Wiksiyonaryo tlwiktionary https://tl.wiktionary.org/wiki/Wiksiyonaryo:Unang_Pahina MediaWiki 1.46.0-wmf.23 case-sensitive Midya Natatangi Usapan Tagagamit Usapang tagagamit Wiksiyonaryo Usapang Wiksiyonaryo Talaksan Usapang talaksan MediaWiki Usapang MediaWiki Padron Usapang padron Tulong Usapang tulong Kategorya Usapang kategorya TimedText TimedText talk Module Module talk Event Event talk 828 30846 176309 175676 2026-04-13T15:08:05Z Yivan000 4078 176309 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 = {} ---------------------------------------------------------------------------------------------------------------------- -- Afroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Berber varieties -- -------------------------------------------------------------------------------------- m["shi-med"] = { "Medieval Tashelhit", 34152, "shi", } -- Tuareg lects m["thv"] = { "Tamahaq", 56703, "tmh", } m["ttq"] = { "Tawellemmet", 56390, "tmh", } m["taq"] = { "Tamasheq", 4670066, "tmh", } m["thz"] = { "Tayert", 56388, "tmh", } m["thv-ght"] = { "Ghat", 47012900, "thv", } -------------------------------------------------------------------------------------- -- Cushitic varieties -- -------------------------------------------------------------------------------------- -- Oromo varieties m["hae"] = { "Harar Oromo", 5330355, "om", aliases = {"Eastern Oromo"}, } m["gax"] = { "Borana", 2910610, "om", aliases = {"Southern Oromo"}, } m["orc"] = { "Orma", 2919128, "om", } m["ssn"] = { "Waata", 3501553, "om", } -------------------------------------------------------------------------------------- -- Egyptian varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Ancient Egyptian varieties -- ----------------------------------------------------- m["egy-old"] = { "Old Egyptian", 447117, "egy", } m["egy-mid"] = { "Middle Egyptian", 657330, "egy", aliases = {"Classical Egyptian"}, } m["egy-nmi"] = { "Neo-Middle Egyptian", 123735278, "egy", aliases = {"Égyptien de tradition", "Traditional Egyptian"}, } m["egy-lat"] = { "Late Egyptian", 1852329, "egy", } ----------------------------------------------------- -- Coptic varieties -- ----------------------------------------------------- m["cop-akh"] = { "Akhmimic Coptic", 125176464, "cop", aliases = {"Akhmimic"}, } m["cop-boh"] = { "Bohairic Coptic", 890733, "cop", aliases = {"Bohairic", "Memphitic Coptic", "Memphitic"}, } m["cop-ggg"] = { "Coptic Dialect G", nil, "cop", aliases = {"Dialect G", "Mansuric Coptic", "Mansuric"}, } m["cop-jjj"] = { "Coptic Dialect J", nil, "cop", } m["cop-kkk"] = { "Coptic Dialect K", nil, "cop", } m["cop-ppp"] = { "Coptic Dialect P", nil, "cop", aliases = {"Proto-Theban Coptic", "Palaeo-Theban Coptic"}, } m["cop-fay"] = { "Fayyumic Coptic", 1399115, "cop", aliases = {"Fayyumic", "Faiyumic Coptic", "Faiyumic", "Fayumic Coptic", "Fayumic", "Bashmuric Coptic", "Bashmuric"}, } m["cop-her"] = { "Hermopolitan Coptic", nil, "cop", aliases = {"Hermopolitan", "Coptic Dialect H", "Ashmuninic", "Ashmuninic Coptic"}, } m["cop-lyc"] = { "Lycopolitan Coptic", nil, "cop", aliases = { "Lycopolitan", "Assiutic Coptic", "Asyutic Coptic", "Assiutic", "Asyutic", "Lyco-Diospolitan Coptic", "Lyco-Diospolitan", "Subakhmimic Coptic", "Subakhmimic" }, } m["cop-old"] = { "Old Coptic", 115518040, "cop", } m["cop-oxy"] = { "Oxyrhynchite Coptic", nil, "cop", aliases = {"Oxyrhynchite", "Mesokemic Coptic", "Mesokemic", "Middle Egyptian Coptic"}, } m["cop-ply"] = { "Proto-Lycopolitan Coptic", nil, "cop", aliases = {"Coptic Dialect i", "Proto-Lyco-Diospolitan Coptic"}, } m["cop-sah"] = { "Sahidic Coptic", 2645851, "cop", aliases = {"Sahidic", "Saidic Coptic", "Saidic", "Thebaic Coptic", "Thebaic"}, } -------------------------------------------------------------------------------------- -- Semitic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akkadian varieties -- ----------------------------------------------------- m["akk-old"] = { "Old Akkadian", nil, "akk", } m["akk-obb"] = { "Old Babylonian", nil, "akk", } m["akk-oas"] = { "Old Assyrian", nil, "akk", } m["akk-mbb"] = { "Middle Babylonian", nil, "akk", } m["akk-mas"] = { "Middle Assyrian", nil, "akk", } m["akk-nbb"] = { "Neo-Babylonian", nil, "akk", } m["akk-nas"] = { "Neo-Assyrian", nil, "akk", } m["akk-lbb"] = { "Late Babylonian", nil, "akk", } m["akk-stb"] = { "Standard Babylonian", nil, "akk", } ----------------------------------------------------- -- Arabic varieties -- ----------------------------------------------------- m["jrb"] = { "Hudeoarabe", --TLCHANGE 37733, "ar", pseudo_families = "qfa-jew", english_name = "Judeo-Arabic", --TLCHANGE spanish_name = "Judeoárabe", --TLCHANGE } m["apc-leb"] = { "Arabe Hilagang Levantino Libanes", --TLCHANGE 1516642, "apc", aliases = {"Lebanese Arabic"}, english_name = "Lebanese North Levantine Arabic", --TLCHANGE } m["apc-sle"] = { "Arabe Hilagang Levantino Timog Libanes", --TLCHANGE 14206590, "apc", aliases = {"South Lebanese Arabic"}, english_name = "South Lebanese North Levantine Arabic", --TLCHANGE } m["apc-nle"] = { "Arabe Hilagang Levantino Hilagang Libanes", --TLCHANGE nil, "apc", aliases = {"North Lebanese Arabic"}, english_name = "North Lebanese North Levantine Arabic", --TLCHANGE } m["apc-syr"] = { "Arabe Hilagang Levantino Siryo", --TLCHANGE 2143071, "apc", aliases = {"Syrian Arabic"}, english_name = "Syrian North Levantine Arabic", --TLCHANGE } m["apc-ale"] = { "Arabe Hilagang Levantino Alepino", --TLCHANGE 7056921, "apc-syr", aliases = {"Aleppo Arabic", "Aleppine Arabic"}, english_name = "Aleppine North Levantine Arabic", --TLCHANGE } m["apc-dam"] = { "Arabe Hilagang Levantino Damaseno", --TLCHANGE 12237466, "apc-syr", aliases = {"Damascus Arabic", "Damascene Arabic"}, english_name = "Damascene North Levantine Arabic", --TLCHANGE } m["acm-khu"] = { "Arabe Huzestani", --TLCHANGE 1040944, "acm", english_name = "Khuzestani Arabic", --TLCHANGE spanish_name = "Árabe juzestaní", --TLCHANGE } ----------------------------------------------------- -- Aramaic varieties -- ----------------------------------------------------- m["arc-bib"] = { "Biblical Aramaic", 843235, "arc", family = "sem-are", } m["arc-cpa"] = { "Christian Palestinian Aramaic", 60790119, "arc", family = "sem-arw", aliases = {"Melkite Aramaic", "Palestinian Syriac", "Syropalestinian Aramaic"}, } m["arc-imp"] = { "Imperial Aramaic", 7079491, "arc", aliases = {"Official Aramaic"}, } m["arc-hat"] = { "Hatran Aramaic", 3832926, "arc", family = "sem-are", } m["arc-jla"] = { "Jewish Literary Aramaic", 105952842, "arc", pseudo_families = "qfa-jew", } m["arc-nab"] = { "Nabataean Aramaic", 36178, "arc", } m["arc-old"] = { "Lumang Arameas", --TLCHANGE 3398392, "arc", english_name = "Old Aramaic", --TLCHANGE } m["arc-pal"] = { "Palmyrene Aramaic", 1510113, "arc", family = "sem-arw", } m["tmr"] = { "Jewish Babylonian Aramaic", 33407, "arc", family = "sem-ase", pseudo_families = "qfa-jew", } m["jpa"] = { "Jewish Palestinian Aramaic", 948909, "arc", family = "sem-arw", aliases = {"Galilean Aramaic"}, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Hebrew varieties -- ----------------------------------------------------- m["hbo"] = { "Biblical Hebrew", 1982248, "he", aliases = {"Classical Hebrew"}, } m["he-mis"] = { "Mishnaic Hebrew", 1649362, "he", ancestors = "hbo", } m["he-med"] = { "Medieval Hebrew", 2712572, "he", ancestors = "he-mis", } m["he-IL"] = { "Israeli Hebrew", 8141, "he", } ---------------------------------------------------------------------------------------------------------------------- -- Ainu varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ain-hok"] = { "Hokkaido Ainu", 20968488, "ain", aliases = {"Hokkaidō Ainu"}, } m["ain-kur"] = { "Kuril Ainu", 20967012, "ain", } m["ain-sak"] = { "Sakhalin Ainu", 20747371, "ain", } ---------------------------------------------------------------------------------------------------------------------- -- American indigenous varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Inuit varieties -- ----------------------------------------------------- m["esi"] = { "North Alaskan Inupiatun", nil, "ik" } m["esk"] = { "Northwest Alaskan Inupiatun", 25559714, "ik" } ----------------------------------------------------- -- Iroquoian varieties -- ----------------------------------------------------- m["iro-ohu"] = { "Old Wendat", nil, "wdt", } m["iro-omo"] = { "Old Mohawk", nil, "moh", } m["iro-oon"] = { "Old Onondaga", nil, "ono", } ----------------------------------------------------- -- Tupi-Guarani varieties -- ----------------------------------------------------- -- Old Tupi varieties m["tpw-lga"] = { "Língua Geral Amazônica", 18275323, "tpw", aliases = {"Língua Geral"}, } m["tpw-lgp"] = { "Língua Geral Paulista", 2669239, "tpw", } ---------------------------------------------------------------------------------------------------------------------- -- Austroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Khmer varieties m["okz-ang"] = { "Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } m["okz-pre"] = { "Pre-Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } -- Central Nicobarese varieties m["ncb-cam"] = { "Camorta", 5026908, "ncb", aliases = {"Kamorta"}, } m["ncb-kat"] = { "Katchal", 17064263, "ncb", aliases = {"Tehnu"}, } m["ncb-nan"] = { "Nancowry", 6962504, "ncb", aliases = {"Nankwari"}, } ---------------------------------------------------------------------------------------------------------------------- -- Austronesian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Malay and related varieties m["ms-old"] = { -- this has the ISO code 'omy' "Old Malay", nil, "ms", } m["ms-cla"] = { "Malay Klasikal", --TLCHANGE nil, "ms", ancestors = "ms-old", english_name = "Classical Malay", --TLCHANGE } m["pse-bsm"] = { "Besemah", nil, "pse", } m["bew-kot"] = { "Betawi Kota", nil, "bew", aliases = {"Urban Betawi"}, -- in Jakarta } -- Philippine varieties m["xnn"] = { "Kankanaëy Aplay", --TLCHANGE -- use this for now; correction must be "Northern Kankanaey" 12953609, "kne", aliases = {"Northern Kankanay", "Northern Kankana-ey"}, is_official_kwf_name = "https://kwfwikaatkultura.ph/kankanaey/", --TLCHANGE english_name = "Northern Kankanay" --TLCHANGE } m["tl-old"] = { "Lumang Tagalog", --TLCHANGE 12967437, "tl", english_name = "Old Tagalog", --TLCHANGE } m["tl-cls"] = { "Tagalog Klasikal", --TLCHANGE nil, "tl", english_name = "Classical Tagalog", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Caucasian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Kartvelian varieties m["ka-mid"] = { "Middle Georgian", nil, "ka", ancestors = "oge", } ---------------------------------------------------------------------------------------------------------------------- -- Dravidian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ta-mid"] = { "Middle Tamil", 20987434, "ta", } m["kn-hav"] = { "Havigannada", 24276369, "kn", } m["kn-kun"] = { "Kundagannada", 6444255, "kn", } ---------------------------------------------------------------------------------------------------------------------- -- Indo-European varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Albanian varieties -- -------------------------------------------------------------------------------------- m["aln"] = { "Gheg Albanian", 181037, "sq", aliases = {"Gheg"}, } m["aae"] = { "Arbëresh Albanian", 1075302, "als", aliases = {"Arbëreshë", "Arbëresh"}, } m["aat"] = { "Arvanitika Albanian", 29347, "als", aliases = {"Arvanitika"}, } m["als"] = { "Tosk Albanian", 180937, "sq", aliases = {"Tosk"}, } -------------------------------------------------------------------------------------- -- Armenian varieties -- -------------------------------------------------------------------------------------- m["hyw"] = { "Western Armenian", 180945, "hy", } m["hye"] = { "Eastern Armenian", 181059, "hy", } -------------------------------------------------------------------------------------- -- Balto-Slavic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Baltic varieties -- ------------------------------------------------------------------------- m["bat-pro"] = { "Proto-Baltic", 1703347, "ine-bsl-pro", } m["bat-dni"] = { "Dnieper Baltic", 4163178, "bat-pro", family = "bat", aliases = {"Dniepr Baltic", "Dnieper-Oka Baltic", "Dniepr-Oka Baltic"}, } m["bat-gol"] = { "Golyad", 4142855, "bat-dni", aliases = {"Eastern Galindian", "East Galindian"}, } ------------------------------------------------------------------------- -- Slavic varieties -- ------------------------------------------------------------------------- ----------------------------------------------------- -- Bulgarian varieties -- ----------------------------------------------------- m["cu-bgm"] = { "Middle Bulgarian", 12294897, "cu", ancestors = "cu" } ----------------------------------------------------- -- Church Slavonic varieties -- ----------------------------------------------------- -- Old Moscow Church Slavonic deleted as it seems not distinct enough from Russian (Synodal) Church Slavonic. m["zls-chs-ru"] = { "Russian Church Slavonic", 21662400, "zls-chs", aliases = {"Synodal Church Slavonic", "New Moscow Church Slavonic", "Novomoskovsk Church Slavonic"}, } m["zls-chs-uk"] = { "Ukrainian Church Slavonic", 12153548, "zls-chs", aliases = {"Rusyn Church Slavonic", "Belarusian Church Slavonic"}, } --[=[ -- Not sure about these yet. m["zls-chs-bg"] = { "Bulgarian Church Slavonic", nil, "zls-chs", } m["zls-chs-cs"] = { "Czech Church Slavonic", nil, "zls-chs", } m["zls-chs-hr"] = { "Croatian Church Slavonic", nil, "zls-chs", } m["zls-chs-mk"] = { "Macedonian Church Slavonic", nil, "zls-chs", } m["zls-chs-ro"] = { "Romanian Church Slavonic", nil, "zls-chs", } m["zls-chs-sr"] = { "Serbian Church Slavonic", nil, "zls-chs", } ]=] ----------------------------------------------------- -- Czech varieties -- ----------------------------------------------------- m["cs-ear"] = { "Early Modern Czech", nil, "cs", ancestors = "zlw-ocs" } ----------------------------------------------------- -- East Slavic varieties -- ----------------------------------------------------- m["zle-ops"] = { "Old Pskovian", 4167885, "zle-ono", } m["zle-mru"] = { "Middle Russian", 35228, "ru", "Cyrs", ancestors = "orv", translit = "ru-translit", strip_diacritics = { Cyrs = { remove_diacritics = c.grave .. c.acute .. c.diaer, }, }, } m["zle-mbe"] = { "Middle Belarusian", 13211, "zle-ort", } m["zle-muk"] = { "Middle Ukrainian", 13211, "zle-ort", } m["uk-CA"] = { "Canadian Ukrainian", 4161010, "uk", } ----------------------------------------------------- -- Polish varieties -- ----------------------------------------------------- m["zlw-mpl"] = { "Gitnang Polako", --TLCHANGE 402878, "pl", ancestors = "zlw-opl", strip_diacritics = { remove_diacritics = c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ó", "ó", "Ś", "ś", "Ź", "ź"}, }, english_name = "Middle Polish", --TLCHANGE } m["pl-gre"] = { "Greater Polish", 4106789, "pl", } m["pl-les"] = { "Lesser Polish", 361709, "pl", } m["pl-mas"] = { "Masovian Polish", 4274559, "pl", } m["pl-gor"] = { "Goral", 452889, "pl", } ----------------------------------------------------- -- Serbo-Croatian varieties -- ----------------------------------------------------- m["ckm"] = { "Serbokroata Tsakavo", --TLCHANGE 337565, "sh", aliases = {"Čakavian"}, english_name = "Chakavian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata chakavo", --TLCHANGE } m["kjv"] = { "Serbokroata Kaykavo", --TLCHANGE 838165, "sh", english_name = "Kajkavian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata kajkavo", --TLCHANGE } m["sh-tor"] = { -- Linguist code srp-tor "Serbokroata Torlak", --TLCHANGE 1078803, "sh", aliases = {"Torlak"}, english_name = "Torlakian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata torlak", --TLCHANGE } -------------------------------------------------------------------------------------- -- Celtic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Brythonic varieties -- ----------------------------------------------------- m["bry-ear"] = { "Early Brythonic", nil, "cel-bry-pro", } m["bry-lat"] = { "Late Brythonic", nil, "cel-bry-pro", } ----------------------------------------------------- -- Gaulish varieties -- ----------------------------------------------------- m["xcg"] = { "Cisalpine Gaulish", 3832927, "cel-gau", } m["xtg"] = { "Transalpine Gaulish", 29977, "cel-gau", } ----------------------------------------------------- -- Welsh varieties -- ----------------------------------------------------- m["cy-nor"] = { "North Wales Welsh", 13127692, "cy", aliases = {"North Walian Welsh", "Northern Welsh"}, } m["cy-sou"] = { "South Wales Welsh", 13127689, "cy", aliases = {"South Walian Welsh", "Southern Welsh"}, } -------------------------------------------------------------------------------------- -- Germanic varieties -- -------------------------------------------------------------------------------------- -- Proto-West Germanic varieties m["frk"] = { "Frankish", 10860505, "gmw-pro", family = "gmw-frk", aliases = {"Old Frankish"}, } m["gem-sue"] = { "Suevic", 134600275, "gmw-pro", aliases = {"Suebian"}, } m["gmw-afr-pro"] = { "Proto-Anglo-Frisian", 134603379, "gmw-nsg-pro", family = "gmw-afr", } m["gmw-nsg-pro"] = { "Proto-North Sea Germanic", 134603374, "gmw-pro", family = "gmw-nsg", aliases = {"Proto-Ingvaeonic"}, } ----------------------------------------------------- -- Dutch varieties -- ----------------------------------------------------- m["nl-BE"] = { "Belgian Dutch", 34147, "nl", aliases = {"Flemish", "Flemish Dutch", "Southern Dutch"}, } ----------------------------------------------------- -- English and Scots varieties -- ----------------------------------------------------- -- English varieties m["en-AU"] = { "Ingles Awstralyano", --TLCHANGE 44679, "en", english_name = "Australian English", --TLCHANGE spanish_name = "Inglés australiano", --TLCHANGE } m["en-GB"] = { "Ingles Britaniko", --TLCHANGE 7979, "en", english_name = "British English", --TLCHANGE spanish_name = "Inglés británico", --TLCHANGE } m["en-GB-SCT"] = { "Ingles Eskoses", --TLCHANGE 44676, "en-GB", english_name = "Scottish English", --TLCHANGE spanish_name = "Inglés escocés", --TLCHANGE } m["en-GB-WLS"] = { "Ingles Gales", --TLCHANGE 44676, "en-GB", english_name = "Welsh English", --TLCHANGE spanish_name = "Inglés galés", --TLCHANGE } m["en-IM"] = { "Ingles Manes", --TLCHANGE 6753295, "en-GB", english_name = "Manx English", --TLCHANGE spanish_name = "Inglés Manés", --TLCHANGE } m["en-aae"] = { "Ingles Katutubong Awstralyano", --TLCHANGE 783347, "en-AU", english_name = "Australian Aboriginal English", --TLCHANGE } m["en-ear"] = { "Ingles Modernong Maaga", --TLCHANGE 1472196, "en", ancestors = "enm", aliases = {"Early New English"}, english_name = "Early Modern English", --TLCHANGE spanish_name = "Inglés moderno temprano", --TLCHANGE } m["en-geo"] = { "Geordie", 653421, "en", ancestors = "enm-nor", } m["en-IE"] = { -- FIXME: "IE" doesn't cover Northern Ireland "Ingles Irlandes", --TLCHANGE 665624, "en", english_name = "Irish English", --TLCHANGE spanish_name = "Inglés irlandés", --TLCHANGE } m["en-uls"] = { "Ingles Ulster", --TLCHANGE 6840826, "en-IE", english_name = "Ulster English", --TLCHANGE spanish_name = "Inglés en Úlster", --TLCHANGE } m["en-GB-NIR"] = { "Ingles Hilagang Irlandes", --TLCHANGE 6840826, -- actually the code for Ulster English "en-uls", english_name = "Northern Irish English", --TLCHANGE } m["en-NNN"] = { -- NA = Namibia; NNN is NATO 3-letter code for North America "Ingles Hilagang Amerikano", --TLCHANGE 7053766, "en", ietf_subtag = "en-021", -- 021 = UN M49 code for "Northern America" (i.e. North America wihout Central America or the Caribbean) english_name = "North American English", --TLCHANGE spanish_name = "Inglés norteamericano", --TLCHANGE } m["en-US"] = { "Ingles Amerikano", --TLCHANGE 7976, "en-NNN", english_name = "American English", --TLCHANGE spanish_name = "Inglés americano", --TLCHANGE } m["en-NZ"] = { "Ingles Neozelandes", --TLCHANGE 44661, "en", english_name = "New Zealand English", --TLCHANGE spanish_name = "Inglés neozelandés", --TLCHANGE this specifically refers to New Zealand English, different from Nueva Zelanda } m["en-ZA"] = { "Ingles Timog Afrikano", --TLCHANGE 1156228, "en", english_name = "South African English", --TLCHANGE spanish_name = "Inglés sudafricano", --TLCHANGE } m["en-US-CA"] = { "Ingles Kalifornya", --TLCHANGE 1026812, "en-US", english_name = "California English", --TLCHANGE spanish_name = "Inglés de California", --TLCHANGE } m["en-CA"] = { "Ingles Kanadyense", --TLCHANGE 44676, "en-US", english_name = "Canadian English", --TLCHANGE spanish_name = "Inglés canadiense", --TLCHANGE } m["en-HK"] = { "Ingles Hong Kong", --TLCHANGE 1068863, "en", english_name = "Hong Kong English", --TLCHANGE spanish_name = "Inglés en Hong Kong", --TLCHANGE } m["en-IN"] = { "Ingles Indyo", --TLCHANGE 1348800, "en", english_name = "Indian English", --TLCHANGE spanish_name = "Inglés indio", --TLCHANGE } m["pld"] = { "Polari", 1359130, "en", } -- Scots varieties m["sco-ins"] = { "Insular Scots", 16919205, "sco", } m["sco-uls"] = { "Ulster Scots", 201966, "sco", } m["sco-nor"] = { "Northern Scots", 16928150, "sco", } m["sco-sou"] = { "Southern Scots", 7570457, "sco", aliases = {"South Scots", "Borders Scots"}, } -- Middle English varieties m["enm-esc"] = { -- Part of Middle English until it developed into Middle Scots. "Early Scots", 5326738, "enm", ancestors = "enm-nor", aliases = {"Old Scots", "Scottish Middle English"}, } m["enm-emi"] = { "East Midland Middle English", 134238810, "enm", ancestors = "ang-ang", -- Technically ang-mer, but attested Mercian is mostly WM IIRC } m["enm-ken"] = { "Kentish Middle English", 134238532, "enm", ancestors = "ang-ken", } m["enm-nor"] = { "Northern Middle English", 134238541, "enm", ancestors = "ang-nor", } m["enm-sou"] = { "Southern Middle English", 134238528, "enm", ancestors = "ang-wsx", } m["enm-wmi"] = { "West Midland Middle English", 134238824, "enm", ancestors = "ang-mer", } -- Old English varieties -- Includes both Mercian and Northumbrian. m["ang-ang"] = { "Anglian Old English", 121142917, "ang", } m["ang-ken"] = { "Kentish Old English", 11687485, "ang", } m["ang-mer"] = { "Mercian Old English", 602072, "ang-ang", } m["ang-nor"] = { "Northumbrian Old English", 1798915, "ang-ang", } m["ang-wsx"] = { "West Saxon Old English", 2658603, "ang", } ----------------------------------------------------- -- High German varieties -- ----------------------------------------------------- -- (modern) German varieties m["de-AT"] = { "Austrian German", 306626, "de", } m["de-AT-vie"] = { "Viennese German", 56474, "de-AT", } m["de-CH"] = { "Switzerland German", 1366643, "de", aliases = {"Schweizer Hochdeutsch", "Swiss Standard German", "Swiss High German"}, } m["de-bal"] = { "Baltic German", 15785413, "de", } m["de-ear"] = { "Aleman Mataas na Bago na Maaga", --TLCHANGE 1472199, "de", ancestors = "gmh", aliases = {"Early Modern High German"}, english_name = "Early New High German", --TLCHANGE } m["ksh"] = { "Kölsch", 4624, "gmw-cfr", } m["pfl"] = { "Palatine German", 23014, "gmw-rfr", aliases = {"Pfälzisch", "Pälzisch", "Palatinate German"}, } m["sli"] = { "Silesian East Central German", 152965, "gmw-ecg", aliases = {"Silesian"}, } m["sxu"] = { "Upper Saxon German", 699284, "gmw-ecg", } -- Old High German varieties m["lng"] = { "Lombardic", 35972, "goh", } -- Alemannic German varieties m["gsw-low"] = { "Low Alemannic German", 503724, "gsw", } m["gsw-FR-als"] = { "Alsatian Alemannic German", 8786, "gsw-low", } m["gsw-hig"] = { "High Alemannic German", 503728, "gsw", } m["gsw-hst"] = { "Highest Alemannic German", 687538, "gsw", } m["wae"] = { "Walser German", 680517, "gsw-hst", } ----------------------------------------------------- -- Low German varieties -- ----------------------------------------------------- m["nds-de"] = { "German Low German", 25433, "nds", ietf_subtag = "nds-DE", -- should we make this the actual code? wikimedia_codes = "nds", } m["nds-nl"] = { "Dutch Low Saxon", 516137, "nds", ietf_subtag = "nds-NL", -- should we make this the actual code? wikimedia_codes = "nds-nl", } m["act"] = { "Achterhoeks", 153627, "nds-nl", aliases = {"Achterhoek", "Achterhooks"}, } m["drt"] = { "Drents", 2736709, "nds-nl", aliases = {"Drèents", "Dreins", "Dreints", "Drints"}, } m["frs"] = { "East Frisian Low German", 149208, "nds-de", aliases = {"East Frisian", "East Frisian Low Saxon"}, } m["gos"] = { "Gronings", 508854, "nds-nl", aliases = {"Grunnegs", "Grönnegs"}, } m["nds-lpr"] = { "Low Prussian", 33982, "nds-de", } m["sdz"] = { "Sallands", 3436668, "nds-nl", aliases = {"Sallaans", "Sallaands"}, } m["stl"] = { "Stellingwerfs", 506010, "nds-nl", aliases = {"Stellingwarfs"}, } m["twd"] = { "Twents", 497363, "nds-nl", aliases = {"Tweants"}, } m["vel"] = { "Veluws", 2484810, "nds-nl", } m["wep"] = { "Westphalian", 505655, "nds-de", aliases = {"Westfalish", "Westphalien"}, } ----------------------------------------------------- -- North Frisian varieties -- ----------------------------------------------------- m["frr-ins"] = { "Insular North Frisian", 110629610, "frr", } m["frr-fam"] = { "Föhr-Amrum North Frisian", 110629601, "frr-ins", } m["frr-foh"] = { "Föhr North Frisian", 28185, "frr-fam", aliases = {"Föhr Frisian", "Fering", "Ferring", -- Glottolog }, varieties = {"Aasdring", "Weesdring"}, } m["frr-amr"] = { "Amrum North Frisian", 28192, "frr-fam", aliases = {"Amrum Frisian", "Amrum", "Öömrang"}, } m["frr-hel"] = { "Heligoland North Frisian", 28086, "frr-ins", aliases = {"Heligoland Frisian", "Halunder", "Heligolandic Frisian", "Heligolandic North Frisian", "Helgoland Frisian", "Helgoland North Frisian", "Helgoland"}, } m["frr-syl"] = { "Sylt North Frisian", 28181, "frr-ins", aliases = {"Sylt Frisian", "Söl'ring", "Sölreng", -- Glottolog }, } m["frr-mai"] = { "Mainland North Frisian", 110629626, "frr", } m["frr-hal"] = { "Halligen North Frisian", 28177, "frr-mai", aliases = {"Halligen Frisian", "Halifreesk", "Hallingen Frisian", "Hallingen North Frisian", "Hallingen", -- Glottolog }, } m["frr-moo"] = { "Mooring North Frisian", 28187, "frr-mai", aliases = {"Bökingharde North Frisian", "Bökingharde Frisian", "Böökinghiirder frasch", "Mooring", "Moring", }, varieties = {{"East Mooring", "Ostermooring"}, {"West Mooring", "Westermooring"}}, } m["frr-kar"] = { "Karrharde North Frisian", 28191, "frr-mai", aliases = {"Karrharde Frisian", "Karrharder", }, } m["frr-goe"] = { -- Technically this refers to three adjacent dialects (Northern, Central and Southern), the latter of which went -- extinct in 1980-1981. As a result, Glottolog speaks of "Norder-Mittelgoesharde", referring to the remaining two. "Goesharde North Frisian", 28183, "frr-mai", aliases = {"Norder-Mittelgoesharde North Frisian", "Norder-Mittelgoesharde Frisian", "Norder-Mittelgoesharde", "Goesharde Frisian", "Goesharde", "Gooshiirder", }, } m["frr-wie"] = { "Wiedingharde North Frisian", 28171, "frr-mai", aliases = {"Wiedingharde Frisian", "Wiedingharde", "Wiringhiirder freesk", }, } ----------------------------------------------------- -- Old Norse varieties -- ----------------------------------------------------- m["non-grn"] = { "Greenlandic Norse", 855236, "non-own", } m["non-oen"] = { "Old East Norse", 10498031, "non", ancestors = "non", } m["non-own"] = { "Old West Norse", 2377483, "non", ancestors = "non", } ----------------------------------------------------- -- Old Swedish varieties -- ----------------------------------------------------- m["gmq-osw-lat"] = { "Late Old Swedish", 10723594, "gmq-osw", ancestors = "gmq-osw", } -------------------------------------------------------------------------------------- -- Greek varieties -- -------------------------------------------------------------------------------------- m["qsb-grc"] = { "Pre-Greek", 965052, "und", family = "qfa-sub", } m["grc-aeo"] = { "Aeolic Greek", 406373, "grc", aliases = {"Lesbic Greek", "Lesbian Greek", "Aeolian Greek"}, } m["grc-arc"] = { "Arcadian Greek", nil, "grc-arp", } m["grc-arp"] = { "Arcadocypriot Greek", 499602, "grc", } m["grc-att"] = { "Attic Greek", 506588, "grc", } m["grc-boi"] = { "Boeotian Greek", 406373, "grc-aeo", } m["grc-dor"] = { "Doric Greek", 285494, "grc", } m["grc-ela"] = { "Elean Greek", nil, "grc", } m["grc-epc"] = { "Epic Greek", 990062, "grc", aliases = {"Homeric Greek"}, } m["grc-ion"] = { "Ionic Greek", 504165, "grc", } m["grc-koi"] = { "Koine Greek", 107358, "grc", ancestors = "grc-att", aliases = {"Hellenistic Greek"}, } m["grc-kre"] = { "Cretan Ancient Greek", -- to distinguish from Cretan Greek below nil, "grc-dor", } m["grc-opl"] = { "Opuntian Locrian", nil, "grc", } m["grc-ozl"] = { "Ozolian Locrian", nil, "grc", } m["grc-pam"] = { "Pamphylian Greek", 2271793, "grc", } m["grc-ths"] = { "Thessalian Greek", 406373, "grc-aeo", } m["gkm"] = { "Byzantine Greek", 36387, "grc", ancestors = "grc-koi", aliases = {"Medieval Greek"}, } m["el-cyp"] = { "Cypriot Greek", 245899, "el", aliases = {"Cypriotic Greek"}, } m["el-pap"] = { "Paphian Greek", nil, "el", } m["el-crt"] = { "Cretan Greek", 588306, "el", } m["el-kth"] = { "Katharevousa", 35961, "el", "Polyt", ancestors = "gkm", aliases = {"Katharevousa Greek"}, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["el-kal"] = { "Kaliarda", 12878658, "el", } -------------------------------------------------------------------------------------- -- Indo-Iranian varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Indo-Aryan varieties -- ------------------------------------------------------------------------- -- reconstructed intermediate stages m["pra-pro"] = { "Proto-New