 3100264, "gio", } m["gis"] = { "North Giziga", 3515084, "cdc-cbm", } m["git"] = { "Gitxsan", 3107862, "nai-tsi", "Latn", } m["giu"] = { "Mulao", 11092831, "gio", } m["giw"] = { "White Gelao", 8843040, "gio", } m["gix"] = { "Gilima", 10977716, "nic-nkm", "Latn", } m["giy"] = { "Giyug", 5565906, } m["giz"] = { "South Giziga", 3502232, "cdc-cbm", } m["gji"] = { "Geji", 3914890, "cdc-wst", "Latn", } m["gjk"] = { "Kachi Koli", 12953646, "inc-wes", } m["gjm"] = { "Gunditjmara", 6448731, "aus-pam", "Latn", } m["gjn"] = { "Gonja", 35267, "alv-gng", "Latn", } m["gjr"] = { "Gurindji Kriol", 5620091, "qfa-mix", "Latn", ancestors = "gue, rop" } m["gju"] = { "Gojri", 3241731, "raj", "ur-Arab, Deva, Takr", strip_diacritics = { ["ur-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.smallv, from = {"ڵ", "ݩ"}, to = {"ل", "ن"} }, }, translit = {["ur-Arab"] = "ur-translit"}, } m["gka"] = { "Guya", 11732221, "ngf-war", "Latn", } m["gkd"] = { "Magi", 55621742, "ngf-ais", "Latn", } m["gke"] = { "Ndai", 6983667, "alv-mbm", } m["gkn"] = { "Gokana", 3075137, "nic-ogo", "Latn", } m["gko"] = { "Kok-Nar", 6426526, "aus-pmn", "Latn", } m["gkp"] = { "Guinea Kpelle", 11052867, "dmn-msw", "Latn, Kpel", ancestors = "kpe", } m["glc"] = { "Bon Gula", 289816, "alv-bua", } m["gld"] = { "Nanai", 13303, "tuw-nan", "Cyrl", translit = "gld-translit", strip_diacritics = {remove_diacritics = c.macron}, sort_key = { from = {"ё", "ӈ"}, to = {"е" .. p[1], "н" .. p[1]} }, } m["glh"] = { "Northwest Pashayi", 23713532, "inc-pas", "fa-Arab", } m["glj"] = { "Kulaal", 33360, "alv-bua", } m["glk"] = { "Gilaki", 33657, "ira-csp", "fa-Arab", } m["glo"] = { "Galambu", 2598797, "cdc-wst", "Latn", } m["glr"] = { "Glaro-Twabo", 3915313, "kro-wee", } m["glu"] = { "Gula", 5617176, "csu-bgr", "Latn", } m["glw"] = { "Glavda", 3441285, "cdc-cbm", "Latn", } m["gly"] = { "Gule", 3120736, "ssa-kom", } m["gma"] = { "Gambera", 10502327, "aus-wor", "Latn", } m["gmb"] = { "Gula'alaa", 3120733, "poz-sls", "Latn", } m["gmd"] = { "Mághdì", 3914475, "alv-bwj", } m["gmg"] = { "Magiyi", 16926155, "ngf-sog", "Latn", } m["gmh"] = { "Middle High German", 837985, "gmw-hgm", "Latn", strip_diacritics = { remove_diacritics = c.circ .. c.macron, from = {"Ë", "ë", "[ƷȤ]", "[ʒȥ]"}, to = {"E", "e", "Z", "z"} }, } m["gml"] = { "Middle Low German", 505674, "gmw-lgm", "Latn", strip_diacritics = {remove_diacritics = c.circ .. c.macron .. c.diaer}, } m["gmm"] = { "Gbaya-Mbodomo", 6799713, "gba-eas", "Latn", } m["gmn"] = { "Gimnime", 11016905, "alv-dur", "Latn", } m["gmr"] = { "Mirning", 6873793, "aus-pam", "Latn", } m["gmu"] = { "Gumalu", 5618027, "ngf-gum", "Latn", } m["gmv"] = { "Gamo", 16116386, "omv-nom", "Latn, Ethi", } m["gmx"] = { "Magoma", 16939552, "bnt-bki", } m["gmy"] = { "Mycenaean Greek", 668366, "grk", "Linb", translit = "Linb-translit", } m["gmz"] = { "Mgbo", 6826835, "alv-igb", ancestors = "izi", } m["gna"] = { "Kaansa", 56802, "nic-gur", } m["gnb"] = { "Gangte", 12952442, "tbq-kuk", } m["gnc"] = { "Guanche", 35762, "ber", } m["gnd"] = { "Zulgo-Gemzek", 56800, "cdc-cbm", "Latn", } m["gne"] = { "Ganang", 63163361, "nic-plc", ancestors = "izr", } m["gng"] = { "Ngangam", 35888, "nic-grm", } m["gnh"] = { "Lere", 3915319, "nic-jer", } m["gni"] = { "Gooniyandi", 2669219, "aus-bub", "Latn", } m["gnj"] = { "Ngen of Djonkro", 63170838, "dmn-nbe", "Latn", } m["gnk"] = { "ǁGana", 1975199, "khi-kal", "Latn", } m["gnl"] = { "Gangulu", 4916329, "aus-pam", "Latn", } m["gnm"] = { "Ginuman", 11732210, "ngf-dag", "Latn", } m["gnn"] = { "Gumatj", 10510745, "aus-yol", "Latn", } m["gnq"] = { "Gana", 5520523, "poz-san", "Latn", } m["gnr"] = { "Gureng Gureng", 5619998, "aus-pam", "Latn", } m["gnt"] = { "Guntai", 12952475, "paa-ton", "Latn", } m["gnu"] = { "Gnau", 3915810, "paa-trr", "Latn", } m["gnw"] = { "Western Bolivian Guarani", 3775037, "gn", "Latn", } m["gnz"] = { "Ganzi", 11137942, "nic-nkb", "Latn", } m["goa"] = { "Guro", 35251, "dmn-mda", "Latn", } m["gob"] = { "Playero", 3027923, "sai-guh", } m["goc"] = { "Gorakor", 12952463, "poz-ocw", "Latn", } m["god"] = { "Godié", 3914412, "kro-bet", } m["goe"] = { "Gongduk", 2669221, "sit", } m["gof"] = { "Gofa", 12631584, "omv-nom", "Latn, Ethi", } m["gog"] = { "Gogo", 3272630, "bnt-ruv", "Latn", } m["goh"] = { "Old High German", 35218, "gmw-hgm", "Latn, Runr", strip_diacritics = { remove_diacritics = c.circ .. c.macron .. c.diaer, from = {"[ƷȤ]", "[ʒȥ]"}, to = {"Z", "z"} }, translit = { Runr = "Runr-translit", }, } m["goi"] = { "Gobasi", 5575414, "ngf-est", "Latn", } m["goj"] = { "Gowlan", 12953532, "inc-sou", } -- gok is a spurious language, see [[w:Spurious languages]] m["gol"] = { "Gola", 35482, "alv", "Latn, Vaii", } m["gon"] = { "Gondi", 1775361, "dra-gon", "Telu, Gonm, Gong, Deva, Orya", translit = { Telu = "te-translit", Gong = "gon-Gong-translit", Gonm = "gon-Gonm-translit", }, } m["goo"] = { "Gone Dau", 3110470, "poz-pcc", "Latn", } m["gop"] = { "Yeretuar", 8052565, "poz-hce", "Latn", } m["goq"] = { "Gorap", 3110816, "crp", "Latn", ancestors = "ms", } m["gor"] = { "Gorontalo", 2501174, "phi", "Latn", } m["got"] = { "Gothic", 35722, "gme", "Goth, Runr, Latn", translit = {Goth = "Goth-translit"}, link_tr = true, strip_diacritics = {Latn = {remove_diacritics = c.macron}}, } m["gou"] = { "Gavar", 3441180, "cdc-cbm", } m["gov"] = { "Goo", 16927208, "dmn", "Latn", } m["gow"] = { "Gorwaa", 3437626, "cus-sou", "Latn", } m["gox"] = { "Gobu", 7194986, "bad-cnt", } m["goy"] = { "Goundo", 317636, "alv-kim", } m["goz"] = { "Gozarkhani", 5590235, "xme-ttc", ancestors = "xme-ttc-eas", } m["gpa"] = { "Gupa-Abawa", 3915352, "alv-ngb", "Latn", } m["gpn"] = { "Taiap", 56237, "qfa-dis", -- Papuan; isolate in Glottolog; relationship with Torricelli proposed by Usher "Latn", } m["gqa"] = { "Ga'anda", 56245, "cdc-cbm", "Latn", } m["gqi"] = { "Guiqiong", 3120647, "sit-qia", } m["gqn"] = { -- a variety of 'ter' "Kinikinao", 53386731, "awd", "Latn", } m["gqr"] = { "Gor", 759992, "csu-sar", "Latn", } m["gqu"] = { "Qau", 17284874, "gio", } m["gra"] = { "Rajput Garasia", 21041529, "inc-bhi", "Deva, Gujr", ancestors = "bhb", } m["grc"] = { "පුරාතන ග්‍රීක", 35497, "grk", "Polyt, Cprt", translit = { Cprt = "Cprt-translit", }, override_translit = true, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Polyt = "ΑΆἈἉἊἋἌἍἎἏᾈᾉᾊᾋᾌᾍᾎᾏᾸᾹᾺᾼΒΓΔΕΈἘἙἚἛἜἝῈΖΗΉἨἩἪἫἬἭἮἯᾘᾙᾚᾛᾜᾝᾞᾟῊῌΘΙΊΪἸἹἺἻἼἽἾἿῘῙῚΚΛΜΝΞΟΌὈὉὊὋὌὍΠΡῬΡ̓ΣΤΥΎΫὙὛὝὟῨῩῪΦΧΨΩΏὨὩὪὫὬὭὮὯᾨᾩᾪᾫᾬᾭᾮᾯῸῺῼαάἀἁἂἃἄἅἆἇὰᾀᾁᾂᾃᾄᾅᾆᾇᾰᾱᾲᾳᾴᾶᾷβγδεέἐἑἒἓἔἕὲζηήἠἡἢἣἤἥἦἧὴᾐᾑᾒᾓᾔᾕᾖᾗῂῃῄῆῇθιίϊΐἰἱἲἳἴἵἶἷὶῐῑῒῖῗκλμνξοόὀὁὂὃὄὅὸπρῤῥςστυύϋΰὐὑὒὓὔὕὖὗὺῠῡῢῦῧφχψωώὠὡὢὣὤὥὦὧὼᾠᾡᾢᾣᾤᾥᾦᾧῲῳῴῶῷ·ͺ΄΅᾽᾿῀῁῍῎῏῝῞῟῭`´῾", Cprt = "𐠀𐠁𐠂𐠃𐠄𐠅𐠈𐠊𐠋𐠌𐠍𐠎𐠏𐠐𐠑𐠒𐠓𐠔𐠕𐠖𐠗𐠘𐠙𐠚𐠛𐠜𐠝𐠞𐠟𐠠𐠡𐠢𐠣𐠤𐠥𐠦𐠧𐠨𐠩𐠪𐠫𐠬𐠭𐠮𐠯𐠰𐠱𐠲𐠳𐠴𐠵𐠷𐠸𐠼𐠿", c.punc }, } m["grd"] = { "Guruntum", 3441272, "cdc-wst", "Latn", } m["grg"] = { "Madi", 6727664, "ngf-gmo", "Latn", } m["grh"] = { "Gbiri-Niragu", 3913936, "nic-kau", "Latn", } m["gri"] = { "Ghari", 3104782, "poz-sls", "Latn", } m["grj"] = { "Southern Grebo", 3914444, "grb", "Latn", } m["grm"] = { "Kota Marudu Talantang", 6433808, "poz-san", "Latn", } m["gro"] = { "Groma", 56551, "sit-tib", } m["grq"] = { "Gorovu", 56355, "paa-por", "Latn", } m["grs"] = { "Gresi", 5607612, "paa-nim", "Latn", } m["grt"] = { "Garo", 36137, "tbq-bdg", "Latn, Beng, Brai", } m["gru"] = { "Kistane", 13273, "sem-eth", "Latn, Ethi", } m["grv"] = { "Central Grebo", 18385114, "grb", "Latn", } m["grw"] = { "Gweda", 5623387, "poz-ocw", "Latn", } m["grx"] = { "Guriaso", 12631954, "qfa-unc", -- no consensus; may be Kwomtari per Baron (1983) and Usher (2020), but no connections accepted by -- Glottolog. "Latn", } m["gry"] = { "Barclayville Grebo", 11157342, "grb", "Latn", } m["grz"] = { "Guramalum", 3120935, "poz-ocw", "Latn", } m["gse"] = { "Ghanaian Sign Language", 35289, "sgn", "Latn", -- when documented } m["gsg"] = { "German Sign Language", 33282, "sgn-gsl", "Sgnw", } m["gsl"] = { "Gusilay", 35439, "alv-jol", "Latn", } m["gsm"] = { "Guatemalan Sign Language", 2886781, "sgn", "Latn", -- when documented } m["gsn"] = { "Gusan", 11732224, "ngf-era", "Latn", } m["gso"] = { "Southwest Gbaya", 4919322, "gba-sou", "Latn", } m["gsp"] = { "Wasembo", 7971402, "ngf-mad", -- placed in under Rai Coast by Glottolog (under Greater Yaganon) and Pawley-Hammarström "Latn", } m["gss"] = { "Greek Sign Language", 3565084, "sgn", } m["gsw"] = { "Alemannic German", 131339, "gmw-hgm", "Latn", wikimedia_codes = "als", ancestors = "gmh", } m["gta"] = { "Guató", 3027940, "qfa-dis", -- isolate or Macro-Jê "Latn", } m["gtu"] = { "Aghu Tharrnggala", 16825981, "aus-pmn", "Latn", } m["gua"] = { "Shiki", 3913946, "nic-jrn", "Latn", } m["gub"] = { "Guajajára", 7699720, "tup-gua", "Latn", } m["guc"] = { "Wayuu", 891085, "awd-taa", "Latn", } m["gud"] = { "Yocoboué Dida", 21074781, "kro-did", "Latn", } m["gue"] = { "Gurindji", 10511016, "aus-pam", "Latn", } m["guf"] = { "Gupapuyngu", 10511004, "aus-yol", "Latn", } m["gug"] = { "Paraguayan Guarani", 17478066, "gn", "Latn", wikimedia_codes = "gn", ancestors = "gn-cls", } m["guh"] = { "Guahibo", 2669193, "sai-guh", "Latn", } m["gui"] = { "Eastern Bolivian Guarani", 2963912, "gn", "Latn", } m["guk"] = { "Gumuz", 2396970, "ssa", "Latn, Ethi", } m["gul"] = { "Gullah", 33395, "crp", "Latn", ancestors = "en", } m["gum"] = { "Guambiano", 2744745, "sai-bar", "Latn", } m["gun"] = { "Mbya Guarani", 3915584, "gn", "Latn", } m["guo"] = { "Guayabero", 2980375, "sai-guh", "Latn", } m["gup"] = { "Gunwinggu", 1406574, "aus-gun", "Latn", } m["guq"] = { "Aché", 383701, "tup", "Latn", } m["gur"] = { "Farefare", 35331, "nic-mre", "Latn", } m["gus"] = { "Guinean Sign Language", 15983937, "sgn", "Latn", -- when documented } m["gut"] = { "Maléku Jaíka", 3915782, "cba", "Latn", } m["guu"] = { "Yanomamö", 8048928, "sai-ynm", "Latn", } m["guv"] = { "Gey", 11137816, "alv-sav", "Latn", } m["guw"] = { "Gun", 3111668, "alv-gbe", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron}, } m["gux"] = { "Gourmanchéma", 35474, "nic-grm", "Latn", } m["guz"] = { "Gusii", 33603, "bnt-lok", "Latn", } m["gva"] = { "Kaskihá", 3033534, "sai-mas", "Latn", } m["gvc"] = { "Guanano", 3566001, "sai-tuc", "Latn", } m["gve"] = { "Duwet", 5317647, "poz-ocw", "Latn", } m["gvf"] = { "Golin", 3110291, "ngf-sim", "Latn", } m["gvj"] = { "Guajá", 3915506, "tup", "Latn", } m["gvl"] = { "Gulay", 641737, "csu-sar", "Latn", } m["gvm"] = { "Gurmana", 3913363, "nic-shi", "Latn", } m["gvn"] = { "Kuku-Yalanji", 5621973, "aus-pam", "Latn", } m["gvo"] = { "Gavião do Jiparaná", 5528335, "tup", "Latn", } m["gvp"] = { "Pará Gavião", 3365443, "sai-nje", "Latn", } m["gvr"] = { "Gurung", 2392342, "sit-tam", "Gukh, Deva", } m["gvs"] = { "Gumawana", 5618041, "poz-ocw", "Latn", } m["gvy"] = { "Guyani", 10511230, "aus-pam", "Latn", } m["gwa"] = { "Mbato", 3914941, "alv-ptn", "Latn", } m["gwb"] = { "Gwa", 5623219, "nic-jrn", "Latn", } m["gwc"] = { "Kalami", 1675961, "inc-koh", "Arab", strip_diacritics = { ["Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ۂ", "ٱ"}, to = {"ہ", "ہ", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef .. u(0x065e) }, }, } m["gwd"] = { "Gawwada", 3032135, "cus-eas", "Latn, Ethi", } m["gwe"] = { "Gweno", 3358211, "bnt-chg", "Latn", } m["gwf"] = { "Gowro", 3812403, "inc-koh", "Arab", } m["gwg"] = { "Moo", 6907057, "alv-bwj", "Latn", } m["gwi"] = { "Gwich'in", 21057, "ath-nor", "Latn", } m["gwj"] = { "Gcwi", 12631978, "khi-kal", "Latn", } m["gwm"] = { "Awngthim", 4830109, "aus-pmn", "Latn", } m["gwn"] = { "Gwandara", 56521, "cdc-wst", "Latn", } m["gwr"] = { "Gwere", 5623559, "bnt-nyg", "Latn", } m["gwt"] = { "Gawar-Bati", 33894, "inc-kun", "Arab", } m["gwu"] = { "Guwamu", 10511225, "aus-pam", "Latn", } m["gww"] = { "Kwini", 10551249, "aus-wor", "Latn", } m["gwx"] = { "Gua", 35422, "alv-gng", "Latn", } m["gxx"] = { "Wè Southern", 19921582, "kro-wee", "Latn", } m["gya"] = { "Northwest Gbaya", 36594, "gba-wes", "Latn", } m["gyb"] = { "Garus", 5524492, "ngf-han", "Latn", } m["gyd"] = { "Kayardild", 3913770, "aus-tnk", "Latn", } m["gye"] = { "Gyem", 5624046, "nic-jer", "Latn", } m["gyf"] = { "Gungabula", 10510783, "aus-pam", "Latn", } m["gyg"] = { "Gbayi", 11137618, "nic-ngd", "Latn", } m["gyi"] = { "Gyele", 35434, "bnt-mnj", "Latn", } m["gyl"] = { "Gayil", 5528771, "omv-aro", "Latn", } m["gym"] = { "Ngäbere", 3915581, "cba", "Latn", } m["gyn"] = { "Guyanese Creole English", 3305477, "crp", "Latn", ancestors = "en", } m["gyo"] = { "Gyalsumdo", 53575940, "sit-kyk", } m["gyr"] = { "Guarayu", 3118779, "tup-gua", "Latn", } m["gyy"] = { "Gunya", 10511001, "aus-pam", "Latn", } m["gza"] = { "Ganza", 5521556, "omv-mao", "Latn", } m["gzn"] = { "Gane", 3095108, "poz-hce", "Latn", } return require("Module:languages").finalizeData(m, "language") h2apkgyy0gfjqow8du3mo7h91q3f93m 828 6081 231388 221362 2026-02-22T16:43:10Z en>沈澄心 0 Undid revision [[Special:Diff/89666530|89666530]] by [[Special:Contributions/沈澄心|沈澄心]] ([[User talk:沈澄心|talk]]) 221361 Scribunto text/plain local export = {} local function_module = "Module:fun" local load_module = "Module:load" local memoize_module = "Module:memoize" local string_char_module = "Module:string/char" local string_charset_escape_module = "Module:string/charsetEscape" local mw = mw local string = string local table = table local ustring = mw.ustring local byte = string.byte local char = string.char local concat = table.concat local find = string.find local format = string.format local gmatch = string.gmatch local gsub = string.gsub local insert = table.insert local len = string.len local lower = string.lower local match = string.match local next = next local require = require local reverse = string.reverse local select = select local sort = table.sort local sub = string.sub local tonumber = tonumber local tostring = tostring local type = type local ucodepoint = ustring.codepoint local ufind = ustring.find local ugcodepoint = ustring.gcodepoint local ugmatch = ustring.gmatch local ugsub = ustring.gsub local ulower = ustring.lower local umatch = ustring.match local unpack = unpack or table.unpack -- Lua 5.2 compatibility local upper = string.upper local usub = ustring.sub local uupper = ustring.upper local memoize = require(memoize_module) -- Defined below. local codepoint local explode_utf8 local format_fun local get_charset local gsplit local pattern_escape local pattern_simplifier local replacement_escape local title_case local trim local ucfirst local ulen --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls. ]==] local function charset_escape(...) charset_escape = require(string_charset_escape_module) return charset_escape(...) end local function is_callable(...) is_callable = require(function_module).is_callable return is_callable(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function u(...) u = require(string_char_module) return u(...) end local function prepare_iter(str, pattern, str_lib, plain) local callable = is_callable(pattern) if str_lib or plain then return pattern, #str, string, callable elseif not callable then local simple = pattern_simplifier(pattern) if simple then return simple, #str, string, false end end return pattern, ulen(str), ustring, callable end --[==[ Returns {nil} if the input value is the empty string, or otherwise the same value. If the input is a string and `do_trim` is set, the input value will be trimmed before returning; if the trimmed value is the empty string, returns {nil}. If `quote_delimiters` is set, then any outer pair of quotation marks ({' '} or {" "}) surrounding the rest of the input string will be stripped, if present. The string will not be trimmed again, converted to {nil}, or have further quotation marks stripped, as it exists as a way to embed spaces or the empty string in an input. Genuine quotation marks may also be embedded this way (e.g. {"''foo''"} returns {"'foo'"}). ]==] function export.is_not_empty(str, do_trim, quote_delimiters) if str == "" then return nil elseif not (str and type(str) == "string") then return str elseif do_trim then str = trim(str) if str == "" then return nil end end return quote_delimiters and gsub(str, "^(['\"])(.*)%1$", "%2") or str end --[==[ Explodes a string into an array of UTF-8 characters. '''Warning''': this function assumes that the input is valid UTF-8 in order to optimize speed and memory use. Passing in an input containing non-UTF-8 byte sequences could result in unexpected behaviour. ]==] function export.explode_utf8(str) local text, i = {}, 0 for ch in gmatch(str, ".[\128-\191]*") do i = i + 1 text[i] = ch end return text end explode_utf8 = export.explode_utf8 --[==[ Returns {true} if `str` is a valid UTF-8 string. This is true if, for each character, all of the following are true: * It has the expected number of bytes, which is determined by value of the leading byte: 1-byte characters are `0x00` to `0x7F`, 2-byte characters start with `0xC2` to `0xDF`, 3-byte characters start with `0xE0` to `0xEF`, and 4-byte characters start with `0xF0` to `0xF4`. * The leading byte must not fall outside of the above ranges. * The trailing byte(s) (if any), must be between `0x80` to `0xBF`. * The character's codepoint must be between U+0000 (`0x00`) and U+10FFFF (`0xF4 0x8F 0xBF 0xBF`). * The character cannot have an overlong encoding: for each byte length, the lowest theoretical encoding is equivalent to U+0000 (e.g. `0xE0 0x80 0x80`, the lowest theoretical 3-byte encoding, is exactly equivalent to U+0000). Encodings that use more than the minimum number of bytes are not considered valid, meaning that the first valid 3-byte character is `0xE0 0xA0 0x80` (U+0800), and the first valid 4-byte character is `0xF0 0x90 0x80 0x80` (U+10000). Formally, 2-byte characters have leading bytes ranging from `0xC0` to `0xDF` (rather than `0xC2` to `0xDF`), but `0xC0 0x80` to `0xC1 0xBF` are overlong encodings, so it is simpler to say that the 2-byte range begins at `0xC2`. If `allow_surrogates` is set, surrogates (U+D800 to U+DFFF) will be treated as valid UTF-8. Surrogates are used in UTF-16, which encodes codepoints U+0000 to U+FFFF with 2 bytes, and codepoints from U+10000 upwards using a pair of surrogates, which are taken together as a 4-byte unit. Since surrogates have no use in UTF-8, as it encodes higher codepoints in a different way, they are not considered valid in UTF-8 text. However, there are limited circumstances where they may be necessary: for instance, JSON escapes characters using the format `\u0000`, which must contain exactly 4 hexadecimal digits; under the scheme, codepoints above U+FFFF must be escaped as the equivalent pair of surrogates, even though the text itself must be encoded in UTF-8 (e.g. U+10000 becomes `\uD800\uDC00`). ]==] function export.isutf8(str, allow_surrogates) for ch in gmatch(str, "[\128-\255][\128-\191]*") do if #ch > 4 then return false end local b1, b2, b3, b4 = byte(ch, 1, 4) if not (b2 and b2 >= 0x80 and b2 <= 0xBF) then return false -- 1-byte is always invalid, as gmatch excludes 0x00 to 0x7F elseif not b3 then -- 2-byte if not (b1 >= 0xC2 and b1 <= 0xDF) then -- b1 == 0xC0 or b1 == 0xC1 is overlong return false end elseif not (b3 >= 0x80 and b3 <= 0xBF) then -- trailing byte return false elseif not b4 then -- 3-byte if b1 > 0xEF then return false elseif b2 < 0xA0 then if b1 < 0xE1 then -- b1 == 0xE0 and b2 < 0xA0 is overlong return false end elseif b1 < 0xE0 or (b1 == 0xED and not allow_surrogates) then -- b1 == 0xED and b2 >= 0xA0 is a surrogate return false end elseif not (b4 >= 0x80 and b4 <= 0xBF) then -- 4-byte return false elseif b2 < 0x90 then if not (b1 >= 0xF1 and b1 <= 0xF4) then -- b1 == 0xF0 and b2 < 0x90 is overlong return false end elseif not (b1 >= 0xF0 and b1 <= 0xF3) then -- b1 == 0xF4 and b2 >= 0x90 is too high return false end end return true end do local charset_chars = { ["\0"] = "%z", ["%"] = "%%", ["-"] = "%-", ["]"] = "%]", ["^"] = "%^" } charset_chars.__index = charset_chars local chars = setmetatable({ ["$"] = "%$", ["("] = "%(", [")"] = "%)", ["*"] = "%*", ["+"] = "%+", ["."] = "%.", ["?"] = "%?", ["["] = "%[" }, charset_chars) --[==[ Escapes the magic characters used in a [[mw:Extension:Scribunto/Lua reference manual#Patterns|pattern]] (Lua's version of regular expressions): {$%()*+-.?[]^}, and converts the null character to {%z}. For example, {"^$()%.[]*+-?\0"} becomes {"%^%$%(%)%%%.%[%]%*%+%-%?%z"}. This is necessary when constructing a pattern involving arbitrary text (e.g. from user input). ]==] function export.pattern_escape(str) return (gsub(str, "[%z$%%()*+%-.?[%]^]", chars)) end pattern_escape = export.pattern_escape --[==[ Escapes only {%}, which is the only magic character used in replacement [[mw:Extension:Scribunto/Lua reference manual#Patterns|patterns]] with string.gsub and mw.ustring.gsub. ]==] function export.replacement_escape(str) return (gsub(str, "%%", "%%%%")) end replacement_escape = export.replacement_escape local function case_insensitive_char(ch) local upper_ch = uupper(ch) if upper_ch == ch then ch = ulower(ch) if ch == upper_ch then return chars[ch] or ch end end return "[" .. (charset_chars[upper_ch] or upper_ch) .. (charset_chars[ch] or ch) .. "]" end local function iterate(str, str_len, text, n, start, _gsub, _sub, loc1, loc2) if not (loc1 and start <= str_len) then -- Add final chunk and return. n = n + 1 text[n] = _gsub(_sub(str, start), ".", chars) return elseif loc2 < loc1 then if _sub == sub then local b = byte(str, loc1) if b and b >= 128 then loc1 = loc1 + (b < 224 and 1 or b < 240 and 2 or 3) end end n = n + 1 text[n] = _gsub(_sub(str, start, loc1), ".", chars) start = loc1 + 1 if start > str_len then return end else -- Add chunk up to the current match. n = n + 1 text[n] = _gsub(_sub(str, start, loc1 - 1), ".", chars) -- Add current match. n = n + 1 text[n] = _gsub(_sub(str, loc1, loc2), ".", case_insensitive_char) start = loc2 + 1 end return n, start end --[==[ Escapes the magic characters used in a [[mw:Extension:Scribunto/Lua reference manual#Patterns|pattern]], and makes all characters case-insensitive. An optional pattern or find function (see {split}) may be supplied as the second argument, the third argument (`str_lib`) forces use of the string library, while the fourth argument (`plain`) turns any pattern matching facilities off in the optional pattern supplied. ]==] function export.case_insensitive_pattern(str, pattern_or_func, str_lib, plain) if pattern_or_func == nil then return (gsub(str, str_lib and "[^\128-\255]" or ".[\128-\191]*", case_insensitive_char)) end local text, n, start, str_len, _string, callable = {}, 0, 1 pattern_or_func, str_len, _string, callable = prepare_iter(str, pattern_or_func, str_lib, plain) local _find, _gsub, _sub = _string.find, _string.gsub, _string.sub if callable then repeat n, start = iterate(str, str_len, text, n, start, _gsub, _sub, pattern_or_func(str, start)) until not start -- Special case if the pattern is anchored to the start: "^" always -- anchors to the start position, not the start of the string, so get -- around this by only attempting one match with the pattern, then match -- the end of the string. elseif byte(pattern_or_func) == 0x5E then -- ^ n, start = iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, pattern_or_func, start, plain)) if start ~= nil then iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, "$", start, plain)) end else repeat n, start = iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, pattern_or_func, start, plain)) until not start end return concat(text) end end do local character_classes local function get_character_classes() character_classes, get_character_classes = { [0x41] = true, [0x61] = true, -- Aa [0x43] = true, [0x63] = true, -- Cc [0x44] = true, [0x64] = true, -- Dd [0x4C] = true, [0x6C] = true, -- Ll [0x50] = true, [0x70] = true, -- Pp [0x53] = true, [0x73] = true, -- Ss [0x55] = true, [0x75] = true, -- Uu [0x57] = true, [0x77] = true, -- Ww [0x58] = true, [0x78] = true, -- Xx [0x5A] = true, -- z dealt with separately. }, nil return character_classes end local function check_sets_equal(set1, set2) local k2 for k1, v1 in next, set1 do local v2 = set2[k1] if v1 ~= v2 and (v2 == nil or not check_sets_equal(v1, v2)) then return false end k2 = next(set2, k2) end return next(set2, k2) == nil end local function check_sets(bytes) local key, set1, set = next(bytes) if set1 == true then return true elseif not check_sets(set1) then return false end while true do key, set = next(bytes, key) if not key then return true elseif not check_sets_equal(set, set1) then return false end end end local function make_charset(range) if #range == 1 then return char(range[1]) end sort(range) local compressed, n, start = {}, 0, range[1] for i = 1, #range do local this, nxt = range[i], range[i + 1] if nxt ~= this + 1 then n = n + 1 compressed[n] = this == start and char(this) or char(start) .. "-" .. char(this) start = nxt end end return "[" .. concat(compressed) .. "]" end local function parse_1_byte_charset(pattern, pos) local ch while true do pos, ch = match(pattern, "()([%%%]\192-\255])", pos) if ch == "%" then local nxt = byte(pattern, pos + 1) if not nxt or nxt >= 128 or (character_classes or get_character_classes())[nxt] then -- acdlpsuwxACDLPSUWXZ, but not z return false end pos = pos + 2 elseif ch == "]" then pos = pos + 1 return pos else return false end end end --[==[ Parses `pattern`, a ustring library pattern, and attempts to convert it into a string library pattern. If conversion isn't possible, returns false. ]==] function pattern_simplifier(pattern) if type(pattern) == "number" then return tostring(pattern) end local pos, capture_groups, start, n, output, ch, nxt_pos = 1, 0, 1, 0 while true do -- FIXME: use "()([%%(.[\128-\255])[\128-\191]?[\128-\191]?[\128-\191]?()" and ensure non-UTF8 always fails. pos, ch, nxt_pos = match(pattern, "()([%%(.[\192-\255])[\128-\191]*()", pos) if not ch then break end local nxt = byte(pattern, nxt_pos) if ch == "%" then if nxt == 0x62 then -- b local nxt2, nxt3 = byte(pattern, pos + 2, pos + 3) if not (nxt2 and nxt2 < 128 and nxt3 and nxt3 < 128) then return false end pos = pos + 4 elseif nxt == 0x66 then -- f nxt_pos = nxt_pos + 2 local nxt2, nxt3 = byte(pattern, nxt_pos - 1, nxt_pos) -- Only possible to convert a positive %f charset which is -- all ASCII, so use parse_1_byte_charset. if not (nxt2 == 0x5B and nxt3 and nxt3 ~= 0x5E and nxt3 < 128) then -- [^ return false elseif nxt3 == 0x5D then -- Initial ] is non-magic. nxt_pos = nxt_pos + 1 end pos = parse_1_byte_charset(pattern, nxt_pos) if not pos then return false end elseif nxt == 0x5A then -- Z nxt = byte(pattern, nxt_pos + 1) if nxt == 0x2A or nxt == 0x2D then -- *- pos = pos + 3 else if output == nil then output = {} end local ins = sub(pattern, start, pos - 1) .. "[\1-\127\192-\255]" n = n + 1 if nxt == 0x2B then -- + output[n] = ins .. "%Z*" pos = pos + 3 elseif nxt == 0x3F then -- ? output[n] = ins .. "?[\128-\191]*" pos = pos + 3 else output[n] = ins .. "[\128-\191]*" pos = pos + 2 end start = pos end elseif not nxt or (character_classes or get_character_classes())[nxt] then -- acdlpsuwxACDLPSUWX, but not Zz return false -- Skip the next character if it's ASCII. Otherwise, we will -- still need to do length checks. else pos = pos + (nxt < 128 and 2 or 1) end elseif ch == "(" then if nxt == 0x29 or capture_groups == 32 then -- ) return false end capture_groups = capture_groups + 1 pos = pos + 1 elseif ch == "." then if nxt == 0x2A or nxt == 0x2D then -- *- pos = pos + 2 else if output == nil then output = {} end local ins = sub(pattern, start, pos - 1) .. "[^\128-\191]" n = n + 1 if nxt == 0x2B then -- + output[n] = ins .. ".*" pos = pos + 2 elseif nxt == 0x3F then -- ? output[n] = ins .. "?[\128-\191]*" pos = pos + 2 else output[n] = ins .. "[\128-\191]*" pos = pos + 1 end start = pos end elseif ch == "[" then -- Fail negative charsets. TODO: 1-byte charsets should be safe. if nxt == 0x5E then -- ^ return false -- If the first character is "%", ch_len is determined by the -- next one instead. elseif nxt == 0x25 then -- % nxt = byte(pattern, nxt_pos + 1) elseif nxt == 0x5D then -- Initial ] is non-magic. nxt_pos = nxt_pos + 1 end if not nxt then return false end local ch_len = nxt < 128 and 1 or nxt < 224 and 2 or nxt < 240 and 3 or 4 if ch_len == 1 then -- Single-byte charset. pos = parse_1_byte_charset(pattern, nxt_pos) if not pos then return false end else -- Multibyte charset. -- TODO: 1-byte chars should be safe to mix with multibyte chars. CONFIRM THIS FIRST. local charset_pos, bytes = pos pos = pos + 1 while true do -- TODO: non-ASCII charset ranges. pos, ch, nxt_pos = match(pattern, "^()([^\128-\191])[\128-\191]*()", pos) -- If escaped, get the next character. No need to -- distinguish magic characters or character classes, -- as they'll all fail for having the wrong length -- anyway. if ch == "%" then pos, ch, nxt_pos = match(pattern, "^()([^\128-\191])[\128-\191]*()", nxt_pos) elseif ch == "]" then pos = nxt_pos break end if not (ch and nxt_pos - pos == ch_len) then return false elseif bytes == nil then bytes = {} end local bytes, last = bytes, nxt_pos - 1 for i = pos, last - 1 do local b = byte(pattern, i) local bytes_b = bytes[b] if bytes_b == nil then bytes_b = {} bytes[b] = bytes_b end bytes[b], bytes = bytes_b, bytes_b end bytes[byte(pattern, last)] = true pos = nxt_pos end if not pos then return false end nxt = byte(pattern, pos) if ( (nxt == 0x2A or nxt == 0x2D or nxt == 0x3F) or -- *-? (nxt == 0x2B and ch_len > 2) or -- + not check_sets(bytes) ) then return false end local ranges, b, key, next_byte = {}, 0 repeat key, next_byte = next(bytes) local range, n = {key}, 1 -- Loop starts on the second iteration. for key in next, bytes, key do n = n + 1 range[n] = key end b = b + 1 ranges[b] = range bytes = next_byte until next_byte == true if nxt == 0x2B then -- + local range1, range2 = ranges[1], ranges[2] ranges[1], ranges[3] = make_charset(range1), make_charset(range2) local n = #range2 for i = 1, #range1 do n = n + 1 range2[n] = range1[i] end ranges[2] = make_charset(range2) .. "*" pos = pos + 1 else for i = 1, #ranges do ranges[i] = make_charset(ranges[i]) end end if output == nil then output = {} end nxt = byte(pattern, pos) n = n + 1 output[n] = sub(pattern, start, charset_pos - 1) .. concat(ranges) .. ((nxt == 0x2A or nxt == 0x2B or nxt == 0x2D or nxt == 0x3F) and "%" or "") -- following *+-? now have to be escaped start = pos end elseif not nxt then break elseif nxt == 0x2B then -- + if nxt_pos - pos ~= 2 then return false elseif output == nil then output = {} end pos, nxt_pos = pos + 1, nxt_pos + 1 nxt = byte(pattern, nxt_pos) local ch2 = sub(pattern, pos, pos) n = n + 1 output[n] = sub(pattern, start, pos - 1) .. "[" .. ch .. ch2 .. "]*" .. ch2 .. ((nxt == 0x2A or nxt == 0x2B or nxt == 0x2D or nxt == 0x3F) and "%" or "") -- following *+-? now have to be escaped pos, start = nxt_pos, nxt_pos elseif nxt == 0x2A or nxt == 0x2D or nxt == 0x3F then -- *-? return false else pos = nxt_pos end end if start == 1 then return pattern end return concat(output) .. sub(pattern, start) end pattern_simplifier = memoize(pattern_simplifier, true) export.pattern_simplifier = pattern_simplifier end --[==[ Parses `charset`, the interior of a string or ustring library character set, and normalizes it into a string or ustring library pattern (e.g. {"abcd-g"} becomes {"[abcd-g]"}, and {"[]"} becomes {"[[%]]"}). The negative (`^`), range (`-`) and literal (`%`) magic characters work as normal, and character classes may be used (e.g. `%d` and `%w`), but opening and closing square brackets are sanitized so that they behave like ordinary characters. ]==] function get_charset(charset) if type(charset) == "number" then return tostring(charset) end local pos, start, n, output = 1, 1, 0 if byte(charset) == 0x5E then -- ^ pos = pos + 1 end -- FIXME: "]" is non-magic if it's the first character in a charset. local nxt_pos, nxt while true do local new_pos, ch = match(charset, "()([%%%-%]])", pos) if not ch then break -- Skip percent escapes. Ranges can't start with them, either. elseif ch == "%" then pos = new_pos + 2 else -- If `ch` is a hyphen, get the character before iff it's at or ahead of `pos`. if ch == "-" and new_pos > pos then pos, nxt_pos, nxt = new_pos - 1, new_pos, ch ch = sub(charset, pos, pos) else pos, nxt_pos = new_pos, new_pos + 1 nxt = sub(charset, nxt_pos, nxt_pos) end -- Range. if nxt == "-" then if output == nil then output = {} end n = n + 1 output[n] = sub(charset, start, pos - 1) nxt_pos = nxt_pos + 1 nxt = sub(charset, nxt_pos, nxt_pos) -- Ranges fail if they end with a percent escape, so escape the hyphen to avoid undefined behaviour. if nxt == "" or nxt == "%" then n = n + 1 output[n] = (ch == "]" and "%]" or ch) .. "%-" start = nxt_pos nxt_pos = nxt_pos + 2 -- Since ranges can't contain "%]", since it's escaped, range inputs like "]-z" or "a-]" must be -- adjusted to the character before or after, plus "%]" (e.g. "%]^-z" or "a-\\%]"). The escaped "%]" is -- omitted if the range would be empty (i.e. if the first byte is greater than the second). else n = n + 1 output[n] = (ch == "]" and (byte(nxt) >= 0x5D and "%]^" or "^") or ch) .. "-" .. (nxt == "]" and (byte(ch) <= 0x5D and "\\%]" or "\\") or nxt) nxt_pos = nxt_pos + 1 start = nxt_pos end elseif ch == "-" or ch == "]" then if output == nil then output = {} end n = n + 1 output[n] = sub(charset, start, pos - 1) .. "%" .. ch start = nxt_pos end pos = nxt_pos end end if start == 1 then return "[" .. charset .. "]" end return "[" .. concat(output) .. sub(charset, start) .. "]" end get_charset = memoize(get_charset, true) export.get_charset = get_charset function export.len(str) return type(str) == "number" and len(str) or #str - #gsub(str, "[^\128-\191]+", "") end ulen = export.len function export.sub(str, i, j) str, i = type(str) == "number" and tostring(str) or str, i or 1 if i < 0 or j and j < 0 then return usub(str, i, j) elseif j and i > j or i > #str then return "" end local n, new_i = 0 for loc1, loc2 in gmatch(str, "()[^\128-\191]+()[\128-\191]*") do n = n + loc2 - loc1 if not new_i and n >= i then new_i = loc2 - (n - i) - 1 if not j then return sub(str, new_i) end end if j and n > j then return sub(str, new_i, loc2 - (n - j) - 1) end end return new_i and sub(str, new_i) or "" end do local function _find(str, loc1, loc2, ...) if loc1 and not match(str, "^()[^\128-\255]*$") then -- Use raw values of loc1 and loc2 to get loc1 and the length of the match. loc1, loc2 = ulen(sub(str, 1, loc1)), ulen(sub(str, loc1, loc2)) -- Offset length with loc1 to get loc2. loc2 = loc1 + loc2 - 1 end return loc1, loc2, ... end --[==[A version of find which uses string.find when possible, but otherwise uses mw.ustring.find.]==] function export.find(str, pattern, init, plain) init = init or 1 if init ~= 1 and not match(str, "^()[^\128-\255]*$") then return ufind(str, pattern, init, plain) elseif plain then return _find(str, find(str, pattern, init, true)) end local simple = pattern_simplifier(pattern) if simple then return _find(str, find(str, simple, init)) end return ufind(str, pattern, init) end end --[==[A version of match which uses string.match when possible, but otherwise uses mw.ustring.match.]==] function export.match(str, pattern, init) init = init or 1 if init ~= 1 and not match(str, "^()[^\128-\255]*$") then return umatch(str, pattern, init) end local simple = pattern_simplifier(pattern) if simple then return match(str, simple, init) end return umatch(str, pattern, init) end --[==[A version of gmatch which uses string.gmatch when possible, but otherwise uses mw.ustring.gmatch.]==] function export.gmatch(str, pattern) local simple = pattern_simplifier(pattern) if simple then return gmatch(str, simple) end return ugmatch(str, pattern) end --[==[A version of gsub which uses string.gsub when possible, but otherwise uses mw.ustring.gsub.]==] function export.gsub(str, pattern, repl, n) local simple = pattern_simplifier(pattern) if simple then return gsub(str, simple, repl, n) end return ugsub(str, pattern, repl, n) end --[==[ Like gsub, but pattern-matching facilities are turned off, so `pattern` and `repl` (if a string) are treated as literal. ]==] function export.plain_gsub(str, pattern, repl, n) return gsub(str, pattern_escape(pattern), type(repl) == "string" and replacement_escape(repl) or repl, n) end --[==[ Reverses a UTF-8 string; equivalent to string.reverse. ]==] function export.reverse(str) return reverse((gsub(str, "[\192-\255][\128-\191]*", reverse))) end function export.char(...) -- To be moved to [[Module:string/char]]. return u(...) end do local function utf8_err(func_name) error(format("bad argument #1 to '%s' (string is not UTF-8)", func_name), 4) end local function get_codepoint(func_name, b1, b2, b3, b4) if b1 <= 0x7F then return b1, 1 elseif not (b2 and b2 >= 0x80 and b2 <= 0xBF) then utf8_err(func_name) elseif b1 <= 0xDF then local cp = 0x40 * b1 + b2 - 0x3080 return cp >= 0x80 and cp or utf8_err(func_name), 2 elseif not (b3 and b3 >= 0x80 and b3 <= 0xBF) then utf8_err(func_name) elseif b1 <= 0xEF then local cp = 0x1000 * b1 + 0x40 * b2 + b3 - 0xE2080 return cp >= 0x800 and cp or utf8_err(func_name), 3 elseif not (b4 and b4 >= 0x80 and b4 <= 0xBF) then utf8_err(func_name) end local cp = 0x40000 * b1 + 0x1000 * b2 + 0x40 * b3 + b4 - 0x3C82080 return cp >= 0x10000 and cp <= 0x10FFFF and cp or utf8_err(func_name), 4 end function export.codepoint(str, i, j) if str == "" then return -- return nothing elseif type(str) == "number" then return byte(str, i, j) end i, j = i or 1, j == -1 and #str or i or 1 if i == 1 and j == 1 then return (get_codepoint("codepoint", byte(str, 1, 4))) elseif i < 0 or j < 0 then return ucodepoint(str, i, j) -- FIXME end local n, nb, ret, nr = 0, 1, {}, 0 while n < j do n = n + 1 if n < i then local b = byte(str, nb) nb = nb + (b < 128 and 1 or b < 224 and 2 or b < 240 and 3 or 4) else local b1, b2, b3, b4 = byte(str, nb, nb + 3) if not b1 then break end nr = nr + 1 local add ret[nr], add = get_codepoint("codepoint", b1, b2, b3, b4) nb = nb + add end end return unpack(ret) end codepoint = export.codepoint function export.gcodepoint(str, i, j) i, j = i or 1, j ~= -1 and j or nil if i < 0 or j and j < 0 then return ugcodepoint(str, i, j) -- FIXME end local n, nb = 1, 1 while n < i do local b = byte(str, nb) if not b then break end nb = nb + (b < 128 and 1 or b < 224 and 2 or b < 240 and 3 or 4) n = n + 1 end return function() if j and n > j then return nil end n = n + 1 local b1, b2, b3, b4 = byte(str, nb, nb + 3) if not b1 then return nil end local ret, add = get_codepoint("gcodepoint", b1, b2, b3, b4) nb = nb + add return ret end end end do local _ulower = ulower --[==[A version of lower which uses string.lower when possible, but otherwise uses mw.ustring.lower.]==] function export.lower(str) return (match(str, "^()[^\128-\255]*$") and lower or _ulower)(str) end end do local _uupper = uupper --[==[A version of upper which uses string.upper when possible, but otherwise uses mw.ustring.upper.]==] function export.upper(str) return (match(str, "^()[^\128-\255]*$") and upper or _uupper)(str) end end do local function add_captures(t, n, ...) if ... == nil then return end -- Insert any captures from the splitting pattern. local offset, capture = n - 1, ... while capture do n = n + 1 t[n] = capture capture = select(n - offset, ...) end return n end --[==[ Reimplementation of mw.text.split() that includes any capturing groups in the splitting pattern. This works like Python's re.split() function, except that it has Lua's behavior when the split pattern is empty (i.e. advancing by one character at a time; Python returns the whole remainder of the string). When possible, it will use the string library, but otherwise uses the ustring library. There are two optional parameters: `str_lib` forces use of the string library, while `plain` turns any pattern matching facilities off, treating `pattern` as literal. In addition, `pattern` may be a custom find function (or callable table), which takes the input string and start index as its two arguments, and must return the start and end index of the match, plus any optional captures, or nil if there are no further matches. By default, the start index will be calculated using the ustring library, unless `str_lib` or `plain` is set. ]==] function export.split(str, pattern_or_func, str_lib, plain) local iter, t, n = gsplit(str, pattern_or_func, str_lib, plain), {}, 0 repeat n = add_captures(t, n, iter()) until n == nil return t end export.capturing_split = export.split -- To be removed. end --[==[ Returns an iterator function, which iterates over the substrings returned by {split}. The first value returned is the string up the splitting pattern, with any capture groups being returned as additional values on that iteration. ]==] function export.gsplit(str, pattern_or_func, str_lib, plain) local start, final, str_len, _string, callable = 1 pattern_or_func, str_len, _string, callable = prepare_iter(str, pattern_or_func, str_lib, plain) local _find, _sub = _string.find, _string.sub local function iter(loc1, loc2, ...) -- If no match, or there is but we're past the end of the string -- (which happens when the match is the empty string), then return -- the final chunk. if not loc1 then final = true return _sub(str, start) end -- Special case: If we match the empty string, then eat the -- next character; this avoids an infinite loop, and makes -- splitting by the empty string work the way mw.text.gsplit() does -- (including non-adjacent empty string matches with %f). If we -- reach the end of the string this way, set `final` to true, so we -- don't get stuck matching the empty string at the end. local chunk if loc2 < loc1 then -- If using the string library, we need to make sure we advance -- by one UTF-8 character. if _sub == sub then local b = byte(str, loc1) if b and b >= 128 then loc1 = loc1 + (b < 224 and 1 or b < 240 and 2 or 3) end end chunk = _sub(str, start, loc1) if loc1 >= str_len then final = true else start = loc1 + 1 end -- Eat chunk up to the current match. else chunk = _sub(str, start, loc1 - 1) start = loc2 + 1 end return chunk, ... end if callable then return function() if not final then return iter(pattern_or_func(str, start)) end end -- Special case if the pattern is anchored to the start: "^" always -- anchors to the start position, not the start of the string, so get -- around this by only attempting one match with the pattern, then match -- the end of the string. elseif byte(pattern_or_func) == 0x5E then -- ^ local returned return function() if not returned then returned = true return iter(_find(str, pattern_or_func, start, plain)) elseif not final then return iter(_find(str, "$", start, plain)) end end end return function() if not final then return iter(_find(str, pattern_or_func, start, plain)) end end end gsplit = export.gsplit function export.count(str, pattern, plain) if plain then return select(2, gsub(str, pattern_escape(pattern), "")) end local simple = pattern_simplifier(pattern) if simple then return select(2, gsub(str, pattern, "")) end return select(2, ugsub(str, pattern, "")) end function export.trim(str, charset, str_lib, plain) if charset == nil then -- "^.*%S" is the fastest trim algorithm except when strings only consist of characters to be trimmed, which are -- very slow due to catastrophic backtracking. gsub with "^%s*" gets around this by trimming such strings to "" -- first. return match(gsub(str, "^%s*", ""), "^.*%S") or "" elseif charset == "" then return str end charset = plain and ("[" .. charset_escape(charset) .. "]") or get_charset(charset) -- The pattern uses a non-greedy quantifier instead of the algorithm used for %s, because negative character sets -- are non-trivial to compute (e.g. "[^^-z]" becomes "[%^_-z]"). Plus, if the ustring library has to be used, there -- would be two callbacks into PHP, which is slower. local pattern = "^" .. charset .. "*(.-)" .. charset .. "*$" if not str_lib then local simple = pattern_simplifier(pattern) if not simple then return umatch(str, pattern) end pattern = simple end return match(str, pattern) end trim = export.trim do local entities local function get_entities() entities, get_entities = load_data("Module:data/entities"), nil return entities end local function decode_entity(hash, x, code) if hash == "" then return (entities or get_entities())[x .. code] end local cp if x == "" then cp = match(code, "^()%d+$") and tonumber(code) else cp = match(code, "^()%x+$") and tonumber(code, 16) end return cp and (cp <= 0xD7FF or cp >= 0xE000 and cp <= 0x10FFFF) and u(cp) or nil end -- Non-ASCII characters aren't valid in proper HTML named entities, but MediaWiki uses them in some custom aliases -- which have also been included in [[Module:data/entities]]. function export.decode_entities(str) local amp = find(str, "&", nil, true) return amp and find(str, ";", amp, true) and gsub(str, "&(#?)([xX]?)([%w\128-\255]+);", decode_entity) or str end end do local entities local function get_entities() -- Memoized HTML entities (taken from mw.text.lua). entities, get_entities = { ["\""] = "&quot;", ["&"] = "&amp;", ["'"] = "&#039;", ["<"] = "&lt;", [">"] = "&gt;", ["\194\160"] = "&nbsp;", }, nil return entities end local function encode_entity(ch) local entity = (entities or get_entities())[ch] if entity == nil then local cp = codepoint(ch) -- U+D800 to U+DFFF are surrogates, so can't be encoded as entities. entity = cp and (cp <= 0xD7FF or cp >= 0xE000) and format("&#%d;", cp) or false entities[ch] = entity end return entity or nil end function export.encode_entities(str, charset, str_lib, plain) if charset == nil then return (gsub(str, "[\"&'<>\194]\160?", entities or get_entities())) elseif charset == "" then return str end local pattern = plain and ("[" .. charset_escape(charset) .. "]") or charset == "." and charset or get_charset(charset) if not str_lib then local simple = pattern_simplifier(pattern) if not simple then return (ugsub(str, pattern, encode_entity)) end pattern = simple end return (gsub(str, pattern, encode_entity)) end end do local function decode_path(code) return char(tonumber(code, 16)) end local function decode(lead, trail) if lead == "+" or lead == "_" then return " " .. trail elseif #trail == 2 then return decode_path(trail) end return lead .. trail end function export.decode_uri(str, enctype) enctype = enctype and upper(enctype) or "QUERY" if enctype == "PATH" then return find(str, "%", nil, true) and gsub(str, "%%(%x%x)", decode_path) or str elseif enctype == "QUERY" then return (find(str, "%", nil, true) or find(str, "+", nil, true)) and gsub(str, "([%%%+])(%x?%x?)", decode) or str elseif enctype == "WIKI" then return (find(str, "%", nil, true) or find(str, "_", nil, true)) and gsub(str, "([%%_])(%x?%x?)", decode) or str end error("bad argument #2 to 'decode_uri' (expected QUERY, PATH, or WIKI)", 2) end end do local function _remove_comments(str, pre) local head = find(str, "<!--", nil, true) if not head then return str end local ret, n = {sub(str, 1, head - 1)}, 1 while true do local loc = find(str, "-->", head + 4, true) if not loc then return pre and concat(ret) or concat(ret) .. sub(str, head) end head = loc + 3 loc = find(str, "<!--", head, true) if not loc then return concat(ret) .. sub(str, head) end n = n + 1 ret[n] = sub(str, head, loc - 1) head = loc end end --[==[ Removes any HTML comments from the input text. `stage` can be one of three options: * {"PRE"} (default) applies the method used by MediaWiki's preprocessor: all {{code|html|<nowiki><!-- ... --></nowiki>}} pairs are removed, as well as any text after an unclosed {{code|html|<nowiki><!--</nowiki>}}. This is generally suitable when parsing raw template or [[mw:Parser extension tags|parser extension tag]] code. (Note, however, that the actual method used by the preprocessor is considerably more complex and differs under certain conditions (e.g. comments inside nowiki tags); if full accuracy is absolutely necessary, use [[Module:template parser]] instead). * {"POST"} applies the method used to generate the final page output once all templates have been expanded: it loops over the text, removing any {{code|html|<nowiki><!-- ... --></nowiki>}} pairs until no more are found (e.g. {{code|html|<nowiki><!-<!-- ... -->- ... --></nowiki>}} would be fully removed), but any unclosed {{code|html|<nowiki><!--</nowiki>}} is ignored. This is suitable for handling links embedded in template inputs, where the {"PRE"} method will have already been applied by the native parser. * {"BOTH"} applies {"PRE"} then {"POST"}. ]==] function export.remove_comments(str, stage) if not stage or stage == "PRE" then return _remove_comments(str, true) end local processed = stage == "POST" and _remove_comments(str) or stage == "BOTH" and _remove_comments(str, true) or error("bad argument #2 to 'remove_comments' (expected PRE, POST, or BOTH)", 2) while processed ~= str do str = processed processed = _remove_comments(str) end return str end end do local byte_escapes local function get_byte_escapes() byte_escapes, get_byte_escapes = load_data("Module:string utilities/data").byte_escapes, nil return byte_escapes end local function escape_byte(b) return (byte_escapes or get_byte_escapes())[b] or format("\\%03d", byte(b)) end function export.escape_bytes(str) return (gsub(str, ".", escape_byte)) end end function export.format_fun(str, fun) return (gsub(str, "{(\\?)((\\?)[^{}]*)}", function(p1, name, p2) if #p1 + #p2 == 1 then return name == "op" and "{" or name == "cl" and "}" or error(mw.getCurrentFrame():getTitle() .. " format: unrecognized escape sequence '{\\" .. name .. "}'") elseif fun(name) and type(fun(name)) ~= "string" then error(mw.getCurrentFrame():getTitle() .. " format: \"" .. name .. "\" is a " .. type(fun(name)) .. ", not a string") end return fun(name) or error(mw.getCurrentFrame():getTitle() .. " format: \"" .. name .. "\" not found in table") end)) end format_fun = export.format_fun --[==[ This function, unlike {string.format} and {mw.ustring.format}, takes just two parameters, a format string and a table, and replaces all instances of { {param_name} } in the format string with the table's entry for {param_name}. The opening and closing brace characters can be escaped with { {\op} } and { {\cl} }, respectively. A table entry beginning with a slash can be escaped by doubling the initial slash. ====Examples==== * {string_utilities.format("{foo} fish, {bar} fish, {baz} fish, {quux} fish", {["foo"]="one", ["bar"]="two", ["baz"]="red", ["quux"]="blue"}) } *: produces: {"one fish, two fish, red fish, blue fish"} * {string_utilities.format("The set {\\op}1, 2, 3{\\cl} contains {\\\\hello} elements.", {["\\hello"]="three"})} *: produces: {"The set {1, 2, 3} contains three elements."} *:* Note that the single and double backslashes should be entered as double and quadruple backslashes when quoted in a literal string. ]==] function export.format(str, tbl) return format_fun(str, function(key) return tbl[key] end) end do local function do_uclcfirst(str, case_func) -- Re-case the first letter. local first, remainder = match(str, "^(.[\128-\191]*)(.*)") return first and (case_func(first) .. remainder) or "" end local function uclcfirst(str, case_func) -- Strip off any HTML tags at the beginning. This currently does not handle comments or <ref>...</ref> -- correctly; it's intended for text wrapped in <span> or the like, as happens when passing text through -- [[Module:links]]. local html_at_beginning = nil if str:match("^<") then while true do local html_tag, rest = str:match("^(<.->)(.*)$") if not html_tag then break end if not html_at_beginning then html_at_beginning = {} end insert(html_at_beginning, html_tag) str = rest end end -- If there's a link at the beginning, re-case the first letter of the -- link text. This pattern matches both piped and unpiped links. -- If the link is not piped, the second capture (linktext) will be empty. local link, linktext, remainder = match(str, "^%[%[([^|%]]+)%|?(.-)%]%](.*)$") local retval if link then retval = "[[" .. link .. "|" .. do_uclcfirst(linktext ~= "" and linktext or link, case_func) .. "]]" .. remainder else retval = do_uclcfirst(str, case_func) end if html_at_beginning then retval = concat(html_at_beginning) .. retval end return retval end --[==[ Uppercase the first character of the input string, correctly handling one-part and two-part links, optionally surrounded by HTML tags such as `<nowiki><span>...</span></nowiki>`, possibly nested. Intended to correctly uppercase the first character of text that may include links that have been passed through `full_link()` in [[Module:links]] or a similar function. ]==] function export.ucfirst(str) return uclcfirst(str, uupper) end ucfirst = export.ucfirst --[==[ Lowercase the first character of the input string, correctly handling one-part and two-part links, optionally surrounded by HTML tags such as `<nowiki><span>...</span></nowiki>`, possibly nested. Intended to correctly lowercase the first character of text that may include links that have been passed through `full_link()` in [[Module:links]] or a similar function. ]==] function export.lcfirst(str) return uclcfirst(str, ulower) end --[==[Capitalizes each word of the input string. WARNING: May be broken in the presence of multiword links.]==] function export.capitalize(str) -- Capitalize multi-word that is separated by spaces -- by uppercasing the first letter of each part. return (ugsub(str, "%w+", ucfirst)) end local function do_title_case(first, remainder) first = uupper(first) return remainder == "" and first or (first .. ulower(remainder)) end --[==[ Capitalizes each word of the input string, with any further letters in each word being converted to lowercase. ]==] function export.title_case(str) return str == "" and "" or ugsub(str, "(%w)(%w*)", do_title_case) end title_case = export.title_case --[==[ Converts the input string to {{w|Camel case|CamelCase}}. Any non-word characters are treated as breaks between words. If `lower_first` is set, then the first character of the string will be lowercase (e.g. camelCase). ]==] function export.camel_case(str, lower_first) str = ugsub(str, "%W*(%w*)", title_case) return lower_first and do_uclcfirst(str, ulower) or str end end do local function do_snake_case(nonword, word) return nonword == "" and word or "_" .. word end --[==[ Converts the input string to {{w|Snake case|snake_case}}. Any non-word characters are treated as breaks between words. ]==] function export.snake_case(str) return (ugsub(str, "(%W*)(%w*)", do_snake_case)) end end return export ndjfpg4lokleft04xzto19wigx7fczh 231389 231388 2026-04-14T07:52:40Z Lee 19 [[:en:Module:string_utilities]] වෙතින් එක් සංශෝධනයක් 221361 Scribunto text/plain local export = {} local function_module = "Module:fun" local load_module = "Module:load" local memoize_module = "Module:memoize" local string_char_module = "Module:string/char" local string_charset_escape_module = "Module:string/charsetEscape" local mw = mw local string = string local table = table local ustring = mw.ustring local byte = string.byte local char = string.char local concat = table.concat local find = string.find local format = string.format local gmatch = string.gmatch local gsub = string.gsub local insert = table.insert local len = string.len local lower = string.lower local match = string.match local next = next local require = require local reverse = string.reverse local select = select local sort = table.sort local sub = string.sub local tonumber = tonumber local tostring = tostring local type = type local ucodepoint = ustring.codepoint local ufind = ustring.find local ugcodepoint = ustring.gcodepoint local ugmatch = ustring.gmatch local ugsub = ustring.gsub local ulower = ustring.lower local umatch = ustring.match local unpack = unpack or table.unpack -- Lua 5.2 compatibility local upper = string.upper local usub = ustring.sub local uupper = ustring.upper local memoize = require(memoize_module) -- Defined below. local codepoint local explode_utf8 local format_fun local get_charset local gsplit local pattern_escape local pattern_simplifier local replacement_escape local title_case local trim local ucfirst local ulen --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls. ]==] local function charset_escape(...) charset_escape = require(string_charset_escape_module) return charset_escape(...) end local function is_callable(...) is_callable = require(function_module).is_callable return is_callable(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function u(...) u = require(string_char_module) return u(...) end local function prepare_iter(str, pattern, str_lib, plain) local callable = is_callable(pattern) if str_lib or plain then return pattern, #str, string, callable elseif not callable then local simple = pattern_simplifier(pattern) if simple then return simple, #str, string, false end end return pattern, ulen(str), ustring, callable end --[==[ Returns {nil} if the input value is the empty string, or otherwise the same value. If the input is a string and `do_trim` is set, the input value will be trimmed before returning; if the trimmed value is the empty string, returns {nil}. If `quote_delimiters` is set, then any outer pair of quotation marks ({' '} or {" "}) surrounding the rest of the input string will be stripped, if present. The string will not be trimmed again, converted to {nil}, or have further quotation marks stripped, as it exists as a way to embed spaces or the empty string in an input. Genuine quotation marks may also be embedded this way (e.g. {"''foo''"} returns {"'foo'"}). ]==] function export.is_not_empty(str, do_trim, quote_delimiters) if str == "" then return nil elseif not (str and type(str) == "string") then return str elseif do_trim then str = trim(str) if str == "" then return nil end end return quote_delimiters and gsub(str, "^(['\"])(.*)%1$", "%2") or str end --[==[ Explodes a string into an array of UTF-8 characters. '''Warning''': this function assumes that the input is valid UTF-8 in order to optimize speed and memory use. Passing in an input containing non-UTF-8 byte sequences could result in unexpected behaviour. ]==] function export.explode_utf8(str) local text, i = {}, 0 for ch in gmatch(str, ".[\128-\191]*") do i = i + 1 text[i] = ch end return text end explode_utf8 = export.explode_utf8 --[==[ Returns {true} if `str` is a valid UTF-8 string. This is true if, for each character, all of the following are true: * It has the expected number of bytes, which is determined by value of the leading byte: 1-byte characters are `0x00` to `0x7F`, 2-byte characters start with `0xC2` to `0xDF`, 3-byte characters start with `0xE0` to `0xEF`, and 4-byte characters start with `0xF0` to `0xF4`. * The leading byte must not fall outside of the above ranges. * The trailing byte(s) (if any), must be between `0x80` to `0xBF`. * The character's codepoint must be between U+0000 (`0x00`) and U+10FFFF (`0xF4 0x8F 0xBF 0xBF`). * The character cannot have an overlong encoding: for each byte length, the lowest theoretical encoding is equivalent to U+0000 (e.g. `0xE0 0x80 0x80`, the lowest theoretical 3-byte encoding, is exactly equivalent to U+0000). Encodings that use more than the minimum number of bytes are not considered valid, meaning that the first valid 3-byte character is `0xE0 0xA0 0x80` (U+0800), and the first valid 4-byte character is `0xF0 0x90 0x80 0x80` (U+10000). Formally, 2-byte characters have leading bytes ranging from `0xC0` to `0xDF` (rather than `0xC2` to `0xDF`), but `0xC0 0x80` to `0xC1 0xBF` are overlong encodings, so it is simpler to say that the 2-byte range begins at `0xC2`. If `allow_surrogates` is set, surrogates (U+D800 to U+DFFF) will be treated as valid UTF-8. Surrogates are used in UTF-16, which encodes codepoints U+0000 to U+FFFF with 2 bytes, and codepoints from U+10000 upwards using a pair of surrogates, which are taken together as a 4-byte unit. Since surrogates have no use in UTF-8, as it encodes higher codepoints in a different way, they are not considered valid in UTF-8 text. However, there are limited circumstances where they may be necessary: for instance, JSON escapes characters using the format `\u0000`, which must contain exactly 4 hexadecimal digits; under the scheme, codepoints above U+FFFF must be escaped as the equivalent pair of surrogates, even though the text itself must be encoded in UTF-8 (e.g. U+10000 becomes `\uD800\uDC00`). ]==] function export.isutf8(str, allow_surrogates) for ch in gmatch(str, "[\128-\255][\128-\191]*") do if #ch > 4 then return false end local b1, b2, b3, b4 = byte(ch, 1, 4) if not (b2 and b2 >= 0x80 and b2 <= 0xBF) then return false -- 1-byte is always invalid, as gmatch excludes 0x00 to 0x7F elseif not b3 then -- 2-byte if not (b1 >= 0xC2 and b1 <= 0xDF) then -- b1 == 0xC0 or b1 == 0xC1 is overlong return false end elseif not (b3 >= 0x80 and b3 <= 0xBF) then -- trailing byte return false elseif not b4 then -- 3-byte if b1 > 0xEF then return false elseif b2 < 0xA0 then if b1 < 0xE1 then -- b1 == 0xE0 and b2 < 0xA0 is overlong return false end elseif b1 < 0xE0 or (b1 == 0xED and not allow_surrogates) then -- b1 == 0xED and b2 >= 0xA0 is a surrogate return false end elseif not (b4 >= 0x80 and b4 <= 0xBF) then -- 4-byte return false elseif b2 < 0x90 then if not (b1 >= 0xF1 and b1 <= 0xF4) then -- b1 == 0xF0 and b2 < 0x90 is overlong return false end elseif not (b1 >= 0xF0 and b1 <= 0xF3) then -- b1 == 0xF4 and b2 >= 0x90 is too high return false end end return true end do local charset_chars = { ["\0"] = "%z", ["%"] = "%%", ["-"] = "%-", ["]"] = "%]", ["^"] = "%^" } charset_chars.__index = charset_chars local chars = setmetatable({ ["$"] = "%$", ["("] = "%(", [")"] = "%)", ["*"] = "%*", ["+"] = "%+", ["."] = "%.", ["?"] = "%?", ["["] = "%[" }, charset_chars) --[==[ Escapes the magic characters used in a [[mw:Extension:Scribunto/Lua reference manual#Patterns|pattern]] (Lua's version of regular expressions): {$%()*+-.?[]^}, and converts the null character to {%z}. For example, {"^$()%.[]*+-?\0"} becomes {"%^%$%(%)%%%.%[%]%*%+%-%?%z"}. This is necessary when constructing a pattern involving arbitrary text (e.g. from user input). ]==] function export.pattern_escape(str) return (gsub(str, "[%z$%%()*+%-.?[%]^]", chars)) end pattern_escape = export.pattern_escape --[==[ Escapes only {%}, which is the only magic character used in replacement [[mw:Extension:Scribunto/Lua reference manual#Patterns|patterns]] with string.gsub and mw.ustring.gsub. ]==] function export.replacement_escape(str) return (gsub(str, "%%", "%%%%")) end replacement_escape = export.replacement_escape local function case_insensitive_char(ch) local upper_ch = uupper(ch) if upper_ch == ch then ch = ulower(ch) if ch == upper_ch then return chars[ch] or ch end end return "[" .. (charset_chars[upper_ch] or upper_ch) .. (charset_chars[ch] or ch) .. "]" end local function iterate(str, str_len, text, n, start, _gsub, _sub, loc1, loc2) if not (loc1 and start <= str_len) then -- Add final chunk and return. n = n + 1 text[n] = _gsub(_sub(str, start), ".", chars) return elseif loc2 < loc1 then if _sub == sub then local b = byte(str, loc1) if b and b >= 128 then loc1 = loc1 + (b < 224 and 1 or b < 240 and 2 or 3) end end n = n + 1 text[n] = _gsub(_sub(str, start, loc1), ".", chars) start = loc1 + 1 if start > str_len then return end else -- Add chunk up to the current match. n = n + 1 text[n] = _gsub(_sub(str, start, loc1 - 1), ".", chars) -- Add current match. n = n + 1 text[n] = _gsub(_sub(str, loc1, loc2), ".", case_insensitive_char) start = loc2 + 1 end return n, start end --[==[ Escapes the magic characters used in a [[mw:Extension:Scribunto/Lua reference manual#Patterns|pattern]], and makes all characters case-insensitive. An optional pattern or find function (see {split}) may be supplied as the second argument, the third argument (`str_lib`) forces use of the string library, while the fourth argument (`plain`) turns any pattern matching facilities off in the optional pattern supplied. ]==] function export.case_insensitive_pattern(str, pattern_or_func, str_lib, plain) if pattern_or_func == nil then return (gsub(str, str_lib and "[^\128-\255]" or ".[\128-\191]*", case_insensitive_char)) end local text, n, start, str_len, _string, callable = {}, 0, 1 pattern_or_func, str_len, _string, callable = prepare_iter(str, pattern_or_func, str_lib, plain) local _find, _gsub, _sub = _string.find, _string.gsub, _string.sub if callable then repeat n, start = iterate(str, str_len, text, n, start, _gsub, _sub, pattern_or_func(str, start)) until not start -- Special case if the pattern is anchored to the start: "^" always -- anchors to the start position, not the start of the string, so get -- around this by only attempting one match with the pattern, then match -- the end of the string. elseif byte(pattern_or_func) == 0x5E then -- ^ n, start = iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, pattern_or_func, start, plain)) if start ~= nil then iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, "$", start, plain)) end else repeat n, start = iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, pattern_or_func, start, plain)) until not start end return concat(text) end end do local character_classes local function get_character_classes() character_classes, get_character_classes = { [0x41] = true, [0x61] = true, -- Aa [0x43] = true, [0x63] = true, -- Cc [0x44] = true, [0x64] = true, -- Dd [0x4C] = true, [0x6C] = true, -- Ll [0x50] = true, [0x70] = true, -- Pp [0x53] = true, [0x73] = true, -- Ss [0x55] = true, [0x75] = true, -- Uu [0x57] = true, [0x77] = true, -- Ww [0x58] = true, [0x78] = true, -- Xx [0x5A] = true, -- z dealt with separately. }, nil return character_classes end local function check_sets_equal(set1, set2) local k2 for k1, v1 in next, set1 do local v2 = set2[k1] if v1 ~= v2 and (v2 == nil or not check_sets_equal(v1, v2)) then return false end k2 = next(set2, k2) end return next(set2, k2) == nil end local function check_sets(bytes) local key, set1, set = next(bytes) if set1 == true then return true elseif not check_sets(set1) then return false end while true do key, set = next(bytes, key) if not key then return true elseif not check_sets_equal(set, set1) then return false end end end local function make_charset(range) if #range == 1 then return char(range[1]) end sort(range) local compressed, n, start = {}, 0, range[1] for i = 1, #range do local this, nxt = range[i], range[i + 1] if nxt ~= this + 1 then n = n + 1 compressed[n] = this == start and char(this) or char(start) .. "-" .. char(this) start = nxt end end return "[" .. concat(compressed) .. "]" end local function parse_1_byte_charset(pattern, pos) local ch while true do pos, ch = match(pattern, "()([%%%]\192-\255])", pos) if ch == "%" then local nxt = byte(pattern, pos + 1) if not nxt or nxt >= 128 or (character_classes or get_character_classes())[nxt] then -- acdlpsuwxACDLPSUWXZ, but not z return false end pos = pos + 2 elseif ch == "]" then pos = pos + 1 return pos else return false end end end --[==[ Parses `pattern`, a ustring library pattern, and attempts to convert it into a string library pattern. If conversion isn't possible, returns false. ]==] function pattern_simplifier(pattern) if type(pattern) == "number" then return tostring(pattern) end local pos, capture_groups, start, n, output, ch, nxt_pos = 1, 0, 1, 0 while true do -- FIXME: use "()([%%(.[\128-\255])[\128-\191]?[\128-\191]?[\128-\191]?()" and ensure non-UTF8 always fails. pos, ch, nxt_pos = match(pattern, "()([%%(.[\192-\255])[\128-\191]*()", pos) if not ch then break end local nxt = byte(pattern, nxt_pos) if ch == "%" then if nxt == 0x62 then -- b local nxt2, nxt3 = byte(pattern, pos + 2, pos + 3) if not (nxt2 and nxt2 < 128 and nxt3 and nxt3 < 128) then return false end pos = pos + 4 elseif nxt == 0x66 then -- f nxt_pos = nxt_pos + 2 local nxt2, nxt3 = byte(pattern, nxt_pos - 1, nxt_pos) -- Only possible to convert a positive %f charset which is -- all ASCII, so use parse_1_byte_charset. if not (nxt2 == 0x5B and nxt3 and nxt3 ~= 0x5E and nxt3 < 128) then -- [^ return false elseif nxt3 == 0x5D then -- Initial ] is non-magic. nxt_pos = nxt_pos + 1 end pos = parse_1_byte_charset(pattern, nxt_pos) if not pos then return false end elseif nxt == 0x5A then -- Z nxt = byte(pattern, nxt_pos + 1) if nxt == 0x2A or nxt == 0x2D then -- *- pos = pos + 3 else if output == nil then output = {} end local ins = sub(pattern, start, pos - 1) .. "[\1-\127\192-\255]" n = n + 1 if nxt == 0x2B then -- + output[n] = ins .. "%Z*" pos = pos + 3 elseif nxt == 0x3F then -- ? output[n] = ins .. "?[\128-\191]*" pos = pos + 3 else output[n] = ins .. "[\128-\191]*" pos = pos + 2 end start = pos end elseif not nxt or (character_classes or get_character_classes())[nxt] then -- acdlpsuwxACDLPSUWX, but not Zz return false -- Skip the next character if it's ASCII. Otherwise, we will -- still need to do length checks. else pos = pos + (nxt < 128 and 2 or 1) end elseif ch == "(" then if nxt == 0x29 or capture_groups == 32 then -- ) return false end capture_groups = capture_groups + 1 pos = pos + 1 elseif ch == "." then if nxt == 0x2A or nxt == 0x2D then -- *- pos = pos + 2 else if output == nil then output = {} end local ins = sub(pattern, start, pos - 1) .. "[^\128-\191]" n = n + 1 if nxt == 0x2B then -- + output[n] = ins .. ".*" pos = pos + 2 elseif nxt == 0x3F then -- ? output[n] = ins .. "?[\128-\191]*" pos = pos + 2 else output[n] = ins .. "[\128-\191]*" pos = pos + 1 end start = pos end elseif ch == "[" then -- Fail negative charsets. TODO: 1-byte charsets should be safe. if nxt == 0x5E then -- ^ return false -- If the first character is "%", ch_len is determined by the -- next one instead. elseif nxt == 0x25 then -- % nxt = byte(pattern, nxt_pos + 1) elseif nxt == 0x5D then -- Initial ] is non-magic. nxt_pos = nxt_pos + 1 end if not nxt then return false end local ch_len = nxt < 128 and 1 or nxt < 224 and 2 or nxt < 240 and 3 or 4 if ch_len == 1 then -- Single-byte charset. pos = parse_1_byte_charset(pattern, nxt_pos) if not pos then return false end else -- Multibyte charset. -- TODO: 1-byte chars should be safe to mix with multibyte chars. CONFIRM THIS FIRST. local charset_pos, bytes = pos pos = pos + 1 while true do -- TODO: non-ASCII charset ranges. pos, ch, nxt_pos = match(pattern, "^()([^\128-\191])[\128-\191]*()", pos) -- If escaped, get the next character. No need to -- distinguish magic characters or character classes, -- as they'll all fail for having the wrong length -- anyway. if ch == "%" then pos, ch, nxt_pos = match(pattern, "^()([^\128-\191])[\128-\191]*()", nxt_pos) elseif ch == "]" then pos = nxt_pos break end if not (ch and nxt_pos - pos == ch_len) then return false elseif bytes == nil then bytes = {} end local bytes, last = bytes, nxt_pos - 1 for i = pos, last - 1 do local b = byte(pattern, i) local bytes_b = bytes[b] if bytes_b == nil then bytes_b = {} bytes[b] = bytes_b end bytes[b], bytes = bytes_b, bytes_b end bytes[byte(pattern, last)] = true pos = nxt_pos end if not pos then return false end nxt = byte(pattern, pos) if ( (nxt == 0x2A or nxt == 0x2D or nxt == 0x3F) or -- *-? (nxt == 0x2B and ch_len > 2) or -- + not check_sets(bytes) ) then return false end local ranges, b, key, next_byte = {}, 0 repeat key, next_byte = next(bytes) local range, n = {key}, 1 -- Loop starts on the second iteration. for key in next, bytes, key do n = n + 1 range[n] = key end b = b + 1 ranges[b] = range bytes = next_byte until next_byte == true if nxt == 0x2B then -- + local range1, range2 = ranges[1], ranges[2] ranges[1], ranges[3] = make_charset(range1), make_charset(range2) local n = #range2 for i = 1, #range1 do n = n + 1 range2[n] = range1[i] end ranges[2] = make_charset(range2) .. "*" pos = pos + 1 else for i = 1, #ranges do ranges[i] = make_charset(ranges[i]) end end if output == nil then output = {} end nxt = byte(pattern, pos) n = n + 1 output[n] = sub(pattern, start, charset_pos - 1) .. concat(ranges) .. ((nxt == 0x2A or nxt == 0x2B or nxt == 0x2D or nxt == 0x3F) and "%" or "") -- following *+-? now have to be escaped start = pos end elseif not nxt then break elseif nxt == 0x2B then -- + if nxt_pos - pos ~= 2 then return false elseif output == nil then output = {} end pos, nxt_pos = pos + 1, nxt_pos + 1 nxt = byte(pattern, nxt_pos) local ch2 = sub(pattern, pos, pos) n = n + 1 output[n] = sub(pattern, start, pos - 1) .. "[" .. ch .. ch2 .. "]*" .. ch2 .. ((nxt == 0x2A or nxt == 0x2B or nxt == 0x2D or nxt == 0x3F) and "%" or "") -- following *+-? now have to be escaped pos, start = nxt_pos, nxt_pos elseif nxt == 0x2A or nxt == 0x2D or nxt == 0x3F then -- *-? return false else pos = nxt_pos end end if start == 1 then return pattern end return concat(output) .. sub(pattern, start) end pattern_simplifier = memoize(pattern_simplifier, true) export.pattern_simplifier = pattern_simplifier end --[==[ Parses `charset`, the interior of a string or ustring library character set, and normalizes it into a string or ustring library pattern (e.g. {"abcd-g"} becomes {"[abcd-g]"}, and {"[]"} becomes {"[[%]]"}). The negative (`^`), range (`-`) and literal (`%`) magic characters work as normal, and character classes may be used (e.g. `%d` and `%w`), but opening and closing square brackets are sanitized so that they behave like ordinary characters. ]==] function get_charset(charset) if type(charset) == "number" then return tostring(charset) end local pos, start, n, output = 1, 1, 0 if byte(charset) == 0x5E then -- ^ pos = pos + 1 end -- FIXME: "]" is non-magic if it's the first character in a charset. local nxt_pos, nxt while true do local new_pos, ch = match(charset, "()([%%%-%]])", pos) if not ch then break -- Skip percent escapes. Ranges can't start with them, either. elseif ch == "%" then pos = new_pos + 2 else -- If `ch` is a hyphen, get the character before iff it's at or ahead of `pos`. if ch == "-" and new_pos > pos then pos, nxt_pos, nxt = new_pos - 1, new_pos, ch ch = sub(charset, pos, pos) else pos, nxt_pos = new_pos, new_pos + 1 nxt = sub(charset, nxt_pos, nxt_pos) end -- Range. if nxt == "-" then if output == nil then output = {} end n = n + 1 output[n] = sub(charset, start, pos - 1) nxt_pos = nxt_pos + 1 nxt = sub(charset, nxt_pos, nxt_pos) -- Ranges fail if they end with a percent escape, so escape the hyphen to avoid undefined behaviour. if nxt == "" or nxt == "%" then n = n + 1 output[n] = (ch == "]" and "%]" or ch) .. "%-" start = nxt_pos nxt_pos = nxt_pos + 2 -- Since ranges can't contain "%]", since it's escaped, range inputs like "]-z" or "a-]" must be -- adjusted to the character before or after, plus "%]" (e.g. "%]^-z" or "a-\\%]"). The escaped "%]" is -- omitted if the range would be empty (i.e. if the first byte is greater than the second). else n = n + 1 output[n] = (ch == "]" and (byte(nxt) >= 0x5D and "%]^" or "^") or ch) .. "-" .. (nxt == "]" and (byte(ch) <= 0x5D and "\\%]" or "\\") or nxt) nxt_pos = nxt_pos + 1 start = nxt_pos end elseif ch == "-" or ch == "]" then if output == nil then output = {} end n = n + 1 output[n] = sub(charset, start, pos - 1) .. "%" .. ch start = nxt_pos end pos = nxt_pos end end if start == 1 then return "[" .. charset .. "]" end return "[" .. concat(output) .. sub(charset, start) .. "]" end get_charset = memoize(get_charset, true) export.get_charset = get_charset function export.len(str) return type(str) == "number" and len(str) or #str - #gsub(str, "[^\128-\191]+", "") end ulen = export.len function export.sub(str, i, j) str, i = type(str) == "number" and tostring(str) or str, i or 1 if i < 0 or j and j < 0 then return usub(str, i, j) elseif j and i > j or i > #str then return "" end local n, new_i = 0 for loc1, loc2 in gmatch(str, "()[^\128-\191]+()[\128-\191]*") do n = n + loc2 - loc1 if not new_i and n >= i then new_i = loc2 - (n - i) - 1 if not j then return sub(str, new_i) end end if j and n > j then return sub(str, new_i, loc2 - (n - j) - 1) end end return new_i and sub(str, new_i) or "" end do local function _find(str, loc1, loc2, ...) if loc1 and not match(str, "^()[^\128-\255]*$") then -- Use raw values of loc1 and loc2 to get loc1 and the length of the match. loc1, loc2 = ulen(sub(str, 1, loc1)), ulen(sub(str, loc1, loc2)) -- Offset length with loc1 to get loc2. loc2 = loc1 + loc2 - 1 end return loc1, loc2, ... end --[==[A version of find which uses string.find when possible, but otherwise uses mw.ustring.find.]==] function export.find(str, pattern, init, plain) init = init or 1 if init ~= 1 and not match(str, "^()[^\128-\255]*$") then return ufind(str, pattern, init, plain) elseif plain then return _find(str, find(str, pattern, init, true)) end local simple = pattern_simplifier(pattern) if simple then return _find(str, find(str, simple, init)) end return ufind(str, pattern, init) end end --[==[A version of match which uses string.match when possible, but otherwise uses mw.ustring.match.]==] function export.match(str, pattern, init) init = init or 1 if init ~= 1 and not match(str, "^()[^\128-\255]*$") then return umatch(str, pattern, init) end local simple = pattern_simplifier(pattern) if simple then return match(str, simple, init) end return umatch(str, pattern, init) end --[==[A version of gmatch which uses string.gmatch when possible, but otherwise uses mw.ustring.gmatch.]==] function export.gmatch(str, pattern) local simple = pattern_simplifier(pattern) if simple then return gmatch(str, simple) end return ugmatch(str, pattern) end --[==[A version of gsub which uses string.gsub when possible, but otherwise uses mw.ustring.gsub.]==] function export.gsub(str, pattern, repl, n) local simple = pattern_simplifier(pattern) if simple then return gsub(str, simple, repl, n) end return ugsub(str, pattern, repl, n) end --[==[ Like gsub, but pattern-matching facilities are turned off, so `pattern` and `repl` (if a string) are treated as literal. ]==] function export.plain_gsub(str, pattern, repl, n) return gsub(str, pattern_escape(pattern), type(repl) == "string" and replacement_escape(repl) or repl, n) end --[==[ Reverses a UTF-8 string; equivalent to string.reverse. ]==] function export.reverse(str) return reverse((gsub(str, "[\192-\255][\128-\191]*", reverse))) end function export.char(...) -- To be moved to [[Module:string/char]]. return u(...) end do local function utf8_err(func_name) error(format("bad argument #1 to '%s' (string is not UTF-8)", func_name), 4) end local function get_codepoint(func_name, b1, b2, b3, b4) if b1 <= 0x7F then return b1, 1 elseif not (b2 and b2 >= 0x80 and b2 <= 0xBF) then utf8_err(func_name) elseif b1 <= 0xDF then local cp = 0x40 * b1 + b2 - 0x3080 return cp >= 0x80 and cp or utf8_err(func_name), 2 elseif not (b3 and b3 >= 0x80 and b3 <= 0xBF) then utf8_err(func_name) elseif b1 <= 0xEF then local cp = 0x1000 * b1 + 0x40 * b2 + b3 - 0xE2080 return cp >= 0x800 and cp or utf8_err(func_name), 3 elseif not (b4 and b4 >= 0x80 and b4 <= 0xBF) then utf8_err(func_name) end local cp = 0x40000 * b1 + 0x1000 * b2 + 0x40 * b3 + b4 - 0x3C82080 return cp >= 0x10000 and cp <= 0x10FFFF and cp or utf8_err(func_name), 4 end function export.codepoint(str, i, j) if str == "" then return -- return nothing elseif type(str) == "number" then return byte(str, i, j) end i, j = i or 1, j == -1 and #str or i or 1 if i == 1 and j == 1 then return (get_codepoint("codepoint", byte(str, 1, 4))) elseif i < 0 or j < 0 then return ucodepoint(str, i, j) -- FIXME end local n, nb, ret, nr = 0, 1, {}, 0 while n < j do n = n + 1 if n < i then local b = byte(str, nb) nb = nb + (b < 128 and 1 or b < 224 and 2 or b < 240 and 3 or 4) else local b1, b2, b3, b4 = byte(str, nb, nb + 3) if not b1 then break end nr = nr + 1 local add ret[nr], add = get_codepoint("codepoint", b1, b2, b3, b4) nb = nb + add end end return unpack(ret) end codepoint = export.codepoint function export.gcodepoint(str, i, j) i, j = i or 1, j ~= -1 and j or nil if i < 0 or j and j < 0 then return ugcodepoint(str, i, j) -- FIXME end local n, nb = 1, 1 while n < i do local b = byte(str, nb) if not b then break end nb = nb + (b < 128 and 1 or b < 224 and 2 or b < 240 and 3 or 4) n = n + 1 end return function() if j and n > j then return nil end n = n + 1 local b1, b2, b3, b4 = byte(str, nb, nb + 3) if not b1 then return nil end local ret, add = get_codepoint("gcodepoint", b1, b2, b3, b4) nb = nb + add return ret end end end do local _ulower = ulower --[==[A version of lower which uses string.lower when possible, but otherwise uses mw.ustring.lower.]==] function export.lower(str) return (match(str, "^()[^\128-\255]*$") and lower or _ulower)(str) end end do local _uupper = uupper --[==[A version of upper which uses string.upper when possible, but otherwise uses mw.ustring.upper.]==] function export.upper(str) return (match(str, "^()[^\128-\255]*$") and upper or _uupper)(str) end end do local function add_captures(t, n, ...) if ... == nil then return end -- Insert any captures from the splitting pattern. local offset, capture = n - 1, ... while capture do n = n + 1 t[n] = capture capture = select(n - offset, ...) end return n end --[==[ Reimplementation of mw.text.split() that includes any capturing groups in the splitting pattern. This works like Python's re.split() function, except that it has Lua's behavior when the split pattern is empty (i.e. advancing by one character at a time; Python returns the whole remainder of the string). When possible, it will use the string library, but otherwise uses the ustring library. There are two optional parameters: `str_lib` forces use of the string library, while `plain` turns any pattern matching facilities off, treating `pattern` as literal. In addition, `pattern` may be a custom find function (or callable table), which takes the input string and start index as its two arguments, and must return the start and end index of the match, plus any optional captures, or nil if there are no further matches. By default, the start index will be calculated using the ustring library, unless `str_lib` or `plain` is set. ]==] function export.split(str, pattern_or_func, str_lib, plain) local iter, t, n = gsplit(str, pattern_or_func, str_lib, plain), {}, 0 repeat n = add_captures(t, n, iter()) until n == nil return t end export.capturing_split = export.split -- To be removed. end --[==[ Returns an iterator function, which iterates over the substrings returned by {split}. The first value returned is the string up the splitting pattern, with any capture groups being returned as additional values on that iteration. ]==] function export.gsplit(str, pattern_or_func, str_lib, plain) local start, final, str_len, _string, callable = 1 pattern_or_func, str_len, _string, callable = prepare_iter(str, pattern_or_func, str_lib, plain) local _find, _sub = _string.find, _string.sub local function iter(loc1, loc2, ...) -- If no match, or there is but we're past the end of the string -- (which happens when the match is the empty string), then return -- the final chunk. if not loc1 then final = true return _sub(str, start) end -- Special case: If we match the empty string, then eat the -- next character; this avoids an infinite loop, and makes -- splitting by the empty string work the way mw.text.gsplit() does -- (including non-adjacent empty string matches with %f). If we -- reach the end of the string this way, set `final` to true, so we -- don't get stuck matching the empty string at the end. local chunk if loc2 < loc1 then -- If using the string library, we need to make sure we advance -- by one UTF-8 character. if _sub == sub then local b = byte(str, loc1) if b and b >= 128 then loc1 = loc1 + (b < 224 and 1 or b < 240 and 2 or 3) end end chunk = _sub(str, start, loc1) if loc1 >= str_len then final = true else start = loc1 + 1 end -- Eat chunk up to the current match. else chunk = _sub(str, start, loc1 - 1) start = loc2 + 1 end return chunk, ... end if callable then return function() if not final then return iter(pattern_or_func(str, start)) end end -- Special case if the pattern is anchored to the start: "^" always -- anchors to the start position, not the start of the string, so get -- around this by only attempting one match with the pattern, then match -- the end of the string. elseif byte(pattern_or_func) == 0x5E then -- ^ local returned return function() if not returned then returned = true return iter(_find(str, pattern_or_func, start, plain)) elseif not final then return iter(_find(str, "$", start, plain)) end end end return function() if not final then return iter(_find(str, pattern_or_func, start, plain)) end end end gsplit = export.gsplit function export.count(str, pattern, plain) if plain then return select(2, gsub(str, pattern_escape(pattern), "")) end local simple = pattern_simplifier(pattern) if simple then return select(2, gsub(str, pattern, "")) end return select(2, ugsub(str, pattern, "")) end function export.trim(str, charset, str_lib, plain) if charset == nil then -- "^.*%S" is the fastest trim algorithm except when strings only consist of characters to be trimmed, which are -- very slow due to catastrophic backtracking. gsub with "^%s*" gets around this by trimming such strings to "" -- first. return match(gsub(str, "^%s*", ""), "^.*%S") or "" elseif charset == "" then return str end charset = plain and ("[" .. charset_escape(charset) .. "]") or get_charset(charset) -- The pattern uses a non-greedy quantifier instead of the algorithm used for %s, because negative character sets -- are non-trivial to compute (e.g. "[^^-z]" becomes "[%^_-z]"). Plus, if the ustring library has to be used, there -- would be two callbacks into PHP, which is slower. local pattern = "^" .. charset .. "*(.-)" .. charset .. "*$" if not str_lib then local simple = pattern_simplifier(pattern) if not simple then return umatch(str, pattern) end pattern = simple end return match(str, pattern) end trim = export.trim do local entities local function get_entities() entities, get_entities = load_data("Module:data/entities"), nil return entities end local function decode_entity(hash, x, code) if hash == "" then return (entities or get_entities())[x .. code] end local cp if x == "" then cp = match(code, "^()%d+$") and tonumber(code) else cp = match(code, "^()%x+$") and tonumber(code, 16) end return cp and (cp <= 0xD7FF or cp >= 0xE000 and cp <= 0x10FFFF) and u(cp) or nil end -- Non-ASCII characters aren't valid in proper HTML named entities, but MediaWiki uses them in some custom aliases -- which have also been included in [[Module:data/entities]]. function export.decode_entities(str) local amp = find(str, "&", nil, true) return amp and find(str, ";", amp, true) and gsub(str, "&(#?)([xX]?)([%w\128-\255]+);", decode_entity) or str end end do local entities local function get_entities() -- Memoized HTML entities (taken from mw.text.lua). entities, get_entities = { ["\""] = "&quot;", ["&"] = "&amp;", ["'"] = "&#039;", ["<"] = "&lt;", [">"] = "&gt;", ["\194\160"] = "&nbsp;", }, nil return entities end local function encode_entity(ch) local entity = (entities or get_entities())[ch] if entity == nil then local cp = codepoint(ch) -- U+D800 to U+DFFF are surrogates, so can't be encoded as entities. entity = cp and (cp <= 0xD7FF or cp >= 0xE000) and format("&#%d;", cp) or false entities[ch] = entity end return entity or nil end function export.encode_entities(str, charset, str_lib, plain) if charset == nil then return (gsub(str, "[\"&'<>\194]\160?", entities or get_entities())) elseif charset == "" then return str end local pattern = plain and ("[" .. charset_escape(charset) .. "]") or charset == "." and charset or get_charset(charset) if not str_lib then local simple = pattern_simplifier(pattern) if not simple then return (ugsub(str, pattern, encode_entity)) end pattern = simple end return (gsub(str, pattern, encode_entity)) end end do local function decode_path(code) return char(tonumber(code, 16)) end local function decode(lead, trail) if lead == "+" or lead == "_" then return " " .. trail elseif #trail == 2 then return decode_path(trail) end return lead .. trail end function export.decode_uri(str, enctype) enctype = enctype and upper(enctype) or "QUERY" if enctype == "PATH" then return find(str, "%", nil, true) and gsub(str, "%%(%x%x)", decode_path) or str elseif enctype == "QUERY" then return (find(str, "%", nil, true) or find(str, "+", nil, true)) and gsub(str, "([%%%+])(%x?%x?)", decode) or str elseif enctype == "WIKI" then return (find(str, "%", nil, true) or find(str, "_", nil, true)) and gsub(str, "([%%_])(%x?%x?)", decode) or str end error("bad argument #2 to 'decode_uri' (expected QUERY, PATH, or WIKI)", 2) end end do local function _remove_comments(str, pre) local head = find(str, "<!--", nil, true) if not head then return str end local ret, n = {sub(str, 1, head - 1)}, 1 while true do local loc = find(str, "-->", head + 4, true) if not loc then return pre and concat(ret) or concat(ret) .. sub(str, head) end head = loc + 3 loc = find(str, "<!--", head, true) if not loc then return concat(ret) .. sub(str, head) end n = n + 1 ret[n] = sub(str, head, loc - 1) head = loc end end --[==[ Removes any HTML comments from the input text. `stage` can be one of three options: * {"PRE"} (default) applies the method used by MediaWiki's preprocessor: all {{code|html|<nowiki><!-- ... --></nowiki>}} pairs are removed, as well as any text after an unclosed {{code|html|<nowiki><!--</nowiki>}}. This is generally suitable when parsing raw template or [[mw:Parser extension tags|parser extension tag]] code. (Note, however, that the actual method used by the preprocessor is considerably more complex and differs under certain conditions (e.g. comments inside nowiki tags); if full accuracy is absolutely necessary, use [[Module:template parser]] instead). * {"POST"} applies the method used to generate the final page output once all templates have been expanded: it loops over the text, removing any {{code|html|<nowiki><!-- ... --></nowiki>}} pairs until no more are found (e.g. {{code|html|<nowiki><!-<!-- ... -->- ... --></nowiki>}} would be fully removed), but any unclosed {{code|html|<nowiki><!--</nowiki>}} is ignored. This is suitable for handling links embedded in template inputs, where the {"PRE"} method will have already been applied by the native parser. * {"BOTH"} applies {"PRE"} then {"POST"}. ]==] function export.remove_comments(str, stage) if not stage or stage == "PRE" then return _remove_comments(str, true) end local processed = stage == "POST" and _remove_comments(str) or stage == "BOTH" and _remove_comments(str, true) or error("bad argument #2 to 'remove_comments' (expected PRE, POST, or BOTH)", 2) while processed ~= str do str = processed processed = _remove_comments(str) end return str end end do local byte_escapes local function get_byte_escapes() byte_escapes, get_byte_escapes = load_data("Module:string utilities/data").byte_escapes, nil return byte_escapes end local function escape_byte(b) return (byte_escapes or get_byte_escapes())[b] or format("\\%03d", byte(b)) end function export.escape_bytes(str) return (gsub(str, ".", escape_byte)) end end function export.format_fun(str, fun) return (gsub(str, "{(\\?)((\\?)[^{}]*)}", function(p1, name, p2) if #p1 + #p2 == 1 then return name == "op" and "{" or name == "cl" and "}" or error(mw.getCurrentFrame():getTitle() .. " format: unrecognized escape sequence '{\\" .. name .. "}'") elseif fun(name) and type(fun(name)) ~= "string" then error(mw.getCurrentFrame():getTitle() .. " format: \"" .. name .. "\" is a " .. type(fun(name)) .. ", not a string") end return fun(name) or error(mw.getCurrentFrame():getTitle() .. " format: \"" .. name .. "\" not found in table") end)) end format_fun = export.format_fun --[==[ This function, unlike {string.format} and {mw.ustring.format}, takes just two parameters, a format string and a table, and replaces all instances of { {param_name} } in the format string with the table's entry for {param_name}. The opening and closing brace characters can be escaped with { {\op} } and { {\cl} }, respectively. A table entry beginning with a slash can be escaped by doubling the initial slash. ====Examples==== * {string_utilities.format("{foo} fish, {bar} fish, {baz} fish, {quux} fish", {["foo"]="one", ["bar"]="two", ["baz"]="red", ["quux"]="blue"}) } *: produces: {"one fish, two fish, red fish, blue fish"} * {string_utilities.format("The set {\\op}1, 2, 3{\\cl} contains {\\\\hello} elements.", {["\\hello"]="three"})} *: produces: {"The set {1, 2, 3} contains three elements."} *:* Note that the single and double backslashes should be entered as double and quadruple backslashes when quoted in a literal string. ]==] function export.format(str, tbl) return format_fun(str, function(key) return tbl[key] end) end do local function do_uclcfirst(str, case_func) -- Re-case the first letter. local first, remainder = match(str, "^(.[\128-\191]*)(.*)") return first and (case_func(first) .. remainder) or "" end local function uclcfirst(str, case_func) -- Strip off any HTML tags at the beginning. This currently does not handle comments or <ref>...</ref> -- correctly; it's intended for text wrapped in <span> or the like, as happens when passing text through -- [[Module:links]]. local html_at_beginning = nil if str:match("^<") then while true do local html_tag, rest = str:match("^(<.->)(.*)$") if not html_tag then break end if not html_at_beginning then html_at_beginning = {} end insert(html_at_beginning, html_tag) str = rest end end -- If there's a link at the beginning, re-case the first letter of the -- link text. This pattern matches both piped and unpiped links. -- If the link is not piped, the second capture (linktext) will be empty. local link, linktext, remainder = match(str, "^%[%[([^|%]]+)%|?(.-)%]%](.*)$") local retval if link then retval = "[[" .. link .. "|" .. do_uclcfirst(linktext ~= "" and linktext or link, case_func) .. "]]" .. remainder else retval = do_uclcfirst(str, case_func) end if html_at_beginning then retval = concat(html_at_beginning) .. retval end return retval end --[==[ Uppercase the first character of the input string, correctly handling one-part and two-part links, optionally surrounded by HTML tags such as `<nowiki><span>...</span></nowiki>`, possibly nested. Intended to correctly uppercase the first character of text that may include links that have been passed through `full_link()` in [[Module:links]] or a similar function. ]==] function export.ucfirst(str) return uclcfirst(str, uupper) end ucfirst = export.ucfirst --[==[ Lowercase the first character of the input string, correctly handling one-part and two-part links, optionally surrounded by HTML tags such as `<nowiki><span>...</span></nowiki>`, possibly nested. Intended to correctly lowercase the first character of text that may include links that have been passed through `full_link()` in [[Module:links]] or a similar function. ]==] function export.lcfirst(str) return uclcfirst(str, ulower) end --[==[Capitalizes each word of the input string. WARNING: May be broken in the presence of multiword links.]==] function export.capitalize(str) -- Capitalize multi-word that is separated by spaces -- by uppercasing the first letter of each part. return (ugsub(str, "%w+", ucfirst)) end local function do_title_case(first, remainder) first = uupper(first) return remainder == "" and first or (first .. ulower(remainder)) end --[==[ Capitalizes each word of the input string, with any further letters in each word being converted to lowercase. ]==] function export.title_case(str) return str == "" and "" or ugsub(str, "(%w)(%w*)", do_title_case) end title_case = export.title_case --[==[ Converts the input string to {{w|Camel case|CamelCase}}. Any non-word characters are treated as breaks between words. If `lower_first` is set, then the first character of the string will be lowercase (e.g. camelCase). ]==] function export.camel_case(str, lower_first) str = ugsub(str, "%W*(%w*)", title_case) return lower_first and do_uclcfirst(str, ulower) or str end end do local function do_snake_case(nonword, word) return nonword == "" and word or "_" .. word end --[==[ Converts the input string to {{w|Snake case|snake_case}}. Any non-word characters are treated as breaks between words. ]==] function export.snake_case(str) return (ugsub(str, "(%W*)(%w*)", do_snake_case)) end end return export ndjfpg4lokleft04xzto19wigx7fczh 828 6238 231358 228901 2026-03-23T20:47:29Z en>Juwan 0 added QIDs to Otomian languages; [[Special:FindComment/c-Jlwoodwa-20260323155100]] 231358 Scribunto text/plain --[=[ This module contains definitions for all language family codes on Wiktionary. ]=]-- local m = {} m["aav"] = { "Austroasiatic", 33199, aliases = {"Austro-Asiatic"}, } m["aav-khs"] = { "Khasian", 3073734, "aav", aliases = {"Khasic"}, } m["aav-nic"] = { "Nicobarese", 217380, "aav", } m["aav-pkl"] = { "Pnar-Khasi-Lyngngam", nil, "aav-khs", } m["afa"] = { "Afroasiatic", 25268, aliases = {"Afro-Asiatic"}, } m["alg"] = { "Algonquian", 33392, "aql", } m["alg-abp"] = { "Abenaki-Penobscot", 197936, "alg-eas", } m["alg-ara"] = { "Arapahoan", 2153686, "alg", } m["alg-eas"] = { "Eastern Algonquian", 2257525, "alg", } m["alg-sfk"] = { "Sac-Fox-Kickapoo", 1440172, "alg", } m["alv"] = { "Atlantic-Congo", 771124, "nic", } m["alv-aah"] = { "Ayere-Ahan", 750953, "alv-von", } m["alv-ada"] = { "Adamawa", 32906, "alv-sav", } m["alv-bag"] = { "Baga", 2746083, "alv-mel", } m["alv-bak"] = { "Bak", 1708174, "alv-sng", } m["alv-bam"] = { "Bambukic", 4853456, "alv-ada", aliases = {"Yungur-Jen"}, } m["alv-bny"] = { "Banyum", 2892477, "alv-nyn", } m["alv-bua"] = { "Bua", 4982094, "alv-mbd", } m["alv-bwj"] = { "Bikwin-Jen", 84542501, "alv-bam", } m["alv-cng"] = { "Cangin", 1033184, "alv-fwo", } m["alv-ctn"] = { "Central Tano", 1658486, "alv-ptn", aliases = {"Akan"}, } m["alv-dlt"] = { "Delta Edoid", nil, "alv-edo", } m["alv-dur"] = { "Duru", 5316788, "alv-lni", } m["alv-ede"] = { "Ede", 35368, "alv-yor", } m["alv-edk"] = { "Edekiri", 5336735, "alv-yrd", } m["alv-edo"] = { "Edoid", 1287469, "alv-von", } m["alv-eeo"] = { "Edo-Esan-Ora", 12630439, "alv-nce", } m["alv-fli"] = { "Fali", 3450166, "alv", } m["alv-fwo"] = { "Fula-Wolof", 12631267, "alv-sng", } m["alv-gbe"] = { "Gbe", 668284, "alv-von", } m["alv-gda"] = { "Ga-Dangme", 3443338, "alv-kwa", } m["alv-gng"] = { "Guang", 684009, "alv-ptn", } m["alv-gtm"] = { "Ghana-Togo Mountain", 493020, "alv-kwa", aliases = {"Togo Remnant", "Central Togo"}, } m["alv-hei"] = { "Heiban", 108752116, "alv-the", } m["alv-ido"] = { "Idomoid", 974196, "alv-von", } m["alv-igb"] = { "Igboid", 1429100, "alv-von", } m["alv-jfe"] = { "Jola-Felupe", 1708174, "alv-jol", aliases = {"Ejamat"}, } m["alv-jol"] = { "Jola", 35176, "alv-bak", aliases = {"Diola"}, } m["alv-kim"] = { "Kim", 6409701, "alv-mbd", } m["alv-kis"] = { "Kissi", 35696, "alv-mel", } m["alv-krb"] = { "Karaboro", 4213541, "alv-snf", } m["alv-ktg"] = { "Ka-Togo", 5972796, "alv-gtm", } m["alv-kul"] = { "Kulango", 16977424, "alv-sav", aliases = {"Kulango-Lorhon", "Kulango-Lorom"}, } m["alv-kwa"] = { "Kwa", 33430, "nic-vco", } m["alv-lag"] = { "Lagoon", 111210042, "alv-kwa", } m["alv-lek"] = { "Leko", 6520642, other_names = {"Sambaic"}, -- appears to be an alias in Glottolog "alv-lni", } m["alv-lim"] = { "Limba", 35825, "alv", } m["alv-lni"] = { "Leko-Nimbari", 1708170, "alv-ada", other_names = {"Central Adamawa"}, aliases = {"Chamba-Mumuye"}, } m["alv-mbd"] = { "Mbum-Day", 6799816, "alv-ada", } m["alv-mbm"] = { "Mbum", 6799814, "alv-mbd", } m["alv-mel"] = { "Mel", 12122355, "alv", } m["alv-mum"] = { "Mumuye", 84607009, "alv-mye", } m["alv-mye"] = { "Mumuye-Yendang", 6935539, "alv-lni", } m["alv-nal"] = { "Nalu", nil, "alv-sng", } m["alv-nce"] = { "North-Central Edoid", 16110869, "alv-edo", } m["alv-ngb"] = { "Nupe-Gbagyi", 12638649, "alv-nup", aliases = {"Nupe-Gbari"}, } m["alv-ntg"] = { "Na-Togo", nil, "alv-gtm", } m["alv-nup"] = { "Nupoid", 1429143, "alv-von", } m["alv-nwd"] = { "Northwestern Edoid", 16111012, "alv-edo", } m["alv-nyn"] = { "Nyun", nil, "alv-fwo", } m["alv-pap"] = { "Papel", 7132562, "alv-bak", } m["alv-pph"] = { "Phla-Pherá", 3849625, "alv-gbe", } m["alv-ptn"] = { "Potou-Tano", 1475003, "alv-kwa", } m["alv-sav"] = { "Savanna", 4403672, "nic-vco", aliases = {"Savannas"}, } m["alv-sma"] = { "Supyire-Mamara", 4446348, "alv-snf", aliases = {"Suppire-Mamara"}, } m["alv-snf"] = { "Senufo", 33795, "alv", aliases = {"Senufic", "Senoufo", "Sénoufo"}, } m["alv-sng"] = { "Senegambian", 1708753, "alv", } m["alv-snr"] = { "Senari", 4416084, "alv-snf", } m["alv-swd"] = { "Southwestern Edoid", 12633903, "alv-edo", } m["alv-tal"] = { "Talodi", 12643302, "alv-the", } m["alv-tdj"] = { "Tagwana-Djimini", 7675362, "alv-snf", } m["alv-ten"] = { "Tenda", 3217535, "alv-fwo", } m["alv-the"] = { "Talodi-Heiban", 1521145, "alv", } m["alv-von"] = { "Volta-Niger", 34177, "nic-vco", } m["alv-wan"] = { "Wara-Natyoro", 7968830, "alv-sav", } m["alv-wjk"] = { "Waja-Kam", nil, "alv-ada", } m["alv-yek"] = { "Yekhee", nil, "alv-nce", } m["alv-yor"] = { "Yoruba", nil, "alv-edk", } m["alv-yrd"] = { "Yoruboid", 1789745, "alv-von", } m["alv-yun"] = { "Yungur", 84601642, "alv-bam", aliases = {"Bena-Mboi"}, } m["apa"] = { "Apachean", 27758, "ath", aliases = {"Southern Athabaskan"}, } m["aqa"] = { "Alacalufan", 1288430, } m["aql"] = { "Algic", 721612, aliases = {"Algonquian-Ritwan", "Algonquian-Wiyot-Yurok"}, } m["art"] = { "constructed", 33215, "qfa-not", aliases = {"artificial", "planned"}, } m["ath"] = { "Athabaskan", 27475, "xnd", } m["ath-nor"] = { "North Athabaskan", 20738, "ath", aliases = {"Northern Athabaskan"}, } m["ath-pco"] = { "Pacific Coast Athabaskan", 20654, "ath", } m["auf"] = { "Arauan", 626772, aliases = {"Arahuan", "Arauán", "Arawa", "Arawan", "Arawán"}, } --[=[ Exceptional language and family codes for Australian Aboriginal languages can use the prefix "aus-", though "aus" is no longer itself a family code. ]=]-- m["aus-arn"] = { "Arnhem", 2581700, aliases = {"Gunwinyguan", "Macro-Gunwinyguan"}, } m["aus-bub"] = { "Bunuban", 2495148, aliases = {"Bunaban"}, } m["aus-cww"] = { "Central New South Wales", 5061507, "aus-pam", } m["aus-dal"] = { "Daly", 2478079, } m["aus-dyb"] = { "Dyirbalic", 1850666, "aus-pam", } m["aus-gar"] = { "Garawan", 5521951, } m["aus-gun"] = { "Gunwinyguan", 2581700, "aus-arn", aliases = {"Gunwingguan"}, } m["aus-jar"] = { "Jarrakan", 2039423, } m["aus-kar"] = { "Karnic", 4215578, "aus-pam", } m["aus-mir"] = { "Mirndi", 4294095, } m["aus-nga"] = { "Ngayarda", 16153490, "aus-psw", } m["aus-nyu"] = { "Nyulnyulan", 2039408, } m["aus-pam"] = { "Pama-Nyungan", 33942, } m["aus-pmn"] = { "Paman", 2640654, "aus-pam", } m["aus-psw"] = { "Southwest Pama-Nyungan", 2258160, "aus-pam", } m["aus-rnd"] = { "Arandic", 4784071, "aus-pam", } m["aus-tnk"] = { "Tangkic", 1823065, } m["aus-wdj"] = { "Iwaidjan", 4196968, aliases = {"Yiwaidjan"}, } m["aus-wor"] = { "Worrorran", 2038619, } m["aus-yid"] = { "Yidinyic", 4205849, "aus-pam", } m["aus-yng"] = { "Yangmanic", 42727644, } m["aus-yol"] = { "Yolngu", 2511254, "aus-pam", aliases = {"Yolŋu", "Yolngu Matha"}, } m["aus-yuk"] = { "Yuin-Kuric", 3833021, "aus-pam", } m["awd"] = { "Arawak", 626753, aliases = {"Arawakan", "Maipurean", "Maipuran"}, } m["awd-nwk"] = { "Nawiki", nil, "awd", aliases = {"Newiki"}, } m["awd-taa"] = { "Ta-Arawak", 7672731, "awd", aliases = {"Ta-Arawakan", "Ta-Maipurean"}, } m["azc"] = { "Uto-Aztecan", 34073, aliases = {"Uto-Aztekan"}, } m["azc-cup"] = { "Cupan", 19866871, "azc-tak", } m["azc-dur"] = { "Durango Nahuatl", 2386361, "azc-nah", aliases = {"Mexicanero"} } m["azc-hua"] = { "Huasteca Nahuatl", 3832950, "azc-nah", } m["azc-nah"] = { "Nahuan", 11965602, "azc", aliases = {"Aztecan"}, } m["azc-num"] = { "Numic", 2657541, "azc", } m["azc-pim"] = { "Piman", 7194600, "azc", aliases = {"Tepiman"}, } m["azc-tak"] = { "Takic", 1280305, "azc", } m["azc-trc"] = { "Taracahitic", 4245032, "azc", aliases = {"Taracahitan"}, } m["bad"] = { "Banda", 806234, "nic-ubg", } m["bad-cnt"] = { "Central Banda", 3438391, "bad", } m["bai"] = { "Bamileke", 806005, "nic-gre", } m["bat"] = { "Baltic", 33136, "ine-bsl", } m["bat-eas"] = { "East Baltic", 149944, "bat", } m["bat-wes"] = { "West Baltic", 149946, "bat", } m["ber"] = { "Berber", 25448, "afa", aliases = {"Tamazight"}, } m["bnt"] = { "Bantu", 33146, "nic-bds", } m["bnt-baf"] = { "Bafia", 799784, "bnt", } m["bnt-bbo"] = { "Bafo-Bonkeng", nil, "bnt-saw", } m["bnt-bdz"] = { "Boma-Dzing", 1729203, "bnt", } m["bnt-bek"] = { "Bekwilic", nil, "bnt-ndb", } m["bnt-bki"] = { "Bena-Kinga", 16113307, "bnt-bne", } m["bnt-bmo"] = { "Bangi-Moi", nil, "bnt-bnm", } m["bnt-bne"] = { "Northeast Bantu", 7057832, "bnt", } m["bnt-bnm"] = { "Bangi-Ntomba", 806477, "bnt-bte", } m["bnt-boa"] = { "Boan", 4931250, "bnt", aliases = {"Buan", "Ababuan"}, } m["bnt-bot"] = { "Botatwe", 4948532, "bnt", } m["bnt-bsa"] = { "Basaa", 809739, "bnt", } m["bnt-bsh"] = { "Bushoong", 5001551, "bnt-bte", } m["bnt-bso"] = { "Southern Bantu", 980498, "bnt", } m["bnt-bta"] = { "Bati-Angba", 4869303, "bnt-boa", other_names = {"Late Bomokandian"}, aliases = {"Bwa"}, } m["bnt-btb"] = { "Beti", 35118, "bnt", } m["bnt-bte"] = { "Bangi-Tetela", 4855181, "bnt", } m["bnt-bun"] = { "Buja-Ngombe", 4986733, "bnt-mbb", } m["bnt-chg"] = { "Chaga", 33016, "bnt-cht", } m["bnt-cht"] = { "Chaga-Taita", nil, "bnt-bne", } m["bnt-clu"] = { "Chokwe-Luchazi", 3339273, "bnt", } m["bnt-com"] = { "Comorian", 33077, "bnt-sab", } m["bnt-glb"] = { "Great Lakes Bantu", 5599420, "bnt-bne", } m["bnt-haj"] = { "Haya-Jita", 25502360, "bnt-glb", } m["bnt-kak"] = { "Kako", nil, "bnt-pob", } m["bnt-kav"] = { "Kavango", 116544179, "bnt-ksb", } m["bnt-kbi"] = { "Komo-Bira", 6428591, "bnt-boa", } m["bnt-kel"] = { "Kele", 1738162, "bnt-kts", aliases = {"Sheke"}, } m["bnt-kil"] = { "Kilombero", 6408121, "bnt", } m["bnt-kka"] = { "Kikuyu-Kamba", 16114410, "bnt-bne", aliases = {"Thagiicu"}, } m["bnt-kmb"] = { "Kimbundu", 16947687, "bnt", } m["bnt-kng"] = { "Kongo", 6429214, "bnt", } m["bnt-kpw"] = { "Kpwe", 36428, "bnt-saw", } m["bnt-ksb"] = { "Kavango-Southwest Bantu", 6379098, "bnt", } m["bnt-kts"] = { "Kele-Tsogo", 6385577, "bnt", } m["bnt-lbn"] = { "Luban", 4536504, "bnt", } m["bnt-leb"] = { "Lebonya", 6511395, "bnt", } m["bnt-lgb"] = { "Lega-Binja", 6517694, "bnt", } m["bnt-lok"] = { "Logooli-Kuria", nil, "bnt-glb", } m["bnt-lub"] = { "Luba", nil, "bnt-lbn", } m["bnt-lun"] = { "Lunda", 6704091, "bnt", } m["bnt-mak"] = { "Makua", 6740431, "bnt-bso", aliases = {"Makhuwa"}, } m["bnt-mbb"] = { "Mboshi-Buja", 6799764, "bnt", } m["bnt-mbe"] = { "Mbole-Enya", 6799728, "bnt", } m["bnt-mbi"] = { "Mbinga", nil, "bnt-rur", } m["bnt-mbo"] = { "Mboshi", 6799763, "bnt-mbb", } m["bnt-mbt"] = { "Mbete", 1346910, "bnt-tmb", aliases = {"Mbere"}, } m["bnt-mby"] = { "Mbeya", nil, "bnt-ruk", } m["bnt-mij"] = { "Mijikenda", 6845474, "bnt-sab", } m["bnt-mka"] = { "Makaa", nil, "bnt-ndb", } m["bnt-mne"] = { "Manenguba", 31147471, "bnt", aliases = {"Mbo", "Ngoe"}, } m["bnt-mnj"] = { "Makaa-Njem", 1603899, "bnt-pob", } m["bnt-mon"] = { "Mongo", nil, "bnt-bnm", } m["bnt-mra"] = { "Mbugwe-Rangi", 6799795, "bnt", } m["bnt-msl"] = { "Masaba-Luhya", 12636428, "bnt-glb", } m["bnt-mwi"] = { "Mwika", nil, "bnt-ruk", } m["bnt-ncb"] = { "Northeast Coast Bantu", 7057848, "bnt-bne", } m["bnt-ndb"] = { "Ndzem-Bomwali", nil, "bnt-mnj", } m["bnt-ngn"] = { "Ngondi-Ngiri", 7022532, "bnt-mbb", } m["bnt-ngu"] = { "Nguni", 961559, "bnt-bso", aliases = {"Ngoni"}, } m["bnt-nya"] = { "Nyali", 7070832, "bnt-leb", } m["bnt-nyb"] = { "Nyanga-Buyi", 7070882, "bnt", } m["bnt-nyg"] = { "Nyoro-Ganda", 12638666, "bnt-glb", } m["bnt-nys"] = { "Nyasa", 7070921, "bnt", } m["bnt-nze"] = { "Nzebi", 1755498, "bnt-tmb", aliases = {"Njebi"}, } m["bnt-ova"] = { "Ovambo", 36489, "bnt-swb", aliases = {"Oshivambo", "Oshiwambo", "Owambo"}, } m["bnt-par"] = { "Pare", nil, "bnt-ncb", } m["bnt-pen"] = { "Pende", 7162373, "bnt", } m["bnt-pob"] = { "Pomo-Bomwali", nil, "bnt", } m["bnt-ruk"] = { "Rukwa", 7378902, "bnt", } m["bnt-run"] = { "Rungwe", nil, "bnt-ruk", } m["bnt-rur"] = { "Rufiji-Ruvuma", 7377947, "bnt", } m["bnt-ruv"] = { "Ruvu", nil, "bnt-ncb", } m["bnt-rvm"] = { "Ruvuma", nil, "bnt-rur", } m["bnt-sab"] = { "Sabaki", 2209395, "bnt-ncb", } m["bnt-saw"] = { "Sawabantu", 532003, "bnt", } m["bnt-sbi"] = { "Sabi", 7396071, "bnt", } m["bnt-seu"] = { "Seuta", nil, "bnt-ncb", } m["bnt-shh"] = { "Shi-Havu", nil, "bnt-glb", } m["bnt-sho"] = { "Shona", 2904660, "bnt", } m["bnt-sir"] = { "Sira", 1436372, "bnt", aliases = {"Shira-Punu"}, } m["bnt-ske"] = { "Soko-Kele", nil, "bnt-bte", } m["bnt-sna"] = { "Sena", nil, "bnt-nys", } m["bnt-sts"] = { "Sotho-Tswana", 2038386, "bnt-bso", } m["bnt-swb"] = { "Southwest Bantu", 116543539, "bnt-ksb", } m["bnt-swh"] = { "Swahili", nil, "bnt-sab", } m["bnt-tek"] = { "Teke", 36528, "bnt-tmb", } m["bnt-tet"] = { "Tetela", 7706059, "bnt-bte", } m["bnt-tkc"] = { "Central Teke", 36473, "bnt-tek", } m["bnt-tkm"] = { "Takama", nil, "bnt-bne", } m["bnt-tmb"] = { "Teke-Mbede", 7695332, "bnt", aliases = {"Teke-Mbere"}, } m["bnt-tso"] = { "Tsogo", 2458420, other_names = {"Okani"}, --appears to be an alias in Glottolog "bnt-kts", } m["bnt-tsr"] = { "Tswa-Ronga", 12643962, "bnt-bso", } m["bnt-yak"] = { "Yaka", 8047027, "bnt", } m["bnt-yko"] = { "Yasa-Kombe", nil, "bnt-saw", } m["bnt-zbi"] = { "Zamba-Binza", nil, "bnt-bnm", } m["btk"] = { "Batak", 1998595, "poz-nws", } --[=[ Exceptional language and family codes for Central American Indian languages may use the prefix "cai-", though "cai" is no longer itself a family code. ]=]-- --[=[ Exceptional language and family codes for Caucasian languages can use the prefix "cau-", though "cau" is no longer itself a family code. ]=]-- m["cau-abz"] = { "Abkhaz-Abaza", 4663617, "cau-nwc", other_names = {"Abkhaz-Tapanta"}, aliases = {"Abazgi"}, } m["cau-and"] = { "Andian", 492152, "cau-ava", aliases = {"Andic"}, } m["cau-ava"] = { "Avaro-Andian", 4055404, "cau-nec", aliases = {"Avar-Andian", "Avar-Andi", "Avar-Andic"}, } m["cau-cir"] = { "Circassian", 858543, "cau-nwc", aliases = {"Cherkess"}, } m["cau-drg"] = { "Dargwa", 5222637, "cau-nec", other_names = {"Dargin"}, } m["cau-esm"] = { "Eastern Samur", nil, "cau-sam", } m["cau-ets"] = { "East Tsezian", 121437666, "cau-tsz", aliases = {"East Tsezic", "East Didoic"}, } m["cau-lzg"] = { "Lezghian", 2144370, "cau-nec", aliases = {"Lezgi", "Lezgian", "Lezgic"}, } m["cau-nkh"] = { "Nakh", 24441, "cau-nec", aliases = {"North-Central Caucasian"}, } m["cau-nec"] = { "Northeast Caucasian", 27387, aliases = {"Dagestanian", "Nakho-Dagestanian", "Caspian"}, } m["cau-nwc"] = { "Northwest Caucasian", 33852, aliases = {"Abkhazo-Adyghean", "Abkhaz-Adyghe", "Pontic"}, } m["cau-sam"] = { "Samur", 15229151, "cau-lzg", } m["cau-ssm"] = { "Southern Samur", nil, "cau-sam", } m["cau-tsz"] = { "Tsezian", 1651530, "cau-nec", aliases = {"Tsezic", "Didoic"}, } m["cau-vay"] = { "Vainakh", 4102486, "cau-nkh", aliases = {"Veinakh", "Vaynakh"}, } m["cau-wsm"] = { "Western Samur", nil, "cau-sam", } m["cau-wts"] = { "West Tsezian", 121437697, "cau-tsz", aliases = {"West Tsezic", "West Didoic"}, } m["cba"] = { "Chibchan", 520478, "qfa-mch", -- or none if Macro-Chibchan is considered undemonstrated } m["ccs"] = { "Kartvelian", 34030, aliases = {"South Caucasian"}, } m["ccs-gzn"] = { "Georgian-Zan", 34030, "ccs", aliases = {"Karto-Zan"}, } m["ccs-zan"] = { "Zan", 2606912, "ccs-gzn", aliases = {"Zanuri", "Colchian"}, } m["cdc"] = { "Chadic", 33184, "afa", } m["cdc-cbm"] = { "Central Chadic", 2251547, "cdc", aliases = {"Biu-Mandara"}, } m["cdc-est"] = { "East Chadic", 2276221, "cdc", } m["cdc-mas"] = { "Masa", 2136092, "cdc", } m["cdc-wst"] = { "West Chadic", 2447774, "cdc", } m["cdd"] = { "Caddoan", 1025090, } m["cel"] = { "Celtic", 25293, "ine", } m["cel-bry"] = { "Brythonic", 156877, "cel-ins", aliases = {"Brittonic"}, } m["cel-brs"] = { "Southwestern Brythonic", 2612853, "cel-bry", aliases = {"Southwestern Brittonic"}, } m["cel-brw"] = { "Western Brythonic", 593069, "cel-bry", aliases = {"Western Brittonic"}, } m["cel-gae"] = { "Goidelic", 56433, "cel-ins", aliases = {"Gaelic"}, protoLanguage = "pgl", } m["cel-his"] = { "Hispano-Celtic", 4204136, "cel", } m["cel-ins"] = { "Insular Celtic", 214506, "cel", } m["chi"] = { "Chimakuan", 1073088, } m["chm"] = { "Mari", 973685, "urj", } m["cmc"] = { "Chamic", 2997506, "poz-mcm", } m["crp"] = { "creole or pidgin", 19682167, "qfa-cnt", } m["csu"] = { "Central Sudanic", 190822, "ssa", } m["csu-bba"] = { "Bongo-Bagirmi", 3505042, "csu", } m["csu-bbk"] = { "Bongo-Baka", 4941917, "csu-bba", } m["csu-bgr"] = { "Bagirmi", 4841948, "csu-bba", aliases = {"Bagirmic"}, } m["csu-bkr"] = { "Birri-Kresh", nil, "csu", } m["csu-ecs"] = { "Eastern Central Sudanic", 16911698, "csu", aliases = {"East Central Sudanic", "Central Sudanic East", "Lendu-Mangbetu"}, } m["csu-kab"] = { "Kaba", 6343715, "csu-bba", } m["csu-lnd"] = { "Lendu", 6522357, "csu-ecs", aliases = {"Lenduic"}, } m["csu-maa"] = { "Mangbetu", 6748874, "csu-ecs", aliases = {"Mangbetu-Asoa", "Mangbetu-Asua"}, } m["csu-mle"] = { "Mangbutu-Lese", 17009406, "csu-ecs", aliases = {"Mangbutu-Efe", "Mangbutu", "Membi-Mangbutu-Efe"}, } m["csu-mma"] = { "Moru-Madi", 6915156, "csu-ecs", } m["csu-sar"] = { "Sara", 2036691, "csu-bba", } m["csu-val"] = { "Vale", 7909520, "csu-bba", } m["cus"] = { "Cushitic", 33248, "afa", } m["cus-cen"] = { "Central Cushitic", 56569, "cus", } m["cus-eas"] = { "East Cushitic", 56568, "cus", } m["cus-hec"] = { "Highland East Cushitic", 56524, "cus-eas", } m["cus-som"] = { "Somaloid", 56774, "cus-eas", aliases = {"Sam", "Macro-Somali"}, } m["cus-sou"] = { "South Cushitic", 56525, "cus", } m["day"] = { "Land Dayak", 2760613, "poz", } m["del"] = { "Lenape", 2665761, "alg-eas", aliases = {"Delaware"}, } m["den"] = { "Slavey", 13272, "ath-nor", aliases = {"Slave", "Slavé"}, } m["dmn"] = { "Mande", 33681, "nic", } m["dmn-bbu"] = { "Bisa-Busa", 12627956, "dmn-mde", } m["dmn-emn"] = { "East Manding", nil, "dmn-man", } m["dmn-jje"] = { "Jogo-Jeri", nil, "dmn-mjo", } m["dmn-man"] = { "Manding", 35772, "dmn-mmo", } m["dmn-mda"] = { "Mano-Dan", nil, "dmn-mse", } m["dmn-mdc"] = { "Central Mande", 5972907, "dmn-mdw", } m["dmn-mde"] = { "Eastern Mande", 12633080, "dmn", } m["dmn-mdw"] = { "Western Mande", 16113831, "dmn", } m["dmn-mjo"] = { "Manding-Jogo", 12636153, "dmn-mdc", } m["dmn-mmo"] = { "Manding-Mokole", nil, "dmn-mva", } m["dmn-mnk"] = { "Maninka", 36186, "dmn-emn", } m["dmn-mnw"] = { "Northwestern Mande", 5972910, "dmn-mdw", } m["dmn-mok"] = { "Mokole", 16935447, "dmn-mmo", } m["dmn-mse"] = { "Southeastern Mande", 5972912, "dmn-mde", } m["dmn-msw"] = { "Southwestern Mande", 12633904, "dmn-mdw", } m["dmn-mva"] = { "Manding-Vai", nil, "dmn-mjo", } m["dmn-nbe"] = { "Nwa-Beng", nil, "dmn-mse", } m["dmn-sam"] = { "Samo", 36327, "dmn-bbu", aliases = {"Samuic"}, } m["dmn-smg"] = { "Samogo", 7410000, "dmn-mnw", aliases = {"Duun-Seenku"}, } m["dmn-snb"] = { "Soninke-Bobo", 16111680, "dmn-mnw", } m["dmn-sya"] = { "Susu-Yalunka", nil, "dmn-mdc", } m["dmn-vak"] = { "Vai-Kono", nil, "dmn-mva", } m["dmn-wmn"] = { "West Manding", nil, "dmn-man", } m["dra"] = { "Dravidian", 33311, } m["dra-cen"] = { "Central Dravidian", 12628823, "dra", } m["dra-gki"] = { "Gondi-Kui", 12631610, "dra-sdt", } m["dra-gon"] = { "Gondi", 55639812, "dra-gki", } m["dra-imd"] = { "Irula-Muduga", nil, "dra-tkn", } m["dra-kan"] = { "Kannadoid", 6363888, "dra-tkn", protoLanguage = "dra-okn", } m["dra-kki"] = { "Konda-Kui", nil, "dra-gki", } m["dra-kml"] = { "Kurux-Malto", 68002822, "dra-nor", } m["dra-knk"] = { "Kolami-Naiki", 10547037, "dra-cen", } m["dra-kod"] = { "Kodagu", 67983106, "dra-tkd", } m["dra-kor"] = { "Koraga", 33394, "dra-tlk", } m["dra-mal"] = { "Malayalamoid", 6741581, "dra-tml", } m["dra-mdy"] = { "Madiya", 27602, "dra-gon", } m["dra-mlo"] = { "Malto", nil, "dra-kml", } m["dra-mur"] = { "Muria", 6938499, "dra-gon", } m["dra-nor"] = { "North Dravidian", 16110967, "dra", } m["dra-pgd"] = { "Parji-Gadaba", 10620428, "dra-cen", } m["dra-sdo"] = { "South Dravidian I", 16112843, -- Wikipedia's "South Dravidian" is South Dravidian I in this scheme. "dra-sou", aliases = {"South Dravidian"}, -- This is why I and II are used. } m["dra-sdt"] = { "South Dravidian II", 12633975, "dra-sou", aliases = {"South-Central Dravidian"}, } m["dra-sou"] = { "South Dravidian", 128886618, "dra", aliases = {"Southern Dravidian"}, } m["dra-tam"] = { "Tamiloid", 7681417, "dra-tml", protoLanguage = "oty", } m["dra-tel"] = { "Teluguic", nil, "dra-sdt", protoLanguage = "dra-ote", } m["dra-tkd"] = { "Tamil-Kodagu", 25494510, "dra-tkn", } m["dra-tkn"] = { "Tamil-Kannada", 6478506, "dra-sdo", } m["dra-tkt"] = { "Toda-Kota", 67983857, "dra-tkd", } m["dra-tlk"] = { "Tulu-Koraga", nil, "dra-sdo", } m["dra-tml"] = { "Tamil-Malayalam", 10690507, "dra-tkd", } m["egx"] = { "Egyptian", 50868, "afa", protoLanguage = "egy", } m["ero"] = { "Horpa", 56854, "sit-wgy", } m["esx"] = { "Eskimo-Aleut", 25946, } m["esx-esk"] = { "Eskimo", 25946, "esx", } m["esx-inu"] = { "Inuit", 27796, "esx-esk", } m["euq"] = { "Vasconic", 4669240, } m["gba"] = { "Gbaya", 3099986, "alv-sav", } m["gba-eas"] = { "Eastern Gbaya", nil, "gba", } m["gba-sou"] = { "Southern Gbaya", nil, "gba", } m["gba-wes"] = { "Western Gbaya", nil, "gba", } m["gem"] = { "Germanic", 21200, "ine", } m["gio"] = { "Gelao", 56401, "qfa-kra", } m["gme"] = { "East Germanic", 108662, "gem", } m["gmq"] = { "North Germanic", 106085, "gem", } m["gmq-eas"] = { "East Scandinavian", 3090263, "gmq", protoLanguage = "non-oen", } m["gmq-ins"] = { "Insular Scandinavian", nil, "gmq-wes", } m["gmq-wes"] = { "West Scandinavian", 1792570, "gmq", protoLanguage = "non-own", } m["gmw"] = { "West Germanic", 26721, "gem", } m["gmw-afr"] = { "Anglo-Frisian", 5329170, "gmw-nsg", } m["gmw-ang"] = { "Anglic", 1346342, "gmw-afr", protoLanguage = "ang", } m["gmw-fri"] = { "Frisian", 25325, "gmw-afr", protoLanguage = "ofs", } m["gmw-frk"] = { "Low Franconian", 153050, "gmw", protoLanguage = "frk", } m["gmw-hgm"] = { "High German", 52040, "gmw", protoLanguage = "goh", } m["gmw-ian"] = { "Irish Anglo-Norman", 120719384, "gmw-ang", protoLanguage = "enm", } m["gmw-lgm"] = { "Low German", 25433, "gmw-nsg", protoLanguage = "osx", } m["gmw-nsg"] = { "North Sea Germanic", 30134, "gmw", aliases = {"Ingvaeonic"}, } m["gn"] = { "Guarani", 35876, "tup-gua", aliases = {"Guaraní"}, } m["grb"] = { "Grebo proper", 35257, "kro-grb", } m["grk"] = { "Hellenic", 2042538, "ine", aliases = {"Greek"}, } m["him"] = { "Western Pahari", 10939493, "inc-pah", aliases = {"Himachali"}, } m["hmn"] = { "Hmongic", 3307894, "hmx", } m["hmx"] = { "Hmong-Mien", 33322, aliases = {"Miao-Yao"}, } m["hmx-mie"] = { "Mienic", 7992695, "hmx", } m["hok"] = { "Hokan", 33406, } m["hyx"] = { "Armenian", 8785, "ine", } m["iir"] = { "Indo-Iranian", 33514, "ine", } m["iir-nur"] = { "Nuristani", 161804, "iir", } m["nur-nor"] = { "Northern Nuristani", nil, "iir-nur", } m["nur-sou"] = { "Southern Nuristani", nil, "iir-nur", } m["ijo"] = { "Ijoid", 1325759, "nic", other_names = {"Ijaw"}, -- Ijaw may be a subfamily } m["inc"] = { "Indo-Aryan", 33577, "iir", aliases = {"Indic"}, } m["inc-bas"] = { "Bengali-Assamese", 4179137, "inc-eas", aliases = {"Assamese-Bengali", "Gauda-Kamarupa"}, } m["inc-bhi"] = { "Bhil", 4901727, "inc-cen", } m["inc-bih"] = { "Bihari", 135305, "inc-eas", } m["inc-cen"] = { "Central Indo-Aryan", 10979187, "inc", protoLanguage = "inc-asa", } m["inc-chi"] = { "Chitrali", 11732797, "inc-dar", } m["inc-dar"] = { "Dardic", 161101, "inc", protoLanguage = "inc-ash", } m["inc-dre"] = { "Eastern Dardic", nil, "inc-dar", } m["inc-dng"] = { "Dangari", nil, "inc-shn", } m["inc-eas"] = { "Eastern Indo-Aryan", 12593391, "inc", protoLanguage = "inc-aav", } m["inc-hal"] = { "Halbic", 16910593, "inc-eas", aliases = {"Halbi"}, } m["inc-hie"] = { "Eastern Hindi", 4126648, "inc-cen", aliases = {"Purabiyā"}, protoLanguage = "inc-apa", } m["inc-hiw"] = { "Western Hindi", 12600937, "inc-cen", protoLanguage = "inc-ohi", } m["inc-hnd"] = { "Hindustani", 11051, "inc-hiw", aliases = {"Hindi-Urdu"}, protoLanguage = "hi-mid", } m["inc-ins"] = { "Insular Indo-Aryan", 12179302, "inc", protoLanguage = "inc-apa", } m["inc-kas"] = { "Kashmiric", nil, "inc-dre", aliases = {"Kashmiri"}, } m["inc-koh"] = { "Kohistani", 13018610, "inc-dre", } m["inc-krd"] = { "KRDS languages", 6356154, "inc-eas", aliases = {"Kamta, Rajbanshi, Deshi and Surjapuri", "KRNB languages", "Kamta, Rajbanshi and Northern Deshi Bangla"}, } m["inc-kun"] = { "Kunar", nil, "inc-dar", } m["inc-mid"] = { "Middle Indo-Aryan", 3236316, "inc", aliases = {"Middle Indic"}, } m["inc-nwe"] = { "Northwestern Indo-Aryan", 16111018, "inc", protoLanguage = "inc-apa", } m["inc-nor"] = { "Northern Indo-Aryan", 946077, "inc", protoLanguage = "inc-aka", } m["inc-old"] = { "Old Indo-Aryan", 118976896, "inc", aliases = {"Old Indic"}, } m["inc-pah"] = { "Pahari", 946077, "inc-nor", aliases = {"Pahadi"}, protoLanguage = "inc-aka", } m["inc-pan"] = { "Punjabic", 2656685, "inc-nwe", aliases = {"Greater Punjabic"}, protoLanguage = "inc-opa", } m["inc-pas"] = { "Pashayi", 36670, "inc-dar", aliases = {"Pashai"}, } m["inc-rom"] = { "Romani", 13201, "inc-wes", aliases = {"Romany", "Gypsy", "Gipsy"}, } m["inc-shn"] = { "Shinaic", 12646125, "inc-dre", } m["inc-snd"] = { "Sindhic", 7522212, "inc-nwe", protoLanguage = "inc-avr", } m["inc-sou"] = { "Southern Indo-Aryan", 10856062, "inc", protoLanguage = "inc-ama", } m["inc-tha"] = { "Tharu", 34035, "inc-eas", } m["inc-wes"] = { "Western Indo-Aryan", nil, "inc", protoLanguage = "inc-agu", } m["ine"] = { "Indo-European", 19860, aliases = {"Indo-Germanic"}, } m["ine-ana"] = { "Anatolian", 147085, "ine", } m["ine-bsl"] = { "Balto-Slavic", 147356, "ine", } m["ine-toc"] = { "Tocharian", 37029, "ine", aliases = {"Tokharian"}, } m["ira"] = { "Iranian", 33527, "iir", } m["ira-csp"] = { "Caspian", 5049123, "ira-mpr", } m["ira-cen"] = { "Central Iranian", nil, "ira", } m["ira-kms"] = { "Komisenian", nil, "ira-mpr", aliases = {"Semnani"}, } m["ine-luw"] = { "Luwic", 115748615, "ine-ana", aliases = {"Luvic"}, } m["ira-mid"] = { "Middle Iranian", 6841465, "ira", } m["ira-mny"] = { "Munji-Yidgha", nil, "ira-sym", aliases = {"Yidgha-Munji"}, } m["ira-msh"] = { "Mazanderani-Shahmirzadi", nil, "ira-csp", } m["ira-nei"] = { "Northeastern Iranian", 10775567, "ira", } m["ira-nwi"] = { "Northwestern Iranian", 390576, "ira-wes", } m["ira-old"] = { "Old Iranian", 23301845, "ira", } m["ira-orp"] = { "Ormuri-Parachi", nil, "ira-sei", } m["ira-pat"] = { "Pathan", nil, "ira-sei", } m["ira-sbc"] = { "Sogdo-Bactrian", nil, "ira-nei", } m["ira-mpr"] = { "Medo-Parthian", nil, "ira-nwi", aliases = {"Partho-Median"}, } m["ira-sgi"] = { "Sanglechi-Ishkashimi", 18711232, "ira-sei", } m["ira-shr"] = { "Shughni-Roshani", 11732824, "ira-shy", } m["ira-shy"] = { "Shughni-Yazghulami", nil, "ira-sym", } m["ira-sgc"] = { "Sogdic", nil, "ira-sbc", aliases = {"Sogdian"}, } m["ira-sei"] = { "Southeastern Iranian", 3833002, "ira", } m["ira-swi"] = { "Southwestern Iranian", 390424, "ira-wes", } m["ira-sym"] = { "Shughni-Yazghulami-Munji", nil, "ira-sei", } m["ira-wes"] = { "Western Iranian", 129850, "ira", } m["ira-zgr"] = { "Zaza-Gorani", 167854, "ira-mpr", aliases = {"Zaza-Gurani", "Gorani-Zaza"}, } m["iro"] = { "Iroquoian", 33623, } m["iro-nor"] = { "North Iroquoian", nil, "iro", } m["itc"] = { "Italic", 131848, "ine", } m["itc-laf"] = { "Latino-Faliscan", 33478, "itc", aliases = {"Latinian"}, } m["itc-sbl"] = { "Osco-Umbrian", 515194, "itc", aliases = {"Sabellic", "Sabellian"}, } m["jpx"] = { "Japonic", 33612, aliases = {"Japanese", "Japanese-Ryukyuan"}, } m["jpx-nry"] = { "Northern Ryukyuan", 20862796, "jpx-ryu", } m["jpx-ryu"] = { "Ryukyuan", 56393, "jpx", } m["jpx-sry"] = { "Southern Ryukyuan", 18392243, "jpx-ryu", } m["kar"] = { "Karen", 1364815, "sit", } m["kca"] = { "Khanty", 33563, "urj-ugr", aliases = {"Khantyic", "Khantic"}, } --[=[ Exceptional language and family codes for Khoisan and Kordofanian languages can use the prefix "khi-" and "kdo-" respectively, though they are no longer family codes themselves. ]=]-- m["khi-kal"] = { "Kalahari Khoe", nil, "khi-kho", } m["khi-khk"] = { "Khoekhoe", nil, "khi-kho", } m["khi-kkw"] = { "Khoe-Kwadi", 60785084, aliases = {"Kwadi-Khoe"}, } m["khi-kho"] = { "Khoe", 2736449, "khi-kkw", aliases = {"Central Khoisan"}, } m["khi-kxa"] = { "Kx'a", 6450587, aliases = {"Kxa", "Ju-ǂHoan"}, } m["khi-tuu"] = { "Tuu", 631046, aliases = {"Kwi", "Taa-Kwi", "Southern Khoisan", "Taa-ǃKwi", "Taa-ǃUi", "ǃUi-Taa"}, } m["kro"] = { "Kru", 33535, "nic-vco", } m["kro-aiz"] = { "Aizi", 4699431, "kro", } m["kro-bet"] = { "Bété", 32956, "kro-ekr", } m["kro-did"] = { "Dida", 32685, "kro-ekr", } m["kro-ekr"] = { "Eastern Kru", 5972899, "kro", } m["kro-grb"] = { "Grebo", 5601537, "kro-wkr", } m["kro-wee"] = { "Wee", nil, "kro-wkr", } m["kro-wkr"] = { "Western Kru", 5972897, "kro", } m["ku"] = { "Kurdish", 36368, "ira-nwi", } m["kv"] = { "Komi", 36126, -- "Komi language" in Wikipedia but refers specifically to Komi-Zyrian; no Wikidata item for Komi family "urj-prm", } m["map"] = { "Austronesian", 49228, } m["map-ata"] = { "Atayalic", 716610, "map", } m["mjg"] = { "Monguor", 34214, "xgn-shr", } m["mkh"] = { "Mon-Khmer", 33199, "aav", } m["mkh-asl"] = { "Aslian", 3111082, "mkh", } m["mkh-ban"] = { "Bahnaric", 56309, "mkh", } m["mkh-kat"] = { "Katuic", 56697, "mkh", } m["mkh-khm"] = { "Khmuic", 1323245, "mkh", } m["mkh-kmr"] = { "Khmeric", nil, "mkh", } m["mkh-mnc"] = { "Monic", 3217497, "mkh", } m["mkh-mng"] = { "Mangic", 3509556, "mkh", } m["mkh-nbn"] = { "North Bahnaric", 56309, "mkh-ban", } m["mkh-pal"] = { "Palaungic", 2391173, "mkh", } m["mkh-pea"] = { "Pearic", 3073022, "mkh", } m["mkh-pkn"] = { "Pakanic", nil, "mkh-mng", } m["mkh-vie"] = { "Vietic", 2355546, "mkh", } m["mno"] = { "Manobo", 3217483, "phi", } m["mns"] = { "Mansi", 33759, "urj-ugr", aliases = {"Mansic"}, } m["mun"] = { "Munda", 33892, "aav", } m["myn"] = { "Mayan", 33738, } --[=[ Exceptional language and family codes for North American Indian languages can use the prefix "nai-", though "nai" is no longer itself a family code. ]=]-- m["nai-cat"] = { "Catawban", 3446638, "nai-sca", } m["nai-chu"] = { "Chumashan", 1288420, } m["nai-ckn"] = { "Chinookan", 610586, } m["nai-coo"] = { "Coosan", 940278, } m["nai-jcq"] = { "Jicaquean", 12179308, "hok" } m["nai-ker"] = { "Keresan", 35878, } m["nai-klp"] = { "Kalapuyan", 1569040, } m["nai-kta"] = { "Kiowa-Tanoan", 386288, } m["nai-len"] = { "Lencan", 36189, aliases = {"Lenca"}, } m["nai-mdu"] = { "Maiduan", 33502, } m["nai-miz"] = { "Mixe-Zoquean", 954016, aliases = {"Mixe-Zoque"}, } m["nai-min"] = { "Misumalpan", 281693, "qfa-mch", aliases = {"Misuluan", "Misumalpa"}, } m["nai-mus"] = { "Muskogean", 902978, aliases = {"Muskhogean"}, } m["nai-pak"] = { "Pakawan", 65085487, "hok", } m["nai-pal"] = { "Palaihnihan", 1288332, } m["nai-plp"] = { "Plateau Penutian", 2307476, } m["nai-pom"] = { "Pomoan", 2618420, "hok", aliases = {"Pomo", "Kulanapan"}, } m["nai-sca"] = { "Siouan-Catawban", 34181, } m["nai-shp"] = { "Sahaptian", 114782, "nai-plp", } m["nai-shs"] = { "Shastan", 2991735, "hok", } m["nai-tot"] = { "Totozoquean", 7828419, } m["nai-ttn"] = { "Totonacan", 34039, aliases = {"Totonac-Tepehua", "Totonacan-Tepehuan"}, varieties = {"Totonac"}, } m["nai-tqn"] = { "Tequistlatecan", 1568317, "hok", aliases = {"Tequistlatec", "Chontal", "Chontalan", "Oaxacan Chontal", "Chontal of Oaxaca"}, } m["nai-tsi"] = { "Tsimshianic", 34134, } m["nai-utn"] = { "Utian", 13371763, "nai-you", aliases = {"Miwok-Costanoan", "Mutsun"}, } m["nai-wtq"] = { "Wintuan", 1294259, aliases = {"Wintun"}, } m["nai-xin"] = { "Xincan", 1546494, aliases = {"Xinca"}, } m["nai-ykn"] = { "Yukian", 2406722, aliases = {"Yuki-Wappo"}, } m["nai-you"] = { "Yok-Utian", 2886186, } m["nai-yuc"] = { "Yuman-Cochimí", 579137, } m["ngf"] = { "Trans-New Guinea", 34018, } m["ngf-ais"] = { "Aisian", nil, "ngf-eso", } m["ngf-ang"] = { "Angan", 3217366, "ngf", aliases = {"Kratke Range"}, -- Usher } m["ngf-ank"] = { "Angal-Kewa", 12626916, -- exist in dewiki and hrwiki "ngf-sak", } m["ngf-ask"] = { "Asmat-Kamoro", 3031400, "ngf", -- Wikipedia uses Asmat-Kamoro to refer to a narrower group excluding the Sabakor languages (Buruwai and Kamberau, -- which Glottolog splits into North Kamrau and South Kamrau [sic]), and uses Asmat-Kamrau to refer to what we and -- Glottolog call Asmat-Kamoro. Glottolog does not recognize the narrower grouping. aliases = {"Asmat-Kamrau", -- Wikipedia "Asmat-Kamrau Bay", -- Usher }, } m["ngf-asm"] = { "Asmat", 4807421, "ngf-ask", } m["ngf-ata"] = { "Ankave-Tainae-Akoye", nil, "ngf-ang", aliases = {"Southwest Kratke Range"}, -- Usher } m["ngf-awd"] = { "Awyu-Dumut", -- [[w:Awyu-Dumut languages]] redirects to [[w:Greater Awyu languages]] 4830163, -- exist in eswiki, hrwiki and ruwiki "ngf-gaw", aliases = {"Central Digul River"}, -- Usher } m["ngf-awy"] = { "Awyu", 96372866, "ngf-awd", } m["ngf-bda"] = { "Becking-Dawi", nil, -- Q55993716 ([[Category:Becking–Dawi languages]]) exists in enwiki "ngf-gaw", aliases = {"Becking and Dawi Rivers"}, -- Usher } m["ngf-bin"] = { "Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf-gbi", aliases = {"Oro"}, -- Usher (2020) } m["ngf-boa"] = { "Boane", nil, "ngf-era", aliases = {"Boana", -- Glottolog's name "Wain"}, -- not in Usher; "Wain" often excludes Mungkip, perhaps because it's poorly documented } m["ngf-bos"] = { "Bosavi", 4947122, "ngf", aliases = {"Papuan Plateau"}, -- alternative name given by Wikipedia } m["ngf-bsi"] = { "Baruya-Simbari", nil, "ngf-ang", aliases = {"Northwest Kratke Range"}, -- Usher } m["ngf-cda"] = { "Central Dani", nil, "ngf-dan", aliases = {"Dani"}, -- Usher } m["ngf-chw"] = { "Chimbu-Wahgi", 3217383, "ngf", aliases = {"Simbu-Western Highlands"}, -- alternative name given by Wikipedia } m["ngf-dag"] = { "Dagan", 5208454, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Meneao Range"}, } m["ngf-dal"] = { "Dallman", nil, "ngf-huo", aliases = {"Kinalakna-Kumukio", -- Pawley-Hammarström, who exclude Nomu, but they only had a numeral list of that language to work from "Northeast Huon", -- Usher }, } m["ngf-dan"] = { "Dani", 3217389, "ngf", -- Wikipedia renames the Dani languages to the Baliem Valley languages and sometimes (but not consistently) -- reserves the name Dani (or "Dani proper") for a narrower group excluding Wano and the poorly attested Ngalik -- languages (Nduga, Silimo, and the Yali dialect cluster, which we, following Ethnologue and Glottolog, split into -- Anggurk Yali, Ninia Yali and Pass Valley Yali). Glottolog does not recognize the narrower grouping. aliases = {"Baliem Valley", -- Wikipedia "Balim Valley", -- Usher }, } m["ngf-dum"] = { "Dumut", -- [[w:Dumut languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Wambon"}, -- Usher } m["ngf-ehu"] = { "Eastern Huon", -- Glottolog adds Ono and Sialum, Pawley-Hammarström adds Dedua 10567087, "ngf-huo", aliases = {"East Huon"}, -- Usher } m["ngf-eku"] = { "East Kutubuan", 5328752, "ngf", -- Not in TNG per Glottolog but accepted by all others. Sometimes grouped with Fasu to form a Kutubuan family. aliases = {"East Kutubu"}, -- Glottolog's name } m["ngf-enc"] = { "Engic", nil, "ngf-eng", aliases = {"Engan", -- Glottolog "Engan proper", -- Wikipedia "North Engan", -- alternative name given by Wikipedia "Trans-Enga", -- Usher }, } m["ngf-eng"] = { "Engan", 3217449, "ngf", aliases = {"Enga-Kewa-Huli", -- Glottolog, Pawley-Hammarström "Enga-Southern Highlands", -- Usher }, } m["ngf-era"] = { "Erap", nil, "ngf-fin", aliases = {"Erap River"}, -- Usher? } m["ngf-eso"] = { "East Sogeram", nil, "ngf-sog", } m["ngf-est"] = { "East Strickland", 5329440, "ngf", aliases = {"Strickland River"}, -- alternative name given by Wikipedia } m["ngf-eva"] = { "Evapia", nil, "ngf-rai", aliases = {"Evapia River"}, -- Usher } m["ngf-fgi"] = { "Fore-Gimi", nil, "ngf-gor", aliases = {"South Goroka"}, -- Usher } m["ngf-fhu"] = { "Finisterre-Huon", 3217453, "ngf", aliases = {"Finisterre Range-Huon Peninsula"}, -- per Usher } m["ngf-fin"] = { "Finisterre", 5450373, "ngf-fhu", aliases = {"Finisterre-Saruwaged", -- Glottolog's name "Finisterre Range"}, -- per Usher } m["ngf-gah"] = { "Gahuku", nil, "ngf-gor", aliases = {"Alekano-Asaro River"}, -- Usher } m["ngf-gau"] = { "Gauwa", nil, "ngf-kai", aliases = {"West Kainantu"}, -- Usher } m["ngf-gaw"] = { "Greater Awyu", 12627424, "ngf", aliases = {"Digul River"}, -- used by Usher (2020) } m["ngf-gbi"] = { "Greater Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf", -- not placed in Trans-New Guinea in Usher (2020) aliases = {"Guhu-Oro"}, -- Guhu-Oro is used in Usher (2020) } m["ngf-gko"] = { "Gaena-Korafe", 11732347, -- considered a single Korafe language by Wikipedia "ngf-bin", aliases = {"Gaina-Korafe"}, -- Usher } m["ngf-gmo"] = { "Gusap-Mot", 16110857, "ngf-fin", aliases = {"Mot River"}, -- Usher? } m["ngf-gor"] = { "Goroka", 15478597, "ngf-kgo", } m["ngf-gsu"] = { "Gogodala-Suki", 5577428, "ngf", -- Possibly in the proposed Papuan Gulf family. Not in TNG per Glottolog but accepted by all others. aliases = {"Suki-Gogodala", -- Glottolog's name "Suki-Aramia River", -- Used in Usher (2020) }, } m["ngf-gum"] = { "Gum", 5618008, "ngf-mab", } m["ngf-gvd"] = { "Grand Valley Dani", -- considered a single language by Wikipedia 5595219, "ngf-cda", } m["ngf-hag"] = { "Hagen", -- [[w:Hagen languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Melpa-Kaugel River"}, -- Usher } m["ngf-han"] = { "Hanseman", 5651020, "ngf-mab", aliases = {"Hansemann Range"}, -- Usher } m["ngf-huo"] = { "Huon", 5946109, "ngf-fhu", aliases = {"Huon Peninsula"}, -- per Usher } m["ngf-jim"] = { "Jimi", -- [[w:Jimi languages]] and [[w:Jimi River languages]] redirect to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Jimi River"}, -- Usher } m["ngf-kab"] = { "Kabwum", nil, "ngf-huo", aliases = {"Timbe-Selepet-Komba", -- Pawley-Hammarström, "Northwest Huon", -- Usher }, } m["ngf-kai"] = { "Kainantu", -- Kambaira: under "unclassified Kainantu" (Glottolog), Tairora (Pawley-Hammarström), Gauwa (Usher) 15478590, "ngf-kgo", aliases = {"Gadsup-Auyana-Awa-Tairora"}, -- Wurm, } m["ngf-kak"] = { "Kalam-Kobon", 6350303, "ngf-ksa", aliases = {"Kalam", "Kaironk River"}, -- Usher (2020) } m["ngf-kau"] = { "Kaukombar", nil, "ngf-nad", aliases = {"Kaukombaran", -- Glottolog following Z'graggen (1975) "Kaukombar River"}, -- Usher's term } m["ngf-kbm"] = { "Kosorong-Burum-Mindik", nil, "ngf-huo", aliases = {"Bulum River"}, -- Usher } m["ngf-kgo"] = { "Kainantu-Goroka", 3217463, "ngf", aliases = {"Eastern Highlands"}, -- per Usher (2020) } m["ngf-khu"] = { "Kewa-Huli", nil, "ngf-eng", aliases = {"Huli-Southern Highlands"}, -- Usher } m["ngf-kma"] = { "Kâte-Mape", nil, "ngf-ehu", aliases = {"Kate-Mape-Sene", -- Pawley-Hammarström (with Sene), "Southeast Huon", -- Usher }, } m["ngf-kme"] = { "Kapau-Menya", nil, "ngf-ang", aliases = {"Southeast Kratke Range"}, -- Usher } m["ngf-koi"] = { "Koiarian", 11154240, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Koiari-Managalas Plateau"}, } m["ngf-kok"] = { "Kokon", -- Usher calls it South Mabuso but includes Gum in it nil, "ngf-mab", } m["ngf-kow"] = { "Kowan", 6435004, "ngf-mad", aliases = {"Isumrud Strait"}, -- per Usher (2020) } m["ngf-ksa"] = { "Kalam-Southern Adelbert", nil, "ngf-mad", aliases = {"Kalamic-South Adelbert", -- Glottolog "West Madang"}, -- Usher (2020) } m["ngf-kto"] = { "Kube-Tobo", -- per Glottolog, one language "Kulungtfu-Yuanggeng-Tobo" 1173235, -- code for Tobo-Kube language "ngf-huo", aliases = {"Tobo-Kube"}, } m["ngf-kts"] = { "Komyandaret-Tsaukambo", nil, "ngf-bda", aliases = {"Becking River"}, -- Usher } m["ngf-kum"] = { "Kumil", nil, "ngf-nad", aliases = {"Kumilan", -- Pawley-Hammarström following Z'graggen (1975) "Kumil River"}, -- Usher's term } m["ngf-kya"] = { "Kamano-Yagaria", nil, "ngf-gor", aliases = {"Henganofi", -- Usher "Kamano-Yagaria-Keigana", }, } m["ngf-lok"] = { "Lowland Ok", nil, "ngf-okk", } m["ngf-mab"] = { "Mabuso", 6721668, "ngf-mad", } m["ngf-mad"] = { "Madang", 11217556, "ngf", aliases = {"Madang-Adelbert Range"}, -- Z'graggen (1975), corresponding to today's Madang except in lacking Kalam and Gants } m["ngf-mek"] = { "Mek", 6810515, "ngf", aliases = {"Goliath"}, -- outdated alternative name given by Wikipedia } m["ngf-min"] = { "Mindjim", 86749913, "ngf-mad", aliases = {"Lower Minjim", -- Glottolog, placed in Rai Coast by Glottolog and Pawley-Hammarström; Glottolog's -- Mindjim has 6 languages, including "Upper Minjim" (Rerau and Sgi Bara) "Mindjim River", -- Usher "Minjim", "Minjim River", }, } -- Add if Molet is separated from Asaro'o -- m["ngf-moa"] = { -- "Molet-Asaro'o", -- nil, -- "ngf-war", -- } m["ngf-mok"] = { "Mountain Ok", -- [[w:Mountain Ok languages]] redirects to [[w:Ok languages]] nil, "ngf-okk", } m["ngf-mom"] = { "Mombum", 6897077, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Mombum-Koneraw", "Komolom", "Muli Strait"}, -- Pawley-Hammarström uses Komolom, Usher uses Muli Strait } m["ngf-msu"] = { "Mian-Suganga", -- considred a single Mian language by Wikipedia 12952846, "ngf-mok", aliases = {"Mianic"}, -- Glottolog } m["ngf-nad"] = { "Northern Adelbert", -- not accepted by Pawley-Hammarström 16952821, -- code for Croisilles linkage "ngf-mad", aliases = {"Adelbert Range-Isumrud Strait", -- Usher (2020) "North Adelbert", "Pihom-Isumrud"}, -- Ross? } m["ngf-nbi"] = { "North Binanderean", nil, "ngf-bin", aliases = {"Suena-Zia"}, -- Usher } m["ngf-nde"] = { "Ndeiram", -- [[w:Ndeiram River languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Ndeiram River"}, -- Usher? } m["ngf-ngn"] = { "Ngalik-Nduga", -- [[w:Ngalik languages]] redirects to [[w:Baliem Valley languages]] = Dani languages nil, "ngf-dan", aliases = {"Ngalik"}, -- Usher } m["ngf-nso"] = { "North Sogeram", nil, "ngf-sog", aliases = {"Mum-Sirva", -- Usher "North Central Sogeram", -- used by those who accept Central Sogeram (= North Sogeram + Apali and Manat) "North-Central Sogeram", -- rarer than without the dash "Sikan"}, -- Z’graggen (1975?) } m["ngf-num"] = { "Numugen", nil, "ngf-nad", aliases = {"Numugenan", -- Glottolog following Z'graggen 1975 "Numugen River"}, -- Usher's term } m["ngf-nur"] = { "Nuru", -- Usher excludes Yangulam, Pawley-Hammarström include Jilim and Rerau nil, "ngf-rai", aliases = {"Nuru River"}, -- Usher? } m["ngf-nwh"] = { "Northwest Hanseman", -- Usher nil, "ngf-han", aliases = {"Wamas-Samosa-Murupi-Mosimo"}, -- Glottolog, Greenhill, and Pawley-Hammarström following Z'graggen; the most common name, but very unwieldy } m["ngf-oen"] = { "Outer Engan", -- considered a single Nete language by Wikipedia 6998869, "ngf-enc", aliases = {"Nete-Bisorio"}, -- Usher } m["ngf-okk"] = { "Ok", 7081687, "ngf", } m["ngf-omo"] = { "Omosan", -- not included in (Greater) Northern Adelbert by Glottolog, but a sister nil, "ngf-nad", } m["ngf-oro"] = { "Orokaivic", 7103752, -- considered a single Orokaiva language by Wikipedia "ngf-bin", aliases = {"Central Oro"}, -- Usher } m["ngf-pan"] = { "Paniai Lakes", 6035631, "ngf", aliases = {"Wissel Lakes", "Wissel Lakes-Kemandoga River"}, -- alternative names given by Wikipedia } m["ngf-pek"] = { "Peka", nil, "ngf-rai", aliases = {"Peka River"}, -- Usher? } m["ngf-pom"] = { "Pomoikan", nil, "ngf-sad", } m["ngf-rai"] = { "Rai Coast", 7283663, "ngf-mad", aliases = {"South Madang"}, -- Usher } m["ngf-sab"] = { "Sabakor", -- [[w:Sabakor languages]] redirects to [[w:Asmat–Kamrau languages]] nil, -- 55994614 is for [[Category:Kamrau Bay languages]], which exists on enwiki "ngf-ask", aliases = {"Kamrau Bay"}, -- Usher } m["ngf-sad"] = { "Southern Adelbert", 12633980, "ngf-ksa", aliases = {"South Adelbert", -- Glottolog "Southern Adelbert Range", -- Z'graggen (1980) "Sogeram and Tomul Rivers"}, -- Usher (2020)? } m["ngf-sak"] = { "Sau-Angal-Kewa", nil, "ngf-khu", aliases = {"Southern Highlands"}, -- Usher } m["ngf-san"] = { "Sankwep", nil, "ngf-huo", aliases = {"Nabak-Momolili", -- Pawley-Hammarström, "Southwest Huon", -- Usher }, } m["ngf-sbh"] = { "South Bird's Head", 7566330, "ngf", } m["ngf-sim"] = { "Simbu", nil, "ngf-chw", } m["ngf-sog"] = { "Sogeram", 86750419, "ngf-sad", aliases = {"Sogeram River", -- Usher "Wanang"}, } m["ngf-sop"] = { "Sopac", nil, "ngf-ehu", aliases = {"Momare-Migabac", -- Pawley-Hammarström, "Masaweng River", -- Usher }, } m["ngf-taa"] = { "Tainae-Akoye", nil, "ngf-ata", aliases = {"Akoye-Tainae"}, -- Usher } m["ngf-tai"] = { "Tairora", nil, "ngf-kai", aliases = {"Tairoric", -- Glottolog, "East Kainantu", -- Usher }, } m["ngf-tib"] = { "Tiboran", nil, "ngf-nad", aliases = {"Nuclear Tibor", -- Glottolog, excluding Wanambre/Mokati "Tiboran River", -- Usher (2020) "Tibor", -- Pick (2020) and Glottolog including Wanambre/Mokati } } m["ngf-tna"] = { "Tangko-Nakai", nil, "ngf-okk", aliases = {"Central Ok"}, -- Usher } m["ngf-uru"] = { "Uruwa", nil, "ngf-fin", aliases = {"Uruwa River"}, -- Usher? } m["ngf-usi"] = { "Utu-Silopi", nil, "ngf-han", aliases = {"Silopi-Utu"}, -- Usher } m["ngf-waa"] = { "Wantoat-Awara", -- not in Usher but Wantoat and Awara form a dialect chain nil, "ngf-wan", aliases = {"Awara-Wantoat"}, -- per Wikipedia } m["ngf-wah"] = { "Wahgi", -- [[w:Wahgi languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Wahgi Valley"}, -- Usher } m["ngf-wan"] = { "Wantoatic", nil, "ngf-fin", aliases = {"Wantoat", "Wantoat River", -- Usher? }, } m["ngf-war"] = { "Warup", 12645082, "ngf-fin", aliases = {"Warup River"}, -- Usher? } m["ngf-woj"] = { "Wojokesic", nil, "ngf-ang", aliases = {"Northeast Kratke Range"}, -- Usher } m["ngf-wok"] = { "West Ok", nil, "ngf-okk", aliases = {"Kwer-Kopkaka-Burumakok"}, -- Glottolog, Pawley-Hammarström } m["ngf-wso"] = { "West Sogeram", nil, "ngf-sog", aliases = {"Mand-Nend", -- Usher "Atan", -- Wurm following Z'graggen }, } m["ngf-yag"] = { "Yaganon", -- placed in Rai Coast by Glottolog and Pawley-Hammarström 35323986, "ngf-mad", aliases = {"Yaganon River"}, -- Usher } m["ngf-yal"] = { "Yali", -- considered a single language by Wikipedia 8047468, "ngf-ngn", aliases = {"Ngalik"}, -- Glottolog, Pawley-Hammarström } m["ngf-yar"] = { "Yareban", 16977672, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Musa River"}, } m["ngf-ynu"] = { "Yau-Nungon", 12953319, -- for the single Yau language in Wikipedia ([[w:Yau language (Trans–New Guinea)]]) "ngf-uru", } m["ngf-yup"] = { "Yupna", nil, "ngf-fin", aliases = {"Yupna River"}, -- Usher? } m["nic"] = { "Niger-Congo", 33838, aliases = {"Niger-Kordofanian"}, } m["nic-alu"] = { "Alumic", 4737355, "nic-plt", } m["nic-bas"] = { "Basa", 4866154, "nic-knj", } m["nic-bbe"] = { "Eastern Beboid", nil, "nic-beb", } m["nic-bco"] = { "Benue-Congo", 33253, "nic-vco", } m["nic-bcr"] = { "Bantoid-Cross", 806983, "nic-bco", } m["nic-bdn"] = { "Northern Bantoid", nil, "nic-bod", aliases = {"North Bantoid"}, } m["nic-bds"] = { "Southern Bantoid", 3183152, "nic-bod", aliases = {"Wide Bantu", "Bin"}, } m["nic-beb"] = { "Beboid", 813549, "nic-bds", } m["nic-ben"] = { "Bendi", 4887065, "nic-bcr", } m["nic-beo"] = { "Beromic", 4894642, "nic-plt", } m["nic-bod"] = { "Bantoid", 806992, "nic-bcr", } m["nic-buk"] = { "Buli-Koma", nil, "nic-ovo", } m["nic-bwa"] = { "Bwa", 12628562, "nic-gur", other_names = {"Bwamu", "Bomu"}, } m["nic-cde"] = { "Central Delta", 3813191, "nic-cri", } m["nic-cri"] = { "Cross River", 1141096, "nic-bcr", } m["nic-dag"] = { "Dagbani", nil, "nic-wov", } m["nic-dak"] = { "Dakoid", 1157745, "nic-bdn", } m["nic-dge"] = { "Escarpment Dogon", 5397128, "qfa-dgn", } m["nic-dgw"] = { "West Dogon", nil, "qfa-dgn", } m["nic-eko"] = { "Ekoid", 1323395, "nic-bds", } m["nic-eov"] = { "Eastern Oti-Volta", nil, "nic-ovo", aliases = {"Samba"}, } m["nic-fru"] = { "Furu", 5509783, "nic-bds", } m["nic-gne"] = { "Eastern Gurunsi", 12633072, "nic-gns", aliases = {"Eastern Grũsi"}, } m["nic-gnn"] = { "Northern Gurunsi", nil, "nic-gns", aliases = {"Northern Grũsi"}, } m["nic-gnw"] = { "Western Gurunsi", nil, "nic-gns", aliases = {"Western Grũsi"}, } m["nic-gns"] = { "Gurunsi", 721007, "nic-gur", aliases = {"Grũsi"}, } m["nic-gre"] = { "Eastern Grassfields", 5330160, "nic-grf", } m["nic-grf"] = { "Grassfields", 750932, "nic-bds", aliases = {"Grassfields Bantu", "Wide Grassfields"}, } m["nic-grm"] = { "Gurma", 30587833, "nic-ovo", } m["nic-grs"] = { "Southwest Grassfields", 7571285, "nic-grf", } m["nic-gur"] = { "Gur", 33536, "alv-sav", aliases = {"Voltaic"}, } m["nic-ief"] = { "Ibibio-Efik", 2743643, "nic-lcr", } m["nic-jer"] = { "Jera", nil, "nic-kne", } m["nic-jkn"] = { "Jukunoid", 1711622, "nic-pla", } m["nic-jrn"] = { "Jarawan", 1683430, "nic-mba", } m["nic-jrw"] = { "Jarawa", 35423, "nic-jrn", } m["nic-kam"] = { "Kambari", 6356294, "nic-knj", } m["nic-ktl"] = { "Katloid", nil, "nic", } m["nic-kau"] = { "Kauru", nil, "nic-kne", } m["nic-kmk"] = { "Kamuku", 6359821, "nic-knj", } m["nic-kne"] = { "East Kainji", 5328687, "nic-knj", } m["nic-knj"] = { "Kainji", 681495, "nic-pla", } m["nic-knn"] = { "Northwest Kainji", 7060098, "nic-knj", } m["nic-ktl"] = { "Katloid", 6377681, "nic", aliases = {"Katla", "Katla-Tima"}, } m["nic-lcr"] = { "Lower Cross River", 3813193, "nic-cri", } m["nic-mam"] = { "Mamfe", 2005898, "nic-bds", aliases = {"Nyang"}, } m["nic-mba"] = { "Mbam", 687826, "nic-bds", } m["nic-mbc"] = { "Mba", 6799561, "nic-ubg", } m["nic-mbw"] = { "West Mbam", nil, "nic-mba", } m["nic-mmb"] = { "Mambiloid", 1888151, other_names = {"North Bantoid"}, -- per Wikipedia, North Bantoid is the parent family "nic-bdn", } m["nic-mom"] = { "Momo", 6897393, "nic-grf", } m["nic-mre"] = { "Moré", nil, "nic-wov", } m["nic-ngd"] = { "Ngbandi", 36439, "nic-ubg", } m["nic-nge"] = { "Ngemba", 7022271, "nic-gre", } m["nic-ngk"] = { "Ngbaka", 3217499, "nic-ubg", } m["nic-nin"] = { "Ninzic", 7039282, "nic-plt", } m["nic-nka"] = { "Nkambe", 7042520, "nic-gre", } m["nic-nkb"] = { "Baka", nil, "nic-nkw", } m["nic-nke"] = { "Eastern Ngbaka", nil, "nic-ngk", } m["nic-nkg"] = { "Gbanziri", nil, "nic-nkw", } m["nic-nkk"] = { "Kpala", nil, "nic-nkw", } m["nic-nkm"] = { "Mbaka", nil, "nic-nkw", } m["nic-nkw"] = { "Western Ngbaka", nil, "nic-ngk", } m["nic-npd"] = { "North Plateau Dogon", nil, "qfa-dgn", } m["nic-nun"] = { "Nun", 13654297, "nic-gre", } m["nic-nwa"] = { "Nanga-Walo", nil, "qfa-dgn", } m["nic-ogo"] = { "Ogoni", 2350726, "nic-cri", aliases = {"Ogonoid"}, } m["nic-ovo"] = { "Oti-Volta", 1157178, "nic-gur", } m["nic-pla"] = { "Platoid", 453244, "nic-bco", aliases = {"Central Nigerian"}, } m["nic-plc"] = { "Central Plateau", 5061668, "nic-plt", } m["nic-pld"] = { "Plains Dogon", nil, "qfa-dgn", } m["nic-ple"] = { "East Plateau", 5329154, "nic-plt", } m["nic-pls"] = { "South Plateau", 7568236, "nic-plt", aliases = {"Jilic-Eggonic"}, } m["nic-plt"] = { "Plateau", 1267471, "nic-pla", } m["nic-ras"] = { "Rashad", 3401986, "nic", } m["nic-rnc"] = { "Central Ring", nil, "nic-rng", } m["nic-rng"] = { "Ring", 2269051, "nic-grf", aliases = {"Ring Road"}, } m["nic-rnn"] = { "Northern Ring", nil, "nic-rng", } m["nic-rnw"] = { "Western Ring", nil, "nic-rng", } m["nic-ser"] = { "Sere", 7453058, "nic-ubg", } m["nic-shi"] = { "Shiroro", 7498953, "nic-knj", aliases = {"Pongu"}, } m["nic-sis"] = { "Sisaala", 36532, "nic-gnw", } m["nic-tar"] = { "Tarokoid", 2394472, "nic-plt", } m["nic-tiv"] = { "Tivoid", 752377, "nic-bds", } m["nic-tvc"] = { "Central Tivoid", nil, "nic-tiv", } m["nic-tvn"] = { "Northern Tivoid", nil, "nic-tiv", } m["nic-ubg"] = { "Ubangian", 33932, "nic-vco", -- or none } m["nic-uce"] = { "East-West Upper Cross River", nil, "nic-ucr", } m["nic-ucn"] = { "North-South Upper Cross River", nil, "nic-ucr", } m["nic-ucr"] = { "Upper Cross River", 4108624, "nic-cri", aliases = {"Upper Cross"}, } m["nic-vco"] = { "Volta-Congo", 37228, "alv", } m["nic-wov"] = { "Western Oti-Volta", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nic-ykb"] = { "Yukubenic", 16909196, "nic-plt", aliases = {"Oohum"}, } m["nic-ymb"] = { "Yambasa", nil, "nic-mba", } m["nic-yon"] = { "Yom-Nawdm", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nub"] = { "Nubian", 1517194, "sdv-nes", } m["nub-hil"] = { "Hill Nubian", 5762211, "nub", aliases = {"Kordofan Nubian"}, } m["omq"] = { "Oto-Manguean", 33669, } m["omq-cha"] = { "Chatino", 35111, "omq-zap", } m["omq-chi"] = { "Chinantecan", 35828, "omq", } m["omq-cui"] = { "Cuicatec", 616024, "omq-mix", } m["omq-maz"] = { "Mazatecan", 36230, "omq", aliases = {"Mazatec"}, } m["omq-mix"] = { "Mixtecan", 21083066, "omq", } m["omq-mxt"] = { "Mixtec", 36363, "omq-mix", } m["omq-otp"] = { "Oto-Pamean", 1270220, "omq", } m["omq-pop"] = { "Popolocan", 5132273, "omq", } m["omq-tri"] = { "Triqui", 780200, "omq-mix", aliases = {"Trique"}, } m["omq-zap"] = { "Zapotecan", 8066463, "omq", } m["omq-zpc"] = { "Zapotec", 13214, "omq-zap", } m["omv"] = { "Omotic", 33860, "afa", } m["omv-aro"] = { "Aroid", 3699526, "omv", aliases = {"Ari-Banna", "South Omotic", "Somotic"}, } m["omv-diz"] = { "Dizoid", 430251, "omv", aliases = {"Maji", "Majoid"}, } m["omv-eom"] = { "East Ometo", 20527288, "omv-ome", } m["omv-gon"] = { "Gonga", 4143043, "omv", aliases = {"Kefoid"}, } m["omv-mao"] = { "Mao", 1351495, "omv", } m["omv-nom"] = { "North Ometo", nil, "omv-ome", } m["omv-ome"] = { "Ometo", 36310, "omv", } m["oto"] = { "Otomian", 130372545, "omq-otp", } m["oto-otm"] = { "Otomi", 36355, "oto", } m["paa"] = { "Papuan", 236425, "qfa-not", } m["paa-aia"] = { "Aian", 4767739, -- Annaberg languages "paa-ram", aliases = {"Middle Ramu", -- Foley (with Rao), "Annaberg", -- with Rao "Aram-Aren", -- Usher }, } m["paa-alp"] = { "Alor-Pantar", 3502429, "paa-tap", } m["paa-amu"] = { "Amto-Musan", 480281, aliases = {"Samaia River"}, } m["paa-ani"] = { "Anim", 55603991, aliases = {"Fly River"}, } m["paa-ara"] = { "Arapesh", 4784223, "paa-koa", aliases = {"Arapeshan"}, -- Foley } m["paa-arf"] = { "Arafundi", 4783702, } m["paa-ata"] = { "Ataitan", 4812652, "paa-ram", aliases = {"Tangu", -- Foley "Tanggu", -- alternative name given by Wikipedia "Moam River", -- Usher }, } m["paa-baa"] = { "Bayono-Awbono", 2424781, } m["paa-bai"] = { "Baining", 748487, aliases = {"East New Britain"}, } m["paa-baw"] = { "Bosngun-Awar", nil, "paa-ott", aliases = {"East Ramu Coast", -- Usher "Bosman-Awar", -- Wikipedia }, } m["paa-bew"] = { "Bewani", -- [[w:Bewani languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 16113460, "paa-bor", aliases = {"Poal River"}, -- Usher } m["paa-boa"] = { "Boazi", 48803717, "paa-mby", aliases = {"Lake Murray"}, -- Usher } m["paa-bor"] = { "Border", 1752158, aliases = {"Upper Tami", "Tami River-Bewani Range", -- Usher }, } m["paa-bul"] = { "Bulaka River", 4987195, aliases = {"Yelmek-Maklew", "Jabga"}, -- Yelmek-Maklew in Evans (2018) and Gregor (2021) } m["paa-bvi"] = { "Betaf-Vitou", -- Glottolog nil, "paa-tor", aliases = {"Vitou-Betaf", -- Wikipedia "Fitou-Tena", -- Usher "Manirem", }, } m["paa-clp"] = { "Central Lakes Plain", -- [[w:Central Lakes Plain languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86780132 is for the corresponding category, which exists in enwiki "paa-lpl", aliases = {"East Tariku", -- Glottolog "Central Lakes Plains", -- Usher }, } m["paa-dtu"] = { "Doso-Turumsa", 16917784, -- possibly related to East Strickland languages aliases = {"Soari River"}, -- Usher's name } m["paa-ebh"] = { "East Bird's Head", 338064, aliases = {"Mantion-Meax", "Mantion-Meyah", -- Mantion-Meax is Wikipedia's term "Southeast Bird's Head", -- Usher (2020) }, } m["paa-eel"] = { "Eastern Eleman", nil, "paa-ele", aliases = {"East Eleman"}, } m["paa-egb"] = { "East Geelvink Bay", 1497678, aliases = {"Geelvink Bay", "East Cenderawasih"}, -- Geelvink Bay per Glottolog } m["paa-eke"] = { "East Keram", nil, "paa-ker", } m["paa-ele"] = { "Eleman", 3034298, aliases = {"Kerema Bay"}, } m["paa-elp"] = { "East Lakes Plain", -- [[w:East Lakes Plain languages]] redirects to [[w:Lakes Plain languages]]; but Croatian Wikipedia has an entry 12633078, "paa-lpl", aliases = {"East Lakes Plains"}, -- Usher } m["paa-epw"] = { "Eastern Pauwasi", 16115496, aliases = {"East Pauwasi"}, } m["paa-etf"] = { "Eastern Trans-Fly", 5330530, aliases = {"Oriomo"}, -- in increasing recent use, probably originating in Evans (2018) } m["paa-eti"] = { "East Timor", 15496066, "paa-tap", aliases = {"Oirata-Makasae", -- Wikipedia's name "Eastern Timor", -- alternative name given by Wikipedia "Fataluku-Makasai", "Oirata-Makasai", -- alternative names given by Wikidata }, } m["paa-fas"] = { "Fas", 3502658, aliases = {"Baibai-Fas"}, -- Glottolog's name } m["paa-flp"] = { "Far West Lakes Plain", -- [[w:Wapoga River languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86808337 is for the corresponding Wapoga languages category, which exists in enwiki "paa-lpl", aliases = {"Rasawa", -- Clouse (1997) "Wapoga River", -- Usher, including Kehu/Keuw (unclassified by others) }, } m["paa-gkw"] = { "Greater Kwerba", 12635134, aliases = {"West Foja Range", -- Usher "Kwerbic", -- Wikipedia "Kwerba", -- Foley (2018) }, } m["paa-gto"] = { "Galela-Tobelo", nil, "paa-nnh", aliases = {"Mainland North Halmaheran", -- Glottolog "Mainland North Halmahera", "Northeast Halmahera", -- alternative names "Northeast Halmaheran", -- Wikipedia, from Verhoeve 1988 }, } m["paa-hya"] = { "Heyo-Yahang", nil, "paa-mam", aliases = {"Yahang-Heyo"}, -- Wikipedia's name } m["paa-ing"] = { "Inland Gulf", 6034783, "paa-ani", aliases = {"Inland Gulf of Papua"}, -- Glottolog } m["paa-isk"] = { "Inner Sko", 65043889, "paa-sko", aliases = {"Skouic", -- Glottolog "West Vanimo Coast", -- Usher "Western Skou", -- Wikipedia "Inner Skou", "Nuclear Skou", -- alternative names given by Wikipedia }, } m["paa-iwa"] = { "Iwam", 15147853, "paa-sep", } m["paa-kae"] = { "Kamula-Elevala", 130390498, -- often placed in TNG aliases = {"Kamula-Elevala River"}, } m["paa-kan"] = { "Kanum", -- removed from Tonda by Glottolog nil, "paa-ton", } m["paa-kay"] = { "Kayagaric", 7566330, aliases = {"Kayagar", -- formerly common "Cook River"}, -- per Usher (2020) } m["paa-ker"] = { "Keram", 48768173, -- often grouped within or coordinate with the Ramu languages aliases = {"Keram River"}, } m["paa-kiw"] = { "Kiwaian", 338449, aliases = {"Kiwai"}, -- formerly common, still sees some use } m["paa-kko"] = { "Kaure-Kosare", -- rejected by Pawley-Hammarström but accepted by Glottolog, Foley (2018) and Usher (2020) 48767891, aliases = {"Nawa River"}, -- Usher's term } m["paa-koa"] = { "Kombio-Arapesh", 16115049, "paa-trr", aliases = {"Kombio-Arapeshan", -- Laycock, who includes Wom "Kombio-Arapesh-Urat", -- Glottolog, including Urat }, } m["paa-kol"] = { "Kolopom", 6427807, } m["paa-kom"] = { "Kombio", 65044238, "paa-koa", aliases = {"Kombian", -- Laycock "Kombio-Yambes", -- Glottolog }, } m["paa-kun"] = { "Kunimaipan", 134973258, aliases = {"Northwest Wharton Range"}, -- per Usher (2020) -- often considered a subfamily of Goilalan } m["paa-kwa"] = { "Kwalean", 6450053, aliases = {"Humene-Uare"}, } m["paa-kwe"] = { "Kwerba proper", 12635134, "paa-gkw", aliases = {"Kwerba", -- Usher "Kwerbaic", -- Glottolog }, } m["paa-kwo"] = { "Kwomtari", 2075415, aliases = {"Kwomtari-Nai"}, -- Senu River is a larger unproven proposal } m["paa-lla"] = { "Loloda-Laba", -- a single language in Glottolog (Loloda-Laba) and Wikipedia (Loloda) 11732388, -- for the Loloda language "paa-gto", aliases = {"Loloda"}, -- Wikipedia's name } m["paa-lma"] = { "Left May", 614468, aliases = {"Arai River"}, -- per Usher (2020) -- Sometimes in a putative Arai-Samaia family along with Amto-Musan and the Pyu language } m["paa-lmu"] = { "Lepki-Murkim", -- Kembra accepted by Glottolog and Usher; not by Foley (2020) but does not exclude the possibility -- of a relationship 85776285, -- independent family per Glottolog, part of South Pauwasi River family (under Pauwasi) per Usher (2020) aliases = {"Lepki-Murkim-Kembra"}, -- Glottolog } m["paa-lpl"] = { "Lakes Plain", 6478969, aliases = {"Lakes Plains"}, } m["paa-lra"] = { "Lower Ramu", 65089469, "paa-ram", aliases = {"Ottilien-Misegian"}, -- alternative name given by Wikipedia } m["paa-lse"] = { "Lower Sepik", 7061700, aliases = {"Nor-Pondo"}, } m["paa-mai"] = { "Mairasi", 6736896, aliases = {"Mairasic"}, -- per Glottolog } m["paa-mal"] = { "Mailuan", 6735839, aliases = {"Cloudy Bay"}, } m["paa-mam"] = { "Maimai", -- Foley's Maimai is expanded 53679325, -- this is the code for the expanded Maimai with 6 languages, as opposed to the 3 in "Nuclear Maimai" "paa-trr", aliases = {"Nuclear Maimai", -- Glottolog's name "Maimai proper", -- Wikipedia's name }, } m["paa-man"] = { "Manubaran", 6752335, aliases = {"Mount Brown"}, } m["paa-mar"] = { "Marienberg", 1570589, "paa-trr", aliases = {"Marienberg Hills"}, -- Usher } m["paa-may"] = { "Maybratic", 4830892, -- the code for the Maybrat language in Wikipedia, which subsumes the two languages of this family -- putatively included in West Papuan but generally considered an isolated family aliases = {"Maybrat-Karon"}, } m["paa-mbi"] = { "Mbaham-Iha", 85784512, "qfa-dis", -- Papuan languages; Glottolog groups Karas (Kalamang) with Mbaham-Iha into a (mainland) West Bomberai -- family and stops there; Wikipedia, following Usher and Schapper (2022), groups Karas, Mbaham-Iha -- and the large Timor-Alor-Pantar family into a (Greater) West Bomberai family, saying that Karas is no -- closer to Mbaham-Iha than to Timor-Alor-Pantar. aliases = {"Mbahaam-Iha", -- used by Wikidata "Nuclear West Bomberai", -- Glottolog's name }, } m["paa-mby"] = { "Marind-Boazi-Yaqay", 3217484, "paa-ani", aliases = {"Marind-Boazi-Yaqai", -- Glottolog "Marind-Yakhai", -- Usher, without Boazi "Marind-Yaqai", -- Wikidata "Marind", -- alternative name given by Wikipedia "Marind-Arandai", -- alternative name given by Spanish Wikipedia }, } m["paa-mmu"] = { "Mandi-Muniwara", nil, "paa-mar", aliases = {"West Marienberg Hills"}, -- Usher } m["paa-mon"] = { "Monumbo", -- per Glottolog: "No evidence for the Bogia (Monumbo) languages being related to other Torricelli languages was ever presented" 16928417, aliases = {"Bogia", -- Glottolog "Bogia Bay", -- Usher (2020) }, } m["paa-mri"] = { "Marindic", -- [[w:Marindic languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Marind"}, -- Usher; a single language } m["paa-nam"] = { "Nambu", 6961418, "paa-yam", aliases = {"East Morehead River"}, -- Usher } m["paa-nbo"] = { "North Bougainville", 749496, } m["paa-ndu"] = { "Ndu", 3217498, "paa-sep", -- Not accepted by Glottolog aliases = {"Ndu-Nggala"}, -- Usher } m["paa-ngk"] = { "Ngkolmpu", -- considered a single language by Wikipedia 5908646, "paa-kan", aliases = {"Ngkantr", -- Glottolog "Ngkolmpu Kanum", -- Wikipedia "Ngkontar", -- alternative name given by Wikipedia "Kanum", -- used by Wikidata }, } m["paa-nha"] = { "North Halmahera", 3217358, -- possibly in a proposed West Papuan family or an independent family } m["paa-nim"] = { "Nimboran", 12638426, aliases = {"Nimboranic", -- per Glottolog "Grime River", -- per Usher (2020) } } m["paa-nnd"] = { "Nuclear Ndu", nil, "paa-ndu", aliases = {"Ndu", -- Usher, with Boiken/Boikin "Ndu proper", -- Wikipedia }, } m["paa-nnh"] = { "Northern North Halmahera", nil, "paa-nha", aliases = {"Northern North Halmaheran", -- Glottolog "Halmahera", -- Usher "Core Halmaheran", -- Wikipedia }, } m["paa-nto"] = { "Namla-Tofanma", 16918187, -- independent family per Glottolog and Foley (2018), part of West Pauwasi family (under Pauwasi) per Usher (2020) } m["paa-ott"] = { "Ottilien", 7109477, "paa-lra", aliases = {"Ramu Coast", -- Usher "Watam-Awar-Gamay", -- alternative name given by Wikipedia }, } m["paa-pah"] = { "Pahoturi River", 17049141, aliases = {"Pahoturi"}, -- per Glottolog } m["paa-pal"] = { "Palei", -- Laycock adds Agi and Nabi/Nambi(-Metan) 65089113, "paa-wpa", aliases = {"Nuclear Palai"}, } m["paa-pia"] = { "Piawi", -- per Wikipedia, grouped with Arafundi languages to form Upper Yuat, which is a sister to Madang 7190400, aliases = {"Schraeder Range", -- Usher? "Waibuk"}, } m["paa-pio"] = { "Piore River", 65043152, "paa-sko", aliases = {"Barupu Lagoon", -- Glottolog "Lagoon", -- alternative name given by Wikipedia }, } m["paa-por"] = { "Porapora", -- Foley includes Ambakich (which we, Glottolog, and Usher treat as Keram) 65044258, "paa-ram", aliases = {"Agoan", -- Glottolog "Porapora River", -- Usher "core Grass", -- alternative name given by Wikipedia }, } m["paa-ram"] = { "Ramu", 3442808, aliases = {"Ramu River"}, -- per Usher (2020) } m["paa-rsa"] = { "Rasawa-Saponi", -- [[w:Rasawa-Saponi languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q9859418 is for the coresponding category, which exists in the Piedmontese Wikipedia (?!) "paa-flp", aliases = {"Rombak River"}, -- Usher } m["paa-rub"] = { "Ruboni", 6875319, "paa-lra", aliases = {"Misegian", -- Wikipedia's name "Mikarew", -- alternative name given by Wikipedia "Ruboni Range"}, -- Usher } m["paa-saa"] = { "Samarokena-Airoran", 96417699, "paa-gkw", aliases = {"Apauwar Coast"}, -- Usher } m["paa-sah"] = { "Sahu", nil, "paa-nnh", } m["paa-sbo"] = { "South Bougainville", 3217380, } m["paa-sen"] = { "Sentani", 17044584, -- no consensus on higher affiliations, if any aliases = {"Sentanic", "Demta-Sentani", "Demta-Lake Sentani"}, -- Sentanic per Glottolog, Demta-Sentani per Wikipedia } m["paa-sep"] = { "Sepik", 3508772, } m["paa-shi"] = { "Serra Hills", 65043154, "paa-sko", } m["paa-sko"] = { "Sko", 953509, aliases = {"Skou"}, } m["paa-sng"] = { "Senagi", 2066550, } m["paa-taa"] = { "Taikat-Awyi", -- [[w:Taikat languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12643265, "paa-bor", aliases = {"Taikat", -- Foley "Upper Tami River", -- Usher }, } m["paa-tam"] = { "Tamolan", 7681634, "paa-ram", aliases = {"Guam River"}, -- Usher } m["paa-tap"] = { "Timor-Alor-Pantar", 16590002, } m["paa-teb"] = { "Teberan", 7692052, -- Often grouped with Trans-New Guinea, but per Pawley-Hammarström (2018), it has "weaker or disputed claims to membership in TNG". aliases = {"Dadibi-Folopa"}, } m["paa-tir"] = { "Tirio", 7809225, "paa-ani", aliases = {"Nuclear Lower Fly", -- Pawley-Hammarström ("Lower Fly" includes Abom) "Nuclear Tirio", -- Glottolog ("Tirio" includes Abom) "Lower Fly River", -- Usher (without Abom) }, } m["paa-tki"] = { "Turama-Kikori", 7853680, aliases = {"Turama-Kikorian", "Rumu-Omati River"}, } m["paa-ton"] = { "Tonda", 8581005, "paa-yam", aliases = {"West Morehead River"}, -- Usher } m["paa-too"] = { "Tor-Orya", 16590099, aliases = {"Orya-Tor"}, } m["paa-tor"] = { "Tor", -- [[w:Tor languages]] redirects to [[w:Orya–Tor languages]] nil, "paa-too", } m["paa-trr"] = { "Torricelli", 1333831, } m["paa-tti"] = { "Ternate-Tidore", nil, "paa-nnh", } m["paa-wal"] = { "Walio", 16919872, -- Often placed in Sepik (e.g. by Laycock and Z'graggen (1975)), but not by Foley (2018), and not accepted by Glottolog. aliases = {"Walioic", -- Glottolog "Central Leonhard Schultze River", }, } m["paa-wap"] = { "Wapei", -- Glottolog includes Nabi/Nambi(-Metan) in Wapeic 65089115, "paa-wpa", aliases = {"Wapeic"}, -- Glottolog } m["paa-war"] = { "Waris", -- [[w:Waris languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12645076, "paa-bor", aliases = {"Warisic", -- Glottolog "Bapi River", -- Usher (without Manem or Senggi) }, } m["paa-wbh"] = { "West Bird's Head", 5330530, -- Kuwani is sometimes included; probably related to North Halmahera languages. } m["paa-wel"] = { "Western Eleman", nil, "paa-ele", aliases = {"West Eleman"}, } m["paa-wig"] = { "West Inland Gulf", nil, "paa-ing", aliases = {"West Inland Gulf of Papua"}, -- Glottolog } m["paa-wke"] = { "West Keram", nil, "paa-ker", aliases = {"Koam", "Mongol-Langam", "Ulmapo"}, -- Koam used by Foley, Ulmapo used by Glottolog } m["paa-wko"] = { "Wára-Kómnzo", -- since we split out Kómnzo as a separate language 11732474, -- for the Wara language "paa-ton", aliases = {"Anta-Komnzo-Wára-Wérè-Kémä", -- Glottolog's name "Wára", "Wara", -- Wikipedia }, } m["paa-wlp"] = { "West Lakes Plain", -- [[w:Tariku languages]] redirects to [[w:Lakes Plain languages]] 47007503, -- actually for "Tariku languages", which per Wikipedia covers Fayu, Kirikiri, Iau and Tause "paa-lpl", aliases = {"West Tariku", -- Glottolog "West Lakes Plains"}, -- Usher, with Edopi/Iau } m["paa-wpa"] = { "Wapei-Palei", 65043156, "paa-trr", } m["paa-wpw"] = { -- paa-wpa already used by Wapei-Palei "Western Pauwasi", -- 2 langs per Glottolog and Pawley-Hammarström; Usher also includes Namla-Tofanma and Usku 85815062, aliases = {"West Pauwasi", -- Wikipedia, Usher "Tebi-Towe", "Dubu-Towei"}, } m["paa-yam"] = { "Yam", 15062272, aliases = {"Morehead and Upper Maro River", "Morehead River", -- Usher }, } m["paa-yaq"] = { "Yaqayic", -- [[w:Yaqai languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Yakhai-Warkay"}, -- Usher } m["paa-ysa"] = { "Yawa-Saweru", 3217545, aliases = {"Yawa", "Yawan", "Yapen"}, } m["paa-yua"] = { "Yuat", 8060096, } m["phi"] = { "Philippine", 947858, "poz", } m["phi-kal"] = { "Kalamian", 3217466, "phi", aliases = {"Calamian"}, } m["poz"] = { "Malayo-Polynesian", 143158, "map", } m["poz-aay"] = { "Admiralty Islands", 2701306, "poz-oce", } m["poz-bnn"] = { "North Bornean", 1427907, "poz", } m["poz-bre"] = { "East Barito", 2701314, "poz", } m["poz-brw"] = { "West Barito", 2761679, "poz", } m["poz-bss"] = { "Bali-Sasak-Sumbawa", 3396043, "poz-msa", } m["poz-btk"] = { "Bungku-Tolaki", 3217381, "poz-clb", } m["poz-cet"] = { "Central-Eastern Malayo-Polynesian", 2269883, "poz", } m["poz-clb"] = { "Celebic", 1078041, "poz", } m["poz-cln"] = { "New Caledonian", 3091221, "poz-ocs", } m["poz-cma"] = { "Central Maluku", 3217479, "poz-cet", } m["poz-hce"] = { "Halmahera-Cenderawasih", 2526616, "pqe", } m["poz-kal"] = { "Kaili-Pamona", 3217465, "poz-clb", } m["poz-lgx"] = { "Lampungic", 49215, "poz", } m["poz-mcm"] = { "Malayo-Chamic", nil, "poz-msa", } m["poz-mic"] = { "Micronesian", 420591, "poz-occ", } m["poz-mly"] = { "Malayic", 662628, "poz-mcm", } m["poz-msa"] = { "Malayo-Sumbawan", 1363818, "poz", } m["poz-mun"] = { "Muna-Buton", 3037924, "poz-clb", } m["poz-nws"] = { "Northwest Sumatran", 2071308, "poz", } m["poz-occ"] = { "Central-Eastern Oceanic", 2068435, "poz-oce", } m["poz-oce"] = { "Oceanic", 324457, "pqe", } m["poz-ocs"] = { "Southern Oceanic", 3039118, "poz-occ", } m["poz-ocw"] = { "Western Oceanic", 2701282, "poz-oce", } m["poz-pcc"] = { "Central Pacific", 3130237, "poz-occ", } m["poz-pep"] = { "Eastern Polynesian", 390979, "poz-pnp", } m["poz-pnp"] = { "Nuclear Polynesian", 743851, "poz-pol", } m["poz-pol"] = { "Polynesian", 390979, "poz-pcc", } m["poz-san"] = { "Sabahan", 3217517, "poz-bnn", } m["poz-sbj"] = { "Sama-Bajaw", 2160409, "poz", } m["poz-slb"] = { "Saluan-Banggai", 3217519, "poz-clb", } m["poz-sls"] = { "Southeast Solomonic", 3119671, "poz-occ", } m["poz-ssw"] = { "South Sulawesi", 2778190, "poz", } m["poz-stm"] = { "St. Matthias", 6484143, "poz-oce", aliases = {"St Matthias"}, } m["poz-swa"] = { "North Sarawakan", 538569, "poz-bnn", } m["poz-tem"] = { "Temotu", 3075769, "poz-oce", } m["poz-tim"] = { "Timoric", 7806987, "poz-cet", } m["poz-ton"] = { "Tongic", 3397263, "poz-pol", } m["poz-tot"] = { "Tomini-Tolitoli", 3217541, "poz-clb", } m["poz-vnc"] = { "Central Vanuatu", 5061988, "poz-ocs", } m["poz-vnn"] = { "North Vanuatu", 85789650, "poz-ocs", } m["poz-vns"] = { "South Vanuatu", 3070173, "poz-ocs", } m["poz-wot"] = { "Wotu-Wolio", 1041317, "poz-clb", aliases = {"Island Kaili-Wolio"}, -- Glottolog } m["pqe"] = { "Eastern Malayo-Polynesian", 2269883, "poz-cet", } m["qfa-adc"] = { "Central Great Andamanese", nil, "qfa-adm", } m["qfa-adm"] = { "Great Andamanese", 3515103, } m["qfa-adn"] = { "Northern Great Andamanese", nil, "qfa-adm", } m["qfa-ads"] = { "Southern Great Andamanese", nil, "qfa-adm", } m["qfa-ain"] = { "Ainuic", 50111972, aliases = {"Ainu"}, } m["qfa-bej"] = { "Be-Jizhao", nil, "qfa-bet", } m["qfa-bet"] = { "Be-Tai", 12627719, "qfa-tak", aliases = {"Tai-Be", "Daic-Beic", "Beic-Daic"}, } m["qfa-buy"] = { "Buyang", 1109927, "qfa-kra", } m["qfa-cka"] = { "Chukotko-Kamchatkan", 33255, } m["qfa-cre"] = { "creole", 33289, "crp", } m["qfa-ckn"] = { "Chukotkan", 2606732, "qfa-cka", } m["qfa-cnt"] = { "contact", 133253514, "qfa-not", } m["qfa-dis"] = { -- Languages that are not unclassifiable (qfa-unc) but where there is no consensus on classification. Usually -- this is because the languages are divergent and it's disputed whether they are isolates or distantly related -- to other languages. "disputed affiliation", nil, "qfa-not", } m["qfa-dgn"] = { "Dogon", 1234776, "nic", } m["qfa-dny"] = { "Dene-Yeniseian", 21103, aliases = {"Dené-Yeniseian"}, } m["qfa-hur"] = { "Hurro-Urartian", 1144159, } m["qfa-iso"] = { "isolate", 33648, "qfa-not", } m["qfa-kad"] = { "Kadu", -- considered either Nilo-Saharan or independent/none 1720989, } m["qfa-kms"] = { "Kam-Sui", 1023641, "qfa-tak", } m["qfa-kor"] = { "Koreanic", 11263525, } m["qfa-kra"] = { "Kra", 1022087, "qfa-tak", } m["qfa-lic"] = { "Hlai", 1023648, "qfa-tak", aliases = {"Hlaic"}, } m["qfa-mch"] = { -- used in both N and S America "Macro-Chibchan", 3438062, } m["qfa-mix"] = { "mixed", 33694, "qfa-cnt", } m["qfa-not"] = { "not a family", nil, "qfa-not", } m["qfa-onb"] = { "Be", nil, "qfa-bej", aliases = {"Ong-Be", "Beic"}, } m["qfa-ong"] = { "Ongan", 2090575, aliases = {"Angan", "South Andamanese", "Jarawa-Onge"}, } m["qfa-pid"] = { "pidgin", 33831, "crp", } m["qfa-sub"] = { "substrate", 20730913, "qfa-not", } m["qfa-tak"] = { "Kra-Dai", 34171, aliases = {"Tai-Kadai", "Kadai"}, } m["qfa-tyn"] = { "Tyrsenian", 1344038, } m["qfa-unc"] = { -- This corresponds to languages normally called "unclassified", i.e. there is insufficient data or research to -- classify them, whereas our [[:Category:Unclassified languages]] is just languages that no Wiktionary editor -- has classified yet (the family code in the language data is missing). "unclassifiable", 33956, "qfa-not", } m["qfa-xgs"] = { "Serbi-Mongolic", 108887939, } m["qfa-xgx"] = { "Para-Mongolic", 107619002, "qfa-xgs", } m["qfa-yen"] = { "Yeniseian", 27639, "qfa-dny", aliases = {"Yeniseic", "Yenisei-Ostyak"}, } m["qfa-yke"] = { "Ketic", nil, "qfa-yen", } m["qfa-yko"] = { "Kottic", nil, "qfa-yen", } m["qfa-yrn"] = { "Arinic", nil, "qfa-yen", } m["qfa-ypm"] = { "Pumpokolic", nil, "qfa-yen", } m["qfa-yuk"] = { "Yukaghir", 34164, aliases = {"Yukagir", "Jukagir"}, } m["qwe"] = { "Quechuan", 5218, } m["raj"] = { "Rajasthani", 13196, "inc-wes", protoLanguage = "inc-ogu", } m["roa"] = { "Romance", 19814, "itc", aliases = {"Romanic", "Latin", "Neolatin", "Neo-Latin"}, protoLanguage = "la", } m["roa-asl"] = { "Asturleonese", 35390, "roa-ibe", protoLanguage = "roa-ole", } m["roa-cas"] = { "Castilian", 71924, "roa-ibe", aliases = {"Castillian", "Castilic", "Castillic"}, protoLanguage = "osp", } m["roa-dal"] = { "Dalmatian Romance", 97646077, "roa-itd", } m["roa-eas"] = { "Eastern Romance", 147576, "roa", } m["roa-emr"] = { "Emilian-Romagnol", 242648, "roa-git", } m["roa-gap"] = { "Galician-Portuguese", 9080204, "roa-ibe", aliases = {"Galician Romance", "Galaic-Portuguese"}, protoLanguage = "roa-opt", } m["roa-gar"] = { "Gallo-Romance", 500394, "roa-wes", } m["roa-itd"] = { "Italo-Dalmatian", 3313381, "roa-iwr", aliases = {"Central Romance"} } m["roa-itr"] = { "Italo-Romance", 3356483, "roa-itd", } m["roa-iwr"] = { "Italo-Western Romance", 112608, "roa", aliases = {"Italo-Western"}, } m["roa-git"] = { "Gallo-Italic", 516074, "roa-gar", aliases = {"Gallo-Italian", "Gallo-Cisalpine", "Cisalpine"}, } m["roa-grh"] = { "Gallo-Rhaetian", 97646466, "roa-gar", } m["roa-ibe"] = { "Ibero-Romance", 749533, "roa-wes", aliases = {"Iberian Romance", "West Ibero-Romance", "Western Ibero-Romance", "West Iberian Romance", "Western Iberian Romance"} } m["roa-nar"] = { "Navarro-Aragonese", 133252927, "roa-ibe", protoLanguage = "roa-ona", } m["roa-oil"] = { "Oïl", 37351, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, protoLanguage = "fro", } m["roa-ocr"] = { "Occitano-Romance", 599958, "roa-gar", aliases = {"Gallo-Narbonnese", "East Iberian", "Eastern Iberian"}, } m["roa-rhe"] = { "Rhaeto-Romance", 515593, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, } m["roa-sou"] = { "Southern Romance", 145345, "roa", } m["roa-wes"] = { "Western Romance", 2714388, "roa-iwr", } --[=[ Exceptional language and family codes for South American Indian languages can use the prefix "sai-", though "sai" is no longer itself a family code. ]=]-- m["sai-ara"] = { "Araucanian", 626630, } m["sai-aym"] = { "Aymaran", 33010, } m["sai-bar"] = { "Barbacoan", 807304, aliases = {"Barbakoan"}, } m["sai-bor"] = { "Boran", 5371776, } m["sai-cah"] = { "Cahuapanan", 1025793, } m["sai-car"] = { "Cariban", 33090, aliases = {"Carib"}, } m["sai-cer"] = { "Cerrado", 98078151, "sai-jee", aliases = {"Amazonian Jê"}, } m["sai-chc"] = { "Chocoan", 1075616, aliases = {"Choco", "Chocó"}, } m["sai-cho"] = { "Chonan", 33019, aliases = {"Chon"}, } m["sai-cje"] = { "Central Jê", 18010843, "sai-cer", aliases = {"Akuwẽ"}, } m["sai-cpc"] = { "Chapacuran", 1062626, } m["sai-crn"] = { "Charruan", 3112423, aliases = {"Charrúan"}, } m["sai-ctc"] = { "Catacaoan", 5051139, } m["sai-guc"] = { "Guaicuruan", 1974973, "sai-mgc", aliases = {"Guaicurú", "Guaycuruana", "Guaikurú", "Guaycuruano", "Guaykuruan", "Waikurúan"}, } m["sai-guh"] = { "Guahiban", 944056, aliases = {"Guahiboan", "Guajiboan", "Wahivoan"}, } m["sai-gui"] = { "Guianan", nil, "sai-car", aliases = {"Guianan Carib", "Guiana Carib"}, } m["sai-har"] = { "Harákmbut", 1584402, "sai-hkt", aliases = {"Harákmbet"}, } m["sai-hkt"] = { "Harákmbut-Katukinan", 17107635, } m["sai-hrp"] = { "Huarpean", 1578336, aliases = {"Warpean", "Huarpe", "Warpe"}, } m["sai-jee"] = { "Jê", 1483594, "sai-mje", aliases = {"Gê", "Jean", "Gean", "Jê-Kaingang", "Ye"}, } m["sai-jir"] = { "Jirajaran", 3028651, aliases = {"Hiraháran"}, } m["sai-jiv"] = { "Jivaroan", 1393074, aliases = {"Hívaro", "Jibaro", "Jibaroan", "Jibaroana", "Jívaro"}, } m["sai-ktk"] = { "Katukinan", 2636000, "sai-hkt", aliases = {"Catuquinan"}, } m["sai-kui"] = { "Kuikuroan", nil, "sai-car", aliases = {"Kuikuro", "Nahukwa"}, } m["sai-map"] = { "Mapoyan", 61096301, "sai-ven", aliases = {"Mapoyo", "Mapoyo-Yabarana", "Mapoyo-Yavarana", "Mapoyo-Yawarana"}, } m["sai-mas"] = { "Mascoian", 1906952, aliases = {"Mascoyan", "Maskoian", "Enlhet-Enenlhet"}, } m["sai-mgc"] = { "Mataco-Guaicuru", 255512, } m["sai-mje"] = { "Macro-Jê", 887133, aliases = {"Macro-Gê"}, } m["sai-mtc"] = { "Matacoan", 2447424, "sai-mgc", } m["sai-mur"] = { "Muran", 33826, aliases = {"Mura"}, } m["sai-nad"] = { "Nadahup", 1856439, aliases = {"Makú", "Macú", "Vaupés-Japurá"}, } m["sai-nje"] = { "Northern Jê", 98078225, "sai-cer", aliases = {"Core Jê"}, } m["sai-nmk"] = { "Nambikwaran", 15548027, aliases = {"Nambicuaran", "Nambiquaran", "Nambikuaran"}, } m["sai-otm"] = { "Otomacoan", 3217503, aliases = {"Otomákoan", "Otomakoan"}, } m["sai-pan"] = { "Panoan", 1544537, "sai-pat", aliases = {"Pano"}, } m["sai-pat"] = { "Pano-Tacanan", 2475746, aliases = {"Pano-Tacana", "Pano-Takana", "Páno-Takána", "Pano-Takánan"}, } m["sai-pek"] = { "Pekodian", 107451736, "sai-car", aliases = {"South Amazonian Carib", "Southern Cariban", "Pekodi"}, } m["sai-pem"] = { "Pemongan", nil, "sai-ven", aliases = {"Pemong", "Pemóng", "Purukoto"}, } m["sai-pey"] = { "Peba-Yaguan", 174015, aliases = {"Peba-Yagua", "Yaguan", "Peban", "Yáwan"}, } m["sai-prk"] = { "Parukotoan", 107451482, "sai-car", aliases = {"Parukoto"}, } m["sai-sje"] = { "Southern Jê", 98078245, "sai-jee", } m["sai-tac"] = { "Tacanan", 3113762, "sai-pat", } m["sai-tar"] = { "Taranoan", 105097814, "sai-gui", aliases = {"Trio", "Tarano"}, } m["sai-tuc"] = { "Tucanoan", 788144, } m["sai-tyu"] = { "Ticuna-Yuri", 4467010, } m["sai-ucp"] = { "Uru-Chipaya", 2475488, aliases = {"Uru-Chipayan"}, } m["sai-ven"] = { "Venezuelan Cariban", nil, "sai-car", aliases = {"Venezuelan Carib", "Venezuelan", "Venezuelano"}, } m["sai-wic"] = { "Wichí", 3027047, } m["sai-wit"] = { "Witotoan", 43079317, aliases = {"Huitotoan", "Uitotoan"}, } m["sai-ynm"] = { "Yanomami", nil, aliases = {"Yanomam", "Shamatari", "Yamomami", "Yanomaman"}, } m["sai-yuk"] = { "Yukpan", nil, "sai-car", aliases = {"Yukpa", "Yukpano", "Yukpa-Japreria"}, } m["sai-zam"] = { "Zamucoan", 3048461, aliases = {"Samúkoan"}, } m["sai-zap"] = { "Zaparoan", 33911, aliases = {"Záparoan", "Saparoan", "Sáparoan", "Záparo", "Zaparoano", "Zaparoana"}, } m["sal"] = { "Salish", 33985, } m["sdv"] = { "Eastern Sudanic", 2036148, "ssa", } m["sdv-bri"] = { "Bari", nil, "sdv-nie", } m["sdv-daj"] = { "Daju", 956724, "sdv", } m["sdv-dnu"] = { "Dinka-Nuer", nil, "sdv-niw", } m["sdv-eje"] = { "Eastern Jebel", 3408878, "sdv", } m["sdv-kln"] = { "Kalenjin", 637228, "sdv-nis", } m["sdv-lma"] = { "Lotuko-Maa", nil, "sdv-nie", } m["sdv-lon"] = { "Northern Luo", nil, "sdv-luo", } m["sdv-los"] = { "Southern Luo", 7570103, "sdv-luo", } m["sdv-luo"] = { "Luo", nil, "sdv-niw", } m["sdv-nes"] = { "Northern Eastern Sudanic", 4810496, "sdv", aliases = {"Astaboran", "Ek Sudanic"}, } m["sdv-nie"] = { "Eastern Nilotic", 153795, "sdv-nil", } m["sdv-nil"] = { "Nilotic", 513408, "sdv", } m["sdv-nis"] = { "Southern Nilotic", 1552410, "sdv-nil", } m["sdv-niw"] = { "Western Nilotic", 3114989, "sdv-nil", } m["sdv-nma"] = { "Nandi-Markweta", nil, "sdv-kln", } m["sdv-nyi"] = { "Nyima", 11688746, "sdv-nes", aliases = {"Nyimang"}, } m["sdv-tmn"] = { "Taman", 3408873, "sdv-nes", aliases = {"Tamaic"}, } m["sdv-ttu"] = { "Teso-Turkana", 7705551, "sdv-nie", aliases = {"Ateker"}, } m["sel"] = { "Selkup", 34008, "syd", } m["sem"] = { "Semitic", 34049, "afa", } m["sem-ara"] = { "Aramaic", 28602, "sem-nwe", protoLanguage = "arc", } m["sem-arb"] = { "Arabic", 164667, "sem-cen", protoLanguage = "ar", } m["sem-are"] = { "Eastern Aramaic", 3410322, "sem-ara", } m["sem-arw"] = { "Western Aramaic", 3394214, "sem-ara", } m["sem-ase"] = { "Southeastern Aramaic", 3410322, "sem-are", } m["sem-can"] = { "Canaanite", 747547, "sem-nwe", } m["sem-cen"] = { "Central Semitic", 3433228, "sem-wes", } m["sem-cna"] = { "Central Neo-Aramaic", 3410322, "sem-are", } m["sem-eas"] = { "East Semitic", 164273, "sem", } m["sem-eth"] = { "Ethiopian Semitic", 163629, "sem-wes", aliases = {"Afro-Semitic", "Ethiopian", "Ethiopic", "Ethiosemitic"}, } m["sem-nna"] = { "Northeastern Neo-Aramaic", 2560578, "sem-are", } m["sem-nwe"] = { "Northwest Semitic", 162996, "sem-cen", } m["sem-osa"] = { "Old South Arabian", 35025, "sem-cen", aliases = {"Epigraphic South Arabian", "Sayhadic"}, } m["sem-sar"] = { "Modern South Arabian", 1981908, "sem-wes", } m["sem-wes"] = { "West Semitic", 124901, "sem", } m["sgn"] = { "sign", 34228, "qfa-not", } m["sgn-fsl"] = { "French Sign Languages", 5501921, "sgn", } m["sgn-gsl"] = { "German Sign Languages", 5551235, "sgn", } m["sgn-jsl"] = { "Japanese Sign Languages", 11722508, "sgn", } m["sio"] = { "Siouan", 34181, "nai-sca", } m["sio-dhe"] = { "Dhegihan", 3217420, "sio-msv", } m["sio-dkt"] = { "Dakotan", 4154122, "sio-msv", } m["sio-mor"] = { "Missouri River Siouan", 26807266, "sio", } m["sio-msv"] = { "Mississippi Valley Siouan", 12637104, "sio", } m["sio-ohv"] = { "Ohio Valley Siouan", 21070931, "sio", } m["sit"] = { "Sino-Tibetan", 45961, aliases = {"Trans-Himalayan"}, } m["sit-aao"] = { "Central Naga", 615474, "sit", } m["sit-alm"] = { "Almora", nil, "sit-whm", } m["sit-bai"] = { "Bai", 35103, "sit-mba", } m["sit-bdi"] = { "Bodish", 1814078, "sit", } m["sit-cln"] = { "Cai-Long", 107182612, "sit-mba", aliases = {"Ta-Li"}, } m["sit-dhi"] = { "Dhimalish", 1207648, "sit", } m["sit-ebo"] = { "East Bodish", 56402, "sit-bdi", } m["sit-egy"] = { "East rGyalrongic", 832026, "sit-rgy", } m["sit-ers"] = { "Ersuic", 56335, "sit", } m["sit-gma"] = { "Greater Magaric", 55612963, "sit", } m["sit-gsi"] = { "Greater Siangic", 52698851, "sit", } m["sit-hrs"] = { "Hrusish", 1632501, "sit", aliases = {"Southeast Kamengic"}, } m["sit-jnp"] = { "Jingphoic", nil, "sit-jpl", aliases = {"Jingpho"}, } m["sit-jpl"] = { "Kachin-Luic", 1515454, "tbq-bkj", aliases = {"Jingpho-Luish", "Jingpho-Asakian", "Kachinic"}, } m["sit-kch"] = { "Konyak-Chang", nil, "sit-kon", } m["sit-kha"] = { "Kham", 33305, "sit-gma", } m["sit-khb"] = { "Kho-Bwa", 6401917, "sit", aliases = {"Bugunish", "Kamengic"}, } m["sit-khw"] = { "Western Kho-Bwa", nil, "sit-khb", } m["sit-khc"] = { "Chug-Lish", nil, "sit-khw", aliases = {"Duhumbi-Khispi"}, } m["sit-khm"] = { "Mey-Sartang", nil, "sit-khw", aliases = {"Sartang-Sherdukpen"}, } m["sit-kic"] = { "Central Kiranti", nil, "sit-kir", } m["sit-kie"] = { "Eastern Kiranti", nil, "sit-kir", } m["sit-kin"] = { "Kinnauric", nil, "sit-whm", aliases = {"Kinnauri"}, } m["sit-kir"] = { "Kiranti", 922148, "sit", } m["sit-kiw"] = { "Western Kiranti", 922148, "sit-kir", } m["sit-kon"] = { "Northern Naga", 774590, "tbq-bkj", aliases = {"Konyakian", "Konyak"}, } m["sit-kyk"] = { "Kyirong-Kagate", 6450957, "sit-tib", } m["sit-lab"] = { "Ladakhi-Balti", 6450957, "sit-tib", } m["sit-las"] = { "Lahuli-Spiti", 6473510, "sit-tib", } m["sit-luu"] = { "Luish", 55621439, "sit-jpl", aliases = {"Asakian", "Sak"}, } m["sit-mar"] = { "Maringic", nil, "sit-tma", } m["sit-mba"] = { "Macro-Bai", 16963847, "sit-sba", aliases = {"Greater Bai"}, } m["sit-mdz"] = { "Midzu", 6843504, "sit", aliases = {"Geman", "Midzuish", "Miju-Meyor", "Southern Mishmi"}, } m["sit-mnz"] = { "Mondzish", 6898839, "tbq-lob", aliases = {"Mangish"}, } m["sit-mru"] = { "Mruic", 16908870, "sit", aliases = {"Mru-Hkongso"}, } m["sit-nas"] = { "Naish", 25047956, "sit-nax", } m["sit-nax"] = { "Naic", 6982999, "tbq-buq", aliases = {"Naxish"}, } m["sit-nba"] = { "Northern Bai", 122463830, "sit-bai", } m["sit-new"] = { "Newaric", 55625069, "sit", } m["sit-nng"] = { "Nungish", 1515482, "sit", aliases = {"Nung"}, } m["sit-qia"] = { "Qiangic", 1636765, "tbq-buq", } m["sit-rgy"] = { "Rgyalrongic", 56936, "sit-qia", aliases = {"Jiarongic"}, } m["sit-sba"] = { "Sino-Bai", nil, "sit", aliases = {"Greater Bai"}, } m["sit-tam"] = { "Tamangic", 3309439, "sit", aliases = {"West Bodish"}, } m["sit-tan"] = { "Tani", 3217538, "sit", } m["sit-tib"] = { "Tibetic", 1641150, "sit-bdi", protoLanguage = "otb", } m["sit-tja"] = { "Tujia", nil, "sit", } m["sit-tma"] = { "Tangkhul-Maring", nil, "sit", } m["sit-tng"] = { "Tangkhulic", 1516657, "sit-tma", aliases = {"Tangkhul"}, } m["sit-tno"] = { "Tangsa-Nocte", nil, "sit-kon", } m["sit-tsk"] = { "Tshangla", nil, "sit", } m["sit-wgy"] = { "West rGyalrongic", nil, "sit-rgy" } m["sit-whm"] = { "West Himalayish", 2301695, "sit", } m["sit-zem"] = { "Zeme", 189291, "sit", aliases = {"Zeliangrong", "Zemeic"}, } m["sla"] = { "Slavic", 23526, "ine-bsl", aliases = {"Slavonic"}, } m["smi"] = { "Sami", 56463, "urj", aliases = {"Saami", "Samic", "Saamic"}, } m["son"] = { "Songhay", 505198, "ssa", aliases = {"Songhai"}, } m["sqj"] = { "Albanian", 8748, "ine", } m["ssa"] = { "Nilo-Saharan", -- possibly not a genetic grouping 33705, } m["ssa-fur"] = { "Fur", 2989512, "ssa", } m["ssa-klk"] = { "Kuliak", 1791476, "ssa", aliases = {"Rub"}, } m["ssa-kom"] = { "Koman", 1781084, "ssa", } m["ssa-sah"] = { "Saharan", 1757661, "ssa", } m["syd"] = { "Samoyedic", 34005, "urj", aliases = {"Samoyed", "Samodeic"}, } m["syd-ene"] = { "Enets", 29942, "syd", } m["tai"] = { "Tai", 749720, "qfa-bet", aliases = {"Daic"}, } m["tai-wen"] = { "Wenma-Southwestern Tai", nil, "tai", } m["tai-tay"] = { "Tày", nil, "tai-wen", } m["tai-sap"] = { "Sapa-Southwestern Tai", nil, "tai-wen", aliases = {"Sapa-Thai"}, } m["tai-swe"] = { "Southwestern Tai", 10889250, "tai-sap", } m["tai-cho"] = { "Chongzuo Tai", 13216, "tai", } m["tai-cen"] = { "Central Tai", 5061891, "tai", } m["tai-nor"] = { "Northern Tai", 7059014, "tai", } m["tbq"] = { "Tibeto-Burman", 34064, "sit", } m["tbq-anp"] = { "Angami-Pochuri", 530460, "sit", } m["tbq-axi"] = { "Axioid", nil, "tbq-sel", } m["tbq-bdg"] = { "Bodo-Garo", 4090000, "tbq-bkj", } m["tbq-bis"] = { "Bisoid", 48844742, "tbq-slo", } m["tbq-bka"] = { "Bi-Ka", 12627890, "tbq-slo", } m["tbq-bkj"] = { "Sal", 889900, "sit", -- Brahmaputran appears to be Glottolog's term aliases = {"Bodo-Konyak-Jinghpaw", "Brahmaputran", "Jingpho-Konyak-Bodo"}, } m["tbq-brm"] = { "Burmish", 865713, "tbq-lob", } m["tbq-buq"] = { "Burmo-Qiangic", 16056278, "sit", aliases = {"Eastern Tibeto-Burman"}, } m["tbq-drp"] = { "Downriver Phula", 7188378, "tbq-rph", } m["tbq-han"] = { "Hanoid", 17004185, "tbq-slo", } m["tbq-hph"] = { "Highland Phula", nil, "tbq-sel", } m["tbq-jin"] = { "Jino", 6202716, "tbq-slo", } m["tbq-kzh"] = { "Kazhuoish", 48834669, "tbq-lol", } m["tbq-kuk"] = { "Kuki-Chin", 832413, "sit", aliases = {"Kukish", "South-Central Tibeto-Burman"}, } m["tbq-lal"] = { "Lalo", 56548, "tbq-lso", } m["tbq-lho"] = { "Lahoish", nil, "tbq-lol", } m["tbq-llo"] = { "Lipo-Lolopo", nil, "tbq-lso", } m["tbq-lob"] = { "Lolo-Burmese", 1635712, "tbq-buq", } m["tbq-lol"] = { "Loloish", 37035, "tbq-lob", aliases = {"Yi", "Ngwi", "Nisoic"}, } m["tbq-lso"] = { "Lisoish", 6559055, "tbq-lol", } m["tbq-lwo"] = { "Lawoish", 48847673, "tbq-lol", } m["tbq-muj"] = { "Muji", 11221327, "tbq-hph", } m["tbq-nas"] = { "Nasoid", nil, "tbq-nlo", } m["tbq-nis"] = { "Nisu", 56404, "tbq-nlo", } m["tbq-nlo"] = { "Northern Loloish", 7058676, "tbq-nso", } m["tbq-nso"] = { "Nisoish", 56990, "tbq-lol", } m["tbq-nus"] = { "Nusoish", 114245231, "tbq-lol", } m["tbq-phw"] = { "Phowa", 7187959, "tbq-hph", } m["tbq-rph"] = { "Riverine Phula", nil, "tbq-sel", } m["tbq-sel"] = { "Southeastern Loloish", 16111894, "tbq-nso", } m["tbq-sil"] = { "Siloid", 60787071, "tbq-slo", } m["tbq-slo"] = { "Southern Loloish", 5649340, "tbq-lol", } m["tbq-tal"] = { "Taloid", 48804018, "tbq-lso", } m["tbq-urp"] = { "Upriver Phula", 7187058, "tbq-rph", } m["trk"] = { "Turkic", 34090, } m["trk-cmn"] = { "Common Turkic", 1126028, "trk", aliases = {"Shaz Turkic", "Shaz-Turkic"}, } m["trk-kar"] = { "Karluk", 703173, "trk-cmn", aliases = {"Qarluq", "Uyghur-Uzbek", "Southeastern Turkic"}, } m["trk-kbu"] = { "Kipchak-Bulgar", 3512539, "trk-kip", aliases = {"Uralian", "Uralo-Caspian"}, } m["trk-kcu"] = { "Kipchak-Cuman", 4370412, "trk-kip", aliases = {"Ponto-Caspian"}, } m["trk-kip"] = { "Kipchak", 1339898, "trk-cmn", -- Russian Wikipedia article [[w:ru:Западнотюркские_языки]] says "Western Turkic" is used by N.A. Baskakov and includes Oghuz, Kipchak and Karluk. -- Azerbaijani Wikipedia article [[w:az:Qərbi_türk_dilləri]] clarifies that "Western Turkic" is not a clade. other_names = {"Western Turkic"}, aliases = {"Kypchak", "Qypchaq", "Northwestern Turkic"}, protoLanguage = "qwm", } m["trk-kkp"] = { "Kyrgyz-Kipchak", 4221189, "trk-kip", } m["trk-kno"] = { "Kipchak-Nogai", 4326954, "trk-kip", aliases = {"Aralo-Caspian"}, } m["trk-nsb"] = { "North Siberian Turkic", 4537269, "trk-sib", aliases = {"Northern Siberian Turkic"}, } m["trk-ogr"] = { "Oghur", 1422731, "trk", aliases = {"Lir-Turkic", "r-Turkic"}, } m["trk-ogz"] = { "Oghuz", 494600, "trk-cmn", aliases = {"Southwestern Turkic"}, } m["trk-sib"] = { "Siberian Turkic", 354353, "trk-cmn", other_names = {"Northern Turkic"}, -- per [[w:ru:Восточнотюркские_языки]], "Eastern Turkic" is an alias for Siberian Turkic in the work of O.A. Mudrak, -- but has a different non-clade meaning in the older work of N.A. Baskakov. aliases = {"Eastern Turkic", "Northeastern Turkic"}, } m["trk-ssb"] = { "South Siberian Turkic", nil, "trk-sib", aliases = {"Southern Siberian Turkic"}, } m["tup"] = { "Tupian", 34070, aliases = {"Tupi"}, } m["tup-gua"] = { "Tupi-Guarani", 148610, "tup", aliases = {"Tupí-Guaraní"}, } m["tuw"] = { "Tungusic", 34230, aliases = {"Manchu-Tungus", "Tungus"}, } m["tuw-ewe"] = { "Ewenic", 105889448, "tuw", aliases = {"Northern Tungusic"}, } m["tuw-jrc"] = { "Jurchenic", 105889432, "tuw", aliases = {"Manchuric"}, } m["tuw-nan"] = { "Nanaic", 105889264, "tuw", } m["tuw-udg"] = { "Udegheic", 105889266, "tuw", } m["urj"] = { "Uralic", 34113, varieties = {"Finno-Ugric"}, } m["urj-fin"] = { "Finnic", 33328, "urj", aliases = {"Baltic-Finnic", "Balto-Finnic", "Fennic"}, } m["urj-mdv"] = { "Mordvinic", 627313, "urj", } m["urj-prm"] = { "Permic", 161493, "urj", } m["urj-ugr"] = { "Ugric", 156631, "urj", } m["wak"] = { "Wakashan", 60069, } m["wen"] = { "Sorbian", 25442, "zlw", aliases = {"Lusatian", "Wendish"}, } m["xgn"] = { "Mongolic", 33750, "qfa-xgs", aliases = {"Mongolian"}, } m["xgn-cen"] = { "Central Mongolic", 28719447, "xgn", protoLanguage = "xng-lat", } m["xgn-sou"] = { "Southern Mongolic", nil, "xgn", protoLanguage = "xng-ear", } m["xgn-shr"] = { "Shirongolic", 107539435, "xgn-sou", } m["xme"] = { "Median", nil, "ira-mpr", protoLanguage = "xme-old", } m["xme-ttc"] = { "Tatic", nil, "xme", } m["xnd"] = { "Na-Dene", 26986, "qfa-dny", aliases = {"Na-Dené"}, } m["xsc"] = { "Scythian", nil, "ira-nei", } m["xsc-sak"] = { "Saka", nil, "xsc-skw", aliases = {"Sakan"}, } m["xsc-sar"] = { "Sarmatian", nil, "xsc", } m["xsc-skw"] = { "Saka-Wakhi", nil, "xsc", } m["yok"] = { "Yokuts", 34249, "nai-you", aliases = {"Yokutsan", "Mariposan", "Mariposa"}, } m["ypk"] = { "Yupik", 27970, "esx-esk", aliases = {"Yup'ik", "Yuit"}, } m["yrk"] = { "Nenets", 36452, "syd", } m["zhx"] = { "Sinitic", 33857, "sit-sba", aliases = {"Chinese"}, protoLanguage = "och", } m["zhx-com"] = { "Coastal Min", 20667215, "zhx-min", } m["zhx-inm"] = { "Inland Min", 20667237, "zhx-min", } m["zhx-man"] = { "Mandarinic", nil, "zhx", protoLanguage = "cmn-ear", } m["zhx-min"] = { "Min", 56504, "zhx", } m["zhx-nan"] = { "Southern Min", 36495, "zhx-com", } m["zhx-pin"] = { "Pinghua", 2735715, "zhx", protoLanguage = "ltc", } m["zhx-yue"] = { "Yue", 7033959, "zhx", protoLanguage = "ltc", } m["zle"] = { "East Slavic", 144713, "sla", } m["zls"] = { "South Slavic", 146665, "sla", } m["zlw"] = { "West Slavic", 145852, "sla", } m["zlw-lch"] = { "Lechitic", 742782, "zlw", aliases = {"Lekhitic"}, } m["zlw-pom"] = { "Pomeranian", nil, "zlw-lch", } m["znd"] = { "Zande", 8066072, "nic-ubg", } return require("Module:languages").finalizeData(m, "family") b2ls9igr0aaopschwn348mbj9eodtxj 231359 231358 2026-04-14T05:41:33Z Lee 19 [[:en:Module:families/data]] වෙතින් එක් සංශෝධනයක් 231358 Scribunto text/plain --[=[ This module contains definitions for all language family codes on Wiktionary. ]=]-- local m = {} m["aav"] = { "Austroasiatic", 33199, aliases = {"Austro-Asiatic"}, } m["aav-khs"] = { "Khasian", 3073734, "aav", aliases = {"Khasic"}, } m["aav-nic"] = { "Nicobarese", 217380, "aav", } m["aav-pkl"] = { "Pnar-Khasi-Lyngngam", nil, "aav-khs", } m["afa"] = { "Afroasiatic", 25268, aliases = {"Afro-Asiatic"}, } m["alg"] = { "Algonquian", 33392, "aql", } m["alg-abp"] = { "Abenaki-Penobscot", 197936, "alg-eas", } m["alg-ara"] = { "Arapahoan", 2153686, "alg", } m["alg-eas"] = { "Eastern Algonquian", 2257525, "alg", } m["alg-sfk"] = { "Sac-Fox-Kickapoo", 1440172, "alg", } m["alv"] = { "Atlantic-Congo", 771124, "nic", } m["alv-aah"] = { "Ayere-Ahan", 750953, "alv-von", } m["alv-ada"] = { "Adamawa", 32906, "alv-sav", } m["alv-bag"] = { "Baga", 2746083, "alv-mel", } m["alv-bak"] = { "Bak", 1708174, "alv-sng", } m["alv-bam"] = { "Bambukic", 4853456, "alv-ada", aliases = {"Yungur-Jen"}, } m["alv-bny"] = { "Banyum", 2892477, "alv-nyn", } m["alv-bua"] = { "Bua", 4982094, "alv-mbd", } m["alv-bwj"] = { "Bikwin-Jen", 84542501, "alv-bam", } m["alv-cng"] = { "Cangin", 1033184, "alv-fwo", } m["alv-ctn"] = { "Central Tano", 1658486, "alv-ptn", aliases = {"Akan"}, } m["alv-dlt"] = { "Delta Edoid", nil, "alv-edo", } m["alv-dur"] = { "Duru", 5316788, "alv-lni", } m["alv-ede"] = { "Ede", 35368, "alv-yor", } m["alv-edk"] = { "Edekiri", 5336735, "alv-yrd", } m["alv-edo"] = { "Edoid", 1287469, "alv-von", } m["alv-eeo"] = { "Edo-Esan-Ora", 12630439, "alv-nce", } m["alv-fli"] = { "Fali", 3450166, "alv", } m["alv-fwo"] = { "Fula-Wolof", 12631267, "alv-sng", } m["alv-gbe"] = { "Gbe", 668284, "alv-von", } m["alv-gda"] = { "Ga-Dangme", 3443338, "alv-kwa", } m["alv-gng"] = { "Guang", 684009, "alv-ptn", } m["alv-gtm"] = { "Ghana-Togo Mountain", 493020, "alv-kwa", aliases = {"Togo Remnant", "Central Togo"}, } m["alv-hei"] = { "Heiban", 108752116, "alv-the", } m["alv-ido"] = { "Idomoid", 974196, "alv-von", } m["alv-igb"] = { "Igboid", 1429100, "alv-von", } m["alv-jfe"] = { "Jola-Felupe", 1708174, "alv-jol", aliases = {"Ejamat"}, } m["alv-jol"] = { "Jola", 35176, "alv-bak", aliases = {"Diola"}, } m["alv-kim"] = { "Kim", 6409701, "alv-mbd", } m["alv-kis"] = { "Kissi", 35696, "alv-mel", } m["alv-krb"] = { "Karaboro", 4213541, "alv-snf", } m["alv-ktg"] = { "Ka-Togo", 5972796, "alv-gtm", } m["alv-kul"] = { "Kulango", 16977424, "alv-sav", aliases = {"Kulango-Lorhon", "Kulango-Lorom"}, } m["alv-kwa"] = { "Kwa", 33430, "nic-vco", } m["alv-lag"] = { "Lagoon", 111210042, "alv-kwa", } m["alv-lek"] = { "Leko", 6520642, other_names = {"Sambaic"}, -- appears to be an alias in Glottolog "alv-lni", } m["alv-lim"] = { "Limba", 35825, "alv", } m["alv-lni"] = { "Leko-Nimbari", 1708170, "alv-ada", other_names = {"Central Adamawa"}, aliases = {"Chamba-Mumuye"}, } m["alv-mbd"] = { "Mbum-Day", 6799816, "alv-ada", } m["alv-mbm"] = { "Mbum", 6799814, "alv-mbd", } m["alv-mel"] = { "Mel", 12122355, "alv", } m["alv-mum"] = { "Mumuye", 84607009, "alv-mye", } m["alv-mye"] = { "Mumuye-Yendang", 6935539, "alv-lni", } m["alv-nal"] = { "Nalu", nil, "alv-sng", } m["alv-nce"] = { "North-Central Edoid", 16110869, "alv-edo", } m["alv-ngb"] = { "Nupe-Gbagyi", 12638649, "alv-nup", aliases = {"Nupe-Gbari"}, } m["alv-ntg"] = { "Na-Togo", nil, "alv-gtm", } m["alv-nup"] = { "Nupoid", 1429143, "alv-von", } m["alv-nwd"] = { "Northwestern Edoid", 16111012, "alv-edo", } m["alv-nyn"] = { "Nyun", nil, "alv-fwo", } m["alv-pap"] = { "Papel", 7132562, "alv-bak", } m["alv-pph"] = { "Phla-Pherá", 3849625, "alv-gbe", } m["alv-ptn"] = { "Potou-Tano", 1475003, "alv-kwa", } m["alv-sav"] = { "Savanna", 4403672, "nic-vco", aliases = {"Savannas"}, } m["alv-sma"] = { "Supyire-Mamara", 4446348, "alv-snf", aliases = {"Suppire-Mamara"}, } m["alv-snf"] = { "Senufo", 33795, "alv", aliases = {"Senufic", "Senoufo", "Sénoufo"}, } m["alv-sng"] = { "Senegambian", 1708753, "alv", } m["alv-snr"] = { "Senari", 4416084, "alv-snf", } m["alv-swd"] = { "Southwestern Edoid", 12633903, "alv-edo", } m["alv-tal"] = { "Talodi", 12643302, "alv-the", } m["alv-tdj"] = { "Tagwana-Djimini", 7675362, "alv-snf", } m["alv-ten"] = { "Tenda", 3217535, "alv-fwo", } m["alv-the"] = { "Talodi-Heiban", 1521145, "alv", } m["alv-von"] = { "Volta-Niger", 34177, "nic-vco", } m["alv-wan"] = { "Wara-Natyoro", 7968830, "alv-sav", } m["alv-wjk"] = { "Waja-Kam", nil, "alv-ada", } m["alv-yek"] = { "Yekhee", nil, "alv-nce", } m["alv-yor"] = { "Yoruba", nil, "alv-edk", } m["alv-yrd"] = { "Yoruboid", 1789745, "alv-von", } m["alv-yun"] = { "Yungur", 84601642, "alv-bam", aliases = {"Bena-Mboi"}, } m["apa"] = { "Apachean", 27758, "ath", aliases = {"Southern Athabaskan"}, } m["aqa"] = { "Alacalufan", 1288430, } m["aql"] = { "Algic", 721612, aliases = {"Algonquian-Ritwan", "Algonquian-Wiyot-Yurok"}, } m["art"] = { "constructed", 33215, "qfa-not", aliases = {"artificial", "planned"}, } m["ath"] = { "Athabaskan", 27475, "xnd", } m["ath-nor"] = { "North Athabaskan", 20738, "ath", aliases = {"Northern Athabaskan"}, } m["ath-pco"] = { "Pacific Coast Athabaskan", 20654, "ath", } m["auf"] = { "Arauan", 626772, aliases = {"Arahuan", "Arauán", "Arawa", "Arawan", "Arawán"}, } --[=[ Exceptional language and family codes for Australian Aboriginal languages can use the prefix "aus-", though "aus" is no longer itself a family code. ]=]-- m["aus-arn"] = { "Arnhem", 2581700, aliases = {"Gunwinyguan", "Macro-Gunwinyguan"}, } m["aus-bub"] = { "Bunuban", 2495148, aliases = {"Bunaban"}, } m["aus-cww"] = { "Central New South Wales", 5061507, "aus-pam", } m["aus-dal"] = { "Daly", 2478079, } m["aus-dyb"] = { "Dyirbalic", 1850666, "aus-pam", } m["aus-gar"] = { "Garawan", 5521951, } m["aus-gun"] = { "Gunwinyguan", 2581700, "aus-arn", aliases = {"Gunwingguan"}, } m["aus-jar"] = { "Jarrakan", 2039423, } m["aus-kar"] = { "Karnic", 4215578, "aus-pam", } m["aus-mir"] = { "Mirndi", 4294095, } m["aus-nga"] = { "Ngayarda", 16153490, "aus-psw", } m["aus-nyu"] = { "Nyulnyulan", 2039408, } m["aus-pam"] = { "Pama-Nyungan", 33942, } m["aus-pmn"] = { "Paman", 2640654, "aus-pam", } m["aus-psw"] = { "Southwest Pama-Nyungan", 2258160, "aus-pam", } m["aus-rnd"] = { "Arandic", 4784071, "aus-pam", } m["aus-tnk"] = { "Tangkic", 1823065, } m["aus-wdj"] = { "Iwaidjan", 4196968, aliases = {"Yiwaidjan"}, } m["aus-wor"] = { "Worrorran", 2038619, } m["aus-yid"] = { "Yidinyic", 4205849, "aus-pam", } m["aus-yng"] = { "Yangmanic", 42727644, } m["aus-yol"] = { "Yolngu", 2511254, "aus-pam", aliases = {"Yolŋu", "Yolngu Matha"}, } m["aus-yuk"] = { "Yuin-Kuric", 3833021, "aus-pam", } m["awd"] = { "Arawak", 626753, aliases = {"Arawakan", "Maipurean", "Maipuran"}, } m["awd-nwk"] = { "Nawiki", nil, "awd", aliases = {"Newiki"}, } m["awd-taa"] = { "Ta-Arawak", 7672731, "awd", aliases = {"Ta-Arawakan", "Ta-Maipurean"}, } m["azc"] = { "Uto-Aztecan", 34073, aliases = {"Uto-Aztekan"}, } m["azc-cup"] = { "Cupan", 19866871, "azc-tak", } m["azc-dur"] = { "Durango Nahuatl", 2386361, "azc-nah", aliases = {"Mexicanero"} } m["azc-hua"] = { "Huasteca Nahuatl", 3832950, "azc-nah", } m["azc-nah"] = { "Nahuan", 11965602, "azc", aliases = {"Aztecan"}, } m["azc-num"] = { "Numic", 2657541, "azc", } m["azc-pim"] = { "Piman", 7194600, "azc", aliases = {"Tepiman"}, } m["azc-tak"] = { "Takic", 1280305, "azc", } m["azc-trc"] = { "Taracahitic", 4245032, "azc", aliases = {"Taracahitan"}, } m["bad"] = { "Banda", 806234, "nic-ubg", } m["bad-cnt"] = { "Central Banda", 3438391, "bad", } m["bai"] = { "Bamileke", 806005, "nic-gre", } m["bat"] = { "Baltic", 33136, "ine-bsl", } m["bat-eas"] = { "East Baltic", 149944, "bat", } m["bat-wes"] = { "West Baltic", 149946, "bat", } m["ber"] = { "Berber", 25448, "afa", aliases = {"Tamazight"}, } m["bnt"] = { "Bantu", 33146, "nic-bds", } m["bnt-baf"] = { "Bafia", 799784, "bnt", } m["bnt-bbo"] = { "Bafo-Bonkeng", nil, "bnt-saw", } m["bnt-bdz"] = { "Boma-Dzing", 1729203, "bnt", } m["bnt-bek"] = { "Bekwilic", nil, "bnt-ndb", } m["bnt-bki"] = { "Bena-Kinga", 16113307, "bnt-bne", } m["bnt-bmo"] = { "Bangi-Moi", nil, "bnt-bnm", } m["bnt-bne"] = { "Northeast Bantu", 7057832, "bnt", } m["bnt-bnm"] = { "Bangi-Ntomba", 806477, "bnt-bte", } m["bnt-boa"] = { "Boan", 4931250, "bnt", aliases = {"Buan", "Ababuan"}, } m["bnt-bot"] = { "Botatwe", 4948532, "bnt", } m["bnt-bsa"] = { "Basaa", 809739, "bnt", } m["bnt-bsh"] = { "Bushoong", 5001551, "bnt-bte", } m["bnt-bso"] = { "Southern Bantu", 980498, "bnt", } m["bnt-bta"] = { "Bati-Angba", 4869303, "bnt-boa", other_names = {"Late Bomokandian"}, aliases = {"Bwa"}, } m["bnt-btb"] = { "Beti", 35118, "bnt", } m["bnt-bte"] = { "Bangi-Tetela", 4855181, "bnt", } m["bnt-bun"] = { "Buja-Ngombe", 4986733, "bnt-mbb", } m["bnt-chg"] = { "Chaga", 33016, "bnt-cht", } m["bnt-cht"] = { "Chaga-Taita", nil, "bnt-bne", } m["bnt-clu"] = { "Chokwe-Luchazi", 3339273, "bnt", } m["bnt-com"] = { "Comorian", 33077, "bnt-sab", } m["bnt-glb"] = { "Great Lakes Bantu", 5599420, "bnt-bne", } m["bnt-haj"] = { "Haya-Jita", 25502360, "bnt-glb", } m["bnt-kak"] = { "Kako", nil, "bnt-pob", } m["bnt-kav"] = { "Kavango", 116544179, "bnt-ksb", } m["bnt-kbi"] = { "Komo-Bira", 6428591, "bnt-boa", } m["bnt-kel"] = { "Kele", 1738162, "bnt-kts", aliases = {"Sheke"}, } m["bnt-kil"] = { "Kilombero", 6408121, "bnt", } m["bnt-kka"] = { "Kikuyu-Kamba", 16114410, "bnt-bne", aliases = {"Thagiicu"}, } m["bnt-kmb"] = { "Kimbundu", 16947687, "bnt", } m["bnt-kng"] = { "Kongo", 6429214, "bnt", } m["bnt-kpw"] = { "Kpwe", 36428, "bnt-saw", } m["bnt-ksb"] = { "Kavango-Southwest Bantu", 6379098, "bnt", } m["bnt-kts"] = { "Kele-Tsogo", 6385577, "bnt", } m["bnt-lbn"] = { "Luban", 4536504, "bnt", } m["bnt-leb"] = { "Lebonya", 6511395, "bnt", } m["bnt-lgb"] = { "Lega-Binja", 6517694, "bnt", } m["bnt-lok"] = { "Logooli-Kuria", nil, "bnt-glb", } m["bnt-lub"] = { "Luba", nil, "bnt-lbn", } m["bnt-lun"] = { "Lunda", 6704091, "bnt", } m["bnt-mak"] = { "Makua", 6740431, "bnt-bso", aliases = {"Makhuwa"}, } m["bnt-mbb"] = { "Mboshi-Buja", 6799764, "bnt", } m["bnt-mbe"] = { "Mbole-Enya", 6799728, "bnt", } m["bnt-mbi"] = { "Mbinga", nil, "bnt-rur", } m["bnt-mbo"] = { "Mboshi", 6799763, "bnt-mbb", } m["bnt-mbt"] = { "Mbete", 1346910, "bnt-tmb", aliases = {"Mbere"}, } m["bnt-mby"] = { "Mbeya", nil, "bnt-ruk", } m["bnt-mij"] = { "Mijikenda", 6845474, "bnt-sab", } m["bnt-mka"] = { "Makaa", nil, "bnt-ndb", } m["bnt-mne"] = { "Manenguba", 31147471, "bnt", aliases = {"Mbo", "Ngoe"}, } m["bnt-mnj"] = { "Makaa-Njem", 1603899, "bnt-pob", } m["bnt-mon"] = { "Mongo", nil, "bnt-bnm", } m["bnt-mra"] = { "Mbugwe-Rangi", 6799795, "bnt", } m["bnt-msl"] = { "Masaba-Luhya", 12636428, "bnt-glb", } m["bnt-mwi"] = { "Mwika", nil, "bnt-ruk", } m["bnt-ncb"] = { "Northeast Coast Bantu", 7057848, "bnt-bne", } m["bnt-ndb"] = { "Ndzem-Bomwali", nil, "bnt-mnj", } m["bnt-ngn"] = { "Ngondi-Ngiri", 7022532, "bnt-mbb", } m["bnt-ngu"] = { "Nguni", 961559, "bnt-bso", aliases = {"Ngoni"}, } m["bnt-nya"] = { "Nyali", 7070832, "bnt-leb", } m["bnt-nyb"] = { "Nyanga-Buyi", 7070882, "bnt", } m["bnt-nyg"] = { "Nyoro-Ganda", 12638666, "bnt-glb", } m["bnt-nys"] = { "Nyasa", 7070921, "bnt", } m["bnt-nze"] = { "Nzebi", 1755498, "bnt-tmb", aliases = {"Njebi"}, } m["bnt-ova"] = { "Ovambo", 36489, "bnt-swb", aliases = {"Oshivambo", "Oshiwambo", "Owambo"}, } m["bnt-par"] = { "Pare", nil, "bnt-ncb", } m["bnt-pen"] = { "Pende", 7162373, "bnt", } m["bnt-pob"] = { "Pomo-Bomwali", nil, "bnt", } m["bnt-ruk"] = { "Rukwa", 7378902, "bnt", } m["bnt-run"] = { "Rungwe", nil, "bnt-ruk", } m["bnt-rur"] = { "Rufiji-Ruvuma", 7377947, "bnt", } m["bnt-ruv"] = { "Ruvu", nil, "bnt-ncb", } m["bnt-rvm"] = { "Ruvuma", nil, "bnt-rur", } m["bnt-sab"] = { "Sabaki", 2209395, "bnt-ncb", } m["bnt-saw"] = { "Sawabantu", 532003, "bnt", } m["bnt-sbi"] = { "Sabi", 7396071, "bnt", } m["bnt-seu"] = { "Seuta", nil, "bnt-ncb", } m["bnt-shh"] = { "Shi-Havu", nil, "bnt-glb", } m["bnt-sho"] = { "Shona", 2904660, "bnt", } m["bnt-sir"] = { "Sira", 1436372, "bnt", aliases = {"Shira-Punu"}, } m["bnt-ske"] = { "Soko-Kele", nil, "bnt-bte", } m["bnt-sna"] = { "Sena", nil, "bnt-nys", } m["bnt-sts"] = { "Sotho-Tswana", 2038386, "bnt-bso", } m["bnt-swb"] = { "Southwest Bantu", 116543539, "bnt-ksb", } m["bnt-swh"] = { "Swahili", nil, "bnt-sab", } m["bnt-tek"] = { "Teke", 36528, "bnt-tmb", } m["bnt-tet"] = { "Tetela", 7706059, "bnt-bte", } m["bnt-tkc"] = { "Central Teke", 36473, "bnt-tek", } m["bnt-tkm"] = { "Takama", nil, "bnt-bne", } m["bnt-tmb"] = { "Teke-Mbede", 7695332, "bnt", aliases = {"Teke-Mbere"}, } m["bnt-tso"] = { "Tsogo", 2458420, other_names = {"Okani"}, --appears to be an alias in Glottolog "bnt-kts", } m["bnt-tsr"] = { "Tswa-Ronga", 12643962, "bnt-bso", } m["bnt-yak"] = { "Yaka", 8047027, "bnt", } m["bnt-yko"] = { "Yasa-Kombe", nil, "bnt-saw", } m["bnt-zbi"] = { "Zamba-Binza", nil, "bnt-bnm", } m["btk"] = { "Batak", 1998595, "poz-nws", } --[=[ Exceptional language and family codes for Central American Indian languages may use the prefix "cai-", though "cai" is no longer itself a family code. ]=]-- --[=[ Exceptional language and family codes for Caucasian languages can use the prefix "cau-", though "cau" is no longer itself a family code. ]=]-- m["cau-abz"] = { "Abkhaz-Abaza", 4663617, "cau-nwc", other_names = {"Abkhaz-Tapanta"}, aliases = {"Abazgi"}, } m["cau-and"] = { "Andian", 492152, "cau-ava", aliases = {"Andic"}, } m["cau-ava"] = { "Avaro-Andian", 4055404, "cau-nec", aliases = {"Avar-Andian", "Avar-Andi", "Avar-Andic"}, } m["cau-cir"] = { "Circassian", 858543, "cau-nwc", aliases = {"Cherkess"}, } m["cau-drg"] = { "Dargwa", 5222637, "cau-nec", other_names = {"Dargin"}, } m["cau-esm"] = { "Eastern Samur", nil, "cau-sam", } m["cau-ets"] = { "East Tsezian", 121437666, "cau-tsz", aliases = {"East Tsezic", "East Didoic"}, } m["cau-lzg"] = { "Lezghian", 2144370, "cau-nec", aliases = {"Lezgi", "Lezgian", "Lezgic"}, } m["cau-nkh"] = { "Nakh", 24441, "cau-nec", aliases = {"North-Central Caucasian"}, } m["cau-nec"] = { "Northeast Caucasian", 27387, aliases = {"Dagestanian", "Nakho-Dagestanian", "Caspian"}, } m["cau-nwc"] = { "Northwest Caucasian", 33852, aliases = {"Abkhazo-Adyghean", "Abkhaz-Adyghe", "Pontic"}, } m["cau-sam"] = { "Samur", 15229151, "cau-lzg", } m["cau-ssm"] = { "Southern Samur", nil, "cau-sam", } m["cau-tsz"] = { "Tsezian", 1651530, "cau-nec", aliases = {"Tsezic", "Didoic"}, } m["cau-vay"] = { "Vainakh", 4102486, "cau-nkh", aliases = {"Veinakh", "Vaynakh"}, } m["cau-wsm"] = { "Western Samur", nil, "cau-sam", } m["cau-wts"] = { "West Tsezian", 121437697, "cau-tsz", aliases = {"West Tsezic", "West Didoic"}, } m["cba"] = { "Chibchan", 520478, "qfa-mch", -- or none if Macro-Chibchan is considered undemonstrated } m["ccs"] = { "Kartvelian", 34030, aliases = {"South Caucasian"}, } m["ccs-gzn"] = { "Georgian-Zan", 34030, "ccs", aliases = {"Karto-Zan"}, } m["ccs-zan"] = { "Zan", 2606912, "ccs-gzn", aliases = {"Zanuri", "Colchian"}, } m["cdc"] = { "Chadic", 33184, "afa", } m["cdc-cbm"] = { "Central Chadic", 2251547, "cdc", aliases = {"Biu-Mandara"}, } m["cdc-est"] = { "East Chadic", 2276221, "cdc", } m["cdc-mas"] = { "Masa", 2136092, "cdc", } m["cdc-wst"] = { "West Chadic", 2447774, "cdc", } m["cdd"] = { "Caddoan", 1025090, } m["cel"] = { "Celtic", 25293, "ine", } m["cel-bry"] = { "Brythonic", 156877, "cel-ins", aliases = {"Brittonic"}, } m["cel-brs"] = { "Southwestern Brythonic", 2612853, "cel-bry", aliases = {"Southwestern Brittonic"}, } m["cel-brw"] = { "Western Brythonic", 593069, "cel-bry", aliases = {"Western Brittonic"}, } m["cel-gae"] = { "Goidelic", 56433, "cel-ins", aliases = {"Gaelic"}, protoLanguage = "pgl", } m["cel-his"] = { "Hispano-Celtic", 4204136, "cel", } m["cel-ins"] = { "Insular Celtic", 214506, "cel", } m["chi"] = { "Chimakuan", 1073088, } m["chm"] = { "Mari", 973685, "urj", } m["cmc"] = { "Chamic", 2997506, "poz-mcm", } m["crp"] = { "creole or pidgin", 19682167, "qfa-cnt", } m["csu"] = { "Central Sudanic", 190822, "ssa", } m["csu-bba"] = { "Bongo-Bagirmi", 3505042, "csu", } m["csu-bbk"] = { "Bongo-Baka", 4941917, "csu-bba", } m["csu-bgr"] = { "Bagirmi", 4841948, "csu-bba", aliases = {"Bagirmic"}, } m["csu-bkr"] = { "Birri-Kresh", nil, "csu", } m["csu-ecs"] = { "Eastern Central Sudanic", 16911698, "csu", aliases = {"East Central Sudanic", "Central Sudanic East", "Lendu-Mangbetu"}, } m["csu-kab"] = { "Kaba", 6343715, "csu-bba", } m["csu-lnd"] = { "Lendu", 6522357, "csu-ecs", aliases = {"Lenduic"}, } m["csu-maa"] = { "Mangbetu", 6748874, "csu-ecs", aliases = {"Mangbetu-Asoa", "Mangbetu-Asua"}, } m["csu-mle"] = { "Mangbutu-Lese", 17009406, "csu-ecs", aliases = {"Mangbutu-Efe", "Mangbutu", "Membi-Mangbutu-Efe"}, } m["csu-mma"] = { "Moru-Madi", 6915156, "csu-ecs", } m["csu-sar"] = { "Sara", 2036691, "csu-bba", } m["csu-val"] = { "Vale", 7909520, "csu-bba", } m["cus"] = { "Cushitic", 33248, "afa", } m["cus-cen"] = { "Central Cushitic", 56569, "cus", } m["cus-eas"] = { "East Cushitic", 56568, "cus", } m["cus-hec"] = { "Highland East Cushitic", 56524, "cus-eas", } m["cus-som"] = { "Somaloid", 56774, "cus-eas", aliases = {"Sam", "Macro-Somali"}, } m["cus-sou"] = { "South Cushitic", 56525, "cus", } m["day"] = { "Land Dayak", 2760613, "poz", } m["del"] = { "Lenape", 2665761, "alg-eas", aliases = {"Delaware"}, } m["den"] = { "Slavey", 13272, "ath-nor", aliases = {"Slave", "Slavé"}, } m["dmn"] = { "Mande", 33681, "nic", } m["dmn-bbu"] = { "Bisa-Busa", 12627956, "dmn-mde", } m["dmn-emn"] = { "East Manding", nil, "dmn-man", } m["dmn-jje"] = { "Jogo-Jeri", nil, "dmn-mjo", } m["dmn-man"] = { "Manding", 35772, "dmn-mmo", } m["dmn-mda"] = { "Mano-Dan", nil, "dmn-mse", } m["dmn-mdc"] = { "Central Mande", 5972907, "dmn-mdw", } m["dmn-mde"] = { "Eastern Mande", 12633080, "dmn", } m["dmn-mdw"] = { "Western Mande", 16113831, "dmn", } m["dmn-mjo"] = { "Manding-Jogo", 12636153, "dmn-mdc", } m["dmn-mmo"] = { "Manding-Mokole", nil, "dmn-mva", } m["dmn-mnk"] = { "Maninka", 36186, "dmn-emn", } m["dmn-mnw"] = { "Northwestern Mande", 5972910, "dmn-mdw", } m["dmn-mok"] = { "Mokole", 16935447, "dmn-mmo", } m["dmn-mse"] = { "Southeastern Mande", 5972912, "dmn-mde", } m["dmn-msw"] = { "Southwestern Mande", 12633904, "dmn-mdw", } m["dmn-mva"] = { "Manding-Vai", nil, "dmn-mjo", } m["dmn-nbe"] = { "Nwa-Beng", nil, "dmn-mse", } m["dmn-sam"] = { "Samo", 36327, "dmn-bbu", aliases = {"Samuic"}, } m["dmn-smg"] = { "Samogo", 7410000, "dmn-mnw", aliases = {"Duun-Seenku"}, } m["dmn-snb"] = { "Soninke-Bobo", 16111680, "dmn-mnw", } m["dmn-sya"] = { "Susu-Yalunka", nil, "dmn-mdc", } m["dmn-vak"] = { "Vai-Kono", nil, "dmn-mva", } m["dmn-wmn"] = { "West Manding", nil, "dmn-man", } m["dra"] = { "Dravidian", 33311, } m["dra-cen"] = { "Central Dravidian", 12628823, "dra", } m["dra-gki"] = { "Gondi-Kui", 12631610, "dra-sdt", } m["dra-gon"] = { "Gondi", 55639812, "dra-gki", } m["dra-imd"] = { "Irula-Muduga", nil, "dra-tkn", } m["dra-kan"] = { "Kannadoid", 6363888, "dra-tkn", protoLanguage = "dra-okn", } m["dra-kki"] = { "Konda-Kui", nil, "dra-gki", } m["dra-kml"] = { "Kurux-Malto", 68002822, "dra-nor", } m["dra-knk"] = { "Kolami-Naiki", 10547037, "dra-cen", } m["dra-kod"] = { "Kodagu", 67983106, "dra-tkd", } m["dra-kor"] = { "Koraga", 33394, "dra-tlk", } m["dra-mal"] = { "Malayalamoid", 6741581, "dra-tml", } m["dra-mdy"] = { "Madiya", 27602, "dra-gon", } m["dra-mlo"] = { "Malto", nil, "dra-kml", } m["dra-mur"] = { "Muria", 6938499, "dra-gon", } m["dra-nor"] = { "North Dravidian", 16110967, "dra", } m["dra-pgd"] = { "Parji-Gadaba", 10620428, "dra-cen", } m["dra-sdo"] = { "South Dravidian I", 16112843, -- Wikipedia's "South Dravidian" is South Dravidian I in this scheme. "dra-sou", aliases = {"South Dravidian"}, -- This is why I and II are used. } m["dra-sdt"] = { "South Dravidian II", 12633975, "dra-sou", aliases = {"South-Central Dravidian"}, } m["dra-sou"] = { "South Dravidian", 128886618, "dra", aliases = {"Southern Dravidian"}, } m["dra-tam"] = { "Tamiloid", 7681417, "dra-tml", protoLanguage = "oty", } m["dra-tel"] = { "Teluguic", nil, "dra-sdt", protoLanguage = "dra-ote", } m["dra-tkd"] = { "Tamil-Kodagu", 25494510, "dra-tkn", } m["dra-tkn"] = { "Tamil-Kannada", 6478506, "dra-sdo", } m["dra-tkt"] = { "Toda-Kota", 67983857, "dra-tkd", } m["dra-tlk"] = { "Tulu-Koraga", nil, "dra-sdo", } m["dra-tml"] = { "Tamil-Malayalam", 10690507, "dra-tkd", } m["egx"] = { "Egyptian", 50868, "afa", protoLanguage = "egy", } m["ero"] = { "Horpa", 56854, "sit-wgy", } m["esx"] = { "Eskimo-Aleut", 25946, } m["esx-esk"] = { "Eskimo", 25946, "esx", } m["esx-inu"] = { "Inuit", 27796, "esx-esk", } m["euq"] = { "Vasconic", 4669240, } m["gba"] = { "Gbaya", 3099986, "alv-sav", } m["gba-eas"] = { "Eastern Gbaya", nil, "gba", } m["gba-sou"] = { "Southern Gbaya", nil, "gba", } m["gba-wes"] = { "Western Gbaya", nil, "gba", } m["gem"] = { "Germanic", 21200, "ine", } m["gio"] = { "Gelao", 56401, "qfa-kra", } m["gme"] = { "East Germanic", 108662, "gem", } m["gmq"] = { "North Germanic", 106085, "gem", } m["gmq-eas"] = { "East Scandinavian", 3090263, "gmq", protoLanguage = "non-oen", } m["gmq-ins"] = { "Insular Scandinavian", nil, "gmq-wes", } m["gmq-wes"] = { "West Scandinavian", 1792570, "gmq", protoLanguage = "non-own", } m["gmw"] = { "West Germanic", 26721, "gem", } m["gmw-afr"] = { "Anglo-Frisian", 5329170, "gmw-nsg", } m["gmw-ang"] = { "Anglic", 1346342, "gmw-afr", protoLanguage = "ang", } m["gmw-fri"] = { "Frisian", 25325, "gmw-afr", protoLanguage = "ofs", } m["gmw-frk"] = { "Low Franconian", 153050, "gmw", protoLanguage = "frk", } m["gmw-hgm"] = { "High German", 52040, "gmw", protoLanguage = "goh", } m["gmw-ian"] = { "Irish Anglo-Norman", 120719384, "gmw-ang", protoLanguage = "enm", } m["gmw-lgm"] = { "Low German", 25433, "gmw-nsg", protoLanguage = "osx", } m["gmw-nsg"] = { "North Sea Germanic", 30134, "gmw", aliases = {"Ingvaeonic"}, } m["gn"] = { "Guarani", 35876, "tup-gua", aliases = {"Guaraní"}, } m["grb"] = { "Grebo proper", 35257, "kro-grb", } m["grk"] = { "Hellenic", 2042538, "ine", aliases = {"Greek"}, } m["him"] = { "Western Pahari", 10939493, "inc-pah", aliases = {"Himachali"}, } m["hmn"] = { "Hmongic", 3307894, "hmx", } m["hmx"] = { "Hmong-Mien", 33322, aliases = {"Miao-Yao"}, } m["hmx-mie"] = { "Mienic", 7992695, "hmx", } m["hok"] = { "Hokan", 33406, } m["hyx"] = { "Armenian", 8785, "ine", } m["iir"] = { "Indo-Iranian", 33514, "ine", } m["iir-nur"] = { "Nuristani", 161804, "iir", } m["nur-nor"] = { "Northern Nuristani", nil, "iir-nur", } m["nur-sou"] = { "Southern Nuristani", nil, "iir-nur", } m["ijo"] = { "Ijoid", 1325759, "nic", other_names = {"Ijaw"}, -- Ijaw may be a subfamily } m["inc"] = { "Indo-Aryan", 33577, "iir", aliases = {"Indic"}, } m["inc-bas"] = { "Bengali-Assamese", 4179137, "inc-eas", aliases = {"Assamese-Bengali", "Gauda-Kamarupa"}, } m["inc-bhi"] = { "Bhil", 4901727, "inc-cen", } m["inc-bih"] = { "Bihari", 135305, "inc-eas", } m["inc-cen"] = { "Central Indo-Aryan", 10979187, "inc", protoLanguage = "inc-asa", } m["inc-chi"] = { "Chitrali", 11732797, "inc-dar", } m["inc-dar"] = { "Dardic", 161101, "inc", protoLanguage = "inc-ash", } m["inc-dre"] = { "Eastern Dardic", nil, "inc-dar", } m["inc-dng"] = { "Dangari", nil, "inc-shn", } m["inc-eas"] = { "Eastern Indo-Aryan", 12593391, "inc", protoLanguage = "inc-aav", } m["inc-hal"] = { "Halbic", 16910593, "inc-eas", aliases = {"Halbi"}, } m["inc-hie"] = { "Eastern Hindi", 4126648, "inc-cen", aliases = {"Purabiyā"}, protoLanguage = "inc-apa", } m["inc-hiw"] = { "Western Hindi", 12600937, "inc-cen", protoLanguage = "inc-ohi", } m["inc-hnd"] = { "Hindustani", 11051, "inc-hiw", aliases = {"Hindi-Urdu"}, protoLanguage = "hi-mid", } m["inc-ins"] = { "Insular Indo-Aryan", 12179302, "inc", protoLanguage = "inc-apa", } m["inc-kas"] = { "Kashmiric", nil, "inc-dre", aliases = {"Kashmiri"}, } m["inc-koh"] = { "Kohistani", 13018610, "inc-dre", } m["inc-krd"] = { "KRDS languages", 6356154, "inc-eas", aliases = {"Kamta, Rajbanshi, Deshi and Surjapuri", "KRNB languages", "Kamta, Rajbanshi and Northern Deshi Bangla"}, } m["inc-kun"] = { "Kunar", nil, "inc-dar", } m["inc-mid"] = { "Middle Indo-Aryan", 3236316, "inc", aliases = {"Middle Indic"}, } m["inc-nwe"] = { "Northwestern Indo-Aryan", 16111018, "inc", protoLanguage = "inc-apa", } m["inc-nor"] = { "Northern Indo-Aryan", 946077, "inc", protoLanguage = "inc-aka", } m["inc-old"] = { "Old Indo-Aryan", 118976896, "inc", aliases = {"Old Indic"}, } m["inc-pah"] = { "Pahari", 946077, "inc-nor", aliases = {"Pahadi"}, protoLanguage = "inc-aka", } m["inc-pan"] = { "Punjabic", 2656685, "inc-nwe", aliases = {"Greater Punjabic"}, protoLanguage = "inc-opa", } m["inc-pas"] = { "Pashayi", 36670, "inc-dar", aliases = {"Pashai"}, } m["inc-rom"] = { "Romani", 13201, "inc-wes", aliases = {"Romany", "Gypsy", "Gipsy"}, } m["inc-shn"] = { "Shinaic", 12646125, "inc-dre", } m["inc-snd"] = { "Sindhic", 7522212, "inc-nwe", protoLanguage = "inc-avr", } m["inc-sou"] = { "Southern Indo-Aryan", 10856062, "inc", protoLanguage = "inc-ama", } m["inc-tha"] = { "Tharu", 34035, "inc-eas", } m["inc-wes"] = { "Western Indo-Aryan", nil, "inc", protoLanguage = "inc-agu", } m["ine"] = { "Indo-European", 19860, aliases = {"Indo-Germanic"}, } m["ine-ana"] = { "Anatolian", 147085, "ine", } m["ine-bsl"] = { "Balto-Slavic", 147356, "ine", } m["ine-toc"] = { "Tocharian", 37029, "ine", aliases = {"Tokharian"}, } m["ira"] = { "Iranian", 33527, "iir", } m["ira-csp"] = { "Caspian", 5049123, "ira-mpr", } m["ira-cen"] = { "Central Iranian", nil, "ira", } m["ira-kms"] = { "Komisenian", nil, "ira-mpr", aliases = {"Semnani"}, } m["ine-luw"] = { "Luwic", 115748615, "ine-ana", aliases = {"Luvic"}, } m["ira-mid"] = { "Middle Iranian", 6841465, "ira", } m["ira-mny"] = { "Munji-Yidgha", nil, "ira-sym", aliases = {"Yidgha-Munji"}, } m["ira-msh"] = { "Mazanderani-Shahmirzadi", nil, "ira-csp", } m["ira-nei"] = { "Northeastern Iranian", 10775567, "ira", } m["ira-nwi"] = { "Northwestern Iranian", 390576, "ira-wes", } m["ira-old"] = { "Old Iranian", 23301845, "ira", } m["ira-orp"] = { "Ormuri-Parachi", nil, "ira-sei", } m["ira-pat"] = { "Pathan", nil, "ira-sei", } m["ira-sbc"] = { "Sogdo-Bactrian", nil, "ira-nei", } m["ira-mpr"] = { "Medo-Parthian", nil, "ira-nwi", aliases = {"Partho-Median"}, } m["ira-sgi"] = { "Sanglechi-Ishkashimi", 18711232, "ira-sei", } m["ira-shr"] = { "Shughni-Roshani", 11732824, "ira-shy", } m["ira-shy"] = { "Shughni-Yazghulami", nil, "ira-sym", } m["ira-sgc"] = { "Sogdic", nil, "ira-sbc", aliases = {"Sogdian"}, } m["ira-sei"] = { "Southeastern Iranian", 3833002, "ira", } m["ira-swi"] = { "Southwestern Iranian", 390424, "ira-wes", } m["ira-sym"] = { "Shughni-Yazghulami-Munji", nil, "ira-sei", } m["ira-wes"] = { "Western Iranian", 129850, "ira", } m["ira-zgr"] = { "Zaza-Gorani", 167854, "ira-mpr", aliases = {"Zaza-Gurani", "Gorani-Zaza"}, } m["iro"] = { "Iroquoian", 33623, } m["iro-nor"] = { "North Iroquoian", nil, "iro", } m["itc"] = { "Italic", 131848, "ine", } m["itc-laf"] = { "Latino-Faliscan", 33478, "itc", aliases = {"Latinian"}, } m["itc-sbl"] = { "Osco-Umbrian", 515194, "itc", aliases = {"Sabellic", "Sabellian"}, } m["jpx"] = { "Japonic", 33612, aliases = {"Japanese", "Japanese-Ryukyuan"}, } m["jpx-nry"] = { "Northern Ryukyuan", 20862796, "jpx-ryu", } m["jpx-ryu"] = { "Ryukyuan", 56393, "jpx", } m["jpx-sry"] = { "Southern Ryukyuan", 18392243, "jpx-ryu", } m["kar"] = { "Karen", 1364815, "sit", } m["kca"] = { "Khanty", 33563, "urj-ugr", aliases = {"Khantyic", "Khantic"}, } --[=[ Exceptional language and family codes for Khoisan and Kordofanian languages can use the prefix "khi-" and "kdo-" respectively, though they are no longer family codes themselves. ]=]-- m["khi-kal"] = { "Kalahari Khoe", nil, "khi-kho", } m["khi-khk"] = { "Khoekhoe", nil, "khi-kho", } m["khi-kkw"] = { "Khoe-Kwadi", 60785084, aliases = {"Kwadi-Khoe"}, } m["khi-kho"] = { "Khoe", 2736449, "khi-kkw", aliases = {"Central Khoisan"}, } m["khi-kxa"] = { "Kx'a", 6450587, aliases = {"Kxa", "Ju-ǂHoan"}, } m["khi-tuu"] = { "Tuu", 631046, aliases = {"Kwi", "Taa-Kwi", "Southern Khoisan", "Taa-ǃKwi", "Taa-ǃUi", "ǃUi-Taa"}, } m["kro"] = { "Kru", 33535, "nic-vco", } m["kro-aiz"] = { "Aizi", 4699431, "kro", } m["kro-bet"] = { "Bété", 32956, "kro-ekr", } m["kro-did"] = { "Dida", 32685, "kro-ekr", } m["kro-ekr"] = { "Eastern Kru", 5972899, "kro", } m["kro-grb"] = { "Grebo", 5601537, "kro-wkr", } m["kro-wee"] = { "Wee", nil, "kro-wkr", } m["kro-wkr"] = { "Western Kru", 5972897, "kro", } m["ku"] = { "Kurdish", 36368, "ira-nwi", } m["kv"] = { "Komi", 36126, -- "Komi language" in Wikipedia but refers specifically to Komi-Zyrian; no Wikidata item for Komi family "urj-prm", } m["map"] = { "Austronesian", 49228, } m["map-ata"] = { "Atayalic", 716610, "map", } m["mjg"] = { "Monguor", 34214, "xgn-shr", } m["mkh"] = { "Mon-Khmer", 33199, "aav", } m["mkh-asl"] = { "Aslian", 3111082, "mkh", } m["mkh-ban"] = { "Bahnaric", 56309, "mkh", } m["mkh-kat"] = { "Katuic", 56697, "mkh", } m["mkh-khm"] = { "Khmuic", 1323245, "mkh", } m["mkh-kmr"] = { "Khmeric", nil, "mkh", } m["mkh-mnc"] = { "Monic", 3217497, "mkh", } m["mkh-mng"] = { "Mangic", 3509556, "mkh", } m["mkh-nbn"] = { "North Bahnaric", 56309, "mkh-ban", } m["mkh-pal"] = { "Palaungic", 2391173, "mkh", } m["mkh-pea"] = { "Pearic", 3073022, "mkh", } m["mkh-pkn"] = { "Pakanic", nil, "mkh-mng", } m["mkh-vie"] = { "Vietic", 2355546, "mkh", } m["mno"] = { "Manobo", 3217483, "phi", } m["mns"] = { "Mansi", 33759, "urj-ugr", aliases = {"Mansic"}, } m["mun"] = { "Munda", 33892, "aav", } m["myn"] = { "Mayan", 33738, } --[=[ Exceptional language and family codes for North American Indian languages can use the prefix "nai-", though "nai" is no longer itself a family code. ]=]-- m["nai-cat"] = { "Catawban", 3446638, "nai-sca", } m["nai-chu"] = { "Chumashan", 1288420, } m["nai-ckn"] = { "Chinookan", 610586, } m["nai-coo"] = { "Coosan", 940278, } m["nai-jcq"] = { "Jicaquean", 12179308, "hok" } m["nai-ker"] = { "Keresan", 35878, } m["nai-klp"] = { "Kalapuyan", 1569040, } m["nai-kta"] = { "Kiowa-Tanoan", 386288, } m["nai-len"] = { "Lencan", 36189, aliases = {"Lenca"}, } m["nai-mdu"] = { "Maiduan", 33502, } m["nai-miz"] = { "Mixe-Zoquean", 954016, aliases = {"Mixe-Zoque"}, } m["nai-min"] = { "Misumalpan", 281693, "qfa-mch", aliases = {"Misuluan", "Misumalpa"}, } m["nai-mus"] = { "Muskogean", 902978, aliases = {"Muskhogean"}, } m["nai-pak"] = { "Pakawan", 65085487, "hok", } m["nai-pal"] = { "Palaihnihan", 1288332, } m["nai-plp"] = { "Plateau Penutian", 2307476, } m["nai-pom"] = { "Pomoan", 2618420, "hok", aliases = {"Pomo", "Kulanapan"}, } m["nai-sca"] = { "Siouan-Catawban", 34181, } m["nai-shp"] = { "Sahaptian", 114782, "nai-plp", } m["nai-shs"] = { "Shastan", 2991735, "hok", } m["nai-tot"] = { "Totozoquean", 7828419, } m["nai-ttn"] = { "Totonacan", 34039, aliases = {"Totonac-Tepehua", "Totonacan-Tepehuan"}, varieties = {"Totonac"}, } m["nai-tqn"] = { "Tequistlatecan", 1568317, "hok", aliases = {"Tequistlatec", "Chontal", "Chontalan", "Oaxacan Chontal", "Chontal of Oaxaca"}, } m["nai-tsi"] = { "Tsimshianic", 34134, } m["nai-utn"] = { "Utian", 13371763, "nai-you", aliases = {"Miwok-Costanoan", "Mutsun"}, } m["nai-wtq"] = { "Wintuan", 1294259, aliases = {"Wintun"}, } m["nai-xin"] = { "Xincan", 1546494, aliases = {"Xinca"}, } m["nai-ykn"] = { "Yukian", 2406722, aliases = {"Yuki-Wappo"}, } m["nai-you"] = { "Yok-Utian", 2886186, } m["nai-yuc"] = { "Yuman-Cochimí", 579137, } m["ngf"] = { "Trans-New Guinea", 34018, } m["ngf-ais"] = { "Aisian", nil, "ngf-eso", } m["ngf-ang"] = { "Angan", 3217366, "ngf", aliases = {"Kratke Range"}, -- Usher } m["ngf-ank"] = { "Angal-Kewa", 12626916, -- exist in dewiki and hrwiki "ngf-sak", } m["ngf-ask"] = { "Asmat-Kamoro", 3031400, "ngf", -- Wikipedia uses Asmat-Kamoro to refer to a narrower group excluding the Sabakor languages (Buruwai and Kamberau, -- which Glottolog splits into North Kamrau and South Kamrau [sic]), and uses Asmat-Kamrau to refer to what we and -- Glottolog call Asmat-Kamoro. Glottolog does not recognize the narrower grouping. aliases = {"Asmat-Kamrau", -- Wikipedia "Asmat-Kamrau Bay", -- Usher }, } m["ngf-asm"] = { "Asmat", 4807421, "ngf-ask", } m["ngf-ata"] = { "Ankave-Tainae-Akoye", nil, "ngf-ang", aliases = {"Southwest Kratke Range"}, -- Usher } m["ngf-awd"] = { "Awyu-Dumut", -- [[w:Awyu-Dumut languages]] redirects to [[w:Greater Awyu languages]] 4830163, -- exist in eswiki, hrwiki and ruwiki "ngf-gaw", aliases = {"Central Digul River"}, -- Usher } m["ngf-awy"] = { "Awyu", 96372866, "ngf-awd", } m["ngf-bda"] = { "Becking-Dawi", nil, -- Q55993716 ([[Category:Becking–Dawi languages]]) exists in enwiki "ngf-gaw", aliases = {"Becking and Dawi Rivers"}, -- Usher } m["ngf-bin"] = { "Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf-gbi", aliases = {"Oro"}, -- Usher (2020) } m["ngf-boa"] = { "Boane", nil, "ngf-era", aliases = {"Boana", -- Glottolog's name "Wain"}, -- not in Usher; "Wain" often excludes Mungkip, perhaps because it's poorly documented } m["ngf-bos"] = { "Bosavi", 4947122, "ngf", aliases = {"Papuan Plateau"}, -- alternative name given by Wikipedia } m["ngf-bsi"] = { "Baruya-Simbari", nil, "ngf-ang", aliases = {"Northwest Kratke Range"}, -- Usher } m["ngf-cda"] = { "Central Dani", nil, "ngf-dan", aliases = {"Dani"}, -- Usher } m["ngf-chw"] = { "Chimbu-Wahgi", 3217383, "ngf", aliases = {"Simbu-Western Highlands"}, -- alternative name given by Wikipedia } m["ngf-dag"] = { "Dagan", 5208454, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Meneao Range"}, } m["ngf-dal"] = { "Dallman", nil, "ngf-huo", aliases = {"Kinalakna-Kumukio", -- Pawley-Hammarström, who exclude Nomu, but they only had a numeral list of that language to work from "Northeast Huon", -- Usher }, } m["ngf-dan"] = { "Dani", 3217389, "ngf", -- Wikipedia renames the Dani languages to the Baliem Valley languages and sometimes (but not consistently) -- reserves the name Dani (or "Dani proper") for a narrower group excluding Wano and the poorly attested Ngalik -- languages (Nduga, Silimo, and the Yali dialect cluster, which we, following Ethnologue and Glottolog, split into -- Anggurk Yali, Ninia Yali and Pass Valley Yali). Glottolog does not recognize the narrower grouping. aliases = {"Baliem Valley", -- Wikipedia "Balim Valley", -- Usher }, } m["ngf-dum"] = { "Dumut", -- [[w:Dumut languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Wambon"}, -- Usher } m["ngf-ehu"] = { "Eastern Huon", -- Glottolog adds Ono and Sialum, Pawley-Hammarström adds Dedua 10567087, "ngf-huo", aliases = {"East Huon"}, -- Usher } m["ngf-eku"] = { "East Kutubuan", 5328752, "ngf", -- Not in TNG per Glottolog but accepted by all others. Sometimes grouped with Fasu to form a Kutubuan family. aliases = {"East Kutubu"}, -- Glottolog's name } m["ngf-enc"] = { "Engic", nil, "ngf-eng", aliases = {"Engan", -- Glottolog "Engan proper", -- Wikipedia "North Engan", -- alternative name given by Wikipedia "Trans-Enga", -- Usher }, } m["ngf-eng"] = { "Engan", 3217449, "ngf", aliases = {"Enga-Kewa-Huli", -- Glottolog, Pawley-Hammarström "Enga-Southern Highlands", -- Usher }, } m["ngf-era"] = { "Erap", nil, "ngf-fin", aliases = {"Erap River"}, -- Usher? } m["ngf-eso"] = { "East Sogeram", nil, "ngf-sog", } m["ngf-est"] = { "East Strickland", 5329440, "ngf", aliases = {"Strickland River"}, -- alternative name given by Wikipedia } m["ngf-eva"] = { "Evapia", nil, "ngf-rai", aliases = {"Evapia River"}, -- Usher } m["ngf-fgi"] = { "Fore-Gimi", nil, "ngf-gor", aliases = {"South Goroka"}, -- Usher } m["ngf-fhu"] = { "Finisterre-Huon", 3217453, "ngf", aliases = {"Finisterre Range-Huon Peninsula"}, -- per Usher } m["ngf-fin"] = { "Finisterre", 5450373, "ngf-fhu", aliases = {"Finisterre-Saruwaged", -- Glottolog's name "Finisterre Range"}, -- per Usher } m["ngf-gah"] = { "Gahuku", nil, "ngf-gor", aliases = {"Alekano-Asaro River"}, -- Usher } m["ngf-gau"] = { "Gauwa", nil, "ngf-kai", aliases = {"West Kainantu"}, -- Usher } m["ngf-gaw"] = { "Greater Awyu", 12627424, "ngf", aliases = {"Digul River"}, -- used by Usher (2020) } m["ngf-gbi"] = { "Greater Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf", -- not placed in Trans-New Guinea in Usher (2020) aliases = {"Guhu-Oro"}, -- Guhu-Oro is used in Usher (2020) } m["ngf-gko"] = { "Gaena-Korafe", 11732347, -- considered a single Korafe language by Wikipedia "ngf-bin", aliases = {"Gaina-Korafe"}, -- Usher } m["ngf-gmo"] = { "Gusap-Mot", 16110857, "ngf-fin", aliases = {"Mot River"}, -- Usher? } m["ngf-gor"] = { "Goroka", 15478597, "ngf-kgo", } m["ngf-gsu"] = { "Gogodala-Suki", 5577428, "ngf", -- Possibly in the proposed Papuan Gulf family. Not in TNG per Glottolog but accepted by all others. aliases = {"Suki-Gogodala", -- Glottolog's name "Suki-Aramia River", -- Used in Usher (2020) }, } m["ngf-gum"] = { "Gum", 5618008, "ngf-mab", } m["ngf-gvd"] = { "Grand Valley Dani", -- considered a single language by Wikipedia 5595219, "ngf-cda", } m["ngf-hag"] = { "Hagen", -- [[w:Hagen languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Melpa-Kaugel River"}, -- Usher } m["ngf-han"] = { "Hanseman", 5651020, "ngf-mab", aliases = {"Hansemann Range"}, -- Usher } m["ngf-huo"] = { "Huon", 5946109, "ngf-fhu", aliases = {"Huon Peninsula"}, -- per Usher } m["ngf-jim"] = { "Jimi", -- [[w:Jimi languages]] and [[w:Jimi River languages]] redirect to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Jimi River"}, -- Usher } m["ngf-kab"] = { "Kabwum", nil, "ngf-huo", aliases = {"Timbe-Selepet-Komba", -- Pawley-Hammarström, "Northwest Huon", -- Usher }, } m["ngf-kai"] = { "Kainantu", -- Kambaira: under "unclassified Kainantu" (Glottolog), Tairora (Pawley-Hammarström), Gauwa (Usher) 15478590, "ngf-kgo", aliases = {"Gadsup-Auyana-Awa-Tairora"}, -- Wurm, } m["ngf-kak"] = { "Kalam-Kobon", 6350303, "ngf-ksa", aliases = {"Kalam", "Kaironk River"}, -- Usher (2020) } m["ngf-kau"] = { "Kaukombar", nil, "ngf-nad", aliases = {"Kaukombaran", -- Glottolog following Z'graggen (1975) "Kaukombar River"}, -- Usher's term } m["ngf-kbm"] = { "Kosorong-Burum-Mindik", nil, "ngf-huo", aliases = {"Bulum River"}, -- Usher } m["ngf-kgo"] = { "Kainantu-Goroka", 3217463, "ngf", aliases = {"Eastern Highlands"}, -- per Usher (2020) } m["ngf-khu"] = { "Kewa-Huli", nil, "ngf-eng", aliases = {"Huli-Southern Highlands"}, -- Usher } m["ngf-kma"] = { "Kâte-Mape", nil, "ngf-ehu", aliases = {"Kate-Mape-Sene", -- Pawley-Hammarström (with Sene), "Southeast Huon", -- Usher }, } m["ngf-kme"] = { "Kapau-Menya", nil, "ngf-ang", aliases = {"Southeast Kratke Range"}, -- Usher } m["ngf-koi"] = { "Koiarian", 11154240, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Koiari-Managalas Plateau"}, } m["ngf-kok"] = { "Kokon", -- Usher calls it South Mabuso but includes Gum in it nil, "ngf-mab", } m["ngf-kow"] = { "Kowan", 6435004, "ngf-mad", aliases = {"Isumrud Strait"}, -- per Usher (2020) } m["ngf-ksa"] = { "Kalam-Southern Adelbert", nil, "ngf-mad", aliases = {"Kalamic-South Adelbert", -- Glottolog "West Madang"}, -- Usher (2020) } m["ngf-kto"] = { "Kube-Tobo", -- per Glottolog, one language "Kulungtfu-Yuanggeng-Tobo" 1173235, -- code for Tobo-Kube language "ngf-huo", aliases = {"Tobo-Kube"}, } m["ngf-kts"] = { "Komyandaret-Tsaukambo", nil, "ngf-bda", aliases = {"Becking River"}, -- Usher } m["ngf-kum"] = { "Kumil", nil, "ngf-nad", aliases = {"Kumilan", -- Pawley-Hammarström following Z'graggen (1975) "Kumil River"}, -- Usher's term } m["ngf-kya"] = { "Kamano-Yagaria", nil, "ngf-gor", aliases = {"Henganofi", -- Usher "Kamano-Yagaria-Keigana", }, } m["ngf-lok"] = { "Lowland Ok", nil, "ngf-okk", } m["ngf-mab"] = { "Mabuso", 6721668, "ngf-mad", } m["ngf-mad"] = { "Madang", 11217556, "ngf", aliases = {"Madang-Adelbert Range"}, -- Z'graggen (1975), corresponding to today's Madang except in lacking Kalam and Gants } m["ngf-mek"] = { "Mek", 6810515, "ngf", aliases = {"Goliath"}, -- outdated alternative name given by Wikipedia } m["ngf-min"] = { "Mindjim", 86749913, "ngf-mad", aliases = {"Lower Minjim", -- Glottolog, placed in Rai Coast by Glottolog and Pawley-Hammarström; Glottolog's -- Mindjim has 6 languages, including "Upper Minjim" (Rerau and Sgi Bara) "Mindjim River", -- Usher "Minjim", "Minjim River", }, } -- Add if Molet is separated from Asaro'o -- m["ngf-moa"] = { -- "Molet-Asaro'o", -- nil, -- "ngf-war", -- } m["ngf-mok"] = { "Mountain Ok", -- [[w:Mountain Ok languages]] redirects to [[w:Ok languages]] nil, "ngf-okk", } m["ngf-mom"] = { "Mombum", 6897077, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Mombum-Koneraw", "Komolom", "Muli Strait"}, -- Pawley-Hammarström uses Komolom, Usher uses Muli Strait } m["ngf-msu"] = { "Mian-Suganga", -- considred a single Mian language by Wikipedia 12952846, "ngf-mok", aliases = {"Mianic"}, -- Glottolog } m["ngf-nad"] = { "Northern Adelbert", -- not accepted by Pawley-Hammarström 16952821, -- code for Croisilles linkage "ngf-mad", aliases = {"Adelbert Range-Isumrud Strait", -- Usher (2020) "North Adelbert", "Pihom-Isumrud"}, -- Ross? } m["ngf-nbi"] = { "North Binanderean", nil, "ngf-bin", aliases = {"Suena-Zia"}, -- Usher } m["ngf-nde"] = { "Ndeiram", -- [[w:Ndeiram River languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Ndeiram River"}, -- Usher? } m["ngf-ngn"] = { "Ngalik-Nduga", -- [[w:Ngalik languages]] redirects to [[w:Baliem Valley languages]] = Dani languages nil, "ngf-dan", aliases = {"Ngalik"}, -- Usher } m["ngf-nso"] = { "North Sogeram", nil, "ngf-sog", aliases = {"Mum-Sirva", -- Usher "North Central Sogeram", -- used by those who accept Central Sogeram (= North Sogeram + Apali and Manat) "North-Central Sogeram", -- rarer than without the dash "Sikan"}, -- Z’graggen (1975?) } m["ngf-num"] = { "Numugen", nil, "ngf-nad", aliases = {"Numugenan", -- Glottolog following Z'graggen 1975 "Numugen River"}, -- Usher's term } m["ngf-nur"] = { "Nuru", -- Usher excludes Yangulam, Pawley-Hammarström include Jilim and Rerau nil, "ngf-rai", aliases = {"Nuru River"}, -- Usher? } m["ngf-nwh"] = { "Northwest Hanseman", -- Usher nil, "ngf-han", aliases = {"Wamas-Samosa-Murupi-Mosimo"}, -- Glottolog, Greenhill, and Pawley-Hammarström following Z'graggen; the most common name, but very unwieldy } m["ngf-oen"] = { "Outer Engan", -- considered a single Nete language by Wikipedia 6998869, "ngf-enc", aliases = {"Nete-Bisorio"}, -- Usher } m["ngf-okk"] = { "Ok", 7081687, "ngf", } m["ngf-omo"] = { "Omosan", -- not included in (Greater) Northern Adelbert by Glottolog, but a sister nil, "ngf-nad", } m["ngf-oro"] = { "Orokaivic", 7103752, -- considered a single Orokaiva language by Wikipedia "ngf-bin", aliases = {"Central Oro"}, -- Usher } m["ngf-pan"] = { "Paniai Lakes", 6035631, "ngf", aliases = {"Wissel Lakes", "Wissel Lakes-Kemandoga River"}, -- alternative names given by Wikipedia } m["ngf-pek"] = { "Peka", nil, "ngf-rai", aliases = {"Peka River"}, -- Usher? } m["ngf-pom"] = { "Pomoikan", nil, "ngf-sad", } m["ngf-rai"] = { "Rai Coast", 7283663, "ngf-mad", aliases = {"South Madang"}, -- Usher } m["ngf-sab"] = { "Sabakor", -- [[w:Sabakor languages]] redirects to [[w:Asmat–Kamrau languages]] nil, -- 55994614 is for [[Category:Kamrau Bay languages]], which exists on enwiki "ngf-ask", aliases = {"Kamrau Bay"}, -- Usher } m["ngf-sad"] = { "Southern Adelbert", 12633980, "ngf-ksa", aliases = {"South Adelbert", -- Glottolog "Southern Adelbert Range", -- Z'graggen (1980) "Sogeram and Tomul Rivers"}, -- Usher (2020)? } m["ngf-sak"] = { "Sau-Angal-Kewa", nil, "ngf-khu", aliases = {"Southern Highlands"}, -- Usher } m["ngf-san"] = { "Sankwep", nil, "ngf-huo", aliases = {"Nabak-Momolili", -- Pawley-Hammarström, "Southwest Huon", -- Usher }, } m["ngf-sbh"] = { "South Bird's Head", 7566330, "ngf", } m["ngf-sim"] = { "Simbu", nil, "ngf-chw", } m["ngf-sog"] = { "Sogeram", 86750419, "ngf-sad", aliases = {"Sogeram River", -- Usher "Wanang"}, } m["ngf-sop"] = { "Sopac", nil, "ngf-ehu", aliases = {"Momare-Migabac", -- Pawley-Hammarström, "Masaweng River", -- Usher }, } m["ngf-taa"] = { "Tainae-Akoye", nil, "ngf-ata", aliases = {"Akoye-Tainae"}, -- Usher } m["ngf-tai"] = { "Tairora", nil, "ngf-kai", aliases = {"Tairoric", -- Glottolog, "East Kainantu", -- Usher }, } m["ngf-tib"] = { "Tiboran", nil, "ngf-nad", aliases = {"Nuclear Tibor", -- Glottolog, excluding Wanambre/Mokati "Tiboran River", -- Usher (2020) "Tibor", -- Pick (2020) and Glottolog including Wanambre/Mokati } } m["ngf-tna"] = { "Tangko-Nakai", nil, "ngf-okk", aliases = {"Central Ok"}, -- Usher } m["ngf-uru"] = { "Uruwa", nil, "ngf-fin", aliases = {"Uruwa River"}, -- Usher? } m["ngf-usi"] = { "Utu-Silopi", nil, "ngf-han", aliases = {"Silopi-Utu"}, -- Usher } m["ngf-waa"] = { "Wantoat-Awara", -- not in Usher but Wantoat and Awara form a dialect chain nil, "ngf-wan", aliases = {"Awara-Wantoat"}, -- per Wikipedia } m["ngf-wah"] = { "Wahgi", -- [[w:Wahgi languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Wahgi Valley"}, -- Usher } m["ngf-wan"] = { "Wantoatic", nil, "ngf-fin", aliases = {"Wantoat", "Wantoat River", -- Usher? }, } m["ngf-war"] = { "Warup", 12645082, "ngf-fin", aliases = {"Warup River"}, -- Usher? } m["ngf-woj"] = { "Wojokesic", nil, "ngf-ang", aliases = {"Northeast Kratke Range"}, -- Usher } m["ngf-wok"] = { "West Ok", nil, "ngf-okk", aliases = {"Kwer-Kopkaka-Burumakok"}, -- Glottolog, Pawley-Hammarström } m["ngf-wso"] = { "West Sogeram", nil, "ngf-sog", aliases = {"Mand-Nend", -- Usher "Atan", -- Wurm following Z'graggen }, } m["ngf-yag"] = { "Yaganon", -- placed in Rai Coast by Glottolog and Pawley-Hammarström 35323986, "ngf-mad", aliases = {"Yaganon River"}, -- Usher } m["ngf-yal"] = { "Yali", -- considered a single language by Wikipedia 8047468, "ngf-ngn", aliases = {"Ngalik"}, -- Glottolog, Pawley-Hammarström } m["ngf-yar"] = { "Yareban", 16977672, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Musa River"}, } m["ngf-ynu"] = { "Yau-Nungon", 12953319, -- for the single Yau language in Wikipedia ([[w:Yau language (Trans–New Guinea)]]) "ngf-uru", } m["ngf-yup"] = { "Yupna", nil, "ngf-fin", aliases = {"Yupna River"}, -- Usher? } m["nic"] = { "Niger-Congo", 33838, aliases = {"Niger-Kordofanian"}, } m["nic-alu"] = { "Alumic", 4737355, "nic-plt", } m["nic-bas"] = { "Basa", 4866154, "nic-knj", } m["nic-bbe"] = { "Eastern Beboid", nil, "nic-beb", } m["nic-bco"] = { "Benue-Congo", 33253, "nic-vco", } m["nic-bcr"] = { "Bantoid-Cross", 806983, "nic-bco", } m["nic-bdn"] = { "Northern Bantoid", nil, "nic-bod", aliases = {"North Bantoid"}, } m["nic-bds"] = { "Southern Bantoid", 3183152, "nic-bod", aliases = {"Wide Bantu", "Bin"}, } m["nic-beb"] = { "Beboid", 813549, "nic-bds", } m["nic-ben"] = { "Bendi", 4887065, "nic-bcr", } m["nic-beo"] = { "Beromic", 4894642, "nic-plt", } m["nic-bod"] = { "Bantoid", 806992, "nic-bcr", } m["nic-buk"] = { "Buli-Koma", nil, "nic-ovo", } m["nic-bwa"] = { "Bwa", 12628562, "nic-gur", other_names = {"Bwamu", "Bomu"}, } m["nic-cde"] = { "Central Delta", 3813191, "nic-cri", } m["nic-cri"] = { "Cross River", 1141096, "nic-bcr", } m["nic-dag"] = { "Dagbani", nil, "nic-wov", } m["nic-dak"] = { "Dakoid", 1157745, "nic-bdn", } m["nic-dge"] = { "Escarpment Dogon", 5397128, "qfa-dgn", } m["nic-dgw"] = { "West Dogon", nil, "qfa-dgn", } m["nic-eko"] = { "Ekoid", 1323395, "nic-bds", } m["nic-eov"] = { "Eastern Oti-Volta", nil, "nic-ovo", aliases = {"Samba"}, } m["nic-fru"] = { "Furu", 5509783, "nic-bds", } m["nic-gne"] = { "Eastern Gurunsi", 12633072, "nic-gns", aliases = {"Eastern Grũsi"}, } m["nic-gnn"] = { "Northern Gurunsi", nil, "nic-gns", aliases = {"Northern Grũsi"}, } m["nic-gnw"] = { "Western Gurunsi", nil, "nic-gns", aliases = {"Western Grũsi"}, } m["nic-gns"] = { "Gurunsi", 721007, "nic-gur", aliases = {"Grũsi"}, } m["nic-gre"] = { "Eastern Grassfields", 5330160, "nic-grf", } m["nic-grf"] = { "Grassfields", 750932, "nic-bds", aliases = {"Grassfields Bantu", "Wide Grassfields"}, } m["nic-grm"] = { "Gurma", 30587833, "nic-ovo", } m["nic-grs"] = { "Southwest Grassfields", 7571285, "nic-grf", } m["nic-gur"] = { "Gur", 33536, "alv-sav", aliases = {"Voltaic"}, } m["nic-ief"] = { "Ibibio-Efik", 2743643, "nic-lcr", } m["nic-jer"] = { "Jera", nil, "nic-kne", } m["nic-jkn"] = { "Jukunoid", 1711622, "nic-pla", } m["nic-jrn"] = { "Jarawan", 1683430, "nic-mba", } m["nic-jrw"] = { "Jarawa", 35423, "nic-jrn", } m["nic-kam"] = { "Kambari", 6356294, "nic-knj", } m["nic-ktl"] = { "Katloid", nil, "nic", } m["nic-kau"] = { "Kauru", nil, "nic-kne", } m["nic-kmk"] = { "Kamuku", 6359821, "nic-knj", } m["nic-kne"] = { "East Kainji", 5328687, "nic-knj", } m["nic-knj"] = { "Kainji", 681495, "nic-pla", } m["nic-knn"] = { "Northwest Kainji", 7060098, "nic-knj", } m["nic-ktl"] = { "Katloid", 6377681, "nic", aliases = {"Katla", "Katla-Tima"}, } m["nic-lcr"] = { "Lower Cross River", 3813193, "nic-cri", } m["nic-mam"] = { "Mamfe", 2005898, "nic-bds", aliases = {"Nyang"}, } m["nic-mba"] = { "Mbam", 687826, "nic-bds", } m["nic-mbc"] = { "Mba", 6799561, "nic-ubg", } m["nic-mbw"] = { "West Mbam", nil, "nic-mba", } m["nic-mmb"] = { "Mambiloid", 1888151, other_names = {"North Bantoid"}, -- per Wikipedia, North Bantoid is the parent family "nic-bdn", } m["nic-mom"] = { "Momo", 6897393, "nic-grf", } m["nic-mre"] = { "Moré", nil, "nic-wov", } m["nic-ngd"] = { "Ngbandi", 36439, "nic-ubg", } m["nic-nge"] = { "Ngemba", 7022271, "nic-gre", } m["nic-ngk"] = { "Ngbaka", 3217499, "nic-ubg", } m["nic-nin"] = { "Ninzic", 7039282, "nic-plt", } m["nic-nka"] = { "Nkambe", 7042520, "nic-gre", } m["nic-nkb"] = { "Baka", nil, "nic-nkw", } m["nic-nke"] = { "Eastern Ngbaka", nil, "nic-ngk", } m["nic-nkg"] = { "Gbanziri", nil, "nic-nkw", } m["nic-nkk"] = { "Kpala", nil, "nic-nkw", } m["nic-nkm"] = { "Mbaka", nil, "nic-nkw", } m["nic-nkw"] = { "Western Ngbaka", nil, "nic-ngk", } m["nic-npd"] = { "North Plateau Dogon", nil, "qfa-dgn", } m["nic-nun"] = { "Nun", 13654297, "nic-gre", } m["nic-nwa"] = { "Nanga-Walo", nil, "qfa-dgn", } m["nic-ogo"] = { "Ogoni", 2350726, "nic-cri", aliases = {"Ogonoid"}, } m["nic-ovo"] = { "Oti-Volta", 1157178, "nic-gur", } m["nic-pla"] = { "Platoid", 453244, "nic-bco", aliases = {"Central Nigerian"}, } m["nic-plc"] = { "Central Plateau", 5061668, "nic-plt", } m["nic-pld"] = { "Plains Dogon", nil, "qfa-dgn", } m["nic-ple"] = { "East Plateau", 5329154, "nic-plt", } m["nic-pls"] = { "South Plateau", 7568236, "nic-plt", aliases = {"Jilic-Eggonic"}, } m["nic-plt"] = { "Plateau", 1267471, "nic-pla", } m["nic-ras"] = { "Rashad", 3401986, "nic", } m["nic-rnc"] = { "Central Ring", nil, "nic-rng", } m["nic-rng"] = { "Ring", 2269051, "nic-grf", aliases = {"Ring Road"}, } m["nic-rnn"] = { "Northern Ring", nil, "nic-rng", } m["nic-rnw"] = { "Western Ring", nil, "nic-rng", } m["nic-ser"] = { "Sere", 7453058, "nic-ubg", } m["nic-shi"] = { "Shiroro", 7498953, "nic-knj", aliases = {"Pongu"}, } m["nic-sis"] = { "Sisaala", 36532, "nic-gnw", } m["nic-tar"] = { "Tarokoid", 2394472, "nic-plt", } m["nic-tiv"] = { "Tivoid", 752377, "nic-bds", } m["nic-tvc"] = { "Central Tivoid", nil, "nic-tiv", } m["nic-tvn"] = { "Northern Tivoid", nil, "nic-tiv", } m["nic-ubg"] = { "Ubangian", 33932, "nic-vco", -- or none } m["nic-uce"] = { "East-West Upper Cross River", nil, "nic-ucr", } m["nic-ucn"] = { "North-South Upper Cross River", nil, "nic-ucr", } m["nic-ucr"] = { "Upper Cross River", 4108624, "nic-cri", aliases = {"Upper Cross"}, } m["nic-vco"] = { "Volta-Congo", 37228, "alv", } m["nic-wov"] = { "Western Oti-Volta", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nic-ykb"] = { "Yukubenic", 16909196, "nic-plt", aliases = {"Oohum"}, } m["nic-ymb"] = { "Yambasa", nil, "nic-mba", } m["nic-yon"] = { "Yom-Nawdm", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nub"] = { "Nubian", 1517194, "sdv-nes", } m["nub-hil"] = { "Hill Nubian", 5762211, "nub", aliases = {"Kordofan Nubian"}, } m["omq"] = { "Oto-Manguean", 33669, } m["omq-cha"] = { "Chatino", 35111, "omq-zap", } m["omq-chi"] = { "Chinantecan", 35828, "omq", } m["omq-cui"] = { "Cuicatec", 616024, "omq-mix", } m["omq-maz"] = { "Mazatecan", 36230, "omq", aliases = {"Mazatec"}, } m["omq-mix"] = { "Mixtecan", 21083066, "omq", } m["omq-mxt"] = { "Mixtec", 36363, "omq-mix", } m["omq-otp"] = { "Oto-Pamean", 1270220, "omq", } m["omq-pop"] = { "Popolocan", 5132273, "omq", } m["omq-tri"] = { "Triqui", 780200, "omq-mix", aliases = {"Trique"}, } m["omq-zap"] = { "Zapotecan", 8066463, "omq", } m["omq-zpc"] = { "Zapotec", 13214, "omq-zap", } m["omv"] = { "Omotic", 33860, "afa", } m["omv-aro"] = { "Aroid", 3699526, "omv", aliases = {"Ari-Banna", "South Omotic", "Somotic"}, } m["omv-diz"] = { "Dizoid", 430251, "omv", aliases = {"Maji", "Majoid"}, } m["omv-eom"] = { "East Ometo", 20527288, "omv-ome", } m["omv-gon"] = { "Gonga", 4143043, "omv", aliases = {"Kefoid"}, } m["omv-mao"] = { "Mao", 1351495, "omv", } m["omv-nom"] = { "North Ometo", nil, "omv-ome", } m["omv-ome"] = { "Ometo", 36310, "omv", } m["oto"] = { "Otomian", 130372545, "omq-otp", } m["oto-otm"] = { "Otomi", 36355, "oto", } m["paa"] = { "Papuan", 236425, "qfa-not", } m["paa-aia"] = { "Aian", 4767739, -- Annaberg languages "paa-ram", aliases = {"Middle Ramu", -- Foley (with Rao), "Annaberg", -- with Rao "Aram-Aren", -- Usher }, } m["paa-alp"] = { "Alor-Pantar", 3502429, "paa-tap", } m["paa-amu"] = { "Amto-Musan", 480281, aliases = {"Samaia River"}, } m["paa-ani"] = { "Anim", 55603991, aliases = {"Fly River"}, } m["paa-ara"] = { "Arapesh", 4784223, "paa-koa", aliases = {"Arapeshan"}, -- Foley } m["paa-arf"] = { "Arafundi", 4783702, } m["paa-ata"] = { "Ataitan", 4812652, "paa-ram", aliases = {"Tangu", -- Foley "Tanggu", -- alternative name given by Wikipedia "Moam River", -- Usher }, } m["paa-baa"] = { "Bayono-Awbono", 2424781, } m["paa-bai"] = { "Baining", 748487, aliases = {"East New Britain"}, } m["paa-baw"] = { "Bosngun-Awar", nil, "paa-ott", aliases = {"East Ramu Coast", -- Usher "Bosman-Awar", -- Wikipedia }, } m["paa-bew"] = { "Bewani", -- [[w:Bewani languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 16113460, "paa-bor", aliases = {"Poal River"}, -- Usher } m["paa-boa"] = { "Boazi", 48803717, "paa-mby", aliases = {"Lake Murray"}, -- Usher } m["paa-bor"] = { "Border", 1752158, aliases = {"Upper Tami", "Tami River-Bewani Range", -- Usher }, } m["paa-bul"] = { "Bulaka River", 4987195, aliases = {"Yelmek-Maklew", "Jabga"}, -- Yelmek-Maklew in Evans (2018) and Gregor (2021) } m["paa-bvi"] = { "Betaf-Vitou", -- Glottolog nil, "paa-tor", aliases = {"Vitou-Betaf", -- Wikipedia "Fitou-Tena", -- Usher "Manirem", }, } m["paa-clp"] = { "Central Lakes Plain", -- [[w:Central Lakes Plain languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86780132 is for the corresponding category, which exists in enwiki "paa-lpl", aliases = {"East Tariku", -- Glottolog "Central Lakes Plains", -- Usher }, } m["paa-dtu"] = { "Doso-Turumsa", 16917784, -- possibly related to East Strickland languages aliases = {"Soari River"}, -- Usher's name } m["paa-ebh"] = { "East Bird's Head", 338064, aliases = {"Mantion-Meax", "Mantion-Meyah", -- Mantion-Meax is Wikipedia's term "Southeast Bird's Head", -- Usher (2020) }, } m["paa-eel"] = { "Eastern Eleman", nil, "paa-ele", aliases = {"East Eleman"}, } m["paa-egb"] = { "East Geelvink Bay", 1497678, aliases = {"Geelvink Bay", "East Cenderawasih"}, -- Geelvink Bay per Glottolog } m["paa-eke"] = { "East Keram", nil, "paa-ker", } m["paa-ele"] = { "Eleman", 3034298, aliases = {"Kerema Bay"}, } m["paa-elp"] = { "East Lakes Plain", -- [[w:East Lakes Plain languages]] redirects to [[w:Lakes Plain languages]]; but Croatian Wikipedia has an entry 12633078, "paa-lpl", aliases = {"East Lakes Plains"}, -- Usher } m["paa-epw"] = { "Eastern Pauwasi", 16115496, aliases = {"East Pauwasi"}, } m["paa-etf"] = { "Eastern Trans-Fly", 5330530, aliases = {"Oriomo"}, -- in increasing recent use, probably originating in Evans (2018) } m["paa-eti"] = { "East Timor", 15496066, "paa-tap", aliases = {"Oirata-Makasae", -- Wikipedia's name "Eastern Timor", -- alternative name given by Wikipedia "Fataluku-Makasai", "Oirata-Makasai", -- alternative names given by Wikidata }, } m["paa-fas"] = { "Fas", 3502658, aliases = {"Baibai-Fas"}, -- Glottolog's name } m["paa-flp"] = { "Far West Lakes Plain", -- [[w:Wapoga River languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86808337 is for the corresponding Wapoga languages category, which exists in enwiki "paa-lpl", aliases = {"Rasawa", -- Clouse (1997) "Wapoga River", -- Usher, including Kehu/Keuw (unclassified by others) }, } m["paa-gkw"] = { "Greater Kwerba", 12635134, aliases = {"West Foja Range", -- Usher "Kwerbic", -- Wikipedia "Kwerba", -- Foley (2018) }, } m["paa-gto"] = { "Galela-Tobelo", nil, "paa-nnh", aliases = {"Mainland North Halmaheran", -- Glottolog "Mainland North Halmahera", "Northeast Halmahera", -- alternative names "Northeast Halmaheran", -- Wikipedia, from Verhoeve 1988 }, } m["paa-hya"] = { "Heyo-Yahang", nil, "paa-mam", aliases = {"Yahang-Heyo"}, -- Wikipedia's name } m["paa-ing"] = { "Inland Gulf", 6034783, "paa-ani", aliases = {"Inland Gulf of Papua"}, -- Glottolog } m["paa-isk"] = { "Inner Sko", 65043889, "paa-sko", aliases = {"Skouic", -- Glottolog "West Vanimo Coast", -- Usher "Western Skou", -- Wikipedia "Inner Skou", "Nuclear Skou", -- alternative names given by Wikipedia }, } m["paa-iwa"] = { "Iwam", 15147853, "paa-sep", } m["paa-kae"] = { "Kamula-Elevala", 130390498, -- often placed in TNG aliases = {"Kamula-Elevala River"}, } m["paa-kan"] = { "Kanum", -- removed from Tonda by Glottolog nil, "paa-ton", } m["paa-kay"] = { "Kayagaric", 7566330, aliases = {"Kayagar", -- formerly common "Cook River"}, -- per Usher (2020) } m["paa-ker"] = { "Keram", 48768173, -- often grouped within or coordinate with