Indo-Aryan", nil, "pra", } m["inc-ash-pro"] = { "Proto-Middle Indo-Aryan", nil, "inc-ash", } m["inc-mit"] = { "Mitanni", 1986700, "inc-pro", } m["bra-old"] = { "Old Braj", nil, "bra", } -- Apabhramsas m["inc-aav"] = { "Avahattha", nil, "inc-apa", aliases = {"Abahattha"}, } m["inc-asa"] = { "Sauraseni Apabhramsa", nil, "inc-apa", } m["inc-agu"] = { "Gurjara Apabhramsa", nil, "inc-apa", } m["inc-aka"] = { "Kasmiri Apabhramsa", nil, "inc-apa", } m["inc-ama"] = { "Maharastri Apabhramsa", nil, "inc-apa", } m["inc-ata"] = { "Takka Apabhramsa", nil, "inc-apa", } m["inc-avr"] = { "Vracada Apabhramsa", nil, "inc-apa", } -- Assamese varieties m["as-bkm"] = { "Barpetia Kamrupi Assamese", 30642960, "as", } m["as-nkm"] = { "Nalbaria Kamrupi Assamese", 85787678, "as", } m["as-pkm"] = { "Palasbaria Kamrupi Assamese", nil, "as", } -- Bengali varieties m["bn-dvn"] = { "Dhakaiya Vaṅga Bengali", 48726851, "bn", -- Eastern Bengali variety } m["bn-nvn"] = { "Noakhailla Vaṅga Bengali", 107548681, "bn", -- Eastern Bengali variety } -- Dhivehi varieties m["dv-old"] = { "Old Dhivehi", 117790875, "dv", } m["dv-mul"] = { "Mulaku Dhivehi", nil, "dv", aliases = {"Mulaku Divehi", "Mulaku Bas"}, } m["dv-huv"] = { "Huvadhu Dhivehi", nil, "dv", aliases = {"Huvadhu Divehi", "Huvadhu Bas"}, } m["dv-add"] = { "Addu Dhivehi", nil, "dv", aliases = {"Addu Divehi", "Addu Bas"}, } -- Gujarati varieties m["gu-kat"] = { "Kathiyawadi", nil, "gu", aliases = {"Kathiyawadi Gujarati", "Kathiawadi"}, } m["gu-lda"] = { "Lisan ud-Dawat Gujarati", nil, "gu", aliases = {"Lisan ud-Dawat", "LDA"}, } -- Hindi varieties m["hi-mum"] = { "Bombay Hindi", 3543151, "hi", aliases = {"Mumbai Hindi", "Bambaiyya Hindi"}, } m["hi-mid"] = { "Middle Hindi", nil, "inc-ohi", ancestors = "inc-ohi", } -- Konkani varieties m["kok-mid"] = { "Middle Konkani", nil, "kok", aliases = {"Medieval Konkani"}, } m["kok-old"] = { "Old Konkani", nil, "kok", aliases = {"Early Konkani"}, } -- Prakrits m["pra-ard"] = { "Ardhamagadhi Prakrit", 35217, "pra", aliases = {"Ardhamagadhi"}, } m["pra-hel"] = { "Helu Prakrit", 15080869, "pra", aliases = {"Elu", "Elu Prakrit", "Helu"}, } m["pra-kha"] = { "Khasa Prakrit", nil, "pra", aliases = {"Khasa"}, } m["pra-mag"] = { "Magadhi Prakrit", -- Not to be confused with Magahi (mag) 2652214, "pra", aliases = {"Magadhi"}, } m["pra-mah"] = { "Maharastri Prakrit", 2586773, "pra", aliases = {"Maharashtri Prakrit", "Maharastri", "Maharashtri"}, } m["pra-pai"] = { "Paisaci Prakrit", 2995607, "pra-sau", aliases = {"Paisaci", "Paisachi"}, ancestors = "pra-sau" } m["pra-sau"] = { "Sauraseni Prakrit", 2452885, "pra", aliases = {"Sauraseni", "Shauraseni"}, } m["pra-ava"] = { "Avanti", nil, "pra", aliases = {"Avanti Prakrit"}, } m["pra-pra"] = { "Pracya", nil, "pra", aliases = {"Pracya Prakrit"}, } m["pra-bah"] = { "Bahliki", nil, "pra", aliases = {"Bahliki Prakrit"}, } m["pra-dak"] = { "Daksinatya", nil, "pra", aliases = {"Daksinatya Prakrit"}, } m["pra-sak"] = { "Sakari", nil, "pra", aliases = {"Sakari Prakrit"}, } m["pra-can"] = { "Candali", nil, "pra", aliases = {"Candali Prakrit"}, } m["pra-sab"] = { "Sabari", nil, "pra", aliases = {"Sabari Prakrit"}, } m["pra-abh"] = { "Abhiri", nil, "pra", aliases = {"Abhiri Prakrit"}, } m["pra-dra"] = { "Dramili", nil, "pra", aliases = {"Dramili Prakrit"}, } m["pra-odr"] = { "Odri", nil, "pra", aliases = {"Odri Prakrit"}, } -- Punjabi varieties m["pnb"] = { "Western Punjabi", 58635, "pa", "pa-Arab", } -- Sanskrit varieties m["vsn"] = { "Vedic Sanskrit", 36858, "sa", } m["cls"] = { "Classical Sanskrit", 11059, "sa", } m["sa-bhs"] = { "Buddhist Hybrid Sanskrit", 248758, "sa", } m["sa-bra"] = { "Brahmanic Sanskrit", 36858, "sa", } m["sa-neo"] = { "New Sanskrit", 11059, "sa", } -- Sinhalese varieties m["si-med"] = { "Medieval Sinhalese", nil, "si", aliases = {"Medieval Sinhala"}, } ------------------------------------------------------------------------- -- Iranian varieties -- ------------------------------------------------------------------------- m["qsb-bma"] = { "the BMAC substrate", 133187435, "und", family = "qfa-sub", aliases = {"the Bactria-Margiana substrate", "the Bactria-Margiana Archaeological Complex substrate"}, } -- Historical and current Iranian dialects m["ae-old"] = { "Old Avestan", 29572, "ae", aliases = {"Gathic Avestan"}, } m["ae-yng"] = { "Younger Avestan", 29572, "ae-old", aliases = {"Young Avestan"}, } m["bcc"] = { "Southern Balochi", 33049, "bal", aliases = {"Southern Baluchi"}, } m["bgp"] = { "Eastern Balochi", 33049, "bal", aliases = {"Eastern Baluchi"}, } m["bgn"] = { "Western Balochi", 33049, "bal", aliases = {"Western Baluchi"}, } m["bsg-ban"] = { "Bandari", nil, "bsg", } m["bsg-hor"] = { "Hormozi", nil, "bsg", } m["bsg-min"] = { "Minabi", nil, "bsg", } m["kho-old"] = { "Old Khotanese", nil, "kho", } m["kho-lat"] = { "Late Khotanese", nil, "kho-old", } m["peo-ear"] = { "Early Old Persian", nil, "peo", } m["peo-lat"] = { "Late Old Persian", nil, "peo", } m["pal-ear"] = { "Early Middle Persian", nil, "pal", } m["pal-lat"] = { "Late Middle Persian", nil, "pal", ancestors = "pal-ear", } m["ps-nwe"] = { "Northwestern Pashto", nil, "ps", } m["ps-cgi"] = { "Central Ghilzay", nil, "ps-nwe", } m["ps-mah"] = { "Mahsudi", nil, "ps-nwe", } m["ps-nea"] = { "Northeastern Pashto", nil, "ps", } m["ps-afr"] = { "Afridi", nil, "ps-nea", } m["ps-bng"] = { "Bangash", nil, "ps-nea", } m["ps-xat"] = { "Khatak", nil, "ps-nea", } m["ps-pes"] = { "Peshawari", nil, "ps-nea", } m["ps-sea"] = { "Timog Silanganing Pastun", --TLCHANGE nil, "ps", english_name = "Southeastern Pashto", --TLCHANGE } m["ps-ban"] = { "Bannu", nil, "ps-sea", } m["ps-kak"] = { "Kakari", nil, "ps-sea", } m["ps-ser"] = { "Sher", nil, "ps-sea", } m["ps-waz"] = { "Waziri", 12274473, "ps-sea", } m["ps-swe"] = { "Timog Kanluraning Pastun", --TLCHANGE nil, "ps", english_name = "Southwestern Pashto", --TLCHANGE } m["ps-kan"] = { "Kandahari", nil, "ps-swe", } m["ps-jad"] = { "Jadrani", nil, "ps", ancestors = "ira-pat-pro" } m["xme-azr"] = { "Old Azari", nil, "xme-ott", aliases = {"Old Azeri", "Azari", "Azeri", "Āḏarī", "Adari", "Adhari"}, } m["xme-ttc-cen"] = { "Central Tati", nil, "xme-ott", } m["xme-ttc-eas"] = { "Eastern Tati", nil, "xme-ott", } m["xme-ttc-nor"] = { "Northern Tati", nil, "xme-ott", } m["xme-ttc-sou"] = { "Southern Tati", nil, "xme-ott", } m["xme-ttc-wes"] = { "Western Tati", nil, "xme-ott", } m["xmn"] = { "Manichaean Middle Persian", nil, "pal-lat", } m["fa-ear"] = { "Early New Persian", 127413796, "fa", ancestors = "pal-lat", translit = "fa-cls-translit", } m["fa-cls"] = { "Classical Persian", 9168, "fa", ancestors = "fa-ear", translit = "fa-cls-translit", } m["fa-ira"] = { "Iranian Persian", 3513637, "fa", aliases = {"Modern Persian", "Western Persian"}, translit = "fa-ira-translit", } m["prs"] = { "Dari", 178440, "fa", aliases = {"Dari Persian", "Central Persian", "Eastern Persian", "Afghan Persian"}, translit = "fa-cls-translit", } m["haz"] = { "Hazaragi", 33398, "prs", translit = "fa-cls-translit", } m["os-dig"] = { "Digor Ossetian", 3027861, "os", aliases = {"Digoron", "Digor"}, } m["os-iro"] = { "Iron Ossetian", nil, "os", aliases = {"Iron"}, } m["sog-ear"] = { "Early Sogdian", nil, "sog", } m["sog-lat"] = { "Late Sogdian", nil, "sog-ear", } m["ro-MD"] = { "Moldavo", --TLCHANGE 36392, "ro", aliases = {"Moldavian"}, english_name = "Moldovan", --TLCHANGE spanish_name = "Moldavo", --TLCHANGE } m["oru-kan"] = { "Kaniguram", 6363164, "oru", } m["oru-log"] = { "Logar", nil, "oru", } m["oos"] = { "Old Ossetic", 65455882, "xln", } m["oos-ear"] = { "Early Old Ossetic", nil, "oos", } m["oos-lat"] = { "Late Old Ossetic", nil, "oos", } m["rdb-jir"] = { "Jirofti", nil, "rdb", } m["rdb-kah"] = { "Kahnuji", nil, "rdb", } -- Southwestern Fars lects m["fay-bur"] = { "Burenjani", nil, "fay", } m["fay-bsh"] = { "Bushehri", nil, "fay", } m["fay-dsh"] = { "Dashtaki", nil, "fay", } m["fay-dav"] = { "Davani", 5228140, "fay", } m["fay-eze"] = { "Emamzada Esmaili", nil, "fay", } m["fay-gav"] = { "Gavkoshaki", nil, "fay", } m["fay-kho"] = { "Khollari", nil, "fay", } m["fay-kon"] = { "Kondazi", nil, "fay", } m["fay-kzo"] = { "Old Kazeruni", nil, "fay", } m["fay-mas"] = { "Masarami", nil, "fay", } m["fay-pap"] = { "Papuni", nil, "fay", } m["fay-sam"] = { "Samghani", nil, "fay", } m["fay-shr"] = { "Shirazi", nil, "fay", } m["fay-sho"] = { "Old Shirazi", nil, "fay", } m["fay-kar"] = { "Khargi", nil, "fay", } m["fay-sor"] = { "Sorkhi", nil, "fay", } -- Talysh lects m["tly-cen"] = { "Central Talysh", nil, "tly", } m["tly-asa"] = { "Asalemi", nil, "tly-cen", } m["tly-kar"] = { "Karganrudi", nil, "tly-cen", } m["tly-tul"] = { "Tularudi", nil, "tly-cen", } m["tly-tal"] = { "Taleshdulabi", nil, "tly-cen", } m["tly-nor"] = { "Northern Talysh", nil, "tly", } m["tly-aze"] = { "Azerbaijani Talysh", nil, "tly-nor", } m["tly-anb"] = { "Anbarani", nil, "tly-nor", } m["tly-sou"] = { "Southern Talysh", nil, "tly", } m["tly-fum"] = { "Fumani", nil, "tly-sou", } m["tly-msu"] = { "Masulei", nil, "tly-sou", } m["tly-msa"] = { "Masali", nil, "tly-sou", } m["tly-san"] = { "Shandarmani", nil, "tly-sou", } -- Tafreshi lects m["xme-amo"] = { "Amorehi", nil, "xme-taf", } m["atn"] = { "Ashtiani", 3436590, "xme-taf", } m["xme-bor"] = { "Borujerdi", nil, "xme-taf", } m["xme-ham"] = { "Hamadani", 6302426, "xme-taf", } m["xme-kah"] = { "Kahaki", nil, "xme-taf", } m["vaf"] = { "Vafsi", 32611, "xme-taf", } -- Kermanic lects m["kfm"] = { "Khunsari", 6403030, "xme-ker", } m["xme-mah"] = { "Mahallati", nil, "xme-ker", } m["xme-von"] = { "Vonishuni", nil, "xme-ker", } m["xme-bdr"] = { "Badrudi", nil, "xme-ker", } m["xme-del"] = { "Delijani", nil, "xme-ker", } m["xme-kas"] = { "Kashani", nil, "xme-ker", } m["xme-kes"] = { "Kesehi", nil, "xme-ker", } m["xme-mey"] = { "Meymehi", nil, "xme-ker", } m["ntz"] = { "Natanzi", 6968399, "xme-ker", } m["xme-abz"] = { "Abuzeydabadi", nil, "xme-ker", } m["xme-aby"] = { "Abyanehi", nil, "xme-ker", } m["xme-far"] = { "Farizandi", nil, "xme-ker", } m["xme-jow"] = { "Jowshaqani", nil, "xme-ker", } m["xme-nas"] = { "Nashalji", nil, "xme-ker", } m["xme-qoh"] = { "Qohrudi", nil, "xme-ker", } m["xme-yar"] = { "Yarandi", nil, "xme-ker", } m["soj"] = { "Soi", 7930463, "xme-ker", aliases = {"Sohi"}, } m["xme-tar"] = { "Tari", nil, "xme-ker", } m["gzi"] = { "Gazi", 5529130, "xme-ker", } m["xme-sed"] = { "Sedehi", nil, "xme-ker", } m["xme-ard"] = { "Ardestani", nil, "xme-ker", } m["xme-zef"] = { "Zefrehi", nil, "xme-ker", } m["xme-isf"] = { "Isfahani", nil, "xme-ker", } m["xme-kaf"] = { "Kafroni", nil, "xme-ker", } m["xme-vrz"] = { "Varzenehi", nil, "xme-ker", } m["xme-xur"] = { "Khuri", nil, "xme-ker", } m["nyq"] = { "Nayini", 6983146, "xme-ker", } m["xme-ana"] = { "Anaraki", nil, "xme-ker", } m["gbz"] = { "Zoroastrian Dari", 32389, "xme-ker", aliases = {"Behdināni", "Gabri", "Gavrŭni", "Gabrōni"}, } m["xme-krm"] = { "Kermani", nil, "xme-ker", } m["xme-yaz"] = { "Yazdi", nil, "xme-ker", } m["xme-bid"] = { "Bidhandi", nil, "xme-ker", } m["xme-bij"] = { "Bijagani", nil, "xme-ker", } m["xme-cim"] = { "Chimehi", nil, "xme-ker", } m["xme-han"] = { "Hanjani", nil, "xme-ker", } m["xme-kom"] = { "Komjani", nil, "xme-ker", } m["xme-nar"] = { "Naraqi", nil, "xme-ker", } m["xme-nus"] = { "Nushabadi", nil, "xme-ker", } m["xme-qal"] = { "Qalhari", nil, "xme-ker", } m["xme-trh"] = { "Tarehi", nil, "xme-ker", } m["xme-val"] = { "Valujerdi", nil, "xme-ker", } m["xme-var"] = { "Varani", nil, "xme-ker", } m["xme-zor"] = { "Zori", nil, "xme-ker", } -- Ramandi lects m["tks-ebr"] = { "Ebrahimabadi", nil, "tks", } m["tks-sag"] = { "Sagzabadi", nil, "tks", } m["tks-esf"] = { "Esfarvarini", nil, "tks", } m["tks-tak"] = { "Takestani", nil, "tks", } m["tks-cal"] = { "Chali Tati", nil, "tks", aliases = {"Chāli"}, } m["tks-dan"] = { "Danesfani", nil, "tks", } m["tks-xia"] = { "Khiaraji", nil, "tks", } m["tks-xoz"] = { "Khoznini", nil, "tks", } -- Shughni dialects m["sgh-bro"] = { "Bartangi-Oroshori", nil, "sgh", } m["sgh-bar"] = { "Bartangi", nil, "sgh-bro", } m["sgh-oro"] = { "Oroshori", nil, "sgh-bro", aliases = {"Roshorvi"}, } m["sgh-rsx"] = { "Roshani-Khufi", nil, "sgh", } m["sgh-xuf"] = { "Khufi", 2562249, "sgh-rsx", aliases = {"Xufi", "Xūfī"}, } m["sgh-ros"] = { "Roshani", 2597566, "sgh-rsx", aliases = {"Rushani", "Rōšāni"}, } m["sgh-xgb"] = { "Khughni-Bajui", nil, "sgh", } m["sgh-xug"] = { "Khughni", nil, "sgh-xgb", } m["sgh-baj"] = { "Bajui", nil, "sgh-xgb", } ------------------------------------------------------------------------- -- Nuristani varieties -- ------------------------------------------------------------------------- m["bsh-kat"] = { "Kativiri", 2605045, "bsh", aliases = {"Katə́viri"}, } m["xvi"] = { "Kamviri", 1193495, "bsh", aliases = {"Kamvíri"}, } m["bsh-mum"] = { "Mumviri", nil, "bsh", aliases = {"Mumvíri"}, } -------------------------------------------------------------------------------------- -- Italic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Latin varieties -- ------------------------------------------------------------------------- -- Latin varieties by period m["itc-ola"] = { "Old Latin", 12289, "la", "Latn, Ital", translit = { Ital = "Ital-translit" }, } m["itc-lan"] = { "Lanuvian", 16890829, "itc-ola", aliases = {"Lanuvine"}, } m["itc-pra"] = { "Praenestine", 16889772, "itc-ola", aliases = {"Praenestinian"}, } m["la-cla"] = { "Classical Latin", 253854, "la", } m["la-vul"] = { "Vulgar Latin", 37560, "la-cla", } m["la-afr"] = { "African Romance", 162064, "roa-pro", } m["la-lat"] = { "Late Latin", 1503113, "la", ancestors = "la-cla", } m["la-med"] = { "Medieval Latin", 1163234, "la", ancestors = "la-lat", } m["la-eme"] = { "Early Medieval Latin", nil, "la-med", } m["la-ecc"] = { "Ecclesiastical Latin", 1247932, "la", aliases = {"Church Latin", "Liturgical Latin"}, ancestors = "la-lat", } m["la-ren"] = { "Renaissance Latin", 499083, "la", ancestors = "la-med", } m["la-new"] = { "New Latin", 1248221, "la", aliases = {"Modern Latin"}, ancestors = "la-ren", } m["la-con"] = { "Contemporary Latin", 1246397, "la-new", } ------------------------------------------------------------------------- -- Miscellaneous Italic varieties -- ------------------------------------------------------------------------- m["xfa-cap"] = { "Capenate", 133182969, "xfa", } m["osc-luc"] = { "Lucanian", 3265025, "osc", } m["osc-sam"] = { "Samnite", 133184287, "osc", } ------------------------------------------------------------------------- -- Romance varieties -- ------------------------------------------------------------------------- m["roa-pro"] = { "Proto-Romance", 3408029, "la-lat", ancestors = "la-vul", } ----------------------------------------------------- -- Catalan varieties -- ----------------------------------------------------- m["ca-val"] = { "Valencian", 32641, "ca", } ----------------------------------------------------- -- Franco-Provençal varieties -- ----------------------------------------------------- m["frp-old"] = { "Old Franco-Provençal", nil, "frp", } ----------------------------------------------------- -- French and derived creole varieties -- ----------------------------------------------------- m["fro-nor"] = { "Old Northern French", 2044917, "fro", aliases = {"Old Norman", "Old Norman French"}, } m["fro-pic"] = { "Picard Old French", nil, "fro", } m["xno"] = { "Anglo-Norman", 35214, "fro-nor", } m["xno-law"] = { "Law French", 2044323, "xno", } m["zrp"] = { "Zarphatic", 36994, "fro", aliases = {"Judeo-French"}, pseudo_families = "qfa-jew", } m["fr-CA"] = { "Canadian French", 1450506, "fr", } m["fr-CH"] = { "Swiss French", 1480152, "fr", } m["fr-aca"] = { "Acadian French", 415109, "fr", } m["fr-lou"] = { "Louisiana French", 3083213, "fr", } m["fr-mis"] = { "Missouri French", 3083210, "fr", } m["frc"] = { "Cajun French", 880301, "fr-lou", } m["ht-sdm"] = { "Saint Dominican Creole French", nil, "ht", ancestors = "fr", } -- Norman varieties m["nrf-grn"] = { "Guernsey Norman", 56428, "nrf", aliases = {"Guernsey"}, } m["nrf-jer"] = { "Jersey Norman", 56430, "nrf", aliases = {"Jersey"}, } ----------------------------------------------------- -- Gallo-Italic varieties -- ----------------------------------------------------- m["egl-old"] = { "Old Emilian", nil, "egl", } m["lij-old"] = { "Old Ligurian", nil, "lij", aliases = {"Old Genoese"}, } m["lmo-old"] = { "Old Lombard", 97165320, "lmo", } m["pms-old"] = { "Old Piedmontese", nil, "pms", aliases = {"Old Piemontese"}, } m["vec-old"] = { "Old Venetan", nil, "vec", aliases = {"Old Venetian"}, } m["rgn-old"] = { "Old Romagnol", nil, "rgn", } ----------------------------------------------------- -- Italo-Romance varieties -- ----------------------------------------------------- -- Italian varieties m["roa-oit"] = { "Old Italian", nil, "it", } m["it-CH"] = { "Switzerland Italian", 672147, "it", } -- Other Italo-Romance varieties m["nap-old"] = { "Old Neapolitan", nil, "nap", } m["scn-old"] = { "Old Sicilian", nil, "scn", } ----------------------------------------------------- -- Occitan varieties -- ----------------------------------------------------- m["oc-auv"] = { "Auvergnat", 35359, "oc", aliases = {"Auvernhat", "Auvergnese"}, } m["oc-gas"] = { "Gaskón", --TLCHANGE 35735, "oc", english_name = "Gascon", --TLCHANGE spanish_name = "Gascón", --TLCHANGE } -- standardized dialect of Gascon m["oc-ara"] = { "Aranes", --TLCHANGE 10196, "oc-gas", english_name = "Aranese", --TLCHANGE spanish_name = "Aranés", --TLCHANGE } m["oc-lan"] = { "Languedocien", 942602, "oc", aliases = {"Lengadocian"}, } m["oc-lim"] = { "Limousin", 427614, "oc", } m["oc-pro"] = { "Provençal", 241243, "oc", aliases = {"Provencal"}, } m["oc-pro-old"] = { "Old Provençal", 2779185, "pro", } m["oc-viv"] = { "Vivaro-Alpine", 1649613, "oc", } m["oc-jud"] = { "Shuadit", 56472, "oc", aliases = { "Chouhadite", "Chouhadit", "Chouadite", "Chouadit", "Shuhadit", "Judeo-Occitan", "Judæo-Occitan", "Judaeo-Occitan", "Judeo-Provençal", "Judæo-Provençal", "Judaeo-Provençal", "Judeo-Provencal", "Judaeo-Provencal", "Judeo-Comtadin", "Judæo-Comtadin", "Judaeo-Comtadin", }, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Portuguese and derived creole varieties -- ----------------------------------------------------- -- Portuguese m["pt-BR"] = { "Brazilian Portuguese", 750553, "pt", } m["pt-PT"] = { "European Portuguese", 922399, "pt", } -- Kabuverdianu (Cape Verde Creole, Cape Verdean Creole) m["kea-bar"] = { "Barlavento Kabuverdianu", 2217638, "kea", aliases = {"Barlavento", "Barlavento Creole", "Sampadjudu"}, } m["kea-bvi"] = { "Boa Vista Kabuverdianu", 16501837, "kea-bar", aliases = {"Boa Vista Creole"}, } m["kea-sal"] = { "Sal Kabuverdianu", 18707467, "kea-bar", aliases = {"Sal Creole"}, } m["kea-saa"] = { "Santo Antão Kabuverdianu", 18707472, "kea-bar", aliases = {"Santo Antão Creole"}, } m["kea-sni"] = { "São Nicolau Kabuverdianu", 18707549, "kea-bar", aliases = {"São Nicolau Creole"}, } m["kea-svi"] = { "São Vicente Kabuverdianu", 18707550, "kea-bar", aliases = {"São Vicente Creole"}, } m["kea-sot"] = { "Sotavento Kabuverdianu", 10261559, "kea", aliases = {"Sotavento", "Sotavento Creole", "Badiu"}, } m["kea-bra"] = { "Brava Kabuverdianu", 18670181, "kea-sot", aliases = {"Brava Creole"}, } m["kea-fog"] = { "Fogo Kabuverdianu", 18706861, "kea-sot", aliases = {"Fogo Creole"}, } m["kea-mai"] = { "Maio Kabuverdianu", 18707286, "kea-sot", aliases = {"Maio Creole"}, } m["kea-san"] = { "Santiago Kabuverdianu", 35117, "kea-sot", aliases = {"Santiago Creole"}, } m["kea-alu"] = { "ALUPEC Kabuverdianu", 375704, "kea", aliases = {"ALUPEC", "Alfabeto Unificado para a Escrita do Cabo-Verdiano"}, } ----------------------------------------------------- -- Rhaeto-Romance varieties -- ----------------------------------------------------- -- Friulian varieties m["fur-old"] = { "Old Friulian", nil, "fur", } -- Ladin varieties m["lld-amp"] = { "Ampezan Ladin", 25617466, "lld", aliases = {"Anpezan", "Ampezan", "Ampezzan", "Ampezzano"}, } m["lld-bad"] = { "Badiot Ladin", 3706562, "lld", aliases = {"Badiot", "Badioto", "Badiotto"}, } m["lld-cad"] = { "Cadorino Ladin", 3706570, "lld", aliases = {"Cadorino"}, } m["lld-fas"] = { "Fascian Ladin", 742627, "lld", aliases = {"Fascian", "Fassano"}, } m["lld-fod"] = { "Fodom Ladin", 3706605, "lld", aliases = {"Fodom", "Livinallese"}, } m["lld-for"] = { "Fornes Ladin", 5470374, "lld", aliases = {"Fornes"}, } m["lld-ghe"] = { "Gherdëina Ladin", 3706597, "lld", aliases = {"Gherdëina", "Gardenese", "Val Gardena"}, } m["lld-non"] = { "Nones Ladin", 1055027, "lld", aliases = {"Nones", "Noneso"}, } -- Romansh varieties m["rm-old"] = { "Old Romansh", nil, "rm", } m["rm-put"] = { "Puter Romansh", 688309, "rm", aliases = {"Puter", "Putèr", "Upper Engadine", "rm-puter"}, } m["rm-srm"] = { "Surmiran Romansh", 690216, "rm", aliases = {"Surmiran", "rm-surmiran", "Surmiran-Albula", -- Glottolog }, } m["rm-srs"] = { "Sursilvan Romansh", 688348, "rm", aliases = {"Sursilvan", "rm-sursilv"}, } m["rm-sut"] = { "Sutsilvan Romansh", 688272, "rm", aliases = {"Sutsilvan", "rm-sutsilv"}, varieties = {"Scharans Sutsilvan"}, -- per Glottolog } m["rm-val"] = { "Vallader Romansh", 690226, "rm", aliases = {"Vallader", "Putèr", "Lower Engadine", "rm-vallader"}, } m["rm-gri"] = { "Rumantsch Grischun", 688873, "rm", aliases = {"rm-rumgr"}, } ----------------------------------------------------- -- Sardinian varieties -- ----------------------------------------------------- m["sc-old"] = { "Old Sardinian", nil, "sc", } m["sc-src"] = { "Logudorese", 777974, "sc", aliases = {"Logudorese Sardinian"}, } m["sc-nuo"] = { "Nuorese", nil, "sc-src", aliases = {"Nuorese Sardinian"}, } m["sc-sro"] = { "Campidanese", 35348, "sc", aliases = {"Campidanese Sardinian"}, } ----------------------------------------------------- -- Spanish varieties -- ----------------------------------------------------- m["es-ear"] = { "Espanyol Modernong Maaga", --TLCHANGE 5364419, "es", english_name = "Early Modern Spanish", --TLCHANGE spanish_name = "Español moderno temprano", --TLCHANGE } m["es-AR"] = { "Rioplatense Spanish", 509780, "es", } m["es-BO"] = { "Bolivian Spanish", 510730, "es", } m["es-CL"] = { "Chilean Spanish", 857295, "es", } m["es-CO"] = { "Colombian Spanish", 1115875, "es", } m["es-CU"] = { "Cuban Spanish", 824909, "es", } m["es-MX"] = { "Mexican Spanish", 616620, "es", } m["es-PE"] = { "Peruvian Spanish", 736236, "es", } m["es-PH"] = { "Espanyol Pilipino", --TLCHANGE 22091406, "es", english_name = "Philippine Spanish", --TLCHANGE spanish_name = "Español filipino", --TLCHANGE } m["es-US"] = { "Espanyol Estados Unidos", --TLCHANGE 2301077, "es", aliases = {"US Spanish"}, english_name = "United States Spanish", --TLCHANGE spanish_name = "Español en Estados Unidos", --TLCHANGE } --use label "US Spanish" to put Spanish terms in this category m["es-PR"] = { "Puerto Rican Spanish", 7258609, "es", } m["es-VE"] = { "Venezuelan Spanish", 840017, "es", } m["es-lun"] = { "Lunfardo", 1401612, "es", } ---------------------------------------------------------------------------------------------------------------------- -- Japonic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Japanese varieties m["ja-mid"] = { "Gitnang Hapones", --TLCHANGE 6841474, "ojp", ancestors = "ojp", english_name = "Middle Japanese", --TLCHANGE } m["ja-mid-ear"] = { "Hapones Gitnang Maaga", --TLCHANGE 182695, "ja-mid", english_name = "Early Middle Japanese", --TLCHANGE } m["ja-mid-lat"] = { "Late Middle Japanese", 1816184, "ja-mid", ancestors = "ja-mid-ear", } m["ja-ear"] = { "Hapones Modernong Maaga", --TLCHANGE 5326692, "ja", ancestors = "ja-mid-lat", english_name = "Early Modern Japanese", --TLCHANGE } m["ojp-eas"] = { "Hapones Lumang Silanganin", --TLCHANGE 65247957, "ojp", english_name = "Eastern Old Japanese", --TLCHANGE } m["ja-cla"] = { "Hapones Klasikal", --TLCHANGE 1332057, "ja", -- FIXME: This is redundant because Classical Japanese is considered a child of (Modern) Japanese, which has ja-mid-ear -- (as well as ja-mid-lat) as ancestors. However, the intent here is that the *direct* ancestor of ja-cla is ja-mid-ear -- and ja-mid-lat is not an ancestor. Need to rethink ancestor handling. -- ancestors = "ja-mid-ear", english_name = "Classical Japanese", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Koreanic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Korean varieties m["oko-lat"] = { "Late Old Korean", nil, "oko", } m["okm-ear"] = { "Early Middle Korean", nil, "okm", } m["ko-cen"] = { "Koreano Sentral", --TLCHANGE nil, "ko", english_name = "Central Korean", --TLCHANGE } m["ko-gyg"] = { "Koreano Gyeonggi", --TLCHANGE 485492, "ko-cen", aliases = {"Seoul Korean"}, english_name = "Gyeonggi Korean", --TLCHANGE } m["ko-chu"] = { "Koreano Chungcheong", --TLCHANGE 625800, "ko-cen", aliases = {"Hoseo Korean"}, english_name = "Chungcheong Korean", --TLCHANGE } m["ko-hwa"] = { "Koreano Hwanghae", --TLCHANGE 16183706, "ko-cen", english_name = "Hwanghae Korean", --TLCHANGE } m["ko-gan"] = { "Koreano Yeongdong", --TLCHANGE 11260444, "ko-cen", aliases = {"Yeongdong Korean"}, english_name = "Gangwon Korean", --TLCHANGE } m["ko-gys"] = { "Koreano Gyeongsang", --TLCHANGE 488002, "ko", aliases = {"Southeastern Korean"}, english_name = "Gyeongsang Korean", --TLCHANGE } m["ko-jeo"] = { "Koreano Jeolla", --TLCHANGE 11250166, "ko", aliases = {"Southwestern Korean"}, english_name = "Jeolla Korean", --TLCHANGE } m["ko-pyo"] = { "Koreano Pyongan", --TLCHANGE 7263142, "ko", aliases = {"Northwestern Korean"}, english_name = "Pyongan Korean", --TLCHANGE } m["ko-ham"] = { "Koreano Hamgyong", --TLCHANGE 860702, "ko", aliases = {"Northeastern Korean"}, english_name = "Hamgyong Korean", --TLCHANGE } m["ko-yuk"] = { "Koreano Yukjin", --TLCHANGE 16171275, "ko", aliases = {"Yukchin Korean", "Ryukjin Korean", "Ryukchin Korean"}, english_name = "Yukjin Korean", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Mongolic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["xng-ear"] = { "Early Middle Mongol", nil, "xng", } m["xng-lat"] = { "Late Middle Mongol", nil, "xng", ancestors = "xng-ear", } m["mn-kha"] = { "Khalkha Mongolian", 6399808, "mn", aliases = {"Khalkha"}, } m["mn-ord"] = { "Ordos Mongolian", 716904, "mn", aliases = {"Ordos"}, } m["mn-cha"] = { "Chakhar Mongolian", 907425, "mn", aliases = {"Chakhar"}, } m["mn-khr"] = { "Khorchin Mongolian", 3196210, "mn", aliases = {"Khorchin"}, } ---------------------------------------------------------------------------------------------------------------------- -- Niger-Congo varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akan varieties -- ----------------------------------------------------- m["tw"] = { "Twi Akan", 36850, "ak", aliases = {"Twi"}, } m["abr"] = { "Abron", 34831, "tw", aliases = {"Brong", "Bono", "Bono Twi"}, } m["tw-asa"] = { "Asante Twi", 19261685, "tw", aliases = {"Asante", "Ashanti", "Ashante"}, } m["tw-aku"] = { "Akuapem Twi", 31150449, "tw", aliases = {"Akuapem", "Akuapim", "Akwapem Twi", "Akwapi"}, } m["fat"] = { "Fante Akan", 35570, "ak", aliases = {"Fante", "Fanti", "Fantse", "Mfantse"}, } m["wss"] = { "Wasa", 36914, "ak", } -- creole m["alv-kro"] = { "Kromanti", 1093206, "crp-mar", } ----------------------------------------------------- -- Bantu varieties -- ----------------------------------------------------- m["bnt-cmn"] = { "Common Bantu", nil, "bnt-pro", } m["xh-bha"] = { "Bhaca", 4900493, "xh", aliases = {"isiBhaca", "IsiBhaca"}, } -- Rwanda-Rundi varieties m["rw-kin"] = { "Kinyarwanda", 33573, "rw", aliases = {"Rwanda"}, } m["rw-run"] = { "Kirundi", 33583, "rw", aliases = {"Rundi"}, } ----------------------------------------------------- -- Fula varieties -- ----------------------------------------------------- m["fuc"] = { "Pulaar", 1420205, "ff", } m["fuf"] = { "Pular", 3915357, "ff", } m["ffm"] = { "Maasina Fulfulde", 3915322, "ff", } m["fue"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Borgu Fulfulde", 12952426, "ff", } m["fuh"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Western Niger Fulfulde", 12952430, "ff", } m["fuq"] = { -- no enwiki entry as of yet but frwiki, hrwiki and pmswiki have one "Central-Eastern Niger Fulfulde", 12628799, "ff", } m["fuv"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki and swwiki have one "Nigerian Fulfulde", 36129, "ff", } m["fub"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki, ptwiki, swwiki and yowiki have one "Adamawa Fulfulde", 34776, "ff", } m["fui"] = { -- no enwiki entry as of yet but pmswiki and swwiki have one "Bagirmi Fulfulde", 11003859, "ff", } ---------------------------------------------------------------------------------------------------------------------- -- Papuan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["kze"] = { "Kosena", 12952663, "auy", } m["ont"] = { "Ontenu", 3352827, "gaj", aliases = {"Ontena"}, } ---------------------------------------------------------------------------------------------------------------------- -- Salishan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["lut-nor"] = { "Northern Lushootseed", nil, "lut", aliases = {"Northern Puget Sound Salish"}, } m["slh"] = { "Southern Lushootseed", 7997684, "lut", aliases = {"Southern Puget Sound Salish", "Twulshootseed", "Whulshootseed"}, } m["ska"] = { "Skagit", 12642471, "lut-nor", } m["sno"] = { "Snohomish", 25559662, "lut-nor", } ---------------------------------------------------------------------------------------------------------------------- -- Sino-Tibetan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["tbq-pro"] = { "Proto-Tibeto-Burman", 7251864, "sit-pro", } ----------------------------------------------------- -- Chinese varieties -- ----------------------------------------------------- ------------- Old Chinese, Middle Chinese ------------- m["och-ear"] = { "Tsino Lumang Maaga", --TLCHANGE nil, "och", english_name = "Early Old Chinese", --TLCHANGE } m["och-lat"] = { "Late Old Chinese", nil, "och", } m["ltc-ear"] = { "Tsino Gitnang Maaga", --TLCHANGE nil, "ltc", english_name = "Early Middle Chinese", --TLCHANGE } m["ltc-lat"] = { "Late Middle Chinese", nil, "ltc", } ------------- Classical/Literary varieties ------------- -- FIXME: Temporary. m["lzh-shi"] = { "Traditional Chinese poetry", 1759242, "lzh", } -- FIXME: Temporary. m["lzh-cii"] = { "Ci", 1091366, "lzh", } -- FIXME: Temporary. m["lzh-yue"] = { "Classical Cantonese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn"] = { "Classical Mandarin", nil, "lzh", } -- FIXME: Temporary. m["lzh-tai"] = { "Classical Taishanese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn-TW"] = { "Classical Taiwanese Mandarin", nil, "lzh-cmn", } -- FIXME: Temporary. m["lzh-VI"] = { "Vietnamese Classical Chinese", 17034227, "lzh", } -- FIXME: Temporary. m["lzh-KO"] = { "Korean Classical Chinese", 10496257, "lzh", ietf_subtag = "lzh-KR" -- KR = South Korea, as there is no code for Korea as a whole } -- FIXME: Temporary. m["lzh-lit"] = { "Literary Chinese", nil, "lzh", } -- FIXME: Temporary. FIXME: Do we need this? How does it differ from Old Chinese? m["lzh-pre"] = { "Pre-Classical Chinese", nil, "lzh", } ------------- Written Vernacular varieties ------------- -- FIXME: Temporary. m["cmn-wvc"] = { "Written vernacular Mandarin", 783605, "cmn", } -- FIXME: Temporary. FIXME: How does this differ from "Literary Cantonese"? m["yue-wvc"] = { "Written vernacular Cantonese", nil, "yue", } -- FIXME: Temporary. m["zhx-tai-wvc"] = { "Written vernacular Taishanese", nil, "zhx-tai", } ------------- Mandarin varieties ------------- -- FIXME: Temporary. NOTE: The Linguist List assigns the "w:Beijing dialect" (Wikidata 1147606) the code "cmn-bej" and -- the larger "w:Beijing Mandarin (division of Mandarin)" dialect group (Wikidata 2169652; what we call "Beijingic -- Mandarin", after Glottolog) the code "cmn-bei". m["cmn-bei"] = { "Beijing Mandarin", 1147606, "cmn-bec", } -- FIXME: Temporary. m["cmn-bec"] = { "Beijingic Mandarin", 2169652, "cmn", } -- FIXME: Temporary. NOTE: The Linguist List uses the code cmn-zho. m["cmn-cep"] = { "Central Plains Mandarin", 3048775, "cmn", aliases = {"Zhongyuan Mandarin"}, } m["cmn-ear"] = { "Early Mandarin", 837169, "cmn", ancestors = "ltc", } -- FIXME: Temporary. m["cmn-gua"] = { "Guanzhong Mandarin", 3431648, "cmn-cep", } -- FIXME: Temporary. Appears to be a subdialect of Guiliu Mandarin, which in turn is a subdialect of Southwestern Mandarin. m["cmn-gui"] = { "Guilin Mandarin", 11111636, "cmn-sow", } m["cmn-jhu"] = { "Jianghuai Mandarin", 2128953, "cmn", aliases = {"Lower Yangtze Mandarin"}, } -- FIXME: Temporary. m["cmn-lan"] = { "Lanyin Mandarin", 662754, "cmn", } -- FIXME: Temporary. m["cmn-MY"] = { "Malaysian Mandarin", 13646143, "cmn", } -- FIXME: Temporary. m["cmn-nan"] = { "Nanjing Mandarin", 2681098, "cmn-jhu", } -- FIXME: Temporary. m["cmn-noe"] = { "Northeastern Mandarin", 1064504, "cmn", } -- FIXME: Temporary. m["cmn-PH"] = { "Philippine Mandarin", 7185155, "cmn", } -- FIXME: Temporary. m["cmn-SG"] = { "Singapore Mandarin", 1048980, "cmn", } -- FIXME: Temporary. m["cmn-sow"] = { "Southwestern Mandarin", 2609239, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Jilu Mandarin. m["cmn-tia"] = { "Tianjin Mandarin", 7800220, "cmn", } -- FIXME: Temporary. NOTE: Wikidata also has Q4380827 "Taiwanese Mandarin", defined as "rare dialect of Standard Chinese -- (Mandarin) used in Taiwan, which is strongly influenced by Taiwanese Hokkien; mostly used by elderlies" and having no -- English Wikipedia article (but see w:zh:臺灣國語). m["cmn-TW"] = { "Taiwanese Mandarin", 262828, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Wu-Tian Mandarin, in turn a subdialect of Southwestern Mandarin. -- Given the code cmn-xwu in the Linguist List. m["cmn-wuh"] = { "Wuhan Mandarin", 11124731, "cmn-sow", aliases = {"Wuhanese"}, } -- FIXME: Temporary. Appears to be a subdialect of Lanyin Mandarin. m["cmn-xin"] = { "Xining Mandarin", nil, "cmn-lan", } -- FIXME: Temporary. m["cmn-yan"] = { "Yangzhou Mandarin", nil, "cmn-jhu", } ------------- Cantonese varieties ------------- -- FIXME: Temporary. m["yue-gua"] = { "Guangzhou Cantonese", nil, "yue", } -- FIXME: Temporary. Given the codes yue-yue or yue-can in the Linguist List. m["yue-HK"] = { "Hong Kong Cantonese", 5894342, "yue", } -- FIXME: Temporary. FIXME: How does this differ from "Written vernacular Cantonese"? m["yue-lit"] = { "Literary Cantonese", 2472605, "yue", } ------------- Wu varieties ------------- m["wuu-han"] = { "Hangzhounese", 5648144, "wuu", } m["wuu-nin"] = { "Ningbonese", 3972199, "wuu", } -- FIXME: Temporary. m["wuu-nor"] = { "Northern Wu", 7675988, "wuu", aliases = {"Taihu Wu"}, } -- FIXME: Temporary? Subvariety of Taihu Wu. NOTE: "chm" stands for Chongming, the main dialect, to avoid a conflict -- with Shanghainese. m["wuu-chm"] = { "Shadi Wu", 6112340, "wuu-nor", } m["wuu-sha"] = { "Shanghainese", 36718, "wuu-nor", } m["wuu-suz"] = { "Suzhounese", 831744, "wuu-nor", } -- FIXME: Temporary. May be converted into a full language and/or split. m["wuu-wen"] = { "Wenzhounese", 710218, "wuu", } ------------- Xiang varieties ------------- m["hsn-lou"] = { "Loudi Xiang", 10943823, "hsn-old", } m["hsn-hya"] = { "Hengyang Xiang", 20689035, "hsn-hzh", } m["hsn-hzh"] = { "Hengzhou Xiang", nil, "hsn", } m["hsn-new"] = { "New Xiang", 7012696, "hsn", aliases = {"Chang-Yi"}, } m["hsn-old"] = { "Old Xiang", 7085453, "hsn", aliases = {"Lou-Shao"}, } ------------- Hakka varieties ------------- -- FIXME: Temporary. m["hak-dab"] = { "Dabu Hakka", 19855566, "hak", -- formerly hak-TW but seems to be spoken primary in Dabu County in Guangdong } -- FIXME: Temporary. m["hak-eam"] = { "Early Modern Hakka", nil, "hak", } -- FIXME: Temporary. m["hak-hai"] = { "Hailu Hakka", 17038519, "hak", -- often considered a Taiwanese lect but also spoken in [[Shanwei]], [[Guangdong]] } -- FIXME: Temporary. m["hak-HK"] = { "Hong Kong Hakka", 2675834, "hak", } -- FIXME: Temporary. m["hak-hui"] = { "Huiyang Hakka", 16873881, "hak", } -- FIXME: Temporary. m["hak-hui-MY"] = { "Malaysian Huiyang Hakka", nil, "hak-hui", } -- FIXME: Temporary. Similar to and possibly the parent of Sixian Hakka in Taiwan. m["hak-mei"] = { "Meixian Hakka", 839295, "hak", aliases = {"Moiyan Hakka", "Meizhou Hakka"}, } -- FIXME: Temporary. m["hak-six"] = { "Sixian Hakka", 9668261, "hak-TW", } -- FIXME: Temporary. m["hak-TW"] = { "Taiwanese Hakka", 2391532, "hak", } -- FIXME: Temporary. m["hak-zha"] = { "Zhao'an Hakka", 6703311, "hak", aliases = {"Zhangzhou Hakka"}, } -- Southern Min varieties -- m["nan-anx"] = { "Anxi Hokkien", 97064149, "nan-qua", } m["nan-cha"] = { "Changtai Hokkien", nil, "nan-zha", } m["nan-hou"] = { "Houlu Min", 19855492, "nan-dat", } m["nan-hui"] = { "Hui'an Hokkien", 16241797, "nan-qua", } m["nan-jin"] = { "Jinjiang Hokkien", 11089375, "nan-qua", } m["nan-kin"] = { "Kinmenese Hokkien", 56278342, "nan-xia", aliases = {"Kinmen Hokkien"}, } m["nan-med"] = { "Medan Hokkien", 6805114, "nan-zha", } m["nan-pen"] = { "Penang Hokkien", 11120689, "nan-zha", } m["nan-hbl-PH"] = { "Philippine Hokkien", 3236692, "nan-qua", } m["nan-qia"] = { "Qianlu Min", 19842517, "nan-dat", } m["nan-qua"] = { "Quanzhou Hokkien", 2251677, "nan-hbl", aliases = {"Chinchew", "Choanchew"}, } -- FIXME: Temporary? Derived from both Quanzhou and Zhangzhou Hokkien. m["nan-hbl-SG"] = { "Singapore Hokkien", 3846528, "nan-hbl", } m["nan-spm"] = { "Southern Malaysian Hokkien", 7570322, "nan-qua", aliases = {"Southern Malaysia Hokkien", "Southern Peninsular Malaysian Hokkien", "Southern Peninsular Malaysia Hokkien"} } m["nan-hbl-TW"] = { "Taiwanese Hokkien", 36778, "nan-hbl", } m["nan-ton"] = { "Tong'an Hokkien", nil, "nan-xia", } m["nan-xia"] = { "Xiamen Hokkien", 68744, "nan-hbl", aliases = {"Amoy", "Amoyese", "Amoynese", "Xiamenese"}, } m["nan-yon"] = { "Yongchun Hokkien", 65118728, "nan-qua", } m["nan-zha"] = { "Zhangzhou Hokkien", 8070492, "nan-hbl", aliases = {"Changchew", "Chiangchew", "Changchow"}, } m["nan-zho"] = { "Zhao'an Hokkien", 65118728, "nan-zha", aliases = {"Zhao'an", "Chawan", "Chawan Hokkien"}, } m["nan-zhp"] = { "Zhangping Hokkien", 15937822, "nan-zha", } ------------- Other Min varieties ------------- -- FIXME: Temporary. Affiliation within Min uncertain; some combination of Eastern and Southern. m["zhx-zho"] = { "Zhongshan Min", 8070958, "zh", } ------------- Other Chinese varieties ------------- -- FIXME: Temporary. Affiliation within Chinese uncertain; possibly Yue. m["zhx-dan"] = { "Danzhou Chinese", 2578935, "zh", } ------------- Chinese romanization varieties ------------- -- [[Wiktionary:Information desk/2022/June#Etymology Coding Issue]] -- [[Wiktionary:Grease pit/2022/June#Transliteration Systems in Etymologies 2]] m["cmn-pinyin"] = { "Hanyu Pinyin", 42222, "cmn", aliases = {"Pinyin"}, } m["cmn-tongyong"] = { "Tongyong Pinyin", 700739, "cmn", } m["cmn-wadegiles"] = { "Wade–Giles", 208442, "cmn", aliases = {"Wade-Giles", "Wade Giles"}, } m["zh-postal"] = { "Postal Romanization", 151868, "zh", } -- Chinese cyrillization m["cmn-palladius"] = { "Palladius", 1234239, "cmn", aliases = {"Palladius system"}, } ----------------------------------------------------- -- Tibetic varieties -- ----------------------------------------------------- m["adx"] = { "Amdo Tibetan", 56509, "bo", } m["kbg"] = { "Khamba", 12952626, "bo", } m["khg"] = { "Khams Tibetan", 56601, "bo", } m["tsk"] = { "Tseku", 11159532, "bo", } ---------------------------------------------------------------------------------------------------------------------- -- Tai-Kadai varieties -- ---------------------------------------------------------------------------------------------------------------------- m["th-old"] = { "Old Thai", nil, "tai-swe-pro", wikipedia_article = "Thai language#Old Thai", } m["th-suk"] = { "Sukhothai Old Thai", -- 1238-1438. Cannot use "Sukhothai Thai" as Sukhothai is the current city and "Sukhothai Thai" is a lect. nil, "th-old", aliases = {"Sukhothai Siamese"}, wikipedia_article = "Thai language#Old Thai", } m["th-ayu"] = { "Ayutthaya Old Thai", -- 1351-1767. Cannot use "Ayutthaya Thai" as Ayutthaya is the current city. nil, "th-old", aliases = {"Ayutthaya Siamese"}, wikipedia_article = "Thai language#Old Thai", } --[[ m["th-new"] = { "Hacked Thai", -- temporary for testing new translit/display methods nil, "th", translit = "User:Benwing2/th-scraping-translit", display_text = "User:Benwing2/th-scraping-translit", strip_diacritics = "User:Benwing2/th-scraping-translit", preprocess_links = "User:Benwing2/th-scraping-translit", } ]] m["tai-shz"] = { "Shangsi Zhuang", 13216, "za", } ---------------------------------------------------------------------------------------------------------------------- -- Turkic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["trk-cmn-pro"] = { "Proto-Common Turkic", 1126028, "trk-pro", } m["trk-ogr-pro"] = { "Proto-Oghur", 1422731, "trk-pro", family = "trk-ogr", } m["trk-bul-pro"] = { "Proto-Bulgar", nil, "trk-ogr-pro", } m["trk-ogz-pro"] = { "Proto-Oghuz", 494600, "trk-pro", family = "trk-ogz", aliases = {"Southwestern Common Turkic"}, } m["crh-dbj"] = { "Dobrujan Tatar", 12811566, "crh", aliases = {"Romanian Tatar"}, } m["cv-ana"] = { "Anatri Chuvash", nil, "cv", aliases = {"Anatri", "Lower Chuvash"}, } m["cv-mid"] = { "Middle Chuvash", nil, "cv", ancestors = "cv-old", } m["cv-old"] = { "Old Chuvash", nil, "cv", ancestors = "xbo-vol", } m["cv-vir"] = { "Viryal Chuvash", 4278332, "cv", aliases = {"Viryal", "Upper Chuvash"}, } m["kjh-fyu"] = { "Fuyu Kyrgyz", 2598963, "kjh", aliases = {"Fuyu Kirgiz", "Fuyu Kirghiz", "Manchurian Kyrgyz", "Manchurian Kirgiz", "Manchurian Kirghiz"}, } m["klj-arg"] = { "Arghu", 33455, "klj", ancestors = "trk-cmn-pro", } m["otk-kir"] = { "Old Kirghiz", 83142, "otk", aliases = {"Yenisei Turkic", "Yenisei Kyrgyz"}, } m["otk-ork"] = { "Orkhon Turkic", 31295480, "otk", } m["qwm-cum"] = { "Cuman", 1075050, "qwm", aliases = {"Kuman", "Polovtsian", "Polovcian"}, } m["qwm-arm"] = { "Armeno-Kipchak", 2027503, "qwm", ancestors = "qwm-cum", aliases = {"Xıpçaχ tili", "Tatarça"}, } m["qwm-mam"] = { "Mamluk-Kipchak", 4279942, "qwm", aliases = {"Mameluk-Kipchak"}, } m["az-cls"] = { "Azeri Klasikal", --TLCHANGE nil, "az", aliases = {"Classical Azeri"}, english_name = "Classical Azerbaijani", --TLCHANGE } m["qxq"] = { "Qashqai", 13192, "az", aliases = {"Qaşqay", "Qashqayi", "Kashkai", "Kashkay"}, } m["tr-CY"] = { "Cypriot Turkish", 7917392, "tr", } m["uz-afg"] = { -- NOTE: has ISO 639-3 code uzs assigned to it. "Afghan Uzbek", 1066787, "uz", aliases = {"Southern Uzbek"}, translit = "uz-afg-translit", } m["xbo-dan"] = { "Danube Bulgar", nil, "xbo", } m["xbo-vol"] = { "Volga Bulgar", nil, "xbo", } ---------------------------------------------------------------------------------------------------------------------- -- Uralic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["fiu-pro"] = { "Proto-Finno-Ugric", 79890, "urj-pro", } m["urj-fpr-pro"] = { "Proto-Finno-Permic", nil, "urj-pro", } m["krl-nor"] = { "North Karelian", 125501196, "krl", } m["krl-sou"] = { "South Karelian", 129812730, "krl", } m["mns-eas"] = { "Eastern Mansi", 30311755, "mns-cen", } m["mns-wes"] = { "Western Mansi", 30311756, "mns-cen", } ---------------------------------------------------------------------------------------------------------------------- -- Yeneseian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["qfa-yke-pro"] = { "Proto-Ketic", nil, "qfa-yen-pro", family = "qfa-yke", } m["qfa-yko-pro"] = { "Proto-Kottic", nil, "qfa-yen-pro", family = "qfa-yko", } m["qfa-yrn-pro"] = { "Proto-Arinic", nil, "qfa-yen-pro", family = "qfa-yrn", } m["qfa-ypm-pro"] = { "Proto-Pumpokolic", nil, "qfa-yen-pro", family = "qfa-ypm", } ---------------------------------------------------------------------------------------------------------------------- -- Miscellaneous varieties -- ---------------------------------------------------------------------------------------------------------------------- m["mul-tax"] = { "taxonomic name", 522190, "mul", } ----------------------------------------------------- -- Elamite varieties -- ----------------------------------------------------- m["elx-old"] = { "Old Elamite", nil, "elx", } m["elx-mid"] = { "Middle Elamite", nil, "elx", } m["elx-neo"] = { "Neo-Elamite", nil, "elx", } m["elx-ach"] = { "Achaemenid Elamite", nil, "elx", } ----------------------------------------------------- -- Substrates -- ----------------------------------------------------- -- Pre-Roman substrates m["qsb-ibe"] = { "Paleo-Hispanic", 246801, "und", family = "qfa-sub", aliases = {"Palaeo-Hispanic", "Paleohispanic", "Palaeohispanic", "Paleo-Iberian", "Palaeo-Iberian"}, } m["qsb-bal"] = { "Paleo-Balkan", 1815070, "und", family = "qfa-sub", aliases = {"Palaeo-Balkan", "Paleobalkan", "Palaeobalkan"}, } m["xaq"] = { "Aquitanian", 500522, "euq-pro", family = "euq", } -- TLCHANGE add these stuff BELOW THIS ----------------------------------------------------- -- Philippine languages varieties -- ----------------------------------------------------- --- Tagalog varieties, as per https://kwfwikaatkultura.ph/tagalog-2/ m["tl-nor"] = { "Kahilagaang Tagalog", nil, "tl", english_name = "Northern Tagalog", } m["tl-cen"] = { "Tagalog Sentral", nil, "tl", english_name = "Central Tagalog", } m["tl-sou"] = { "Katimugang Tagalog", 838580, "tl", english_name = "Southern Tagalog", } -- province codes based on https://en.wikipedia.org/wiki/ISO_3166-2:PH m["tl-bul"] = { "Tagalog Bulacan", 123900044, "tl-nor", aliases = {"Tagalog Bulakenyo", "Tagalog Bulakeño"}, english_name = "Bulacan Tagalog", } m["tl-ban"] = { "Tagalog Bataan", nil, "tl-nor", aliases = {"Tagalog Batanense"}, english_name = "Bataan Tagalog", } m["tl-nue"] = { "Tagalog Nueva Ecija", nil, "tl-nor", english_name = "Nueva Ecija Tagalog", } m["tl-aur"] = { "Tagalog Aurora", nil, "tl-sou", english_name = "Aurora Tagalog", } m["tl-riz"] = { "Tagalog Rizal", nil, "tl-cen", aliases = {"Tagalog Rizalenyo", "Tagalog Rizaleño"}, english_name = "Rizal Tagalog", } m["tl-cav"] = { "Tagalog Cavite", 97255128, "tl-sou", aliases = {"Tagalog Kabitenyo", "Tagalog Caviteño"}, english_name = "Cavite Tagalog", } m["tl-lag"] = { "Tagalog Laguna", nil, "tl-sou", aliases = {"Tagalog Lagunense"}, english_name = "Laguna Tagalog", } m["tl-btg"] = { "Tagalog Batangas", 4868610, "tl-sou", aliases = {"Tagalog Batanggenyo", "Tagalog Batangueño"}, english_name = "Batangas Tagalog", } m["tl-que"] = { "Tagalog Quezon", nil, "tl-sou", english_name = "Quezon Tagalog", } m["tl-mdo"] = { --made-up code "mdo" "Tagalog Mindoro", nil, "tl-sou", english_name = "Mindoro Tagalog", } m["tl-mad"] = { "Tagalog Marinduque", nil, "tl-sou", aliases = {"Tagalog Marindukenyo", "Tagalog Marinduqueño"}, english_name = "Marinduque Tagalog", } m["tl-can"] = { "Tagalog Camarines Norte", nil, "tl-sou", english_name = "Camarines Norte Tagalog", } -- other variants m["tl-bag"] = { "Tagalog Baguio", nil, "tl", english_name = "Baguio Tagalog", } m["tl-zho"] = { "Tagalog Tsinoy", nil, "tl", english_name = "Chinese Filipino Tagalog", } -------------- --- Ilocano varieties from https://kwfwikaatkultura.ph/ilokano/ m["ilo-nor"] = { "Ilokano Amianan", nil, "ilo", } m["ilo-sou"] = { "Ilokano Abagatan", nil, "ilo", } m["ilo-cvy"] = { "Ilokano Cagayan Valley", nil, "ilo", } m["ilo-car"] = { "Ilokano Kaigorotan", nil, "ilo", } -------------- --- Sebwano varieties from https://kwfwikaatkultura.ph/sebwano-2/ m["ceb-min"] = { "Binisayang Mindanaw", nil, "ceb", english_name = "Mindanao Cebuano", } m["ceb-min"] = { "Binul-anong Binisaya", nil, "ceb", english_name = "Boholano Cebuano", } m["ceb-sle"] = { "Katimugang Leyte Binisaya", nil, "ceb", english_name = "Southern Leyte Cebuano", } m["ceb-ner"] = { "Negrensing Binisaya", nil, "ceb", english_name = "Negros Cebuano", } m["ceb-mas"] = { "Masbatenyong Binisaya", nil, "ceb", english_name = "Negros Cebuano", } m["ceb-sig"] = { "Binisayang Siquijor", nil, "ceb", english_name = "Siquijor Cebuano", } -------------- --- Tinagbanwa varieties from https://kwfwikaatkultura.ph/ortograpiyang-tinagbanwa/ m["tbk-bat"] = { "Batuwanën", nil, "tbk", } m["tbk-sug"] = { "S̃ug̓udnun", nil, "tbk", } m["tbk-pul"] = { "Puluwanën", nil, "tbk", } -- TLCHANGE END ----------------------------------------------------- return require("Module:languages").finalizeData(m, "language", true) c58gx9yokouhbwedyti38pi9jxggw8b 176313 176309 2026-04-14T02:03:39Z Yivan000 4078 176313 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 = {} ---------------------------------------------------------------------------------------------------------------------- -- Afroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Berber varieties -- -------------------------------------------------------------------------------------- m["shi-med"] = { "Medieval Tashelhit", 34152, "shi", } -- Tuareg lects m["thv"] = { "Tamahaq", 56703, "tmh", } m["ttq"] = { "Tawellemmet", 56390, "tmh", } m["taq"] = { "Tamasheq", 4670066, "tmh", } m["thz"] = { "Tayert", 56388, "tmh", } m["thv-ght"] = { "Ghat", 47012900, "thv", } -------------------------------------------------------------------------------------- -- Cushitic varieties -- -------------------------------------------------------------------------------------- -- Oromo varieties m["hae"] = { "Harar Oromo", 5330355, "om", aliases = {"Eastern Oromo"}, } m["gax"] = { "Borana", 2910610, "om", aliases = {"Southern Oromo"}, } m["orc"] = { "Orma", 2919128, "om", } m["ssn"] = { "Waata", 3501553, "om", } -------------------------------------------------------------------------------------- -- Egyptian varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Ancient Egyptian varieties -- ----------------------------------------------------- m["egy-old"] = { "Old Egyptian", 447117, "egy", } m["egy-mid"] = { "Middle Egyptian", 657330, "egy", aliases = {"Classical Egyptian"}, } m["egy-nmi"] = { "Neo-Middle Egyptian", 123735278, "egy", aliases = {"Égyptien de tradition", "Traditional Egyptian"}, } m["egy-lat"] = { "Late Egyptian", 1852329, "egy", } ----------------------------------------------------- -- Coptic varieties -- ----------------------------------------------------- m["cop-akh"] = { "Akhmimic Coptic", 125176464, "cop", aliases = {"Akhmimic"}, } m["cop-boh"] = { "Bohairic Coptic", 890733, "cop", aliases = {"Bohairic", "Memphitic Coptic", "Memphitic"}, } m["cop-ggg"] = { "Coptic Dialect G", nil, "cop", aliases = {"Dialect G", "Mansuric Coptic", "Mansuric"}, } m["cop-jjj"] = { "Coptic Dialect J", nil, "cop", } m["cop-kkk"] = { "Coptic Dialect K", nil, "cop", } m["cop-ppp"] = { "Coptic Dialect P", nil, "cop", aliases = {"Proto-Theban Coptic", "Palaeo-Theban Coptic"}, } m["cop-fay"] = { "Fayyumic Coptic", 1399115, "cop", aliases = {"Fayyumic", "Faiyumic Coptic", "Faiyumic", "Fayumic Coptic", "Fayumic", "Bashmuric Coptic", "Bashmuric"}, } m["cop-her"] = { "Hermopolitan Coptic", nil, "cop", aliases = {"Hermopolitan", "Coptic Dialect H", "Ashmuninic", "Ashmuninic Coptic"}, } m["cop-lyc"] = { "Lycopolitan Coptic", nil, "cop", aliases = { "Lycopolitan", "Assiutic Coptic", "Asyutic Coptic", "Assiutic", "Asyutic", "Lyco-Diospolitan Coptic", "Lyco-Diospolitan", "Subakhmimic Coptic", "Subakhmimic" }, } m["cop-old"] = { "Old Coptic", 115518040, "cop", } m["cop-oxy"] = { "Oxyrhynchite Coptic", nil, "cop", aliases = {"Oxyrhynchite", "Mesokemic Coptic", "Mesokemic", "Middle Egyptian Coptic"}, } m["cop-ply"] = { "Proto-Lycopolitan Coptic", nil, "cop", aliases = {"Coptic Dialect i", "Proto-Lyco-Diospolitan Coptic"}, } m["cop-sah"] = { "Sahidic Coptic", 2645851, "cop", aliases = {"Sahidic", "Saidic Coptic", "Saidic", "Thebaic Coptic", "Thebaic"}, } -------------------------------------------------------------------------------------- -- Semitic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akkadian varieties -- ----------------------------------------------------- m["akk-old"] = { "Old Akkadian", nil, "akk", } m["akk-obb"] = { "Old Babylonian", nil, "akk", } m["akk-oas"] = { "Old Assyrian", nil, "akk", } m["akk-mbb"] = { "Middle Babylonian", nil, "akk", } m["akk-mas"] = { "Middle Assyrian", nil, "akk", } m["akk-nbb"] = { "Neo-Babylonian", nil, "akk", } m["akk-nas"] = { "Neo-Assyrian", nil, "akk", } m["akk-lbb"] = { "Late Babylonian", nil, "akk", } m["akk-stb"] = { "Standard Babylonian", nil, "akk", } ----------------------------------------------------- -- Arabic varieties -- ----------------------------------------------------- m["jrb"] = { "Hudeoarabe", --TLCHANGE 37733, "ar", pseudo_families = "qfa-jew", english_name = "Judeo-Arabic", --TLCHANGE spanish_name = "Judeoárabe", --TLCHANGE } m["apc-leb"] = { "Arabe Hilagang Levantino Libanes", --TLCHANGE 1516642, "apc", aliases = {"Lebanese Arabic"}, english_name = "Lebanese North Levantine Arabic", --TLCHANGE } m["apc-sle"] = { "Arabe Hilagang Levantino Timog Libanes", --TLCHANGE 14206590, "apc", aliases = {"South Lebanese Arabic"}, english_name = "South Lebanese North Levantine Arabic", --TLCHANGE } m["apc-nle"] = { "Arabe Hilagang Levantino Hilagang Libanes", --TLCHANGE nil, "apc", aliases = {"North Lebanese Arabic"}, english_name = "North Lebanese North Levantine Arabic", --TLCHANGE } m["apc-syr"] = { "Arabe Hilagang Levantino Siryo", --TLCHANGE 2143071, "apc", aliases = {"Syrian Arabic"}, english_name = "Syrian North Levantine Arabic", --TLCHANGE } m["apc-ale"] = { "Arabe Hilagang Levantino Alepino", --TLCHANGE 7056921, "apc-syr", aliases = {"Aleppo Arabic", "Aleppine Arabic"}, english_name = "Aleppine North Levantine Arabic", --TLCHANGE } m["apc-dam"] = { "Arabe Hilagang Levantino Damaseno", --TLCHANGE 12237466, "apc-syr", aliases = {"Damascus Arabic", "Damascene Arabic"}, english_name = "Damascene North Levantine Arabic", --TLCHANGE } m["acm-khu"] = { "Arabe Huzestani", --TLCHANGE 1040944, "acm", english_name = "Khuzestani Arabic", --TLCHANGE spanish_name = "Árabe juzestaní", --TLCHANGE } ----------------------------------------------------- -- Aramaic varieties -- ----------------------------------------------------- m["arc-bib"] = { "Biblical Aramaic", 843235, "arc", family = "sem-are", } m["arc-cpa"] = { "Christian Palestinian Aramaic", 60790119, "arc", family = "sem-arw", aliases = {"Melkite Aramaic", "Palestinian Syriac", "Syropalestinian Aramaic"}, } m["arc-imp"] = { "Imperial Aramaic", 7079491, "arc", aliases = {"Official Aramaic"}, } m["arc-hat"] = { "Hatran Aramaic", 3832926, "arc", family = "sem-are", } m["arc-jla"] = { "Jewish Literary Aramaic", 105952842, "arc", pseudo_families = "qfa-jew", } m["arc-nab"] = { "Nabataean Aramaic", 36178, "arc", } m["arc-old"] = { "Lumang Arameas", --TLCHANGE 3398392, "arc", english_name = "Old Aramaic", --TLCHANGE } m["arc-pal"] = { "Palmyrene Aramaic", 1510113, "arc", family = "sem-arw", } m["tmr"] = { "Jewish Babylonian Aramaic", 33407, "arc", family = "sem-ase", pseudo_families = "qfa-jew", } m["jpa"] = { "Jewish Palestinian Aramaic", 948909, "arc", family = "sem-arw", aliases = {"Galilean Aramaic"}, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Hebrew varieties -- ----------------------------------------------------- m["hbo"] = { "Biblical Hebrew", 1982248, "he", aliases = {"Classical Hebrew"}, } m["he-mis"] = { "Mishnaic Hebrew", 1649362, "he", ancestors = "hbo", } m["he-med"] = { "Medieval Hebrew", 2712572, "he", ancestors = "he-mis", } m["he-IL"] = { "Israeli Hebrew", 8141, "he", } ---------------------------------------------------------------------------------------------------------------------- -- Ainu varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ain-hok"] = { "Hokkaido Ainu", 20968488, "ain", aliases = {"Hokkaidō Ainu"}, } m["ain-kur"] = { "Kuril Ainu", 20967012, "ain", } m["ain-sak"] = { "Sakhalin Ainu", 20747371, "ain", } ---------------------------------------------------------------------------------------------------------------------- -- American indigenous varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Inuit varieties -- ----------------------------------------------------- m["esi"] = { "North Alaskan Inupiatun", nil, "ik" } m["esk"] = { "Northwest Alaskan Inupiatun", 25559714, "ik" } ----------------------------------------------------- -- Iroquoian varieties -- ----------------------------------------------------- m["iro-ohu"] = { "Old Wendat", nil, "wdt", } m["iro-omo"] = { "Old Mohawk", nil, "moh", } m["iro-oon"] = { "Old Onondaga", nil, "ono", } ----------------------------------------------------- -- Tupi-Guarani varieties -- ----------------------------------------------------- -- Old Tupi varieties m["tpw-lga"] = { "Língua Geral Amazônica", 18275323, "tpw", aliases = {"Língua Geral"}, } m["tpw-lgp"] = { "Língua Geral Paulista", 2669239, "tpw", } ---------------------------------------------------------------------------------------------------------------------- -- Austroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Khmer varieties m["okz-ang"] = { "Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } m["okz-pre"] = { "Pre-Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } -- Central Nicobarese varieties m["ncb-cam"] = { "Camorta", 5026908, "ncb", aliases = {"Kamorta"}, } m["ncb-kat"] = { "Katchal", 17064263, "ncb", aliases = {"Tehnu"}, } m["ncb-nan"] = { "Nancowry", 6962504, "ncb", aliases = {"Nankwari"}, } ---------------------------------------------------------------------------------------------------------------------- -- Austronesian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Malay and related varieties m["ms-old"] = { -- this has the ISO code 'omy' "Lumang Malayo", --TLCHANGE nil, "ms", english_name = "Old Malay", --TLCHANGE } m["ms-cla"] = { "Malay Klasikal", --TLCHANGE nil, "ms", ancestors = "ms-old", english_name = "Classical Malay", --TLCHANGE } m["pse-bsm"] = { "Besemah", nil, "pse", } m["bew-kot"] = { "Betawi Kota", nil, "bew", aliases = {"Urban Betawi"}, -- in Jakarta } -- Philippine varieties m["xnn"] = { "Kankanaëy Aplay", --TLCHANGE 12953609, "kne", aliases = {"Northern Kankanay", "Northern Kankana-ey"}, is_official_kwf_name = "https://kwfwikaatkultura.ph/kankanaey/", --TLCHANGE english_name = "Northern Kankanay" --TLCHANGE } m["tl-old"] = { "Lumang Tagalog", --TLCHANGE 12967437, "tl", english_name = "Old Tagalog", --TLCHANGE } m["tl-cls"] = { "Tagalog Klasikal", --TLCHANGE nil, "tl", english_name = "Classical Tagalog", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Caucasian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Kartvelian varieties m["ka-mid"] = { "Middle Georgian", nil, "ka", ancestors = "oge", } ---------------------------------------------------------------------------------------------------------------------- -- Dravidian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ta-mid"] = { "Middle Tamil", 20987434, "ta", } m["kn-hav"] = { "Havigannada", 24276369, "kn", } m["kn-kun"] = { "Kundagannada", 6444255, "kn", } ---------------------------------------------------------------------------------------------------------------------- -- Indo-European varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Albanian varieties -- -------------------------------------------------------------------------------------- m["aln"] = { "Gheg Albanian", 181037, "sq", aliases = {"Gheg"}, } m["aae"] = { "Arbëresh Albanian", 1075302, "als", aliases = {"Arbëreshë", "Arbëresh"}, } m["aat"] = { "Arvanitika Albanian", 29347, "als", aliases = {"Arvanitika"}, } m["als"] = { "Tosk Albanian", 180937, "sq", aliases = {"Tosk"}, } -------------------------------------------------------------------------------------- -- Armenian varieties -- -------------------------------------------------------------------------------------- m["hyw"] = { "Western Armenian", 180945, "hy", } m["hye"] = { "Eastern Armenian", 181059, "hy", } -------------------------------------------------------------------------------------- -- Balto-Slavic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Baltic varieties -- ------------------------------------------------------------------------- m["bat-pro"] = { "Proto-Baltic", 1703347, "ine-bsl-pro", } m["bat-dni"] = { "Dnieper Baltic", 4163178, "bat-pro", family = "bat", aliases = {"Dniepr Baltic", "Dnieper-Oka Baltic", "Dniepr-Oka Baltic"}, } m["bat-gol"] = { "Golyad", 4142855, "bat-dni", aliases = {"Eastern Galindian", "East Galindian"}, } ------------------------------------------------------------------------- -- Slavic varieties -- ------------------------------------------------------------------------- ----------------------------------------------------- -- Bulgarian varieties -- ----------------------------------------------------- m["cu-bgm"] = { "Middle Bulgarian", 12294897, "cu", ancestors = "cu" } ----------------------------------------------------- -- Church Slavonic varieties -- ----------------------------------------------------- -- Old Moscow Church Slavonic deleted as it seems not distinct enough from Russian (Synodal) Church Slavonic. m["zls-chs-ru"] = { "Russian Church Slavonic", 21662400, "zls-chs", aliases = {"Synodal Church Slavonic", "New Moscow Church Slavonic", "Novomoskovsk Church Slavonic"}, } m["zls-chs-uk"] = { "Ukrainian Church Slavonic", 12153548, "zls-chs", aliases = {"Rusyn Church Slavonic", "Belarusian Church Slavonic"}, } --[=[ -- Not sure about these yet. m["zls-chs-bg"] = { "Bulgarian Church Slavonic", nil, "zls-chs", } m["zls-chs-cs"] = { "Czech Church Slavonic", nil, "zls-chs", } m["zls-chs-hr"] = { "Croatian Church Slavonic", nil, "zls-chs", } m["zls-chs-mk"] = { "Macedonian Church Slavonic", nil, "zls-chs", } m["zls-chs-ro"] = { "Romanian Church Slavonic", nil, "zls-chs", } m["zls-chs-sr"] = { "Serbian Church Slavonic", nil, "zls-chs", } ]=] ----------------------------------------------------- -- Czech varieties -- ----------------------------------------------------- m["cs-ear"] = { "Early Modern Czech", nil, "cs", ancestors = "zlw-ocs" } ----------------------------------------------------- -- East Slavic varieties -- ----------------------------------------------------- m["zle-ops"] = { "Old Pskovian", 4167885, "zle-ono", } m["zle-mru"] = { "Middle Russian", 35228, "ru", "Cyrs", ancestors = "orv", translit = "ru-translit", strip_diacritics = { Cyrs = { remove_diacritics = c.grave .. c.acute .. c.diaer, }, }, } m["zle-mbe"] = { "Middle Belarusian", 13211, "zle-ort", } m["zle-muk"] = { "Middle Ukrainian", 13211, "zle-ort", } m["uk-CA"] = { "Canadian Ukrainian", 4161010, "uk", } ----------------------------------------------------- -- Polish varieties -- ----------------------------------------------------- m["zlw-mpl"] = { "Gitnang Polako", --TLCHANGE 402878, "pl", ancestors = "zlw-opl", strip_diacritics = { remove_diacritics = c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ó", "ó", "Ś", "ś", "Ź", "ź"}, }, english_name = "Middle Polish", --TLCHANGE } m["pl-gre"] = { "Greater Polish", 4106789, "pl", } m["pl-les"] = { "Lesser Polish", 361709, "pl", } m["pl-mas"] = { "Masovian Polish", 4274559, "pl", } m["pl-gor"] = { "Goral", 452889, "pl", } ----------------------------------------------------- -- Serbo-Croatian varieties -- ----------------------------------------------------- m["ckm"] = { "Serbokroata Tsakavo", --TLCHANGE 337565, "sh", aliases = {"Čakavian"}, english_name = "Chakavian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata chakavo", --TLCHANGE } m["kjv"] = { "Serbokroata Kaykavo", --TLCHANGE 838165, "sh", english_name = "Kajkavian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata kajkavo", --TLCHANGE } m["sh-tor"] = { -- Linguist code srp-tor "Serbokroata Torlak", --TLCHANGE 1078803, "sh", aliases = {"Torlak"}, english_name = "Torlakian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata torlak", --TLCHANGE } -------------------------------------------------------------------------------------- -- Celtic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Brythonic varieties -- ----------------------------------------------------- m["bry-ear"] = { "Early Brythonic", nil, "cel-bry-pro", } m["bry-lat"] = { "Late Brythonic", nil, "cel-bry-pro", } ----------------------------------------------------- -- Gaulish varieties -- ----------------------------------------------------- m["xcg"] = { "Cisalpine Gaulish", 3832927, "cel-gau", } m["xtg"] = { "Transalpine Gaulish", 29977, "cel-gau", } ----------------------------------------------------- -- Welsh varieties -- ----------------------------------------------------- m["cy-nor"] = { "North Wales Welsh", 13127692, "cy", aliases = {"North Walian Welsh", "Northern Welsh"}, } m["cy-sou"] = { "South Wales Welsh", 13127689, "cy", aliases = {"South Walian Welsh", "Southern Welsh"}, } -------------------------------------------------------------------------------------- -- Germanic varieties -- -------------------------------------------------------------------------------------- -- Proto-West Germanic varieties m["frk"] = { "Frankish", 10860505, "gmw-pro", family = "gmw-frk", aliases = {"Old Frankish"}, } m["gem-sue"] = { "Suevic", 134600275, "gmw-pro", aliases = {"Suebian"}, } m["gmw-afr-pro"] = { "Proto-Anglo-Frisian", 134603379, "gmw-nsg-pro", family = "gmw-afr", } m["gmw-nsg-pro"] = { "Proto-North Sea Germanic", 134603374, "gmw-pro", family = "gmw-nsg", aliases = {"Proto-Ingvaeonic"}, } ----------------------------------------------------- -- Dutch varieties -- ----------------------------------------------------- m["nl-BE"] = { "Belgian Dutch", 34147, "nl", aliases = {"Flemish", "Flemish Dutch", "Southern Dutch"}, } ----------------------------------------------------- -- English and Scots varieties -- ----------------------------------------------------- -- English varieties m["en-AU"] = { "Ingles Awstralyano", --TLCHANGE 44679, "en", english_name = "Australian English", --TLCHANGE spanish_name = "Inglés australiano", --TLCHANGE } m["en-GB"] = { "Ingles Britaniko", --TLCHANGE 7979, "en", english_name = "British English", --TLCHANGE spanish_name = "Inglés británico", --TLCHANGE } m["en-GB-SCT"] = { "Ingles Eskoses", --TLCHANGE 44676, "en-GB", english_name = "Scottish English", --TLCHANGE spanish_name = "Inglés escocés", --TLCHANGE } m["en-GB-WLS"] = { "Ingles Gales", --TLCHANGE 44676, "en-GB", english_name = "Welsh English", --TLCHANGE spanish_name = "Inglés galés", --TLCHANGE } m["en-IM"] = { "Ingles Manes", --TLCHANGE 6753295, "en-GB", english_name = "Manx English", --TLCHANGE spanish_name = "Inglés Manés", --TLCHANGE } m["en-aae"] = { "Ingles Katutubong Awstralyano", --TLCHANGE 783347, "en-AU", english_name = "Australian Aboriginal English", --TLCHANGE } m["en-ear"] = { "Ingles Modernong Maaga", --TLCHANGE 1472196, "en", ancestors = "enm", aliases = {"Early New English"}, english_name = "Early Modern English", --TLCHANGE spanish_name = "Inglés moderno temprano", --TLCHANGE } m["en-geo"] = { "Geordie", 653421, "en", ancestors = "enm-nor", } m["en-IE"] = { -- FIXME: "IE" doesn't cover Northern Ireland "Ingles Irlandes", --TLCHANGE 665624, "en", english_name = "Irish English", --TLCHANGE spanish_name = "Inglés irlandés", --TLCHANGE } m["en-uls"] = { "Ingles Ulster", --TLCHANGE 6840826, "en-IE", english_name = "Ulster English", --TLCHANGE spanish_name = "Inglés en Úlster", --TLCHANGE } m["en-GB-NIR"] = { "Ingles Hilagang Irlandes", --TLCHANGE 6840826, -- actually the code for Ulster English "en-uls", english_name = "Northern Irish English", --TLCHANGE } m["en-NNN"] = { -- NA = Namibia; NNN is NATO 3-letter code for North America "Ingles Hilagang Amerikano", --TLCHANGE 7053766, "en", ietf_subtag = "en-021", -- 021 = UN M49 code for "Northern America" (i.e. North America wihout Central America or the Caribbean) english_name = "North American English", --TLCHANGE spanish_name = "Inglés norteamericano", --TLCHANGE } m["en-US"] = { "Ingles Amerikano", --TLCHANGE 7976, "en-NNN", english_name = "American English", --TLCHANGE spanish_name = "Inglés americano", --TLCHANGE } m["en-NZ"] = { "Ingles Neozelandes", --TLCHANGE 44661, "en", english_name = "New Zealand English", --TLCHANGE spanish_name = "Inglés neozelandés", --TLCHANGE this specifically refers to New Zealand English, different from Nueva Zelanda } m["en-ZA"] = { "Ingles Timog Afrikano", --TLCHANGE 1156228, "en", english_name = "South African English", --TLCHANGE spanish_name = "Inglés sudafricano", --TLCHANGE } m["en-US-CA"] = { "Ingles Kalifornya", --TLCHANGE 1026812, "en-US", english_name = "California English", --TLCHANGE spanish_name = "Inglés de California", --TLCHANGE } m["en-CA"] = { "Ingles Kanadyense", --TLCHANGE 44676, "en-US", english_name = "Canadian English", --TLCHANGE spanish_name = "Inglés canadiense", --TLCHANGE } m["en-HK"] = { "Ingles Hong Kong", --TLCHANGE 1068863, "en", english_name = "Hong Kong English", --TLCHANGE spanish_name = "Inglés en Hong Kong", --TLCHANGE } m["en-IN"] = { "Ingles Indyo", --TLCHANGE 1348800, "en", english_name = "Indian English", --TLCHANGE spanish_name = "Inglés indio", --TLCHANGE } m["pld"] = { "Polari", 1359130, "en", } -- Scots varieties m["sco-ins"] = { "Insular Scots", 16919205, "sco", } m["sco-uls"] = { "Ulster Scots", 201966, "sco", } m["sco-nor"] = { "Northern Scots", 16928150, "sco", } m["sco-sou"] = { "Southern Scots", 7570457, "sco", aliases = {"South Scots", "Borders Scots"}, } -- Middle English varieties m["enm-esc"] = { -- Part of Middle English until it developed into Middle Scots. "Early Scots", 5326738, "enm", ancestors = "enm-nor", aliases = {"Old Scots", "Scottish Middle English"}, } m["enm-emi"] = { "East Midland Middle English", 134238810, "enm", ancestors = "ang-ang", -- Technically ang-mer, but attested Mercian is mostly WM IIRC } m["enm-ken"] = { "Kentish Middle English", 134238532, "enm", ancestors = "ang-ken", } m["enm-nor"] = { "Northern Middle English", 134238541, "enm", ancestors = "ang-nor", } m["enm-sou"] = { "Southern Middle English", 134238528, "enm", ancestors = "ang-wsx", } m["enm-wmi"] = { "West Midland Middle English", 134238824, "enm", ancestors = "ang-mer", } -- Old English varieties -- Includes both Mercian and Northumbrian. m["ang-ang"] = { "Anglian Old English", 121142917, "ang", } m["ang-ken"] = { "Kentish Old English", 11687485, "ang", } m["ang-mer"] = { "Mercian Old English", 602072, "ang-ang", } m["ang-nor"] = { "Northumbrian Old English", 1798915, "ang-ang", } m["ang-wsx"] = { "West Saxon Old English", 2658603, "ang", } ----------------------------------------------------- -- High German varieties -- ----------------------------------------------------- -- (modern) German varieties m["de-AT"] = { "Austrian German", 306626, "de", } m["de-AT-vie"] = { "Viennese German", 56474, "de-AT", } m["de-CH"] = { "Switzerland German", 1366643, "de", aliases = {"Schweizer Hochdeutsch", "Swiss Standard German", "Swiss High German"}, } m["de-bal"] = { "Baltic German", 15785413, "de", } m["de-ear"] = { "Aleman Mataas na Bago na Maaga", --TLCHANGE 1472199, "de", ancestors = "gmh", aliases = {"Early Modern High German"}, english_name = "Early New High German", --TLCHANGE } m["ksh"] = { "Kölsch", 4624, "gmw-cfr", } m["pfl"] = { "Palatine German", 23014, "gmw-rfr", aliases = {"Pfälzisch", "Pälzisch", "Palatinate German"}, } m["sli"] = { "Silesian East Central German", 152965, "gmw-ecg", aliases = {"Silesian"}, } m["sxu"] = { "Upper Saxon German", 699284, "gmw-ecg", } -- Old High German varieties m["lng"] = { "Lombardic", 35972, "goh", } -- Alemannic German varieties m["gsw-low"] = { "Low Alemannic German", 503724, "gsw", } m["gsw-FR-als"] = { "Alsatian Alemannic German", 8786, "gsw-low", } m["gsw-hig"] = { "High Alemannic German", 503728, "gsw", } m["gsw-hst"] = { "Highest Alemannic German", 687538, "gsw", } m["wae"] = { "Walser German", 680517, "gsw-hst", } ----------------------------------------------------- -- Low German varieties -- ----------------------------------------------------- m["nds-de"] = { "German Low German", 25433, "nds", ietf_subtag = "nds-DE", -- should we make this the actual code? wikimedia_codes = "nds", } m["nds-nl"] = { "Dutch Low Saxon", 516137, "nds", ietf_subtag = "nds-NL", -- should we make this the actual code? wikimedia_codes = "nds-nl", } m["act"] = { "Achterhoeks", 153627, "nds-nl", aliases = {"Achterhoek", "Achterhooks"}, } m["drt"] = { "Drents", 2736709, "nds-nl", aliases = {"Drèents", "Dreins", "Dreints", "Drints"}, } m["frs"] = { "East Frisian Low German", 149208, "nds-de", aliases = {"East Frisian", "East Frisian Low Saxon"}, } m["gos"] = { "Gronings", 508854, "nds-nl", aliases = {"Grunnegs", "Grönnegs"}, } m["nds-lpr"] = { "Low Prussian", 33982, "nds-de", } m["sdz"] = { "Sallands", 3436668, "nds-nl", aliases = {"Sallaans", "Sallaands"}, } m["stl"] = { "Stellingwerfs", 506010, "nds-nl", aliases = {"Stellingwarfs"}, } m["twd"] = { "Twents", 497363, "nds-nl", aliases = {"Tweants"}, } m["vel"] = { "Veluws", 2484810, "nds-nl", } m["wep"] = { "Westphalian", 505655, "nds-de", aliases = {"Westfalish", "Westphalien"}, } ----------------------------------------------------- -- North Frisian varieties -- ----------------------------------------------------- m["frr-ins"] = { "Insular North Frisian", 110629610, "frr", } m["frr-fam"] = { "Föhr-Amrum North Frisian", 110629601, "frr-ins", } m["frr-foh"] = { "Föhr North Frisian", 28185, "frr-fam", aliases = {"Föhr Frisian", "Fering", "Ferring", -- Glottolog }, varieties = {"Aasdring", "Weesdring"}, } m["frr-amr"] = { "Amrum North Frisian", 28192, "frr-fam", aliases = {"Amrum Frisian", "Amrum", "Öömrang"}, } m["frr-hel"] = { "Heligoland North Frisian", 28086, "frr-ins", aliases = {"Heligoland Frisian", "Halunder", "Heligolandic Frisian", "Heligolandic North Frisian", "Helgoland Frisian", "Helgoland North Frisian", "Helgoland"}, } m["frr-syl"] = { "Sylt North Frisian", 28181, "frr-ins", aliases = {"Sylt Frisian", "Söl'ring", "Sölreng", -- Glottolog }, } m["frr-mai"] = { "Mainland North Frisian", 110629626, "frr", } m["frr-hal"] = { "Halligen North Frisian", 28177, "frr-mai", aliases = {"Halligen Frisian", "Halifreesk", "Hallingen Frisian", "Hallingen North Frisian", "Hallingen", -- Glottolog }, } m["frr-moo"] = { "Mooring North Frisian", 28187, "frr-mai", aliases = {"Bökingharde North Frisian", "Bökingharde Frisian", "Böökinghiirder frasch", "Mooring", "Moring", }, varieties = {{"East Mooring", "Ostermooring"}, {"West Mooring", "Westermooring"}}, } m["frr-kar"] = { "Karrharde North Frisian", 28191, "frr-mai", aliases = {"Karrharde Frisian", "Karrharder", }, } m["frr-goe"] = { -- Technically this refers to three adjacent dialects (Northern, Central and Southern), the latter of which went -- extinct in 1980-1981. As a result, Glottolog speaks of "Norder-Mittelgoesharde", referring to the remaining two. "Goesharde North Frisian", 28183, "frr-mai", aliases = {"Norder-Mittelgoesharde North Frisian", "Norder-Mittelgoesharde Frisian", "Norder-Mittelgoesharde", "Goesharde Frisian", "Goesharde", "Gooshiirder", }, } m["frr-wie"] = { "Wiedingharde North Frisian", 28171, "frr-mai", aliases = {"Wiedingharde Frisian", "Wiedingharde", "Wiringhiirder freesk", }, } ----------------------------------------------------- -- Old Norse varieties -- ----------------------------------------------------- m["non-grn"] = { "Greenlandic Norse", 855236, "non-own", } m["non-oen"] = { "Old East Norse", 10498031, "non", ancestors = "non", } m["non-own"] = { "Old West Norse", 2377483, "non", ancestors = "non", } ----------------------------------------------------- -- Old Swedish varieties -- ----------------------------------------------------- m["gmq-osw-lat"] = { "Late Old Swedish", 10723594, "gmq-osw", ancestors = "gmq-osw", } -------------------------------------------------------------------------------------- -- Greek varieties -- -------------------------------------------------------------------------------------- m["qsb-grc"] = { "Pre-Greek", 965052, "und", family = "qfa-sub", } m["grc-aeo"] = { "Aeolic Greek", 406373, "grc", aliases = {"Lesbic Greek", "Lesbian Greek", "Aeolian Greek"}, } m["grc-arc"] = { "Arcadian Greek", nil, "grc-arp", } m["grc-arp"] = { "Arcadocypriot Greek", 499602, "grc", } m["grc-att"] = { "Attic Greek", 506588, "grc", } m["grc-boi"] = { "Boeotian Greek", 406373, "grc-aeo", } m["grc-dor"] = { "Doric Greek", 285494, "grc", } m["grc-ela"] = { "Elean Greek", nil, "grc", } m["grc-epc"] = { "Epic Greek", 990062, "grc", aliases = {"Homeric Greek"}, } m["grc-ion"] = { "Ionic Greek", 504165, "grc", } m["grc-koi"] = { "Koine Greek", 107358, "grc", ancestors = "grc-att", aliases = {"Hellenistic Greek"}, } m["grc-kre"] = { "Cretan Ancient Greek", -- to distinguish from Cretan Greek below nil, "grc-dor", } m["grc-opl"] = { "Opuntian Locrian", nil, "grc", } m["grc-ozl"] = { "Ozolian Locrian", nil, "grc", } m["grc-pam"] = { "Pamphylian Greek", 2271793, "grc", } m["grc-ths"] = { "Thessalian Greek", 406373, "grc-aeo", } m["gkm"] = { "Byzantine Greek", 36387, "grc", ancestors = "grc-koi", aliases = {"Medieval Greek"}, } m["el-cyp"] = { "Cypriot Greek", 245899, "el", aliases = {"Cypriotic Greek"}, } m["el-pap"] = { "Paphian Greek", nil, "el", } m["el-crt"] = { "Cretan Greek", 588306, "el", } m["el-kth"] = { "Katharevousa", 35961, "el", "Polyt", ancestors = "gkm", aliases = {"Katharevousa Greek"}, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["el-kal"] = { "Kaliarda", 12878658, "el", } -------------------------------------------------------------------------------------- -- Indo-Iranian varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Indo-Aryan varieties -- ------------------------------------------------------------------------- -- reconstructed intermediate stages m["pra-pro"] = { "Proto-New Indo-Aryan", nil, "pra", } m["inc-ash-pro"] = { "Proto-Middle Indo-Aryan", nil, "inc-ash", } m["inc-mit"] = { "Mitanni", 1986700, "inc-pro", } m["bra-old"] = { "Old Braj", nil, "bra", } -- Apabhramsas m["inc-aav"] = { "Avahattha", nil, "inc-apa", aliases = {"Abahattha"}, } m["inc-asa"] = { "Sauraseni Apabhramsa", nil, "inc-apa", } m["inc-agu"] = { "Gurjara Apabhramsa", nil, "inc-apa", } m["inc-aka"] = { "Kasmiri Apabhramsa", nil, "inc-apa", } m["inc-ama"] = { "Maharastri Apabhramsa", nil, "inc-apa", } m["inc-ata"] = { "Takka Apabhramsa", nil, "inc-apa", } m["inc-avr"] = { "Vracada Apabhramsa", nil, "inc-apa", } -- Assamese varieties m["as-bkm"] = { "Barpetia Kamrupi Assamese", 30642960, "as", } m["as-nkm"] = { "Nalbaria Kamrupi Assamese", 85787678, "as", } m["as-pkm"] = { "Palasbaria Kamrupi Assamese", nil, "as", } -- Bengali varieties m["bn-dvn"] = { "Dhakaiya Vaṅga Bengali", 48726851, "bn", -- Eastern Bengali variety } m["bn-nvn"] = { "Noakhailla Vaṅga Bengali", 107548681, "bn", -- Eastern Bengali variety } -- Dhivehi varieties m["dv-old"] = { "Old Dhivehi", 117790875, "dv", } m["dv-mul"] = { "Mulaku Dhivehi", nil, "dv", aliases = {"Mulaku Divehi", "Mulaku Bas"}, } m["dv-huv"] = { "Huvadhu Dhivehi", nil, "dv", aliases = {"Huvadhu Divehi", "Huvadhu Bas"}, } m["dv-add"] = { "Addu Dhivehi", nil, "dv", aliases = {"Addu Divehi", "Addu Bas"}, } -- Gujarati varieties m["gu-kat"] = { "Kathiyawadi", nil, "gu", aliases = {"Kathiyawadi Gujarati", "Kathiawadi"}, } m["gu-lda"] = { "Lisan ud-Dawat Gujarati", nil, "gu", aliases = {"Lisan ud-Dawat", "LDA"}, } -- Hindi varieties m["hi-mum"] = { "Bombay Hindi", 3543151, "hi", aliases = {"Mumbai Hindi", "Bambaiyya Hindi"}, } m["hi-mid"] = { "Middle Hindi", nil, "inc-ohi", ancestors = "inc-ohi", } -- Konkani varieties m["kok-mid"] = { "Middle Konkani", nil, "kok", aliases = {"Medieval Konkani"}, } m["kok-old"] = { "Old Konkani", nil, "kok", aliases = {"Early Konkani"}, } -- Prakrits m["pra-ard"] = { "Ardhamagadhi Prakrit", 35217, "pra", aliases = {"Ardhamagadhi"}, } m["pra-hel"] = { "Helu Prakrit", 15080869, "pra", aliases = {"Elu", "Elu Prakrit", "Helu"}, } m["pra-kha"] = { "Khasa Prakrit", nil, "pra", aliases = {"Khasa"}, } m["pra-mag"] = { "Magadhi Prakrit", -- Not to be confused with Magahi (mag) 2652214, "pra", aliases = {"Magadhi"}, } m["pra-mah"] = { "Maharastri Prakrit", 2586773, "pra", aliases = {"Maharashtri Prakrit", "Maharastri", "Maharashtri"}, } m["pra-pai"] = { "Paisaci Prakrit", 2995607, "pra-sau", aliases = {"Paisaci", "Paisachi"}, ancestors = "pra-sau" } m["pra-sau"] = { "Sauraseni Prakrit", 2452885, "pra", aliases = {"Sauraseni", "Shauraseni"}, } m["pra-ava"] = { "Avanti", nil, "pra", aliases = {"Avanti Prakrit"}, } m["pra-pra"] = { "Pracya", nil, "pra", aliases = {"Pracya Prakrit"}, } m["pra-bah"] = { "Bahliki", nil, "pra", aliases = {"Bahliki Prakrit"}, } m["pra-dak"] = { "Daksinatya", nil, "pra", aliases = {"Daksinatya Prakrit"}, } m["pra-sak"] = { "Sakari", nil, "pra", aliases = {"Sakari Prakrit"}, } m["pra-can"] = { "Candali", nil, "pra", aliases = {"Candali Prakrit"}, } m["pra-sab"] = { "Sabari", nil, "pra", aliases = {"Sabari Prakrit"}, } m["pra-abh"] = { "Abhiri", nil, "pra", aliases = {"Abhiri Prakrit"}, } m["pra-dra"] = { "Dramili", nil, "pra", aliases = {"Dramili Prakrit"}, } m["pra-odr"] = { "Odri", nil, "pra", aliases = {"Odri Prakrit"}, } -- Punjabi varieties m["pnb"] = { "Western Punjabi", 58635, "pa", "pa-Arab", } -- Sanskrit varieties m["vsn"] = { "Vedic Sanskrit", 36858, "sa", } m["cls"] = { "Classical Sanskrit", 11059, "sa", } m["sa-bhs"] = { "Buddhist Hybrid Sanskrit", 248758, "sa", } m["sa-bra"] = { "Brahmanic Sanskrit", 36858, "sa", } m["sa-neo"] = { "New Sanskrit", 11059, "sa", } -- Sinhalese varieties m["si-med"] = { "Medieval Sinhalese", nil, "si", aliases = {"Medieval Sinhala"}, } ------------------------------------------------------------------------- -- Iranian varieties -- ------------------------------------------------------------------------- m["qsb-bma"] = { "the BMAC substrate", 133187435, "und", family = "qfa-sub", aliases = {"the Bactria-Margiana substrate", "the Bactria-Margiana Archaeological Complex substrate"}, } -- Historical and current Iranian dialects m["ae-old"] = { "Old Avestan", 29572, "ae", aliases = {"Gathic Avestan"}, } m["ae-yng"] = { "Younger Avestan", 29572, "ae-old", aliases = {"Young Avestan"}, } m["bcc"] = { "Southern Balochi", 33049, "bal", aliases = {"Southern Baluchi"}, } m["bgp"] = { "Eastern Balochi", 33049, "bal", aliases = {"Eastern Baluchi"}, } m["bgn"] = { "Western Balochi", 33049, "bal", aliases = {"Western Baluchi"}, } m["bsg-ban"] = { "Bandari", nil, "bsg", } m["bsg-hor"] = { "Hormozi", nil, "bsg", } m["bsg-min"] = { "Minabi", nil, "bsg", } m["kho-old"] = { "Old Khotanese", nil, "kho", } m["kho-lat"] = { "Late Khotanese", nil, "kho-old", } m["peo-ear"] = { "Early Old Persian", nil, "peo", } m["peo-lat"] = { "Late Old Persian", nil, "peo", } m["pal-ear"] = { "Early Middle Persian", nil, "pal", } m["pal-lat"] = { "Late Middle Persian", nil, "pal", ancestors = "pal-ear", } m["ps-nwe"] = { "Northwestern Pashto", nil, "ps", } m["ps-cgi"] = { "Central Ghilzay", nil, "ps-nwe", } m["ps-mah"] = { "Mahsudi", nil, "ps-nwe", } m["ps-nea"] = { "Northeastern Pashto", nil, "ps", } m["ps-afr"] = { "Afridi", nil, "ps-nea", } m["ps-bng"] = { "Bangash", nil, "ps-nea", } m["ps-xat"] = { "Khatak", nil, "ps-nea", } m["ps-pes"] = { "Peshawari", nil, "ps-nea", } m["ps-sea"] = { "Timog Silanganing Pastun", --TLCHANGE nil, "ps", english_name = "Southeastern Pashto", --TLCHANGE } m["ps-ban"] = { "Bannu", nil, "ps-sea", } m["ps-kak"] = { "Kakari", nil, "ps-sea", } m["ps-ser"] = { "Sher", nil, "ps-sea", } m["ps-waz"] = { "Waziri", 12274473, "ps-sea", } m["ps-swe"] = { "Timog Kanluraning Pastun", --TLCHANGE nil, "ps", english_name = "Southwestern Pashto", --TLCHANGE } m["ps-kan"] = { "Kandahari", nil, "ps-swe", } m["ps-jad"] = { "Jadrani", nil, "ps", ancestors = "ira-pat-pro" } m["xme-azr"] = { "Old Azari", nil, "xme-ott", aliases = {"Old Azeri", "Azari", "Azeri", "Āḏarī", "Adari", "Adhari"}, } m["xme-ttc-cen"] = { "Central Tati", nil, "xme-ott", } m["xme-ttc-eas"] = { "Eastern Tati", nil, "xme-ott", } m["xme-ttc-nor"] = { "Northern Tati", nil, "xme-ott", } m["xme-ttc-sou"] = { "Southern Tati", nil, "xme-ott", } m["xme-ttc-wes"] = { "Western Tati", nil, "xme-ott", } m["xmn"] = { "Manichaean Middle Persian", nil, "pal-lat", } m["fa-ear"] = { "Early New Persian", 127413796, "fa", ancestors = "pal-lat", translit = "fa-cls-translit", } m["fa-cls"] = { "Classical Persian", 9168, "fa", ancestors = "fa-ear", translit = "fa-cls-translit", } m["fa-ira"] = { "Iranian Persian", 3513637, "fa", aliases = {"Modern Persian", "Western Persian"}, translit = "fa-ira-translit", } m["prs"] = { "Dari", 178440, "fa", aliases = {"Dari Persian", "Central Persian", "Eastern Persian", "Afghan Persian"}, translit = "fa-cls-translit", } m["haz"] = { "Hazaragi", 33398, "prs", translit = "fa-cls-translit", } m["os-dig"] = { "Digor Ossetian", 3027861, "os", aliases = {"Digoron", "Digor"}, } m["os-iro"] = { "Iron Ossetian", nil, "os", aliases = {"Iron"}, } m["sog-ear"] = { "Early Sogdian", nil, "sog", } m["sog-lat"] = { "Late Sogdian", nil, "sog-ear", } m["ro-MD"] = { "Moldavo", --TLCHANGE 36392, "ro", aliases = {"Moldavian"}, english_name = "Moldovan", --TLCHANGE spanish_name = "Moldavo", --TLCHANGE } m["oru-kan"] = { "Kaniguram", 6363164, "oru", } m["oru-log"] = { "Logar", nil, "oru", } m["oos"] = { "Old Ossetic", 65455882, "xln", } m["oos-ear"] = { "Early Old Ossetic", nil, "oos", } m["oos-lat"] = { "Late Old Ossetic", nil, "oos", } m["rdb-jir"] = { "Jirofti", nil, "rdb", } m["rdb-kah"] = { "Kahnuji", nil, "rdb", } -- Southwestern Fars lects m["fay-bur"] = { "Burenjani", nil, "fay", } m["fay-bsh"] = { "Bushehri", nil, "fay", } m["fay-dsh"] = { "Dashtaki", nil, "fay", } m["fay-dav"] = { "Davani", 5228140, "fay", } m["fay-eze"] = { "Emamzada Esmaili", nil, "fay", } m["fay-gav"] = { "Gavkoshaki", nil, "fay", } m["fay-kho"] = { "Khollari", nil, "fay", } m["fay-kon"] = { "Kondazi", nil, "fay", } m["fay-kzo"] = { "Old Kazeruni", nil, "fay", } m["fay-mas"] = { "Masarami", nil, "fay", } m["fay-pap"] = { "Papuni", nil, "fay", } m["fay-sam"] = { "Samghani", nil, "fay", } m["fay-shr"] = { "Shirazi", nil, "fay", } m["fay-sho"] = { "Old Shirazi", nil, "fay", } m["fay-kar"] = { "Khargi", nil, "fay", } m["fay-sor"] = { "Sorkhi", nil, "fay", } -- Talysh lects m["tly-cen"] = { "Central Talysh", nil, "tly", } m["tly-asa"] = { "Asalemi", nil, "tly-cen", } m["tly-kar"] = { "Karganrudi", nil, "tly-cen", } m["tly-tul"] = { "Tularudi", nil, "tly-cen", } m["tly-tal"] = { "Taleshdulabi", nil, "tly-cen", } m["tly-nor"] = { "Northern Talysh", nil, "tly", } m["tly-aze"] = { "Azerbaijani Talysh", nil, "tly-nor", } m["tly-anb"] = { "Anbarani", nil, "tly-nor", } m["tly-sou"] = { "Southern Talysh", nil, "tly", } m["tly-fum"] = { "Fumani", nil, "tly-sou", } m["tly-msu"] = { "Masulei", nil, "tly-sou", } m["tly-msa"] = { "Masali", nil, "tly-sou", } m["tly-san"] = { "Shandarmani", nil, "tly-sou", } -- Tafreshi lects m["xme-amo"] = { "Amorehi", nil, "xme-taf", } m["atn"] = { "Ashtiani", 3436590, "xme-taf", } m["xme-bor"] = { "Borujerdi", nil, "xme-taf", } m["xme-ham"] = { "Hamadani", 6302426, "xme-taf", } m["xme-kah"] = { "Kahaki", nil, "xme-taf", } m["vaf"] = { "Vafsi", 32611, "xme-taf", } -- Kermanic lects m["kfm"] = { "Khunsari", 6403030, "xme-ker", } m["xme-mah"] = { "Mahallati", nil, "xme-ker", } m["xme-von"] = { "Vonishuni", nil, "xme-ker", } m["xme-bdr"] = { "Badrudi", nil, "xme-ker", } m["xme-del"] = { "Delijani", nil, "xme-ker", } m["xme-kas"] = { "Kashani", nil, "xme-ker", } m["xme-kes"] = { "Kesehi", nil, "xme-ker", } m["xme-mey"] = { "Meymehi", nil, "xme-ker", } m["ntz"] = { "Natanzi", 6968399, "xme-ker", } m["xme-abz"] = { "Abuzeydabadi", nil, "xme-ker", } m["xme-aby"] = { "Abyanehi", nil, "xme-ker", } m["xme-far"] = { "Farizandi", nil, "xme-ker", } m["xme-jow"] = { "Jowshaqani", nil, "xme-ker", } m["xme-nas"] = { "Nashalji", nil, "xme-ker", } m["xme-qoh"] = { "Qohrudi", nil, "xme-ker", } m["xme-yar"] = { "Yarandi", nil, "xme-ker", } m["soj"] = { "Soi", 7930463, "xme-ker", aliases = {"Sohi"}, } m["xme-tar"] = { "Tari", nil, "xme-ker", } m["gzi"] = { "Gazi", 5529130, "xme-ker", } m["xme-sed"] = { "Sedehi", nil, "xme-ker", } m["xme-ard"] = { "Ardestani", nil, "xme-ker", } m["xme-zef"] = { "Zefrehi", nil, "xme-ker", } m["xme-isf"] = { "Isfahani", nil, "xme-ker", } m["xme-kaf"] = { "Kafroni", nil, "xme-ker", } m["xme-vrz"] = { "Varzenehi", nil, "xme-ker", } m["xme-xur"] = { "Khuri", nil, "xme-ker", } m["nyq"] = { "Nayini", 6983146, "xme-ker", } m["xme-ana"] = { "Anaraki", nil, "xme-ker", } m["gbz"] = { "Zoroastrian Dari", 32389, "xme-ker", aliases = {"Behdināni", "Gabri", "Gavrŭni", "Gabrōni"}, } m["xme-krm"] = { "Kermani", nil, "xme-ker", } m["xme-yaz"] = { "Yazdi", nil, "xme-ker", } m["xme-bid"] = { "Bidhandi", nil, "xme-ker", } m["xme-bij"] = { "Bijagani", nil, "xme-ker", } m["xme-cim"] = { "Chimehi", nil, "xme-ker", } m["xme-han"] = { "Hanjani", nil, "xme-ker", } m["xme-kom"] = { "Komjani", nil, "xme-ker", } m["xme-nar"] = { "Naraqi", nil, "xme-ker", } m["xme-nus"] = { "Nushabadi", nil, "xme-ker", } m["xme-qal"] = { "Qalhari", nil, "xme-ker", } m["xme-trh"] = { "Tarehi", nil, "xme-ker", } m["xme-val"] = { "Valujerdi", nil, "xme-ker", } m["xme-var"] = { "Varani", nil, "xme-ker", } m["xme-zor"] = { "Zori", nil, "xme-ker", } -- Ramandi