the Ramu languages aliases = {"Keram River"}, } m["paa-kiw"] = { "Kiwaian", 338449, aliases = {"Kiwai"}, -- formerly common, still sees some use } m["paa-kko"] = { "Kaure-Kosare", -- rejected by Pawley-Hammarström but accepted by Glottolog, Foley (2018) and Usher (2020) 48767891, aliases = {"Nawa River"}, -- Usher's term } m["paa-koa"] = { "Kombio-Arapesh", 16115049, "paa-trr", aliases = {"Kombio-Arapeshan", -- Laycock, who includes Wom "Kombio-Arapesh-Urat", -- Glottolog, including Urat }, } m["paa-kol"] = { "Kolopom", 6427807, } m["paa-kom"] = { "Kombio", 65044238, "paa-koa", aliases = {"Kombian", -- Laycock "Kombio-Yambes", -- Glottolog }, } m["paa-kun"] = { "Kunimaipan", 134973258, aliases = {"Northwest Wharton Range"}, -- per Usher (2020) -- often considered a subfamily of Goilalan } m["paa-kwa"] = { "Kwalean", 6450053, aliases = {"Humene-Uare"}, } m["paa-kwe"] = { "Kwerba proper", 12635134, "paa-gkw", aliases = {"Kwerba", -- Usher "Kwerbaic", -- Glottolog }, } m["paa-kwo"] = { "Kwomtari", 2075415, aliases = {"Kwomtari-Nai"}, -- Senu River is a larger unproven proposal } m["paa-lla"] = { "Loloda-Laba", -- a single language in Glottolog (Loloda-Laba) and Wikipedia (Loloda) 11732388, -- for the Loloda language "paa-gto", aliases = {"Loloda"}, -- Wikipedia's name } m["paa-lma"] = { "Left May", 614468, aliases = {"Arai River"}, -- per Usher (2020) -- Sometimes in a putative Arai-Samaia family along with Amto-Musan and the Pyu language } m["paa-lmu"] = { "Lepki-Murkim", -- Kembra accepted by Glottolog and Usher; not by Foley (2020) but does not exclude the possibility -- of a relationship 85776285, -- independent family per Glottolog, part of South Pauwasi River family (under Pauwasi) per Usher (2020) aliases = {"Lepki-Murkim-Kembra"}, -- Glottolog } m["paa-lpl"] = { "Lakes Plain", 6478969, aliases = {"Lakes Plains"}, } m["paa-lra"] = { "Lower Ramu", 65089469, "paa-ram", aliases = {"Ottilien-Misegian"}, -- alternative name given by Wikipedia } m["paa-lse"] = { "Lower Sepik", 7061700, aliases = {"Nor-Pondo"}, } m["paa-mai"] = { "Mairasi", 6736896, aliases = {"Mairasic"}, -- per Glottolog } m["paa-mal"] = { "Mailuan", 6735839, aliases = {"Cloudy Bay"}, } m["paa-mam"] = { "Maimai", -- Foley's Maimai is expanded 53679325, -- this is the code for the expanded Maimai with 6 languages, as opposed to the 3 in "Nuclear Maimai" "paa-trr", aliases = {"Nuclear Maimai", -- Glottolog's name "Maimai proper", -- Wikipedia's name }, } m["paa-man"] = { "Manubaran", 6752335, aliases = {"Mount Brown"}, } m["paa-mar"] = { "Marienberg", 1570589, "paa-trr", aliases = {"Marienberg Hills"}, -- Usher } m["paa-may"] = { "Maybratic", 4830892, -- the code for the Maybrat language in Wikipedia, which subsumes the two languages of this family -- putatively included in West Papuan but generally considered an isolated family aliases = {"Maybrat-Karon"}, } m["paa-mbi"] = { "Mbaham-Iha", 85784512, "qfa-dis", -- Papuan languages; Glottolog groups Karas (Kalamang) with Mbaham-Iha into a (mainland) West Bomberai -- family and stops there; Wikipedia, following Usher and Schapper (2022), groups Karas, Mbaham-Iha -- and the large Timor-Alor-Pantar family into a (Greater) West Bomberai family, saying that Karas is no -- closer to Mbaham-Iha than to Timor-Alor-Pantar. aliases = {"Mbahaam-Iha", -- used by Wikidata "Nuclear West Bomberai", -- Glottolog's name }, } m["paa-mby"] = { "Marind-Boazi-Yaqay", 3217484, "paa-ani", aliases = {"Marind-Boazi-Yaqai", -- Glottolog "Marind-Yakhai", -- Usher, without Boazi "Marind-Yaqai", -- Wikidata "Marind", -- alternative name given by Wikipedia "Marind-Arandai", -- alternative name given by Spanish Wikipedia }, } m["paa-mmu"] = { "Mandi-Muniwara", nil, "paa-mar", aliases = {"West Marienberg Hills"}, -- Usher } m["paa-mon"] = { "Monumbo", -- per Glottolog: "No evidence for the Bogia (Monumbo) languages being related to other Torricelli languages was ever presented" 16928417, aliases = {"Bogia", -- Glottolog "Bogia Bay", -- Usher (2020) }, } m["paa-mri"] = { "Marindic", -- [[w:Marindic languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Marind"}, -- Usher; a single language } m["paa-nam"] = { "Nambu", 6961418, "paa-yam", aliases = {"East Morehead River"}, -- Usher } m["paa-nbo"] = { "North Bougainville", 749496, } m["paa-ndu"] = { "Ndu", 3217498, "paa-sep", -- Not accepted by Glottolog aliases = {"Ndu-Nggala"}, -- Usher } m["paa-ngk"] = { "Ngkolmpu", -- considered a single language by Wikipedia 5908646, "paa-kan", aliases = {"Ngkantr", -- Glottolog "Ngkolmpu Kanum", -- Wikipedia "Ngkontar", -- alternative name given by Wikipedia "Kanum", -- used by Wikidata }, } m["paa-nha"] = { "North Halmahera", 3217358, -- possibly in a proposed West Papuan family or an independent family } m["paa-nim"] = { "Nimboran", 12638426, aliases = {"Nimboranic", -- per Glottolog "Grime River", -- per Usher (2020) } } m["paa-nnd"] = { "Nuclear Ndu", nil, "paa-ndu", aliases = {"Ndu", -- Usher, with Boiken/Boikin "Ndu proper", -- Wikipedia }, } m["paa-nnh"] = { "Northern North Halmahera", nil, "paa-nha", aliases = {"Northern North Halmaheran", -- Glottolog "Halmahera", -- Usher "Core Halmaheran", -- Wikipedia }, } m["paa-nto"] = { "Namla-Tofanma", 16918187, -- independent family per Glottolog and Foley (2018), part of West Pauwasi family (under Pauwasi) per Usher (2020) } m["paa-ott"] = { "Ottilien", 7109477, "paa-lra", aliases = {"Ramu Coast", -- Usher "Watam-Awar-Gamay", -- alternative name given by Wikipedia }, } m["paa-pah"] = { "Pahoturi River", 17049141, aliases = {"Pahoturi"}, -- per Glottolog } m["paa-pal"] = { "Palei", -- Laycock adds Agi and Nabi/Nambi(-Metan) 65089113, "paa-wpa", aliases = {"Nuclear Palai"}, } m["paa-pia"] = { "Piawi", -- per Wikipedia, grouped with Arafundi languages to form Upper Yuat, which is a sister to Madang 7190400, aliases = {"Schraeder Range", -- Usher? "Waibuk"}, } m["paa-pio"] = { "Piore River", 65043152, "paa-sko", aliases = {"Barupu Lagoon", -- Glottolog "Lagoon", -- alternative name given by Wikipedia }, } m["paa-por"] = { "Porapora", -- Foley includes Ambakich (which we, Glottolog, and Usher treat as Keram) 65044258, "paa-ram", aliases = {"Agoan", -- Glottolog "Porapora River", -- Usher "core Grass", -- alternative name given by Wikipedia }, } m["paa-ram"] = { "Ramu", 3442808, aliases = {"Ramu River"}, -- per Usher (2020) } m["paa-rsa"] = { "Rasawa-Saponi", -- [[w:Rasawa-Saponi languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q9859418 is for the coresponding category, which exists in the Piedmontese Wikipedia (?!) "paa-flp", aliases = {"Rombak River"}, -- Usher } m["paa-rub"] = { "Ruboni", 6875319, "paa-lra", aliases = {"Misegian", -- Wikipedia's name "Mikarew", -- alternative name given by Wikipedia "Ruboni Range"}, -- Usher } m["paa-saa"] = { "Samarokena-Airoran", 96417699, "paa-gkw", aliases = {"Apauwar Coast"}, -- Usher } m["paa-sah"] = { "Sahu", nil, "paa-nnh", } m["paa-sbo"] = { "South Bougainville", 3217380, } m["paa-sen"] = { "Sentani", 17044584, -- no consensus on higher affiliations, if any aliases = {"Sentanic", "Demta-Sentani", "Demta-Lake Sentani"}, -- Sentanic per Glottolog, Demta-Sentani per Wikipedia } m["paa-sep"] = { "Sepik", 3508772, } m["paa-shi"] = { "Serra Hills", 65043154, "paa-sko", } m["paa-sko"] = { "Sko", 953509, aliases = {"Skou"}, } m["paa-sng"] = { "Senagi", 2066550, } m["paa-taa"] = { "Taikat-Awyi", -- [[w:Taikat languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12643265, "paa-bor", aliases = {"Taikat", -- Foley "Upper Tami River", -- Usher }, } m["paa-tam"] = { "Tamolan", 7681634, "paa-ram", aliases = {"Guam River"}, -- Usher } m["paa-tap"] = { "Timor-Alor-Pantar", 16590002, } m["paa-teb"] = { "Teberan", 7692052, -- Often grouped with Trans-New Guinea, but per Pawley-Hammarström (2018), it has "weaker or disputed claims to membership in TNG". aliases = {"Dadibi-Folopa"}, } m["paa-tir"] = { "Tirio", 7809225, "paa-ani", aliases = {"Nuclear Lower Fly", -- Pawley-Hammarström ("Lower Fly" includes Abom) "Nuclear Tirio", -- Glottolog ("Tirio" includes Abom) "Lower Fly River", -- Usher (without Abom) }, } m["paa-tki"] = { "Turama-Kikori", 7853680, aliases = {"Turama-Kikorian", "Rumu-Omati River"}, } m["paa-ton"] = { "Tonda", 8581005, "paa-yam", aliases = {"West Morehead River"}, -- Usher } m["paa-too"] = { "Tor-Orya", 16590099, aliases = {"Orya-Tor"}, } m["paa-tor"] = { "Tor", -- [[w:Tor languages]] redirects to [[w:Orya–Tor languages]] nil, "paa-too", } m["paa-trr"] = { "Torricelli", 1333831, } m["paa-tti"] = { "Ternate-Tidore", nil, "paa-nnh", } m["paa-wal"] = { "Walio", 16919872, -- Often placed in Sepik (e.g. by Laycock and Z'graggen (1975)), but not by Foley (2018), and not accepted by Glottolog. aliases = {"Walioic", -- Glottolog "Central Leonhard Schultze River", }, } m["paa-wap"] = { "Wapei", -- Glottolog includes Nabi/Nambi(-Metan) in Wapeic 65089115, "paa-wpa", aliases = {"Wapeic"}, -- Glottolog } m["paa-war"] = { "Waris", -- [[w:Waris languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12645076, "paa-bor", aliases = {"Warisic", -- Glottolog "Bapi River", -- Usher (without Manem or Senggi) }, } m["paa-wbh"] = { "West Bird's Head", 5330530, -- Kuwani is sometimes included; probably related to North Halmahera languages. } m["paa-wel"] = { "Western Eleman", nil, "paa-ele", aliases = {"West Eleman"}, } m["paa-wig"] = { "West Inland Gulf", nil, "paa-ing", aliases = {"West Inland Gulf of Papua"}, -- Glottolog } m["paa-wke"] = { "West Keram", nil, "paa-ker", aliases = {"Koam", "Mongol-Langam", "Ulmapo"}, -- Koam used by Foley, Ulmapo used by Glottolog } m["paa-wko"] = { "Wára-Kómnzo", -- since we split out Kómnzo as a separate language 11732474, -- for the Wara language "paa-ton", aliases = {"Anta-Komnzo-Wára-Wérè-Kémä", -- Glottolog's name "Wára", "Wara", -- Wikipedia }, } m["paa-wlp"] = { "West Lakes Plain", -- [[w:Tariku languages]] redirects to [[w:Lakes Plain languages]] 47007503, -- actually for "Tariku languages", which per Wikipedia covers Fayu, Kirikiri, Iau and Tause "paa-lpl", aliases = {"West Tariku", -- Glottolog "West Lakes Plains"}, -- Usher, with Edopi/Iau } m["paa-wpa"] = { "Wapei-Palei", 65043156, "paa-trr", } m["paa-wpw"] = { -- paa-wpa already used by Wapei-Palei "Western Pauwasi", -- 2 langs per Glottolog and Pawley-Hammarström; Usher also includes Namla-Tofanma and Usku 85815062, aliases = {"West Pauwasi", -- Wikipedia, Usher "Tebi-Towe", "Dubu-Towei"}, } m["paa-yam"] = { "Yam", 15062272, aliases = {"Morehead and Upper Maro River", "Morehead River", -- Usher }, } m["paa-yaq"] = { "Yaqayic", -- [[w:Yaqai languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Yakhai-Warkay"}, -- Usher } m["paa-ysa"] = { "Yawa-Saweru", 3217545, aliases = {"Yawa", "Yawan", "Yapen"}, } m["paa-yua"] = { "Yuat", 8060096, } m["phi"] = { "Philippine", 947858, "poz", } m["phi-kal"] = { "Kalamian", 3217466, "phi", aliases = {"Calamian"}, } m["poz"] = { "Malayo-Polynesian", 143158, "map", } m["poz-aay"] = { "Admiralty Islands", 2701306, "poz-oce", } m["poz-bnn"] = { "North Bornean", 1427907, "poz", } m["poz-bre"] = { "East Barito", 2701314, "poz", } m["poz-brw"] = { "West Barito", 2761679, "poz", } m["poz-bss"] = { "Bali-Sasak-Sumbawa", 3396043, "poz-msa", } m["poz-btk"] = { "Bungku-Tolaki", 3217381, "poz-clb", } m["poz-cet"] = { "Central-Eastern Malayo-Polynesian", 2269883, "poz", } m["poz-clb"] = { "Celebic", 1078041, "poz", } m["poz-cln"] = { "New Caledonian", 3091221, "poz-ocs", } m["poz-cma"] = { "Central Maluku", 3217479, "poz-cet", } m["poz-hce"] = { "Halmahera-Cenderawasih", 2526616, "pqe", } m["poz-kal"] = { "Kaili-Pamona", 3217465, "poz-clb", } m["poz-lgx"] = { "Lampungic", 49215, "poz", } m["poz-mcm"] = { "Malayo-Chamic", nil, "poz-msa", } m["poz-mic"] = { "Micronesian", 420591, "poz-occ", } m["poz-mly"] = { "Malayic", 662628, "poz-mcm", } m["poz-msa"] = { "Malayo-Sumbawan", 1363818, "poz", } m["poz-mun"] = { "Muna-Buton", 3037924, "poz-clb", } m["poz-nws"] = { "Northwest Sumatran", 2071308, "poz", } m["poz-occ"] = { "Central-Eastern Oceanic", 2068435, "poz-oce", } m["poz-oce"] = { "Oceanic", 324457, "pqe", } m["poz-ocs"] = { "Southern Oceanic", 3039118, "poz-occ", } m["poz-ocw"] = { "Western Oceanic", 2701282, "poz-oce", } m["poz-pcc"] = { "Central Pacific", 3130237, "poz-occ", } m["poz-pep"] = { "Eastern Polynesian", 390979, "poz-pnp", } m["poz-pnp"] = { "Nuclear Polynesian", 743851, "poz-pol", } m["poz-pol"] = { "Polynesian", 390979, "poz-pcc", } m["poz-san"] = { "Sabahan", 3217517, "poz-bnn", } m["poz-sbj"] = { "Sama-Bajaw", 2160409, "poz", } m["poz-slb"] = { "Saluan-Banggai", 3217519, "poz-clb", } m["poz-sls"] = { "Southeast Solomonic", 3119671, "poz-occ", } m["poz-ssw"] = { "South Sulawesi", 2778190, "poz", } m["poz-stm"] = { "St. Matthias", 6484143, "poz-oce", aliases = {"St Matthias"}, } m["poz-swa"] = { "North Sarawakan", 538569, "poz-bnn", } m["poz-tem"] = { "Temotu", 3075769, "poz-oce", } m["poz-tim"] = { "Timoric", 7806987, "poz-cet", } m["poz-ton"] = { "Tongic", 3397263, "poz-pol", } m["poz-tot"] = { "Tomini-Tolitoli", 3217541, "poz-clb", } m["poz-vnc"] = { "Central Vanuatu", 5061988, "poz-ocs", } m["poz-vnn"] = { "North Vanuatu", 85789650, "poz-ocs", } m["poz-vns"] = { "South Vanuatu", 3070173, "poz-ocs", } m["poz-wot"] = { "Wotu-Wolio", 1041317, "poz-clb", aliases = {"Island Kaili-Wolio"}, -- Glottolog } m["pqe"] = { "Eastern Malayo-Polynesian", 2269883, "poz-cet", } m["qfa-adc"] = { "Central Great Andamanese", nil, "qfa-adm", } m["qfa-adm"] = { "Great Andamanese", 3515103, } m["qfa-adn"] = { "Northern Great Andamanese", nil, "qfa-adm", } m["qfa-ads"] = { "Southern Great Andamanese", nil, "qfa-adm", } m["qfa-ain"] = { "Ainuic", 50111972, aliases = {"Ainu"}, } m["qfa-bej"] = { "Be-Jizhao", nil, "qfa-bet", } m["qfa-bet"] = { "Be-Tai", 12627719, "qfa-tak", aliases = {"Tai-Be", "Daic-Beic", "Beic-Daic"}, } m["qfa-buy"] = { "Buyang", 1109927, "qfa-kra", } m["qfa-cka"] = { "Chukotko-Kamchatkan", 33255, } m["qfa-cre"] = { "creole", 33289, "crp", } m["qfa-ckn"] = { "Chukotkan", 2606732, "qfa-cka", } m["qfa-cnt"] = { "contact", 133253514, "qfa-not", } m["qfa-dis"] = { -- Languages that are not unclassifiable (qfa-unc) but where there is no consensus on classification. Usually -- this is because the languages are divergent and it's disputed whether they are isolates or distantly related -- to other languages. "disputed affiliation", nil, "qfa-not", } m["qfa-dgn"] = { "Dogon", 1234776, "nic", } m["qfa-dny"] = { "Dene-Yeniseian", 21103, aliases = {"Dené-Yeniseian"}, } m["qfa-hur"] = { "Hurro-Urartian", 1144159, } m["qfa-iso"] = { "isolate", 33648, "qfa-not", } m["qfa-kad"] = { "Kadu", -- considered either Nilo-Saharan or independent/none 1720989, } m["qfa-kms"] = { "Kam-Sui", 1023641, "qfa-tak", } m["qfa-kor"] = { "Koreanic", 11263525, } m["qfa-kra"] = { "Kra", 1022087, "qfa-tak", } m["qfa-lic"] = { "Hlai", 1023648, "qfa-tak", aliases = {"Hlaic"}, } m["qfa-mch"] = { -- used in both N and S America "Macro-Chibchan", 3438062, } m["qfa-mix"] = { "mixed", 33694, "qfa-cnt", } m["qfa-not"] = { "not a family", nil, "qfa-not", } m["qfa-onb"] = { "Be", nil, "qfa-bej", aliases = {"Ong-Be", "Beic"}, } m["qfa-ong"] = { "Ongan", 2090575, aliases = {"Angan", "South Andamanese", "Jarawa-Onge"}, } m["qfa-pid"] = { "pidgin", 33831, "crp", } m["qfa-sub"] = { "substrate", 20730913, "qfa-not", } m["qfa-tak"] = { "Kra-Dai", 34171, aliases = {"Tai-Kadai", "Kadai"}, } m["qfa-tyn"] = { "Tyrsenian", 1344038, } m["qfa-unc"] = { -- This corresponds to languages normally called "unclassified", i.e. there is insufficient data or research to -- classify them, whereas our [[:Category:Unclassified languages]] is just languages that no Wiktionary editor -- has classified yet (the family code in the language data is missing). "unclassifiable", 33956, "qfa-not", } m["qfa-xgs"] = { "Serbi-Mongolic", 108887939, } m["qfa-xgx"] = { "Para-Mongolic", 107619002, "qfa-xgs", } m["qfa-yen"] = { "Yeniseian", 27639, "qfa-dny", aliases = {"Yeniseic", "Yenisei-Ostyak"}, } m["qfa-yke"] = { "Ketic", nil, "qfa-yen", } m["qfa-yko"] = { "Kottic", nil, "qfa-yen", } m["qfa-yrn"] = { "Arinic", nil, "qfa-yen", } m["qfa-ypm"] = { "Pumpokolic", nil, "qfa-yen", } m["qfa-yuk"] = { "Yukaghir", 34164, aliases = {"Yukagir", "Jukagir"}, } m["qwe"] = { "Quechuan", 5218, } m["raj"] = { "Rajasthani", 13196, "inc-wes", protoLanguage = "inc-ogu", } m["roa"] = { "Romance", 19814, "itc", aliases = {"Romanic", "Latin", "Neolatin", "Neo-Latin"}, protoLanguage = "la", } m["roa-asl"] = { "Asturleonese", 35390, "roa-ibe", protoLanguage = "roa-ole", } m["roa-cas"] = { "Castilian", 71924, "roa-ibe", aliases = {"Castillian", "Castilic", "Castillic"}, protoLanguage = "osp", } m["roa-dal"] = { "Dalmatian Romance", 97646077, "roa-itd", } m["roa-eas"] = { "Eastern Romance", 147576, "roa", } m["roa-emr"] = { "Emilian-Romagnol", 242648, "roa-git", } m["roa-gap"] = { "Galician-Portuguese", 9080204, "roa-ibe", aliases = {"Galician Romance", "Galaic-Portuguese"}, protoLanguage = "roa-opt", } m["roa-gar"] = { "Gallo-Romance", 500394, "roa-wes", } m["roa-itd"] = { "Italo-Dalmatian", 3313381, "roa-iwr", aliases = {"Central Romance"} } m["roa-itr"] = { "Italo-Romance", 3356483, "roa-itd", } m["roa-iwr"] = { "Italo-Western Romance", 112608, "roa", aliases = {"Italo-Western"}, } m["roa-git"] = { "Gallo-Italic", 516074, "roa-gar", aliases = {"Gallo-Italian", "Gallo-Cisalpine", "Cisalpine"}, } m["roa-grh"] = { "Gallo-Rhaetian", 97646466, "roa-gar", } m["roa-ibe"] = { "Ibero-Romance", 749533, "roa-wes", aliases = {"Iberian Romance", "West Ibero-Romance", "Western Ibero-Romance", "West Iberian Romance", "Western Iberian Romance"} } m["roa-nar"] = { "Navarro-Aragonese", 133252927, "roa-ibe", protoLanguage = "roa-ona", } m["roa-oil"] = { "Oïl", 37351, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, protoLanguage = "fro", } m["roa-ocr"] = { "Occitano-Romance", 599958, "roa-gar", aliases = {"Gallo-Narbonnese", "East Iberian", "Eastern Iberian"}, } m["roa-rhe"] = { "Rhaeto-Romance", 515593, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, } m["roa-sou"] = { "Southern Romance", 145345, "roa", } m["roa-wes"] = { "Western Romance", 2714388, "roa-iwr", } --[=[ Exceptional language and family codes for South American Indian languages can use the prefix "sai-", though "sai" is no longer itself a family code. ]=]-- m["sai-ara"] = { "Araucanian", 626630, } m["sai-aym"] = { "Aymaran", 33010, } m["sai-bar"] = { "Barbacoan", 807304, aliases = {"Barbakoan"}, } m["sai-bor"] = { "Boran", 5371776, } m["sai-cah"] = { "Cahuapanan", 1025793, } m["sai-car"] = { "Cariban", 33090, aliases = {"Carib"}, } m["sai-cer"] = { "Cerrado", 98078151, "sai-jee", aliases = {"Amazonian Jê"}, } m["sai-chc"] = { "Chocoan", 1075616, aliases = {"Choco", "Chocó"}, } m["sai-cho"] = { "Chonan", 33019, aliases = {"Chon"}, } m["sai-cje"] = { "Central Jê", 18010843, "sai-cer", aliases = {"Akuwẽ"}, } m["sai-cpc"] = { "Chapacuran", 1062626, } m["sai-crn"] = { "Charruan", 3112423, aliases = {"Charrúan"}, } m["sai-ctc"] = { "Catacaoan", 5051139, } m["sai-guc"] = { "Guaicuruan", 1974973, "sai-mgc", aliases = {"Guaicurú", "Guaycuruana", "Guaikurú", "Guaycuruano", "Guaykuruan", "Waikurúan"}, } m["sai-guh"] = { "Guahiban", 944056, aliases = {"Guahiboan", "Guajiboan", "Wahivoan"}, } m["sai-gui"] = { "Guianan", nil, "sai-car", aliases = {"Guianan Carib", "Guiana Carib"}, } m["sai-har"] = { "Harákmbut", 1584402, "sai-hkt", aliases = {"Harákmbet"}, } m["sai-hkt"] = { "Harákmbut-Katukinan", 17107635, } m["sai-hrp"] = { "Huarpean", 1578336, aliases = {"Warpean", "Huarpe", "Warpe"}, } m["sai-jee"] = { "Jê", 1483594, "sai-mje", aliases = {"Gê", "Jean", "Gean", "Jê-Kaingang", "Ye"}, } m["sai-jir"] = { "Jirajaran", 3028651, aliases = {"Hiraháran"}, } m["sai-jiv"] = { "Jivaroan", 1393074, aliases = {"Hívaro", "Jibaro", "Jibaroan", "Jibaroana", "Jívaro"}, } m["sai-ktk"] = { "Katukinan", 2636000, "sai-hkt", aliases = {"Catuquinan"}, } m["sai-kui"] = { "Kuikuroan", nil, "sai-car", aliases = {"Kuikuro", "Nahukwa"}, } m["sai-map"] = { "Mapoyan", 61096301, "sai-ven", aliases = {"Mapoyo", "Mapoyo-Yabarana", "Mapoyo-Yavarana", "Mapoyo-Yawarana"}, } m["sai-mas"] = { "Mascoian", 1906952, aliases = {"Mascoyan", "Maskoian", "Enlhet-Enenlhet"}, } m["sai-mgc"] = { "Mataco-Guaicuru", 255512, } m["sai-mje"] = { "Macro-Jê", 887133, aliases = {"Macro-Gê"}, } m["sai-mtc"] = { "Matacoan", 2447424, "sai-mgc", } m["sai-mur"] = { "Muran", 33826, aliases = {"Mura"}, } m["sai-nad"] = { "Nadahup", 1856439, aliases = {"Makú", "Macú", "Vaupés-Japurá"}, } m["sai-nje"] = { "Northern Jê", 98078225, "sai-cer", aliases = {"Core Jê"}, } m["sai-nmk"] = { "Nambikwaran", 15548027, aliases = {"Nambicuaran", "Nambiquaran", "Nambikuaran"}, } m["sai-otm"] = { "Otomacoan", 3217503, aliases = {"Otomákoan", "Otomakoan"}, } m["sai-pan"] = { "Panoan", 1544537, "sai-pat", aliases = {"Pano"}, } m["sai-pat"] = { "Pano-Tacanan", 2475746, aliases = {"Pano-Tacana", "Pano-Takana", "Páno-Takána", "Pano-Takánan"}, } m["sai-pek"] = { "Pekodian", 107451736, "sai-car", aliases = {"South Amazonian Carib", "Southern Cariban", "Pekodi"}, } m["sai-pem"] = { "Pemongan", nil, "sai-ven", aliases = {"Pemong", "Pemóng", "Purukoto"}, } m["sai-pey"] = { "Peba-Yaguan", 174015, aliases = {"Peba-Yagua", "Yaguan", "Peban", "Yáwan"}, } m["sai-prk"] = { "Parukotoan", 107451482, "sai-car", aliases = {"Parukoto"}, } m["sai-sje"] = { "Southern Jê", 98078245, "sai-jee", } m["sai-tac"] = { "Tacanan", 3113762, "sai-pat", } m["sai-tar"] = { "Taranoan", 105097814, "sai-gui", aliases = {"Trio", "Tarano"}, } m["sai-tuc"] = { "Tucanoan", 788144, } m["sai-tyu"] = { "Ticuna-Yuri", 4467010, } m["sai-ucp"] = { "Uru-Chipaya", 2475488, aliases = {"Uru-Chipayan"}, } m["sai-ven"] = { "Venezuelan Cariban", nil, "sai-car", aliases = {"Venezuelan Carib", "Venezuelan", "Venezuelano"}, } m["sai-wic"] = { "Wichí", 3027047, } m["sai-wit"] = { "Witotoan", 43079317, aliases = {"Huitotoan", "Uitotoan"}, } m["sai-ynm"] = { "Yanomami", nil, aliases = {"Yanomam", "Shamatari", "Yamomami", "Yanomaman"}, } m["sai-yuk"] = { "Yukpan", nil, "sai-car", aliases = {"Yukpa", "Yukpano", "Yukpa-Japreria"}, } m["sai-zam"] = { "Zamucoan", 3048461, aliases = {"Samúkoan"}, } m["sai-zap"] = { "Zaparoan", 33911, aliases = {"Záparoan", "Saparoan", "Sáparoan", "Záparo", "Zaparoano", "Zaparoana"}, } m["sal"] = { "Salish", 33985, } m["sdv"] = { "Eastern Sudanic", 2036148, "ssa", } m["sdv-bri"] = { "Bari", nil, "sdv-nie", } m["sdv-daj"] = { "Daju", 956724, "sdv", } m["sdv-dnu"] = { "Dinka-Nuer", nil, "sdv-niw", } m["sdv-eje"] = { "Eastern Jebel", 3408878, "sdv", } m["sdv-kln"] = { "Kalenjin", 637228, "sdv-nis", } m["sdv-lma"] = { "Lotuko-Maa", nil, "sdv-nie", } m["sdv-lon"] = { "Northern Luo", nil, "sdv-luo", } m["sdv-los"] = { "Southern Luo", 7570103, "sdv-luo", } m["sdv-luo"] = { "Luo", nil, "sdv-niw", } m["sdv-nes"] = { "Northern Eastern Sudanic", 4810496, "sdv", aliases = {"Astaboran", "Ek Sudanic"}, } m["sdv-nie"] = { "Eastern Nilotic", 153795, "sdv-nil", } m["sdv-nil"] = { "Nilotic", 513408, "sdv", } m["sdv-nis"] = { "Southern Nilotic", 1552410, "sdv-nil", } m["sdv-niw"] = { "Western Nilotic", 3114989, "sdv-nil", } m["sdv-nma"] = { "Nandi-Markweta", nil, "sdv-kln", } m["sdv-nyi"] = { "Nyima", 11688746, "sdv-nes", aliases = {"Nyimang"}, } m["sdv-tmn"] = { "Taman", 3408873, "sdv-nes", aliases = {"Tamaic"}, } m["sdv-ttu"] = { "Teso-Turkana", 7705551, "sdv-nie", aliases = {"Ateker"}, } m["sel"] = { "Selkup", 34008, "syd", } m["sem"] = { "Semitic", 34049, "afa", } m["sem-ara"] = { "Aramaic", 28602, "sem-nwe", protoLanguage = "arc", } m["sem-arb"] = { "Arabic", 164667, "sem-cen", protoLanguage = "ar", } m["sem-are"] = { "Eastern Aramaic", 3410322, "sem-ara", } m["sem-arw"] = { "Western Aramaic", 3394214, "sem-ara", } m["sem-ase"] = { "Southeastern Aramaic", 3410322, "sem-are", } m["sem-can"] = { "Canaanite", 747547, "sem-nwe", } m["sem-cen"] = { "Central Semitic", 3433228, "sem-wes", } m["sem-cna"] = { "Central Neo-Aramaic", 3410322, "sem-are", } m["sem-eas"] = { "East Semitic", 164273, "sem", } m["sem-eth"] = { "Ethiopian Semitic", 163629, "sem-wes", aliases = {"Afro-Semitic", "Ethiopian", "Ethiopic", "Ethiosemitic"}, } m["sem-nna"] = { "Northeastern Neo-Aramaic", 2560578, "sem-are", } m["sem-nwe"] = { "Northwest Semitic", 162996, "sem-cen", } m["sem-osa"] = { "Old South Arabian", 35025, "sem-cen", aliases = {"Epigraphic South Arabian", "Sayhadic"}, } m["sem-sar"] = { "Modern South Arabian", 1981908, "sem-wes", } m["sem-wes"] = { "West Semitic", 124901, "sem", } m["sgn"] = { "sign", 34228, "qfa-not", } m["sgn-fsl"] = { "French Sign Languages", 5501921, "sgn", } m["sgn-gsl"] = { "German Sign Languages", 5551235, "sgn", } m["sgn-jsl"] = { "Japanese Sign Languages", 11722508, "sgn", } m["sio"] = { "Siouan", 34181, "nai-sca", } m["sio-dhe"] = { "Dhegihan", 3217420, "sio-msv", } m["sio-dkt"] = { "Dakotan", 4154122, "sio-msv", } m["sio-mor"] = { "Missouri River Siouan", 26807266, "sio", } m["sio-msv"] = { "Mississippi Valley Siouan", 12637104, "sio", } m["sio-ohv"] = { "Ohio Valley Siouan", 21070931, "sio", } m["sit"] = { "Sino-Tibetan", 45961, aliases = {"Trans-Himalayan"}, } m["sit-aao"] = { "Central Naga", 615474, "sit", } m["sit-alm"] = { "Almora", nil, "sit-whm", } m["sit-bai"] = { "Bai", 35103, "sit-mba", } m["sit-bdi"] = { "Bodish", 1814078, "sit", } m["sit-cln"] = { "Cai-Long", 107182612, "sit-mba", aliases = {"Ta-Li"}, } m["sit-dhi"] = { "Dhimalish", 1207648, "sit", } m["sit-ebo"] = { "East Bodish", 56402, "sit-bdi", } m["sit-egy"] = { "East rGyalrongic", 832026, "sit-rgy", } m["sit-ers"] = { "Ersuic", 56335, "sit", } m["sit-gma"] = { "Greater Magaric", 55612963, "sit", } m["sit-gsi"] = { "Greater Siangic", 52698851, "sit", } m["sit-hrs"] = { "Hrusish", 1632501, "sit", aliases = {"Southeast Kamengic"}, } m["sit-jnp"] = { "Jingphoic", nil, "sit-jpl", aliases = {"Jingpho"}, } m["sit-jpl"] = { "Kachin-Luic", 1515454, "tbq-bkj", aliases = {"Jingpho-Luish", "Jingpho-Asakian", "Kachinic"}, } m["sit-kch"] = { "Konyak-Chang", nil, "sit-kon", } m["sit-kha"] = { "Kham", 33305, "sit-gma", } m["sit-khb"] = { "Kho-Bwa", 6401917, "sit", aliases = {"Bugunish", "Kamengic"}, } m["sit-khw"] = { "Western Kho-Bwa", nil, "sit-khb", } m["sit-khc"] = { "Chug-Lish", nil, "sit-khw", aliases = {"Duhumbi-Khispi"}, } m["sit-khm"] = { "Mey-Sartang", nil, "sit-khw", aliases = {"Sartang-Sherdukpen"}, } m["sit-kic"] = { "Central Kiranti", nil, "sit-kir", } m["sit-kie"] = { "Eastern Kiranti", nil, "sit-kir", } m["sit-kin"] = { "Kinnauric", nil, "sit-whm", aliases = {"Kinnauri"}, } m["sit-kir"] = { "Kiranti", 922148, "sit", } m["sit-kiw"] = { "Western Kiranti", 922148, "sit-kir", } m["sit-kon"] = { "Northern Naga", 774590, "tbq-bkj", aliases = {"Konyakian", "Konyak"}, } m["sit-kyk"] = { "Kyirong-Kagate", 6450957, "sit-tib", } m["sit-lab"] = { "Ladakhi-Balti", 6450957, "sit-tib", } m["sit-las"] = { "Lahuli-Spiti", 6473510, "sit-tib", } m["sit-luu"] = { "Luish", 55621439, "sit-jpl", aliases = {"Asakian", "Sak"}, } m["sit-mar"] = { "Maringic", nil, "sit-tma", } m["sit-mba"] = { "Macro-Bai", 16963847, "sit-sba", aliases = {"Greater Bai"}, } m["sit-mdz"] = { "Midzu", 6843504, "sit", aliases = {"Geman", "Midzuish", "Miju-Meyor", "Southern Mishmi"}, } m["sit-mnz"] = { "Mondzish", 6898839, "tbq-lob", aliases = {"Mangish"}, } m["sit-mru"] = { "Mruic", 16908870, "sit", aliases = {"Mru-Hkongso"}, } m["sit-nas"] = { "Naish", 25047956, "sit-nax", } m["sit-nax"] = { "Naic", 6982999, "tbq-buq", aliases = {"Naxish"}, } m["sit-nba"] = { "Northern Bai", 122463830, "sit-bai", } m["sit-new"] = { "Newaric", 55625069, "sit", } m["sit-nng"] = { "Nungish", 1515482, "sit", aliases = {"Nung"}, } m["sit-qia"] = { "Qiangic", 1636765, "tbq-buq", } m["sit-rgy"] = { "Rgyalrongic", 56936, "sit-qia", aliases = {"Jiarongic"}, } m["sit-sba"] = { "Sino-Bai", nil, "sit", aliases = {"Greater Bai"}, } m["sit-tam"] = { "Tamangic", 3309439, "sit", aliases = {"West Bodish"}, } m["sit-tan"] = { "Tani", 3217538, "sit", } m["sit-tib"] = { "Tibetic", 1641150, "sit-bdi", protoLanguage = "otb", } m["sit-tja"] = { "Tujia", nil, "sit", } m["sit-tma"] = { "Tangkhul-Maring", nil, "sit", } m["sit-tng"] = { "Tangkhulic", 1516657, "sit-tma", aliases = {"Tangkhul"}, } m["sit-tno"] = { "Tangsa-Nocte", nil, "sit-kon", } m["sit-tsk"] = { "Tshangla", nil, "sit", } m["sit-wgy"] = { "West rGyalrongic", nil, "sit-rgy" } m["sit-whm"] = { "West Himalayish", 2301695, "sit", } m["sit-zem"] = { "Zeme", 189291, "sit", aliases = {"Zeliangrong", "Zemeic"}, } m["sla"] = { "Slavic", 23526, "ine-bsl", aliases = {"Slavonic"}, } m["smi"] = { "Sami", 56463, "urj", aliases = {"Saami", "Samic", "Saamic"}, } m["son"] = { "Songhay", 505198, "ssa", aliases = {"Songhai"}, } m["sqj"] = { "Albanian", 8748, "ine", } m["ssa"] = { "Nilo-Saharan", -- possibly not a genetic grouping 33705, } m["ssa-fur"] = { "Fur", 2989512, "ssa", } m["ssa-klk"] = { "Kuliak", 1791476, "ssa", aliases = {"Rub"}, } m["ssa-kom"] = { "Koman", 1781084, "ssa", } m["ssa-sah"] = { "Saharan", 1757661, "ssa", } m["syd"] = { "Samoyedic", 34005, "urj", aliases = {"Samoyed", "Samodeic"}, } m["syd-ene"] = { "Enets", 29942, "syd", } m["tai"] = { "Tai", 749720, "qfa-bet", aliases = {"Daic"}, } m["tai-wen"] = { "Wenma-Southwestern Tai", nil, "tai", } m["tai-tay"] = { "Tày", nil, "tai-wen", } m["tai-sap"] = { "Sapa-Southwestern Tai", nil, "tai-wen", aliases = {"Sapa-Thai"}, } m["tai-swe"] = { "Southwestern Tai", 10889250, "tai-sap", } m["tai-cho"] = { "Chongzuo Tai", 13216, "tai", } m["tai-cen"] = { "Central Tai", 5061891, "tai", } m["tai-nor"] = { "Northern Tai", 7059014, "tai", } m["tbq"] = { "Tibeto-Burman", 34064, "sit", } m["tbq-anp"] = { "Angami-Pochuri", 530460, "sit", } m["tbq-axi"] = { "Axioid", nil, "tbq-sel", } m["tbq-bdg"] = { "Bodo-Garo", 4090000, "tbq-bkj", } m["tbq-bis"] = { "Bisoid", 48844742, "tbq-slo", } m["tbq-bka"] = { "Bi-Ka", 12627890, "tbq-slo", } m["tbq-bkj"] = { "Sal", 889900, "sit", -- Brahmaputran appears to be Glottolog's term aliases = {"Bodo-Konyak-Jinghpaw", "Brahmaputran", "Jingpho-Konyak-Bodo"}, } m["tbq-brm"] = { "Burmish", 865713, "tbq-lob", } m["tbq-buq"] = { "Burmo-Qiangic", 16056278, "sit", aliases = {"Eastern Tibeto-Burman"}, } m["tbq-drp"] = { "Downriver Phula", 7188378, "tbq-rph", } m["tbq-han"] = { "Hanoid", 17004185, "tbq-slo", } m["tbq-hph"] = { "Highland Phula", nil, "tbq-sel", } m["tbq-jin"] = { "Jino", 6202716, "tbq-slo", } m["tbq-kzh"] = { "Kazhuoish", 48834669, "tbq-lol", } m["tbq-kuk"] = { "Kuki-Chin", 832413, "sit", aliases = {"Kukish", "South-Central Tibeto-Burman"}, } m["tbq-lal"] = { "Lalo", 56548, "tbq-lso", } m["tbq-lho"] = { "Lahoish", nil, "tbq-lol", } m["tbq-llo"] = { "Lipo-Lolopo", nil, "tbq-lso", } m["tbq-lob"] = { "Lolo-Burmese", 1635712, "tbq-buq", } m["tbq-lol"] = { "Loloish", 37035, "tbq-lob", aliases = {"Yi", "Ngwi", "Nisoic"}, } m["tbq-lso"] = { "Lisoish", 6559055, "tbq-lol", } m["tbq-lwo"] = { "Lawoish", 48847673, "tbq-lol", } m["tbq-muj"] = { "Muji", 11221327, "tbq-hph", } m["tbq-nas"] = { "Nasoid", nil, "tbq-nlo", } m["tbq-nis"] = { "Nisu", 56404, "tbq-nlo", } m["tbq-nlo"] = { "Northern Loloish", 7058676, "tbq-nso", } m["tbq-nso"] = { "Nisoish", 56990, "tbq-lol", } m["tbq-nus"] = { "Nusoish", 114245231, "tbq-lol", } m["tbq-phw"] = { "Phowa", 7187959, "tbq-hph", } m["tbq-rph"] = { "Riverine Phula", nil, "tbq-sel", } m["tbq-sel"] = { "Southeastern Loloish", 16111894, "tbq-nso", } m["tbq-sil"] = { "Siloid", 60787071, "tbq-slo", } m["tbq-slo"] = { "Southern Loloish", 5649340, "tbq-lol", } m["tbq-tal"] = { "Taloid", 48804018, "tbq-lso", } m["tbq-urp"] = { "Upriver Phula", 7187058, "tbq-rph", } m["trk"] = { "Turkic", 34090, } m["trk-cmn"] = { "Common Turkic", 1126028, "trk", aliases = {"Shaz Turkic", "Shaz-Turkic"}, } m["trk-kar"] = { "Karluk", 703173, "trk-cmn", aliases = {"Qarluq", "Uyghur-Uzbek", "Southeastern Turkic"}, } m["trk-kbu"] = { "Kipchak-Bulgar", 3512539, "trk-kip", aliases = {"Uralian", "Uralo-Caspian"}, } m["trk-kcu"] = { "Kipchak-Cuman", 4370412, "trk-kip", aliases = {"Ponto-Caspian"}, } m["trk-kip"] = { "Kipchak", 1339898, "trk-cmn", -- Russian Wikipedia article [[w:ru:Западнотюркские_языки]] says "Western Turkic" is used by N.A. Baskakov and includes Oghuz, Kipchak and Karluk. -- Azerbaijani Wikipedia article [[w:az:Qərbi_türk_dilləri]] clarifies that "Western Turkic" is not a clade. other_names = {"Western Turkic"}, aliases = {"Kypchak", "Qypchaq", "Northwestern Turkic"}, protoLanguage = "qwm", } m["trk-kkp"] = { "Kyrgyz-Kipchak", 4221189, "trk-kip", } m["trk-kno"] = { "Kipchak-Nogai", 4326954, "trk-kip", aliases = {"Aralo-Caspian"}, } m["trk-nsb"] = { "North Siberian Turkic", 4537269, "trk-sib", aliases = {"Northern Siberian Turkic"}, } m["trk-ogr"] = { "Oghur", 1422731, "trk", aliases = {"Lir-Turkic", "r-Turkic"}, } m["trk-ogz"] = { "Oghuz", 494600, "trk-cmn", aliases = {"Southwestern Turkic"}, } m["trk-sib"] = { "Siberian Turkic", 354353, "trk-cmn", other_names = {"Northern Turkic"}, -- per [[w:ru:Восточнотюркские_языки]], "Eastern Turkic" is an alias for Siberian Turkic in the work of O.A. Mudrak, -- but has a different non-clade meaning in the older work of N.A. Baskakov. aliases = {"Eastern Turkic", "Northeastern Turkic"}, } m["trk-ssb"] = { "South Siberian Turkic", nil, "trk-sib", aliases = {"Southern Siberian Turkic"}, } m["tup"] = { "Tupian", 34070, aliases = {"Tupi"}, } m["tup-gua"] = { "Tupi-Guarani", 148610, "tup", aliases = {"Tupí-Guaraní"}, } m["tuw"] = { "Tungusic", 34230, aliases = {"Manchu-Tungus", "Tungus"}, } m["tuw-ewe"] = { "Ewenic", 105889448, "tuw", aliases = {"Northern Tungusic"}, } m["tuw-jrc"] = { "Jurchenic", 105889432, "tuw", aliases = {"Manchuric"}, } m["tuw-nan"] = { "Nanaic", 105889264, "tuw", } m["tuw-udg"] = { "Udegheic", 105889266, "tuw", } m["urj"] = { "Uralic", 34113, varieties = {"Finno-Ugric"}, } m["urj-fin"] = { "Finnic", 33328, "urj", aliases = {"Baltic-Finnic", "Balto-Finnic", "Fennic"}, } m["urj-mdv"] = { "Mordvinic", 627313, "urj", } m["urj-prm"] = { "Permic", 161493, "urj", } m["urj-ugr"] = { "Ugric", 156631, "urj", } m["wak"] = { "Wakashan", 60069, } m["wen"] = { "Sorbian", 25442, "zlw", aliases = {"Lusatian", "Wendish"}, } m["xgn"] = { "Mongolic", 33750, "qfa-xgs", aliases = {"Mongolian"}, } m["xgn-cen"] = { "Central Mongolic", 28719447, "xgn", protoLanguage = "xng-lat", } m["xgn-sou"] = { "Southern Mongolic", nil, "xgn", protoLanguage = "xng-ear", } m["xgn-shr"] = { "Shirongolic", 107539435, "xgn-sou", } m["xme"] = { "Median", nil, "ira-mpr", protoLanguage = "xme-old", } m["xme-ttc"] = { "Tatic", nil, "xme", } m["xnd"] = { "Na-Dene", 26986, "qfa-dny", aliases = {"Na-Dené"}, } m["xsc"] = { "Scythian", nil, "ira-nei", } m["xsc-sak"] = { "Saka", nil, "xsc-skw", aliases = {"Sakan"}, } m["xsc-sar"] = { "Sarmatian", nil, "xsc", } m["xsc-skw"] = { "Saka-Wakhi", nil, "xsc", } m["yok"] = { "Yokuts", 34249, "nai-you", aliases = {"Yokutsan", "Mariposan", "Mariposa"}, } m["ypk"] = { "Yupik", 27970, "esx-esk", aliases = {"Yup'ik", "Yuit"}, } m["yrk"] = { "Nenets", 36452, "syd", } m["zhx"] = { "Sinitic", 33857, "sit-sba", aliases = {"Chinese"}, protoLanguage = "och", } m["zhx-com"] = { "Coastal Min", 20667215, "zhx-min", } m["zhx-inm"] = { "Inland Min", 20667237, "zhx-min", } m["zhx-man"] = { "Mandarinic", nil, "zhx", protoLanguage = "cmn-ear", } m["zhx-min"] = { "Min", 56504, "zhx", } m["zhx-nan"] = { "Southern Min", 36495, "zhx-com", } m["zhx-pin"] = { "Pinghua", 2735715, "zhx", protoLanguage = "ltc", } m["zhx-yue"] = { "Yue", 7033959, "zhx", protoLanguage = "ltc", } m["zle"] = { "East Slavic", 144713, "sla", } m["zls"] = { "South Slavic", 146665, "sla", } m["zlw"] = { "West Slavic", 145852, "sla", } m["zlw-lch"] = { "Lechitic", 742782, "zlw", aliases = {"Lekhitic"}, } m["zlw-pom"] = { "Pomeranian", nil, "zlw-lch", } m["znd"] = { "Zande", 8066072, "nic-ubg", } return require("Module:languages").finalizeData(m, "family") b2ls9igr0aaopschwn348mbj9eodtxj 231360 231359 2026-04-14T05:44:33Z Lee 19 පැරණි සංස්කරණයකින් ගත් කොටස්... 231360 Scribunto text/plain --[=[ This module contains definitions for all language family codes on Wiktionary. ]=]-- local m = {} m["aav"] = { "Austroasiatic", 33199, aliases = {"Austro-Asiatic"}, } m["aav-khs"] = { "Khasian", 3073734, "aav", aliases = {"Khasic"}, } m["aav-nic"] = { "Nicobarese", 217380, "aav", } m["aav-pkl"] = { "Pnar-Khasi-Lyngngam", nil, "aav-khs", } m["afa"] = { "Afroasiatic", 25268, aliases = {"Afro-Asiatic"}, } m["alg"] = { "Algonquian", 33392, "aql", } m["alg-abp"] = { "Abenaki-Penobscot", 197936, "alg-eas", } m["alg-ara"] = { "Arapahoan", 2153686, "alg", } m["alg-eas"] = { "Eastern Algonquian", 2257525, "alg", } m["alg-sfk"] = { "Sac-Fox-Kickapoo", 1440172, "alg", } m["alv"] = { "Atlantic-Congo", 771124, "nic", } m["alv-aah"] = { "Ayere-Ahan", 750953, "alv-von", } m["alv-ada"] = { "Adamawa", 32906, "alv-sav", } m["alv-bag"] = { "Baga", 2746083, "alv-mel", } m["alv-bak"] = { "Bak", 1708174, "alv-sng", } m["alv-bam"] = { "Bambukic", 4853456, "alv-ada", aliases = {"Yungur-Jen"}, } m["alv-bny"] = { "Banyum", 2892477, "alv-nyn", } m["alv-bua"] = { "Bua", 4982094, "alv-mbd", } m["alv-bwj"] = { "Bikwin-Jen", 84542501, "alv-bam", } m["alv-cng"] = { "Cangin", 1033184, "alv-fwo", } m["alv-ctn"] = { "Central Tano", 1658486, "alv-ptn", aliases = {"Akan"}, } m["alv-dlt"] = { "Delta Edoid", nil, "alv-edo", } m["alv-dur"] = { "Duru", 5316788, "alv-lni", } m["alv-ede"] = { "Ede", 35368, "alv-yor", } m["alv-edk"] = { "Edekiri", 5336735, "alv-yrd", } m["alv-edo"] = { "Edoid", 1287469, "alv-von", } m["alv-eeo"] = { "Edo-Esan-Ora", 12630439, "alv-nce", } m["alv-fli"] = { "Fali", 3450166, "alv", } m["alv-fwo"] = { "Fula-Wolof", 12631267, "alv-sng", } m["alv-gbe"] = { "Gbe", 668284, "alv-von", } m["alv-gda"] = { "Ga-Dangme", 3443338, "alv-kwa", } m["alv-gng"] = { "Guang", 684009, "alv-ptn", } m["alv-gtm"] = { "Ghana-Togo Mountain", 493020, "alv-kwa", aliases = {"Togo Remnant", "Central Togo"}, } m["alv-hei"] = { "Heiban", 108752116, "alv-the", } m["alv-ido"] = { "Idomoid", 974196, "alv-von", } m["alv-igb"] = { "Igboid", 1429100, "alv-von", } m["alv-jfe"] = { "Jola-Felupe", 1708174, "alv-jol", aliases = {"Ejamat"}, } m["alv-jol"] = { "Jola", 35176, "alv-bak", aliases = {"Diola"}, } m["alv-kim"] = { "Kim", 6409701, "alv-mbd", } m["alv-kis"] = { "Kissi", 35696, "alv-mel", } m["alv-krb"] = { "Karaboro", 4213541, "alv-snf", } m["alv-ktg"] = { "Ka-Togo", 5972796, "alv-gtm", } m["alv-kul"] = { "Kulango", 16977424, "alv-sav", aliases = {"Kulango-Lorhon", "Kulango-Lorom"}, } m["alv-kwa"] = { "Kwa", 33430, "nic-vco", } m["alv-lag"] = { "Lagoon", 111210042, "alv-kwa", } m["alv-lek"] = { "Leko", 6520642, other_names = {"Sambaic"}, -- appears to be an alias in Glottolog "alv-lni", } m["alv-lim"] = { "Limba", 35825, "alv", } m["alv-lni"] = { "Leko-Nimbari", 1708170, "alv-ada", other_names = {"Central Adamawa"}, aliases = {"Chamba-Mumuye"}, } m["alv-mbd"] = { "Mbum-Day", 6799816, "alv-ada", } m["alv-mbm"] = { "Mbum", 6799814, "alv-mbd", } m["alv-mel"] = { "Mel", 12122355, "alv", } m["alv-mum"] = { "Mumuye", 84607009, "alv-mye", } m["alv-mye"] = { "Mumuye-Yendang", 6935539, "alv-lni", } m["alv-nal"] = { "Nalu", nil, "alv-sng", } m["alv-nce"] = { "North-Central Edoid", 16110869, "alv-edo", } m["alv-ngb"] = { "Nupe-Gbagyi", 12638649, "alv-nup", aliases = {"Nupe-Gbari"}, } m["alv-ntg"] = { "Na-Togo", nil, "alv-gtm", } m["alv-nup"] = { "Nupoid", 1429143, "alv-von", } m["alv-nwd"] = { "Northwestern Edoid", 16111012, "alv-edo", } m["alv-nyn"] = { "Nyun", nil, "alv-fwo", } m["alv-pap"] = { "Papel", 7132562, "alv-bak", } m["alv-pph"] = { "Phla-Pherá", 3849625, "alv-gbe", } m["alv-ptn"] = { "Potou-Tano", 1475003, "alv-kwa", } m["alv-sav"] = { "Savanna", 4403672, "nic-vco", aliases = {"Savannas"}, } m["alv-sma"] = { "Supyire-Mamara", 4446348, "alv-snf", aliases = {"Suppire-Mamara"}, } m["alv-snf"] = { "Senufo", 33795, "alv", aliases = {"Senufic", "Senoufo", "Sénoufo"}, } m["alv-sng"] = { "Senegambian", 1708753, "alv", } m["alv-snr"] = { "Senari", 4416084, "alv-snf", } m["alv-swd"] = { "Southwestern Edoid", 12633903, "alv-edo", } m["alv-tal"] = { "Talodi", 12643302, "alv-the", } m["alv-tdj"] = { "Tagwana-Djimini", 7675362, "alv-snf", } m["alv-ten"] = { "Tenda", 3217535, "alv-fwo", } m["alv-the"] = { "Talodi-Heiban", 1521145, "alv", } m["alv-von"] = { "Volta-Niger", 34177, "nic-vco", } m["alv-wan"] = { "Wara-Natyoro", 7968830, "alv-sav", } m["alv-wjk"] = { "Waja-Kam", nil, "alv-ada", } m["alv-yek"] = { "Yekhee", nil, "alv-nce", } m["alv-yor"] = { "Yoruba", nil, "alv-edk", } m["alv-yrd"] = { "Yoruboid", 1789745, "alv-von", } m["alv-yun"] = { "Yungur", 84601642, "alv-bam", aliases = {"Bena-Mboi"}, } m["apa"] = { "Apachean", 27758, "ath", aliases = {"Southern Athabaskan"}, } m["aqa"] = { "Alacalufan", 1288430, } m["aql"] = { "Algic", 721612, aliases = {"Algonquian-Ritwan", "Algonquian-Wiyot-Yurok"}, } m["art"] = { "constructed", 33215, "qfa-not", aliases = {"artificial", "planned"}, } m["ath"] = { "Athabaskan", 27475, "xnd", } m["ath-nor"] = { "North Athabaskan", 20738, "ath", aliases = {"Northern Athabaskan"}, } m["ath-pco"] = { "Pacific Coast Athabaskan", 20654, "ath", } m["auf"] = { "Arauan", 626772, aliases = {"Arahuan", "Arauán", "Arawa", "Arawan", "Arawán"}, } --[=[ Exceptional language and family codes for Australian Aboriginal languages can use the prefix "aus-", though "aus" is no longer itself a family code. ]=]-- m["aus-arn"] = { "Arnhem", 2581700, aliases = {"Gunwinyguan", "Macro-Gunwinyguan"}, } m["aus-bub"] = { "Bunuban", 2495148, aliases = {"Bunaban"}, } m["aus-cww"] = { "Central New South Wales", 5061507, "aus-pam", } m["aus-dal"] = { "Daly", 2478079, } m["aus-dyb"] = { "Dyirbalic", 1850666, "aus-pam", } m["aus-gar"] = { "Garawan", 5521951, } m["aus-gun"] = { "Gunwinyguan", 2581700, "aus-arn", aliases = {"Gunwingguan"}, } m["aus-jar"] = { "Jarrakan", 2039423, } m["aus-kar"] = { "Karnic", 4215578, "aus-pam", } m["aus-mir"] = { "Mirndi", 4294095, } m["aus-nga"] = { "Ngayarda", 16153490, "aus-psw", } m["aus-nyu"] = { "Nyulnyulan", 2039408, } m["aus-pam"] = { "Pama-Nyungan", 33942, } m["aus-pmn"] = { "Paman", 2640654, "aus-pam", } m["aus-psw"] = { "Southwest Pama-Nyungan", 2258160, "aus-pam", } m["aus-rnd"] = { "Arandic", 4784071, "aus-pam", } m["aus-tnk"] = { "Tangkic", 1823065, } m["aus-wdj"] = { "Iwaidjan", 4196968, aliases = {"Yiwaidjan"}, } m["aus-wor"] = { "Worrorran", 2038619, } m["aus-yid"] = { "Yidinyic", 4205849, "aus-pam", } m["aus-yng"] = { "Yangmanic", 42727644, } m["aus-yol"] = { "Yolngu", 2511254, "aus-pam", aliases = {"Yolŋu", "Yolngu Matha"}, } m["aus-yuk"] = { "Yuin-Kuric", 3833021, "aus-pam", } m["awd"] = { "Arawak", 626753, aliases = {"Arawakan", "Maipurean", "Maipuran"}, } m["awd-nwk"] = { "Nawiki", nil, "awd", aliases = {"Newiki"}, } m["awd-taa"] = { "Ta-Arawak", 7672731, "awd", aliases = {"Ta-Arawakan", "Ta-Maipurean"}, } m["azc"] = { "Uto-Aztecan", 34073, aliases = {"Uto-Aztekan"}, } m["azc-cup"] = { "Cupan", 19866871, "azc-tak", } m["azc-dur"] = { "Durango Nahuatl", 2386361, "azc-nah", aliases = {"Mexicanero"} } m["azc-hua"] = { "Huasteca Nahuatl", 3832950, "azc-nah", } m["azc-nah"] = { "Nahuan", 11965602, "azc", aliases = {"Aztecan"}, } m["azc-num"] = { "Numic", 2657541, "azc", } m["azc-pim"] = { "Piman", 7194600, "azc", aliases = {"Tepiman"}, } m["azc-tak"] = { "Takic", 1280305, "azc", } m["azc-trc"] = { "Taracahitic", 4245032, "azc", aliases = {"Taracahitan"}, } m["bad"] = { "Banda", 806234, "nic-ubg", } m["bad-cnt"] = { "Central Banda", 3438391, "bad", } m["bai"] = { "Bamileke", 806005, "nic-gre", } m["bat"] = { "Baltic", 33136, "ine-bsl", } m["bat-eas"] = { "East Baltic", 149944, "bat", } m["bat-wes"] = { "West Baltic", 149946, "bat", } m["ber"] = { "Berber", 25448, "afa", aliases = {"Tamazight"}, } m["bnt"] = { "Bantu", 33146, "nic-bds", } m["bnt-baf"] = { "Bafia", 799784, "bnt", } m["bnt-bbo"] = { "Bafo-Bonkeng", nil, "bnt-saw", } m["bnt-bdz"] = { "Boma-Dzing", 1729203, "bnt", } m["bnt-bek"] = { "Bekwilic", nil, "bnt-ndb", } m["bnt-bki"] = { "Bena-Kinga", 16113307, "bnt-bne", } m["bnt-bmo"] = { "Bangi-Moi", nil, "bnt-bnm", } m["bnt-bne"] = { "Northeast Bantu", 7057832, "bnt", } m["bnt-bnm"] = { "Bangi-Ntomba", 806477, "bnt-bte", } m["bnt-boa"] = { "Boan", 4931250, "bnt", aliases = {"Buan", "Ababuan"}, } m["bnt-bot"] = { "Botatwe", 4948532, "bnt", } m["bnt-bsa"] = { "Basaa", 809739, "bnt", } m["bnt-bsh"] = { "Bushoong", 5001551, "bnt-bte", } m["bnt-bso"] = { "Southern Bantu", 980498, "bnt", } m["bnt-bta"] = { "Bati-Angba", 4869303, "bnt-boa", other_names = {"Late Bomokandian"}, aliases = {"Bwa"}, } m["bnt-btb"] = { "Beti", 35118, "bnt", } m["bnt-bte"] = { "Bangi-Tetela", 4855181, "bnt", } m["bnt-bun"] = { "Buja-Ngombe", 4986733, "bnt-mbb", } m["bnt-chg"] = { "Chaga", 33016, "bnt-cht", } m["bnt-cht"] = { "Chaga-Taita", nil, "bnt-bne", } m["bnt-clu"] = { "Chokwe-Luchazi", 3339273, "bnt", } m["bnt-com"] = { "Comorian", 33077, "bnt-sab", } m["bnt-glb"] = { "Great Lakes Bantu", 5599420, "bnt-bne", } m["bnt-haj"] = { "Haya-Jita", 25502360, "bnt-glb", } m["bnt-kak"] = { "Kako", nil, "bnt-pob", } m["bnt-kav"] = { "Kavango", 116544179, "bnt-ksb", } m["bnt-kbi"] = { "Komo-Bira", 6428591, "bnt-boa", } m["bnt-kel"] = { "Kele", 1738162, "bnt-kts", aliases = {"Sheke"}, } m["bnt-kil"] = { "Kilombero", 6408121, "bnt", } m["bnt-kka"] = { "Kikuyu-Kamba", 16114410, "bnt-bne", aliases = {"Thagiicu"}, } m["bnt-kmb"] = { "Kimbundu", 16947687, "bnt", } m["bnt-kng"] = { "Kongo", 6429214, "bnt", } m["bnt-kpw"] = { "Kpwe", 36428, "bnt-saw", } m["bnt-ksb"] = { "Kavango-Southwest Bantu", 6379098, "bnt", } m["bnt-kts"] = { "Kele-Tsogo", 6385577, "bnt", } m["bnt-lbn"] = { "Luban", 4536504, "bnt", } m["bnt-leb"] = { "Lebonya", 6511395, "bnt", } m["bnt-lgb"] = { "Lega-Binja", 6517694, "bnt", } m["bnt-lok"] = { "Logooli-Kuria", nil, "bnt-glb", } m["bnt-lub"] = { "Luba", nil, "bnt-lbn", } m["bnt-lun"] = { "Lunda", 6704091, "bnt", } m["bnt-mak"] = { "Makua", 6740431, "bnt-bso", aliases = {"Makhuwa"}, } m["bnt-mbb"] = { "Mboshi-Buja", 6799764, "bnt", } m["bnt-mbe"] = { "Mbole-Enya", 6799728, "bnt", } m["bnt-mbi"] = { "Mbinga", nil, "bnt-rur", } m["bnt-mbo"] = { "Mboshi", 6799763, "bnt-mbb", } m["bnt-mbt"] = { "Mbete", 1346910, "bnt-tmb", aliases = {"Mbere"}, } m["bnt-mby"] = { "Mbeya", nil, "bnt-ruk", } m["bnt-mij"] = { "Mijikenda", 6845474, "bnt-sab", } m["bnt-mka"] = { "Makaa", nil, "bnt-ndb", } m["bnt-mne"] = { "Manenguba", 31147471, "bnt", aliases = {"Mbo", "Ngoe"}, } m["bnt-mnj"] = { "Makaa-Njem", 1603899, "bnt-pob", } m["bnt-mon"] = { "Mongo", nil, "bnt-bnm", } m["bnt-mra"] = { "Mbugwe-Rangi", 6799795, "bnt", } m["bnt-msl"] = { "Masaba-Luhya", 12636428, "bnt-glb", } m["bnt-mwi"] = { "Mwika", nil, "bnt-ruk", } m["bnt-ncb"] = { "Northeast Coast Bantu", 7057848, "bnt-bne", } m["bnt-ndb"] = { "Ndzem-Bomwali", nil, "bnt-mnj", } m["bnt-ngn"] = { "Ngondi-Ngiri", 7022532, "bnt-mbb", } m["bnt-ngu"] = { "Nguni", 961559, "bnt-bso", aliases = {"Ngoni"}, } m["bnt-nya"] = { "Nyali", 7070832, "bnt-leb", } m["bnt-nyb"] = { "Nyanga-Buyi", 7070882, "bnt", } m["bnt-nyg"] = { "Nyoro-Ganda", 12638666, "bnt-glb", } m["bnt-nys"] = { "Nyasa", 7070921, "bnt", } m["bnt-nze"] = { "Nzebi", 1755498, "bnt-tmb", aliases = {"Njebi"}, } m["bnt-ova"] = { "Ovambo", 36489, "bnt-swb", aliases = {"Oshivambo", "Oshiwambo", "Owambo"}, } m["bnt-par"] = { "Pare", nil, "bnt-ncb", } m["bnt-pen"] = { "Pende", 7162373, "bnt", } m["bnt-pob"] = { "Pomo-Bomwali", nil, "bnt", } m["bnt-ruk"] = { "Rukwa", 7378902, "bnt", } m["bnt-run"] = { "Rungwe", nil, "bnt-ruk", } m["bnt-rur"] = { "Rufiji-Ruvuma", 7377947, "bnt", } m["bnt-ruv"] = { "Ruvu", nil, "bnt-ncb", } m["bnt-rvm"] = { "Ruvuma", nil, "bnt-rur", } m["bnt-sab"] = { "Sabaki", 2209395, "bnt-ncb", } m["bnt-saw"] = { "Sawabantu", 532003, "bnt", } m["bnt-sbi"] = { "Sabi", 7396071, "bnt", } m["bnt-seu"] = { "Seuta", nil, "bnt-ncb", } m["bnt-shh"] = { "Shi-Havu", nil, "bnt-glb", } m["bnt-sho"] = { "Shona", 2904660, "bnt", } m["bnt-sir"] = { "Sira", 1436372, "bnt", aliases = {"Shira-Punu"}, } m["bnt-ske"] = { "Soko-Kele", nil, "bnt-bte", } m["bnt-sna"] = { "Sena", nil, "bnt-nys", } m["bnt-sts"] = { "Sotho-Tswana", 2038386, "bnt-bso", } m["bnt-swb"] = { "Southwest Bantu", 116543539, "bnt-ksb", } m["bnt-swh"] = { "Swahili", nil, "bnt-sab", } m["bnt-tek"] = { "Teke", 36528, "bnt-tmb", } m["bnt-tet"] = { "Tetela", 7706059, "bnt-bte", } m["bnt-tkc"] = { "Central Teke", 36473, "bnt-tek", } m["bnt-tkm"] = { "Takama", nil, "bnt-bne", } m["bnt-tmb"] = { "Teke-Mbede", 7695332, "bnt", aliases = {"Teke-Mbere"}, } m["bnt-tso"] = { "Tsogo", 2458420, other_names = {"Okani"}, --appears to be an alias in Glottolog "bnt-kts", } m["bnt-tsr"] = { "Tswa-Ronga", 12643962, "bnt-bso", } m["bnt-yak"] = { "Yaka", 8047027, "bnt", } m["bnt-yko"] = { "Yasa-Kombe", nil, "bnt-saw", } m["bnt-zbi"] = { "Zamba-Binza", nil, "bnt-bnm", } m["btk"] = { "Batak", 1998595, "poz-nws", } --[=[ Exceptional language and family codes for Central American Indian languages may use the prefix "cai-", though "cai" is no longer itself a family code. ]=]-- --[=[ Exceptional language and family codes for Caucasian languages can use the prefix "cau-", though "cau" is no longer itself a family code. ]=]-- m["cau-abz"] = { "Abkhaz-Abaza", 4663617, "cau-nwc", other_names = {"Abkhaz-Tapanta"}, aliases = {"Abazgi"}, } m["cau-and"] = { "Andian", 492152, "cau-ava", aliases = {"Andic"}, } m["cau-ava"] = { "Avaro-Andian", 4055404, "cau-nec", aliases = {"Avar-Andian", "Avar-Andi", "Avar-Andic"}, } m["cau-cir"] = { "Circassian", 858543, "cau-nwc", aliases = {"Cherkess"}, } m["cau-drg"] = { "Dargwa", 5222637, "cau-nec", other_names = {"Dargin"}, } m["cau-esm"] = { "Eastern Samur", nil, "cau-sam", } m["cau-ets"] = { "East Tsezian", 121437666, "cau-tsz", aliases = {"East Tsezic", "East Didoic"}, } m["cau-lzg"] = { "Lezghian", 2144370, "cau-nec", aliases = {"Lezgi", "Lezgian", "Lezgic"}, } m["cau-nkh"] = { "Nakh", 24441, "cau-nec", aliases = {"North-Central Caucasian"}, } m["cau-nec"] = { "Northeast Caucasian", 27387, aliases = {"Dagestanian", "Nakho-Dagestanian", "Caspian"}, } m["cau-nwc"] = { "Northwest Caucasian", 33852, aliases = {"Abkhazo-Adyghean", "Abkhaz-Adyghe", "Pontic"}, } m["cau-sam"] = { "Samur", 15229151, "cau-lzg", } m["cau-ssm"] = { "Southern Samur", nil, "cau-sam", } m["cau-tsz"] = { "Tsezian", 1651530, "cau-nec", aliases = {"Tsezic", "Didoic"}, } m["cau-vay"] = { "Vainakh", 4102486, "cau-nkh", aliases = {"Veinakh", "Vaynakh"}, } m["cau-wsm"] = { "Western Samur", nil, "cau-sam", } m["cau-wts"] = { "West Tsezian", 121437697, "cau-tsz", aliases = {"West Tsezic", "West Didoic"}, } m["cba"] = { "Chibchan", 520478, "qfa-mch", -- or none if Macro-Chibchan is considered undemonstrated } m["ccs"] = { "Kartvelian", 34030, aliases = {"South Caucasian"}, } m["ccs-gzn"] = { "Georgian-Zan", 34030, "ccs", aliases = {"Karto-Zan"}, } m["ccs-zan"] = { "Zan", 2606912, "ccs-gzn", aliases = {"Zanuri", "Colchian"}, } m["cdc"] = { "Chadic", 33184, "afa", } m["cdc-cbm"] = { "Central Chadic", 2251547, "cdc", aliases = {"Biu-Mandara"}, } m["cdc-est"] = { "East Chadic", 2276221, "cdc", } m["cdc-mas"] = { "Masa", 2136092, "cdc", } m["cdc-wst"] = { "West Chadic", 2447774, "cdc", } m["cdd"] = { "Caddoan", 1025090, } m["cel"] = { "Celtic", 25293, "ine", } m["cel-bry"] = { "Brythonic", 156877, "cel-ins", aliases = {"Brittonic"}, } m["cel-brs"] = { "Southwestern Brythonic", 2612853, "cel-bry", aliases = {"Southwestern Brittonic"}, } m["cel-brw"] = { "Western Brythonic", 593069, "cel-bry", aliases = {"Western Brittonic"}, } m["cel-gae"] = { "Goidelic", 56433, "cel-ins", aliases = {"Gaelic"}, protoLanguage = "pgl", } m["cel-his"] = { "Hispano-Celtic", 4204136, "cel", } m["cel-ins"] = { "Insular Celtic", 214506, "cel", } m["chi"] = { "Chimakuan", 1073088, } m["chm"] = { "Mari", 973685, "urj", } m["cmc"] = { "Chamic", 2997506, "poz-mcm", } m["crp"] = { "creole or pidgin", 19682167, "qfa-cnt", } m["csu"] = { "Central Sudanic", 190822, "ssa", } m["csu-bba"] = { "Bongo-Bagirmi", 3505042, "csu", } m["csu-bbk"] = { "Bongo-Baka", 4941917, "csu-bba", } m["csu-bgr"] = { "Bagirmi", 4841948, "csu-bba", aliases = {"Bagirmic"}, } m["csu-bkr"] = { "Birri-Kresh", nil, "csu", } m["csu-ecs"] = { "Eastern Central Sudanic", 16911698, "csu", aliases = {"East Central Sudanic", "Central Sudanic East", "Lendu-Mangbetu"}, } m["csu-kab"] = { "Kaba", 6343715, "csu-bba", } m["csu-lnd"] = { "Lendu", 6522357, "csu-ecs", aliases = {"Lenduic"}, } m["csu-maa"] = { "Mangbetu", 6748874, "csu-ecs", aliases = {"Mangbetu-Asoa", "Mangbetu-Asua"}, } m["csu-mle"] = { "Mangbutu-Lese", 17009406, "csu-ecs", aliases = {"Mangbutu-Efe", "Mangbutu", "Membi-Mangbutu-Efe"}, } m["csu-mma"] = { "Moru-Madi", 6915156, "csu-ecs", } m["csu-sar"] = { "Sara", 2036691, "csu-bba", } m["csu-val"] = { "Vale", 7909520, "csu-bba", } m["cus"] = { "Cushitic", 33248, "afa", } m["cus-cen"] = { "Central Cushitic", 56569, "cus", } m["cus-eas"] = { "East Cushitic", 56568, "cus", } m["cus-hec"] = { "Highland East Cushitic", 56524, "cus-eas", } m["cus-som"] = { "Somaloid", 56774, "cus-eas", aliases = {"Sam", "Macro-Somali"}, } m["cus-sou"] = { "South Cushitic", 56525, "cus", } m["day"] = { "Land Dayak", 2760613, "poz", } m["del"] = { "Lenape", 2665761, "alg-eas", aliases = {"Delaware"}, } m["den"] = { "Slavey", 13272, "ath-nor", aliases = {"Slave", "Slavé"}, } m["dmn"] = { "Mande", 33681, "nic", } m["dmn-bbu"] = { "Bisa-Busa", 12627956, "dmn-mde", } m["dmn-emn"] = { "East Manding", nil, "dmn-man", } m["dmn-jje"] = { "Jogo-Jeri", nil, "dmn-mjo", } m["dmn-man"] = { "Manding", 35772, "dmn-mmo", } m["dmn-mda"] = { "Mano-Dan", nil, "dmn-mse", } m["dmn-mdc"] = { "Central Mande", 5972907, "dmn-mdw", } m["dmn-mde"] = { "Eastern Mande", 12633080, "dmn", } m["dmn-mdw"] = { "Western Mande", 16113831, "dmn", } m["dmn-mjo"] = { "Manding-Jogo", 12636153, "dmn-mdc", } m["dmn-mmo"] = { "Manding-Mokole", nil, "dmn-mva", } m["dmn-mnk"] = { "Maninka", 36186, "dmn-emn", } m["dmn-mnw"] = { "Northwestern Mande", 5972910, "dmn-mdw", } m["dmn-mok"] = { "Mokole", 16935447, "dmn-mmo", } m["dmn-mse"] = { "Southeastern Mande", 5972912, "dmn-mde", } m["dmn-msw"] = { "Southwestern Mande", 12633904, "dmn-mdw", } m["dmn-mva"] = { "Manding-Vai", nil, "dmn-mjo", } m["dmn-nbe"] = { "Nwa-Beng", nil, "dmn-mse", } m["dmn-sam"] = { "Samo", 36327, "dmn-bbu", aliases = {"Samuic"}, } m["dmn-smg"] = { "Samogo", 7410000, "dmn-mnw", aliases = {"Duun-Seenku"}, } m["dmn-snb"] = { "Soninke-Bobo", 16111680, "dmn-mnw", } m["dmn-sya"] = { "Susu-Yalunka", nil, "dmn-mdc", } m["dmn-vak"] = { "Vai-Kono", nil, "dmn-mva", } m["dmn-wmn"] = { "West Manding", nil, "dmn-man", } m["dra"] = { "Dravidian", 33311, } m["dra-cen"] = { "Central Dravidian", 12628823, "dra", } m["dra-gki"] = { "Gondi-Kui", 12631610, "dra-sdt", } m["dra-gon"] = { "Gondi", 55639812, "dra-gki", } m["dra-imd"] = { "Irula-Muduga", nil, "dra-tkn", } m["dra-kan"] = { "Kannadoid", 6363888, "dra-tkn", protoLanguage = "dra-okn", } m["dra-kki"] = { "Konda-Kui", nil, "dra-gki", } m["dra-kml"] = { "Kurux-Malto", 68002822, "dra-nor", } m["dra-knk"] = { "Kolami-Naiki", 10547037, "dra-cen", } m["dra-kod"] = { "Kodagu", 67983106, "dra-tkd", } m["dra-kor"] = { "Koraga", 33394, "dra-tlk", } m["dra-mal"] = { "Malayalamoid", 6741581, "dra-tml", } m["dra-mdy"] = { "Madiya", 27602, "dra-gon", } m["dra-mlo"] = { "Malto", nil, "dra-kml", } m["dra-mur"] = { "Muria", 6938499, "dra-gon", } m["dra-nor"] = { "North Dravidian", 16110967, "dra", } m["dra-pgd"] = { "Parji-Gadaba", 10620428, "dra-cen", } m["dra-sdo"] = { "South Dravidian I", 16112843, -- Wikipedia's "South Dravidian" is South Dravidian I in this scheme. "dra-sou", aliases = {"South Dravidian"}, -- This is why I and II are used. } m["dra-sdt"] = { "South Dravidian II", 12633975, "dra-sou", aliases = {"South-Central Dravidian"}, } m["dra-sou"] = { "South Dravidian", 128886618, "dra", aliases = {"Southern Dravidian"}, } m["dra-tam"] = { "Tamiloid", 7681417, "dra-tml", protoLanguage = "oty", } m["dra-tel"] = { "Teluguic", nil, "dra-sdt", protoLanguage = "dra-ote", } m["dra-tkd"] = { "Tamil-Kodagu", 25494510, "dra-tkn", } m["dra-tkn"] = { "Tamil-Kannada", 6478506, "dra-sdo", } m["dra-tkt"] = { "Toda-Kota", 67983857, "dra-tkd", } m["dra-tlk"] = { "Tulu-Koraga", nil, "dra-sdo", } m["dra-tml"] = { "Tamil-Malayalam", 10690507, "dra-tkd", } m["egx"] = { "Egyptian", 50868, "afa", protoLanguage = "egy", } m["ero"] = { "Horpa", 56854, "sit-wgy", } m["esx"] = { "Eskimo-Aleut", 25946, } m["esx-esk"] = { "Eskimo", 25946, "esx", } m["esx-inu"] = { "Inuit", 27796, "esx-esk", } m["euq"] = { "Vasconic", 4669240, } m["gba"] = { "Gbaya", 3099986, "alv-sav", } m["gba-eas"] = { "Eastern Gbaya", nil, "gba", } m["gba-sou"] = { "Southern Gbaya", nil, "gba", } m["gba-wes"] = { "Western Gbaya", nil, "gba", } m["gem"] = { "ජර්මානු", 21200, "ine", } m["gio"] = { "Gelao", 56401, "qfa-kra", } m["gme"] = { "East Germanic", 108662, "gem", } m["gmq"] = { "North Germanic", 106085, "gem", } m["gmq-eas"] = { "East Scandinavian", 3090263, "gmq", protoLanguage = "non-oen", } m["gmq-ins"] = { "Insular Scandinavian", nil, "gmq-wes", } m["gmq-wes"] = { "West Scandinavian", 1792570, "gmq", protoLanguage = "non-own", } m["gmw"] = { "බටහිර ජර්මානු", 26721, "gem", } m["gmw-afr"] = { "ඇන්ග්ලෝ-ෆ්‍රිසියන්", 5329170, "gmw-nsg", } m["gmw-ang"] = { "ඇන්ග්ලික්", 1346342, "gmw-afr", protoLanguage = "ang", } m["gmw-fri"] = { "Frisian", 25325, "gmw-afr", protoLanguage = "ofs", } m["gmw-frk"] = { "Low Franconian", 153050, "gmw", protoLanguage = "frk", } m["gmw-hgm"] = { "High German", 52040, "gmw", protoLanguage = "goh", } m["gmw-ian"] = { "Irish Anglo-Norman", 120719384, "gmw-ang", protoLanguage = "enm", } m["gmw-lgm"] = { "Low German", 25433, "gmw-nsg", protoLanguage = "osx", } m["gmw-nsg"] = { "North Sea Germanic", 30134, "gmw", aliases = {"Ingvaeonic"}, } m["gn"] = { "Guarani", 35876, "tup-gua", aliases = {"Guaraní"}, } m["grb"] = { "Grebo proper", 35257, "kro-grb", } m["grk"] = { "Hellenic", 2042538, "ine", aliases = {"Greek"}, } m["him"] = { "Western Pahari", 10939493, "inc-pah", aliases = {"Himachali"}, } m["hmn"] = { "Hmongic", 3307894, "hmx", } m["hmx"] = { "Hmong-Mien", 33322, aliases = {"Miao-Yao"}, } m["hmx-mie"] = { "Mienic", 7992695, "hmx", } m["hok"] = { "Hokan", 33406, } m["hyx"] = { "Armenian", 8785, "ine", } m["iir"] = { "ඉන්දු-ඉරාන", 33514, "ine", } m["iir-nur"] = { "Nuristani", 161804, "iir", } m["nur-nor"] = { "Northern Nuristani", nil, "iir-nur", } m["nur-sou"] = { "Southern Nuristani", nil, "iir-nur", } m["ijo"] = { "Ijoid", 1325759, "nic", other_names = {"Ijaw"}, -- Ijaw may be a subfamily } m["inc"] = { "ඉන්දු-ආර්ය", 33577, "iir", aliases = {"Indo-Aryan", "Indic"}, } m["inc-bas"] = { "Bengali-Assamese", 4179137, "inc-eas", aliases = {"Assamese-Bengali", "Gauda-Kamarupa"}, } m["inc-bhi"] = { "Bhil", 4901727, "inc-cen", } m["inc-bih"] = { "Bihari", 135305, "inc-eas", } m["inc-cen"] = { "Central Indo-Aryan", 10979187, "inc", protoLanguage = "inc-asa", } m["inc-chi"] = { "Chitrali", 11732797, "inc-dar", } m["inc-dar"] = { "Dardic", 161101, "inc", protoLanguage = "inc-ash", } m["inc-dre"] = { "Eastern Dardic", nil, "inc-dar", } m["inc-dng"] = { "Dangari", nil, "inc-shn", } m["inc-eas"] = { "Eastern Indo-Aryan", 12593391, "inc", protoLanguage = "inc-aav", } m["inc-hal"] = { "Halbic", 16910593, "inc-eas", aliases = {"Halbi"}, } m["inc-hie"] = { "Eastern Hindi", 4126648, "inc-cen", aliases = {"Purabiyā"}, protoLanguage = "inc-apa", } m["inc-hiw"] = { "Western Hindi", 12600937, "inc-cen", protoLanguage = "inc-ohi", } m["inc-hnd"] = { "Hindustani", 11051, "inc-hiw", aliases = {"Hindi-Urdu"}, protoLanguage = "hi-mid", } m["inc-ins"] = { "Insular Indo-Aryan", 12179302, "inc", protoLanguage = "inc-apa", } m["inc-kas"] = { "Kashmiric", nil, "inc-dre", aliases = {"Kashmiri"}, } m["inc-koh"] = { "Kohistani", 13018610, "inc-dre", } m["inc-krd"] = { "KRDS languages", 6356154, "inc-eas", aliases = {"Kamta, Rajbanshi, Deshi and Surjapuri", "KRNB languages", "Kamta, Rajbanshi and Northern Deshi Bangla"}, } m["inc-kun"] = { "Kunar", nil, "inc-dar", } m["inc-mid"] = { "මධ්‍යකාලීන ඉන්දු-ආර්ය", 3236316, "inc", aliases = {"Middle Indic"}, } m["inc-nwe"] = { "Northwestern Indo-Aryan", 16111018, "inc", protoLanguage = "inc-apa", } m["inc-nor"] = { "Northern Indo-Aryan", 946077, "inc", protoLanguage = "inc-aka", } m["inc-old"] = { "Old Indo-Aryan", 118976896, "inc", aliases = {"Old Indic"}, } m["inc-pah"] = { "Pahari", 946077, "inc-nor", aliases = {"Pahadi"}, protoLanguage = "inc-aka", } m["inc-pan"] = { "Punjabic", 2656685, "inc-nwe", aliases = {"Greater Punjabic"}, protoLanguage = "inc-opa", } m["inc-pas"] = { "Pashayi", 36670, "inc-dar", aliases = {"Pashai"}, } m["inc-rom"] = { "Romani", 13201, "inc-wes", aliases = {"Romany", "Gypsy", "Gipsy"}, } m["inc-shn"] = { "Shinaic", 12646125, "inc-dre", } m["inc-snd"] = { "Sindhic", 7522212, "inc-nwe", protoLanguage = "inc-avr", } m["inc-sou"] = { "Southern Indo-Aryan", 10856062, "inc", protoLanguage = "inc-ama", } m["inc-tha"] = { "Tharu", 34035, "inc-eas", } m["inc-wes"] = { "Western Indo-Aryan", nil, "inc", protoLanguage = "inc-agu", } m["ine"] = { "ඉන්දු-යුරෝපීය", 19860, aliases = {"ඉන්දු-ජර්මානු", "Indo-Germanic"}, } m["ine-ana"] = { "Anatolian", 147085, "ine", } m["ine-bsl"] = { "Balto-Slavic", 147356, "ine", } m["ine-toc"] = { "Tocharian", 37029, "ine", aliases = {"Tokharian"}, } m["ira"] = { "Iranian", 33527, "iir", } m["ira-csp"] = { "Caspian", 5049123, "ira-mpr", } m["ira-cen"] = { "Central Iranian", nil, "ira", } m["ira-kms"] = { "Komisenian", nil, "ira-mpr", aliases = {"Semnani"}, } m["ine-luw"] = { "Luwic", 115748615, "ine-ana", aliases = {"Luvic"}, } m["ira-mid"] = { "Middle Iranian", 6841465, "ira", } m["ira-mny"] = { "Munji-Yidgha", nil, "ira-sym", aliases = {"Yidgha-Munji"}, } m["ira-msh"] = { "Mazanderani-Shahmirzadi", nil, "ira-csp", } m["ira-nei"] = { "Northeastern Iranian", 10775567, "ira", } m["ira-nwi"] = { "Northwestern Iranian", 390576, "ira-wes", } m["ira-old"] = { "Old Iranian", 23301845, "ira", } m["ira-orp"] = { "Ormuri-Parachi", nil, "ira-sei", } m["ira-pat"] = { "Pathan", nil, "ira-sei", } m["ira-sbc"] = { "Sogdo-Bactrian", nil, "ira-nei", } m["ira-mpr"] = { "Medo-Parthian", nil, "ira-nwi", aliases = {"Partho-Median"}, } m["ira-sgi"] = { "Sanglechi-Ishkashimi", 18711232, "ira-sei", } m["ira-shr"] = { "Shughni-Roshani", 11732824, "ira-shy", } m["ira-shy"] = { "Shughni-Yazghulami", nil, "ira-sym", } m["ira-sgc"] = { "Sogdic", nil, "ira-sbc", aliases = {"Sogdian"}, } m["ira-sei"] = { "Southeastern Iranian", 3833002, "ira", } m["ira-swi"] = { "Southwestern Iranian", 390424, "ira-wes", } m["ira-sym"] = { "Shughni-Yazghulami-Munji", nil, "ira-sei", } m["ira-wes"] = { "Western Iranian", 129850, "ira", } m["ira-zgr"] = { "Zaza-Gorani", 167854, "ira-mpr", aliases = {"Zaza-Gurani", "Gorani-Zaza"}, } m["iro"] = { "Iroquoian", 33623, } m["iro-nor"] = { "North Iroquoian", nil, "iro", } m["itc"] = { "Italic", 131848, "ine", } m["itc-laf"] = { "Latino-Faliscan", 33478, "itc", aliases = {"Latinian"}, } m["itc-sbl"] = { "Osco-Umbrian", 515194, "itc", aliases = {"Sabellic", "Sabellian"}, } m["jpx"] = { "Japonic", 33612, aliases = {"Japanese", "Japanese-Ryukyuan"}, } m["jpx-nry"] = { "Northern Ryukyuan", 20862796, "jpx-ryu", } m["jpx-ryu"] = { "Ryukyuan", 56393, "jpx", } m["jpx-sry"] = { "Southern Ryukyuan", 18392243, "jpx-ryu", } m["kar"] = { "Karen", 1364815, "sit", } m["kca"] = { "Khanty", 33563, "urj-ugr", aliases = {"Khantyic", "Khantic"}, } --[=[ Exceptional language and family codes for Khoisan and Kordofanian languages can use the prefix "khi-" and "kdo-" respectively, though they are no longer family codes themselves. ]=]-- m["khi-kal"] = { "Kalahari Khoe", nil, "khi-kho", } m["khi-khk"] = { "Khoekhoe", nil, "khi-kho", } m["khi-kkw"] = { "Khoe-Kwadi", 60785084, aliases = {"Kwadi-Khoe"}, } m["khi-kho"] = { "Khoe", 2736449, "khi-kkw", aliases = {"Central Khoisan"}, } m["khi-kxa"] = { "Kx'a", 6450587, aliases = {"Kxa", "Ju-ǂHoan"}, } m["khi-tuu"] = { "Tuu", 631046, aliases = {"Kwi", "Taa-Kwi", "Southern Khoisan", "Taa-ǃKwi", "Taa-ǃUi", "ǃUi-Taa"}, } m["kro"] = { "Kru", 33535, "nic-vco", } m["kro-aiz"] = { "Aizi", 4699431, "kro", } m["kro-bet"] = { "Bété", 32956, "kro-ekr", } m["kro-did"] = { "Dida", 32685, "kro-ekr", } m["kro-ekr"] = { "Eastern Kru", 5972899, "kro", } m["kro-grb"] = { "Grebo", 5601537, "kro-wkr", } m["kro-wee"] = { "Wee", nil, "kro-wkr", } m["kro-wkr"] = { "Western Kru", 5972897, "kro", } m["ku"] = { "Kurdish", 36368, "ira-nwi", } m["kv"] = { "Komi", 36126, -- "Komi language" in Wikipedia but refers specifically to Komi-Zyrian; no Wikidata item for Komi family "urj-prm", } m["map"] = { "Austronesian", 49228, } m["map-ata"] = { "Atayalic", 716610, "map", } m["mjg"] = { "Monguor", 34214, "xgn-shr", } m["mkh"] = { "Mon-Khmer", 33199, "aav", } m["mkh-asl"] = { "Aslian", 3111082, "mkh", } m["mkh-ban"] = { "Bahnaric", 56309, "mkh", } m["mkh-kat"] = { "Katuic", 56697, "mkh", } m["mkh-khm"] = { "Khmuic", 1323245, "mkh", } m["mkh-kmr"] = { "Khmeric", nil, "mkh", } m["mkh-mnc"] = { "Monic", 3217497, "mkh", } m["mkh-mng"] = { "Mangic", 3509556, "mkh", } m["mkh-nbn"] = { "North Bahnaric", 56309, "mkh-ban", } m["mkh-pal"] = { "Palaungic", 2391173, "mkh", } m["mkh-pea"] = { "Pearic", 3073022, "mkh", } m["mkh-pkn"] = { "Pakanic", nil, "mkh-mng", } m["mkh-vie"] = { "Vietic", 2355546, "mkh", } m["mno"] = { "Manobo", 3217483, "phi", } m["mns"] = { "Mansi", 33759, "urj-ugr", aliases = {"Mansic"}, } m["mun"] = { "Munda", 33892, "aav", } m["myn"] = { "Mayan", 33738, } --[=[ Exceptional language and family codes for North American Indian languages can use the prefix "nai-", though "nai" is no longer itself a family code. ]=]-- m["nai-cat"] = { "Catawban", 3446638, "nai-sca", } m["nai-chu"] = { "Chumashan", 1288420, } m["nai-ckn"] = { "Chinookan", 610586, } m["nai-coo"] = { "Coosan", 940278, } m["nai-jcq"] = { "Jicaquean", 12179308, "hok" } m["nai-ker"] = { "Keresan", 35878, } m["nai-klp"] = { "Kalapuyan", 1569040, } m["nai-kta"] = { "Kiowa-Tanoan", 386288, } m["nai-len"] = { "Lencan", 36189, aliases = {"Lenca"}, } m["nai-mdu"] = { "Maiduan", 33502, } m["nai-miz"] = { "Mixe-Zoquean", 954016, aliases = {"Mixe-Zoque"}, } m["nai-min"] = { "Misumalpan", 281693, "qfa-mch", aliases = {"Misuluan", "Misumalpa"}, } m["nai-mus"] = { "Muskogean", 902978, aliases = {"Muskhogean"}, } m["nai-pak"] = { "Pakawan", 65085487, "hok", } m["nai-pal"] = { "Palaihnihan", 1288332, } m["nai-plp"] = { "Plateau Penutian", 2307476, } m["nai-pom"] = { "Pomoan", 2618420, "hok", aliases = {"Pomo", "Kulanapan"}, } m["nai-sca"] = { "Siouan-Catawban", 34181, } m["nai-shp"] = { "Sahaptian", 114782, "nai-plp", } m["nai-shs"] = { "Shastan", 2991735, "hok", } m["nai-tot"] = { "Totozoquean", 7828419, } m["nai-ttn"] = { "Totonacan", 34039, aliases = {"Totonac-Tepehua", "Totonacan-Tepehuan"}, varieties = {"Totonac"}, } m["nai-tqn"] = { "Tequistlatecan", 1568317, "hok", aliases = {"Tequistlatec", "Chontal", "Chontalan", "Oaxacan Chontal", "Chontal of Oaxaca"}, } m["nai-tsi"] = { "Tsimshianic", 34134, } m["nai-utn"] = { "Utian", 13371763, "nai-you", aliases = {"Miwok-Costanoan", "Mutsun"}, } m["nai-wtq"] = { "Wintuan", 1294259, aliases = {"Wintun"}, } m["nai-xin"] = { "Xincan", 1546494, aliases = {"Xinca"}, } m["nai-ykn"] = { "Yukian", 2406722, aliases = {"Yuki-Wappo"}, } m["nai-you"] = { "Yok-Utian", 2886186, } m["nai-yuc"] = { "Yuman-Cochimí", 579137, } m["ngf"] = { "Trans-New Guinea", 34018, } m["ngf-ais"] = { "Aisian", nil, "ngf-eso", } m["ngf-ang"] = { "Angan", 3217366, "ngf", aliases = {"Kratke Range"}, -- Usher } m["ngf-ank"] = { "Angal-Kewa", 12626916, -- exist in dewiki and hrwiki "ngf-sak", } m["ngf-ask"] = { "Asmat-Kamoro", 3031400, "ngf", -- Wikipedia uses Asmat-Kamoro to refer to a narrower group excluding the Sabakor languages (Buruwai and Kamberau, -- which Glottolog splits into North Kamrau and South Kamrau [sic]), and uses Asmat-Kamrau to refer to what we and -- Glottolog call Asmat-Kamoro. Glottolog does not recognize the narrower grouping. aliases = {"Asmat-Kamrau", -- Wikipedia "Asmat-Kamrau Bay", -- Usher }, } m["ngf-asm"] = { "Asmat", 4807421, "ngf-ask", } m["ngf-ata"] = { "Ankave-Tainae-Akoye", nil, "ngf-ang", aliases = {"Southwest Kratke Range"}, -- Usher } m["ngf-awd"] = { "Awyu-Dumut", -- [[w:Awyu-Dumut languages]] redirects to [[w:Greater Awyu languages]] 4830163, -- exist in eswiki, hrwiki and ruwiki "ngf-gaw", aliases = {"Central Digul River"}, -- Usher } m["ngf-awy"] = { "Awyu", 96372866, "ngf-awd", } m["ngf-bda"] = { "Becking-Dawi", nil, -- Q55993716 ([[Category:Becking–Dawi languages]]) exists in enwiki "ngf-gaw", aliases = {"Becking and Dawi Rivers"}, -- Usher } m["ngf-bin"] = { "Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf-gbi", aliases = {"Oro"}, -- Usher (2020) } m["ngf-boa"] = { "Boane", nil, "ngf-era", aliases = {"Boana", -- Glottolog's name "Wain"}, -- not in Usher; "Wain" often excludes Mungkip, perhaps because it's poorly documented } m["ngf-bos"] = { "Bosavi", 4947122, "ngf", aliases = {"Papuan Plateau"}, -- alternative name given by Wikipedia } m["ngf-bsi"] = { "Baruya-Simbari", nil, "ngf-ang", aliases = {"Northwest Kratke Range"}, -- Usher } m["ngf-cda"] = { "Central Dani", nil, "ngf-dan", aliases = {"Dani"}, -- Usher } m["ngf-chw"] = { "Chimbu-Wahgi", 3217383, "ngf", aliases = {"Simbu-Western Highlands"}, -- alternative name given by Wikipedia } m["ngf-dag"] = { "Dagan", 5208454, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Meneao Range"}, } m["ngf-dal"] = { "Dallman", nil, "ngf-huo", aliases = {"Kinalakna-Kumukio", -- Pawley-Hammarström, who exclude Nomu, but they only had a numeral list of that language to work from "Northeast Huon", -- Usher }, } m["ngf-dan"] = { "Dani", 3217389, "ngf", -- Wikipedia renames the Dani languages to the Baliem Valley languages and sometimes (but not consistently) -- reserves the name Dani (or "Dani proper") for a narrower group excluding Wano and the poorly attested Ngalik -- languages (Nduga, Silimo, and the Yali dialect cluster, which we, following Ethnologue and Glottolog, split into -- Anggurk Yali, Ninia Yali and Pass Valley Yali). Glottolog does not recognize the narrower grouping. aliases = {"Baliem Valley", -- Wikipedia "Balim Valley", -- Usher }, } m["ngf-dum"] = { "Dumut", -- [[w:Dumut languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Wambon"}, -- Usher } m["ngf-ehu"] = { "Eastern Huon", -- Glottolog adds Ono and Sialum, Pawley-Hammarström adds Dedua 10567087, "ngf-huo", aliases = {"East Huon"}, -- Usher } m["ngf-eku"] = { "East Kutubuan", 5328752, "ngf", -- Not in TNG per Glottolog but accepted by all others. Sometimes grouped with Fasu to form a Kutubuan family. aliases = {"East Kutubu"}, -- Glottolog's name } m["ngf-enc"] = { "Engic", nil, "ngf-eng", aliases = {"Engan", -- Glottolog "Engan proper", -- Wikipedia "North Engan", -- alternative name given by Wikipedia "Trans-Enga", -- Usher }, } m["ngf-eng"] = { "Engan", 3217449, "ngf", aliases = {"Enga-Kewa-Huli", -- Glottolog, Pawley-Hammarström "Enga-Southern Highlands", -- Usher }, } m["ngf-era"] = { "Erap", nil, "ngf-fin", aliases = {"Erap River"}, -- Usher? } m["ngf-eso"] = { "East Sogeram", nil, "ngf-sog", } m["ngf-est"] = { "East Strickland", 5329440, "ngf", aliases = {"Strickland River"}, -- alternative name given by Wikipedia } m["ngf-eva"] = { "Evapia", nil, "ngf-rai", aliases = {"Evapia River"}, -- Usher } m["ngf-fgi"] = { "Fore-Gimi", nil, "ngf-gor", aliases = {"South Goroka"}, -- Usher } m["ngf-fhu"] = { "Finisterre-Huon", 3217453, "ngf", aliases = {"Finisterre Range-Huon Peninsula"}, -- per Usher } m["ngf-fin"] = { "Finisterre", 5450373, "ngf-fhu", aliases = {"Finisterre-Saruwaged", -- Glottolog's name "Finisterre Range"}, -- per Usher } m["ngf-gah"] = { "Gahuku", nil, "ngf-gor", aliases = {"Alekano-Asaro River"}, -- Usher } m["ngf-gau"] = { "Gauwa", nil, "ngf-kai", aliases = {"West Kainantu"}, -- Usher } m["ngf-gaw"] = { "Greater Awyu", 12627424, "ngf", aliases = {"Digul River"}, -- used by Usher (2020) } m["ngf-gbi"] = { "Greater Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf", -- not placed in Trans-New Guinea in Usher (2020) aliases = {"Guhu-Oro"}, -- Guhu-Oro is used in Usher (2020) } m["ngf-gko"] = { "Gaena-Korafe", 11732347, -- considered a single Korafe language by Wikipedia "ngf-bin", aliases = {"Gaina-Korafe"}, -- Usher } m["ngf-gmo"] = { "Gusap-Mot", 16110857, "ngf-fin", aliases = {"Mot River"}, -- Usher? } m["ngf-gor"] = { "Goroka", 15478597, "ngf-kgo", } m["ngf-gsu"] = { "Gogodala-Suki", 5577428, "ngf", -- Possibly in the proposed Papuan Gulf family. Not in TNG per Glottolog but accepted by all others. aliases = {"Suki-Gogodala", -- Glottolog's name "Suki-Aramia River", -- Used in Usher (2020) }, } m["ngf-gum"] = { "Gum", 5618008, "ngf-mab", } m["ngf-gvd"] = { "Grand Valley Dani", -- considered a single language by Wikipedia 5595219, "ngf-cda", } m["ngf-hag"] = { "Hagen", -- [[w:Hagen languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Melpa-Kaugel River"}, -- Usher } m["ngf-han"] = { "Hanseman", 5651020, "ngf-mab", aliases = {"Hansemann Range"}, -- Usher } m["ngf-huo"] = { "Huon", 5946109, "ngf-fhu", aliases = {"Huon Peninsula"}, -- per Usher } m["ngf-jim"] = { "Jimi", -- [[w:Jimi languages]] and [[w:Jimi River languages]] redirect to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Jimi River"}, -- Usher } m["ngf-kab"] = { "Kabwum", nil, "ngf-huo", aliases = {"Timbe-Selepet-Komba", -- Pawley-Hammarström, "Northwest Huon", -- Usher }, } m["ngf-kai"] = { "Kainantu", -- Kambaira: under "unclassified Kainantu" (Glottolog), Tairora (Pawley-Hammarström), Gauwa (Usher) 15478590, "ngf-kgo", aliases = {"Gadsup-Auyana-Awa-Tairora"}, -- Wurm, } m["ngf-kak"] = { "Kalam-Kobon", 6350303, "ngf-ksa", aliases = {"Kalam", "Kaironk River"}, -- Usher (2020) } m["ngf-kau"] = { "Kaukombar", nil, "ngf-nad", aliases = {"Kaukombaran", -- Glottolog following Z'graggen (1975) "Kaukombar River"}, -- Usher's term } m["ngf-kbm"] = { "Kosorong-Burum-Mindik", nil, "ngf-huo", aliases = {"Bulum River"}, -- Usher } m["ngf-kgo"] = { "Kainantu-Goroka", 3217463, "ngf", aliases = {"Eastern Highlands"}, -- per Usher (2020) } m["ngf-khu"] = { "Kewa-Huli", nil, "ngf-eng", aliases = {"Huli-Southern Highlands"}, -- Usher } m["ngf-kma"] = { "Kâte-Mape", nil, "ngf-ehu", aliases = {"Kate-Mape-Sene", -- Pawley-Hammarström (with Sene), "Southeast Huon", -- Usher }, } m["ngf-kme"] = { "Kapau-Menya", nil, "ngf-ang", aliases = {"Southeast Kratke Range"}, -- Usher } m["ngf-koi"] = { "Koiarian", 11154240, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Koiari-Managalas Plateau"}, } m["ngf-kok"] = { "Kokon", -- Usher calls it South Mabuso but includes Gum in it nil, "ngf-mab", } m["ngf-kow"] = { "Kowan", 6435004, "ngf-mad", aliases = {"Isumrud Strait"}, -- per Usher (2020) } m["ngf-ksa"] = { "Kalam-Southern Adelbert", nil, "ngf-mad", aliases = {"Kalamic-South Adelbert", -- Glottolog "West Madang"}, -- Usher (2020) } m["ngf-kto"] = { "Kube-Tobo", -- per Glottolog, one language "Kulungtfu-Yuanggeng-Tobo" 1173235, -- code for Tobo-Kube language "ngf-huo", aliases = {"Tobo-Kube"}, } m["ngf-kts"] = { "Komyandaret-Tsaukambo", nil, "ngf-bda", aliases = {"Becking River"}, -- Usher } m["ngf-kum"] = { "Kumil", nil, "ngf-nad", aliases = {"Kumilan", -- Pawley-Hammarström following Z'graggen (1975) "Kumil River"}, -- Usher's term } m["ngf-kya"] = { "Kamano-Yagaria", nil, "ngf-gor", aliases = {"Henganofi", -- Usher "Kamano-Yagaria-Keigana", }, } m["ngf-lok"] = { "Lowland Ok", nil, "ngf-okk", } m["ngf-mab"] = { "Mabuso", 6721668, "ngf-mad", } m["ngf-mad"] = { "Madang", 11217556, "ngf", aliases = {"Madang-Adelbert Range"}, -- Z'graggen (1975), corresponding to today's Madang except in lacking Kalam and Gants } m["ngf-mek"] = { "Mek", 6810515, "ngf", aliases = {"Goliath"}, -- outdated alternative name given by Wikipedia } m["ngf-min"] = { "Mindjim", 86749913, "ngf-mad", aliases = {"Lower Minjim", -- Glottolog, placed in Rai Coast by Glottolog and Pawley-Hammarström; Glottolog's -- Mindjim has 6 languages, including "Upper Minjim" (Rerau and Sgi Bara) "Mindjim River", -- Usher "Minjim", "Minjim River", }, } -- Add if Molet is separated from Asaro'o -- m["ngf-moa"] = { -- "Molet-Asaro'o", -- nil, -- "ngf-war", -- } m["ngf-mok"] = { "Mountain Ok", -- [[w:Mountain Ok languages]] redirects to [[w:Ok languages]] nil, "ngf-okk", } m["ngf-mom"] = { "Mombum", 6897077, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Mombum-Koneraw", "Komolom", "Muli Strait"}, -- Pawley-Hammarström uses Komolom, Usher uses Muli Strait } m["ngf-msu"] = { "Mian-Suganga", -- considred a single Mian language by Wikipedia 12952846, "ngf-mok", aliases = {"Mianic"}, -- Glottolog } m["ngf-nad"] = { "Northern Adelbert", -- not accepted by Pawley-Hammarström 16952821, -- code for Croisilles linkage "ngf-mad", aliases = {"Adelbert Range-Isumrud Strait", -- Usher (2020) "North Adelbert", "Pihom-Isumrud"}, -- Ross? } m["ngf-nbi"] = { "North Binanderean", nil, "ngf-bin", aliases = {"Suena-Zia"}, -- Usher } m["ngf-nde"] = { "Ndeiram", -- [[w:Ndeiram River languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Ndeiram River"}, -- Usher? } m["ngf-ngn"] = { "Ngalik-Nduga", -- [[w:Ngalik languages]] redirects to [[w:Baliem Valley languages]] = Dani languages nil, "ngf-dan", aliases = {"Ngalik"}, -- Usher } m["ngf-nso"] = { "North Sogeram", nil, "ngf-sog", aliases = {"Mum-Sirva", -- Usher "North Central Sogeram", -- used by those who accept Central Sogeram (= North Sogeram + Apali and Manat) "North-Central Sogeram", -- rarer than without the dash "Sikan"}, -- Z’graggen (1975?) } m["ngf-num"] = { "Numugen", nil, "ngf-nad", aliases = {"Numugenan", -- Glottolog following Z'graggen 1975 "Numugen River"}, -- Usher's term } m["ngf-nur"] = { "Nuru", -- Usher excludes Yangulam, Pawley-Hammarström include Jilim and Rerau nil, "ngf-rai", aliases = {"Nuru River"}, -- Usher? } m["ngf-nwh"] = { "Northwest Hanseman", -- Usher nil, "ngf-han", aliases = {"Wamas-Samosa-Murupi-Mosimo"}, -- Glottolog, Greenhill, and Pawley-Hammarström following Z'graggen; the most common name, but very unwieldy } m["ngf-oen"] = { "Outer Engan", -- considered a single Nete language by Wikipedia 6998869, "ngf-enc", aliases = {"Nete-Bisorio"}, -- Usher } m["ngf-okk"] = { "Ok", 7081687, "ngf", } m["ngf-omo"] = { "Omosan", -- not included in (Greater) Northern Adelbert by Glottolog, but a sister nil, "ngf-nad", } m["ngf-oro"] = { "Orokaivic", 7103752, -- considered a single Orokaiva language by Wikipedia "ngf-bin", aliases = {"Central Oro"}, -- Usher } m["ngf-pan"] = { "Paniai Lakes", 6035631, "ngf", aliases = {"Wissel Lakes", "Wissel Lakes-Kemandoga River"}, -- alternative names given by Wikipedia } m["ngf-pek"] = { "Peka", nil, "ngf-rai", aliases = {"Peka River"}, -- Usher? } m["ngf-pom"] = { "Pomoikan", nil, "ngf-sad", } m["ngf-rai"] = { "Rai Coast", 7283663, "ngf-mad", aliases = {"South Madang"}, -- Usher } m["ngf-sab"] = { "Sabakor", -- [[w:Sabakor languages]] redirects to [[w:Asmat–Kamrau languages]] nil, -- 55994614 is for [[Category:Kamrau Bay languages]], which exists on enwiki "ngf-ask", aliases = {"Kamrau Bay"}, -- Usher } m["ngf-sad"] = { "Southern Adelbert", 12633980, "ngf-ksa", aliases = {"South Adelbert", -- Glottolog "Southern Adelbert Range", -- Z'graggen (1980) "Sogeram and Tomul Rivers"}, -- Usher (2020)? } m["ngf-sak"] = { "Sau-Angal-Kewa", nil, "ngf-khu", aliases = {"Southern Highlands"}, -- Usher } m["ngf-san"] = { "Sankwep", nil, "ngf-huo", aliases = {"Nabak-Momolili", -- Pawley-Hammarström, "Southwest Huon", -- Usher }, } m["ngf-sbh"] = { "South Bird's Head", 7566330, "ngf", } m["ngf-sim"] = { "Simbu", nil, "ngf-chw", } m["ngf-sog"] = { "Sogeram", 86750419, "ngf-sad", aliases = {"Sogeram River", -- Usher "Wanang"}, } m["ngf-sop"] = { "Sopac", nil, "ngf-ehu", aliases = {"Momare-Migabac", -- Pawley-Hammarström, "Masaweng River", -- Usher }, } m["ngf-taa"] = { "Tainae-Akoye", nil, "ngf-ata", aliases = {"Akoye-Tainae"}, -- Usher } m["ngf-tai"] = { "Tairora", nil, "ngf-kai", aliases = {"Tairoric", -- Glottolog, "East Kainantu", -- Usher }, } m["ngf-tib"] = { "Tiboran", nil, "ngf-nad", aliases = {"Nuclear Tibor", -- Glottolog, excluding Wanambre/Mokati "Tiboran River", -- Usher (2020) "Tibor", -- Pick (2020) and Glottolog including Wanambre/Mokati } } m["ngf-tna"] = { "Tangko-Nakai", nil, "ngf-okk", aliases = {"Central Ok"}, -- Usher } m["ngf-uru"] = { "Uruwa", nil, "ngf-fin", aliases = {"Uruwa River"}, -- Usher? } m["ngf-usi"] = { "Utu-Silopi", nil, "ngf-han", aliases = {"Silopi-Utu"}, -- Usher } m["ngf-waa"] = { "Wantoat-Awara", -- not in Usher but Wantoat and Awara form a dialect chain nil, "ngf-wan", aliases = {"Awara-Wantoat"}, -- per Wikipedia } m["ngf-wah"] = { "Wahgi", -- [[w:Wahgi languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Wahgi Valley"}, -- Usher } m["ngf-wan"] = { "Wantoatic", nil, "ngf-fin", aliases = {"Wantoat", "Wantoat River", -- Usher? }, } m["ngf-war"] = { "Warup", 12645082, "ngf-fin", aliases = {"Warup River"}, -- Usher? } m["ngf-woj"] = { "Wojokesic", nil, "ngf-ang", aliases = {"Northeast Kratke Range"}, -- Usher } m["ngf-wok"] = { "West Ok", nil, "ngf-okk", aliases = {"Kwer-Kopkaka-Burumakok"}, -- Glottolog, Pawley-Hammarström } m["ngf-wso"] = { "West Sogeram", nil, "ngf-sog", aliases = {"Mand-Nend", -- Usher "Atan", -- Wurm following Z'graggen }, } m["ngf-yag"] = { "Yaganon", -- placed in Rai Coast by Glottolog and Pawley-Hammarström 35323986, "ngf-mad", aliases = {"Yaganon River"}, -- Usher } m["ngf-yal"] = { "Yali", -- considered a single language by Wikipedia 8047468, "ngf-ngn", aliases = {"Ngalik"}, -- Glottolog, Pawley-Hammarström } m["ngf-yar"] = { "Yareban", 16977672, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Musa River"}, } m["ngf-ynu"] = { "Yau-Nungon", 12953319, -- for the single Yau language in Wikipedia ([[w:Yau language (Trans–New Guinea)]]) "ngf-uru", } m["ngf-yup"] = { "Yupna", nil, "ngf-fin", aliases = {"Yupna River"}, -- Usher? } m["nic"] = { "Niger-Congo", 33838, aliases = {"Niger-Kordofanian"}, } m["nic-alu"] = { "Alumic", 4737355, "nic-plt", } m["nic-bas"] = { "Basa", 4866154, "nic-knj", } m["nic-bbe"] = { "Eastern Beboid", nil, "nic-beb", } m["nic-bco"] = { "Benue-Congo", 33253, "nic-vco", } m["nic-bcr"] = { "Bantoid-Cross", 806983, "nic-bco", } m["nic-bdn"] = { "Northern Bantoid", nil, "nic-bod", aliases = {"North Bantoid"}, } m["nic-bds"] = { "Southern Bantoid", 3183152, "nic-bod", aliases = {"Wide Bantu", "Bin"}, } m["nic-beb"] = { "Beboid", 813549, "nic-bds", } m["nic-ben"] = { "Bendi", 4887065, "nic-bcr", } m["nic-beo"] = { "Beromic", 4894642, "nic-plt", } m["nic-bod"] = { "Bantoid", 806992, "nic-bcr", } m["nic-buk"] = { "Buli-Koma", nil, "nic-ovo", } m["nic-bwa"] = { "Bwa", 12628562, "nic-gur", other_names = {"Bwamu", "Bomu"}, } m["nic-cde"] = { "Central Delta", 3813191, "nic-cri", } m["nic-cri"] = { "Cross River", 1141096, "nic-bcr", } m["nic-dag"] = { "Dagbani", nil, "nic-wov", } m["nic-dak"] = { "Dakoid", 1157745, "nic-bdn", } m["nic-dge"] = { "Escarpment Dogon", 5397128, "qfa-dgn", } m["nic-dgw"] = { "West Dogon", nil, "qfa-dgn", } m["nic-eko"] = { "Ekoid", 1323395, "nic-bds", } m["nic-eov"] = { "Eastern Oti-Volta", nil, "nic-ovo", aliases = {"Samba"}, } m["nic-fru"] = { "Furu", 5509783, "nic-bds", } m["nic-gne"] = { "Eastern Gurunsi", 12633072, "nic-gns", aliases = {"Eastern Grũsi"}, } m["nic-gnn"] = { "Northern Gurunsi", nil, "nic-gns", aliases = {"Northern Grũsi"}, } m["nic-gnw"] = { "Western Gurunsi", nil, "nic-gns", aliases = {"Western Grũsi"}, } m["nic-gns"] = { "Gurunsi", 721007, "nic-gur", aliases = {"Grũsi"}, } m["nic-gre"] = { "Eastern Grassfields", 5330160, "nic-grf", } m["nic-grf"] = { "Grassfields", 750932, "nic-bds", aliases = {"Grassfields Bantu", "Wide Grassfields"}, } m["nic-grm"] = { "Gurma", 30587833, "nic-ovo", } m["nic-grs"] = { "Southwest Grassfields", 7571285, "nic-grf", } m["nic-gur"] = { "Gur", 33536, "alv-sav", aliases = {"Voltaic"}, } m["nic-ief"] = { "Ibibio-Efik", 2743643, "nic-lcr", } m["nic-jer"] = { "Jera", nil, "nic-kne", } m["nic-jkn"] = { "Jukunoid", 1711622, "nic-pla", } m["nic-jrn"] = { "Jarawan", 1683430, "nic-mba", } m["nic-jrw"] = { "Jarawa", 35423, "nic-jrn", } m["nic-kam"] = { "Kambari", 6356294, "nic-knj", } m["nic-ktl"] = { "Katloid", nil, "nic", } m["nic-kau"] = { "Kauru", nil, "nic-kne", } m["nic-kmk"] = { "Kamuku", 6359821, "nic-knj", } m["nic-kne"] = { "East Kainji", 5328687, "nic-knj", } m["nic-knj"] = { "Kainji", 681495, "nic-pla", } m["nic-knn"] = { "Northwest Kainji", 7060098, "nic-knj", } m["nic-ktl"] = { "Katloid", 6377681, "nic", aliases = {"Katla", "Katla-Tima"}, } m["nic-lcr"] = { "Lower Cross River", 3813193, "nic-cri", } m["nic-mam"] = { "Mamfe", 2005898, "nic-bds", aliases = {"Nyang"}, } m["nic-mba"] = { "Mbam", 687826, "nic-bds", } m["nic-mbc"] = { "Mba", 6799561, "nic-ubg", } m["nic-mbw"] = { "West Mbam", nil, "nic-mba", } m["nic-mmb"] = { "Mambiloid", 1888151, other_names = {"North Bantoid"}, -- per Wikipedia, North Bantoid is the parent family "nic-bdn", } m["nic-mom"] = { "Momo", 6897393, "nic-grf", } m["nic-mre"] = { "Moré", nil, "nic-wov", } m["nic-ngd"] = { "Ngbandi", 36439, "nic-ubg", } m["nic-nge"] = { "Ngemba", 7022271, "nic-gre", } m["nic-ngk"] = { "Ngbaka", 3217499, "nic-ubg", } m["nic-nin"] = { "Ninzic", 7039282, "nic-plt", } m["nic-nka"] = { "Nkambe", 7042520, "nic-gre", } m["nic-nkb"] = { "Baka", nil, "nic-nkw", } m["nic-nke"] = { "Eastern Ngbaka", nil, "nic-ngk", } m["nic-nkg"] = { "Gbanziri", nil, "nic-nkw", } m["nic-nkk"] = { "Kpala", nil, "nic-nkw", } m["nic-nkm"] = { "Mbaka", nil, "nic-nkw", } m["nic-nkw"] = { "Western Ngbaka", nil, "nic-ngk", } m["nic-npd"] = { "North Plateau Dogon", nil, "qfa-dgn", } m["nic-nun"] = { "Nun", 13654297, "nic-gre", } m["nic-nwa"] = { "Nanga-Walo", nil, "qfa-dgn", } m["nic-ogo"] = { "Ogoni", 2350726, "nic-cri", aliases = {"Ogonoid"}, } m["nic-ovo"] = { "Oti-Volta", 1157178, "nic-gur", } m["nic-pla"] = { "Platoid", 453244, "nic-bco", aliases = {"Central Nigerian"}, } m["nic-plc"] = { "Central Plateau", 5061668, "nic-plt", } m["nic-pld"] = { "Plains Dogon", nil, "qfa-dgn", } m["nic-ple"] = { "East Plateau", 5329154, "nic-plt", } m["nic-pls"] = { "South Plateau", 7568236, "nic-plt", aliases = {"Jilic-Eggonic"}, } m["nic-plt"] = { "Plateau", 1267471, "nic-pla", } m["nic-ras"] = { "Rashad", 3401986, "nic", } m["nic-rnc"] = { "Central Ring", nil, "nic-rng", } m["nic-rng"] = { "Ring", 2269051, "nic-grf", aliases = {"Ring Road"}, } m["nic-rnn"] = { "Northern Ring", nil, "nic-rng", } m["nic-rnw"] = { "Western Ring", nil, "nic-rng", } m["nic-ser"] = { "Sere", 7453058, "nic-ubg", } m["nic-shi"] = { "Shiroro", 7498953, "nic-knj", aliases = {"Pongu"}, } m["nic-sis"] = { "Sisaala", 36532, "nic-gnw", } m["nic-tar"] = { "Tarokoid", 2394472, "nic-plt", } m["nic-tiv"] = { "Tivoid", 752377, "nic-bds", } m["nic-tvc"] = { "Central Tivoid", nil, "nic-tiv", } m["nic-tvn"] = { "Northern Tivoid", nil, "nic-tiv", } m["nic-ubg"] = { "Ubangian", 33932, "nic-vco", -- or none } m["nic-uce"] = { "East-West Upper Cross River", nil, "nic-ucr", } m["nic-ucn"] = { "North-South Upper Cross River", nil, "nic-ucr", } m["nic-ucr"] = { "Upper Cross River", 4108624, "nic-cri", aliases = {"Upper Cross"}, } m["nic-vco"] = { "Volta-Congo", 37228, "alv", } m["nic-wov"] = { "Western Oti-Volta", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nic-ykb"] = { "Yukubenic", 16909196, "nic-plt", aliases = {"Oohum"}, } m["nic-ymb"] = { "Yambasa", nil, "nic-mba", } m["nic-yon"] = { "Yom-Nawdm", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nub"] = { "Nubian", 1517194, "sdv-nes", } m["nub-hil"] = { "Hill Nubian", 5762211, "nub", aliases = {"Kordofan Nubian"}, } m["omq"] = { "Oto-Manguean", 33669, } m["omq-cha"] = { "Chatino", 35111, "omq-zap", } m["omq-chi"] = { "Chinantecan", 35828, "omq", } m["omq-cui"] = { "Cuicatec", 616024, "omq-mix", } m["omq-maz"] = { "Mazatecan", 36230, "omq", aliases = {"Mazatec"}, } m["omq-mix"] = { "Mixtecan", 21083066, "omq", } m["omq-mxt"] = { "Mixtec", 36363, "omq-mix", } m["omq-otp"] = { "Oto-Pamean", 1270220, "omq", } m["omq-pop"] = { "Popolocan", 5132273, "omq", } m["omq-tri"] = { "Triqui", 780200, "omq-mix", aliases = {"Trique"}, } m["omq-zap"] = { "Zapotecan", 8066463, "omq", } m["omq-zpc"] = { "Zapotec", 13214, "omq-zap", } m["omv"] = { "Omotic", 33860, "afa", } m["omv-aro"] = { "Aroid", 3699526, "omv", aliases = {"Ari-Banna", "South Omotic", "Somotic"}, } m["omv-diz"] = { "Dizoid", 430251, "omv", aliases = {"Maji", "Majoid"}, } m["omv-eom"] = { "East Ometo", 20527288, "omv-ome", } m["omv-gon"] = { "Gonga", 4143043, "omv", aliases = {"Kefoid"}, } m["omv-mao"] = { "Mao", 1351495, "omv", } m["omv-nom"] = { "North Ometo", nil, "omv-ome", } m["omv-ome"] = { "Ometo", 36310, "omv", } m["oto"] = { "Otomian", 130372545, "omq-otp", } m["oto-otm"] = { "Otomi", 36355, "oto", } m["paa"] = { "Papuan", 236425, "qfa-not", } m["paa-aia"] = { "Aian", 4767739, -- Annaberg languages "paa-ram", aliases = {"Middle Ramu", -- Foley (with Rao), "Annaberg", -- with Rao "Aram-Aren", -- Usher }, } m["paa-alp"] = { "Alor-Pantar", 3502429, "paa-tap", } m["paa-amu"] = { "Amto-Musan", 480281, aliases = {"Samaia River"}, } m["paa-ani"] = { "Anim", 55603991, aliases = {"Fly River"}, } m["paa-ara"] = { "Arapesh", 4784223, "paa-koa", aliases = {"Arapeshan"}, -- Foley } m["paa-arf"] = { "Arafundi", 4783702, } m["paa-ata"] = { "Ataitan", 4812652, "paa-ram", aliases = {"Tangu", -- Foley "Tanggu", -- alternative name given by Wikipedia "Moam River", -- Usher }, } m["paa-baa"] = { "Bayono-Awbono", 2424781, } m["paa-bai"] = { "Baining", 748487, aliases = {"East New Britain"}, } m["paa-baw"] = { "Bosngun-Awar", nil, "paa-ott", aliases = {"East Ramu Coast", -- Usher "Bosman-Awar", -- Wikipedia }, } m["paa-bew"] = { "Bewani", -- [[w:Bewani languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 16113460, "paa-bor", aliases = {"Poal River"}, -- Usher } m["paa-boa"] = { "Boazi", 48803717, "paa-mby", aliases = {"Lake Murray"}, -- Usher } m["paa-bor"] = { "Border", 1752158, aliases = {"Upper Tami", "Tami River-Bewani Range", -- Usher }, } m["paa-bul"] = { "Bulaka River", 4987195, aliases = {"Yelmek-Maklew", "Jabga"}, -- Yelmek-Maklew in Evans (2018) and Gregor (2021) } m["paa-bvi"] = { "Betaf-Vitou", -- Glottolog nil, "paa-tor", aliases = {"Vitou-Betaf", -- Wikipedia "Fitou-Tena", -- Usher "Manirem", }, } m["paa-clp"] = { "Central Lakes Plain", -- [[w:Central Lakes Plain languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86780132 is for the corresponding category, which exists in enwiki "paa-lpl", aliases = {"East Tariku", -- Glottolog "Central Lakes Plains", -- Usher }, } m["paa-dtu"] = { "Doso-Turumsa", 16917784, -- possibly related to East Strickland languages aliases = {"Soari River"}, -- Usher's name } m["paa-ebh"] = { "East Bird's Head", 338064, aliases = {"Mantion-Meax", "Mantion-Meyah", -- Mantion-Meax is Wikipedia's term "Southeast Bird's Head", -- Usher (2020) }, } m["paa-eel"] = { "Eastern Eleman", nil, "paa-ele", aliases = {"East Eleman"}, } m["paa-egb"] = { "East Geelvink Bay", 1497678, aliases = {"Geelvink Bay", "East Cenderawasih"}, -- Geelvink Bay per Glottolog } m["paa-eke"] = { "East Keram", nil, "paa-ker", } m["paa-ele"] = { "Eleman", 3034298, aliases = {"Kerema Bay"}, } m["paa-elp"] = { "East Lakes Plain", -- [[w:East Lakes Plain languages]] redirects to [[w:Lakes Plain languages]]; but Croatian Wikipedia has an entry 12633078, "paa-lpl", aliases = {"East Lakes Plains"}, -- Usher } m["paa-epw"] = { "Eastern Pauwasi", 16115496, aliases = {"East Pauwasi"}, } m["paa-etf"] = { "Eastern Trans-Fly", 5330530, aliases = {"Oriomo"}, -- in increasing recent use, probably originating in Evans (2018) } m["paa-eti"] = { "East Timor", 15496066, "paa-tap", aliases = {"Oirata-Makasae", -- Wikipedia's name "Eastern Timor", -- alternative name given by Wikipedia "Fataluku-Makasai", "Oirata-Makasai", -- alternative names given by Wikidata }, } m["paa-fas"] = { "Fas", 3502658, aliases = {"Baibai-Fas"}, -- Glottolog's name } m["paa-flp"] = { "Far West Lakes Plain", -- [[w:Wapoga River languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86808337 is for the corresponding Wapoga languages category, which exists in enwiki "paa-lpl", aliases = {"Rasawa", -- Clouse (1997) "Wapoga River", -- Usher, including Kehu/Keuw (unclassified by others) }, } m["paa-gkw"] = { "Greater Kwerba", 12635134, aliases = {"West Foja Range", -- Usher "Kwerbic", -- Wikipedia "Kwerba", -- Foley (2018) }, } m["paa-gto"] = { "Galela-Tobelo", nil, "paa-nnh", aliases = {"Mainland North Halmaheran", -- Glottolog "Mainland North Halmahera", "Northeast Halmahera", -- alternative names "Northeast Halmaheran", -- Wikipedia, from Verhoeve 1988 }, } m["paa-hya"] = { "Heyo-Yahang", nil, "paa-mam", aliases = {"Yahang-Heyo"}, -- Wikipedia's name } m["paa-ing"] = { "Inland Gulf", 6034783, "paa-ani", aliases = {"Inland Gulf of Papua"}, -- Glottolog } m["paa-isk"] = { "Inner Sko", 65043889, "paa-sko", aliases = {"Skouic", -- Glottolog "West Vanimo Coast", -- Usher "Western Skou", -- Wikipedia "Inner Skou", "Nuclear Skou", -- alternative names given by Wikipedia }, } m["paa-iwa"] = { "Iwam", 15147853, "paa-sep", } m["paa-kae"] = { "Kamula-Elevala", 130390498, -- often placed in TNG aliases = {"Kamula-Elevala River"}, } m["paa-kan"] = { "Kanum", -- removed from Tonda by Glottolog nil, "paa-ton", } m["paa-kay"] = { "Kayagaric", 7566330, aliases = {"Kayagar", -- formerly common "Cook River"}, -- per Usher (2020) } m["paa-ker"] = { "Keram", 48768173, -- often grouped within or coordinate with the Ramu languages aliases = {"Keram River"}, } m["paa-kiw"] = { "Kiwaian", 338449, aliases = {"Kiwai"}, -- formerly common, still sees some use } m["paa-kko"] = { "Kaure-Kosare", -- rejected by Pawley-Hammarström but accepted by Glottolog, Foley (2018) and Usher (2020) 48767891, aliases = {"Nawa River"}, -- Usher's term } m["paa-koa"] = { "Kombio-Arapesh", 16115049, "paa-trr", aliases = {"Kombio-Arapeshan", -- Laycock, who includes Wom "Kombio-Arapesh-Urat", -- Glottolog, including Urat }, } m["paa-kol"] = { "Kolopom", 6427807, } m["paa-kom"] = { "Kombio", 65044238, "paa-koa", aliases = {"Kombian", -- Laycock "Kombio-Yambes", -- Glottolog }, } m["paa-kun"] = { "Kunimaipan", 134973258, aliases = {"Northwest Wharton Range"}, -- per Usher (2020) -- often considered a subfamily of Goilalan } m["paa-kwa"] = { "Kwalean", 6450053, aliases = {"Humene-Uare"}, } m["paa-kwe"] = { "Kwerba proper", 12635134, "paa-gkw", aliases = {"Kwerba", -- Usher "Kwerbaic", -- Glottolog }, } m["paa-kwo"] = { "Kwomtari", 2075415, aliases = {"Kwomtari-Nai"}, -- Senu River is a larger unproven proposal } m["paa-lla"] = { "Loloda-Laba", -- a single language in Glottolog (Loloda-Laba) and Wikipedia (Loloda) 11732388, -- for the Loloda language "paa-gto", aliases = {"Loloda"}, -- Wikipedia's name } m["paa-lma"] = { "Left May", 614468, aliases = {"Arai River"}, -- per Usher (2020) -- Sometimes in a putative Arai-Samaia family along with Amto-Musan and the Pyu language } m["paa-lmu"] = { "Lepki-Murkim", -- Kembra accepted by Glottolog and Usher; not by Foley (2020) but does not exclude the possibility -- of a relationship 85776285, -- independent family per Glottolog, part of South Pauwasi River family (under Pauwasi) per Usher (2020) aliases = {"Lepki-Murkim-Kembra"}, -- Glottolog } m["paa-lpl"] = { "Lakes Plain", 6478969, aliases = {"Lakes Plains"}, } m["paa-lra"] = { "Lower Ramu", 65089469, "paa-ram", aliases = {"Ottilien-Misegian"}, -- alternative name given by Wikipedia } m["paa-lse"] = { "Lower Sepik", 7061700, aliases = {"Nor-Pondo"}, } m["paa-mai"] = { "Mairasi", 6736896, aliases = {"Mairasic"}, -- per Glottolog } m["paa-mal"] = { "Mailuan", 6735839, aliases = {"Cloudy Bay"}, } m["paa-mam"] = { "Maimai", -- Foley's Maimai is expanded 53679325, -- this is the code for the expanded Maimai with 6 languages, as opposed to the 3 in "Nuclear Maimai" "paa-trr", aliases = {"Nuclear Maimai", -- Glottolog's name "Maimai proper", -- Wikipedia's name }, } m["paa-man"] = { "Manubaran", 6752335, aliases = {"Mount Brown"}, } m["paa-mar"] = { "Marienberg", 1570589, "paa-trr", aliases = {"Marienberg Hills"}, -- Usher } m["paa-may"] = { "Maybratic", 4830892, -- the code for the Maybrat language in Wikipedia, which subsumes the two languages of this family -- putatively included in West Papuan but generally considered an isolated family aliases = {"Maybrat-Karon"}, } m["paa-mbi"] = { "Mbaham-Iha", 85784512, "qfa-dis", -- Papuan languages; Glottolog groups Karas (Kalamang) with Mbaham-Iha into a (mainland) West Bomberai -- family and stops there; Wikipedia, following Usher and Schapper (2022), groups Karas, Mbaham-Iha -- and the large Timor-Alor-Pantar family into a (Greater) West Bomberai family, saying that Karas is no -- closer to Mbaham-Iha than to Timor-Alor-Pantar. aliases = {"Mbahaam-Iha", -- used by Wikidata "Nuclear West Bomberai", -- Glottolog's name }, } m["paa-mby"] = { "Marind-Boazi-Yaqay", 3217484, "paa-ani", aliases = {"Marind-Boazi-Yaqai", -- Glottolog "Marind-Yakhai", -- Usher, without Boazi "Marind-Yaqai", -- Wikidata "Marind", -- alternative name given by Wikipedia "Marind-Arandai", -- alternative name given by Spanish Wikipedia }, } m["paa-mmu"] = { "Mandi-Muniwara", nil, "paa-mar", aliases = {"West Marienberg Hills"}, -- Usher } m["paa-mon"] = { "Monumbo", -- per Glottolog: "No evidence for the Bogia (Monumbo) languages being related to other Torricelli languages was ever presented" 16928417, aliases = {"Bogia", -- Glottolog "Bogia Bay", -- Usher (2020) }, } m["paa-mri"] = { "Marindic", -- [[w:Marindic languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Marind"}, -- Usher; a single language } m["paa-nam"] = { "Nambu", 6961418, "paa-yam", aliases = {"East Morehead River"}, -- Usher } m["paa-nbo"] = { "North Bougainville", 749496, } m["paa-ndu"] = { "Ndu", 3217498, "paa-sep", -- Not accepted by Glottolog aliases = {"Ndu-Nggala"}, -- Usher } m["paa-ngk"] = { "Ngkolmpu", -- considered a single language by Wikipedia 5908646, "paa-kan", aliases = {"Ngkantr", -- Glottolog "Ngkolmpu Kanum", -- Wikipedia "Ngkontar", -- alternative name given by Wikipedia "Kanum", -- used by Wikidata }, } m["paa-nha"] = { "North Halmahera", 3217358, -- possibly in a proposed West Papuan family or an independent family } m["paa-nim"] = { "Nimboran", 12638426, aliases = {"Nimboranic", -- per Glottolog "Grime River", -- per Usher (2020) } } m["paa-nnd"] = { "Nuclear Ndu", nil, "paa-ndu", aliases = {"Ndu", -- Usher, with Boiken/Boikin "Ndu proper", -- Wikipedia }, } m["paa-nnh"] = { "Northern North Halmahera", nil, "paa-nha", aliases = {"Northern North Halmaheran", -- Glottolog "Halmahera", -- Usher "Core Halmaheran", -- Wikipedia }, } m["paa-nto"] = { "Namla-Tofanma", 16918187, -- independent family per Glottolog and Foley (2018), part of West Pauwasi family (under Pauwasi) per Usher (2020) } m["paa-ott"] = { "Ottilien", 7109477, "paa-lra", aliases = {"Ramu Coast", -- Usher "Watam-Awar-Gamay", -- alternative name given by Wikipedia }, } m["paa-pah"] = { "Pahoturi River", 17049141, aliases = {"Pahoturi"}, -- per Glottolog } m["paa-pal"] = { "Palei", -- Laycock adds Agi and Nabi/Nambi(-Metan) 65089113, "paa-wpa", aliases = {"Nuclear Palai"}, } m["paa-pia"] = { "Piawi", -- per Wikipedia, grouped with Arafundi languages to form Upper Yuat, which is a sister to Madang 7190400, aliases = {"Schraeder Range", -- Usher? "Waibuk"}, } m["paa-pio"] = { "Piore River", 65043152, "paa-sko", aliases = {"Barupu Lagoon", -- Glottolog "Lagoon", -- alternative name given by Wikipedia }, } m["paa-por"] = { "Porapora", -- Foley includes Ambakich (which we, Glottolog, and Usher treat as Keram) 65044258, "paa-ram", aliases = {"Agoan", -- Glottolog "Porapora River", -- Usher "core Grass", -- alternative name given by Wikipedia }, } m["paa-ram"] = { "Ramu", 3442808, aliases = {"Ramu River"}, -- per Usher (2020) } m["paa-rsa"] = { "Rasawa-Saponi", -- [[w:Rasawa-Saponi languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q9859418 is for the coresponding category, which exists in the Piedmontese Wikipedia (?!) "paa-flp", aliases = {"Rombak River"}, -- Usher } m["paa-rub"] = { "Ruboni", 6875319, "paa-lra", aliases = {"Misegian", -- Wikipedia's name "Mikarew", -- alternative name given by Wikipedia "Ruboni Range"}, -- Usher } m["paa-saa"] = { "Samarokena-Airoran", 96417699, "paa-gkw", aliases = {"Apauwar Coast"}, -- Usher } m["paa-sah"] = { "Sahu", nil, "paa-nnh", } m["paa-sbo"] = { "South Bougainville", 3217380, } m["paa-sen"] = { "Sentani", 17044584, -- no consensus on higher affiliations, if any aliases = {"Sentanic", "Demta-Sentani", "Demta-Lake Sentani"}, -- Sentanic per Glottolog, Demta-Sentani per Wikipedia } m["paa-sep"] = { "Sepik", 3508772, } m["paa-shi"] = { "Serra Hills", 65043154, "paa-sko", } m["paa-sko"] = { "Sko", 953509, aliases = {"Skou"}, } m["paa-sng"] = { "Senagi", 2066550, } m["paa-taa"] = { "Taikat-Awyi", -- [[w:Taikat languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12643265, "paa-bor", aliases = {"Taikat", -- Foley "Upper Tami River", -- Usher }, } m["paa-tam"] = { "Tamolan", 7681634, "paa-ram", aliases = {"Guam River"}, -- Usher } m["paa-tap"] = { "Timor-Alor-Pantar", 16590002, } m["paa-teb"] = { "Teberan", 7692052, -- Often grouped with Trans-New Guinea, but per Pawley-Hammarström (2018), it has "weaker or disputed claims to membership in TNG". aliases = {"Dadibi-Folopa"}, } m["paa-tir"] = { "Tirio", 7809225, "paa-ani", aliases = {"Nuclear Lower Fly", -- Pawley-Hammarström ("Lower Fly" includes Abom) "Nuclear Tirio", -- Glottolog ("Tirio" includes Abom) "Lower Fly River", -- Usher (without Abom) }, } m["paa-tki"] = { "Turama-Kikori", 7853680, aliases = {"Turama-Kikorian", "Rumu-Omati River"}, } m["paa-ton"] = { "Tonda", 8581005, "paa-yam", aliases = {"West Morehead River"}, -- Usher } m["paa-too"] = { "Tor-Orya", 16590099, aliases = {"Orya-Tor"}, } m["paa-tor"] = { "Tor", -- [[w:Tor languages]] redirects to [[w:Orya–Tor languages]] nil, "paa-too", } m["paa-trr"] = { "Torricelli", 1333831, } m["paa-tti"] = { "Ternate-Tidore", nil, "paa-nnh", } m["paa-wal"] = { "Walio", 16919872, -- Often placed in Sepik (e.g. by Laycock and Z'graggen (1975)), but not by Foley (2018), and not accepted by Glottolog. aliases = {"Walioic", -- Glottolog "Central Leonhard Schultze River", }, } m["paa-wap"] = { "Wapei", -- Glottolog includes Nabi/Nambi(-Metan) in Wapeic 65089115, "paa-wpa", aliases = {"Wapeic"}, -- Glottolog } m["paa-war"] = { "Waris", -- [[w:Waris languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12645076, "paa-bor", aliases = {"Warisic", -- Glottolog "Bapi River", -- Usher (without Manem or Senggi) }, } m["paa-wbh"] = { "West Bird's Head", 5330530, -- Kuwani is sometimes included; probably related to North Halmahera languages. } m["paa-wel"] = { "Western Eleman", nil, "paa-ele", aliases = {"West Eleman"}, } m["paa-wig"] = { "West Inland Gulf", nil, "paa-ing", aliases = {"West Inland Gulf of Papua"}, -- Glottolog } m["paa-wke"] = { "West Keram", nil, "paa-ker", aliases = {"Koam", "Mongol-Langam", "Ulmapo"}, -- Koam used by Foley, Ulmapo used by Glottolog } m["paa-wko"] = { "Wára-Kómnzo", -- since we split out Kómnzo as a separate language 11732474, -- for the Wara language "paa-ton", aliases = {"Anta-Komnzo-Wára-Wérè-Kémä", -- Glottolog's name "Wára", "Wara", -- Wikipedia }, } m["paa-wlp"] = { "West Lakes Plain", -- [[w:Tariku languages]] redirects to [[w:Lakes Plain languages]] 47007503, -- actually for "Tariku languages", which per Wikipedia covers Fayu, Kirikiri, Iau and Tause "paa-lpl", aliases = {"West Tariku", -- Glottolog "West Lakes Plains"}, -- Usher, with Edopi/Iau } m["paa-wpa"] = { "Wapei-Palei", 65043156, "paa-trr", } m["paa-wpw"] = { -- paa-wpa already used by Wapei-Palei "Western Pauwasi", -- 2 langs per Glottolog and Pawley-Hammarström; Usher also includes Namla-Tofanma and Usku 85815062, aliases = {"West Pauwasi", -- Wikipedia, Usher "Tebi-Towe", "Dubu-Towei"}, } m["paa-yam"] = { "Yam", 15062272, aliases = {"Morehead and Upper Maro River", "Morehead River", -- Usher }, } m["paa-yaq"] = { "Yaqayic", -- [[w:Yaqai languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Yakhai-Warkay"}, -- Usher } m["paa-ysa"] = { "Yawa-Saweru", 3217545, aliases = {"Yawa", "Yawan", "Yapen"}, } m["paa-yua"] = { "Yuat", 8060096, } m["phi"] = { "Philippine", 947858, "poz", } m["phi-kal"] = { "Kalamian", 3217466, "phi", aliases = {"Calamian"}, } m["poz"] = { "Malayo-Polynesian", 143158, "map", } m["poz-aay"] = { "Admiralty Islands", 2701306, "poz-oce", } m["poz-bnn"] = { "North Bornean", 1427907, "poz", } m["poz-bre"] = { "East Barito", 2701314, "poz", } m["poz-brw"] = { "West Barito", 2761679, "poz", } m["poz-bss"] = { "Bali-Sasak-Sumbawa", 3396043, "poz-msa", } m["poz-btk"] = { "Bungku-Tolaki", 3217381, "poz-clb", } m["poz-cet"] = { "Central-Eastern Malayo-Polynesian", 2269883, "poz", } m["poz-clb"] = { "Celebic", 1078041, "poz", } m["poz-cln"] = { "New Caledonian", 3091221, "poz-ocs", } m["poz-cma"] = { "Central Maluku", 3217479, "poz-cet", } m["poz-hce"] = { "Halmahera-Cenderawasih", 2526616, "pqe", } m["poz-kal"] = { "Kaili-Pamona", 3217465, "poz-clb", } m["poz-lgx"] = { "Lampungic", 49215, "poz", } m["poz-mcm"] = { "Malayo-Chamic", nil, "poz-msa", } m["poz-mic"] = { "Micronesian", 420591, "poz-occ", } m["poz-mly"] = { "Malayic", 662628, "poz-mcm", } m["poz-msa"] = { "Malayo-Sumbawan", 1363818, "poz", } m["poz-mun"] = { "Muna-Buton", 3037924, "poz-clb", } m["poz-nws"] = { "Northwest Sumatran", 2071308, "poz", } m["poz-occ"] = { "Central-Eastern Oceanic", 2068435, "poz-oce", } m["poz-oce"] = { "Oceanic", 324457, "pqe", } m["poz-ocs"] = { "Southern Oceanic", 3039118, "poz-occ", } m["poz-ocw"] = { "Western Oceanic", 2701282, "poz-oce", } m["poz-pcc"] = { "Central Pacific", 3130237, "poz-occ", } m["poz-pep"] = { "Eastern Polynesian", 390979, "poz-pnp", } m["poz-pnp"] = { "Nuclear Polynesian", 743851, "poz-pol", } m["poz-pol"] = { "Polynesian", 390979, "poz-pcc", } m["poz-san"] = { "Sabahan", 3217517, "poz-bnn", } m["poz-sbj"] = { "Sama-Bajaw", 2160409, "poz", } m["poz-slb"] = { "Saluan-Banggai", 3217519, "poz-clb", } m["poz-sls"] = { "Southeast Solomonic", 3119671, "poz-occ", } m["poz-ssw"] = { "South Sulawesi", 2778190, "poz", } m["poz-stm"] = { "St. Matthias", 6484143, "poz-oce", aliases = {"St Matthias"}, } m["poz-swa"] = { "North Sarawakan", 538569, "poz-bnn", } m["poz-tem"] = { "Temotu", 3075769, "poz-oce", } m["poz-tim"] = { "Timoric", 7806987, "poz-cet", } m["poz-ton"] = { "Tongic", 3397263, "poz-pol", } m["poz-tot"] = { "Tomini-Tolitoli", 3217541, "poz-clb", } m["poz-vnc"] = { "Central Vanuatu", 5061988, "poz-ocs", } m["poz-vnn"] = { "North Vanuatu", 85789650, "poz-ocs", } m["poz-vns"] = { "South Vanuatu", 3070173, "poz-ocs", } m["poz-wot"] = { "Wotu-Wolio", 1041317, "poz-clb", aliases = {"Island Kaili-Wolio"}, -- Glottolog } m["pqe"] = { "Eastern Malayo-Polynesian", 2269883, "poz-cet", } m["qfa-adc"] = { "Central Great Andamanese", nil, "qfa-adm", } m["qfa-adm"] = { "Great Andamanese", 3515103, } m["qfa-adn"] = { "Northern Great Andamanese", nil, "qfa-adm", } m["qfa-ads"] = { "Southern Great Andamanese", nil, "qfa-adm", } m["qfa-ain"] = { "Ainuic", 50111972, aliases = {"Ainu"}, } m["qfa-bej"] = { "Be-Jizhao", nil, "qfa-bet", } m["qfa-bet"] = { "Be-Tai", 12627719, "qfa-tak", aliases = {"Tai-Be", "Daic-Beic", "Beic-Daic"}, } m["qfa-buy"] = { "Buyang", 1109927, "qfa-kra", } m["qfa-cka"] = { "Chukotko-Kamchatkan", 33255, } m["qfa-cre"] = { "creole", 33289, "crp", } m["qfa-ckn"] = { "Chukotkan", 2606732, "qfa-cka", } m["qfa-cnt"] = { "contact", 133253514, "qfa-not", } m["qfa-dis"] = { -- Languages that are not unclassifiable (qfa-unc) but where there is no consensus on classification. Usually -- this is because the languages are divergent and it's disputed whether they are isolates or distantly related -- to other languages. "disputed affiliation", nil, "qfa-not", } m["qfa-dgn"] = { "Dogon", 1234776, "nic", } m["qfa-dny"] = { "Dene-Yeniseian", 21103, aliases = {"Dené-Yeniseian"}, } m["qfa-hur"] = { "Hurro-Urartian", 1144159, } m["qfa-iso"] = { "isolate", 33648, "qfa-not", } m["qfa-kad"] = { "Kadu", -- considered either Nilo-Saharan or independent/none 1720989, } m["qfa-kms"] = { "Kam-Sui", 1023641, "qfa-tak", } m["qfa-kor"] = { "කොරියානු", 11263525, } m["qfa-kra"] = { "Kra", 1022087, "qfa-tak", } m["qfa-lic"] = { "Hlai", 1023648, "qfa-tak", aliases = {"Hlaic"}, } m["qfa-mch"] = { -- used in both N and S America "Macro-Chibchan", 3438062, } m["qfa-mix"] = { "mixed", 33694, "qfa-cnt", } m["qfa-not"] = { "not a family", nil, "qfa-not", } m["qfa-onb"] = { "Be", nil, "qfa-bej", aliases = {"Ong-Be", "Beic"}, } m["qfa-ong"] = { "Ongan", 2090575, aliases = {"Angan", "South Andamanese", "Jarawa-Onge"}, } m["qfa-pid"] = { "pidgin", 33831, "crp", } m["qfa-sub"] = { "substrate", 20730913, "qfa-not", } m["qfa-tak"] = { "Kra-Dai", 34171, aliases = {"Tai-Kadai", "Kadai"}, } m["qfa-tyn"] = { "Tyrsenian", 1344038, } m["qfa-unc"] = { -- This corresponds to languages normally called "unclassified", i.e. there is insufficient data or research to -- classify them, whereas our [[:Category:Unclassified languages]] is just languages that no Wiktionary editor -- has classified yet (the family code in the language data is missing). "unclassifiable", 33956, "qfa-not", } m["qfa-xgs"] = { "Serbi-Mongolic", 108887939, } m["qfa-xgx"] = { "Para-Mongolic", 107619002, "qfa-xgs", } m["qfa-yen"] = { "Yeniseian", 27639, "qfa-dny", aliases = {"Yeniseic", "Yenisei-Ostyak"}, } m["qfa-yke"] = { "Ketic", nil, "qfa-yen", } m["qfa-yko"] = { "Kottic", nil, "qfa-yen", } m["qfa-yrn"] = { "Arinic", nil, "qfa-yen", } m["qfa-ypm"] = { "Pumpokolic", nil, "qfa-yen", } m["qfa-yuk"] = { "Yukaghir", 34164, aliases = {"Yukagir", "Jukagir"}, } m["qwe"] = { "Quechuan", 5218, } m["raj"] = { "Rajasthani", 13196, "inc-wes", protoLanguage = "inc-ogu", } m["roa"] = { "Romance", 19814, "itc", aliases = {"Romanic", "Latin", "Neolatin", "Neo-Latin"}, protoLanguage = "la", } m["roa-asl"] = { "Asturleonese", 35390, "roa-ibe", protoLanguage = "roa-ole", } m["roa-cas"] = { "Castilian", 71924, "roa-ibe", aliases = {"Castillian", "Castilic", "Castillic"}, protoLanguage = "osp", } m["roa-dal"] = { "Dalmatian Romance", 97646077, "roa-itd", } m["roa-eas"] = { "Eastern Romance", 147576, "roa", } m["roa-emr"] = { "Emilian-Romagnol", 242648, "roa-git", } m["roa-gap"] = { "Galician-Portuguese", 9080204, "roa-ibe", aliases = {"Galician Romance", "Galaic-Portuguese"}, protoLanguage = "roa-opt", } m["roa-gar"] = { "Gallo-Romance", 500394, "roa-wes", } m["roa-itd"] = { "Italo-Dalmatian", 3313381, "roa-iwr", aliases = {"Central Romance"} } m["roa-itr"] = { "Italo-Romance", 3356483, "roa-itd", } m["roa-iwr"] = { "Italo-Western Romance", 112608, "roa", aliases = {"Italo-Western"}, } m["roa-git"] = { "Gallo-Italic", 516074, "roa-gar", aliases = {"Gallo-Italian", "Gallo-Cisalpine", "Cisalpine"}, } m["roa-grh"] = { "Gallo-Rhaetian", 97646466, "roa-gar", } m["roa-ibe"] = { "Ibero-Romance", 749533, "roa-wes", aliases = {"Iberian Romance", "West Ibero-Romance", "Western Ibero-Romance", "West Iberian Romance", "Western Iberian Romance"} } m["roa-nar"] = { "Navarro-Aragonese", 133252927, "roa-ibe", protoLanguage = "roa-ona", } m["roa-oil"] = { "Oïl", 37351, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, protoLanguage = "fro", } m["roa-ocr"] = { "Occitano-Romance", 599958, "roa-gar", aliases = {"Gallo-Narbonnese", "East Iberian", "Eastern Iberian"}, } m["roa-rhe"] = { "Rhaeto-Romance", 515593, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, } m["roa-sou"] = { "Southern Romance", 145345, "roa", } m["roa-wes"] = { "Western Romance", 2714388, "roa-iwr", } --[=[ Exceptional language and family codes for South American Indian languages can use the prefix "sai-", though "sai" is no longer itself a family code. ]=]-- m["sai-ara"] = { "Araucanian", 626630, } m["sai-aym"] = { "Aymaran", 33010, } m["sai-bar"] = { "Barbacoan", 807304, aliases = {"Barbakoan"}, } m["sai-bor"] = { "Boran", 5371776, } m["sai-cah"] = { "Cahuapanan", 1025793, } m["sai-car"] = { "Cariban", 33090, aliases = {"Carib"}, } m["sai-cer"] = { "Cerrado", 98078151, "sai-jee", aliases = {"Amazonian Jê"}, } m["sai-chc"] = { "Chocoan", 1075616, aliases = {"Choco", "Chocó"}, } m["sai-cho"] = { "Chonan", 33019, aliases = {"Chon"}, } m["sai-cje"] = { "Central Jê", 18010843, "sai-cer", aliases = {"Akuwẽ"}, } m["sai-cpc"] = { "Chapacuran", 1062626, } m["sai-crn"] = { "Charruan", 3112423, aliases = {"Charrúan"}, } m["sai-ctc"] = { "Catacaoan", 5051139, } m["sai-guc"] = { "Guaicuruan", 1974973, "sai-mgc", aliases = {"Guaicurú", "Guaycuruana", "Guaikurú", "Guaycuruano", "Guaykuruan", "Waikurúan"}, } m["sai-guh"] = { "Guahiban", 944056, aliases = {"Guahiboan", "Guajiboan", "Wahivoan"}, } m["sai-gui"] = { "Guianan", nil, "sai-car", aliases = {"Guianan Carib", "Guiana Carib"}, } m["sai-har"] = { "Harákmbut", 1584402, "sai-hkt", aliases = {"Harákmbet"}, } m["sai-hkt"] = { "Harákmbut-Katukinan", 17107635, } m["sai-hrp"] = { "Huarpean", 1578336, aliases = {"Warpean", "Huarpe", "Warpe"}, } m["sai-jee"] = { "Jê", 1483594, "sai-mje", aliases = {"Gê", "Jean", "Gean", "Jê-Kaingang", "Ye"}, } m["sai-jir"] = { "Jirajaran", 3028651, aliases = {"Hiraháran"}, } m["sai-jiv"] = { "Jivaroan", 1393074, aliases = {"Hívaro", "Jibaro", "Jibaroan", "Jibaroana", "Jívaro"}, } m["sai-ktk"] = { "Katukinan", 2636000, "sai-hkt", aliases = {"Catuquinan"}, } m["sai-kui"] = { "Kuikuroan", nil, "sai-car", aliases = {"Kuikuro", "Nahukwa"}, } m["sai-map"] = { "Mapoyan", 61096301, "sai-ven", aliases = {"Mapoyo", "Mapoyo-Yabarana", "Mapoyo-Yavarana", "Mapoyo-Yawarana"}, } m["sai-mas"] = { "Mascoian", 1906952, aliases = {"Mascoyan", "Maskoian", "Enlhet-Enenlhet"}, } m["sai-mgc"] = { "Mataco-Guaicuru", 255512, } m["sai-mje"] = { "Macro-Jê", 887133, aliases = {"Macro-Gê"}, } m["sai-mtc"] = { "Matacoan", 2447424, "sai-mgc", } m["sai-mur"] = { "Muran", 33826, aliases = {"Mura"}, } m["sai-nad"] = { "Nadahup", 1856439, aliases = {"Makú", "Macú", "Vaupés-Japurá"}, } m["sai-nje"] = { "Northern Jê", 98078225, "sai-cer", aliases = {"Core Jê"}, } m["sai-nmk"] = { "Nambikwaran", 15548027, aliases = {"Nambicuaran", "Nambiquaran", "Nambikuaran"}, } m["sai-otm"] = { "Otomacoan", 3217503, aliases = {"Otomákoan", "Otomakoan"}, } m["sai-pan"] = { "Panoan", 1544537, "sai-pat", aliases = {"Pano"}, } m["sai-pat"] = { "Pano-Tacanan", 2475746, aliases = {"Pano-Tacana", "Pano-Takana", "Páno-Takána", "Pano-Takánan"}, } m["sai-pek"] = { "Pekodian", 107451736, "sai-car", aliases = {"South Amazonian Carib", "Southern Cariban", "Pekodi"}, } m["sai-pem"] = { "Pemongan", nil, "sai-ven", aliases = {"Pemong", "Pemóng", "Purukoto"}, } m["sai-pey"] = { "Peba-Yaguan", 174015, aliases = {"Peba-Yagua", "Yaguan", "Peban", "Yáwan"}, } m["sai-prk"] = { "Parukotoan", 107451482, "sai-car", aliases = {"Parukoto"}, } m["sai-sje"] = { "Southern Jê", 98078245, "sai-jee", } m["sai-tac"] = { "Tacanan", 3113762, "sai-pat", } m["sai-tar"] = { "Taranoan", 105097814, "sai-gui", aliases = {"Trio", "Tarano"}, } m["sai-tuc"] = { "Tucanoan", 788144, } m["sai-tyu"] = { "Ticuna-Yuri", 4467010, } m["sai-ucp"] = { "Uru-Chipaya", 2475488, aliases = {"Uru-Chipayan"}, } m["sai-ven"] = { "Venezuelan Cariban", nil, "sai-car", aliases = {"Venezuelan Carib", "Venezuelan", "Venezuelano"}, } m["sai-wic"] = { "Wichí", 3027047, } m["sai-wit"] = { "Witotoan", 43079317, aliases = {"Huitotoan", "Uitotoan"}, } m["sai-ynm"] = { "Yanomami", nil, aliases = {"Yanomam", "Shamatari", "Yamomami", "Yanomaman"}, } m["sai-yuk"] = { "Yukpan", nil, "sai-car", aliases = {"Yukpa", "Yukpano", "Yukpa-Japreria"}, } m["sai-zam"] = { "Zamucoan", 3048461, aliases = {"Samúkoan"}, } m["sai-zap"] = { "Zaparoan", 33911, aliases = {"Záparoan", "Saparoan", "Sáparoan", "Záparo", "Zaparoano", "Zaparoana"}, } m["sal"] = { "Salish", 33985, } m["sdv"] = { "Eastern Sudanic", 2036148, "ssa", } m["sdv-bri"] = { "Bari", nil, "sdv-nie", } m["sdv-daj"] = { "Daju", 956724, "sdv", } m["sdv-dnu"] = { "Dinka-Nuer", nil, "sdv-niw", } m["sdv-eje"] = { "Eastern Jebel", 3408878, "sdv", } m["sdv-kln"] = { "Kalenjin", 637228, "sdv-nis", } m["sdv-lma"] = { "Lotuko-Maa", nil, "sdv-nie", } m["sdv-lon"] = { "Northern Luo", nil, "sdv-luo", } m["sdv-los"] = { "Southern Luo", 7570103, "sdv-luo", } m["sdv-luo"] = { "Luo", nil, "sdv-niw", } m["sdv-nes"] = { "Northern Eastern Sudanic", 4810496, "sdv", aliases = {"Astaboran", "Ek Sudanic"}, } m["sdv-nie"] = { "Eastern Nilotic", 153795, "sdv-nil", } m["sdv-nil"] = { "Nilotic", 513408, "sdv", } m["sdv-nis"] = { "Southern Nilotic", 1552410, "sdv-nil", } m["sdv-niw"] = { "Western Nilotic", 3114989, "sdv-nil", } m["sdv-nma"] = { "Nandi-Markweta", nil, "sdv-kln", } m["sdv-nyi"] = { "Nyima", 11688746, "sdv-nes", aliases = {"Nyimang"}, } m["sdv-tmn"] = { "Taman", 3408873, "sdv-nes", aliases = {"Tamaic"}, } m["sdv-ttu"] = { "Teso-Turkana", 7705551, "sdv-nie", aliases = {"Ateker"}, } m["sel"] = { "Selkup", 34008, "syd", } m["sem"] = { "Semitic", 34049, "afa", } m["sem-ara"] = { "Aramaic", 28602, "sem-nwe", protoLanguage = "arc", } m["sem-arb"] = { "අරාබි", 164667, "sem-cen", protoLanguage = "ar", } m["sem-are"] = { "Eastern Aramaic", 3410322, "sem-ara", } m["sem-arw"] = { "Western Aramaic", 3394214, "sem-ara", } m["sem-ase"] = { "Southeastern Aramaic", 3410322, "sem-are", } m["sem-can"] = { "Canaanite", 747547, "sem-nwe", } m["sem-cen"] = { "Central Semitic", 3433228, "sem-wes", } m["sem-cna"] = { "Central Neo-Aramaic", 3410322, "sem-are", } m["sem-eas"] = { "East Semitic", 164273, "sem", } m["sem-eth"] = { "Ethiopian Semitic", 163629, "sem-wes", aliases = {"Afro-Semitic", "Ethiopian", "Ethiopic", "Ethiosemitic"}, } m["sem-nna"] = { "Northeastern Neo-Aramaic", 2560578, "sem-are", } m["sem-nwe"] = { "Northwest Semitic", 162996, "sem-cen", } m["sem-osa"] = { "Old South Arabian", 35025, "sem-cen", aliases = {"Epigraphic South Arabian", "Sayhadic"}, } m["sem-sar"] = { "Modern South Arabian", 1981908, "sem-wes", } m["sem-wes"] = { "West Semitic", 124901, "sem", } m["sgn"] = { "sign", 34228, "qfa-not", } m["sgn-fsl"] = { "French Sign Languages", 5501921, "sgn", } m["sgn-gsl"] = { "German Sign Languages", 5551235, "sgn", } m["sgn-jsl"] = { "Japanese Sign Languages", 11722508, "sgn", } m["sio"] = { "Siouan", 34181, "nai-sca", } m["sio-dhe"] = { "Dhegihan", 3217420, "sio-msv", } m["sio-dkt"] = { "Dakotan", 4154122, "sio-msv", } m["sio-mor"] = { "Missouri River Siouan", 26807266, "sio", } m["sio-msv"] = { "Mississippi Valley Siouan", 12637104, "sio", } m["sio-ohv"] = { "Ohio Valley Siouan", 21070931, "sio", } m["sit"] = { "Sino-Tibetan", 45961, aliases = {"Trans-Himalayan"}, } m["sit-aao"] = { "Central Naga", 615474, "sit", } m["sit-alm"] = { "Almora", nil, "sit-whm", } m["sit-bai"] = { "Bai", 35103, "sit-mba", } m["sit-bdi"] = { "Bodish", 1814078, "sit", } m["sit-cln"] = { "Cai-Long", 107182612, "sit-mba", aliases = {"Ta-Li"}, } m["sit-dhi"] = { "Dhimalish", 1207648, "sit", } m["sit-ebo"] = { "East Bodish", 56402, "sit-bdi", } m["sit-egy"] = { "East rGyalrongic", 832026, "sit-rgy", } m["sit-ers"] = { "Ersuic", 56335, "sit", } m["sit-gma"] = { "Greater Magaric", 55612963, "sit", } m["sit-gsi"] = { "Greater Siangic", 52698851, "sit", } m["sit-hrs"] = { "Hrusish", 1632501, "sit", aliases = {"Southeast Kamengic"}, } m["sit-jnp"] = { "Jingphoic", nil, "sit-jpl", aliases = {"Jingpho"}, } m["sit-jpl"] = { "Kachin-Luic", 1515454, "tbq-bkj", aliases = {"Jingpho-Luish", "Jingpho-Asakian", "Kachinic"}, } m["sit-kch"] = { "Konyak-Chang", nil, "sit-kon", } m["sit-kha"] = { "Kham", 33305, "sit-gma", } m["sit-khb"] = { "Kho-Bwa", 6401917, "sit", aliases = {"Bugunish", "Kamengic"}, } m["sit-khw"] = { "Western Kho-Bwa", nil, "sit-khb", } m["sit-khc"] = { "Chug-Lish", nil, "sit-khw", aliases = {"Duhumbi-Khispi"}, } m["sit-khm"] = { "Mey-Sartang", nil, "sit-khw", aliases = {"Sartang-Sherdukpen"}, } m["sit-kic"] = { "Central Kiranti", nil, "sit-kir", } m["sit-kie"] = { "Eastern Kiranti", nil, "sit-kir", } m["sit-kin"] = { "Kinnauric", nil, "sit-whm", aliases = {"Kinnauri"}, } m["sit-kir"] = { "Kiranti", 922148, "sit", } m["sit-kiw"] = { "Western Kiranti", 922148, "sit-kir", } m["sit-kon"] = { "Northern Naga", 774590, "tbq-bkj", aliases = {"Konyakian", "Konyak"}, } m["sit-kyk"] = { "Kyirong-Kagate", 6450957, "sit-tib", } m["sit-lab"] = { "Ladakhi-Balti", 6450957, "sit-tib", } m["sit-las"] = { "Lahuli-Spiti", 6473510, "sit-tib", } m["sit-luu"] = { "Luish", 55621439, "sit-jpl", aliases = {"Asakian", "Sak"}, } m["sit-mar"] = { "Maringic", nil, "sit-tma", } m["sit-mba"] = { "Macro-Bai", 16963847, "sit-sba", aliases = {"Greater Bai"}, } m["sit-mdz"] = { "Midzu", 6843504, "sit", aliases = {"Geman", "Midzuish", "Miju-Meyor", "Southern Mishmi"}, } m["sit-mnz"] = { "Mondzish", 6898839, "tbq-lob", aliases = {"Mangish"}, } m["sit-mru"] = { "Mruic", 16908870, "sit", aliases = {"Mru-Hkongso"}, } m["sit-nas"] = { "Naish", 25047956, "sit-nax", } m["sit-nax"] = { "Naic", 6982999, "tbq-buq", aliases = {"Naxish"}, } m["sit-nba"] = { "Northern Bai", 122463830, "sit-bai", } m["sit-new"] = { "Newaric", 55625069, "sit", } m["sit-nng"] = { "Nungish", 1515482, "sit", aliases = {"Nung"}, } m["sit-qia"] = { "Qiangic", 1636765, "tbq-buq", } m["sit-rgy"] = { "Rgyalrongic", 56936, "sit-qia", aliases = {"Jiarongic"}, } m["sit-sba"] = { "Sino-Bai", nil, "sit", aliases = {"Greater Bai"}, } m["sit-tam"] = { "Tamangic", 3309439, "sit", aliases = {"West Bodish"}, } m["sit-tan"] = { "Tani", 3217538, "sit", } m["sit-tib"] = { "Tibetic", 1641150, "sit-bdi", protoLanguage = "otb", } m["sit-tja"] = { "Tujia", nil, "sit", } m["sit-tma"] = { "Tangkhul-Maring", nil, "sit", } m["sit-tng"] = { "Tangkhulic", 1516657, "sit-tma", aliases = {"Tangkhul"}, } m["sit-tno"] = { "Tangsa-Nocte", nil, "sit-kon", } m["sit-tsk"] = { "Tshangla", nil, "sit", } m["sit-wgy"] = { "West rGyalrongic", nil, "sit-rgy" } m["sit-whm"] = { "West Himalayish", 2301695, "sit", } m["sit-zem"] = { "Zeme", 189291, "sit", aliases = {"Zeliangrong", "Zemeic"}, } m["sla"] = { "Slavic", 23526, "ine-bsl", aliases = {"Slavonic"}, } m["smi"] = { "Sami", 56463, "urj", aliases = {"Saami", "Samic", "Saamic"}, } m["son"] = { "Songhay", 505198, "ssa", aliases = {"Songhai"}, } m["sqj"] = { "Albanian", 8748, "ine", } m["ssa"] = { "Nilo-Saharan", -- possibly not a genetic grouping 33705, } m["ssa-fur"] = { "Fur", 2989512, "ssa", } m["ssa-klk"] = { "Kuliak", 1791476, "ssa", aliases = {"Rub"}, } m["ssa-kom"] = { "Koman", 1781084, "ssa", } m["ssa-sah"] = { "Saharan", 1757661, "ssa", } m["syd"] = { "Samoyedic", 34005, "urj", aliases = {"Samoyed", "Samodeic"}, } m["syd-ene"] = { "Enets", 29942, "syd", } m["tai"] = { "Tai", 749720, "qfa-bet", aliases = {"Daic"}, } m["tai-wen"] = { "Wenma-Southwestern Tai", nil, "tai", } m["tai-tay"] = { "Tày", nil, "tai-wen", } m["tai-sap"] = { "Sapa-Southwestern Tai", nil, "tai-wen", aliases = {"Sapa-Thai"}, } m["tai-swe"] = { "Southwestern Tai", 10889250, "tai-sap", } m["tai-cho"] = { "Chongzuo Tai", 13216, "tai", } m["tai-cen"] = { "Central Tai", 5061891, "tai", } m["tai-nor"] = { "Northern Tai", 7059014, "tai", } m["tbq"] = { "Tibeto-Burman", 34064, "sit", } m["tbq-anp"] = { "Angami-Pochuri", 530460, "sit", } m["tbq-axi"] = { "Axioid", nil, "tbq-sel", } m["tbq-bdg"] = { "Bodo-Garo", 4090000, "tbq-bkj", } m["tbq-bis"] = { "Bisoid", 48844742, "tbq-slo", } m["tbq-bka"] = { "Bi-Ka", 12627890, "tbq-slo", } m["tbq-bkj"] = { "Sal", 889900, "sit", -- Brahmaputran appears to be Glottolog's term aliases = {"Bodo-Konyak-Jinghpaw", "Brahmaputran", "Jingpho-Konyak-Bodo"}, } m["tbq-brm"] = { "Burmish", 865713, "tbq-lob", } m["tbq-buq"] = { "Burmo-Qiangic", 16056278, "sit", aliases = {"Eastern Tibeto-Burman"}, } m["tbq-drp"] = { "Downriver Phula", 7188378, "tbq-rph", } m["tbq-han"] = { "Hanoid", 17004185, "tbq-slo", } m["tbq-hph"] = { "Highland Phula", nil, "tbq-sel", } m["tbq-jin"] = { "Jino", 6202716, "tbq-slo", } m["tbq-kzh"] = { "Kazhuoish", 48834669, "tbq-lol", } m["tbq-kuk"] = { "Kuki-Chin", 832413, "sit", aliases = {"Kukish", "South-Central Tibeto-Burman"}, } m["tbq-lal"] = { "Lalo", 56548, "tbq-lso", } m["tbq-lho"] = { "Lahoish", nil, "tbq-lol", } m["tbq-llo"] = { "Lipo-Lolopo", nil, "tbq-lso", } m["tbq-lob"] = { "Lolo-Burmese", 1635712, "tbq-buq", } m["tbq-lol"] = { "Loloish", 37035, "tbq-lob", aliases = {"Yi", "Ngwi", "Nisoic"}, } m["tbq-lso"] = { "Lisoish", 6559055, "tbq-lol", } m["tbq-lwo"] = { "Lawoish", 48847673, "tbq-lol", } m["tbq-muj"] = { "Muji", 11221327, "tbq-hph", } m["tbq-nas"] = { "Nasoid", nil, "tbq-nlo", } m["tbq-nis"] = { "Nisu", 56404, "tbq-nlo", } m["tbq-nlo"] = { "Northern Loloish", 7058676, "tbq-nso", } m["tbq-nso"] = { "Nisoish", 56990, "tbq-lol", } m["tbq-nus"] = { "Nusoish", 114245231, "tbq-lol", } m["tbq-phw"] = { "Phowa", 7187959, "tbq-hph", } m["tbq-rph"] = { "Riverine Phula", nil, "tbq-sel", } m["tbq-sel"] = { "Southeastern Loloish", 16111894, "tbq-nso", } m["tbq-sil"] = { "Siloid", 60787071, "tbq-slo", } m["tbq-slo"] = { "Southern Loloish", 5649340, "tbq-lol", } m["tbq-tal"] = { "Taloid", 48804018, "tbq-lso", } m["tbq-urp"] = { "Upriver Phula", 7187058, "tbq-rph", } m["trk"] = { "Turkic", 34090, } m["trk-cmn"] = { "Common Turkic", 1126028, "trk", aliases = {"Shaz Turkic", "Shaz-Turkic"}, } m["trk-kar"] = { "Karluk", 703173, "trk-cmn", aliases = {"Qarluq", "Uyghur-Uzbek", "Southeastern Turkic"}, } m["trk-kbu"] = { "Kipchak-Bulgar", 3512539, "trk-kip", aliases = {"Uralian", "Uralo-Caspian"}, } m["trk-kcu"] = { "Kipchak-Cuman", 4370412, "trk-kip", aliases = {"Ponto-Caspian"}, } m["trk-kip"] = { "Kipchak", 1339898, "trk-cmn", -- Russian Wikipedia article [[w:ru:Западнотюркские_языки]] says "Western Turkic" is used by N.A. Baskakov and includes Oghuz, Kipchak and Karluk. -- Azerbaijani Wikipedia article [[w:az:Qərbi_türk_dilləri]] clarifies that "Western Turkic" is not a clade. other_names = {"Western Turkic"}, aliases = {"Kypchak", "Qypchaq", "Northwestern Turkic"}, protoLanguage = "qwm", } m["trk-kkp"] = { "Kyrgyz-Kipchak", 4221189, "trk-kip", } m["trk-kno"] = { "Kipchak-Nogai", 4326954, "trk-kip", aliases = {"Aralo-Caspian"}, } m["trk-nsb"] = { "North Siberian Turkic", 4537269, "trk-sib", aliases = {"Northern Siberian Turkic"}, } m["trk-ogr"] = { "Oghur", 1422731, "trk", aliases = {"Lir-Turkic", "r-Turkic"}, } m["trk-ogz"] = { "Oghuz", 494600, "trk-cmn", aliases = {"Southwestern Turkic"}, } m["trk-sib"] = { "Siberian Turkic", 354353, "trk-cmn", other_names = {"Northern Turkic"}, -- per [[w:ru:Восточнотюркские_языки]], "Eastern Turkic" is an alias for Siberian Turkic in the work of O.A. Mudrak, -- but has a different non-clade meaning in the older work of N.A. Baskakov. aliases = {"Eastern Turkic", "Northeastern Turkic"}, } m["trk-ssb"] = { "South Siberian Turkic", nil, "trk-sib", aliases = {"Southern Siberian Turkic"}, } m["tup"] = { "Tupian", 34070, aliases = {"Tupi"}, } m["tup-gua"] = { "Tupi-Guarani", 148610, "tup", aliases = {"Tupí-Guaraní"}, } m["tuw"] = { "Tungusic", 34230, aliases = {"Manchu-Tungus", "Tungus"}, } m["tuw-ewe"] = { "Ewenic", 105889448, "tuw", aliases = {"Northern Tungusic"}, } m["tuw-jrc"] = { "Jurchenic", 105889432, "tuw", aliases = {"Manchuric"}, } m["tuw-nan"] = { "Nanaic", 105889264, "tuw", } m["tuw-udg"] = { "Udegheic", 105889266, "tuw", } m["urj"] = { "Uralic", 34113, varieties = {"Finno-Ugric"}, } m["urj-fin"] = { "Finnic", 33328, "urj", aliases = {"Baltic-Finnic", "Balto-Finnic", "Fennic"}, } m["urj-mdv"] = { "Mordvinic", 627313, "urj", } m["urj-prm"] = { "Permic", 161493, "urj", } m["urj-ugr"] = { "Ugric", 156631, "urj", } m["wak"] = { "Wakashan", 60069, } m["wen"] = { "Sorbian", 25442, "zlw", aliases = {"Lusatian", "Wendish"}, } m["xgn"] = { "Mongolic", 33750, "qfa-xgs", aliases = {"Mongolian"}, } m["xgn-cen"] = { "Central Mongolic", 28719447, "xgn", protoLanguage = "xng-lat", } m["xgn-sou"] = { "Southern Mongolic", nil, "xgn", protoLanguage = "xng-ear", } m["xgn-shr"] = { "Shirongolic", 107539435, "xgn-sou", } m["xme"] = { "Median", nil, "ira-mpr", protoLanguage = "xme-old", } m["xme-ttc"] = { "Tatic", nil, "xme", } m["xnd"] = { "Na-Dene", 26986, "qfa-dny", aliases = {"Na-Dené"}, } m["xsc"] = { "Scythian", nil, "ira-nei", } m["xsc-sak"] = { "Saka", nil, "xsc-skw", aliases = {"Sakan"}, } m["xsc-sar"] = { "Sarmatian", nil, "xsc", } m["xsc-skw"] = { "Saka-Wakhi", nil, "xsc", } m["yok"] = { "Yokuts", 34249, "nai-you", aliases = {"Yokutsan", "Mariposan", "Mariposa"}, } m["ypk"] = { "Yupik", 27970, "esx-esk", aliases = {"Yup'ik", "Yuit"}, } m["yrk"] = { "Nenets", 36452, "syd", } m["zhx"] = { "Sinitic", 33857, "sit-sba", aliases = {"Chinese"}, protoLanguage = "och", } m["zhx-com"] = { "Coastal Min", 20667215, "zhx-min", } m["zhx-inm"] = { "Inland Min", 20667237, "zhx-min", } m["zhx-man"] = { "Mandarinic", nil, "zhx", protoLanguage = "cmn-ear", } m["zhx-min"] = { "Min", 56504, "zhx", } m["zhx-nan"] = { "Southern Min", 36495, "zhx-com", } m["zhx-pin"] = { "Pinghua", 2735715, "zhx", protoLanguage = "ltc", } m["zhx-yue"] = { "Yue", 7033959, "zhx", protoLanguage = "ltc", } m["zle"] = { "East Slavic", 144713, "sla", } m["zls"] = { "South Slavic", 146665, "sla", } m["zlw"] = { "West Slavic", 145852, "sla", } m["zlw-lch"] = { "Lechitic", 742782, "zlw", aliases = {"Lekhitic"}, } m["zlw-pom"] = { "Pomeranian", nil, "zlw-lch", } m["znd"] = { "Zande", 8066072, "nic-ubg", } return require("Module:languages").finalizeData(m, "family") 6r9698ry2dh0nimqax8wgv04joz7tvi 10 6400 231372 32072 2025-12-22T21:06:56Z en>Benwing2 0 update link_tr documentation 231372 wikitext text/x-wiki {{language data search}} This module contains definitions and metadata for {{#switch:{{#titleparts:{{PAGENAME}}|1|3}}|2='''two-letter language codes'''|3='''three-letter language codes''' starting with <code>{{#titleparts:{{PAGENAME}}|1|4}}</code>|exceptional='''exceptional''' language codes: those that consist of two- or three-letter sequences separated by hyphens|#default=language codes}}. See [[Wiktionary:Languages]] for more information. This module '''must not''' be used directly in other modules or templates. The data should be accessed through [[Module:languages]]. {{#ifeq:{{NAMESPACENUMBER}}|828|For the corresponding extra data, see [[{{FULLPAGENAME}}/extra]].