lects m["tks-ebr"] = { "Ebrahimabadi", nil, "tks", } m["tks-sag"] = { "Sagzabadi", nil, "tks", } m["tks-esf"] = { "Esfarvarini", nil, "tks", } m["tks-tak"] = { "Takestani", nil, "tks", } m["tks-cal"] = { "Chali Tati", nil, "tks", aliases = {"Chāli"}, } m["tks-dan"] = { "Danesfani", nil, "tks", } m["tks-xia"] = { "Khiaraji", nil, "tks", } m["tks-xoz"] = { "Khoznini", nil, "tks", } -- Shughni dialects m["sgh-bro"] = { "Bartangi-Oroshori", nil, "sgh", } m["sgh-bar"] = { "Bartangi", nil, "sgh-bro", } m["sgh-oro"] = { "Oroshori", nil, "sgh-bro", aliases = {"Roshorvi"}, } m["sgh-rsx"] = { "Roshani-Khufi", nil, "sgh", } m["sgh-xuf"] = { "Khufi", 2562249, "sgh-rsx", aliases = {"Xufi", "Xūfī"}, } m["sgh-ros"] = { "Roshani", 2597566, "sgh-rsx", aliases = {"Rushani", "Rōšāni"}, } m["sgh-xgb"] = { "Khughni-Bajui", nil, "sgh", } m["sgh-xug"] = { "Khughni", nil, "sgh-xgb", } m["sgh-baj"] = { "Bajui", nil, "sgh-xgb", } ------------------------------------------------------------------------- -- Nuristani varieties -- ------------------------------------------------------------------------- m["bsh-kat"] = { "Kativiri", 2605045, "bsh", aliases = {"Katə́viri"}, } m["xvi"] = { "Kamviri", 1193495, "bsh", aliases = {"Kamvíri"}, } m["bsh-mum"] = { "Mumviri", nil, "bsh", aliases = {"Mumvíri"}, } -------------------------------------------------------------------------------------- -- Italic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Latin varieties -- ------------------------------------------------------------------------- -- Latin varieties by period m["itc-ola"] = { "Old Latin", 12289, "la", "Latn, Ital", translit = { Ital = "Ital-translit" }, } m["itc-lan"] = { "Lanuvian", 16890829, "itc-ola", aliases = {"Lanuvine"}, } m["itc-pra"] = { "Praenestine", 16889772, "itc-ola", aliases = {"Praenestinian"}, } m["la-cla"] = { "Classical Latin", 253854, "la", } m["la-vul"] = { "Vulgar Latin", 37560, "la-cla", } m["la-afr"] = { "African Romance", 162064, "roa-pro", } m["la-lat"] = { "Late Latin", 1503113, "la", ancestors = "la-cla", } m["la-med"] = { "Medieval Latin", 1163234, "la", ancestors = "la-lat", } m["la-eme"] = { "Early Medieval Latin", nil, "la-med", } m["la-ecc"] = { "Ecclesiastical Latin", 1247932, "la", aliases = {"Church Latin", "Liturgical Latin"}, ancestors = "la-lat", } m["la-ren"] = { "Renaissance Latin", 499083, "la", ancestors = "la-med", } m["la-new"] = { "New Latin", 1248221, "la", aliases = {"Modern Latin"}, ancestors = "la-ren", } m["la-con"] = { "Contemporary Latin", 1246397, "la-new", } ------------------------------------------------------------------------- -- Miscellaneous Italic varieties -- ------------------------------------------------------------------------- m["xfa-cap"] = { "Capenate", 133182969, "xfa", } m["osc-luc"] = { "Lucanian", 3265025, "osc", } m["osc-sam"] = { "Samnite", 133184287, "osc", } ------------------------------------------------------------------------- -- Romance varieties -- ------------------------------------------------------------------------- m["roa-pro"] = { "Proto-Romance", 3408029, "la-lat", ancestors = "la-vul", } ----------------------------------------------------- -- Catalan varieties -- ----------------------------------------------------- m["ca-val"] = { "Valencian", 32641, "ca", } ----------------------------------------------------- -- Franco-Provençal varieties -- ----------------------------------------------------- m["frp-old"] = { "Old Franco-Provençal", nil, "frp", } ----------------------------------------------------- -- French and derived creole varieties -- ----------------------------------------------------- m["fro-nor"] = { "Old Northern French", 2044917, "fro", aliases = {"Old Norman", "Old Norman French"}, } m["fro-pic"] = { "Picard Old French", nil, "fro", } m["xno"] = { "Anglo-Norman", 35214, "fro-nor", } m["xno-law"] = { "Law French", 2044323, "xno", } m["zrp"] = { "Zarphatic", 36994, "fro", aliases = {"Judeo-French"}, pseudo_families = "qfa-jew", } m["fr-CA"] = { "Canadian French", 1450506, "fr", } m["fr-CH"] = { "Swiss French", 1480152, "fr", } m["fr-aca"] = { "Acadian French", 415109, "fr", } m["fr-lou"] = { "Louisiana French", 3083213, "fr", } m["fr-mis"] = { "Missouri French", 3083210, "fr", } m["frc"] = { "Cajun French", 880301, "fr-lou", } m["ht-sdm"] = { "Saint Dominican Creole French", nil, "ht", ancestors = "fr", } -- Norman varieties m["nrf-grn"] = { "Guernsey Norman", 56428, "nrf", aliases = {"Guernsey"}, } m["nrf-jer"] = { "Jersey Norman", 56430, "nrf", aliases = {"Jersey"}, } ----------------------------------------------------- -- Gallo-Italic varieties -- ----------------------------------------------------- m["egl-old"] = { "Old Emilian", nil, "egl", } m["lij-old"] = { "Old Ligurian", nil, "lij", aliases = {"Old Genoese"}, } m["lmo-old"] = { "Old Lombard", 97165320, "lmo", } m["pms-old"] = { "Old Piedmontese", nil, "pms", aliases = {"Old Piemontese"}, } m["vec-old"] = { "Old Venetan", nil, "vec", aliases = {"Old Venetian"}, } m["rgn-old"] = { "Old Romagnol", nil, "rgn", } ----------------------------------------------------- -- Italo-Romance varieties -- ----------------------------------------------------- -- Italian varieties m["roa-oit"] = { "Old Italian", nil, "it", } m["it-CH"] = { "Switzerland Italian", 672147, "it", } -- Other Italo-Romance varieties m["nap-old"] = { "Old Neapolitan", nil, "nap", } m["scn-old"] = { "Old Sicilian", nil, "scn", } ----------------------------------------------------- -- Occitan varieties -- ----------------------------------------------------- m["oc-auv"] = { "Auvergnat", 35359, "oc", aliases = {"Auvernhat", "Auvergnese"}, } m["oc-gas"] = { "Gaskon", --TLCHANGE 35735, "oc", english_name = "Gascon", --TLCHANGE spanish_name = "Gascón", --TLCHANGE } -- standardized dialect of Gascon m["oc-ara"] = { "Aranes", --TLCHANGE 10196, "oc-gas", english_name = "Aranese", --TLCHANGE spanish_name = "Aranés", --TLCHANGE } m["oc-lan"] = { "Languedocien", 942602, "oc", aliases = {"Lengadocian"}, } m["oc-lim"] = { "Limousin", 427614, "oc", } m["oc-pro"] = { "Provençal", 241243, "oc", aliases = {"Provencal"}, } m["oc-pro-old"] = { "Old Provençal", 2779185, "pro", } m["oc-viv"] = { "Vivaro-Alpine", 1649613, "oc", } m["oc-jud"] = { "Shuadit", 56472, "oc", aliases = { "Chouhadite", "Chouhadit", "Chouadite", "Chouadit", "Shuhadit", "Judeo-Occitan", "Judæo-Occitan", "Judaeo-Occitan", "Judeo-Provençal", "Judæo-Provençal", "Judaeo-Provençal", "Judeo-Provencal", "Judaeo-Provencal", "Judeo-Comtadin", "Judæo-Comtadin", "Judaeo-Comtadin", }, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Portuguese and derived creole varieties -- ----------------------------------------------------- -- Portuguese m["pt-BR"] = { "Portugues Brasileño", --TLCHANGE 750553, "pt", english_name = "Brazilian Portuguese", --TLCHANGE spanish_name = "Portugués brasileño", --TLCHANGE } m["pt-PT"] = { "Portugues Europeo", --TLCHANGE 922399, "pt", english_name = "European Portuguese", --TLCHANGE spanish_name = "Portugués europeo", --TLCHANGE } -- Kabuverdianu (Cape Verde Creole, Cape Verdean Creole) m["kea-bar"] = { "Barlavento Kabuverdianu", 2217638, "kea", aliases = {"Barlavento", "Barlavento Creole", "Sampadjudu"}, } m["kea-bvi"] = { "Boa Vista Kabuverdianu", 16501837, "kea-bar", aliases = {"Boa Vista Creole"}, } m["kea-sal"] = { "Sal Kabuverdianu", 18707467, "kea-bar", aliases = {"Sal Creole"}, } m["kea-saa"] = { "Santo Antão Kabuverdianu", 18707472, "kea-bar", aliases = {"Santo Antão Creole"}, } m["kea-sni"] = { "São Nicolau Kabuverdianu", 18707549, "kea-bar", aliases = {"São Nicolau Creole"}, } m["kea-svi"] = { "São Vicente Kabuverdianu", 18707550, "kea-bar", aliases = {"São Vicente Creole"}, } m["kea-sot"] = { "Sotavento Kabuverdianu", 10261559, "kea", aliases = {"Sotavento", "Sotavento Creole", "Badiu"}, } m["kea-bra"] = { "Brava Kabuverdianu", 18670181, "kea-sot", aliases = {"Brava Creole"}, } m["kea-fog"] = { "Fogo Kabuverdianu", 18706861, "kea-sot", aliases = {"Fogo Creole"}, } m["kea-mai"] = { "Maio Kabuverdianu", 18707286, "kea-sot", aliases = {"Maio Creole"}, } m["kea-san"] = { "Santiago Kabuverdianu", 35117, "kea-sot", aliases = {"Santiago Creole"}, } m["kea-alu"] = { "ALUPEC Kabuverdianu", 375704, "kea", aliases = {"ALUPEC", "Alfabeto Unificado para a Escrita do Cabo-Verdiano"}, } ----------------------------------------------------- -- Rhaeto-Romance varieties -- ----------------------------------------------------- -- Friulian varieties m["fur-old"] = { "Old Friulian", nil, "fur", } -- Ladin varieties m["lld-amp"] = { "Ampezan Ladin", 25617466, "lld", aliases = {"Anpezan", "Ampezan", "Ampezzan", "Ampezzano"}, } m["lld-bad"] = { "Badiot Ladin", 3706562, "lld", aliases = {"Badiot", "Badioto", "Badiotto"}, } m["lld-cad"] = { "Cadorino Ladin", 3706570, "lld", aliases = {"Cadorino"}, } m["lld-fas"] = { "Fascian Ladin", 742627, "lld", aliases = {"Fascian", "Fassano"}, } m["lld-fod"] = { "Fodom Ladin", 3706605, "lld", aliases = {"Fodom", "Livinallese"}, } m["lld-for"] = { "Fornes Ladin", 5470374, "lld", aliases = {"Fornes"}, } m["lld-ghe"] = { "Gherdëina Ladin", 3706597, "lld", aliases = {"Gherdëina", "Gardenese", "Val Gardena"}, } m["lld-non"] = { "Nones Ladin", 1055027, "lld", aliases = {"Nones", "Noneso"}, } -- Romansh varieties m["rm-old"] = { "Old Romansh", nil, "rm", } m["rm-put"] = { "Puter Romansh", 688309, "rm", aliases = {"Puter", "Putèr", "Upper Engadine", "rm-puter"}, } m["rm-srm"] = { "Surmiran Romansh", 690216, "rm", aliases = {"Surmiran", "rm-surmiran", "Surmiran-Albula", -- Glottolog }, } m["rm-srs"] = { "Sursilvan Romansh", 688348, "rm", aliases = {"Sursilvan", "rm-sursilv"}, } m["rm-sut"] = { "Sutsilvan Romansh", 688272, "rm", aliases = {"Sutsilvan", "rm-sutsilv"}, varieties = {"Scharans Sutsilvan"}, -- per Glottolog } m["rm-val"] = { "Vallader Romansh", 690226, "rm", aliases = {"Vallader", "Putèr", "Lower Engadine", "rm-vallader"}, } m["rm-gri"] = { "Rumantsch Grischun", 688873, "rm", aliases = {"rm-rumgr"}, } ----------------------------------------------------- -- Sardinian varieties -- ----------------------------------------------------- m["sc-old"] = { "Old Sardinian", nil, "sc", } m["sc-src"] = { "Logudorese", 777974, "sc", aliases = {"Logudorese Sardinian"}, } m["sc-nuo"] = { "Nuorese", nil, "sc-src", aliases = {"Nuorese Sardinian"}, } m["sc-sro"] = { "Campidanese", 35348, "sc", aliases = {"Campidanese Sardinian"}, } ----------------------------------------------------- -- Spanish varieties -- ----------------------------------------------------- m["es-ear"] = { "Espanyol Modernong Maaga", --TLCHANGE 5364419, "es", english_name = "Early Modern Spanish", --TLCHANGE spanish_name = "Español moderno temprano", --TLCHANGE } m["es-AR"] = { "Espanyol Riyoplatense", --TLCHANGE 509780, "es", english_name = "Rioplatense Spanish", --TLCHANGE spanish_name = "Español rioplatense", --TLCHANGE } m["es-BO"] = { "Espanyol Bolivyano", --TLCHANGE 510730, "es", english_name = "Bolivian Spanish", --TLCHANGE spanish_name = "Español boliviano", --TLCHANGE } m["es-CL"] = { "Espanyol Tsileno", --TLCHANGE 857295, "es", english_name = "Chilean Spanish", --TLCHANGE spanish_name = "Español chileno", --TLCHANGE } m["es-CO"] = { "Espanyol Colombiyano", --TLCHANGE 1115875, "es", english_name = "Colombian Spanish", --TLCHANGE spanish_name = "Español colombiano", --TLCHANGE } m["es-CU"] = { "Espanyol Kubano", --TLCHANGE 824909, "es", english_name = "Cuban Spanish", --TLCHANGE spanish_name = "Español cubano", --TLCHANGE } m["es-MX"] = { "Espanyol Mehikano", --TLCHANGE 616620, "es", english_name = "Mexican Spanish", --TLCHANGE spanish_name = "Español mexicano", --TLCHANGE } m["es-PE"] = { "Espanyol Perwano", --TLCHANGE 736236, "es", english_name = "Peruvian Spanish", --TLCHANGE spanish_name = "Español peruano", --TLCHANGE } m["es-PH"] = { "Espanyol Pilipino", --TLCHANGE 22091406, "es", english_name = "Philippine Spanish", --TLCHANGE spanish_name = "Español filipino", --TLCHANGE } m["es-US"] = { "Espanyol Estados Unidos", --TLCHANGE 2301077, "es", aliases = {"US Spanish"}, english_name = "United States Spanish", --TLCHANGE spanish_name = "Español en Estados Unidos", --TLCHANGE } --use label "US Spanish" to put Spanish terms in this category m["es-PR"] = { "Espanyol Puwertorikeño", --TLCHANGE 7258609, "es", english_name = "Puerto Rican Spanish", --TLCHANGE spanish_name = "Español puertorriqueño", --TLCHANGE } m["es-VE"] = { "Espanyol Venezolano", --TLCHANGE 840017, "es", english_name = "Venezuelan Spanish", --TLCHANGE spanish_name = "Español venezolano", --TLCHANGE } m["es-lun"] = { "Lunfardo", 1401612, "es", english_name = "Lunfardo", --TLCHANGE spanish_name = "Lunfardo", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Japonic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Japanese varieties m["ja-mid"] = { "Gitnang Hapones", --TLCHANGE 6841474, "ojp", ancestors = "ojp", english_name = "Middle Japanese", --TLCHANGE } m["ja-mid-ear"] = { "Hapones Gitnang Maaga", --TLCHANGE 182695, "ja-mid", english_name = "Early Middle Japanese", --TLCHANGE } m["ja-mid-lat"] = { "Late Middle Japanese", 1816184, "ja-mid", ancestors = "ja-mid-ear", } m["ja-ear"] = { "Hapones Modernong Maaga", --TLCHANGE 5326692, "ja", ancestors = "ja-mid-lat", english_name = "Early Modern Japanese", --TLCHANGE } m["ojp-eas"] = { "Hapones Lumang Silanganin", --TLCHANGE 65247957, "ojp", english_name = "Eastern Old Japanese", --TLCHANGE } m["ja-cla"] = { "Hapones Klasikal", --TLCHANGE 1332057, "ja", -- FIXME: This is redundant because Classical Japanese is considered a child of (Modern) Japanese, which has ja-mid-ear -- (as well as ja-mid-lat) as ancestors. However, the intent here is that the *direct* ancestor of ja-cla is ja-mid-ear -- and ja-mid-lat is not an ancestor. Need to rethink ancestor handling. -- ancestors = "ja-mid-ear", english_name = "Classical Japanese", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Koreanic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Korean varieties m["oko-lat"] = { "Late Old Korean", nil, "oko", } m["okm-ear"] = { "Early Middle Korean", nil, "okm", } m["ko-cen"] = { "Koreano Sentral", --TLCHANGE nil, "ko", english_name = "Central Korean", --TLCHANGE } m["ko-gyg"] = { "Koreano Gyeonggi", --TLCHANGE 485492, "ko-cen", aliases = {"Seoul Korean"}, english_name = "Gyeonggi Korean", --TLCHANGE } m["ko-chu"] = { "Koreano Chungcheong", --TLCHANGE 625800, "ko-cen", aliases = {"Hoseo Korean"}, english_name = "Chungcheong Korean", --TLCHANGE } m["ko-hwa"] = { "Koreano Hwanghae", --TLCHANGE 16183706, "ko-cen", english_name = "Hwanghae Korean", --TLCHANGE } m["ko-gan"] = { "Koreano Yeongdong", --TLCHANGE 11260444, "ko-cen", aliases = {"Yeongdong Korean"}, english_name = "Gangwon Korean", --TLCHANGE } m["ko-gys"] = { "Koreano Gyeongsang", --TLCHANGE 488002, "ko", aliases = {"Southeastern Korean"}, english_name = "Gyeongsang Korean", --TLCHANGE } m["ko-jeo"] = { "Koreano Jeolla", --TLCHANGE 11250166, "ko", aliases = {"Southwestern Korean"}, english_name = "Jeolla Korean", --TLCHANGE } m["ko-pyo"] = { "Koreano Pyongan", --TLCHANGE 7263142, "ko", aliases = {"Northwestern Korean"}, english_name = "Pyongan Korean", --TLCHANGE } m["ko-ham"] = { "Koreano Hamgyong", --TLCHANGE 860702, "ko", aliases = {"Northeastern Korean"}, english_name = "Hamgyong Korean", --TLCHANGE } m["ko-yuk"] = { "Koreano Yukjin", --TLCHANGE 16171275, "ko", aliases = {"Yukchin Korean", "Ryukjin Korean", "Ryukchin Korean"}, english_name = "Yukjin Korean", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Mongolic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["xng-ear"] = { "Early Middle Mongol", nil, "xng", } m["xng-lat"] = { "Late Middle Mongol", nil, "xng", ancestors = "xng-ear", } m["mn-kha"] = { "Khalkha Mongolian", 6399808, "mn", aliases = {"Khalkha"}, } m["mn-ord"] = { "Ordos Mongolian", 716904, "mn", aliases = {"Ordos"}, } m["mn-cha"] = { "Chakhar Mongolian", 907425, "mn", aliases = {"Chakhar"}, } m["mn-khr"] = { "Khorchin Mongolian", 3196210, "mn", aliases = {"Khorchin"}, } ---------------------------------------------------------------------------------------------------------------------- -- Niger-Congo varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akan varieties -- ----------------------------------------------------- m["tw"] = { "Twi Akan", 36850, "ak", aliases = {"Twi"}, } m["abr"] = { "Abron", 34831, "tw", aliases = {"Brong", "Bono", "Bono Twi"}, } m["tw-asa"] = { "Asante Twi", 19261685, "tw", aliases = {"Asante", "Ashanti", "Ashante"}, } m["tw-aku"] = { "Akuapem Twi", 31150449, "tw", aliases = {"Akuapem", "Akuapim", "Akwapem Twi", "Akwapi"}, } m["fat"] = { "Fante Akan", 35570, "ak", aliases = {"Fante", "Fanti", "Fantse", "Mfantse"}, } m["wss"] = { "Wasa", 36914, "ak", } -- creole m["alv-kro"] = { "Kromanti", 1093206, "crp-mar", } ----------------------------------------------------- -- Bantu varieties -- ----------------------------------------------------- m["bnt-cmn"] = { "Common Bantu", nil, "bnt-pro", } m["xh-bha"] = { "Bhaca", 4900493, "xh", aliases = {"isiBhaca", "IsiBhaca"}, } -- Rwanda-Rundi varieties m["rw-kin"] = { "Kinyarwanda", 33573, "rw", aliases = {"Rwanda"}, } m["rw-run"] = { "Kirundi", 33583, "rw", aliases = {"Rundi"}, } ----------------------------------------------------- -- Fula varieties -- ----------------------------------------------------- m["fuc"] = { "Pulaar", 1420205, "ff", } m["fuf"] = { "Pular", 3915357, "ff", } m["ffm"] = { "Maasina Fulfulde", 3915322, "ff", } m["fue"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Borgu Fulfulde", 12952426, "ff", } m["fuh"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Western Niger Fulfulde", 12952430, "ff", } m["fuq"] = { -- no enwiki entry as of yet but frwiki, hrwiki and pmswiki have one "Central-Eastern Niger Fulfulde", 12628799, "ff", } m["fuv"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki and swwiki have one "Nigerian Fulfulde", 36129, "ff", } m["fub"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki, ptwiki, swwiki and yowiki have one "Adamawa Fulfulde", 34776, "ff", } m["fui"] = { -- no enwiki entry as of yet but pmswiki and swwiki have one "Bagirmi Fulfulde", 11003859, "ff", } ---------------------------------------------------------------------------------------------------------------------- -- Papuan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["kze"] = { "Kosena", 12952663, "auy", } m["ont"] = { "Ontenu", 3352827, "gaj", aliases = {"Ontena"}, } ---------------------------------------------------------------------------------------------------------------------- -- Salishan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["lut-nor"] = { "Northern Lushootseed", nil, "lut", aliases = {"Northern Puget Sound Salish"}, } m["slh"] = { "Southern Lushootseed", 7997684, "lut", aliases = {"Southern Puget Sound Salish", "Twulshootseed", "Whulshootseed"}, } m["ska"] = { "Skagit", 12642471, "lut-nor", } m["sno"] = { "Snohomish", 25559662, "lut-nor", } ---------------------------------------------------------------------------------------------------------------------- -- Sino-Tibetan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["tbq-pro"] = { "Proto-Tibeto-Burman", 7251864, "sit-pro", } ----------------------------------------------------- -- Chinese varieties -- ----------------------------------------------------- ------------- Old Chinese, Middle Chinese ------------- m["och-ear"] = { "Tsino Lumang Maaga", --TLCHANGE nil, "och", english_name = "Early Old Chinese", --TLCHANGE } m["och-lat"] = { "Late Old Chinese", nil, "och", } m["ltc-ear"] = { "Tsino Gitnang Maaga", --TLCHANGE nil, "ltc", english_name = "Early Middle Chinese", --TLCHANGE } m["ltc-lat"] = { "Late Middle Chinese", nil, "ltc", } ------------- Classical/Literary varieties ------------- -- FIXME: Temporary. m["lzh-shi"] = { "Traditional Chinese poetry", 1759242, "lzh", } -- FIXME: Temporary. m["lzh-cii"] = { "Ci", 1091366, "lzh", } -- FIXME: Temporary. m["lzh-yue"] = { "Classical Cantonese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn"] = { "Classical Mandarin", nil, "lzh", } -- FIXME: Temporary. m["lzh-tai"] = { "Classical Taishanese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn-TW"] = { "Classical Taiwanese Mandarin", nil, "lzh-cmn", } -- FIXME: Temporary. m["lzh-VI"] = { "Vietnamese Classical Chinese", 17034227, "lzh", } -- FIXME: Temporary. m["lzh-KO"] = { "Korean Classical Chinese", 10496257, "lzh", ietf_subtag = "lzh-KR" -- KR = South Korea, as there is no code for Korea as a whole } -- FIXME: Temporary. m["lzh-lit"] = { "Literary Chinese", nil, "lzh", } -- FIXME: Temporary. FIXME: Do we need this? How does it differ from Old Chinese? m["lzh-pre"] = { "Pre-Classical Chinese", nil, "lzh", } ------------- Written Vernacular varieties ------------- -- FIXME: Temporary. m["cmn-wvc"] = { "Written vernacular Mandarin", 783605, "cmn", } -- FIXME: Temporary. FIXME: How does this differ from "Literary Cantonese"? m["yue-wvc"] = { "Written vernacular Cantonese", nil, "yue", } -- FIXME: Temporary. m["zhx-tai-wvc"] = { "Written vernacular Taishanese", nil, "zhx-tai", } ------------- Mandarin varieties ------------- -- FIXME: Temporary. NOTE: The Linguist List assigns the "w:Beijing dialect" (Wikidata 1147606) the code "cmn-bej" and -- the larger "w:Beijing Mandarin (division of Mandarin)" dialect group (Wikidata 2169652; what we call "Beijingic -- Mandarin", after Glottolog) the code "cmn-bei". m["cmn-bei"] = { "Beijing Mandarin", 1147606, "cmn-bec", } -- FIXME: Temporary. m["cmn-bec"] = { "Beijingic Mandarin", 2169652, "cmn", } -- FIXME: Temporary. NOTE: The Linguist List uses the code cmn-zho. m["cmn-cep"] = { "Central Plains Mandarin", 3048775, "cmn", aliases = {"Zhongyuan Mandarin"}, } m["cmn-ear"] = { "Early Mandarin", 837169, "cmn", ancestors = "ltc", } -- FIXME: Temporary. m["cmn-gua"] = { "Guanzhong Mandarin", 3431648, "cmn-cep", } -- FIXME: Temporary. Appears to be a subdialect of Guiliu Mandarin, which in turn is a subdialect of Southwestern Mandarin. m["cmn-gui"] = { "Guilin Mandarin", 11111636, "cmn-sow", } m["cmn-jhu"] = { "Jianghuai Mandarin", 2128953, "cmn", aliases = {"Lower Yangtze Mandarin"}, } -- FIXME: Temporary. m["cmn-lan"] = { "Lanyin Mandarin", 662754, "cmn", } -- FIXME: Temporary. m["cmn-MY"] = { "Malaysian Mandarin", 13646143, "cmn", } -- FIXME: Temporary. m["cmn-nan"] = { "Nanjing Mandarin", 2681098, "cmn-jhu", } -- FIXME: Temporary. m["cmn-noe"] = { "Northeastern Mandarin", 1064504, "cmn", } -- FIXME: Temporary. m["cmn-PH"] = { "Philippine Mandarin", 7185155, "cmn", } -- FIXME: Temporary. m["cmn-SG"] = { "Singapore Mandarin", 1048980, "cmn", } -- FIXME: Temporary. m["cmn-sow"] = { "Southwestern Mandarin", 2609239, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Jilu Mandarin. m["cmn-tia"] = { "Tianjin Mandarin", 7800220, "cmn", } -- FIXME: Temporary. NOTE: Wikidata also has Q4380827 "Taiwanese Mandarin", defined as "rare dialect of Standard Chinese -- (Mandarin) used in Taiwan, which is strongly influenced by Taiwanese Hokkien; mostly used by elderlies" and having no -- English Wikipedia article (but see w:zh:臺灣國語). m["cmn-TW"] = { "Taiwanese Mandarin", 262828, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Wu-Tian Mandarin, in turn a subdialect of Southwestern Mandarin. -- Given the code cmn-xwu in the Linguist List. m["cmn-wuh"] = { "Wuhan Mandarin", 11124731, "cmn-sow", aliases = {"Wuhanese"}, } -- FIXME: Temporary. Appears to be a subdialect of Lanyin Mandarin. m["cmn-xin"] = { "Xining Mandarin", nil, "cmn-lan", } -- FIXME: Temporary. m["cmn-yan"] = { "Yangzhou Mandarin", nil, "cmn-jhu", } ------------- Cantonese varieties ------------- -- FIXME: Temporary. m["yue-gua"] = { "Guangzhou Cantonese", nil, "yue", } -- FIXME: Temporary. Given the codes yue-yue or yue-can in the Linguist List. m["yue-HK"] = { "Hong Kong Cantonese", 5894342, "yue", } -- FIXME: Temporary. FIXME: How does this differ from "Written vernacular Cantonese"? m["yue-lit"] = { "Literary Cantonese", 2472605, "yue", } ------------- Wu varieties ------------- m["wuu-han"] = { "Hangzhounese", 5648144, "wuu", } m["wuu-nin"] = { "Ningbonese", 3972199, "wuu", } -- FIXME: Temporary. m["wuu-nor"] = { "Northern Wu", 7675988, "wuu", aliases = {"Taihu Wu"}, } -- FIXME: Temporary? Subvariety of Taihu Wu. NOTE: "chm" stands for Chongming, the main dialect, to avoid a conflict -- with Shanghainese. m["wuu-chm"] = { "Shadi Wu", 6112340, "wuu-nor", } m["wuu-sha"] = { "Shanghainese", 36718, "wuu-nor", } m["wuu-suz"] = { "Suzhounese", 831744, "wuu-nor", } -- FIXME: Temporary. May be converted into a full language and/or split. m["wuu-wen"] = { "Wenzhounese", 710218, "wuu", } ------------- Xiang varieties ------------- m["hsn-lou"] = { "Loudi Xiang", 10943823, "hsn-old", } m["hsn-hya"] = { "Hengyang Xiang", 20689035, "hsn-hzh", } m["hsn-hzh"] = { "Hengzhou Xiang", nil, "hsn", } m["hsn-new"] = { "New Xiang", 7012696, "hsn", aliases = {"Chang-Yi"}, } m["hsn-old"] = { "Old Xiang", 7085453, "hsn", aliases = {"Lou-Shao"}, } ------------- Hakka varieties ------------- -- FIXME: Temporary. m["hak-dab"] = { "Dabu Hakka", 19855566, "hak", -- formerly hak-TW but seems to be spoken primary in Dabu County in Guangdong } -- FIXME: Temporary. m["hak-eam"] = { "Early Modern Hakka", nil, "hak", } -- FIXME: Temporary. m["hak-hai"] = { "Hailu Hakka", 17038519, "hak", -- often considered a Taiwanese lect but also spoken in [[Shanwei]], [[Guangdong]] } -- FIXME: Temporary. m["hak-HK"] = { "Hong Kong Hakka", 2675834, "hak", } -- FIXME: Temporary. m["hak-hui"] = { "Huiyang Hakka", 16873881, "hak", } -- FIXME: Temporary. m["hak-hui-MY"] = { "Malaysian Huiyang Hakka", nil, "hak-hui", } -- FIXME: Temporary. Similar to and possibly the parent of Sixian Hakka in Taiwan. m["hak-mei"] = { "Meixian Hakka", 839295, "hak", aliases = {"Moiyan Hakka", "Meizhou Hakka"}, } -- FIXME: Temporary. m["hak-six"] = { "Sixian Hakka", 9668261, "hak-TW", } -- FIXME: Temporary. m["hak-TW"] = { "Taiwanese Hakka", 2391532, "hak", } -- FIXME: Temporary. m["hak-zha"] = { "Zhao'an Hakka", 6703311, "hak", aliases = {"Zhangzhou Hakka"}, } -- Southern Min varieties -- m["nan-anx"] = { "Anxi Hokkien", 97064149, "nan-qua", } m["nan-cha"] = { "Changtai Hokkien", nil, "nan-zha", } m["nan-hou"] = { "Houlu Min", 19855492, "nan-dat", } m["nan-hui"] = { "Hui'an Hokkien", 16241797, "nan-qua", } m["nan-jin"] = { "Jinjiang Hokkien", 11089375, "nan-qua", } m["nan-kin"] = { "Kinmenese Hokkien", 56278342, "nan-xia", aliases = {"Kinmen Hokkien"}, } m["nan-med"] = { "Medan Hokkien", 6805114, "nan-zha", } m["nan-pen"] = { "Penang Hokkien", 11120689, "nan-zha", } m["nan-hbl-PH"] = { "Philippine Hokkien", 3236692, "nan-qua", } m["nan-qia"] = { "Qianlu Min", 19842517, "nan-dat", } m["nan-qua"] = { "Quanzhou Hokkien", 2251677, "nan-hbl", aliases = {"Chinchew", "Choanchew"}, } -- FIXME: Temporary? Derived from both Quanzhou and Zhangzhou Hokkien. m["nan-hbl-SG"] = { "Singapore Hokkien", 3846528, "nan-hbl", } m["nan-spm"] = { "Southern Malaysian Hokkien", 7570322, "nan-qua", aliases = {"Southern Malaysia Hokkien", "Southern Peninsular Malaysian Hokkien", "Southern Peninsular Malaysia Hokkien"} } m["nan-hbl-TW"] = { "Taiwanese Hokkien", 36778, "nan-hbl", } m["nan-ton"] = { "Tong'an Hokkien", nil, "nan-xia", } m["nan-xia"] = { "Xiamen Hokkien", 68744, "nan-hbl", aliases = {"Amoy", "Amoyese", "Amoynese", "Xiamenese"}, } m["nan-yon"] = { "Yongchun Hokkien", 65118728, "nan-qua", } m["nan-zha"] = { "Zhangzhou Hokkien", 8070492, "nan-hbl", aliases = {"Changchew", "Chiangchew", "Changchow"}, } m["nan-zho"] = { "Zhao'an Hokkien", 65118728, "nan-zha", aliases = {"Zhao'an", "Chawan", "Chawan Hokkien"}, } m["nan-zhp"] = { "Zhangping Hokkien", 15937822, "nan-zha", } ------------- Other Min varieties ------------- -- FIXME: Temporary. Affiliation within Min uncertain; some combination of Eastern and Southern. m["zhx-zho"] = { "Zhongshan Min", 8070958, "zh", } ------------- Other Chinese varieties ------------- -- FIXME: Temporary. Affiliation within Chinese uncertain; possibly Yue. m["zhx-dan"] = { "Danzhou Chinese", 2578935, "zh", } ------------- Chinese romanization varieties ------------- -- [[Wiktionary:Information desk/2022/June#Etymology Coding Issue]] -- [[Wiktionary:Grease pit/2022/June#Transliteration Systems in Etymologies 2]] m["cmn-pinyin"] = { "Hanyu Pinyin", 42222, "cmn", aliases = {"Pinyin"}, } m["cmn-tongyong"] = { "Tongyong Pinyin", 700739, "cmn", } m["cmn-wadegiles"] = { "Wade–Giles", 208442, "cmn", aliases = {"Wade-Giles", "Wade Giles"}, } m["zh-postal"] = { "Postal Romanization", 151868, "zh", } -- Chinese cyrillization m["cmn-palladius"] = { "Palladius", 1234239, "cmn", aliases = {"Palladius system"}, } ----------------------------------------------------- -- Tibetic varieties -- ----------------------------------------------------- m["adx"] = { "Amdo Tibetan", 56509, "bo", } m["kbg"] = { "Khamba", 12952626, "bo", } m["khg"] = { "Khams Tibetan", 56601, "bo", } m["tsk"] = { "Tseku", 11159532, "bo", } ---------------------------------------------------------------------------------------------------------------------- -- Tai-Kadai varieties -- ---------------------------------------------------------------------------------------------------------------------- m["th-old"] = { "Old Thai", nil, "tai-swe-pro", wikipedia_article = "Thai language#Old Thai", } m["th-suk"] = { "Sukhothai Old Thai", -- 1238-1438. Cannot use "Sukhothai Thai" as Sukhothai is the current city and "Sukhothai Thai" is a lect. nil, "th-old", aliases = {"Sukhothai Siamese"}, wikipedia_article = "Thai language#Old Thai", } m["th-ayu"] = { "Ayutthaya Old Thai", -- 1351-1767. Cannot use "Ayutthaya Thai" as Ayutthaya is the current city. nil, "th-old", aliases = {"Ayutthaya Siamese"}, wikipedia_article = "Thai language#Old Thai", } --[[ m["th-new"] = { "Hacked Thai", -- temporary for testing new translit/display methods nil, "th", translit = "User:Benwing2/th-scraping-translit", display_text = "User:Benwing2/th-scraping-translit", strip_diacritics = "User:Benwing2/th-scraping-translit", preprocess_links = "User:Benwing2/th-scraping-translit", } ]] m["tai-shz"] = { "Shangsi Zhuang", 13216, "za", } ---------------------------------------------------------------------------------------------------------------------- -- Turkic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["trk-cmn-pro"] = { "Proto-Common Turkic", 1126028, "trk-pro", } m["trk-ogr-pro"] = { "Proto-Oghur", 1422731, "trk-pro", family = "trk-ogr", } m["trk-bul-pro"] = { "Proto-Bulgar", nil, "trk-ogr-pro", } m["trk-ogz-pro"] = { "Proto-Oghuz", 494600, "trk-pro", family = "trk-ogz", aliases = {"Southwestern Common Turkic"}, } m["crh-dbj"] = { "Dobrujan Tatar", 12811566, "crh", aliases = {"Romanian Tatar"}, } m["cv-ana"] = { "Anatri Chuvash", nil, "cv", aliases = {"Anatri", "Lower Chuvash"}, } m["cv-mid"] = { "Middle Chuvash", nil, "cv", ancestors = "cv-old", } m["cv-old"] = { "Old Chuvash", nil, "cv", ancestors = "xbo-vol", } m["cv-vir"] = { "Viryal Chuvash", 4278332, "cv", aliases = {"Viryal", "Upper Chuvash"}, } m["kjh-fyu"] = { "Fuyu Kyrgyz", 2598963, "kjh", aliases = {"Fuyu Kirgiz", "Fuyu Kirghiz", "Manchurian Kyrgyz", "Manchurian Kirgiz", "Manchurian Kirghiz"}, } m["klj-arg"] = { "Arghu", 33455, "klj", ancestors = "trk-cmn-pro", } m["otk-kir"] = { "Old Kirghiz", 83142, "otk", aliases = {"Yenisei Turkic", "Yenisei Kyrgyz"}, } m["otk-ork"] = { "Orkhon Turkic", 31295480, "otk", } m["qwm-cum"] = { "Cuman", 1075050, "qwm", aliases = {"Kuman", "Polovtsian", "Polovcian"}, } m["qwm-arm"] = { "Armeno-Kipchak", 2027503, "qwm", ancestors = "qwm-cum", aliases = {"Xıpçaχ tili", "Tatarça"}, } m["qwm-mam"] = { "Mamluk-Kipchak", 4279942, "qwm", aliases = {"Mameluk-Kipchak"}, } m["az-cls"] = { "Azeri Klasikal", --TLCHANGE nil, "az", aliases = {"Classical Azeri"}, english_name = "Classical Azerbaijani", --TLCHANGE } m["qxq"] = { "Qashqai", 13192, "az", aliases = {"Qaşqay", "Qashqayi", "Kashkai", "Kashkay"}, } m["tr-CY"] = { "Cypriot Turkish", 7917392, "tr", } m["uz-afg"] = { -- NOTE: has ISO 639-3 code uzs assigned to it. "Afghan Uzbek", 1066787, "uz", aliases = {"Southern Uzbek"}, translit = "uz-afg-translit", } m["xbo-dan"] = { "Danube Bulgar", nil, "xbo", } m["xbo-vol"] = { "Volga Bulgar", nil, "xbo", } ---------------------------------------------------------------------------------------------------------------------- -- Uralic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["fiu-pro"] = { "Proto-Finno-Ugric", 79890, "urj-pro", } m["urj-fpr-pro"] = { "Proto-Finno-Permic", nil, "urj-pro", } m["krl-nor"] = { "North Karelian", 125501196, "krl", } m["krl-sou"] = { "South Karelian", 129812730, "krl", } m["mns-eas"] = { "Eastern Mansi", 30311755, "mns-cen", } m["mns-wes"] = { "Western Mansi", 30311756, "mns-cen", } ---------------------------------------------------------------------------------------------------------------------- -- Yeneseian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["qfa-yke-pro"] = { "Proto-Ketic", nil, "qfa-yen-pro", family = "qfa-yke", } m["qfa-yko-pro"] = { "Proto-Kottic", nil, "qfa-yen-pro", family = "qfa-yko", } m["qfa-yrn-pro"] = { "Proto-Arinic", nil, "qfa-yen-pro", family = "qfa-yrn", } m["qfa-ypm-pro"] = { "Proto-Pumpokolic", nil, "qfa-yen-pro", family = "qfa-ypm", } ---------------------------------------------------------------------------------------------------------------------- -- Miscellaneous varieties -- ---------------------------------------------------------------------------------------------------------------------- m["mul-tax"] = { "taxonomic name", 522190, "mul", } ----------------------------------------------------- -- Elamite varieties -- ----------------------------------------------------- m["elx-old"] = { "Old Elamite", nil, "elx", } m["elx-mid"] = { "Middle Elamite", nil, "elx", } m["elx-neo"] = { "Neo-Elamite", nil, "elx", } m["elx-ach"] = { "Achaemenid Elamite", nil, "elx", } ----------------------------------------------------- -- Substrates -- ----------------------------------------------------- -- Pre-Roman substrates m["qsb-ibe"] = { "Paleo-Hispanic", 246801, "und", family = "qfa-sub", aliases = {"Palaeo-Hispanic", "Paleohispanic", "Palaeohispanic", "Paleo-Iberian", "Palaeo-Iberian"}, } m["qsb-bal"] = { "Paleo-Balkan", 1815070, "und", family = "qfa-sub", aliases = {"Palaeo-Balkan", "Paleobalkan", "Palaeobalkan"}, } m["xaq"] = { "Aquitanian", 500522, "euq-pro", family = "euq", } -- TLCHANGE add these stuff BELOW THIS ----------------------------------------------------- -- Philippine languages varieties -- ----------------------------------------------------- --- Tagalog varieties, as per https://kwfwikaatkultura.ph/tagalog-2/ m["tl-nor"] = { "Kahilagaang Tagalog", nil, "tl", english_name = "Northern Tagalog", } m["tl-cen"] = { "Tagalog Sentral", nil, "tl", english_name = "Central Tagalog", } m["tl-sou"] = { "Katimugang Tagalog", 838580, "tl", english_name = "Southern Tagalog", } -- province codes based on https://en.wikipedia.org/wiki/ISO_3166-2:PH m["tl-bul"] = { "Tagalog Bulacan", 123900044, "tl-nor", aliases = {"Tagalog Bulakenyo", "Tagalog Bulakeño"}, english_name = "Bulacan Tagalog", } m["tl-ban"] = { "Tagalog Bataan", nil, "tl-nor", aliases = {"Tagalog Batanense"}, english_name = "Bataan Tagalog", } m["tl-nue"] = { "Tagalog Nueva Ecija", nil, "tl-nor", english_name = "Nueva Ecija Tagalog", } m["tl-aur"] = { "Tagalog Aurora", nil, "tl-sou", english_name = "Aurora Tagalog", } m["tl-riz"] = { "Tagalog Rizal", nil, "tl-cen", aliases = {"Tagalog Rizalenyo", "Tagalog Rizaleño"}, english_name = "Rizal Tagalog", } m["tl-cav"] = { "Tagalog Cavite", 97255128, "tl-sou", aliases = {"Tagalog Kabitenyo", "Tagalog Caviteño"}, english_name = "Cavite Tagalog", } m["tl-lag"] = { "Tagalog Laguna", nil, "tl-sou", aliases = {"Tagalog Lagunense"}, english_name = "Laguna Tagalog", } m["tl-btg"] = { "Tagalog Batangas", 4868610, "tl-sou", aliases = {"Tagalog Batanggenyo", "Tagalog Batangueño"}, english_name = "Batangas Tagalog", } m["tl-que"] = { "Tagalog Quezon", nil, "tl-sou", english_name = "Quezon Tagalog", } m["tl-mdo"] = { --made-up code "mdo" "Tagalog Mindoro", nil, "tl-sou", english_name = "Mindoro Tagalog", } m["tl-mad"] = { "Tagalog Marinduque", nil, "tl-sou", aliases = {"Tagalog Marindukenyo", "Tagalog Marinduqueño"}, english_name = "Marinduque Tagalog", } m["tl-can"] = { "Tagalog Camarines Norte", nil, "tl-sou", english_name = "Camarines Norte Tagalog", } -- other variants m["tl-bag"] = { "Tagalog Baguio", nil, "tl", english_name = "Baguio Tagalog", } m["tl-zho"] = { "Tagalog Tsinoy", nil, "tl", english_name = "Chinese Filipino Tagalog", } -------------- --- Ilocano varieties from https://kwfwikaatkultura.ph/ilokano/ m["ilo-nor"] = { "Ilokano Amianan", nil, "ilo", } m["ilo-sou"] = { "Ilokano Abagatan", nil, "ilo", } m["ilo-cvy"] = { "Ilokano Cagayan Valley", nil, "ilo", } m["ilo-car"] = { "Ilokano Kaigorotan", nil, "ilo", } -------------- --- Sebwano varieties from https://kwfwikaatkultura.ph/sebwano-2/ m["ceb-min"] = { "Binisayang Mindanaw", nil, "ceb", english_name = "Mindanao Cebuano", } m["ceb-min"] = { "Binul-anong Binisaya", nil, "ceb", english_name = "Boholano Cebuano", } m["ceb-sle"] = { "Katimugang Leyte Binisaya", nil, "ceb", english_name = "Southern Leyte Cebuano", } m["ceb-ner"] = { "Negrensing Binisaya", nil, "ceb", english_name = "Negros Cebuano", } m["ceb-mas"] = { "Masbatenyong Binisaya", nil, "ceb", english_name = "Negros Cebuano", } m["ceb-sig"] = { "Binisayang Siquijor", nil, "ceb", english_name = "Siquijor Cebuano", } -------------- --- Tinagbanwa varieties from https://kwfwikaatkultura.ph/ortograpiyang-tinagbanwa/ m["tbk-bat"] = { "Batuwanën", nil, "tbk", } m["tbk-sug"] = { "S̃ug̓udnun", nil, "tbk", } m["tbk-pul"] = { "Puluwanën", nil, "tbk", } -- TLCHANGE END ----------------------------------------------------- return require("Module:languages").finalizeData(m, "language", true) l8xzt5n32u0yre4sfo062yy2s4vxgas 176327 176313 2026-04-14T04:51:46Z Yivan000 4078 176327 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 = {} ---------------------------------------------------------------------------------------------------------------------- -- Afroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Berber varieties -- -------------------------------------------------------------------------------------- m["shi-med"] = { "Medieval Tashelhit", 34152, "shi", } -- Tuareg lects m["thv"] = { "Tamahaq", 56703, "tmh", } m["ttq"] = { "Tawellemmet", 56390, "tmh", } m["taq"] = { "Tamasheq", 4670066, "tmh", } m["thz"] = { "Tayert", 56388, "tmh", } m["thv-ght"] = { "Ghat", 47012900, "thv", } -------------------------------------------------------------------------------------- -- Cushitic varieties -- -------------------------------------------------------------------------------------- -- Oromo varieties m["hae"] = { "Harar Oromo", 5330355, "om", aliases = {"Eastern Oromo"}, } m["gax"] = { "Borana", 2910610, "om", aliases = {"Southern Oromo"}, } m["orc"] = { "Orma", 2919128, "om", } m["ssn"] = { "Waata", 3501553, "om", } -------------------------------------------------------------------------------------- -- Egyptian varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Ancient Egyptian varieties -- ----------------------------------------------------- m["egy-old"] = { "Old Egyptian", 447117, "egy", } m["egy-mid"] = { "Middle Egyptian", 657330, "egy", aliases = {"Classical Egyptian"}, } m["egy-nmi"] = { "Neo-Middle Egyptian", 123735278, "egy", aliases = {"Égyptien de tradition", "Traditional Egyptian"}, } m["egy-lat"] = { "Late Egyptian", 1852329, "egy", } ----------------------------------------------------- -- Coptic varieties -- ----------------------------------------------------- m["cop-akh"] = { "Akhmimic Coptic", 125176464, "cop", aliases = {"Akhmimic"}, } m["cop-boh"] = { "Bohairic Coptic", 890733, "cop", aliases = {"Bohairic", "Memphitic Coptic", "Memphitic"}, } m["cop-ggg"] = { "Coptic Dialect G", nil, "cop", aliases = {"Dialect G", "Mansuric Coptic", "Mansuric"}, } m["cop-jjj"] = { "Coptic Dialect J", nil, "cop", } m["cop-kkk"] = { "Coptic Dialect K", nil, "cop", } m["cop-ppp"] = { "Coptic Dialect P", nil, "cop", aliases = {"Proto-Theban Coptic", "Palaeo-Theban Coptic"}, } m["cop-fay"] = { "Fayyumic Coptic", 1399115, "cop", aliases = {"Fayyumic", "Faiyumic Coptic", "Faiyumic", "Fayumic Coptic", "Fayumic", "Bashmuric Coptic", "Bashmuric"}, } m["cop-her"] = { "Hermopolitan Coptic", nil, "cop", aliases = {"Hermopolitan", "Coptic Dialect H", "Ashmuninic", "Ashmuninic Coptic"}, } m["cop-lyc"] = { "Lycopolitan Coptic", nil, "cop", aliases = { "Lycopolitan", "Assiutic Coptic", "Asyutic Coptic", "Assiutic", "Asyutic", "Lyco-Diospolitan Coptic", "Lyco-Diospolitan", "Subakhmimic Coptic", "Subakhmimic" }, } m["cop-old"] = { "Old Coptic", 115518040, "cop", } m["cop-oxy"] = { "Oxyrhynchite Coptic", nil, "cop", aliases = {"Oxyrhynchite", "Mesokemic Coptic", "Mesokemic", "Middle Egyptian Coptic"}, } m["cop-ply"] = { "Proto-Lycopolitan Coptic", nil, "cop", aliases = {"Coptic Dialect i", "Proto-Lyco-Diospolitan Coptic"}, } m["cop-sah"] = { "Sahidic Coptic", 2645851, "cop", aliases = {"Sahidic", "Saidic Coptic", "Saidic", "Thebaic Coptic", "Thebaic"}, } -------------------------------------------------------------------------------------- -- Semitic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akkadian varieties -- ----------------------------------------------------- m["akk-old"] = { "Old Akkadian", nil, "akk", } m["akk-obb"] = { "Old Babylonian", nil, "akk", } m["akk-oas"] = { "Old Assyrian", nil, "akk", } m["akk-mbb"] = { "Middle Babylonian", nil, "akk", } m["akk-mas"] = { "Middle Assyrian", nil, "akk", } m["akk-nbb"] = { "Neo-Babylonian", nil, "akk", } m["akk-nas"] = { "Neo-Assyrian", nil, "akk", } m["akk-lbb"] = { "Late Babylonian", nil, "akk", } m["akk-stb"] = { "Standard Babylonian", nil, "akk", } ----------------------------------------------------- -- Arabic varieties -- ----------------------------------------------------- m["jrb"] = { "Hudeoarabe", --TLCHANGE 37733, "ar", pseudo_families = "qfa-jew", english_name = "Judeo-Arabic", --TLCHANGE spanish_name = "Judeoárabe", --TLCHANGE } m["apc-leb"] = { "Arabe Hilagang Levantino Libanes", --TLCHANGE 1516642, "apc", aliases = {"Lebanese Arabic"}, english_name = "Lebanese North Levantine Arabic", --TLCHANGE } m["apc-sle"] = { "Arabe Hilagang Levantino Timog Libanes", --TLCHANGE 14206590, "apc", aliases = {"South Lebanese Arabic"}, english_name = "South Lebanese North Levantine Arabic", --TLCHANGE } m["apc-nle"] = { "Arabe Hilagang Levantino Hilagang Libanes", --TLCHANGE nil, "apc", aliases = {"North Lebanese Arabic"}, english_name = "North Lebanese North Levantine Arabic", --TLCHANGE } m["apc-syr"] = { "Arabe Hilagang Levantino Siryo", --TLCHANGE 2143071, "apc", aliases = {"Syrian Arabic"}, english_name = "Syrian North Levantine Arabic", --TLCHANGE } m["apc-ale"] = { "Arabe Hilagang Levantino Alepino", --TLCHANGE 7056921, "apc-syr", aliases = {"Aleppo Arabic", "Aleppine Arabic"}, english_name = "Aleppine North Levantine Arabic", --TLCHANGE } m["apc-dam"] = { "Arabe Hilagang Levantino Damaseno", --TLCHANGE 12237466, "apc-syr", aliases = {"Damascus Arabic", "Damascene Arabic"}, english_name = "Damascene North Levantine Arabic", --TLCHANGE } m["acm-khu"] = { "Arabe Huzestani", --TLCHANGE 1040944, "acm", english_name = "Khuzestani Arabic", --TLCHANGE spanish_name = "Árabe juzestaní", --TLCHANGE } ----------------------------------------------------- -- Aramaic varieties -- ----------------------------------------------------- m["arc-bib"] = { "Biblical Aramaic", 843235, "arc", family = "sem-are", } m["arc-cpa"] = { "Christian Palestinian Aramaic", 60790119, "arc", family = "sem-arw", aliases = {"Melkite Aramaic", "Palestinian Syriac", "Syropalestinian Aramaic"}, } m["arc-imp"] = { "Imperial Aramaic", 7079491, "arc", aliases = {"Official Aramaic"}, } m["arc-hat"] = { "Hatran Aramaic", 3832926, "arc", family = "sem-are", } m["arc-jla"] = { "Jewish Literary Aramaic", 105952842, "arc", pseudo_families = "qfa-jew", } m["arc-nab"] = { "Nabataean Aramaic", 36178, "arc", } m["arc-old"] = { "Lumang Arameas", --TLCHANGE 3398392, "arc", english_name = "Old Aramaic", --TLCHANGE } m["arc-pal"] = { "Palmyrene Aramaic", 1510113, "arc", family = "sem-arw", } m["tmr"] = { "Jewish Babylonian Aramaic", 33407, "arc", family = "sem-ase", pseudo_families = "qfa-jew", } m["jpa"] = { "Jewish Palestinian Aramaic", 948909, "arc", family = "sem-arw", aliases = {"Galilean Aramaic"}, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Hebrew varieties -- ----------------------------------------------------- m["hbo"] = { "Biblical Hebrew", 1982248, "he", aliases = {"Classical Hebrew"}, } m["he-mis"] = { "Mishnaic Hebrew", 1649362, "he", ancestors = "hbo", } m["he-med"] = { "Medieval Hebrew", 2712572, "he", ancestors = "he-mis", } m["he-IL"] = { "Israeli Hebrew", 8141, "he", } ---------------------------------------------------------------------------------------------------------------------- -- Ainu varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ain-hok"] = { "Hokkaido Ainu", 20968488, "ain", aliases = {"Hokkaidō Ainu"}, } m["ain-kur"] = { "Kuril Ainu", 20967012, "ain", } m["ain-sak"] = { "Sakhalin Ainu", 20747371, "ain", } ---------------------------------------------------------------------------------------------------------------------- -- American indigenous varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Inuit varieties -- ----------------------------------------------------- m["esi"] = { "North Alaskan Inupiatun", nil, "ik" } m["esk"] = { "Northwest Alaskan Inupiatun", 25559714, "ik" } ----------------------------------------------------- -- Iroquoian varieties -- ----------------------------------------------------- m["iro-ohu"] = { "Old Wendat", nil, "wdt", } m["iro-omo"] = { "Old Mohawk", nil, "moh", } m["iro-oon"] = { "Old Onondaga", nil, "ono", } ----------------------------------------------------- -- Tupi-Guarani varieties -- ----------------------------------------------------- -- Old Tupi varieties m["tpw-lga"] = { "Língua Geral Amazônica", 18275323, "tpw", aliases = {"Língua Geral"}, } m["tpw-lgp"] = { "Língua Geral Paulista", 2669239, "tpw", } ---------------------------------------------------------------------------------------------------------------------- -- Austroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Khmer varieties m["okz-ang"] = { "Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } m["okz-pre"] = { "Pre-Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } -- Central Nicobarese varieties m["ncb-cam"] = { "Camorta", 5026908, "ncb", aliases = {"Kamorta"}, } m["ncb-kat"] = { "Katchal", 17064263, "ncb", aliases = {"Tehnu"}, } m["ncb-nan"] = { "Nancowry", 6962504, "ncb", aliases = {"Nankwari"}, } ---------------------------------------------------------------------------------------------------------------------- -- Austronesian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Malay and related varieties m["ms-old"] = { -- this has the ISO code 'omy' "Lumang Malayo", --TLCHANGE nil, "ms", english_name = "Old Malay", --TLCHANGE } m["ms-cla"] = { "Malay Klasikal", --TLCHANGE nil, "ms", ancestors = "ms-old", english_name = "Classical Malay", --TLCHANGE } m["pse-bsm"] = { "Besemah", nil, "pse", } m["bew-kot"] = { "Betawi Kota", nil, "bew", aliases = {"Urban Betawi"}, -- in Jakarta } -- Philippine varieties m["xnn"] = { "Kankanaëy Aplay", --TLCHANGE 12953609, "kne", aliases = {"Northern Kankanay", "Northern Kankana-ey"}, is_official_kwf_name = "https://kwfwikaatkultura.ph/kankanaey/", --TLCHANGE english_name = "Northern Kankanay" --TLCHANGE } m["tl-old"] = { "Lumang Tagalog", --TLCHANGE 12967437, "tl", english_name = "Old Tagalog", --TLCHANGE } m["tl-cls"] = { "Tagalog Klasikal", --TLCHANGE nil, "tl", english_name = "Classical Tagalog", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Caucasian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Kartvelian varieties m["ka-mid"] = { "Middle Georgian", nil, "ka", ancestors = "oge", } ---------------------------------------------------------------------------------------------------------------------- -- Dravidian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ta-mid"] = { "Middle Tamil", 20987434, "ta", } m["kn-hav"] = { "Havigannada", 24276369, "kn", } m["kn-kun"] = { "Kundagannada", 6444255, "kn", } ---------------------------------------------------------------------------------------------------------------------- -- Indo-European varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Albanian varieties -- -------------------------------------------------------------------------------------- m["aln"] = { "Gheg Albanian", 181037, "sq", aliases = {"Gheg"}, } m["aae"] = { "Arbëresh Albanian", 1075302, "als", aliases = {"Arbëreshë", "Arbëresh"}, } m["aat"] = { "Arvanitika Albanian", 29347, "als", aliases = {"Arvanitika"}, } m["als"] = { "Tosk Albanian", 180937, "sq", aliases = {"Tosk"}, } -------------------------------------------------------------------------------------- -- Armenian varieties -- -------------------------------------------------------------------------------------- m["hyw"] = { "Western Armenian", 180945, "hy", } m["hye"] = { "Eastern Armenian", 181059, "hy", } -------------------------------------------------------------------------------------- -- Balto-Slavic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Baltic varieties -- ------------------------------------------------------------------------- m["bat-pro"] = { "Proto-Baltic", 1703347, "ine-bsl-pro", } m["bat-dni"] = { "Dnieper Baltic", 4163178, "bat-pro", family = "bat", aliases = {"Dniepr Baltic", "Dnieper-Oka Baltic", "Dniepr-Oka Baltic"}, } m["bat-gol"] = { "Golyad", 4142855, "bat-dni", aliases = {"Eastern Galindian", "East Galindian"}, } ------------------------------------------------------------------------- -- Slavic varieties -- ------------------------------------------------------------------------- ----------------------------------------------------- -- Bulgarian varieties -- ----------------------------------------------------- m["cu-bgm"] = { "Middle Bulgarian", 12294897, "cu", ancestors = "cu" } ----------------------------------------------------- -- Church Slavonic varieties -- ----------------------------------------------------- -- Old Moscow Church Slavonic deleted as it seems not distinct enough from Russian (Synodal) Church Slavonic. m["zls-chs-ru"] = { "Russian Church Slavonic", 21662400, "zls-chs", aliases = {"Synodal Church Slavonic", "New Moscow Church Slavonic", "Novomoskovsk Church Slavonic"}, } m["zls-chs-uk"] = { "Ukrainian Church Slavonic", 12153548, "zls-chs", aliases = {"Rusyn Church Slavonic", "Belarusian Church Slavonic"}, } --[=[ -- Not sure about these yet. m["zls-chs-bg"] = { "Bulgarian Church Slavonic", nil, "zls-chs", } m["zls-chs-cs"] = { "Czech Church Slavonic", nil, "zls-chs", } m["zls-chs-hr"] = { "Croatian Church Slavonic", nil, "zls-chs", } m["zls-chs-mk"] = { "Macedonian Church Slavonic", nil, "zls-chs", } m["zls-chs-ro"] = { "Romanian Church Slavonic", nil, "zls-chs", } m["zls-chs-sr"] = { "Serbian Church Slavonic", nil, "zls-chs", } ]=] ----------------------------------------------------- -- Czech varieties -- ----------------------------------------------------- m["cs-ear"] = { "Early Modern Czech", nil, "cs", ancestors = "zlw-ocs" } ----------------------------------------------------- -- East Slavic varieties -- ----------------------------------------------------- m["zle-ops"] = { "Old Pskovian", 4167885, "zle-ono", } m["zle-mru"] = { "Middle Russian", 35228, "ru", "Cyrs", ancestors = "orv", translit = "ru-translit", strip_diacritics = { Cyrs = { remove_diacritics = c.grave .. c.acute .. c.diaer, }, }, } m["zle-mbe"] = { "Middle Belarusian", 13211, "zle-ort", } m["zle-muk"] = { "Middle Ukrainian", 13211, "zle-ort", } m["uk-CA"] = { "Canadian Ukrainian", 4161010, "uk", } ----------------------------------------------------- -- Polish varieties -- ----------------------------------------------------- m["zlw-mpl"] = { "Gitnang Polako", --TLCHANGE 402878, "pl", ancestors = "zlw-opl", strip_diacritics = { remove_diacritics = c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ó", "ó", "Ś", "ś", "Ź", "ź"}, }, english_name = "Middle Polish", --TLCHANGE } m["pl-gre"] = { "Greater Polish", 4106789, "pl", } m["pl-les"] = { "Lesser Polish", 361709, "pl", } m["pl-mas"] = { "Masovian Polish", 4274559, "pl", } m["pl-gor"] = { "Goral", 452889, "pl", } ----------------------------------------------------- -- Serbo-Croatian varieties -- ----------------------------------------------------- m["ckm"] = { "Serbokroata Tsakavo", --TLCHANGE 337565, "sh", aliases = {"Čakavian"}, english_name = "Chakavian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata chakavo", --TLCHANGE } m["kjv"] = { "Serbokroata Kaykavo", --TLCHANGE 838165, "sh", english_name = "Kajkavian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata kajkavo", --TLCHANGE } m["sh-tor"] = { -- Linguist code srp-tor "Serbokroata Torlak", --TLCHANGE 1078803, "sh", aliases = {"Torlak"}, english_name = "Torlakian Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata torlak", --TLCHANGE } -------------------------------------------------------------------------------------- -- Celtic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Brythonic varieties -- ----------------------------------------------------- m["bry-ear"] = { "Early Brythonic", nil, "cel-bry-pro", } m["bry-lat"] = { "Late Brythonic", nil, "cel-bry-pro", } ----------------------------------------------------- -- Gaulish varieties -- ----------------------------------------------------- m["xcg"] = { "Cisalpine Gaulish", 3832927, "cel-gau", } m["xtg"] = { "Transalpine Gaulish", 29977, "cel-gau", } ----------------------------------------------------- -- Welsh varieties -- ----------------------------------------------------- m["cy-nor"] = { "North Wales Welsh", 13127692, "cy", aliases = {"North Walian Welsh", "Northern Welsh"}, } m["cy-sou"] = { "South Wales Welsh", 13127689, "cy", aliases = {"South Walian Welsh", "Southern Welsh"}, } -------------------------------------------------------------------------------------- -- Germanic varieties -- -------------------------------------------------------------------------------------- -- Proto-West Germanic varieties m["frk"] = { "Frankish", 10860505, "gmw-pro", family = "gmw-frk", aliases = {"Old Frankish"}, } m["gem-sue"] = { "Suevic", 134600275, "gmw-pro", aliases = {"Suebian"}, } m["gmw-afr-pro"] = { "Proto-Anglo-Frisian", 134603379, "gmw-nsg-pro", family = "gmw-afr", } m["gmw-nsg-pro"] = { "Proto-North Sea Germanic", 134603374, "gmw-pro", family = "gmw-nsg", aliases = {"Proto-Ingvaeonic"}, } ----------------------------------------------------- -- Dutch varieties -- ----------------------------------------------------- m["nl-BE"] = { "Belgian Dutch", 34147, "nl", aliases = {"Flemish", "Flemish Dutch", "Southern Dutch"}, } ----------------------------------------------------- -- English and Scots varieties -- ----------------------------------------------------- -- English varieties m["en-AU"] = { "Ingles Awstralyano", --TLCHANGE 44679, "en", english_name = "Australian English", --TLCHANGE spanish_name = "Inglés australiano", --TLCHANGE } m["en-GB"] = { "Ingles Britaniko", --TLCHANGE 7979, "en", english_name = "British English", --TLCHANGE spanish_name = "Inglés británico", --TLCHANGE } m["en-GB-SCT"] = { "Ingles Eskoses", --TLCHANGE 44676, "en-GB", english_name = "Scottish English", --TLCHANGE spanish_name = "Inglés escocés", --TLCHANGE } m["en-GB-WLS"] = { "Ingles Gales", --TLCHANGE 44676, "en-GB", english_name = "Welsh English", --TLCHANGE spanish_name = "Inglés galés", --TLCHANGE } m["en-IM"] = { "Ingles Manes", --TLCHANGE 6753295, "en-GB", english_name = "Manx English", --TLCHANGE spanish_name = "Inglés Manés", --TLCHANGE } m["en-aae"] = { "Ingles Katutubong Awstralyano", --TLCHANGE 783347, "en-AU", english_name = "Australian Aboriginal English", --TLCHANGE } m["en-ear"] = { "Ingles Modernong Maaga", --TLCHANGE 1472196, "en", ancestors = "enm", aliases = {"Early New English"}, english_name = "Early Modern English", --TLCHANGE spanish_name = "Inglés moderno temprano", --TLCHANGE } m["en-geo"] = { "Geordie", 653421, "en", ancestors = "enm-nor", } m["en-IE"] = { -- FIXME: "IE" doesn't cover Northern Ireland "Ingles Irlandes", --TLCHANGE 665624, "en", english_name = "Irish English", --TLCHANGE spanish_name = "Inglés irlandés", --TLCHANGE } m["en-uls"] = { "Ingles Ulster", --TLCHANGE 6840826, "en-IE", english_name = "Ulster English", --TLCHANGE spanish_name = "Inglés en Úlster", --TLCHANGE } m["en-GB-NIR"] = { "Ingles Hilagang Irlandes", --TLCHANGE 6840826, -- actually the code for Ulster English "en-uls", english_name = "Northern Irish English", --TLCHANGE } m["en-NNN"] = { -- NA = Namibia; NNN is NATO 3-letter code for North America "Ingles Hilagang Amerikano", --TLCHANGE 7053766, "en", ietf_subtag = "en-021", -- 021 = UN M49 code for "Northern America" (i.e. North America wihout Central America or the Caribbean) english_name = "North American English", --TLCHANGE spanish_name = "Inglés norteamericano", --TLCHANGE } m["en-US"] = { "Ingles Amerikano", --TLCHANGE 7976, "en-NNN", english_name = "American English", --TLCHANGE spanish_name = "Inglés americano", --TLCHANGE } m["en-NZ"] = { "Ingles Neozelandes", --TLCHANGE 44661, "en", english_name = "New Zealand English", --TLCHANGE spanish_name = "Inglés neozelandés", --TLCHANGE this specifically refers to New Zealand English, different from Nueva Zelanda } m["en-ZA"] = { "Ingles Timog Afrikano", --TLCHANGE 1156228, "en", english_name = "South African English", --TLCHANGE spanish_name = "Inglés sudafricano", --TLCHANGE } m["en-US-CA"] = { "Ingles Kalifornya", --TLCHANGE 1026812, "en-US", english_name = "California English", --TLCHANGE spanish_name = "Inglés de California", --TLCHANGE } m["en-CA"] = { "Ingles Kanadyense", --TLCHANGE 44676, "en-US", english_name = "Canadian English", --TLCHANGE spanish_name = "Inglés canadiense", --TLCHANGE } m["en-HK"] = { "Ingles Hong Kong", --TLCHANGE 1068863, "en", english_name = "Hong Kong English", --TLCHANGE spanish_name = "Inglés en Hong Kong", --TLCHANGE } m["en-IN"] = { "Ingles Indyo", --TLCHANGE 1348800, "en", english_name = "Indian English", --TLCHANGE spanish_name = "Inglés indio", --TLCHANGE } m["pld"] = { "Polari", 1359130, "en", } -- Scots varieties m["sco-ins"] = { "Insular Scots", 16919205, "sco", } m["sco-uls"] = { "Ulster Scots", 201966, "sco", } m["sco-nor"] = { "Northern Scots", 16928150, "sco", } m["sco-sou"] = { "Southern Scots", 7570457, "sco", aliases = {"South Scots", "Borders Scots"}, } -- Middle English varieties m["enm-esc"] = { -- Part of Middle English until it developed into Middle Scots. "Early Scots", 5326738, "enm", ancestors = "enm-nor", aliases = {"Old Scots", "Scottish Middle English"}, } m["enm-emi"] = { "East Midland Middle English", 134238810, "enm", ancestors = "ang-ang", -- Technically ang-mer, but attested