}} ==Errors== {{language data consistency check}} ==Required values== Every entry in the table must contain the following indexed fields: ; <code>1</code> : The "canonical" name of the language. This is the name that is used in Wiktionary entries and category names. ; <code>2</code> : The Wikidata item ID (Q number) for the language. Must be specified as a number (a positive integer). Set to <code>nil</code> if not known/present. This replaces the older <code>wikipedia_article</code> property, which can still be used to link to specific sections or language editions. ==Optional values== ; <code>3</code> : The code for the family that the language belongs to. See [[Wiktionary:Families]]. ; <code>4</code> : A list of script codes. See [[Wiktionary:Scripts]]. These represent all the scripts (writing systems) that this language uses in the real world, as well as the ones that Wiktionary uses. The scripts that are used most often on Wiktionary should be first in the list, as this will speed up script detection. : Many templates and modules detect the script of text in a particular language using the {{code|lua|Language:findBestScript}} method in [[Module:languages]]. This function goes down the list of scripts and counts how many characters in the text belong to each script. If all the characters belong to one script, that script will be returned; otherwise, the script with the most characters will be returned. Thus, script detection will be faster if the most frequently used scripts are first in the list. If none of the characters match any of the listed scripts, then the <code>None</code> script is returned (even if the characters would match a script not listed). Translingual (<code>mul</code>) and Undetermined (<code>und</code>) have the special value {{code|lua|"All"}}, which means they are treated as having every script. This value should not be set for any other language codes. : Due to the [[WT:Lua memory errors|ongoing problems with Lua memory limits]], this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: {{code|lua|"Latn, Brai, Shaw, Dsrt"}}. ; <code>type</code> : The type of language (which affects how it is handled on Wiktionary). Possible values are: :* <code>regular</code> - This value is the default, so it doesn't need to be specified. It indicates that the is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the Reconstruction namespace and must be prefixed with * to indicate a reconstruction. :* <code>reconstructed</code> - This language is not attested according to CFI, and therefore is allowed only in the Reconstruction namespace. All terms in this language are reconstructed, and must be prefixed with *. :* <code>appendix-constructed</code> - This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. ; <code>ancestors</code> : A list of the language codes of the direct ancestors of this language. For example, the ancestor of English is listed as <code>enm</code> (Middle English); <code>ang</code> (Old English, the ancestor of Middle English), <code>gem-pro</code> (Proto-Germanic, the ancestor of Old English){{,}} and <code>ine-pro</code> (Proto-Indo-European, the ancestor of Proto-Germanic) are not listed. : For most languages, only one ancestor code should be given, but multiple ancestors can be listed for pidgins, creoles and mixed languages. : The ancestor language list should not be included if the language's direct ancestor is the proto-language of the family to which the language belongs. In such a case, if the family code has been provided, [[Module:languages]] will automatically add the proto-language as the language's ancestor. For example, Proto-Germanic (<code>gem-pro</code>) belongs to the Indo-European (<code>ine</code>) family, and its direct ancestor is Proto-Indo-European (<code>ine-pro</code>). Because Proto-Indo-European is the proto-language of the Indo-European languages, Proto-Germanic does not need an <code>ancestors</code> table; Proto-Indo-European will be automatically returned as its ancestor by the {{code|lua|getAncestors}} function. : Due to the [[WT:Lua memory errors|ongoing problems with Lua memory limits]], this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: {{code|lua|"cr, fr"}}. ; <code>wikimedia_codes</code> : A list of the [[Wiktionary:Wikimedia language codes|Wikimedia language codes]] that this language maps to. This is used to translate Wiktionary codes to Wikimedia codes, which are usually the same but there are a few languages where it is different. The language codes must be valid Wikimedia codes (as determined by the wiki software), and if they are not defined in one of the language data modules, they must be defined in [[Module:wikimedia languages/data]]. : Due to the [[WT:Lua memory errors|ongoing problems with Lua memory limits]], this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: {{code|lua|"en, simple"}}. : Note that Wikimedia <-> Wiktionary language codes are currently defined in four places: the language modules (as documented here); [[Module:wikimedia languages/data]]; {{code||interwiki_langs}} in [[Module:translations/data]]; and the {{code||wiktprefix}} field of the `metadata` variable in [[MediaWiki:Gadget-TranslationAdder-Data.js]]. FIXME: Unify this data. ; <code>wikipedia_article</code> : The name of the Wikipedia article for the language. Should normally only be supplied if the Wikidata id cannot be used. ; <code>translit</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines how a language should be transliterated, which will be automatically applied to any terms in scripts that do not have their <code>isTransliterated</code> value set to {{code|lua|false}} in [[Module:scripts/data]]. This is used by <code>transliterate</code> in [[Module:languages]]. ; <code>link_tr</code> : Set this to <code>true</code> to link the language's transliteration in headwords. This can also be a comma-separated list of script codes, which means that links are only applied to terms using those scripts. Note that transliterations are not linked in links other than headwords (those generated using {{cd|full_link()}} in [[Module:links]]) unless the {{cd|respect_link_tr}} flag is set in {{cd|full_link()}}'s data structure. ; <code>override_translit</code> : Set this to <code>true</code> to make the automatic transliteration override an any given manual transliteration. Otherwise, this can be a comma-separated list of script codes, which means that the override is only applied to terms using those scripts. ; <code>display_text</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines replacements to create the display form of the text, which is the form actually displayed on the page. This is occasionally necessary if there is a recurring issue of editors adding the wrong character, which is sometimes an issue when two or more characters are easy to confuse. For example, the palochka <code>ӏ</code>, used in Cyrillic in many Caucasian languages, is frequently entered as <code>I</code>, or even Latin <code>l</code> or <code>I</code>. As this is an ongoing issue (even among native speakers), the easiest way to solve the problem is to automatically correct the display form for those languages. This is used by <code>makeDisplayText</code> in [[Module:languages]]. ; <code>strip_diacritics</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines replacements to strip diacritics from the displayed form of a term in order to get the logical pagename. This is typically used to remove certain diacritical marks according to the customs or standard practice of the language. For example, it is used to remove accent marks from Russian words (<code>ру́сский</code> &rarr; <code>русский</code>), and macrons from Latin and Old English words (<code>ōs</code> &rarr; <code>os</code>), as these are not used in the normal written form of these languages. This is used by <code>stripDiacritics</code> in [[Module:languages]]. ; <code>sort_key</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines replacements to create a category sort key from the page name. The purpose is to: :# Remove any characters that should be ignored in sorting. :# Replace characters with other characters, if the sorting rules for that language do not distinguish them. For example, in German, the characters "ä" and "a" are considered equivalent for sorting, and are both treated as "a". :# Replace characters that should be sorted in different places with special characters that mimic that behaviour, (which is necessary due to MediaWiki software using the Unicode codepoint to determine sort order, which is often arbitrary). For instance, in Mongolian, the letter "ү" should be sorted after "у", but due to its codepoint it is sorted after the final letter "я" by default. As such, we can replace "ү" with "у" plus a character with a very high codepoint, which ensures that it is always sorted straight after. The data modules contain an in-built way to do this for the sake of convenience: with the above example, this would be done by using {{code|lua|"у" .. p[1]}}. Another character could be inserted straight after by using {{code|lua|"у" .. p[2]}} (and so on). : Note: the term is converted to lowercase before applying any substitutions, so you should not try to process capital letters (as it will not work). This is used by <code>makeSortKey</code> in [[Module:languages]]. ; <code>dotted_dotless_i</code> : Set this to <code>true</code> for languages that distinguish between the {{w|Dotted and dotless I in computing|dotted and dotless I}} (such as some Turkic languages). ==Substitutions== : {{code|lua|translit}}, {{code|lua|display_text}}, {{code|lua|strip_diacritics}} and {{code|lua|sort_key}} all use the same syntax, which is designed to be as flexible as possible: :* If they are a string, then this is treated as the name of a dedicated module which will be used to generate the output. For example, {{code|lua|"sa-translit"}} refers to [[Module:sa-translit]]. :* If they are a table, then it can contain two kinds of keys: :*# The keys {{code|lua|from}}, {{code|lua|to}}, {{code|lua|remove_diacritics}} and {{code|lua|remove_exceptions}} relate to text substitution (see below). :*# Script code keys are used to specify script-specific behaviour. These, in turn, can be strings (for dedicated modules) or tables (for text substitution). In addition, a value with the key {{code|Lua|1}} can be used as a fallback, which will be used if no specific behaviour is defined for that script. :: Note: if script keys and text substitution keys are given in the same table, then the text substitution will be applied after the script-specific behaviour has completed. Ensure any fallback text substitutions are given as a subtable with key {{code|Lua|1}} if you want to avoid this. It is not possible to process the output of a script-specific module with another module, however: this should be done (for example) with a [[tail call]] in the first module. : Dedicated modules must take the arguments {{code|lua|text, lang, sc}}, where {{code|lua|text}} is the input text (usually the page name or input by the user), {{code|lua|lang}} is the language code (not the language object), and {{code|lua|sc}} is the script code (not the script object). For performance reasons, they should <u>only</u> be used when it is not possible to achieve the desired result via text substitution. : Text substitution replaces or removes certain characters (or sets of characters) for particular contexts. There are three ways to do this: :# Using the {{code|lua|from}} and {{code|lua|to}} keys. :# {{code|lua|remove_diacritics}} (and optionally {{code|lua|remove_exceptions}}). :# Both of the above (in that order). : {{code|lua|from}} is paired with {{code|lua|to}}, and both of them must be tables that are organised pairwise: each element in {{code|lua|from}} is a pattern to identify which characters in the term to replace, while the corresponding element in {{code|lua|to}} defines what to replace them with (as arguments to [[mw:Extension:Scribunto/Lua_reference_manual#mw.ustring.gsub|{{code|lua|mw.ustring.gsub}}]]). : If the replacement is not present (or if it is {{code|lua|false}} or {{code|lua|nil}}), then any matching characters are removed altogether. This means that the {{code|lua|from}} list can be longer than the {{code|lua|to}} list, and an empty replacement will be assumed for any elements in {{code|lua|from}} that have no counterpart in {{code|lua|to}}. : The tables can contain literal characters, or the patterns (a simplified form [[regular expression]]s) that are used by the standard Scribunto [[mw:Extension:Scribunto/Lua reference manual#mw.ustring.gsub|{{code|lua|mw.ustring.gsub}}]] function. See [[mw:Extension:Scribunto/Lua reference manual#Patterns|the Scribunto reference manual]] for more information. Note that patterns make double substitutions a viable way to achieve more complex results. See the Latin sortkey for Mandarin (<code>cmn</code>) as an example of this. : {{code|lua|remove_diacritics}} is a string which contains characters that will be removed after the text is decomposed. For instance, if {{code|lua|remove_diacritics}} is a combining acute accent, all acute accents will be stripped, even if they are part of precomposed characters (such as {{l|mul|á}} or {{l|mul|ά|tr=-}}). Despite the name, the characters to be stripped need not be diacritics: for instance, including an apostrophe would remove all apostrophes (though be careful with hyphens, which must be be [[mw:Extension:Scribunto/Lua_reference_manual#Patterns|escaped]] as {{code|lua|%-}}). : Furthermore, if {{code|lua|remove_diacritics}} is given, then it is possible to specify a {{code|lua|remove_exceptions}} table, which prevents specific characters from having their diacritics stripped. For instance, if {{code|lua|remove_diacritics}} is a combining diaeresis, but {{code|lua|remove_exceptions}} contains {{code|lua|"ё"}}, then any instances of <code>ё</code> will remain unchanged. On the other hand, an instance of <code>ӱ</code> would still become <code>у</code> (unless {{code|lua|"ӱ"}} is also added to {{code|lua|remove_exceptions}}). : If no value is specified for a given field, or a table of script-specific values is given but there is no value for the script in question and no {{code|lua|from}}/{{code|lua|to}} or {{code|lua|remove_diacritics}} fields, the script will be checked for a script-wide fallback, which uses the same data format. This is used, for example, to supply a script-wide sort key module for Ethiopic in lieu of specifying the same value for all languages that have Ethiopic as their script (or one of their scripts). == Formerly supported values == ; <code>aliases</code>, <code>varieties</code>, <code>otherNames</code> : This data is now located in the extra data modules; see [[Module:languages]] and [[Template:language extradata documentation]]. ; <code>family</code> : Now <code>3</code>. ; <code>scripts</code> : Now <code>4</code>. <!-- --><noinclude>{{documentation}}</noinclude> qbb4dm3a85l7k71o302ii0rcj3gm0g7 231373 231372 2026-04-14T07:31:39Z Lee 19 [[:en:Template:language_data_documentation]] වෙතින් එක් සංශෝධනයක් 231372 wikitext text/x-wiki {{language data search}} This module contains definitions and metadata for {{#switch:{{#titleparts:{{PAGENAME}}|1|3}}|2='''two-letter language codes'''|3='''three-letter language codes''' starting with <code>{{#titleparts:{{PAGENAME}}|1|4}}</code>|exceptional='''exceptional''' language codes: those that consist of two- or three-letter sequences separated by hyphens|#default=language codes}}. See [[Wiktionary:Languages]] for more information. This module '''must not''' be used directly in other modules or templates. The data should be accessed through [[Module:languages]]. {{#ifeq:{{NAMESPACENUMBER}}|828|For the corresponding extra data, see [[{{FULLPAGENAME}}/extra]].}} ==Errors== {{language data consistency check}} ==Required values== Every entry in the table must contain the following indexed fields: ; <code>1</code> : The "canonical" name of the language. This is the name that is used in Wiktionary entries and category names. ; <code>2</code> : The Wikidata item ID (Q number) for the language. Must be specified as a number (a positive integer). Set to <code>nil</code> if not known/present. This replaces the older <code>wikipedia_article</code> property, which can still be used to link to specific sections or language editions. ==Optional values== ; <code>3</code> : The code for the family that the language belongs to. See [[Wiktionary:Families]]. ; <code>4</code> : A list of script codes. See [[Wiktionary:Scripts]]. These represent all the scripts (writing systems) that this language uses in the real world, as well as the ones that Wiktionary uses. The scripts that are used most often on Wiktionary should be first in the list, as this will speed up script detection. : Many templates and modules detect the script of text in a particular language using the {{code|lua|Language:findBestScript}} method in [[Module:languages]]. This function goes down the list of scripts and counts how many characters in the text belong to each script. If all the characters belong to one script, that script will be returned; otherwise, the script with the most characters will be returned. Thus, script detection will be faster if the most frequently used scripts are first in the list. If none of the characters match any of the listed scripts, then the <code>None</code> script is returned (even if the characters would match a script not listed). Translingual (<code>mul</code>) and Undetermined (<code>und</code>) have the special value {{code|lua|"All"}}, which means they are treated as having every script. This value should not be set for any other language codes. : Due to the [[WT:Lua memory errors|ongoing problems with Lua memory limits]], this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: {{code|lua|"Latn, Brai, Shaw, Dsrt"}}. ; <code>type</code> : The type of language (which affects how it is handled on Wiktionary). Possible values are: :* <code>regular</code> - This value is the default, so it doesn't need to be specified. It indicates that the is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the Reconstruction namespace and must be prefixed with * to indicate a reconstruction. :* <code>reconstructed</code> - This language is not attested according to CFI, and therefore is allowed only in the Reconstruction namespace. All terms in this language are reconstructed, and must be prefixed with *. :* <code>appendix-constructed</code> - This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. ; <code>ancestors</code> : A list of the language codes of the direct ancestors of this language. For example, the ancestor of English is listed as <code>enm</code> (Middle English); <code>ang</code> (Old English, the ancestor of Middle English), <code>gem-pro</code> (Proto-Germanic, the ancestor of Old English){{,}} and <code>ine-pro</code> (Proto-Indo-European, the ancestor of Proto-Germanic) are not listed. : For most languages, only one ancestor code should be given, but multiple ancestors can be listed for pidgins, creoles and mixed languages. : The ancestor language list should not be included if the language's direct ancestor is the proto-language of the family to which the language belongs. In such a case, if the family code has been provided, [[Module:languages]] will automatically add the proto-language as the language's ancestor. For example, Proto-Germanic (<code>gem-pro</code>) belongs to the Indo-European (<code>ine</code>) family, and its direct ancestor is Proto-Indo-European (<code>ine-pro</code>). Because Proto-Indo-European is the proto-language of the Indo-European languages, Proto-Germanic does not need an <code>ancestors</code> table; Proto-Indo-European will be automatically returned as its ancestor by the {{code|lua|getAncestors}} function. : Due to the [[WT:Lua memory errors|ongoing problems with Lua memory limits]], this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: {{code|lua|"cr, fr"}}. ; <code>wikimedia_codes</code> : A list of the [[Wiktionary:Wikimedia language codes|Wikimedia language codes]] that this language maps to. This is used to translate Wiktionary codes to Wikimedia codes, which are usually the same but there are a few languages where it is different. The language codes must be valid Wikimedia codes (as determined by the wiki software), and if they are not defined in one of the language data modules, they must be defined in [[Module:wikimedia languages/data]]. : Due to the [[WT:Lua memory errors|ongoing problems with Lua memory limits]], this should be given as a comma-separated list in a string (and not a table). This is then converted into a table when returned. For example: {{code|lua|"en, simple"}}. : Note that Wikimedia <-> Wiktionary language codes are currently defined in four places: the language modules (as documented here); [[Module:wikimedia languages/data]]; {{code||interwiki_langs}} in [[Module:translations/data]]; and the {{code||wiktprefix}} field of the `metadata` variable in [[MediaWiki:Gadget-TranslationAdder-Data.js]]. FIXME: Unify this data. ; <code>wikipedia_article</code> : The name of the Wikipedia article for the language. Should normally only be supplied if the Wikidata id cannot be used. ; <code>translit</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines how a language should be transliterated, which will be automatically applied to any terms in scripts that do not have their <code>isTransliterated</code> value set to {{code|lua|false}} in [[Module:scripts/data]]. This is used by <code>transliterate</code> in [[Module:languages]]. ; <code>link_tr</code> : Set this to <code>true</code> to link the language's transliteration in headwords. This can also be a comma-separated list of script codes, which means that links are only applied to terms using those scripts. Note that transliterations are not linked in links other than headwords (those generated using {{cd|full_link()}} in [[Module:links]]) unless the {{cd|respect_link_tr}} flag is set in {{cd|full_link()}}'s data structure. ; <code>override_translit</code> : Set this to <code>true</code> to make the automatic transliteration override an any given manual transliteration. Otherwise, this can be a comma-separated list of script codes, which means that the override is only applied to terms using those scripts. ; <code>display_text</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines replacements to create the display form of the text, which is the form actually displayed on the page. This is occasionally necessary if there is a recurring issue of editors adding the wrong character, which is sometimes an issue when two or more characters are easy to confuse. For example, the palochka <code>ӏ</code>, used in Cyrillic in many Caucasian languages, is frequently entered as <code>I</code>, or even Latin <code>l</code> or <code>I</code>. As this is an ongoing issue (even among native speakers), the easiest way to solve the problem is to automatically correct the display form for those languages. This is used by <code>makeDisplayText</code> in [[Module:languages]]. ; <code>strip_diacritics</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines replacements to strip diacritics from the displayed form of a term in order to get the logical pagename. This is typically used to remove certain diacritical marks according to the customs or standard practice of the language. For example, it is used to remove accent marks from Russian words (<code>ру́сский</code> &rarr; <code>русский</code>), and macrons from Latin and Old English words (<code>ōs</code> &rarr; <code>os</code>), as these are not used in the normal written form of these languages. This is used by <code>stripDiacritics</code> in [[Module:languages]]. ; <code>sort_key</code> : <small>''See the [[#Substitutions|Substitutions]] section for instructions on syntax.''</small> : Defines replacements to create a category sort key from the page name. The purpose is to: :# Remove any characters that should be ignored in sorting. :# Replace characters with other characters, if the sorting rules for that language do not distinguish them. For example, in German, the characters "ä" and "a" are considered equivalent for sorting, and are both treated as "a". :# Replace characters that should be sorted in different places with special characters that mimic that behaviour, (which is necessary due to MediaWiki software using the Unicode codepoint to determine sort order, which is often arbitrary). For instance, in Mongolian, the letter "ү" should be sorted after "у", but due to its codepoint it is sorted after the final letter "я" by default. As such, we can replace "ү" with "у" plus a character with a very high codepoint, which ensures that it is always sorted straight after. The data modules contain an in-built way to do this for the sake of convenience: with the above example, this would be done by using {{code|lua|"у" .. p[1]}}. Another character could be inserted straight after by using {{code|lua|"у" .. p[2]}} (and so on). : Note: the term is converted to lowercase before applying any substitutions, so you should not try to process capital letters (as it will not work). This is used by <code>makeSortKey</code> in [[Module:languages]]. ; <code>dotted_dotless_i</code> : Set this to <code>true</code> for languages that distinguish between the {{w|Dotted and dotless I in computing|dotted and dotless I}} (such as some Turkic languages). ==Substitutions== : {{code|lua|translit}}, {{code|lua|display_text}}, {{code|lua|strip_diacritics}} and {{code|lua|sort_key}} all use the same syntax, which is designed to be as flexible as possible: :* If they are a string, then this is treated as the name of a dedicated module which will be used to generate the output. For example, {{code|lua|"sa-translit"}} refers to [[Module:sa-translit]]. :* If they are a table, then it can contain two kinds of keys: :*# The keys {{code|lua|from}}, {{code|lua|to}}, {{code|lua|remove_diacritics}} and {{code|lua|remove_exceptions}} relate to text substitution (see below). :*# Script code keys are used to specify script-specific behaviour. These, in turn, can be strings (for dedicated modules) or tables (for text substitution). In addition, a value with the key {{code|Lua|1}} can be used as a fallback, which will be used if no specific behaviour is defined for that script. :: Note: if script keys and text substitution keys are given in the same table, then the text substitution will be applied after the script-specific behaviour has completed. Ensure any fallback text substitutions are given as a subtable with key {{code|Lua|1}} if you want to avoid this. It is not possible to process the output of a script-specific module with another module, however: this should be done (for example) with a [[tail call]] in the first module. : Dedicated modules must take the arguments {{code|lua|text, lang, sc}}, where {{code|lua|text}} is the input text (usually the page name or input by the user), {{code|lua|lang}} is the language code (not the language object), and {{code|lua|sc}} is the script code (not the script object). For performance reasons, they should <u>only</u> be used when it is not possible to achieve the desired result via text substitution. : Text substitution replaces or removes certain characters (or sets of characters) for particular contexts. There are three ways to do this: :# Using the {{code|lua|from}} and {{code|lua|to}} keys. :# {{code|lua|remove_diacritics}} (and optionally {{code|lua|remove_exceptions}}). :# Both of the above (in that order). : {{code|lua|from}} is paired with {{code|lua|to}}, and both of them must be tables that are organised pairwise: each element in {{code|lua|from}} is a pattern to identify which characters in the term to replace, while the corresponding element in {{code|lua|to}} defines what to replace them with (as arguments to [[mw:Extension:Scribunto/Lua_reference_manual#mw.ustring.gsub|{{code|lua|mw.ustring.gsub}}]]). : If the replacement is not present (or if it is {{code|lua|false}} or {{code|lua|nil}}), then any matching characters are removed altogether. This means that the {{code|lua|from}} list can be longer than the {{code|lua|to}} list, and an empty replacement will be assumed for any elements in {{code|lua|from}} that have no counterpart in {{code|lua|to}}. : The tables can contain literal characters, or the patterns (a simplified form [[regular expression]]s) that are used by the standard Scribunto [[mw:Extension:Scribunto/Lua reference manual#mw.ustring.gsub|{{code|lua|mw.ustring.gsub}}]] function. See [[mw:Extension:Scribunto/Lua reference manual#Patterns|the Scribunto reference manual]] for more information. Note that patterns make double substitutions a viable way to achieve more complex results. See the Latin sortkey for Mandarin (<code>cmn</code>) as an example of this. : {{code|lua|remove_diacritics}} is a string which contains characters that will be removed after the text is decomposed. For instance, if {{code|lua|remove_diacritics}} is a combining acute accent, all acute accents will be stripped, even if they are part of precomposed characters (such as {{l|mul|á}} or {{l|mul|ά|tr=-}}). Despite the name, the characters to be stripped need not be diacritics: for instance, including an apostrophe would remove all apostrophes (though be careful with hyphens, which must be be [[mw:Extension:Scribunto/Lua_reference_manual#Patterns|escaped]] as {{code|lua|%-}}). : Furthermore, if {{code|lua|remove_diacritics}} is given, then it is possible to specify a {{code|lua|remove_exceptions}} table, which prevents specific characters from having their diacritics stripped. For instance, if {{code|lua|remove_diacritics}} is a combining diaeresis, but {{code|lua|remove_exceptions}} contains {{code|lua|"ё"}}, then any instances of <code>ё</code> will remain unchanged. On the other hand, an instance of <code>ӱ</code> would still become <code>у</code> (unless {{code|lua|"ӱ"}} is also added to {{code|lua|remove_exceptions}}). : If no value is specified for a given field, or a table of script-specific values is given but there is no value for the script in question and no {{code|lua|from}}/{{code|lua|to}} or {{code|lua|remove_diacritics}} fields, the script will be checked for a script-wide fallback, which uses the same data format. This is used, for example, to supply a script-wide sort key module for Ethiopic in lieu of specifying the same value for all languages that have Ethiopic as their script (or one of their scripts). == Formerly supported values == ; <code>aliases</code>, <code>varieties</code>, <code>otherNames</code> : This data is now located in the extra data modules; see [[Module:languages]] and [[Template:language extradata documentation]]. ; <code>family</code> : Now <code>3</code>. ; <code>scripts</code> : Now <code>4</code>. <!-- --><noinclude>{{documentation}}</noinclude> qbb4dm3a85l7k71o302ii0rcj3gm0g7 828 7905 231379 220206 2026-02-08T02:41:46Z en>Benwing2 0 +lzh for use in finding places where it should say "Literary Chinese"; remove uun as the splitting is done per [[User:-sche]] 231379 Scribunto text/plain local export = {} -- We can't use mw.loadData() on [[Module:languages/chars]] because [[Module:languages/data]] itself is sometimes loaded -- using mw.loadData(), and calling mw.loadData() on [[Module:languages/chars]] will insert metatables into the -- character tables, which the second mw.loadData() will choke on. local m_chars = require("Module:languages/chars") local u = require("Module:string/char") local c = m_chars.chars export.chars = c local p = m_chars.puaChars export.puaChars = p local cs = m_chars.chars_substitutions export.chars_substitutions = cs -- FIXME! Many of the script-specific values below can be moved to [[Module:scripts/data]] to serve as script-wide -- fallback values instead of specifying them for each language using the script. local s = {} -- These values are placed here to make it possible to synchronise a group of languages without the need for a dedicated function module. -- cau do local cau_remove_diacritics = c.grave .. c.acute .. c.macron local cau_from = {"[IlΙІӀᴴ]"} local cau_to = {{ ["l"] = "ӏ", ["Ι"] = "ӏ", ["І"] = "ӏ", ["Ӏ"] = "ӏ", ["ᴴ"] = "ᵸ", }} s["cau-Cyrl-displaytext"] = { from = cau_from, to = cau_to, } s["cau-Cyrl-stripdiacritics"] = { remove_diacritics = cau_remove_diacritics, from = cau_from, to = cau_to, } s["cau-Latn-stripdiacritics"] = {remove_diacritics = cau_remove_diacritics} end s["itc-Latn-displaytext"] = { from = {c.caron}, to = {c.breve}, } s["itc-Latn-stripdiacritics"] = {remove_diacritics = c.macron .. c.breve .. c.diaer .. c.caron .. c.dinvbreve} s["itc-Latn-sortkey"] = { remove_diacritics = c.circ .. c.tilde .. c.macron .. c.breve .. c.diaer .. c.caron .. c.zigzag .. c.dmacron .. c.dtilde .. c.dinvbreve .. c.small_a .. c.small_e .. c.small_i .. c.small_o .. c.small_u, -- Chiefly medieval abbreviations. from = {"ᵃ", "æ", "[đꝱꟈ]", "ᵉ", "ⁱ", "ꝁ", "[ƚꝉꝲ]", "ꝳ", "ꝴ", "[ꝋᵒ]", "œ", "[ꝑꝓꝕ]", "[ꝗꝙ]", "[ꝛꝵꝶꝝ]", "[ꟊˢ]", "[ꝷᵗ]", "ᵘ", "ꝟ", "⁊"}, to = {"a", "ae", "d", "e", "i", "k", "l", "m", "n", "o", "oe", "p", "q", "r", "s", "t", "u", "v", "&"} } s["Jpan-standardchars"] = -- exclude ぢづヂヅ "ぁあぃいぅうぇえぉおかがきぎくぐけげこごさざしじすずせぜそぞただちっつてでとどなにぬねのはばぱひびぴふぶぷへべぺほぼぽまみむめもゃやゅゆょよらりるれろん" .. "ァアィイゥウェエォオカガキギクグケゲコゴサザシジスズセゼソゾタダチッツテデトドナニヌネノハバパヒビピフブプヘベペホボポマミムメモャヤュユョヨラリルレロン" local jpx_displaytext = { from = {"～", "＝"}, to = {"〜", "゠"} } s["jpx-displaytext"] = { Jpan = jpx_displaytext, Hani = jpx_displaytext, Hrkt = jpx_displaytext, Hira = jpx_displaytext, Kana = jpx_displaytext -- not Latn or Brai } s["jpx-stripdiacritics"] = s["jpx-displaytext"] s["jpx-sortkey"] = { Jpan = "Jpan-sortkey", Hani = "Hani-sortkey", Hrkt = "Hira-sortkey", -- sort general kana by normalizing to Hira Hira = "Hira-sortkey", Kana = "Kana-sortkey", Latn = {remove_diacritics = c.tilde .. c.macron .. c.diaer} } s["jpx-translit"] = { Hrkt = "Hrkt-translit", Hira = "Hrkt-translit", Kana = "Hrkt-translit" } s["roa-oil-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'", from = {"æ", "œ", "·"}, to = {"ae", "oe", " "} } s["wen-sortkey"] = { from = {"ch", "[lłßꞩẜ]", "dz[" .. c.caron .. c.acute .. "]", "[bcefmnoprswz][" .. c.caron .. c.acute .. c.dotabove .. "]"}, to = { "h" .. p[1], { ["l"] = "l" .. p[1], ["ł"] = "l", ["ß"] = "s", ["ꞩ"] = "š", ["ẜ"] = "š", }, { ["dz" .. c.caron] = "d" .. p[1], ["dz" .. c.acute] = "d" .. p[2] }, { ["b" .. c.acute] = "b" .. p[1], ["c" .. c.caron] = "c" .. p[1], ["c" .. c.acute] = "c" .. p[2], ["e" .. c.caron] = "e" .. p[1], ["e" .. c.dotabove] = "e" .. p[1], ["f" .. c.acute] = "f" .. p[1], ["m" .. c.acute] = "m" .. p[1], ["n" .. c.acute] = "n" .. p[1], ["o" .. c.acute] = "o" .. p[1], ["p" .. c.acute] = "p" .. p[1], ["r" .. c.caron] = "r" .. p[1], ["r" .. c.acute] = "r" .. p[2], ["s" .. c.caron] = "s" .. p[1], ["s" .. c.acute] = "s" .. p[2], ["w" .. c.acute] = "w" .. p[1], ["z" .. c.caron] = "z" .. p[1], ["z" .. c.acute] = "z" .. p[2], } } } -- Myanmar dotted form : https://www.unicode.org/Public/UNIDATA/StandardizedVariants.txt s["aio-displaytext"] = { from = {"([ကဂငတထပမယလဝဢေၵၸၺႀꩠꩡꩢꩣꩤꩥꩦꩫꩬꩯꩺ])"}, to = {"%1" .. c.VS01} } s["aio-stripdiacritics"] = { remove_diacritics = c.VS01, } s["phk-displaytext"] = s["aio-displaytext"] s["phk-stripdiacritics"] = s["aio-stripdiacritics"] s["kht-displaytext"] = s["aio-displaytext"] s["kht-stripdiacritics"] = s["aio-stripdiacritics"] export.shared = s --[==[ var: Short-term solution to override the standard substitution process, by forcing the module to substitute the entire text in one pass, if "cont" is given. This results in any PUA characters that are used as stand-ins for formatting being handled by the language-specific substitution process, which is usually undesirable. If the value is "none" then the formatting tags do not get turned into PUA characters in the first place. This override is provided for languages which use formatting between strings of text which might need to interact with each other (e.g. Korean 값이 transliterates as "gaps-i", but [[값]] has the formatting '''값'''[[-이]]. The normal process would split the text at the second '''.) ]==] export.substitution = { ["gmy"] = "none", ["ja"] = "cont", ["jje"] = "cont", ["ko"] = "cont", ["ko-ear"] = "cont", ["ru"] = "cont", ["th-new"] = "cont", ["sa"] = "cont", ["zkt"] = "cont", } --[==[ var: Code aliases. The left side is the alias and the right side is the canonical code. NOTE: These are gradually being deprecated, so should not be added to on a permanent basis. Temporary additions are permitted under reasonable circumstances (e.g. to facilitate changing a language's code). When an alias is no longer used, it should be removed. Aliases in this table are tracked at [[Wiktionary:Tracking/languages/LANG]]; see e.g. [[Special:WhatLinksHere/Wiktionary:Tracking/languages/VL.]] for the `VL.` alias. ]==] export.aliases = { ["EL."] = "la-ecc", ["LL."] = "la-lat", ["ML."] = "la-med", ["NL."] = "la-new", ["VL."] = "la-vul", ["nds-DE"] = "nds-de", ["nds-NL"] = "nds-nl", ["roa-oan"] = "roa-ona", ["sa-cls"] = "cls", ["sa-ved"] = "vsn", } --[==[ var: Codes which are tracked. Note that all aliases listed above are also tracked, so should not be duplicated here. Tracking uses the same mechanism described above in the comment above `export.aliases`. ]==] export.track = { -- Codes duplicated between full and etymology-only languages. ["lzh-lit"] = true, ["lzh"] = true, -- Languages actively being converted to families. ["bh"] = true, -- inc-bih ["nan"] = true, -- zhx-nan } return export b89ykupfotcto2w975o7485wv63kf7f 231380 231379 2026-04-14T07:36:08Z Lee 19 [[:en:Module:languages/data]] වෙතින් එක් සංශෝධනයක් 231379 Scribunto text/plain local export = {} -- We can't use mw.loadData() on [[Module:languages/chars]] because [[Module:languages/data]] itself is sometimes loaded -- using mw.loadData(), and calling mw.loadData() on [[Module:languages/chars]] will insert metatables into the -- character tables, which the second mw.loadData() will choke on. local m_chars = require("Module:languages/chars") local u = require("Module:string/char") local c = m_chars.chars export.chars = c local p = m_chars.puaChars export.puaChars = p local cs = m_chars.chars_substitutions export.chars_substitutions = cs -- FIXME! Many of the script-specific values below can be moved to [[Module:scripts/data]] to serve as script-wide -- fallback values instead of specifying them for each language using the script. local s = {} -- These values are placed here to make it possible to synchronise a group of languages without the need for a dedicated function module. -- cau do local cau_remove_diacritics = c.grave .. c.acute .. c.macron local cau_from = {"[IlΙІӀᴴ]"} local cau_to = {{ ["l"] = "ӏ", ["Ι"] = "ӏ", ["І"] = "ӏ", ["Ӏ"] = "ӏ", ["ᴴ"] = "ᵸ", }} s["cau-Cyrl-displaytext"] = { from = cau_from, to = cau_to, } s["cau-Cyrl-stripdiacritics"] = { remove_diacritics = cau_remove_diacritics, from = cau_from, to = cau_to, } s["cau-Latn-stripdiacritics"] = {remove_diacritics = cau_remove_diacritics} end s["itc-Latn-displaytext"] = { from = {c.caron}, to = {c.breve}, } s["itc-Latn-stripdiacritics"] = {remove_diacritics = c.macron .. c.breve .. c.diaer .. c.caron .. c.dinvbreve} s["itc-Latn-sortkey"] = { remove_diacritics = c.circ .. c.tilde .. c.macron .. c.breve .. c.diaer .. c.caron .. c.zigzag .. c.dmacron .. c.dtilde .. c.dinvbreve .. c.small_a .. c.small_e .. c.small_i .. c.small_o .. c.small_u, -- Chiefly medieval abbreviations. from = {"ᵃ", "æ", "[đꝱꟈ]", "ᵉ", "ⁱ", "ꝁ", "[ƚꝉꝲ]", "ꝳ", "ꝴ", "[ꝋᵒ]", "œ", "[ꝑꝓꝕ]", "[ꝗꝙ]", "[ꝛꝵꝶꝝ]", "[ꟊˢ]", "[ꝷᵗ]", "ᵘ", "ꝟ", "⁊"}, to = {"a", "ae", "d", "e", "i", "k", "l", "m", "n", "o", "oe", "p", "q", "r", "s", "t", "u", "v", "&"} } s["Jpan-standardchars"] = -- exclude ぢづヂヅ "ぁあぃいぅうぇえぉおかがきぎくぐけげこごさざしじすずせぜそぞただちっつてでとどなにぬねのはばぱひびぴふぶぷへべぺほぼぽまみむめもゃやゅゆょよらりるれろん" .. "ァアィイゥウェエォオカガキギクグケゲコゴサザシジスズセゼソゾタダチッツテデトドナニヌネノハバパヒビピフブプヘベペホボポマミムメモャヤュユョヨラリルレロン" local jpx_displaytext = { from = {"～", "＝"}, to = {"〜", "゠"} } s["jpx-displaytext"] = { Jpan = jpx_displaytext, Hani = jpx_displaytext, Hrkt = jpx_displaytext, Hira = jpx_displaytext, Kana = jpx_displaytext -- not Latn or Brai } s["jpx-stripdiacritics"] = s["jpx-displaytext"] s["jpx-sortkey"] = { Jpan = "Jpan-sortkey", Hani = "Hani-sortkey", Hrkt = "Hira-sortkey", -- sort general kana by normalizing to Hira Hira = "Hira-sortkey", Kana = "Kana-sortkey", Latn = {remove_diacritics = c.tilde .. c.macron .. c.diaer} } s["jpx-translit"] = { Hrkt = "Hrkt-translit", Hira = "Hrkt-translit", Kana = "Hrkt-translit" } s["roa-oil-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'", from = {"æ", "œ", "·"}, to = {"ae", "oe", " "} } s["wen-sortkey"] = { from = {"ch", "[lłßꞩẜ]", "dz[" .. c.caron .. c.acute .. "]", "[bcefmnoprswz][" .. c.caron .. c.acute .. c.dotabove .. "]"}, to = { "h" .. p[1], { ["l"] = "l" .. p[1], ["ł"] = "l", ["ß"] = "s", ["ꞩ"] = "š", ["ẜ"] = "š", }, { ["dz" .. c.caron] = "d" .. p[1], ["dz" .. c.acute] = "d" .. p[2] }, { ["b" .. c.acute] = "b" .. p[1], ["c" .. c.caron] = "c" .. p[1], ["c" .. c.acute] = "c" .. p[2], ["e" .. c.caron] = "e" .. p[1], ["e" .. c.dotabove] = "e" .. p[1], ["f" .. c.acute] = "f" .. p[1], ["m" .. c.acute] = "m" .. p[1], ["n" .. c.acute] = "n" .. p[1], ["o" .. c.acute] = "o" .. p[1], ["p" .. c.acute] = "p" .. p[1], ["r" .. c.caron] = "r" .. p[1], ["r" .. c.acute] = "r" .. p[2], ["s" .. c.caron] = "s" .. p[1], ["s" .. c.acute] = "s" .. p[2], ["w" .. c.acute] = "w" .. p[1], ["z" .. c.caron] = "z" .. p[1], ["z" .. c.acute] = "z" .. p[2], } } } -- Myanmar dotted form : https://www.unicode.org/Public/UNIDATA/StandardizedVariants.txt s["aio-displaytext"] = { from = {"([ကဂငတထပမယလဝဢေၵၸၺႀꩠꩡꩢꩣꩤꩥꩦꩫꩬꩯꩺ])"}, to = {"%1" .. c.VS01} } s["aio-stripdiacritics"] = { remove_diacritics = c.VS01, } s["phk-displaytext"] = s["aio-displaytext"] s["phk-stripdiacritics"] = s["aio-stripdiacritics"] s["kht-displaytext"] = s["aio-displaytext"] s["kht-stripdiacritics"] = s["aio-stripdiacritics"] export.shared = s --[==[ var: Short-term solution to override the standard substitution process, by forcing the module to substitute the entire text in one pass, if "cont" is given. This results in any PUA characters that are used as stand-ins for formatting being handled by the language-specific substitution process, which is usually undesirable. If the value is "none" then the formatting tags do not get turned into PUA characters in the first place. This override is provided for languages which use formatting between strings of text which might need to interact with each other (e.g. Korean 값이 transliterates as "gaps-i", but [[값]] has the formatting '''값'''[[-이]]. The normal process would split the text at the second '''.) ]==] export.substitution = { ["gmy"] = "none", ["ja"] = "cont", ["jje"] = "cont", ["ko"] = "cont", ["ko-ear"] = "cont", ["ru"] = "cont", ["th-new"] = "cont", ["sa"] = "cont", ["zkt"] = "cont", } --[==[ var: Code aliases. The left side is the alias and the right side is the canonical code. NOTE: These are gradually being deprecated, so should not be added to on a permanent basis. Temporary additions are permitted under reasonable circumstances (e.g. to facilitate changing a language's code). When an alias is no longer used, it should be removed. Aliases in this table are tracked at [[Wiktionary:Tracking/languages/LANG]]; see e.g. [[Special:WhatLinksHere/Wiktionary:Tracking/languages/VL.]] for the `VL.` alias. ]==] export.aliases = { ["EL."] = "la-ecc", ["LL."] = "la-lat", ["ML."] = "la-med", ["NL."] = "la-new", ["VL."] = "la-vul", ["nds-DE"] = "nds-de", ["nds-NL"] = "nds-nl", ["roa-oan"] = "roa-ona", ["sa-cls"] = "cls", ["sa-ved"] = "vsn", } --[==[ var: Codes which are tracked. Note that all aliases listed above are also tracked, so should not be duplicated here. Tracking uses the same mechanism described above in the comment above `export.aliases`. ]==] export.track = { -- Codes duplicated between full and etymology-only languages. ["lzh-lit"] = true, ["lzh"] = true, -- Languages actively being converted to families. ["bh"] = true, -- inc-bih ["nan"] = true, -- zhx-nan } return export b89ykupfotcto2w975o7485wv63kf7f 828 7906 231382 222259 2026-03-29T01:28:30Z en>Chuck Entz 0 Undid revision [[Special:Diff/89976079|89976079]] by [[Special:Contributions/Chuck Entz|Chuck Entz]] ([[User talk:Chuck Entz|talk]]) had absolutely no effect- might as well revert to be on the safe side 231382 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared -- Ideally, we want to move these into [[Module:languages/data]], but because (a) it's necessary to use require on that module, and (b) they're only used in this data module, it's less memory-efficient to do that at the moment. If it becomes possible to use mw.loadData, then these should be moved there. s["de-Latn-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove, from = {"æ", "œ", "ß"}, to = {"ae", "oe", "ss"} } s["de-Latn-standardchars"] = "AaÄäBbCcDdEeFfGgHhIiJjKkLlMmNnOoÖöPpQqRrSsẞßTtUuÜüVvWwXxYyZz" s["ka-stripdiacritics"] = {remove_diacritics = c.circ} s["no-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } s["no-standardchars"] = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc s["sa-Deva-stripdiacritics"] = { -- Don't use remove_diacritics for accent marks, as १ and ३ should also be removed if (and only if) they carry any. from = {"[१३]?[" .. c.anudatta .. c.udatta .. c.dsvarita .. c.tsvarita .. "]+"}, to = {""}, } s["tg-stripdiacritics"] = {remove_diacritics = c.grave .. c.acute} s["tk-stripdiacritics"] = {remove_diacritics = c.macron} local m = {} m["aa"] = { "Afar", 27811, "cus-eas", "Latn, Ethi", strip_diacritics = { Latn = {remove_diacritics = c.acute}, }, } m["ab"] = { "Abkhaz", 5111, "cau-abz", "Cyrl, Geor, Latn", translit = { Cyrl = "ab-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, from = {"^а%-"}, to = {"а"}, }, Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = { "х'ә", -- 3 chars "гь", "гә", "ӷь", "ҕь", "ӷә", "ҕә", "дә", "ё", "жь", "жә", "ҙә", "ӡә", "ӡ'", "кь", "кә", "қь", "қә", "ҟь", "ҟә", "ҫә", "тә", "ҭә", "ф'", "хь", "хә", "х'", "ҳә", "ць", "цә", "ц'", "ҵә", "ҵ'", "шь", "шә", "џь", -- 2 chars "ӷ", "ҕ", "ҙ", "ӡ", "қ", "ҟ", "ԥ", "ҧ", "ҫ", "ҭ", "ҳ", "ҵ", "ҷ", "ҽ", "ҿ", "ҩ", "џ", "ә", -- 1 char "^а", }, to = { "х" .. p[4], "г" .. p[1], "г" .. p[2], "г" .. p[5], "г" .. p[6], "г" .. p[7], "г" .. p[8], "д" .. p[1], "е" .. p[1], "ж" .. p[1], "ж" .. p[2], "з" .. p[2], "з" .. p[4], "з" .. p[5], "к" .. p[1], "к" .. p[2], "к" .. p[4], "к" .. p[5], "к" .. p[7], "к" .. p[8], "с" .. p[2], "т" .. p[1], "т" .. p[3], "ф" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[6], "ц" .. p[1], "ц" .. p[2], "ц" .. p[3], "ц" .. p[5], "ц" .. p[6], "ш" .. p[1], "ш" .. p[2], "ы" .. p[3], "г" .. p[3], "г" .. p[4], "з" .. p[1], "з" .. p[3], "к" .. p[3], "к" .. p[6], "п" .. p[1], "п" .. p[2], "с" .. p[1], "т" .. p[2], "х" .. p[5], "ц" .. p[4], "ч" .. p[1], "ч" .. p[2], "ч" .. p[3], "ы" .. p[1], "ы" .. p[2], "ь" .. p[1], "", } }, }, } m["ae"] = { "Avestan", 29572, "ira-cen", "Avst, Gujr, Deva", translit = { Avst = "Avst-translit" }, } m["af"] = { "Afrikaans", 14196, "gmw-frk", "Latn, Arab", ancestors = "nl", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'", from = {"['ʼ]n"}, to = {"n" .. p[1]} } }, } m["ak"] = { "Akan", 28026, "alv-ctn", "Latn", } m["am"] = { "Amharic", 28244, "sem-eth", "Ethi", translit = "Ethi-translit", } m["an"] = { "Aragonese", 8765, "roa-nar", "Latn", } m["ar"] = { "Arabic", 13955, "sem-arb", "Arab, Hebr, Syrc, Brai, Nbat", translit = { Arab = "ar-translit" }, strip_diacritics = { Arab = "ar-stripdiacritics", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["as"] = { "Assamese", 29401, "inc-bas", "as-Beng", ancestors = "inc-mas", translit = "as-translit", } m["av"] = { "Avar", 29561, "cau-ava", "Cyrl, Latn, Arab", ancestors = "oav", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"], }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"гъ", "гь", "гӏ", "ё", "кк", "къ", "кь", "кӏ", "лъ", "лӏ", "тӏ", "хх", "хъ", "хь", "хӏ", "цӏ", "чӏ"}, to = {"г" .. p[1], "г" .. p[2], "г" .. p[3], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "к" .. p[4], "л" .. p[1], "л" .. p[2], "т" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[4], "ц" .. p[1], "ч" .. p[1]} }, }, } m["ay"] = { "Aymara", 4627, "sai-aym", "Latn", } m["az"] = { "Azerbaijani", 9292, "trk-ogz", "Latn, Cyrl, fa-Arab", ancestors = "trk-oat", dotted_dotless_i = true, strip_diacritics = { Latn = { from = {"ʼ"}, to = {"'"}, }, ["fa-Arab"] = { module = "ar-stripdiacritics", ["from"] = { "ۆ", "ۇ", "وْ", "ڲ", "ؽ", }, ["to"] = { "و", "و", "و", "گ", "ی", }, }, }, display_text = { Latn = { from = {"'"}, to = {"ʼ"} } }, sort_key = { Latn = { from = { "i", -- Ensure "i" comes after "ı". "ç", "ə", "ğ", "x", "ı", "q", "ö", "ş", "ü", "w" }, to = { "i" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "h" .. p[1], "i", "k" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1] } }, Cyrl = { from = {"ғ", "ә", "ы", "ј", "ҝ", "ө", "ү", "һ", "ҹ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "и" .. p[2], "к" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["ba"] = { "Bashkir", 13389, "trk-kbu", "Cyrl", translit = "ba-translit", override_translit = true, sort_key = { from = {"ғ", "ҙ", "ё", "ҡ", "ң", "ө", "ҫ", "ү", "һ", "ә"}, to = {"г" .. p[1], "д" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "с" .. p[1], "у" .. p[1], "х" .. p[1], "э" .. p[1]} }, } m["be"] = { "Belarusian", 9091, "zle", "Cyrl, Latn", ancestors = "zle-mbe", translit = { Cyrl = "be-translit", }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"ґ", "ё", "і", "ў"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "у" .. p[1]} }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, from = {"ć", "č", "dz", "dź", "dž", "ch", "ł", "ń", "ś", "š", "ŭ", "ź", "ž"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "d" .. p[3], "h" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзІіЙйКкЛлМмНнОоПпРрСсТтУуЎўФфХхЦцЧчШшЫыЬьЭэЮюЯя", Latn = "AaBbCcĆćČčDdEeFfGgHhIiJjKkLlŁłMmNnŃńOoPpRrSsŚśŠšTtUuŬŭVvYyZzŹźŽž", (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["bg"] = { "Bulgarian", 7918, "zls", "Cyrl", ancestors = "cu-bgm", translit = "bg-translit", strip_diacritics = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, sort_key = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, standard_chars = "АаБбВвГгДдЕеЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЬьЮюЯя" .. c.punc, } m["bh"] = { "Bihari", 135305, "inc-eas", "Deva", } m["bi"] = { "Bislama", 35452, "crp", "Latn", ancestors = "en", } m["bm"] = { "Bambara", 33243, "dmn-emn", "Latn, Nkoo", sort_key = { Latn = { from = {"ɛ", "ɲ", "ŋ", "ɔ"}, to = {"e" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1]} }, }, } m["bn"] = { "Bengali", 9610, "inc-bas", "Beng, Newa", ancestors = "inc-mbn", translit = { Beng = "bn-translit" }, } m["bo"] = { "Tibetan", 34271, "sit-tib", "Tibt", -- sometimes Deva? ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["br"] = { "Breton", 12107, "cel-brs", "Latn", ancestors = "xbm", sort_key = { from = {"ch", "c['ʼ’]h"}, to = {"c" .. p[1], "c" .. p[2]} }, } m["ca"] = { "Catalan", 7026, "roa-ocr", "Latn", ancestors = "roa-oca", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, standard_chars = "AaÀàBbCcÇçDdEeÉéÈèFfGgHhIiÍíÏïJjLlMmNnOoÓóÒòPpQqRrSsTtUuÚúÜüVvXxYyZz·" .. c.punc, } m["ce"] = { "Chechen", 33350, "cau-vay", "Cyrl, Latn, Arab", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"аь", "гӏ", "ё", "кх", "къ", "кӏ", "оь", "пӏ", "тӏ", "уь", "хь", "хӏ", "цӏ", "чӏ", "юь", "яь"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "о" .. p[1], "п" .. p[1], "т" .. p[1], "у" .. p[1], "х" .. p[1], "х" .. p[2], "ц" .. p[1], "ч" .. p[1], "ю" .. p[1], "я" .. p[1]} }, }, } m["ch"] = { "Chamorro", 33262, "poz", "Latn", sort_key = { remove_diacritics = "'", from = {"å", "ch", "ñ", "ng"}, to = {"a" .. p[1], "c" .. p[1], "n" .. p[1], "n" .. p[2]} }, } m["co"] = { "Corsican", 33111, "roa-itr", "Latn", sort_key = { from = {"chj", "ghj", "sc", "sg"}, to = {"c" .. p[1], "g" .. p[1], "s" .. p[1], "s" .. p[2]} }, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìÏïJjLlMmNnOoÒòPpQqRrSsTtUuÙùÜüVvZz" .. c.punc, } m["cr"] = { "Cree", 33390, "alg", "Latn, Cans", translit = { Cans = "cr-translit" }, } m["cs"] = { "Czech", 9056, "zlw", "Latn", ancestors = "cs-ear", sort_key = { from = {"á", "č", "ď", "é", "ě", "ch", "í", "ň", "ó", "ř", "š", "ť", "ú", "ů", "ý", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "h" .. p[1], "i" .. p[1], "n" .. p[1], "o" .. p[1], "r" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "y" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĎďEeÉéĚěFfGgHhIiÍíJjKkLlMmNnŇňOoÓóPpRrŘřSsŠšTtŤťUuÚúŮůVvYyÝýZzŽž" .. c.punc, } m["cu"] = { "Old Church Slavonic", 35499, "zls", "Cyrs, Glag, Zname", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["cv"] = { "Chuvash", 33348, "trk-ogr", "Cyrl", ancestors = "cv-mid", translit = "cv-translit", override_translit = true, sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = {"а" .. p[1], "е" .. p[1], "е" .. p[2], "с" .. p[1], "у" .. p[1]} }, } m["cy"] = { "Welsh", 9309, "cel-brw", "Latn", ancestors = "wlm", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. "'", from = {"ch", "dd", "ff", "ng", "ll", "ph", "rh", "th"}, to = {"c" .. p[1], "d" .. p[1], "f" .. p[1], "g" .. p[1], "l" .. p[1], "p" .. p[1], "r" .. p[1], "t" .. p[1]} }, standard_chars = "ÂâAaBbCcDdEeÊêFfGgHhIiÎîLlMmNnOoÔôPpRrSsTtUuÛûWwŴŵYyŶŷ" .. c.punc, } m["da"] = { "Danish", 9035, "gmq-eas", "Latn", ancestors = "gmq-oda", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc, } m["de"] = { "German", 188, "gmw-hgm", "Latn, Latf, Brai", ancestors = "de-ear", sort_key = { Latn = s["de-Latn-sortkey"], Latf = s["de-Latn-sortkey"], }, standard_chars = { Latn = s["de-Latn-standardchars"], Latf = s["de-Latn-standardchars"], Brai = c.braille, c.punc } } m["dv"] = { "Dhivehi", 32656, "inc-ins", "Thaa, Diak", translit = { Thaa = "dv-translit", Diak = "Diak-translit", }, ancestors = "dv-old", override_translit = true, } m["dz"] = { "Dzongkha", 33081, "sit-tib", "Tibt", ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ee"] = { "Ewe", 30005, "alv-gbe", "Latn", sort_key = { remove_diacritics = c.tilde, from = {"ɖ", "dz", "ɛ", "ƒ", "gb", "ɣ", "kp", "ny", "ŋ", "ɔ", "ts", "ʋ"}, to = {"d" .. p[1], "d" .. p[2], "e" .. p[1], "f" .. p[1], "g" .. p[1], "g" .. p[2], "k" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "t" .. p[1], "v" .. p[1]} }, } m["el"] = { "Greek", 9129, "grk", "Grek, Polyt, Brai", ancestors = "el-kth", translit = "el-translit", override_translit = true, -- Grek and Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Grek = "΅·ͺ΄ΑαΆάΒβΓγΔδΕεέΈΖζΗηΉήΘθΙιΊίΪϊΐΚκΛλΜμΝνΞξΟοΌόΠπΡρΣσςΤτΥυΎύΫϋΰΦφΧχΨψΩωΏώ", Brai = c.braille, c.punc }, } m["en"] = { "English", 1860, "gmw-ang", "Latn, Brai, Shaw, Dsrt", -- entries in Shaw or Dsrt might require prior discussion wikimedia_codes = "en, simple", ancestors = "en-ear", sort_key = { Latn = { -- Many of these are needed for sorting language names. remove_diacritics = "'\"%-%.,%s·ʻʼ" .. c.diacritics, -- These are found in pagenames. from = {"[ɒæ🅱¢©ᴄðđəǝɜɡħʜıɨłŋɲøɔœꝑꝓꝕßʋ]"}, to = {{ ["ɒ"] = "a", ["æ"] = "ae", ["🅱"] = "b", ["¢"] = "c", ["©"] = "c", ["ᴄ"] = "c", ["ð"] = "d", ["đ"] = "d", ["ə"] = "e", ["ǝ"] = "e", ["ɜ"] = "e", ["ɡ"] = "g", ["ħ"] = "h", ["ʜ"] = "h", ["ı"] = "i", ["ɨ"] = "i", ["ł"] = "l", ["ŋ"] = "n", ["ɲ"] = "n", ["ø"] = "o", ["ɔ"] = "o", ["œ"] = "oe", ["ꝑ"] = "p", ["ꝓ"] = "p", ["ꝕ"] = "p", ["ß"] = "ss", ["ʋ"] = "v", }}, }, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", Brai = c.braille, c.punc }, } m["eo"] = { "Esperanto", 143, "art", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute, from = {"ĉ", "ĝ", "ĥ", "ĵ", "ŝ", "ŭ"}, to = {"c" .. p[1], "g" .. p[1], "h" .. p[1], "j" .. p[1], "s" .. p[1], "u" .. p[1]} }, standard_chars = "AaBbCcĈĉDdEeFfGgĜĝHhĤĥIiJjĴĵKkLlMmNnOoPpRrSsŜŝTtUuŬŭVvZz" .. c.punc, } m["es"] = { "Spanish", 1321, "roa-cas", "Latn, Brai", ancestors = "es-ear", sort_key = { Latn = { remove_exceptions = {"ñ"}, remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "ñ", "º", "œ"}, to = {"a", "ae", "n" .. p[1], "o", "oe"} }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["et"] = { "Estonian", 9072, "urj-fin", "Latn", sort_key = { from = { "š", "ž", "õ", "ä", "ö", "ü", -- 2 chars "z" -- 1 char }, to = { "s" .. p[1], "s" .. p[3], "w" .. p[1], "w" .. p[2], "w" .. p[3], "w" .. p[4], "s" .. p[2] } }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvÕõÄäÖöÜü" .. c.punc, } m["eu"] = { "Basque", 8752, "euq", "Latn", sort_key = { from = {"ç", "ñ"}, to = {"c" .. p[1], "n" .. p[1]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnÑñOoPpRrSsTtUuXxZz" .. c.punc, } m["fa"] = { "Persian", 9168, "ira-swi", "fa-Arab, Hebr", ancestors = "fa-cls", strip_diacritics = { ["fa-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ٱ"}, -- character "ۂ" code U+06C2 to "ه"; hamzatu l-waṣli to a regular alif to = {"ه", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ff"] = { "Fula", 33454, "alv-fwo", "Latn, Adlm", } m["fi"] = { "Finnish", 1412, "urj-fin", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { -- used to indicate gemination of the next consonant remove_diacritics = "ˣ", from = {"’"}, to = {"'"}, }, sort_key = { -- [[Appendix:Finnish alphabet#Collation]] + "aͤ" and "oͤ" as historical variants of "ä" and "ö". remove_diacritics = "'’:" .. c.diacritics, remove_exceptions = { "a[" .. c.ringabove .. c.diaer .. c.small_e .. "]", -- åäaͤ "o[" .. c.diaer .. c.tilde .. c.dacute .. c.small_e .. "]", -- öõőoͤ "u[" .. c.diaer .. c.dacute .. "]" -- üű }, from = {"æ", "[ðđ]", "ł", "ŋ", "œ", "ß", "þ", "u[" .. c.diaer .. c.dacute .. "]", "å", "aͤ", "o[" .. c.tilde .. c.dacute .. c.small_e .. "]", "ø", "(.)['%-]"}, to = {"ae", "d", "l", "n", "oe", "ss", "th", "y", "z" .. p[1], "ä", "ö", "ö", "%1"} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÄäÖö" .. c.punc, } m["fj"] = { "Fijian", 33295, "poz-pcc", "Latn", } m["fo"] = { "Faroese", 25258, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "í", "ó", "ú", "ý", "æ", "ø"}, to = {"a" .. p[1], "d" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaÁáBbDdÐðEeFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvYyÝýÆæØø" .. c.punc, } m["fr"] = { "French", 150, "roa-oil", "Latn, Brai", ancestors = "frm", sort_key = { Latn = s["roa-oil-sortkey"] }, standard_chars = { Latn = "AaÀàÂâBbCcÇçDdEeÉéÈèÊêËëFfGgHhIiÎîÏïJjLlMmNnOoÔôŒœPpQqRrSsTtUuÙùÛûÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["fy"] = { "West Frisian", 27175, "gmw-fri", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer, from = {"y"}, to = {"i"} }, standard_chars = "AaâäàÆæBbCcDdEeéêëèFfGgHhIiïìYyỳJjKkLlMmNnOoôöòPpRrSsTtUuúûüùVvWwZz" .. c.punc, } m["ga"] = { "Irish", 9142, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = { remove_diacritics = c.acute, from = {"ḃ", "ċ", "ḋ", "ḟ", "ġ", "ṁ", "ṗ", "ṡ", "ṫ"}, to = {"bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíLlMmNnOoÓóPpRrSsTtUuÚúVv" .. c.punc, } m["gd"] = { "Scottish Gaelic", 9314, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = {remove_diacritics = c.grave .. c.acute}, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙù" .. c.punc, } m["gl"] = { "Galician", 9307, "roa-gap", "Latn", sort_key = { remove_diacritics = c.acute, from = {"ñ"}, to = {"n" .. p[1]} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíÏïLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxZz" .. c.punc, } m["gu"] = { "Gujarati", 5137, "inc-wes", "Arab, Gujr", ancestors = "inc-mgu", translit = { Gujr = "gu-translit", }, strip_diacritics = { Arab = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.kasra .. c.shadda .. c.sukun}, Gujr = {remove_diacritics = "઼"}, }, } m["gv"] = { "Manx", 12175, "cel-gae", "Latn", ancestors = "mga", sort_key = {remove_diacritics = c.cedilla .. "-"}, standard_chars = "AaBbCcÇçDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYy" .. c.punc, } m["ha"] = { "Hausa", 56475, "cdc-wst", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron} }, sort_key = { Latn = { from = {"ɓ", "b'", "ɗ", "d'", "ƙ", "k'", "sh", "ƴ", "'y"}, to = {"b" .. p[1], "b" .. p[2], "d" .. p[1], "d" .. p[2], "k" .. p[1], "k" .. p[2], "s" .. p[1], "y" .. p[1], "y" .. p[2]} }, }, } m["he"] = { "Hebrew", 9288, "sem-can", "Hebr, Phnx, Brai, Samr", ancestors = "he-med", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- Samr strip_diacritics, sort_key in [[Module:scripts/data]] -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["hi"] = { "Hindi", 1568, "inc-hnd", "Deva, Kthi, Newa", translit = { Deva = "hi-translit" }, standard_chars = { Deva = "अआइईउऊएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषसहत्रज्ञक्षक़ख़ग़ज़झ़ड़ढ़फ़काखागाघाङाचाछाजाझाञाटाठाडाढाणाताथादाधानापाफाबाभामायारालावाशाषासाहात्राज्ञाक्षाक़ाख़ाग़ाज़ाझ़ाड़ाढ़ाफ़ाकिखिगिघिङिचिछिजिझिञिटिठिडिढिणितिथिदिधिनिपिफिबिभिमियिरिलिविशिषिसिहित्रिज्ञिक्षिक़िख़िग़िज़िझ़िड़िढ़िफ़िकीखीगीघीङीचीछीजीझीञीटीठीडीढीणीतीथीदीधीनीपीफीबीभीमीयीरीलीवीशीषीसीहीत्रीज्ञीक्षीक़ीख़ीग़ीज़ीझ़ीड़ीढ़ीफ़ीकुखुगुघुङुचुछुजुझुञुटुठुडुढुणुतुथुदुधुनुपुफुबुभुमुयुरुलुवुशुषुसुहुत्रुज्ञुक्षुक़ुख़ुग़ुज़ुझ़ुड़ुढ़ुफ़ुकूखूगूघूङूचूछूजूझूञूटूठूडूढूणूतूथूदूधूनूपूफूबूभूमूयूरूलूवूशूषूसूहूत्रूज्ञूक्षूक़ूख़ूग़ूज़ूझ़ूड़ूढ़ूफ़ूकेखेगेघेङेचेछेजेझेञेटेठेडेढेणेतेथेदेधेनेपेफेबेभेमेयेरेलेवेशेषेसेहेत्रेज्ञेक्षेक़ेख़ेग़ेज़ेझ़ेड़ेढ़ेफ़ेकैखैगैघैङैचैछैजैझैञैटैठैडैढैणैतैथैदैधैनैपैफैबैभैमैयैरैलैवैशैषैसैहैत्रैज्ञैक्षैक़ैख़ैग़ैज़ैझ़ैड़ैढ़ैफ़ैकोखोगोघोङोचोछोजोझोञोटोठोडोढोणोतोथोदोधोनोपोफोबोभोमोयोरोलोवोशोषोसोहोत्रोज्ञोक्षोक़ोख़ोग़ोज़ोझ़ोड़ोढ़ोफ़ोकौखौगौघौङौचौछौजौझौञौटौठौडौढौणौतौथौदौधौनौपौफौबौभौमौयौरौलौवौशौषौसौहौत्रौज्ञौक्षौक़ौख़ौग़ौज़ौझ़ौड़ौढ़ौफ़ौक्ख्ग्घ्ङ्च्छ्ज्झ्ञ्ट्ठ्ड्ढ्ण्त्थ्द्ध्न्प्फ्ब्भ्म्य्र्ल्व्श्ष्स्ह्त्र्ज्ञ्क्ष्क़्ख़्ग़्ज़्झ़्ड़्ढ़्फ़्।॥०१२३४५६७८९॰", c.punc }, } m["ho"] = { "Hiri Motu", 33617, "crp", "Latn", ancestors = "meu", } m["ht"] = { "Haitian Creole", 33491, "crp", "Latn", ancestors = "ht-sdm", sort_key = { from = { "oun", -- 3 chars "an", "ch", "è", "en", "ng", "ò", "on", "ou", "ui" -- 2 chars }, to = { "o" .. p[4], "a" .. p[1], "c" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "u" .. p[1] } }, } m["hu"] = { "Hungarian", 9067, "urj-ugr", "Latn, Hung", ancestors = "ohu", sort_key = { Latn = { from = { "dzs", -- 3 chars "á", "cs", "dz", "é", "gy", "í", "ly", "ny", "ó", "ö", "ő", "sz", "ty", "ú", "ü", "ű", "zs", -- 2 chars }, to = { "d" .. p[2], "a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "u" .. p[3], "z" .. p[1], } }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóÖöŐőPpQqRrSsTtUuÚúÜüŰűVvWwXxYyZz", c.punc }, } m["hy"] = { "Armenian", 8785, "hyx", "Armn, Brai", ancestors = "axm", -- Armn translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Armn = { remove_diacritics = "՛՜՞՟", from = {"եւ", "<sup>յ</sup>", "<sup>ի</sup>", "<sup>է</sup>", "յ̵", "ՙ", "՚"}, to = {"և", "յ", "ի", "է", "ֈ", "ʻ", "’"} }, }, sort_key = { Armn = { from = { "ու", "եւ", -- 2 chars "և" -- 1 char }, to = { "ւ", "եվ", "եվ" } }, }, } m["hz"] = { "Herero", 33315, "bnt-swb", "Latn", } m["ia"] = { "Interlingua", 35934, "art", "Latn", } m["id"] = { "Indonesian", 9240, "poz-mly", "Latn", ancestors = "ms", standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc, } m["ie"] = { "Interlingue", 35850, "art", "Latn", type = "appendix-constructed", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["ig"] = { "Igbo", 33578, "alv-igb", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron}, sort_key = { from = {"gb", "gh", "gw", "ị", "kp", "kw", "ṅ", "nw", "ny", "ọ", "sh", "ụ"}, to = {"g" .. p[1], "g" .. p[2], "g" .. p[3], "i" .. p[1], "k" .. p[1], "k" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "o" .. p[1], "s" .. p[1], "u" .. p[1]} }, } m["ii"] = { "Nuosu", 34235, "tbq-nlo", "Yiii", translit = "ii-translit", } m["ik"] = { "Inupiaq", 27183, "esx-inu", "Latn", sort_key = { from = { "ch", "ġ", "dj", "ḷ", "ł̣", "ñ", "ng", "r̂", "sr", "zr", -- 2 chars "ł", "ŋ", "ʼ" -- 1 char }, to = { "c" .. p[1], "g" .. p[1], "h" .. p[1], "l" .. p[1], "l" .. p[3], "n" .. p[1], "n" .. p[2], "r" .. p[1], "s" .. p[1], "z" .. p[1], "l" .. p[2], "n" .. p[2], "z" .. p[2] } }, } m["io"] = { "Ido", 35224, "art", "Latn", } m["is"] = { "Icelandic", 294, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "é", "í", "ó", "ú", "ý", "þ", "æ", "ö"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaÁáBbDdÐðEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvXxYyÝýÞþÆæÖö" .. c.punc, } m["it"] = { "Italian", 652, "roa-itr", "Latn", ancestors = "roa-oit", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove}, standard_chars = "AaÀàBbCcDdEeÈèÉéFfGgHhIiÌìLlMmNnOoÒòPpQqRrSsTtUuÙùVvZz" .. c.punc, } m["iu"] = { "Inuktitut", 29921, "esx-inu", "Cans, Latn", translit = { Cans = "cr-translit" }, override_translit = true, } m["ja"] = { "Japanese", 5287, "jpx", "Jpan, Latn, Brai", ancestors = "ja-ear", translit = s["jpx-translit"], link_tr = true, display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jv"] = { "Javanese", 33549, "poz", "Latn, Java, Arab", ancestors = "kaw", translit = { Java = "jv-translit" }, link_tr = true, strip_diacritics = { Latn = {remove_diacritics = c.circ} -- Modern jv don't use ê }, sort_key = { Latn = { from = {"å", "dh", "é", "è", "ng", "ny", "th"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "n" .. p[2], "t" .. p[1]} }, }, } m["ka"] = { "Georgian", 8108, "ccs-gzn", "Geor, Geok, Hebr", -- Hebr is used to write Judeo-Georgian ancestors = "ka-mid", -- Geor, Geok translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Geor = s["ka-stripdiacritics"], Geok = s["ka-stripdiacritics"], }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["kg"] = { "Kongo", 33702, "bnt-kng", "Latn", } m["ki"] = { "Kikuyu", 33587, "bnt-kka", "Latn", } m["kj"] = { "Kwanyama", 1405077, "bnt-ova", "Latn", } m["kk"] = { "Kazakh", 9252, "trk-kno", "Cyrl, Latn, kk-Arab", translit = { Cyrl = { from = { "Ё", "ё", "Й", "й", "Нг", "нг", "Ӯ", "ӯ", -- 2 chars; are "Ӯ" and "ӯ" actually used? "А", "а", "Ә", "ә", "Б", "б", "В", "в", "Г", "г", "Ғ", "ғ", "Д", "д", "Е", "е", "Ж", "ж", "З", "з", "И", "и", "К", "к", "Қ", "қ", "Л", "л", "М", "м", "Н", "н", "Ң", "ң", "О", "о", "Ө", "ө", "П", "п", "Р", "р", "С", "с", "Т", "т", "У", "у", "Ұ", "ұ", "Ү", "ү", "Ф", "ф", "Х", "х", "Һ", "һ", "Ц", "ц", "Ч", "ч", "Ш", "ш", "Щ", "щ", "Ъ", "ъ", "Ы", "ы", "І", "і", "Ь", "ь", "Э", "э", "Ю", "ю", "Я", "я", -- 1 char }, to = { "E", "e", "İ", "i", "Ñ", "ñ", "U", "u", "A", "a", "Ä", "ä", "B", "b", "V", "v", "G", "g", "Ğ", "ğ", "D", "d", "E", "e", "J", "j", "Z", "z", "İ", "i", "K", "k", "Q", "q", "L", "l", "M", "m", "N", "n", "Ñ", "ñ", "O", "o", "Ö", "ö", "P", "p", "R", "r", "S", "s", "T", "t", "U", "u", "Ū", "ū", "Ü", "ü", "F", "f", "X", "x", "H", "h", "S", "s", "Ç", "ç", "Ş", "ş", "Ş", "ş", "", "", "Y", "y", "I", "ı", "", "", "É", "é", "Ü", "ü", "Ä", "ä", } } }, -- override_translit = true, sort_key = { Cyrl = { from = {"ә", "ғ", "ё", "қ", "ң", "ө", "ұ", "ү", "һ", "і"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "у" .. p[2], "х" .. p[1], "ы" .. p[1]} }, }, standard_chars = { Cyrl = "АаӘәБбВвГгҒғДдЕеЁёЖжЗзИиЙйКкҚқЛлМмНнҢңОоӨөПпРрСсТтУуҰұҮүФфХхҺһЦцЧчШшЩщЪъЫыІіЬьЭэЮюЯя", c.punc }, } m["kl"] = { "Greenlandic", 25355, "esx-inu", "Latn", sort_key = { from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } } m["km"] = { "Khmer", 9205, "mkh-kmr", "Khmr", ancestors = "xhm", translit = "km-translit", } m["kn"] = { "Kannada", 33673, "dra-kan", "Knda, Tutg", ancestors = "dra-mkn", -- Knda translit in [[Module:scripts/data]] } m["ko"] = { "Korean", 9176, "qfa-kor", "Kore, Brai", ancestors = "ko-ear", translit = { Kore = "ko-translit", }, -- Kore strip_diacritics in [[Module:scripts/data]] } m["kr"] = { "Kanuri", 36094, "ssa-sah", "Latn, Arab", -- the sortkey and strip_diacritics are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.breve} }, sort_key = { Latn = { from = {"ǝ", "ny", "ɍ", "sh"}, to = {"e" .. p[1], "n" .. p[1], "r" .. p[1], "s" .. p[1]} }, }, } m["ks"] = { "Kashmiri", 33552, "inc-kas", "ks-Arab, Deva, Shrd, Latn", translit = { ["ks-Arab"] = "ks-Arab-translit", Deva = "ks-Deva-translit", -- Shrd translit in [[Module:scripts/data]] }, } -- "kv" is treated as "koi", "kpv", see [[WT:LT]] m["kw"] = { "Cornish", 25289, "cel-brs", "Latn", ancestors = "cnx", sort_key = { from = {"ch"}, to = {"c" .. p[1]} }, } m["ky"] = { "Kyrgyz", 9255, "trk-kkp", "Cyrl, Latn, Arab", translit = { Cyrl = "ky-translit" }, override_translit = true, sort_key = { Cyrl = { from = {"ё", "ң", "ө", "ү"}, to = {"е" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, } m["la"] = { "Latin", 397, "itc-laf", "Latn, Ital", ancestors = "itc-ola", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) display_text = { Latn = s["itc-Latn-displaytext"] }, strip_diacritics = { Latn = s["itc-Latn-stripdiacritics"] }, sort_key = { Latn = s["itc-Latn-sortkey"] }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiLlMmNnOoPpQqRrSsTtUuVvXx", c.punc }, } m["lb"] = { "Luxembourgish", 9051, "gmw-hgm", "Latn, Brai", ancestors = "gmw-cfr", sort_key = { Latn = { from = {"ä", "ë", "é"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, }, } m["lg"] = { "Luganda", 33368, "bnt-nyg", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ŋ"}, to = {"n" .. p[1]} }, } m["li"] = { "Limburgish", 102172, "gmw-frk", "Latn", ancestors = "dum", } m["ln"] = { "Lingala", 36217, "bnt-bmo", "Latn", sort_key = { remove_diacritics = c.acute .. c.circ .. c.caron, from = {"ɛ", "gb", "mb", "mp", "nd", "ng", "nk", "ns", "nt", "ny", "nz", "ɔ"}, to = {"e" .. p[1], "g" .. p[1], "m" .. p[1], "m" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "n" .. p[4], "n" .. p[5], "n" .. p[6], "n" .. p[7], "o" .. p[1]} }, } m["lo"] = { "Lao", 9211, "tai-swe", "Laoo", -- also Tai Noi/Lao Buhan script translit = "lo-translit", sort_key = "Laoo-sortkey", standard_chars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. c.punc, } m["lt"] = { "Lithuanian", 9083, "bat-eas", "Latn", ancestors = "olt", display_text = "lt-common", strip_diacritics = "lt-common", sort_key = "lt-common", standard_chars = "AaĄąBbCcČčDdEeĘęĖėFfGgHhIiĮįYyJjKkLlMmNnOoPpRrSsŠšTtUuŲųŪūVvZzŽž" .. c.punc, } m["lu"] = { "Luba-Katanga", 36157, "bnt-lub", "Latn", } m["lv"] = { "Latvian", 9078, "bat-eas", "Latn", strip_diacritics = { -- 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 = {"([Ee])" .. c.cedilla, "[" .. c.grave .. c.circ .. c.tilde .."]", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .. "?([^aAeEiIoOuU])", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .."?$", "([iI])" .. c.tilde .. "?([eE])" .. c.tilde .. "?", "([aAeEiIuU])" .. c.tilde, c.tilde}, to = {"%1", c.tilde, "%1%2%3", "%1%2", "%1%2", "%1" .. c.macron} }, sort_key = { from = {"ā", "č", "ē", "ģ", "ī", "ķ", "ļ", "ņ", "š", "ū", "ž"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1]} }, standard_chars = "AaĀāBbCcČčDdEeĒēFfGgĢģHhIiĪīJjKkĶķLlĻļMmNnŅņOoPpRrSsŠšTtUuŪūVvZzŽž" .. c.punc, } m["mg"] = { "Malagasy", 7930, "poz-bre", "Latn, Arab", } m["mh"] = { "Marshallese", 36280, "poz-mic", "Latn", sort_key = { from = {"ā", "ļ", "m̧", "ņ", "n̄", "o̧", "ō", "ū"}, to = {"a" .. p[1], "l" .. p[1], "m" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "u" .. p[1]} }, } m["mi"] = { "Māori", 36451, "poz-pep", "Latn", sort_key = { remove_diacritics = c.macron, from = {"ng", "wh"}, to = {"n" .. p[1], "w" .. p[1]} }, } m["mk"] = { "Macedonian", 9296, "zls", "Cyrl, Polyt", ancestors = "cu", translit = { Cyrl = "mk-translit", -- FIXME: formerly no translit specified for Polyt; unclear if the default [[Module:grc-translit]] is -- acceptable, so we disable it for now Polyt = false, }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, remove_exceptions = {"Ѓ", "ѓ", "Ќ", "ќ"} }, }, sort_key = { Cyrl = { remove_diacritics = c.grave, remove_exceptions = {"ѓ", "ќ"}, from = {"ѓ", "ѕ", "ј", "љ", "њ", "ќ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Cyrl = "АаБбВвГгДдЃѓЕеЖжЗзЅѕИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЌќУуФфХхЦцЧчЏџШш", c.punc }, } m["ml"] = { "Malayalam", 36236, "dra-mal", "Mlym", override_translit = true, -- Mlym translit in [[Module:scripts/data]] } m["mn"] = { "Mongolian", 9246, "xgn-cen", "Cyrl, Mong, Latn, Brai", ancestors = "cmg", translit = { Cyrl = "mn-translit", -- Mong translit in [[Module:scripts/data]] }, override_translit = true, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] strip_diacritics = { Cyrl = {remove_diacritics = c.grave .. c.acute}, }, sort_key = { Cyrl = { remove_diacritics = c.grave, from = {"ё", "ө", "ү"}, to = {"е" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйЛлМмНнОоӨөРрСсТтУуҮүХхЦцЧчШшЫыЬьЭэЮюЯя—", Brai = c.braille, c.punc }, } -- "mo" is treated as "ro", see [[WT:LT]] m["mr"] = { "Marathi", 1571, "inc-sou", "Deva, Modi", ancestors = "omr", translit = { Deva = "mr-translit", Modi = "mr-Modi-translit", }, strip_diacritics = { Deva = { from = {"च़", "ज़", "झ़"}, to = {"च", "ज", "झ"} }, }, } m["ms"] = { "Malay", 9237, "poz-mly", "Latn, ms-Arab", ancestors = "ms-cla", standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", c.punc }, } m["mt"] = { "Maltese", 9166, "sem-arb", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { from = {"’"}, to = {"'"}, }, ancestors = "sqr", sort_key = { from = { "ċ", "ġ", "ż", -- Convert into PUA so that decomposed form does not get caught by the next step. "([cgz])", -- Ensure "c" comes after "ċ", "g" comes after "ġ" and "z" comes after "ż". "g" .. p[1] .. "ħ", -- "għ" after initial conversion of "g". p[3], p[4], "ħ", "ie", p[5] -- Convert "ċ", "ġ", "ħ", "ie", "ż" into final output. }, to = { p[3], p[4], p[5], "%1" .. p[1], "g" .. p[2], "c", "g", "h" .. p[1], "i" .. p[1], "z" } }, } m["my"] = { "Burmese", 9228, "tbq-brm", "Mymr", ancestors = "obr", translit = "my-translit", override_translit = true, sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"} }, } m["na"] = { "Nauruan", 13307, "poz-mic", "Latn", } m["nb"] = { "Norwegian Bokmål", 25167, "gmq", "Latn", wikimedia_codes = "no", ancestors = "gmq-mno, da", -- da as an (but not the) ancestor of nb was agreed on - do not change without discussion sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nd"] = { "Northern Ndebele", 35613, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["ne"] = { "Nepali", 33823, "inc-pah", "Deva, Newa", translit = { Deva = "ne-translit" }, } m["ng"] = { "Ndonga", 33900, "bnt-ova", "Latn", } m["nl"] = { "Dutch", 7411, "gmw-frk", "Latn, Brai", ancestors = "dum", sort_key = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'"}, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZzÄäËëÏïÖöÜü", Brai = c.braille, c.punc }, } m["nn"] = { "Norwegian Nynorsk", 25164, "gmq-wes", "Latn", ancestors = "gmq-mno", strip_diacritics = { remove_diacritics = c.grave .. c.acute, }, sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["no"] = { "Norwegian", 9043, "gmq-wes", "Latn", ancestors = "gmq-mno", sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nr"] = { "Southern Ndebele", 36785, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["nv"] = { "Navajo", 13310, "apa", "Latn, Brai", sort_key = { remove_diacritics = c.acute .. c.ogonek, from = { "chʼ", "tłʼ", "tsʼ", -- 3 chars "ch", "dl", "dz", "gh", "hw", "kʼ", "kw", "sh", "tł", "ts", "zh", -- 2 chars "ł", "ʼ" -- 1 char }, to = { "c" .. p[2], "t" .. p[2], "t" .. p[4], "c" .. p[1], "d" .. p[1], "d" .. p[2], "g" .. p[1], "h" .. p[1], "k" .. p[1], "k" .. p[2], "s" .. p[1], "t" .. p[1], "t" .. p[3], "z" .. p[1], "l" .. p[1], "z" .. p[2] } }, } m["ny"] = { "Chichewa", 33273, "bnt-nys", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ng'"}, to = {"ng"} }, } m["oc"] = { "Occitan", 14185, "roa-ocr", "Latn, Hebr", ancestors = "pro", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla, from = {"([lns])·h"}, to = {"%1h"} }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["oj"] = { "Ojibwe", 33875, "alg", "Cans, Latn", sort_key = { Latn = { from = {"aa", "ʼ", "ii", "oo", "sh", "zh"}, to = {"a" .. p[1], "h" .. p[1], "i" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1]} }, }, } m["om"] = { "Oromo", 33864, "cus-eas", "Latn, Ethi", } m["or"] = { "Odia", 33810, "inc-eas", "Orya", ancestors = "inc-mor", translit = "or-translit", } m["os"] = { "Ossetian", 33968, "xsc-sar", "Cyrl, Geor, Latn", ancestors = "oos", translit = { Cyrl = "os-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = { from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, sort_key = { Cyrl = { from = {"ӕ", "гъ", "дж", "дз", "ё", "къ", "пъ", "тъ", "хъ", "цъ", "чъ"}, to = {"а" .. p[1], "г" .. p[1], "д" .. p[1], "д" .. p[2], "е" .. p[1], "к" .. p[1], "п" .. p[1], "т" .. p[1], "х" .. p[1], "ц" .. p[1], "ч" .. p[1]} }, }, } m["pa"] = { "Punjabi", 58635, "inc-pan", "Guru, pa-Arab", translit = { Guru = "Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = { ["pa-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna, from = {"ݨ", "ࣇ"}, to = {"ن", "ل"} }, }, } m["pi"] = { "Pali", 36727, "inc-mid", "Latn, Brah, Deva, Beng, Sinh, Mymr, Thai, Lana, Laoo, Khmr, Cakm", --and also Khom ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Beng = "pi-translit", Sinh = "si-translit", Mymr = "pi-translit", Thai = "pi-translit", Lana = "pi-translit", Laoo = "pi-translit", Khmr = "pi-translit", Cakm = "Cakm-translit", }, strip_diacritics = { Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, Mymr = { remove_diacritics = c.VS01, }, }, sort_key = { -- FIXME: This needs to be converted into the current standardized format. from = {"ā", "ī", "ū", "ḍ", "ḷ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"} }, } m["pl"] = { "Polish", 809, "zlw-lch", "Latn", ancestors = "zlw-mpl", sort_key = { from = {"ą", "ć", "ę", "ł", "ń", "ó", "ś", "ź", "ż"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaĄąBbCcĆćDdEeĘęFfGgHhIiJjKkLlŁłMmNnŃńOoÓóPpRrSsŚśTtUuWwYyZzŹźŻż" .. c.punc, } m["ps"] = { "Pashto", 58680, "ira-pat", "ps-Arab", strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.zwarakay .. c.superalef}, } m["pt"] = { "Portuguese", 5146, "roa-gap", "Latn, Brai", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "º", "œ"}, to = {"a", "ae", "o", "oe"} }, }, standard_chars = { Latn = "AaÁáÂâÃãBbCcÇçDdEeÉéÊêFfGgHhIiÍíJjLlMmNnOoÓóÔôÕõPpQqRrSsTtUuÚúVvXxZz", Brai = c.braille, c.punc }, } m["qu"] = { "Quechua", 5218, "qwe", "Latn", } m["rm"] = { "Romansh", 13199, "roa-rhe", ancestors = "rm-old", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.small_e}, } m["ro"] = { "Romanian", 7913, "roa-eas", "Latn, Cyrl, Cyrs", translit = { Cyrl = "ro-translit" }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute, from = {"ă", "â", "î", "ș", "ț"}, to = {"a" .. p[1], "a" .. p[2], "i" .. p[1], "s" .. p[1], "t" .. p[1]} }, Cyrl = { from = {"ӂ"}, to = {"ж" .. p[1]} }, }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; presumably not present standard_chars = { Latn = "AaĂăÂâBbCcDdEeFfGgHhIiÎîJjLlMmNnOoPpRrSsȘșTtȚțUuVvXxZz", Cyrl = "АаБбВвГгДдЕеЖжӁӂЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЫыЬьЭэЮюЯя", c.punc }, } m["ru"] = { "Russian", 7737, "zle", "Cyrl, Brai", ancestors = "zle-mru", translit = { Cyrl = "ru-translit" }, display_text = { Cyrl = { from = {"'"}, to = {"’"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, remove_exceptions = {"Ё", "ё", "Ѣ̈", "ѣ̈", "Я̈", "я̈"}, from = {"’"}, to = {"'"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, from = { "і", "ѣ", "ѳ", "ѵ" }, to = { "и" .. p[1], "ь" .. p[1], "я" .. p[2], "я" .. p[3] } }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЫыЬьЭэЮюЯя—", Brai = c.braille, (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["rw"] = { "Rwanda-Rundi", 3217514, "bnt-glb", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.caron}, } m["sa"] = { "Sanskrit", 11059, "inc", "as-Beng, Bali, Beng, Bhks, Brah, Mymr, xwo-Mong, Deva, Gujr, Guru, Gran, Hani, Java, Kthi, Knda, Kawi, Khar, Khmr, Laoo, Mlym, mnc-Mong, Marc, Modi, Mong, Nand, Newa, Orya, Phag, Ranj, Saur, Shrd, Sidd, Sinh, Soyo, Lana, Takr, Taml, Tang, Telu, Thai, Tibt, Tutg, Tirh, Zanb", --and also Khom; script codes sorted by canonical name rather than code for [[MOD:sa-convert]] translit = { Beng = "sa-Beng-translit", ["as-Beng"] = "sa-Beng-translit", -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Gujr = "sa-Gujr-translit", Guru = "sa-Guru-translit", Java = "sa-Java-translit", Kthi = "sa-Kthi-translit", Khmr = "pi-translit", Knda = "sa-Knda-translit", Lana = "pi-translit", Laoo = "pi-translit", Mlym = "sa-Mlym-translit", Modi = "sa-Modi-translit", -- Mong, mnc-Mong, xwo-Mong translit in [[Module:scripts/data]] -- NOTE: Formerly used xal-translit for transliterating xwo-Mong but that only handles Cyrillic; it has -- code to transliterate xwo-Mong but it's broken so I've replaced it with the default xwo-translit. Mymr = "pi-translit", Orya = "sa-Orya-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] Sinh = "si-translit", Taml = "sa-Taml-translit", Telu = "sa-Telu-translit", Thai = "pi-translit", -- Tibt translit in [[Module:scripts/data]] }, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] -- Tibt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] strip_diacritics = { Deva = s["sa-Deva-stripdiacritics"], Mymr = { remove_diacritics = c.VS01, }, Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, }, sort_key = { Deva = s["sa-Deva-stripdiacritics"], -- until we have a proper Sanskrit sorting algorithm. Lana = { -- Tai Tham from = {"ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ"}, to = {"ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}, }, Laoo = "Laoo-sortkey", Latn = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ"}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~"}, }, Mymr = { remove_diacritics = c.VS01, }, Thai = "Thai-sortkey", -- FIXME: The previous sort key which mixed all scripts removed ZWJ; I don't know which script(s) this was -- intended for and there are no other languages which remove it in the sort key AFAIK. If it needs to be -- removed, specify the script(s) it needs to be removed under or add handling for the "all" script that applies -- regardless of script. --all = { -- remove_diacritics = c.ZWJ, --}, }, } m["sc"] = { "Sardinian", 33976, "roa-sou", "Latn", ancestors = "sc-old", } m["sd"] = { "Sindhi", 33997, "inc-snd", "sd-Arab, Deva, Sind, Khoj", translit = { Sind = "Sind-translit", ["sd-Arab"] = "sd-Arab-translit" }, strip_diacritics = { ["sd-Arab"] = { remove_diacritics = c.kashida .. c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, from = {"ٱ"}, to = {"ا"} }, }, } m["se"] = { "Northern Sami", 33947, "smi", "Latn", display_text = { from = {"'"}, to = {"ˈ"} }, strip_diacritics = {remove_diacritics = c.macron .. c.dotbelow .. "'ˈ"}, sort_key = { from = {"á", "č", "đ", "ŋ", "š", "ŧ", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "n" .. p[1], "s" .. p[1], "t" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĐđEeFfGgHhIiJjKkLlMmNnŊŋOoPpRrSsŠšTtŦŧUuVvZzŽž" .. c.punc, } m["sg"] = { "Sango", 33954, "crp", "Latn", ancestors = "ngb", } m["sh"] = { "Serbo-Croatian", 9301, "zls", "Latn, Cyrl, Glag, Arab", ietf_subtag = "hbs", -- ISO 639-3 code, since "sh" is deprecated from ISO 639-1 wikimedia_codes = "sh, bs, hr, sr", strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"Ć", "ć", "Ś", "ś", "Ź", "ź"} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"З́", "з́", "С́", "с́"} }, }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"ć", "ś", "ź"}, from = {"č", "ć", "dž", "đ", "lj", "nj", "š", "ś", "ž", "ź"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "z" .. p[1], "z" .. p[2]} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"з́", "с́"}, from = {"ђ", "з́", "ј", "љ", "њ", "с́", "ћ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "с" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, standard_chars = { Latn = "AaBbCcČčĆćDdĐđEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž", Cyrl = "АаБбВвГгДдЂђЕеЖжЗзИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЋћУуФфХхЦцЧчЏџШш", c.punc }, } m["si"] = { "Sinhalese", 13267, "inc-ins", "Sinh", translit = "si-translit", override_translit = true, } m["sk"] = { "Slovak", 9058, "zlw", "Latn", ancestors = "zlw-osk", sort_key = {remove_diacritics = c.acute .. c.circ .. c.diaer .. c.caron}, standard_chars = "AaÁáÄäBbCcČčDdĎďEeÉéFfGgHhIiÍíJjKkLlĹ弾MmNnŇňOoÓóÔôPpRrŔŕSsŠšTtŤťUuÚúVvYyÝýZzŽž" .. c.punc, } m["sl"] = { "Slovene", 9063, "zls", "Latn", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.dgrave .. c.invbreve .. c.dotbelow, remove_exceptions = {"Ć", "ć", "Ǵ", "ǵ", "Ś", "ś", "Ź", "ź"}, from = {"Ə", "ə", "Ł", "ł"}, to = {"E", "e", "L", "l"}, }, sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dotabove .. c.ringabove .. c.dgrave .. c.invbreve .. c.dotbelow .. c.ringbelow .. c.ogonek, remove_exceptions = {"ć", "ǵ", "ś", "ź"}, from = {"ä", "č", "ć", "đ", "ə", "ë", "ǧ", "ǵ", "ï", "ł", "ö", "š", "ś", "ü", "ž", "ź"}, to = {"a" .. p[1], "c" .. p[1], "c" .. p[2], "d" .. p[1], "e", "e" .. p[1], "g" .. p[1], "g" .. p[2], "i" .. p[1], "l", "o" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]}, }, standard_chars = "AaBbCcČčDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž" .. c.punc, } m["sm"] = { "Samoan", 34011, "poz-pnp", "Latn", } m["sn"] = { "Shona", 34004, "bnt-sho", "Latn", strip_diacritics = {remove_diacritics = c.acute}, } m["so"] = { "Somali", 13275, "cus-som", "Latn, Arab, Osma", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, } m["sq"] = { "Albanian", 8748, "sqj", "Latn, Grek, ota-Arab, Elba, Todr, Vith", translit = { Elba = "Elba-translit", Vith = "Vith-translit", }, -- Grek display_text, sort_key in [[Module:scripts/data]] strip_diacritics = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron, from = {'^[ie] (%w)', '^të (%w)'}, to = {'%1', '%1'}, }, Grek = { -- Diacritic removal from Grek-stripdiacritics excluded. from = m_langdata.chars_substitutions["Grek-stripdiacritics"].from, to = m_langdata.chars_substitutions["Grek-stripdiacritics"].to, }, }, sort_key = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron .. c.tilde .. c.breve .. c.caron, from = {'^[ie] (%w)', '^të (%w)', 'ç', 'dh', 'ë', 'gj', 'll', 'nj', 'rr', 'sh', 'th', 'xh', 'zh'}, to = {'%1', '%1', 'c'..p[1], 'd'..p[1], 'e'..p[1], 'g'..p[1], 'l'..p[1], 'n'..p[1], 'r'..p[1], 's'..p[1], 't'..p[1], 'x'..p[1], 'z'..p[1]}, } -- TODO: Grek if the default sort key is unsuitable }, standard_chars = { Latn = "AaBbCcÇçDdEeËëFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvXxYyZz", c.punc }, } m["ss"] = { "Swazi", 34014, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["st"] = { "Sotho", 34340, "bnt-sts", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["su"] = { "Sundanese", 34002, "poz-msa", "Latn, Sund, Arab", ancestors = "osn", translit = { Sund = "Sund-translit" }, } m["sv"] = { "Swedish", 9027, "gmq-eas", "Latn", ancestors = "gmq-osw-lat", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla .. "':", remove_exceptions = {"å"}, from = {"ø", "æ", "œ", "ß", "å", "aͤ", "oͤ"}, to = {"o", "ae", "oe", "ss", "z" .. p[1], "ä", "ö"} }, standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvXxYyÅåÄäÖö" .. c.punc, } m["sw"] = { "Swahili", 7838, "bnt-swh", "Latn, Arab", sort_key = { Latn = { from = {"ng'"}, to = {"ng" .. p[1]} }, }, } m["ta"] = { "Tamil", 5885, "dra-tam", "Taml", ancestors = "ta-mid", translit = "ta-translit", override_translit = true, } m["te"] = { "Telugu", 8097, "dra-tel", "Telu", translit = "te-translit", override_translit = true, } m["tg"] = { "Tajik", 9260, "ira-swi", "Cyrl, fa-Arab, Latn", ancestors = "fa-cls", translit = { Cyrl = "tg-translit" }, override_translit = true, strip_diacritics = { Cyrl = s["tg-stripdiacritics"], Latn = s["tg-stripdiacritics"], }, sort_key = { Cyrl = { from = {"ғ", "ё", "ӣ", "қ", "ӯ", "ҳ", "ҷ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "к" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["th"] = { "Thai", 9217, "tai-swe", "Thai, Khomt, Brai", translit = { Thai = "th-translit" }, sort_key = { Thai = "Thai-sortkey" }, } m["ti"] = { "Tigrinya", 34124, "sem-eth", "Ethi", translit = "Ethi-translit", } m["tk"] = { "Turkmen", 9267, "trk-ogz", "Latn, Cyrl, Arab", strip_diacritics = { Latn = s["tk-stripdiacritics"], Cyrl = s["tk-stripdiacritics"], }, sort_key = { Latn = { from = {"ç", "ä", "ž", "ň", "ö", "ş", "ü", "ý"}, to = {"c" .. p[1], "e" .. p[1], "j" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "y" .. p[1]} }, Cyrl = { from = {"ё", "җ", "ң", "ө", "ү", "ә"}, to = {"е" .. p[1], "ж" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "э" .. p[1]} }, }, ancestors = "trk-eog", } m["tl"] = { "Tagalog", 34057, "phi", "Latn, Tglg", translit = { Tglg = "tl-translit" }, override_translit = true, strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, standard_chars = { Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy", c.punc }, sort_key = { Latn = "tl-sortkey", }, } m["tn"] = { "Tswana", 34137, "bnt-sts", "Latn", } m["to"] = { "Tongan", 34094, "poz-ton", "Latn", strip_diacritics = {remove_diacritics = c.acute}, sort_key = {remove_diacritics = c.macron}, } m["tr"] = { "Turkish", 256, "trk-ogz", "Latn", ancestors = "ota", dotted_dotless_i = true, sort_key = { from = { -- Ignore circumflex, but account for capital Î wrongly becoming ı + circ due to dotted dotless I logic. "ı" .. c.circ, c.circ, "i", -- Ensure "i" comes after "ı". "ç", "ğ", "ı", "ö", "ş", "ü" }, to = { "i", "", "i" .. p[1], "c" .. p[1], "g" .. p[1], "i", "o" .. p[1], "s" .. p[1], "u" .. p[1] } }, standard_chars = "AaÂâBbCcÇçDdEeFfGgĞğHhIıİiÎîJjKkLlMmNnOoÖöPpRrSsŞşTtUuÛûÜüVvYyZz" .. c.punc, } m["ts"] = { "Tsonga", 34327, "bnt-tsr", "Latn", } m["tt"] = { "Tatar", 25285, "trk-kbu", "Cyrl, Latn, tt-Arab", translit = { Cyrl = "tt-translit", ["tt-Arab"] = "tt-translit" }, --override_translit = true, -- enable override until Module code can detect Russian loans such as [[аэропорт]] dotted_dotless_i = true, sort_key = { Cyrl = { from = {"ә", "ў", "ғ", "ё", "җ", "қ", "ң", "ө", "ү", "һ"}, to = {"а" .. p[1], "в" .. p[1], "г" .. p[1], "е" .. p[1], "ж" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1]} }, Latn = { from = { "i", -- Ensure "i" comes after "ı". "ä", "ə", "ç", "ğ", "ı", "ñ", "ŋ", "ö", "ɵ", "ş", "ü" }, to = { "i" .. p[1], "a" .. p[1], "a" .. p[2], "c" .. p[1], "g" .. p[1], "i", "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "s" .. p[1], "u" .. p[1] } }, }, } -- "tw" is treated as "ak", see [[WT:LT]] m["ty"] = { "Tahitian", 34128, "poz-pep", "Latn", } m["ug"] = { "Uyghur", 13263, "trk-kar", "ug-Arab, Latn, Cyrl", ancestors = "chg", translit = { ["ug-Arab"] = "ug-translit", Cyrl = "ug-translit", }, override_translit = true, } m["uk"] = { "Ukrainian", 8798, "zle", "Cyrl", ancestors = "zle-muk", translit = "uk-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, sort_key = { remove_diacritics = c.grave .. c.acute, from = { "ї", -- 2 chars "ґ", "є", "і" -- 1 char }, to = { "и" .. p[2], "г" .. p[1], "е" .. p[1], "и" .. p[1] } }, standard_chars = "АаБбВвГгДдЕеЄєЖжЗзИиІіЇїЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЬьЮюЯя" .. c.punc:gsub("'", ""), -- Exclude apostrophe. } m["ur"] = { "Urdu", 1617, "inc-hnd", "ur-Arab, Hebr", translit = { ["ur-Arab"] = "ur-translit" }, strip_diacritics = { ["ur-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ۂ", "ٱ"}, to = {"ہ", "ہ", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { ["ur-Arab"] = "ایببپتثجچحخدذرزژسشصضطظعغفقکگلࣇڷمنݨوؤہھئٹڈڑآے", c.punc, }, } m["uz"] = { "Uzbek", 9264, "trk-kar", "Latn, Cyrl, fa-Arab", ancestors = "chg", translit = { Cyrl = "uz-translit" }, sort_key = { Latn = { from = {"oʻ", "gʻ", "sh", "ch", "ng"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3], "z" .. p[4], "z" .. p[5]} }, Cyrl = { from = {"ё", "ў", "қ", "ғ", "ҳ"}, to = {"е" .. p[1], "я" .. p[1], "я" .. p[2], "я" .. p[3], "я" .. p[4]} }, }, strip_diacritics = { ["fa-Arab"] = "ar-stripdiacritics", }, } m["ve"] = { "Venda", 32704, "bnt-bso", "Latn", } m["vi"] = { "Vietnamese", 9199, "mkh-vie", "Latn, Hani", ancestors = "mkh-mvi", sort_key = { Latn = "vi-sortkey", Hani = "Hani-sortkey", }, } m["vo"] = { "Volapük", 36986, "art", "Latn", } m["wa"] = { "Walloon", 34219, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["wo"] = { "Wolof", 34257, "alv-fwo", "Latn, Arab, Gara", } m["xh"] = { "Xhosa", 13218, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["yi"] = { "Yiddish", 8641, "gmw-hgm", "Hebr, Latn", ancestors = "gmh", translit = { Hebr = "yi-translit", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["yo"] = { "Yoruba", 34311, "alv-yor", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.macron} }, sort_key = { Latn = { from = {"ẹ", "ɛ", "gb", "ị", "kp", "ọ", "ɔ", "ṣ", "sh", "ụ"}, to = {"e" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "o" .. p[1], "o" .. p[1], "s" .. p[1], "s" .. p[1], "u" .. p[1]} }, }, } m["za"] = { "Zhuang", 13216, "tai", "Latn, Hani", sort_key = { Latn = "za-sortkey", Hani = "Hani-sortkey", }, } m["zh"] = { "Chinese", 7850, "zhx", "Hants, Latn, Bopo, Nshu, Brai", ancestors = "ltc", generate_forms = "zh-generateforms", translit = { Hani = "zh-translit", Bopo = "zh-translit", }, sort_key = { Hani = "Hani-sortkey" }, } m["zu"] = { "Zulu", 10179, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } return require("Module:languages").finalizeData(m, "language") 0m6ennhmvoyt6gbvvrn6ae6qo3n5rac 231383 231382 2026-04-14T07:48:28Z Lee 19 [[:en:Module:languages/data/2]] වෙතින් එක් සංශෝධනයක් 231382 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared -- Ideally, we want to move these into [[Module:languages/data]], but because (a) it's necessary to use require on that module, and (b) they're only used in this data module, it's less memory-efficient to do that at the moment. If it becomes possible to use mw.loadData, then these should be moved there. s["de-Latn-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove, from = {"æ", "œ", "ß"}, to = {"ae", "oe", "ss"} } s["de-Latn-standardchars"] = "AaÄäBbCcDdEeFfGgHhIiJjKkLlMmNnOoÖöPpQqRrSsẞßTtUuÜüVvWwXxYyZz" s["ka-stripdiacritics"] = {remove_diacritics = c.circ} s["no-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } s["no-standardchars"] = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc s["sa-Deva-stripdiacritics"] = { -- Don't use remove_diacritics for accent marks, as १ and ३ should also be removed if (and only if) they carry any. from = {"[१३]?[" .. c.anudatta .. c.udatta .. c.dsvarita .. c.tsvarita .. "]+"}, to = {""}, } s["tg-stripdiacritics"] = {remove_diacritics = c.grave .. c.acute} s["tk-stripdiacritics"] = {remove_diacritics = c.macron} local m = {} m["aa"] = { "Afar", 27811, "cus-eas", "Latn, Ethi", strip_diacritics = { Latn = {remove_diacritics = c.acute}, }, } m["ab"] = { "Abkhaz", 5111, "cau-abz", "Cyrl, Geor, Latn", translit = { Cyrl = "ab-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, from = {"^а%-"}, to = {"а"}, }, Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = { "х'ә", -- 3 chars "гь", "гә", "ӷь", "ҕь", "ӷә", "ҕә", "дә", "ё", "жь", "жә", "ҙә", "ӡә", "ӡ'", "кь", "кә", "қь", "қә", "ҟь", "ҟә", "ҫә", "тә", "ҭә", "ф'", "хь", "хә", "х'", "ҳә", "ць", "цә", "ц'", "ҵә", "ҵ'", "шь", "шә", "џь", -- 2 chars "ӷ", "ҕ", "ҙ", "ӡ", "қ", "ҟ", "ԥ", "ҧ", "ҫ", "ҭ", "ҳ", "ҵ", "ҷ", "ҽ", "ҿ", "ҩ", "џ", "ә", -- 1 char "^а", }, to = { "х" .. p[4], "г" .. p[1], "г" .. p[2], "г" .. p[5], "г" .. p[6], "г" .. p[7], "г" .. p[8], "д" .. p[1], "е" .. p[1], "ж" .. p[1], "ж" .. p[2], "з" .. p[2], "з" .. p[4], "з" .. p[5], "к" .. p[1], "к" .. p[2], "к" .. p[4], "к" .. p[5], "к" .. p[7], "к" .. p[8], "с" .. p[2], "т" .. p[1], "т" .. p[3], "ф" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[6], "ц" .. p[1], "ц" .. p[2], "ц" .. p[3], "ц" .. p[5], "ц" .. p[6], "ш" .. p[1], "ш" .. p[2], "ы" .. p[3], "г" .. p[3], "г" .. p[4], "з" .. p[1], "з" .. p[3], "к" .. p[3], "к" .. p[6], "п" .. p[1], "п" .. p[2], "с" .. p[1], "т" .. p[2], "х" .. p[5], "ц" .. p[4], "ч" .. p[1], "ч" .. p[2], "ч" .. p[3], "ы" .. p[1], "ы" .. p[2], "ь" .. p[1], "", } }, }, } m["ae"] = { "Avestan", 29572, "ira-cen", "Avst, Gujr, Deva", translit = { Avst = "Avst-translit" }, } m["af"] = { "Afrikaans", 14196, "gmw-frk", "Latn, Arab", ancestors = "nl", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'", from = {"['ʼ]n"}, to = {"n" .. p[1]} } }, } m["ak"] = { "Akan", 28026, "alv-ctn", "Latn", } m["am"] = { "Amharic", 28244, "sem-eth", "Ethi", translit = "Ethi-translit", } m["an"] = { "Aragonese", 8765, "roa-nar", "Latn", } m["ar"] = { "Arabic", 13955, "sem-arb", "Arab, Hebr, Syrc, Brai, Nbat", translit = { Arab = "ar-translit" }, strip_diacritics = { Arab = "ar-stripdiacritics", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["as"] = { "Assamese", 29401, "inc-bas", "as-Beng", ancestors = "inc-mas", translit = "as-translit", } m["av"] = { "Avar", 29561, "cau-ava", "Cyrl, Latn, Arab", ancestors = "oav", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"], }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"гъ", "гь", "гӏ", "ё", "кк", "къ", "кь", "кӏ", "лъ", "лӏ", "тӏ", "хх", "хъ", "хь", "хӏ", "цӏ", "чӏ"}, to = {"г" .. p[1], "г" .. p[2], "г" .. p[3], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "к" .. p[4], "л" .. p[1], "л" .. p[2], "т" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[4], "ц" .. p[1], "ч" .. p[1]} }, }, } m["ay"] = { "Aymara", 4627, "sai-aym", "Latn", } m["az"] = { "Azerbaijani", 9292, "trk-ogz", "Latn, Cyrl, fa-Arab", ancestors = "trk-oat", dotted_dotless_i = true, strip_diacritics = { Latn = { from = {"ʼ"}, to = {"'"}, }, ["fa-Arab"] = { module = "ar-stripdiacritics", ["from"] = { "ۆ", "ۇ", "وْ", "ڲ", "ؽ", }, ["to"] = { "و", "و", "و", "گ", "ی", }, }, }, display_text = { Latn = { from = {"'"}, to = {"ʼ"} } }, sort_key = { Latn = { from = { "i", -- Ensure "i" comes after "ı". "ç", "ə", "ğ", "x", "ı", "q", "ö", "ş", "ü", "w" }, to = { "i" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "h" .. p[1], "i", "k" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1] } }, Cyrl = { from = {"ғ", "ә", "ы", "ј", "ҝ", "ө", "ү", "һ", "ҹ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "и" .. p[2], "к" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["ba"] = { "Bashkir", 13389, "trk-kbu", "Cyrl", translit = "ba-translit", override_translit = true, sort_key = { from = {"ғ", "ҙ", "ё", "ҡ", "ң", "ө", "ҫ", "ү", "һ", "ә"}, to = {"г" .. p[1], "д" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "с" .. p[1], "у" .. p[1], "х" .. p[1], "э" .. p[1]} }, } m["be"] = { "Belarusian", 9091, "zle", "Cyrl, Latn", ancestors = "zle-mbe", translit = { Cyrl = "be-translit", }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"ґ", "ё", "і", "ў"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "у" .. p[1]} }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, from = {"ć", "č", "dz", "dź", "dž", "ch", "ł", "ń", "ś", "š", "ŭ", "ź", "ž"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "d" .. p[3], "h" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзІіЙйКкЛлМмНнОоПпРрСсТтУуЎўФфХхЦцЧчШшЫыЬьЭэЮюЯя", Latn = "AaBbCcĆćČčDdEeFfGgHhIiJjKkLlŁłMmNnŃńOoPpRrSsŚśŠšTtUuŬŭVvYyZzŹźŽž", (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["bg"] = { "Bulgarian", 7918, "zls", "Cyrl", ancestors = "cu-bgm", translit = "bg-translit", strip_diacritics = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, sort_key = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, standard_chars = "АаБбВвГгДдЕеЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЬьЮюЯя" .. c.punc, } m["bh"] = { "Bihari", 135305, "inc-eas", "Deva", } m["bi"] = { "Bislama", 35452, "crp", "Latn", ancestors = "en", } m["bm"] = { "Bambara", 33243, "dmn-emn", "Latn, Nkoo", sort_key = { Latn = { from = {"ɛ", "ɲ", "ŋ", "ɔ"}, to = {"e" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1]} }, }, } m["bn"] = { "Bengali", 9610, "inc-bas", "Beng, Newa", ancestors = "inc-mbn", translit = { Beng = "bn-translit" }, } m["bo"] = { "Tibetan", 34271, "sit-tib", "Tibt", -- sometimes Deva? ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["br"] = { "Breton", 12107, "cel-brs", "Latn", ancestors = "xbm", sort_key = { from = {"ch", "c['ʼ’]h"}, to = {"c" .. p[1], "c" .. p[2]} }, } m["ca"] = { "Catalan", 7026, "roa-ocr", "Latn", ancestors = "roa-oca", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, standard_chars = "AaÀàBbCcÇçDdEeÉéÈèFfGgHhIiÍíÏïJjLlMmNnOoÓóÒòPpQqRrSsTtUuÚúÜüVvXxYyZz·" .. c.punc, } m["ce"] = { "Chechen", 33350, "cau-vay", "Cyrl, Latn, Arab", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"аь", "гӏ", "ё", "кх", "къ", "кӏ", "оь", "пӏ", "тӏ", "уь", "хь", "хӏ", "цӏ", "чӏ", "юь", "яь"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "о" .. p[1], "п" .. p[1], "т" .. p[1], "у" .. p[1], "х" .. p[1], "х" .. p[2], "ц" .. p[1], "ч" .. p[1], "ю" .. p[1], "я" .. p[1]} }, }, } m["ch"] = { "Chamorro", 33262, "poz", "Latn", sort_key = { remove_diacritics = "'", from = {"å", "ch", "ñ", "ng"}, to = {"a" .. p[1], "c" .. p[1], "n" .. p[1], "n" .. p[2]} }, } m["co"] = { "Corsican", 33111, "roa-itr", "Latn", sort_key = { from = {"chj", "ghj", "sc", "sg"}, to = {"c" .. p[1], "g" .. p[1], "s" .. p[1], "s" .. p[2]} }, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìÏïJjLlMmNnOoÒòPpQqRrSsTtUuÙùÜüVvZz" .. c.punc, } m["cr"] = { "Cree", 33390, "alg", "Latn, Cans", translit = { Cans = "cr-translit" }, } m["cs"] = { "Czech", 9056, "zlw", "Latn", ancestors = "cs-ear", sort_key = { from = {"á", "č", "ď", "é", "ě", "ch", "í", "ň", "ó", "ř", "š", "ť", "ú", "ů", "ý", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "h" .. p[1], "i" .. p[1], "n" .. p[1], "o" .. p[1], "r" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "y" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĎďEeÉéĚěFfGgHhIiÍíJjKkLlMmNnŇňOoÓóPpRrŘřSsŠšTtŤťUuÚúŮůVvYyÝýZzŽž" .. c.punc, } m["cu"] = { "Old Church Slavonic", 35499, "zls", "Cyrs, Glag, Zname", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["cv"] = { "Chuvash", 33348, "trk-ogr", "Cyrl", ancestors = "cv-mid", translit = "cv-translit", override_translit = true, sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = {"а" .. p[1], "е" .. p[1], "е" .. p[2], "с" .. p[1], "у" .. p[1]} }, } m["cy"] = { "Welsh", 9309, "cel-brw", "Latn", ancestors = "wlm", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. "'", from = {"ch", "dd", "ff", "ng", "ll", "ph", "rh", "th"}, to = {"c" .. p[1], "d" .. p[1], "f" .. p[1], "g" .. p[1], "l" .. p[1], "p" .. p[1], "r" .. p[1], "t" .. p[1]} }, standard_chars = "ÂâAaBbCcDdEeÊêFfGgHhIiÎîLlMmNnOoÔôPpRrSsTtUuÛûWwŴŵYyŶŷ" .. c.punc, } m["da"] = { "Danish", 9035, "gmq-eas", "Latn", ancestors = "gmq-oda", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc, } m["de"] = { "German", 188, "gmw-hgm", "Latn, Latf, Brai", ancestors = "de-ear", sort_key = { Latn = s["de-Latn-sortkey"], Latf = s["de-Latn-sortkey"], }, standard_chars = { Latn = s["de-Latn-standardchars"], Latf = s["de-Latn-standardchars"], Brai = c.braille, c.punc } } m["dv"] = { "Dhivehi", 32656, "inc-ins", "Thaa, Diak", translit = { Thaa = "dv-translit", Diak = "Diak-translit", }, ancestors = "dv-old", override_translit = true, } m["dz"] = { "Dzongkha", 33081, "sit-tib", "Tibt", ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ee"] = { "Ewe", 30005, "alv-gbe", "Latn", sort_key = { remove_diacritics = c.tilde, from = {"ɖ", "dz", "ɛ", "ƒ", "gb", "ɣ", "kp", "ny", "ŋ", "ɔ", "ts", "ʋ"}, to = {"d" .. p[1], "d" .. p[2], "e" .. p[1], "f" .. p[1], "g" .. p[1], "g" .. p[2], "k" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "t" .. p[1], "v" .. p[1]} }, } m["el"] = { "Greek", 9129, "grk", "Grek, Polyt, Brai", ancestors = "el-kth", translit = "el-translit", override_translit = true, -- Grek and Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Grek = "΅·ͺ΄ΑαΆάΒβΓγΔδΕεέΈΖζΗηΉήΘθΙιΊίΪϊΐΚκΛλΜμΝνΞξΟοΌόΠπΡρΣσςΤτΥυΎύΫϋΰΦφΧχΨψΩωΏώ", Brai = c.braille, c.punc }, } m["en"] = { "English", 1860, "gmw-ang", "Latn, Brai, Shaw, Dsrt", -- entries in Shaw or Dsrt might require prior discussion wikimedia_codes = "en, simple", ancestors = "en-ear", sort_key = { Latn = { -- Many of these are needed for sorting language names. remove_diacritics = "'\"%-%.,%s·ʻʼ" .. c.diacritics, -- These are found in pagenames. from = {"[ɒæ🅱¢©ᴄðđəǝɜɡħʜıɨłŋɲøɔœꝑꝓꝕßʋ]"}, to = {{ ["ɒ"] = "a", ["æ"] = "ae", ["🅱"] = "b", ["¢"] = "c", ["©"] = "c", ["ᴄ"] = "c", ["ð"] = "d", ["đ"] = "d", ["ə"] = "e", ["ǝ"] = "e", ["ɜ"] = "e", ["ɡ"] = "g", ["ħ"] = "h", ["ʜ"] = "h", ["ı"] = "i", ["ɨ"] = "i", ["ł"] = "l", ["ŋ"] = "n", ["ɲ"] = "n", ["ø"] = "o", ["ɔ"] = "o", ["œ"] = "oe", ["ꝑ"] = "p", ["ꝓ"] = "p", ["ꝕ"] = "p", ["ß"] = "ss", ["ʋ"] = "v", }}, }, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", Brai = c.braille, c.punc }, } m["eo"] = { "Esperanto", 143, "art", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute, from = {"ĉ", "ĝ", "ĥ", "ĵ", "ŝ", "ŭ"}, to = {"c" .. p[1], "g" .. p[1], "h" .. p[1], "j" .. p[1], "s" .. p[1], "u" .. p[1]} }, standard_chars = "AaBbCcĈĉDdEeFfGgĜĝHhĤĥIiJjĴĵKkLlMmNnOoPpRrSsŜŝTtUuŬŭVvZz" .. c.punc, } m["es"] = { "Spanish", 1321, "roa-cas", "Latn, Brai", ancestors = "es-ear", sort_key = { Latn = { remove_exceptions = {"ñ"}, remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "ñ", "º", "œ"}, to = {"a", "ae", "n" .. p[1], "o", "oe"} }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["et"] = { "Estonian", 9072, "urj-fin", "Latn", sort_key = { from = { "š", "ž", "õ", "ä", "ö", "ü", -- 2 chars "z" -- 1 char }, to = { "s" .. p[1], "s" .. p[3], "w" .. p[1], "w" .. p[2], "w" .. p[3], "w" .. p[4], "s" .. p[2] } }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvÕõÄäÖöÜü" .. c.punc, } m["eu"] = { "Basque", 8752, "euq", "Latn", sort_key = { from = {"ç", "ñ"}, to = {"c" .. p[1], "n" .. p[1]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnÑñOoPpRrSsTtUuXxZz" .. c.punc, } m["fa"] = { "Persian", 9168, "ira-swi", "fa-Arab, Hebr", ancestors = "fa-cls", strip_diacritics = { ["fa-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ٱ"}, -- character "ۂ" code U+06C2 to "ه"; hamzatu l-waṣli to a regular alif to = {"ه", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ff"] = { "Fula", 33454, "alv-fwo", "Latn, Adlm", } m["fi"] = { "Finnish", 1412, "urj-fin", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { -- used to indicate gemination of the next consonant remove_diacritics = "ˣ", from = {"’"}, to = {"'"}, }, sort_key = { -- [[Appendix:Finnish alphabet#Collation]] + "aͤ" and "oͤ" as historical variants of "ä" and "ö". remove_diacritics = "'’:" .. c.diacritics, remove_exceptions = { "a[" .. c.ringabove .. c.diaer .. c.small_e .. "]", -- åäaͤ "o[" .. c.diaer .. c.tilde .. c.dacute .. c.small_e .. "]", -- öõőoͤ "u[" .. c.diaer .. c.dacute .. "]" -- üű }, from = {"æ", "[ðđ]", "ł", "ŋ", "œ", "ß", "þ", "u[" .. c.diaer .. c.dacute .. "]", "å", "aͤ", "o[" .. c.tilde .. c.dacute .. c.small_e .. "]", "ø", "(.)['%-]"}, to = {"ae", "d", "l", "n", "oe", "ss", "th", "y", "z" .. p[1], "ä", "ö", "ö", "%1"} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÄäÖö" .. c.punc, } m["fj"] = { "Fijian", 33295, "poz-pcc", "Latn", } m["fo"] = { "Faroese", 25258, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "í", "ó", "ú", "ý", "æ", "ø"}, to = {"a" .. p[1], "d" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaÁáBbDdÐðEeFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvYyÝýÆæØø" .. c.punc, } m["fr"] = { "French", 150, "roa-oil", "Latn, Brai", ancestors = "frm", sort_key = { Latn = s["roa-oil-sortkey"] }, standard_chars = { Latn = "AaÀàÂâBbCcÇçDdEeÉéÈèÊêËëFfGgHhIiÎîÏïJjLlMmNnOoÔôŒœPpQqRrSsTtUuÙùÛûÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["fy"] = { "West Frisian", 27175, "gmw-fri", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer, from = {"y"}, to = {"i"} }, standard_chars = "AaâäàÆæBbCcDdEeéêëèFfGgHhIiïìYyỳJjKkLlMmNnOoôöòPpRrSsTtUuúûüùVvWwZz" .. c.punc, } m["ga"] = { "Irish", 9142, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = { remove_diacritics = c.acute, from = {"ḃ", "ċ", "ḋ", "ḟ", "ġ", "ṁ", "ṗ", "ṡ", "ṫ"}, to = {"bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíLlMmNnOoÓóPpRrSsTtUuÚúVv" .. c.punc, } m["gd"] = { "Scottish Gaelic", 9314, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = {remove_diacritics = c.grave .. c.acute}, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙù" .. c.punc, } m["gl"] = { "Galician", 9307, "roa-gap", "Latn", sort_key = { remove_diacritics = c.acute, from = {"ñ"}, to = {"n" .. p[1]} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíÏïLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxZz" .. c.punc, } m["gu"] = { "Gujarati", 5137, "inc-wes", "Arab, Gujr", ancestors = "inc-mgu", translit = { Gujr = "gu-translit", }, strip_diacritics = { Arab = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.kasra .. c.shadda .. c.sukun}, Gujr = {remove_diacritics = "઼"}, }, } m["gv"] = { "Manx", 12175, "cel-gae", "Latn", ancestors = "mga", sort_key = {remove_diacritics = c.cedilla .. "-"}, standard_chars = "AaBbCcÇçDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYy" .. c.punc, } m["ha"] = { "Hausa", 56475, "cdc-wst", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron} }, sort_key = { Latn = { from = {"ɓ", "b'", "ɗ", "d'", "ƙ", "k'", "sh", "ƴ", "'y"}, to = {"b" .. p[1], "b" .. p[2], "d" .. p[1], "d" .. p[2], "k" .. p[1], "k" .. p[2], "s" .. p[1], "y" .. p[1], "y" .. p[2]} }, }, } m["he"] = { "Hebrew", 9288, "sem-can", "Hebr, Phnx, Brai, Samr", ancestors = "he-med", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- Samr strip_diacritics, sort_key in [[Module:scripts/data]] -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["hi"] = { "Hindi", 1568, "inc-hnd", "Deva, Kthi, Newa", translit = { Deva = "hi-translit" }, standard_chars = { Deva = "अआइईउऊएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषसहत्रज्ञक्षक़ख़ग़ज़झ़ड़ढ़फ़काखागाघाङाचाछाजाझाञाटाठाडाढाणाताथादाधानापाफाबाभामायारालावाशाषासाहात्राज्ञाक्षाक़ाख़ाग़ाज़ाझ़ाड़ाढ़ाफ़ाकिखिगिघिङिचिछिजिझिञिटिठिडिढिणितिथिदिधिनिपिफिबिभिमियिरिलिविशिषिसिहित्रिज्ञिक्षिक़िख़िग़िज़िझ़िड़िढ़िफ़िकीखीगीघीङीचीछीजीझीञीटीठीडीढीणीतीथीदीधीनीपीफीबीभीमीयीरीलीवीशीषीसीहीत्रीज्ञीक्षीक़ीख़ीग़ीज़ीझ़ीड़ीढ़ीफ़ीकुखुगुघुङुचुछुजुझुञुटुठुडुढुणुतुथुदुधुनुपुफुबुभुमुयुरुलुवुशुषुसुहुत्रुज्ञुक्षुक़ुख़ुग़ुज़ुझ़ुड़ुढ़ुफ़ुकूखूगूघूङूचूछूजूझूञूटूठूडूढूणूतूथूदूधूनूपूफूबूभूमूयूरूलूवूशूषूसूहूत्रूज्ञूक्षूक़ूख़ूग़ूज़ूझ़ूड़ूढ़ूफ़ूकेखेगेघेङेचेछेजेझेञेटेठेडेढेणेतेथेदेधेनेपेफेबेभेमेयेरेलेवेशेषेसेहेत्रेज्ञेक्षेक़ेख़ेग़ेज़ेझ़ेड़ेढ़ेफ़ेकैखैगैघैङैचैछैजैझैञैटैठैडैढैणैतैथैदैधैनैपैफैबैभैमैयैरैलैवैशैषैसैहैत्रैज्ञैक्षैक़ैख़ैग़ैज़ैझ़ैड़ैढ़ैफ़ैकोखोगोघोङोचोछोजोझोञोटोठोडोढोणोतोथोदोधोनोपोफोबोभोमोयोरोलोवोशोषोसोहोत्रोज्ञोक्षोक़ोख़ोग़ोज़ोझ़ोड़ोढ़ोफ़ोकौखौगौघौङौचौछौजौझौञौटौठौडौढौणौतौथौदौधौनौपौफौबौभौमौयौरौलौवौशौषौसौहौत्रौज्ञौक्षौक़ौख़ौग़ौज़ौझ़ौड़ौढ़ौफ़ौक्ख्ग्घ्ङ्च्छ्ज्झ्ञ्ट्ठ्ड्ढ्ण्त्थ्द्ध्न्प्फ्ब्भ्म्य्र्ल्व्श्ष्स्ह्त्र्ज्ञ्क्ष्क़्ख़्ग़्ज़्झ़्ड़्ढ़्फ़्।॥०१२३४५६७८९॰", c.punc }, } m["ho"] = { "Hiri Motu", 33617, "crp", "Latn", ancestors = "meu", } m["ht"] = { "Haitian Creole", 33491, "crp", "Latn", ancestors = "ht-sdm", sort_key = { from = { "oun", -- 3 chars "an", "ch", "è", "en", "ng", "ò", "on", "ou", "ui" -- 2 chars }, to = { "o" .. p[4], "a" .. p[1], "c" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "u" .. p[1] } }, } m["hu"] = { "Hungarian", 9067, "urj-ugr", "Latn, Hung", ancestors = "ohu", sort_key = { Latn = { from = { "dzs", -- 3 chars "á", "cs", "dz", "é", "gy", "í", "ly", "ny", "ó", "ö", "ő", "sz", "ty", "ú", "ü", "ű", "zs", -- 2 chars }, to = { "d" .. p[2], "a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "u" .. p[3], "z" .. p[1], } }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóÖöŐőPpQqRrSsTtUuÚúÜüŰűVvWwXxYyZz", c.punc }, } m["hy"] = { "Armenian", 8785, "hyx", "Armn, Brai", ancestors = "axm", -- Armn translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Armn = { remove_diacritics = "՛՜՞՟", from = {"եւ", "<sup>յ</sup>", "<sup>ի</sup>", "<sup>է</sup>", "յ̵", "ՙ", "՚"}, to = {"և", "յ", "ի", "է", "ֈ", "ʻ", "’"} }, }, sort_key = { Armn = { from = { "ու", "եւ", -- 2 chars "և" -- 1 char }, to = { "ւ", "եվ", "եվ" } }, }, } m["hz"] = { "Herero", 33315, "bnt-swb", "Latn", } m["ia"] = { "Interlingua", 35934, "art", "Latn", } m["id"] = { "Indonesian", 9240, "poz-mly", "Latn", ancestors = "ms", standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc, } m["ie"] = { "Interlingue", 35850, "art", "Latn", type = "appendix-constructed", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["ig"] = { "Igbo", 33578, "alv-igb", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron}, sort_key = { from = {"gb", "gh", "gw", "ị", "kp", "kw", "ṅ", "nw", "ny", "ọ", "sh", "ụ"}, to = {"g" .. p[1], "g" .. p[2], "g" .. p[3], "i" .. p[1], "k" .. p[1], "k" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "o" .. p[1], "s" .. p[1], "u" .. p[1]} }, } m["ii"] = { "Nuosu", 34235, "tbq-nlo", "Yiii", translit = "ii-translit", } m["ik"] = { "Inupiaq", 27183, "esx-inu", "Latn", sort_key = { from = { "ch", "ġ", "dj", "ḷ", "ł̣", "ñ", "ng", "r̂", "sr", "zr", -- 2 chars "ł", "ŋ", "ʼ" -- 1 char }, to = { "c" .. p[1], "g" .. p[1], "h" .. p[1], "l" .. p[1], "l" .. p[3], "n" .. p[1], "n" .. p[2], "r" .. p[1], "s" .. p[1], "z" .. p[1], "l" .. p[2], "n" .. p[2], "z" .. p[2] } }, } m["io"] = { "Ido", 35224, "art", "Latn", } m["is"] = { "Icelandic", 294, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "é", "í", "ó", "ú", "ý", "þ", "æ", "ö"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaÁáBbDdÐðEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvXxYyÝýÞþÆæÖö" .. c.punc, } m["it"] = { "Italian", 652, "roa-itr", "Latn", ancestors = "roa-oit", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove}, standard_chars = "AaÀàBbCcDdEeÈèÉéFfGgHhIiÌìLlMmNnOoÒòPpQqRrSsTtUuÙùVvZz" .. c.punc, } m["iu"] = { "Inuktitut", 29921, "esx-inu", "Cans, Latn", translit = { Cans = "cr-translit" }, override_translit = true, } m["ja"] = { "Japanese", 5287, "jpx", "Jpan, Latn, Brai", ancestors = "ja-ear", translit = s["jpx-translit"], link_tr = true, display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jv"] = { "Javanese", 33549, "poz", "Latn, Java, Arab", ancestors = "kaw", translit = { Java = "jv-translit" }, link_tr = true, strip_diacritics = { Latn = {remove_diacritics = c.circ} -- Modern jv don't use ê }, sort_key = { Latn = { from = {"å", "dh", "é", "è", "ng", "ny", "th"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "n" .. p[2], "t" .. p[1]} }, }, } m["ka"] = { "Georgian", 8108, "ccs-gzn", "Geor, Geok, Hebr", -- Hebr is used to write Judeo-Georgian ancestors = "ka-mid", -- Geor, Geok translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Geor = s["ka-stripdiacritics"], Geok = s["ka-stripdiacritics"], }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["kg"] = { "Kongo", 33702, "bnt-kng", "Latn", } m["ki"] = { "Kikuyu", 33587, "bnt-kka", "Latn", } m["kj"] = { "Kwanyama", 1405077, "bnt-ova", "Latn", } m["kk"] = { "Kazakh", 9252, "trk-kno", "Cyrl, Latn, kk-Arab", translit = { Cyrl = { from = { "Ё", "ё", "Й", "й", "Нг", "нг", "Ӯ", "ӯ", -- 2 chars; are "Ӯ" and "ӯ" actually used? "А", "а", "Ә", "ә", "Б", "б", "В", "в", "Г", "г", "Ғ", "ғ", "Д", "д", "Е", "е", "Ж", "ж", "З", "з", "И", "и", "К", "к", "Қ", "қ", "Л", "л", "М", "м", "Н", "н", "Ң", "ң", "О", "о", "Ө", "ө", "П", "п", "Р", "р", "С", "с", "Т", "т", "У", "у", "Ұ", "ұ", "Ү", "ү", "Ф", "ф", "Х", "х", "Һ", "һ", "Ц", "ц", "Ч", "ч", "Ш", "ш", "Щ", "щ", "Ъ", "ъ", "Ы", "ы", "І", "і", "Ь", "ь", "Э", "э", "Ю", "ю", "Я", "я", -- 1 char }, to = { "E", "e", "İ", "i", "Ñ", "ñ", "U", "u", "A", "a", "Ä", "ä", "B", "b", "V", "v", "G", "g", "Ğ", "ğ", "D", "d", "E", "e", "J", "j", "Z", "z", "İ", "i", "K", "k", "Q", "q", "L", "l", "M", "m", "N", "n", "Ñ", "ñ", "O", "o", "Ö", "ö", "P", "p", "R", "r", "S", "s", "T", "t", "U", "u", "Ū", "ū", "Ü", "ü", "F", "f", "X", "x", "H", "h", "S", "s", "Ç", "ç", "Ş", "ş", "Ş", "ş", "", "", "Y", "y", "I", "ı", "", "", "É", "é", "Ü", "ü", "Ä", "ä", } } }, -- override_translit = true, sort_key = { Cyrl = { from = {"ә", "ғ", "ё", "қ", "ң", "ө", "ұ", "ү", "һ", "і"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "у" .. p[2], "х" .. p[1], "ы" .. p[1]} }, }, standard_chars = { Cyrl = "АаӘәБбВвГгҒғДдЕеЁёЖжЗзИиЙйКкҚқЛлМмНнҢңОоӨөПпРрСсТтУуҰұҮүФфХхҺһЦцЧчШшЩщЪъЫыІіЬьЭэЮюЯя", c.punc }, } m["kl"] = { "Greenlandic", 25355, "esx-inu", "Latn", sort_key = { from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } } m["km"] = { "Khmer", 9205, "mkh-kmr", "Khmr", ancestors = "xhm", translit = "km-translit", } m["kn"] = { "Kannada", 33673, "dra-kan", "Knda, Tutg", ancestors = "dra-mkn", -- Knda translit in [[Module:scripts/data]] } m["ko"] = { "Korean", 9176, "qfa-kor", "Kore, Brai", ancestors = "ko-ear", translit = { Kore = "ko-translit", }, -- Kore strip_diacritics in [[Module:scripts/data]] } m["kr"] = { "Kanuri", 36094, "ssa-sah", "Latn, Arab", -- the sortkey and strip_diacritics are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.breve} }, sort_key = { Latn = { from = {"ǝ", "ny", "ɍ", "sh"}, to = {"e" .. p[1], "n" .. p[1], "r" .. p[1], "s" .. p[1]} }, }, } m["ks"] = { "Kashmiri", 33552, "inc-kas", "ks-Arab, Deva, Shrd, Latn", translit = { ["ks-Arab"] = "ks-Arab-translit", Deva = "ks-Deva-translit", -- Shrd translit in [[Module:scripts/data]] }, } -- "kv" is treated as "koi", "kpv", see [[WT:LT]] m["kw"] = { "Cornish", 25289, "cel-brs", "Latn", ancestors = "cnx", sort_key = { from = {"ch"}, to = {"c" .. p[1]} }, } m["ky"] = { "Kyrgyz", 9255, "trk-kkp", "Cyrl, Latn, Arab", translit = { Cyrl = "ky-translit" }, override_translit = true, sort_key = { Cyrl = { from = {"ё", "ң", "ө", "ү"}, to = {"е" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, } m["la"] = { "Latin", 397, "itc-laf", "Latn, Ital", ancestors = "itc-ola", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) display_text = { Latn = s["itc-Latn-displaytext"] }, strip_diacritics = { Latn = s["itc-Latn-stripdiacritics"] }, sort_key = { Latn = s["itc-Latn-sortkey"] }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiLlMmNnOoPpQqRrSsTtUuVvXx", c.punc }, } m["lb"] = { "Luxembourgish", 9051, "gmw-hgm", "Latn, Brai", ancestors = "gmw-cfr", sort_key = { Latn = { from = {"ä", "ë", "é"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, }, } m["lg"] = { "Luganda", 33368, "bnt-nyg", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ŋ"}, to = {"n" .. p[1]} }, } m["li"] = { "Limburgish", 102172, "gmw-frk", "Latn", ancestors = "dum", } m["ln"] = { "Lingala", 36217, "bnt-bmo", "Latn", sort_key = { remove_diacritics = c.acute .. c.circ .. c.caron, from = {"ɛ", "gb", "mb", "mp", "nd", "ng", "nk", "ns", "nt", "ny", "nz", "ɔ"}, to = {"e" .. p[1], "g" .. p[1], "m" .. p[1], "m" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "n" .. p[4], "n" .. p[5], "n" .. p[6], "n" .. p[7], "o" .. p[1]} }, } m["lo"] = { "Lao", 9211, "tai-swe", "Laoo", -- also Tai Noi/Lao Buhan script translit = "lo-translit", sort_key = "Laoo-sortkey", standard_chars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. c.punc, } m["lt"] = { "Lithuanian", 9083, "bat-eas", "Latn", ancestors = "olt", display_text = "lt-common", strip_diacritics = "lt-common", sort_key = "lt-common", standard_chars = "AaĄąBbCcČčDdEeĘęĖėFfGgHhIiĮįYyJjKkLlMmNnOoPpRrSsŠšTtUuŲųŪūVvZzŽž" .. c.punc, } m["lu"] = { "Luba-Katanga", 36157, "bnt-lub", "Latn", } m["lv"] = { "Latvian", 9078, "bat-eas", "Latn", strip_diacritics = { -- 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 = {"([Ee])" .. c.cedilla, "[" .. c.grave .. c.circ .. c.tilde .."]", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .. "?