Mercian is mostly WM IIRC } m["enm-ken"] = { "Kentish Middle English", 134238532, "enm", ancestors = "ang-ken", } m["enm-nor"] = { "Northern Middle English", 134238541, "enm", ancestors = "ang-nor", } m["enm-sou"] = { "Southern Middle English", 134238528, "enm", ancestors = "ang-wsx", } m["enm-wmi"] = { "West Midland Middle English", 134238824, "enm", ancestors = "ang-mer", } -- Old English varieties -- Includes both Mercian and Northumbrian. m["ang-ang"] = { "Anglian Old English", 121142917, "ang", } m["ang-ken"] = { "Kentish Old English", 11687485, "ang", } m["ang-mer"] = { "Mercian Old English", 602072, "ang-ang", } m["ang-nor"] = { "Northumbrian Old English", 1798915, "ang-ang", } m["ang-wsx"] = { "West Saxon Old English", 2658603, "ang", } ----------------------------------------------------- -- High German varieties -- ----------------------------------------------------- -- (modern) German varieties m["de-AT"] = { "Austrian German", 306626, "de", } m["de-AT-vie"] = { "Viennese German", 56474, "de-AT", } m["de-CH"] = { "Switzerland German", 1366643, "de", aliases = {"Schweizer Hochdeutsch", "Swiss Standard German", "Swiss High German"}, } m["de-bal"] = { "Baltic German", 15785413, "de", } m["de-ear"] = { "Aleman Mataas na Bago na Maaga", --TLCHANGE 1472199, "de", ancestors = "gmh", aliases = {"Early Modern High German"}, english_name = "Early New High German", --TLCHANGE } m["ksh"] = { "Kölsch", 4624, "gmw-cfr", } m["pfl"] = { "Palatine German", 23014, "gmw-rfr", aliases = {"Pfälzisch", "Pälzisch", "Palatinate German"}, } m["sli"] = { "Silesian East Central German", 152965, "gmw-ecg", aliases = {"Silesian"}, } m["sxu"] = { "Upper Saxon German", 699284, "gmw-ecg", } -- Old High German varieties m["lng"] = { "Lombardic", 35972, "goh", } -- Alemannic German varieties m["gsw-low"] = { "Low Alemannic German", 503724, "gsw", } m["gsw-FR-als"] = { "Alsatian Alemannic German", 8786, "gsw-low", } m["gsw-hig"] = { "High Alemannic German", 503728, "gsw", } m["gsw-hst"] = { "Highest Alemannic German", 687538, "gsw", } m["wae"] = { "Walser German", 680517, "gsw-hst", } ----------------------------------------------------- -- Low German varieties -- ----------------------------------------------------- m["nds-de"] = { "German Low German", 25433, "nds", ietf_subtag = "nds-DE", -- should we make this the actual code? wikimedia_codes = "nds", } m["nds-nl"] = { "Dutch Low Saxon", 516137, "nds", ietf_subtag = "nds-NL", -- should we make this the actual code? wikimedia_codes = "nds-nl", } m["act"] = { "Achterhoeks", 153627, "nds-nl", aliases = {"Achterhoek", "Achterhooks"}, } m["drt"] = { "Drents", 2736709, "nds-nl", aliases = {"Drèents", "Dreins", "Dreints", "Drints"}, } m["frs"] = { "East Frisian Low German", 149208, "nds-de", aliases = {"East Frisian", "East Frisian Low Saxon"}, } m["gos"] = { "Gronings", 508854, "nds-nl", aliases = {"Grunnegs", "Grönnegs"}, } m["nds-lpr"] = { "Low Prussian", 33982, "nds-de", } m["sdz"] = { "Sallands", 3436668, "nds-nl", aliases = {"Sallaans", "Sallaands"}, } m["stl"] = { "Stellingwerfs", 506010, "nds-nl", aliases = {"Stellingwarfs"}, } m["twd"] = { "Twents", 497363, "nds-nl", aliases = {"Tweants"}, } m["vel"] = { "Veluws", 2484810, "nds-nl", } m["wep"] = { "Westphalian", 505655, "nds-de", aliases = {"Westfalish", "Westphalien"}, } ----------------------------------------------------- -- North Frisian varieties -- ----------------------------------------------------- m["frr-ins"] = { "Insular North Frisian", 110629610, "frr", } m["frr-fam"] = { "Föhr-Amrum North Frisian", 110629601, "frr-ins", } m["frr-foh"] = { "Föhr North Frisian", 28185, "frr-fam", aliases = {"Föhr Frisian", "Fering", "Ferring", -- Glottolog }, varieties = {"Aasdring", "Weesdring"}, } m["frr-amr"] = { "Amrum North Frisian", 28192, "frr-fam", aliases = {"Amrum Frisian", "Amrum", "Öömrang"}, } m["frr-hel"] = { "Heligoland North Frisian", 28086, "frr-ins", aliases = {"Heligoland Frisian", "Halunder", "Heligolandic Frisian", "Heligolandic North Frisian", "Helgoland Frisian", "Helgoland North Frisian", "Helgoland"}, } m["frr-syl"] = { "Sylt North Frisian", 28181, "frr-ins", aliases = {"Sylt Frisian", "Söl'ring", "Sölreng", -- Glottolog }, } m["frr-mai"] = { "Mainland North Frisian", 110629626, "frr", } m["frr-hal"] = { "Halligen North Frisian", 28177, "frr-mai", aliases = {"Halligen Frisian", "Halifreesk", "Hallingen Frisian", "Hallingen North Frisian", "Hallingen", -- Glottolog }, } m["frr-moo"] = { "Mooring North Frisian", 28187, "frr-mai", aliases = {"Bökingharde North Frisian", "Bökingharde Frisian", "Böökinghiirder frasch", "Mooring", "Moring", }, varieties = {{"East Mooring", "Ostermooring"}, {"West Mooring", "Westermooring"}}, } m["frr-kar"] = { "Karrharde North Frisian", 28191, "frr-mai", aliases = {"Karrharde Frisian", "Karrharder", }, } m["frr-goe"] = { -- Technically this refers to three adjacent dialects (Northern, Central and Southern), the latter of which went -- extinct in 1980-1981. As a result, Glottolog speaks of "Norder-Mittelgoesharde", referring to the remaining two. "Goesharde North Frisian", 28183, "frr-mai", aliases = {"Norder-Mittelgoesharde North Frisian", "Norder-Mittelgoesharde Frisian", "Norder-Mittelgoesharde", "Goesharde Frisian", "Goesharde", "Gooshiirder", }, } m["frr-wie"] = { "Wiedingharde North Frisian", 28171, "frr-mai", aliases = {"Wiedingharde Frisian", "Wiedingharde", "Wiringhiirder freesk", }, } ----------------------------------------------------- -- Old Norse varieties -- ----------------------------------------------------- m["non-grn"] = { "Greenlandic Norse", 855236, "non-own", } m["non-oen"] = { "Old East Norse", 10498031, "non", ancestors = "non", } m["non-own"] = { "Old West Norse", 2377483, "non", ancestors = "non", } ----------------------------------------------------- -- Old Swedish varieties -- ----------------------------------------------------- m["gmq-osw-lat"] = { "Late Old Swedish", 10723594, "gmq-osw", ancestors = "gmq-osw", } -------------------------------------------------------------------------------------- -- Greek varieties -- -------------------------------------------------------------------------------------- m["qsb-grc"] = { "Pre-Greek", 965052, "und", family = "qfa-sub", } m["grc-aeo"] = { "Aeolic Greek", 406373, "grc", aliases = {"Lesbic Greek", "Lesbian Greek", "Aeolian Greek"}, } m["grc-arc"] = { "Arcadian Greek", nil, "grc-arp", } m["grc-arp"] = { "Arcadocypriot Greek", 499602, "grc", } m["grc-att"] = { "Attic Greek", 506588, "grc", } m["grc-boi"] = { "Boeotian Greek", 406373, "grc-aeo", } m["grc-dor"] = { "Doric Greek", 285494, "grc", } m["grc-ela"] = { "Elean Greek", nil, "grc", } m["grc-epc"] = { "Epic Greek", 990062, "grc", aliases = {"Homeric Greek"}, } m["grc-ion"] = { "Ionic Greek", 504165, "grc", } m["grc-koi"] = { "Koine Greek", 107358, "grc", ancestors = "grc-att", aliases = {"Hellenistic Greek"}, } m["grc-kre"] = { "Cretan Ancient Greek", -- to distinguish from Cretan Greek below nil, "grc-dor", } m["grc-opl"] = { "Opuntian Locrian", nil, "grc", } m["grc-ozl"] = { "Ozolian Locrian", nil, "grc", } m["grc-pam"] = { "Pamphylian Greek", 2271793, "grc", } m["grc-ths"] = { "Thessalian Greek", 406373, "grc-aeo", } m["gkm"] = { "Byzantine Greek", 36387, "grc", ancestors = "grc-koi", aliases = {"Medieval Greek"}, } m["el-cyp"] = { "Cypriot Greek", 245899, "el", aliases = {"Cypriotic Greek"}, } m["el-pap"] = { "Paphian Greek", nil, "el", } m["el-crt"] = { "Cretan Greek", 588306, "el", } m["el-kth"] = { "Katharevousa", 35961, "el", "Polyt", ancestors = "gkm", aliases = {"Katharevousa Greek"}, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["el-kal"] = { "Kaliarda", 12878658, "el", } -------------------------------------------------------------------------------------- -- Indo-Iranian varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Indo-Aryan varieties -- ------------------------------------------------------------------------- -- reconstructed intermediate stages m["pra-pro"] = { "Proto-New Indo-Aryan", nil, "pra", } m["inc-ash-pro"] = { "Proto-Middle Indo-Aryan", nil, "inc-ash", } m["inc-mit"] = { "Mitanni", 1986700, "inc-pro", } m["bra-old"] = { "Old Braj", nil, "bra", } -- Apabhramsas m["inc-aav"] = { "Avahattha", nil, "inc-apa", aliases = {"Abahattha"}, } m["inc-asa"] = { "Sauraseni Apabhramsa", nil, "inc-apa", } m["inc-agu"] = { "Gurjara Apabhramsa", nil, "inc-apa", } m["inc-aka"] = { "Kasmiri Apabhramsa", nil, "inc-apa", } m["inc-ama"] = { "Maharastri Apabhramsa", nil, "inc-apa", } m["inc-ata"] = { "Takka Apabhramsa", nil, "inc-apa", } m["inc-avr"] = { "Vracada Apabhramsa", nil, "inc-apa", } -- Assamese varieties m["as-bkm"] = { "Barpetia Kamrupi Assamese", 30642960, "as", } m["as-nkm"] = { "Nalbaria Kamrupi Assamese", 85787678, "as", } m["as-pkm"] = { "Palasbaria Kamrupi Assamese", nil, "as", } -- Bengali varieties m["bn-dvn"] = { "Dhakaiya Vaṅga Bengali", 48726851, "bn", -- Eastern Bengali variety } m["bn-nvn"] = { "Noakhailla Vaṅga Bengali", 107548681, "bn", -- Eastern Bengali variety } -- Dhivehi varieties m["dv-old"] = { "Old Dhivehi", 117790875, "dv", } m["dv-mul"] = { "Mulaku Dhivehi", nil, "dv", aliases = {"Mulaku Divehi", "Mulaku Bas"}, } m["dv-huv"] = { "Huvadhu Dhivehi", nil, "dv", aliases = {"Huvadhu Divehi", "Huvadhu Bas"}, } m["dv-add"] = { "Addu Dhivehi", nil, "dv", aliases = {"Addu Divehi", "Addu Bas"}, } -- Gujarati varieties m["gu-kat"] = { "Kathiyawadi", nil, "gu", aliases = {"Kathiyawadi Gujarati", "Kathiawadi"}, } m["gu-lda"] = { "Lisan ud-Dawat Gujarati", nil, "gu", aliases = {"Lisan ud-Dawat", "LDA"}, } -- Hindi varieties m["hi-mum"] = { "Bombay Hindi", 3543151, "hi", aliases = {"Mumbai Hindi", "Bambaiyya Hindi"}, } m["hi-mid"] = { "Middle Hindi", nil, "inc-ohi", ancestors = "inc-ohi", } -- Konkani varieties m["kok-mid"] = { "Middle Konkani", nil, "kok", aliases = {"Medieval Konkani"}, } m["kok-old"] = { "Old Konkani", nil, "kok", aliases = {"Early Konkani"}, } -- Prakrits m["pra-ard"] = { "Ardhamagadhi Prakrit", 35217, "pra", aliases = {"Ardhamagadhi"}, } m["pra-hel"] = { "Helu Prakrit", 15080869, "pra", aliases = {"Elu", "Elu Prakrit", "Helu"}, } m["pra-kha"] = { "Khasa Prakrit", nil, "pra", aliases = {"Khasa"}, } m["pra-mag"] = { "Magadhi Prakrit", -- Not to be confused with Magahi (mag) 2652214, "pra", aliases = {"Magadhi"}, } m["pra-mah"] = { "Maharastri Prakrit", 2586773, "pra", aliases = {"Maharashtri Prakrit", "Maharastri", "Maharashtri"}, } m["pra-pai"] = { "Paisaci Prakrit", 2995607, "pra-sau", aliases = {"Paisaci", "Paisachi"}, ancestors = "pra-sau" } m["pra-sau"] = { "Sauraseni Prakrit", 2452885, "pra", aliases = {"Sauraseni", "Shauraseni"}, } m["pra-ava"] = { "Avanti", nil, "pra", aliases = {"Avanti Prakrit"}, } m["pra-pra"] = { "Pracya", nil, "pra", aliases = {"Pracya Prakrit"}, } m["pra-bah"] = { "Bahliki", nil, "pra", aliases = {"Bahliki Prakrit"}, } m["pra-dak"] = { "Daksinatya", nil, "pra", aliases = {"Daksinatya Prakrit"}, } m["pra-sak"] = { "Sakari", nil, "pra", aliases = {"Sakari Prakrit"}, } m["pra-can"] = { "Candali", nil, "pra", aliases = {"Candali Prakrit"}, } m["pra-sab"] = { "Sabari", nil, "pra", aliases = {"Sabari Prakrit"}, } m["pra-abh"] = { "Abhiri", nil, "pra", aliases = {"Abhiri Prakrit"}, } m["pra-dra"] = { "Dramili", nil, "pra", aliases = {"Dramili Prakrit"}, } m["pra-odr"] = { "Odri", nil, "pra", aliases = {"Odri Prakrit"}, } -- Punjabi varieties m["pnb"] = { "Western Punjabi", 58635, "pa", "pa-Arab", } -- Sanskrit varieties m["vsn"] = { "Vedic Sanskrit", 36858, "sa", } m["cls"] = { "Classical Sanskrit", 11059, "sa", } m["sa-bhs"] = { "Buddhist Hybrid Sanskrit", 248758, "sa", } m["sa-bra"] = { "Brahmanic Sanskrit", 36858, "sa", } m["sa-neo"] = { "New Sanskrit", 11059, "sa", } -- Sinhalese varieties m["si-med"] = { "Medieval Sinhalese", nil, "si", aliases = {"Medieval Sinhala"}, } ------------------------------------------------------------------------- -- Iranian varieties -- ------------------------------------------------------------------------- m["qsb-bma"] = { "the BMAC substrate", 133187435, "und", family = "qfa-sub", aliases = {"the Bactria-Margiana substrate", "the Bactria-Margiana Archaeological Complex substrate"}, } -- Historical and current Iranian dialects m["ae-old"] = { "Old Avestan", 29572, "ae", aliases = {"Gathic Avestan"}, } m["ae-yng"] = { "Younger Avestan", 29572, "ae-old", aliases = {"Young Avestan"}, } m["bcc"] = { "Southern Balochi", 33049, "bal", aliases = {"Southern Baluchi"}, } m["bgp"] = { "Eastern Balochi", 33049, "bal", aliases = {"Eastern Baluchi"}, } m["bgn"] = { "Western Balochi", 33049, "bal", aliases = {"Western Baluchi"}, } m["bsg-ban"] = { "Bandari", nil, "bsg", } m["bsg-hor"] = { "Hormozi", nil, "bsg", } m["bsg-min"] = { "Minabi", nil, "bsg", } m["kho-old"] = { "Old Khotanese", nil, "kho", } m["kho-lat"] = { "Late Khotanese", nil, "kho-old", } m["peo-ear"] = { "Early Old Persian", nil, "peo", } m["peo-lat"] = { "Late Old Persian", nil, "peo", } m["pal-ear"] = { "Early Middle Persian", nil, "pal", } m["pal-lat"] = { "Late Middle Persian", nil, "pal", ancestors = "pal-ear", } m["ps-nwe"] = { "Northwestern Pashto", nil, "ps", } m["ps-cgi"] = { "Central Ghilzay", nil, "ps-nwe", } m["ps-mah"] = { "Mahsudi", nil, "ps-nwe", } m["ps-nea"] = { "Northeastern Pashto", nil, "ps", } m["ps-afr"] = { "Afridi", nil, "ps-nea", } m["ps-bng"] = { "Bangash", nil, "ps-nea", } m["ps-xat"] = { "Khatak", nil, "ps-nea", } m["ps-pes"] = { "Peshawari", nil, "ps-nea", } m["ps-sea"] = { "Timog Silanganing Pastun", --TLCHANGE nil, "ps", english_name = "Southeastern Pashto", --TLCHANGE } m["ps-ban"] = { "Bannu", nil, "ps-sea", } m["ps-kak"] = { "Kakari", nil, "ps-sea", } m["ps-ser"] = { "Sher", nil, "ps-sea", } m["ps-waz"] = { "Waziri", 12274473, "ps-sea", } m["ps-swe"] = { "Timog Kanluraning Pastun", --TLCHANGE nil, "ps", english_name = "Southwestern Pashto", --TLCHANGE } m["ps-kan"] = { "Kandahari", nil, "ps-swe", } m["ps-jad"] = { "Jadrani", nil, "ps", ancestors = "ira-pat-pro" } m["xme-azr"] = { "Old Azari", nil, "xme-ott", aliases = {"Old Azeri", "Azari", "Azeri", "Āḏarī", "Adari", "Adhari"}, } m["xme-ttc-cen"] = { "Central Tati", nil, "xme-ott", } m["xme-ttc-eas"] = { "Eastern Tati", nil, "xme-ott", } m["xme-ttc-nor"] = { "Northern Tati", nil, "xme-ott", } m["xme-ttc-sou"] = { "Southern Tati", nil, "xme-ott", } m["xme-ttc-wes"] = { "Western Tati", nil, "xme-ott", } m["xmn"] = { "Manichaean Middle Persian", nil, "pal-lat", } m["fa-ear"] = { "Early New Persian", 127413796, "fa", ancestors = "pal-lat", translit = "fa-cls-translit", } m["fa-cls"] = { "Classical Persian", 9168, "fa", ancestors = "fa-ear", translit = "fa-cls-translit", } m["fa-ira"] = { "Iranian Persian", 3513637, "fa", aliases = {"Modern Persian", "Western Persian"}, translit = "fa-ira-translit", } m["prs"] = { "Dari", 178440, "fa", aliases = {"Dari Persian", "Central Persian", "Eastern Persian", "Afghan Persian"}, translit = "fa-cls-translit", } m["haz"] = { "Hazaragi", 33398, "prs", translit = "fa-cls-translit", } m["os-dig"] = { "Digor Ossetian", 3027861, "os", aliases = {"Digoron", "Digor"}, } m["os-iro"] = { "Iron Ossetian", nil, "os", aliases = {"Iron"}, } m["sog-ear"] = { "Early Sogdian", nil, "sog", } m["sog-lat"] = { "Late Sogdian", nil, "sog-ear", } m["ro-MD"] = { "Moldavo", --TLCHANGE 36392, "ro", aliases = {"Moldavian"}, english_name = "Moldovan", --TLCHANGE spanish_name = "Moldavo", --TLCHANGE } m["oru-kan"] = { "Kaniguram", 6363164, "oru", } m["oru-log"] = { "Logar", nil, "oru", } m["oos"] = { "Old Ossetic", 65455882, "xln", } m["oos-ear"] = { "Early Old Ossetic", nil, "oos", } m["oos-lat"] = { "Late Old Ossetic", nil, "oos", } m["rdb-jir"] = { "Jirofti", nil, "rdb", } m["rdb-kah"] = { "Kahnuji", nil, "rdb", } -- Southwestern Fars lects m["fay-bur"] = { "Burenjani", nil, "fay", } m["fay-bsh"] = { "Bushehri", nil, "fay", } m["fay-dsh"] = { "Dashtaki", nil, "fay", } m["fay-dav"] = { "Davani", 5228140, "fay", } m["fay-eze"] = { "Emamzada Esmaili", nil, "fay", } m["fay-gav"] = { "Gavkoshaki", nil, "fay", } m["fay-kho"] = { "Khollari", nil, "fay", } m["fay-kon"] = { "Kondazi", nil, "fay", } m["fay-kzo"] = { "Old Kazeruni", nil, "fay", } m["fay-mas"] = { "Masarami", nil, "fay", } m["fay-pap"] = { "Papuni", nil, "fay", } m["fay-sam"] = { "Samghani", nil, "fay", } m["fay-shr"] = { "Shirazi", nil, "fay", } m["fay-sho"] = { "Old Shirazi", nil, "fay", } m["fay-kar"] = { "Khargi", nil, "fay", } m["fay-sor"] = { "Sorkhi", nil, "fay", } -- Talysh lects m["tly-cen"] = { "Central Talysh", nil, "tly", } m["tly-asa"] = { "Asalemi", nil, "tly-cen", } m["tly-kar"] = { "Karganrudi", nil, "tly-cen", } m["tly-tul"] = { "Tularudi", nil, "tly-cen", } m["tly-tal"] = { "Taleshdulabi", nil, "tly-cen", } m["tly-nor"] = { "Northern Talysh", nil, "tly", } m["tly-aze"] = { "Azerbaijani Talysh", nil, "tly-nor", } m["tly-anb"] = { "Anbarani", nil, "tly-nor", } m["tly-sou"] = { "Southern Talysh", nil, "tly", } m["tly-fum"] = { "Fumani", nil, "tly-sou", } m["tly-msu"] = { "Masulei", nil, "tly-sou", } m["tly-msa"] = { "Masali", nil, "tly-sou", } m["tly-san"] = { "Shandarmani", nil, "tly-sou", } -- Tafreshi lects m["xme-amo"] = { "Amorehi", nil, "xme-taf", } m["atn"] = { "Ashtiani", 3436590, "xme-taf", } m["xme-bor"] = { "Borujerdi", nil, "xme-taf", } m["xme-ham"] = { "Hamadani", 6302426, "xme-taf", } m["xme-kah"] = { "Kahaki", nil, "xme-taf", } m["vaf"] = { "Vafsi", 32611, "xme-taf", } -- Kermanic lects m["kfm"] = { "Khunsari", 6403030, "xme-ker", } m["xme-mah"] = { "Mahallati", nil, "xme-ker", } m["xme-von"] = { "Vonishuni", nil, "xme-ker", } m["xme-bdr"] = { "Badrudi", nil, "xme-ker", } m["xme-del"] = { "Delijani", nil, "xme-ker", } m["xme-kas"] = { "Kashani", nil, "xme-ker", } m["xme-kes"] = { "Kesehi", nil, "xme-ker", } m["xme-mey"] = { "Meymehi", nil, "xme-ker", } m["ntz"] = { "Natanzi", 6968399, "xme-ker", } m["xme-abz"] = { "Abuzeydabadi", nil, "xme-ker", } m["xme-aby"] = { "Abyanehi", nil, "xme-ker", } m["xme-far"] = { "Farizandi", nil, "xme-ker", } m["xme-jow"] = { "Jowshaqani", nil, "xme-ker", } m["xme-nas"] = { "Nashalji", nil, "xme-ker", } m["xme-qoh"] = { "Qohrudi", nil, "xme-ker", } m["xme-yar"] = { "Yarandi", nil, "xme-ker", } m["soj"] = { "Soi", 7930463, "xme-ker", aliases = {"Sohi"}, } m["xme-tar"] = { "Tari", nil, "xme-ker", } m["gzi"] = { "Gazi", 5529130, "xme-ker", } m["xme-sed"] = { "Sedehi", nil, "xme-ker", } m["xme-ard"] = { "Ardestani", nil, "xme-ker", } m["xme-zef"] = { "Zefrehi", nil, "xme-ker", } m["xme-isf"] = { "Isfahani", nil, "xme-ker", } m["xme-kaf"] = { "Kafroni", nil, "xme-ker", } m["xme-vrz"] = { "Varzenehi", nil, "xme-ker", } m["xme-xur"] = { "Khuri", nil, "xme-ker", } m["nyq"] = { "Nayini", 6983146, "xme-ker", } m["xme-ana"] = { "Anaraki", nil, "xme-ker", } m["gbz"] = { "Zoroastrian Dari", 32389, "xme-ker", aliases = {"Behdināni", "Gabri", "Gavrŭni", "Gabrōni"}, } m["xme-krm"] = { "Kermani", nil, "xme-ker", } m["xme-yaz"] = { "Yazdi", nil, "xme-ker", } m["xme-bid"] = { "Bidhandi", nil, "xme-ker", } m["xme-bij"] = { "Bijagani", nil, "xme-ker", } m["xme-cim"] = { "Chimehi", nil, "xme-ker", } m["xme-han"] = { "Hanjani", nil, "xme-ker", } m["xme-kom"] = { "Komjani", nil, "xme-ker", } m["xme-nar"] = { "Naraqi", nil, "xme-ker", } m["xme-nus"] = { "Nushabadi", nil, "xme-ker", } m["xme-qal"] = { "Qalhari", nil, "xme-ker", } m["xme-trh"] = { "Tarehi", nil, "xme-ker", } m["xme-val"] = { "Valujerdi", nil, "xme-ker", } m["xme-var"] = { "Varani", nil, "xme-ker", } m["xme-zor"] = { "Zori", nil, "xme-ker", } -- Ramandi lects m["tks-ebr"] = { "Ebrahimabadi", nil, "tks", } m["tks-sag"] = { "Sagzabadi", nil, "tks", } m["tks-esf"] = { "Esfarvarini", nil, "tks", } m["tks-tak"] = { "Takestani", nil, "tks", } m["tks-cal"] = { "Chali Tati", nil, "tks", aliases = {"Chāli"}, } m["tks-dan"] = { "Danesfani", nil, "tks", } m["tks-xia"] = { "Khiaraji", nil, "tks", } m["tks-xoz"] = { "Khoznini", nil, "tks", } -- Shughni dialects m["sgh-bro"] = { "Bartangi-Oroshori", nil, "sgh", } m["sgh-bar"] = { "Bartangi", nil, "sgh-bro", } m["sgh-oro"] = { "Oroshori", nil, "sgh-bro", aliases = {"Roshorvi"}, } m["sgh-rsx"] = { "Roshani-Khufi", nil, "sgh", } m["sgh-xuf"] = { "Khufi", 2562249, "sgh-rsx", aliases = {"Xufi", "Xūfī"}, } m["sgh-ros"] = { "Roshani", 2597566, "sgh-rsx", aliases = {"Rushani", "Rōšāni"}, } m["sgh-xgb"] = { "Khughni-Bajui", nil, "sgh", } m["sgh-xug"] = { "Khughni", nil, "sgh-xgb", } m["sgh-baj"] = { "Bajui", nil, "sgh-xgb", } ------------------------------------------------------------------------- -- Nuristani varieties -- ------------------------------------------------------------------------- m["bsh-kat"] = { "Kativiri", 2605045, "bsh", aliases = {"Katə́viri"}, } m["xvi"] = { "Kamviri", 1193495, "bsh", aliases = {"Kamvíri"}, } m["bsh-mum"] = { "Mumviri", nil, "bsh", aliases = {"Mumvíri"}, } -------------------------------------------------------------------------------------- -- Italic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Latin varieties -- ------------------------------------------------------------------------- -- Latin varieties by period m["itc-ola"] = { "Old Latin", 12289, "la", "Latn, Ital", translit = { Ital = "Ital-translit" }, } m["itc-lan"] = { "Lanuvian", 16890829, "itc-ola", aliases = {"Lanuvine"}, } m["itc-pra"] = { "Praenestine", 16889772, "itc-ola", aliases = {"Praenestinian"}, } m["la-cla"] = { "Classical Latin", 253854, "la", } m["la-vul"] = { "Vulgar Latin", 37560, "la-cla", } m["la-afr"] = { "African Romance", 162064, "roa-pro", } m["la-lat"] = { "Late Latin", 1503113, "la", ancestors = "la-cla", } m["la-med"] = { "Medieval Latin", 1163234, "la", ancestors = "la-lat", } m["la-eme"] = { "Early Medieval Latin", nil, "la-med", } m["la-ecc"] = { "Ecclesiastical Latin", 1247932, "la", aliases = {"Church Latin", "Liturgical Latin"}, ancestors = "la-lat", } m["la-ren"] = { "Renaissance Latin", 499083, "la", ancestors = "la-med", } m["la-new"] = { "New Latin", 1248221, "la", aliases = {"Modern Latin"}, ancestors = "la-ren", } m["la-con"] = { "Contemporary Latin", 1246397, "la-new", } ------------------------------------------------------------------------- -- Miscellaneous Italic varieties -- ------------------------------------------------------------------------- m["xfa-cap"] = { "Capenate", 133182969, "xfa", } m["osc-luc"] = { "Lucanian", 3265025, "osc", } m["osc-sam"] = { "Samnite", 133184287, "osc", } ------------------------------------------------------------------------- -- Romance varieties -- ------------------------------------------------------------------------- m["roa-pro"] = { "Proto-Romance", 3408029, "la-lat", ancestors = "la-vul", } ----------------------------------------------------- -- Catalan varieties -- ----------------------------------------------------- m["ca-val"] = { "Valencian", 32641, "ca", } ----------------------------------------------------- -- Franco-Provençal varieties -- ----------------------------------------------------- m["frp-old"] = { "Old Franco-Provençal", nil, "frp", } ----------------------------------------------------- -- French and derived creole varieties -- ----------------------------------------------------- m["fro-nor"] = { "Old Northern French", 2044917, "fro", aliases = {"Old Norman", "Old Norman French"}, } m["fro-pic"] = { "Picard Old French", nil, "fro", } m["xno"] = { "Anglo-Norman", 35214, "fro-nor", } m["xno-law"] = { "Law French", 2044323, "xno", } m["zrp"] = { "Zarphatic", 36994, "fro", aliases = {"Judeo-French"}, pseudo_families = "qfa-jew", } m["fr-CA"] = { "Canadian French", 1450506, "fr", } m["fr-CH"] = { "Swiss French", 1480152, "fr", } m["fr-aca"] = { "Acadian French", 415109, "fr", } m["fr-lou"] = { "Louisiana French", 3083213, "fr", } m["fr-mis"] = { "Missouri French", 3083210, "fr", } m["frc"] = { "Cajun French", 880301, "fr-lou", } m["ht-sdm"] = { "Saint Dominican Creole French", nil, "ht", ancestors = "fr", } -- Norman varieties m["nrf-grn"] = { "Guernsey Norman", 56428, "nrf", aliases = {"Guernsey"}, } m["nrf-jer"] = { "Jersey Norman", 56430, "nrf", aliases = {"Jersey"}, } ----------------------------------------------------- -- Gallo-Italic varieties -- ----------------------------------------------------- m["egl-old"] = { "Old Emilian", nil, "egl", } m["lij-old"] = { "Old Ligurian", nil, "lij", aliases = {"Old Genoese"}, } m["lmo-old"] = { "Old Lombard", 97165320, "lmo", } m["pms-old"] = { "Old Piedmontese", nil, "pms", aliases = {"Old Piemontese"}, } m["vec-old"] = { "Old Venetan", nil, "vec", aliases = {"Old Venetian"}, } m["rgn-old"] = { "Old Romagnol", nil, "rgn", } ----------------------------------------------------- -- Italo-Romance varieties -- ----------------------------------------------------- -- Italian varieties m["roa-oit"] = { "Old Italian", nil, "it", } m["it-CH"] = { "Switzerland Italian", 672147, "it", } -- Other Italo-Romance varieties m["nap-old"] = { "Old Neapolitan", nil, "nap", } m["scn-old"] = { "Old Sicilian", nil, "scn", } ----------------------------------------------------- -- Occitan varieties -- ----------------------------------------------------- m["oc-auv"] = { "Auvergnat", 35359, "oc", aliases = {"Auvernhat", "Auvergnese"}, } m["oc-gas"] = { "Gaskon", --TLCHANGE 35735, "oc", english_name = "Gascon", --TLCHANGE spanish_name = "Gascón", --TLCHANGE } -- standardized dialect of Gascon m["oc-ara"] = { "Aranes", --TLCHANGE 10196, "oc-gas", english_name = "Aranese", --TLCHANGE spanish_name = "Aranés", --TLCHANGE } m["oc-lan"] = { "Languedocien", 942602, "oc", aliases = {"Lengadocian"}, } m["oc-lim"] = { "Limousin", 427614, "oc", } m["oc-pro"] = { "Provençal", 241243, "oc", aliases = {"Provencal"}, } m["oc-pro-old"] = { "Old Provençal", 2779185, "pro", } m["oc-viv"] = { "Vivaro-Alpine", 1649613, "oc", } m["oc-jud"] = { "Shuadit", 56472, "oc", aliases = { "Chouhadite", "Chouhadit", "Chouadite", "Chouadit", "Shuhadit", "Judeo-Occitan", "Judæo-Occitan", "Judaeo-Occitan", "Judeo-Provençal", "Judæo-Provençal", "Judaeo-Provençal", "Judeo-Provencal", "Judaeo-Provencal", "Judeo-Comtadin", "Judæo-Comtadin", "Judaeo-Comtadin", }, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Portuguese and derived creole varieties -- ----------------------------------------------------- -- Portuguese m["pt-BR"] = { "Portugues Brasileño", --TLCHANGE 750553, "pt", english_name = "Brazilian Portuguese", --TLCHANGE spanish_name = "Portugués brasileño", --TLCHANGE } m["pt-PT"] = { "Portugues Europeo", --TLCHANGE 922399, "pt", english_name = "European Portuguese", --TLCHANGE spanish_name = "Portugués europeo", --TLCHANGE } -- Kabuverdianu (Cape Verde Creole, Cape Verdean Creole) m["kea-bar"] = { "Barlavento Kabuverdianu", 2217638, "kea", aliases = {"Barlavento", "Barlavento Creole", "Sampadjudu"}, } m["kea-bvi"] = { "Boa Vista Kabuverdianu", 16501837, "kea-bar", aliases = {"Boa Vista Creole"}, } m["kea-sal"] = { "Sal Kabuverdianu", 18707467, "kea-bar", aliases = {"Sal Creole"}, } m["kea-saa"] = { "Santo Antão Kabuverdianu", 18707472, "kea-bar", aliases = {"Santo Antão Creole"}, } m["kea-sni"] = { "São Nicolau Kabuverdianu", 18707549, "kea-bar", aliases = {"São Nicolau Creole"}, } m["kea-svi"] = { "São Vicente Kabuverdianu", 18707550, "kea-bar", aliases = {"São Vicente Creole"}, } m["kea-sot"] = { "Sotavento Kabuverdianu", 10261559, "kea", aliases = {"Sotavento", "Sotavento Creole", "Badiu"}, } m["kea-bra"] = { "Brava Kabuverdianu", 18670181, "kea-sot", aliases = {"Brava Creole"}, } m["kea-fog"] = { "Fogo Kabuverdianu", 18706861, "kea-sot", aliases = {"Fogo Creole"}, } m["kea-mai"] = { "Maio Kabuverdianu", 18707286, "kea-sot", aliases = {"Maio Creole"}, } m["kea-san"] = { "Santiago Kabuverdianu", 35117, "kea-sot", aliases = {"Santiago Creole"}, } m["kea-alu"] = { "ALUPEC Kabuverdianu", 375704, "kea", aliases = {"ALUPEC", "Alfabeto Unificado para a Escrita do Cabo-Verdiano"}, } ----------------------------------------------------- -- Rhaeto-Romance varieties -- ----------------------------------------------------- -- Friulian varieties m["fur-old"] = { "Old Friulian", nil, "fur", } -- Ladin varieties m["lld-amp"] = { "Ampezan Ladin", 25617466, "lld", aliases = {"Anpezan", "Ampezan", "Ampezzan", "Ampezzano"}, } m["lld-bad"] = { "Badiot Ladin", 3706562, "lld", aliases = {"Badiot", "Badioto", "Badiotto"}, } m["lld-cad"] = { "Cadorino Ladin", 3706570, "lld", aliases = {"Cadorino"}, } m["lld-fas"] = { "Fascian Ladin", 742627, "lld", aliases = {"Fascian", "Fassano"}, } m["lld-fod"] = { "Fodom Ladin", 3706605, "lld", aliases = {"Fodom", "Livinallese"}, } m["lld-for"] = { "Fornes Ladin", 5470374, "lld", aliases = {"Fornes"}, } m["lld-ghe"] = { "Gherdëina Ladin", 3706597, "lld", aliases = {"Gherdëina", "Gardenese", "Val Gardena"}, } m["lld-non"] = { "Nones Ladin", 1055027, "lld", aliases = {"Nones", "Noneso"}, } -- Romansh varieties m["rm-old"] = { "Old Romansh", nil, "rm", } m["rm-put"] = { "Puter Romansh", 688309, "rm", aliases = {"Puter", "Putèr", "Upper Engadine", "rm-puter"}, } m["rm-srm"] = { "Surmiran Romansh", 690216, "rm", aliases = {"Surmiran", "rm-surmiran", "Surmiran-Albula", -- Glottolog }, } m["rm-srs"] = { "Sursilvan Romansh", 688348, "rm", aliases = {"Sursilvan", "rm-sursilv"}, } m["rm-sut"] = { "Sutsilvan Romansh", 688272, "rm", aliases = {"Sutsilvan", "rm-sutsilv"}, varieties = {"Scharans Sutsilvan"}, -- per Glottolog } m["rm-val"] = { "Vallader Romansh", 690226, "rm", aliases = {"Vallader", "Putèr", "Lower Engadine", "rm-vallader"}, } m["rm-gri"] = { "Rumantsch Grischun", 688873, "rm", aliases = {"rm-rumgr"}, } ----------------------------------------------------- -- Sardinian varieties -- ----------------------------------------------------- m["sc-old"] = { "Old