([^aAeEiIoOuU])", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .."?$", "([iI])" .. c.tilde .. "?([eE])" .. c.tilde .. "?", "([aAeEiIuU])" .. c.tilde, c.tilde}, to = {"%1", c.tilde, "%1%2%3", "%1%2", "%1%2", "%1" .. c.macron} }, sort_key = { from = {"ā", "č", "ē", "ģ", "ī", "ķ", "ļ", "ņ", "š", "ū", "ž"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1]} }, standard_chars = "AaĀāBbCcČčDdEeĒēFfGgĢģHhIiĪīJjKkĶķLlĻļMmNnŅņOoPpRrSsŠšTtUuŪūVvZzŽž" .. c.punc, } m["mg"] = { "Malagasy", 7930, "poz-bre", "Latn, Arab", } m["mh"] = { "Marshallese", 36280, "poz-mic", "Latn", sort_key = { from = {"ā", "ļ", "m̧", "ņ", "n̄", "o̧", "ō", "ū"}, to = {"a" .. p[1], "l" .. p[1], "m" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "u" .. p[1]} }, } m["mi"] = { "Māori", 36451, "poz-pep", "Latn", sort_key = { remove_diacritics = c.macron, from = {"ng", "wh"}, to = {"n" .. p[1], "w" .. p[1]} }, } m["mk"] = { "Macedonian", 9296, "zls", "Cyrl, Polyt", ancestors = "cu", translit = { Cyrl = "mk-translit", -- FIXME: formerly no translit specified for Polyt; unclear if the default [[Module:grc-translit]] is -- acceptable, so we disable it for now Polyt = false, }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, remove_exceptions = {"Ѓ", "ѓ", "Ќ", "ќ"} }, }, sort_key = { Cyrl = { remove_diacritics = c.grave, remove_exceptions = {"ѓ", "ќ"}, from = {"ѓ", "ѕ", "ј", "љ", "њ", "ќ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Cyrl = "АаБбВвГгДдЃѓЕеЖжЗзЅѕИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЌќУуФфХхЦцЧчЏџШш", c.punc }, } m["ml"] = { "Malayalam", 36236, "dra-mal", "Mlym", override_translit = true, -- Mlym translit in [[Module:scripts/data]] } m["mn"] = { "Mongolian", 9246, "xgn-cen", "Cyrl, Mong, Latn, Brai", ancestors = "cmg", translit = { Cyrl = "mn-translit", -- Mong translit in [[Module:scripts/data]] }, override_translit = true, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] strip_diacritics = { Cyrl = {remove_diacritics = c.grave .. c.acute}, }, sort_key = { Cyrl = { remove_diacritics = c.grave, from = {"ё", "ө", "ү"}, to = {"е" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйЛлМмНнОоӨөРрСсТтУуҮүХхЦцЧчШшЫыЬьЭэЮюЯя—", Brai = c.braille, c.punc }, } -- "mo" is treated as "ro", see [[WT:LT]] m["mr"] = { "Marathi", 1571, "inc-sou", "Deva, Modi", ancestors = "omr", translit = { Deva = "mr-translit", Modi = "mr-Modi-translit", }, strip_diacritics = { Deva = { from = {"च़", "ज़", "झ़"}, to = {"च", "ज", "झ"} }, }, } m["ms"] = { "Malay", 9237, "poz-mly", "Latn, ms-Arab", ancestors = "ms-cla", standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", c.punc }, } m["mt"] = { "Maltese", 9166, "sem-arb", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { from = {"’"}, to = {"'"}, }, ancestors = "sqr", sort_key = { from = { "ċ", "ġ", "ż", -- Convert into PUA so that decomposed form does not get caught by the next step. "([cgz])", -- Ensure "c" comes after "ċ", "g" comes after "ġ" and "z" comes after "ż". "g" .. p[1] .. "ħ", -- "għ" after initial conversion of "g". p[3], p[4], "ħ", "ie", p[5] -- Convert "ċ", "ġ", "ħ", "ie", "ż" into final output. }, to = { p[3], p[4], p[5], "%1" .. p[1], "g" .. p[2], "c", "g", "h" .. p[1], "i" .. p[1], "z" } }, } m["my"] = { "Burmese", 9228, "tbq-brm", "Mymr", ancestors = "obr", translit = "my-translit", override_translit = true, sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"} }, } m["na"] = { "Nauruan", 13307, "poz-mic", "Latn", } m["nb"] = { "Norwegian Bokmål", 25167, "gmq", "Latn", wikimedia_codes = "no", ancestors = "gmq-mno, da", -- da as an (but not the) ancestor of nb was agreed on - do not change without discussion sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nd"] = { "Northern Ndebele", 35613, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["ne"] = { "Nepali", 33823, "inc-pah", "Deva, Newa", translit = { Deva = "ne-translit" }, } m["ng"] = { "Ndonga", 33900, "bnt-ova", "Latn", } m["nl"] = { "Dutch", 7411, "gmw-frk", "Latn, Brai", ancestors = "dum", sort_key = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'"}, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZzÄäËëÏïÖöÜü", Brai = c.braille, c.punc }, } m["nn"] = { "Norwegian Nynorsk", 25164, "gmq-wes", "Latn", ancestors = "gmq-mno", strip_diacritics = { remove_diacritics = c.grave .. c.acute, }, sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["no"] = { "Norwegian", 9043, "gmq-wes", "Latn", ancestors = "gmq-mno", sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nr"] = { "Southern Ndebele", 36785, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["nv"] = { "Navajo", 13310, "apa", "Latn, Brai", sort_key = { remove_diacritics = c.acute .. c.ogonek, from = { "chʼ", "tłʼ", "tsʼ", -- 3 chars "ch", "dl", "dz", "gh", "hw", "kʼ", "kw", "sh", "tł", "ts", "zh", -- 2 chars "ł", "ʼ" -- 1 char }, to = { "c" .. p[2], "t" .. p[2], "t" .. p[4], "c" .. p[1], "d" .. p[1], "d" .. p[2], "g" .. p[1], "h" .. p[1], "k" .. p[1], "k" .. p[2], "s" .. p[1], "t" .. p[1], "t" .. p[3], "z" .. p[1], "l" .. p[1], "z" .. p[2] } }, } m["ny"] = { "Chichewa", 33273, "bnt-nys", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ng'"}, to = {"ng"} }, } m["oc"] = { "Occitan", 14185, "roa-ocr", "Latn, Hebr", ancestors = "pro", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla, from = {"([lns])·h"}, to = {"%1h"} }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["oj"] = { "Ojibwe", 33875, "alg", "Cans, Latn", sort_key = { Latn = { from = {"aa", "ʼ", "ii", "oo", "sh", "zh"}, to = {"a" .. p[1], "h" .. p[1], "i" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1]} }, }, } m["om"] = { "Oromo", 33864, "cus-eas", "Latn, Ethi", } m["or"] = { "Odia", 33810, "inc-eas", "Orya", ancestors = "inc-mor", translit = "or-translit", } m["os"] = { "Ossetian", 33968, "xsc-sar", "Cyrl, Geor, Latn", ancestors = "oos", translit = { Cyrl = "os-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = { from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, sort_key = { Cyrl = { from = {"ӕ", "гъ", "дж", "дз", "ё", "къ", "пъ", "тъ", "хъ", "цъ", "чъ"}, to = {"а" .. p[1], "г" .. p[1], "д" .. p[1], "д" .. p[2], "е" .. p[1], "к" .. p[1], "п" .. p[1], "т" .. p[1], "х" .. p[1], "ц" .. p[1], "ч" .. p[1]} }, }, } m["pa"] = { "Punjabi", 58635, "inc-pan", "Guru, pa-Arab", translit = { Guru = "Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = { ["pa-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna, from = {"ݨ", "ࣇ"}, to = {"ن", "ل"} }, }, } m["pi"] = { "Pali", 36727, "inc-mid", "Latn, Brah, Deva, Beng, Sinh, Mymr, Thai, Lana, Laoo, Khmr, Cakm", --and also Khom ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Beng = "pi-translit", Sinh = "si-translit", Mymr = "pi-translit", Thai = "pi-translit", Lana = "pi-translit", Laoo = "pi-translit", Khmr = "pi-translit", Cakm = "Cakm-translit", }, strip_diacritics = { Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, Mymr = { remove_diacritics = c.VS01, }, }, sort_key = { -- FIXME: This needs to be converted into the current standardized format. from = {"ā", "ī", "ū", "ḍ", "ḷ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"} }, } m["pl"] = { "Polish", 809, "zlw-lch", "Latn", ancestors = "zlw-mpl", sort_key = { from = {"ą", "ć", "ę", "ł", "ń", "ó", "ś", "ź", "ż"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaĄąBbCcĆćDdEeĘęFfGgHhIiJjKkLlŁłMmNnŃńOoÓóPpRrSsŚśTtUuWwYyZzŹźŻż" .. c.punc, } m["ps"] = { "Pashto", 58680, "ira-pat", "ps-Arab", strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.zwarakay .. c.superalef}, } m["pt"] = { "Portuguese", 5146, "roa-gap", "Latn, Brai", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "º", "œ"}, to = {"a", "ae", "o", "oe"} }, }, standard_chars = { Latn = "AaÁáÂâÃãBbCcÇçDdEeÉéÊêFfGgHhIiÍíJjLlMmNnOoÓóÔôÕõPpQqRrSsTtUuÚúVvXxZz", Brai = c.braille, c.punc }, } m["qu"] = { "Quechua", 5218, "qwe", "Latn", } m["rm"] = { "Romansh", 13199, "roa-rhe", ancestors = "rm-old", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.small_e}, } m["ro"] = { "Romanian", 7913, "roa-eas", "Latn, Cyrl, Cyrs", translit = { Cyrl = "ro-translit" }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute, from = {"ă", "â", "î", "ș", "ț"}, to = {"a" .. p[1], "a" .. p[2], "i" .. p[1], "s" .. p[1], "t" .. p[1]} }, Cyrl = { from = {"ӂ"}, to = {"ж" .. p[1]} }, }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; presumably not present standard_chars = { Latn = "AaĂăÂâBbCcDdEeFfGgHhIiÎîJjLlMmNnOoPpRrSsȘșTtȚțUuVvXxZz", Cyrl = "АаБбВвГгДдЕеЖжӁӂЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЫыЬьЭэЮюЯя", c.punc }, } m["ru"] = { "Russian", 7737, "zle", "Cyrl, Brai", ancestors = "zle-mru", translit = { Cyrl = "ru-translit" }, display_text = { Cyrl = { from = {"'"}, to = {"’"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, remove_exceptions = {"Ё", "ё", "Ѣ̈", "ѣ̈", "Я̈", "я̈"}, from = {"’"}, to = {"'"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, from = { "і", "ѣ", "ѳ", "ѵ" }, to = { "и" .. p[1], "ь" .. p[1], "я" .. p[2], "я" .. p[3] } }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЫыЬьЭэЮюЯя—", Brai = c.braille, (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["rw"] = { "Rwanda-Rundi", 3217514, "bnt-glb", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.caron}, } m["sa"] = { "Sanskrit", 11059, "inc", "as-Beng, Bali, Beng, Bhks, Brah, Mymr, xwo-Mong, Deva, Gujr, Guru, Gran, Hani, Java, Kthi, Knda, Kawi, Khar, Khmr, Laoo, Mlym, mnc-Mong, Marc, Modi, Mong, Nand, Newa, Orya, Phag, Ranj, Saur, Shrd, Sidd, Sinh, Soyo, Lana, Takr, Taml, Tang, Telu, Thai, Tibt, Tutg, Tirh, Zanb", --and also Khom; script codes sorted by canonical name rather than code for [[MOD:sa-convert]] translit = { Beng = "sa-Beng-translit", ["as-Beng"] = "sa-Beng-translit", -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Gujr = "sa-Gujr-translit", Guru = "sa-Guru-translit", Java = "sa-Java-translit", Kthi = "sa-Kthi-translit", Khmr = "pi-translit", Knda = "sa-Knda-translit", Lana = "pi-translit", Laoo = "pi-translit", Mlym = "sa-Mlym-translit", Modi = "sa-Modi-translit", -- Mong, mnc-Mong, xwo-Mong translit in [[Module:scripts/data]] -- NOTE: Formerly used xal-translit for transliterating xwo-Mong but that only handles Cyrillic; it has -- code to transliterate xwo-Mong but it's broken so I've replaced it with the default xwo-translit. Mymr = "pi-translit", Orya = "sa-Orya-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] Sinh = "si-translit", Taml = "sa-Taml-translit", Telu = "sa-Telu-translit", Thai = "pi-translit", -- Tibt translit in [[Module:scripts/data]] }, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] -- Tibt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] strip_diacritics = { Deva = s["sa-Deva-stripdiacritics"], Mymr = { remove_diacritics = c.VS01, }, Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, }, sort_key = { Deva = s["sa-Deva-stripdiacritics"], -- until we have a proper Sanskrit sorting algorithm. Lana = { -- Tai Tham from = {"ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ"}, to = {"ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}, }, Laoo = "Laoo-sortkey", Latn = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ"}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~"}, }, Mymr = { remove_diacritics = c.VS01, }, Thai = "Thai-sortkey", -- FIXME: The previous sort key which mixed all scripts removed ZWJ; I don't know which script(s) this was -- intended for and there are no other languages which remove it in the sort key AFAIK. If it needs to be -- removed, specify the script(s) it needs to be removed under or add handling for the "all" script that applies -- regardless of script. --all = { -- remove_diacritics = c.ZWJ, --}, }, } m["sc"] = { "Sardinian", 33976, "roa-sou", "Latn", ancestors = "sc-old", } m["sd"] = { "Sindhi", 33997, "inc-snd", "sd-Arab, Deva, Sind, Khoj", translit = { Sind = "Sind-translit", ["sd-Arab"] = "sd-Arab-translit" }, strip_diacritics = { ["sd-Arab"] = { remove_diacritics = c.kashida .. c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, from = {"ٱ"}, to = {"ا"} }, }, } m["se"] = { "Northern Sami", 33947, "smi", "Latn", display_text = { from = {"'"}, to = {"ˈ"} }, strip_diacritics = {remove_diacritics = c.macron .. c.dotbelow .. "'ˈ"}, sort_key = { from = {"á", "č", "đ", "ŋ", "š", "ŧ", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "n" .. p[1], "s" .. p[1], "t" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĐđEeFfGgHhIiJjKkLlMmNnŊŋOoPpRrSsŠšTtŦŧUuVvZzŽž" .. c.punc, } m["sg"] = { "Sango", 33954, "crp", "Latn", ancestors = "ngb", } m["sh"] = { "Serbo-Croatian", 9301, "zls", "Latn, Cyrl, Glag, Arab", ietf_subtag = "hbs", -- ISO 639-3 code, since "sh" is deprecated from ISO 639-1 wikimedia_codes = "sh, bs, hr, sr", strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"Ć", "ć", "Ś", "ś", "Ź", "ź"} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"З́", "з́", "С́", "с́"} }, }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"ć", "ś", "ź"}, from = {"č", "ć", "dž", "đ", "lj", "nj", "š", "ś", "ž", "ź"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "z" .. p[1], "z" .. p[2]} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"з́", "с́"}, from = {"ђ", "з́", "ј", "љ", "њ", "с́", "ћ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "с" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, standard_chars = { Latn = "AaBbCcČčĆćDdĐđEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž", Cyrl = "АаБбВвГгДдЂђЕеЖжЗзИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЋћУуФфХхЦцЧчЏџШш", c.punc }, } m["si"] = { "Sinhalese", 13267, "inc-ins", "Sinh", translit = "si-translit", override_translit = true, } m["sk"] = { "Slovak", 9058, "zlw", "Latn", ancestors = "zlw-osk", sort_key = {remove_diacritics = c.acute .. c.circ .. c.diaer .. c.caron}, standard_chars = "AaÁáÄäBbCcČčDdĎďEeÉéFfGgHhIiÍíJjKkLlĹ弾MmNnŇňOoÓóÔôPpRrŔŕSsŠšTtŤťUuÚúVvYyÝýZzŽž" .. c.punc, } m["sl"] = { "Slovene", 9063, "zls", "Latn", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.dgrave .. c.invbreve .. c.dotbelow, remove_exceptions = {"Ć", "ć", "Ǵ", "ǵ", "Ś", "ś", "Ź", "ź"}, from = {"Ə", "ə", "Ł", "ł"}, to = {"E", "e", "L", "l"}, }, sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dotabove .. c.ringabove .. c.dgrave .. c.invbreve .. c.dotbelow .. c.ringbelow .. c.ogonek, remove_exceptions = {"ć", "ǵ", "ś", "ź"}, from = {"ä", "č", "ć", "đ", "ə", "ë", "ǧ", "ǵ", "ï", "ł", "ö", "š", "ś", "ü", "ž", "ź"}, to = {"a" .. p[1], "c" .. p[1], "c" .. p[2], "d" .. p[1], "e", "e" .. p[1], "g" .. p[1], "g" .. p[2], "i" .. p[1], "l", "o" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]}, }, standard_chars = "AaBbCcČčDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž" .. c.punc, } m["sm"] = { "Samoan", 34011, "poz-pnp", "Latn", } m["sn"] = { "Shona", 34004, "bnt-sho", "Latn", strip_diacritics = {remove_diacritics = c.acute}, } m["so"] = { "Somali", 13275, "cus-som", "Latn, Arab, Osma", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, } m["sq"] = { "Albanian", 8748, "sqj", "Latn, Grek, ota-Arab, Elba, Todr, Vith", translit = { Elba = "Elba-translit", Vith = "Vith-translit", }, -- Grek display_text, sort_key in [[Module:scripts/data]] strip_diacritics = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron, from = {'^[ie] (%w)', '^të (%w)'}, to = {'%1', '%1'}, }, Grek = { -- Diacritic removal from Grek-stripdiacritics excluded. from = m_langdata.chars_substitutions["Grek-stripdiacritics"].from, to = m_langdata.chars_substitutions["Grek-stripdiacritics"].to, }, }, sort_key = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron .. c.tilde .. c.breve .. c.caron, from = {'^[ie] (%w)', '^të (%w)', 'ç', 'dh', 'ë', 'gj', 'll', 'nj', 'rr', 'sh', 'th', 'xh', 'zh'}, to = {'%1', '%1', 'c'..p[1], 'd'..p[1], 'e'..p[1], 'g'..p[1], 'l'..p[1], 'n'..p[1], 'r'..p[1], 's'..p[1], 't'..p[1], 'x'..p[1], 'z'..p[1]}, } -- TODO: Grek if the default sort key is unsuitable }, standard_chars = { Latn = "AaBbCcÇçDdEeËëFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvXxYyZz", c.punc }, } m["ss"] = { "Swazi", 34014, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["st"] = { "Sotho", 34340, "bnt-sts", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["su"] = { "Sundanese", 34002, "poz-msa", "Latn, Sund, Arab", ancestors = "osn", translit = { Sund = "Sund-translit" }, } m["sv"] = { "Swedish", 9027, "gmq-eas", "Latn", ancestors = "gmq-osw-lat", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla .. "':", remove_exceptions = {"å"}, from = {"ø", "æ", "œ", "ß", "å", "aͤ", "oͤ"}, to = {"o", "ae", "oe", "ss", "z" .. p[1], "ä", "ö"} }, standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvXxYyÅåÄäÖö" .. c.punc, } m["sw"] = { "Swahili", 7838, "bnt-swh", "Latn, Arab", sort_key = { Latn = { from = {"ng'"}, to = {"ng" .. p[1]} }, }, } m["ta"] = { "Tamil", 5885, "dra-tam", "Taml", ancestors = "ta-mid", translit = "ta-translit", override_translit = true, } m["te"] = { "Telugu", 8097, "dra-tel", "Telu", translit = "te-translit", override_translit = true, } m["tg"] = { "Tajik", 9260, "ira-swi", "Cyrl, fa-Arab, Latn", ancestors = "fa-cls", translit = { Cyrl = "tg-translit" }, override_translit = true, strip_diacritics = { Cyrl = s["tg-stripdiacritics"], Latn = s["tg-stripdiacritics"], }, sort_key = { Cyrl = { from = {"ғ", "ё", "ӣ", "қ", "ӯ", "ҳ", "ҷ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "к" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["th"] = { "Thai", 9217, "tai-swe", "Thai, Khomt, Brai", translit = { Thai = "th-translit" }, sort_key = { Thai = "Thai-sortkey" }, } m["ti"] = { "Tigrinya", 34124, "sem-eth", "Ethi", translit = "Ethi-translit", } m["tk"] = { "Turkmen", 9267, "trk-ogz", "Latn, Cyrl, Arab", strip_diacritics = { Latn = s["tk-stripdiacritics"], Cyrl = s["tk-stripdiacritics"], }, sort_key = { Latn = { from = {"ç", "ä", "ž", "ň", "ö", "ş", "ü", "ý"}, to = {"c" .. p[1], "e" .. p[1], "j" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "y" .. p[1]} }, Cyrl = { from = {"ё", "җ", "ң", "ө", "ү", "ә"}, to = {"е" .. p[1], "ж" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "э" .. p[1]} }, }, ancestors = "trk-eog", } m["tl"] = { "Tagalog", 34057, "phi", "Latn, Tglg", translit = { Tglg = "tl-translit" }, override_translit = true, strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, standard_chars = { Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy", c.punc }, sort_key = { Latn = "tl-sortkey", }, } m["tn"] = { "Tswana", 34137, "bnt-sts", "Latn", } m["to"] = { "Tongan", 34094, "poz-ton", "Latn", strip_diacritics = {remove_diacritics = c.acute}, sort_key = {remove_diacritics = c.macron}, } m["tr"] = { "Turkish", 256, "trk-ogz", "Latn", ancestors = "ota", dotted_dotless_i = true, sort_key = { from = { -- Ignore circumflex, but account for capital Î wrongly becoming ı + circ due to dotted dotless I logic. "ı" .. c.circ, c.circ, "i", -- Ensure "i" comes after "ı". "ç", "ğ", "ı", "ö", "ş", "ü" }, to = { "i", "", "i" .. p[1], "c" .. p[1], "g" .. p[1], "i", "o" .. p[1], "s" .. p[1], "u" .. p[1] } }, standard_chars = "AaÂâBbCcÇçDdEeFfGgĞğHhIıİiÎîJjKkLlMmNnOoÖöPpRrSsŞşTtUuÛûÜüVvYyZz" .. c.punc, } m["ts"] = { "Tsonga", 34327, "bnt-tsr", "Latn", } m["tt"] = { "Tatar", 25285, "trk-kbu", "Cyrl, Latn, tt-Arab", translit = { Cyrl = "tt-translit", ["tt-Arab"] = "tt-translit" }, --override_translit = true, -- enable override until Module code can detect Russian loans such as [[аэропорт]] dotted_dotless_i = true, sort_key = { Cyrl = { from = {"ә", "ў", "ғ", "ё", "җ", "қ", "ң", "ө", "ү", "һ"}, to = {"а" .. p[1], "в" .. p[1], "г" .. p[1], "е" .. p[1], "ж" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1]} }, Latn = { from = { "i", -- Ensure "i" comes after "ı". "ä", "ə", "ç", "ğ", "ı", "ñ", "ŋ", "ö", "ɵ", "ş", "ü" }, to = { "i" .. p[1], "a" .. p[1], "a" .. p[2], "c" .. p[1], "g" .. p[1], "i", "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "s" .. p[1], "u" .. p[1] } }, }, } -- "tw" is treated as "ak", see [[WT:LT]] m["ty"] = { "Tahitian", 34128, "poz-pep", "Latn", } m["ug"] = { "Uyghur", 13263, "trk-kar", "ug-Arab, Latn, Cyrl", ancestors = "chg", translit = { ["ug-Arab"] = "ug-translit", Cyrl = "ug-translit", }, override_translit = true, } m["uk"] = { "Ukrainian", 8798, "zle", "Cyrl", ancestors = "zle-muk", translit = "uk-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, sort_key = { remove_diacritics = c.grave .. c.acute, from = { "ї", -- 2 chars "ґ", "є", "і" -- 1 char }, to = { "и" .. p[2], "г" .. p[1], "е" .. p[1], "и" .. p[1] } }, standard_chars = "АаБбВвГгДдЕеЄєЖжЗзИиІіЇїЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЬьЮюЯя" .. c.punc:gsub("'", ""), -- Exclude apostrophe. } m["ur"] = { "Urdu", 1617, "inc-hnd", "ur-Arab, Hebr", translit = { ["ur-Arab"] = "ur-translit" }, strip_diacritics = { ["ur-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ۂ", "ٱ"}, to = {"ہ", "ہ", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { ["ur-Arab"] = "ایببپتثجچحخدذرزژسشصضطظعغفقکگلࣇڷمنݨوؤہھئٹڈڑآے", c.punc, }, } m["uz"] = { "Uzbek", 9264, "trk-kar", "Latn, Cyrl, fa-Arab", ancestors = "chg", translit = { Cyrl = "uz-translit" }, sort_key = { Latn = { from = {"oʻ", "gʻ", "sh", "ch", "ng"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3], "z" .. p[4], "z" .. p[5]} }, Cyrl = { from = {"ё", "ў", "қ", "ғ", "ҳ"}, to = {"е" .. p[1], "я" .. p[1], "я" .. p[2], "я" .. p[3], "я" .. p[4]} }, }, strip_diacritics = { ["fa-Arab"] = "ar-stripdiacritics", }, } m["ve"] = { "Venda", 32704, "bnt-bso", "Latn", } m["vi"] = { "Vietnamese", 9199, "mkh-vie", "Latn, Hani", ancestors = "mkh-mvi", sort_key = { Latn = "vi-sortkey", Hani = "Hani-sortkey", }, } m["vo"] = { "Volapük", 36986, "art", "Latn", } m["wa"] = { "Walloon", 34219, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["wo"] = { "Wolof", 34257, "alv-fwo", "Latn, Arab, Gara", } m["xh"] = { "Xhosa", 13218, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["yi"] = { "Yiddish", 8641, "gmw-hgm", "Hebr, Latn", ancestors = "gmh", translit = { Hebr = "yi-translit", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["yo"] = { "Yoruba", 34311, "alv-yor", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.macron} }, sort_key = { Latn = { from = {"ẹ", "ɛ", "gb", "ị", "kp", "ọ", "ɔ", "ṣ", "sh", "ụ"}, to = {"e" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "o" .. p[1], "o" .. p[1], "s" .. p[1], "s" .. p[1], "u" .. p[1]} }, }, } m["za"] = { "Zhuang", 13216, "tai", "Latn, Hani", sort_key = { Latn = "za-sortkey", Hani = "Hani-sortkey", }, } m["zh"] = { "Chinese", 7850, "zhx", "Hants, Latn, Bopo, Nshu, Brai", ancestors = "ltc", generate_forms = "zh-generateforms", translit = { Hani = "zh-translit", Bopo = "zh-translit", }, sort_key = { Hani = "Hani-sortkey" }, } m["zu"] = { "Zulu", 10179, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } return require("Module:languages").finalizeData(m, "language") 0m6ennhmvoyt6gbvvrn6ae6qo3n5rac 231384 231383 2026-04-14T07:48:55Z Pinthura 2424 භාෂා නාම සිංහලට පරිවර්තනය 231384 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared -- Ideally, we want to move these into [[Module:languages/data]], but because (a) it's necessary to use require on that module, and (b) they're only used in this data module, it's less memory-efficient to do that at the moment. If it becomes possible to use mw.loadData, then these should be moved there. s["de-Latn-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove, from = {"æ", "œ", "ß"}, to = {"ae", "oe", "ss"} } s["de-Latn-standardchars"] = "AaÄäBbCcDdEeFfGgHhIiJjKkLlMmNnOoÖöPpQqRrSsẞßTtUuÜüVvWwXxYyZz" s["ka-stripdiacritics"] = {remove_diacritics = c.circ} s["no-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } s["no-standardchars"] = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc s["sa-Deva-stripdiacritics"] = { -- Don't use remove_diacritics for accent marks, as १ and ३ should also be removed if (and only if) they carry any. from = {"[१३]?[" .. c.anudatta .. c.udatta .. c.dsvarita .. c.tsvarita .. "]+"}, to = {""}, } s["tg-stripdiacritics"] = {remove_diacritics = c.grave .. c.acute} s["tk-stripdiacritics"] = {remove_diacritics = c.macron} local m = {} m["aa"] = { "Afar", 27811, "cus-eas", "Latn, Ethi", strip_diacritics = { Latn = {remove_diacritics = c.acute}, }, } m["ab"] = { "Abkhaz", 5111, "cau-abz", "Cyrl, Geor, Latn", translit = { Cyrl = "ab-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, from = {"^а%-"}, to = {"а"}, }, Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = { "х'ә", -- 3 chars "гь", "гә", "ӷь", "ҕь", "ӷә", "ҕә", "дә", "ё", "жь", "жә", "ҙә", "ӡә", "ӡ'", "кь", "кә", "қь", "қә", "ҟь", "ҟә", "ҫә", "тә", "ҭә", "ф'", "хь", "хә", "х'", "ҳә", "ць", "цә", "ц'", "ҵә", "ҵ'", "шь", "шә", "џь", -- 2 chars "ӷ", "ҕ", "ҙ", "ӡ", "қ", "ҟ", "ԥ", "ҧ", "ҫ", "ҭ", "ҳ", "ҵ", "ҷ", "ҽ", "ҿ", "ҩ", "џ", "ә", -- 1 char "^а", }, to = { "х" .. p[4], "г" .. p[1], "г" .. p[2], "г" .. p[5], "г" .. p[6], "г" .. p[7], "г" .. p[8], "д" .. p[1], "е" .. p[1], "ж" .. p[1], "ж" .. p[2], "з" .. p[2], "з" .. p[4], "з" .. p[5], "к" .. p[1], "к" .. p[2], "к" .. p[4], "к" .. p[5], "к" .. p[7], "к" .. p[8], "с" .. p[2], "т" .. p[1], "т" .. p[3], "ф" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[6], "ц" .. p[1], "ц" .. p[2], "ц" .. p[3], "ц" .. p[5], "ц" .. p[6], "ш" .. p[1], "ш" .. p[2], "ы" .. p[3], "г" .. p[3], "г" .. p[4], "з" .. p[1], "з" .. p[3], "к" .. p[3], "к" .. p[6], "п" .. p[1], "п" .. p[2], "с" .. p[1], "т" .. p[2], "х" .. p[5], "ц" .. p[4], "ч" .. p[1], "ч" .. p[2], "ч" .. p[3], "ы" .. p[1], "ы" .. p[2], "ь" .. p[1], "", } }, }, } m["ae"] = { "Avestan", 29572, "ira-cen", "Avst, Gujr, Deva", translit = { Avst = "Avst-translit" }, } m["af"] = { "Afrikaans", 14196, "gmw-frk", "Latn, Arab", ancestors = "nl", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'", from = {"['ʼ]n"}, to = {"n" .. p[1]} } }, } m["ak"] = { "Akan", 28026, "alv-ctn", "Latn", } m["am"] = { "ඇම්හාරික්", 28244, "sem-eth", "Ethi", translit = "Ethi-translit", } m["an"] = { "Aragonese", 8765, "roa-nar", "Latn", } m["ar"] = { "අරාබි", 13955, "sem-arb", "Arab, Hebr, Syrc, Brai, Nbat", translit = { Arab = "ar-translit" }, strip_diacritics = { Arab = "ar-stripdiacritics", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["as"] = { "Assamese", 29401, "inc-bas", "as-Beng", ancestors = "inc-mas", translit = "as-translit", } m["av"] = { "Avar", 29561, "cau-ava", "Cyrl, Latn, Arab", ancestors = "oav", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"], }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"гъ", "гь", "гӏ", "ё", "кк", "къ", "кь", "кӏ", "лъ", "лӏ", "тӏ", "хх", "хъ", "хь", "хӏ", "цӏ", "чӏ"}, to = {"г" .. p[1], "г" .. p[2], "г" .. p[3], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "к" .. p[4], "л" .. p[1], "л" .. p[2], "т" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[4], "ц" .. p[1], "ч" .. p[1]} }, }, } m["ay"] = { "අයිමාරා", 4627, "sai-aym", "Latn", } m["az"] = { "අසර්බයිජානි", 9292, "trk-ogz", "Latn, Cyrl, fa-Arab", ancestors = "trk-oat", dotted_dotless_i = true, strip_diacritics = { Latn = { from = {"ʼ"}, to = {"'"}, }, ["fa-Arab"] = { module = "ar-stripdiacritics", ["from"] = { "ۆ", "ۇ", "وْ", "ڲ", "ؽ", }, ["to"] = { "و", "و", "و", "گ", "ی", }, }, }, display_text = { Latn = { from = {"'"}, to = {"ʼ"} } }, sort_key = { Latn = { from = { "i", -- Ensure "i" comes after "ı". "ç", "ə", "ğ", "x", "ı", "q", "ö", "ş", "ü", "w" }, to = { "i" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "h" .. p[1], "i", "k" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1] } }, Cyrl = { from = {"ғ", "ә", "ы", "ј", "ҝ", "ө", "ү", "һ", "ҹ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "и" .. p[2], "к" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["ba"] = { "Bashkir", 13389, "trk-kbu", "Cyrl", translit = "ba-translit", override_translit = true, sort_key = { from = {"ғ", "ҙ", "ё", "ҡ", "ң", "ө", "ҫ", "ү", "һ", "ә"}, to = {"г" .. p[1], "д" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "с" .. p[1], "у" .. p[1], "х" .. p[1], "э" .. p[1]} }, } m["be"] = { "Belarusian", 9091, "zle", "Cyrl, Latn", ancestors = "zle-mbe", translit = { Cyrl = "be-translit", }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"ґ", "ё", "і", "ў"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "у" .. p[1]} }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, from = {"ć", "č", "dz", "dź", "dž", "ch", "ł", "ń", "ś", "š", "ŭ", "ź", "ž"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "d" .. p[3], "h" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзІіЙйКкЛлМмНнОоПпРрСсТтУуЎўФфХхЦцЧчШшЫыЬьЭэЮюЯя", Latn = "AaBbCcĆćČčDdEeFfGgHhIiJjKkLlŁłMmNnŃńOoPpRrSsŚśŠšTtUuŬŭVvYyZzŹźŽž", (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["bg"] = { "බල්ගේරියානු", 7918, "zls", "Cyrl", ancestors = "cu-bgm", translit = "bg-translit", strip_diacritics = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, sort_key = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, standard_chars = "АаБбВвГгДдЕеЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЬьЮюЯя" .. c.punc, } m["bh"] = { "බිහාරී", 135305, "inc-eas", "Deva", } m["bi"] = { "Bislama", 35452, "crp", "Latn", ancestors = "en", } m["bm"] = { "Bambara", 33243, "dmn-emn", "Latn, Nkoo", sort_key = { Latn = { from = {"ɛ", "ɲ", "ŋ", "ɔ"}, to = {"e" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1]} }, }, } m["bn"] = { "බෙංගාලි", 9610, "inc-bas", "Beng, Newa", ancestors = "inc-mbn", translit = { Beng = "bn-translit" }, } m["bo"] = { "ටිබෙට්", 34271, "sit-tib", "Tibt", -- sometimes Deva? ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["br"] = { "බ්‍රෙටන්", 12107, "cel-brs", "Latn", ancestors = "xbm", sort_key = { from = {"ch", "c['ʼ’]h"}, to = {"c" .. p[1], "c" .. p[2]} }, } m["ca"] = { "Catalan", 7026, "roa-ocr", "Latn", ancestors = "roa-oca", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, standard_chars = "AaÀàBbCcÇçDdEeÉéÈèFfGgHhIiÍíÏïJjLlMmNnOoÓóÒòPpQqRrSsTtUuÚúÜüVvXxYyZz·" .. c.punc, } m["ce"] = { "Chechen", 33350, "cau-vay", "Cyrl, Latn, Arab", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"аь", "гӏ", "ё", "кх", "къ", "кӏ", "оь", "пӏ", "тӏ", "уь", "хь", "хӏ", "цӏ", "чӏ", "юь", "яь"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "о" .. p[1], "п" .. p[1], "т" .. p[1], "у" .. p[1], "х" .. p[1], "х" .. p[2], "ц" .. p[1], "ч" .. p[1], "ю" .. p[1], "я" .. p[1]} }, }, } m["ch"] = { "Chamorro", 33262, "poz", "Latn", sort_key = { remove_diacritics = "'", from = {"å", "ch", "ñ", "ng"}, to = {"a" .. p[1], "c" .. p[1], "n" .. p[1], "n" .. p[2]} }, } m["co"] = { "Corsican", 33111, "roa-itr", "Latn", sort_key = { from = {"chj", "ghj", "sc", "sg"}, to = {"c" .. p[1], "g" .. p[1], "s" .. p[1], "s" .. p[2]} }, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìÏïJjLlMmNnOoÒòPpQqRrSsTtUuÙùÜüVvZz" .. c.punc, } m["cr"] = { "Cree", 33390, "alg", "Latn, Cans", translit = { Cans = "cr-translit" }, } m["cs"] = { "චෙක්", 9056, "zlw", "Latn", ancestors = "cs-ear", sort_key = { from = {"á", "č", "ď", "é", "ě", "ch", "í", "ň", "ó", "ř", "š", "ť", "ú", "ů", "ý", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "h" .. p[1], "i" .. p[1], "n" .. p[1], "o" .. p[1], "r" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "y" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĎďEeÉéĚěFfGgHhIiÍíJjKkLlMmNnŇňOoÓóPpRrŘřSsŠšTtŤťUuÚúŮůVvYyÝýZzŽž" .. c.punc, } m["cu"] = { "Old Church Slavonic", 35499, "zls", "Cyrs, Glag, Zname", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["cv"] = { "Chuvash", 33348, "trk-ogr", "Cyrl", ancestors = "cv-mid", translit = "cv-translit", override_translit = true, sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = {"а" .. p[1], "е" .. p[1], "е" .. p[2], "с" .. p[1], "у" .. p[1]} }, } m["cy"] = { "වේල්ස", 9309, "cel-brw", "Latn", ancestors = "wlm", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. "'", from = {"ch", "dd", "ff", "ng", "ll", "ph", "rh", "th"}, to = {"c" .. p[1], "d" .. p[1], "f" .. p[1], "g" .. p[1], "l" .. p[1], "p" .. p[1], "r" .. p[1], "t" .. p[1]} }, standard_chars = "ÂâAaBbCcDdEeÊêFfGgHhIiÎîLlMmNnOoÔôPpRrSsTtUuÛûWwŴŵYyŶŷ" .. c.punc, } m["da"] = { "ඩෙන්මාර්ක", 9035, "gmq-eas", "Latn", ancestors = "gmq-oda", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc, } m["de"] = { "ජර්මානු", 188, "gmw-hgm", "Latn, Latf, Brai", ancestors = "de-ear", sort_key = { Latn = s["de-Latn-sortkey"], Latf = s["de-Latn-sortkey"], }, standard_chars = { Latn = s["de-Latn-standardchars"], Latf = s["de-Latn-standardchars"], Brai = c.braille, c.punc } } m["dv"] = { "දිවෙහි", 32656, "inc-ins", "Thaa, Diak", translit = { Thaa = "dv-translit", Diak = "Diak-translit", }, ancestors = "dv-old", override_translit = true, } m["dz"] = { "Dzongkha", 33081, "sit-tib", "Tibt", ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ee"] = { "Ewe", 30005, "alv-gbe", "Latn", sort_key = { remove_diacritics = c.tilde, from = {"ɖ", "dz", "ɛ", "ƒ", "gb", "ɣ", "kp", "ny", "ŋ", "ɔ", "ts", "ʋ"}, to = {"d" .. p[1], "d" .. p[2], "e" .. p[1], "f" .. p[1], "g" .. p[1], "g" .. p[2], "k" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "t" .. p[1], "v" .. p[1]} }, } m["el"] = { "ග්‍රීක", 9129, "grk", "Grek, Polyt, Brai", ancestors = "el-kth", translit = "el-translit", override_translit = true, -- Grek and Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Grek = "΅·ͺ΄ΑαΆάΒβΓγΔδΕεέΈΖζΗηΉήΘθΙιΊίΪϊΐΚκΛλΜμΝνΞξΟοΌόΠπΡρΣσςΤτΥυΎύΫϋΰΦφΧχΨψΩωΏώ", Brai = c.braille, c.punc }, } m["en"] = { "ඉංග්‍රීසි", 1860, "gmw-ang", "Latn, Brai, Shaw, Dsrt", -- entries in Shaw or Dsrt might require prior discussion wikimedia_codes = "en, simple", ancestors = "en-ear", sort_key = { Latn = { -- Many of these are needed for sorting language names. remove_diacritics = "'\"%-%.,%s·ʻʼ" .. c.diacritics, -- These are found in pagenames. from = {"[ɒæ🅱¢©ᴄðđəǝɜɡħʜıɨłŋɲøɔœꝑꝓꝕßʋ]"}, to = {{ ["ɒ"] = "a", ["æ"] = "ae", ["🅱"] = "b", ["¢"] = "c", ["©"] = "c", ["ᴄ"] = "c", ["ð"] = "d", ["đ"] = "d", ["ə"] = "e", ["ǝ"] = "e", ["ɜ"] = "e", ["ɡ"] = "g", ["ħ"] = "h", ["ʜ"] = "h", ["ı"] = "i", ["ɨ"] = "i", ["ł"] = "l", ["ŋ"] = "n", ["ɲ"] = "n", ["ø"] = "o", ["ɔ"] = "o", ["œ"] = "oe", ["ꝑ"] = "p", ["ꝓ"] = "p", ["ꝕ"] = "p", ["ß"] = "ss", ["ʋ"] = "v", }}, }, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", Brai = c.braille, c.punc }, } m["eo"] = { "එස්පෙරාන්තො", 143, "art", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute, from = {"ĉ", "ĝ", "ĥ", "ĵ", "ŝ", "ŭ"}, to = {"c" .. p[1], "g" .. p[1], "h" .. p[1], "j" .. p[1], "s" .. p[1], "u" .. p[1]} }, standard_chars = "AaBbCcĈĉDdEeFfGgĜĝHhĤĥIiJjĴĵKkLlMmNnOoPpRrSsŜŝTtUuŬŭVvZz" .. c.punc, } m["es"] = { "ස්පාඤ්ඤ", 1321, "roa-cas", "Latn, Brai", ancestors = "es-ear", sort_key = { Latn = { remove_exceptions = {"ñ"}, remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "ñ", "º", "œ"}, to = {"a", "ae", "n" .. p[1], "o", "oe"} }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["et"] = { "එස්තෝනියානු", 9072, "urj-fin", "Latn", sort_key = { from = { "š", "ž", "õ", "ä", "ö", "ü", -- 2 chars "z" -- 1 char }, to = { "s" .. p[1], "s" .. p[3], "w" .. p[1], "w" .. p[2], "w" .. p[3], "w" .. p[4], "s" .. p[2] } }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvÕõÄäÖöÜü" .. c.punc, } m["eu"] = { "බාස්ක්", 8752, "euq", "Latn", sort_key = { from = {"ç", "ñ"}, to = {"c" .. p[1], "n" .. p[1]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnÑñOoPpRrSsTtUuXxZz" .. c.punc, } m["fa"] = { "පර්සියානු", 9168, "ira-swi", "fa-Arab, Hebr", ancestors = "fa-cls", strip_diacritics = { ["fa-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ٱ"}, -- character "ۂ" code U+06C2 to "ه"; hamzatu l-waṣli to a regular alif to = {"ه", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ff"] = { "Fula", 33454, "alv-fwo", "Latn, Adlm", } m["fi"] = { "ෆින්ලන්ත", 1412, "urj-fin", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { -- used to indicate gemination of the next consonant remove_diacritics = "ˣ", from = {"’"}, to = {"'"}, }, sort_key = { -- [[Appendix:Finnish alphabet#Collation]] + "aͤ" and "oͤ" as historical variants of "ä" and "ö". remove_diacritics = "'’:" .. c.diacritics, remove_exceptions = { "a[" .. c.ringabove .. c.diaer .. c.small_e .. "]", -- åäaͤ "o[" .. c.diaer .. c.tilde .. c.dacute .. c.small_e .. "]", -- öõőoͤ "u[" .. c.diaer .. c.dacute .. "]" -- üű }, from = {"æ", "[ðđ]", "ł", "ŋ", "œ", "ß", "þ", "u[" .. c.diaer .. c.dacute .. "]", "å", "aͤ", "o[" .. c.tilde .. c.dacute .. c.small_e .. "]", "ø", "(.)['%-]"}, to = {"ae", "d", "l", "n", "oe", "ss", "th", "y", "z" .. p[1], "ä", "ö", "ö", "%1"} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÄäÖö" .. c.punc, } m["fj"] = { "Fijian", 33295, "poz-pcc", "Latn", } m["fo"] = { "Faroese", 25258, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "í", "ó", "ú", "ý", "æ", "ø"}, to = {"a" .. p[1], "d" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaÁáBbDdÐðEeFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvYyÝýÆæØø" .. c.punc, } m["fr"] = { "ප්‍රංශ", 150, "roa-oil", "Latn, Brai", ancestors = "frm", sort_key = { Latn = s["roa-oil-sortkey"] }, standard_chars = { Latn = "AaÀàÂâBbCcÇçDdEeÉéÈèÊêËëFfGgHhIiÎîÏïJjLlMmNnOoÔôŒœPpQqRrSsTtUuÙùÛûÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["fy"] = { "West Frisian", 27175, "gmw-fri", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer, from = {"y"}, to = {"i"} }, standard_chars = "AaâäàÆæBbCcDdEeéêëèFfGgHhIiïìYyỳJjKkLlMmNnOoôöòPpRrSsTtUuúûüùVvWwZz" .. c.punc, } m["ga"] = { "අයිරිෂ්", 9142, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = { remove_diacritics = c.acute, from = {"ḃ", "ċ", "ḋ", "ḟ", "ġ", "ṁ", "ṗ", "ṡ", "ṫ"}, to = {"bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíLlMmNnOoÓóPpRrSsTtUuÚúVv" .. c.punc, } m["gd"] = { "ස්කොට්ස් ගේලික්", 9314, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = {remove_diacritics = c.grave .. c.acute}, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙù" .. c.punc, } m["gl"] = { "Galician", 9307, "roa-gap", "Latn", sort_key = { remove_diacritics = c.acute, from = {"ñ"}, to = {"n" .. p[1]} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíÏïLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxZz" .. c.punc, } m["gu"] = { "ගුජරාටි", 5137, "inc-wes", "Arab, Gujr", ancestors = "inc-mgu", translit = { Gujr = "gu-translit", }, strip_diacritics = { Arab = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.kasra .. c.shadda .. c.sukun}, Gujr = {remove_diacritics = "઼"}, }, } m["gv"] = { "මැන්ක්ස්", 12175, "cel-gae", "Latn", ancestors = "mga", sort_key = {remove_diacritics = c.cedilla .. "-"}, standard_chars = "AaBbCcÇçDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYy" .. c.punc, } m["ha"] = { "Hausa", 56475, "cdc-wst", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron} }, sort_key = { Latn = { from = {"ɓ", "b'", "ɗ", "d'", "ƙ", "k'", "sh", "ƴ", "'y"}, to = {"b" .. p[1], "b" .. p[2], "d" .. p[1], "d" .. p[2], "k" .. p[1], "k" .. p[2], "s" .. p[1], "y" .. p[1], "y" .. p[2]} }, }, } m["he"] = { "හීබෲ", 9288, "sem-can", "Hebr, Phnx, Brai, Samr", ancestors = "he-med", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- Samr strip_diacritics, sort_key in [[Module:scripts/data]] -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["hi"] = { "හින්දි", 1568, "inc-hnd", "Deva, Kthi, Newa", translit = { Deva = "hi-translit" }, standard_chars = { Deva = "अआइईउऊएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषसहत्रज्ञक्षक़ख़ग़ज़झ़ड़ढ़फ़काखागाघाङाचाछाजाझाञाटाठाडाढाणाताथादाधानापाफाबाभामायारालावाशाषासाहात्राज्ञाक्षाक़ाख़ाग़ाज़ाझ़ाड़ाढ़ाफ़ाकिखिगिघिङिचिछिजिझिञिटिठिडिढिणितिथिदिधिनिपिफिबिभिमियिरिलिविशिषिसिहित्रिज्ञिक्षिक़िख़िग़िज़िझ़िड़िढ़िफ़िकीखीगीघीङीचीछीजीझीञीटीठीडीढीणीतीथीदीधीनीपीफीबीभीमीयीरीलीवीशीषीसीहीत्रीज्ञीक्षीक़ीख़ीग़ीज़ीझ़ीड़ीढ़ीफ़ीकुखुगुघुङुचुछुजुझुञुटुठुडुढुणुतुथुदुधुनुपुफुबुभुमुयुरुलुवुशुषुसुहुत्रुज्ञुक्षुक़ुख़ुग़ुज़ुझ़ुड़ुढ़ुफ़ुकूखूगूघूङूचूछूजूझूञूटूठूडूढूणूतूथूदूधूनूपूफूबूभूमूयूरूलूवूशूषूसूहूत्रूज्ञूक्षूक़ूख़ूग़ूज़ूझ़ूड़ूढ़ूफ़ूकेखेगेघेङेचेछेजेझेञेटेठेडेढेणेतेथेदेधेनेपेफेबेभेमेयेरेलेवेशेषेसेहेत्रेज्ञेक्षेक़ेख़ेग़ेज़ेझ़ेड़ेढ़ेफ़ेकैखैगैघैङैचैछैजैझैञैटैठैडैढैणैतैथैदैधैनैपैफैबैभैमैयैरैलैवैशैषैसैहैत्रैज्ञैक्षैक़ैख़ैग़ैज़ैझ़ैड़ैढ़ैफ़ैकोखोगोघोङोचोछोजोझोञोटोठोडोढोणोतोथोदोधोनोपोफोबोभोमोयोरोलोवोशोषोसोहोत्रोज्ञोक्षोक़ोख़ोग़ोज़ोझ़ोड़ोढ़ोफ़ोकौखौगौघौङौचौछौजौझौञौटौठौडौढौणौतौथौदौधौनौपौफौबौभौमौयौरौलौवौशौषौसौहौत्रौज्ञौक्षौक़ौख़ौग़ौज़ौझ़ौड़ौढ़ौफ़ौक्ख्ग्घ्ङ्च्छ्ज्झ्ञ्ट्ठ्ड्ढ्ण्त्थ्द्ध्न्प्फ्ब्भ्म्य्र्ल्व्श्ष्स्ह्त्र्ज्ञ्क्ष्क़्ख़्ग़्ज़्झ़्ड़्ढ़्फ़्।॥०१२३४५६७८९॰", c.punc }, } m["ho"] = { "Hiri Motu", 33617, "crp", "Latn", ancestors = "meu", } m["ht"] = { "Haitian Creole", 33491, "crp", "Latn", ancestors = "ht-sdm", sort_key = { from = { "oun", -- 3 chars "an", "ch", "è", "en", "ng", "ò", "on", "ou", "ui" -- 2 chars }, to = { "o" .. p[4], "a" .. p[1], "c" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "u" .. p[1] } }, } m["hu"] = { "හංගේරියානු", 9067, "urj-ugr", "Latn, Hung", ancestors = "ohu", sort_key = { Latn = { from = { "dzs", -- 3 chars "á", "cs", "dz", "é", "gy", "í", "ly", "ny", "ó", "ö", "ő", "sz", "ty", "ú", "ü", "ű", "zs", -- 2 chars }, to = { "d" .. p[2], "a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "u" .. p[3], "z" .. p[1], } }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóÖöŐőPpQqRrSsTtUuÚúÜüŰűVvWwXxYyZz", c.punc }, } m["hy"] = { "ආමේනියානු", 8785, "hyx", "Armn, Brai", ancestors = "axm", -- Armn translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Armn = { remove_diacritics = "՛՜՞՟", from = {"եւ", "<sup>յ</sup>", "<sup>ի</sup>", "<sup>է</sup>", "յ̵", "ՙ", "՚"}, to = {"և", "յ", "ի", "է", "ֈ", "ʻ", "’"} }, }, sort_key = { Armn = { from = { "ու", "եւ", -- 2 chars "և" -- 1 char }, to = { "ւ", "եվ", "եվ" } }, }, } m["hz"] = { "Herero", 33315, "bnt-swb", "Latn", } m["ia"] = { "Interlingua", 35934, "art", "Latn", } m["id"] = { "ඉන්දුනීසියානු", 9240, "poz-mly", "Latn", ancestors = "ms", standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc, } m["ie"] = { "Interlingue", 35850, "art", "Latn", type = "appendix-constructed", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["ig"] = { "Igbo", 33578, "alv-igb", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron}, sort_key = { from = {"gb", "gh", "gw", "ị", "kp", "kw", "ṅ", "nw", "ny", "ọ", "sh", "ụ"}, to = {"g" .. p[1], "g" .. p[2], "g" .. p[3], "i" .. p[1], "k" .. p[1], "k" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "o" .. p[1], "s" .. p[1], "u" .. p[1]} }, } m["ii"] = { "Nuosu", 34235, "tbq-nlo", "Yiii", translit = "ii-translit", } m["ik"] = { "Inupiaq", 27183, "esx-inu", "Latn", sort_key = { from = { "ch", "ġ", "dj", "ḷ", "ł̣", "ñ", "ng", "r̂", "sr", "zr", -- 2 chars "ł", "ŋ", "ʼ" -- 1 char }, to = { "c" .. p[1], "g" .. p[1], "h" .. p[1], "l" .. p[1], "l" .. p[3], "n" .. p[1], "n" .. p[2], "r" .. p[1], "s" .. p[1], "z" .. p[1], "l" .. p[2], "n" .. p[2], "z" .. p[2] } }, } m["io"] = { "Ido", 35224, "art", "Latn", } m["is"] = { "අයිස්ලන්ත", 294, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "é", "í", "ó", "ú", "ý", "þ", "æ", "ö"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaÁáBbDdÐðEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvXxYyÝýÞþÆæÖö" .. c.punc, } m["it"] = { "ඉතාලි", 652, "roa-itr", "Latn", ancestors = "roa-oit", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove}, standard_chars = "AaÀàBbCcDdEeÈèÉéFfGgHhIiÌìLlMmNnOoÒòPpQqRrSsTtUuÙùVvZz" .. c.punc, } m["iu"] = { "Inuktitut", 29921, "esx-inu", "Cans, Latn", translit = { Cans = "cr-translit" }, override_translit = true, } m["ja"] = { "ජපන්", 5287, "jpx", "Jpan, Latn, Brai", ancestors = "ja-ear", translit = s["jpx-translit"], link_tr = true, display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jv"] = { "ජාවා", 33549, "poz", "Latn, Java, Arab", ancestors = "kaw", translit = { Java = "jv-translit" }, link_tr = true, strip_diacritics = { Latn = {remove_diacritics = c.circ} -- Modern jv don't use ê }, sort_key = { Latn = { from = {"å", "dh", "é", "è", "ng", "ny", "th"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "n" .. p[2], "t" .. p[1]} }, }, } m["ka"] = { "ජෝර්ජියානු", 8108, "ccs-gzn", "Geor, Geok, Hebr", -- Hebr is used to write Judeo-Georgian ancestors = "ka-mid", -- Geor, Geok translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Geor = s["ka-stripdiacritics"], Geok = s["ka-stripdiacritics"], }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["kg"] = { "කොංගෝ", 33702, "bnt-kng", "Latn", } m["ki"] = { "Kikuyu", 33587, "bnt-kka", "Latn", } m["kj"] = { "Kwanyama", 1405077, "bnt-ova", "Latn", } m["kk"] = { "Kazakh", 9252, "trk-kno", "Cyrl, Latn, kk-Arab", translit = { Cyrl = { from = { "Ё", "ё", "Й", "й", "Нг", "нг", "Ӯ", "ӯ", -- 2 chars; are "Ӯ" and "ӯ" actually used? "А", "а", "Ә", "ә", "Б", "б", "В", "в", "Г", "г", "Ғ", "ғ", "Д", "д", "Е", "е", "Ж", "ж", "З", "з", "И", "и", "К", "к", "Қ", "қ", "Л", "л", "М", "м", "Н", "н", "Ң", "ң", "О", "о", "Ө", "ө", "П", "п", "Р", "р", "С", "с", "Т", "т", "У", "у", "Ұ", "ұ", "Ү", "ү", "Ф", "ф", "Х", "х", "Һ", "һ", "Ц", "ц", "Ч", "ч", "Ш", "ш", "Щ", "щ", "Ъ", "ъ", "Ы", "ы", "І", "і", "Ь", "ь", "Э", "э", "Ю", "ю", "Я", "я", -- 1 char }, to = { "E", "e", "İ", "i", "Ñ", "ñ", "U", "u", "A", "a", "Ä", "ä", "B", "b", "V", "v", "G", "g", "Ğ", "ğ", "D", "d", "E", "e", "J", "j", "Z", "z", "İ", "i", "K", "k", "Q", "q", "L", "l", "M", "m", "N", "n", "Ñ", "ñ", "O", "o", "Ö", "ö", "P", "p", "R", "r", "S", "s", "T", "t", "U", "u", "Ū", "ū", "Ü", "ü", "F", "f", "X", "x", "H", "h", "S", "s", "Ç", "ç", "Ş", "ş", "Ş", "ş", "", "", "Y", "y", "I", "ı", "", "", "É", "é", "Ü", "ü", "Ä", "ä", } } }, -- override_translit = true, sort_key = { Cyrl = { from = {"ә", "ғ", "ё", "қ", "ң", "ө", "ұ", "ү", "һ", "і"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "у" .. p[2], "х" .. p[1], "ы" .. p[1]} }, }, standard_chars = { Cyrl = "АаӘәБбВвГгҒғДдЕеЁёЖжЗзИиЙйКкҚқЛлМмНнҢңОоӨөПпРрСсТтУуҰұҮүФфХхҺһЦцЧчШшЩщЪъЫыІіЬьЭэЮюЯя", c.punc }, } m["kl"] = { "Greenlandic", 25355, "esx-inu", "Latn", sort_key = { from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } } m["km"] = { "Khmer", 9205, "mkh-kmr", "Khmr", ancestors = "xhm", translit = "km-translit", } m["kn"] = { "කන්නඩ", 33673, "dra-kan", "Knda, Tutg", ancestors = "dra-mkn", -- Knda translit in [[Module:scripts/data]] } m["ko"] = { "කොරියානු", 9176, "qfa-kor", "Kore, Brai", ancestors = "ko-ear", translit = { Kore = "ko-translit", }, -- Kore strip_diacritics in [[Module:scripts/data]] } m["kr"] = { "Kanuri", 36094, "ssa-sah", "Latn, Arab", -- the sortkey and strip_diacritics are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.breve} }, sort_key = { Latn = { from = {"ǝ", "ny", "ɍ", "sh"}, to = {"e" .. p[1], "n" .. p[1], "r" .. p[1], "s" .. p[1]} }, }, } m["ks"] = { "කාෂ්මීරි", 33552, "inc-kas", "ks-Arab, Deva, Shrd, Latn", translit = { ["ks-Arab"] = "ks-Arab-translit", Deva = "ks-Deva-translit", -- Shrd translit in [[Module:scripts/data]] }, } -- "kv" is treated as "koi", "kpv", see [[WT:LT]] m["kw"] = { "කෝනිෂ්", 25289, "cel-brs", "Latn", ancestors = "cnx", sort_key = { from = {"ch"}, to = {"c" .. p[1]} }, } m["ky"] = { "Kyrgyz", 9255, "trk-kkp", "Cyrl, Latn, Arab", translit = { Cyrl = "ky-translit" }, override_translit = true, sort_key = { Cyrl = { from = {"ё", "ң", "ө", "ү"}, to = {"е" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, } m["la"] = { "ලතින්", 397, "itc-laf", "Latn, Ital", ancestors = "itc-ola", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) display_text = { Latn = s["itc-Latn-displaytext"] }, strip_diacritics = { Latn = s["itc-Latn-stripdiacritics"] }, sort_key = { Latn = s["itc-Latn-sortkey"] }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiLlMmNnOoPpQqRrSsTtUuVvXx", c.punc }, } m["lb"] = { "Luxembourgish", 9051, "gmw-hgm", "Latn, Brai", ancestors = "gmw-cfr", sort_key = { Latn = { from = {"ä", "ë", "é"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, }, } m["lg"] = { "Luganda", 33368, "bnt-nyg", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ŋ"}, to = {"n" .. p[1]} }, } m["li"] = { "Limburgish", 102172, "gmw-frk", "Latn", ancestors = "dum", } m["ln"] = { "Lingala", 36217, "bnt-bmo", "Latn", sort_key = { remove_diacritics = c.acute .. c.circ .. c.caron, from = {"ɛ", "gb", "mb", "mp", "nd", "ng", "nk", "ns", "nt", "ny", "nz", "ɔ"}, to = {"e" .. p[1], "g" .. p[1], "m" .. p[1], "m" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "n" .. p[4], "n" .. p[5], "n" .. p[6], "n" .. p[7], "o" .. p[1]} }, } m["lo"] = { "ලාඕ", 9211, "tai-swe", "Laoo", -- also Tai Noi/Lao Buhan script translit = "lo-translit", sort_key = "Laoo-sortkey", standard_chars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. c.punc, } m["lt"] = { "Lithuanian", 9083, "bat-eas", "Latn", ancestors = "olt", display_text = "lt-common", strip_diacritics = "lt-common", sort_key = "lt-common", standard_chars = "AaĄąBbCcČčDdEeĘęĖėFfGgHhIiĮįYyJjKkLlMmNnOoPpRrSsŠšTtUuŲųŪūVvZzŽž" .. c.punc, } m["lu"] = { "Luba-Katanga", 36157, "bnt-lub", "Latn", } m["lv"] = { "Latvian", 9078, "bat-eas", "Latn", strip_diacritics = { -- 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 = {"([Ee])" .. c.cedilla, "[" .. c.grave .. c.circ .. c.tilde .."]", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .. "?([^aAeEiIoOuU])", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .."?$", "([iI])" .. c.tilde .. "?([eE])" .. c.tilde .. "?", "([aAeEiIuU])" .. c.tilde, c.tilde}, to = {"%1", c.tilde, "%1%2%3", "%1%2", "%1%2", "%1" .. c.macron} }, sort_key = { from = {"ā", "č", "ē", "ģ", "ī", "ķ", "ļ", "ņ", "š", "ū", "ž"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1]} }, standard_chars = "AaĀāBbCcČčDdEeĒēFfGgĢģHhIiĪīJjKkĶķLlĻļMmNnŅņOoPpRrSsŠšTtUuŪūVvZzŽž" .. c.punc, } m["mg"] = { "Malagasy", 7930, "poz-bre", "Latn, Arab", } m["mh"] = { "Marshallese", 36280, "poz-mic", "Latn", sort_key = { from = {"ā", "ļ", "m̧", "ņ", "n̄", "o̧", "ō", "ū"}, to = {"a" .. p[1], "l" .. p[1], "m" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "u" .. p[1]} }, } m["mi"] = { "Māori", 36451, "poz-pep", "Latn", sort_key = { remove_diacritics = c.macron, from = {"ng", "wh"}, to = {"n" .. p[1], "w" .. p[1]} }, } m["mk"] = { "Macedonian", 9296, "zls", "Cyrl, Polyt", ancestors = "cu", translit = { Cyrl = "mk-translit", -- FIXME: formerly no translit specified for Polyt; unclear if the default [[Module:grc-translit]] is -- acceptable, so we disable it for now Polyt = false, }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, remove_exceptions = {"Ѓ", "ѓ", "Ќ", "ќ"} }, }, sort_key = { Cyrl = { remove_diacritics = c.grave, remove_exceptions = {"ѓ", "ќ"}, from = {"ѓ", "ѕ", "ј", "љ", "њ", "ќ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Cyrl = "АаБбВвГгДдЃѓЕеЖжЗзЅѕИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЌќУуФфХхЦцЧчЏџШш", c.punc }, } m["ml"] = { "මලයාලම්", 36236, "dra-mal", "Mlym", override_translit = true, -- Mlym translit in [[Module:scripts/data]] } m["mn"] = { "මොංගෝලියානු", 9246, "xgn-cen", "Cyrl, Mong, Latn, Brai", ancestors = "cmg", translit = { Cyrl = "mn-translit", -- Mong translit in [[Module:scripts/data]] }, override_translit = true, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] strip_diacritics = { Cyrl = {remove_diacritics = c.grave .. c.acute}, }, sort_key = { Cyrl = { remove_diacritics = c.grave, from = {"ё", "ө", "ү"}, to = {"е" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйЛлМмНнОоӨөРрСсТтУуҮүХхЦцЧчШшЫыЬьЭэЮюЯя—", Brai = c.braille, c.punc }, } -- "mo" is treated as "ro", see [[WT:LT]] m["mr"] = { "මරාථි", 1571, "inc-sou", "Deva, Modi", ancestors = "omr", translit = { Deva = "mr-translit", Modi = "mr-Modi-translit", }, strip_diacritics = { Deva = { from = {"च़", "ज़", "झ़"}, to = {"च", "ज", "झ"} }, }, } m["ms"] = { "මැලේ", 9237, "poz-mly", "Latn, ms-Arab", ancestors = "ms-cla", standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", c.punc }, } m["mt"] = { "Maltese", 9166, "sem-arb", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { from = {"’"}, to = {"'"}, }, ancestors = "sqr", sort_key = { from = { "ċ", "ġ", "ż", -- Convert into PUA so that decomposed form does not get caught by the next step. "([cgz])", -- Ensure "c" comes after "ċ", "g" comes after "ġ" and "z" comes after "ż". "g" .. p[1] .. "ħ", -- "għ" after initial conversion of "g". p[3], p[4], "ħ", "ie", p[5] -- Convert "ċ", "ġ", "ħ", "ie", "ż" into final output. }, to = { p[3], p[4], p[5], "%1" .. p[1], "g" .. p[2], "c", "g", "h" .. p[1], "i" .. p[1], "z" } }, } m["my"] = { "බුරුම", 9228, "tbq-brm", "Mymr", ancestors = "obr", translit = "my-translit", override_translit = true, sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"} }, } m["na"] = { "Nauruan", 13307, "poz-mic", "Latn", } m["nb"] = { "Norwegian Bokmål", 25167, "gmq", "Latn", wikimedia_codes = "no", ancestors = "gmq-mno, da", -- da as an (but not the) ancestor of nb was agreed on - do not change without discussion sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nd"] = { "Northern Ndebele", 35613, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["ne"] = { "Nepali", 33823, "inc-pah", "Deva, Newa", translit = { Deva = "ne-translit" }, } m["ng"] = { "Ndonga", 33900, "bnt-ova", "Latn", } m["nl"] = { "ඕලන්ද", 7411, "gmw-frk", "Latn, Brai", ancestors = "dum", sort_key = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'"}, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZzÄäËëÏïÖöÜü", Brai = c.braille, c.punc }, } m["nn"] = { "Norwegian Nynorsk", 25164, "gmq-wes", "Latn", ancestors = "gmq-mno", strip_diacritics = { remove_diacritics = c.grave .. c.acute, }, sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["no"] = { "නෝර්වීජියානු", 9043, "gmq-wes", "Latn", ancestors = "gmq-mno", sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nr"] = { "Southern Ndebele", 36785, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["nv"] = { "Navajo", 13310, "apa", "Latn, Brai", sort_key = { remove_diacritics = c.acute .. c.ogonek, from = { "chʼ", "tłʼ", "tsʼ", -- 3 chars "ch", "dl", "dz", "gh", "hw", "kʼ", "kw", "sh", "tł", "ts", "zh", -- 2 chars "ł", "ʼ" -- 1 char }, to = { "c" .. p[2], "t" .. p[2], "t" .. p[4], "c" .. p[1], "d" .. p[1], "d" .. p[2], "g" .. p[1], "h" .. p[1], "k" .. p[1], "k" .. p[2], "s" .. p[1], "t" .. p[1], "t" .. p[3], "z" .. p[1], "l" .. p[1], "z" .. p[2] } }, } m["ny"] = { "Chichewa", 33273, "bnt-nys", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ng'"}, to = {"ng"} }, } m["oc"] = { "Occitan", 14185, "roa-ocr", "Latn, Hebr", ancestors = "pro", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla, from = {"([lns])·h"}, to = {"%1h"} }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["oj"] = { "Ojibwe", 33875, "alg", "Cans, Latn", sort_key = { Latn = { from = {"aa", "ʼ", "ii", "oo", "sh", "zh"}, to = {"a" .. p[1], "h" .. p[1], "i" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1]} }, }, } m["om"] = { "Oromo", 33864, "cus-eas", "Latn, Ethi", } m["or"] = { "Odia", 33810, "inc-eas", "Orya", ancestors = "inc-mor", translit = "or-translit", } m["os"] = { "Ossetian", 33968, "xsc-sar", "Cyrl, Geor, Latn", ancestors = "oos", translit = { Cyrl = "os-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = { from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, sort_key = { Cyrl = { from = {"ӕ", "гъ", "дж", "дз", "ё", "къ", "пъ", "тъ", "хъ", "цъ", "чъ"}, to = {"а" .. p[1], "г" .. p[1], "д" .. p[1], "д" .. p[2], "е" .. p[1], "к" .. p[1], "п" .. p[1], "т" .. p[1], "х" .. p[1], "ц" .. p[1], "ч" .. p[1]} }, }, } m["pa"] = { "Punjabi", 58635, "inc-pan", "Guru, pa-Arab", translit = { Guru = "Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = { ["pa-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna, from = {"ݨ", "ࣇ"}, to = {"ن", "ل"} }, }, } m["pi"] = { "පාලි", 36727, "inc-mid", "Latn, Brah, Deva, Beng, Sinh, Mymr, Thai, Lana, Laoo, Khmr, Cakm", --and also Khom ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Beng = "pi-translit", Sinh = "si-translit", Mymr = "pi-translit", Thai = "pi-translit", Lana = "pi-translit", Laoo = "pi-translit", Khmr = "pi-translit", Cakm = "Cakm-translit", }, strip_diacritics = { Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, Mymr = { remove_diacritics = c.VS01, }, }, sort_key = { -- FIXME: This needs to be converted into the current standardized format. from = {"ā", "ī", "ū", "ḍ", "ḷ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"} }, } m["pl"] = { "පෝලන්ත", 809, "zlw-lch", "Latn", ancestors = "zlw-mpl", sort_key = { from = {"ą", "ć", "ę", "ł", "ń", "ó", "ś", "ź", "ż"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaĄąBbCcĆćDdEeĘęFfGgHhIiJjKkLlŁłMmNnŃńOoÓóPpRrSsŚśTtUuWwYyZzŹźŻż" .. c.punc, } m["ps"] = { "Pashto", 58680, "ira-pat", "ps-Arab", strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.zwarakay .. c.superalef}, } m["pt"] = { "පෘතුගීසි", 5146, "roa-gap", "Latn, Brai", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "º", "œ"}, to = {"a", "ae", "o", "oe"} }, }, standard_chars = { Latn = "AaÁáÂâÃãBbCcÇçDdEeÉéÊêFfGgHhIiÍíJjLlMmNnOoÓóÔôÕõPpQqRrSsTtUuÚúVvXxZz", Brai = c.braille, c.punc }, } m["qu"] = { "ක්වෙච්වා", 5218, "qwe", "Latn", } m["rm"] = { "Romansh", 13199, "roa-rhe", ancestors = "rm-old", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.small_e}, } m["ro"] = { "රුමේනියානු", 7913, "roa-eas", "Latn, Cyrl, Cyrs", translit = { Cyrl = "ro-translit" }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute, from = {"ă", "â", "î", "ș", "ț"}, to = {"a" .. p[1], "a" .. p[2], "i" .. p[1], "s" .. p[1], "t" .. p[1]} }, Cyrl = { from = {"ӂ"}, to = {"ж" .. p[1]} }, }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; presumably not present standard_chars = { Latn = "AaĂăÂâBbCcDdEeFfGgHhIiÎîJjLlMmNnOoPpRrSsȘșTtȚțUuVvXxZz", Cyrl = "АаБбВвГгДдЕеЖжӁӂЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЫыЬьЭэЮюЯя", c.punc }, } m["ru"] = { "රුසියානු", 7737, "zle", "Cyrl, Brai", ancestors = "zle-mru", translit = { Cyrl = "ru-translit" }, display_text = { Cyrl = { from = {"'"}, to = {"’"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, remove_exceptions = {"Ё", "ё", "Ѣ̈", "ѣ̈", "Я̈", "я̈"}, from = {"’"}, to = {"'"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, from = { "і", "ѣ", "ѳ", "ѵ" }, to = { "и" .. p[1], "ь" .. p[1], "я" .. p[2], "я" .. p[3] } }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЫыЬьЭэЮюЯя—", Brai = c.braille, (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["rw"] = { "Rwanda-Rundi", 3217514, "bnt-glb", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.caron}, } m["sa"] = { "සංස්කෘත", 11059, "inc", "as-Beng, Bali, Beng, Bhks, Brah, Mymr, xwo-Mong, Deva, Gujr, Guru, Gran, Hani, Java, Kthi, Knda, Kawi, Khar, Khmr, Laoo, Mlym, mnc-Mong, Marc, Modi, Mong, Nand, Newa, Orya, Phag, Ranj, Saur, Shrd, Sidd, Sinh, Soyo, Lana, Takr, Taml, Tang, Telu, Thai, Tibt, Tutg, Tirh, Zanb", --and also Khom; script codes sorted by canonical name rather than code for [[MOD:sa-convert]] translit = { Beng = "sa-Beng-translit", ["as-Beng"] = "sa-Beng-translit", -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Gujr = "sa-Gujr-translit", Guru = "sa-Guru-translit", Java = "sa-Java-translit", Kthi = "sa-Kthi-translit", Khmr = "pi-translit", Knda = "sa-Knda-translit", Lana = "pi-translit", Laoo = "pi-translit", Mlym = "sa-Mlym-translit", Modi = "sa-Modi-translit", -- Mong, mnc-Mong, xwo-Mong translit in [[Module:scripts/data]] -- NOTE: Formerly used xal-translit for transliterating xwo-Mong but that only handles Cyrillic; it has -- code to transliterate xwo-Mong but it's broken so I've replaced it with the default xwo-translit. Mymr = "pi-translit", Orya = "sa-Orya-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] Sinh = "si-translit", Taml = "sa-Taml-translit", Telu = "sa-Telu-translit", Thai = "pi-translit", -- Tibt translit in [[Module:scripts/data]] }, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] -- Tibt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] strip_diacritics = { Deva = s["sa-Deva-stripdiacritics"], Mymr = { remove_diacritics = c.VS01, }, Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, }, sort_key = { Deva = s["sa-Deva-stripdiacritics"], -- until we have a proper Sanskrit sorting algorithm. Lana = { -- Tai Tham from = {"ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ"}, to = {"ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}, }, Laoo = "Laoo-sortkey", Latn = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ"}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~"}, }, Mymr = { remove_diacritics = c.VS01, }, Thai = "Thai-sortkey", -- FIXME: The previous sort key which mixed all scripts removed ZWJ; I don't know which script(s) this was -- intended for and there are no other languages which remove it in the sort key AFAIK. If it needs to be -- removed, specify the script(s) it needs to be removed under or add handling for the "all" script that applies -- regardless of script. --all = { -- remove_diacritics = c.ZWJ, --}, }, } m["sc"] = { "Sardinian", 33976, "roa-sou", "Latn", ancestors = "sc-old", } m["sd"] = { "සින්ධි", 33997, "inc-snd", "sd-Arab, Deva, Sind, Khoj", translit = { Sind = "Sind-translit", ["sd-Arab"] = "sd-Arab-translit" }, strip_diacritics = { ["sd-Arab"] = { remove_diacritics = c.kashida .. c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, from = {"ٱ"}, to = {"ا"} }, }, } m["se"] = { "Northern Sami", 33947, "smi", "Latn", display_text = { from = {"'"}, to = {"ˈ"} }, strip_diacritics = {remove_diacritics = c.macron .. c.dotbelow .. "'ˈ"}, sort_key = { from = {"á", "č", "đ", "ŋ", "š", "ŧ", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "n" .. p[1], "s" .. p[1], "t" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĐđEeFfGgHhIiJjKkLlMmNnŊŋOoPpRrSsŠšTtŦŧUuVvZzŽž" .. c.punc, } m["sg"] = { "Sango", 33954, "crp", "Latn", ancestors = "ngb", } m["sh"] = { "Serbo-Croatian", 9301, "zls", "Latn, Cyrl, Glag, Arab", ietf_subtag = "hbs", -- ISO 639-3 code, since "sh" is deprecated from ISO 639-1 wikimedia_codes = "sh, bs, hr, sr", strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"Ć", "ć", "Ś", "ś", "Ź", "ź"} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"З́", "з́", "С́", "с́"} }, }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"ć", "ś", "ź"}, from = {"č", "ć", "dž", "đ", "lj", "nj", "š", "ś", "ž", "ź"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "z" .. p[1], "z" .. p[2]} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"з́", "с́"}, from = {"ђ", "з́", "ј", "љ", "њ", "с́", "ћ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "с" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, standard_chars = { Latn = "AaBbCcČčĆćDdĐđEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž", Cyrl = "АаБбВвГгДдЂђЕеЖжЗзИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЋћУуФфХхЦцЧчЏџШш", c.punc }, } m["si"] = { "සිංහල", 13267, "inc-ins", "Sinh", translit = "si-translit", override_translit = true, } m["sk"] = { "Slovak", 9058, "zlw", "Latn", ancestors = "zlw-osk", sort_key = {remove_diacritics = c.acute .. c.circ .. c.diaer .. c.caron}, standard_chars = "AaÁáÄäBbCcČčDdĎďEeÉéFfGgHhIiÍíJjKkLlĹ弾MmNnŇňOoÓóÔôPpRrŔŕSsŠšTtŤťUuÚúVvYyÝýZzŽž" .. c.punc, } m["sl"] = { "Slovene", 9063, "zls", "Latn", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.dgrave .. c.invbreve .. c.dotbelow, remove_exceptions = {"Ć", "ć", "Ǵ", "ǵ", "Ś", "ś", "Ź", "ź"}, from = {"Ə", "ə", "Ł", "ł"}, to = {"E", "e", "L", "l"}, }, sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dotabove .. c.ringabove .. c.dgrave .. c.invbreve .. c.dotbelow .. c.ringbelow .. c.ogonek, remove_exceptions = {"ć", "ǵ", "ś", "ź"}, from = {"ä", "č", "ć", "đ", "ə", "ë", "ǧ", "ǵ", "ï", "ł", "ö", "š", "ś", "ü", "ž", "ź"}, to = {"a" .. p[1], "c" .. p[1], "c" .. p[2], "d" .. p[1], "e", "e" .. p[1], "g" .. p[1], "g" .. p[2], "i" .. p[1], "l", "o" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]}, }, standard_chars = "AaBbCcČčDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž" .. c.punc, } m["sm"] = { "Samoan", 34011, "poz-pnp", "Latn", } m["sn"] = { "Shona", 34004, "bnt-sho", "Latn", strip_diacritics = {remove_diacritics = c.acute}, } m["so"] = { "සෝමාලි", 13275, "cus-som", "Latn, Arab, Osma", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, } m["sq"] = { "Albanian", 8748, "sqj", "Latn, Grek, ota-Arab, Elba, Todr, Vith", translit = { Elba = "Elba-translit", Vith = "Vith-translit", }, -- Grek display_text, sort_key in [[Module:scripts/data]] strip_diacritics = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron, from = {'^[ie] (%w)', '^të (%w)'}, to = {'%1', '%1'}, }, Grek = { -- Diacritic removal from Grek-stripdiacritics excluded. from = m_langdata.chars_substitutions["Grek-stripdiacritics"].from, to = m_langdata.chars_substitutions["Grek-stripdiacritics"].to, }, }, sort_key = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron .. c.tilde .. c.breve .. c.caron, from = {'^[ie] (%w)', '^të (%w)', 'ç', 'dh', 'ë', 'gj', 'll', 'nj', 'rr', 'sh', 'th', 'xh', 'zh'}, to = {'%1', '%1', 'c'..p[1], 'd'..p[1], 'e'..p[1], 'g'..p[1], 'l'..p[1], 'n'..p[1], 'r'..p[1], 's'..p[1], 't'..p[1], 'x'..p[1], 'z'..p[1]}, } -- TODO: Grek if the default sort key is unsuitable }, standard_chars = { Latn = "AaBbCcÇçDdEeËëFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvXxYyZz", c.punc }, } m["ss"] = { "Swazi", 34014, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["st"] = { "Sotho", 34340, "bnt-sts", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["su"] = { "සුන්ඩා", 34002, "poz-msa", "Latn, Sund, Arab", ancestors = "osn", translit = { Sund = "Sund-translit" }, } m["sv"] = { "ස්වීඩන්", 9027, "gmq-eas", "Latn", ancestors = "gmq-osw-lat", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla .. "':", remove_exceptions = {"å"}, from = {"ø", "æ", "œ", "ß", "å", "aͤ", "oͤ"}, to = {"o", "ae", "oe", "ss", "z" .. p[1], "ä", "ö"} }, standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvXxYyÅåÄäÖö" .. c.punc, } m["sw"] = { "Swahili", 7838, "bnt-swh", "Latn, Arab", sort_key = { Latn = { from = {"ng'"}, to = {"ng" .. p[1]} }, }, } m["ta"] = { "දෙමළ", 5885, "dra-tam", "Taml", ancestors = "ta-mid", translit = "ta-translit", override_translit = true, } m["te"] = { "තෙලිඟු", 8097, "dra-tel", "Telu", translit = "te-translit", override_translit = true, } m["tg"] = { "Tajik", 9260, "ira-swi", "Cyrl, fa-Arab, Latn", ancestors = "fa-cls", translit = { Cyrl = "tg-translit" }, override_translit = true, strip_diacritics = { Cyrl = s["tg-stripdiacritics"], Latn = s["tg-stripdiacritics"], }, sort_key = { Cyrl = { from = {"ғ", "ё", "ӣ", "қ", "ӯ", "ҳ", "ҷ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "к" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["th"] = { "තායි", 9217, "tai-swe", "Thai, Khomt, Brai", translit = { Thai = "th-translit" }, sort_key = { Thai = "Thai-sortkey" }, } m["ti"] = { "Tigrinya", 34124, "sem-eth", "Ethi", translit = "Ethi-translit", } m["tk"] = { "Turkmen", 9267, "trk-ogz", "Latn, Cyrl, Arab", strip_diacritics = { Latn = s["tk-stripdiacritics"], Cyrl = s["tk-stripdiacritics"], }, sort_key = { Latn = { from = {"ç", "ä", "ž", "ň", "ö", "ş", "ü", "ý"}, to = {"c" .. p[1], "e" .. p[1], "j" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "y" .. p[1]} }, Cyrl = { from = {"ё", "җ", "ң", "ө", "ү", "ә"}, to = {"е" .. p[1], "ж" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "э" .. p[1]} }, }, ancestors = "trk-eog", } m["tl"] = { "Tagalog", 34057, "phi", "Latn, Tglg", translit = { Tglg = "tl-translit" }, override_translit = true, strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, standard_chars = { Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy", c.punc }, sort_key = { Latn = "tl-sortkey", }, } m["tn"] = { "Tswana", 34137, "bnt-sts", "Latn", } m["to"] = { "Tongan", 34094, "poz-ton", "Latn", strip_diacritics = {remove_diacritics = c.acute}, sort_key = {remove_diacritics = c.macron}, } m["tr"] = { "තුර්කි", 256, "trk-ogz", "Latn", ancestors = "ota", dotted_dotless_i = true, sort_key = { from = { -- Ignore circumflex, but account for capital Î wrongly becoming ı + circ due to dotted dotless I logic. "ı" .. c.circ, c.circ, "i", -- Ensure "i" comes after "ı". "ç", "ğ", "ı", "ö", "ş", "ü" }, to = { "i", "", "i" .. p[1], "c" .. p[1], "g" .. p[1], "i", "o" .. p[1], "s" .. p[1], "u" .. p[1] } }, standard_chars = "AaÂâBbCcÇçDdEeFfGgĞğHhIıİiÎîJjKkLlMmNnOoÖöPpRrSsŞşTtUuÛûÜüVvYyZz" .. c.punc, } m["ts"] = { "Tsonga", 34327, "bnt-tsr", "Latn", } m["tt"] = { "Tatar", 25285, "trk-kbu", "Cyrl, Latn, tt-Arab", translit = { Cyrl = "tt-translit", ["tt-Arab"] = "tt-translit" }, --override_translit = true, -- enable override until Module code can detect Russian loans such as [[аэропорт]] dotted_dotless_i = true, sort_key = { Cyrl = { from = {"ә", "ў", "ғ", "ё", "җ", "қ", "ң", "ө", "ү", "һ"}, to = {"а" .. p[1], "в" .. p[1], "г" .. p[1], "е" .. p[1], "ж" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1]} }, Latn = { from = { "i", -- Ensure "i" comes after "ı". "ä", "ə", "ç", "ğ", "ı", "ñ", "ŋ", "ö", "ɵ", "ş", "ü" }, to = { "i" .. p[1], "a" .. p[1], "a" .. p[2], "c" .. p[1], "g" .. p[1], "i", "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "s" .. p[1], "u" .. p[1] } }, }, } -- "tw" is treated as "ak", see [[WT:LT]] m["ty"] = { "Tahitian", 34128, "poz-pep", "Latn", } m["ug"] = { "Uyghur", 13263, "trk-kar", "ug-Arab, Latn, Cyrl", ancestors = "chg", translit = { ["ug-Arab"] = "ug-translit", Cyrl = "ug-translit", }, override_translit = true, } m["uk"] = { "යුක්‍රේනියානු", 8798, "zle", "Cyrl", ancestors = "zle-muk", translit = "uk-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, sort_key = { remove_diacritics = c.grave .. c.acute, from = { "ї", -- 2 chars "ґ", "є", "і" -- 1 char }, to = { "и" .. p[2], "г" .. p[1], "е" .. p[1], "и" .. p[1] } }, standard_chars = "АаБбВвГгДдЕеЄєЖжЗзИиІіЇїЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЬьЮюЯя" .. c.punc:gsub("'", ""), -- Exclude apostrophe. } m["ur"] = { "උර්දු", 1617, "inc-hnd", "ur-Arab, Hebr", translit = { ["ur-Arab"] = "ur-translit" }, strip_diacritics = { ["ur-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ۂ", "ٱ"}, to = {"ہ", "ہ", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { ["ur-Arab"] = "ایببپتثجچحخدذرزژسشصضطظعغفقکگلࣇڷمنݨوؤہھئٹڈڑآے", c.punc, }, } m["uz"] = { "උස්බෙක්", 9264, "trk-kar", "Latn, Cyrl, fa-Arab", ancestors = "chg", translit = { Cyrl = "uz-translit" }, sort_key = { Latn = { from = {"oʻ", "gʻ", "sh", "ch", "ng"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3], "z" .. p[4], "z" .. p[5]} }, Cyrl = { from = {"ё", "ў", "қ", "ғ", "ҳ"}, to = {"е" .. p[1], "я" .. p[1], "я" .. p[2], "я" .. p[3], "я" .. p[4]} }, }, strip_diacritics = { ["fa-Arab"] = "ar-stripdiacritics", }, } m["ve"] = { "Venda", 32704, "bnt-bso", "Latn", } m["vi"] = { "වියට්නාම", 9199, "mkh-vie", "Latn, Hani", ancestors = "mkh-mvi", sort_key = { Latn = "vi-sortkey", Hani = "Hani-sortkey", }, } m["vo"] = { "Volapük", 36986, "art", "Latn", } m["wa"] = { "Walloon", 34219, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["wo"] = { "Wolof", 34257, "alv-fwo", "Latn, Arab, Gara", } m["xh"] = { "Xhosa", 13218, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["yi"] = { "යිඩිශ්", 8641, "gmw-hgm", "Hebr, Latn", ancestors = "gmh", translit = { Hebr = "yi-translit", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["yo"] = { "Yoruba", 34311, "alv-yor", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.macron} }, sort_key = { Latn = { from = {"ẹ", "ɛ", "gb", "ị", "kp", "ọ", "ɔ", "ṣ", "sh", "ụ"}, to = {"e" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "o" .. p[1], "o" .. p[1], "s" .. p[1], "s" .. p[1], "u" .. p[1]} }, }, } m["za"] = { "Zhuang", 13216, "tai", "Latn, Hani", sort_key = { Latn = "za-sortkey", Hani = "Hani-sortkey", }, } m["zh"] = { "චීන", 7850, "zhx", "Hants, Latn, Bopo, Nshu, Brai", ancestors = "ltc", generate_forms = "zh-generateforms", translit = { Hani = "zh-translit", Bopo = "zh-translit", }, sort_key = { Hani = "Hani-sortkey" }, } m["zu"] = { "සූලූ", 10179, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } return require("Module:languages").finalizeData(m, "language") 6yk4rrxtt5a7kwrivcjgdsseqh6law5 828 7919 231361 32445 2025-09-09T16:11:09Z en>Surjection 0 231361 Scribunto text/plain local p = {} local fam = mw.loadData("Module:families/data") local function format(code) if code == "sgn" then return "<code>[[:Category:Sign languages|sign <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" elseif code == "sgn-fsl" then return "<code>[[:Category:French Sign Languages|French Sign Languages <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" elseif code == "sgn-gsl" then return "<code>[[:Category:German Sign Languages|German Sign Languages <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" elseif code == "sgn-jsl" then return "<code>[[:Category:Japanese Sign Languages|Japanese Sign Languages <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" else return "<code>[[:Category:" .. fam[code][1] .. " languages|" .. fam[code][1] .. " <span style=\"color:var(--wikt-palette-green-9,green);\">(" .. code .. ")</span>]]</code>" end end local function dump(data, prefix) if type(data) == "string" then return format(data) else local result = "" local branch = "├───" local next_level = prefix .. "│　　　　" local current = "" for i,val in ipairs(data) do if i == #data then branch = "└───" next_level = prefix .. "　　　 　" end if #val == 0 then result = result .. prefix .. branch .. dump(val.name) .. "<br/>" else result = result .. "{{(!}} class=mw-collapsible style=border-collapse:collapse\n{{!}}" result = result .. prefix .. branch .. dump(val.name) result = result .. "\n{{!-}}\n{{!}}" result = result .. dump(val, next_level) result = result .. "\n{{!)}}\n" end end return result end end local function deep_sort(current) local result = {} local is_table = {} for key,val in pairs(current) do if type(key) == "number" then table.insert(result, val) else is_table[key] = true table.insert(result, key) end end table.sort(result, function(a,b) return (fam[a] or error(a))[1] < (fam[b] or error(b))[1] end) local i = 2 while i<#result do while fam[result[i-1]] == fam[result[i]] do table.remove(result,i) end i = i + 1 end for i=1,#result do if is_table[result[i]] then local name = result[i] result[i] = deep_sort(current[result[i]]) result[i].name = name else result[i] = {name = result[i]} end end return result end function p.show(frame) local children = {} for key,val in pairs(fam) do if val[3] and val[3] ~= "qfa-not" and val[3] ~= "qfa-und" then if children[val[3]] then table.insert(children[val[3]], key) else children[val[3]] = {key} end end end local function make_nested(data) local make_nil = {} for key,val in pairs(data) do if type(key) == "number" then if children[val] then data[val] = make_nested(children[val]) table.insert(make_nil, key) children[val] = nil end else data[key] = make_nested(val) end end for _,key in ipairs(make_nil) do data[key] = nil end return data end children = make_nested(children) children = deep_sort(children) local result = "" for i=1,#children do result = result .. "\n\n\n{| class=mw-collapsible style=border-collapse:collapse\n|" .. format(children[i].name) .. "\n|-\n|" result = result .. dump(children[i], "　　") result = result .. "\n|}" end return frame:preprocess(result) end return p jthkw1d7e3p46vsu8yivvidmq8riplh 231362 231361 2026-04-14T05:46:57Z Lee 19 [[:en:Module:families/data/hierarchy]] වෙතින් එක් සංශෝධනයක් 231361 Scribunto text/plain local p = {} local fam = mw.loadData("Module:families/data") local function format(code) if code == "sgn" then return "<code>[[:Category:Sign languages|sign <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" elseif code == "sgn-fsl" then return "<code>[[:Category:French Sign Languages|French Sign Languages <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" elseif code == "sgn-gsl" then return "<code>[[:Category:German Sign Languages|German Sign Languages <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" elseif code == "sgn-jsl" then return "<code>[[:Category:Japanese Sign Languages|Japanese Sign Languages <span style=\"color:var(--wikt-palette-green-9,green);\">(sgn)</span>]]</code>" else return "<code>[[:Category:" .. fam[code][1] .. " languages|" .. fam[code][1] .. " <span style=\"color:var(--wikt-palette-green-9,green);\">(" .. code .. ")</span>]]</code>" end end local function dump(data, prefix) if type(data) == "string" then return format(data) else local result = "" local branch = "├───" local next_level = prefix .. "│　　　　" local current = "" for i,val in ipairs(data) do if i == #data then branch = "└───" next_level = prefix .. "　　　 　" end if #val == 0 then result = result .. prefix .. branch .. dump(val.name) .. "<br/>" else result = result .. "{{(!}} class=mw-collapsible style=border-collapse:collapse\n{{!}}" result = result .. prefix .. branch .. dump(val.name) result = result .. "\n{{!-}}\n{{!}}" result = result .. dump(val, next_level) result = result .. "\n{{!)}}\n" end end return result end end local function deep_sort(current) local result = {} local is_table = {} for key,val in pairs(current) do if type(key) == "number" then table.insert(result, val) else is_table[key] = true table.insert(result, key) end end table.sort(result, function(a,b) return (fam[a] or error(a))[1] < (fam[b] or error(b))[1] end) local i = 2 while i<#result do while fam[result[i-1]] == fam[result[i]] do table.remove(result,i) end i = i + 1 end for i=1,#result do if is_table[result[i]] then local name = result[i] result[i] = deep_sort(current[result[i]]) result[i].name = name else result[i] = {name = result[i]} end end return result end function p.show(frame) local children = {} for key,val in pairs(fam) do if val[3] and val[3] ~= "qfa-not" and val[3] ~= "qfa-und" then if children[val[3]] then table.insert(children[val[3]], key) else children[val[3]] = {key} end end end local function make_nested(data) local make_nil = {} for key,val in pairs(data) do if type(key) == "number" then if children[val] then data[val] = make_nested(children[val]) table.insert(make_nil, key) children[val] = nil end else data[key] = make_nested(val) end end for _,key in ipairs(make_nil) do data[key] = nil end return data end children = make_nested(children) children = deep_sort(children) local result = "" for i=1,#children do result = result .. "\n\n\n{| class=mw-collapsible style=border-collapse:collapse\n|" .. format(children[i].name) .. "\n|-\n|" result = result .. dump(children[i], "　　") result = result .. "\n|}" end return frame:preprocess(result) end return p jthkw1d7e3p46vsu8yivvidmq8riplh 828 8212 231344 29374 2026-02-10T07:00:21Z en>Thadh 0 231344 Scribunto text/plain local export = {} local tab = { ["А"]="A", ["Б"]="B", ["В"]="V", ["Г"]="G", ["Д"]="D", ["Е"]="E", ["Ё"]="O", ["Ж"]="Ž", ["З"]="Z", ["И"]="I", ["І"]="I", ["Й"]="J", ["К"]="K", ["Л"]="L", ["М"]="M", ["Н"]="N", ["О"]="O", ["Ӧ"]="Ö", ["П"]="P", ["Р"]="R", ["С"]="S", ["Т"]="T", ["У"]="U", ["Ф"]="F", ["Х"]="X", ["Ц"]="C", ["Ч"]="Ć", ["Ш"]="Š", ["Щ"]="Šč", ["Ъ"]="", ["Ы"]="Y", ["Ь"]="", ["Э"]="E", ["Ю"]="U", ["Я"]="A", ['а']='a', ['б']='b', ['в']='v', ['г']='g', ['д']='d', ['е']='e', ['ё']='o', ['ж']='ž', ['з']='z', ['и']='i', ['і']='i', ['й']='j', ['к']='k', ['л']='l', ['м']='m', ['н']='n', ['о']='o', ['ӧ']='ö', ['п']='p', ['р']='r', ['с']='s', ['т']='t', ['у']='u', ['ф']='f', ['х']='x', ['ц']='c', ['ч']='ć', ['ш']='š', ['щ']='šč', ['ъ']='', ['ы']='y', ['ь']='', ['э']='e', ['ю']='u', ['я']='a', ['Ө']='Å', ['ө']='å', ['Ӱ']='Ü', ['ӱ']='ü', } function export.tr(text, lang, sc) local language = lang -- Ё needs converting if is decomposed text = text:gsub("ё","ё"):gsub("Ё","Ё") -- тш text = mw.ustring.gsub(text, "Тш", "Č") text = mw.ustring.gsub(text, "тш", "č") -- soft consonants text = mw.ustring.gsub(text, "([Дд])з", "%1зQ") text = mw.ustring.gsub(text, "([ДЗЛНСТдзлнст])([еёияюь])", "%1Q%2") -- geminates text = mw.ustring.gsub(text, "([ДЗЛНСТдзлнст])([ДЗЛНСТдзлнст])([еёияюь])", "%1Q%2Q%3") if lang ~= "kpv" then text = mw.ustring.gsub(text, "([БВГЖКМПРФХЦЧШЩбвгжкмпрфхцчшщ])([ёяюь])", "%1Q%2") end -- soft vowels after a vowel or at the beginning of a word become j- text = mw.ustring.gsub(text, "([АОÖӨУӰЫЕЯЁЮИІЕЪЬЙаоöөуӱыэяёюиіеъьй%A][\204\129\204\128]?)([еёюя])", "%1j%2") text = mw.ustring.gsub(text, "^Е", "Jе") text = mw.ustring.gsub(text, "^Ё", "Jё") text = mw.ustring.gsub(text, "^Ю", "Jю") text = mw.ustring.gsub(text, "^Я", "jя") text = mw.ustring.gsub(text, "^([еёюя])", "j%1") -- palatalisation text = mw.ustring.gsub(text, "ДQ", "Ď") text = mw.ustring.gsub(text, "дQ", "ď") text = mw.ustring.gsub(text, "ЗQ", "Ź") text = mw.ustring.gsub(text, "зQ", "ź") text = mw.ustring.gsub(text, "ЛQ", "Ľ") text = mw.ustring.gsub(text, "лQ", "ľ") text = mw.ustring.gsub(text, "НQ", "Ń") text = mw.ustring.gsub(text, "нQ", "ń") text = mw.ustring.gsub(text, "СQ", "Ś") text = mw.ustring.gsub(text, "сQ", "ś") text = mw.ustring.gsub(text, "ТQ", "Ť") text = mw.ustring.gsub(text, "тQ", "ť") text = mw.ustring.gsub(text, "Q", "ʹ") return (mw.ustring.gsub(text,'.',tab)) end return export ily11k1qcdrsdgtlpcct8jcb8jj7zw6 231345 231344 2026-04-13T17:03:31Z Lee 19 [[:en:Module:kv-translit]] වෙතින් එක් සංශෝධනයක් 231344 Scribunto text/plain local export = {} local tab = { ["А"]="A", ["Б"]="B", ["В"]="V", ["Г"]="G", ["Д"]="D", ["Е"]="E", ["Ё"]="O", ["Ж"]="Ž", ["З"]="Z", ["И"]="I", ["І"]="I", ["Й"]="J", ["К"]="K", ["Л"]="L", ["М"]="M", ["Н"]="N", ["О"]="O", ["Ӧ"]="Ö", ["П"]="P", ["Р"]="R", ["С"]="S", ["Т"]="T", ["У"]="U", ["Ф"]="F", ["Х"]="X", ["Ц"]="C", ["Ч"]="Ć", ["Ш"]="Š", ["Щ"]="Šč", ["Ъ"]="", ["Ы"]="Y", ["Ь"]="", ["Э"]="E", ["Ю"]="U", ["Я"]="A", ['а']='a', ['б']='b', ['в']='v', ['г']='g', ['д']='d', ['е']='e', ['ё']='o', ['ж']='ž', ['з']='z', ['и']='i', ['і']='i', ['й']='j', ['к']='k', ['л']='l', ['м']='m', ['н']='n', ['о']='o', ['ӧ']='ö', ['п']='p', ['р']='r', ['с']='s', ['т']='t', ['у']='u', ['ф']='f', ['х']='x', ['ц']='c', ['ч']='ć', ['ш']='š', ['щ']='šč', ['ъ']='', ['ы']='y', ['ь']='', ['э']='e', ['ю']='u', ['я']='a', ['Ө']='Å', ['ө']='å', ['Ӱ']='Ü', ['ӱ']='ü', } function export.tr(text, lang, sc) local language = lang -- Ё needs converting if is decomposed text = text:gsub("ё","ё"):gsub("Ё","Ё") -- тш text = mw.ustring.gsub(text, "Тш", "Č") text = mw.ustring.gsub(text, "тш", "č") -- soft consonants text = mw.ustring.gsub(text, "([Дд])з", "%1зQ") text = mw.ustring.gsub(text, "([ДЗЛНСТдзлнст])([еёияюь])", "%1Q%2") -- geminates text = mw.ustring.gsub(text, "([ДЗЛНСТдзлнст])([ДЗЛНСТдзлнст])([еёияюь])", "%1Q%2Q%3") if lang ~= "kpv" then text = mw.ustring.gsub(text, "([БВГЖКМПРФХЦЧШЩбвгжкмпрфхцчшщ])([ёяюь])", "%1Q%2") end -- soft vowels after a vowel or at the beginning of a word become j- text = mw.ustring.gsub(text, "([АОÖӨУӰЫЕЯЁЮИІЕЪЬЙаоöөуӱыэяёюиіеъьй%A][\204\129\204\128]?)([еёюя])", "%1j%2") text = mw.ustring.gsub(text, "^Е", "Jе") text = mw.ustring.gsub(text, "^Ё", "Jё") text = mw.ustring.gsub(text, "^Ю", "Jю") text = mw.ustring.gsub(text, "^Я", "jя") text = mw.ustring.gsub(text, "^([еёюя])", "j%1") -- palatalisation text = mw.ustring.gsub(text, "ДQ", "Ď") text = mw.ustring.gsub(text, "дQ", "ď") text = mw.ustring.gsub(text, "ЗQ", "Ź") text = mw.ustring.gsub(text, "зQ", "ź") text = mw.ustring.gsub(text, "ЛQ", "Ľ") text = mw.ustring.gsub(text, "лQ", "ľ") text = mw.ustring.gsub(text, "НQ", "Ń") text = mw.ustring.gsub(text, "нQ", "ń") text = mw.ustring.gsub(text, "СQ", "Ś") text = mw.ustring.gsub(text, "сQ", "ś") text = mw.ustring.gsub(text, "ТQ", "Ť") text = mw.ustring.gsub(text, "тQ", "ť") text = mw.ustring.gsub(text, "Q", "ʹ") return (mw.ustring.gsub(text,'.',tab)) end return export ily11k1qcdrsdgtlpcct8jcb8jj7zw6 828 9436 231369 220335 2026-03-05T07:10:05Z en>Mellohi! 0 231369 Scribunto text/plain local m = {} m["aav-khs-pro"] = { aliases = {"Proto-Khasic"}, } m["aav-nic-pro"] = { } m["aav-pkl-pro"] = { } m["aav-pro"] = { -- mkh-pro will merge into this. } m["afa-pro"] = { aliases = {"Proto-Afro-Asiatic", "Hamito-Semitic"}, } m["alg-aga"] = { aliases = {"Agwam", "Agaam"}, } m["alg-pro"] = { } m["alv-ama"] = { } m["alv-bgu"] = { aliases = {"Baïnounk Gubëeher", -- Wikipedia's name "Gubeeher-Gufangor-Gubelor", -- Glottolog's name, "Gubëeher", "Nyun Gubëeher", "Nun Gubëeher"}, -- N(y)un appears to be the family name varieties = {"Gubeeher", "Gufangor", "Gubelor"}, } m["alv-bua-pro"] = { } m["alv-cng-pro"] = { } m["alv-edk-pro"] = { } m["alv-edo-pro"] = { } m["alv-fli-pro"] = { } m["alv-gbe-pro"] = { } m["alv-gng-pro"] = { } m["alv-gtm-pro"] = { aliases = {"Proto-Ghana-Togo Mountain"}, } m["alv-gwa"] = { } m["alv-hei-pro"] = { } m["alv-ido-pro"] = { } m["alv-igb-pro"] = { } m["alv-kwa-pro"] = { } m["alv-mum-pro"] = { } m["alv-nup-pro"] = { } m["alv-pro"] = { } m["alv-von-pro"] = { } m["alv-yor-pro"] = { } m["alv-yrd-pro"] = { } m["apa-pro"] = { aliases = {"Proto-Apache", "Proto-Southern Athabaskan"}, } m["aql-pro"] = { } m["art-adu"] = { aliases = {"Westron"}, } m["art-bel"] = { } m["art-blk"] = { } m["art-bsp"] = { } m["art-com"] = { } m["art-dtk"] = { } m["art-elo"] = { } m["art-gld"] = { } m["art-lap"] = { } m["art-man"] = { } m["art-mun"] = { } m["art-nav"] = { } m["art-vlh"] = { } m["ath-nic"] = { } m["ath-pro"] = { } m["auf-pro"] = { aliases = {"Proto-Arawan", "Proto-Arauan"}, } m["aus-alu"] = { other_names = {"Ogh-Alungul", "Alngula"}, } m["aus-and"] = { aliases = {"Adithinngithigh"}, } m["aus-ang"] = { other_names = {"Ogh-Anggula", "Anggula", "Ogh-Anggul", "Anggul"}, } m["aus-arn-pro"] = { } m["aus-bra"] = { aliases = {"Barranbinja", "Baranbinya", "Burranbinya", "Burrumbiniya", "Burrunbinya", "Barrumbinya", "Barren-binya", "Parran-binye"}, } m["aus-brm"] = { } m["aus-cww-pro"] = { } m["aus-dal-pro"] = { } m["aus-guw"] = { other_names = {"Gowar", "Goowar", "Gooar", "Guar", "Gowr-burra", "Ngugi", "Mugee", "Wogee", "Gnoogee", "Chunchiburri", "Booroo-geen-merrie"}, } m["aus-lsw"] = { aliases = {"Little Swanport Tasmanian"}, } m["aus-mbi"] = { other_names = {"Mbeiwum"}, } m["aus-ngk"] = { other_names = {"Ngkot", "Nggoth"}, } m["aus-nyu-pro"] = { } m["aus-pam-pro"] = { } m["aus-tul"] = { other_names = {"Dappil", "Dapil", "Toolooa", "Dulua", "Narung", "Dandan"}, } m["aus-uwi"] = { other_names = {"Uwinjmil"}, } m["aus-wdj-pro"] = { } m["aus-won"] = { } m["aus-wul"] = { other_names = {"Manbara", "Wulgurugaba", "Wulgurukaba", "Nhawalgaba"}, } m["aus-ynk"] = { -- contrast nny } m["awd-amc-pro"] = { other_names = {"Western Maipuran"}, } m["awd-kmp-pro"] = { other_names = {"Campa", "Kampan", "Campan", "Pre-Andine Maipurean"}, } m["awd-prw-pro"] = { other_names = {"Paresí-Waurá", "Parecí–Xingú", "Paresí–Xingu", "Central Arawak", "Central Maipurean"}, } m["awd-ama"] = { } m["awd-ana"] = { aliases = {"Anauya"}, } m["awd-apo"] = { other_names = {"Lapachu"}, } m["awd-cab"] = { aliases = {"Cabere", "Cávere", "Cavere"}, } m["awd-gnu"] = { other_names = {"Guinao", "Inao", "Guniare", "Quinhau", "Guiano"}, } m["awd-kar"] = { aliases = {"Kariaí", "Kariai", "Cariyai", "Carihiahy"}, } m["awd-kaw"] = { aliases = {"Cawishana", "Cayuishana", "Kaishana", "Cauixana"}, } m["awd-kus"] = { aliases = {"Kustenaú", "Custenau", "Kutenabu"}, } m["awd-man"] = { } m["awd-mar"] = { aliases = {"Marawán"}, } m["awd-mpr"] = { aliases = {"Maypure", "Mejepure"}, } m["awd-mrt"] = { aliases = {"Mariate"}, } m["awd-nwk-pro"] = { aliases = {"Proto-Newiki"}, } m["awd-pai"] = { aliases = {"Paiconeca", "Paikone", "Paicone"}, } m["awd-pas"] = { aliases = {"Passé", "Pazé"}, } m["awd-pro"] = { other_names = {"Proto-Arawakan", "Proto-Maipurean", "Proto-Maipuran"}, } m["awd-she"] = { aliases = {"Shebaya", "Shebaye"}, } m["awd-taa-pro"] = { other_names = {"Proto-Ta-Arawakan", "Proto-Caribbean Northern Arawak"}, } m["awd-wai"] = { other_names = {"Wainuma", "Wai", "Waima", "Wainumi", "Wainambí", "Waiwana", "Waipi", "Yanuma"}, } m["awd-yum"] = { aliases = {"Jumana"}, } m["azc-caz"] = { aliases = {"Caxcan", "Kaskán"}, } m["azc-cup-pro"] = { } m["azc-ktn"] = { aliases = {"Gitanemuk"}, } m["azc-nah-pro"] = { } m["azc-num-pro"] = { } m["azc-pro"] = { } m["azc-tak-pro"] = { } m["azc-tat"] = { } m["ber-fog"] = { other_names = {"El-Fogaha", "El-Foqaha", "Foqaha", "Fuqaha"}, } m["ber-pro"] = { } m["ber-zuw"] = { } m["bnt-bal"] = { } m["bnt-bon"] = { } m["bnt-boy"] = { } m["bnt-bwa"] = { } m["bnt-cmw"] = { other_names = {"Bravanese", "Mwiini", "Mwini", "Chimwini", "Chimini", "Brava"}, } m["bnt-ind"] = { other_names = {"Kɔlɔmɔnyi", "Kɔlɛ", "Kasaï Oriental"}, } m["bnt-lal"] = { } m["bnt-mpi"] = { } m["bnt-mpu"] = { } m["bnt-ngu-pro"] = { } m["bnt-phu"] = { aliases = {"Siphuthi"}, } m["bnt-pro"] = { } m["bnt-sab-pro"] = { } m["bnt-sbo"] = { } m["bnt-sts-pro"] = { } m["btk-pro"] = { } m["cau-abz-pro"] = { other_names = {"Proto-Abazgi", "Proto-Abkhaz-Tapanta"}, } m["cau-and-pro"] = { aliases = {"Proto-Andi", "Proto-Andic"}, } m["cau-ava-pro"] = { aliases = {"Proto-Avar-Andian", "Proto-Avar-Andi", "Proto-Avar-Andic"}, } m["cau-cir-pro"] = { other_names = {"Proto-Adyghe-Kabardian", "Proto-Adyghe-Circassian"}, } m["cau-drg-pro"] = { other_names = {"Proto-Dargin"}, } m["cau-lzg-pro"] = { aliases = {"Proto-Lezgi", "Proto-Lezgian", "Proto-Lezgic"}, } m["cau-nec-pro"] = { } m["cau-nkh-pro"] = { } m["cau-nwc-pro"] = { } m["cau-tsz-pro"] = { other_names = {"Proto-Tsezic", "Proto-Didoic"}, } m["cba-ata"] = { other_names = {"Atanque", "Cancuamo", "Kankuamo", "Kankwe", "Kankuí", "Atanke"}, } m["cba-cat"] = { other_names = {"Catio Chibcha", "Old Catio"}, } m["cba-dor"] = { other_names = {"Chumulu", "Changuena", "Changuina", "Chánguena", "Gualaca"}, } m["cba-dui"] = { } m["cba-hue"] = { other_names = {"Güetar", "Guetar", "Brusela"}, } m["cba-nut"] = { other_names = {"Nutabane"}, } m["cba-pro"] = { } m["ccs-pro"] = { } m["ccs-gzn-pro"] = { aliases = {"Proto-Karto-Zan"}, } m["cdc-cbm-pro"] = { aliases = {"Proto-Central-Chadic", "Proto-Biu-Mandara"}, } m["cdc-mas-pro"] = { } m["cdc-pro"] = { } m["cdd-pro"] = { } m["cel-bry-pro"] = { aliases = {"Proto-Brittonic", "Common Brythonic", "Common Brittonic"}, } m["cel-gal"] = { } m["cel-gau"] = { } m["cel-pro"] = { } m["chi-pro"] = { } m["chm-pro"] = { } m["cmc-pro"] = { } m["crp-bip"] = { } m["crp-gep"] = { aliases = {"Greenlandic Pidgin", "Greenlandic Eskimo Pidgin"}, } m["crp-kia"] = { aliases = {"Kiautschou Pidgin German"}, } m["crp-mar"] = { other_names = {"Jamaican Maroon Spirit Possession Language"}, } m["crp-mpp"] = { aliases = {"Macao Pidgin Portuguese"}, } m["crp-rsn"] = { } m["crp-slb"] = { other_names = {"Solombala-English", "Solombala English-Russian Pidgin"}, } m["crp-spp"] = { } m["crp-tpr"] = { } m["csu-bba-pro"] = { } m["csu-maa-pro"] = { } m["csu-pro"] = { } m["csu-sar-pro"] = { } m["cus-ash"] = { other_names = {"Ashraf", "Af-Ashraaf"}, varieties = { {"Marka, Lower Shabelle"}, "Shingani"}, } m["cus-hec-pro"] = { } m["cus-som-pro"] = { aliases = {"Proto-Sam", "Proto-Macro-Somali"}, } m["cus-sou-pro"] = { other_names = {"Proto-Rift"}, } m["cus-pro"] = { } m["dmn-dam"] = { } m["dra-bry"] = { aliases = {"Byari"}, } m["dra-cen-pro"] = { } m["dra-mkn"] = { aliases = {"Nadugannada"}, } m["dra-nor-pro"] = { } m["dra-okn"] = { aliases = {"Halegannada"}, } m["dra-ote"] = { } m["dra-pro"] = { } m["dra-sdo-pro"] = { aliases = {"Proto-South Dravidian"}, } m["dra-sdt-pro"] = { aliases = {"Proto-South-Central Dravidian"}, } m["dra-sou-pro"] = { aliases = {"Proto-Southern Dravidian"}, } m["egx-dem"] = { aliases = {"Demotic", "Enchorial"}, } m["dmn-pro"] = { } m["dmn-mdw-pro"] = { } m["dru-pro"] = { } m["ero-gsz"] = { } m["ero-nya"] = { } m["ero-tau"] = { other_names = {"Rtau"}, } m["esx-esk-pro"] = { } m["esx-ink"] = { } m["esx-inq"] = { } m["esx-inu-pro"] = { } m["esx-pro"] = { } m["esx-tut"] = { } m["euq-pro"] = { aliases = {"Proto-Vasconic"}, } m["gba-pro"] = { } m["gem-pro"] = { aliases = {"Common Germanic"}, } m["gme-bur"] = { aliases = {"Burgundish", "Burgundic"}, } m["gme-cgo"] = { } m["gmq-gut"] = { } m["gmq-jmk"] = { aliases = {"Jamtlandic"}, } m["gmq-mno"] = { } m["gmq-oda"] = { } m["gmq-ogt"] = { aliases = {"Old Gotlandic"}, } m["gmq-osw"] = { } m["gmq-pro"] = { aliases = {"Proto-Scandinavian", "Primitive Norse", "Proto-Nordic", "Ancient Nordic", "Ancient Scandinavian", "Old Nordic", "Old Scandinavian", "Proto-North Germanic", "North Proto-Germanic", "Common Scandinavian"}, } m["gmq-scy"] = { } m["gmw-bgh"] = { } m["gmw-cfr"] = { varieties = {"Mittelfränkisch", "Ripuarian", "Moselle Franconian", "Colognian", "Kölsch"}, } m["gmw-ecg"] = { varieties = {"Thuringian", "Thüringisch", "Upper Saxon", "Upper Saxon German", "Obersächsisch", "Lusatian", "Erzgebirgisch", "Silesian", "Silesian German", "High Prussian"}, } m["gmw-fin"] = { aliases = {"Fingal"}, } m["gmw-gts"] = { aliases = {"Gottscheerisch"}, } m["gmw-jdt"] = { } m["gmw-msc"] = { } m["gmw-pro"] = { } m["gmw-rfr"] = { aliases = {"Rheinfränkisch", "Rhenish Franconian"}, varieties = {"Hessian", "Lorraine Franconian", "Lorrainian", "Lothringisch", "Palatine German", "Pfälzisch", "Pälzisch", "Palatinate German"}, } m["gmw-stm"] = { aliases = {"Satu Mare Swabian", "Sathmarschwäbisch", "Sathmarisch"}, } m["gmw-tsx"] = { aliases = {"Siebenbürger Saxon"}, } m["gmw-vog"] = { } m["gmw-zps"] = { aliases = {"Zipser", "Zipserisch", "Outzäpsersch"}, } m["gn-cls"] = { } m["grk-cal"] = { aliases = {"Italian Greek", "Bova"}, } m["grk-ita"] = { aliases = {"Griko", "Grico", "Grecanic"}, } m["grk-mar"] = { aliases = {"Mariupolitan Greek", "Rumeíka", "Rumeika"}, } m["grk-pro"] = { aliases = {"Proto-Greek"}, } m["hmn-pro"] = { } m["hmx-mie-pro"] = { } m["hmx-pro"] = { } m["hyx-pro"] = { } m["iir-nur-pro"] = { } m["iir-pro"] = { } m["ijo-pro"] = { aliases = {"Proto-Ijaw"}, } m["inc-apa"] = { aliases = {"Apabhraṃśa"}, } m["inc-ash"] = { aliases = {"Asokan Prakrit", "Aśokan Prakrit"}, } m["inc-dng-pro"] = { } m["inc-kam"] = { } m["inc-kho"] = { } m["inc-krd-pro"] = { aliases = {"Proto-Kamata"}, } m["inc-mas"] = { } m["inc-mbn"] = { } m["inc-mgu"] = { } m["inc-mor"] = { aliases = {"Middle Oriya"}, } m["inc-oas"] = { } m["inc-oaw"] = { aliases = {"Early Awadhi"}, } m["inc-obn"] = { } m["inc-ogu"] = { aliases = {"Old Western Rajasthani"}, } m["inc-ohi"] = { aliases = {"Dehlavi"}, } m["inc-oor"] = { aliases = {"Old Oriya"}, } m["inc-opa"] = { } m["inc-pro"] = { } m["ine-ana-pro"] = { } m["ine-bsl-pro"] = { } m["ine-kal"] = { aliases = {"Kalasma", "Kalashma", "Kalašmaic", "Kalasmaic", "Kalašmian", "Kalasmian"}, } m["ine-pae"] = { } m["ine-pro"] = { } m["ine-toc-pro"] = { } m["xme-old"] = { } m["xme-mid"] = { aliases = {"Atropatenian"}, } m["xme-ker"] = { other_names = {"Kermanian", "Central Iranian Dialects", "Central Plateau Dialects", "Central Iranian", "South Median", "Gazi", "Soi", "Sohi", "Abuzeydabadi", "Abyanehi", "Farizandi", "Jowshaqani", "Nashalji", "Qohrudi", "Yarandi", "Tari", "Sedehi", "Ardestani", "Zefrehi", "Isfahani", "Kafroni", "Varzenehi", "Khuri", "Nayini", "Anaraki", "Zoroastrian Dari", "Behdināni", "Behdinani", "Gabri", "Gavrŭni", "Gavruni", "Gabrōni", "Gabroni", "Kermani", "Yazdi", "Bidhandi", "Bijagani", "Chimehi", "Hanjani", "Komjani", "Naraqi", "Qalhari", "Varani", "Zori"}, } m["xme-taf"] = { } m["xme-ttc-pro"] = { } m["xme-kls"] = { aliases = {"Kalāsuri", "Kalasur", "Kalāsur"}, } m["xme-klt"] = { } m["xme-ott"] = { other_names = {"Old Tatic", "Old Azeri", "Azari", "Azeri", "Āḏarī", "Adari", "Adhari"}, } m["ira-kms-pro"] = { } m["ira-mpr-pro"] = { } m["ira-pat-pro"] = { } m["ira-pro"] = { } m["ira-zgr-pro"] = { } m["xsc-pro"] = { } m["xsc-sar-pro"] = { } m["xsc-skw-pro"] = { } m["xsc-sak-pro"] = { aliases = {"Proto-Sakan", "Proto-Tumshuqese-Khotanese"}, } m["ira-sym-pro"] = { } m["ira-sgi-pro"] = { } m["ira-mny-pro"] = { } m["ira-shy-pro"] = { } m["ira-shr-pro"] = { } m["ira-sgc-pro"] = { aliases = {"Proto-Sogdian"}, } m["ira-wnj"] = { aliases = {"Old Vanji", "Vanchi", "Vanži", "Wanji"}, } m["iro-ere"] = { } m["iro-min"] = { } m["iro-nor-pro"] = { } m["iro-pro"] = { } m["itc-pro"] = { } m["itc-psa"] = { } m["jpx-hcj"] = { aliases = {"Hachijo"}, } m["jpx-pro"] = { } m["jpx-ryu-pro"] = { } m["kar-pro"] = { } m["kca-eas"] = { } m["kca-nor"] = { } m["kca-pro"] = { } m["kca-sou"] = { } m["khi-kho-pro"] = { } m["khi-kun"] = { other_names = {"ǃOǃKung", "ǃ'OǃKung", "Kung", "Ekoka ǃKung", "Ekoka Kung", "Sekele"}, } m["ko-ear"] = { } m["kro-pro"] = { } m["ku-pro"] = { } m["map-ata-pro"] = { } m["map-bms"] = { } m["map-pro"] = { } m["mis-hkl"] = { aliases = {"Kelantan Peranakan Chinese", "Hokkien Kelantan", "Kelantan Local Hokkien"} } m["mis-idn"] = { } m["mis-isa"] = { } m["mis-jie"] = { aliases = {"Chieh", "Kjet"}, } m["mis-jzh"] = { aliases = {"Haihua"}, } m["mis-kas"] = { aliases = {"Cassite", "Kassitic", "Kaššite"}, } m["mis-mmd"] = { other_names = {"Mimi of Gaudefroy-Demombynes", "Mimi-D"}, } m["mis-mmn"] = { other_names = {"Mimi-N"}, } m["mis-phi"] = { aliases = {"Philistian", "Philistinian"}, } m["mis-rou"] = { aliases = {"Ruanruan", "Ruan-ruan", "Juan-juan"}, } m["mis-tdl"] = { aliases = {"Turduli"}, } m["mis-tdt"] = { aliases = {"Turdetani"}, } m["mis-tnw"] = { aliases = {"Tangwanghua"}, } m["mis-tuh"] = { aliases = {"'Azha"}, } m["mis-tuo"] = { aliases = {"Tabghach", "Taghbach"}, } m["mis-wuh"] = { aliases = {"Wuwan", "Awar"}, } m["mis-xbi"] = { aliases = {"Serbi", "Shirwi"}, } m["mis-xnu"] = { aliases = {"Hsiung-nu", "Hiong-nu"}, } m["mjg-mgl"] = { aliases = {"Huzhu", "Huzhu Monguor"}, } m["mjg-mgr"] = { aliases = {"Minhe", "Minhe Monguor"}, } m["mkh-asl-pro"] = { } m["mkh-ban-pro"] = { } m["mkh-kat-pro"] = { } m["mkh-khm-pro"] = { } m["mkh-kmr-pro"] = { } m["mkh-mmn"] = { } m["mkh-mnc-pro"] = { } m["mkh-mvi"] = { } m["mkh-pal-pro"] = { } m["mkh-pea-pro"] = { } m["mkh-pkn-pro"] = { } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. } m["mnw-tha"] = { aliases = {"Raman", "Thai Raman", "Siamese Mon"}, } m["mkh-vie-pro"] = { } m["mns-cen"] = { } m["mns-nor"] = { } m["mns-pro"] = { } m["mns-sou"] = { } m["mun-pro"] = { aliases = {"Proto-Mundan"}, } m["myn-chl"] = { -- the stage after ''emy'' other_names = {"Cholti", "Colonial Ch'olti'", "Colonial Cholti"}, } m["myn-pro"] = { aliases = {"Proto-Maya"}, } m["nai-ala"] = { other_names = {"Alasapa", "Pinto"}, } m["nai-bay"] = { other_names = {"Bayougoula", "Bayou Goula", "Ischenoca"}, -- tribe merged with "Mougulasha", "Mongoulacha", "Mugulasha", "Mougulasha", "Muglahsa", "Muglasha", "Muguasha", "Imongolosha", "Houma", "Acolapissa" } m["nai-cal"] = { } m["nai-chi"] = { } m["nai-chu-pro"] = { aliases = {"Proto-Chumashan"}, } m["nai-cig"] = { } m["nai-ckn-pro"] = { aliases = {"Proto-Chinook"}, } m["nai-guz"] = { aliases = {"Guazacapan"}, } m["nai-hit"] = { other_names = {"Atcik-hata", "At-pasha-shliha"}, } m["nai-ipa"] = { other_names = {"'Iipay 'aa", "Northern Diegueño", "Diegueño"}, } m["nai-jtp"] = { other_names = {"Xutiapa", "Jalapa", "Xalapa"}, } m["nai-jum"] = { aliases = {"Jumaitepeque", "Jumaytepec"}, } m["nai-kat"] = { other_names = {"Kathlamet Chinook"}, } m["nai-klp-pro"] = { } m["nai-knm"] = { } m["nai-kum"] = { other_names = {"Kumiai", "Central Diegueño", "Diegueño"}, } m["nai-mac"] = { aliases = {"Macorís", "Macorix", "Mazorij", "Mazorig", "Mazoriges"}, } m["nai-mdu-pro"] = { aliases = {"Proto-Maiduan"}, } m["nai-miz-pro"] = { aliases = {"Proto-Mixe-Zoquean"}, } m["nai-mus-pro"] = { aliases = {"Proto-Muskhogean", "Proto-Muskogee"}, } m["nai-nao"] = { } m["nai-nrs"] = { } m["nai-okw"] = { } m["nai-per"] = { } m["nai-pic"] = { } m["nai-plp-pro"] = { } m["nai-pom-pro"] = { aliases = {"Proto-Pomoan"}, } m["nai-qng"] = { } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan } m["nai-sin"] = { aliases = {"Sinacantan", "Zinacantán", "Zinacantan"}, } m["nai-sln"] = { } m["nai-spt"] = { aliases = {"Shahaptin"}, } m["nai-tap"] = { other_names = {"Tapachulteca", "Tapachulteco", "Tapachula"}, } m["nai-taw"] = { } m["nai-teq"] = { other_names = {"Tequistlateco", "Tequistlateca", "Chontal", "Chontol of Oaxaca", "Oaxaca Chontal", "Oaxacan Chontal"}, } m["nai-tip"] = { other_names = {"Tipay", "Tiipai", "Tiipay", "Jamul Tiipay", "Southern Digueño", "Diegueño"}, } m["nai-tot-pro"] = { } m["nai-tsi-pro"] = { } m["nai-utn-pro"] = { other_names = {"Proto-Miwok-Costanoan"}, } m["nai-wai"] = { aliases = {"Guaycura", "Waicura"}, } m["nai-wji"] = { other_names = {"Jicaque of El Palmar", "Sula"}, } m["nai-yup"] = { aliases = {"Jupiltepeque", "Yupiltepec", "Jupiltepec", "Xupiltepec"}, } m["nan-dat"] = { aliases = {"Datian"}, } m["nan-hbl"] = { aliases = {"Hokkienese", "Quanzhang", "Fukien", "Banlam", "Banlamese", "Ban-lam"}, } m["nan-hlh"] = { aliases = {"Hailufeng", "Hoklo Min", "Hai Lok Hong"}, } m["nan-lnx"] = { aliases = {"Longyan", "Liongna"}, } m["nan-tws"] = { aliases = {"Teochew Min", "Chiuchow", "Teo-Swa", "Teo-Swa Min", "Tio-Sua"}, } m["nan-zhe"] = { aliases = {"Zhenan"}, } m["nan-zsh"] = { aliases = {"Sanxiang", "Samheung", "Sahiu"}, } m["ngf-pro"] = { } m["nic-bco-pro"] = { } m["nic-bod-pro"] = { } m["nic-eov-pro"] = { } m["nic-gns-pro"] = { } m["nic-grf-pro"] = { } m["nic-gur-pro"] = { } m["nic-jkn-pro"] = { } m["nic-lcr-pro"] = { } m["nic-ogo-pro"] = { } m["nic-ovo-pro"] = { } m["nic-plt-pro"] = { } m["nic-pro"] = { } m["nic-ubg-pro"] = { } m["nic-ucr-pro"] = { } m["nic-vco-pro"] = { } m["njo-jgl"] = { } m["nub-har"] = { aliases = {"Ḥarāza"}, } m["nub-pro"] = { } m["omq-cha-pro"] = { } m["omq-maz-pro"] = { aliases = {"Proto-Mazatecan"}, } m["omq-mix-pro"] = { } m["omq-mxt-pro"] = { } m["omq-otp-pro"] = { } m["omq-pro"] = { aliases = {"Proto-Otomanguean", "Proto-Oto-Mangue"}, } m["omq-sjq"] = { } m["omq-tel"] = { } m["omq-teo"] = { } m["omq-tri-pro"] = { aliases = {"Proto-Trique"}, } m["omq-zap-pro"] = { } m["omq-zpc-pro"] = { } m["omv-aro-pro"] = { } m["omv-diz-pro"] = { aliases = {"Proto-Maji"}, } m["omv-pro"] = { } m["oto-otm-pro"] = { } m["oto-pro"] = { } m["ngf-bin-pro"] = { } m["paa-kmn"] = { aliases = {"Komnzo", "Kómnjo", "Komnjo", "Kamundjo", "Rouku"}, } m["paa-kwn"] = { } m["paa-lei"] = { } m["paa-nha-pro"] = { } m["paa-nun"] = { } m["phi-din"] = { } m["phi-kal-pro"] = { aliases = {"Proto-Calamian"}, } m["phi-nag"] = { } m["phi-pro"] = { } m["poz-abi"] = { other_names = {"Sembuak", "Tubu"}, } m["poz-bal"] = { } m["poz-btk-pro"] = { } m["poz-cet-pro"] = { } m["poz-hce-pro"] = { other_names = {"Proto-South Halmahera - West New Guinea"}, } m["poz-lgx-pro"] = { } m["poz-mcm-pro"] = { } m["poz-mic-pro"] = { } m["poz-mly-pro"] = { } m["poz-msa-pro"] = { } m["poz-oce-pro"] = { } m["poz-pep-pro"] = { aliases = {"Proto-Eastern-Polynesian", "Proto-East Polynesian", "Proto-East-Polynesian"}, } m["poz-pnp-pro"] = { } m["poz-pol-pro"] = { } m["poz-pro"] = { other_names = {"Proto-Western Malayo-Polynesian"}, -- Western is subsumed into general Proto-MP } m["poz-sml"] = { aliases = {"Sarawak"}, } m["poz-ssw-pro"] = { } m["poz-swa-pro"] = { } m["poz-ter"] = { aliases = {"Terengganu"}, } m["pqe-pro"] = { } m["pra-niy"] = { } m["qfa-adm-pro"] = { } m["qfa-bet-pro"] = { aliases = {"Proto-Tai-Be"}, } m["qfa-cka-pro"] = { } m["qfa-hur-pro"] = { } m["qfa-kad-pro"] = { } m["qfa-kms-pro"] = { } m["qfa-kor-pro"] = { } m["qfa-kra-pro"] = { } m["qfa-lic-pro"] = { } m["qfa-onb-pro"] = { aliases = {"Proto-Ong-Be", "Proto-Bê"}, } m["qfa-ong-pro"] = { } m["qfa-tak-pro"] = { aliases = {"Proto-Tai-Kadai"}, } m["qfa-yen-pro"] = { } m["qfa-yuk-pro"] = { } m["qwe-kch"] = { other_names = {"Kichwa shimi", "Runashimi", "Runa", "Quichua", "Quecha", "Inga", "Chimborazo", "Imbabura Highland Kichwa", "Cañar Highland Quecha", "Quechua"}, } m["qwe-pro"] = { } m["roa-ang"] = { other_names = {"Craonnais", "Baugeois", "Saumurois"}, } m["roa-bbn"] = { other_names = {"Bourbonnais", "Berrichon", "Moulins", "Allier", "Nivernais", "Haut-Berrichon", "Bas-Berrichon"}, } m["roa-brg"] = { other_names = {"Burgundian", "Bregognon", "Dijonnais", "Morvandiau", "Morvandeau", "Morvan", "Bourguignon-Morvandiau", "Mâconnais", "Brionnais", "Brionnais-Charolais", "Auxerrois", "Beaunois", "Langrois", "Valsaônois", "Verduno-Chalonnais", "Sédelocien"}, } m["roa-can"] = { } m["roa-cha"] = { other_names = {"Bassignot", "Langrois", "Sennonais", "Vallage", "Troyen", "Briard", "Der", "Perthois", "Rémois", "Argonnais", "Porcien", "Ardennais", "Sugny"}, } m["roa-fcm"] = { other_names = {"Frainc-Comtou", "Comtois", "Jurassien", "Ajoulot", "Vâdais", "Taignon", "Bisontin", "Bousbot"}, } m["roa-gal"] = { } m["roa-gib"] = { } m["roa-gis"] = { } m["roa-leo"] = { } m["roa-lor"] = { other_names = {"Gaumais", "Vosgien", "Welche", "Argonnais", "Longovicien", "Messin", "Nancéien", "Spinalien", "Déodatien"}, } m["roa-oca"] = { aliases = {"Medieval Catalan"}, } m["roa-ole"] = { aliases = {"Medieval Leonese"}, } m["roa-ona"] = { aliases = {"Navarro-Aragonese", "Medieval Navarro-Aragonese", "Old Aragonese", "Medieval Aragonese"}, } m["roa-opt"] = { aliases = {"Old Galician Portuguese", "Old Galician–Portuguese", "Old Galician", "Old Portuguese", "Galician-Portuguese", "Galician Portuguese", "Galician–Portuguese", "Medieval Galician-Portuguese", "Medieval Galician Portuguese", "Medieval Galician–Portuguese", "Medieval Galician", "Medieval Portuguese", "Galaic-Portuguese"}, } m["roa-orl"] = { other_names = {"Beauceron", "Solognot", "Gâtinais", "Blaisois", "Vendômois"}, } m["roa-poi"] = { other_names = {"Poitevin", "Saintongeais", "Maraîchin"}, } m["roa-tar"] = { } m["sai-all"] = { other_names = {"Alyentiyak", "Huarpe", "Warpe"}, } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' other_names = {"Miranya", "Miranha", "Miranha Carapana-Tapuya", "Miraña-Carapana-Tapuyo", "Andokero", "Miranya-Karapana-Tapuyo", "Miraña", "Carapana"}, } m["sai-ayo"] = { aliases = {"Ayoman", "Ayamán", "Ayaman"}, } m["sai-bae"] = { aliases = {"Baenã", "Baenán", "Baena"}, } m["sai-bag"] = { other_names = {"Patagón de Bagua"}, } m["sai-bet"] = { other_names = {"Betoy", "Betoya", "Betoye", "Betoi-Jirara", "Jirara"}, } m["sai-bor-pro"] = { other_names = {"Proto-Bora-Muinane", "Proto-Bora-Muiname"}, } m["sai-cac"] = { other_names = {"Kakán", "Diaguita", "Cacan", "Kakan", "Calchaquí", "Chaka", "Kaka", "Kaká", "Caca", "Caca-Diaguita", "Catamarcano", "Capayán", "Capayana", "Yacampis"}, } m["sai-caq"] = { other_names = {"Cara", "Kara"}, } m["sai-car-pro"] = { } m["sai-cat"] = { } m["sai-cer-pro"] = { other_names = {"Proto-Amazonian Jê"}, } m["sai-chi"] = { } m["sai-chn"] = { aliases = {"Chana"}, } m["sai-chp"] = { aliases = {"Txapacura", "Xapacura", "Guapore", "Šapakura", "Txapakura", "Txapakúra", "Xapakúra"}, } m["sai-chr"] = { aliases = {"Charrúa", "Charruá"}, } m["sai-chu"] = { aliases = {"Churoya"}, } m["sai-cje-pro"] = { other_names = {"Proto-Akuwẽ"}, } m["sai-cmg"] = { aliases = {"Comechingón", "Comechingona", "Comechingone"}, } m["sai-cno"] = { other_names = {"Chonos", "Caucau"}, } m["sai-cnr"] = { aliases = {"Cañar"}, } m["sai-coe"] = { aliases = {"Koeruna"}, } m["sai-col"] = { aliases = {"Colan"}, } m["sai-cop"] = { } m["sai-crd"] = { other_names = {"Coroado"}, } m["sai-ctq"] = { aliases = {"Catuquinarú", "Katukinaru"}, } m["sai-cul"] = { other_names = {"Culle", "Kulyi", "Ilinga", "Linga"}, } m["sai-cva"] = { } m["sai-esm"] = { other_names = {"Esmeraldeño", "Atacame", "Takame"}, } m["sai-ewa"] = { } m["sai-gam"] = { aliases = {"Gamella", "Acobu", "Curinsi", "Barbados"}, } m["sai-gay"] = { aliases = {"Gayon"}, } m["sai-gmo"] = { other_names = {"Wamo", "Santa Rosa", "San Jose", "Barinas", "Guamotey", "Guama"}, } m["sai-gua"] = { aliases = {"Guachi", "Wachí", "Wachi"}, } m["sai-gue"] = { aliases = {"Guenoa"}, } m["sai-hau"] = { other_names = {"Manek'enk"}, } m["sai-jee-pro"] = { other_names = {"Proto-Gê", "Proto-Jean", "Proto-Gean", "Proto-Jê-Kaingang", "Proto-Ye"}, } m["sai-jko"] = { aliases = {"Geicó", "Jeicó", "Jaikó", "Geikó", "Yeikó", "Jeiko", "Geico", "Jeico", "Jaiko", "Geiko", "Yeiko", "Eyco"}, } m["sai-jrj"] = { } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc other_names = {"Catrimbi", "Catembri", "Kariri de Mirandela", "Mirandela", "Kariri", "Kiriri"}, } m["sai-mal"] = { aliases = {"Malali"}, } m["sai-mar"] = { } m["sai-mat"] = { other_names = {"Matanauí", "Matanaui", "Matanawü", "Mitandua", "Moutoniway"}, } m["sai-mcn"] = { aliases = {"Mokana"}, } m["sai-men"] = { aliases = {"Menién"}, } m["sai-mil"] = { other_names = {"Milykayak", "Huarpe", "Warpe"}, } m["sai-mlb"] = { aliases = {"Malibú", "Malebú"}, } m["sai-msk"] = { aliases = {"Masakara", "Masacará", "Masacara"}, } m["sai-muc"] = { other_names = {"Mucuchi", "Mokochi", "Mocochí", "Mirripú", "Maripú", "Mucuchí-Maripú"}, } m["sai-mue"] = { aliases = {"Muellamués"}, } m["sai-muz"] = { } m["sai-mys"] = { other_names = {"Mayna", "Maina", "Rimachu"}, } m["sai-nat"] = { other_names = {"Natu", "Peagaxinan"}, } m["sai-nje-pro"] = { other_names = {"Proto-Core Jê"}, } m["sai-opo"] = { other_names = {"Opon", "Opón-Karare", "Opón-Carare", "Carare", "Carare-Opón"}, } m["sai-oto"] = { aliases = {"Otomako", "Otomacan", "Otomac", "Otomak"}, } m["sai-pal"] = { } m["sai-pam"] = { aliases = {"Pamiwa"}, } m["sai-par"] = { aliases = {"Paratio", "Prarto"}, } m["sai-peb"] = { aliases = {"Peva"}, varieties = {"Cauwachi", "Caumari", "Pacaya"}, -- per Wikipedia, according to the American anthropologist and linguist John Alden Mason (1950) } m["sai-pnz"] = { aliases = {"Pansaleo"}, } m["sai-prh"] = { } m["sai-ptg"] = { other_names = {"Patagón de Perico"}, } m["sai-pur"] = { aliases = {"Purukoto", "Purucotó", "Purucoto"}, } m["sai-pyg"] = { aliases = {"Payawá", "Payagua"}, } m["sai-pyk"] = { aliases = {"Gavião-Pykobjê", "Pykobjê-Gavião", "Gavião", "Pyhcopji", "Gavião-Pyhcopji"}, } m["sai-qmb"] = { other_names = {"Kimbaya", "Quindío", "Quindio", "Quindo"}, } m["sai-qtm"] = { aliases = {"Quitemoca"}, } m["sai-rab"] = { } m["sai-ram"] = { } m["sai-sac"] = { other_names = {"Sacata", "Zácata", "Chillao"}, } m["sai-san"] = { aliases = {"Sanavirón", "Sanabirón", "Sanabiron", "Sanavirona", "Zanavirona"}, } m["sai-sap"] = { aliases = {"Zapará", "Zapara"}, } m["sai-sec"] = { other_names = {"Sek", "Sec"}, } m["sai-sin"] = { other_names = {"Cenúfana", "Zenúfana", "Cinifaná", "Sinufana", "Sinú", "Cenú", "Zenú", "Finzenú", "Fincenú", "Pancenú", "Sutagao"}, } m["sai-sje-pro"] = { } m["sai-tab"] = { other_names = {"Aconipa"}, } m["sai-tal"] = { other_names = {"Atalán", "Tallan", "Tallanca", "Atalan", "Sek"}, } m["sai-tap"] = { other_names = {"Tapayúna", "Kajkwakhrattxi"}, } m["sai-tar-pro"] = { } m["sai-teu"] = { aliases = {"Tehues", "Teuéx"}, } m["sai-tim"] = { other_names = {"Cuica", "Timote-Cuica"}, } m["sai-tpr"] = { aliases = {"Taparito"}, } m["sai-trr"] = { other_names = {"Caratiú"}, } m["sai-wai"] = { aliases = {"Waitaka", "Waitacá", "Waitaca", "Goytacá", "Goitacá", "Guaitacá", "Guiatacá", "Guiatacás", "Goiatacá", "Goiatacás", "Guaiatacá", "Goytacaz", "Goitacaz", "Goyataca", "Aitacaz", "Uetacaz", "Uetacá", "Outacá", "Ouetacá", "Eutacá", "Itacaz", "Vaitacá"}, } m["sai-way"] = { aliases = {"Wajumará", "Wajumara", "Wayumará", "Azumara", "Guimara"}, } m["sai-wit-pro"] = { other_names = {"Proto-Huitotoan", "Proto-Uitotoan"}, } m["sai-wnm"] = { other_names = {"Wañam", "Wanyam", "Huanyam", "Uanham", "Abitana"}, } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat other_names = {"Xoco", "Chocó", "Shokó", "Shoko", "Shocó", "Shoco", "Choco", "Chocaz", "Kariri-Xocó", "Kariri-Xoco", "Kariri-Shoko", "Cariri-Chocó", "Xukuru-Kariri", "Xucuru-Kariri", "Xucuru-Cariri", "Xukurú-Kirirí"}, } m["sai-yao"] = { aliases = {"Yao", "Jaoi", "Yaoi", "Yaio", "Anacaioury"}, } m["sai-yar"] = { -- not the same family as 'suy' aliases = {"Yaruma"}, } m["sai-yri"] = { aliases = {"Jurí"}, } m["sai-yup"] = { other_names = {"Yupuá", "Yupúa", "Jupua", "Jupuá", "Jupúa", "Hiupiá", "Yupuá-Duriña", "Duriña"}, } m["sai-yur"] = { aliases = {"Yurumangui", "Yurimangí", "Yurimangi", "Yurimanguí", "Yurimangui"}, } m["sal-pro"] = { aliases = {"Proto-Salishan"}, } m["sdv-daj-pro"] = { } m["sdv-eje-pro"] = { } m["sdv-nil-pro"] = { } m["sdv-nyi-pro"] = { } m["sdv-tmn-pro"] = { } m["sel-nor"] = { aliases = {"Taz Selkup"}, } m["sel-pro"] = { } m["sel-sou"] = { } m["sem-amm"] = { } m["sem-amo"] = { aliases = {"Amoritic"}, } m["sem-cha"] = { aliases = {"Cheha", "Čäha", "Čäxa"}, } m["sem-dad"] = { other_names = {"Dadanite", "Lihyanite", "Lihyanitic"}, } m["sem-dum"] = { } m["sem-has"] = { } m["sem-his"] = { other_names = {"Thamudic E"}, } m["sem-mhr"] = { other_names = {"Muher Gurage", "Muxar", "Muxər", "Muhər", "Muḫər"}, } m["sem-pro"] = { } m["sem-saf"] = { } m["sem-sam"] = { other_names = {"Sam'alian"}, } m["sem-srb"] = { } m["sem-tay"] = { other_names = {"Taymanite", "Thamudic A"}, } m["sem-tha"] = { } m["sem-wes-pro"] = { } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' } m["sit-aao-pro"] = { } m["sit-bok"] = { other_names = {"Ramo", "Pailibo"}, } m["sit-bai-pro"] = { } m["sit-ban"] = { } m["sit-bdi-pro"] = { } m["sit-cai"] = { } m["sit-cha"] = { } m["sit-ers-pro"] = { } m["sit-hrs-pro"] = { } m["sit-jap"] = { other_names = {"Chabao", "Kuru"}, } m["sit-kha-pro"] = { } m["sit-khb-pro"] = { } m["sit-khp-pro"] = { } m["sit-khw-pro"] = { } m["sit-kon-pro"] = { } m["sit-liz"] = { } m["sit-lnj"] = { } m["sit-lrn"] = { } m["sit-luu-pro"] = { } m["sit-nas-pro"] = { } m["sit-prn"] = { } m["sit-pro"] = { } m["sit-sit"] = { other_names = {"Eastern rGyalrong", "rGyalrong", "Rgyalrong", "rGyalrongic", "Gyalrong", "Gyarong", "rGyarong", "Gyarung", "Jiarong", "Jiarongyu", "Jyarong", "Jyarung", "Yelong", "Kuru"}, } m["sit-tam-pro"] = { aliases = {"Proto-Tamang"}, } m["sit-tan-pro"] = { } m["sit-tgm"] = { } m["sit-tng-pro"] = { } m["sit-tos"] = { } m["sit-tsh"] = { other_names = {"Caodeng", "Sidaba", "rGyalrong", "Rgyalrong", "Jiarong", "Gyarung", "Kuru"}, } m["sit-zbu"] = { other_names = {"Ribu", "Rdzong'bur", "Rdzongmbur", "Showu", "rGyalrong", "Rgyalrong", "Jiarong", "Gyarung", "Kuru"}, } m["sla-pro"] = { aliases = {"Common Slavic"}, } m["smi-pro"] = { aliases = {"Proto-Sami"}, } m["son-pro"] = { aliases = {"Proto-Songhai"}, } m["sqj-pro"] = { } m["ssa-klk-pro"] = { aliases = {"Proto-Rub"}, } m["ssa-kom-pro"] = { } m["ssa-pro"] = { } m["syd-pro"] = { } m["tai-pro"] = { } m["tai-swe-pro"] = { } m["tbq-bdg-pro"] = { } m["tbq-blg"] = { aliases = {"Pai-lang", "Pailang"}, } m["tbq-brm-pro"] = { } m["tbq-gkh"] = { aliases = {"Gɔkhý", "Gɔkhy", "Gouke"}, } m["tbq-kuk-pro"] = { other_names = {"Proto-Kukish"}, } m["tbq-lal-pro"] = { } m["tbq-laz"] = { other_names = {"Lare", "Shuitianhua"}, } m["tbq-lob-pro"] = { } m["tbq-lol-pro"] = { aliases = {"Proto-Yi", "Proto-Ngwi", "Proto-Nisoic"}, } m["tbq-mil"] = { } m["tbq-mor"] = { aliases = {"Morān"}, } m["tbq-ngo"] = { other_names = {"Ngachang", "Achang"}, } -- tbq-pro is now etymology-only m["trk-dkh"] = { aliases = {"Dukha"}, } m["trk-eog"] = { } m["trk-oat"] = { } m["trk-pro"] = { } m["tup-gua-pro"] = { } m["tup-kab"] = { aliases = {"Kabixiana", "Cabixiana", "Cabishiana", "Kapishana", "Capishana", "Kapišana", "Cabichiana", "Capichana", "Capixana"}, } m["tuw-alk"] = { aliases = {"Alechuka"}, } m["tuw-bal"] = { } m["tuw-kkl"] = { aliases = {"Chinese Kyakala"}, } m["tuw-kli"] = { aliases = {"Kilen", "Kirin", "Kila", "Hezhe", "Qile'en"}, } m["tup-pro"] = { } m["tuw-pro"] = { } m["tuw-sol"] = { } m["urj-fin-pro"] = { } m["urj-koo"] = { aliases = {"Old Permian"}, } m["urj-kuk"] = { aliases = {"Kukkuzi Votic", "Kukkuzi Ingrian", "Kukkusi"}, } m["urj-kya"] = { } m["urj-mdv-pro"] = { } m["urj-prm-pro"] = { } m["urj-pro"] = { other_names = {"Proto-Finno-Ugric", "Proto-Finno-Permic"}, -- PFU and PFP are subsumed into PU per [[Wiktionary:Beer parlour/2015/January#Merging Finno-Volgaic, Finno-Samic, Finno-Permic and Finno-Ugric into Uralic]] } m["urj-ugr-pro"] = { } m["xgn-pro"] = { } m["xnd-pro"] = { other_names = {"Proto-Na-Dené", "Proto-Athabaskan-Eyak-Tlingit"}, } m["yok-bvy"] = { other_names = {"Tulamni-Hometwoli", "Tulamni", "Tulamne", "Tuolumne", "Tawitchi", "Hometwoli", "Taneshach"}, } m["yok-dly"] = { other_names = {"Far Northern Valley Yokuts", "Yachikumne", "Yachikumni", "Chulamni", "Lower San Joaquin", "Lakisamni", "Tawalimni"}, } m["yok-gsy"] = { } m["yok-kry"] = { other_names = {"Choinimni", "Choynimni", "Ayticha", "Kocheyali", "Ayitcha", "Michahay", "Chukaymina", "Chukaimina"}, } m["yok-nvy"] = { other_names = {"Chukchansi", "Kechayi", "Dumna", "Chawchila", "Noptinte", "Nopṭinṭe", "Nopthrinthre", "Nopchinchi", "Takin"}, } m["yok-ply"] = { other_names = {"Paleuyami", "Altinin", "Poso Creek", "Poso Creek Yokuts"}, } m["yok-svy"] = { other_names = {"Yawelmani", "Tachi", "Koyeti", "Nutunutu", "Chunut", "Wo'lasi", "Choynok", "Choinok", "Wechihit"}, } m["yok-tky"] = { other_names = {"Wikchamni", "Wukchamni", "Wukchumni", "Yawdanchi"}, } m["ypk-pro"] = { } m["yrk-for"] = { } m["yrk-tun"] = { other_names = {"Yurak"}, varieties = { { "Western Nenets" }, { "Eastern Nenets" }, } } m["zhx-min-pro"] = { } m["zhx-sht"] = { other_names = {"Xiangnan Tuhua", "Yuebei Tuhua", "Shipo", "Shina"}, } m["zhx-sic"] = { aliases = {"Sichuanese Mandarin"}, } m["zhx-tai"] = { aliases = {"Toishanese"}, } m["zle-ono"] = { } m["zle-ort"] = { } m["zls-chs"] = { } m["zlw-ocs"] = { } m["zlw-opl"] = { } m["zlw-osk"] = { } m["zlw-slv"] = { } return m m81rgjdlzd5vbhimng8lss36yrye0nn 231370 231369 2026-04-14T07:30:32Z Lee 19 [[:en:Module:languages/data/exceptional/extra]] වෙතින් එක් සංශෝධනයක් 231369 Scribunto text/plain local m = {} m["aav-khs-pro"] = { aliases = {"Proto-Khasic"}, } m["aav-nic-pro"] = { } m["aav-pkl-pro"] = { } m["aav-pro"] = { -- mkh-pro will merge into this. } m["afa-pro"] = { aliases = {"Proto-Afro-Asiatic", "Hamito-Semitic"}, } m["alg-aga"] = { aliases = {"Agwam", "Agaam"}, } m["alg-pro"] = { } m["alv-ama"] = { } m["alv-bgu"] = { aliases = {"Baïnounk Gubëeher", -- Wikipedia's name "Gubeeher-Gufangor-Gubelor", -- Glottolog's name, "Gubëeher", "Nyun Gubëeher", "Nun Gubëeher"}, -- N(y)un appears to be the family name varieties = {"Gubeeher", "Gufangor", "Gubelor"}, } m["alv-bua-pro"] = { } m["alv-cng-pro"] = { } m["alv-edk-pro"] = { } m["alv-edo-pro"] = { } m["alv-fli-pro"] = { } m["alv-gbe-pro"] = { } m["alv-gng-pro"] = { } m["alv-gtm-pro"] = { aliases = {"Proto-Ghana-Togo Mountain"}, } m["alv-gwa"] = { } m["alv-hei-pro"] = { } m["alv-ido-pro"] = { } m["alv-igb-pro"] = { } m["alv-kwa-pro"] = { } m["alv-mum-pro"] = { } m["alv-nup-pro"] = { } m["alv-pro"] = { } m["alv-von-pro"] = { } m["alv-yor-pro"] = { } m["alv-yrd-pro"] = { } m["apa-pro"] = { aliases = {"Proto-Apache", "Proto-Southern Athabaskan"}, } m["aql-pro"] = { } m["art-adu"] = { aliases = {"Westron"}, } m["art-bel"] = { } m["art-blk"] = { } m["art-bsp"] = { } m["art-com"] = { } m["art-dtk"] = { } m["art-elo"] = { } m["art-gld"] = { } m["art-lap"] = { } m["art-man"] = { } m["art-mun"] = { } m["art-nav"] = { } m["art-vlh"] = { } m["ath-nic"] = { } m["ath-pro"] = { } m["auf-pro"] = { aliases = {"Proto-Arawan", "Proto-Arauan"}, } m["aus-alu"] = { other_names = {"Ogh-Alungul", "Alngula"}, } m["aus-and"] = { aliases = {"Adithinngithigh"}, } m["aus-ang"] = { other_names = {"Ogh-Anggula", "Anggula", "Ogh-Anggul", "Anggul"}, } m["aus-arn-pro"] = { } m["aus-bra"] = { aliases = {"Barranbinja", "Baranbinya", "Burranbinya", "Burrumbiniya", "Burrunbinya", "Barrumbinya", "Barren-binya", "Parran-binye"}, } m["aus-brm"] = { } m["aus-cww-pro"] = { } m["aus-dal-pro"] = { } m["aus-guw"] = { other_names = {"Gowar", "Goowar", "Gooar", "Guar", "Gowr-burra", "Ngugi", "Mugee", "Wogee", "Gnoogee", "Chunchiburri", "Booroo-geen-merrie"}, } m["aus-lsw"] = { aliases = {"Little Swanport Tasmanian"}, } m["aus-mbi"] = { other_names = {"Mbeiwum"}, } m["aus-ngk"] = { other_names = {"Ngkot", "Nggoth"}, } m["aus-nyu-pro"] = { } m["aus-pam-pro"] = { } m["aus-tul"] = { other_names = {"Dappil", "Dapil", "Toolooa", "Dulua", "Narung", "Dandan"}, } m["aus-uwi"] = { other_names = {"Uwinjmil"}, } m["aus-wdj-pro"] = { } m["aus-won"] = { } m["aus-wul"] = { other_names = {"Manbara", "Wulgurugaba", "Wulgurukaba", "Nhawalgaba"}, } m["aus-ynk"] = { -- contrast nny } m["awd-amc-pro"] = { other_names = {"Western Maipuran"}, } m["awd-kmp-pro"] = { other_names = {"Campa", "Kampan", "Campan", "Pre-Andine Maipurean"}, } m["awd-prw-pro"] = { other_names = {"Paresí-Waurá", "Parecí–Xingú", "Paresí–Xingu", "Central Arawak", "Central Maipurean"}, } m["awd-ama"] = { } m["awd-ana"] = { aliases = {"Anauya"}, } m["awd-apo"] = { other_names = {"Lapachu"}, } m["awd-cab"] = { aliases = {"Cabere", "Cávere", "Cavere"}, } m["awd-gnu"] = { other_names = {"Guinao", "Inao", "Guniare", "Quinhau", "Guiano"}, } m["awd-kar"] = { aliases = {"Kariaí", "Kariai", "Cariyai", "Carihiahy"}, } m["awd-kaw"] = { aliases = {"Cawishana", "Cayuishana", "Kaishana", "Cauixana"}, } m["awd-kus"] = { aliases = {"Kustenaú", "Custenau", "Kutenabu"}, } m["awd-man"] = { } m["awd-mar"] = { aliases = {"Marawán"}, } m["awd-mpr"] = { aliases = {"Maypure", "Mejepure"}, } m["awd-mrt"] = { aliases = {"Mariate"}, } m["awd-nwk-pro"] = { aliases = {"Proto-Newiki"}, } m["awd-pai"] = { aliases = {"Paiconeca", "Paikone", "Paicone"}, } m["awd-pas"] = { aliases = {"Passé", "Pazé"}, } m["awd-pro"] = { other_names = {"Proto-Arawakan", "Proto-Maipurean", "Proto-Maipuran"}, } m["awd-she"] = { aliases = {"Shebaya", "Shebaye"}, } m["awd-taa-pro"] = { other_names = {"Proto-Ta-Arawakan", "Proto-Caribbean Northern Arawak"}, } m["awd-wai"] = { other_names = {"Wainuma", "Wai", "Waima", "Wainumi", "Wainambí", "Waiwana", "Waipi", "Yanuma"}, } m["awd-yum"] = { aliases = {"Jumana"}, } m["azc-caz"] = { aliases = {"Caxcan", "Kaskán"}, } m["azc-cup-pro"] = { } m["azc-ktn"] = { aliases = {"Gitanemuk"}, } m["azc-nah-pro"] = { } m["azc-num-pro"] = { } m["azc-pro"] = { } m["azc-tak-pro"] = { } m["azc-tat"] = { } m["ber-fog"] = { other_names = {"El-Fogaha", "El-Foqaha", "Foqaha", "Fuqaha"}, } m["ber-pro"] = { } m["ber-zuw"] = { } m["bnt-bal"] = { } m["bnt-bon"] = { } m["bnt-boy"] = { } m["bnt-bwa"] = { } m["bnt-cmw"] = { other_names = {"Bravanese", "Mwiini", "Mwini", "Chimwini", "Chimini", "Brava"}, } m["bnt-ind"] = { other_names = {"Kɔlɔmɔnyi", "Kɔlɛ", "Kasaï Oriental"}, } m["bnt-lal"] = { } m["bnt-mpi"] = { } m["bnt-mpu"] = { } m["bnt-ngu-pro"] = { } m["bnt-phu"] = { aliases = {"Siphuthi"}, } m["bnt-pro"] = { } m["bnt-sab-pro"] = { } m["bnt-sbo"] = { } m["bnt-sts-pro"] = { } m["btk-pro"] = { } m["cau-abz-pro"] = { other_names = {"Proto-Abazgi", "Proto-Abkhaz-Tapanta"}, } m["cau-and-pro"] = { aliases = {"Proto-Andi", "Proto-Andic"}, } m["cau-ava-pro"] = { aliases = {"Proto-Avar-Andian", "Proto-Avar-Andi", "Proto-Avar-Andic"}, } m["cau-cir-pro"] = { other_names = {"Proto-Adyghe-Kabardian", "Proto-Adyghe-Circassian"}, } m["cau-drg-pro"] = { other_names = {"Proto-Dargin"}, } m["cau-lzg-pro"] = { aliases = {"Proto-Lezgi", "Proto-Lezgian", "Proto-Lezgic"}, } m["cau-nec-pro"] = { } m["cau-nkh-pro"] = { } m["cau-nwc-pro"] = { } m["cau-tsz-pro"] = { other_names = {"Proto-Tsezic", "Proto-Didoic"}, } m["cba-ata"] = { other_names = {"Atanque", "Cancuamo", "Kankuamo", "Kankwe", "Kankuí", "Atanke"}, } m["cba-cat"] = { other_names = {"Catio Chibcha", "Old Catio"}, } m["cba-dor"] = { other_names = {"Chumulu", "Changuena", "Changuina", "Chánguena", "Gualaca"}, } m["cba-dui"] = { } m["cba-hue"] = { other_names = {"Güetar", "Guetar", "Brusela"}, } m["cba-nut"] = { other_names = {"Nutabane"}, } m["cba-pro"] = { } m["ccs-pro"] = { } m["ccs-gzn-pro"] = { aliases = {"Proto-Karto-Zan"}, } m["cdc-cbm-pro"] = { aliases = {"Proto-Central-Chadic", "Proto-Biu-Mandara"}, } m["cdc-mas-pro"] = { } m["cdc-pro"] = { } m["cdd-pro"] = { } m["cel-bry-pro"] = { aliases = {"Proto-Brittonic", "Common Brythonic", "Common Brittonic"}, } m["cel-gal"] = { } m["cel-gau"] = { } m["cel-pro"] = { } m["chi-pro"] = { } m["chm-pro"] = { } m["cmc-pro"] = { } m["crp-bip"] = { } m["crp-gep"] = { aliases = {"Greenlandic Pidgin", "Greenlandic Eskimo Pidgin"}, } m["crp-kia"] = { aliases = {"Kiautschou Pidgin German"}, } m["crp-mar"] = { other_names = {"Jamaican Maroon Spirit Possession Language"}, } m["crp-mpp"] = { aliases = {"Macao Pidgin Portuguese"}, } m["crp-rsn"] = { } m["crp-slb"] = { other_names = {"Solombala-English", "Solombala English-Russian Pidgin"}, } m["crp-spp"] = { } m["crp-tpr"] = { } m["csu-bba-pro"] = { } m["csu-maa-pro"] = { } m["csu-pro"] = { } m["csu-sar-pro"] = { } m["cus-ash"] = { other_names = {"Ashraf", "Af-Ashraaf"}, varieties = { {"Marka, Lower Shabelle"}, "Shingani"}, } m["cus-hec-pro"] = { } m["cus-som-pro"] = { aliases = {"Proto-Sam", "Proto-Macro-Somali"}, } m["cus-sou-pro"] = { other_names = {"Proto-Rift"}, } m["cus-pro"] = { } m["dmn-dam"] = { } m["dra-bry"] = { aliases = {"Byari"}, } m["dra-cen-pro"] = { } m["dra-mkn"] = { aliases = {"Nadugannada"}, } m["dra-nor-pro"] = { } m["dra-okn"] = { aliases = {"Halegannada"}, } m["dra-ote"] = { } m["dra-pro"] = { } m["dra-sdo-pro"] = { aliases = {"Proto-South Dravidian"}, } m["dra-sdt-pro"] = { aliases = {"Proto-South-Central Dravidian"}, } m["dra-sou-pro"] = { aliases = {"Proto-Southern Dravidian"}, } m["egx-dem"] = { aliases = {"Demotic", "Enchorial"}, } m["dmn-pro"] = { } m["dmn-mdw-pro"] = { } m["dru-pro"] = { } m["ero-gsz"] = { } m["ero-nya"] = { } m["ero-tau"] = { other_names = {"Rtau"}, } m["esx-esk-pro"] = { } m["esx-ink"] = { } m["esx-inq"] = { } m["esx-inu-pro"] = { } m["esx-pro"] = { } m["esx-tut"] = { } m["euq-pro"] = { aliases = {"Proto-Vasconic"}, } m["gba-pro"] = { } m["gem-pro"] = { aliases = {"Common Germanic"}, } m["gme-bur"] = { aliases = {"Burgundish", "Burgundic"}, } m["gme-cgo"] = { } m["gmq-gut"] = { } m["gmq-jmk"] = { aliases = {"Jamtlandic"}, } m["gmq-mno"] = { } m["gmq-oda"] = { } m["gmq-ogt"] = { aliases = {"Old Gotlandic"}, } m["gmq-osw"] = { } m["gmq-pro"] = { aliases = {"Proto-Scandinavian", "Primitive Norse", "Proto-Nordic", "Ancient Nordic", "Ancient Scandinavian", "Old Nordic", "Old Scandinavian", "Proto-North Germanic", "North Proto-Germanic", "Common Scandinavian"}, } m["gmq-scy"] = { } m["gmw-bgh"] = { } m["gmw-cfr"] = { varieties = {"Mittelfränkisch", "Ripuarian", "Moselle Franconian", "Colognian", "Kölsch"}, } m["gmw-ecg"] = { varieties = {"Thuringian", "Thüringisch", "Upper Saxon", "Upper Saxon German", "Obersächsisch", "Lusatian", "Erzgebirgisch", "Silesian", "Silesian German", "High Prussian"}, } m["gmw-fin"] = { aliases = {"Fingal"}, } m["gmw-gts"] = { aliases = {"Gottscheerisch"}, } m["gmw-jdt"] = { } m["gmw-msc"] = { } m["gmw-pro"] = { } m["gmw-rfr"] = { aliases = {"Rheinfränkisch", "Rhenish Franconian"}, varieties = {"Hessian", "Lorraine Franconian", "Lorrainian", "Lothringisch", "Palatine German", "Pfälzisch", "Pälzisch", "Palatinate German"}, } m["gmw-stm"] = { aliases = {"Satu Mare Swabian", "Sathmarschwäbisch", "Sathmarisch"}, } m["gmw-tsx"] = { aliases = {"Siebenbürger Saxon"}, } m["gmw-vog"] = { } m["gmw-zps"] = { aliases = {"Zipser", "Zipserisch", "Outzäpsersch"}, } m["gn-cls"] = { } m["grk-cal"] = { aliases = {"Italian Greek", "Bova"}, } m["grk-ita"] = { aliases = {"Griko", "Grico", "Grecanic"}, } m["grk-mar"] = { aliases = {"Mariupolitan Greek", "Rumeíka", "Rumeika"}, } m["grk-pro"] = { aliases = {"Proto-Greek"}, } m["hmn-pro"] = { } m["hmx-mie-pro"] = { } m["hmx-pro"] = { } m["hyx-pro"] = { } m["iir-nur-pro"] = { } m["iir-pro"] = { } m["ijo-pro"] = { aliases = {"Proto-Ijaw"}, } m["inc-apa"] = { aliases = {"Apabhraṃśa"}, } m["inc-ash"] = { aliases = {"Asokan Prakrit", "Aśokan Prakrit"}, } m["inc-dng-pro"] = { } m["inc-kam"] = { } m["inc-kho"] = { } m["inc-krd-pro"] = { aliases = {"Proto-Kamata"}, } m["inc-mas"] = { } m["inc-mbn"] = { } m["inc-mgu"] = { } m["inc-mor"] = { aliases = {"Middle Oriya"}, } m["inc-oas"] = { } m["inc-oaw"] = { aliases = {"Early Awadhi"}, } m["inc-obn"] = { } m["inc-ogu"] = { aliases = {"Old Western Rajasthani"}, } m["inc-ohi"] = { aliases = {"Dehlavi"}, } m["inc-oor"] = { aliases = {"Old Oriya"}, } m["inc-opa"] = { } m["inc-pro"] = { } m["ine-ana-pro"] = { } m["ine-bsl-pro"] = { } m["ine-kal"] = { aliases = {"Kalasma", "Kalashma", "Kalašmaic", "Kalasmaic", "Kalašmian", "Kalasmian"}, } m["ine-pae"] = { } m["ine-pro"] = { } m["ine-toc-pro"] = { } m["xme-old"] = { } m["xme-mid"] = { aliases = {"Atropatenian"}, } m["xme-ker"] = { other_names = {"Kermanian", "Central Iranian Dialects", "Central Plateau Dialects", "Central Iranian", "South Median", "Gazi", "Soi", "Sohi", "Abuzeydabadi", "Abyanehi", "Farizandi", "Jowshaqani", "Nashalji", "Qohrudi", "Yarandi", "Tari", "Sedehi", "Ardestani", "Zefrehi", "Isfahani", "Kafroni", "Varzenehi", "Khuri", "Nayini", "Anaraki", "Zoroastrian Dari", "Behdināni", "Behdinani", "Gabri", "Gavrŭni", "Gavruni", "Gabrōni", "Gabroni", "Kermani", "Yazdi", "Bidhandi", "Bijagani", "Chimehi", "Hanjani", "Komjani", "Naraqi", "Qalhari", "Varani", "Zori"}, } m["xme-taf"] = { } m["xme-ttc-pro"] = { } m["xme-kls"] = { aliases = {"Kalāsuri", "Kalasur", "Kalāsur"}, } m["xme-klt"] = { } m["xme-ott"] = { other_names = {"Old Tatic", "Old Azeri", "Azari", "Azeri", "Āḏarī", "Adari", "Adhari"}, } m["ira-kms-pro"] = { } m["ira-mpr-pro"] = { } m["ira-pat-pro"] = { } m["ira-pro"] = { } m["ira-zgr-pro"] = { } m["xsc-pro"] = { } m["xsc-sar-pro"] = { } m["xsc-skw-pro"] = { } m["xsc-sak-pro"] = { aliases = {"Proto-Sakan", "Proto-Tumshuqese-Khotanese"}, } m["ira-sym-pro"] = { } m["ira-sgi-pro"] = { } m["ira-mny-pro"] = { } m["ira-shy-pro"] = { } m["ira-shr-pro"] = { } m["ira-sgc-pro"] = { aliases = {"Proto-Sogdian"}, } m["ira-wnj"] = { aliases = {"Old Vanji", "Vanchi", "Vanži", "Wanji"}, } m["iro-ere"] = { } m["iro-min"] = { } m["iro-nor-pro"] = { } m["iro-pro"] = { } m["itc-pro"] = { } m["itc-psa"] = { } m["jpx-hcj"] = { aliases = {"Hachijo"}, } m["jpx-pro"] = { } m["jpx-ryu-pro"] = { } m["kar-pro"] = { } m["kca-eas"] = { } m["kca-nor"] = { } m["kca-pro"] = { } m["kca-sou"] = { } m["khi-kho-pro"] = { } m["khi-kun"] = { other_names = {"ǃOǃKung", "ǃ'OǃKung", "Kung", "Ekoka ǃKung", "Ekoka Kung", "Sekele"}, } m["ko-ear"] = { } m["kro-pro"] = { } m["ku-pro"] = { } m["map-ata-pro"] = { } m["map-bms"] = { } m["map-pro"] = { } m["mis-hkl"] = { aliases = {"Kelantan Peranakan Chinese", "Hokkien Kelantan", "Kelantan Local Hokkien"} } m["mis-idn"] = { } m["mis-isa"] = { } m["mis-jie"] = { aliases = {"Chieh", "Kjet"}, } m["mis-jzh"] = { aliases = {"Haihua"}, } m["mis-kas"] = { aliases = {"Cassite", "Kassitic", "Kaššite"}, } m["mis-mmd"] = { other_names = {"Mimi of Gaudefroy-Demombynes", "Mimi-D"}, } m["mis-mmn"] = { other_names = {"Mimi-N"}, } m["mis-phi"] = { aliases = {"Philistian", "Philistinian"}, } m["mis-rou"] = { aliases = {"Ruanruan", "Ruan-ruan", "Juan-juan"}, } m["mis-tdl"] = { aliases = {"Turduli"}, } m["mis-tdt"] = { aliases = {"Turdetani"}, } m["mis-tnw"] = { aliases = {"Tangwanghua"}, } m["mis-tuh"] = { aliases = {"'Azha"}, } m["mis-tuo"] = { aliases = {"Tabghach", "Taghbach"}, } m["mis-wuh"] = { aliases = {"Wuwan", "Awar"}, } m["mis-xbi"] = { aliases = {"Serbi", "Shirwi"}, } m["mis-xnu"] = { aliases = {"Hsiung-nu", "Hiong-nu"}, } m["mjg-mgl"] = { aliases = {"Huzhu", "Huzhu Monguor"}, } m["mjg-mgr"] = { aliases = {"Minhe", "Minhe Monguor"}, } m["mkh-asl-pro"] = { } m["mkh-ban-pro"] = { } m["mkh-kat-pro"] = { } m["mkh-khm-pro"] = { } m["mkh-kmr-pro"] = { } m["mkh-mmn"] = { } m["mkh-mnc-pro"] = { } m["mkh-mvi"] = { } m["mkh-pal-pro"] = { } m["mkh-pea-pro"] = { } m["mkh-pkn-pro"] = { } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. } m["mnw-tha"] = { aliases = {"Raman", "Thai Raman", "Siamese Mon"}, } m["mkh-vie-pro"] = { } m["mns-cen"] = { } m["mns-nor"] = { } m["mns-pro"] = { } m["mns-sou"] = { } m["mun-pro"] = { aliases = {"Proto-Mundan"}, } m["myn-chl"] = { -- the stage after ''emy'' other_names = {"Cholti", "Colonial Ch'olti'", "Colonial Cholti"}, } m["myn-pro"] = { aliases = {"Proto-Maya"}, } m["nai-ala"] = { other_names = {"Alasapa", "Pinto"}, } m["nai-bay"] = { other_names = {"Bayougoula", "Bayou Goula", "Ischenoca"}, -- tribe merged with "Mougulasha", "Mongoulacha", "Mugulasha", "Mougulasha", "Muglahsa", "Muglasha", "Muguasha", "Imongolosha", "Houma", "Acolapissa" } m["nai-cal"] = { } m["nai-chi"] = { } m["nai-chu-pro"] = { aliases = {"Proto-Chumashan"}, } m["nai-cig"] = { } m["nai-ckn-pro"] = { aliases = {"Proto-Chinook"}, } m["nai-guz"] = { aliases = {"Guazacapan"}, } m["nai-hit"] = { other_names = {"Atcik-hata", "At-pasha-shliha"}, } m["nai-ipa"] = { other_names = {"'Iipay 'aa", "Northern Diegueño", "Diegueño"}, } m["nai-jtp"] = { other_names = {"Xutiapa", "Jalapa", "Xalapa"}, } m["nai-jum"] = { aliases = {"Jumaitepeque", "Jumaytepec"}, } m["nai-kat"] = { other_names = {"Kathlamet Chinook"}, } m["nai-klp-pro"] = { } m["nai-knm"] = { } m["nai-kum"] = { other_names = {"Kumiai", "Central Diegueño", "Diegueño"}, } m["nai-mac"] = { aliases = {"Macorís", "Macorix", "Mazorij", "Mazorig", "Mazoriges"}, } m["nai-mdu-pro"] = { aliases = {"Proto-Maiduan"}, } m["nai-miz-pro"] = { aliases = {"Proto-Mixe-Zoquean"}, } m["nai-mus-pro"] = { aliases = {"Proto-Muskhogean", "Proto-Muskogee"}, } m["nai-nao"] = { } m["nai-nrs"] = { } m["nai-okw"] = { } m["nai-per"] = { } m["nai-pic"] = { } m["nai-plp-pro"] = { } m["nai-pom-pro"] = { aliases = {"Proto-Pomoan"}, } m["nai-qng"] = { } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan } m["nai-sin"] = { aliases = {"Sinacantan", "Zinacantán", "Zinacantan"}, } m["nai-sln"] = { } m["nai-spt"] = { aliases = {"Shahaptin"}, } m["nai-tap"] = { other_names = {"Tapachulteca", "Tapachulteco", "Tapachula"}, } m["nai-taw"] = { } m["nai-teq"] = { other_names = {"Tequistlateco", "Tequistlateca", "Chontal", "Chontol of Oaxaca", "Oaxaca Chontal", "Oaxacan Chontal"}, } m["nai-tip"] = { other_names = {"Tipay", "Tiipai", "Tiipay", "Jamul Tiipay", "Southern Digueño", "Diegueño"}, } m["nai-tot-pro"] = { } m["nai-tsi-pro"] = { } m["nai-utn-pro"] = { other_names = {"Proto-Miwok-Costanoan"}, } m["nai-wai"] = { aliases = {"Guaycura", "Waicura"}, } m["nai-wji"] = { other_names = {"Jicaque of El Palmar", "Sula"}, } m["nai-yup"] = { aliases = {"Jupiltepeque", "Yupiltepec", "Jupiltepec", "Xupiltepec"}, } m["nan-dat"] = { aliases = {"Datian"}, } m["nan-hbl"] = { aliases = {"Hokkienese", "Quanzhang", "Fukien", "Banlam", "Banlamese", "Ban-lam"}, } m["nan-hlh"] = { aliases = {"Hailufeng", "Hoklo Min", "Hai Lok Hong"}, } m["nan-lnx"] = { aliases = {"Longyan", "Liongna"}, } m["nan-tws"] = { aliases = {"Teochew Min", "Chiuchow", "Teo-Swa", "Teo-Swa Min", "Tio-Sua"}, } m["nan-zhe"] = { aliases = {"Zhenan"}, } m["nan-zsh"] = { aliases = {"Sanxiang", "Samheung", "Sahiu"}, } m["ngf-pro"] = { } m["nic-bco-pro"] = { } m["nic-bod-pro"] = { } m["nic-eov-pro"] = { } m["nic-gns-pro"] = { } m["nic-grf-pro"] = { } m["nic-gur-pro"] = { } m["nic-jkn-pro"] = { } m["nic-lcr-pro"] = { } m["nic-ogo-pro"] = { } m["nic-ovo-pro"] = { } m["nic-plt-pro"] = { } m["nic-pro"] = { } m["nic-ubg-pro"] = { } m["nic-ucr-pro"] = { } m["nic-vco-pro"] = { } m["njo-jgl"] = { } m["nub-har"] = { aliases = {"Ḥarāza"}, } m["nub-pro"] = { } m["omq-cha-pro"] = { } m["omq-maz-pro"] = { aliases = {"Proto-Mazatecan"}, } m["omq-mix-pro"] = { } m["omq-mxt-pro"] = { } m["omq-otp-pro"] = { } m["omq-pro"] = { aliases = {"Proto-Otomanguean", "Proto-Oto-Mangue"}, } m["omq-sjq"] = { } m["omq-tel"] = { } m["omq-teo"] = { } m["omq-tri-pro"] = { aliases = {"Proto-Trique"}, } m["omq-zap-pro"] = { } m["omq-zpc-pro"] = { } m["omv-aro-pro"] = { } m["omv-diz-pro"] = { aliases = {"Proto-Maji"}, } m["omv-pro"] = { } m["oto-otm-pro"] = { } m["oto-pro"] = { } m["ngf-bin-pro"] = { } m["paa-kmn"] = { aliases = {"Komnzo", "Kómnjo", "Komnjo", "Kamundjo", "Rouku"}, } m["paa-kwn"] = { } m["paa-lei"] = { } m["paa-nha-pro"] = { } m["paa-nun"] = { } m["phi-din"] = { } m["phi-kal-pro"] = { aliases = {"Proto-Calamian"}, } m["phi-nag"] = { } m["phi-pro"] = { } m["poz-abi"] = { other_names = {"Sembuak", "Tubu"}, } m["poz-bal"] = { } m["poz-btk-pro"] = { } m["poz-cet-pro"] = { } m["poz-hce-pro"] = { other_names = {"Proto-South Halmahera - West New Guinea"}, } m["poz-lgx-pro"] = { } m["poz-mcm-pro"] = { } m["poz-mic-pro"] = { } m["poz-mly-pro"] = { } m["poz-msa-pro"] = { } m["poz-oce-pro"] = { } m["poz-pep-pro"] = { aliases = {"Proto-Eastern-Polynesian", "Proto-East Polynesian", "Proto-East-Polynesian"}, } m["poz-pnp-pro"] = { } m["poz-pol-pro"] = { } m["poz-pro"] = { other_names = {"Proto-Western Malayo-Polynesian"}, -- Western is subsumed into general Proto-MP } m["poz-sml"] = { aliases = {"Sarawak"}, } m["poz-ssw-pro"] = { } m["poz-swa-pro"] = { } m["poz-ter"] = { aliases = {"Terengganu"}, } m["pqe-pro"] = { } m["pra-niy"] = { } m["qfa-adm-pro"] = { } m["qfa-bet-pro"] = { aliases = {"Proto-Tai-Be"}, } m["qfa-cka-pro"] = { } m["qfa-hur-pro"] = { } m["qfa-kad-pro"] = { } m["qfa-kms-pro"] = { } m["qfa-kor-pro"] = { } m["qfa-kra-pro"] = { } m["qfa-lic-pro"] = { } m["qfa-onb-pro"] = { aliases = {"Proto-Ong-Be", "Proto-Bê"}, } m["qfa-ong-pro"] = { } m["qfa-tak-pro"] = { aliases = {"Proto-Tai-Kadai"}, } m["qfa-yen-pro"] = { } m["qfa-yuk-pro"] = { } m["qwe-kch"] = { other_names = {"Kichwa shimi", "Runashimi", "Runa", "Quichua", "Quecha", "Inga", "Chimborazo", "Imbabura Highland Kichwa", "Cañar Highland Quecha", "Quechua"}, } m["qwe-pro"] = { } m["roa-ang"] = { other_names = {"Craonnais", "Baugeois", "Saumurois"}, } m["roa-bbn"] = { other_names = {"Bourbonnais", "Berrichon", "Moulins", "Allier", "Nivernais", "Haut-Berrichon", "Bas-Berrichon"}, } m["roa-brg"] = { other_names = {"Burgundian", "Bregognon", "Dijonnais", "Morvandiau", "Morvandeau", "Morvan", "Bourguignon-Morvandiau", "Mâconnais", "Brionnais", "Brionnais-Charolais", "Auxerrois", "Beaunois", "Langrois", "Valsaônois", "Verduno-Chalonnais", "Sédelocien"}, } m["roa-can"] = { } m["roa-cha"] = { other_names = {"Bassignot", "Langrois", "Sennonais", "Vallage", "Troyen", "Briard", "Der", "Perthois", "Rémois", "Argonnais", "Porcien", "Ardennais", "Sugny"}, } m["roa-fcm"] = { other_names = {"Frainc-Comtou", "Comtois", "Jurassien", "Ajoulot", "Vâdais", "Taignon", "Bisontin", "Bousbot"}, } m["roa-gal"] = { } m["roa-gib"] = { } m["roa-gis"] = { } m["roa-leo"] = { } m["roa-lor"] = { other_names = {"Gaumais", "Vosgien", "Welche", "Argonnais", "Longovicien", "Messin", "Nancéien", "Spinalien", "Déodatien"}, } m["roa-oca"] = { aliases = {"Medieval Catalan"}, } m["roa-ole"] = { aliases = {"Medieval Leonese"}, } m["roa-ona"] = { aliases = {"Navarro-Aragonese", "Medieval Navarro-Aragonese", "Old Aragonese", "Medieval Aragonese"}, } m["roa-opt"] = { aliases = {"Old Galician Portuguese", "Old Galician–Portuguese", "Old Galician", "Old Portuguese", "Galician-Portuguese", "Galician Portuguese", "Galician–Portuguese", "Medieval Galician-Portuguese", "Medieval Galician Portuguese", "Medieval Galician–Portuguese", "Medieval Galician", "Medieval Portuguese", "Galaic-Portuguese"}, } m["roa-orl"] = { other_names = {"Beauceron", "Solognot", "Gâtinais", "Blaisois", "Vendômois"}, } m["roa-poi"] = { other_names = {"Poitevin", "Saintongeais", "Maraîchin"}, } m["roa-tar"] = { } m["sai-all"] = { other_names = {"Alyentiyak", "Huarpe", "Warpe"}, } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' other_names = {"Miranya", "Miranha", "Miranha Carapana-Tapuya", "Miraña-Carapana-Tapuyo", "Andokero", "Miranya-Karapana-Tapuyo", "Miraña", "Carapana"}, } m["sai-ayo"] = { aliases = {"Ayoman", "Ayamán", "Ayaman"}, } m["sai-bae"] = { aliases = {"Baenã", "Baenán", "Baena"}, } m["sai-bag"] = { other_names = {"Patagón de Bagua"}, } m["sai-bet"] = { other_names = {"Betoy", "Betoya", "Betoye", "Betoi-Jirara", "Jirara"}, } m["sai-bor-pro"] = { other_names = {"Proto-Bora-Muinane", "Proto-Bora-Muiname"}, } m["sai-cac"] = { other_names = {"Kakán", "Diaguita", "Cacan", "Kakan", "Calchaquí", "Chaka", "Kaka", "Kaká", "Caca", "Caca-Diaguita", "Catamarcano", "Capayán", "Capayana", "Yacampis"}, } m["sai-caq"] = { other_names = {"Cara", "Kara"}, } m["sai-car-pro"] = { } m["sai-cat"] = { } m["sai-cer-pro"] = { other_names = {"Proto-Amazonian Jê"}, } m["sai-chi"] = { } m["sai-chn"] = { aliases = {"Chana"}, } m["sai-chp"] = { aliases = {"Txapacura", "Xapacura", "Guapore", "Šapakura", "Txapakura", "Txapakúra", "Xapakúra"}, } m["sai-chr"] = { aliases = {"Charrúa", "Charruá"}, } m["sai-chu"] = { aliases = {"Churoya"}, } m["sai-cje-pro"] = { other_names = {"Proto-Akuwẽ"}, } m["sai-cmg"] = { aliases = {"Comechingón", "Comechingona", "Comechingone"}, } m["sai-cno"] = { other_names = {"Chonos", "Caucau"}, } m["sai-cnr"] = { aliases = {"Cañar"}, } m["sai-coe"] = { aliases = {"Koeruna"}, } m["sai-col"] = { aliases = {"Colan"}, } m["sai-cop"] = { } m["sai-crd"] = { other_names = {"Coroado"}, } m["sai-ctq"] = { aliases = {"Catuquinarú", "Katukinaru"}, } m["sai-cul"] = { other_names = {"Culle", "Kulyi", "Ilinga", "Linga"}, } m["sai-cva"] = { } m["sai-esm"] = { other_names = {"Esmeraldeño", "Atacame", "Takame"}, } m["sai-ewa"] = { } m["sai-gam"] = { aliases = {"Gamella", "Acobu", "Curinsi", "Barbados"}, } m["sai-gay"] = { aliases = {"Gayon"}, } m["sai-gmo"] = { other_names = {"Wamo", "Santa Rosa", "San Jose", "Barinas", "Guamotey", "Guama"}, } m["sai-gua"] = { aliases = {"Guachi", "Wachí", "Wachi"}, } m["sai-gue"] = { aliases = {"Guenoa"}, } m["sai-hau"] = { other_names = {"Manek'enk"}, } m["sai-jee-pro"] = { other_names = {"Proto-Gê", "Proto-Jean", "Proto-Gean", "Proto-Jê-Kaingang", "Proto-Ye"}, } m["sai-jko"] = { aliases = {"Geicó", "Jeicó", "Jaikó", "Geikó", "Yeikó", "Jeiko", "Geico", "Jeico", "Jaiko", "Geiko", "Yeiko", "Eyco"}, } m["sai-jrj"] = { } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc other_names = {"Catrimbi", "Catembri", "Kariri de Mirandela", "Mirandela", "Kariri", "Kiriri"}, } m["sai-mal"] = { aliases = {"Malali"}, } m["sai-mar"] = { } m["sai-mat"] = { other_names = {"Matanauí", "Matanaui", "Matanawü", "Mitandua", "Moutoniway"}, } m["sai-mcn"] = { aliases = {"Mokana"}, } m["sai-men"] = { aliases = {"Menién"}, } m["sai-mil"] = { other_names = {"Milykayak", "Huarpe", "Warpe"}, } m["sai-mlb"] = { aliases = {"Malibú", "Malebú"}, } m["sai-msk"] = { aliases = {"Masakara", "Masacará", "Masacara"}, } m["sai-muc"] = { other_names = {"Mucuchi", "Mokochi", "Mocochí", "Mirripú", "Maripú", "Mucuchí-Maripú"}, } m["sai-mue"] = { aliases = {"Muellamués"}, } m["sai-muz"] = { } m["sai-mys"] = { other_names = {"Mayna", "Maina", "Rimachu"}, } m["sai-nat"] = { other_names = {"Natu", "Peagaxinan"}, } m["sai-nje-pro"] = { other_names = {"Proto-Core Jê"}, } m["sai-opo"] = { other_names = {"Opon", "Opón-Karare", "Opón-Carare", "Carare", "Carare-Opón"}, } m["sai-oto"] = { aliases = {"Otomako", "Otomacan", "Otomac", "Otomak"}, } m["sai-pal"] = { } m["sai-pam"] = { aliases = {"Pamiwa"}, } m["sai-par"] = { aliases = {"Paratio", "Prarto"}, } m["sai-peb"] = { aliases = {"Peva"}, varieties = {"Cauwachi", "Caumari", "Pacaya"}, -- per Wikipedia, according to the American anthropologist and linguist John Alden Mason (1950) } m["sai-pnz"] = { aliases = {"Pansaleo"}, } m["sai-prh"] = { } m["sai-ptg"] = { other_names = {"Patagón de Perico"}, } m["sai-pur"] = { aliases = {"Purukoto", "Purucotó", "Purucoto"}, } m["sai-pyg"] = { aliases = {"Payawá", "Payagua"}, } m["sai-pyk"] = { aliases = {"Gavião-Pykobjê", "Pykobjê-Gavião", "Gavião", "Pyhcopji", "Gavião-Pyhcopji"}, } m["sai-qmb"] = { other_names = {"Kimbaya", "Quindío", "Quindio", "Quindo"}, } m["sai-qtm"] = { aliases = {"Quitemoca"}, } m["sai-rab"] = { } m["sai-ram"] = { } m["sai-sac"] = { other_names = {"Sacata", "Zácata", "Chillao"}, } m["sai-san"] = { aliases = {"Sanavirón", "Sanabirón", "Sanabiron", "Sanavirona", "Zanavirona"}, } m["sai-sap"] = { aliases = {"Zapará", "Zapara"}, } m["sai-sec"] = { other_names = {"Sek", "Sec"}, } m["sai-sin"] = { other_names = {"Cenúfana", "Zenúfana", "Cinifaná", "Sinufana", "Sinú", "Cenú", "Zenú", "Finzenú", "Fincenú", "Pancenú", "Sutagao"}, } m["sai-sje-pro"] = { } m["sai-tab"] = { other_names = {"Aconipa"}, } m["sai-tal"] = { other_names = {"Atalán", "Tallan", "Tallanca", "Atalan", "Sek"}, } m["sai-tap"] = { other_names = {"Tapayúna", "Kajkwakhrattxi"}, } m["sai-tar-pro"] = { } m["sai-teu"] = { aliases = {"Tehues", "Teuéx"}, } m["sai-tim"] = { other_names = {"Cuica", "Timote-Cuica"}, } m["sai-tpr"] = { aliases = {"Taparito"}, } m["sai-trr"] = { other_names = {"Caratiú"}, } m["sai-wai"] = { aliases = {"Waitaka", "Waitacá", "Waitaca", "Goytacá", "Goitacá", "Guaitacá", "Guiatacá", "Guiatacás", "Goiatacá", "Goiatacás", "Guaiatacá", "Goytacaz", "Goitacaz", "Goyataca", "Aitacaz", "Uetacaz", "Uetacá", "Outacá", "Ouetacá", "Eutacá", "Itacaz", "Vaitacá"}, } m["sai-way"] = { aliases = {"Wajumará", "Wajumara", "Wayumará", "Azumara", "Guimara"}, } m["sai-wit-pro"] = { other_names = {"Proto-Huitotoan", "Proto-Uitotoan"}, } m["sai-wnm"] = { other_names = {"Wañam", "Wanyam", "Huanyam", "Uanham", "Abitana"}, } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat other_names = {"Xoco", "Chocó", "Shokó", "Shoko", "Shocó", "Shoco", "Choco", "Chocaz", "Kariri-Xocó", "Kariri-Xoco", "Kariri-Shoko", "Cariri-Chocó", "Xukuru-Kariri", "Xucuru-Kariri", "Xucuru-Cariri", "Xukurú-Kirirí"}, } m["sai-yao"] = { aliases = {"Yao", "Jaoi", "Yaoi", "Yaio", "Anacaioury"}, } m["sai-yar"] = { -- not the same family as 'suy' aliases = {"Yaruma"}, } m["sai-yri"] = { aliases = {"Jurí"}, } m["sai-yup"] = { other_names = {"Yupuá", "Yupúa", "Jupua", "Jupuá", "Jupúa", "Hiupiá", "Yupuá-Duriña", "Duriña"}, } m["sai-yur"] = { aliases = {"Yurumangui", "Yurimangí", "Yurimangi", "Yurimanguí", "Yurimangui"}, } m["sal-pro"] = { aliases = {"Proto-Salishan"}, } m["sdv-daj-pro"] = { } m["sdv-eje-pro"] = { } m["sdv-nil-pro"] = { } m["sdv-nyi-pro"] = { } m["sdv-tmn-pro"] = { } m["sel-nor"] = { aliases = {"Taz Selkup"}, } m["sel-pro"] = { } m["sel-sou"] = { } m["sem-amm"] = { } m["sem-amo"] = { aliases = {"Amoritic"}, } m["sem-cha"] = { aliases = {"Cheha", "Čäha", "Čäxa"}, } m["sem-dad"] = { other_names = {"Dadanite", "Lihyanite", "Lihyanitic"}, } m["sem-dum"] = { } m["sem-has"] = { } m["sem-his"] = { other_names = {"Thamudic E"}, } m["sem-mhr"] = { other_names = {"Muher Gurage", "Muxar", "Muxər", "Muhər", "Muḫər"}, } m["sem-pro"] = { } m["sem-saf"] = { } m["sem-sam"] = { other_names = {"Sam'alian"}, } m["sem-srb"] = { } m["sem-tay"] = { other_names = {"Taymanite", "Thamudic A"}, } m["sem-tha"] = { } m["sem-wes-pro"] = { } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' } m["sit-aao-pro"] = { } m["sit-bok"] = { other_names = {"Ramo", "Pailibo"}, } m["sit-bai-pro"] = { } m["sit-ban"] = { } m["sit-bdi-pro"] = { } m["sit-cai"] = { } m["sit-cha"] = { } m["sit-ers-pro"] = { } m["sit-hrs-pro"] = { } m["sit-jap"] = { other_names = {"Chabao", "Kuru"}, } m["sit-kha-pro"] = { } m["sit-khb-pro"] = { } m["sit-khp-pro"] = { } m["sit-khw-pro"] = { } m["sit-kon-pro"] = { } m["sit-liz"] = { } m["sit-lnj"] = { } m["sit-lrn"] = { } m["sit-luu-pro"] = { } m["sit-nas-pro"] = { } m["sit-prn"] = { } m["sit-pro"] = { } m["sit-sit"] = { other_names = {"Eastern rGyalrong", "rGyalrong", "Rgyalrong", "rGyalrongic", "Gyalrong", "Gyarong", "rGyarong", "Gyarung", "Jiarong", "Jiarongyu", "Jyarong", "Jyarung", "Yelong", "Kuru"}, } m["sit-tam-pro"] = { aliases = {"Proto-Tamang"}, } m["sit-tan-pro"] = { } m["sit-tgm"] = { } m["sit-tng-pro"] = { } m["sit-tos"] = { } m["sit-tsh"] = { other_names = {"Caodeng", "Sidaba", "rGyalrong", "Rgyalrong", "Jiarong", "Gyarung", "Kuru"}, } m["sit-zbu"] = { other_names = {"Ribu", "Rdzong'bur", "Rdzongmbur", "Showu", "rGyalrong", "Rgyalrong", "Jiarong", "Gyarung", "Kuru"}, } m["sla-pro"] = { aliases = {"Common Slavic"}, } m["smi-pro"] = { aliases = {"Proto-Sami"}, } m["son-pro"] = { aliases = {"Proto-Songhai"}, } m["sqj-pro"] = { } m["ssa-klk-pro"] = { aliases = {"Proto-Rub"}, } m["ssa-kom-pro"] = { } m["ssa-pro"] = { } m["syd-pro"] = { } m["tai-pro"] = { } m["tai-swe-pro"] = { } m["tbq-bdg-pro"] = { } m["tbq-blg"] = { aliases = {"Pai-lang", "Pailang"}, } m["tbq-brm-pro"] = { } m["tbq-gkh"] = { aliases = {"Gɔkhý", "Gɔkhy", "Gouke"}, } m["tbq-kuk-pro"] = { other_names = {"Proto-Kukish"}, } m["tbq-lal-pro"] = { } m["tbq-laz"] = { other_names = {"Lare", "Shuitianhua"}, } m["tbq-lob-pro"] = { } m["tbq-lol-pro"] = { aliases = {"Proto-Yi", "Proto-Ngwi", "Proto-Nisoic"}, } m["tbq-mil"] = { } m["tbq-mor"] = { aliases = {"Morān"}, } m["tbq-ngo"] = { other_names = {"Ngachang", "Achang"}, } -- tbq-pro is now etymology-only m["trk-dkh"] = { aliases = {"Dukha"}, } m["trk-eog"] = { } m["trk-oat"] = { } m["trk-pro"] = { } m["tup-gua-pro"] = { } m["tup-kab"] = { aliases = {"Kabixiana", "Cabixiana", "Cabishiana", "Kapishana", "Capishana", "Kapišana", "Cabichiana", "Capichana", "Capixana"}, } m["tuw-alk"] = { aliases = {"Alechuka"}, } m["tuw-bal"] = { } m["tuw-kkl"] = { aliases = {"Chinese Kyakala"}, } m["tuw-kli"] = { aliases = {"Kilen", "Kirin", "Kila", "Hezhe", "Qile'en"}, } m["tup-pro"] = { } m["tuw-pro"] = { } m["tuw-sol"] = { } m["urj-fin-pro"] = { } m["urj-koo"] = { aliases = {"Old Permian"}, } m["urj-kuk"] = { aliases = {"Kukkuzi Votic", "Kukkuzi Ingrian", "Kukkusi"}, } m["urj-kya"] = { } m["urj-mdv-pro"] = { } m["urj-prm-pro"] = { } m["urj-pro"] = { other_names = {"Proto-Finno-Ugric", "Proto-Finno-Permic"}, -- PFU and PFP are subsumed into PU per [[Wiktionary:Beer parlour/2015/January#Merging Finno-Volgaic, Finno-Samic, Finno-Permic and Finno-Ugric into Uralic]] } m["urj-ugr-pro"] = { } m["xgn-pro"] = { } m["xnd-pro"] = { other_names = {"Proto-Na-Dené", "Proto-Athabaskan-Eyak-Tlingit"}, } m["yok-bvy"] = { other_names = {"Tulamni-Hometwoli", "Tulamni", "Tulamne", "Tuolumne", "Tawitchi", "Hometwoli", "Taneshach"}, } m["yok-dly"] = { other_names = {"Far Northern Valley Yokuts", "Yachikumne", "Yachikumni", "Chulamni", "Lower San Joaquin", "Lakisamni", "Tawalimni"}, } m["yok-gsy"] = { } m["yok-kry"] = { other_names = {"Choinimni", "Choynimni", "Ayticha", "Kocheyali", "Ayitcha", "Michahay", "Chukaymina", "Chukaimina"}, } m["yok-nvy"] = { other_names = {"Chukchansi", "Kechayi", "Dumna", "Chawchila", "Noptinte", "Nopṭinṭe", "Nopthrinthre", "Nopchinchi", "Takin"}, } m["yok-ply"] = { other_names = {"Paleuyami", "Altinin", "Poso Creek", "Poso Creek Yokuts"}, } m["yok-svy"] = { other_names = {"Yawelmani", "Tachi", "Koyeti", "Nutunutu", "Chunut", "Wo'lasi", "Choynok", "Choinok", "Wechihit"}, } m["yok-tky"] = { other_names = {"Wikchamni", "Wukchamni", "Wukchumni", "Yawdanchi"}, } m["ypk-pro"] = { } m["yrk-for"] = { } m["yrk-tun"] = { other_names = {"Yurak"}, varieties = { { "Western Nenets" }, { "Eastern Nenets" }, } } m["zhx-min-pro"] = { } m["zhx-sht"] = { other_names = {"Xiangnan Tuhua", "Yuebei Tuhua", "Shipo", "Shina"}, } m["zhx-sic"] = { aliases = {"Sichuanese Mandarin"}, } m["zhx-tai"] = { aliases = {"Toishanese"}, } m["zle-ono"] = { } m["zle-ort"] = { } m["zls-chs"] = { } m["zlw-ocs"] = { } m["zlw-opl"] = { } m["zlw-osk"] = { } m["zlw-slv"] = { } return m m81rgjdlzd5vbhimng8lss36yrye0nn 10 9438 231375 32074 2023-03-19T05:20:52Z en>WingerBot 0 [[:Category:Template documentation templates]] -> [[:Category:Documentation templates]] (manually assisted) 231375 wikitext text/x-wiki {{documentation subpage}} <includeonly> [[Category:Documentation templates]] </includeonly> jk9piljissv5x18sgky6zk1jimrm4u0 231376 211535 2026-04-14T07:34:27Z Lee 19 [[:en:Template:language_data_documentation/documentation]] වෙතින් එක් සංශෝධනයක් 211535 wikitext text/x-wiki {{documentation subpage}} <includeonly> [[ප්‍රවර්ගය:උපදෙස් සැකිලි]]<!-- Should perhaps be "Module documentation templates". --> </includeonly> 2tsa44vzwudcucuswtgl3j5y40w2ydp 828 83640 231352 205016 2026-01-11T23:45:47Z en>Benwing2 0 check_missing should be done through checkredlinks=1 in [[Module:headword]] 231352 Scribunto text/plain local export = {} local pos_functions = {} local force_cat = false -- for testing; if true, categories appear in non-mainspace pages local require_when_needed = require("Module:utilities/require when needed") local m_table = require("Module:table") local en_utilities_module = "Module:en-utilities" local headword_utilities_module = "Module:headword utilities" local m_en_utilities = require_when_needed(en_utilities_module) local m_headword_utilities = require_when_needed(headword_utilities_module) local m_string_utilities = require_when_needed("Module:string utilities") local glossary_link = require_when_needed(headword_utilities_module, "glossary_link") local boolean_param = {type = "boolean"} local list_param = {list = true, disallow_holes = true} local concat = table.concat local insert = table.insert local remove = table.remove local rfind = mw.ustring.find local unpack = unpack or table.unpack -- Lua 5.2 compatibility local langs_supported = { ["pl"] = { peri_comp = "bardziej", sup = "naj", -- participle endings act = {"ąc[yae]$"}, -- biegnący pass = {"[ntł][yae]$"}, -- otwarty, uwielbiany, legły cont_adv = {"ąc$"}, ant_adv = {"szy$"}, }, ["csb"] = { peri_comp = "barżi", sup = "nô", -- participle endings act = {"ący$"}, pass = {"[ao]ny$", "ty$", "łi$"}, cont_adv = {"ōnc$"}, ant_adv = {"[wł]szë$"}, }, ["szl"] = { peri_comp = "bardzij", sup = "noj", -- participle endings act = {"ōncy$"}, pass = {"[aō]ny$", "[tł]y$"}, cont_adv = {"ąc$"}, ant_adv = false, }, ["zlw-opl"] = { peri_comp = "barziej", sup = false, -- participle endings act = {"ąc[yae]$"}, -- biegnący pass = {"[ntł][yae]$"}, -- otwarty, uwielbiany, legły cont_adv = {"ąc$"}, ant_adv = {"szy$"}, }, ["pox"] = { peri_comp = false, sup = false, -- participle endings act = false, pass = false, cont_adv = false, ant_adv = false, has_dual = true, }, ["zlw-slv"] = { peri_comp = "barżé", sup = "no", -- participle endings act = false, pass = false, cont_adv = false, ant_adv = false, has_dual = true, }, } ----------------------------------------------- Utilities -------------------------------------------- local function track(page) require("Module:debug").track("zlw-lch-headword/" .. page) return true end local function replace_hash_with_lemma(term, lemma) -- If there is a % sign in the lemma, we have to replace it with %% so it doesn't get interpreted as a capture -- replace expression. lemma = m_string_utilities.replacement_escape(lemma) return (term:gsub("#", lemma)) -- discard second retval end local function frob_term_with_hash(term, lemma) if term:find("#") then term = replace_hash_with_lemma(term, lemma) end return term end -- Parse and insert an inflection not requiring additional processing into `data.inflections`. The raw arguments come -- from `args[field]`, which is parsed for inline modifiers. `label` is the label that the inflections are given; -- `accel` is the accelerator form, or nil. local function parse_and_insert_inflection(data, args, field, label, accel) m_headword_utilities.parse_and_insert_inflection { headdata = data, forms = args[field], paramname = field, splitchar = ",", include_mods = {"g"}, frob = function(term) return frob_term_with_hash(term, data.pagename) end, label = label, accel = accel and {form = accel} or nil, } end -- Parse and return an inflection not requiring additional processing. The raw arguments come from `args[field]`, which -- is parsed for inline modifiers. local function parse_inflection(data, args, field) return m_headword_utilities.parse_term_list_with_modifiers { paramname = field, forms = args[field], splitchar = ",", include_mods = {"g"}, frob = function(term) return frob_term_with_hash(term, data.pagename) end, } end -- Insert the parsed inflections in `infls` (as parsed by `parse_inflection`) into `data.inflections`, with label -- `label` and optional accelerator spec `accel`. local function insert_inflection(data, terms, label, accel) m_headword_utilities.insert_inflection { headdata = data, terms = terms, label = label, accel = accel and {form = accel} or nil, } end ----------------------------------------------- Main entry point -------------------------------------------- function export.show(frame) local iparams = { [1] = {required = true}, ["lang"] = {required = true}, } local iargs = require("Module:parameters").process(frame.args, iparams) local poscat = iargs[1] langcode = iargs.lang if not langs_supported[langcode] then local langcodes_supported = {} for lang, _ in pairs(langs_supported) do insert(langcodes_supported, lang) end error("This module currently only works for lang=" .. concat(langcodes_supported, "/")) end local lang = require("Module:languages").getByCode(langcode) local langname = lang:getCanonicalName() local params = { ["head"] = {list = true}, ["nolink"] = boolean_param, ["nolinkhead"] = {type = "boolean", alias_of = "nolink"}, ["suffix"] = boolean_param, ["nosuffix"] = boolean_param, ["json"] = boolean_param, ["abbr"] = {list = true}, ["pagename"] = {}, -- for testing } if pos_functions[poscat] then local posparams = pos_functions[poscat].params if type(posparams) == "function" then posparams = posparams(langcode) end for key, val in pairs(posparams) do params[key] = val end end local parargs = frame:getParent().args local args = require("Module:parameters").process(parargs, params) local pagename = args.pagename or mw.loadData("Module:headword/data").pagename local user_specified_heads = args.head local heads = user_specified_heads if args.nolink then if #heads == 0 then heads = {pagename} end end local data = { lang = lang, langcode = langcode, langname = langname, pos_category = poscat, categories = {}, heads = heads, user_specified_heads = user_specified_heads, no_redundant_head_cat = not user_specified_heads[1], genders = {}, inflections = {}, categories = {}, pagename = pagename, id = args.id, force_cat_output = force_cat, } data.is_suffix = false if args.suffix or ( not args.nosuffix and pagename:find("^%-") and poscat ~= "suffixes" and poscat ~= "suffix forms" ) then data.is_suffix = true data.pos_category = "suffixes" local singular_poscat = m_en_utilities.singularize(poscat) insert(data.categories, langname .. " " .. singular_poscat .. "-forming suffixes") insert(data.inflections, {label = singular_poscat .. "-forming suffix"}) end if pos_functions[poscat] then pos_functions[poscat].func(args, data) end parse_and_insert_inflection(data, args, "abbr", "abbreviation") if args.json then return require("Module:JSON").toJSON(data) end return require("Module:headword").full_headword(data) end ----------------------------------------------- Nouns -------------------------------------------- local function get_noun_inflection_specs(langcode) local noun_inflection_specs = { {"gen", "genitive singular"}, } if langs_supported[langcode].has_dual then insert(noun_inflection_specs, {"du", "nominative dual"}) end for _, spec in ipairs { {"pl", "nominative plural"}, {"genpl", "genitive plural"}, {"f", "female equivalent"}, {"m", "male equivalent"}, {"n", "neuter equivalent"}, {"marr", "traditional married form"}, {"unmarr", "traditional unmarried form"}, {"dim", "diminutive"}, {"pej", "pejorative"}, {"aug", "augmentative"}, {"adj", "related adjective"}, {"poss", "possessive adjective"}, {"dem", "demonym"}, {"fdem", "female demonym"}, } do insert(noun_inflection_specs, spec) end return noun_inflection_specs end local function get_noun_pos(is_proper) return { params = function(langcode) local params = { ["indecl"] = boolean_param, [1] = {list = "g", disallow_holes = true, type = "genders", flatten = true}, -- gender(s) } for _, spec in ipairs(get_noun_inflection_specs(langcode)) do local param, desc = unpack(spec) params[param] = list_param end params["rel"] = {list = true, alias_of = "adj"} return params end, func = function(args, data) -- Compute allowed genders, and map incomplete genders to specs with a "?" in them. local genders = {false, "m", "mf", "mfbysense", "f", "n", "g!"} local animacies = {false, "in", "anml", "pr", "an!"} local numbers = {false, "p", "num!"} local allowed_genders = {} for _, g in ipairs(genders) do for _, an in ipairs(animacies) do for _, num in ipairs(numbers) do local source_gender_parts = {} local dest_gender_parts = {} local function ins_part(part, partname) if part then insert(source_gender_parts, part) insert(dest_gender_parts, part) elseif partname == "g" and num == false or partname == "an" and g ~= "f" and g ~= "n" then -- allow incomplete gender plurale tantum nouns; also allow incomplete -- animacy for fem/neut, where it makes no difference for agreement -- purposes; otherwise insert a ? to indicate incomplete gender spec insert(dest_gender_parts, "?") end end ins_part(g, "g") ins_part(an, "an") ins_part(num, "num") if #source_gender_parts == 0 then allowed_genders["?"] = "?" else allowed_genders[concat(source_gender_parts, "-")] = concat(dest_gender_parts, "-") end -- "Virile" = masculine personal, allow in the plural and convert appropriately; -- "Nonvirile" = anything but masculine personal, allow in the plural; -- "Nonpersonal" = anything but personal, i.e. animal or inanimate; allow in the plural. allowed_genders["vr-p"] = "m-pr-p" allowed_genders["nv-p"] = "nv-p" allowed_genders["np-p"] = "np-p" end end end -- Validate and canonicalize genders. for _, g in ipairs(args[1]) do if not allowed_genders[g.spec] then error("Unrecognized " .. data.langname .. " gender: " .. g.spec) else g.spec = allowed_genders[g.spec] end end data.genders = args[1] if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) insert(data.categories, data.langname .. " indeclinable nouns") end -- Process all inflections. for _, spec in ipairs(get_noun_inflection_specs(data.langcode)) do local param, desc = unpack(spec) parse_and_insert_inflection(data, args, param, desc) end end } end pos_functions["nouns"] = get_noun_pos(false) pos_functions["proper nouns"] = get_noun_pos(true) ----------------------------------------------- Verbs -------------------------------------------- local function get_verb_pos() local verb_inflection_specs = { -- order per old [[Module:pl-headword]] {"det", "imperfective determinate"}, {"pf", "perfective"}, {"impf", "imperfective"}, {"indet", "indeterminate"}, {"freq", "frequentative"}, } local params = { [1] = {default = "?"}, ["def"] = boolean_param, } for _, spec in ipairs(verb_inflection_specs) do local param, desc = unpack(spec) params[param] = list_param end return { params = params, func = function(args, data) local allowed_aspects = require("Module:table").listToSet { "pf", "impf", "biasp", "both", "impf-det", "impf-indet", "impf-freq", "?" } local impf_allowed = true local pf_allowed = true local indet_allowed = true local det_allowed = true local freq_allowed = true local function insert_label_and_cat(aspect, label) -- Preserve qualifiers, labels, references. aspect = aspect and m_table.shallowCopy(aspect) or {} aspect.term = nil aspect.label = label insert(data.inflections, aspect) insert(data.categories, data.langname .. " " .. label .. " verbs") end local aspects = m_headword_utilities.parse_term_with_modifiers { paramname = 1, val = args[1], splitchar = ",", exclude_mods = {"id"}, -- doesn't make sense for gender specs } -- Validate and canonicalize aspects. for i, aspect in ipairs(aspects) do local a = aspect.term if not allowed_aspects[a] then error("Unrecognized " .. data.langname .. " aspect: " .. a) elseif a == "both" then a = "biasp" elseif a == "impf-det" then a = "impf" insert_label_and_cat(aspect, "determinate") det_allowed = false elseif a == "impf-indet" then a = "impf" insert_label_and_cat(aspect, "indeterminate") indet_allowed = false elseif a == "impf-freq" then a = "impf" insert_label_and_cat(aspect, "indeterminate") insert_label_and_cat(aspect, "frequentative") indet_allowed = false freq_allowed = false elseif a == "pf" then pf_allowed = false elseif a == "impf" then impf_allowed = false end aspect.spec = a aspect.term = nil end data.genders = aspects if args.def then insert_label_and_cat(nil, "defective") end -- Process all inflections. for _, spec in ipairs(verb_inflection_specs) do local param, desc = unpack(spec) local infls = parse_inflection(data, args, param) if infls[1] then if param == "pf" and not pf_allowed then error("Aspectual-pair perfectives not allowed with perfective-only verb") end if param == "impf" and not impf_allowed then error("Aspectual-pair imperfectives not allowed with imperfective-only verb") end if param == "det" and not det_allowed then error("Aspectual-pair determinates not allowed with imperfective-only determinate verb") end if param == "indet" and not indet_allowed then error("Aspectual-pair indeterminates not allowed with imperfective-only indeterminate or frequentative verb") end if param == "freq" and not freq_allowed then error("Aspectual-pair frequentatives not allowed with imperfective-only frequentative verb") end insert_inflection(data, infls, desc) end end end } end pos_functions["verbs"] = get_verb_pos() ----------------------------------------------- Adjectives, Adverbs -------------------------------------------- local function get_adj_adv_pos(pos) return { params = function(langcode) local params = { [1] = list_param, ["dim"] = list_param, ["sup"] = list_param, ["nodefsup"] = boolean_param, } if pos == "adjective" then params["adv"] = list_param params["indecl"] = boolean_param end if langcode == "pl" then params["mpcomp"] = list_param params["mpsup"] = list_param end return params end, func = function(args, data) local default_sups = {} local comps = parse_inflection(data, args, 1) if comps[1] then local lang_data = langs_supported[data.langcode] if comps[1].term == "-" then if not comps[2] then -- Preserve any qualifiers, labels, etc. comps[1].label = "not " .. glossary_link("comparable") comps[1].term = nil insert(data.inflections, comps[1]) insert(data.categories, data.langname .. " uncomparable " .. data.pos_category) else -- Preserve any qualifiers, labels, etc. comps[1].label = "not generally " .. glossary_link("comparable") comps[1].term = nil insert(data.inflections, comps[1]) end remove(comps, 1) end for i, comp in ipairs(comps) do if comp.term == "peri" then if not lang_data.peri_comp then error("Don't know how to form periphrastic comparatives for " .. data.langname) end comp.term = ("[[%s]] [[%s]]"):format(lang_data.peri_comp, data.pagename) if lang_data.sup then local default_sup = m_table.shallowCopy(comp) default_sup.term = ("[[%s%s]] [[%s]]"):format(lang_data.sup, lang_data.peri_comp, data.pagename) insert(default_sups, default_sup) end elseif lang_data.sup then local default_sup = m_table.shallowCopy(comp) default_sup.term = ("%s%s"):format(lang_data.sup, comp.term) insert(default_sups, default_sup) end end end insert_inflection(data, comps, "comparative", "comparative") local sups = parse_inflection(data, args, "sup") if not sups[1] then sups = args.nodefsup and {} or {{term = "+"}} end local combined_sups = {} for _, sup in ipairs(sups) do if sup.term == "+" then for _, def_sup in ipairs(default_sups) do def_sup = m_table.shallowCopy(def_sup) m_headword_utilities.combine_termobj_qualifiers_labels(def_sup, sup) insert(combined_sups, def_sup) end else insert(combined_sups, sup) end end insert_inflection(data, combined_sups, "superlative", "superlative") if data.langcode == "pl" then parse_and_insert_inflection(data, args, "mpcomp", "Middle Polish comparative") parse_and_insert_inflection(data, args, "mpsup", "Middle Polish superlative") end if pos == "adjective" then if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) insert(data.categories, data.langname .. " indeclinable adjectives") end parse_and_insert_inflection(data, args, "adv", "derived adverb") end parse_and_insert_inflection(data, args, "dim", "diminutive") end, } end pos_functions["adjectives"] = get_adj_adv_pos("adjective") pos_functions["adverbs"] = get_adj_adv_pos("adverb") ----------------------------------------------- Participles -------------------------------------------- local function get_part_pos() local params = { [1] = {}, ["a"] = list_param, } return { params = params, func = function(args, data) if data.langcode ~= "pl" then error("Internal error: Unable to handle languages other than Polish for participles: " .. data.langname) end -- Compute allowed aspects, and map incomplete aspects to specs with a "?" in them. local allowed_aspects = require("Module:table").listToSet { "pf", "impf", "biasp", "both", "pf-it", "pf-sem", "impf-it", "impf-dur", "?" } local allowed_types = require("Module:table").listToSet { "pass", "act", "ant-adv", "cont-adv", "?" } local function insert_label_and_cat(aspect, label, nolink) if not nolink then label = glossary_link(label) end -- Preserve qualifiers, labels, references. aspect = aspect and m_table.shallowCopy(aspect) or {} aspect.term = nil aspect.label = label insert(data.inflections, aspect) insert(data.categories, data.langname .. " " .. label .. " participles") end local aspects = m_headword_utilities.parse_term_list_with_modifiers { paramname = "a", forms = args.a, splitchar = ",", exclude_mods = {"id"}, -- doesn't make sense for gender specs } -- Validate and canonicalize aspects. for i, aspect in ipairs(aspects) do local a = aspect.term if not allowed_aspects[a] then error("Unrecognized " .. data.langname .. " participle aspect: " .. a) elseif a == "both" then a = "biasp" elseif a == "impf-it" then a = "impf" insert_label_and_cat(aspect, "iterative") elseif a == "impf-dur" then a = "impf" insert_label_and_cat(aspect, "durative") elseif a == "pf-it" then a = "pf" insert_label_and_cat(aspect, "iterative") elseif a == "pf-sem" then a = "pf" insert_label_and_cat(aspect, "semelfactive") end aspect.spec = a aspect.term = nil end data.genders = aspects -- Validate or autodetect participle type. local function matches_parttype(typ) local endings = langs_supported[data.langcode][typ] if not endings then return false end for _, ending in ipairs(endings) do if rfind(data.pagename, ending) then return true end end return false end local ptype = args[1] if ptype then if not allowed_types[ptype] then error("Unrecognized " .. data.langname .. " participle type: " .. ptype) end elseif matches_parttype("act") then -- biegnący ptype = "act" elseif matches_parttype("pass") then -- otwarty, uwielbiany, legły ptype = "pass" elseif matches_parttype("cont_adv") then ptype = "cont-adv" elseif matches_parttype("ant_adv") then ptype = "ant-adv" elseif (data.pagename:find("%-participle$") or data.pagename:find("%-part$")) and mw.title.getCurrentTitle().nsText == "Template" then ptype = "pass" else error(("Missing %s participle type and can't infer from pagename '%s'"):format(data.langname, data.pagename)) end if ptype == "act" then insert_label_and_cat(nil, "active adjectival", true) elseif ptype == "pass" then insert_label_and_cat(nil, "passive adjectival", true) elseif ptype == "cont-adv" then insert_label_and_cat(nil, "contemporary adverbial", true) elseif ptype == "ant-adv" then insert_label_and_cat(nil, "anterior adverbial", true) end end } end pos_functions["participles"] = get_part_pos() return export 3pba2oq6hrgqyuzjj6wlarpsy903vip 231353 231352 2026-04-13T17:06:27Z Lee 19 [[:en:Module:zlw-lch-headword]] වෙතින් එක් සංශෝධනයක් 231352 Scribunto text/plain local export = {} local pos_functions = {} local force_cat = false -- for testing; if true, categories appear in non-mainspace pages local require_when_needed = require("Module:utilities/require when needed") local m_table = require("Module:table") local en_utilities_module = "Module:en-utilities" local headword_utilities_module = "Module:headword utilities" local m_en_utilities = require_when_needed(en_utilities_module) local m_headword_utilities = require_when_needed(headword_utilities_module) local m_string_utilities = require_when_needed("Module:string utilities") local glossary_link = require_when_needed(headword_utilities_module, "glossary_link") local boolean_param = {type = "boolean"} local list_param = {list = true, disallow_holes = true} local concat = table.concat local insert = table.insert local remove = table.remove local rfind = mw.ustring.find local unpack = unpack or table.unpack -- Lua 5.2 compatibility local langs_supported = { ["pl"] = { peri_comp = "bardziej", sup = "naj", -- participle endings act = {"ąc[yae]$"}, -- biegnący pass = {"[ntł][yae]$"}, -- otwarty, uwielbiany, legły cont_adv = {"ąc$"}, ant_adv = {"szy$"}, }, ["csb"] = { peri_comp = "barżi", sup = "nô", -- participle endings act = {"ący$"}, pass = {"[ao]ny$", "ty$", "łi$"}, cont_adv = {"ōnc$"}, ant_adv = {"[wł]szë$"}, }, ["szl"] = { peri_comp = "bardzij", sup = "noj", -- participle endings act = {"ōncy$"}, pass = {"[aō]ny$", "[tł]y$"}, cont_adv = {"ąc$"}, ant_adv = false, }, ["zlw-opl"] = { peri_comp = "barziej", sup = false, -- participle endings act = {"ąc[yae]$"}, -- biegnący pass = {"[ntł][yae]$"}, -- otwarty, uwielbiany, legły cont_adv = {"ąc$"}, ant_adv = {"szy$"}, }, ["pox"] = { peri_comp = false, sup = false, -- participle endings act = false, pass = false, cont_adv = false, ant_adv = false, has_dual = true, }, ["zlw-slv"] = { peri_comp = "barżé", sup = "no", -- participle endings act = false, pass = false, cont_adv = false, ant_adv = false, has_dual = true, }, } ----------------------------------------------- Utilities -------------------------------------------- local function track(page) require("Module:debug").track("zlw-lch-headword/" .. page) return true end local function replace_hash_with_lemma(term, lemma) -- If there is a % sign in the lemma, we have to replace it with %% so it doesn't get interpreted as a capture -- replace expression. lemma = m_string_utilities.replacement_escape(lemma) return (term:gsub("#", lemma)) -- discard second retval end local function frob_term_with_hash(term, lemma) if term:find("#") then term = replace_hash_with_lemma(term, lemma) end return term end -- Parse and insert an inflection not requiring additional processing into `data.inflections`. The raw arguments come -- from `args[field]`, which is parsed for inline modifiers. `label` is the label that the inflections are given; -- `accel` is the accelerator form, or nil. local function parse_and_insert_inflection(data, args, field, label, accel) m_headword_utilities.parse_and_insert_inflection { headdata = data, forms = args[field], paramname = field, splitchar = ",", include_mods = {"g"}, frob = function(term) return frob_term_with_hash(term, data.pagename) end, label = label, accel = accel and {form = accel} or nil, } end -- Parse and return an inflection not requiring additional processing. The raw arguments come from `args[field]`, which -- is parsed for inline modifiers. local function parse_inflection(data, args, field) return m_headword_utilities.parse_term_list_with_modifiers { paramname = field, forms = args[field], splitchar = ",", include_mods = {"g"}, frob = function(term) return frob_term_with_hash(term, data.pagename) end, } end -- Insert the parsed inflections in `infls` (as parsed by `parse_inflection`) into `data.inflections`, with label -- `label` and optional accelerator spec `accel`. local function insert_inflection(data, terms, label, accel) m_headword_utilities.insert_inflection { headdata = data, terms = terms, label = label, accel = accel and {form = accel} or nil, } end ----------------------------------------------- Main entry point -------------------------------------------- function export.show(frame) local iparams = { [1] = {required = true}, ["lang"] = {required = true}, } local iargs = require("Module:parameters").process(frame.args, iparams) local poscat = iargs[1] langcode = iargs.lang if not langs_supported[langcode] then local langcodes_supported = {} for lang, _ in pairs(langs_supported) do insert(langcodes_supported, lang) end error("This module currently only works for lang=" .. concat(langcodes_supported, "/")) end local lang = require("Module:languages").getByCode(langcode) local langname = lang:getCanonicalName() local params = { ["head"] = {list = true}, ["nolink"] = boolean_param, ["nolinkhead"] = {type = "boolean", alias_of = "nolink"}, ["suffix"] = boolean_param, ["nosuffix"] = boolean_param, ["json"] = boolean_param, ["abbr"] = {list = true}, ["pagename"] = {}, -- for testing } if pos_functions[poscat] then local posparams = pos_functions[poscat].params if type(posparams) == "function" then posparams = posparams(langcode) end for key, val in pairs(posparams) do params[key] = val end end local parargs = frame:getParent().args local args = require("Module:parameters").process(parargs, params) local pagename = args.pagename or mw.loadData("Module:headword/data").pagename local user_specified_heads = args.head local heads = user_specified_heads if args.nolink then if #heads == 0 then heads = {pagename} end end local data = { lang = lang, langcode = langcode, langname = langname, pos_category = poscat, categories = {}, heads = heads, user_specified_heads = user_specified_heads, no_redundant_head_cat = not user_specified_heads[1], genders = {}, inflections = {}, categories = {}, pagename = pagename, id = args.id, force_cat_output = force_cat, } data.is_suffix = false if args.suffix or ( not args.nosuffix and pagename:find("^%-") and poscat ~= "suffixes" and poscat ~= "suffix forms" ) then data.is_suffix = true data.pos_category = "suffixes" local singular_poscat = m_en_utilities.singularize(poscat) insert(data.categories, langname .. " " .. singular_poscat .. "-forming suffixes") insert(data.inflections, {label = singular_poscat .. "-forming suffix"}) end if pos_functions[poscat] then pos_functions[poscat].func(args, data) end parse_and_insert_inflection(data, args, "abbr", "abbreviation") if args.json then return require("Module:JSON").toJSON(data) end return require("Module:headword").full_headword(data) end ----------------------------------------------- Nouns -------------------------------------------- local function get_noun_inflection_specs(langcode) local noun_inflection_specs = { {"gen", "genitive singular"}, } if langs_supported[langcode].has_dual then insert(noun_inflection_specs, {"du", "nominative dual"}) end for _, spec in ipairs { {"pl", "nominative plural"}, {"genpl", "genitive plural"}, {"f", "female equivalent"}, {"m", "male equivalent"}, {"n", "neuter equivalent"}, {"marr", "traditional married form"}, {"unmarr", "traditional unmarried form"}, {"dim", "diminutive"}, {"pej", "pejorative"}, {"aug", "augmentative"}, {"adj", "related adjective"}, {"poss", "possessive adjective"}, {"dem", "demonym"}, {"fdem", "female demonym"}, } do insert(noun_inflection_specs, spec) end return noun_inflection_specs end local function get_noun_pos(is_proper) return { params = function(langcode) local params = { ["indecl"] = boolean_param, [1] = {list = "g", disallow_holes = true, type = "genders", flatten = true}, -- gender(s) } for _, spec in ipairs(get_noun_inflection_specs(langcode)) do local param, desc = unpack(spec) params[param] = list_param end params["rel"] = {list = true, alias_of = "adj"} return params end, func = function(args, data) -- Compute allowed genders, and map incomplete genders to specs with a "?" in them. local genders = {false, "m", "mf", "mfbysense", "f", "n", "g!"} local animacies = {false, "in", "anml", "pr", "an!"} local numbers = {false, "p", "num!"} local allowed_genders = {} for _, g in ipairs(genders) do for _, an in ipairs(animacies) do for _, num in ipairs(numbers) do local source_gender_parts = {} local dest_gender_parts = {} local function ins_part(part, partname) if part then insert(source_gender_parts, part) insert(dest_gender_parts, part) elseif partname == "g" and num == false or partname == "an" and g ~= "f" and g ~= "n" then -- allow incomplete gender plurale tantum nouns; also allow incomplete -- animacy for fem/neut, where it makes no difference for agreement -- purposes; otherwise insert a ? to indicate incomplete gender spec insert(dest_gender_parts, "?") end end ins_part(g, "g") ins_part(an, "an") ins_part(num, "num") if #source_gender_parts == 0 then allowed_genders["?"] = "?" else allowed_genders[concat(source_gender_parts, "-")] = concat(dest_gender_parts, "-") end -- "Virile" = masculine personal, allow in the plural and convert appropriately; -- "Nonvirile" = anything but masculine personal, allow in the plural; -- "Nonpersonal" = anything but personal, i.e. animal or inanimate; allow in the plural. allowed_genders["vr-p"] = "m-pr-p" allowed_genders["nv-p"] = "nv-p" allowed_genders["np-p"] = "np-p" end end end -- Validate and canonicalize genders. for _, g in ipairs(args[1]) do if not allowed_genders[g.spec] then error("Unrecognized " .. data.langname .. " gender: " .. g.spec) else g.spec = allowed_genders[g.spec] end end data.genders = args[1] if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) insert(data.categories, data.langname .. " indeclinable nouns") end -- Process all inflections. for _, spec in ipairs(get_noun_inflection_specs(data.langcode)) do local param, desc = unpack(spec) parse_and_insert_inflection(data, args, param, desc) end end } end pos_functions["nouns"] = get_noun_pos(false) pos_functions["proper nouns"] = get_noun_pos(true) ----------------------------------------------- Verbs -------------------------------------------- local function get_verb_pos() local verb_inflection_specs = { -- order per old [[Module:pl-headword]] {"det", "imperfective determinate"}, {"pf", "perfective"}, {"impf", "imperfective"}, {"indet", "indeterminate"}, {"freq", "frequentative"}, } local params = { [1] = {default = "?"}, ["def"] = boolean_param, } for _, spec in ipairs(verb_inflection_specs) do local param, desc = unpack(spec) params[param] = list_param end return { params = params, func = function(args, data) local allowed_aspects = require("Module:table").listToSet { "pf", "impf", "biasp", "both", "impf-det", "impf-indet", "impf-freq", "?" } local impf_allowed = true local pf_allowed = true local indet_allowed = true local det_allowed = true local freq_allowed = true local function insert_label_and_cat(aspect, label) -- Preserve qualifiers, labels, references. aspect = aspect and m_table.shallowCopy(aspect) or {} aspect.term = nil aspect.label = label insert(data.inflections, aspect) insert(data.categories, data.langname .. " " .. label .. " verbs") end local aspects = m_headword_utilities.parse_term_with_modifiers { paramname = 1, val = args[1], splitchar = ",", exclude_mods = {"id"}, -- doesn't make sense for gender specs } -- Validate and canonicalize aspects. for i, aspect in ipairs(aspects) do local a = aspect.term if not allowed_aspects[a] then error("Unrecognized " .. data.langname .. " aspect: " .. a) elseif a == "both" then a = "biasp" elseif a == "impf-det" then a = "impf" insert_label_and_cat(aspect, "determinate") det_allowed = false elseif a == "impf-indet" then a = "impf" insert_label_and_cat(aspect, "indeterminate") indet_allowed = false elseif a == "impf-freq" then a = "impf" insert_label_and_cat(aspect, "indeterminate") insert_label_and_cat(aspect, "frequentative") indet_allowed = false freq_allowed = false elseif a == "pf" then pf_allowed = false elseif a == "impf" then impf_allowed = false end aspect.spec = a aspect.term = nil end data.genders = aspects if args.def then insert_label_and_cat(nil, "defective") end -- Process all inflections. for _, spec in ipairs(verb_inflection_specs) do local param, desc = unpack(spec) local infls = parse_inflection(data, args, param) if infls[1] then if param == "pf" and not pf_allowed then error("Aspectual-pair perfectives not allowed with perfective-only verb") end if param == "impf" and not impf_allowed then error("Aspectual-pair imperfectives not allowed with imperfective-only verb") end if param == "det" and not det_allowed then error("Aspectual-pair determinates not allowed with imperfective-only determinate verb") end if param == "indet" and not indet_allowed then error("Aspectual-pair indeterminates not allowed with imperfective-only indeterminate or frequentative verb") end if param == "freq" and not freq_allowed then error("Aspectual-pair frequentatives not allowed with imperfective-only frequentative verb") end insert_inflection(data, infls, desc) end end end } end pos_functions["verbs"] = get_verb_pos() ----------------------------------------------- Adjectives, Adverbs -------------------------------------------- local function get_adj_adv_pos(pos) return { params = function(langcode) local params = { [1] = list_param, ["dim"] = list_param, ["sup"] = list_param, ["nodefsup"] = boolean_param, } if pos == "adjective" then params["adv"] = list_param params["indecl"] = boolean_param end if langcode == "pl" then params["mpcomp"] = list_param params["mpsup"] = list_param end return params end, func = function(args, data) local default_sups = {} local comps = parse_inflection(data, args, 1) if comps[1] then local lang_data = langs_supported[data.langcode] if comps[1].term == "-" then if not comps[2] then -- Preserve any qualifiers, labels, etc. comps[1].label = "not " .. glossary_link("comparable") comps[1].term = nil insert(data.inflections, comps[1]) insert(data.categories, data.langname .. " uncomparable " .. data.pos_category) else -- Preserve any qualifiers, labels, etc. comps[1].label = "not generally " .. glossary_link("comparable") comps[1].term = nil insert(data.inflections, comps[1]) end remove(comps, 1) end for i, comp in ipairs(comps) do if comp.term == "peri" then if not lang_data.peri_comp then error("Don't know how to form periphrastic comparatives for " .. data.langname) end comp.term = ("[[%s]] [[%s]]"):format(lang_data.peri_comp, data.pagename) if lang_data.sup then local default_sup = m_table.shallowCopy(comp) default_sup.term = ("[[%s%s]] [[%s]]"):format(lang_data.sup, lang_data.peri_comp, data.pagename) insert(default_sups, default_sup) end elseif lang_data.sup then local default_sup = m_table.shallowCopy(comp) default_sup.term = ("%s%s"):format(lang_data.sup, comp.term) insert(default_sups, default_sup) end end end insert_inflection(data, comps, "comparative", "comparative") local sups = parse_inflection(data, args, "sup") if not sups[1] then sups = args.nodefsup and {} or {{term = "+"}} end local combined_sups = {} for _, sup in ipairs(sups) do if sup.term == "+" then for _, def_sup in ipairs(default_sups) do def_sup = m_table.shallowCopy(def_sup) m_headword_utilities.combine_termobj_qualifiers_labels(def_sup, sup) insert(combined_sups, def_sup) end else insert(combined_sups, sup) end end insert_inflection(data, combined_sups, "superlative", "superlative") if data.langcode == "pl" then parse_and_insert_inflection(data, args, "mpcomp", "Middle Polish comparative") parse_and_insert_inflection(data, args, "mpsup", "Middle Polish superlative") end if pos == "adjective" then if args.indecl then insert(data.inflections, {label = glossary_link("indeclinable")}) insert(data.categories, data.langname .. " indeclinable adjectives") end parse_and_insert_inflection(data, args, "adv", "derived adverb") end parse_and_insert_inflection(data, args, "dim", "diminutive") end, } end pos_functions["adjectives"] = get_adj_adv_pos("adjective") pos_functions["adverbs"] = get_adj_adv_pos("adverb") ----------------------------------------------- Participles -------------------------------------------- local function get_part_pos() local params = { [1] = {}, ["a"] = list_param, } return { params = params, func = function(args, data) if data.langcode ~= "pl" then error("Internal error: Unable to handle languages other than Polish for participles: " .. data.langname) end -- Compute allowed aspects, and map incomplete aspects to specs with a "?" in them. local allowed_aspects = require("Module:table").listToSet { "pf", "impf", "biasp", "both", "pf-it", "pf-sem", "impf-it", "impf-dur", "?" } local allowed_types = require("Module:table").listToSet { "pass", "act", "ant-adv", "cont-adv", "?" } local function insert_label_and_cat(aspect, label, nolink) if not nolink then label = glossary_link(label) end -- Preserve qualifiers, labels, references. aspect = aspect and m_table.shallowCopy(aspect) or {} aspect.term = nil aspect.label = label insert(data.inflections, aspect) insert(data.categories, data.langname .. " " .. label .. " participles") end local aspects = m_headword_utilities.parse_term_list_with_modifiers { paramname = "a", forms = args.a, splitchar = ",", exclude_mods = {"id"}, -- doesn't make sense for gender specs } -- Validate and canonicalize aspects. for i, aspect in ipairs(aspects) do local a = aspect.term if not allowed_aspects[a] then error("Unrecognized " .. data.langname .. " participle aspect: " .. a) elseif a == "both" then a = "biasp" elseif a == "impf-it" then a = "impf" insert_label_and_cat(aspect, "iterative") elseif a == "impf-dur" then a = "impf" insert_label_and_cat(aspect, "durative") elseif a == "pf-it" then a = "pf" insert_label_and_cat(aspect, "iterative") elseif a == "pf-sem" then a = "pf" insert_label_and_cat(aspect, "semelfactive") end aspect.spec = a aspect.term = nil end data.genders = aspects -- Validate or autodetect participle type. local function matches_parttype(typ) local endings = langs_supported[data.langcode][typ] if not endings then return false end for _, ending in ipairs(endings) do if rfind(data.pagename, ending) then return true end end return false end local ptype = args[1] if ptype then if not allowed_types[ptype] then error("Unrecognized " .. data.langname .. " participle type: " .. ptype) end elseif matches_parttype("act") then -- biegnący ptype = "act" elseif matches_parttype("pass") then -- otwarty, uwielbiany, legły ptype = "pass" elseif matches_parttype("cont_adv") then ptype = "cont-adv" elseif matches_parttype("ant_adv") then ptype = "ant-adv" elseif (data.pagename:find("%-participle$") or data.pagename:find("%-part$")) and mw.title.getCurrentTitle().nsText == "Template" then ptype = "pass" else error(("Missing %s participle type and can't infer from pagename '%s'"):format(data.langname, data.pagename)) end if ptype == "act" then insert_label_and_cat(nil, "active adjectival", true) elseif ptype == "pass" then insert_label_and_cat(nil, "passive adjectival", true) elseif ptype == "cont-adv" then insert_label_and_cat(nil, "contemporary adverbial", true) elseif ptype == "ant-adv" then insert_label_and_cat(nil, "anterior adverbial", true) end end } end pos_functions["participles"] = get_part_pos() return export 3pba2oq6hrgqyuzjj6wlarpsy903vip 828 83642 231354 205021 2025-09-29T03:02:11Z en>Benwing2 0 remove fucked up changes by new user 231354 wikitext text/x-wiki This module implements headword templates for all Lechitic languages: Polish, Kashubian, Silesian, Masurian, Old Polish, Polabian and Slovincian. The parts of speech supported are nouns, proper nouns, verbs, adjectives, adverbs and participles. The Wikicode of a template invoking this module should look similarly to the following (shown is the code for Silesian nouns, i.e. {{tl|szl-noun}}): <pre> {{#invoke:zlw-lch-headword|show|nouns|lang=szl}}<!-- --><noinclude>{{documentation}}</noinclude> </pre> {{module cat|fam:zlw-lch|type=Headword-line}} 9454402z0iq56a8o0rsqwpeamny642l 231355 231354 2026-04-13T17:06:47Z Lee 19 [[:en:Module:zlw-lch-headword/documentation]] වෙතින් එක් සංශෝධනයක් 231354 wikitext text/x-wiki This module implements headword templates for all Lechitic languages: Polish, Kashubian, Silesian, Masurian, Old Polish, Polabian and Slovincian. The parts of speech supported are nouns, proper nouns, verbs, adjectives, adverbs and participles. The Wikicode of a template invoking this module should look similarly to the following (shown is the code for Silesian nouns, i.e. {{tl|szl-noun}}): <pre> {{#invoke:zlw-lch-headword|show|nouns|lang=szl}}<!-- --><noinclude>{{documentation}}</noinclude> </pre> {{module cat|fam:zlw-lch|type=Headword-line}} 9454402z0iq56a8o0rsqwpeamny642l 14 116256 231402 174240 2026-04-14T11:50:19Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit ප්‍රවේශ නඩත්තුව]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත ප්‍රවේශ නඩත්තුව]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 174240 wikitext text/x-wiki {{auto cat}} [[en:Category:Ashokan Prakrit entry maintenance]] 710tm0aa58h9qp4n3oesi4opmamufcw 10 121603 231390 193197 2026-04-14T07:57:11Z Lee 19 /* Examples */ 231390 wikitext text/x-wiki {{documentation subpage}} {{shortcut|T:R:MED}} ===Usage=== This template may be used in "References" and "Further reading" sections, and on talk pages, for citing the ''{{w|Middle English Dictionary}}'' website (''[http://quod.lib.umich.edu/m/med/ MED Online]''). ===Parameters=== The template takes the following parameters: * {{para|1}} or {{para|entry}} – the name of the entry on the ''MED Online'' website, and an abbreviation indicating the [[part of speech]] (see the examples below). If this parameter is omitted, the name of the Wiktionary entry is used as a default. * {{para|2}}, {{para|pos}}, or {{para|part of speech}} – the [[part of speech]] of the entry. By default, the template italicizes the value assigned to the parameter and adds a [[full stop]] ([[period]]) to the end. To turn off the default formatting for the purpose of specifying a different formatting using wikitext markup and templates, specify {{para|noformat|1}} or {{para|noformat|yes}}: see the example [[#Examples|below]]. * {{para|3}}, {{para|code}}, or {{para|id}} – '''mandatory''': the ''MED Online'' identification code for the entry which is in the form "<kbd>MED</kbd>" followed by a number. The code can be found in the [[URL]]. * {{para|date}} – the date of the ''MED Online'' entry webpage. If this parameter is omitted, the template defaults to "2007". * {{para|4}} or {{para|accessdate}} – the date when the ''MED Online'' webpage was accessed, in one of the following formats: <kbd>1 January 2017</kbd> or <kbd>January 1, 2017</kbd> * {{para|subentry}} – a term that appears as a subentry under an entry. * {{para|subpos}} – the part of speech of the subentry. * {{para|5}}, {{para|text}}, or {{para|passage}} – a passage quoted from the webpage. * {{para|quotes}} or {{para|q}} – To search words in quotations, use {{para|quotes|1}} or {{para|quotes|yes}}. * {{para|nodot}} – by default, the template adds a full stop (period) at the end of the citation. To suppress this punctuation, use {{para|nodot|1}} or {{para|nodot|yes}}. ===Examples=== ; General * '''Wikitext''': ** {{temp|R:MED Online|2=entry=traunce|3=part of speech=n|4=id=MED46844|5=access-date=1 January 2017}}; or ** {{temp|R:MED Online|2=traunce|3=n|4=MED46844|5=1 January 2017}} * '''Result''': {{R:MED Online|entry=traunce|part of speech=n|id=MED46844|access-date=1 January 2017}} * '''Wikitext''': {{temp|R:MED Online|2=entry=sǒuel|3=part of speech=<nowiki>''n.''(2)</nowiki>|4=noformat=yes|5=id=MED41777|6=access-date=1 January 2018|7=passage=<nowiki>Something eaten with bread, such as meat, pottage, a sauce, etc.; food in general, nourishment;{{nb...}}</nowiki>|8=nodot=1}} * '''Result''': {{R:MED Online|entry=sǒuel|part of speech=''n.''(2)|noformat=yes|id=MED41777|access-date=1 January 2018|passage=Something eaten with bread, such as meat, pottage, a sauce, etc.; food in general, nourishment;{{nb...}}|nodot=1}} ; Citing a subentry * '''Wikitext''': {{temp|R:MED Online|2=subentry=cat of the mountain|3=subpos=n|4=entry=cat|5=pos=n|6=id=MED6929}} * '''Result''': ** {{R:MED Online|subentry=cat of the mountain|subpos=n|entry=cat|pos=n|id=MED6929}} <includeonly> [[ප්‍රවර්ගය:මධ්‍යකාලීන ඉංග්‍රීසි මූලාශ්‍ර සැකිලි|MED Online]] </includeonly> c8rrranlj6zuynlaq49mkhi67uf36mt 0 130008 231371 204667 2026-04-14T07:30:59Z WrdSrchSi 3305 + etymon|si + IPA|si 231371 wikitext text/x-wiki ==සිංහල== === නිරුක්තිය 1 === {{etymon|si|id=ව ඊ|af|si>ව#ධාතු ප්‍රකෘතිය>ප්‍රකෘතිය|si>-ඊ>ප්‍රත්‍ය|tree=1}} ''[[ව#ධාතු ප්‍රකෘතිය|ව]] (ප්‍රකෘතිය) + [[-ඊ]] (ප්‍රත්‍ය) > ව් - '''අ''' ([[ස්වර ලොපය]]) + -ඊ >'' [[වී]] ===උච්චාරණය=== * {{IPA|si|/ˈʋiː/}} ===ක්‍රියා පද=== {{head|si|verb forms|head=වී|අතීත අන්‍ය පුරුෂ බහුවචන|වූ#ක්‍රියා පද}} # {{{1|{{rfdef|si}}}}} #: ''{{{2|<!-- example sentence -->}}}'' #:* අරීසෙන් අහුබුදු, ''[https://www.scribd.com/doc/225741420/HelaAwuruduWaga හෙළ අවුරුදු වග]'', 2006, 20 පිටුව #:*: ''එ හෙයින් උසස් නිලදරුවනට සේ මැ ඔවුනට ද ....... සොම්නසින් අවුරුදු සමය ගෙවිය හැකි '''වී'''.'' === නිරුක්තිය 2 === {{rfe|si}} === නාම පදය === {{si-noun}} # {{rfdef|si}} === අමතර අවධානයට === * {{l|si|බත්}} * {{l|si|සහල්}} <!-- ==== පරිවර්තන ==== {{trans-top|පරිවර්තන}} * ඉංග්‍රීසි: {{t|en|<<ඉංග්‍රීසි වචනය>>}} {{trans-bottom}} --> toxv1uvysg6zxdparyh8w6acfawxz9x 0 130911 231381 223849 2026-04-14T07:38:44Z WrdSrchSi 3305 + head|si|verb forms|head= 231381 wikitext text/x-wiki ==සිංහල== === නිරුක්තිය === {{etymon|si|id=වද ඇ|af|si>වද#ධාතු ප්‍රකෘතිය>ප්‍රකෘතිය|si>-ඇ>ප්‍රත්‍ය|tree=1}} ''[[වද#ධාතු ප්‍රකෘතිය|වද]] (ප්‍රකෘතිය) + [[-ඇ]] (ප්‍රත්‍ය) > [[වැදැ]] ===උච්චාරණය=== * {{IPA|si|/ˈʋædæ/}} === ක්‍රියා පද === {{head|si|verb forms|head=වැදැ|වර්තමාන-නිපාත|වදිමින්|අනාගත-නිපාත|වදිනුව}} # {{infl of|si|වදී#ක්‍රියා පද||අතීත|නිපාත ක්‍රියා}} [[ප්‍රවර්ගය: සිංහල නිපාත ක්‍රියා පද]] e9v7dsjpumbanlshdziad9d4a4bfg3x 0 131139 231368 207497 2026-04-14T07:13:56Z WrdSrchSi 3305 + head|si|verb forms|head= 231368 wikitext text/x-wiki == සිංහල == === ක්‍රියා පද === {{head|si|verb forms|head=වමු}} # {{{1|{{rfdef|si}}}}} #: ''{{{2|<!-- example sentence -->}}}'' [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] k86jt7t40c44hrme27ed1gv01ihzg0w 0 134571 231374 215488 2026-04-14T07:33:13Z WrdSrchSi 3305 + IPA|si + head|si|verb forms 231374 wikitext text/x-wiki == සිංහල == ===උච්චාරණය=== * {{IPA|si|/ˈʋuːmu/}} === ක්‍රියා පද === {{head|si|verb forms}} # {{{1|{{rfdef|si}}}}} #: ''{{{2|<!-- example sentence -->}}}'' [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] fk8llpt02d5n6lhpeqgu80clvy83qnm 0 134884 231392 216153 2026-04-14T11:38:31Z WrdSrchSi 3305 + head|si|verb forms|head= 231392 wikitext text/x-wiki == සිංහල == ===උච්චාරණය=== * {{IPA|si|/ˈɦuʋəmi/}} ===ක්‍රියා පද=== {{head|si|verb forms|head=හුවමි|අතීත-සකර්මක උත්තම ඒකවචන|හිවීමි|අනතීත-කර්ම කාරක උත්තම ඒකවචන|හිවෙමි|අතීත-කර්ම කාරක උත්තම ඒකවචන|හිවිණිමි}} # {{lb|si|සකර්මක}} {{infl of|si|හුවයි||අනතීත|උත්තම පුරුෂ|ඒකවචන|ආඛ්‍යාත ක්‍රියා}} [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] 04pys8y404adw0qx4l9ub19ixw4vaap 0 134885 231391 216154 2026-04-14T11:35:15Z WrdSrchSi 3305 + head|si|verb forms|head= 231391 wikitext text/x-wiki == සිංහල == ===උච්චාරණය=== * {{IPA|si|/ˈɦuʋəmu/}} ===ක්‍රියා පද=== {{head|si|verb forms|head=හුවමු|අතීත-සකර්මක උත්තම බහුවචන|හිවූමු|අනතීත-කර්ම කාරක උත්තම බහුවචන|හිවෙමු|අතීත-කර්ම කාරක උත්තම බහුවචන|හිවුණුමු}} # {{lb|si|සකර්මක}} {{infl of|si|හුවයි||අනතීත|උත්තම පුරුෂ|බහුවචන|ආඛ්‍යාත ක්‍රියා}} [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] 9kwuhsjo7iqoe9zl2b29wwnrimao5py 0 134886 231357 216156 2026-04-14T05:07:51Z WrdSrchSi 3305 + head|si|verb forms|head= 231357 wikitext text/x-wiki ==සිංහල== === නිරුක්තිය === {{etymon|si|id=හුව ආ|af|si>හුව#ධාතු ප්‍රකෘතිය>ප්‍රකෘතිය|si>-ආ>ප්‍රත්‍ය|tree=1}} ''[[හුව#ධාතු ප්‍රකෘතිය|හුව]] (ප්‍රකෘතිය) + [[-ආ]] (ප්‍රත්‍ය) > හුව් - '''අ''' ([[ස්වර ලොපය]]) + -ආ >'' [[හුවා]] ===උච්චාරණය=== * {{IPA|si|/ˈɦuʋaː/}} === ක්‍රියා පද === {{head|si|verb forms|head=හුවා|වර්තමාන-නිපාත|හුවමින්}} # {{alternative form of|si|හුවයි#ක්‍රියා පද}} # {{infl of|si|හුවයි#ක්‍රියා පද||අතීත|නිපාත ක්‍රියා}} [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] [[ප්‍රවර්ගය: සිංහල නිපාත ක්‍රියා පද]] b0771ajlib0k47p7rkqusicmyna0kbg 0 135093 231431 216777 2026-04-14T11:58:47Z WrdSrchSi 3305 + head|si|verb forms|head= + ක්‍රියා පද 2 231431 wikitext text/x-wiki ==සිංහල== === නිරුක්තිය === {{rfe|si}} ===උච්චාරණය=== * {{IPA|si|/ˈɦæremi/}} ===ක්‍රියා පද=== {{head|si|verb forms|head=හැරෙමි|අතීත-අකර්මක උත්තම පුරුෂ ඒකවචන|හැරිණිමි#ක්‍රියා පද 1}} # {{lb|si|අකර්මක}} {{infl of|si|හැරේ||අනතීත|උත්තම පුරුෂ|ඒකවචන|ආඛ්‍යාත ක්‍රියා}} ===ක්‍රියා පද 2=== {{head|si|verb forms|head=හැරෙමි|අතීත-කර්ම කාරක උත්තම ඒකවචන|හැරිණිමි#ක්‍රියා පද 2|අනතීත-සකර්මක උත්තම ඒකවචන|හරිමි#ක්‍රියා පද}} # {{infl of|si|හරී#ක්‍රියා පද||අනතීත|කර්ම කාරක|උත්තම පුරුෂ|ඒකවචන|ආඛ්‍යාත ක්‍රියා}} [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] 5gpmkudpthur85abtzxz7f8atakhkg1 0 135094 231419 216776 2026-04-14T11:52:17Z WrdSrchSi 3305 + head|si|verb forms|head= + ක්‍රියා පද 2 231419 wikitext text/x-wiki ==සිංහල== === නිරුක්තිය === {{rfe|si}} ===උච්චාරණය=== * {{IPA|si|/ˈɦæremu/}} ===ක්‍රියා පද 1=== {{head|si|verb forms|head=හැරෙමු|අතීත-අකර්මක උත්තම බහුවචන|හැරුණුමු#ක්‍රියා පද 1}} # {{lb|si|අකර්මක}} {{infl of|si|හැරේ||අනතීත|උත්තම පුරුෂ|බහුවචන|ආඛ්‍යාත ක්‍රියා}} ===ක්‍රියා පද 2=== {{head|si|verb forms|head=හැරෙමු|අතීත-කර්ම කාරක උත්තම බහුවචන|හැරුණුමු#ක්‍රියා පද 2|අනතීත-සකර්මක උත්තම බහුවචන|හරිමු#ක්‍රියා පද}} # {{infl of|si|හරී#ක්‍රියා පද||අනතීත|කර්ම කාරක|උත්තම පුරුෂ|බහුවචන|ආඛ්‍යාත ක්‍රියා}} [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] 200sbqbz7d52h7h6mdobnne8duckvsi 0 136420 231367 219317 2026-04-14T07:11:51Z WrdSrchSi 3305 + වෙනත් ආකාර + head|si|verb forms|head= 231367 wikitext text/x-wiki ==සිංහල== ===වෙනත් ආකාර=== * {{l|si|හජාරා#ක්‍රියා පද|හජාරා}} * {{l|si|හදහරා#ක්‍රියා පද|හදහරා}} === නිරුක්තිය === {{etymon|si|id=හදාර ආ|af|si>හදාර#ධාතු ප්‍රකෘතිය>ප්‍රකෘතිය|si>-ආ>ප්‍රත්‍ය|tree=1}} ''[[හදාර#ධාතු ප්‍රකෘතිය|හදාර]] (ප්‍රකෘතිය) + [[-ආ]] (ප්‍රත්‍ය) > හදාර් - '''අ''' ([[ස්වර ලොපය]]) + -ආ >'' [[හදාරා]] ===උච්චාරණය=== * {{IPA|si|/ˈɦadaːraː/}} === ක්‍රියා පද === {{head|si|verb forms|head=හදාරා|වර්තමාන-නිපාත|හදාරමින්|අනාගත-නිපාත|හදාරනුව}} # {{alternative form of|si|හදාරයි}} # {{infl of|si|හදාරයි||අතීත|නිපාත ක්‍රියා}} [[ප්‍රවර්ගය: සිංහල ආඛ්‍යාත ක්‍රියා පද]] [[ප්‍රවර්ගය: සිංහල නිපාත ක්‍රියා පද]] rcb8vluj8zybqaa8tbcbx9kwzlg6ezz 0 142021 231300 2025-12-30T09:03:36Z en>WingerBot 0 replace trivial {{head}}-wrapper letter templates with calls to {{letter|LANG}} (manually assisted) 231300 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{head|mul|letter|sc=Brah|tr=ḻa}} # {{n-g|the [[thirty-fifth]] [[Brahmi]] [[consonant]]}} ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/ɻɐ/}} ===Letter=== {{letter|oty}} # Tamil-Brahmi letter ḻa. dfqhy1gv7uze1zv5w90hy3f1ajbrfwd 231301 231300 2026-04-13T15:14:51Z Lee 19 [[:en:𑀵]] වෙතින් එක් සංශෝධනයක් 231300 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{head|mul|letter|sc=Brah|tr=ḻa}} # {{n-g|the [[thirty-fifth]] [[Brahmi]] [[consonant]]}} ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/ɻɐ/}} ===Letter=== {{letter|oty}} # Tamil-Brahmi letter ḻa. dfqhy1gv7uze1zv5w90hy3f1ajbrfwd 231339 231301 2026-04-13T15:22:15Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231339 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{head|mul|letter|sc=Brah|tr=ḻa}} # {{n-g|the [[thirty-fifth]] [[Brahmi]] [[consonant]]}} ==Old Tamil== === උච්චාරණය === * {{IPA|oty|/ɻɐ/}} === අකුර === {{letter|oty}} # Tamil-Brahmi letter ḻa. 191nay1ibnpnusggx3y4fk8y1m020sb 0 142022 231302 2025-12-30T09:03:37Z en>WingerBot 0 replace trivial {{head}}-wrapper letter templates with calls to {{letter|LANG}} (manually assisted) 231302 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{head|mul|letter|sc=Brah|tr=ṟa}} # {{n-g|the [[thirty-sixth]] [[Brahmi]] [[consonant]]}} ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/rɐ/}} ===Letter=== {{letter|oty}} # Tamil-Brahmi letter ṟa. tdr62h6mu62hef188mp53wnygbnxw61 231303 231302 2026-04-13T15:15:08Z Lee 19 [[:en:𑀶]] වෙතින් එක් සංශෝධනයක් 231302 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{head|mul|letter|sc=Brah|tr=ṟa}} # {{n-g|the [[thirty-sixth]] [[Brahmi]] [[consonant]]}} ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/rɐ/}} ===Letter=== {{letter|oty}} # Tamil-Brahmi letter ṟa. tdr62h6mu62hef188mp53wnygbnxw61 231338 231303 2026-04-13T15:22:05Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231338 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{head|mul|letter|sc=Brah|tr=ṟa}} # {{n-g|the [[thirty-sixth]] [[Brahmi]] [[consonant]]}} ==Old Tamil== === උච්චාරණය === * {{IPA|oty|/rɐ/}} === අකුර === {{letter|oty}} # Tamil-Brahmi letter ṟa. is6sdn1ag4on5pfq1r8ovc1m5aun0vg 0 142023 231304 2025-12-30T09:03:37Z en>WingerBot 0 replace trivial {{head}}-wrapper letter templates with calls to {{letter|LANG}} (manually assisted) 231304 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{head|mul|letter|sc=Brah|tr=ṉa}} # {{n-g|the [[thirty-seventh]] [[Brahmi]] [[consonant]]}} ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/nɐ/}} ===Letter=== {{letter|oty}} # Tamil-Brahmi letter ṉa. 286xn9apfnj4envln6iz972nt6ls2b8 231305 231304 2026-04-13T15:15:28Z Lee 19 [[:en:𑀷]] වෙතින් එක් සංශෝධනයක් 231304 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{head|mul|letter|sc=Brah|tr=ṉa}} # {{n-g|the [[thirty-seventh]] [[Brahmi]] [[consonant]]}} ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/nɐ/}} ===Letter=== {{letter|oty}} # Tamil-Brahmi letter ṉa. 286xn9apfnj4envln6iz972nt6ls2b8 231337 231305 2026-04-13T15:21:55Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231337 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{head|mul|letter|sc=Brah|tr=ṉa}} # {{n-g|the [[thirty-seventh]] [[Brahmi]] [[consonant]]}} ==Old Tamil== === උච්චාරණය === * {{IPA|oty|/nɐ/}} === අකුර === {{letter|oty}} # Tamil-Brahmi letter ṉa. ldqih33rabedc3qhoqqjyvnlemu8mmn 0 142024 231306 2025-12-30T09:03:42Z en>WingerBot 0 replace trivial {{head}}-wrapper letter templates with calls to {{letter|LANG}} (manually assisted) 231306 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ā}} # The Brahmi diacritic for the vowel {{l|mul|𑀆|sc=Brah|tr=ā}}. ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/a/|/aː/}} ===Letter=== {{letter|oty}} # There are 2 orthographies for Tamil-Brahmi; in the first one, this vowel diacritic represents both [[𑀅]] and [[𑀆]], consonants with unmarked vowels are vowelless plain consonants. In the second one, this vowel diacritic represents long [[𑀆]], consonants with unmarked vowels are vowelless plain consonants or have the inherent short a.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> ===References=== <references/> ==Old Telugu== ===Pronunciation=== * {{IPA|dra-ote|/a/}} ===Letter=== {{head|dra-ote|letter}} # In Bhattiprolu Brahmi, this vowel diacritic is used for the short a [[𑀅]] and [[𑀹]] is used for the long ā [[𑀆]]. Consonants with unmarked vowels are vowelless plain consonants.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> ===References=== <references/> 3wm538isrfqshbq2tmxs2o2enzi97dw 231307 231306 2026-04-13T15:15:43Z Lee 19 [[:en:𑀸]] වෙතින් එක් සංශෝධනයක් 231306 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ā}} # The Brahmi diacritic for the vowel {{l|mul|𑀆|sc=Brah|tr=ā}}. ==Old Tamil== ===Pronunciation=== * {{IPA|oty|/a/|/aː/}} ===Letter=== {{letter|oty}} # There are 2 orthographies for Tamil-Brahmi; in the first one, this vowel diacritic represents both [[𑀅]] and [[𑀆]], consonants with unmarked vowels are vowelless plain consonants. In the second one, this vowel diacritic represents long [[𑀆]], consonants with unmarked vowels are vowelless plain consonants or have the inherent short a.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> ===References=== <references/> ==Old Telugu== ===Pronunciation=== * {{IPA|dra-ote|/a/}} ===Letter=== {{head|dra-ote|letter}} # In Bhattiprolu Brahmi, this vowel diacritic is used for the short a [[𑀅]] and [[𑀹]] is used for the long ā [[𑀆]]. Consonants with unmarked vowels are vowelless plain consonants.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> ===References=== <references/> 3wm538isrfqshbq2tmxs2o2enzi97dw 231336 231307 2026-04-13T15:21:45Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231336 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|ā}} # The Brahmi diacritic for the vowel {{l|mul|𑀆|sc=Brah|tr=ā}}. ==Old Tamil== === උච්චාරණය === * {{IPA|oty|/a/|/aː/}} === අකුර === {{letter|oty}} # There are 2 orthographies for Tamil-Brahmi; in the first one, this vowel diacritic represents both [[𑀅]] and [[𑀆]], consonants with unmarked vowels are vowelless plain consonants. In the second one, this vowel diacritic represents long [[𑀆]], consonants with unmarked vowels are vowelless plain consonants or have the inherent short a.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> === මූලාශ්‍ර === <references/> ==Old Telugu== === උච්චාරණය === * {{IPA|dra-ote|/a/}} === අකුර === {{head|dra-ote|letter}} # In Bhattiprolu Brahmi, this vowel diacritic is used for the short a [[𑀅]] and [[𑀹]] is used for the long ā [[𑀆]]. Consonants with unmarked vowels are vowelless plain consonants.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> === මූලාශ්‍ර === <references/> sottl6hb9l079j8at4m5wufhyepghjt 0 142025 231308 2025-12-30T09:09:45Z en>WingerBot 0 replace trivial {{head}}-wrapper letter templates with calls to {{letter|LANG}} (manually assisted) 231308 wikitext text/x-wiki {{character info}} ==Telugu== ===Pronunciation=== * {{IPA|te|/aː/}} ===Letter=== {{letter|te}} # in Bhattiprolu Brahmi, this vowel diacritic is used for the long ā [[𑀆]] and [[𑀸]] is used for the short a [[𑀅]]. Consonants with unmarked vowels are vowelless plain consonants.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> ===References=== {{reflist}} 72ub6l700qpw0rnqlerv7lxb2zw79pd 231309 231308 2026-04-13T15:15:59Z Lee 19 [[:en:𑀹]] වෙතින් එක් සංශෝධනයක් 231308 wikitext text/x-wiki {{character info}} ==Telugu== ===Pronunciation=== * {{IPA|te|/aː/}} ===Letter=== {{letter|te}} # in Bhattiprolu Brahmi, this vowel diacritic is used for the long ā [[𑀆]] and [[𑀸]] is used for the short a [[𑀅]]. Consonants with unmarked vowels are vowelless plain consonants.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> ===References=== {{reflist}} 72ub6l700qpw0rnqlerv7lxb2zw79pd 231335 231309 2026-04-13T15:21:35Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231335 wikitext text/x-wiki {{character info}} == තෙලිඟු == === උච්චාරණය === * {{IPA|te|/aː/}} === අකුර === {{letter|te}} # in Bhattiprolu Brahmi, this vowel diacritic is used for the long ā [[𑀆]] and [[𑀸]] is used for the short a [[𑀅]]. Consonants with unmarked vowels are vowelless plain consonants.<ref>https://www.unicode.org/L2/L2007/07342-brahmi.pdf</ref> === මූලාශ්‍ර === {{reflist}} 3ei5ji3mqffq3yw26xaqkv634q05tbm 0 142026 231310 2022-06-23T15:30:38Z en>AleksiB 1945 0 Created page with "{{character info}} ==Translingual== ===Letter=== {{mul-Brah|i}} # The Brahmi diacritic for the vowel {{l|mul|𑀇|sc=Brah|tr=i}}." 231310 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|i}} # The Brahmi diacritic for the vowel {{l|mul|𑀇|sc=Brah|tr=i}}. d4we4n4oqo45ve0l0j7pkupjl4vejx0 231311 231310 2026-04-13T15:16:13Z Lee 19 [[:en:𑀺]] වෙතින් එක් සංශෝධනයක් 231310 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|i}} # The Brahmi diacritic for the vowel {{l|mul|𑀇|sc=Brah|tr=i}}. d4we4n4oqo45ve0l0j7pkupjl4vejx0 231334 231311 2026-04-13T15:21:25Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231334 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|i}} # The Brahmi diacritic for the vowel {{l|mul|𑀇|sc=Brah|tr=i}}. joob6cuj55xkdfdtmeywks8sg3to6sz 0 142027 231312 2022-06-23T15:31:04Z en>AleksiB 1945 0 Created page with "{{character info}} ==Translingual== ===Letter=== {{mul-Brah|ī}} # The Brahmi diacritic for the vowel {{l|mul|𑀈|sc=Brah|tr=ī}}." 231312 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ī}} # The Brahmi diacritic for the vowel {{l|mul|𑀈|sc=Brah|tr=ī}}. tsie3fsfuyw4x5u2ht434vkj2j3ywxy 231313 231312 2026-04-13T15:16:26Z Lee 19 [[:en:𑀻]] වෙතින් එක් සංශෝධනයක් 231312 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ī}} # The Brahmi diacritic for the vowel {{l|mul|𑀈|sc=Brah|tr=ī}}. tsie3fsfuyw4x5u2ht434vkj2j3ywxy 231333 231313 2026-04-13T15:21:15Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231333 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|ī}} # The Brahmi diacritic for the vowel {{l|mul|𑀈|sc=Brah|tr=ī}}. jmh1yx36tfsuqbktzw49ndto9nkox9p 0 142028 231314 2022-06-23T15:31:27Z en>AleksiB 1945 0 Created page with "{{character info}} ==Translingual== ===Letter=== {{mul-Brah|u}} # The Brahmi diacritic for the vowel {{l|mul|𑀉|sc=Brah|tr=u}}." 231314 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|u}} # The Brahmi diacritic for the vowel {{l|mul|𑀉|sc=Brah|tr=u}}. hxswvo3lmlho8ss2958o2nun59bjepx 231315 231314 2026-04-13T15:16:42Z Lee 19 [[:en:𑀼]] වෙතින් එක් සංශෝධනයක් 231314 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|u}} # The Brahmi diacritic for the vowel {{l|mul|𑀉|sc=Brah|tr=u}}. hxswvo3lmlho8ss2958o2nun59bjepx 231332 231315 2026-04-13T15:21:05Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231332 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|u}} # The Brahmi diacritic for the vowel {{l|mul|𑀉|sc=Brah|tr=u}}. bpbg3hlsqfy681iqboqthylna79ncvw 0 142029 231316 2022-06-23T15:31:53Z en>AleksiB 1945 0 Created page with "{{character info}} ==Translingual== ===Letter=== {{mul-Brah|ū}} # The Brahmi diacritic for the vowel {{l|mul|𑀊|sc=Brah|tr=ū}}." 231316 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ū}} # The Brahmi diacritic for the vowel {{l|mul|𑀊|sc=Brah|tr=ū}}. pf4q7ekb4i5xlc824xuu3lxer29jhrc 231317 231316 2026-04-13T15:17:01Z Lee 19 [[:en:𑀽]] වෙතින් එක් සංශෝධනයක් 231316 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ū}} # The Brahmi diacritic for the vowel {{l|mul|𑀊|sc=Brah|tr=ū}}. pf4q7ekb4i5xlc824xuu3lxer29jhrc 231331 231317 2026-04-13T15:20:55Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231331 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|ū}} # The Brahmi diacritic for the vowel {{l|mul|𑀊|sc=Brah|tr=ū}}. 7wn9s5uj7mfw5hdyklux1yi9v84xp7u 0 142030 231318 2022-06-23T15:32:48Z en>AleksiB 1945 0 Created page with "{{character info}} ==Translingual== ===Letter=== {{mul-Brah|ṛ}} # The Brahmi diacritic for the vowel {{l|mul|𑀋|sc=Brah|tr=ṛ}}." 231318 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ṛ}} # The Brahmi diacritic for the vowel {{l|mul|𑀋|sc=Brah|tr=ṛ}}. 2xgzskaf6fbidu5dludwteqg09ycvdb 231319 231318 2026-04-13T15:17:18Z Lee 19 [[:en:𑀾]] වෙතින් එක් සංශෝධනයක් 231318 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ṛ}} # The Brahmi diacritic for the vowel {{l|mul|𑀋|sc=Brah|tr=ṛ}}. 2xgzskaf6fbidu5dludwteqg09ycvdb 231330 231319 2026-04-13T15:20:45Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231330 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|ṛ}} # The Brahmi diacritic for the vowel {{l|mul|𑀋|sc=Brah|tr=ṛ}}. hew9nhsp09tp8khd56373064frwxnia 0 142031 231320 2022-06-23T15:33:11Z en>AleksiB 1945 0 Created page with "{{character info}} ==Translingual== ===Letter=== {{mul-Brah|ṝ}} # The Brahmi diacritic for the vowel {{l|mul|𑀌|sc=Brah|tr=ṝ}}." 231320 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ṝ}} # The Brahmi diacritic for the vowel {{l|mul|𑀌|sc=Brah|tr=ṝ}}. cjj5xc0ybgh16hbarxwzmj23fsnk5ab 231321 231320 2026-04-13T15:17:40Z Lee 19 [[:en:𑀿]] වෙතින් එක් සංශෝධනයක් 231320 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ṝ}} # The Brahmi diacritic for the vowel {{l|mul|𑀌|sc=Brah|tr=ṝ}}. cjj5xc0ybgh16hbarxwzmj23fsnk5ab 231329 231321 2026-04-13T15:20:35Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231329 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|ṝ}} # The Brahmi diacritic for the vowel {{l|mul|𑀌|sc=Brah|tr=ṝ}}. im9ju0jw8gz8ykf7flrwxw413ib3vcw 0 142032 231322 2022-06-23T15:33:34Z en>AleksiB 1945 0 Created page with "{{character info}} ==Translingual== ===Letter=== {{mul-Brah|ḷ}} # The Brahmi diacritic for the vowel {{l|mul|𑀍|sc=Brah|tr=ḷ}}." 231322 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ḷ}} # The Brahmi diacritic for the vowel {{l|mul|𑀍|sc=Brah|tr=ḷ}}. kjp44puqlvnklywulbhfoemb6owrps3 231323 231322 2026-04-13T15:17:56Z Lee 19 [[:en:𑁀]] වෙතින් එක් සංශෝධනයක් 231322 wikitext text/x-wiki {{character info}} ==Translingual== ===Letter=== {{mul-Brah|ḷ}} # The Brahmi diacritic for the vowel {{l|mul|𑀍|sc=Brah|tr=ḷ}}. kjp44puqlvnklywulbhfoemb6owrps3 231328 231323 2026-04-13T15:20:25Z Pinthura 2424 යොමු තොරතුරු පරිවර්තනය 231328 wikitext text/x-wiki {{character info}} == සර්ව භාෂාමය == === අකුර === {{mul-Brah|ḷ}} # The Brahmi diacritic for the vowel {{l|mul|𑀍|sc=Brah|tr=ḷ}}. bbfw742oog9bbok7djxd9zqypguddzm 10 142033 231324 2022-06-23T15:29:38Z en>AleksiB 1945 0 Created page with "{{head|mul|symbol|sc=Brah}}<!-- -->{{#if:{{{1|}}}|&#32;({{{1}}})}}<!-- -->{{#if:{{NAMESPACE}}||[[Category:Brahmi script characters]]}}<!-- --><noinclude>{{documentation}}</noinclude>" 231324 wikitext text/x-wiki {{head|mul|symbol|sc=Brah}}<!-- -->{{#if:{{{1|}}}|&#32;({{{1}}})}}<!-- -->{{#if:{{NAMESPACE}}||[[Category:Brahmi script characters]]}}<!-- --><noinclude>{{documentation}}</noinclude> risadl3zp0sf9fr3ufxhm64aowv0zg2 231325 231324 2026-04-13T15:19:17Z Lee 19 [[:en:Template:mul-Brah]] වෙතින් එක් සංශෝධනයක් 231324 wikitext text/x-wiki {{head|mul|symbol|sc=Brah}}<!-- -->{{#if:{{{1|}}}|&#32;({{{1}}})}}<!-- -->{{#if:{{NAMESPACE}}||[[Category:Brahmi script characters]]}}<!-- --><noinclude>{{documentation}}</noinclude> risadl3zp0sf9fr3ufxhm64aowv0zg2 10 142034 231326 2025-07-06T05:29:52Z en>WingerBot 0 use {{hwcat}} instead of manual headword-line categorization, misc cleanups (manually assisted) 231326 wikitext text/x-wiki {{documentation subpage}} {{documentation needed}}<!-- Replace this with a short description of the purpose of the template, and how to use it. --> <includeonly> {{hwcat}} [[Category:Brahmi script templates]] </includeonly> l7f2gj2xjk4oi092fpdsuiz3xmnob4o 231327 231326 2026-04-13T15:19:42Z Lee 19 [[:en:Template:mul-Brah/documentation]] වෙතින් එක් සංශෝධනයක් 231326 wikitext text/x-wiki {{documentation subpage}} {{documentation needed}}<!-- Replace this with a short description of the purpose of the template, and how to use it. --> <includeonly> {{hwcat}} [[Category:Brahmi script templates]] </includeonly> l7f2gj2xjk4oi092fpdsuiz3xmnob4o 10 142035 231340 2026-01-09T19:20:06Z en>Surjection 0 Protected "[[Template:letter]]": Highly visible template/module ([Edit=Allow only autopatrollers] (indefinite) [Move=Allow only autopatrollers] (indefinite)) 231340 wikitext text/x-wiki {{#invoke:letter headword|show}}<noinclude>{{documentation}}</noinclude> h8o8stcifm08qgb8pk8txdm4efq7da8 231341 231340 2026-04-13T15:22:30Z Lee 19 [[:en:Template:letter]] වෙතින් එක් සංශෝධනයක් 231340 wikitext text/x-wiki {{#invoke:letter headword|show}}<noinclude>{{documentation}}</noinclude> h8o8stcifm08qgb8pk8txdm4efq7da8 10 142036 231342 2026-01-12T04:25:07Z en>Benwing2 0 put full documentation here instead of in module 231342 wikitext text/x-wiki {{documentation subpage}} This template should be used to generate the headword line for letters in a specified language. '''Most of the time, only the language code needs to be specified.'''" ==Parameters== The following parameters are supported: ;{{para|1|req=1}} : Language code (see {{slink|WT:Languages#Language codes}}) for the language of the letter. ;{{para|type}} : Explicitly specify the case of the letter: {{cd|nocase}} (for letters without case); {{cd|upper}}; {{cd|lower}}; {{cd|allcaps}} (for all-capital-letter variants of digraphs, trigraphs, etc. whose normal uppercase version has only the first character capitalized); or {{cd|mixed}} (for the rare case of a mixture of uppercase and lowercase letters in a digraph, trigraph, etc. that is not the uppercase form). This usually does not need to be given, as it is autodetected; but some lowercase or uppercase characters need it because Unicode does not correctly register the character as having case. ;{{para|upper}} : Explicitly specify the uppercase equivalent(s) of a lowercase, all-caps or mixed-case letter. Cannot be specified for already-uppercase or caseless letters. This usually does not need to be given as it is normally auto-generated by uppercasing the pagename (or the first letter in the case of a digraph, trigraph, etc.). In some cases, however, Unicode does not correctly register a case pair but treats the two letters as caseless; in thiscase, both {{para|type}} and {{para|upper}} must be given. Multiple comma-separated values are allowed, along with qualifier, label, reference, transliteration and gloss inline modifiers. See below. ;{{para|lower}} : Explicitly specify the lowercase equivalent(s) of an uppercase, all-caps or mixed-case letter. Cannot be specified for already-lowercase or caseless letters. This usually does not need to be given as it is normally auto-generated by lowercasing the pagename. The same syntax and considerations apply as for {{para|upper}}. ;{{para|allcaps}} : Explicitly specify the all-caps equivalent(s) of an uppercase, lowercase or mixed-case letter. Cannot be specified for already-all-caps or caseless letters. This usually does not need to be given as it is normally auto-generated by uppercasing (all letters of) the pagename. The same syntax and considerations apply as for {{para|upper}}. ;{{para|mixed}} : Explicitly specify the mixed-case equivalent(s) of an uppercase, lowercase or all-caps letter. Cannot be specified for already mixed-case or caseless letters. There is no default for this parameter, so it will only appear when explicitly given. The syntax is the same as for {{para|upper}}. ;{{para|pl}} : Explicitly specify the plural(s) of the letter. A value of {{cd|+}} explicitly requests the default value(s) (which are available only for some languages; otherwise, an error will occur). The syntax is the same as for {{para|upper}}. ;{{para|nopl|1}} : Specify that the letter does not have a plural form. ;{{para|g}} : Explicitly specify the gender(s) of the letter. Multiple comma-separated values are allowed, along with qualifier, label and reference inline modifiers. See [[Module:gender and number]] for more information, including the allowed values. ;{{para|nog|1}} : In case the language specifies a default gender, cancel out the gender(s) without supplying any replacement. No gender will be shown. ;{{para|sc}} : Specify an explicit value for the script of the letter. Rarely necessary as the script is autodetected. ;{{para|id}} : Specify a sense ID (see {{tl|senseid}}) for linking to this particular sense/part of speech of the term using the {{para|id}} parameter of {{tl|l}}, {{tl|m}} and the like. Useful when the entry also has meanings other than as a letter. ;{{para|tr}}, {{para|tr2}}, ... : Specify transliteration(s) of the letter, for letters not in the Latin script. Not usually necessary, as most languages have automatic transliteration, which is usually correct. ;{{para|pagename}} :Override the pagename, for use on documentation or test pages. ;{{para|sort}} : Sort key. Rarely needs to be specified, as it is normally automatically generated. ;{{para|json|1}} : Output the headword data in JSON form instead of the normal output. For testing purposes. <includeonly> [[Category:Headword-line templates]] </includeonly> h5fea17ktfkfc2dc8r8nerb3bnkr21e 231343 231342 2026-04-13T15:22:50Z Lee 19 [[:en:Template:letter/documentation]] වෙතින් එක් සංශෝධනයක් 231342 wikitext text/x-wiki {{documentation subpage}} This template should be used to generate the headword line for letters in a specified language. '''Most of the time, only the language code needs to be specified.'''" ==Parameters== The following parameters are supported: ;{{para|1|req=1}} : Language code (see {{slink|WT:Languages#Language codes}}) for the language of the letter. ;{{para|type}} : Explicitly specify the case of the letter: {{cd|nocase}} (for letters without case); {{cd|upper}}; {{cd|lower}}; {{cd|allcaps}} (for all-capital-letter variants of digraphs, trigraphs, etc. whose normal uppercase version has only the first character capitalized); or {{cd|mixed}} (for the rare case of a mixture of uppercase and lowercase letters in a digraph, trigraph, etc. that is not the uppercase form). This usually does not need to be given, as it is autodetected; but some lowercase or uppercase characters need it because Unicode does not correctly register the character as having case. ;{{para|upper}} : Explicitly specify the uppercase equivalent(s) of a lowercase, all-caps or mixed-case letter. Cannot be specified for already-uppercase or caseless letters. This usually does not need to be given as it is normally auto-generated by uppercasing the pagename (or the first letter in the case of a digraph, trigraph, etc.). In some cases, however, Unicode does not correctly register a case pair but treats the two letters as caseless; in thiscase, both {{para|type}} and {{para|upper}} must be given. Multiple comma-separated values are allowed, along with qualifier, label, reference, transliteration and gloss inline modifiers. See below. ;{{para|lower}} : Explicitly specify the lowercase equivalent(s) of an uppercase, all-caps or mixed-case letter. Cannot be specified for already-lowercase or caseless letters. This usually does not need to be given as it is normally auto-generated by lowercasing the pagename. The same syntax and considerations apply as for {{para|upper}}. ;{{para|allcaps}} : Explicitly specify the all-caps equivalent(s) of an uppercase, lowercase or mixed-case letter. Cannot be specified for already-all-caps or caseless letters. This usually does not need to be given as it is normally auto-generated by uppercasing (all letters of) the pagename. The same syntax and considerations apply as for {{para|upper}}. ;{{para|mixed}} : Explicitly specify the mixed-case equivalent(s) of an uppercase, lowercase or all-caps letter. Cannot be specified for already mixed-case or caseless letters. There is no default for this parameter, so it will only appear when explicitly given. The syntax is the same as for {{para|upper}}. ;{{para|pl}} : Explicitly specify the plural(s) of the letter. A value of {{cd|+}} explicitly requests the default value(s) (which are available only for some languages; otherwise, an error will occur). The syntax is the same as for {{para|upper}}. ;{{para|nopl|1}} : Specify that the letter does not have a plural form. ;{{para|g}} : Explicitly specify the gender(s) of the letter. Multiple comma-separated values are allowed, along with qualifier, label and reference inline modifiers. See [[Module:gender and number]] for more information, including the allowed values. ;{{para|nog|1}} : In case the language specifies a default gender, cancel out the gender(s) without supplying any replacement. No gender will be shown. ;{{para|sc}} : Specify an explicit value for the script of the letter. Rarely necessary as the script is autodetected. ;{{para|id}} : Specify a sense ID (see {{tl|senseid}}) for linking to this particular sense/part of speech of the term using the {{para|id}} parameter of {{tl|l}}, {{tl|m}} and the like. Useful when the entry also has meanings other than as a letter. ;{{para|tr}}, {{para|tr2}}, ... : Specify transliteration(s) of the letter, for letters not in the Latin script. Not usually necessary, as most languages have automatic transliteration, which is usually correct. ;{{para|pagename}} :Override the pagename, for use on documentation or test pages. ;{{para|sort}} : Sort key. Rarely needs to be specified, as it is normally automatically generated. ;{{para|json|1}} : Output the headword data in JSON form instead of the normal output. For testing purposes. <includeonly> [[Category:Headword-line templates]] </includeonly> h5fea17ktfkfc2dc8r8nerb3bnkr21e 828 142037 231346 2024-03-06T03:58:59Z en>WingerBot 0 remove unnecessary categorization now handled automatically by [[Module:documentation]] and [[Module:module categorization]] (manually assisted) 231346 wikitext text/x-wiki {{#invoke:kv-translit/testcases|run_tests}} cwg62zcshwketikcn1veouncgkgb87n 231347 231346 2026-04-13T17:04:23Z Lee 19 [[:en:Module:kv-translit/testcases/documentation]] වෙතින් එක් සංශෝධනයක් 231346 wikitext text/x-wiki {{#invoke:kv-translit/testcases|run_tests}} cwg62zcshwketikcn1veouncgkgb87n 828 142038 231348 2023-12-05T21:36:17Z en>Bababashqort 0 231348 Scribunto text/plain local tests = require("Module:UnitTests") local kv_translit = require("Module:kv-translit") function tests:check_translit(Cyrl, Latn) self:equals(('<span lang="kv" class="Cyrl mention">[[%s#Komi|%s]]</span>'):format(Cyrl, Cyrl), kv_translit.tr(Cyrl, 'kv', 'Cyrl'), Latn) end function tests:test_translit() local examples = { { "аддзыны", "addźyny" }, { "ассьым", "aśśym" }, { "аттьӧ", "aťťö" }, } self:iterate(examples, "check_translit") end return tests aqlw3f9c2cyq9nuv8qd27ltn1whu2ui 231349 231348 2026-04-13T17:04:37Z Lee 19 [[:en:Module:kv-translit/testcases]] වෙතින් එක් සංශෝධනයක් 231348 Scribunto text/plain local tests = require("Module:UnitTests") local kv_translit = require("Module:kv-translit") function tests:check_translit(Cyrl, Latn) self:equals(('<span lang="kv" class="Cyrl mention">[[%s#Komi|%s]]</span>'):format(Cyrl, Cyrl), kv_translit.tr(Cyrl, 'kv', 'Cyrl'), Latn) end function tests:test_translit() local examples = { { "аддзыны", "addźyny" }, { "ассьым", "aśśym" }, { "аттьӧ", "aťťö" }, } self:iterate(examples, "check_translit") end return tests aqlw3f9c2cyq9nuv8qd27ltn1whu2ui 828 142039 231350 2026-01-22T06:46:09Z en>Benwing2 0 231350 wikitext text/x-wiki {{translit module documentation|kpv}} {{module cat|kpv,koi,urj-kya}} 70z7znqcd9s7jbms0e76tnxfvtpgnbx 231351 231350 2026-04-13T17:04:42Z Lee 19 [[:en:Module:kv-translit/documentation]] වෙතින් එක් සංශෝධනයක් 231350 wikitext text/x-wiki {{translit module documentation|kpv}} {{module cat|kpv,koi,urj-kya}} 70z7znqcd9s7jbms0e76tnxfvtpgnbx 0 142040 231356 2026-04-14T03:24:18Z Lee 19 '== සිංහල == === නිරුක්තිය === {{rfe|si}} === නාම පදය === {{si-noun}} # {{singular of|si|මැතිවරණමය පර්ෂද}} <!-- ==== පරිවර්තන ==== {{trans-top|පරිවර්තන}} * ඉංග්‍රීසි: {{t|en|<<ඉංග්‍රීසි වචනය>>}} {{trans-bottom}} === අමතර අවධානයට === * {{l|si|<<ආශ...' යොදමින් නව පිටුවක් තනන ලදි 231356 wikitext text/x-wiki == සිංහල == === නිරුක්තිය === {{rfe|si}} === නාම පදය === {{si-noun}} # {{singular of|si|මැතිවරණමය පර්ෂද}} <!-- ==== පරිවර්තන ==== {{trans-top|පරිවර්තන}} * ඉංග්‍රීසි: {{t|en|<<ඉංග්‍රීසි වචනය>>}} {{trans-bottom}} === අමතර අවධානයට === * {{l|si|<<ආශ්‍රිත පවතින වෙනත් වචන>>}} --> jicqlh9rd90bq6z9q8rjzd0by9ngis1 828 142041 231363 2026-03-05T07:12:03Z en>Mellohi! 0 Undid revision [[Special:Diff/89762529|89762529]] by [[Special:Contributions/Mellohi!|Mellohi!]] ([[User talk:Mellohi!|talk]]) try to jolt the update button to show up 231363 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "Proto-Khasian", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "aav-nic", "Latn", type = "reconstructed", } m["aav-pkl-pro"] = { "Proto-Pnar-Khasi-Lyngngam", 116773259, "aav-pkl", "Latn", type = "reconstructed", } m["aav-pro"] = { -- mkh-pro will merge into this "Proto-Austroasiatic", 116773186, "aav", "Latn", type = "reconstructed", } m["afa-pro"] = { "Proto-Afroasiatic", 269125, "afa", "Latn", type = "reconstructed", } m["alg-aga"] = { "Agawam", nil, "alg-eas", "Latn", } m["alg-pro"] = { "Proto-Algonquian", 7251834, "alg", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["alv-ama"] = { "Amasi", 4740400, "nic-grs", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}, } m["alv-bgu"] = { "Bainouk Gubeeher", 17002646, "alv-bny", "Latn", } m["alv-bua-pro"] = { "Proto-Bua", 116773723, "alv-bua", "Latn", type = "reconstructed", } m["alv-cng-pro"] = { "Proto-Cangin", 116773726, "alv-cng", "Latn", type = "reconstructed", } m["alv-edo-pro"] = { "Proto-Edoid", 116773206, "alv-edo", "Latn", type = "reconstructed", } m["alv-fli-pro"] = { "Proto-Fali", 116773754, "alv-fli", "Latn", type = "reconstructed", } m["alv-gbe-pro"] = { "Proto-Gbe", 116773208, "alv-gbe", "Latn", type = "reconstructed", } m["alv-gng-pro"] = { "Proto-Guang", 116773757, "alv-gng", "Latn", type = "reconstructed", } m["alv-gtm-pro"] = { "Proto-Central Togo", 116773732, "alv-gtm", "Latn", type = "reconstructed", } m["alv-gwa"] = { "Gwara", 16945580, "nic-pla", "Latn", } m["alv-hei-pro"] = { "Proto-Heiban", 116773760, "alv-hei", "Latn", type = "reconstructed", } m["alv-ido-pro"] = { "Proto-Idomoid", 116773764, "alv-ido", "Latn", type = "reconstructed", } m["alv-igb-pro"] = { "Proto-Igboid", 116773765, "alv-igb", "Latn", type = "reconstructed", } m["alv-kwa-pro"] = { "Proto-Kwa", 116773780, "alv-kwa", "Latn", type = "reconstructed", } m["alv-mum-pro"] = { "Proto-Mumuye", 116773791, "alv-mum", "Latn", type = "reconstructed", } m["alv-nup-pro"] = { "Proto-Nupoid", 116773795, "alv-nup", "Latn", type = "reconstructed", } m["alv-pro"] = { "Proto-Atlantic-Congo", 116732838, "alv", "Latn", type = "reconstructed", } m["alv-edk-pro"] = { "Proto-Edekiri", nil, "alv-edk", "Latn", type = "reconstructed", } m["alv-yor-pro"] = { "Proto-Yoruba", nil, "alv-yor", "Latn", type = "reconstructed", } m["alv-yrd-pro"] = { "Proto-Yoruboid", 116773824, "alv-yrd", "Latn", type = "reconstructed", } m["alv-von-pro"] = { "Proto-Volta-Niger", 116773820, "alv-von", "Latn", type = "reconstructed", } m["apa-pro"] = { "Proto-Apachean", 116773135, "apa", "Latn", type = "reconstructed", } m["aql-pro"] = { "Proto-Algic", 18389588, "aql", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["art-adu"] = { "Adûni", 1232159, "art", "Latn", type = "appendix-constructed", } m["art-bel"] = { "Belter Creole", 108055510, "art", "Latn", type = "appendix-constructed", sort_key = { remove_diacritics = c.acute, from = {"ɒ"}, to = {"a"}, }, } m["art-blk"] = { "Bolak", 2909283, "art", "Latn", type = "appendix-constructed", } m["art-bsp"] = { "Black Speech", 686210, "art", "Latn, Teng", type = "appendix-constructed", } m["art-com"] = { "Communicationssprache", 35227, "art", "Latn", type = "appendix-constructed", } m["art-dtk"] = { "Dothraki", 2914733, "art", "Latn", type = "appendix-constructed", } m["art-elo"] = { "Eloi", nil, "art", "Latn", type = "appendix-constructed", } m["art-gld"] = { "Goa'uld", 19823, "art", "Latn, Egyp, Mero", type = "appendix-constructed", } m["art-lap"] = { "Lapine", 6488195, "art", "Latn", type = "appendix-constructed", } m["art-man"] = { "Mandalorian", 54289, "art", "Latn", type = "appendix-constructed", } m["art-mun"] = { "Mundolinco", 851355, "art", "Latn", type = "appendix-constructed", } m["art-nav"] = { "Naʼvi", 316939, "art", "Latn", type = "appendix-constructed", } m["art-vlh"] = { "High Valyrian", 64483808, "art", "Latn", type = "appendix-constructed", } m["ath-nic"] = { "Nicola", 20609, "ath-nor", "Latn", } m["ath-pro"] = { "Proto-Athabaskan", 104841722, "ath", "Latn", type = "reconstructed", } m["auf-pro"] = { "Proto-Arawa", 116773706, "auf", "Latn", type = "reconstructed", } m["aus-alu"] = { "Alungul", 16827670, "aus-pmn", "Latn", } m["aus-and"] = { "Andjingith", 4754509, "aus-pmn", "Latn", } m["aus-ang"] = { "Angkula", 16828520, "aus-pmn", "Latn", } m["aus-arn-pro"] = { "Proto-Arnhem", 116773720, "aus-arn", "Latn", type = "reconstructed", } m["aus-bra"] = { "Barranbinya", 4863220, "aus-pmn", "Latn", } m["aus-brm"] = { "Barunggam", 4865914, "aus-pmn", "Latn", } m["aus-cww-pro"] = { "Proto-Central New South Wales", 116773199, "aus-cww", "Latn", type = "reconstructed", } m["aus-dal-pro"] = { "Proto-Daly", 116773743, "aus-dal", "Latn", type = "reconstructed", } m["aus-guw"] = { "Guwar", 6652138, "aus-pam", "Latn", } m["aus-lsw"] = { "Little Swanport", 6652138, "qfa-unc", "Latn", } m["aus-mbi"] = { "Mbiywom", 6799701, "aus-pmn", "Latn", } m["aus-ngk"] = { "Ngkoth", 7022405, "aus-pmn", "Latn", } m["aus-nyu-pro"] = { "Proto-Nyulnyulan", 116773797, "aus-nyu", "Latn", type = "reconstructed", } m["aus-pam-pro"] = { "Proto-Pama-Nyungan", 33942, "aus-pam", "Latn", type = "reconstructed", } m["aus-tul"] = { "Tulua", 16938541, "aus-pam", "Latn", } m["aus-uwi"] = { "Uwinymil", 7903995, "aus-arn", "Latn", } m["aus-wdj-pro"] = { "Proto-Iwaidjan", 116773767, "aus-wdj", "Latn", type = "reconstructed", } m["aus-won"] = { "Wong-gie", nil, "aus-pam", "Latn", } m["aus-wul"] = { "Wulguru", 8039196, "aus-dyb", "Latn", } m["aus-ynk"] = { -- contrast nny "Yangkaal", 3913770, "aus-tnk", "Latn", } m["awd-amc-pro"] = { "Proto-Amuesha-Chamicuro", nil, "awd", "Latn", type = "reconstructed", } m["awd-kmp-pro"] = { "Proto-Kampa", nil, "awd", "Latn", type = "reconstructed", } m["awd-prw-pro"] = { "Proto-Paresi-Waura", nil, "awd", "Latn", type = "reconstructed", } m["awd-ama"] = { "Amarizana", 16827787, "awd", "Latn", } m["awd-ana"] = { "Anauyá", 16828252, "awd", "Latn", } m["awd-apo"] = { "Apolista", 16916645, "awd", "Latn", } m["awd-cab"] = { "Cabre", 16850160, "awd", "Latn", } m["awd-gnu"] = { "Guinau", 3504087, "awd", "Latn", } m["awd-kar"] = { "Cariay", 16920253, "awd", "Latn", } m["awd-kaw"] = { "Kawishana", 6379993, "awd-nwk", "Latn", } m["awd-kus"] = { "Kustenau", 5196293, "awd", "Latn", } m["awd-man"] = { "Manao", 6746920, "awd", "Latn", } m["awd-mar"] = { "Marawan", 6755108, "awd", "Latn", } m["awd-mpr"] = { "Maipure", 6736872, "awd", "Latn", } m["awd-mrt"] = { "Mariaté", 16910017, "awd-nwk", "Latn", } m["awd-nwk-pro"] = { "Proto-Nawiki", 116773234, "awd-nwk", "Latn", type = "reconstructed", } m["awd-pai"] = { "Paikoneka", 128807835, "awd", "Latn", } m["awd-pas"] = { "Pasé", 7143168, "awd-nwk", "Latn", } m["awd-pro"] = { "Proto-Arawak", 97573478, "awd", "Latn", type = "reconstructed", } m["awd-she"] = { "Shebayo", 7492248, "awd", "Latn", } m["awd-taa-pro"] = { "Proto-Ta-Arawak", 116773282, "awd-taa", "Latn", type = "reconstructed", } m["awd-wai"] = { "Wainumá", 16910017, "awd-nwk", "Latn", } m["awd-yum"] = { "Yumana", 8061062, "awd-nwk", "Latn", } m["azc-caz"] = { "Cazcan", 5055514, "azc", "Latn", } m["azc-cup-pro"] = { "Proto-Cupan", 116773738, "azc-cup", "Latn", type = "reconstructed", } m["azc-ktn"] = { "Kitanemuk", 3197558, "azc-tak", "Latn", } m["azc-nah-pro"] = { "Proto-Nahuan", 7251860, "azc-nah", "Latn", type = "reconstructed", } m["azc-num-pro"] = { "Proto-Numic", 116773247, "azc-num", "Latn", type = "reconstructed", } m["azc-pro"] = { "Proto-Uto-Aztecan", 96400333, "azc", "Latn", type = "reconstructed", } m["azc-tak-pro"] = { "Proto-Takic", 116773283, "azc-tak", "Latn", type = "reconstructed", } m["azc-tat"] = { "Tataviam", 743736, "azc", "Latn", } m["ber-pro"] = { "Proto-Berber", 2855698, "ber", "Latn", type = "reconstructed", } m["ber-fog"] = { "Fogaha", 107610173, "ber", "Latn", } m["ber-zuw"] = { "Zuwara", 4117169, "ber", "Latn", } m["bnt-bal"] = { "Balong", 93935237, "bnt-bbo", "Latn", } m["bnt-bon"] = { "Boma Nkuu", nil, "bnt", "Latn", } m["bnt-boy"] = { "Boma Yumu", nil, "bnt", "Latn", } m["bnt-bwa"] = { "Bwala", 128810345, "bnt-tek", "Latn", } m["bnt-cmw"] = { "Chimwiini", 4958328, "bnt-swh", "Latn", } m["bnt-ind"] = { "Indanga", 51412803, "bnt", "Latn", } m["bnt-lal"] = { "Lala (South Africa)", 6480154, "bnt-ngu", "Latn", } m["bnt-mpi"] = { "Mpiin", 93937013, "bnt-bdz", "Latn", } m["bnt-mpu"] = { "Mpuono", -- not to be confused with Mbuun zmp 36056, "bnt", "Latn", } m["bnt-ngu-pro"] = { "Proto-Nguni", 961559, "bnt-ngu", "Latn", type = "reconstructed", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron}, } m["bnt-phu"] = { "Phuthi", 33796, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, } m["bnt-pro"] = { "Proto-Bantu", 3408025, "bnt", "Latn", type = "reconstructed", sort_key = "bnt-pro-sortkey", } m["bnt-sab-pro"] = { "Proto-Sabaki", nil, -- Q2209395 is the code for the Sabaki family "bnt-sab", "Latn", type = "reconstructed", } m["bnt-sbo"] = { "South Boma", nil, "bnt", "Latn", } m["bnt-sts-pro"] = { "Proto-Sotho-Tswana", 116773278, "bnt-sts", "Latn", type = "reconstructed", } m["btk-pro"] = { "Proto-Batak", 116773191, "btk", "Latn", type = "reconstructed", } m["cau-abz-pro"] = { "Proto-Abkhaz-Abaza", 7251831, "cau-abz", "Latn", type = "reconstructed", } m["cau-and-pro"] = { "Proto-Andian", nil, "cau-and", "Latn", type = "reconstructed", } m["cau-ava-pro"] = { "Proto-Avaro-Andian", 116773187, "cau-ava", "Latn", type = "reconstructed", } m["cau-cir-pro"] = { "Proto-Circassian", 7251838, "cau-cir", "Latn", type = "reconstructed", } m["cau-drg-pro"] = { "Proto-Dargwa", 116773205, "cau-drg", "Latn", type = "reconstructed", } m["cau-lzg-pro"] = { "Proto-Lezghian", 116773223, "cau-lzg", "Latn", type = "reconstructed", } m["cau-nec-pro"] = { "Proto-Northeast Caucasian", 116773244, "cau-nec", "Latn", type = "reconstructed", } m["cau-nkh-pro"] = { "Proto-Nakh", 108032840, "cau-nkh", "Latn", type = "reconstructed", } m["cau-nwc-pro"] = { "Proto-Northwest Caucasian", 7251861, "cau-nwc", "Latn", type = "reconstructed", } m["cau-tsz-pro"] = { "Proto-Tsezian", 116773287, "cau-tsz", "Latn", type = "reconstructed", } m["cba-ata"] = { "Atanques", 4812783, "cba", "Latn", } m["cba-cat"] = { "Catío Chibcha", 7083619, "cba", "Latn", } m["cba-dor"] = { "Dorasque", 5297532, "cba", "Latn", } m["cba-dui"] = { "Duit", 3041061, "cba", "Latn", } m["cba-hue"] = { "Huetar", 35514, "cba", "Latn", } m["cba-nut"] = { "Nutabe", 7070405, "cba", "Latn", } m["cba-pro"] = { "Proto-Chibchan", 116773203, "cba", "Latn", type = "reconstructed", } m["ccs-pro"] = { "Proto-Kartvelian", 2608203, "ccs", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["ccs-gzn-pro"] = { "Proto-Georgian-Zan", 23808119, "ccs-gzn", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["cdc-cbm-pro"] = { "Proto-Central Chadic", 116773197, "cdc-cbm", "Latn", type = "reconstructed", } m["cdc-mas-pro"] = { "Proto-Masa", 116773789, "cdc-mas", "Latn", type = "reconstructed", } m["cdc-pro"] = { "Proto-Chadic", 116773201, "cdc", "Latn", type = "reconstructed", } m["cdd-pro"] = { "Proto-Caddoan", 116773725, "cdd", "Latn", type = "reconstructed", } m["cel-bry-pro"] = { "Proto-Brythonic", 1248800, "cel-bry", "Latn, Polyt", sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-gal"] = { "Gallaecian", 3094789, "cel-his", } m["cel-gau"] = { "Gaulish", 29977, "cel", "Latn, Polyt, Ital", strip_diacritics = { Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer}, }, sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-pro"] = { "Proto-Celtic", 653649, "cel", "Latn", type = "reconstructed", sort_key = "cel-pro-sortkey", } m["chi-pro"] = { "Proto-Chimakuan", 116773734, "chi", "Latn", type = "reconstructed", } m["chm-pro"] = { "Proto-Mari", 116773788, "chm", "Latn", type = "reconstructed", } m["cmc-pro"] = { "Proto-Chamic", 114793834, "cmc", "Latn", type = "reconstructed", } m["crp-bip"] = { "Basque-Icelandic Pidgin", 810378, "crp", "Latn", ancestors = "eu", } m["crp-gep"] = { "West Greenlandic Pidgin", 17036301, "crp", "Latn", ancestors = "kl", } m["crp-kia"] = { "Kiautschou German Pidgin", 108314615, "crp", "Latn", ancestors = "de", } m["crp-mar"] = { "Maroon Spirit Language", 1093206, "crp", "Latn", ancestors = "en", } m["crp-mpp"] = { "Macau Pidgin Portuguese", 128804537, "crp", "Hant, Latn", ancestors = "pt", sort_key = {Hant = "Hani-sortkey"}, } m["crp-rsn"] = { "Russenorsk", 505125, "crp", "Cyrl, Latn", ancestors = "nn, ru", translit = {Cyrl = "ru-translit"}, } m["crp-spp"] = { "Samoan Plantation Pidgin", 7409948, "crp", "Latn", ancestors = "en", } m["crp-slb"] = { "Solombala English", 7558525, "crp", "Cyrl, Latn", ancestors = "en, ru", translit = {Cyrl = "ru-translit"}, } m["crp-tpr"] = { "Taimyr Pidgin Russian", 16930506, "crp", "Cyrl", ancestors = "ru", translit = "ru-translit", } m["csu-bba-pro"] = { "Proto-Bongo-Bagirmi", 116773722, "csu-bba", "Latn", type = "reconstructed", } m["csu-maa-pro"] = { "Proto-Mangbetu", 116773786, "csu-maa", "Latn", type = "reconstructed", } m["csu-pro"] = { "Proto-Central Sudanic", 116773730, "csu", "Latn", type = "reconstructed", } m["csu-sar-pro"] = { "Proto-Sara", 116773809, "csu-sar", "Latn", type = "reconstructed", } m["cus-ash"] = { "Ashraaf", 4805855, "cus-som", "Latn", } m["cus-hec-pro"] = { "Proto-Highland East Cushitic", 116773761, "cus-hec", "Latn", type = "reconstructed", } m["cus-som-pro"] = { "Proto-Somaloid", nil, "cus-som", "Latn", type = "reconstructed", } m["cus-sou-pro"] = { "Proto-South Cushitic", 126081567, "cus-sou", "Latn", type = "reconstructed", } m["cus-pro"] = { "Proto-Cushitic", 116773204, "cus", "Latn", type = "reconstructed", } m["dmn-dam"] = { "Dama (Sierra Leone)", 19601574, "dmn", "Latn", } m["dra-bry"] = { "Beary", 1089116, "qfa-mix", "Mlym, Knda", ancestors = "ml, tcy", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["dra-cen-pro"] = { "Proto-Central Dravidian", nil, "dra-cen", "Latn", type = "reconstructed", } m["dra-mkn"] = { "Middle Kannada", 128810572, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-nor-pro"] = { "Proto-North Dravidian", 124433593, "dra-nor", "Latn", type = "reconstructed", } m["dra-okn"] = { "Old Kannada", 15723156, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-ote"] = { "Old Telugu", 126720868, "dra-tel", "Telu", translit = "te-translit", } m["dra-pro"] = { "Proto-Dravidian", 1702853, "dra", "Latn", type = "reconstructed", } m["dra-sdo-pro"] = { "Proto-South Dravidian I", 104847952, -- Wikipedia's "Proto-South Dravidian" is Proto-South Dravidian I in this scheme. "dra-sdo", "Latn", type = "reconstructed", } m["dra-sdt-pro"] = { "Proto-South Dravidian II", 128885257, "dra-sdt", "Latn", type = "reconstructed", } m["dra-sou-pro"] = { "Proto-South Dravidian", 128886121, "dra-sou", "Latn", type = "reconstructed", } m["egx-dem"] = { "Demotic Egyptian", 36765, "egx", "Latn, Egyd, Polyt", sort_key = { Latn = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "e", "ꜥ", "y", "w", "b", "p", "f", "m", "n", "r", "l", "ḥ", "ḫ", "h̭", "ẖ", "h", "š", "s", "q", "k", "g", "ṱ", "ṯ", "t", "ḏ", "%.", "⸗"}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]} }, }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dmn-pro"] = { "Proto-Mande", 116773785, "dmn", "Latn", type = "reconstructed", } m["dmn-mdw-pro"] = { "Proto-Western Mande", 116773822, "dmn-mdw", "Latn", type = "reconstructed", } m["dru-pro"] = { "Proto-Rukai", 116773807, "map", "Latn", type = "reconstructed", } m["ero-gsz"] = { "Geshiza", nil, "ero", "Latn", } m["ero-nya"] = { "Nyagrong Minyag", nil, "ero", "Latn", } m["ero-tau"] = { "Stau", nil, "ero", "Latn", } m["esx-esk-pro"] = { "Proto-Eskimo", 7251842, "esx-esk", "Latn", type = "reconstructed", } m["esx-ink"] = { "Inuktun", 1671647, "esx-inu", "Latn", } m["esx-inq"] = { "Inuinnaqtun", 28070, "esx-inu", "Latn", } m["esx-inu-pro"] = { "Proto-Inuit", 60785588, "esx-inu", "Latn", type = "reconstructed", } m["esx-pro"] = { "Proto-Eskimo-Aleut", 7251843, "esx", "Latn", type = "reconstructed", } m["esx-tut"] = { "Tunumiisut", 15665389, "esx-inu", "Latn", } m["euq-pro"] = { "Proto-Basque", 938011, "euq", "Latn", type = "reconstructed", } m["gba-pro"] = { "Proto-Gbaya", nil, "gba", "Latn", type = "reconstructed", } m["gem-pro"] = { "Proto-Germanic", 669623, "gem", "Latn", type = "reconstructed", sort_key = "gem-pro-sortkey", } m["gme-bur"] = { "Burgundian", 47625, "gme", "Latn", } m["gme-cgo"] = { "Crimean Gothic", 36211, "gme", "Latn", } m["gmq-gut"] = { "Gutnish", 1256646, "gmq", "Latn", ancestors = "gmq-ogt", } m["gmq-jmk"] = { "Jamtish", 35512, "gmq-eas", "Latn", } m["gmq-mno"] = { "Middle Norwegian", 3417070, "gmq-wes", "Latn", } m["gmq-oda"] = { "Old Danish", 12330003, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-ogt"] = { "Old Gutnish", 1133488, "gmq", "Latn, Runr", ancestors = "non", } m["gmq-osw"] = { "Old Swedish", 2417210, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-pro"] = { "Proto-Norse", 1671294, "gmq", "Runr", translit = "Runr-translit", } m["gmq-scy"] = { "Scanian", 768017, "gmq-eas", "Latn", } m["gmw-bgh"] = { "Bergish", 329030, "gmw-frk", "Latn", } m["gmw-cfr"] = { "Central Franconian", 572197, "gmw-hgm", "Latn", ancestors = "gmh", wikimedia_codes = "ksh", } m["gmw-ecg"] = { "East Central German", 499344, -- subsumes Q699284, Q152965 "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-fin"] = { "Fingallian", 3072588, "gmw-ian", "Latn", } m["gmw-gts"] = { "Gottscheerish", 533109, "gmw-hgm", "Latn", ancestors = "bar", } m["gmw-jdt"] = { "Jersey Dutch", 1687911, "gmw-frk", "Latn", ancestors = "nl", } m["gmw-msc"] = { "Middle Scots", 3327000, "gmw-ang", "Latn", ancestors = "enm-esc", } m["gmw-pro"] = { "Proto-West Germanic", 78079021, "gmw", "Latn, Runr", -- type = "reconstructed", -- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added sort_key = "gmw-pro-sortkey", } m["gmw-rfr"] = { "Rhine Franconian", 707007, "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-stm"] = { "Sathmar Swabian", 2223059, "gmw-hgm", "Latn", ancestors = "swg", } m["gmw-tsx"] = { "Transylvanian Saxon", 260942, "gmw-hgm", "Latn", ancestors = "gmw-cfr", } m["gmw-vog"] = { "Volga German", 312574, "gmw-hgm", "Latn", ancestors = "gmw-rfr", } m["gmw-zps"] = { "Zipser German", 205548, "gmw-hgm", "Latn", ancestors = "gmh", } m["gn-cls"] = { "Classical Guarani", 17478065, "gn", "Latn", } m["grk-cal"] = { "Calabrian Greek", 1146398, "grk", "Latn, Grek", ancestors = "grk-ita", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-ita"] = { "Italiot Greek", 19720507, "grk", "Latn, Grek", ancestors = "gkm", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-mar"] = { "Mariupol Greek", 4400023, "grk", "Cyrl, Latn, Grek", ancestors = "gkm", translit = { Cyrl = "grk-mar-translit", Grek = "grk-mar-translit", }, override_translit = true, strip_diacritics = { Cyrl = {remove_diacritics = c.acute}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-pro"] = { "Proto-Hellenic", 1231805, "grk", "Latn, Polyt", type = "reconstructed", sort_key = {Latn = { from = {"ʰ", "ʷ"}, to = {"h", "w"}, remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron }}, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in -- the translit section } m["hmn-pro"] = { "Proto-Hmongic", 116773210, "hmn", "Latn", type = "reconstructed", } m["hmx-mie-pro"] = { "Proto-Mienic", 116773229, "hmx-mie", "Latn", type = "reconstructed", } m["hmx-pro"] = { "Proto-Hmong-Mien", 7251846, "hmx", "Latn", type = "reconstructed", } m["hyx-pro"] = { "Proto-Armenian", 3848498, "hyx", "Latn", type = "reconstructed", } m["iir-nur-pro"] = { "Proto-Nuristani", 116773248, "iir-nur", "Latn", type = "reconstructed", } m["iir-pro"] = { "Proto-Indo-Iranian", 966439, "iir", "Latn", type = "reconstructed", } m["ijo-pro"] = { "Proto-Ijoid", 116773766, "ijo", "Latn", type = "reconstructed", } m["inc-apa"] = { "Apabhramsa", 616419, "inc-mid", "Deva, Shrd, Sidd", ancestors = "pra", translit = { Deva = "sa-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] }, } m["inc-ash"] = { "Ashokan Prakrit", 104854379, "inc-mid", "Brah, Khar", ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Khar = "Khar-translit", }, } m["inc-dng-pro"] = { "Proto-Dangari", nil, "inc-dng", "Latn", type = "reconstructed", } m["inc-kam"] = { "Kamarupi Prakrit", 6356097, "inc-bas", "Brah, Sidd", -- Brah, Sidd translit in [[Module:scripts/data]] } m["inc-kho"] = { "Kholosi", 24952008, "inc-snd", "Latn", } m["inc-krd-pro"] = { "Proto-Kamta", 128816843, "inc-bas", "Latn", ancestors = "inc-kam", type = "reconstructed", } m["inc-mas"] = { "Middle Assamese", 128806836, "inc-bas", "as-Beng", ancestors = "inc-oas", translit = "inc-mas-translit", } m["inc-mbn"] = { "Middle Bengali", 113559927, "inc-bas", "Beng", ancestors = "inc-obn", translit = "inc-mbn-translit", } m["inc-mgu"] = { "Middle Gujarati", 24907429, "inc-wes", "Deva", ancestors = "inc-ogu", } m["inc-mor"] = { "Middle Odia", 128810882, "inc-eas", "Orya", ancestors = "inc-oor", } m["inc-oas"] = { "Early Assamese", 85758237, "inc-bas", "as-Beng", ancestors = "inc-kam", translit = "inc-oas-translit", } m["inc-oaw"] = { "Old Awadhi", nil, "inc-hie", "Deva, Kthi, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Kthi = "sa-Kthi-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-obn"] = { "Old Bengali", 113559926, "inc-bas", "Beng", } m["inc-ogu"] = { "Old Gujarati", 24907427, "inc-wes", "Deva", translit = "sa-translit", } m["inc-ohi"] = { "Old Hindi", 48767781, "inc-hiw", "Deva, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-oor"] = { "Old Odia", 128807801, "inc-eas", "Orya", } m["inc-opa"] = { "Old Punjabi", 115270971, "inc-pan", "Guru, pa-Arab", translit = { Guru = "inc-opa-Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun}, } m["inc-pro"] = { "Proto-Indo-Aryan", 23808344, "inc", "Latn", type = "reconstructed", } m["ine-ana-pro"] = { "Proto-Anatolian", 7251833, "ine-ana", "Latn", type = "reconstructed", } m["ine-bsl-pro"] = { "Proto-Balto-Slavic", 1703347, "ine-bsl", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", c.acute, c.macron, "ˀ"}, to = {"a", "e", "i", "o", "u"} }, } m["ine-kal"] = { "Kalašma", 122770439, "ine-ana", "Xsux", } m["ine-pae"] = { "Paeonian", 2705672, "ine", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ine-pro"] = { "Proto-Indo-European", 37178, "ine", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ĺ", "ḿ", "ń", "ŕ", "ǵ", "ḱ", "ʰ", "ʷ", "₁", "₂", "₃", c.ringbelow, c.acute, c.macron}, to = {"a", "e", "i", "o", "u", "l", "m", "n", "r", "g'", "k'", "¯h", "¯w", "1", "2", "3"} }, } m["ine-toc-pro"] = { "Proto-Tocharian", 104841462, "ine-toc", "Latn", type = "reconstructed", } m["xme-old"] = { "Old Median", 36461, "xme", "Polyt, Latn", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-mid"] = { "Middle Median", 12836150, "xme", "Latn", } m["xme-ker"] = { "Kermanic", 129850, "xme", "fa-Arab, Latn, Hebr", ancestors = "xme-mid", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-taf"] = { "Tafreshi", nil, "xme", "fa-Arab, Latn", ancestors = "xme-mid", } m["xme-ttc-pro"] = { "Proto-Tatic", 122973870, "xme-ttc", "Latn", ancestors = "xme-mid", } m["xme-kls"] = { "Kalasuri", nil, "xme-ttc", ancestors = "xme-ttc-nor", } m["xme-klt"] = { "Kilit", 3612452, "xme-ttc", "Cyrl", -- and fa-Arab? } m["xme-ott"] = { "Old Tati", 434697, "xme-ttc", "fa-Arab, Latn", } m["ira-kms-pro"] = { "Proto-Komisenian", 116773777, "ira-kms", "Latn", type = "reconstructed", } m["ira-mpr-pro"] = { "Proto-Medo-Parthian", 116773227, "ira-mpr", "Latn", type = "reconstructed", } m["ira-pat-pro"] = { "Proto-Pathan", 116773255, "ira-pat", "Latn", type = "reconstructed", } m["ira-pro"] = { "Proto-Iranian", 4167865, "ira", "Latn", type = "reconstructed", } m["ira-zgr-pro"] = { "Proto-Zaza-Gorani", 116775031, "ira-zgr", "Latn", type = "reconstructed", } m["xsc-pro"] = { "Proto-Scythian", 116773273, "xsc", "Latn", type = "reconstructed", } m["xsc-sar-pro"] = { "Proto-Sarmatian", 116773249, "xsc-sar", "Latn", type = "reconstructed", } m["xsc-skw-pro"] = { "Proto-Saka-Wakhi", 116773267, "xsc-skw", "Latn", type = "reconstructed", } m["xsc-sak-pro"] = { "Proto-Saka", 116773264, "xsc-sak", "Latn", type = "reconstructed", } m["ira-sym-pro"] = { "Proto-Shughni-Yazghulami-Munji", 116773813, "ira-sym", "Latn", type = "reconstructed", } m["ira-sgi-pro"] = { "Proto-Sanglechi-Ishkashimi", 116773808, "ira-sgi", "Latn", type = "reconstructed", } m["ira-mny-pro"] = { "Proto-Munji-Yidgha", 116773792, "ira-mny", "Latn", type = "reconstructed", } m["ira-shy-pro"] = { "Proto-Shughni-Yazghulami", 116773812, "ira-shy", "Latn", type = "reconstructed", } m["ira-shr-pro"] = { "Proto-Shughni-Roshani", 116773811, "ira-shr", "Latn", type = "reconstructed", } m["ira-sgc-pro"] = { "Proto-Sogdic", 116773276, "ira-sgc", "Latn", type = "reconstructed", } m["ira-wnj"] = { "Vanji", 3398419, "ira-shy", "Latn", } m["iro-ere"] = { "Erie", 5388365, "iro-nor", "Latn", } m["iro-min"] = { "Mingo", 128531, "iro-nor", "Latn", ietf_subtag = "i-mingo", -- grandfathered IETF tag } m["iro-nor-pro"] = { "Proto-North Iroquoian", 116773242, "iro-nor", "Latn", type = "reconstructed", } m["iro-pro"] = { "Proto-Iroquoian", 7251852, "iro", "Latn", type = "reconstructed", } m["itc-pro"] = { "Proto-Italic", 17102720, "itc", "Latn", type = "reconstructed", } m["itc-psa"] = { "Pre-Samnite", 7239186, "itc-sbl", "Ital, Polyt, Latn", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["jpx-hcj"] = { "Hachijō", 5637049, "jpx", "Jpan", ancestors = "ojp-eas", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jpx-pro"] = { "Proto-Japonic", 3924309, "jpx", "Latn", type = "reconstructed", } m["jpx-ryu-pro"] = { "Proto-Ryukyuan", 56349069, "jpx-ryu", "Latn", type = "reconstructed", } m["kar-pro"] = { "Proto-Karen", 85794783, "kar", "Latn", type = "reconstructed", } m["kca-eas"] = { "Eastern Khanty", 30304622, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-nor"] = { "Northern Khanty", 30304527, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-pro"] = { "Proto-Khanty", 127505171, "kca", "Latn", type = "reconstructed", } m["kca-sou"] = { "Southern Khanty", 30304618, "kca", "Cyrl", translit = "kca-translit", override_translit = true, } m["khi-kho-pro"] = { "Proto-Khoe", 116773218, "khi-kho", "Latn", type = "reconstructed", } m["khi-kun"] = { "ǃKung", 32904, "khi-kxa", "Latn", } m["ko-ear"] = { "Early Modern Korean", 756014, "qfa-kor", "Kore", ancestors = "okm", translit = "okm-translit", -- Kore strip_diacritics in [[Module:scripts/data]] } m["kro-pro"] = { "Proto-Kru", 116773778, "kro", "Latn", type = "reconstructed", } m["ku-pro"] = { "Proto-Kurdish", 116773221, "ku", "Latn", type = "reconstructed", } m["map-ata-pro"] = { "Proto-Atayalic", 116773151, "map-ata", "Latn", type = "reconstructed", } m["map-bms"] = { "Banyumasan", 33219, "map", "Latn, Java", } m["map-pro"] = { "Proto-Austronesian", 49230, "map", "Latn", type = "reconstructed", } m["mis-hkl"] = { "Kelantan Peranakan Hokkien", 108794818, "qfa-mix", ancestors = "nan-hbl, sou, mfa", } m["mis-idn"] = { "Idiom Neutral", 35847, "art", "Latn", type = "appendix-constructed", } m["mis-isa"] = { "Isaurian", 16956868, nil, -- "Xsux, Hluw, Latn", } m["mis-jie"] = { "Jie", 124424186, nil, "Hani", sort_key = "Hani-sortkey", } m["mis-jzh"] = { "Jizhao", 45242758, "qfa-bej", "Latn", } m["mis-kas"] = { "Kassite", 35612, nil, "Xsux", } m["mis-mmd"] = { "Mimi of Decorse", 6862206, nil, "Latn", } m["mis-mmn"] = { "Mimi of Nachtigal", 6862207, nil, "Latn", } m["mis-phi"] = { "Philistine", 2230924, nil, "Phnx", -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["mis-rou"] = { "Rouran", 48816637, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tdl"] = { "Turdulian", 133176492, } m["mis-tdt"] = { "Turdetanian", 133176461, } m["mis-tnw"] = { "Tangwang", 7683179, "qfa-mix", "Latn", ancestors = "cmn, sce", } m["mis-tuh"] = { "Tuyuhun", 48816625, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tuo"] = { "Tuoba", 48816629, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-wuh"] = { "Wuhuan", 118976867, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xbi"] = { "Xianbei", 4448647, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xnu"] = { "Xiongnu", 10901674, nil, "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mjg-mgl"] = { "Mongghul", 53765528, "mjg", "Latn", -- also Mong, Cyrl ? } m["mjg-mgr"] = { "Mangghuer", 56285392, "mjg", "Latn", -- also Mong, Cyrl ? } m["mkh-asl-pro"] = { "Proto-Aslian", 55630680, "mkh-asl", "Latn", type = "reconstructed", } m["mkh-ban-pro"] = { "Proto-Bahnaric", 116773189, "mkh-ban", "Latn", type = "reconstructed", } m["mkh-kat-pro"] = { "Proto-Katuic", 116773772, "mkh-kat", "Latn", type = "reconstructed", } m["mkh-khm-pro"] = { "Proto-Khmuic", 116773774, "mkh-khm", "Latn", type = "reconstructed", } m["mkh-kmr-pro"] = { "Proto-Khmeric", 55630684, "mkh-kmr", "Latn", type = "reconstructed", } m["mkh-mmn"] = { "Middle Mon", 121337926, "mkh-mnc", "Latn, Mymr", --and also Pallava ancestors = "omx", } m["mkh-mnc-pro"] = { "Proto-Monic", 116773231, "mkh-mnc", "Latn", type = "reconstructed", } m["mkh-mvi"] = { "Middle Vietnamese", 9199, "mkh-vie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mkh-pal-pro"] = { "Proto-Palaungic", 104847372, "mkh-pal", "Latn", type = "reconstructed", } m["mkh-pea-pro"] = { "Proto-Pearic", 116773804, "mkh-pea", "Latn", type = "reconstructed", } m["mkh-pkn-pro"] = { "Proto-Pakanic", 116773803, "mkh-pkn", "Latn", type = "reconstructed", } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. "Proto-Mon-Khmer", 7251859, "mkh", "Latn", type = "reconstructed", } m["mnw-tha"] = { -- To be removed. "Thai Mon", nil, "mkh-mnc", "Mymr, Thai", ancestors = "mkh-mmn", sort_key = { from = {"[%p]", "ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ", "[็-๎]", "([เแโใไ])([ก-ฮ])ฺ?"}, to = {"", "္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ", "", "%2%1"} }, } m["mkh-vie-pro"] = { "Proto-Vietic", 109432616, "mkh-vie", "Latn", type = "reconstructed", } m["mns-cen"] = { "Central Mansi", 128810384, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-nor"] = { "Northern Mansi", 30304537, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-pro"] = { "Proto-Mansi", 128883093, "mns", "Latn", type = "reconstructed", } m["mns-sou"] = { "Southern Mansi", 30304629, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mun-pro"] = { "Proto-Munda", 105102373, "mun", "Latn", type = "reconstructed", } m["myn-chl"] = { -- the stage after ''emy'' "Ch'olti'", 873995, "myn", "Latn", } m["myn-pro"] = { "Proto-Mayan", 3321532, "myn", "Latn", type = "reconstructed", } m["nai-ala"] = { "Alazapa", 128810233, nil, "Latn", } m["nai-bay"] = { "Bayogoula", 1563704, nil, "Latn", } m["nai-cal"] = { "Calusa", 51782, nil, "Latn", } m["nai-chi"] = { "Chiquimulilla", 25339627, "nai-xin", "Latn", } m["nai-chu-pro"] = { "Proto-Chumash", 116773736, "nai-chu", "Latn", type = "reconstructed", } m["nai-cig"] = { "Ciguayo", 20741700, nil, "Latn", } m["nai-ckn-pro"] = { "Proto-Chinookan", 116773735, "nai-ckn", "Latn", type = "reconstructed", } m["nai-guz"] = { "Guazacapán", 19572028, "nai-xin", "Latn", } m["nai-hit"] = { "Hitchiti", 1542882, "nai-mus", "Latn", } m["nai-ipa"] = { "Ipai", 3027474, "nai-yuc", "Latn", } m["nai-jtp"] = { "Jutiapa", nil, "nai-xin", "Latn", } m["nai-jum"] = { "Jumaytepeque", 25339626, "nai-xin", "Latn", } m["nai-kat"] = { "Kathlamet", 6376639, "nai-ckn", "Latn", } m["nai-klp-pro"] = { "Proto-Kalapuyan", 116773771, "nai-klp", "Latn", type = "reconstructed", } m["nai-knm"] = { "Konomihu", 3198734, "nai-shs", "Latn", } m["nai-kum"] = { "Kumeyaay", 4910139, "nai-yuc", "Latn", } m["nai-mac"] = { "Macoris", 21070851, nil, "Latn", } m["nai-mdu-pro"] = { "Proto-Maidun", 116773784, "nai-mdu", "Latn", type = "reconstructed", } m["nai-miz-pro"] = { "Proto-Mixe-Zoque", 7251858, "nai-miz", "Latn", type = "reconstructed", } m["nai-mus-pro"] = { "Proto-Muskogean", 116775368, "nai-mus", "Latn", type = "reconstructed", } m["nai-nao"] = { "Naolan", 6964594, nil, "Latn", } m["nai-nrs"] = { "New River Shasta", 7011254, "nai-shs", "Latn", } m["nai-okw"] = { "Okwanuchu", 3350126, "nai-shs", "Latn", } m["nai-per"] = { "Pericú", 3375369, nil, "Latn", } m["nai-pic"] = { "Picuris", 7191257, "nai-kta", "Latn", } m["nai-plp-pro"] = { "Proto-Plateau Penutian", 116773806, "nai-plp", "Latn", type = "reconstructed", } m["nai-pom-pro"] = { "Proto-Pomo", 116773262, "nai-pom", "Latn", type = "reconstructed", } m["nai-qng"] = { "Quinigua", 36360, nil, "Latn", } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan "Proto-Siouan-Catawban", 116773275, "nai-sca", "Latn", type = "reconstructed", } m["nai-sin"] = { "Sinacantán", 24190249, "nai-xin", "Latn", } m["nai-sln"] = { "Salvadoran Lenca", 3229434, "nai-len", "Latn", } m["nai-spt"] = { "Sahaptin", 3833015, "nai-shp", "Latn", } m["nai-tap"] = { "Tapachultec", 7684401, "nai-miz", "Latn", } m["nai-taw"] = { "Tawasa", 7689233, nil, "Latn", } m["nai-teq"] = { "Tequistlatec", 2964454, "nai-tqn", "Latn", } m["nai-tip"] = { "Tipai", 3027471, "nai-yuc", "Latn", } m["nai-tot-pro"] = { "Proto-Totozoquean", 116773285, "nai-tot", "Latn", type = "reconstructed", } m["nai-tsi-pro"] = { "Proto-Tsimshianic", nil, "nai-tsi", "Latn", type = "reconstructed", } m["nai-utn-pro"] = { "Proto-Utian", 116773290, "nai-utn", "Latn", type = "reconstructed", } m["nai-wai"] = { "Waikuri", 3118702, nil, "Latn", } m["nai-wji"] = { "Western Jicaque", 3178610, "nai-jcq", "Latn", } m["nai-yup"] = { "Yupiltepeque", 25339628, "nai-xin", "Latn", } m["nan-dat"] = { "Datian Min", 19855572, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-hbl"] = { "Hokkien", 1624231, "zhx-nan", "Hants, Latn, Bopo, Kana", wikimedia_codes = "zh-min-nan", generate_forms = "zh-generateforms", sort_key = { Hani = "Hani-sortkey", Kana = "Kana-sortkey" }, } m["nan-hlh"] = { "Hailufeng Min", 120755728, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-lnx"] = { "Longyan Min", 6674568, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-tws"] = { "Teochew", 36759, "zhx-nan", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["nan-zhe"] = { "Zhenan Min", 3846710, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-zsh"] = { "Sanxiang Min", 7420769, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["ngf-bin-pro"] = { "Proto-Binanderean", 137881672, "ngf-bin", "Latn", type = "reconstructed", } m["ngf-pro"] = { "Proto-Trans-New Guinea", 85794785, "ngf", "Latn", type = "reconstructed", } m["nic-bco-pro"] = { "Proto-Benue-Congo", 116773194, "nic-bco", "Latn", type = "reconstructed", } m["nic-bod-pro"] = { "Proto-Bantoid", 116773190, "nic-bod", "Latn", type = "reconstructed", } m["nic-eov-pro"] = { "Proto-Eastern Oti-Volta", 116773753, "nic-eov", "Latn", type = "reconstructed", } m["nic-gns-pro"] = { "Proto-Gurunsi", 116773759, "nic-gns", "Latn", type = "reconstructed", } m["nic-grf-pro"] = { "Proto-Grassfields", 116773755, "nic-grf", "Latn", type = "reconstructed", } m["nic-gur-pro"] = { "Proto-Gur", 116773758, "nic-gur", "Latn", type = "reconstructed", } m["nic-jkn-pro"] = { "Proto-Jukunoid", 116773769, "nic-jkn", "Latn", type = "reconstructed", } m["nic-lcr-pro"] = { "Proto-Lower Cross River", 116773782, "nic-lcr", "Latn", type = "reconstructed", } m["nic-ogo-pro"] = { "Proto-Ogoni", 116773799, "nic-ogo", "Latn", type = "reconstructed", } m["nic-ovo-pro"] = { "Proto-Oti-Volta", 116773802, "nic-ovo", "Latn", type = "reconstructed", } m["nic-plt-pro"] = { "Proto-Plateau", 116773805, "nic-plt", "Latn", type = "reconstructed", } m["nic-pro"] = { "Proto-Niger-Congo", 108000748, "nic", "Latn", type = "reconstructed", } m["nic-ubg-pro"] = { "Proto-Ubangian", 116773818, "nic-ubg", "Latn", type = "reconstructed", } m["nic-ucr-pro"] = { "Proto-Upper Cross River", 116773819, "nic-ucr", "Latn", type = "reconstructed", } m["nic-vco-pro"] = { "Proto-Volta-Congo", 116773293, "nic-vco", "Latn", type = "reconstructed", } m["njo-jgl"] = { "Chungli Ao", 55607615, "sit-aao", "Latn", } m["nub-har"] = { "Haraza", 19572059, "nub", "Arab, Latn", } m["nub-pro"] = { "Proto-Nubian", 116773246, "nub", "Latn", type = "reconstructed", } m["omq-cha-pro"] = { "Proto-Chatino", 116773202, "omq-cha", "Latn", type = "reconstructed", } m["omq-maz-pro"] = { "Proto-Mazatec", 116773790, "omq-maz", "Latn", type = "reconstructed", } m["omq-mix-pro"] = { "Proto-Mixtecan", 21573423, "omq-mix", "Latn", type = "reconstructed", } m["omq-mxt-pro"] = { "Proto-Mixtec", 21573424, "omq-mxt", "Latn", type = "reconstructed", } m["omq-otp-pro"] = { "Proto-Oto-Pamean", 116773251, "omq-otp", "Latn", type = "reconstructed", } m["omq-pro"] = { "Proto-Oto-Manguean", 33669, "omq", "Latn", type = "reconstructed", } m["omq-sjq"] = { "San Juan Quiahije Chatino", 138330751, "omq-cha", "Latn", } m["omq-tel"] = { "Teposcolula Mixtec", nil, "omq-mxt", "Latn", } m["omq-teo"] = { "Teojomulco Chatino", 25340451, "omq-cha", "Latn", } m["omq-tri-pro"] = { "Proto-Triqui", 116773817, "omq-tri", "Latn", type = "reconstructed", } m["omq-zap-pro"] = { "Proto-Zapotecan", 116773297, "omq-zap", "Latn", type = "reconstructed", } m["omq-zpc-pro"] = { "Proto-Zapotec", 116773296, "omq-zpc", "Latn", type = "reconstructed", } m["omv-aro-pro"] = { "Proto-Aroid", 116773721, "omv-aro", "Latn", type = "reconstructed", } m["omv-diz-pro"] = { "Proto-Dizoid", 116773750, "omv-diz", "Latn", type = "reconstructed", } m["omv-pro"] = { "Proto-Omotic", 116773800, "omv", "Latn", type = "reconstructed", } m["oto-otm-pro"] = { "Proto-Otomi", 5908710, "oto-otm", "Latn", type = "reconstructed", } m["oto-pro"] = { "Proto-Otomian", 116773252, "oto", "Latn", type = "reconstructed", } m["paa-kmn"] = { "Kómnzo", 18344310, "paa-wko", "Latn", } m["paa-kwn"] = { "Kuwani", 6449056, "qfa-unc", -- poorly attested, possibly the same as or related to Kalabra "Latn", } m["paa-lei"] = { "Leitre", 85776228, "paa-isk", } m["paa-nha-pro"] = { "Proto-North Halmahera", 116773241, "paa-nha", "Latn", type = "reconstructed" } m["paa-nun"] = { "Nungon", 128807788, "ngf-ynu", "Latn", } m["phi-din"] = { "Dinapigue Agta", 16945774, "phi", "Latn", } m["phi-kal-pro"] = { "Proto-Kalamian", 116773213, "phi-kal", "Latn", type = "reconstructed", } m["phi-nag"] = { "Nagtipunan Agta", 16966111, "phi", "Latn", } m["phi-pro"] = { "Proto-Philippine", 18204898, "phi", "Latn", type = "reconstructed", } m["poz-abi"] = { "Abai", 19570729, "poz-san", "Latn", } m["poz-bal"] = { "Baliledo", 4850912, "poz", "Latn", } m["poz-btk-pro"] = { "Proto-Bungku-Tolaki", 116773724, "poz-btk", "Latn", type = "reconstructed", } m["poz-cet-pro"] = { "Proto-Central-Eastern Malayo-Polynesian", 2269883, "poz-cet", "Latn", type = "reconstructed", } m["poz-hce-pro"] = { "Proto-Halmahera-Cenderawasih", 116773209, "poz-hce", "Latn", type = "reconstructed", } m["poz-lgx-pro"] = { "Proto-Lampungic", 116773222, "poz-lgx", "Latn", type = "reconstructed", } m["poz-mcm-pro"] = { "Proto-Malayo-Chamic", 116773225, "poz-mcm", "Latn", type = "reconstructed", } m["poz-mic-pro"] = { "Proto-Micronesian", 111939079, "poz-mic", "Latn", type = "reconstructed", } m["poz-mly-pro"] = { "Proto-Malayic", 98057728, "poz-mly", "Latn", type = "reconstructed", } m["poz-msa-pro"] = { "Proto-Malayo-Sumbawan", 116773226, "poz-msa", "Latn", type = "reconstructed", } m["poz-oce-pro"] = { "Proto-Oceanic", 141741, "poz-oce", "Latn", type = "reconstructed", } m["poz-pep-pro"] = { "Proto-Eastern Polynesian", 113988745, "poz-pep", "Latn", type = "reconstructed", } m["poz-pnp-pro"] = { "Proto-Nuclear Polynesian", 113988746, "poz-pnp", "Latn", type = "reconstructed", } m["poz-pol-pro"] = { "Proto-Polynesian", 1658709, "poz-pol", "Latn", type = "reconstructed", } m["poz-pro"] = { "Proto-Malayo-Polynesian", 3832960, "poz", "Latn", type = "reconstructed", } m["poz-sml"] = { "Sarawak Malay", 4251702, "poz-mly", "Latn, ms-Arab", } m["poz-ssw-pro"] = { "Proto-South Sulawesi", 116773279, "poz-ssw", "Latn", type = "reconstructed", } m["poz-swa-pro"] = { "Proto-North Sarawak", 116773243, "poz-swa", "Latn", type = "reconstructed", } m["poz-ter"] = { "Terengganu Malay", 4207412, "poz-mly", "Latn, ms-Arab", } m["pqe-pro"] = { "Proto-Eastern Malayo-Polynesian", 2269883, "pqe", "Latn", type = "reconstructed", } m["pra-niy"] = { "Niya Prakrit", 11991601, "inc-mid", "Khar", ancestors = "inc-ash", translit = "Khar-translit", } m["qfa-adm-pro"] = { "Proto-Great Andamanese", 116773756, "qfa-adm", "Latn", type = "reconstructed", } m["qfa-bet-pro"] = { "Proto-Be-Tai", 116773193, "qfa-bet", "Latn", type = "reconstructed", } m["qfa-cka-pro"] = { "Proto-Chukotko-Kamchatkan", 7251837, "qfa-cka", "Latn", type = "reconstructed", } m["qfa-hur-pro"] = { "Proto-Hurro-Urartian", 116773211, "qfa-hur", "Latn", type = "reconstructed", } m["qfa-kad-pro"] = { "Proto-Kadu", 116773770, "qfa-kad", "Latn", type = "reconstructed", } m["qfa-kms-pro"] = { "Proto-Kam-Sui", 55630682, "qfa-kms", "Latn", type = "reconstructed", } m["qfa-kor-pro"] = { "Proto-Koreanic", 467883, "qfa-kor", "Latn", type = "reconstructed", } m["qfa-kra-pro"] = { "Proto-Kra", 7251854, "qfa-kra", "Latn", type = "reconstructed", } m["qfa-lic-pro"] = { "Proto-Hlai", 7251845, "qfa-lic", "Latn", type = "reconstructed", } m["qfa-onb-pro"] = { "Proto-Be", 116773192, "qfa-onb", "Latn", type = "reconstructed", } m["qfa-ong-pro"] = { "Proto-Ongan", 116773801, "qfa-ong", "Latn", type = "reconstructed", } m["qfa-tak-pro"] = { "Proto-Kra-Dai", 104901616, "qfa-tak", "Latn", type = "reconstructed", } m["qfa-yen-pro"] = { "Proto-Yeniseian", 27639, "qfa-yen", "Latn", type = "reconstructed", } m["qfa-yuk-pro"] = { "Proto-Yukaghir", 116773294, "qfa-yuk", "Latn", type = "reconstructed", } m["qwe-kch"] = { "Kichwa", 1740805, "qwe", "Latn", ancestors = "qu", } m["qwe-pro"] = { "Proto-Quechuan", 5575757, "qwe", "Latn", type = "reconstructed", } m["roa-ang"] = { "Angevin", 56782, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-bbn"] = { "Bourbonnais-Berrichon", 2899128, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-brg"] = { "Bourguignon", 508332, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-can"] = { "Cantabrian", 917021, "roa-asl", "Latn", } m["roa-cha"] = { "Champenois", 430018, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-fcm"] = { "Franc-Comtois", 510561, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gal"] = { "Gallo", 37300, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gib"] = { "Gallo-Italic of Basilicata", 3094838, "roa-git", ancestors = "pms-old", "Latn", } m["roa-gis"] = { "Gallo-Italic of Sicily", 2629019, "roa-git", "Latn", ancestors = "pms-old", } m["roa-leo"] = { "Leonese", 34108, "roa-asl", "Latn", } m["roa-lor"] = { "Lorrain", 671198, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-oca"] = { "Old Catalan", 15478520, "roa-ocr", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, } m["roa-ole"] = { "Old Leonese", 125977465, "roa-asl", "Latn", } m["roa-ona"] = { "Old Navarro-Aragonese", 2736184, "roa-nar", "Latn", } m["roa-opt"] = { "Old Galician-Portuguese", 1072111, "roa-gap", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["roa-orl"] = { "Orléanais", 28497058, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-poi"] = { "Poitevin-Saintongeais", 514123, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-tar"] = { "Tarantino", 695526, "roa-itr", "Latn", wikimedia_codes = "roa-tara", } m["sai-all"] = { "Allentiac", 19570789, "sai-hrp", "Latn", } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' "Andoquero", 16828359, "sai-wit", "Latn", } m["sai-ayo"] = { "Ayomán", 16937754, "sai-jir", "Latn", } m["sai-bae"] = { "Baenan", 3401998, "qfa-unc", -- extinct, poorly attested; only known through 9 words "Latn", } m["sai-bag"] = { "Bagua", 5390321, "qfa-unc", -- extinct, poorly attested; possibly Cariban "Latn", } m["sai-bet"] = { "Betoi", 926551, "qfa-iso", "Latn", } m["sai-bor-pro"] = { "Proto-Boran", nil, "sai-bor", "Latn", } m["sai-cac"] = { "Cacán", 945482, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-caq"] = { "Caranqui", 2937753, "sai-bar", "Latn", } m["sai-car-pro"] = { "Proto-Cariban", 116773196, "sai-car", "Latn", type = "reconstructed", } m["sai-cat"] = { "Catacao", 5051136, "sai-ctc", "Latn", } m["sai-cer-pro"] = { "Proto-Cerrado", 116773200, "sai-cer", "Latn", type = "reconstructed", } m["sai-chi"] = { "Chirino", 5390321, "qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu) "Latn", } m["sai-chn"] = { "Chaná", 5072718, "sai-crn", "Latn", } m["sai-chp"] = { "Chapacura", 5072884, "sai-cpc", "Latn", } m["sai-chr"] = { "Charrua", 5086680, "sai-crn", "Latn", } m["sai-chu"] = { "Churuya", 5118339, "sai-guh", "Latn", } m["sai-cje-pro"] = { "Proto-Central Jê", 116773198, "sai-cje", "Latn", type = "reconstructed", } m["sai-cmg"] = { "Comechingon", 6644203, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-cno"] = { "Chono", 5104704, "qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious "Latn", } m["sai-cnr"] = { "Cañari", 5055572, "qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan "Latn", } m["sai-coe"] = { "Coeruna", 6425639, "sai-wit", "Latn", } m["sai-col"] = { "Colán", 5141893, "sai-ctc", "Latn", } m["sai-cop"] = { "Copallén", 5390321, "qfa-unc", -- extinct, only four words attested; possibly Cholonan "Latn", } m["sai-crd"] = { "Coroado Puri", 24191321, "sai-mje", "Latn", } m["sai-ctq"] = { "Catuquinaru", 16858455, "qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages "Latn", } m["sai-cul"] = { "Culli", 2879660, "qfa-unc", -- extinct, poorly attested; often considered an isolate "Latn", } m["sai-cva"] = { "Cueva", 5192644, "qfa-unc", -- extinct, poorly attested; possibly Chocoan "Latn", } m["sai-esm"] = { "Esmeralda", 3058083, "qfa-unc", -- extinct, poorly attested; possibly related to Yaruro "Latn", } m["sai-ewa"] = { "Ewarhuyana", 16898104, nil, "Latn", } m["sai-gam"] = { "Gamela", 5403661, "qfa-unc", -- extinct, poorly attested; possibly an isolate "Latn", } m["sai-gay"] = { "Gayón", 5528902, "sai-jir", "Latn", } m["sai-gmo"] = { "Guamo", 5613495, "qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024). "Latn", } m["sai-gua"] = { "Guachí", 5613172, "sai-guc", "Latn", } m["sai-gue"] = { "Güenoa", 5626799, "sai-crn", "Latn", } m["sai-hau"] = { "Haush", 3128376, "sai-cho", "Latn", } m["sai-jee-pro"] = { "Proto-Jê", 116773212, "sai-jee", "Latn", type = "reconstructed", } m["sai-jko"] = { "Jeikó", 6176527, "sai-mje", "Latn", } m["sai-jrj"] = { "Jirajara", 6202966, "sai-jir", "Latn", } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc "Katembri", 6375925, "qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia] "Latn", } m["sai-mal"] = { "Malalí", 6741212, "sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry "Latn", } m["sai-mar"] = { "Maratino", 6755055, "qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan "Latn", } m["sai-mat"] = { "Matanawi", 6786047, "qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified "Latn", } m["sai-mcn"] = { "Mocana", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-men"] = { "Menien", 16890110, "sai-mje", "Latn", } m["sai-mil"] = { "Millcayac", 19573012, "sai-hrp", "Latn", } m["sai-mlb"] = { "Malibu", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-msk"] = { "Masakará", 6782426, "sai-mje", "Latn", } m["sai-muc"] = { "Mucuchí", 6931290, nil, -- generally considered Timotean, for which we have no entry "Latn", } m["sai-mue"] = { "Muellama", 16886936, "sai-bar", "Latn", } m["sai-muz"] = { "Muzo", 6644203, "qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban) "Latn", } m["sai-mys"] = { "Maynas", 16919393, "sai-cah", -- per Campbell (2024); formerly considered unclassified "Latn", } m["sai-nat"] = { "Natú", 9006749, "qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages] "Latn", } m["sai-nje-pro"] = { "Proto-Northern Jê", 116773245, "sai-nje", "Latn", type = "reconstructed", } m["sai-opo"] = { "Opón", 7099152, "sai-car", "Latn", } m["sai-oto"] = { "Otomaco", 16879234, "sai-otm", "Latn", } m["sai-pal"] = { "Palta", 3042978, "qfa-unc", -- extinct, unclassified; possibly Chicham "Latn", } m["sai-pam"] = { "Pamigua", 5908689, "sai-otm", "Latn", } m["sai-par"] = { "Paratió", 16890038, "qfa-unc", -- extinct, poorly attested; possibly Xukuruan "Latn", } m["sai-peb"] = { "Peba", 3373890, "sai-pey", "Latn", } m["sai-pnz"] = { "Panzaleo", 3123275, "qfa-unc", -- extinct, unclassified; possibly Paezan "Latn", } m["sai-prh"] = { "Puruhá", 3410994, "qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari "Latn", } m["sai-ptg"] = { "Patagón", 128807870, "sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024) "Latn", } m["sai-pur"] = { "Purukotó", 7261622, "sai-pem", "Latn", } m["sai-pyg"] = { "Payaguá", 7156643, "sai-guc", "Latn", } m["sai-pyk"] = { "Pykobjê", 98113977, "sai-nje", "Latn", } m["sai-qmb"] = { "Quimbaya", 7272043, "qfa-unc", -- extinct, might not exist; few known words "Latn", } m["sai-qtm"] = { "Quitemo", 7272651, "sai-cpc", "Latn", } m["sai-rab"] = { "Rabona", 6644203, "qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra "Latn", } m["sai-ram"] = { "Ramanos", 16902824, "qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages" "Latn", } m["sai-sac"] = { "Sácata", 5390321, "qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan "Latn", } m["sai-san"] = { "Sanaviron", 16895999, "qfa-unc", -- extinct, unclassified; no consensus on classification "Latn", } m["sai-sap"] = { "Sapará", 7420922, "sai-car", "Latn", } m["sai-sec"] = { "Sechura", 7442912, "qfa-unc", -- extinct, poorly attested; possibly Catacaoan "Latn", } m["sai-sin"] = { "Sinúfana", 7525275, "qfa-unc", -- moribund, poorly attested; possibly Chocoan "Latn", } m["sai-sje-pro"] = { "Proto-Southern Jê", 116773814, "sai-sje", "Latn", type = "reconstructed", } m["sai-tab"] = { "Tabancale", 5390321, "qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate "Latn", } m["sai-tal"] = { "Tallán", 16910468, "qfa-unc", -- extinct, poorly attested; might be Catacaoan "Latn", } m["sai-tap"] = { "Tapayuna", 30719984, "sai-nje", "Latn", } m["sai-tar-pro"] = { "Proto-Taranoan", 116773816, "sai-tar", "Latn", type = "reconstructed", } m["sai-teu"] = { "Teushen", 3519243, "qfa-unc", -- probably extinct by the 1950's; possibly Chonan "Latn", } m["sai-tim"] = { "Timote", 7806995, nil, -- possibly in a small Timotean family "Latn", } m["sai-tpr"] = { "Taparita", 7684460, "sai-otm", "Latn", } m["sai-trr"] = { "Tarairiú", 7685313, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sai-wai"] = { "Waitaká", 16918610, "qfa-unc", -- extinct, possibly Purian "Latn", } m["sai-way"] = { "Wayumara", 7960726, "sai-car", "Latn", } m["sai-wit-pro"] = { "Proto-Witotoan", 116773823, "sai-wit", "Latn", type = "reconstructed", } m["sai-wnm"] = { "Wanham", 16879440, "sai-cpc", "Latn", } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat "Xocó", 12953620, "qfa-unc", -- extinct and poorly attested; not clear if one or three languages "Latn", } m["sai-yao"] = { "Yao (South America)", 16979655, "sai-ven", "Latn", } m["sai-yar"] = { -- not the same family as 'suy' "Yarumá", 3505859, "sai-pek", "Latn", } m["sai-yri"] = { "Yuri", 2669157, "sai-tyu", "Latn", } m["sai-yup"] = { "Yupua", 8061430, "sai-tuc", "Latn", } m["sai-yur"] = { "Yurumanguí", 1281291, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sal-pro"] = { "Proto-Salish", 116773269, "sal", "Latn", type = "reconstructed", } m["sdv-daj-pro"] = { "Proto-Daju", 116773739, "sdv-daj", "Latn", type = "reconstructed", } m["sdv-eje-pro"] = { "Proto-Eastern Jebel", 116773751, "sdv-eje", "Latn", type = "reconstructed", } m["sdv-nil-pro"] = { "Proto-Nilotic", 116773794, "sdv-nil", "Latn", type = "reconstructed", } m["sdv-nyi-pro"] = { "Proto-Nyima", 116773796, "sdv-nyi", "Latn", type = "reconstructed", } m["sdv-tmn-pro"] = { "Proto-Taman", 116773815, "sdv-tmn", "Latn", type = "reconstructed", } m["sel-nor"] = { "Northern Selkup", 30304565, "sel", "Cyrl", translit = "sel-nor-translit", } m["sel-pro"] = { "Proto-Selkup", 128884235, "sel", "Latn", type = "reconstructed", } m["sel-sou"] = { "Southern Selkup", 30304639, "sel", "Cyrl", translit = "sel-sou-translit", } m["sem-amm"] = { "Ammonite", 279181, "sem-can", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-amo"] = { "Amorite", 35941, "sem-nwe", "Xsux, Latn", } m["sem-cha"] = { "Chaha", 35543, "sem-eth", "Ethi", translit = "Ethi-translit", } m["sem-dad"] = { "Dadanitic", 21838040, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-dum"] = { "Dumaitic", 128810397, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-has"] = { "Hasaitic", 3541433, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-his"] = { "Hismaic", 22948260, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-mhr"] = { "Muher", 33743, "sem-eth", "Latn", } m["sem-pro"] = { "Proto-Semitic", 1658554, "sem", "Latn", type = "reconstructed", } m["sem-saf"] = { "Safaitic", 472586, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-sam"] = { "Samalian", 85847147, "sem-nwe", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-srb"] = { "Old South Arabian", 35025, "sem-osa", "Sarb", -- Sarb translit in [[Module:scripts/data]] } m["sem-tay"] = { "Taymanitic", 24912301, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-tha"] = { "Thamudic", 843030, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-wes-pro"] = { "Proto-West Semitic", 98021726, "sem-wes", "Latn", type = "reconstructed", } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' "Proto-Siouan", 34181, "sio", "Latn", type = "reconstructed", } m["sit-aao-pro"] = { "Proto-Central Naga", nil, "sit-aao", "Latn", type = "reconstructed", } m["sit-bai-pro"] = { "Proto-Bai", nil, "sit-bai", "Latn", type = "reconstructed", } m["sit-ban"] = { "Bangru", 56071779, "sit-hrs", "Latn", } m["sit-bdi-pro"] = { "Proto-Bodish", nil, "sit-bdi", "Latn", type = "reconstructed", } m["sit-bok"] = { "Bokar", 4938727, "sit-tan", "Latn, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["sit-cai"] = { "Caijia", 5017528, "sit-cln", "Latn" } m["sit-cha"] = { "Chairel", 5068066, "sit-luu", "Latn", } m["sit-ers-pro"] = { "Proto-Ersuic", nil, "sit-ers", "Latn", type = "reconstructed", } m["sit-hrs-pro"] = { "Proto-Hrusish", 116773762, "sit-hrs", "Latn", type = "reconstructed", } m["sit-jap"] = { "Japhug", 3162245, "sit-egy", "Latn", } m["sit-kha-pro"] = { "Proto-Kham", 116773773, "sit-kha", "Latn", type = "reconstructed", } m["sit-khb-pro"] = { "Proto-Kho-Bwa", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khp-pro"] = { "Proto-Puroik", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khw-pro"] = { "Proto-Western Kho-Bwa", nil, "sit-khw", "Latn", type = "reconstructed", } m["sit-kon-pro"] = { "Proto-Northern Naga", nil, "sit-kon", "Latn", type = "reconstructed", } m["sit-liz"] = { "Lizu", 6660653, "sit-ers", "Latn", -- and Ersu Shaba } m["sit-lnj"] = { "Longjia", 17096251, "sit-cln", "Latn" } m["sit-lrn"] = { "Luren", 16946370, "sit-cln", "Latn" } m["sit-luu-pro"] = { "Proto-Luish", 116773783, "sit-luu", "Latn", type = "reconstructed", } m["sit-nas-pro"] = { "Proto-Naish", nil, "sit-nas", "Latn", type = "reconstructed", } m["sit-prn"] = { "Puiron", 7259048, "sit-zem", } m["sit-pro"] = { "Proto-Sino-Tibetan", 24839178, "sit", "Latn", type = "reconstructed", } m["sit-sit"] = { "Situ", 19840830, "sit-egy", "Latn", } m["sit-tam-pro"] = { "Proto-Tamangic", 117469295, "sit-tam", "Latn", type = "reconstructed", } m["sit-tan-pro"] = { "Proto-Tani", 116773284, "sit-tan", "Latn", -- needs verification type = "reconstructed", } m["sit-tgm"] = { "Tangam", 17041370, "sit-tan", "Latn", } m["sit-tng-pro"] = { "Proto-Tangkhulic", nil, "sit-tng", "Latn", type = "reconstructed" } m["sit-tos"] = { "Tosu", 7827899, "sit-ers", "Latn", -- also Ersu Shaba } m["sit-tsh"] = { "Tshobdun", 19840950, "sit-egy", "Latn", } m["sit-zbu"] = { "Zbu", 19841106, "sit-egy", "Latn", } m["sla-pro"] = { "Proto-Slavic", 747537, "sla", "Latn", type = "reconstructed", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {'ś'}, }, sort_key = { from = {"č", "ď", "ě", "ę", "ь", "ľ", "ň", "ǫ", "ř", "š", "ś", "ť", "ъ", "ž"}, to = {"c²", "d²", "e²", "e³", "i²", "l²", "nj", "o²", "r²", "s²", "s³", "t²", "u²", "z²"}, } } m["smi-pro"] = { "Proto-Samic", 7251862, "smi", "Latn", type = "reconstructed", sort_key = { from = {"ā", "č", "δ", "[ëē]", "ŋ", "ń", "ō", "š", "θ", "%([^()]+%)"}, to = {"a", "c²", "d", "e", "n²", "n³", "o", "s²", "t²"} }, } m["son-pro"] = { "Proto-Songhay", 116773277, "son", "Latn", type = "reconstructed", } m["sqj-pro"] = { "Proto-Albanian", 18210846, "sqj", "Latn", type = "reconstructed", } m["ssa-klk-pro"] = { "Proto-Kuliak", 116773779, "ssa-klk", "Latn", type = "reconstructed", } m["ssa-kom-pro"] = { "Proto-Koman", 116773775, "ssa-kom", "Latn", type = "reconstructed", } m["ssa-pro"] = { "Proto-Nilo-Saharan", 116773236, "ssa", "Latn", type = "reconstructed", } m["syd-pro"] = { "Proto-Samoyedic", 7251863, "syd", "Latn", type = "reconstructed", } m["tai-pro"] = { "Proto-Tai", 6583709, "tai", "Latn", type = "reconstructed", } m["tai-swe-pro"] = { "Proto-Southwestern Tai", 116773280, "tai-swe", "Latn", type = "reconstructed", } m["tbq-bdg-pro"] = { "Proto-Bodo-Garo", 116773195, "tbq-bdg", "Latn", type = "reconstructed", } m["tbq-blg"] = { "Bailang", 2879843, "tbq-lob", "Hani", sort_key = "Hani-sortkey", } m["tbq-brm-pro"] = { "Proto-Burmish", nil, "tbq-brm", "Latn", type = "reconstructed", } m["tbq-gkh"] = { "Gokhy", 5578069, "tbq-sil", "Latn", } m["tbq-kuk-pro"] = { "Proto-Kuki-Chin", 116773220, "tbq-kuk", "Latn", type = "reconstructed", } m["tbq-lal-pro"] = { "Proto-Lalo", 116773781, "tbq-lal", "Latn", type = "reconstructed", } m["tbq-laz"] = { "Laze", 17007626, "sit-nas", "Latn", } m["tbq-lob-pro"] = { "Proto-Lolo-Burmese", 116773224, "tbq-lob", "Latn", type = "reconstructed", } m["tbq-lol-pro"] = { "Proto-Loloish", 7251855, "tbq-lol", "Latn", type = "reconstructed", } m["tbq-mil"] = { "Milang", 6850761, "sit-gsi", "Deva, Latn", } m["tbq-mor"] = { "Moran", 6909216, "tbq-bdg", "Latn", } m["tbq-ngo"] = { "Ngochang", 56582, "tbq-brm", "Latn", } -- tbq-pro is now etymology-only m["trk-dkh"] = { "Dukhan", 12809273, "trk-ssb", "Latn, Cyrl, Mong", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] } -- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''. m["trk-eog"] = { "Early Old Oghuz", nil, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, } m["trk-oat"] = { "Old Anatolian Turkish", 7083390, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, ancestors = "trk-eog", } m["trk-pro"] = { "Proto-Turkic", 3657773, "trk", "Latn", type = "reconstructed", standard_chars = { Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron, } } m["tup-gua-pro"] = { "Proto-Tupi-Guarani", 116773288, "tup-gua", "Latn", type = "reconstructed", } m["tup-kab"] = { "Kabishiana", 15302988, "tup", "Latn", } m["tup-pro"] = { "Proto-Tupian", 10354700, "tup", "Latn", type = "reconstructed", } m["tuw-alk"] = { "Alchuka", 113553616, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-bal"] = { "Bala", 86730632, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kkl"] = { "Kyakala", 118875708, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kli"] = { "Kili", 6406892, "tuw-ewe", "Cyrl", } m["tuw-pro"] = { "Proto-Tungusic", 85872335, "tuw", "Latn", type = "reconstructed", } m["tuw-sol"] = { "Solon", 30004, "tuw-ewe", } m["urj-fin-pro"] = { "Proto-Finnic", 11883720, "urj-fin", "Latn", type = "reconstructed", } m["urj-koo"] = { "Old Komi", 86679962, "kv", "Perm, Cyrs", translit = "urj-koo-translit", -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present } m["urj-kuk"] = { "Kukkuzi", 107410460, "urj-fin", "Latn", ancestors = "vot", } m["urj-kya"] = { "Komi-Yazva", 2365210, "kv", "Cyrl", translit = "kv-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.acute}, } m["urj-mdv-pro"] = { "Proto-Mordvinic", 116773232, "urj-mdv", "Latn", type = "reconstructed", } m["urj-prm-pro"] = { "Proto-Permic", 116773257, "urj-prm", "Latn", type = "reconstructed", } m["urj-pro"] = { "Proto-Uralic", 288765, "urj", "Latn", type = "reconstructed", } m["urj-ugr-pro"] = { "Proto-Ugric", 156631, "urj-ugr", "Latn", type = "reconstructed", } m["xnd-pro"] = { "Proto-Na-Dene", 116773233, "xnd", "Latn", type = "reconstructed", } m["xgn-pro"] = { "Proto-Mongolic", 2493677, "xgn", "Latn", type = "reconstructed", sort_key = { from = {"č", "i", "ï", "ǰ", "ŋ", "ö", "š", "ü"}, to = {"c", "i" .. p[1], "i", "j", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]}, }, } m["yok-bvy"] = { "Buena Vista Yokuts", 4985474, "yok", "Latn", } m["yok-dly"] = { "Delta Yokuts", 70923266, "yok", "Latn", } m["yok-gsy"] = { "Gashowu Yokuts", 3098708, "yok", "Latn", } m["yok-kry"] = { "Kings River Yokuts", 6413014, "yok", "Latn", } m["yok-nvy"] = { "Northern Valley Yokuts", 85789777, "yok", "Latn", } m["yok-ply"] = { "Palewyami Yokuts", 2387391, "yok", "Latn", } m["yok-svy"] = { "Southern Valley Yokuts", 12642473, "yok", "Latn", } m["yok-tky"] = { "Tule-Kaweah Yokuts", 7851988, "yok", "Latn", } m["ypk-pro"] = { "Proto-Yupik", 116773295, "ypk", "Latn", type = "reconstructed", } m["yrk-for"] = { "Forest Nenets", 1295107, "yrk", "Cyrl", translit = "yrk-for-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove}, } m["yrk-tun"] = { "Tundra Nenets", 36452, "yrk", "Cyrl", strip_diacritics = { from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"}, to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"}, }, translit = "yrk-tun-translit", } m["zhx-min-pro"] = { "Proto-Min", 19646347, "zhx-min", "Latn", type = "reconstructed", } m["zhx-sht"] = { "Shaozhou Tuhua", 1920769, "zhx", "Nshu, Hants", generate_forms = "zh-generateforms", sort_key = {Hani = "Hani-sortkey"}, } m["zhx-sic"] = { "Sichuanese", 2278732, "zhx-man", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zhx-tai"] = { "Taishanese", 2208940, "zhx-yue", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zle-ono"] = { "Old Novgorodian", 162013, "zle", "Cyrs, Glag", translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zle-ort"] = { "Old Ruthenian", 13211, "zle", "Arab, Cyrs, Latn", ancestors = "orv", translit = { Cyrs = "zle-ort-translit", Arab = "zle-ort-Arab-translit", }, strip_diacritics = { Cyrs = { remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"], remove_exceptions = {"Ї", "ї"}, }, Arab = "ar-stripdiacritics", }, -- Cyrs sort_key in [[Module:scripts/data]] } m["zls-chs"] = { "Church Slavonic", 33251, "zls", "Cyrs, Glag, Latn", ancestors = "cu", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zlw-ocs"] = { "Old Czech", 593096, "zlw", "Latn", } m["zlw-opl"] = { "Old Polish", 149838, "zlw-lch", "Latn", strip_diacritics = {remove_diacritics = c.ringabove}, } m["zlw-osk"] = { "Old Slovak", 12776676, "zlw", "Latn", } m["zlw-slv"] = { "Slovincian", 36822, "zlw-pom", "Latn", strip_diacritics = {remove_diacritics = c.macron .. c.breve}, } return require("Module:languages").finalizeData(m, "language") 4z3umhhk0j9curjvkejw4agfp9ficlc 231364 231363 2026-04-14T05:52:35Z Lee 19 [[:en:Module:languages/data/exceptional]] වෙතින් එක් සංශෝධනයක් 231363 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "Proto-Khasian", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "aav-nic", "Latn", type = "reconstructed", } m["aav-pkl-pro"] = { "Proto-Pnar-Khasi-Lyngngam", 116773259, "aav-pkl", "Latn", type = "reconstructed", } m["aav-pro"] = { -- mkh-pro will merge into this "Proto-Austroasiatic", 116773186, "aav", "Latn", type = "reconstructed", } m["afa-pro"] = { "Proto-Afroasiatic", 269125, "afa", "Latn", type = "reconstructed", } m["alg-aga"] = { "Agawam", nil, "alg-eas", "Latn", } m["alg-pro"] = { "Proto-Algonquian", 7251834, "alg", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["alv-ama"] = { "Amasi", 4740400, "nic-grs", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}, } m["alv-bgu"] = { "Bainouk Gubeeher", 17002646, "alv-bny", "Latn", } m["alv-bua-pro"] = { "Proto-Bua", 116773723, "alv-bua", "Latn", type = "reconstructed", } m["alv-cng-pro"] = { "Proto-Cangin", 116773726, "alv-cng", "Latn", type = "reconstructed", } m["alv-edo-pro"] = { "Proto-Edoid", 116773206, "alv-edo", "Latn", type = "reconstructed", } m["alv-fli-pro"] = { "Proto-Fali", 116773754, "alv-fli", "Latn", type = "reconstructed", } m["alv-gbe-pro"] = { "Proto-Gbe", 116773208, "alv-gbe", "Latn", type = "reconstructed", } m["alv-gng-pro"] = { "Proto-Guang", 116773757, "alv-gng", "Latn", type = "reconstructed", } m["alv-gtm-pro"] = { "Proto-Central Togo", 116773732, "alv-gtm", "Latn", type = "reconstructed", } m["alv-gwa"] = { "Gwara", 16945580, "nic-pla", "Latn", } m["alv-hei-pro"] = { "Proto-Heiban", 116773760, "alv-hei", "Latn", type = "reconstructed", } m["alv-ido-pro"] = { "Proto-Idomoid", 116773764, "alv-ido", "Latn", type = "reconstructed", } m["alv-igb-pro"] = { "Proto-Igboid", 116773765, "alv-igb", "Latn", type = "reconstructed", } m["alv-kwa-pro"] = { "Proto-Kwa", 116773780, "alv-kwa", "Latn", type = "reconstructed", } m["alv-mum-pro"] = { "Proto-Mumuye", 116773791, "alv-mum", "Latn", type = "reconstructed", } m["alv-nup-pro"] = { "Proto-Nupoid", 116773795, "alv-nup", "Latn", type = "reconstructed", } m["alv-pro"] = { "Proto-Atlantic-Congo", 116732838, "alv", "Latn", type = "reconstructed", } m["alv-edk-pro"] = { "Proto-Edekiri", nil, "alv-edk", "Latn", type = "reconstructed", } m["alv-yor-pro"] = { "Proto-Yoruba", nil, "alv-yor", "Latn", type = "reconstructed", } m["alv-yrd-pro"] = { "Proto-Yoruboid", 116773824, "alv-yrd", "Latn", type = "reconstructed", } m["alv-von-pro"] = { "Proto-Volta-Niger", 116773820, "alv-von", "Latn", type = "reconstructed", } m["apa-pro"] = { "Proto-Apachean", 116773135, "apa", "Latn", type = "reconstructed", } m["aql-pro"] = { "Proto-Algic", 18389588, "aql", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["art-adu"] = { "Adûni", 1232159, "art", "Latn", type = "appendix-constructed", } m["art-bel"] = { "Belter Creole", 108055510, "art", "Latn", type = "appendix-constructed", sort_key = { remove_diacritics = c.acute, from = {"ɒ"}, to = {"a"}, }, } m["art-blk"] = { "Bolak", 2909283, "art", "Latn", type = "appendix-constructed", } m["art-bsp"] = { "Black Speech", 686210, "art", "Latn, Teng", type = "appendix-constructed", } m["art-com"] = { "Communicationssprache", 35227, "art", "Latn", type = "appendix-constructed", } m["art-dtk"] = { "Dothraki", 2914733, "art", "Latn", type = "appendix-constructed", } m["art-elo"] = { "Eloi", nil, "art", "Latn", type = "appendix-constructed", } m["art-gld"] = { "Goa'uld", 19823, "art", "Latn, Egyp, Mero", type = "appendix-constructed", } m["art-lap"] = { "Lapine", 6488195, "art", "Latn", type = "appendix-constructed", } m["art-man"] = { "Mandalorian", 54289, "art", "Latn", type = "appendix-constructed", } m["art-mun"] = { "Mundolinco", 851355, "art", "Latn", type = "appendix-constructed", } m["art-nav"] = { "Naʼvi", 316939, "art", "Latn", type = "appendix-constructed", } m["art-vlh"] = { "High Valyrian", 64483808, "art", "Latn", type = "appendix-constructed", } m["ath-nic"] = { "Nicola", 20609, "ath-nor", "Latn", } m["ath-pro"] = { "Proto-Athabaskan", 104841722, "ath", "Latn", type = "reconstructed", } m["auf-pro"] = { "Proto-Arawa", 116773706, "auf", "Latn", type = "reconstructed", } m["aus-alu"] = { "Alungul", 16827670, "aus-pmn", "Latn", } m["aus-and"] = { "Andjingith", 4754509, "aus-pmn", "Latn", } m["aus-ang"] = { "Angkula", 16828520, "aus-pmn", "Latn", } m["aus-arn-pro"] = { "Proto-Arnhem", 116773720, "aus-arn", "Latn", type = "reconstructed", } m["aus-bra"] = { "Barranbinya", 4863220, "aus-pmn", "Latn", } m["aus-brm"] = { "Barunggam", 4865914, "aus-pmn", "Latn", } m["aus-cww-pro"] = { "Proto-Central New South Wales", 116773199, "aus-cww", "Latn", type = "reconstructed", } m["aus-dal-pro"] = { "Proto-Daly", 116773743, "aus-dal", "Latn", type = "reconstructed", } m["aus-guw"] = { "Guwar", 6652138, "aus-pam", "Latn", } m["aus-lsw"] = { "Little Swanport", 6652138, "qfa-unc", "Latn", } m["aus-mbi"] = { "Mbiywom", 6799701, "aus-pmn", "Latn", } m["aus-ngk"] = { "Ngkoth", 7022405, "aus-pmn", "Latn", } m["aus-nyu-pro"] = { "Proto-Nyulnyulan", 116773797, "aus-nyu", "Latn", type = "reconstructed", } m["aus-pam-pro"] = { "Proto-Pama-Nyungan", 33942, "aus-pam", "Latn", type = "reconstructed", } m["aus-tul"] = { "Tulua", 16938541, "aus-pam", "Latn", } m["aus-uwi"] = { "Uwinymil", 7903995, "aus-arn", "Latn", } m["aus-wdj-pro"] = { "Proto-Iwaidjan", 116773767, "aus-wdj", "Latn", type = "reconstructed", } m["aus-won"] = { "Wong-gie", nil, "aus-pam", "Latn", } m["aus-wul"] = { "Wulguru", 8039196, "aus-dyb", "Latn", } m["aus-ynk"] = { -- contrast nny "Yangkaal", 3913770, "aus-tnk", "Latn", } m["awd-amc-pro"] = { "Proto-Amuesha-Chamicuro", nil, "awd", "Latn", type = "reconstructed", } m["awd-kmp-pro"] = { "Proto-Kampa", nil, "awd", "Latn", type = "reconstructed", } m["awd-prw-pro"] = { "Proto-Paresi-Waura", nil, "awd", "Latn", type = "reconstructed", } m["awd-ama"] = { "Amarizana", 16827787, "awd", "Latn", } m["awd-ana"] = { "Anauyá", 16828252, "awd", "Latn", } m["awd-apo"] = { "Apolista", 16916645, "awd", "Latn", } m["awd-cab"] = { "Cabre", 16850160, "awd", "Latn", } m["awd-gnu"] = { "Guinau", 3504087, "awd", "Latn", } m["awd-kar"] = { "Cariay", 16920253, "awd", "Latn", } m["awd-kaw"] = { "Kawishana", 6379993, "awd-nwk", "Latn", } m["awd-kus"] = { "Kustenau", 5196293, "awd", "Latn", } m["awd-man"] = { "Manao", 6746920, "awd", "Latn", } m["awd-mar"] = { "Marawan", 6755108, "awd", "Latn", } m["awd-mpr"] = { "Maipure", 6736872, "awd", "Latn", } m["awd-mrt"] = { "Mariaté", 16910017, "awd-nwk", "Latn", } m["awd-nwk-pro"] = { "Proto-Nawiki", 116773234, "awd-nwk", "Latn", type = "reconstructed", } m["awd-pai"] = { "Paikoneka", 128807835, "awd", "Latn", } m["awd-pas"] = { "Pasé", 7143168, "awd-nwk", "Latn", } m["awd-pro"] = { "Proto-Arawak", 97573478, "awd", "Latn", type = "reconstructed", } m["awd-she"] = { "Shebayo", 7492248, "awd", "Latn", } m["awd-taa-pro"] = { "Proto-Ta-Arawak", 116773282, "awd-taa", "Latn", type = "reconstructed", } m["awd-wai"] = { "Wainumá", 16910017, "awd-nwk", "Latn", } m["awd-yum"] = { "Yumana", 8061062, "awd-nwk", "Latn", } m["azc-caz"] = { "Cazcan", 5055514, "azc", "Latn", } m["azc-cup-pro"] = { "Proto-Cupan", 116773738, "azc-cup", "Latn", type = "reconstructed", } m["azc-ktn"] = { "Kitanemuk", 3197558, "azc-tak", "Latn", } m["azc-nah-pro"] = { "Proto-Nahuan", 7251860, "azc-nah", "Latn", type = "reconstructed", } m["azc-num-pro"] = { "Proto-Numic", 116773247, "azc-num", "Latn", type = "reconstructed", } m["azc-pro"] = { "Proto-Uto-Aztecan", 96400333, "azc", "Latn", type = "reconstructed", } m["azc-tak-pro"] = { "Proto-Takic", 116773283, "azc-tak", "Latn", type = "reconstructed", } m["azc-tat"] = { "Tataviam", 743736, "azc", "Latn", } m["ber-pro"] = { "Proto-Berber", 2855698, "ber", "Latn", type = "reconstructed", } m["ber-fog"] = { "Fogaha", 107610173, "ber", "Latn", } m["ber-zuw"] = { "Zuwara", 4117169, "ber", "Latn", } m["bnt-bal"] = { "Balong", 93935237, "bnt-bbo", "Latn", } m["bnt-bon"] = { "Boma Nkuu", nil, "bnt", "Latn", } m["bnt-boy"] = { "Boma Yumu", nil, "bnt", "Latn", } m["bnt-bwa"] = { "Bwala", 128810345, "bnt-tek", "Latn", } m["bnt-cmw"] = { "Chimwiini", 4958328, "bnt-swh", "Latn", } m["bnt-ind"] = { "Indanga", 51412803, "bnt", "Latn", } m["bnt-lal"] = { "Lala (South Africa)", 6480154, "bnt-ngu", "Latn", } m["bnt-mpi"] = { "Mpiin", 93937013, "bnt-bdz", "Latn", } m["bnt-mpu"] = { "Mpuono", -- not to be confused with Mbuun zmp 36056, "bnt", "Latn", } m["bnt-ngu-pro"] = { "Proto-Nguni", 961559, "bnt-ngu", "Latn", type = "reconstructed", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron}, } m["bnt-phu"] = { "Phuthi", 33796, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, } m["bnt-pro"] = { "Proto-Bantu", 3408025, "bnt", "Latn", type = "reconstructed", sort_key = "bnt-pro-sortkey", } m["bnt-sab-pro"] = { "Proto-Sabaki", nil, -- Q2209395 is the code for the Sabaki family "bnt-sab", "Latn", type = "reconstructed", } m["bnt-sbo"] = { "South Boma", nil, "bnt", "Latn", } m["bnt-sts-pro"] = { "Proto-Sotho-Tswana", 116773278, "bnt-sts", "Latn", type = "reconstructed", } m["btk-pro"] = { "Proto-Batak", 116773191, "btk", "Latn", type = "reconstructed", } m["cau-abz-pro"] = { "Proto-Abkhaz-Abaza", 7251831, "cau-abz", "Latn", type = "reconstructed", } m["cau-and-pro"] = { "Proto-Andian", nil, "cau-and", "Latn", type = "reconstructed", } m["cau-ava-pro"] = { "Proto-Avaro-Andian", 116773187, "cau-ava", "Latn", type = "reconstructed", } m["cau-cir-pro"] = { "Proto-Circassian", 7251838, "cau-cir", "Latn", type = "reconstructed", } m["cau-drg-pro"] = { "Proto-Dargwa", 116773205, "cau-drg", "Latn", type = "reconstructed", } m["cau-lzg-pro"] = { "Proto-Lezghian", 116773223, "cau-lzg", "Latn", type = "reconstructed", } m["cau-nec-pro"] = { "Proto-Northeast Caucasian", 116773244, "cau-nec", "Latn", type = "reconstructed", } m["cau-nkh-pro"] = { "Proto-Nakh", 108032840, "cau-nkh", "Latn", type = "reconstructed", } m["cau-nwc-pro"] = { "Proto-Northwest Caucasian", 7251861, "cau-nwc", "Latn", type = "reconstructed", } m["cau-tsz-pro"] = { "Proto-Tsezian", 116773287, "cau-tsz", "Latn", type = "reconstructed", } m["cba-ata"] = { "Atanques", 4812783, "cba", "Latn", } m["cba-cat"] = { "Catío Chibcha", 7083619, "cba", "Latn", } m["cba-dor"] = { "Dorasque", 5297532, "cba", "Latn", } m["cba-dui"] = { "Duit", 3041061, "cba", "Latn", } m["cba-hue"] = { "Huetar", 35514, "cba", "Latn", } m["cba-nut"] = { "Nutabe", 7070405, "cba", "Latn", } m["cba-pro"] = { "Proto-Chibchan", 116773203, "cba", "Latn", type = "reconstructed", } m["ccs-pro"] = { "Proto-Kartvelian", 2608203, "ccs", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["ccs-gzn-pro"] = { "Proto-Georgian-Zan", 23808119, "ccs-gzn", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["cdc-cbm-pro"] = { "Proto-Central Chadic", 116773197, "cdc-cbm", "Latn", type = "reconstructed", } m["cdc-mas-pro"] = { "Proto-Masa", 116773789, "cdc-mas", "Latn", type = "reconstructed", } m["cdc-pro"] = { "Proto-Chadic", 116773201, "cdc", "Latn", type = "reconstructed", } m["cdd-pro"] = { "Proto-Caddoan", 116773725, "cdd", "Latn", type = "reconstructed", } m["cel-bry-pro"] = { "Proto-Brythonic", 1248800, "cel-bry", "Latn, Polyt", sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-gal"] = { "Gallaecian", 3094789, "cel-his", } m["cel-gau"] = { "Gaulish", 29977, "cel", "Latn, Polyt, Ital", strip_diacritics = { Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer}, }, sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-pro"] = { "Proto-Celtic", 653649, "cel", "Latn", type = "reconstructed", sort_key = "cel-pro-sortkey", } m["chi-pro"] = { "Proto-Chimakuan", 116773734, "chi", "Latn", type = "reconstructed", } m["chm-pro"] = { "Proto-Mari", 116773788, "chm", "Latn", type = "reconstructed", } m["cmc-pro"] = { "Proto-Chamic", 114793834, "cmc", "Latn", type = "reconstructed", } m["crp-bip"] = { "Basque-Icelandic Pidgin", 810378, "crp", "Latn", ancestors = "eu", } m["crp-gep"] = { "West Greenlandic Pidgin", 17036301, "crp", "Latn", ancestors = "kl", } m["crp-kia"] = { "Kiautschou German Pidgin", 108314615, "crp", "Latn", ancestors = "de", } m["crp-mar"] = { "Maroon Spirit Language", 1093206, "crp", "Latn", ancestors = "en", } m["crp-mpp"] = { "Macau Pidgin Portuguese", 128804537, "crp", "Hant, Latn", ancestors = "pt", sort_key = {Hant = "Hani-sortkey"}, } m["crp-rsn"] = { "Russenorsk", 505125, "crp", "Cyrl, Latn", ancestors = "nn, ru", translit = {Cyrl = "ru-translit"}, } m["crp-spp"] = { "Samoan Plantation Pidgin", 7409948, "crp", "Latn", ancestors = "en", } m["crp-slb"] = { "Solombala English", 7558525, "crp", "Cyrl, Latn", ancestors = "en, ru", translit = {Cyrl = "ru-translit"}, } m["crp-tpr"] = { "Taimyr Pidgin Russian", 16930506, "crp", "Cyrl", ancestors = "ru", translit = "ru-translit", } m["csu-bba-pro"] = { "Proto-Bongo-Bagirmi", 116773722, "csu-bba", "Latn", type = "reconstructed", } m["csu-maa-pro"] = { "Proto-Mangbetu", 116773786, "csu-maa", "Latn", type = "reconstructed", } m["csu-pro"] = { "Proto-Central Sudanic", 116773730, "csu", "Latn", type = "reconstructed", } m["csu-sar-pro"] = { "Proto-Sara", 116773809, "csu-sar", "Latn", type = "reconstructed", } m["cus-ash"] = { "Ashraaf", 4805855, "cus-som", "Latn", } m["cus-hec-pro"] = { "Proto-Highland East Cushitic", 116773761, "cus-hec", "Latn", type = "reconstructed", } m["cus-som-pro"] = { "Proto-Somaloid", nil, "cus-som", "Latn", type = "reconstructed", } m["cus-sou-pro"] = { "Proto-South Cushitic", 126081567, "cus-sou", "Latn", type = "reconstructed", } m["cus-pro"] = { "Proto-Cushitic", 116773204, "cus", "Latn", type = "reconstructed", } m["dmn-dam"] = { "Dama (Sierra Leone)", 19601574, "dmn", "Latn", } m["dra-bry"] = { "Beary", 1089116, "qfa-mix", "Mlym, Knda", ancestors = "ml, tcy", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["dra-cen-pro"] = { "Proto-Central Dravidian", nil, "dra-cen", "Latn", type = "reconstructed", } m["dra-mkn"] = { "Middle Kannada", 128810572, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-nor-pro"] = { "Proto-North Dravidian", 124433593, "dra-nor", "Latn", type = "reconstructed", } m["dra-okn"] = { "Old Kannada", 15723156, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-ote"] = { "Old Telugu", 126720868, "dra-tel", "Telu", translit = "te-translit", } m["dra-pro"] = { "Proto-Dravidian", 1702853, "dra", "Latn", type = "reconstructed", } m["dra-sdo-pro"] = { "Proto-South Dravidian I", 104847952, -- Wikipedia's "Proto-South Dravidian" is Proto-South Dravidian I in this scheme. "dra-sdo", "Latn", type = "reconstructed", } m["dra-sdt-pro"] = { "Proto-South Dravidian II", 128885257, "dra-sdt", "Latn", type = "reconstructed", } m["dra-sou-pro"] = { "Proto-South Dravidian", 128886121, "dra-sou", "Latn", type = "reconstructed", } m["egx-dem"] = { "Demotic Egyptian", 36765, "egx", "Latn, Egyd, Polyt", sort_key = { Latn = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "e", "ꜥ", "y", "w", "b", "p", "f", "m", "n", "r", "l", "ḥ", "ḫ", "h̭", "ẖ", "h", "š", "s", "q", "k", "g", "ṱ", "ṯ", "t", "ḏ", "%.", "⸗"}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]} }, }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dmn-pro"] = { "Proto-Mande", 116773785, "dmn", "Latn", type = "reconstructed", } m["dmn-mdw-pro"] = { "Proto-Western Mande", 116773822, "dmn-mdw", "Latn", type = "reconstructed", } m["dru-pro"] = { "Proto-Rukai", 116773807, "map", "Latn", type = "reconstructed", } m["ero-gsz"] = { "Geshiza", nil, "ero", "Latn", } m["ero-nya"] = { "Nyagrong Minyag", nil, "ero", "Latn", } m["ero-tau"] = { "Stau", nil, "ero", "Latn", } m["esx-esk-pro"] = { "Proto-Eskimo", 7251842, "esx-esk", "Latn", type = "reconstructed", } m["esx-ink"] = { "Inuktun", 1671647, "esx-inu", "Latn", } m["esx-inq"] = { "Inuinnaqtun", 28070, "esx-inu", "Latn", } m["esx-inu-pro"] = { "Proto-Inuit", 60785588, "esx-inu", "Latn", type = "reconstructed", } m["esx-pro"] = { "Proto-Eskimo-Aleut", 7251843, "esx", "Latn", type = "reconstructed", } m["esx-tut"] = { "Tunumiisut", 15665389, "esx-inu", "Latn", } m["euq-pro"] = { "Proto-Basque", 938011, "euq", "Latn", type = "reconstructed", } m["gba-pro"] = { "Proto-Gbaya", nil, "gba", "Latn", type = "reconstructed", } m["gem-pro"] = { "Proto-Germanic", 669623, "gem", "Latn", type = "reconstructed", sort_key = "gem-pro-sortkey", } m["gme-bur"] = { "Burgundian", 47625, "gme", "Latn", } m["gme-cgo"] = { "Crimean Gothic", 36211, "gme", "Latn", } m["gmq-gut"] = { "Gutnish", 1256646, "gmq", "Latn", ancestors = "gmq-ogt", } m["gmq-jmk"] = { "Jamtish", 35512, "gmq-eas", "Latn", } m["gmq-mno"] = { "Middle Norwegian", 3417070, "gmq-wes", "Latn", } m["gmq-oda"] = { "Old Danish", 12330003, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-ogt"] = { "Old Gutnish", 1133488, "gmq", "Latn, Runr", ancestors = "non", } m["gmq-osw"] = { "Old Swedish", 2417210, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-pro"] = { "Proto-Norse", 1671294, "gmq", "Runr", translit = "Runr-translit", } m["gmq-scy"] = { "Scanian", 768017, "gmq-eas", "Latn", } m["gmw-bgh"] = { "Bergish", 329030, "gmw-frk", "Latn", } m["gmw-cfr"] = { "Central Franconian", 572197, "gmw-hgm", "Latn", ancestors = "gmh", wikimedia_codes = "ksh", } m["gmw-ecg"] = { "East Central German", 499344, -- subsumes Q699284, Q152965 "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-fin"] = { "Fingallian", 3072588, "gmw-ian", "Latn", } m["gmw-gts"] = { "Gottscheerish", 533109, "gmw-hgm", "Latn", ancestors = "bar", } m["gmw-jdt"] = { "Jersey Dutch", 1687911, "gmw-frk", "Latn", ancestors = "nl", } m["gmw-msc"] = { "Middle Scots", 3327000, "gmw-ang", "Latn", ancestors = "enm-esc", } m["gmw-pro"] = { "Proto-West Germanic", 78079021, "gmw", "Latn, Runr", -- type = "reconstructed", -- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added sort_key = "gmw-pro-sortkey", } m["gmw-rfr"] = { "Rhine Franconian", 707007, "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-stm"] = { "Sathmar Swabian", 2223059, "gmw-hgm", "Latn", ancestors = "swg", } m["gmw-tsx"] = { "Transylvanian Saxon", 260942, "gmw-hgm", "Latn", ancestors = "gmw-cfr", } m["gmw-vog"] = { "Volga German", 312574, "gmw-hgm", "Latn", ancestors = "gmw-rfr", } m["gmw-zps"] = { "Zipser German", 205548, "gmw-hgm", "Latn", ancestors = "gmh", } m["gn-cls"] = { "Classical Guarani", 17478065, "gn", "Latn", } m["grk-cal"] = { "Calabrian Greek", 1146398, "grk", "Latn, Grek", ancestors = "grk-ita", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-ita"] = { "Italiot Greek", 19720507, "grk", "Latn, Grek", ancestors = "gkm", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-mar"] = { "Mariupol Greek", 4400023, "grk", "Cyrl, Latn, Grek", ancestors = "gkm", translit = { Cyrl = "grk-mar-translit", Grek = "grk-mar-translit", }, override_translit = true, strip_diacritics = { Cyrl = {remove_diacritics = c.acute}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-pro"] = { "Proto-Hellenic", 1231805, "grk", "Latn, Polyt", type = "reconstructed", sort_key = {Latn = { from = {"ʰ", "ʷ"}, to = {"h", "w"}, remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron }}, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in -- the translit section } m["hmn-pro"] = { "Proto-Hmongic", 116773210, "hmn", "Latn", type = "reconstructed", } m["hmx-mie-pro"] = { "Proto-Mienic", 116773229, "hmx-mie", "Latn", type = "reconstructed", } m["hmx-pro"] = { "Proto-Hmong-Mien", 7251846, "hmx", "Latn", type = "reconstructed", } m["hyx-pro"] = { "Proto-Armenian", 3848498, "hyx", "Latn", type = "reconstructed", } m["iir-nur-pro"] = { "Proto-Nuristani", 116773248, "iir-nur", "Latn", type = "reconstructed", } m["iir-pro"] = { "Proto-Indo-Iranian", 966439, "iir", "Latn", type = "reconstructed", } m["ijo-pro"] = { "Proto-Ijoid", 116773766, "ijo", "Latn", type = "reconstructed", } m["inc-apa"] = { "Apabhramsa", 616419, "inc-mid", "Deva, Shrd, Sidd", ancestors = "pra", translit = { Deva = "sa-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] }, } m["inc-ash"] = { "Ashokan Prakrit", 104854379, "inc-mid", "Brah, Khar", ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Khar = "Khar-translit", }, } m["inc-dng-pro"] = { "Proto-Dangari", nil, "inc-dng", "Latn", type = "reconstructed", } m["inc-kam"] = { "Kamarupi Prakrit", 6356097, "inc-bas", "Brah, Sidd", -- Brah, Sidd translit in [[Module:scripts/data]] } m["inc-kho"] = { "Kholosi", 24952008, "inc-snd", "Latn", } m["inc-krd-pro"] = { "Proto-Kamta", 128816843, "inc-bas", "Latn", ancestors = "inc-kam", type = "reconstructed", } m["inc-mas"] = { "Middle Assamese", 128806836, "inc-bas", "as-Beng", ancestors = "inc-oas", translit = "inc-mas-translit", } m["inc-mbn"] = { "Middle Bengali", 113559927, "inc-bas", "Beng", ancestors = "inc-obn", translit = "inc-mbn-translit", } m["inc-mgu"] = { "Middle Gujarati", 24907429, "inc-wes", "Deva", ancestors = "inc-ogu", } m["inc-mor"] = { "Middle Odia", 128810882, "inc-eas", "Orya", ancestors = "inc-oor", } m["inc-oas"] = { "Early Assamese", 85758237, "inc-bas", "as-Beng", ancestors = "inc-kam", translit = "inc-oas-translit", } m["inc-oaw"] = { "Old Awadhi", nil, "inc-hie", "Deva, Kthi, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Kthi = "sa-Kthi-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-obn"] = { "Old Bengali", 113559926, "inc-bas", "Beng", } m["inc-ogu"] = { "Old Gujarati", 24907427, "inc-wes", "Deva", translit = "sa-translit", } m["inc-ohi"] = { "Old Hindi", 48767781, "inc-hiw", "Deva, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-oor"] = { "Old Odia", 128807801, "inc-eas", "Orya", } m["inc-opa"] = { "Old Punjabi", 115270971, "inc-pan", "Guru, pa-Arab", translit = { Guru = "inc-opa-Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun}, } m["inc-pro"] = { "Proto-Indo-Aryan", 23808344, "inc", "Latn", type = "reconstructed", } m["ine-ana-pro"] = { "Proto-Anatolian", 7251833, "ine-ana", "Latn", type = "reconstructed", } m["ine-bsl-pro"] = { "Proto-Balto-Slavic", 1703347, "ine-bsl", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", c.acute, c.macron, "ˀ"}, to = {"a", "e", "i", "o", "u"} }, } m["ine-kal"] = { "Kalašma", 122770439, "ine-ana", "Xsux", } m["ine-pae"] = { "Paeonian", 2705672, "ine", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ine-pro"] = { "Proto-Indo-European", 37178, "ine", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ĺ", "ḿ", "ń", "ŕ", "ǵ", "ḱ", "ʰ", "ʷ", "₁", "₂", "₃", c.ringbelow, c.acute, c.macron}, to = {"a", "e", "i", "o", "u", "l", "m", "n", "r", "g'", "k'", "¯h", "¯w", "1", "2", "3"} }, } m["ine-toc-pro"] = { "Proto-Tocharian", 104841462, "ine-toc", "Latn", type = "reconstructed", } m["xme-old"] = { "Old Median", 36461, "xme", "Polyt, Latn", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-mid"] = { "Middle Median", 12836150, "xme", "Latn", } m["xme-ker"] = { "Kermanic", 129850, "xme", "fa-Arab, Latn, Hebr", ancestors = "xme-mid", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-taf"] = { "Tafreshi", nil, "xme", "fa-Arab, Latn", ancestors = "xme-mid", } m["xme-ttc-pro"] = { "Proto-Tatic", 122973870, "xme-ttc", "Latn", ancestors = "xme-mid", } m["xme-kls"] = { "Kalasuri", nil, "xme-ttc", ancestors = "xme-ttc-nor", } m["xme-klt"] = { "Kilit", 3612452, "xme-ttc", "Cyrl", -- and fa-Arab? } m["xme-ott"] = { "Old Tati", 434697, "xme-ttc", "fa-Arab, Latn", } m["ira-kms-pro"] = { "Proto-Komisenian", 116773777, "ira-kms", "Latn", type = "reconstructed", } m["ira-mpr-pro"] = { "Proto-Medo-Parthian", 116773227, "ira-mpr", "Latn", type = "reconstructed", } m["ira-pat-pro"] = { "Proto-Pathan", 116773255, "ira-pat", "Latn", type = "reconstructed", } m["ira-pro"] = { "Proto-Iranian", 4167865, "ira", "Latn", type = "reconstructed", } m["ira-zgr-pro"] = { "Proto-Zaza-Gorani", 116775031, "ira-zgr", "Latn", type = "reconstructed", } m["xsc-pro"] = { "Proto-Scythian", 116773273, "xsc", "Latn", type = "reconstructed", } m["xsc-sar-pro"] = { "Proto-Sarmatian", 116773249, "xsc-sar", "Latn", type = "reconstructed", } m["xsc-skw-pro"] = { "Proto-Saka-Wakhi", 116773267, "xsc-skw", "Latn", type = "reconstructed", } m["xsc-sak-pro"] = { "Proto-Saka", 116773264, "xsc-sak", "Latn", type = "reconstructed", } m["ira-sym-pro"] = { "Proto-Shughni-Yazghulami-Munji", 116773813, "ira-sym", "Latn", type = "reconstructed", } m["ira-sgi-pro"] = { "Proto-Sanglechi-Ishkashimi", 116773808, "ira-sgi", "Latn", type = "reconstructed", } m["ira-mny-pro"] = { "Proto-Munji-Yidgha", 116773792, "ira-mny", "Latn", type = "reconstructed", } m["ira-shy-pro"] = { "Proto-Shughni-Yazghulami", 116773812, "ira-shy", "Latn", type = "reconstructed", } m["ira-shr-pro"] = { "Proto-Shughni-Roshani", 116773811, "ira-shr", "Latn", type = "reconstructed", } m["ira-sgc-pro"] = { "Proto-Sogdic", 116773276, "ira-sgc", "Latn", type = "reconstructed", } m["ira-wnj"] = { "Vanji", 3398419, "ira-shy", "Latn", } m["iro-ere"] = { "Erie", 5388365, "iro-nor", "Latn", } m["iro-min"] = { "Mingo", 128531, "iro-nor", "Latn", ietf_subtag = "i-mingo", -- grandfathered IETF tag } m["iro-nor-pro"] = { "Proto-North Iroquoian", 116773242, "iro-nor", "Latn", type = "reconstructed", } m["iro-pro"] = { "Proto-Iroquoian", 7251852, "iro", "Latn", type = "reconstructed", } m["itc-pro"] = { "Proto-Italic", 17102720, "itc", "Latn", type = "reconstructed", } m["itc-psa"] = { "Pre-Samnite", 7239186, "itc-sbl", "Ital, Polyt, Latn", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["jpx-hcj"] = { "Hachijō", 5637049, "jpx", "Jpan", ancestors = "ojp-eas", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jpx-pro"] = { "Proto-Japonic", 3924309, "jpx", "Latn", type = "reconstructed", } m["jpx-ryu-pro"] = { "Proto-Ryukyuan", 56349069, "jpx-ryu", "Latn", type = "reconstructed", } m["kar-pro"] = { "Proto-Karen", 85794783, "kar", "Latn", type = "reconstructed", } m["kca-eas"] = { "Eastern Khanty", 30304622, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-nor"] = { "Northern Khanty", 30304527, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-pro"] = { "Proto-Khanty", 127505171, "kca", "Latn", type = "reconstructed", } m["kca-sou"] = { "Southern Khanty", 30304618, "kca", "Cyrl", translit = "kca-translit", override_translit = true, } m["khi-kho-pro"] = { "Proto-Khoe", 116773218, "khi-kho", "Latn", type = "reconstructed", } m["khi-kun"] = { "ǃKung", 32904, "khi-kxa", "Latn", } m["ko-ear"] = { "Early Modern Korean", 756014, "qfa-kor", "Kore", ancestors = "okm", translit = "okm-translit", -- Kore strip_diacritics in [[Module:scripts/data]] } m["kro-pro"] = { "Proto-Kru", 116773778, "kro", "Latn", type = "reconstructed", } m["ku-pro"] = { "Proto-Kurdish", 116773221, "ku", "Latn", type = "reconstructed", } m["map-ata-pro"] = { "Proto-Atayalic", 116773151, "map-ata", "Latn", type = "reconstructed", } m["map-bms"] = { "Banyumasan", 33219, "map", "Latn, Java", } m["map-pro"] = { "Proto-Austronesian", 49230, "map", "Latn", type = "reconstructed", } m["mis-hkl"] = { "Kelantan Peranakan Hokkien", 108794818, "qfa-mix", ancestors = "nan-hbl, sou, mfa", } m["mis-idn"] = { "Idiom Neutral", 35847, "art", "Latn", type = "appendix-constructed", } m["mis-isa"] = { "Isaurian", 16956868, nil, -- "Xsux, Hluw, Latn", } m["mis-jie"] = { "Jie", 124424186, nil, "Hani", sort_key = "Hani-sortkey", } m["mis-jzh"] = { "Jizhao", 45242758, "qfa-bej", "Latn", } m["mis-kas"] = { "Kassite", 35612, nil, "Xsux", } m["mis-mmd"] = { "Mimi of Decorse", 6862206, nil, "Latn", } m["mis-mmn"] = { "Mimi of Nachtigal", 6862207, nil, "Latn", } m["mis-phi"] = { "Philistine", 2230924, nil, "Phnx", -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["mis-rou"] = { "Rouran", 48816637, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tdl"] = { "Turdulian", 133176492, } m["mis-tdt"] = { "Turdetanian", 133176461, } m["mis-tnw"] = { "Tangwang", 7683179, "qfa-mix", "Latn", ancestors = "cmn, sce", } m["mis-tuh"] = { "Tuyuhun", 48816625, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tuo"] = { "Tuoba", 48816629, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-wuh"] = { "Wuhuan", 118976867, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xbi"] = { "Xianbei", 4448647, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xnu"] = { "Xiongnu", 10901674, nil, "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mjg-mgl"] = { "Mongghul", 53765528, "mjg", "Latn", -- also Mong, Cyrl ? } m["mjg-mgr"] = { "Mangghuer", 56285392, "mjg", "Latn", -- also Mong, Cyrl ? } m["mkh-asl-pro"] = { "Proto-Aslian", 55630680, "mkh-asl", "Latn", type = "reconstructed", } m["mkh-ban-pro"] = { "Proto-Bahnaric", 116773189, "mkh-ban", "Latn", type = "reconstructed", } m["mkh-kat-pro"] = { "Proto-Katuic", 116773772, "mkh-kat", "Latn", type = "reconstructed", } m["mkh-khm-pro"] = { "Proto-Khmuic", 116773774, "mkh-khm", "Latn", type = "reconstructed", } m["mkh-kmr-pro"] = { "Proto-Khmeric", 55630684, "mkh-kmr", "Latn", type = "reconstructed", } m["mkh-mmn"] = { "Middle Mon", 121337926, "mkh-mnc", "Latn, Mymr", --and also Pallava ancestors = "omx", } m["mkh-mnc-pro"] = { "Proto-Monic", 116773231, "mkh-mnc", "Latn", type = "reconstructed", } m["mkh-mvi"] = { "Middle Vietnamese", 9199, "mkh-vie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mkh-pal-pro"] = { "Proto-Palaungic", 104847372, "mkh-pal", "Latn", type = "reconstructed", } m["mkh-pea-pro"] = { "Proto-Pearic", 116773804, "mkh-pea", "Latn", type = "reconstructed", } m["mkh-pkn-pro"] = { "Proto-Pakanic", 116773803, "mkh-pkn", "Latn", type = "reconstructed", } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. "Proto-Mon-Khmer", 7251859, "mkh", "Latn", type = "reconstructed", } m["mnw-tha"] = { -- To be removed. "Thai Mon", nil, "mkh-mnc", "Mymr, Thai", ancestors = "mkh-mmn", sort_key = { from = {"[%p]", "ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ", "[็-๎]", "([เแโใไ])([ก-ฮ])ฺ?"}, to = {"", "္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ", "", "%2%1"} }, } m["mkh-vie-pro"] = { "Proto-Vietic", 109432616, "mkh-vie", "Latn", type = "reconstructed", } m["mns-cen"] = { "Central Mansi", 128810384, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-nor"] = { "Northern Mansi", 30304537, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-pro"] = { "Proto-Mansi", 128883093, "mns", "Latn", type = "reconstructed", } m["mns-sou"] = { "Southern Mansi", 30304629, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mun-pro"] = { "Proto-Munda", 105102373, "mun", "Latn", type = "reconstructed", } m["myn-chl"] = { -- the stage after ''emy'' "Ch'olti'", 873995, "myn", "Latn", } m["myn-pro"] = { "Proto-Mayan", 3321532, "myn", "Latn", type = "reconstructed", } m["nai-ala"] = { "Alazapa", 128810233, nil, "Latn", } m["nai-bay"] = { "Bayogoula", 1563704, nil, "Latn", } m["nai-cal"] = { "Calusa", 51782, nil, "Latn", } m["nai-chi"] = { "Chiquimulilla", 25339627, "nai-xin", "Latn", } m["nai-chu-pro"] = { "Proto-Chumash", 116773736, "nai-chu", "Latn", type = "reconstructed", } m["nai-cig"] = { "Ciguayo", 20741700, nil, "Latn", } m["nai-ckn-pro"] = { "Proto-Chinookan", 116773735, "nai-ckn", "Latn", type = "reconstructed", } m["nai-guz"] = { "Guazacapán", 19572028, "nai-xin", "Latn", } m["nai-hit"] = { "Hitchiti", 1542882, "nai-mus", "Latn", } m["nai-ipa"] = { "Ipai", 3027474, "nai-yuc", "Latn", } m["nai-jtp"] = { "Jutiapa", nil, "nai-xin", "Latn", } m["nai-jum"] = { "Jumaytepeque", 25339626, "nai-xin", "Latn", } m["nai-kat"] = { "Kathlamet", 6376639, "nai-ckn", "Latn", } m["nai-klp-pro"] = { "Proto-Kalapuyan", 116773771, "nai-klp", "Latn", type = "reconstructed", } m["nai-knm"] = { "Konomihu", 3198734, "nai-shs", "Latn", } m["nai-kum"] = { "Kumeyaay", 4910139, "nai-yuc", "Latn", } m["nai-mac"] = { "Macoris", 21070851, nil, "Latn", } m["nai-mdu-pro"] = { "Proto-Maidun", 116773784, "nai-mdu", "Latn", type = "reconstructed", } m["nai-miz-pro"] = { "Proto-Mixe-Zoque", 7251858, "nai-miz", "Latn", type = "reconstructed", } m["nai-mus-pro"] = { "Proto-Muskogean", 116775368, "nai-mus", "Latn", type = "reconstructed", } m["nai-nao"] = { "Naolan", 6964594, nil, "Latn", } m["nai-nrs"] = { "New River Shasta", 7011254, "nai-shs", "Latn", } m["nai-okw"] = { "Okwanuchu", 3350126, "nai-shs", "Latn", } m["nai-per"] = { "Pericú", 3375369, nil, "Latn", } m["nai-pic"] = { "Picuris", 7191257, "nai-kta", "Latn", } m["nai-plp-pro"] = { "Proto-Plateau Penutian", 116773806, "nai-plp", "Latn", type = "reconstructed", } m["nai-pom-pro"] = { "Proto-Pomo", 116773262, "nai-pom", "Latn", type = "reconstructed", } m["nai-qng"] = { "Quinigua", 36360, nil, "Latn", } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan "Proto-Siouan-Catawban", 116773275, "nai-sca", "Latn", type = "reconstructed", } m["nai-sin"] = { "Sinacantán", 24190249, "nai-xin", "Latn", } m["nai-sln"] = { "Salvadoran Lenca", 3229434, "nai-len", "Latn", } m["nai-spt"] = { "Sahaptin", 3833015, "nai-shp", "Latn", } m["nai-tap"] = { "Tapachultec", 7684401, "nai-miz", "Latn", } m["nai-taw"] = { "Tawasa", 7689233, nil, "Latn", } m["nai-teq"] = { "Tequistlatec", 2964454, "nai-tqn", "Latn", } m["nai-tip"] = { "Tipai", 3027471, "nai-yuc", "Latn", } m["nai-tot-pro"] = { "Proto-Totozoquean", 116773285, "nai-tot", "Latn", type = "reconstructed", } m["nai-tsi-pro"] = { "Proto-Tsimshianic", nil, "nai-tsi", "Latn", type = "reconstructed", } m["nai-utn-pro"] = { "Proto-Utian", 116773290, "nai-utn", "Latn", type = "reconstructed", } m["nai-wai"] = { "Waikuri", 3118702, nil, "Latn", } m["nai-wji"] = { "Western Jicaque", 3178610, "nai-jcq", "Latn", } m["nai-yup"] = { "Yupiltepeque", 25339628, "nai-xin", "Latn", } m["nan-dat"] = { "Datian Min", 19855572, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-hbl"] = { "Hokkien", 1624231, "zhx-nan", "Hants, Latn, Bopo, Kana", wikimedia_codes = "zh-min-nan", generate_forms = "zh-generateforms", sort_key = { Hani = "Hani-sortkey", Kana = "Kana-sortkey" }, } m["nan-hlh"] = { "Hailufeng Min", 120755728, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-lnx"] = { "Longyan Min", 6674568, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-tws"] = { "Teochew", 36759, "zhx-nan", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["nan-zhe"] = { "Zhenan Min", 3846710, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-zsh"] = { "Sanxiang Min", 7420769, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["ngf-bin-pro"] = { "Proto-Binanderean", 137881672, "ngf-bin", "Latn", type = "reconstructed", } m["ngf-pro"] = { "Proto-Trans-New Guinea", 85794785, "ngf", "Latn", type = "reconstructed", } m["nic-bco-pro"] = { "Proto-Benue-Congo", 116773194, "nic-bco", "Latn", type = "reconstructed", } m["nic-bod-pro"] = { "Proto-Bantoid", 116773190, "nic-bod", "Latn", type = "reconstructed", } m["nic-eov-pro"] = { "Proto-Eastern Oti-Volta", 116773753, "nic-eov", "Latn", type = "reconstructed", } m["nic-gns-pro"] = { "Proto-Gurunsi", 116773759, "nic-gns", "Latn", type = "reconstructed", } m["nic-grf-pro"] = { "Proto-Grassfields", 116773755, "nic-grf", "Latn", type = "reconstructed", } m["nic-gur-pro"] = { "Proto-Gur", 116773758, "nic-gur", "Latn", type = "reconstructed", } m["nic-jkn-pro"] = { "Proto-Jukunoid", 116773769, "nic-jkn", "Latn", type = "reconstructed", } m["nic-lcr-pro"] = { "Proto-Lower Cross River", 116773782, "nic-lcr", "Latn", type = "reconstructed", } m["nic-ogo-pro"] = { "Proto-Ogoni", 116773799, "nic-ogo", "Latn", type = "reconstructed", } m["nic-ovo-pro"] = { "Proto-Oti-Volta", 116773802, "nic-ovo", "Latn", type = "reconstructed", } m["nic-plt-pro"] = { "Proto-Plateau", 116773805, "nic-plt", "Latn", type = "reconstructed", } m["nic-pro"] = { "Proto-Niger-Congo", 108000748, "nic", "Latn", type = "reconstructed", } m["nic-ubg-pro"] = { "Proto-Ubangian", 116773818, "nic-ubg", "Latn", type = "reconstructed", } m["nic-ucr-pro"] = { "Proto-Upper Cross River", 116773819, "nic-ucr", "Latn", type = "reconstructed", } m["nic-vco-pro"] = { "Proto-Volta-Congo", 116773293, "nic-vco", "Latn", type = "reconstructed", } m["njo-jgl"] = { "Chungli Ao", 55607615, "sit-aao", "Latn", } m["nub-har"] = { "Haraza", 19572059, "nub", "Arab, Latn", } m["nub-pro"] = { "Proto-Nubian", 116773246, "nub", "Latn", type = "reconstructed", } m["omq-cha-pro"] = { "Proto-Chatino", 116773202, "omq-cha", "Latn", type = "reconstructed", } m["omq-maz-pro"] = { "Proto-Mazatec", 116773790, "omq-maz", "Latn", type = "reconstructed", } m["omq-mix-pro"] = { "Proto-Mixtecan", 21573423, "omq-mix", "Latn", type = "reconstructed", } m["omq-mxt-pro"] = { "Proto-Mixtec", 21573424, "omq-mxt", "Latn", type = "reconstructed", } m["omq-otp-pro"] = { "Proto-Oto-Pamean", 116773251, "omq-otp", "Latn", type = "reconstructed", } m["omq-pro"] = { "Proto-Oto-Manguean", 33669, "omq", "Latn", type = "reconstructed", } m["omq-sjq"] = { "San Juan Quiahije Chatino", 138330751, "omq-cha", "Latn", } m["omq-tel"] = { "Teposcolula Mixtec", nil, "omq-mxt", "Latn", } m["omq-teo"] = { "Teojomulco Chatino", 25340451, "omq-cha", "Latn", } m["omq-tri-pro"] = { "Proto-Triqui", 116773817, "omq-tri", "Latn", type = "reconstructed", } m["omq-zap-pro"] = { "Proto-Zapotecan", 116773297, "omq-zap", "Latn", type = "reconstructed", } m["omq-zpc-pro"] = { "Proto-Zapotec", 116773296, "omq-zpc", "Latn", type = "reconstructed", } m["omv-aro-pro"] = { "Proto-Aroid", 116773721, "omv-aro", "Latn", type = "reconstructed", } m["omv-diz-pro"] = { "Proto-Dizoid", 116773750, "omv-diz", "Latn", type = "reconstructed", } m["omv-pro"] = { "Proto-Omotic", 116773800, "omv", "Latn", type = "reconstructed", } m["oto-otm-pro"] = { "Proto-Otomi", 5908710, "oto-otm", "Latn", type = "reconstructed", } m["oto-pro"] = { "Proto-Otomian", 116773252, "oto", "Latn", type = "reconstructed", } m["paa-kmn"] = { "Kómnzo", 18344310, "paa-wko", "Latn", } m["paa-kwn"] = { "Kuwani", 6449056, "qfa-unc", -- poorly attested, possibly the same as or related to Kalabra "Latn", } m["paa-lei"] = { "Leitre", 85776228, "paa-isk", } m["paa-nha-pro"] = { "Proto-North Halmahera", 116773241, "paa-nha", "Latn", type = "reconstructed" } m["paa-nun"] = { "Nungon", 128807788, "ngf-ynu", "Latn", } m["phi-din"] = { "Dinapigue Agta", 16945774, "phi", "Latn", } m["phi-kal-pro"] = { "Proto-Kalamian", 116773213, "phi-kal", "Latn", type = "reconstructed", } m["phi-nag"] = { "Nagtipunan Agta", 16966111, "phi", "Latn", } m["phi-pro"] = { "Proto-Philippine", 18204898, "phi", "Latn", type = "reconstructed", } m["poz-abi"] = { "Abai", 19570729, "poz-san", "Latn", } m["poz-bal"] = { "Baliledo", 4850912, "poz", "Latn", } m["poz-btk-pro"] = { "Proto-Bungku-Tolaki", 116773724, "poz-btk", "Latn", type = "reconstructed", } m["poz-cet-pro"] = { "Proto-Central-Eastern Malayo-Polynesian", 2269883, "poz-cet", "Latn", type = "reconstructed", } m["poz-hce-pro"] = { "Proto-Halmahera-Cenderawasih", 116773209, "poz-hce", "Latn", type = "reconstructed", } m["poz-lgx-pro"] = { "Proto-Lampungic", 116773222, "poz-lgx", "Latn", type = "reconstructed", } m["poz-mcm-pro"] = { "Proto-Malayo-Chamic", 116773225, "poz-mcm", "Latn", type = "reconstructed", } m["poz-mic-pro"] = { "Proto-Micronesian", 111939079, "poz-mic", "Latn", type = "reconstructed", } m["poz-mly-pro"] = { "Proto-Malayic", 98057728, "poz-mly", "Latn", type = "reconstructed", } m["poz-msa-pro"] = { "Proto-Malayo-Sumbawan", 116773226, "poz-msa", "Latn", type = "reconstructed", } m["poz-oce-pro"] = { "Proto-Oceanic", 141741, "poz-oce", "Latn", type = "reconstructed", } m["poz-pep-pro"] = { "Proto-Eastern Polynesian", 113988745, "poz-pep", "Latn", type = "reconstructed", } m["poz-pnp-pro"] = { "Proto-Nuclear Polynesian", 113988746, "poz-pnp", "Latn", type = "reconstructed", } m["poz-pol-pro"] = { "Proto-Polynesian", 1658709, "poz-pol", "Latn", type = "reconstructed", } m["poz-pro"] = { "Proto-Malayo-Polynesian", 3832960, "poz", "Latn", type = "reconstructed", } m["poz-sml"] = { "Sarawak Malay", 4251702, "poz-mly", "Latn, ms-Arab", } m["poz-ssw-pro"] = { "Proto-South Sulawesi", 116773279, "poz-ssw", "Latn", type = "reconstructed", } m["poz-swa-pro"] = { "Proto-North Sarawak", 116773243, "poz-swa", "Latn", type = "reconstructed", } m["poz-ter"] = { "Terengganu Malay", 4207412, "poz-mly", "Latn, ms-Arab", } m["pqe-pro"] = { "Proto-Eastern Malayo-Polynesian", 2269883, "pqe", "Latn", type = "reconstructed", } m["pra-niy"] = { "Niya Prakrit", 11991601, "inc-mid", "Khar", ancestors = "inc-ash", translit = "Khar-translit", } m["qfa-adm-pro"] = { "Proto-Great Andamanese", 116773756, "qfa-adm", "Latn", type = "reconstructed", } m["qfa-bet-pro"] = { "Proto-Be-Tai", 116773193, "qfa-bet", "Latn", type = "reconstructed", } m["qfa-cka-pro"] = { "Proto-Chukotko-Kamchatkan", 7251837, "qfa-cka", "Latn", type = "reconstructed", } m["qfa-hur-pro"] = { "Proto-Hurro-Urartian", 116773211, "qfa-hur", "Latn", type = "reconstructed", } m["qfa-kad-pro"] = { "Proto-Kadu", 116773770, "qfa-kad", "Latn", type = "reconstructed", } m["qfa-kms-pro"] = { "Proto-Kam-Sui", 55630682, "qfa-kms", "Latn", type = "reconstructed", } m["qfa-kor-pro"] = { "Proto-Koreanic", 467883, "qfa-kor", "Latn", type = "reconstructed", } m["qfa-kra-pro"] = { "Proto-Kra", 7251854, "qfa-kra", "Latn", type = "reconstructed", } m["qfa-lic-pro"] = { "Proto-Hlai", 7251845, "qfa-lic", "Latn", type = "reconstructed", } m["qfa-onb-pro"] = { "Proto-Be", 116773192, "qfa-onb", "Latn", type = "reconstructed", } m["qfa-ong-pro"] = { "Proto-Ongan", 116773801, "qfa-ong", "Latn", type = "reconstructed", } m["qfa-tak-pro"] = { "Proto-Kra-Dai", 104901616, "qfa-tak", "Latn", type = "reconstructed", } m["qfa-yen-pro"] = { "Proto-Yeniseian", 27639, "qfa-yen", "Latn", type = "reconstructed", } m["qfa-yuk-pro"] = { "Proto-Yukaghir", 116773294, "qfa-yuk", "Latn", type = "reconstructed", } m["qwe-kch"] = { "Kichwa", 1740805, "qwe", "Latn", ancestors = "qu", } m["qwe-pro"] = { "Proto-Quechuan", 5575757, "qwe", "Latn", type = "reconstructed", } m["roa-ang"] = { "Angevin", 56782, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-bbn"] = { "Bourbonnais-Berrichon", 2899128, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-brg"] = { "Bourguignon", 508332, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-can"] = { "Cantabrian", 917021, "roa-asl", "Latn", } m["roa-cha"] = { "Champenois", 430018, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-fcm"] = { "Franc-Comtois", 510561, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gal"] = { "Gallo", 37300, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gib"] = { "Gallo-Italic of Basilicata", 3094838, "roa-git", ancestors = "pms-old", "Latn", } m["roa-gis"] = { "Gallo-Italic of Sicily", 2629019, "roa-git", "Latn", ancestors = "pms-old", } m["roa-leo"] = { "Leonese", 34108, "roa-asl", "Latn", } m["roa-lor"] = { "Lorrain", 671198, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-oca"] = { "Old Catalan", 15478520, "roa-ocr", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, } m["roa-ole"] = { "Old Leonese", 125977465, "roa-asl", "Latn", } m["roa-ona"] = { "Old Navarro-Aragonese", 2736184, "roa-nar", "Latn", } m["roa-opt"] = { "Old Galician-Portuguese", 1072111, "roa-gap", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["roa-orl"] = { "Orléanais", 28497058, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-poi"] = { "Poitevin-Saintongeais", 514123, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-tar"] = { "Tarantino", 695526, "roa-itr", "Latn", wikimedia_codes = "roa-tara", } m["sai-all"] = { "Allentiac", 19570789, "sai-hrp", "Latn", } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' "Andoquero", 16828359, "sai-wit", "Latn", } m["sai-ayo"] = { "Ayomán", 16937754, "sai-jir", "Latn", } m["sai-bae"] = { "Baenan", 3401998, "qfa-unc", -- extinct, poorly attested; only known through 9 words "Latn", } m["sai-bag"] = { "Bagua", 5390321, "qfa-unc", -- extinct, poorly attested; possibly Cariban "Latn", } m["sai-bet"] = { "Betoi", 926551, "qfa-iso", "Latn", } m["sai-bor-pro"] = { "Proto-Boran", nil, "sai-bor", "Latn", } m["sai-cac"] = { "Cacán", 945482, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-caq"] = { "Caranqui", 2937753, "sai-bar", "Latn", } m["sai-car-pro"] = { "Proto-Cariban", 116773196, "sai-car", "Latn", type = "reconstructed", } m["sai-cat"] = { "Catacao", 5051136, "sai-ctc", "Latn", } m["sai-cer-pro"] = { "Proto-Cerrado", 116773200, "sai-cer", "Latn", type = "reconstructed", } m["sai-chi"] = { "Chirino", 5390321, "qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu) "Latn", } m["sai-chn"] = { "Chaná", 5072718, "sai-crn", "Latn", } m["sai-chp"] = { "Chapacura", 5072884, "sai-cpc", "Latn", } m["sai-chr"] = { "Charrua", 5086680, "sai-crn", "Latn", } m["sai-chu"] = { "Churuya", 5118339, "sai-guh", "Latn", } m["sai-cje-pro"] = { "Proto-Central Jê", 116773198, "sai-cje", "Latn", type = "reconstructed", } m["sai-cmg"] = { "Comechingon", 6644203, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-cno"] = { "Chono", 5104704, "qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious "Latn", } m["sai-cnr"] = { "Cañari", 5055572, "qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan "Latn", } m["sai-coe"] = { "Coeruna", 6425639, "sai-wit", "Latn", } m["sai-col"] = { "Colán", 5141893, "sai-ctc", "Latn", } m["sai-cop"] = { "Copallén", 5390321, "qfa-unc", -- extinct, only four words attested; possibly Cholonan "Latn", } m["sai-crd"] = { "Coroado Puri", 24191321, "sai-mje", "Latn", } m["sai-ctq"] = { "Catuquinaru", 16858455, "qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages "Latn", } m["sai-cul"] = { "Culli", 2879660, "qfa-unc", -- extinct, poorly attested; often considered an isolate "Latn", } m["sai-cva"] = { "Cueva", 5192644, "qfa-unc", -- extinct, poorly attested; possibly Chocoan "Latn", } m["sai-esm"] = { "Esmeralda", 3058083, "qfa-unc", -- extinct, poorly attested; possibly related to Yaruro "Latn", } m["sai-ewa"] = { "Ewarhuyana", 16898104, nil, "Latn", } m["sai-gam"] = { "Gamela", 5403661, "qfa-unc", -- extinct, poorly attested; possibly an isolate "Latn", } m["sai-gay"] = { "Gayón", 5528902, "sai-jir", "Latn", } m["sai-gmo"] = { "Guamo", 5613495, "qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024). "Latn", } m["sai-gua"] = { "Guachí", 5613172, "sai-guc", "Latn", } m["sai-gue"] = { "Güenoa", 5626799, "sai-crn", "Latn", } m["sai-hau"] = { "Haush", 3128376, "sai-cho", "Latn", } m["sai-jee-pro"] = { "Proto-Jê", 116773212, "sai-jee", "Latn", type = "reconstructed", } m["sai-jko"] = { "Jeikó", 6176527, "sai-mje", "Latn", } m["sai-jrj"] = { "Jirajara", 6202966, "sai-jir", "Latn", } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc "Katembri", 6375925, "qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia] "Latn", } m["sai-mal"] = { "Malalí", 6741212, "sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry "Latn", } m["sai-mar"] = { "Maratino", 6755055, "qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan "Latn", } m["sai-mat"] = { "Matanawi", 6786047, "qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified "Latn", } m["sai-mcn"] = { "Mocana", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-men"] = { "Menien", 16890110, "sai-mje", "Latn", } m["sai-mil"] = { "Millcayac", 19573012, "sai-hrp", "Latn", } m["sai-mlb"] = { "Malibu", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-msk"] = { "Masakará", 6782426, "sai-mje", "Latn", } m["sai-muc"] = { "Mucuchí", 6931290, nil, -- generally considered Timotean, for which we have no entry "Latn", } m["sai-mue"] = { "Muellama", 16886936, "sai-bar", "Latn", } m["sai-muz"] = { "Muzo", 6644203, "qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban) "Latn", } m["sai-mys"] = { "Maynas", 16919393, "sai-cah", -- per Campbell (2024); formerly considered unclassified "Latn", } m["sai-nat"] = { "Natú", 9006749, "qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages] "Latn", } m["sai-nje-pro"] = { "Proto-Northern Jê", 116773245, "sai-nje", "Latn", type = "reconstructed", } m["sai-opo"] = { "Opón", 7099152, "sai-car", "Latn", } m["sai-oto"] = { "Otomaco", 16879234, "sai-otm", "Latn", } m["sai-pal"] = { "Palta", 3042978, "qfa-unc", -- extinct, unclassified; possibly Chicham "Latn", } m["sai-pam"] = { "Pamigua", 5908689, "sai-otm", "Latn", } m["sai-par"] = { "Paratió", 16890038, "qfa-unc", -- extinct, poorly attested; possibly Xukuruan "Latn", } m["sai-peb"] = { "Peba", 3373890, "sai-pey", "Latn", } m["sai-pnz"] = { "Panzaleo", 3123275, "qfa-unc", -- extinct, unclassified; possibly Paezan "Latn", } m["sai-prh"] = { "Puruhá", 3410994, "qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari "Latn", } m["sai-ptg"] = { "Patagón", 128807870, "sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024) "Latn", } m["sai-pur"] = { "Purukotó", 7261622, "sai-pem", "Latn", } m["sai-pyg"] = { "Payaguá", 7156643, "sai-guc", "Latn", } m["sai-pyk"] = { "Pykobjê", 98113977, "sai-nje", "Latn", } m["sai-qmb"] = { "Quimbaya", 7272043, "qfa-unc", -- extinct, might not exist; few known words "Latn", } m["sai-qtm"] = { "Quitemo", 7272651, "sai-cpc", "Latn", } m["sai-rab"] = { "Rabona", 6644203, "qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra "Latn", } m["sai-ram"] = { "Ramanos", 16902824, "qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages" "Latn", } m["sai-sac"] = { "Sácata", 5390321, "qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan "Latn", } m["sai-san"] = { "Sanaviron", 16895999, "qfa-unc", -- extinct, unclassified; no consensus on classification "Latn", } m["sai-sap"] = { "Sapará", 7420922, "sai-car", "Latn", } m["sai-sec"] = { "Sechura", 7442912, "qfa-unc", -- extinct, poorly attested; possibly Catacaoan "Latn", } m["sai-sin"] = { "Sinúfana", 7525275, "qfa-unc", -- moribund, poorly attested; possibly Chocoan "Latn", } m["sai-sje-pro"] = { "Proto-Southern Jê", 116773814, "sai-sje", "Latn", type = "reconstructed", } m["sai-tab"] = { "Tabancale", 5390321, "qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate "Latn", } m["sai-tal"] = { "Tallán", 16910468, "qfa-unc", -- extinct, poorly attested; might be Catacaoan "Latn", } m["sai-tap"] = { "Tapayuna", 30719984, "sai-nje", "Latn", } m["sai-tar-pro"] = { "Proto-Taranoan", 116773816, "sai-tar", "Latn", type = "reconstructed", } m["sai-teu"] = { "Teushen", 3519243, "qfa-unc", -- probably extinct by the 1950's; possibly Chonan "Latn", } m["sai-tim"] = { "Timote", 7806995, nil, -- possibly in a small Timotean family "Latn", } m["sai-tpr"] = { "Taparita", 7684460, "sai-otm", "Latn", } m["sai-trr"] = { "Tarairiú", 7685313, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sai-wai"] = { "Waitaká", 16918610, "qfa-unc", -- extinct, possibly Purian "Latn", } m["sai-way"] = { "Wayumara", 7960726, "sai-car", "Latn", } m["sai-wit-pro"] = { "Proto-Witotoan", 116773823, "sai-wit", "Latn", type = "reconstructed", } m["sai-wnm"] = { "Wanham", 16879440, "sai-cpc", "Latn", } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat "Xocó", 12953620, "qfa-unc", -- extinct and poorly attested; not clear if one or three languages "Latn", } m["sai-yao"] = { "Yao (South America)", 16979655, "sai-ven", "Latn", } m["sai-yar"] = { -- not the same family as 'suy' "Yarumá", 3505859, "sai-pek", "Latn", } m["sai-yri"] = { "Yuri", 2669157, "sai-tyu", "Latn", } m["sai-yup"] = { "Yupua", 8061430, "sai-tuc", "Latn", } m["sai-yur"] = { "Yurumanguí", 1281291, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sal-pro"] = { "Proto-Salish", 116773269, "sal", "Latn", type = "reconstructed", } m["sdv-daj-pro"] = { "Proto-Daju", 116773739, "sdv-daj", "Latn", type = "reconstructed", } m["sdv-eje-pro"] = { "Proto-Eastern Jebel", 116773751, "sdv-eje", "Latn", type = "reconstructed", } m["sdv-nil-pro"] = { "Proto-Nilotic", 116773794, "sdv-nil", "Latn", type = "reconstructed", } m["sdv-nyi-pro"] = { "Proto-Nyima", 116773796, "sdv-nyi", "Latn", type = "reconstructed", } m["sdv-tmn-pro"] = { "Proto-Taman", 116773815, "sdv-tmn", "Latn", type = "reconstructed", } m["sel-nor"] = { "Northern Selkup", 30304565, "sel", "Cyrl", translit = "sel-nor-translit", } m["sel-pro"] = { "Proto-Selkup", 128884235, "sel", "Latn", type = "reconstructed", } m["sel-sou"] = { "Southern Selkup", 30304639, "sel", "Cyrl", translit = "sel-sou-translit", } m["sem-amm"] = { "Ammonite", 279181, "sem-can", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-amo"] = { "Amorite", 35941, "sem-nwe", "Xsux, Latn", } m["sem-cha"] = { "Chaha", 35543, "sem-eth", "Ethi", translit = "Ethi-translit", } m["sem-dad"] = { "Dadanitic", 21838040, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-dum"] = { "Dumaitic", 128810397, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-has"] = { "Hasaitic", 3541433, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-his"] = { "Hismaic", 22948260, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-mhr"] = { "Muher", 33743, "sem-eth", "Latn", } m["sem-pro"] = { "Proto-Semitic", 1658554, "sem", "Latn", type = "reconstructed", } m["sem-saf"] = { "Safaitic", 472586, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-sam"] = { "Samalian", 85847147, "sem-nwe", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-srb"] = { "Old South Arabian", 35025, "sem-osa", "Sarb", -- Sarb translit in [[Module:scripts/data]] } m["sem-tay"] = { "Taymanitic", 24912301, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-tha"] = { "Thamudic", 843030, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-wes-pro"] = { "Proto-West Semitic", 98021726, "sem-wes", "Latn", type = "reconstructed", } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' "Proto-Siouan", 34181, "sio", "Latn", type = "reconstructed", } m["sit-aao-pro"] = { "Proto-Central Naga", nil, "sit-aao", "Latn", type = "reconstructed", } m["sit-bai-pro"] = { "Proto-Bai", nil, "sit-bai", "Latn", type = "reconstructed", } m["sit-ban"] = { "Bangru", 56071779, "sit-hrs", "Latn", } m["sit-bdi-pro"] = { "Proto-Bodish", nil, "sit-bdi", "Latn", type = "reconstructed", } m["sit-bok"] = { "Bokar", 4938727, "sit-tan", "Latn, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["sit-cai"] = { "Caijia", 5017528, "sit-cln", "Latn" } m["sit-cha"] = { "Chairel", 5068066, "sit-luu", "Latn", } m["sit-ers-pro"] = { "Proto-Ersuic", nil, "sit-ers", "Latn", type = "reconstructed", } m["sit-hrs-pro"] = { "Proto-Hrusish", 116773762, "sit-hrs", "Latn", type = "reconstructed", } m["sit-jap"] = { "Japhug", 3162245, "sit-egy", "Latn", } m["sit-kha-pro"] = { "Proto-Kham", 116773773, "sit-kha", "Latn", type = "reconstructed", } m["sit-khb-pro"] = { "Proto-Kho-Bwa", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khp-pro"] = { "Proto-Puroik", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khw-pro"] = { "Proto-Western Kho-Bwa", nil, "sit-khw", "Latn", type = "reconstructed", } m["sit-kon-pro"] = { "Proto-Northern Naga", nil, "sit-kon", "Latn", type = "reconstructed", } m["sit-liz"] = { "Lizu", 6660653, "sit-ers", "Latn", -- and Ersu Shaba } m["sit-lnj"] = { "Longjia", 17096251, "sit-cln", "Latn" } m["sit-lrn"] = { "Luren", 16946370, "sit-cln", "Latn" } m["sit-luu-pro"] = { "Proto-Luish", 116773783, "sit-luu", "Latn", type = "reconstructed", } m["sit-nas-pro"] = { "Proto-Naish", nil, "sit-nas", "Latn", type = "reconstructed", } m["sit-prn"] = { "Puiron", 7259048, "sit-zem", } m["sit-pro"] = { "Proto-Sino-Tibetan", 24839178, "sit", "Latn", type = "reconstructed", } m["sit-sit"] = { "Situ", 19840830, "sit-egy", "Latn", } m["sit-tam-pro"] = { "Proto-Tamangic", 117469295, "sit-tam", "Latn", type = "reconstructed", } m["sit-tan-pro"] = { "Proto-Tani", 116773284, "sit-tan", "Latn", -- needs verification type = "reconstructed", } m["sit-tgm"] = { "Tangam", 17041370, "sit-tan", "Latn", } m["sit-tng-pro"] = { "Proto-Tangkhulic", nil, "sit-tng", "Latn", type = "reconstructed" } m["sit-tos"] = { "Tosu", 7827899, "sit-ers", "Latn", -- also Ersu Shaba } m["sit-tsh"] = { "Tshobdun", 19840950, "sit-egy", "Latn", } m["sit-zbu"] = { "Zbu", 19841106, "sit-egy", "Latn", } m["sla-pro"] = { "Proto-Slavic", 747537, "sla", "Latn", type = "reconstructed", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {'ś'}, }, sort_key = { from = {"č", "ď", "ě", "ę", "ь", "ľ", "ň", "ǫ", "ř", "š", "ś", "ť", "ъ", "ž"}, to = {"c²", "d²", "e²", "e³", "i²", "l²", "nj", "o²", "r²", "s²", "s³", "t²", "u²", "z²"}, } } m["smi-pro"] = { "Proto-Samic", 7251862, "smi", "Latn", type = "reconstructed", sort_key = { from = {"ā", "č", "δ", "[ëē]", "ŋ", "ń", "ō", "š", "θ", "%([^()]+%)"}, to = {"a", "c²", "d", "e", "n²", "n³", "o", "s²", "t²"} }, } m["son-pro"] = { "Proto-Songhay", 116773277, "son", "Latn", type = "reconstructed", } m["sqj-pro"] = { "Proto-Albanian", 18210846, "sqj", "Latn", type = "reconstructed", } m["ssa-klk-pro"] = { "Proto-Kuliak", 116773779, "ssa-klk", "Latn", type = "reconstructed", } m["ssa-kom-pro"] = { "Proto-Koman", 116773775, "ssa-kom", "Latn", type = "reconstructed", } m["ssa-pro"] = { "Proto-Nilo-Saharan", 116773236, "ssa", "Latn", type = "reconstructed", } m["syd-pro"] = { "Proto-Samoyedic", 7251863, "syd", "Latn", type = "reconstructed", } m["tai-pro"] = { "Proto-Tai", 6583709, "tai", "Latn", type = "reconstructed", } m["tai-swe-pro"] = { "Proto-Southwestern Tai", 116773280, "tai-swe", "Latn", type = "reconstructed", } m["tbq-bdg-pro"] = { "Proto-Bodo-Garo", 116773195, "tbq-bdg", "Latn", type = "reconstructed", } m["tbq-blg"] = { "Bailang", 2879843, "tbq-lob", "Hani", sort_key = "Hani-sortkey", } m["tbq-brm-pro"] = { "Proto-Burmish", nil, "tbq-brm", "Latn", type = "reconstructed", } m["tbq-gkh"] = { "Gokhy", 5578069, "tbq-sil", "Latn", } m["tbq-kuk-pro"] = { "Proto-Kuki-Chin", 116773220, "tbq-kuk", "Latn", type = "reconstructed", } m["tbq-lal-pro"] = { "Proto-Lalo", 116773781, "tbq-lal", "Latn", type = "reconstructed", } m["tbq-laz"] = { "Laze", 17007626, "sit-nas", "Latn", } m["tbq-lob-pro"] = { "Proto-Lolo-Burmese", 116773224, "tbq-lob", "Latn", type = "reconstructed", } m["tbq-lol-pro"] = { "Proto-Loloish", 7251855, "tbq-lol", "Latn", type = "reconstructed", } m["tbq-mil"] = { "Milang", 6850761, "sit-gsi", "Deva, Latn", } m["tbq-mor"] = { "Moran", 6909216, "tbq-bdg", "Latn", } m["tbq-ngo"] = { "Ngochang", 56582, "tbq-brm", "Latn", } -- tbq-pro is now etymology-only m["trk-dkh"] = { "Dukhan", 12809273, "trk-ssb", "Latn, Cyrl, Mong", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] } -- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''. m["trk-eog"] = { "Early Old Oghuz", nil, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, } m["trk-oat"] = { "Old Anatolian Turkish", 7083390, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, ancestors = "trk-eog", } m["trk-pro"] = { "Proto-Turkic", 3657773, "trk", "Latn", type = "reconstructed", standard_chars = { Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron, } } m["tup-gua-pro"] = { "Proto-Tupi-Guarani", 116773288, "tup-gua", "Latn", type = "reconstructed", } m["tup-kab"] = { "Kabishiana", 15302988, "tup", "Latn", } m["tup-pro"] = { "Proto-Tupian", 10354700, "tup", "Latn", type = "reconstructed", } m["tuw-alk"] = { "Alchuka", 113553616, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-bal"] = { "Bala", 86730632, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kkl"] = { "Kyakala", 118875708, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kli"] = { "Kili", 6406892, "tuw-ewe", "Cyrl", } m["tuw-pro"] = { "Proto-Tungusic", 85872335, "tuw", "Latn", type = "reconstructed", } m["tuw-sol"] = { "Solon", 30004, "tuw-ewe", } m["urj-fin-pro"] = { "Proto-Finnic", 11883720, "urj-fin", "Latn", type = "reconstructed", } m["urj-koo"] = { "Old Komi", 86679962, "kv", "Perm, Cyrs", translit = "urj-koo-translit", -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present } m["urj-kuk"] = { "Kukkuzi", 107410460, "urj-fin", "Latn", ancestors = "vot", } m["urj-kya"] = { "Komi-Yazva", 2365210, "kv", "Cyrl", translit = "kv-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.acute}, } m["urj-mdv-pro"] = { "Proto-Mordvinic", 116773232, "urj-mdv", "Latn", type = "reconstructed", } m["urj-prm-pro"] = { "Proto-Permic", 116773257, "urj-prm", "Latn", type = "reconstructed", } m["urj-pro"] = { "Proto-Uralic", 288765, "urj", "Latn", type = "reconstructed", } m["urj-ugr-pro"] = { "Proto-Ugric", 156631, "urj-ugr", "Latn", type = "reconstructed", } m["xnd-pro"] = { "Proto-Na-Dene", 116773233, "xnd", "Latn", type = "reconstructed", } m["xgn-pro"] = { "Proto-Mongolic", 2493677, "xgn", "Latn", type = "reconstructed", sort_key = { from = {"č", "i", "ï", "ǰ", "ŋ", "ö", "š", "ü"}, to = {"c", "i" .. p[1], "i", "j", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]}, }, } m["yok-bvy"] = { "Buena Vista Yokuts", 4985474, "yok", "Latn", } m["yok-dly"] = { "Delta Yokuts", 70923266, "yok", "Latn", } m["yok-gsy"] = { "Gashowu Yokuts", 3098708, "yok", "Latn", } m["yok-kry"] = { "Kings River Yokuts", 6413014, "yok", "Latn", } m["yok-nvy"] = { "Northern Valley Yokuts", 85789777, "yok", "Latn", } m["yok-ply"] = { "Palewyami Yokuts", 2387391, "yok", "Latn", } m["yok-svy"] = { "Southern Valley Yokuts", 12642473, "yok", "Latn", } m["yok-tky"] = { "Tule-Kaweah Yokuts", 7851988, "yok", "Latn", } m["ypk-pro"] = { "Proto-Yupik", 116773295, "ypk", "Latn", type = "reconstructed", } m["yrk-for"] = { "Forest Nenets", 1295107, "yrk", "Cyrl", translit = "yrk-for-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove}, } m["yrk-tun"] = { "Tundra Nenets", 36452, "yrk", "Cyrl", strip_diacritics = { from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"}, to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"}, }, translit = "yrk-tun-translit", } m["zhx-min-pro"] = { "Proto-Min", 19646347, "zhx-min", "Latn", type = "reconstructed", } m["zhx-sht"] = { "Shaozhou Tuhua", 1920769, "zhx", "Nshu, Hants", generate_forms = "zh-generateforms", sort_key = {Hani = "Hani-sortkey"}, } m["zhx-sic"] = { "Sichuanese", 2278732, "zhx-man", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zhx-tai"] = { "Taishanese", 2208940, "zhx-yue", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zle-ono"] = { "Old Novgorodian", 162013, "zle", "Cyrs, Glag", translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zle-ort"] = { "Old Ruthenian", 13211, "zle", "Arab, Cyrs, Latn", ancestors = "orv", translit = { Cyrs = "zle-ort-translit", Arab = "zle-ort-Arab-translit", }, strip_diacritics = { Cyrs = { remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"], remove_exceptions = {"Ї", "ї"}, }, Arab = "ar-stripdiacritics", }, -- Cyrs sort_key in [[Module:scripts/data]] } m["zls-chs"] = { "Church Slavonic", 33251, "zls", "Cyrs, Glag, Latn", ancestors = "cu", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zlw-ocs"] = { "Old Czech", 593096, "zlw", "Latn", } m["zlw-opl"] = { "Old Polish", 149838, "zlw-lch", "Latn", strip_diacritics = {remove_diacritics = c.ringabove}, } m["zlw-osk"] = { "Old Slovak", 12776676, "zlw", "Latn", } m["zlw-slv"] = { "Slovincian", 36822, "zlw-pom", "Latn", strip_diacritics = {remove_diacritics = c.macron .. c.breve}, } return require("Module:languages").finalizeData(m, "language") 4z3umhhk0j9curjvkejw4agfp9ficlc 231365 231364 2026-04-14T05:53:21Z Lee 19 Lee විසින් යලියොමුවක් නොදමාම [[Module:languages/data/exceptional/Module:languages/data/exceptional]] පිටුව [[Module:languages/data/exceptional]] වෙත ගෙනයන ලදී 231363 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "Proto-Khasian", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "aav-nic", "Latn", type = "reconstructed", } m["aav-pkl-pro"] = { "Proto-Pnar-Khasi-Lyngngam", 116773259, "aav-pkl", "Latn", type = "reconstructed", } m["aav-pro"] = { -- mkh-pro will merge into this "Proto-Austroasiatic", 116773186, "aav", "Latn", type = "reconstructed", } m["afa-pro"] = { "Proto-Afroasiatic", 269125, "afa", "Latn", type = "reconstructed", } m["alg-aga"] = { "Agawam", nil, "alg-eas", "Latn", } m["alg-pro"] = { "Proto-Algonquian", 7251834, "alg", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["alv-ama"] = { "Amasi", 4740400, "nic-grs", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}, } m["alv-bgu"] = { "Bainouk Gubeeher", 17002646, "alv-bny", "Latn", } m["alv-bua-pro"] = { "Proto-Bua", 116773723, "alv-bua", "Latn", type = "reconstructed", } m["alv-cng-pro"] = { "Proto-Cangin", 116773726, "alv-cng", "Latn", type = "reconstructed", } m["alv-edo-pro"] = { "Proto-Edoid", 116773206, "alv-edo", "Latn", type = "reconstructed", } m["alv-fli-pro"] = { "Proto-Fali", 116773754, "alv-fli", "Latn", type = "reconstructed", } m["alv-gbe-pro"] = { "Proto-Gbe", 116773208, "alv-gbe", "Latn", type = "reconstructed", } m["alv-gng-pro"] = { "Proto-Guang", 116773757, "alv-gng", "Latn", type = "reconstructed", } m["alv-gtm-pro"] = { "Proto-Central Togo", 116773732, "alv-gtm", "Latn", type = "reconstructed", } m["alv-gwa"] = { "Gwara", 16945580, "nic-pla", "Latn", } m["alv-hei-pro"] = { "Proto-Heiban", 116773760, "alv-hei", "Latn", type = "reconstructed", } m["alv-ido-pro"] = { "Proto-Idomoid", 116773764, "alv-ido", "Latn", type = "reconstructed", } m["alv-igb-pro"] = { "Proto-Igboid", 116773765, "alv-igb", "Latn", type = "reconstructed", } m["alv-kwa-pro"] = { "Proto-Kwa", 116773780, "alv-kwa", "Latn", type = "reconstructed", } m["alv-mum-pro"] = { "Proto-Mumuye", 116773791, "alv-mum", "Latn", type = "reconstructed", } m["alv-nup-pro"] = { "Proto-Nupoid", 116773795, "alv-nup", "Latn", type = "reconstructed", } m["alv-pro"] = { "Proto-Atlantic-Congo", 116732838, "alv", "Latn", type = "reconstructed", } m["alv-edk-pro"] = { "Proto-Edekiri", nil, "alv-edk", "Latn", type = "reconstructed", } m["alv-yor-pro"] = { "Proto-Yoruba", nil, "alv-yor", "Latn", type = "reconstructed", } m["alv-yrd-pro"] = { "Proto-Yoruboid", 116773824, "alv-yrd", "Latn", type = "reconstructed", } m["alv-von-pro"] = { "Proto-Volta-Niger", 116773820, "alv-von", "Latn", type = "reconstructed", } m["apa-pro"] = { "Proto-Apachean", 116773135, "apa", "Latn", type = "reconstructed", } m["aql-pro"] = { "Proto-Algic", 18389588, "aql", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["art-adu"] = { "Adûni", 1232159, "art", "Latn", type = "appendix-constructed", } m["art-bel"] = { "Belter Creole", 108055510, "art", "Latn", type = "appendix-constructed", sort_key = { remove_diacritics = c.acute, from = {"ɒ"}, to = {"a"}, }, } m["art-blk"] = { "Bolak", 2909283, "art", "Latn", type = "appendix-constructed", } m["art-bsp"] = { "Black Speech", 686210, "art", "Latn, Teng", type = "appendix-constructed", } m["art-com"] = { "Communicationssprache", 35227, "art", "Latn", type = "appendix-constructed", } m["art-dtk"] = { "Dothraki", 2914733, "art", "Latn", type = "appendix-constructed", } m["art-elo"] = { "Eloi", nil, "art", "Latn", type = "appendix-constructed", } m["art-gld"] = { "Goa'uld", 19823, "art", "Latn, Egyp, Mero", type = "appendix-constructed", } m["art-lap"] = { "Lapine", 6488195, "art", "Latn", type = "appendix-constructed", } m["art-man"] = { "Mandalorian", 54289, "art", "Latn", type = "appendix-constructed", } m["art-mun"] = { "Mundolinco", 851355, "art", "Latn", type = "appendix-constructed", } m["art-nav"] = { "Naʼvi", 316939, "art", "Latn", type = "appendix-constructed", } m["art-vlh"] = { "High Valyrian", 64483808, "art", "Latn", type = "appendix-constructed", } m["ath-nic"] = { "Nicola", 20609, "ath-nor", "Latn", } m["ath-pro"] = { "Proto-Athabaskan", 104841722, "ath", "Latn", type = "reconstructed", } m["auf-pro"] = { "Proto-Arawa", 116773706, "auf", "Latn", type = "reconstructed", } m["aus-alu"] = { "Alungul", 16827670, "aus-pmn", "Latn", } m["aus-and"] = { "Andjingith", 4754509, "aus-pmn", "Latn", } m["aus-ang"] = { "Angkula", 16828520, "aus-pmn", "Latn", } m["aus-arn-pro"] = { "Proto-Arnhem", 116773720, "aus-arn", "Latn", type = "reconstructed", } m["aus-bra"] = { "Barranbinya", 4863220, "aus-pmn", "Latn", } m["aus-brm"] = { "Barunggam", 4865914, "aus-pmn", "Latn", } m["aus-cww-pro"] = { "Proto-Central New South Wales", 116773199, "aus-cww", "Latn", type = "reconstructed", } m["aus-dal-pro"] = { "Proto-Daly", 116773743, "aus-dal", "Latn", type = "reconstructed", } m["aus-guw"] = { "Guwar", 6652138, "aus-pam", "Latn", } m["aus-lsw"] = { "Little Swanport", 6652138, "qfa-unc", "Latn", } m["aus-mbi"] = { "Mbiywom", 6799701, "aus-pmn", "Latn", } m["aus-ngk"] = { "Ngkoth", 7022405, "aus-pmn", "Latn", } m["aus-nyu-pro"] = { "Proto-Nyulnyulan", 116773797, "aus-nyu", "Latn", type = "reconstructed", } m["aus-pam-pro"] = { "Proto-Pama-Nyungan", 33942, "aus-pam", "Latn", type = "reconstructed", } m["aus-tul"] = { "Tulua", 16938541, "aus-pam", "Latn", } m["aus-uwi"] = { "Uwinymil", 7903995, "aus-arn", "Latn", } m["aus-wdj-pro"] = { "Proto-Iwaidjan", 116773767, "aus-wdj", "Latn", type = "reconstructed", } m["aus-won"] = { "Wong-gie", nil, "aus-pam", "Latn", } m["aus-wul"] = { "Wulguru", 8039196, "aus-dyb", "Latn", } m["aus-ynk"] = { -- contrast nny "Yangkaal", 3913770, "aus-tnk", "Latn", } m["awd-amc-pro"] = { "Proto-Amuesha-Chamicuro", nil, "awd", "Latn", type = "reconstructed", } m["awd-kmp-pro"] = { "Proto-Kampa", nil, "awd", "Latn", type = "reconstructed", } m["awd-prw-pro"] = { "Proto-Paresi-Waura", nil, "awd", "Latn", type = "reconstructed", } m["awd-ama"] = { "Amarizana", 16827787, "awd", "Latn", } m["awd-ana"] = { "Anauyá", 16828252, "awd", "Latn", } m["awd-apo"] = { "Apolista", 16916645, "awd", "Latn", } m["awd-cab"] = { "Cabre", 16850160, "awd", "Latn", } m["awd-gnu"] = { "Guinau", 3504087, "awd", "Latn", } m["awd-kar"] = { "Cariay", 16920253, "awd", "Latn", } m["awd-kaw"] = { "Kawishana", 6379993, "awd-nwk", "Latn", } m["awd-kus"] = { "Kustenau", 5196293, "awd", "Latn", } m["awd-man"] = { "Manao", 6746920, "awd", "Latn", } m["awd-mar"] = { "Marawan", 6755108, "awd", "Latn", } m["awd-mpr"] = { "Maipure", 6736872, "awd", "Latn", } m["awd-mrt"] = { "Mariaté", 16910017, "awd-nwk", "Latn", } m["awd-nwk-pro"] = { "Proto-Nawiki", 116773234, "awd-nwk", "Latn", type = "reconstructed", } m["awd-pai"] = { "Paikoneka", 128807835, "awd", "Latn", } m["awd-pas"] = { "Pasé", 7143168, "awd-nwk", "Latn", } m["awd-pro"] = { "Proto-Arawak", 97573478, "awd", "Latn", type = "reconstructed", } m["awd-she"] = { "Shebayo", 7492248, "awd", "Latn", } m["awd-taa-pro"] = { "Proto-Ta-Arawak", 116773282, "awd-taa", "Latn", type = "reconstructed", } m["awd-wai"] = { "Wainumá", 16910017, "awd-nwk", "Latn", } m["awd-yum"] = { "Yumana", 8061062, "awd-nwk", "Latn", } m["azc-caz"] = { "Cazcan", 5055514, "azc", "Latn", } m["azc-cup-pro"] = { "Proto-Cupan", 116773738, "azc-cup", "Latn", type = "reconstructed", } m["azc-ktn"] = { "Kitanemuk", 3197558, "azc-tak", "Latn", } m["azc-nah-pro"] = { "Proto-Nahuan", 7251860, "azc-nah", "Latn", type = "reconstructed", } m["azc-num-pro"] = { "Proto-Numic", 116773247, "azc-num", "Latn", type = "reconstructed", } m["azc-pro"] = { "Proto-Uto-Aztecan", 96400333, "azc", "Latn", type = "reconstructed", } m["azc-tak-pro"] = { "Proto-Takic", 116773283, "azc-tak", "Latn", type = "reconstructed", } m["azc-tat"] = { "Tataviam", 743736, "azc", "Latn", } m["ber-pro"] = { "Proto-Berber", 2855698, "ber", "Latn", type = "reconstructed", } m["ber-fog"] = { "Fogaha", 107610173, "ber", "Latn", } m["ber-zuw"] = { "Zuwara", 4117169, "ber", "Latn", } m["bnt-bal"] = { "Balong", 93935237, "bnt-bbo", "Latn", } m["bnt-bon"] = { "Boma Nkuu", nil, "bnt", "Latn", } m["bnt-boy"] = { "Boma Yumu", nil, "bnt", "Latn", } m["bnt-bwa"] = { "Bwala", 128810345, "bnt-tek", "Latn", } m["bnt-cmw"] = { "Chimwiini", 4958328, "bnt-swh", "Latn", } m["bnt-ind"] = { "Indanga", 51412803, "bnt", "Latn", } m["bnt-lal"] = { "Lala (South Africa)", 6480154, "bnt-ngu", "Latn", } m["bnt-mpi"] = { "Mpiin", 93937013, "bnt-bdz", "Latn", } m["bnt-mpu"] = { "Mpuono", -- not to be confused with Mbuun zmp 36056, "bnt", "Latn", } m["bnt-ngu-pro"] = { "Proto-Nguni", 961559, "bnt-ngu", "Latn", type = "reconstructed", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron}, } m["bnt-phu"] = { "Phuthi", 33796, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, } m["bnt-pro"] = { "Proto-Bantu", 3408025, "bnt", "Latn", type = "reconstructed", sort_key = "bnt-pro-sortkey", } m["bnt-sab-pro"] = { "Proto-Sabaki", nil, -- Q2209395 is the code for the Sabaki family "bnt-sab", "Latn", type = "reconstructed", } m["bnt-sbo"] = { "South Boma", nil, "bnt", "Latn", } m["bnt-sts-pro"] = { "Proto-Sotho-Tswana", 116773278, "bnt-sts", "Latn", type = "reconstructed", } m["btk-pro"] = { "Proto-Batak", 116773191, "btk", "Latn", type = "reconstructed", } m["cau-abz-pro"] = { "Proto-Abkhaz-Abaza", 7251831, "cau-abz", "Latn", type = "reconstructed", } m["cau-and-pro"] = { "Proto-Andian", nil, "cau-and", "Latn", type = "reconstructed", } m["cau-ava-pro"] = { "Proto-Avaro-Andian", 116773187, "cau-ava", "Latn", type = "reconstructed", } m["cau-cir-pro"] = { "Proto-Circassian", 7251838, "cau-cir", "Latn", type = "reconstructed", } m["cau-drg-pro"] = { "Proto-Dargwa", 116773205, "cau-drg", "Latn", type = "reconstructed", } m["cau-lzg-pro"] = { "Proto-Lezghian", 116773223, "cau-lzg", "Latn", type = "reconstructed", } m["cau-nec-pro"] = { "Proto-Northeast Caucasian", 116773244, "cau-nec", "Latn", type = "reconstructed", } m["cau-nkh-pro"] = { "Proto-Nakh", 108032840, "cau-nkh", "Latn", type = "reconstructed", } m["cau-nwc-pro"] = { "Proto-Northwest Caucasian", 7251861, "cau-nwc", "Latn", type = "reconstructed", } m["cau-tsz-pro"] = { "Proto-Tsezian", 116773287, "cau-tsz", "Latn", type = "reconstructed", } m["cba-ata"] = { "Atanques", 4812783, "cba", "Latn", } m["cba-cat"] = { "Catío Chibcha", 7083619, "cba", "Latn", } m["cba-dor"] = { "Dorasque", 5297532, "cba", "Latn", } m["cba-dui"] = { "Duit", 3041061, "cba", "Latn", } m["cba-hue"] = { "Huetar", 35514, "cba", "Latn", } m["cba-nut"] = { "Nutabe", 7070405, "cba", "Latn", } m["cba-pro"] = { "Proto-Chibchan", 116773203, "cba", "Latn", type = "reconstructed", } m["ccs-pro"] = { "Proto-Kartvelian", 2608203, "ccs", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["ccs-gzn-pro"] = { "Proto-Georgian-Zan", 23808119, "ccs-gzn", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["cdc-cbm-pro"] = { "Proto-Central Chadic", 116773197, "cdc-cbm", "Latn", type = "reconstructed", } m["cdc-mas-pro"] = { "Proto-Masa", 116773789, "cdc-mas", "Latn", type = "reconstructed", } m["cdc-pro"] = { "Proto-Chadic", 116773201, "cdc", "Latn", type = "reconstructed", } m["cdd-pro"] = { "Proto-Caddoan", 116773725, "cdd", "Latn", type = "reconstructed", } m["cel-bry-pro"] = { "Proto-Brythonic", 1248800, "cel-bry", "Latn, Polyt", sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-gal"] = { "Gallaecian", 3094789, "cel-his", } m["cel-gau"] = { "Gaulish", 29977, "cel", "Latn, Polyt, Ital", strip_diacritics = { Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer}, }, sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-pro"] = { "Proto-Celtic", 653649, "cel", "Latn", type = "reconstructed", sort_key = "cel-pro-sortkey", } m["chi-pro"] = { "Proto-Chimakuan", 116773734, "chi", "Latn", type = "reconstructed", } m["chm-pro"] = { "Proto-Mari", 116773788, "chm", "Latn", type = "reconstructed", } m["cmc-pro"] = { "Proto-Chamic", 114793834, "cmc", "Latn", type = "reconstructed", } m["crp-bip"] = { "Basque-Icelandic Pidgin", 810378, "crp", "Latn", ancestors = "eu", } m["crp-gep"] = { "West Greenlandic Pidgin", 17036301, "crp", "Latn", ancestors = "kl", } m["crp-kia"] = { "Kiautschou German Pidgin", 108314615, "crp", "Latn", ancestors = "de", } m["crp-mar"] = { "Maroon Spirit Language", 1093206, "crp", "Latn", ancestors = "en", } m["crp-mpp"] = { "Macau Pidgin Portuguese", 128804537, "crp", "Hant, Latn", ancestors = "pt", sort_key = {Hant = "Hani-sortkey"}, } m["crp-rsn"] = { "Russenorsk", 505125, "crp", "Cyrl, Latn", ancestors = "nn, ru", translit = {Cyrl = "ru-translit"}, } m["crp-spp"] = { "Samoan Plantation Pidgin", 7409948, "crp", "Latn", ancestors = "en", } m["crp-slb"] = { "Solombala English", 7558525, "crp", "Cyrl, Latn", ancestors = "en, ru", translit = {Cyrl = "ru-translit"}, } m["crp-tpr"] = { "Taimyr Pidgin Russian", 16930506, "crp", "Cyrl", ancestors = "ru", translit = "ru-translit", } m["csu-bba-pro"] = { "Proto-Bongo-Bagirmi", 116773722, "csu-bba", "Latn", type = "reconstructed", } m["csu-maa-pro"] = { "Proto-Mangbetu", 116773786, "csu-maa", "Latn", type = "reconstructed", } m["csu-pro"] = { "Proto-Central Sudanic", 116773730, "csu", "Latn", type = "reconstructed", } m["csu-sar-pro"] = { "Proto-Sara", 116773809, "csu-sar", "Latn", type = "reconstructed", } m["cus-ash"] = { "Ashraaf", 4805855, "cus-som", "Latn", } m["cus-hec-pro"] = { "Proto-Highland East Cushitic", 116773761, "cus-hec", "Latn", type = "reconstructed", } m["cus-som-pro"] = { "Proto-Somaloid", nil, "cus-som", "Latn", type = "reconstructed", } m["cus-sou-pro"] = { "Proto-South Cushitic", 126081567, "cus-sou", "Latn", type = "reconstructed", } m["cus-pro"] = { "Proto-Cushitic", 116773204, "cus", "Latn", type = "reconstructed", } m["dmn-dam"] = { "Dama (Sierra Leone)", 19601574, "dmn", "Latn", } m["dra-bry"] = { "Beary", 1089116, "qfa-mix", "Mlym, Knda", ancestors = "ml, tcy", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["dra-cen-pro"] = { "Proto-Central Dravidian", nil, "dra-cen", "Latn", type = "reconstructed", } m["dra-mkn"] = { "Middle Kannada", 128810572, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-nor-pro"] = { "Proto-North Dravidian", 124433593, "dra-nor", "Latn", type = "reconstructed", } m["dra-okn"] = { "Old Kannada", 15723156, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-ote"] = { "Old Telugu", 126720868, "dra-tel", "Telu", translit = "te-translit", } m["dra-pro"] = { "Proto-Dravidian", 1702853, "dra", "Latn", type = "reconstructed", } m["dra-sdo-pro"] = { "Proto-South Dravidian I", 104847952, -- Wikipedia's "Proto-South Dravidian" is Proto-South Dravidian I in this scheme. "dra-sdo", "Latn", type = "reconstructed", } m["dra-sdt-pro"] = { "Proto-South Dravidian II", 128885257, "dra-sdt", "Latn", type = "reconstructed", } m["dra-sou-pro"] = { "Proto-South Dravidian", 128886121, "dra-sou", "Latn", type = "reconstructed", } m["egx-dem"] = { "Demotic Egyptian", 36765, "egx", "Latn, Egyd, Polyt", sort_key = { Latn = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "e", "ꜥ", "y", "w", "b", "p", "f", "m", "n", "r", "l", "ḥ", "ḫ", "h̭", "ẖ", "h", "š", "s", "q", "k", "g", "ṱ", "ṯ", "t", "ḏ", "%.", "⸗"}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]} }, }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dmn-pro"] = { "Proto-Mande", 116773785, "dmn", "Latn", type = "reconstructed", } m["dmn-mdw-pro"] = { "Proto-Western Mande", 116773822, "dmn-mdw", "Latn", type = "reconstructed", } m["dru-pro"] = { "Proto-Rukai", 116773807, "map", "Latn", type = "reconstructed", } m["ero-gsz"] = { "Geshiza", nil, "ero", "Latn", } m["ero-nya"] = { "Nyagrong Minyag", nil, "ero", "Latn", } m["ero-tau"] = { "Stau", nil, "ero", "Latn", } m["esx-esk-pro"] = { "Proto-Eskimo", 7251842, "esx-esk", "Latn", type = "reconstructed", } m["esx-ink"] = { "Inuktun", 1671647, "esx-inu", "Latn", } m["esx-inq"] = { "Inuinnaqtun", 28070, "esx-inu", "Latn", } m["esx-inu-pro"] = { "Proto-Inuit", 60785588, "esx-inu", "Latn", type = "reconstructed", } m["esx-pro"] = { "Proto-Eskimo-Aleut", 7251843, "esx", "Latn", type = "reconstructed", } m["esx-tut"] = { "Tunumiisut", 15665389, "esx-inu", "Latn", } m["euq-pro"] = { "Proto-Basque", 938011, "euq", "Latn", type = "reconstructed", } m["gba-pro"] = { "Proto-Gbaya", nil, "gba", "Latn", type = "reconstructed", } m["gem-pro"] = { "Proto-Germanic", 669623, "gem", "Latn", type = "reconstructed", sort_key = "gem-pro-sortkey", } m["gme-bur"] = { "Burgundian", 47625, "gme", "Latn", } m["gme-cgo"] = { "Crimean Gothic", 36211, "gme", "Latn", } m["gmq-gut"] = { "Gutnish", 1256646, "gmq", "Latn", ancestors = "gmq-ogt", } m["gmq-jmk"] = { "Jamtish", 35512, "gmq-eas", "Latn", } m["gmq-mno"] = { "Middle Norwegian", 3417070, "gmq-wes", "Latn", } m["gmq-oda"] = { "Old Danish", 12330003, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-ogt"] = { "Old Gutnish", 1133488, "gmq", "Latn, Runr", ancestors = "non", } m["gmq-osw"] = { "Old Swedish", 2417210, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-pro"] = { "Proto-Norse", 1671294, "gmq", "Runr", translit = "Runr-translit", } m["gmq-scy"] = { "Scanian", 768017, "gmq-eas", "Latn", } m["gmw-bgh"] = { "Bergish", 329030, "gmw-frk", "Latn", } m["gmw-cfr"] = { "Central Franconian", 572197, "gmw-hgm", "Latn", ancestors = "gmh", wikimedia_codes = "ksh", } m["gmw-ecg"] = { "East Central German", 499344, -- subsumes Q699284, Q152965 "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-fin"] = { "Fingallian", 3072588, "gmw-ian", "Latn", } m["gmw-gts"] = { "Gottscheerish", 533109, "gmw-hgm", "Latn", ancestors = "bar", } m["gmw-jdt"] = { "Jersey Dutch", 1687911, "gmw-frk", "Latn", ancestors = "nl", } m["gmw-msc"] = { "Middle Scots", 3327000, "gmw-ang", "Latn", ancestors = "enm-esc", } m["gmw-pro"] = { "Proto-West Germanic", 78079021, "gmw", "Latn, Runr", -- type = "reconstructed", -- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added sort_key = "gmw-pro-sortkey", } m["gmw-rfr"] = { "Rhine Franconian", 707007, "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-stm"] = { "Sathmar Swabian", 2223059, "gmw-hgm", "Latn", ancestors = "swg", } m["gmw-tsx"] = { "Transylvanian Saxon", 260942, "gmw-hgm", "Latn", ancestors = "gmw-cfr", } m["gmw-vog"] = { "Volga German", 312574, "gmw-hgm", "Latn", ancestors = "gmw-rfr", } m["gmw-zps"] = { "Zipser German", 205548, "gmw-hgm", "Latn", ancestors = "gmh", } m["gn-cls"] = { "Classical Guarani", 17478065, "gn", "Latn", } m["grk-cal"] = { "Calabrian Greek", 1146398, "grk", "Latn, Grek", ancestors = "grk-ita", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-ita"] = { "Italiot Greek", 19720507, "grk", "Latn, Grek", ancestors = "gkm", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-mar"] = { "Mariupol Greek", 4400023, "grk", "Cyrl, Latn, Grek", ancestors = "gkm", translit = { Cyrl = "grk-mar-translit", Grek = "grk-mar-translit", }, override_translit = true, strip_diacritics = { Cyrl = {remove_diacritics = c.acute}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-pro"] = { "Proto-Hellenic", 1231805, "grk", "Latn, Polyt", type = "reconstructed", sort_key = {Latn = { from = {"ʰ", "ʷ"}, to = {"h", "w"}, remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron }}, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in -- the translit section } m["hmn-pro"] = { "Proto-Hmongic", 116773210, "hmn", "Latn", type = "reconstructed", } m["hmx-mie-pro"] = { "Proto-Mienic", 116773229, "hmx-mie", "Latn", type = "reconstructed", } m["hmx-pro"] = { "Proto-Hmong-Mien", 7251846, "hmx", "Latn", type = "reconstructed", } m["hyx-pro"] = { "Proto-Armenian", 3848498, "hyx", "Latn", type = "reconstructed", } m["iir-nur-pro"] = { "Proto-Nuristani", 116773248, "iir-nur", "Latn", type = "reconstructed", } m["iir-pro"] = { "Proto-Indo-Iranian", 966439, "iir", "Latn", type = "reconstructed", } m["ijo-pro"] = { "Proto-Ijoid", 116773766, "ijo", "Latn", type = "reconstructed", } m["inc-apa"] = { "Apabhramsa", 616419, "inc-mid", "Deva, Shrd, Sidd", ancestors = "pra", translit = { Deva = "sa-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] }, } m["inc-ash"] = { "Ashokan Prakrit", 104854379, "inc-mid", "Brah, Khar", ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Khar = "Khar-translit", }, } m["inc-dng-pro"] = { "Proto-Dangari", nil, "inc-dng", "Latn", type = "reconstructed", } m["inc-kam"] = { "Kamarupi Prakrit", 6356097, "inc-bas", "Brah, Sidd", -- Brah, Sidd translit in [[Module:scripts/data]] } m["inc-kho"] = { "Kholosi", 24952008, "inc-snd", "Latn", } m["inc-krd-pro"] = { "Proto-Kamta", 128816843, "inc-bas", "Latn", ancestors = "inc-kam", type = "reconstructed", } m["inc-mas"] = { "Middle Assamese", 128806836, "inc-bas", "as-Beng", ancestors = "inc-oas", translit = "inc-mas-translit", } m["inc-mbn"] = { "Middle Bengali", 113559927, "inc-bas", "Beng", ancestors = "inc-obn", translit = "inc-mbn-translit", } m["inc-mgu"] = { "Middle Gujarati", 24907429, "inc-wes", "Deva", ancestors = "inc-ogu", } m["inc-mor"] = { "Middle Odia", 128810882, "inc-eas", "Orya", ancestors = "inc-oor", } m["inc-oas"] = { "Early Assamese", 85758237, "inc-bas", "as-Beng", ancestors = "inc-kam", translit = "inc-oas-translit", } m["inc-oaw"] = { "Old Awadhi", nil, "inc-hie", "Deva, Kthi, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Kthi = "sa-Kthi-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-obn"] = { "Old Bengali", 113559926, "inc-bas", "Beng", } m["inc-ogu"] = { "Old Gujarati", 24907427, "inc-wes", "Deva", translit = "sa-translit", } m["inc-ohi"] = { "Old Hindi", 48767781, "inc-hiw", "Deva, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-oor"] = { "Old Odia", 128807801, "inc-eas", "Orya", } m["inc-opa"] = { "Old Punjabi", 115270971, "inc-pan", "Guru, pa-Arab", translit = { Guru = "inc-opa-Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun}, } m["inc-pro"] = { "Proto-Indo-Aryan", 23808344, "inc", "Latn", type = "reconstructed", } m["ine-ana-pro"] = { "Proto-Anatolian", 7251833, "ine-ana", "Latn", type = "reconstructed", } m["ine-bsl-pro"] = { "Proto-Balto-Slavic", 1703347, "ine-bsl", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", c.acute, c.macron, "ˀ"}, to = {"a", "e", "i", "o", "u"} }, } m["ine-kal"] = { "Kalašma", 122770439, "ine-ana", "Xsux", } m["ine-pae"] = { "Paeonian", 2705672, "ine", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ine-pro"] = { "Proto-Indo-European", 37178, "ine", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ĺ", "ḿ", "ń", "ŕ", "ǵ", "ḱ", "ʰ", "ʷ", "₁", "₂", "₃", c.ringbelow, c.acute, c.macron}, to = {"a", "e", "i", "o", "u", "l", "m", "n", "r", "g'", "k'", "¯h", "¯w", "1", "2", "3"} }, } m["ine-toc-pro"] = { "Proto-Tocharian", 104841462, "ine-toc", "Latn", type = "reconstructed", } m["xme-old"] = { "Old Median", 36461, "xme", "Polyt, Latn", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-mid"] = { "Middle Median", 12836150, "xme", "Latn", } m["xme-ker"] = { "Kermanic", 129850, "xme", "fa-Arab, Latn, Hebr", ancestors = "xme-mid", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-taf"] = { "Tafreshi", nil, "xme", "fa-Arab, Latn", ancestors = "xme-mid", } m["xme-ttc-pro"] = { "Proto-Tatic", 122973870, "xme-ttc", "Latn", ancestors = "xme-mid", } m["xme-kls"] = { "Kalasuri", nil, "xme-ttc", ancestors = "xme-ttc-nor", } m["xme-klt"] = { "Kilit", 3612452, "xme-ttc", "Cyrl", -- and fa-Arab? } m["xme-ott"] = { "Old Tati", 434697, "xme-ttc", "fa-Arab, Latn", } m["ira-kms-pro"] = { "Proto-Komisenian", 116773777, "ira-kms", "Latn", type = "reconstructed", } m["ira-mpr-pro"] = { "Proto-Medo-Parthian", 116773227, "ira-mpr", "Latn", type = "reconstructed", } m["ira-pat-pro"] = { "Proto-Pathan", 116773255, "ira-pat", "Latn", type = "reconstructed", } m["ira-pro"] = { "Proto-Iranian", 4167865, "ira", "Latn", type = "reconstructed", } m["ira-zgr-pro"] = { "Proto-Zaza-Gorani", 116775031, "ira-zgr", "Latn", type = "reconstructed", } m["xsc-pro"] = { "Proto-Scythian", 116773273, "xsc", "Latn", type = "reconstructed", } m["xsc-sar-pro"] = { "Proto-Sarmatian", 116773249, "xsc-sar", "Latn", type = "reconstructed", } m["xsc-skw-pro"] = { "Proto-Saka-Wakhi", 116773267, "xsc-skw", "Latn", type = "reconstructed", } m["xsc-sak-pro"] = { "Proto-Saka", 116773264, "xsc-sak", "Latn", type = "reconstructed", } m["ira-sym-pro"] = { "Proto-Shughni-Yazghulami-Munji", 116773813, "ira-sym", "Latn", type = "reconstructed", } m["ira-sgi-pro"] = { "Proto-Sanglechi-Ishkashimi", 116773808, "ira-sgi", "Latn", type = "reconstructed", } m["ira-mny-pro"] = { "Proto-Munji-Yidgha", 116773792, "ira-mny", "Latn", type = "reconstructed", } m["ira-shy-pro"] = { "Proto-Shughni-Yazghulami", 116773812, "ira-shy", "Latn", type = "reconstructed", } m["ira-shr-pro"] = { "Proto-Shughni-Roshani", 116773811, "ira-shr", "Latn", type = "reconstructed", } m["ira-sgc-pro"] = { "Proto-Sogdic", 116773276, "ira-sgc", "Latn", type = "reconstructed", } m["ira-wnj"] = { "Vanji", 3398419, "ira-shy", "Latn", } m["iro-ere"] = { "Erie", 5388365, "iro-nor", "Latn", } m["iro-min"] = { "Mingo", 128531, "iro-nor", "Latn", ietf_subtag = "i-mingo", -- grandfathered IETF tag } m["iro-nor-pro"] = { "Proto-North Iroquoian", 116773242, "iro-nor", "Latn", type = "reconstructed", } m["iro-pro"] = { "Proto-Iroquoian", 7251852, "iro", "Latn", type = "reconstructed", } m["itc-pro"] = { "Proto-Italic", 17102720, "itc", "Latn", type = "reconstructed", } m["itc-psa"] = { "Pre-Samnite", 7239186, "itc-sbl", "Ital, Polyt, Latn", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["jpx-hcj"] = { "Hachijō", 5637049, "jpx", "Jpan", ancestors = "ojp-eas", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jpx-pro"] = { "Proto-Japonic", 3924309, "jpx", "Latn", type = "reconstructed", } m["jpx-ryu-pro"] = { "Proto-Ryukyuan", 56349069, "jpx-ryu", "Latn", type = "reconstructed", } m["kar-pro"] = { "Proto-Karen", 85794783, "kar", "Latn", type = "reconstructed", } m["kca-eas"] = { "Eastern Khanty", 30304622, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-nor"] = { "Northern Khanty", 30304527, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-pro"] = { "Proto-Khanty", 127505171, "kca", "Latn", type = "reconstructed", } m["kca-sou"] = { "Southern Khanty", 30304618, "kca", "Cyrl", translit = "kca-translit", override_translit = true, } m["khi-kho-pro"] = { "Proto-Khoe", 116773218, "khi-kho", "Latn", type = "reconstructed", } m["khi-kun"] = { "ǃKung", 32904, "khi-kxa", "Latn", } m["ko-ear"] = { "Early Modern Korean", 756014, "qfa-kor", "Kore", ancestors = "okm", translit = "okm-translit", -- Kore strip_diacritics in [[Module:scripts/data]] } m["kro-pro"] = { "Proto-Kru", 116773778, "kro", "Latn", type = "reconstructed", } m["ku-pro"] = { "Proto-Kurdish", 116773221, "ku", "Latn", type = "reconstructed", } m["map-ata-pro"] = { "Proto-Atayalic", 116773151, "map-ata", "Latn", type = "reconstructed", } m["map-bms"] = { "Banyumasan", 33219, "map", "Latn, Java", } m["map-pro"] = { "Proto-Austronesian", 49230, "map", "Latn", type = "reconstructed", } m["mis-hkl"] = { "Kelantan Peranakan Hokkien", 108794818, "qfa-mix", ancestors = "nan-hbl, sou, mfa", } m["mis-idn"] = { "Idiom Neutral", 35847, "art", "Latn", type = "appendix-constructed", } m["mis-isa"] = { "Isaurian", 16956868, nil, -- "Xsux, Hluw, Latn", } m["mis-jie"] = { "Jie", 124424186, nil, "Hani", sort_key = "Hani-sortkey", } m["mis-jzh"] = { "Jizhao", 45242758, "qfa-bej", "Latn", } m["mis-kas"] = { "Kassite", 35612, nil, "Xsux", } m["mis-mmd"] = { "Mimi of Decorse", 6862206, nil, "Latn", } m["mis-mmn"] = { "Mimi of Nachtigal", 6862207, nil, "Latn", } m["mis-phi"] = { "Philistine", 2230924, nil, "Phnx", -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["mis-rou"] = { "Rouran", 48816637, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tdl"] = { "Turdulian", 133176492, } m["mis-tdt"] = { "Turdetanian", 133176461, } m["mis-tnw"] = { "Tangwang", 7683179, "qfa-mix", "Latn", ancestors = "cmn, sce", } m["mis-tuh"] = { "Tuyuhun", 48816625, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tuo"] = { "Tuoba", 48816629, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-wuh"] = { "Wuhuan", 118976867, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xbi"] = { "Xianbei", 4448647, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xnu"] = { "Xiongnu", 10901674, nil, "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mjg-mgl"] = { "Mongghul", 53765528, "mjg", "Latn", -- also Mong, Cyrl ? } m["mjg-mgr"] = { "Mangghuer", 56285392, "mjg", "Latn", -- also Mong, Cyrl ? } m["mkh-asl-pro"] = { "Proto-Aslian", 55630680, "mkh-asl", "Latn", type = "reconstructed", } m["mkh-ban-pro"] = { "Proto-Bahnaric", 116773189, "mkh-ban", "Latn", type = "reconstructed", } m["mkh-kat-pro"] = { "Proto-Katuic", 116773772, "mkh-kat", "Latn", type = "reconstructed", } m["mkh-khm-pro"] = { "Proto-Khmuic", 116773774, "mkh-khm", "Latn", type = "reconstructed", } m["mkh-kmr-pro"] = { "Proto-Khmeric", 55630684, "mkh-kmr", "Latn", type = "reconstructed", } m["mkh-mmn"] = { "Middle Mon", 121337926, "mkh-mnc", "Latn, Mymr", --and also Pallava ancestors = "omx", } m["mkh-mnc-pro"] = { "Proto-Monic", 116773231, "mkh-mnc", "Latn", type = "reconstructed", } m["mkh-mvi"] = { "Middle Vietnamese", 9199, "mkh-vie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mkh-pal-pro"] = { "Proto-Palaungic", 104847372, "mkh-pal", "Latn", type = "reconstructed", } m["mkh-pea-pro"] = { "Proto-Pearic", 116773804, "mkh-pea", "Latn", type = "reconstructed", } m["mkh-pkn-pro"] = { "Proto-Pakanic", 116773803, "mkh-pkn", "Latn", type = "reconstructed", } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. "Proto-Mon-Khmer", 7251859, "mkh", "Latn", type = "reconstructed", } m["mnw-tha"] = { -- To be removed. "Thai Mon", nil, "mkh-mnc", "Mymr, Thai", ancestors = "mkh-mmn", sort_key = { from = {"[%p]", "ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ", "[็-๎]", "([เแโใไ])([ก-ฮ])ฺ?"}, to = {"", "္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ", "", "%2%1"} }, } m["mkh-vie-pro"] = { "Proto-Vietic", 109432616, "mkh-vie", "Latn", type = "reconstructed", } m["mns-cen"] = { "Central Mansi", 128810384, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-nor"] = { "Northern Mansi", 30304537, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-pro"] = { "Proto-Mansi", 128883093, "mns", "Latn", type = "reconstructed", } m["mns-sou"] = { "Southern Mansi", 30304629, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mun-pro"] = { "Proto-Munda", 105102373, "mun", "Latn", type = "reconstructed", } m["myn-chl"] = { -- the stage after ''emy'' "Ch'olti'", 873995, "myn", "Latn", } m["myn-pro"] = { "Proto-Mayan", 3321532, "myn", "Latn", type = "reconstructed", } m["nai-ala"] = { "Alazapa", 128810233, nil, "Latn", } m["nai-bay"] = { "Bayogoula", 1563704, nil, "Latn", } m["nai-cal"] = { "Calusa", 51782, nil, "Latn", } m["nai-chi"] = { "Chiquimulilla", 25339627, "nai-xin", "Latn", } m["nai-chu-pro"] = { "Proto-Chumash", 116773736, "nai-chu", "Latn", type = "reconstructed", } m["nai-cig"] = { "Ciguayo", 20741700, nil, "Latn", } m["nai-ckn-pro"] = { "Proto-Chinookan", 116773735, "nai-ckn", "Latn", type = "reconstructed", } m["nai-guz"] = { "Guazacapán", 19572028, "nai-xin", "Latn", } m["nai-hit"] = { "Hitchiti", 1542882, "nai-mus", "Latn", } m["nai-ipa"] = { "Ipai", 3027474, "nai-yuc", "Latn", } m["nai-jtp"] = { "Jutiapa", nil, "nai-xin", "Latn", } m["nai-jum"] = { "Jumaytepeque", 25339626, "nai-xin", "Latn", } m["nai-kat"] = { "Kathlamet", 6376639, "nai-ckn", "Latn", } m["nai-klp-pro"] = { "Proto-Kalapuyan", 116773771, "nai-klp", "Latn", type = "reconstructed", } m["nai-knm"] = { "Konomihu", 3198734, "nai-shs", "Latn", } m["nai-kum"] = { "Kumeyaay", 4910139, "nai-yuc", "Latn", } m["nai-mac"] = { "Macoris", 21070851, nil, "Latn", } m["nai-mdu-pro"] = { "Proto-Maidun", 116773784, "nai-mdu", "Latn", type = "reconstructed", } m["nai-miz-pro"] = { "Proto-Mixe-Zoque", 7251858, "nai-miz", "Latn", type = "reconstructed", } m["nai-mus-pro"] = { "Proto-Muskogean", 116775368, "nai-mus", "Latn", type = "reconstructed", } m["nai-nao"] = { "Naolan", 6964594, nil, "Latn", } m["nai-nrs"] = { "New River Shasta", 7011254, "nai-shs", "Latn", } m["nai-okw"] = { "Okwanuchu", 3350126, "nai-shs", "Latn", } m["nai-per"] = { "Pericú", 3375369, nil, "Latn", } m["nai-pic"] = { "Picuris", 7191257, "nai-kta", "Latn", } m["nai-plp-pro"] = { "Proto-Plateau Penutian", 116773806, "nai-plp", "Latn", type = "reconstructed", } m["nai-pom-pro"] = { "Proto-Pomo", 116773262, "nai-pom", "Latn", type = "reconstructed", } m["nai-qng"] = { "Quinigua", 36360, nil, "Latn", } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan "Proto-Siouan-Catawban", 116773275, "nai-sca", "Latn", type = "reconstructed", } m["nai-sin"] = { "Sinacantán", 24190249, "nai-xin", "Latn", } m["nai-sln"] = { "Salvadoran Lenca", 3229434, "nai-len", "Latn", } m["nai-spt"] = { "Sahaptin", 3833015, "nai-shp", "Latn", } m["nai-tap"] = { "Tapachultec", 7684401, "nai-miz", "Latn", } m["nai-taw"] = { "Tawasa", 7689233, nil, "Latn", } m["nai-teq"] = { "Tequistlatec", 2964454, "nai-tqn", "Latn", } m["nai-tip"] = { "Tipai", 3027471, "nai-yuc", "Latn", } m["nai-tot-pro"] = { "Proto-Totozoquean", 116773285, "nai-tot", "Latn", type = "reconstructed", } m["nai-tsi-pro"] = { "Proto-Tsimshianic", nil, "nai-tsi", "Latn", type = "reconstructed", } m["nai-utn-pro"] = { "Proto-Utian", 116773290, "nai-utn", "Latn", type = "reconstructed", } m["nai-wai"] = { "Waikuri", 3118702, nil, "Latn", } m["nai-wji"] = { "Western Jicaque", 3178610, "nai-jcq", "Latn", } m["nai-yup"] = { "Yupiltepeque", 25339628, "nai-xin", "Latn", } m["nan-dat"] = { "Datian Min", 19855572, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-hbl"] = { "Hokkien", 1624231, "zhx-nan", "Hants, Latn, Bopo, Kana", wikimedia_codes = "zh-min-nan", generate_forms = "zh-generateforms", sort_key = { Hani = "Hani-sortkey", Kana = "Kana-sortkey" }, } m["nan-hlh"] = { "Hailufeng Min", 120755728, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-lnx"] = { "Longyan Min", 6674568, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-tws"] = { "Teochew", 36759, "zhx-nan", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["nan-zhe"] = { "Zhenan Min", 3846710, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-zsh"] = { "Sanxiang Min", 7420769, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["ngf-bin-pro"] = { "Proto-Binanderean", 137881672, "ngf-bin", "Latn", type = "reconstructed", } m["ngf-pro"] = { "Proto-Trans-New Guinea", 85794785, "ngf", "Latn", type = "reconstructed", } m["nic-bco-pro"] = { "Proto-Benue-Congo", 116773194, "nic-bco", "Latn", type = "reconstructed", } m["nic-bod-pro"] = { "Proto-Bantoid", 116773190, "nic-bod", "Latn", type = "reconstructed", } m["nic-eov-pro"] = { "Proto-Eastern Oti-Volta", 116773753, "nic-eov", "Latn", type = "reconstructed", } m["nic-gns-pro"] = { "Proto-Gurunsi", 116773759, "nic-gns", "Latn", type = "reconstructed", } m["nic-grf-pro"] = { "Proto-Grassfields", 116773755, "nic-grf", "Latn", type = "reconstructed", } m["nic-gur-pro"] = { "Proto-Gur", 116773758, "nic-gur", "Latn", type = "reconstructed", } m["nic-jkn-pro"] = { "Proto-Jukunoid", 116773769, "nic-jkn", "Latn", type = "reconstructed", } m["nic-lcr-pro"] = { "Proto-Lower Cross River", 116773782, "nic-lcr", "Latn", type = "reconstructed", } m["nic-ogo-pro"] = { "Proto-Ogoni", 116773799, "nic-ogo", "Latn", type = "reconstructed", } m["nic-ovo-pro"] = { "Proto-Oti-Volta", 116773802, "nic-ovo", "Latn", type = "reconstructed", } m["nic-plt-pro"] = { "Proto-Plateau", 116773805, "nic-plt", "Latn", type = "reconstructed", } m["nic-pro"] = { "Proto-Niger-Congo", 108000748, "nic", "Latn", type = "reconstructed", } m["nic-ubg-pro"] = { "Proto-Ubangian", 116773818, "nic-ubg", "Latn", type = "reconstructed", } m["nic-ucr-pro"] = { "Proto-Upper Cross River", 116773819, "nic-ucr", "Latn", type = "reconstructed", } m["nic-vco-pro"] = { "Proto-Volta-Congo", 116773293, "nic-vco", "Latn", type = "reconstructed", } m["njo-jgl"] = { "Chungli Ao", 55607615, "sit-aao", "Latn", } m["nub-har"] = { "Haraza", 19572059, "nub", "Arab, Latn", } m["nub-pro"] = { "Proto-Nubian", 116773246, "nub", "Latn", type = "reconstructed", } m["omq-cha-pro"] = { "Proto-Chatino", 116773202, "omq-cha", "Latn", type = "reconstructed", } m["omq-maz-pro"] = { "Proto-Mazatec", 116773790, "omq-maz", "Latn", type = "reconstructed", } m["omq-mix-pro"] = { "Proto-Mixtecan", 21573423, "omq-mix", "Latn", type = "reconstructed", } m["omq-mxt-pro"] = { "Proto-Mixtec", 21573424, "omq-mxt", "Latn", type = "reconstructed", } m["omq-otp-pro"] = { "Proto-Oto-Pamean", 116773251, "omq-otp", "Latn", type = "reconstructed", } m["omq-pro"] = { "Proto-Oto-Manguean", 33669, "omq", "Latn", type = "reconstructed", } m["omq-sjq"] = { "San Juan Quiahije Chatino", 138330751, "omq-cha", "Latn", } m["omq-tel"] = { "Teposcolula Mixtec", nil, "omq-mxt", "Latn", } m["omq-teo"] = { "Teojomulco Chatino", 25340451, "omq-cha", "Latn", } m["omq-tri-pro"] = { "Proto-Triqui", 116773817, "omq-tri", "Latn", type = "reconstructed", } m["omq-zap-pro"] = { "Proto-Zapotecan", 116773297, "omq-zap", "Latn", type = "reconstructed", } m["omq-zpc-pro"] = { "Proto-Zapotec", 116773296, "omq-zpc", "Latn", type = "reconstructed", } m["omv-aro-pro"] = { "Proto-Aroid", 116773721, "omv-aro", "Latn", type = "reconstructed", } m["omv-diz-pro"] = { "Proto-Dizoid", 116773750, "omv-diz", "Latn", type = "reconstructed", } m["omv-pro"] = { "Proto-Omotic", 116773800, "omv", "Latn", type = "reconstructed", } m["oto-otm-pro"] = { "Proto-Otomi", 5908710, "oto-otm", "Latn", type = "reconstructed", } m["oto-pro"] = { "Proto-Otomian", 116773252, "oto", "Latn", type = "reconstructed", } m["paa-kmn"] = { "Kómnzo", 18344310, "paa-wko", "Latn", } m["paa-kwn"] = { "Kuwani", 6449056, "qfa-unc", -- poorly attested, possibly the same as or related to Kalabra "Latn", } m["paa-lei"] = { "Leitre", 85776228, "paa-isk", } m["paa-nha-pro"] = { "Proto-North Halmahera", 116773241, "paa-nha", "Latn", type = "reconstructed" } m["paa-nun"] = { "Nungon", 128807788, "ngf-ynu", "Latn", } m["phi-din"] = { "Dinapigue Agta", 16945774, "phi", "Latn", } m["phi-kal-pro"] = { "Proto-Kalamian", 116773213, "phi-kal", "Latn", type = "reconstructed", } m["phi-nag"] = { "Nagtipunan Agta", 16966111, "phi", "Latn", } m["phi-pro"] = { "Proto-Philippine", 18204898, "phi", "Latn", type = "reconstructed", } m["poz-abi"] = { "Abai", 19570729, "poz-san", "Latn", } m["poz-bal"] = { "Baliledo", 4850912, "poz", "Latn", } m["poz-btk-pro"] = { "Proto-Bungku-Tolaki", 116773724, "poz-btk", "Latn", type = "reconstructed", } m["poz-cet-pro"] = { "Proto-Central-Eastern Malayo-Polynesian", 2269883, "poz-cet", "Latn", type = "reconstructed", } m["poz-hce-pro"] = { "Proto-Halmahera-Cenderawasih", 116773209, "poz-hce", "Latn", type = "reconstructed", } m["poz-lgx-pro"] = { "Proto-Lampungic", 116773222, "poz-lgx", "Latn", type = "reconstructed", } m["poz-mcm-pro"] = { "Proto-Malayo-Chamic", 116773225, "poz-mcm", "Latn", type = "reconstructed", } m["poz-mic-pro"] = { "Proto-Micronesian", 111939079, "poz-mic", "Latn", type = "reconstructed", } m["poz-mly-pro"] = { "Proto-Malayic", 98057728, "poz-mly", "Latn", type = "reconstructed", } m["poz-msa-pro"] = { "Proto-Malayo-Sumbawan", 116773226, "poz-msa", "Latn", type = "reconstructed", } m["poz-oce-pro"] = { "Proto-Oceanic", 141741, "poz-oce", "Latn", type = "reconstructed", } m["poz-pep-pro"] = { "Proto-Eastern Polynesian", 113988745, "poz-pep", "Latn", type = "reconstructed", } m["poz-pnp-pro"] = { "Proto-Nuclear Polynesian", 113988746, "poz-pnp", "Latn", type = "reconstructed", } m["poz-pol-pro"] = { "Proto-Polynesian", 1658709, "poz-pol", "Latn", type = "reconstructed", } m["poz-pro"] = { "Proto-Malayo-Polynesian", 3832960, "poz", "Latn", type = "reconstructed", } m["poz-sml"] = { "Sarawak Malay", 4251702, "poz-mly", "Latn, ms-Arab", } m["poz-ssw-pro"] = { "Proto-South Sulawesi", 116773279, "poz-ssw", "Latn", type = "reconstructed", } m["poz-swa-pro"] = { "Proto-North Sarawak", 116773243, "poz-swa", "Latn", type = "reconstructed", } m["poz-ter"] = { "Terengganu Malay", 4207412, "poz-mly", "Latn, ms-Arab", } m["pqe-pro"] = { "Proto-Eastern Malayo-Polynesian", 2269883, "pqe", "Latn", type = "reconstructed", } m["pra-niy"] = { "Niya Prakrit", 11991601, "inc-mid", "Khar", ancestors = "inc-ash", translit = "Khar-translit", } m["qfa-adm-pro"] = { "Proto-Great Andamanese", 116773756, "qfa-adm", "Latn", type = "reconstructed", } m["qfa-bet-pro"] = { "Proto-Be-Tai", 116773193, "qfa-bet", "Latn", type = "reconstructed", } m["qfa-cka-pro"] = { "Proto-Chukotko-Kamchatkan", 7251837, "qfa-cka", "Latn", type = "reconstructed", } m["qfa-hur-pro"] = { "Proto-Hurro-Urartian", 116773211, "qfa-hur", "Latn", type = "reconstructed", } m["qfa-kad-pro"] = { "Proto-Kadu", 116773770, "qfa-kad", "Latn", type = "reconstructed", } m["qfa-kms-pro"] = { "Proto-Kam-Sui", 55630682, "qfa-kms", "Latn", type = "reconstructed", } m["qfa-kor-pro"] = { "Proto-Koreanic", 467883, "qfa-kor", "Latn", type = "reconstructed", } m["qfa-kra-pro"] = { "Proto-Kra", 7251854, "qfa-kra", "Latn", type = "reconstructed", } m["qfa-lic-pro"] = { "Proto-Hlai", 7251845, "qfa-lic", "Latn", type = "reconstructed", } m["qfa-onb-pro"] = { "Proto-Be", 116773192, "qfa-onb", "Latn", type = "reconstructed", } m["qfa-ong-pro"] = { "Proto-Ongan", 116773801, "qfa-ong", "Latn", type = "reconstructed", } m["qfa-tak-pro"] = { "Proto-Kra-Dai", 104901616, "qfa-tak", "Latn", type = "reconstructed", } m["qfa-yen-pro"] = { "Proto-Yeniseian", 27639, "qfa-yen", "Latn", type = "reconstructed", } m["qfa-yuk-pro"] = { "Proto-Yukaghir", 116773294, "qfa-yuk", "Latn", type = "reconstructed", } m["qwe-kch"] = { "Kichwa", 1740805, "qwe", "Latn", ancestors = "qu", } m["qwe-pro"] = { "Proto-Quechuan", 5575757, "qwe", "Latn", type = "reconstructed", } m["roa-ang"] = { "Angevin", 56782, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-bbn"] = { "Bourbonnais-Berrichon", 2899128, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-brg"] = { "Bourguignon", 508332, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-can"] = { "Cantabrian", 917021, "roa-asl", "Latn", } m["roa-cha"] = { "Champenois", 430018, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-fcm"] = { "Franc-Comtois", 510561, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gal"] = { "Gallo", 37300, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gib"] = { "Gallo-Italic of Basilicata", 3094838, "roa-git", ancestors = "pms-old", "Latn", } m["roa-gis"] = { "Gallo-Italic of Sicily", 2629019, "roa-git", "Latn", ancestors = "pms-old", } m["roa-leo"] = { "Leonese", 34108, "roa-asl", "Latn", } m["roa-lor"] = { "Lorrain", 671198, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-oca"] = { "Old Catalan", 15478520, "roa-ocr", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, } m["roa-ole"] = { "Old Leonese", 125977465, "roa-asl", "Latn", } m["roa-ona"] = { "Old Navarro-Aragonese", 2736184, "roa-nar", "Latn", } m["roa-opt"] = { "Old Galician-Portuguese", 1072111, "roa-gap", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["roa-orl"] = { "Orléanais", 28497058, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-poi"] = { "Poitevin-Saintongeais", 514123, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-tar"] = { "Tarantino", 695526, "roa-itr", "Latn", wikimedia_codes = "roa-tara", } m["sai-all"] = { "Allentiac", 19570789, "sai-hrp", "Latn", } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' "Andoquero", 16828359, "sai-wit", "Latn", } m["sai-ayo"] = { "Ayomán", 16937754, "sai-jir", "Latn", } m["sai-bae"] = { "Baenan", 3401998, "qfa-unc", -- extinct, poorly attested; only known through 9 words "Latn", } m["sai-bag"] = { "Bagua", 5390321, "qfa-unc", -- extinct, poorly attested; possibly Cariban "Latn", } m["sai-bet"] = { "Betoi", 926551, "qfa-iso", "Latn", } m["sai-bor-pro"] = { "Proto-Boran", nil, "sai-bor", "Latn", } m["sai-cac"] = { "Cacán", 945482, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-caq"] = { "Caranqui", 2937753, "sai-bar", "Latn", } m["sai-car-pro"] = { "Proto-Cariban", 116773196, "sai-car", "Latn", type = "reconstructed", } m["sai-cat"] = { "Catacao", 5051136, "sai-ctc", "Latn", } m["sai-cer-pro"] = { "Proto-Cerrado", 116773200, "sai-cer", "Latn", type = "reconstructed", } m["sai-chi"] = { "Chirino", 5390321, "qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu) "Latn", } m["sai-chn"] = { "Chaná", 5072718, "sai-crn", "Latn", } m["sai-chp"] = { "Chapacura", 5072884, "sai-cpc", "Latn", } m["sai-chr"] = { "Charrua", 5086680, "sai-crn", "Latn", } m["sai-chu"] = { "Churuya", 5118339, "sai-guh", "Latn", } m["sai-cje-pro"] = { "Proto-Central Jê", 116773198, "sai-cje", "Latn", type = "reconstructed", } m["sai-cmg"] = { "Comechingon", 6644203, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-cno"] = { "Chono", 5104704, "qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious "Latn", } m["sai-cnr"] = { "Cañari", 5055572, "qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan "Latn", } m["sai-coe"] = { "Coeruna", 6425639, "sai-wit", "Latn", } m["sai-col"] = { "Colán", 5141893, "sai-ctc", "Latn", } m["sai-cop"] = { "Copallén", 5390321, "qfa-unc", -- extinct, only four words attested; possibly Cholonan "Latn", } m["sai-crd"] = { "Coroado Puri", 24191321, "sai-mje", "Latn", } m["sai-ctq"] = { "Catuquinaru", 16858455, "qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages "Latn", } m["sai-cul"] = { "Culli", 2879660, "qfa-unc", -- extinct, poorly attested; often considered an isolate "Latn", } m["sai-cva"] = { "Cueva", 5192644, "qfa-unc", -- extinct, poorly attested; possibly Chocoan "Latn", } m["sai-esm"] = { "Esmeralda", 3058083, "qfa-unc", -- extinct, poorly attested; possibly related to Yaruro "Latn", } m["sai-ewa"] = { "Ewarhuyana", 16898104, nil, "Latn", } m["sai-gam"] = { "Gamela", 5403661, "qfa-unc", -- extinct, poorly attested; possibly an isolate "Latn", } m["sai-gay"] = { "Gayón", 5528902, "sai-jir", "Latn", } m["sai-gmo"] = { "Guamo", 5613495, "qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024). "Latn", } m["sai-gua"] = { "Guachí", 5613172, "sai-guc", "Latn", } m["sai-gue"] = { "Güenoa", 5626799, "sai-crn", "Latn", } m["sai-hau"] = { "Haush", 3128376, "sai-cho", "Latn", } m["sai-jee-pro"] = { "Proto-Jê", 116773212, "sai-jee", "Latn", type = "reconstructed", } m["sai-jko"] = { "Jeikó", 6176527, "sai-mje", "Latn", } m["sai-jrj"] = { "Jirajara", 6202966, "sai-jir", "Latn", } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc "Katembri", 6375925, "qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia] "Latn", } m["sai-mal"] = { "Malalí", 6741212, "sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry "Latn", } m["sai-mar"] = { "Maratino", 6755055, "qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan "Latn", } m["sai-mat"] = { "Matanawi", 6786047, "qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified "Latn", } m["sai-mcn"] = { "Mocana", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-men"] = { "Menien", 16890110, "sai-mje", "Latn", } m["sai-mil"] = { "Millcayac", 19573012, "sai-hrp", "Latn", } m["sai-mlb"] = { "Malibu", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-msk"] = { "Masakará", 6782426, "sai-mje", "Latn", } m["sai-muc"] = { "Mucuchí", 6931290, nil, -- generally considered Timotean, for which we have no entry "Latn", } m["sai-mue"] = { "Muellama", 16886936, "sai-bar", "Latn", } m["sai-muz"] = { "Muzo", 6644203, "qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban) "Latn", } m["sai-mys"] = { "Maynas", 16919393, "sai-cah", -- per Campbell (2024); formerly considered unclassified "Latn", } m["sai-nat"] = { "Natú", 9006749, "qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages] "Latn", } m["sai-nje-pro"] = { "Proto-Northern Jê", 116773245, "sai-nje", "Latn", type = "reconstructed", } m["sai-opo"] = { "Opón", 7099152, "sai-car", "Latn", } m["sai-oto"] = { "Otomaco", 16879234, "sai-otm", "Latn", } m["sai-pal"] = { "Palta", 3042978, "qfa-unc", -- extinct, unclassified; possibly Chicham "Latn", } m["sai-pam"] = { "Pamigua", 5908689, "sai-otm", "Latn", } m["sai-par"] = { "Paratió", 16890038, "qfa-unc", -- extinct, poorly attested; possibly Xukuruan "Latn", } m["sai-peb"] = { "Peba", 3373890, "sai-pey", "Latn", } m["sai-pnz"] = { "Panzaleo", 3123275, "qfa-unc", -- extinct, unclassified; possibly Paezan "Latn", } m["sai-prh"] = { "Puruhá", 3410994, "qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari "Latn", } m["sai-ptg"] = { "Patagón", 128807870, "sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024) "Latn", } m["sai-pur"] = { "Purukotó", 7261622, "sai-pem", "Latn", } m["sai-pyg"] = { "Payaguá", 7156643, "sai-guc", "Latn", } m["sai-pyk"] = { "Pykobjê", 98113977, "sai-nje", "Latn", } m["sai-qmb"] = { "Quimbaya", 7272043, "qfa-unc", -- extinct, might not exist; few known words "Latn", } m["sai-qtm"] = { "Quitemo", 7272651, "sai-cpc", "Latn", } m["sai-rab"] = { "Rabona", 6644203, "qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra "Latn", } m["sai-ram"] = { "Ramanos", 16902824, "qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages" "Latn", } m["sai-sac"] = { "Sácata", 5390321, "qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan "Latn", } m["sai-san"] = { "Sanaviron", 16895999, "qfa-unc", -- extinct, unclassified; no consensus on classification "Latn", } m["sai-sap"] = { "Sapará", 7420922, "sai-car", "Latn", } m["sai-sec"] = { "Sechura", 7442912, "qfa-unc", -- extinct, poorly attested; possibly Catacaoan "Latn", } m["sai-sin"] = { "Sinúfana", 7525275, "qfa-unc", -- moribund, poorly attested; possibly Chocoan "Latn", } m["sai-sje-pro"] = { "Proto-Southern Jê", 116773814, "sai-sje", "Latn", type = "reconstructed", } m["sai-tab"] = { "Tabancale", 5390321, "qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate "Latn", } m["sai-tal"] = { "Tallán", 16910468, "qfa-unc", -- extinct, poorly attested; might be Catacaoan "Latn", } m["sai-tap"] = { "Tapayuna", 30719984, "sai-nje", "Latn", } m["sai-tar-pro"] = { "Proto-Taranoan", 116773816, "sai-tar", "Latn", type = "reconstructed", } m["sai-teu"] = { "Teushen", 3519243, "qfa-unc", -- probably extinct by the 1950's; possibly Chonan "Latn", } m["sai-tim"] = { "Timote", 7806995, nil, -- possibly in a small Timotean family "Latn", } m["sai-tpr"] = { "Taparita", 7684460, "sai-otm", "Latn", } m["sai-trr"] = { "Tarairiú", 7685313, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sai-wai"] = { "Waitaká", 16918610, "qfa-unc", -- extinct, possibly Purian "Latn", } m["sai-way"] = { "Wayumara", 7960726, "sai-car", "Latn", } m["sai-wit-pro"] = { "Proto-Witotoan", 116773823, "sai-wit", "Latn", type = "reconstructed", } m["sai-wnm"] = { "Wanham", 16879440, "sai-cpc", "Latn", } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat "Xocó", 12953620, "qfa-unc", -- extinct and poorly attested; not clear if one or three languages "Latn", } m["sai-yao"] = { "Yao (South America)", 16979655, "sai-ven", "Latn", } m["sai-yar"] = { -- not the same family as 'suy' "Yarumá", 3505859, "sai-pek", "Latn", } m["sai-yri"] = { "Yuri", 2669157, "sai-tyu", "Latn", } m["sai-yup"] = { "Yupua", 8061430, "sai-tuc", "Latn", } m["sai-yur"] = { "Yurumanguí", 1281291, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sal-pro"] = { "Proto-Salish", 116773269, "sal", "Latn", type = "reconstructed", } m["sdv-daj-pro"] = { "Proto-Daju", 116773739, "sdv-daj", "Latn", type = "reconstructed", } m["sdv-eje-pro"] = { "Proto-Eastern Jebel", 116773751, "sdv-eje", "Latn", type = "reconstructed", } m["sdv-nil-pro"] = { "Proto-Nilotic", 116773794, "sdv-nil", "Latn", type = "reconstructed", } m["sdv-nyi-pro"] = { "Proto-Nyima", 116773796, "sdv-nyi", "Latn", type = "reconstructed", } m["sdv-tmn-pro"] = { "Proto-Taman", 116773815, "sdv-tmn", "Latn", type = "reconstructed", } m["sel-nor"] = { "Northern Selkup", 30304565, "sel", "Cyrl", translit = "sel-nor-translit", } m["sel-pro"] = { "Proto-Selkup", 128884235, "sel", "Latn", type = "reconstructed", } m["sel-sou"] = { "Southern Selkup", 30304639, "sel", "Cyrl", translit = "sel-sou-translit", } m["sem-amm"] = { "Ammonite", 279181, "sem-can", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-amo"] = { "Amorite", 35941, "sem-nwe", "Xsux, Latn", } m["sem-cha"] = { "Chaha", 35543, "sem-eth", "Ethi", translit = "Ethi-translit", } m["sem-dad"] = { "Dadanitic", 21838040, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-dum"] = { "Dumaitic", 128810397, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-has"] = { "Hasaitic", 3541433, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-his"] = { "Hismaic", 22948260, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-mhr"] = { "Muher", 33743, "sem-eth", "Latn", } m["sem-pro"] = { "Proto-Semitic", 1658554, "sem", "Latn", type = "reconstructed", } m["sem-saf"] = { "Safaitic", 472586, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-sam"] = { "Samalian", 85847147, "sem-nwe", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-srb"] = { "Old South Arabian", 35025, "sem-osa", "Sarb", -- Sarb translit in [[Module:scripts/data]] } m["sem-tay"] = { "Taymanitic", 24912301, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-tha"] = { "Thamudic", 843030, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-wes-pro"] = { "Proto-West Semitic", 98021726, "sem-wes", "Latn", type = "reconstructed", } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' "Proto-Siouan", 34181, "sio", "Latn", type = "reconstructed", } m["sit-aao-pro"] = { "Proto-Central Naga", nil, "sit-aao", "Latn", type = "reconstructed", } m["sit-bai-pro"] = { "Proto-Bai", nil, "sit-bai", "Latn", type = "reconstructed", } m["sit-ban"] = { "Bangru", 56071779, "sit-hrs", "Latn", } m["sit-bdi-pro"] = { "Proto-Bodish", nil, "sit-bdi", "Latn", type = "reconstructed", } m["sit-bok"] = { "Bokar", 4938727, "sit-tan", "Latn, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["sit-cai"] = { "Caijia", 5017528, "sit-cln", "Latn" } m["sit-cha"] = { "Chairel", 5068066, "sit-luu", "Latn", } m["sit-ers-pro"] = { "Proto-Ersuic", nil, "sit-ers", "Latn", type = "reconstructed", } m["sit-hrs-pro"] = { "Proto-Hrusish", 116773762, "sit-hrs", "Latn", type = "reconstructed", } m["sit-jap"] = { "Japhug", 3162245, "sit-egy", "Latn", } m["sit-kha-pro"] = { "Proto-Kham", 116773773, "sit-kha", "Latn", type = "reconstructed", } m["sit-khb-pro"] = { "Proto-Kho-Bwa", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khp-pro"] = { "Proto-Puroik", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khw-pro"] = { "Proto-Western Kho-Bwa", nil, "sit-khw", "Latn", type = "reconstructed", } m["sit-kon-pro"] = { "Proto-Northern Naga", nil, "sit-kon", "Latn", type = "reconstructed", } m["sit-liz"] = { "Lizu", 6660653, "sit-ers", "Latn", -- and Ersu Shaba } m["sit-lnj"] = { "Longjia", 17096251, "sit-cln", "Latn" } m["sit-lrn"] = { "Luren", 16946370, "sit-cln", "Latn" } m["sit-luu-pro"] = { "Proto-Luish", 116773783, "sit-luu", "Latn", type = "reconstructed", } m["sit-nas-pro"] = { "Proto-Naish", nil, "sit-nas", "Latn", type = "reconstructed", } m["sit-prn"] = { "Puiron", 7259048, "sit-zem", } m["sit-pro"] = { "Proto-Sino-Tibetan", 24839178, "sit", "Latn", type = "reconstructed", } m["sit-sit"] = { "Situ", 19840830, "sit-egy", "Latn", } m["sit-tam-pro"] = { "Proto-Tamangic", 117469295, "sit-tam", "Latn", type = "reconstructed", } m["sit-tan-pro"] = { "Proto-Tani", 116773284, "sit-tan", "Latn", -- needs verification type = "reconstructed", } m["sit-tgm"] = { "Tangam", 17041370, "sit-tan", "Latn", } m["sit-tng-pro"] = { "Proto-Tangkhulic", nil, "sit-tng", "Latn", type = "reconstructed" } m["sit-tos"] = { "Tosu", 7827899, "sit-ers", "Latn", -- also Ersu Shaba } m["sit-tsh"] = { "Tshobdun", 19840950, "sit-egy", "Latn", } m["sit-zbu"] = { "Zbu", 19841106, "sit-egy", "Latn", } m["sla-pro"] = { "Proto-Slavic", 747537, "sla", "Latn", type = "reconstructed", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {'ś'}, }, sort_key = { from = {"č", "ď", "ě", "ę", "ь", "ľ", "ň", "ǫ", "ř", "š", "ś", "ť", "ъ", "ž"}, to = {"c²", "d²", "e²", "e³", "i²", "l²", "nj", "o²", "r²", "s²", "s³", "t²", "u²", "z²"}, } } m["smi-pro"] = { "Proto-Samic", 7251862, "smi", "Latn", type = "reconstructed", sort_key = { from = {"ā", "č", "δ", "[ëē]", "ŋ", "ń", "ō", "š", "θ", "%([^()]+%)"}, to = {"a", "c²", "d", "e", "n²", "n³", "o", "s²", "t²"} }, } m["son-pro"] = { "Proto-Songhay", 116773277, "son", "Latn", type = "reconstructed", } m["sqj-pro"] = { "Proto-Albanian", 18210846, "sqj", "Latn", type = "reconstructed", } m["ssa-klk-pro"] = { "Proto-Kuliak", 116773779, "ssa-klk", "Latn", type = "reconstructed", } m["ssa-kom-pro"] = { "Proto-Koman", 116773775, "ssa-kom", "Latn", type = "reconstructed", } m["ssa-pro"] = { "Proto-Nilo-Saharan", 116773236, "ssa", "Latn", type = "reconstructed", } m["syd-pro"] = { "Proto-Samoyedic", 7251863, "syd", "Latn", type = "reconstructed", } m["tai-pro"] = { "Proto-Tai", 6583709, "tai", "Latn", type = "reconstructed", } m["tai-swe-pro"] = { "Proto-Southwestern Tai", 116773280, "tai-swe", "Latn", type = "reconstructed", } m["tbq-bdg-pro"] = { "Proto-Bodo-Garo", 116773195, "tbq-bdg", "Latn", type = "reconstructed", } m["tbq-blg"] = { "Bailang", 2879843, "tbq-lob", "Hani", sort_key = "Hani-sortkey", } m["tbq-brm-pro"] = { "Proto-Burmish", nil, "tbq-brm", "Latn", type = "reconstructed", } m["tbq-gkh"] = { "Gokhy", 5578069, "tbq-sil", "Latn", } m["tbq-kuk-pro"] = { "Proto-Kuki-Chin", 116773220, "tbq-kuk", "Latn", type = "reconstructed", } m["tbq-lal-pro"] = { "Proto-Lalo", 116773781, "tbq-lal", "Latn", type = "reconstructed", } m["tbq-laz"] = { "Laze", 17007626, "sit-nas", "Latn", } m["tbq-lob-pro"] = { "Proto-Lolo-Burmese", 116773224, "tbq-lob", "Latn", type = "reconstructed", } m["tbq-lol-pro"] = { "Proto-Loloish", 7251855, "tbq-lol", "Latn", type = "reconstructed", } m["tbq-mil"] = { "Milang", 6850761, "sit-gsi", "Deva, Latn", } m["tbq-mor"] = { "Moran", 6909216, "tbq-bdg", "Latn", } m["tbq-ngo"] = { "Ngochang", 56582, "tbq-brm", "Latn", } -- tbq-pro is now etymology-only m["trk-dkh"] = { "Dukhan", 12809273, "trk-ssb", "Latn, Cyrl, Mong", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] } -- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''. m["trk-eog"] = { "Early Old Oghuz", nil, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, } m["trk-oat"] = { "Old Anatolian Turkish", 7083390, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, ancestors = "trk-eog", } m["trk-pro"] = { "Proto-Turkic", 3657773, "trk", "Latn", type = "reconstructed", standard_chars = { Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron, } } m["tup-gua-pro"] = { "Proto-Tupi-Guarani", 116773288, "tup-gua", "Latn", type = "reconstructed", } m["tup-kab"] = { "Kabishiana", 15302988, "tup", "Latn", } m["tup-pro"] = { "Proto-Tupian", 10354700, "tup", "Latn", type = "reconstructed", } m["tuw-alk"] = { "Alchuka", 113553616, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-bal"] = { "Bala", 86730632, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kkl"] = { "Kyakala", 118875708, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kli"] = { "Kili", 6406892, "tuw-ewe", "Cyrl", } m["tuw-pro"] = { "Proto-Tungusic", 85872335, "tuw", "Latn", type = "reconstructed", } m["tuw-sol"] = { "Solon", 30004, "tuw-ewe", } m["urj-fin-pro"] = { "Proto-Finnic", 11883720, "urj-fin", "Latn", type = "reconstructed", } m["urj-koo"] = { "Old Komi", 86679962, "kv", "Perm, Cyrs", translit = "urj-koo-translit", -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present } m["urj-kuk"] = { "Kukkuzi", 107410460, "urj-fin", "Latn", ancestors = "vot", } m["urj-kya"] = { "Komi-Yazva", 2365210, "kv", "Cyrl", translit = "kv-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.acute}, } m["urj-mdv-pro"] = { "Proto-Mordvinic", 116773232, "urj-mdv", "Latn", type = "reconstructed", } m["urj-prm-pro"] = { "Proto-Permic", 116773257, "urj-prm", "Latn", type = "reconstructed", } m["urj-pro"] = { "Proto-Uralic", 288765, "urj", "Latn", type = "reconstructed", } m["urj-ugr-pro"] = { "Proto-Ugric", 156631, "urj-ugr", "Latn", type = "reconstructed", } m["xnd-pro"] = { "Proto-Na-Dene", 116773233, "xnd", "Latn", type = "reconstructed", } m["xgn-pro"] = { "Proto-Mongolic", 2493677, "xgn", "Latn", type = "reconstructed", sort_key = { from = {"č", "i", "ï", "ǰ", "ŋ", "ö", "š", "ü"}, to = {"c", "i" .. p[1], "i", "j", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]}, }, } m["yok-bvy"] = { "Buena Vista Yokuts", 4985474, "yok", "Latn", } m["yok-dly"] = { "Delta Yokuts", 70923266, "yok", "Latn", } m["yok-gsy"] = { "Gashowu Yokuts", 3098708, "yok", "Latn", } m["yok-kry"] = { "Kings River Yokuts", 6413014, "yok", "Latn", } m["yok-nvy"] = { "Northern Valley Yokuts", 85789777, "yok", "Latn", } m["yok-ply"] = { "Palewyami Yokuts", 2387391, "yok", "Latn", } m["yok-svy"] = { "Southern Valley Yokuts", 12642473, "yok", "Latn", } m["yok-tky"] = { "Tule-Kaweah Yokuts", 7851988, "yok", "Latn", } m["ypk-pro"] = { "Proto-Yupik", 116773295, "ypk", "Latn", type = "reconstructed", } m["yrk-for"] = { "Forest Nenets", 1295107, "yrk", "Cyrl", translit = "yrk-for-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove}, } m["yrk-tun"] = { "Tundra Nenets", 36452, "yrk", "Cyrl", strip_diacritics = { from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"}, to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"}, }, translit = "yrk-tun-translit", } m["zhx-min-pro"] = { "Proto-Min", 19646347, "zhx-min", "Latn", type = "reconstructed", } m["zhx-sht"] = { "Shaozhou Tuhua", 1920769, "zhx", "Nshu, Hants", generate_forms = "zh-generateforms", sort_key = {Hani = "Hani-sortkey"}, } m["zhx-sic"] = { "Sichuanese", 2278732, "zhx-man", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zhx-tai"] = { "Taishanese", 2208940, "zhx-yue", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zle-ono"] = { "Old Novgorodian", 162013, "zle", "Cyrs, Glag", translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zle-ort"] = { "Old Ruthenian", 13211, "zle", "Arab, Cyrs, Latn", ancestors = "orv", translit = { Cyrs = "zle-ort-translit", Arab = "zle-ort-Arab-translit", }, strip_diacritics = { Cyrs = { remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"], remove_exceptions = {"Ї", "ї"}, }, Arab = "ar-stripdiacritics", }, -- Cyrs sort_key in [[Module:scripts/data]] } m["zls-chs"] = { "Church Slavonic", 33251, "zls", "Cyrs, Glag, Latn", ancestors = "cu", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zlw-ocs"] = { "Old Czech", 593096, "zlw", "Latn", } m["zlw-opl"] = { "Old Polish", 149838, "zlw-lch", "Latn", strip_diacritics = {remove_diacritics = c.ringabove}, } m["zlw-osk"] = { "Old Slovak", 12776676, "zlw", "Latn", } m["zlw-slv"] = { "Slovincian", 36822, "zlw-pom", "Latn", strip_diacritics = {remove_diacritics = c.macron .. c.breve}, } return require("Module:languages").finalizeData(m, "language") 4z3umhhk0j9curjvkejw4agfp9ficlc 231366 231365 2026-04-14T05:59:07Z Pinthura 2424 භාෂා නාම සිංහලට පරිවර්තනය 231366 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "Proto-Khasian", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "aav-nic", "Latn", type = "reconstructed", } m["aav-pkl-pro"] = { "Proto-Pnar-Khasi-Lyngngam", 116773259, "aav-pkl", "Latn", type = "reconstructed", } m["aav-pro"] = { -- mkh-pro will merge into this "Proto-Austroasiatic", 116773186, "aav", "Latn", type = "reconstructed", } m["afa-pro"] = { "Proto-Afroasiatic", 269125, "afa", "Latn", type = "reconstructed", } m["alg-aga"] = { "Agawam", nil, "alg-eas", "Latn", } m["alg-pro"] = { "Proto-Algonquian", 7251834, "alg", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["alv-ama"] = { "Amasi", 4740400, "nic-grs", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}, } m["alv-bgu"] = { "Bainouk Gubeeher", 17002646, "alv-bny", "Latn", } m["alv-bua-pro"] = { "Proto-Bua", 116773723, "alv-bua", "Latn", type = "reconstructed", } m["alv-cng-pro"] = { "Proto-Cangin", 116773726, "alv-cng", "Latn", type = "reconstructed", } m["alv-edo-pro"] = { "Proto-Edoid", 116773206, "alv-edo", "Latn", type = "reconstructed", } m["alv-fli-pro"] = { "Proto-Fali", 116773754, "alv-fli", "Latn", type = "reconstructed", } m["alv-gbe-pro"] = { "Proto-Gbe", 116773208, "alv-gbe", "Latn", type = "reconstructed", } m["alv-gng-pro"] = { "Proto-Guang", 116773757, "alv-gng", "Latn", type = "reconstructed", } m["alv-gtm-pro"] = { "Proto-Central Togo", 116773732, "alv-gtm", "Latn", type = "reconstructed", } m["alv-gwa"] = { "Gwara", 16945580, "nic-pla", "Latn", } m["alv-hei-pro"] = { "Proto-Heiban", 116773760, "alv-hei", "Latn", type = "reconstructed", } m["alv-ido-pro"] = { "Proto-Idomoid", 116773764, "alv-ido", "Latn", type = "reconstructed", } m["alv-igb-pro"] = { "Proto-Igboid", 116773765, "alv-igb", "Latn", type = "reconstructed", } m["alv-kwa-pro"] = { "Proto-Kwa", 116773780, "alv-kwa", "Latn", type = "reconstructed", } m["alv-mum-pro"] = { "Proto-Mumuye", 116773791, "alv-mum", "Latn", type = "reconstructed", } m["alv-nup-pro"] = { "Proto-Nupoid", 116773795, "alv-nup", "Latn", type = "reconstructed", } m["alv-pro"] = { "Proto-Atlantic-Congo", 116732838, "alv", "Latn", type = "reconstructed", } m["alv-edk-pro"] = { "Proto-Edekiri", nil, "alv-edk", "Latn", type = "reconstructed", } m["alv-yor-pro"] = { "Proto-Yoruba", nil, "alv-yor", "Latn", type = "reconstructed", } m["alv-yrd-pro"] = { "Proto-Yoruboid", 116773824, "alv-yrd", "Latn", type = "reconstructed", } m["alv-von-pro"] = { "Proto-Volta-Niger", 116773820, "alv-von", "Latn", type = "reconstructed", } m["apa-pro"] = { "Proto-Apachean", 116773135, "apa", "Latn", type = "reconstructed", } m["aql-pro"] = { "Proto-Algic", 18389588, "aql", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["art-adu"] = { "Adûni", 1232159, "art", "Latn", type = "appendix-constructed", } m["art-bel"] = { "Belter Creole", 108055510, "art", "Latn", type = "appendix-constructed", sort_key = { remove_diacritics = c.acute, from = {"ɒ"}, to = {"a"}, }, } m["art-blk"] = { "Bolak", 2909283, "art", "Latn", type = "appendix-constructed", } m["art-bsp"] = { "Black Speech", 686210, "art", "Latn, Teng", type = "appendix-constructed", } m["art-com"] = { "Communicationssprache", 35227, "art", "Latn", type = "appendix-constructed", } m["art-dtk"] = { "Dothraki", 2914733, "art", "Latn", type = "appendix-constructed", } m["art-elo"] = { "Eloi", nil, "art", "Latn", type = "appendix-constructed", } m["art-gld"] = { "Goa'uld", 19823, "art", "Latn, Egyp, Mero", type = "appendix-constructed", } m["art-lap"] = { "Lapine", 6488195, "art", "Latn", type = "appendix-constructed", } m["art-man"] = { "Mandalorian", 54289, "art", "Latn", type = "appendix-constructed", } m["art-mun"] = { "Mundolinco", 851355, "art", "Latn", type = "appendix-constructed", } m["art-nav"] = { "Naʼvi", 316939, "art", "Latn", type = "appendix-constructed", } m["art-vlh"] = { "High Valyrian", 64483808, "art", "Latn", type = "appendix-constructed", } m["ath-nic"] = { "Nicola", 20609, "ath-nor", "Latn", } m["ath-pro"] = { "Proto-Athabaskan", 104841722, "ath", "Latn", type = "reconstructed", } m["auf-pro"] = { "Proto-Arawa", 116773706, "auf", "Latn", type = "reconstructed", } m["aus-alu"] = { "Alungul", 16827670, "aus-pmn", "Latn", } m["aus-and"] = { "Andjingith", 4754509, "aus-pmn", "Latn", } m["aus-ang"] = { "Angkula", 16828520, "aus-pmn", "Latn", } m["aus-arn-pro"] = { "Proto-Arnhem", 116773720, "aus-arn", "Latn", type = "reconstructed", } m["aus-bra"] = { "Barranbinya", 4863220, "aus-pmn", "Latn", } m["aus-brm"] = { "Barunggam", 4865914, "aus-pmn", "Latn", } m["aus-cww-pro"] = { "Proto-Central New South Wales", 116773199, "aus-cww", "Latn", type = "reconstructed", } m["aus-dal-pro"] = { "Proto-Daly", 116773743, "aus-dal", "Latn", type = "reconstructed", } m["aus-guw"] = { "Guwar", 6652138, "aus-pam", "Latn", } m["aus-lsw"] = { "Little Swanport", 6652138, "qfa-unc", "Latn", } m["aus-mbi"] = { "Mbiywom", 6799701, "aus-pmn", "Latn", } m["aus-ngk"] = { "Ngkoth", 7022405, "aus-pmn", "Latn", } m["aus-nyu-pro"] = { "Proto-Nyulnyulan", 116773797, "aus-nyu", "Latn", type = "reconstructed", } m["aus-pam-pro"] = { "Proto-Pama-Nyungan", 33942, "aus-pam", "Latn", type = "reconstructed", } m["aus-tul"] = { "Tulua", 16938541, "aus-pam", "Latn", } m["aus-uwi"] = { "Uwinymil", 7903995, "aus-arn", "Latn", } m["aus-wdj-pro"] = { "Proto-Iwaidjan", 116773767, "aus-wdj", "Latn", type = "reconstructed", } m["aus-won"] = { "Wong-gie", nil, "aus-pam", "Latn", } m["aus-wul"] = { "Wulguru", 8039196, "aus-dyb", "Latn", } m["aus-ynk"] = { -- contrast nny "Yangkaal", 3913770, "aus-tnk", "Latn", } m["awd-amc-pro"] = { "Proto-Amuesha-Chamicuro", nil, "awd", "Latn", type = "reconstructed", } m["awd-kmp-pro"] = { "Proto-Kampa", nil, "awd", "Latn", type = "reconstructed", } m["awd-prw-pro"] = { "Proto-Paresi-Waura", nil, "awd", "Latn", type = "reconstructed", } m["awd-ama"] = { "Amarizana", 16827787, "awd", "Latn", } m["awd-ana"] = { "Anauyá", 16828252, "awd", "Latn", } m["awd-apo"] = { "Apolista", 16916645, "awd", "Latn", } m["awd-cab"] = { "Cabre", 16850160, "awd", "Latn", } m["awd-gnu"] = { "Guinau", 3504087, "awd", "Latn", } m["awd-kar"] = { "Cariay", 16920253, "awd", "Latn", } m["awd-kaw"] = { "Kawishana", 6379993, "awd-nwk", "Latn", } m["awd-kus"] = { "Kustenau", 5196293, "awd", "Latn", } m["awd-man"] = { "Manao", 6746920, "awd", "Latn", } m["awd-mar"] = { "Marawan", 6755108, "awd", "Latn", } m["awd-mpr"] = { "Maipure", 6736872, "awd", "Latn", } m["awd-mrt"] = { "Mariaté", 16910017, "awd-nwk", "Latn", } m["awd-nwk-pro"] = { "Proto-Nawiki", 116773234, "awd-nwk", "Latn", type = "reconstructed", } m["awd-pai"] = { "Paikoneka", 128807835, "awd", "Latn", } m["awd-pas"] = { "Pasé", 7143168, "awd-nwk", "Latn", } m["awd-pro"] = { "Proto-Arawak", 97573478, "awd", "Latn", type = "reconstructed", } m["awd-she"] = { "Shebayo", 7492248, "awd", "Latn", } m["awd-taa-pro"] = { "Proto-Ta-Arawak", 116773282, "awd-taa", "Latn", type = "reconstructed", } m["awd-wai"] = { "Wainumá", 16910017, "awd-nwk", "Latn", } m["awd-yum"] = { "Yumana", 8061062, "awd-nwk", "Latn", } m["azc-caz"] = { "Cazcan", 5055514, "azc", "Latn", } m["azc-cup-pro"] = { "Proto-Cupan", 116773738, "azc-cup", "Latn", type = "reconstructed", } m["azc-ktn"] = { "Kitanemuk", 3197558, "azc-tak", "Latn", } m["azc-nah-pro"] = { "Proto-Nahuan", 7251860, "azc-nah", "Latn", type = "reconstructed", } m["azc-num-pro"] = { "Proto-Numic", 116773247, "azc-num", "Latn", type = "reconstructed", } m["azc-pro"] = { "Proto-Uto-Aztecan", 96400333, "azc", "Latn", type = "reconstructed", } m["azc-tak-pro"] = { "Proto-Takic", 116773283, "azc-tak", "Latn", type = "reconstructed", } m["azc-tat"] = { "Tataviam", 743736, "azc", "Latn", } m["ber-pro"] = { "Proto-Berber", 2855698, "ber", "Latn", type = "reconstructed", } m["ber-fog"] = { "Fogaha", 107610173, "ber", "Latn", } m["ber-zuw"] = { "Zuwara", 4117169, "ber", "Latn", } m["bnt-bal"] = { "Balong", 93935237, "bnt-bbo", "Latn", } m["bnt-bon"] = { "Boma Nkuu", nil, "bnt", "Latn", } m["bnt-boy"] = { "Boma Yumu", nil, "bnt", "Latn", } m["bnt-bwa"] = { "Bwala", 128810345, "bnt-tek", "Latn", } m["bnt-cmw"] = { "Chimwiini", 4958328, "bnt-swh", "Latn", } m["bnt-ind"] = { "Indanga", 51412803, "bnt", "Latn", } m["bnt-lal"] = { "Lala (South Africa)", 6480154, "bnt-ngu", "Latn", } m["bnt-mpi"] = { "Mpiin", 93937013, "bnt-bdz", "Latn", } m["bnt-mpu"] = { "Mpuono", -- not to be confused with Mbuun zmp 36056, "bnt", "Latn", } m["bnt-ngu-pro"] = { "Proto-Nguni", 961559, "bnt-ngu", "Latn", type = "reconstructed", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron}, } m["bnt-phu"] = { "Phuthi", 33796, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, } m["bnt-pro"] = { "Proto-Bantu", 3408025, "bnt", "Latn", type = "reconstructed", sort_key = "bnt-pro-sortkey", } m["bnt-sab-pro"] = { "Proto-Sabaki", nil, -- Q2209395 is the code for the Sabaki family "bnt-sab", "Latn", type = "reconstructed", } m["bnt-sbo"] = { "South Boma", nil, "bnt", "Latn", } m["bnt-sts-pro"] = { "Proto-Sotho-Tswana", 116773278, "bnt-sts", "Latn", type = "reconstructed", } m["btk-pro"] = { "Proto-Batak", 116773191, "btk", "Latn", type = "reconstructed", } m["cau-abz-pro"] = { "Proto-Abkhaz-Abaza", 7251831, "cau-abz", "Latn", type = "reconstructed", } m["cau-and-pro"] = { "Proto-Andian", nil, "cau-and", "Latn", type = "reconstructed", } m["cau-ava-pro"] = { "Proto-Avaro-Andian", 116773187, "cau-ava", "Latn", type = "reconstructed", } m["cau-cir-pro"] = { "Proto-Circassian", 7251838, "cau-cir", "Latn", type = "reconstructed", } m["cau-drg-pro"] = { "Proto-Dargwa", 116773205, "cau-drg", "Latn", type = "reconstructed", } m["cau-lzg-pro"] = { "Proto-Lezghian", 116773223, "cau-lzg", "Latn", type = "reconstructed", } m["cau-nec-pro"] = { "Proto-Northeast Caucasian", 116773244, "cau-nec", "Latn", type = "reconstructed", } m["cau-nkh-pro"] = { "Proto-Nakh", 108032840, "cau-nkh", "Latn", type = "reconstructed", } m["cau-nwc-pro"] = { "Proto-Northwest Caucasian", 7251861, "cau-nwc", "Latn", type = "reconstructed", } m["cau-tsz-pro"] = { "Proto-Tsezian", 116773287, "cau-tsz", "Latn", type = "reconstructed", } m["cba-ata"] = { "Atanques", 4812783, "cba", "Latn", } m["cba-cat"] = { "Catío Chibcha", 7083619, "cba", "Latn", } m["cba-dor"] = { "Dorasque", 5297532, "cba", "Latn", } m["cba-dui"] = { "Duit", 3041061, "cba", "Latn", } m["cba-hue"] = { "Huetar", 35514, "cba", "Latn", } m["cba-nut"] = { "Nutabe", 7070405, "cba", "Latn", } m["cba-pro"] = { "Proto-Chibchan", 116773203, "cba", "Latn", type = "reconstructed", } m["ccs-pro"] = { "Proto-Kartvelian", 2608203, "ccs", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["ccs-gzn-pro"] = { "Proto-Georgian-Zan", 23808119, "ccs-gzn", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["cdc-cbm-pro"] = { "Proto-Central Chadic", 116773197, "cdc-cbm", "Latn", type = "reconstructed", } m["cdc-mas-pro"] = { "Proto-Masa", 116773789, "cdc-mas", "Latn", type = "reconstructed", } m["cdc-pro"] = { "Proto-Chadic", 116773201, "cdc", "Latn", type = "reconstructed", } m["cdd-pro"] = { "Proto-Caddoan", 116773725, "cdd", "Latn", type = "reconstructed", } m["cel-bry-pro"] = { "Proto-Brythonic", 1248800, "cel-bry", "Latn, Polyt", sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-gal"] = { "Gallaecian", 3094789, "cel-his", } m["cel-gau"] = { "Gaulish", 29977, "cel", "Latn, Polyt, Ital", strip_diacritics = { Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer}, }, sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-pro"] = { "Proto-Celtic", 653649, "cel", "Latn", type = "reconstructed", sort_key = "cel-pro-sortkey", } m["chi-pro"] = { "Proto-Chimakuan", 116773734, "chi", "Latn", type = "reconstructed", } m["chm-pro"] = { "Proto-Mari", 116773788, "chm", "Latn", type = "reconstructed", } m["cmc-pro"] = { "Proto-Chamic", 114793834, "cmc", "Latn", type = "reconstructed", } m["crp-bip"] = { "Basque-Icelandic Pidgin", 810378, "crp", "Latn", ancestors = "eu", } m["crp-gep"] = { "West Greenlandic Pidgin", 17036301, "crp", "Latn", ancestors = "kl", } m["crp-kia"] = { "Kiautschou German Pidgin", 108314615, "crp", "Latn", ancestors = "de", } m["crp-mar"] = { "Maroon Spirit Language", 1093206, "crp", "Latn", ancestors = "en", } m["crp-mpp"] = { "Macau Pidgin Portuguese", 128804537, "crp", "Hant, Latn", ancestors = "pt", sort_key = {Hant = "Hani-sortkey"}, } m["crp-rsn"] = { "Russenorsk", 505125, "crp", "Cyrl, Latn", ancestors = "nn, ru", translit = {Cyrl = "ru-translit"}, } m["crp-spp"] = { "Samoan Plantation Pidgin", 7409948, "crp", "Latn", ancestors = "en", } m["crp-slb"] = { "Solombala English", 7558525, "crp", "Cyrl, Latn", ancestors = "en, ru", translit = {Cyrl = "ru-translit"}, } m["crp-tpr"] = { "Taimyr Pidgin Russian", 16930506, "crp", "Cyrl", ancestors = "ru", translit = "ru-translit", } m["csu-bba-pro"] = { "Proto-Bongo-Bagirmi", 116773722, "csu-bba", "Latn", type = "reconstructed", } m["csu-maa-pro"] = { "Proto-Mangbetu", 116773786, "csu-maa", "Latn", type = "reconstructed", } m["csu-pro"] = { "Proto-Central Sudanic", 116773730, "csu", "Latn", type = "reconstructed", } m["csu-sar-pro"] = { "Proto-Sara", 116773809, "csu-sar", "Latn", type = "reconstructed", } m["cus-ash"] = { "Ashraaf", 4805855, "cus-som", "Latn", } m["cus-hec-pro"] = { "Proto-Highland East Cushitic", 116773761, "cus-hec", "Latn", type = "reconstructed", } m["cus-som-pro"] = { "Proto-Somaloid", nil, "cus-som", "Latn", type = "reconstructed", } m["cus-sou-pro"] = { "Proto-South Cushitic", 126081567, "cus-sou", "Latn", type = "reconstructed", } m["cus-pro"] = { "Proto-Cushitic", 116773204, "cus", "Latn", type = "reconstructed", } m["dmn-dam"] = { "Dama (Sierra Leone)", 19601574, "dmn", "Latn", } m["dra-bry"] = { "Beary", 1089116, "qfa-mix", "Mlym, Knda", ancestors = "ml, tcy", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["dra-cen-pro"] = { "Proto-Central Dravidian", nil, "dra-cen", "Latn", type = "reconstructed", } m["dra-mkn"] = { "Middle Kannada", 128810572, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-nor-pro"] = { "Proto-North Dravidian", 124433593, "dra-nor", "Latn", type = "reconstructed", } m["dra-okn"] = { "Old Kannada", 15723156, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-ote"] = { "Old Telugu", 126720868, "dra-tel", "Telu", translit = "te-translit", } m["dra-pro"] = { "Proto-Dravidian", 1702853, "dra", "Latn", type = "reconstructed", } m["dra-sdo-pro"] = { "Proto-South Dravidian I", 104847952, -- Wikipedia's "Proto-South Dravidian" is Proto-South Dravidian I in this scheme. "dra-sdo", "Latn", type = "reconstructed", } m["dra-sdt-pro"] = { "Proto-South Dravidian II", 128885257, "dra-sdt", "Latn", type = "reconstructed", } m["dra-sou-pro"] = { "Proto-South Dravidian", 128886121, "dra-sou", "Latn", type = "reconstructed", } m["egx-dem"] = { "Demotic Egyptian", 36765, "egx", "Latn, Egyd, Polyt", sort_key = { Latn = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "e", "ꜥ", "y", "w", "b", "p", "f", "m", "n", "r", "l", "ḥ", "ḫ", "h̭", "ẖ", "h", "š", "s", "q", "k", "g", "ṱ", "ṯ", "t", "ḏ", "%.", "⸗"}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]} }, }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dmn-pro"] = { "Proto-Mande", 116773785, "dmn", "Latn", type = "reconstructed", } m["dmn-mdw-pro"] = { "Proto-Western Mande", 116773822, "dmn-mdw", "Latn", type = "reconstructed", } m["dru-pro"] = { "Proto-Rukai", 116773807, "map", "Latn", type = "reconstructed", } m["ero-gsz"] = { "Geshiza", nil, "ero", "Latn", } m["ero-nya"] = { "Nyagrong Minyag", nil, "ero", "Latn", } m["ero-tau"] = { "Stau", nil, "ero", "Latn", } m["esx-esk-pro"] = { "Proto-Eskimo", 7251842, "esx-esk", "Latn", type = "reconstructed", } m["esx-ink"] = { "Inuktun", 1671647, "esx-inu", "Latn", } m["esx-inq"] = { "Inuinnaqtun", 28070, "esx-inu", "Latn", } m["esx-inu-pro"] = { "Proto-Inuit", 60785588, "esx-inu", "Latn", type = "reconstructed", } m["esx-pro"] = { "Proto-Eskimo-Aleut", 7251843, "esx", "Latn", type = "reconstructed", } m["esx-tut"] = { "Tunumiisut", 15665389, "esx-inu", "Latn", } m["euq-pro"] = { "ප්‍රොටෝ-බාස්ක්", 938011, "euq", "Latn", type = "reconstructed", } m["gba-pro"] = { "Proto-Gbaya", nil, "gba", "Latn", type = "reconstructed", } m["gem-pro"] = { "ප්‍රොටෝ-ජර්මානු", 669623, "gem", "Latn", type = "reconstructed", sort_key = "gem-pro-sortkey", } m["gme-bur"] = { "Burgundian", 47625, "gme", "Latn", } m["gme-cgo"] = { "Crimean Gothic", 36211, "gme", "Latn", } m["gmq-gut"] = { "Gutnish", 1256646, "gmq", "Latn", ancestors = "gmq-ogt", } m["gmq-jmk"] = { "Jamtish", 35512, "gmq-eas", "Latn", } m["gmq-mno"] = { "Middle Norwegian", 3417070, "gmq-wes", "Latn", } m["gmq-oda"] = { "Old Danish", 12330003, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-ogt"] = { "Old Gutnish", 1133488, "gmq", "Latn, Runr", ancestors = "non", } m["gmq-osw"] = { "Old Swedish", 2417210, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-pro"] = { "Proto-Norse", 1671294, "gmq", "Runr", translit = "Runr-translit", } m["gmq-scy"] = { "Scanian", 768017, "gmq-eas", "Latn", } m["gmw-bgh"] = { "Bergish", 329030, "gmw-frk", "Latn", } m["gmw-cfr"] = { "Central Franconian", 572197, "gmw-hgm", "Latn", ancestors = "gmh", wikimedia_codes = "ksh", } m["gmw-ecg"] = { "East Central German", 499344, -- subsumes Q699284, Q152965 "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-fin"] = { "Fingallian", 3072588, "gmw-ian", "Latn", } m["gmw-gts"] = { "Gottscheerish", 533109, "gmw-hgm", "Latn", ancestors = "bar", } m["gmw-jdt"] = { "Jersey Dutch", 1687911, "gmw-frk", "Latn", ancestors = "nl", } m["gmw-msc"] = { "Middle Scots", 3327000, "gmw-ang", "Latn", ancestors = "enm-esc", } m["gmw-pro"] = { "ප්‍රොටෝ-බටහිර ජර්මානු", 78079021, "gmw", "Latn, Runr", -- type = "reconstructed", -- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added sort_key = "gmw-pro-sortkey", } m["gmw-rfr"] = { "Rhine Franconian", 707007, "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-stm"] = { "Sathmar Swabian", 2223059, "gmw-hgm", "Latn", ancestors = "swg", } m["gmw-tsx"] = { "Transylvanian Saxon", 260942, "gmw-hgm", "Latn", ancestors = "gmw-cfr", } m["gmw-vog"] = { "Volga German", 312574, "gmw-hgm", "Latn", ancestors = "gmw-rfr", } m["gmw-zps"] = { "Zipser German", 205548, "gmw-hgm", "Latn", ancestors = "gmh", } m["gn-cls"] = { "Classical Guarani", 17478065, "gn", "Latn", } m["grk-cal"] = { "Calabrian Greek", 1146398, "grk", "Latn, Grek", ancestors = "grk-ita", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-ita"] = { "Italiot Greek", 19720507, "grk", "Latn, Grek", ancestors = "gkm", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-mar"] = { "Mariupol Greek", 4400023, "grk", "Cyrl, Latn, Grek", ancestors = "gkm", translit = { Cyrl = "grk-mar-translit", Grek = "grk-mar-translit", }, override_translit = true, strip_diacritics = { Cyrl = {remove_diacritics = c.acute}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-pro"] = { "Proto-Hellenic", 1231805, "grk", "Latn, Polyt", type = "reconstructed", sort_key = {Latn = { from = {"ʰ", "ʷ"}, to = {"h", "w"}, remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron }}, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in -- the translit section } m["hmn-pro"] = { "Proto-Hmongic", 116773210, "hmn", "Latn", type = "reconstructed", } m["hmx-mie-pro"] = { "Proto-Mienic", 116773229, "hmx-mie", "Latn", type = "reconstructed", } m["hmx-pro"] = { "Proto-Hmong-Mien", 7251846, "hmx", "Latn", type = "reconstructed", } m["hyx-pro"] = { "Proto-Armenian", 3848498, "hyx", "Latn", type = "reconstructed", } m["iir-nur-pro"] = { "Proto-Nuristani", 116773248, "iir-nur", "Latn", type = "reconstructed", } m["iir-pro"] = { "ප්‍රොටෝ-ඉන්දු-ඉරාන", 966439, "iir", "Latn", type = "reconstructed", } m["ijo-pro"] = { "Proto-Ijoid", 116773766, "ijo", "Latn", type = "reconstructed", } m["inc-apa"] = { "Apabhramsa", 616419, "inc-mid", "Deva, Shrd, Sidd", ancestors = "pra", translit = { Deva = "sa-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] }, } m["inc-ash"] = { "අශෝක ප්‍රාකෘත", 104854379, "inc-mid", "Brah, Khar", ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Khar = "Khar-translit", }, } m["inc-dng-pro"] = { "Proto-Dangari", nil, "inc-dng", "Latn", type = "reconstructed", } m["inc-kam"] = { "Kamarupi Prakrit", 6356097, "inc-bas", "Brah, Sidd", -- Brah, Sidd translit in [[Module:scripts/data]] } m["inc-kho"] = { "Kholosi", 24952008, "inc-snd", "Latn", } m["inc-krd-pro"] = { "Proto-Kamta", 128816843, "inc-bas", "Latn", ancestors = "inc-kam", type = "reconstructed", } m["inc-mas"] = { "Middle Assamese", 128806836, "inc-bas", "as-Beng", ancestors = "inc-oas", translit = "inc-mas-translit", } m["inc-mbn"] = { "Middle Bengali", 113559927, "inc-bas", "Beng", ancestors = "inc-obn", translit = "inc-mbn-translit", } m["inc-mgu"] = { "Middle Gujarati", 24907429, "inc-wes", "Deva", ancestors = "inc-ogu", } m["inc-mor"] = { "Middle Odia", 128810882, "inc-eas", "Orya", ancestors = "inc-oor", } m["inc-oas"] = { "Early Assamese", 85758237, "inc-bas", "as-Beng", ancestors = "inc-kam", translit = "inc-oas-translit", } m["inc-oaw"] = { "Old Awadhi", nil, "inc-hie", "Deva, Kthi, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Kthi = "sa-Kthi-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-obn"] = { "Old Bengali", 113559926, "inc-bas", "Beng", } m["inc-ogu"] = { "Old Gujarati", 24907427, "inc-wes", "Deva", translit = "sa-translit", } m["inc-ohi"] = { "Old Hindi", 48767781, "inc-hiw", "Deva, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-oor"] = { "Old Odia", 128807801, "inc-eas", "Orya", } m["inc-opa"] = { "Old Punjabi", 115270971, "inc-pan", "Guru, pa-Arab", translit = { Guru = "inc-opa-Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun}, } m["inc-pro"] = { "Proto-Indo-Aryan", 23808344, "inc", "Latn", type = "reconstructed", } m["ine-ana-pro"] = { "Proto-Anatolian", 7251833, "ine-ana", "Latn", type = "reconstructed", } m["ine-bsl-pro"] = { "Proto-Balto-Slavic", 1703347, "ine-bsl", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", c.acute, c.macron, "ˀ"}, to = {"a", "e", "i", "o", "u"} }, } m["ine-kal"] = { "Kalašma", 122770439, "ine-ana", "Xsux", } m["ine-pae"] = { "Paeonian", 2705672, "ine", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ine-pro"] = { "ප්‍රොටෝ-ඉන්දු-යුරෝපීය", 37178, "ine", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ĺ", "ḿ", "ń", "ŕ", "ǵ", "ḱ", "ʰ", "ʷ", "₁", "₂", "₃", c.ringbelow, c.acute, c.macron}, to = {"a", "e", "i", "o", "u", "l", "m", "n", "r", "g'", "k'", "¯h", "¯w", "1", "2", "3"} }, } m["ine-toc-pro"] = { "Proto-Tocharian", 104841462, "ine-toc", "Latn", type = "reconstructed", } m["xme-old"] = { "Old Median", 36461, "xme", "Polyt, Latn", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-mid"] = { "Middle Median", 12836150, "xme", "Latn", } m["xme-ker"] = { "Kermanic", 129850, "xme", "fa-Arab, Latn, Hebr", ancestors = "xme-mid", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-taf"] = { "Tafreshi", nil, "xme", "fa-Arab, Latn", ancestors = "xme-mid", } m["xme-ttc-pro"] = { "Proto-Tatic", 122973870, "xme-ttc", "Latn", ancestors = "xme-mid", } m["xme-kls"] = { "Kalasuri", nil, "xme-ttc", ancestors = "xme-ttc-nor", } m["xme-klt"] = { "Kilit", 3612452, "xme-ttc", "Cyrl", -- and fa-Arab? } m["xme-ott"] = { "Old Tati", 434697, "xme-ttc", "fa-Arab, Latn", } m["ira-kms-pro"] = { "Proto-Komisenian", 116773777, "ira-kms", "Latn", type = "reconstructed", } m["ira-mpr-pro"] = { "Proto-Medo-Parthian", 116773227, "ira-mpr", "Latn", type = "reconstructed", } m["ira-pat-pro"] = { "Proto-Pathan", 116773255, "ira-pat", "Latn", type = "reconstructed", } m["ira-pro"] = { "Proto-Iranian", 4167865, "ira", "Latn", type = "reconstructed", } m["ira-zgr-pro"] = { "Proto-Zaza-Gorani", 116775031, "ira-zgr", "Latn", type = "reconstructed", } m["xsc-pro"] = { "Proto-Scythian", 116773273, "xsc", "Latn", type = "reconstructed", } m["xsc-sar-pro"] = { "Proto-Sarmatian", 116773249, "xsc-sar", "Latn", type = "reconstructed", } m["xsc-skw-pro"] = { "Proto-Saka-Wakhi", 116773267, "xsc-skw", "Latn", type = "reconstructed", } m["xsc-sak-pro"] = { "Proto-Saka", 116773264, "xsc-sak", "Latn", type = "reconstructed", } m["ira-sym-pro"] = { "Proto-Shughni-Yazghulami-Munji", 116773813, "ira-sym", "Latn", type = "reconstructed", } m["ira-sgi-pro"] = { "Proto-Sanglechi-Ishkashimi", 116773808, "ira-sgi", "Latn", type = "reconstructed", } m["ira-mny-pro"] = { "Proto-Munji-Yidgha", 116773792, "ira-mny", "Latn", type = "reconstructed", } m["ira-shy-pro"] = { "Proto-Shughni-Yazghulami", 116773812, "ira-shy", "Latn", type = "reconstructed", } m["ira-shr-pro"] = { "Proto-Shughni-Roshani", 116773811, "ira-shr", "Latn", type = "reconstructed", } m["ira-sgc-pro"] = { "Proto-Sogdic", 116773276, "ira-sgc", "Latn", type = "reconstructed", } m["ira-wnj"] = { "Vanji", 3398419, "ira-shy", "Latn", } m["iro-ere"] = { "Erie", 5388365, "iro-nor", "Latn", } m["iro-min"] = { "Mingo", 128531, "iro-nor", "Latn", ietf_subtag = "i-mingo", -- grandfathered IETF tag } m["iro-nor-pro"] = { "Proto-North Iroquoian", 116773242, "iro-nor", "Latn", type = "reconstructed", } m["iro-pro"] = { "Proto-Iroquoian", 7251852, "iro", "Latn", type = "reconstructed", } m["itc-pro"] = { "Proto-Italic", 17102720, "itc", "Latn", type = "reconstructed", } m["itc-psa"] = { "Pre-Samnite", 7239186, "itc-sbl", "Ital, Polyt, Latn", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["jpx-hcj"] = { "Hachijō", 5637049, "jpx", "Jpan", ancestors = "ojp-eas", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jpx-pro"] = { "Proto-Japonic", 3924309, "jpx", "Latn", type = "reconstructed", } m["jpx-ryu-pro"] = { "Proto-Ryukyuan", 56349069, "jpx-ryu", "Latn", type = "reconstructed", } m["kar-pro"] = { "Proto-Karen", 85794783, "kar", "Latn", type = "reconstructed", } m["kca-eas"] = { "Eastern Khanty", 30304622, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-nor"] = { "Northern Khanty", 30304527, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-pro"] = { "Proto-Khanty", 127505171, "kca", "Latn", type = "reconstructed", } m["kca-sou"] = { "Southern Khanty", 30304618, "kca", "Cyrl", translit = "kca-translit", override_translit = true, } m["khi-kho-pro"] = { "Proto-Khoe", 116773218, "khi-kho", "Latn", type = "reconstructed", } m["khi-kun"] = { "ǃKung", 32904, "khi-kxa", "Latn", } m["ko-ear"] = { "Early Modern Korean", 756014, "qfa-kor", "Kore", ancestors = "okm", translit = "okm-translit", -- Kore strip_diacritics in [[Module:scripts/data]] } m["kro-pro"] = { "Proto-Kru", 116773778, "kro", "Latn", type = "reconstructed", } m["ku-pro"] = { "Proto-Kurdish", 116773221, "ku", "Latn", type = "reconstructed", } m["map-ata-pro"] = { "Proto-Atayalic", 116773151, "map-ata", "Latn", type = "reconstructed", } m["map-bms"] = { "Banyumasan", 33219, "map", "Latn, Java", } m["map-pro"] = { "Proto-Austronesian", 49230, "map", "Latn", type = "reconstructed", } m["mis-hkl"] = { "Kelantan Peranakan Hokkien", 108794818, "qfa-mix", ancestors = "nan-hbl, sou, mfa", } m["mis-idn"] = { "Idiom Neutral", 35847, "art", "Latn", type = "appendix-constructed", } m["mis-isa"] = { "Isaurian", 16956868, nil, -- "Xsux, Hluw, Latn", } m["mis-jie"] = { "Jie", 124424186, nil, "Hani", sort_key = "Hani-sortkey", } m["mis-jzh"] = { "Jizhao", 45242758, "qfa-bej", "Latn", } m["mis-kas"] = { "Kassite", 35612, nil, "Xsux", } m["mis-mmd"] = { "Mimi of Decorse", 6862206, nil, "Latn", } m["mis-mmn"] = { "Mimi of Nachtigal", 6862207, nil, "Latn", } m["mis-phi"] = { "Philistine", 2230924, nil, "Phnx", -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["mis-rou"] = { "Rouran", 48816637, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tdl"] = { "Turdulian", 133176492, } m["mis-tdt"] = { "Turdetanian", 133176461, } m["mis-tnw"] = { "Tangwang", 7683179, "qfa-mix", "Latn", ancestors = "cmn, sce", } m["mis-tuh"] = { "Tuyuhun", 48816625, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tuo"] = { "Tuoba", 48816629, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-wuh"] = { "Wuhuan", 118976867, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xbi"] = { "Xianbei", 4448647, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xnu"] = { "Xiongnu", 10901674, nil, "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mjg-mgl"] = { "Mongghul", 53765528, "mjg", "Latn", -- also Mong, Cyrl ? } m["mjg-mgr"] = { "Mangghuer", 56285392, "mjg", "Latn", -- also Mong, Cyrl ? } m["mkh-asl-pro"] = { "Proto-Aslian", 55630680, "mkh-asl", "Latn", type = "reconstructed", } m["mkh-ban-pro"] = { "Proto-Bahnaric", 116773189, "mkh-ban", "Latn", type = "reconstructed", } m["mkh-kat-pro"] = { "Proto-Katuic", 116773772, "mkh-kat", "Latn", type = "reconstructed", } m["mkh-khm-pro"] = { "Proto-Khmuic", 116773774, "mkh-khm", "Latn", type = "reconstructed", } m["mkh-kmr-pro"] = { "Proto-Khmeric", 55630684, "mkh-kmr", "Latn", type = "reconstructed", } m["mkh-mmn"] = { "Middle Mon", 121337926, "mkh-mnc", "Latn, Mymr", --and also Pallava ancestors = "omx", } m["mkh-mnc-pro"] = { "Proto-Monic", 116773231, "mkh-mnc", "Latn", type = "reconstructed", } m["mkh-mvi"] = { "Middle Vietnamese", 9199, "mkh-vie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mkh-pal-pro"] = { "Proto-Palaungic", 104847372, "mkh-pal", "Latn", type = "reconstructed", } m["mkh-pea-pro"] = { "Proto-Pearic", 116773804, "mkh-pea", "Latn", type = "reconstructed", } m["mkh-pkn-pro"] = { "Proto-Pakanic", 116773803, "mkh-pkn", "Latn", type = "reconstructed", } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. "Proto-Mon-Khmer", 7251859, "mkh", "Latn", type = "reconstructed", } m["mnw-tha"] = { -- To be removed. "Thai Mon", nil, "mkh-mnc", "Mymr, Thai", ancestors = "mkh-mmn", sort_key = { from = {"[%p]", "ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ", "[็-๎]", "([เแโใไ])([ก-ฮ])ฺ?"}, to = {"", "္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ", "", "%2%1"} }, } m["mkh-vie-pro"] = { "Proto-Vietic", 109432616, "mkh-vie", "Latn", type = "reconstructed", } m["mns-cen"] = { "Central Mansi", 128810384, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-nor"] = { "Northern Mansi", 30304537, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-pro"] = { "Proto-Mansi", 128883093, "mns", "Latn", type = "reconstructed", } m["mns-sou"] = { "Southern Mansi", 30304629, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mun-pro"] = { "Proto-Munda", 105102373, "mun", "Latn", type = "reconstructed", } m["myn-chl"] = { -- the stage after ''emy'' "Ch'olti'", 873995, "myn", "Latn", } m["myn-pro"] = { "Proto-Mayan", 3321532, "myn", "Latn", type = "reconstructed", } m["nai-ala"] = { "Alazapa", 128810233, nil, "Latn", } m["nai-bay"] = { "Bayogoula", 1563704, nil, "Latn", } m["nai-cal"] = { "Calusa", 51782, nil, "Latn", } m["nai-chi"] = { "Chiquimulilla", 25339627, "nai-xin", "Latn", } m["nai-chu-pro"] = { "Proto-Chumash", 116773736, "nai-chu", "Latn", type = "reconstructed", } m["nai-cig"] = { "Ciguayo", 20741700, nil, "Latn", } m["nai-ckn-pro"] = { "Proto-Chinookan", 116773735, "nai-ckn", "Latn", type = "reconstructed", } m["nai-guz"] = { "Guazacapán", 19572028, "nai-xin", "Latn", } m["nai-hit"] = { "Hitchiti", 1542882, "nai-mus", "Latn", } m["nai-ipa"] = { "Ipai", 3027474, "nai-yuc", "Latn", } m["nai-jtp"] = { "Jutiapa", nil, "nai-xin", "Latn", } m["nai-jum"] = { "Jumaytepeque", 25339626, "nai-xin", "Latn", } m["nai-kat"] = { "Kathlamet", 6376639, "nai-ckn", "Latn", } m["nai-klp-pro"] = { "Proto-Kalapuyan", 116773771, "nai-klp", "Latn", type = "reconstructed", } m["nai-knm"] = { "Konomihu", 3198734, "nai-shs", "Latn", } m["nai-kum"] = { "Kumeyaay", 4910139, "nai-yuc", "Latn", } m["nai-mac"] = { "Macoris", 21070851, nil, "Latn", } m["nai-mdu-pro"] = { "Proto-Maidun", 116773784, "nai-mdu", "Latn", type = "reconstructed", } m["nai-miz-pro"] = { "Proto-Mixe-Zoque", 7251858, "nai-miz", "Latn", type = "reconstructed", } m["nai-mus-pro"] = { "Proto-Muskogean", 116775368, "nai-mus", "Latn", type = "reconstructed", } m["nai-nao"] = { "Naolan", 6964594, nil, "Latn", } m["nai-nrs"] = { "New River Shasta", 7011254, "nai-shs", "Latn", } m["nai-okw"] = { "Okwanuchu", 3350126, "nai-shs", "Latn", } m["nai-per"] = { "Pericú", 3375369, nil, "Latn", } m["nai-pic"] = { "Picuris", 7191257, "nai-kta", "Latn", } m["nai-plp-pro"] = { "Proto-Plateau Penutian", 116773806, "nai-plp", "Latn", type = "reconstructed", } m["nai-pom-pro"] = { "Proto-Pomo", 116773262, "nai-pom", "Latn", type = "reconstructed", } m["nai-qng"] = { "Quinigua", 36360, nil, "Latn", } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan "Proto-Siouan-Catawban", 116773275, "nai-sca", "Latn", type = "reconstructed", } m["nai-sin"] = { "Sinacantán", 24190249, "nai-xin", "Latn", } m["nai-sln"] = { "Salvadoran Lenca", 3229434, "nai-len", "Latn", } m["nai-spt"] = { "Sahaptin", 3833015, "nai-shp", "Latn", } m["nai-tap"] = { "Tapachultec", 7684401, "nai-miz", "Latn", } m["nai-taw"] = { "Tawasa", 7689233, nil, "Latn", } m["nai-teq"] = { "Tequistlatec", 2964454, "nai-tqn", "Latn", } m["nai-tip"] = { "Tipai", 3027471, "nai-yuc", "Latn", } m["nai-tot-pro"] = { "Proto-Totozoquean", 116773285, "nai-tot", "Latn", type = "reconstructed", } m["nai-tsi-pro"] = { "Proto-Tsimshianic", nil, "nai-tsi", "Latn", type = "reconstructed", } m["nai-utn-pro"] = { "Proto-Utian", 116773290, "nai-utn", "Latn", type = "reconstructed", } m["nai-wai"] = { "Waikuri", 3118702, nil, "Latn", } m["nai-wji"] = { "Western Jicaque", 3178610, "nai-jcq", "Latn", } m["nai-yup"] = { "Yupiltepeque", 25339628, "nai-xin", "Latn", } m["nan-dat"] = { "Datian Min", 19855572, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-hbl"] = { "Hokkien", 1624231, "zhx-nan", "Hants, Latn, Bopo, Kana", wikimedia_codes = "zh-min-nan", generate_forms = "zh-generateforms", sort_key = { Hani = "Hani-sortkey", Kana = "Kana-sortkey" }, } m["nan-hlh"] = { "Hailufeng Min", 120755728, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-lnx"] = { "Longyan Min", 6674568, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-tws"] = { "Teochew", 36759, "zhx-nan", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["nan-zhe"] = { "Zhenan Min", 3846710, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-zsh"] = { "Sanxiang Min", 7420769, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["ngf-bin-pro"] = { "Proto-Binanderean", 137881672, "ngf-bin", "Latn", type = "reconstructed", } m["ngf-pro"] = { "Proto-Trans-New Guinea", 85794785, "ngf", "Latn", type = "reconstructed", } m["nic-bco-pro"] = { "Proto-Benue-Congo", 116773194, "nic-bco", "Latn", type = "reconstructed", } m["nic-bod-pro"] = { "Proto-Bantoid", 116773190, "nic-bod", "Latn", type = "reconstructed", } m["nic-eov-pro"] = { "Proto-Eastern Oti-Volta", 116773753, "nic-eov", "Latn", type = "reconstructed", } m["nic-gns-pro"] = { "Proto-Gurunsi", 116773759, "nic-gns", "Latn", type = "reconstructed", } m["nic-grf-pro"] = { "Proto-Grassfields", 116773755, "nic-grf", "Latn", type = "reconstructed", } m["nic-gur-pro"] = { "Proto-Gur", 116773758, "nic-gur", "Latn", type = "reconstructed", } m["nic-jkn-pro"] = { "Proto-Jukunoid", 116773769, "nic-jkn", "Latn", type = "reconstructed", } m["nic-lcr-pro"] = { "Proto-Lower Cross River", 116773782, "nic-lcr", "Latn", type = "reconstructed", } m["nic-ogo-pro"] = { "Proto-Ogoni", 116773799, "nic-ogo", "Latn", type = "reconstructed", } m["nic-ovo-pro"] = { "Proto-Oti-Volta", 116773802, "nic-ovo", "Latn", type = "reconstructed", } m["nic-plt-pro"] = { "Proto-Plateau", 116773805, "nic-plt", "Latn", type = "reconstructed", } m["nic-pro"] = { "Proto-Niger-Congo", 108000748, "nic", "Latn", type = "reconstructed", } m["nic-ubg-pro"] = { "Proto-Ubangian", 116773818, "nic-ubg", "Latn", type = "reconstructed", } m["nic-ucr-pro"] = { "Proto-Upper Cross River", 116773819, "nic-ucr", "Latn", type = "reconstructed", } m["nic-vco-pro"] = { "Proto-Volta-Congo", 116773293, "nic-vco", "Latn", type = "reconstructed", } m["njo-jgl"] = { "Chungli Ao", 55607615, "sit-aao", "Latn", } m["nub-har"] = { "Haraza", 19572059, "nub", "Arab, Latn", } m["nub-pro"] = { "Proto-Nubian", 116773246, "nub", "Latn", type = "reconstructed", } m["omq-cha-pro"] = { "Proto-Chatino", 116773202, "omq-cha", "Latn", type = "reconstructed", } m["omq-maz-pro"] = { "Proto-Mazatec", 116773790, "omq-maz", "Latn", type = "reconstructed", } m["omq-mix-pro"] = { "Proto-Mixtecan", 21573423, "omq-mix", "Latn", type = "reconstructed", } m["omq-mxt-pro"] = { "Proto-Mixtec", 21573424, "omq-mxt", "Latn", type = "reconstructed", } m["omq-otp-pro"] = { "Proto-Oto-Pamean", 116773251, "omq-otp", "Latn", type = "reconstructed", } m["omq-pro"] = { "Proto-Oto-Manguean", 33669, "omq", "Latn", type = "reconstructed", } m["omq-sjq"] = { "San Juan Quiahije Chatino", 138330751, "omq-cha", "Latn", } m["omq-tel"] = { "Teposcolula Mixtec", nil, "omq-mxt", "Latn", } m["omq-teo"] = { "Teojomulco Chatino", 25340451, "omq-cha", "Latn", } m["omq-tri-pro"] = { "Proto-Triqui", 116773817, "omq-tri", "Latn", type = "reconstructed", } m["omq-zap-pro"] = { "Proto-Zapotecan", 116773297, "omq-zap", "Latn", type = "reconstructed", } m["omq-zpc-pro"] = { "Proto-Zapotec", 116773296, "omq-zpc", "Latn", type = "reconstructed", } m["omv-aro-pro"] = { "Proto-Aroid", 116773721, "omv-aro", "Latn", type = "reconstructed", } m["omv-diz-pro"] = { "Proto-Dizoid", 116773750, "omv-diz", "Latn", type = "reconstructed", } m["omv-pro"] = { "Proto-Omotic", 116773800, "omv", "Latn", type = "reconstructed", } m["oto-otm-pro"] = { "Proto-Otomi", 5908710, "oto-otm", "Latn", type = "reconstructed", } m["oto-pro"] = { "Proto-Otomian", 116773252, "oto", "Latn", type = "reconstructed", } m["paa-kmn"] = { "Kómnzo", 18344310, "paa-wko", "Latn", } m["paa-kwn"] = { "Kuwani", 6449056, "qfa-unc", -- poorly attested, possibly the same as or related to Kalabra "Latn", } m["paa-lei"] = { "Leitre", 85776228, "paa-isk", } m["paa-nha-pro"] = { "Proto-North Halmahera", 116773241, "paa-nha", "Latn", type = "reconstructed" } m["paa-nun"] = { "Nungon", 128807788, "ngf-ynu", "Latn", } m["phi-din"] = { "Dinapigue Agta", 16945774, "phi", "Latn", } m["phi-kal-pro"] = { "Proto-Kalamian", 116773213, "phi-kal", "Latn", type = "reconstructed", } m["phi-nag"] = { "Nagtipunan Agta", 16966111, "phi", "Latn", } m["phi-pro"] = { "Proto-Philippine", 18204898, "phi", "Latn", type = "reconstructed", } m["poz-abi"] = { "Abai", 19570729, "poz-san", "Latn", } m["poz-bal"] = { "Baliledo", 4850912, "poz", "Latn", } m["poz-btk-pro"] = { "Proto-Bungku-Tolaki", 116773724, "poz-btk", "Latn", type = "reconstructed", } m["poz-cet-pro"] = { "Proto-Central-Eastern Malayo-Polynesian", 2269883, "poz-cet", "Latn", type = "reconstructed", } m["poz-hce-pro"] = { "Proto-Halmahera-Cenderawasih", 116773209, "poz-hce", "Latn", type = "reconstructed", } m["poz-lgx-pro"] = { "Proto-Lampungic", 116773222, "poz-lgx", "Latn", type = "reconstructed", } m["poz-mcm-pro"] = { "Proto-Malayo-Chamic", 116773225, "poz-mcm", "Latn", type = "reconstructed", } m["poz-mic-pro"] = { "Proto-Micronesian", 111939079, "poz-mic", "Latn", type = "reconstructed", } m["poz-mly-pro"] = { "Proto-Malayic", 98057728, "poz-mly", "Latn", type = "reconstructed", } m["poz-msa-pro"] = { "Proto-Malayo-Sumbawan", 116773226, "poz-msa", "Latn", type = "reconstructed", } m["poz-oce-pro"] = { "Proto-Oceanic", 141741, "poz-oce", "Latn", type = "reconstructed", } m["poz-pep-pro"] = { "Proto-Eastern Polynesian", 113988745, "poz-pep", "Latn", type = "reconstructed", } m["poz-pnp-pro"] = { "Proto-Nuclear Polynesian", 113988746, "poz-pnp", "Latn", type = "reconstructed", } m["poz-pol-pro"] = { "Proto-Polynesian", 1658709, "poz-pol", "Latn", type = "reconstructed", } m["poz-pro"] = { "Proto-Malayo-Polynesian", 3832960, "poz", "Latn", type = "reconstructed", } m["poz-sml"] = { "Sarawak Malay", 4251702, "poz-mly", "Latn, ms-Arab", } m["poz-ssw-pro"] = { "Proto-South Sulawesi", 116773279, "poz-ssw", "Latn", type = "reconstructed", } m["poz-swa-pro"] = { "Proto-North Sarawak", 116773243, "poz-swa", "Latn", type = "reconstructed", } m["poz-ter"] = { "Terengganu Malay", 4207412, "poz-mly", "Latn, ms-Arab", } m["pqe-pro"] = { "Proto-Eastern Malayo-Polynesian", 2269883, "pqe", "Latn", type = "reconstructed", } m["pra-niy"] = { "Niya Prakrit", 11991601, "inc-mid", "Khar", ancestors = "inc-ash", translit = "Khar-translit", } m["qfa-adm-pro"] = { "Proto-Great Andamanese", 116773756, "qfa-adm", "Latn", type = "reconstructed", } m["qfa-bet-pro"] = { "Proto-Be-Tai", 116773193, "qfa-bet", "Latn", type = "reconstructed", } m["qfa-cka-pro"] = { "Proto-Chukotko-Kamchatkan", 7251837, "qfa-cka", "Latn", type = "reconstructed", } m["qfa-hur-pro"] = { "Proto-Hurro-Urartian", 116773211, "qfa-hur", "Latn", type = "reconstructed", } m["qfa-kad-pro"] = { "Proto-Kadu", 116773770, "qfa-kad", "Latn", type = "reconstructed", } m["qfa-kms-pro"] = { "Proto-Kam-Sui", 55630682, "qfa-kms", "Latn", type = "reconstructed", } m["qfa-kor-pro"] = { "Proto-Koreanic", 467883, "qfa-kor", "Latn", type = "reconstructed", } m["qfa-kra-pro"] = { "Proto-Kra", 7251854, "qfa-kra", "Latn", type = "reconstructed", } m["qfa-lic-pro"] = { "Proto-Hlai", 7251845, "qfa-lic", "Latn", type = "reconstructed", } m["qfa-onb-pro"] = { "Proto-Be", 116773192, "qfa-onb", "Latn", type = "reconstructed", } m["qfa-ong-pro"] = { "Proto-Ongan", 116773801, "qfa-ong", "Latn", type = "reconstructed", } m["qfa-tak-pro"] = { "Proto-Kra-Dai", 104901616, "qfa-tak", "Latn", type = "reconstructed", } m["qfa-yen-pro"] = { "Proto-Yeniseian", 27639, "qfa-yen", "Latn", type = "reconstructed", } m["qfa-yuk-pro"] = { "Proto-Yukaghir", 116773294, "qfa-yuk", "Latn", type = "reconstructed", } m["qwe-kch"] = { "Kichwa", 1740805, "qwe", "Latn", ancestors = "qu", } m["qwe-pro"] = { "Proto-Quechuan", 5575757, "qwe", "Latn", type = "reconstructed", } m["roa-ang"] = { "Angevin", 56782, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-bbn"] = { "Bourbonnais-Berrichon", 2899128, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-brg"] = { "Bourguignon", 508332, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-can"] = { "Cantabrian", 917021, "roa-asl", "Latn", } m["roa-cha"] = { "Champenois", 430018, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-fcm"] = { "Franc-Comtois", 510561, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gal"] = { "Gallo", 37300, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gib"] = { "Gallo-Italic of Basilicata", 3094838, "roa-git", ancestors = "pms-old", "Latn", } m["roa-gis"] = { "Gallo-Italic of Sicily", 2629019, "roa-git", "Latn", ancestors = "pms-old", } m["roa-leo"] = { "Leonese", 34108, "roa-asl", "Latn", } m["roa-lor"] = { "Lorrain", 671198, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-oca"] = { "Old Catalan", 15478520, "roa-ocr", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, } m["roa-ole"] = { "Old Leonese", 125977465, "roa-asl", "Latn", } m["roa-ona"] = { "Old Navarro-Aragonese", 2736184, "roa-nar", "Latn", } m["roa-opt"] = { "Old Galician-Portuguese", 1072111, "roa-gap", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["roa-orl"] = { "Orléanais", 28497058, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-poi"] = { "Poitevin-Saintongeais", 514123, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-tar"] = { "Tarantino", 695526, "roa-itr", "Latn", wikimedia_codes = "roa-tara", } m["sai-all"] = { "Allentiac", 19570789, "sai-hrp", "Latn", } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' "Andoquero", 16828359, "sai-wit", "Latn", } m["sai-ayo"] = { "Ayomán", 16937754, "sai-jir", "Latn", } m["sai-bae"] = { "Baenan", 3401998, "qfa-unc", -- extinct, poorly attested; only known through 9 words "Latn", } m["sai-bag"] = { "Bagua", 5390321, "qfa-unc", -- extinct, poorly attested; possibly Cariban "Latn", } m["sai-bet"] = { "Betoi", 926551, "qfa-iso", "Latn", } m["sai-bor-pro"] = { "Proto-Boran", nil, "sai-bor", "Latn", } m["sai-cac"] = { "Cacán", 945482, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-caq"] = { "Caranqui", 2937753, "sai-bar", "Latn", } m["sai-car-pro"] = { "Proto-Cariban", 116773196, "sai-car", "Latn", type = "reconstructed", } m["sai-cat"] = { "Catacao", 5051136, "sai-ctc", "Latn", } m["sai-cer-pro"] = { "Proto-Cerrado", 116773200, "sai-cer", "Latn", type = "reconstructed", } m["sai-chi"] = { "Chirino", 5390321, "qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu) "Latn", } m["sai-chn"] = { "Chaná", 5072718, "sai-crn", "Latn", } m["sai-chp"] = { "Chapacura", 5072884, "sai-cpc", "Latn", } m["sai-chr"] = { "Charrua", 5086680, "sai-crn", "Latn", } m["sai-chu"] = { "Churuya", 5118339, "sai-guh", "Latn", } m["sai-cje-pro"] = { "Proto-Central Jê", 116773198, "sai-cje", "Latn", type = "reconstructed", } m["sai-cmg"] = { "Comechingon", 6644203, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-cno"] = { "Chono", 5104704, "qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious "Latn", } m["sai-cnr"] = { "Cañari", 5055572, "qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan "Latn", } m["sai-coe"] = { "Coeruna", 6425639, "sai-wit", "Latn", } m["sai-col"] = { "Colán", 5141893, "sai-ctc", "Latn", } m["sai-cop"] = { "Copallén", 5390321, "qfa-unc", -- extinct, only four words attested; possibly Cholonan "Latn", } m["sai-crd"] = { "Coroado Puri", 24191321, "sai-mje", "Latn", } m["sai-ctq"] = { "Catuquinaru", 16858455, "qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages "Latn", } m["sai-cul"] = { "Culli", 2879660, "qfa-unc", -- extinct, poorly attested; often considered an isolate "Latn", } m["sai-cva"] = { "Cueva", 5192644, "qfa-unc", -- extinct, poorly attested; possibly Chocoan "Latn", } m["sai-esm"] = { "Esmeralda", 3058083, "qfa-unc", -- extinct, poorly attested; possibly related to Yaruro "Latn", } m["sai-ewa"] = { "Ewarhuyana", 16898104, nil, "Latn", } m["sai-gam"] = { "Gamela", 5403661, "qfa-unc", -- extinct, poorly attested; possibly an isolate "Latn", } m["sai-gay"] = { "Gayón", 5528902, "sai-jir", "Latn", } m["sai-gmo"] = { "Guamo", 5613495, "qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024). "Latn", } m["sai-gua"] = { "Guachí", 5613172, "sai-guc", "Latn", } m["sai-gue"] = { "Güenoa", 5626799, "sai-crn", "Latn", } m["sai-hau"] = { "Haush", 3128376, "sai-cho", "Latn", } m["sai-jee-pro"] = { "Proto-Jê", 116773212, "sai-jee", "Latn", type = "reconstructed", } m["sai-jko"] = { "Jeikó", 6176527, "sai-mje", "Latn", } m["sai-jrj"] = { "Jirajara", 6202966, "sai-jir", "Latn", } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc "Katembri", 6375925, "qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia] "Latn", } m["sai-mal"] = { "Malalí", 6741212, "sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry "Latn", } m["sai-mar"] = { "Maratino", 6755055, "qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan "Latn", } m["sai-mat"] = { "Matanawi", 6786047, "qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified "Latn", } m["sai-mcn"] = { "Mocana", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-men"] = { "Menien", 16890110, "sai-mje", "Latn", } m["sai-mil"] = { "Millcayac", 19573012, "sai-hrp", "Latn", } m["sai-mlb"] = { "Malibu", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-msk"] = { "Masakará", 6782426, "sai-mje", "Latn", } m["sai-muc"] = { "Mucuchí", 6931290, nil, -- generally considered Timotean, for which we have no entry "Latn", } m["sai-mue"] = { "Muellama", 16886936, "sai-bar", "Latn", } m["sai-muz"] = { "Muzo", 6644203, "qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban) "Latn", } m["sai-mys"] = { "Maynas", 16919393, "sai-cah", -- per Campbell (2024); formerly considered unclassified "Latn", } m["sai-nat"] = { "Natú", 9006749, "qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages] "Latn", } m["sai-nje-pro"] = { "Proto-Northern Jê", 116773245, "sai-nje", "Latn", type = "reconstructed", } m["sai-opo"] = { "Opón", 7099152, "sai-car", "Latn", } m["sai-oto"] = { "Otomaco", 16879234, "sai-otm", "Latn", } m["sai-pal"] = { "Palta", 3042978, "qfa-unc", -- extinct, unclassified; possibly Chicham "Latn", } m["sai-pam"] = { "Pamigua", 5908689, "sai-otm", "Latn", } m["sai-par"] = { "Paratió", 16890038, "qfa-unc", -- extinct, poorly attested; possibly Xukuruan "Latn", } m["sai-peb"] = { "Peba", 3373890, "sai-pey", "Latn", } m["sai-pnz"] = { "Panzaleo", 3123275, "qfa-unc", -- extinct, unclassified; possibly Paezan "Latn", } m["sai-prh"] = { "Puruhá", 3410994, "qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari "Latn", } m["sai-ptg"] = { "Patagón", 128807870, "sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024) "Latn", } m["sai-pur"] = { "Purukotó", 7261622, "sai-pem", "Latn", } m["sai-pyg"] = { "Payaguá", 7156643, "sai-guc", "Latn", } m["sai-pyk"] = { "Pykobjê", 98113977, "sai-nje", "Latn", } m["sai-qmb"] = { "Quimbaya", 7272043, "qfa-unc", -- extinct, might not exist; few known words "Latn", } m["sai-qtm"] = { "Quitemo", 7272651, "sai-cpc", "Latn", } m["sai-rab"] = { "Rabona", 6644203, "qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra "Latn", } m["sai-ram"] = { "Ramanos", 16902824, "qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages" "Latn", } m["sai-sac"] = { "Sácata", 5390321, "qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan "Latn", } m["sai-san"] = { "Sanaviron", 16895999, "qfa-unc", -- extinct, unclassified; no consensus on classification "Latn", } m["sai-sap"] = { "Sapará", 7420922, "sai-car", "Latn", } m["sai-sec"] = { "Sechura", 7442912, "qfa-unc", -- extinct, poorly attested; possibly Catacaoan "Latn", } m["sai-sin"] = { "Sinúfana", 7525275, "qfa-unc", -- moribund, poorly attested; possibly Chocoan "Latn", } m["sai-sje-pro"] = { "Proto-Southern Jê", 116773814, "sai-sje", "Latn", type = "reconstructed", } m["sai-tab"] = { "Tabancale", 5390321, "qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate "Latn", } m["sai-tal"] = { "Tallán", 16910468, "qfa-unc", -- extinct, poorly attested; might be Catacaoan "Latn", } m["sai-tap"] = { "Tapayuna", 30719984, "sai-nje", "Latn", } m["sai-tar-pro"] = { "Proto-Taranoan", 116773816, "sai-tar", "Latn", type = "reconstructed", } m["sai-teu"] = { "Teushen", 3519243, "qfa-unc", -- probably extinct by the 1950's; possibly Chonan "Latn", } m["sai-tim"] = { "Timote", 7806995, nil, -- possibly in a small Timotean family "Latn", } m["sai-tpr"] = { "Taparita", 7684460, "sai-otm", "Latn", } m["sai-trr"] = { "Tarairiú", 7685313, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sai-wai"] = { "Waitaká", 16918610, "qfa-unc", -- extinct, possibly Purian "Latn", } m["sai-way"] = { "Wayumara", 7960726, "sai-car", "Latn", } m["sai-wit-pro"] = { "Proto-Witotoan", 116773823, "sai-wit", "Latn", type = "reconstructed", } m["sai-wnm"] = { "Wanham", 16879440, "sai-cpc", "Latn", } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat "Xocó", 12953620, "qfa-unc", -- extinct and poorly attested; not clear if one or three languages "Latn", } m["sai-yao"] = { "Yao (South America)", 16979655, "sai-ven", "Latn", } m["sai-yar"] = { -- not the same family as 'suy' "Yarumá", 3505859, "sai-pek", "Latn", } m["sai-yri"] = { "Yuri", 2669157, "sai-tyu", "Latn", } m["sai-yup"] = { "Yupua", 8061430, "sai-tuc", "Latn", } m["sai-yur"] = { "Yurumanguí", 1281291, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sal-pro"] = { "Proto-Salish", 116773269, "sal", "Latn", type = "reconstructed", } m["sdv-daj-pro"] = { "Proto-Daju", 116773739, "sdv-daj", "Latn", type = "reconstructed", } m["sdv-eje-pro"] = { "Proto-Eastern Jebel", 116773751, "sdv-eje", "Latn", type = "reconstructed", } m["sdv-nil-pro"] = { "Proto-Nilotic", 116773794, "sdv-nil", "Latn", type = "reconstructed", } m["sdv-nyi-pro"] = { "Proto-Nyima", 116773796, "sdv-nyi", "Latn", type = "reconstructed", } m["sdv-tmn-pro"] = { "Proto-Taman", 116773815, "sdv-tmn", "Latn", type = "reconstructed", } m["sel-nor"] = { "Northern Selkup", 30304565, "sel", "Cyrl", translit = "sel-nor-translit", } m["sel-pro"] = { "Proto-Selkup", 128884235, "sel", "Latn", type = "reconstructed", } m["sel-sou"] = { "Southern Selkup", 30304639, "sel", "Cyrl", translit = "sel-sou-translit", } m["sem-amm"] = { "Ammonite", 279181, "sem-can", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-amo"] = { "Amorite", 35941, "sem-nwe", "Xsux, Latn", } m["sem-cha"] = { "Chaha", 35543, "sem-eth", "Ethi", translit = "Ethi-translit", } m["sem-dad"] = { "Dadanitic", 21838040, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-dum"] = { "Dumaitic", 128810397, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-has"] = { "Hasaitic", 3541433, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-his"] = { "Hismaic", 22948260, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-mhr"] = { "Muher", 33743, "sem-eth", "Latn", } m["sem-pro"] = { "Proto-Semitic", 1658554, "sem", "Latn", type = "reconstructed", } m["sem-saf"] = { "Safaitic", 472586, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-sam"] = { "Samalian", 85847147, "sem-nwe", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-srb"] = { "Old South Arabian", 35025, "sem-osa", "Sarb", -- Sarb translit in [[Module:scripts/data]] } m["sem-tay"] = { "Taymanitic", 24912301, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-tha"] = { "Thamudic", 843030, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-wes-pro"] = { "Proto-West Semitic", 98021726, "sem-wes", "Latn", type = "reconstructed", } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' "Proto-Siouan", 34181, "sio", "Latn", type = "reconstructed", } m["sit-aao-pro"] = { "Proto-Central Naga", nil, "sit-aao", "Latn", type = "reconstructed", } m["sit-bai-pro"] = { "Proto-Bai", nil, "sit-bai", "Latn", type = "reconstructed", } m["sit-ban"] = { "Bangru", 56071779, "sit-hrs", "Latn", } m["sit-bdi-pro"] = { "Proto-Bodish", nil, "sit-bdi", "Latn", type = "reconstructed", } m["sit-bok"] = { "Bokar", 4938727, "sit-tan", "Latn, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["sit-cai"] = { "Caijia", 5017528, "sit-cln", "Latn" } m["sit-cha"] = { "Chairel", 5068066, "sit-luu", "Latn", } m["sit-ers-pro"] = { "Proto-Ersuic", nil, "sit-ers", "Latn", type = "reconstructed", } m["sit-hrs-pro"] = { "Proto-Hrusish", 116773762, "sit-hrs", "Latn", type = "reconstructed", } m["sit-jap"] = { "Japhug", 3162245, "sit-egy", "Latn", } m["sit-kha-pro"] = { "Proto-Kham", 116773773, "sit-kha", "Latn", type = "reconstructed", } m["sit-khb-pro"] = { "Proto-Kho-Bwa", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khp-pro"] = { "Proto-Puroik", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khw-pro"] = { "Proto-Western Kho-Bwa", nil, "sit-khw", "Latn", type = "reconstructed", } m["sit-kon-pro"] = { "Proto-Northern Naga", nil, "sit-kon", "Latn", type = "reconstructed", } m["sit-liz"] = { "Lizu", 6660653, "sit-ers", "Latn", -- and Ersu Shaba } m["sit-lnj"] = { "Longjia", 17096251, "sit-cln", "Latn" } m["sit-lrn"] = { "Luren", 16946370, "sit-cln", "Latn" } m["sit-luu-pro"] = { "Proto-Luish", 116773783, "sit-luu", "Latn", type = "reconstructed", } m["sit-nas-pro"] = { "Proto-Naish", nil, "sit-nas", "Latn", type = "reconstructed", } m["sit-prn"] = { "Puiron", 7259048, "sit-zem", } m["sit-pro"] = { "Proto-Sino-Tibetan", 24839178, "sit", "Latn", type = "reconstructed", } m["sit-sit"] = { "Situ", 19840830, "sit-egy", "Latn", } m["sit-tam-pro"] = { "Proto-Tamangic", 117469295, "sit-tam", "Latn", type = "reconstructed", } m["sit-tan-pro"] = { "Proto-Tani", 116773284, "sit-tan", "Latn", -- needs verification type = "reconstructed", } m["sit-tgm"] = { "Tangam", 17041370, "sit-tan", "Latn", } m["sit-tng-pro"] = { "Proto-Tangkhulic", nil, "sit-tng", "Latn", type = "reconstructed" } m["sit-tos"] = { "Tosu", 7827899, "sit-ers", "Latn", -- also Ersu Shaba } m["sit-tsh"] = { "Tshobdun", 19840950, "sit-egy", "Latn", } m["sit-zbu"] = { "Zbu", 19841106, "sit-egy", "Latn", } m["sla-pro"] = { "Proto-Slavic", 747537, "sla", "Latn", type = "reconstructed", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {'ś'}, }, sort_key = { from = {"č", "ď", "ě", "ę", "ь", "ľ", "ň", "ǫ", "ř", "š", "ś", "ť", "ъ", "ž"}, to = {"c²", "d²", "e²", "e³", "i²", "l²", "nj", "o²", "r²", "s²", "s³", "t²", "u²", "z²"}, } } m["smi-pro"] = { "Proto-Samic", 7251862, "smi", "Latn", type = "reconstructed", sort_key = { from = {"ā", "č", "δ", "[ëē]", "ŋ", "ń", "ō", "š", "θ", "%([^()]+%)"}, to = {"a", "c²", "d", "e", "n²", "n³", "o", "s²", "t²"} }, } m["son-pro"] = { "Proto-Songhay", 116773277, "son", "Latn", type = "reconstructed", } m["sqj-pro"] = { "Proto-Albanian", 18210846, "sqj", "Latn", type = "reconstructed", } m["ssa-klk-pro"] = { "Proto-Kuliak", 116773779, "ssa-klk", "Latn", type = "reconstructed", } m["ssa-kom-pro"] = { "Proto-Koman", 116773775, "ssa-kom", "Latn", type = "reconstructed", } m["ssa-pro"] = { "Proto-Nilo-Saharan", 116773236, "ssa", "Latn", type = "reconstructed", } m["syd-pro"] = { "Proto-Samoyedic", 7251863, "syd", "Latn", type = "reconstructed", } m["tai-pro"] = { "Proto-Tai", 6583709, "tai", "Latn", type = "reconstructed", } m["tai-swe-pro"] = { "Proto-Southwestern Tai", 116773280, "tai-swe", "Latn", type = "reconstructed", } m["tbq-bdg-pro"] = { "Proto-Bodo-Garo", 116773195, "tbq-bdg", "Latn", type = "reconstructed", } m["tbq-blg"] = { "Bailang", 2879843, "tbq-lob", "Hani", sort_key = "Hani-sortkey", } m["tbq-brm-pro"] = { "Proto-Burmish", nil, "tbq-brm", "Latn", type = "reconstructed", } m["tbq-gkh"] = { "Gokhy", 5578069, "tbq-sil", "Latn", } m["tbq-kuk-pro"] = { "Proto-Kuki-Chin", 116773220, "tbq-kuk", "Latn", type = "reconstructed", } m["tbq-lal-pro"] = { "Proto-Lalo", 116773781, "tbq-lal", "Latn", type = "reconstructed", } m["tbq-laz"] = { "Laze", 17007626, "sit-nas", "Latn", } m["tbq-lob-pro"] = { "Proto-Lolo-Burmese", 116773224, "tbq-lob", "Latn", type = "reconstructed", } m["tbq-lol-pro"] = { "Proto-Loloish", 7251855, "tbq-lol", "Latn", type = "reconstructed", } m["tbq-mil"] = { "Milang", 6850761, "sit-gsi", "Deva, Latn", } m["tbq-mor"] = { "Moran", 6909216, "tbq-bdg", "Latn", } m["tbq-ngo"] = { "Ngochang", 56582, "tbq-brm", "Latn", } -- tbq-pro is now etymology-only m["trk-dkh"] = { "Dukhan", 12809273, "trk-ssb", "Latn, Cyrl, Mong", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] } -- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''. m["trk-eog"] = { "Early Old Oghuz", nil, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, } m["trk-oat"] = { "Old Anatolian Turkish", 7083390, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, ancestors = "trk-eog", } m["trk-pro"] = { "Proto-Turkic", 3657773, "trk", "Latn", type = "reconstructed", standard_chars = { Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron, } } m["tup-gua-pro"] = { "Proto-Tupi-Guarani", 116773288, "tup-gua", "Latn", type = "reconstructed", } m["tup-kab"] = { "Kabishiana", 15302988, "tup", "Latn", } m["tup-pro"] = { "Proto-Tupian", 10354700, "tup", "Latn", type = "reconstructed", } m["tuw-alk"] = { "Alchuka", 113553616, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-bal"] = { "Bala", 86730632, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kkl"] = { "Kyakala", 118875708, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kli"] = { "Kili", 6406892, "tuw-ewe", "Cyrl", } m["tuw-pro"] = { "Proto-Tungusic", 85872335, "tuw", "Latn", type = "reconstructed", } m["tuw-sol"] = { "Solon", 30004, "tuw-ewe", } m["urj-fin-pro"] = { "Proto-Finnic", 11883720, "urj-fin", "Latn", type = "reconstructed", } m["urj-koo"] = { "Old Komi", 86679962, "kv", "Perm, Cyrs", translit = "urj-koo-translit", -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present } m["urj-kuk"] = { "Kukkuzi", 107410460, "urj-fin", "Latn", ancestors = "vot", } m["urj-kya"] = { "Komi-Yazva", 2365210, "kv", "Cyrl", translit = "kv-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.acute}, } m["urj-mdv-pro"] = { "Proto-Mordvinic", 116773232, "urj-mdv", "Latn", type = "reconstructed", } m["urj-prm-pro"] = { "Proto-Permic", 116773257, "urj-prm", "Latn", type = "reconstructed", } m["urj-pro"] = { "Proto-Uralic", 288765, "urj", "Latn", type = "reconstructed", } m["urj-ugr-pro"] = { "Proto-Ugric", 156631, "urj-ugr", "Latn", type = "reconstructed", } m["xnd-pro"] = { "Proto-Na-Dene", 116773233, "xnd", "Latn", type = "reconstructed", } m["xgn-pro"] = { "Proto-Mongolic", 2493677, "xgn", "Latn", type = "reconstructed", sort_key = { from = {"č", "i", "ï", "ǰ", "ŋ", "ö", "š", "ü"}, to = {"c", "i" .. p[1], "i", "j", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]}, }, } m["yok-bvy"] = { "Buena Vista Yokuts", 4985474, "yok", "Latn", } m["yok-dly"] = { "Delta Yokuts", 70923266, "yok", "Latn", } m["yok-gsy"] = { "Gashowu Yokuts", 3098708, "yok", "Latn", } m["yok-kry"] = { "Kings River Yokuts", 6413014, "yok", "Latn", } m["yok-nvy"] = { "Northern Valley Yokuts", 85789777, "yok", "Latn", } m["yok-ply"] = { "Palewyami Yokuts", 2387391, "yok", "Latn", } m["yok-svy"] = { "Southern Valley Yokuts", 12642473, "yok", "Latn", } m["yok-tky"] = { "Tule-Kaweah Yokuts", 7851988, "yok", "Latn", } m["ypk-pro"] = { "Proto-Yupik", 116773295, "ypk", "Latn", type = "reconstructed", } m["yrk-for"] = { "Forest Nenets", 1295107, "yrk", "Cyrl", translit = "yrk-for-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove}, } m["yrk-tun"] = { "Tundra Nenets", 36452, "yrk", "Cyrl", strip_diacritics = { from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"}, to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"}, }, translit = "yrk-tun-translit", } m["zhx-min-pro"] = { "Proto-Min", 19646347, "zhx-min", "Latn", type = "reconstructed", } m["zhx-sht"] = { "Shaozhou Tuhua", 1920769, "zhx", "Nshu, Hants", generate_forms = "zh-generateforms", sort_key = {Hani = "Hani-sortkey"}, } m["zhx-sic"] = { "Sichuanese", 2278732, "zhx-man", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zhx-tai"] = { "Taishanese", 2208940, "zhx-yue", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zle-ono"] = { "Old Novgorodian", 162013, "zle", "Cyrs, Glag", translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zle-ort"] = { "Old Ruthenian", 13211, "zle", "Arab, Cyrs, Latn", ancestors = "orv", translit = { Cyrs = "zle-ort-translit", Arab = "zle-ort-Arab-translit", }, strip_diacritics = { Cyrs = { remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"], remove_exceptions = {"Ї", "ї"}, }, Arab = "ar-stripdiacritics", }, -- Cyrs sort_key in [[Module:scripts/data]] } m["zls-chs"] = { "Church Slavonic", 33251, "zls", "Cyrs, Glag, Latn", ancestors = "cu", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zlw-ocs"] = { "Old Czech", 593096, "zlw", "Latn", } m["zlw-opl"] = { "Old Polish", 149838, "zlw-lch", "Latn", strip_diacritics = {remove_diacritics = c.ringabove}, } m["zlw-osk"] = { "Old Slovak", 12776676, "zlw", "Latn", } m["zlw-slv"] = { "Slovincian", 36822, "zlw-pom", "Latn", strip_diacritics = {remove_diacritics = c.macron .. c.breve}, } return require("Module:languages").finalizeData(m, "language") 1bgermwbvwqmza1dm0hk2c40l668fl9 10 142043 231377 2025-12-22T02:25:19Z en>Benwing2 0 Created page with "{{if then show|{{#invoke:data consistency check|check_modules_t|languages/data/2|languages/data/2/extra|languages/data/3/a|languages/data/3/a/extra|languages/data/3/b|languages/data/3/b/extra|languages/data/3/c|languages/data/3/c/extra|languages/data/3/d|languages/data/3/d/extra|languages/data/3/e|languages/data/3/e/extra|languages/data/3/f|languages/data/3/f/extra|languages/data/3/g|languages/data/3/g/extra|languages/data/3/h|languages/data/3/h/extra|languages/data/3/i|..." 231377 wikitext text/x-wiki {{if then show|{{#invoke:data consistency check|check_modules_t|languages/data/2|languages/data/2/extra|languages/data/3/a|languages/data/3/a/extra|languages/data/3/b|languages/data/3/b/extra|languages/data/3/c|languages/data/3/c/extra|languages/data/3/d|languages/data/3/d/extra|languages/data/3/e|languages/data/3/e/extra|languages/data/3/f|languages/data/3/f/extra|languages/data/3/g|languages/data/3/g/extra|languages/data/3/h|languages/data/3/h/extra|languages/data/3/i|languages/data/3/i/extra|languages/data/3/j|languages/data/3/j/extra|languages/data/3/k|languages/data/3/k/extra|languages/data/3/l|languages/data/3/l/extra|languages/data/3/m|languages/data/3/m/extra|languages/data/3/n|languages/data/3/n/extra|languages/data/3/o|languages/data/3/o/extra|languages/data/3/p|languages/data/3/p/extra|languages/data/3/q|languages/data/3/q/extra|languages/data/3/r|languages/data/3/r/extra|languages/data/3/s|languages/data/3/s/extra|languages/data/3/t|languages/data/3/t/extra|languages/data/3/u|languages/data/3/u/extra|languages/data/3/v|languages/data/3/v/extra|languages/data/3/w|languages/data/3/w/extra|languages/data/3/x|languages/data/3/x/extra|languages/data/3/y|languages/data/3/y/extra|languages/data/3/z|languages/data/3/z/extra|languages/data/exceptional|languages/data/exceptional/extra|etymology languages/data|families/data|languages/canonical names|languages/code to canonical name|etymology languages/canonical names|etymology languages/code to canonical name|families/canonical names|families/code to canonical name|Template:langname-lite}}|[[Module:data consistency check]] shows no relevant errors.|The following errors were detected by [[Module:data consistency check]]: <noinclude/>}} 28y6vmbg6gouingwpevfai8vjzy5jrp 231378 231377 2026-04-14T07:35:01Z Lee 19 [[:en:Template:language_data_consistency_check]] වෙතින් එක් සංශෝධනයක් 231377 wikitext text/x-wiki {{if then show|{{#invoke:data consistency check|check_modules_t|languages/data/2|languages/data/2/extra|languages/data/3/a|languages/data/3/a/extra|languages/data/3/b|languages/data/3/b/extra|languages/data/3/c|languages/data/3/c/extra|languages/data/3/d|languages/data/3/d/extra|languages/data/3/e|languages/data/3/e/extra|languages/data/3/f|languages/data/3/f/extra|languages/data/3/g|languages/data/3/g/extra|languages/data/3/h|languages/data/3/h/extra|languages/data/3/i|languages/data/3/i/extra|languages/data/3/j|languages/data/3/j/extra|languages/data/3/k|languages/data/3/k/extra|languages/data/3/l|languages/data/3/l/extra|languages/data/3/m|languages/data/3/m/extra|languages/data/3/n|languages/data/3/n/extra|languages/data/3/o|languages/data/3/o/extra|languages/data/3/p|languages/data/3/p/extra|languages/data/3/q|languages/data/3/q/extra|languages/data/3/r|languages/data/3/r/extra|languages/data/3/s|languages/data/3/s/extra|languages/data/3/t|languages/data/3/t/extra|languages/data/3/u|languages/data/3/u/extra|languages/data/3/v|languages/data/3/v/extra|languages/data/3/w|languages/data/3/w/extra|languages/data/3/x|languages/data/3/x/extra|languages/data/3/y|languages/data/3/y/extra|languages/data/3/z|languages/data/3/z/extra|languages/data/exceptional|languages/data/exceptional/extra|etymology languages/data|families/data|languages/canonical names|languages/code to canonical name|etymology languages/canonical names|etymology languages/code to canonical name|families/canonical names|families/code to canonical name|Template:langname-lite}}|[[Module:data consistency check]] shows no relevant errors.|The following errors were detected by [[Module:data consistency check]]: <noinclude/>}} 28y6vmbg6gouingwpevfai8vjzy5jrp 14 142044 231393 2020-07-17T01:37:58Z en>WingerBot 0 Created page with "{{auto cat}}" 231393 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231394 231393 2026-04-14T11:48:13Z Lee 19 [[:en:Category:inc-ash:Government]] වෙතින් එක් සංශෝධනයක් 231393 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 14 142045 231395 2024-01-10T11:10:34Z en>WingerBot 0 Created page with "{{auto cat}}" 231395 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231396 231395 2026-04-14T11:48:45Z Lee 19 [[:en:Category:inc-ash:Occupations]] වෙතින් එක් සංශෝධනයක් 231395 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 14 142046 231397 2026-04-14T11:49:11Z Lee 19 නිර්මාණය 231397 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 14 142047 231398 2026-04-14T11:49:39Z Pinthura 2424 සේවා: [[:[[en:Category:Ashokan Prakrit terms derived from Sanskrit]]]] තුළ තිබූ පෙළ මෙහි ඇතුළු කිරීම. 231398 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231404 231398 2026-04-14T11:50:29Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit terms derived from Sanskrit]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් ව්‍යුත්පන්න]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231398 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231412 231404 2026-04-14T11:51:09Z Pinthura 2424 සේවා: ඉංග්‍රීසි ව්‍යාපෘතිය වෙත සබැඳියක් එක් කිරීම. 231412 wikitext text/x-wiki {{auto cat}} [[en:Category:Ashokan Prakrit terms derived from Sanskrit]] 2wt03v0brxmztphiwt8enrqc9o82jxy 14 142048 231399 2026-04-14T11:49:49Z Pinthura 2424 සේවා: [[:[[en:Category:Ashokan Prakrit terms inherited from Sanskrit]]]] තුළ තිබූ පෙළ මෙහි ඇතුළු කිරීම. 231399 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231406 231399 2026-04-14T11:50:39Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit terms inherited from Sanskrit]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් උරුම වූ]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231399 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231413 231406 2026-04-14T11:51:19Z Pinthura 2424 සේවා: ඉංග්‍රීසි ව්‍යාපෘතිය වෙත සබැඳියක් එක් කිරීම. 231413 wikitext text/x-wiki {{auto cat}} [[en:Category:Ashokan Prakrit terms inherited from Sanskrit]] fd4a2d6sop1gqe5iwd0kcrr2jtrze55 14 142049 231400 2026-04-14T11:49:59Z Pinthura 2424 සේවා: [[:[[en:Category:Ashokan Prakrit lemmas]]]] තුළ තිබූ පෙළ මෙහි ඇතුළු කිරීම. 231400 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231408 231400 2026-04-14T11:50:49Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit lemmas]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත පාඨ]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231400 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231414 231408 2026-04-14T11:51:29Z Pinthura 2424 සේවා: ඉංග්‍රීසි ව්‍යාපෘතිය වෙත සබැඳියක් එක් කිරීම. 231414 wikitext text/x-wiki {{auto cat}} [[en:Category:Ashokan Prakrit lemmas]] krnbfvk3ja074xjj2v0apseeiep9ymp 14 142050 231401 2026-04-14T11:50:09Z Pinthura 2424 සේවා: [[:[[en:Category:Ashokan Prakrit terms with quotations]]]] තුළ තිබූ පෙළ මෙහි ඇතුළු කිරීම. 231401 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231410 231401 2026-04-14T11:50:59Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit terms with quotations]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, උපුටා දැක්වීම් සහිත]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231401 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 231415 231410 2026-04-14T11:51:39Z Pinthura 2424 සේවා: ඉංග්‍රීසි ව්‍යාපෘතිය වෙත සබැඳියක් එක් කිරීම. 231415 wikitext text/x-wiki {{auto cat}} [[en:Category:Ashokan Prakrit terms with quotations]] 8iuafzcqpsovun1ck6mcj362d31oi3y 14 142051 231403 2026-04-14T11:50:20Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit ප්‍රවේශ නඩත්තුව]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත ප්‍රවේශ නඩත්තුව]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231403 wikitext text/x-wiki #යළියොමුව [[:ප්‍රවර්ගය:අශෝක ප්‍රාකෘත ප්‍රවේශ නඩත්තුව]] 0wuzaak7zzhwzyhhufcfgh16bazcg97 231416 231403 2026-04-14T11:51:49Z Pinthura 2424 සේවා: යළියොමුව, මෘදු ප්‍රවර්ග යළියොමුවක් බවට හැරවීම. 231416 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත ප්‍රවේශ නඩත්තුව}} 7t5t8xhetcgykaofg60ntand9hj0xxk 14 142052 231405 2026-04-14T11:50:30Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit terms derived from Sanskrit]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් ව්‍යුත්පන්න]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231405 wikitext text/x-wiki #යළියොමුව [[:ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් ව්‍යුත්පන්න]] 4d65qf3ca9u9zf4g3g917e623fjx9kb 231417 231405 2026-04-14T11:51:59Z Pinthura 2424 සේවා: යළියොමුව, මෘදු ප්‍රවර්ග යළියොමුවක් බවට හැරවීම. 231417 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් ව්‍යුත්පන්න}} gii4y2co5xjyard8sv3mbj1bc1p8kj3 14 142053 231407 2026-04-14T11:50:40Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit terms inherited from Sanskrit]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් උරුම වූ]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231407 wikitext text/x-wiki #යළියොමුව [[:ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් උරුම වූ]] alo6y5e91v6ceumhx9q8na5ln2qhhyf 231418 231407 2026-04-14T11:52:09Z Pinthura 2424 සේවා: යළියොමුව, මෘදු ප්‍රවර්ග යළියොමුවක් බවට හැරවීම. 231418 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් උරුම වූ}} b1u2d5jnnur2zidqtmm4lemo36h90in 14 142054 231409 2026-04-14T11:50:49Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit lemmas]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත පාඨ]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231409 wikitext text/x-wiki #යළියොමුව [[:ප්‍රවර්ගය:අශෝක ප්‍රාකෘත පාඨ]] lgy3xmfoc6k4aasnii4lcz8prieap5c 231420 231409 2026-04-14T11:52:19Z Pinthura 2424 සේවා: යළියොමුව, මෘදු ප්‍රවර්ග යළියොමුවක් බවට හැරවීම. 231420 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත පාඨ}} cy638xtde9m084pihpbu082mxx821mg 14 142055 231411 2026-04-14T11:50:59Z Pinthura 2424 Pinthura විසින් [[ප්‍රවර්ගය:Ashokan Prakrit terms with quotations]] සිට [[ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, උපුටා දැක්වීම් සහිත]] වෙත පිටුව ගෙන යන ලදී: සේවා: නව ප්‍රවර්ග නාමය වෙත ගෙනයාම. 231411 wikitext text/x-wiki #යළියොමුව [[:ප්‍රවර්ගය:අශෝක ප්‍රාකෘත යෙදුම්, උපුටා දැක්වීම් සහිත]] ese5mii7rxhtlke67c3uep8ggdvkmbm 231421 231411 2026-04-14T11:52:29Z Pinthura 2424 සේවා: යළියොමුව, මෘදු ප්‍රවර්ග යළියොමුවක් බවට හැරවීම. 231421 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, උපුටා දැක්වීම් සහිත}} j34au2p3nppl2pw25cuxfu1kq93p81b 14 142056 231422 2026-04-14T11:52:39Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231422 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් ව්‍යුත්පන්න}} gii4y2co5xjyard8sv3mbj1bc1p8kj3 14 142057 231423 2026-04-14T11:52:49Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231423 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් උරුම වූ}} b1u2d5jnnur2zidqtmm4lemo36h90in 14 142058 231424 2026-04-14T11:52:59Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231424 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත පාඨ}} cy638xtde9m084pihpbu082mxx821mg 14 142059 231425 2026-04-14T11:53:09Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231425 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, උපුටා දැක්වීම් සහිත}} j34au2p3nppl2pw25cuxfu1kq93p81b 14 142060 231426 2026-04-14T11:53:19Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231426 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත ප්‍රවේශ නඩත්තුව}} 7t5t8xhetcgykaofg60ntand9hj0xxk 14 142061 231427 2026-04-14T11:53:29Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231427 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් ව්‍යුත්පන්න}} gii4y2co5xjyard8sv3mbj1bc1p8kj3 14 142062 231428 2026-04-14T11:53:39Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231428 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, සංස්කෘත වෙතින් උරුම වූ}} b1u2d5jnnur2zidqtmm4lemo36h90in 14 142063 231429 2026-04-14T11:53:49Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231429 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත පාඨ}} cy638xtde9m084pihpbu082mxx821mg 14 142064 231430 2026-04-14T11:53:59Z Pinthura 2424 සේවා: මෘදු ප්‍රවර්ග යළියොමුවක් නිර්මාණය. 231430 wikitext text/x-wiki {{category redirect|අශෝක ප්‍රාකෘත යෙදුම්, උපුටා දැක්වීම් සහිත}} j34au2p3nppl2pw25cuxfu1kq93p81b