Sardinian", nil, "sc", } m["sc-src"] = { "Logudorese", 777974, "sc", aliases = {"Logudorese Sardinian"}, } m["sc-nuo"] = { "Nuorese", nil, "sc-src", aliases = {"Nuorese Sardinian"}, } m["sc-sro"] = { "Campidanese", 35348, "sc", aliases = {"Campidanese Sardinian"}, } ----------------------------------------------------- -- Spanish varieties -- ----------------------------------------------------- m["es-ear"] = { "Espanyol Modernong Maaga", --TLCHANGE 5364419, "es", english_name = "Early Modern Spanish", --TLCHANGE spanish_name = "Español moderno temprano", --TLCHANGE } m["es-AR"] = { "Espanyol Riyoplatense", --TLCHANGE 509780, "es", english_name = "Rioplatense Spanish", --TLCHANGE spanish_name = "Español rioplatense", --TLCHANGE } m["es-BO"] = { "Espanyol Bolivyano", --TLCHANGE 510730, "es", english_name = "Bolivian Spanish", --TLCHANGE spanish_name = "Español boliviano", --TLCHANGE } m["es-CL"] = { "Espanyol Tsileno", --TLCHANGE 857295, "es", english_name = "Chilean Spanish", --TLCHANGE spanish_name = "Español chileno", --TLCHANGE } m["es-CO"] = { "Espanyol Colombiyano", --TLCHANGE 1115875, "es", english_name = "Colombian Spanish", --TLCHANGE spanish_name = "Español colombiano", --TLCHANGE } m["es-CU"] = { "Espanyol Kubano", --TLCHANGE 824909, "es", english_name = "Cuban Spanish", --TLCHANGE spanish_name = "Español cubano", --TLCHANGE } m["es-MX"] = { "Espanyol Mehikano", --TLCHANGE 616620, "es", english_name = "Mexican Spanish", --TLCHANGE spanish_name = "Español mexicano", --TLCHANGE } m["es-PE"] = { "Espanyol Perwano", --TLCHANGE 736236, "es", english_name = "Peruvian Spanish", --TLCHANGE spanish_name = "Español peruano", --TLCHANGE } m["es-PH"] = { "Espanyol Pilipino", --TLCHANGE 22091406, "es", english_name = "Philippine Spanish", --TLCHANGE spanish_name = "Español filipino", --TLCHANGE } m["es-US"] = { "Espanyol Estados Unidos", --TLCHANGE 2301077, "es", aliases = {"US Spanish"}, english_name = "United States Spanish", --TLCHANGE spanish_name = "Español en Estados Unidos", --TLCHANGE } --use label "US Spanish" to put Spanish terms in this category m["es-PR"] = { "Espanyol Puwertorikeño", --TLCHANGE 7258609, "es", english_name = "Puerto Rican Spanish", --TLCHANGE spanish_name = "Español puertorriqueño", --TLCHANGE } m["es-VE"] = { "Espanyol Venezolano", --TLCHANGE 840017, "es", english_name = "Venezuelan Spanish", --TLCHANGE spanish_name = "Español venezolano", --TLCHANGE } m["es-lun"] = { "Lunfardo", 1401612, "es", english_name = "Lunfardo", --TLCHANGE spanish_name = "Lunfardo", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Japonic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Japanese varieties m["ja-mid"] = { "Gitnang Hapones", --TLCHANGE 6841474, "ojp", ancestors = "ojp", english_name = "Middle Japanese", --TLCHANGE } m["ja-mid-ear"] = { "Hapones Gitnang Maaga", --TLCHANGE 182695, "ja-mid", english_name = "Early Middle Japanese", --TLCHANGE } m["ja-mid-lat"] = { "Late Middle Japanese", 1816184, "ja-mid", ancestors = "ja-mid-ear", } m["ja-ear"] = { "Hapones Modernong Maaga", --TLCHANGE 5326692, "ja", ancestors = "ja-mid-lat", english_name = "Early Modern Japanese", --TLCHANGE } m["ojp-eas"] = { "Hapones Lumang Silanganin", --TLCHANGE 65247957, "ojp", english_name = "Eastern Old Japanese", --TLCHANGE } m["ja-cla"] = { "Hapones Klasikal", --TLCHANGE 1332057, "ja", -- FIXME: This is redundant because Classical Japanese is considered a child of (Modern) Japanese, which has ja-mid-ear -- (as well as ja-mid-lat) as ancestors. However, the intent here is that the *direct* ancestor of ja-cla is ja-mid-ear -- and ja-mid-lat is not an ancestor. Need to rethink ancestor handling. -- ancestors = "ja-mid-ear", english_name = "Classical Japanese", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Koreanic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Korean varieties m["oko-lat"] = { "Late Old Korean", nil, "oko", } m["okm-ear"] = { "Early Middle Korean", nil, "okm", } m["ko-cen"] = { "Koreano Sentral", --TLCHANGE nil, "ko", english_name = "Central Korean", --TLCHANGE } m["ko-gyg"] = { "Koreano Gyeonggi", --TLCHANGE 485492, "ko-cen", aliases = {"Seoul Korean"}, english_name = "Gyeonggi Korean", --TLCHANGE } m["ko-chu"] = { "Koreano Chungcheong", --TLCHANGE 625800, "ko-cen", aliases = {"Hoseo Korean"}, english_name = "Chungcheong Korean", --TLCHANGE } m["ko-hwa"] = { "Koreano Hwanghae", --TLCHANGE 16183706, "ko-cen", english_name = "Hwanghae Korean", --TLCHANGE } m["ko-gan"] = { "Koreano Yeongdong", --TLCHANGE 11260444, "ko-cen", aliases = {"Yeongdong Korean"}, english_name = "Gangwon Korean", --TLCHANGE } m["ko-gys"] = { "Koreano Gyeongsang", --TLCHANGE 488002, "ko", aliases = {"Southeastern Korean"}, english_name = "Gyeongsang Korean", --TLCHANGE } m["ko-jeo"] = { "Koreano Jeolla", --TLCHANGE 11250166, "ko", aliases = {"Southwestern Korean"}, english_name = "Jeolla Korean", --TLCHANGE } m["ko-pyo"] = { "Koreano Pyongan", --TLCHANGE 7263142, "ko", aliases = {"Northwestern Korean"}, english_name = "Pyongan Korean", --TLCHANGE } m["ko-ham"] = { "Koreano Hamgyong", --TLCHANGE 860702, "ko", aliases = {"Northeastern Korean"}, english_name = "Hamgyong Korean", --TLCHANGE } m["ko-yuk"] = { "Koreano Yukjin", --TLCHANGE 16171275, "ko", aliases = {"Yukchin Korean", "Ryukjin Korean", "Ryukchin Korean"}, english_name = "Yukjin Korean", --TLCHANGE } ---------------------------------------------------------------------------------------------------------------------- -- Mongolic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["xng-ear"] = { "Early Middle Mongol", nil, "xng", } m["xng-lat"] = { "Late Middle Mongol", nil, "xng", ancestors = "xng-ear", } m["mn-kha"] = { "Khalkha Mongolian", 6399808, "mn", aliases = {"Khalkha"}, } m["mn-ord"] = { "Ordos Mongolian", 716904, "mn", aliases = {"Ordos"}, } m["mn-cha"] = { "Chakhar Mongolian", 907425, "mn", aliases = {"Chakhar"}, } m["mn-khr"] = { "Khorchin Mongolian", 3196210, "mn", aliases = {"Khorchin"}, } ---------------------------------------------------------------------------------------------------------------------- -- Niger-Congo varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akan varieties -- ----------------------------------------------------- m["tw"] = { "Twi Akan", 36850, "ak", aliases = {"Twi"}, } m["abr"] = { "Abron", 34831, "tw", aliases = {"Brong", "Bono", "Bono Twi"}, } m["tw-asa"] = { "Asante Twi", 19261685, "tw", aliases = {"Asante", "Ashanti", "Ashante"}, } m["tw-aku"] = { "Akuapem Twi", 31150449, "tw", aliases = {"Akuapem", "Akuapim", "Akwapem Twi", "Akwapi"}, } m["fat"] = { "Fante Akan", 35570, "ak", aliases = {"Fante", "Fanti", "Fantse", "Mfantse"}, } m["wss"] = { "Wasa", 36914, "ak", } -- creole m["alv-kro"] = { "Kromanti", 1093206, "crp-mar", } ----------------------------------------------------- -- Bantu varieties -- ----------------------------------------------------- m["bnt-cmn"] = { "Common Bantu", nil, "bnt-pro", } m["xh-bha"] = { "Bhaca", 4900493, "xh", aliases = {"isiBhaca", "IsiBhaca"}, } -- Rwanda-Rundi varieties m["rw-kin"] = { "Kinyarwanda", 33573, "rw", aliases = {"Rwanda"}, } m["rw-run"] = { "Kirundi", 33583, "rw", aliases = {"Rundi"}, } ----------------------------------------------------- -- Fula varieties -- ----------------------------------------------------- m["fuc"] = { "Pulaar", 1420205, "ff", } m["fuf"] = { "Pular", 3915357, "ff", } m["ffm"] = { "Maasina Fulfulde", 3915322, "ff", } m["fue"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Borgu Fulfulde", 12952426, "ff", } m["fuh"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Western Niger Fulfulde", 12952430, "ff", } m["fuq"] = { -- no enwiki entry as of yet but frwiki, hrwiki and pmswiki have one "Central-Eastern Niger Fulfulde", 12628799, "ff", } m["fuv"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki and swwiki have one "Nigerian Fulfulde", 36129, "ff", } m["fub"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki, ptwiki, swwiki and yowiki have one "Adamawa Fulfulde", 34776, "ff", } m["fui"] = { -- no enwiki entry as of yet but pmswiki and swwiki have one "Bagirmi Fulfulde", 11003859, "ff", } ---------------------------------------------------------------------------------------------------------------------- -- Papuan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["kze"] = { "Kosena", 12952663, "auy", } m["ont"] = { "Ontenu", 3352827, "gaj", aliases = {"Ontena"}, } ---------------------------------------------------------------------------------------------------------------------- -- Salishan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["lut-nor"] = { "Northern Lushootseed", nil, "lut", aliases = {"Northern Puget Sound Salish"}, } m["slh"] = { "Southern Lushootseed", 7997684, "lut", aliases = {"Southern Puget Sound Salish", "Twulshootseed", "Whulshootseed"}, } m["ska"] = { "Skagit", 12642471, "lut-nor", } m["sno"] = { "Snohomish", 25559662, "lut-nor", } ---------------------------------------------------------------------------------------------------------------------- -- Sino-Tibetan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["tbq-pro"] = { "Proto-Tibeto-Burman", 7251864, "sit-pro", } ----------------------------------------------------- -- Chinese varieties -- ----------------------------------------------------- ------------- Old Chinese, Middle Chinese ------------- m["och-ear"] = { "Tsino Lumang Maaga", --TLCHANGE nil, "och", english_name = "Early Old Chinese", --TLCHANGE } m["och-lat"] = { "Late Old Chinese", nil, "och", } m["ltc-ear"] = { "Tsino Gitnang Maaga", --TLCHANGE nil, "ltc", english_name = "Early Middle Chinese", --TLCHANGE } m["ltc-lat"] = { "Late Middle Chinese", nil, "ltc", } ------------- Classical/Literary varieties ------------- -- FIXME: Temporary. m["lzh-shi"] = { "Traditional Chinese poetry", 1759242, "lzh", } -- FIXME: Temporary. m["lzh-cii"] = { "Ci", 1091366, "lzh", } -- FIXME: Temporary. m["lzh-yue"] = { "Classical Cantonese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn"] = { "Classical Mandarin", nil, "lzh", } -- FIXME: Temporary. m["lzh-tai"] = { "Classical Taishanese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn-TW"] = { "Classical Taiwanese Mandarin", nil, "lzh-cmn", } -- FIXME: Temporary. m["lzh-VI"] = { "Vietnamese Classical Chinese", 17034227, "lzh", } -- FIXME: Temporary. m["lzh-KO"] = { "Korean Classical Chinese", 10496257, "lzh", ietf_subtag = "lzh-KR" -- KR = South Korea, as there is no code for Korea as a whole } -- FIXME: Temporary. m["lzh-lit"] = { "Literary Chinese", nil, "lzh", } -- FIXME: Temporary. FIXME: Do we need this? How does it differ from Old Chinese? m["lzh-pre"] = { "Pre-Classical Chinese", nil, "lzh", } ------------- Written Vernacular varieties ------------- -- FIXME: Temporary. m["cmn-wvc"] = { "Written vernacular Mandarin", 783605, "cmn", } -- FIXME: Temporary. FIXME: How does this differ from "Literary Cantonese"? m["yue-wvc"] = { "Written vernacular Cantonese", nil, "yue", } -- FIXME: Temporary. m["zhx-tai-wvc"] = { "Written vernacular Taishanese", nil, "zhx-tai", } ------------- Mandarin varieties ------------- -- FIXME: Temporary. NOTE: The Linguist List assigns the "w:Beijing dialect" (Wikidata 1147606) the code "cmn-bej" and -- the larger "w:Beijing Mandarin (division of Mandarin)" dialect group (Wikidata 2169652; what we call "Beijingic -- Mandarin", after Glottolog) the code "cmn-bei". m["cmn-bei"] = { "Mandarin Beijing", --TLCHANGE 1147606, "cmn-bec", english_name = "Beijing Mandarin", --TLCHANGE } -- FIXME: Temporary. m["cmn-bec"] = { "Mandarin Beijingiko", --TLCHANGE 2169652, "cmn", english_name = "Beijingic Mandarin", --TLCHANGE } -- FIXME: Temporary. NOTE: The Linguist List uses the code cmn-zho. m["cmn-cep"] = { "Central Plains Mandarin", 3048775, "cmn", aliases = {"Zhongyuan Mandarin"}, } m["cmn-ear"] = { "Early Mandarin", 837169, "cmn", ancestors = "ltc", } -- FIXME: Temporary. m["cmn-gua"] = { "Guanzhong Mandarin", 3431648, "cmn-cep", } -- FIXME: Temporary. Appears to be a subdialect of Guiliu Mandarin, which in turn is a subdialect of Southwestern Mandarin. m["cmn-gui"] = { "Guilin Mandarin", 11111636, "cmn-sow", } m["cmn-jhu"] = { "Jianghuai Mandarin", 2128953, "cmn", aliases = {"Lower Yangtze Mandarin"}, } -- FIXME: Temporary. m["cmn-lan"] = { "Lanyin Mandarin", 662754, "cmn", } -- FIXME: Temporary. m["cmn-MY"] = { "Malaysian Mandarin", 13646143, "cmn", } -- FIXME: Temporary. m["cmn-nan"] = { "Nanjing Mandarin", 2681098, "cmn-jhu", } -- FIXME: Temporary. m["cmn-noe"] = { "Northeastern Mandarin", 1064504, "cmn", } -- FIXME: Temporary. m["cmn-PH"] = { "Mandarin Pilipino", --TLCHANGE 7185155, "cmn", english_name = "Philippine Mandarin", } -- FIXME: Temporary. m["cmn-SG"] = { "Singapore Mandarin", 1048980, "cmn", } -- FIXME: Temporary. m["cmn-sow"] = { "Southwestern Mandarin", 2609239, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Jilu Mandarin. m["cmn-tia"] = { "Tianjin Mandarin", 7800220, "cmn", } -- FIXME: Temporary. NOTE: Wikidata also has Q4380827 "Taiwanese Mandarin", defined as "rare dialect of Standard Chinese -- (Mandarin) used in Taiwan, which is strongly influenced by Taiwanese Hokkien; mostly used by elderlies" and having no -- English Wikipedia article (but see w:zh:臺灣國語). m["cmn-TW"] = { "Taiwanese Mandarin", 262828, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Wu-Tian Mandarin, in turn a subdialect of Southwestern Mandarin. -- Given the code cmn-xwu in the Linguist List. m["cmn-wuh"] = { "Wuhan Mandarin", 11124731, "cmn-sow", aliases = {"Wuhanese"}, } -- FIXME: Temporary. Appears to be a subdialect of Lanyin Mandarin. m["cmn-xin"] = { "Xining Mandarin", nil, "cmn-lan", } -- FIXME: Temporary. m["cmn-yan"] = { "Yangzhou Mandarin", nil, "cmn-jhu", } ------------- Cantonese varieties ------------- -- FIXME: Temporary. m["yue-gua"] = { "Guangzhou Cantonese", nil, "yue", } -- FIXME: Temporary. Given the codes yue-yue or yue-can in the Linguist List. m["yue-HK"] = { "Hong Kong Cantonese", 5894342, "yue", } -- FIXME: Temporary. FIXME: How does this differ from "Written vernacular Cantonese"? m["yue-lit"] = { "Literary Cantonese", 2472605, "yue", } ------------- Wu varieties ------------- m["wuu-han"] = { "Hangzhounese", 5648144, "wuu", } m["wuu-nin"] = { "Ningbonese", 3972199, "wuu", } -- FIXME: Temporary. m["wuu-nor"] = { "Northern Wu", 7675988, "wuu", aliases = {"Taihu Wu"}, } -- FIXME: Temporary? Subvariety of Taihu Wu. NOTE: "chm" stands for Chongming, the main dialect, to avoid a conflict -- with Shanghainese. m["wuu-chm"] = { "Shadi Wu", 6112340, "wuu-nor", } m["wuu-sha"] = { "Shanghainese", 36718, "wuu-nor", } m["wuu-suz"] = { "Suzhounese", 831744, "wuu-nor", } -- FIXME: Temporary. May be converted into a full language and/or split. m["wuu-wen"] = { "Wenzhounese", 710218, "wuu", } ------------- Xiang varieties ------------- m["hsn-lou"] = { "Loudi Xiang", 10943823, "hsn-old", } m["hsn-hya"] = { "Hengyang Xiang", 20689035, "hsn-hzh", } m["hsn-hzh"] = { "Hengzhou Xiang", nil, "hsn", } m["hsn-new"] = { "New Xiang", 7012696, "hsn", aliases = {"Chang-Yi"}, } m["hsn-old"] = { "Old Xiang", 7085453, "hsn", aliases = {"Lou-Shao"}, } ------------- Hakka varieties ------------- -- FIXME: Temporary. m["hak-dab"] = { "Dabu Hakka", 19855566, "hak", -- formerly hak-TW but seems to be spoken primary in Dabu County in Guangdong } -- FIXME: Temporary. m["hak-eam"] = { "Early Modern Hakka", nil, "hak", } -- FIXME: Temporary. m["hak-hai"] = { "Hailu Hakka", 17038519, "hak", -- often considered a Taiwanese lect but also spoken in [[Shanwei]], [[Guangdong]] } -- FIXME: Temporary. m["hak-HK"] = { "Hong Kong Hakka", 2675834, "hak", } -- FIXME: Temporary. m["hak-hui"] = { "Huiyang Hakka", 16873881, "hak", } -- FIXME: Temporary. m["hak-hui-MY"] = { "Malaysian Huiyang Hakka", nil, "hak-hui", } -- FIXME: Temporary. Similar to and possibly the parent of Sixian Hakka in Taiwan. m["hak-mei"] = { "Meixian Hakka", 839295, "hak", aliases = {"Moiyan Hakka", "Meizhou Hakka"}, } -- FIXME: Temporary. m["hak-six"] = { "Sixian Hakka", 9668261, "hak-TW", } -- FIXME: Temporary. m["hak-TW"] = { "Taiwanese Hakka", 2391532, "hak", } -- FIXME: Temporary. m["hak-zha"] = { "Zhao'an Hakka", 6703311, "hak", aliases = {"Zhangzhou Hakka"}, } -- Southern Min varieties -- m["nan-anx"] = { "Anxi Hokkien", 97064149, "nan-qua", } m["nan-cha"] = { "Changtai Hokkien", nil, "nan-zha", } m["nan-hou"] = { "Houlu Min", 19855492, "nan-dat", } m["nan-hui"] = { "Hui'an Hokkien", 16241797, "nan-qua", } m["nan-jin"] = { "Jinjiang Hokkien", 11089375, "nan-qua", } m["nan-kin"] = { "Kinmenese Hokkien", 56278342, "nan-xia", aliases = {"Kinmen Hokkien"}, } m["nan-med"] = { "Medan Hokkien", 6805114, "nan-zha", } m["nan-pen"] = { "Penang Hokkien", 11120689, "nan-zha", } m["nan-hbl-PH"] = { "Philippine Hokkien", 3236692, "nan-qua", } m["nan-qia"] = { "Qianlu Min", 19842517, "nan-dat", } m["nan-qua"] = { "Quanzhou Hokkien", 2251677, "nan-hbl", aliases = {"Chinchew", "Choanchew"}, } -- FIXME: Temporary? Derived from both Quanzhou and Zhangzhou Hokkien. m["nan-hbl-SG"] = { "Singapore Hokkien", 3846528, "nan-hbl", } m["nan-spm"] = { "Southern Malaysian Hokkien", 7570322, "nan-qua", aliases = {"Southern Malaysia Hokkien", "Southern Peninsular Malaysian Hokkien", "Southern Peninsular Malaysia Hokkien"} } m["nan-hbl-TW"] = { "Taiwanese Hokkien", 36778, "nan-hbl", } m["nan-ton"] = { "Tong'an Hokkien", nil, "nan-xia", } m["nan-xia"] = { "Xiamen Hokkien", 68744, "nan-hbl", aliases = {"Amoy", "Amoyese", "Amoynese", "Xiamenese"}, } m["nan-yon"] = { "Yongchun Hokkien", 65118728, "nan-qua", } m["nan-zha"] = { "Zhangzhou Hokkien", 8070492, "nan-hbl", aliases = {"Changchew", "Chiangchew", "Changchow"}, } m["nan-zho"] = { "Zhao'an Hokkien", 65118728, "nan-zha", aliases = {"Zhao'an", "Chawan", "Chawan Hokkien"}, } m["nan-zhp"] = { "Zhangping Hokkien", 15937822, "nan-zha", } ------------- Other Min varieties ------------- -- FIXME: Temporary. Affiliation within Min uncertain; some combination of Eastern and Southern. m["zhx-zho"] = { "Zhongshan Min", 8070958, "zh", } ------------- Other Chinese varieties ------------- -- FIXME: Temporary. Affiliation within Chinese uncertain; possibly Yue. m["zhx-dan"] = { "Danzhou Chinese", 2578935, "zh", } ------------- Chinese romanization varieties ------------- -- [[Wiktionary:Information desk/2022/June#Etymology Coding Issue]] -- [[Wiktionary:Grease pit/2022/June#Transliteration Systems in Etymologies 2]] m["cmn-pinyin"] = { "Hanyu Pinyin", 42222, "cmn", aliases = {"Pinyin"}, } m["cmn-tongyong"] = { "Tongyong Pinyin", 700739, "cmn", } m["cmn-wadegiles"] = { "Wade–Giles", 208442, "cmn", aliases = {"Wade-Giles", "Wade Giles"}, } m["zh-postal"] = { "Postal Romanization", 151868, "zh", } -- Chinese cyrillization m["cmn-palladius"] = { "Palladius", 1234239, "cmn", aliases = {"Palladius system"}, } ----------------------------------------------------- -- Tibetic varieties -- ----------------------------------------------------- m["adx"] = { "Amdo Tibetan", 56509, "bo", } m["kbg"] = { "Khamba", 12952626, "bo", } m["khg"] = { "Khams Tibetan", 56601, "bo", } m["tsk"] = { "Tseku", 11159532, "bo", } ---------------------------------------------------------------------------------------------------------------------- -- Tai-Kadai varieties -- ---------------------------------------------------------------------------------------------------------------------- m["th-old"] = { "Old Thai", nil, "tai-swe-pro", wikipedia_article = "Thai language#Old Thai", } m["th-suk"] = { "Sukhothai Old Thai", -- 1238-1438. Cannot use "Sukhothai Thai" as Sukhothai is the current city and "Sukhothai Thai" is a lect. nil, "th-old", aliases = {"Sukhothai Siamese"}, wikipedia_article = "Thai language#Old Thai", } m["th-ayu"] = { "Ayutthaya Old Thai", -- 1351-1767. Cannot use "Ayutthaya Thai" as Ayutthaya is the current city. nil, "th-old", aliases = {"Ayutthaya Siamese"}, wikipedia_article = "Thai language#Old Thai", } --[[ m["th-new"] = { "Hacked Thai", -- temporary for testing new translit/display methods nil, "th", translit = "User:Benwing2/th-scraping-translit", display_text = "User:Benwing2/th-scraping-translit", strip_diacritics = "User:Benwing2/th-scraping-translit", preprocess_links = "User:Benwing2/th-scraping-translit", } ]] m["tai-shz"] = { "Shangsi Zhuang", 13216, "za", } ---------------------------------------------------------------------------------------------------------------------- -- Turkic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["trk-cmn-pro"] = { "Proto-Common Turkic", 1126028, "trk-pro", } m["trk-ogr-pro"] = { "Proto-Oghur", 1422731, "trk-pro", family = "trk-ogr", } m["trk-bul-pro"] = { "Proto-Bulgar", nil, "trk-ogr-pro", } m["trk-ogz-pro"] = { "Proto-Oghuz", 494600, "trk-pro", family = "trk-ogz", aliases = {"Southwestern Common Turkic"}, } m["crh-dbj"] = { "Dobrujan Tatar", 12811566, "crh", aliases = {"Romanian Tatar"}, } m["cv-ana"] = { "Anatri Chuvash", nil, "cv", aliases = {"Anatri", "Lower Chuvash"}, } m["cv-mid"] = { "Middle Chuvash", nil, "cv", ancestors = "cv-old", } m["cv-old"] = { "Old Chuvash", nil, "cv", ancestors = "xbo-vol", } m["cv-vir"] = { "Viryal Chuvash", 4278332, "cv", aliases = {"Viryal", "Upper Chuvash"}, } m["kjh-fyu"] = { "Fuyu Kyrgyz", 2598963, "kjh", aliases = {"Fuyu Kirgiz", "Fuyu Kirghiz", "Manchurian Kyrgyz", "Manchurian Kirgiz", "Manchurian Kirghiz"}, } m["klj-arg"] = { "Arghu", 33455, "klj", ancestors = "trk-cmn-pro", } m["otk-kir"] = { "Old Kirghiz", 83142, "otk", aliases = {"Yenisei Turkic", "Yenisei Kyrgyz"}, } m["otk-ork"] = { "Orkhon Turkic", 31295480, "otk", } m["qwm-cum"] = { "Cuman", 1075050, "qwm", aliases = {"Kuman", "Polovtsian", "Polovcian"}, } m["qwm-arm"] = { "Armeno-Kipchak", 2027503, "qwm", ancestors = "qwm-cum", aliases = {"Xıpçaχ tili", "Tatarça"}, } m["qwm-mam"] = { "Mamluk-Kipchak", 4279942, "qwm", aliases = {"Mameluk-Kipchak"}, } m["az-cls"] = { "Azeri Klasikal", --TLCHANGE nil, "az", aliases = {"Classical Azeri"}, english_name = "Classical Azerbaijani", --TLCHANGE } m["qxq"] = { "Qashqai", 13192, "az", aliases = {"Qaşqay", "Qashqayi", "Kashkai", "Kashkay"}, } m["tr-CY"] = { "Cypriot Turkish", 7917392, "tr", } m["uz-afg"] = { -- NOTE: has ISO 639-3 code uzs assigned to it. "Afghan Uzbek", 1066787, "uz", aliases = {"Southern Uzbek"}, translit = "uz-afg-translit", } m["xbo-dan"] = { "Danube Bulgar", nil, "xbo", } m["xbo-vol"] = { "Volga Bulgar", nil, "xbo", } ---------------------------------------------------------------------------------------------------------------------- -- Uralic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["fiu-pro"] = { "Proto-Finno-Ugric", 79890, "urj-pro", } m["urj-fpr-pro"] = { "Proto-Finno-Permic", nil, "urj-pro", } m["krl-nor"] = { "North Karelian", 125501196, "krl", } m["krl-sou"] = { "South Karelian", 129812730, "krl", } m["mns-eas"] = { "Eastern Mansi", 30311755, "mns-cen", } m["mns-wes"] = { "Western Mansi", 30311756, "mns-cen", } ---------------------------------------------------------------------------------------------------------------------- -- Yeneseian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["qfa-yke-pro"] = { "Proto-Ketic", nil, "qfa-yen-pro", family = "qfa-yke", } m["qfa-yko-pro"] = { "Proto-Kottic", nil, "qfa-yen-pro", family = "qfa-yko", } m["qfa-yrn-pro"] = { "Proto-Arinic", nil, "qfa-yen-pro", family = "qfa-yrn", } m["qfa-ypm-pro"] = { "Proto-Pumpokolic", nil, "qfa-yen-pro", family = "qfa-ypm", } ---------------------------------------------------------------------------------------------------------------------- -- Miscellaneous varieties -- ---------------------------------------------------------------------------------------------------------------------- m["mul-tax"] = { "taxonomic name", 522190, "mul", } ----------------------------------------------------- -- Elamite varieties -- ----------------------------------------------------- m["elx-old"] = { "Old Elamite", nil, "elx", } m["elx-mid"] = { "Middle Elamite", nil, "elx", } m["elx-neo"] = { "Neo-Elamite", nil, "elx", } m["elx-ach"] = { "Achaemenid Elamite", nil, "elx", } ----------------------------------------------------- -- Substrates -- ----------------------------------------------------- -- Pre-Roman substrates m["qsb-ibe"] = { "Paleo-Hispanic", 246801, "und", family = "qfa-sub", aliases = {"Palaeo-Hispanic", "Paleohispanic", "Palaeohispanic", "Paleo-Iberian", "Palaeo-Iberian"}, } m["qsb-bal"] = { "Paleo-Balkan", 1815070, "und", family = "qfa-sub", aliases = {"Palaeo-Balkan", "Paleobalkan", "Palaeobalkan"}, } m["xaq"] = { "Aquitanian", 500522, "euq-pro", family = "euq", } -- TLCHANGE add these stuff BELOW THIS ----------------------------------------------------- -- Philippine languages varieties -- ----------------------------------------------------- --- Tagalog varieties, as per https://kwfwikaatkultura.ph/tagalog-2/ m["tl-nor"] = { "Kahilagaang Tagalog", nil, "tl", english_name = "Northern Tagalog", } m["tl-cen"] = { "Tagalog Sentral", nil, "tl", english_name = "Central Tagalog", } m["tl-sou"] = { "Katimugang Tagalog", 838580, "tl", english_name = "Southern Tagalog", } -- province codes based on https://en.wikipedia.org/wiki/ISO_3166-2:PH m["tl-bul"] = { "Tagalog Bulacan", 123900044, "tl-nor", aliases = {"Tagalog Bulakenyo", "Tagalog Bulakeño"}, english_name = "Bulacan Tagalog", } m["tl-ban"] = { "Tagalog Bataan", nil, "tl-nor", aliases = {"Tagalog Batanense"}, english_name = "Bataan Tagalog", } m["tl-nue"] = { "Tagalog Nueva Ecija", nil, "tl-nor", english_name = "Nueva Ecija Tagalog", } m["tl-aur"] = { "Tagalog Aurora", nil, "tl-sou", english_name = "Aurora Tagalog", } m["tl-riz"] = { "Tagalog Rizal", nil, "tl-cen", aliases = {"Tagalog Rizalenyo", "Tagalog Rizaleño"}, english_name = "Rizal Tagalog", } m["tl-cav"] = { "Tagalog Cavite", 97255128, "tl-sou", aliases = {"Tagalog Kabitenyo", "Tagalog Caviteño"}, english_name = "Cavite Tagalog", } m["tl-lag"] = { "Tagalog Laguna", nil, "tl-sou", aliases = {"Tagalog Lagunense"}, english_name = "Laguna Tagalog", } m["tl-btg"] = { "Tagalog Batangas", 4868610, "tl-sou", aliases = {"Tagalog Batanggenyo", "Tagalog Batangueño"}, english_name = "Batangas Tagalog", } m["tl-que"] = { "Tagalog Quezon", nil, "tl-sou", english_name = "Quezon Tagalog", } m["tl-mdo"] = { --made-up code "mdo" "Tagalog Mindoro", nil, "tl-sou", english_name = "Mindoro Tagalog", } m["tl-mad"] = { "Tagalog Marinduque", nil, "tl-sou", aliases = {"Tagalog Marindukenyo", "Tagalog Marinduqueño"}, english_name = "Marinduque Tagalog", } m["tl-can"] = { "Tagalog Camarines Norte", nil, "tl-sou", english_name = "Camarines Norte Tagalog", } -- other variants m["tl-bag"] = { "Tagalog Baguio", nil, "tl", english_name = "Baguio Tagalog", } m["tl-zho"] = { "Tagalog Tsinoy", nil, "tl", english_name = "Chinese Filipino Tagalog", } -------------- --- Ilocano varieties from https://kwfwikaatkultura.ph/ilokano/ m["ilo-nor"] = { "Ilokano Amianan", nil, "ilo", } m["ilo-sou"] = { "Ilokano Abagatan", nil, "ilo", } m["ilo-cvy"] = { "Ilokano Cagayan Valley", nil, "ilo", } m["ilo-car"] = { "Ilokano Kaigorotan", nil, "ilo", } -------------- --- Sebwano varieties from https://kwfwikaatkultura.ph/sebwano-2/ m["ceb-min"] = { "Binisayang Mindanaw", nil, "ceb", english_name = "Mindanao Cebuano", } m["ceb-min"] = { "Binul-anong Binisaya", nil, "ceb", english_name = "Boholano Cebuano", } m["ceb-sle"] = { "Katimugang Leyte Binisaya", nil, "ceb", english_name = "Southern Leyte Cebuano", } m["ceb-ner"] = { "Negrensing Binisaya", nil, "ceb", english_name = "Negros Cebuano", } m["ceb-mas"] = { "Masbatenyong Binisaya", nil, "ceb", english_name = "Negros Cebuano", } m["ceb-sig"] = { "Binisayang Siquijor", nil, "ceb", english_name = "Siquijor Cebuano", } -------------- --- Tinagbanwa varieties from https://kwfwikaatkultura.ph/ortograpiyang-tinagbanwa/ m["tbk-bat"] = { "Batuwanën", nil, "tbk", } m["tbk-sug"] = { "S̃ug̓udnun", nil, "tbk", } m["tbk-pul"] = { "Puluwanën", nil, "tbk", } -- TLCHANGE END ----------------------------------------------------- return require("Module:languages").finalizeData(m, "language", true) 0nj2tn8137y8u1msy9n9a48fpfxhx3c 828 30848 176325 176294 2026-04-14T03:25:28Z Yivan000 4078 176325 Scribunto text/plain --[=[ This module contains definitions for all language family codes on Wiktionary. ]=]-- local m = {} m["aav"] = { "Awstroasyatika", --TLCHANGE 33199, aliases = {"Austro-Asiatic"}, english_name = "Austroasiatic", --TLCHANGE spanish_name = "Austroasiática", --TLCHANGE } m["aav-khs"] = { "Khasika", --TLCHANGE 3073734, "aav", aliases = {"Khasic"}, english_name = "Khasian", --TLCHANGE spanish_name = "Khásica", --TLCHANGE } m["aav-nic"] = { "Nikobares", --TLCHANGE 217380, "aav", english_name = "Nicobarese", --TLCHANGE spanish_name = "Nicobarés", --TLCHANGE } m["aav-pkl"] = { "Pnar-Khasi-Lyngngam", nil, "aav-khs", } m["afa"] = { "Afroasyatika", --TLCHANGE 25268, aliases = {"Afro-Asiatic"}, english_name = "Afroasiatic", --TLCHANGE spanish_name = "Afroasiática", --TLCHANGE } m["alg"] = { "Algonkinas", --TLCHANGE 33392, "aql", english_name = "Algonquian", --TLCHANGE spanish_name = "Algonquinas", --TLCHANGE } 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"] = { "Atlantiko-Konggoleñas", --TLCHANGE 771124, "nic", english_name = "Atlantic-Congo", --TLCHANGE spanish_name = "Atlántico-Congoleñas", --TLCHANGE } 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"] = { "Apatseanas", --TLCHANGE 27758, "ath", aliases = {"Southern Athabaskan"}, english_name = "Apachean", --TLCHANGE spanish_name = "Apacheanas", --TLCHANGE } m["aqa"] = { "Alacalufan", 1288430, } m["aql"] = { "Algikas", --TLCHANGE 721612, aliases = {"Algonquian-Ritwan", "Algonquian-Wiyot-Yurok"}, english_name = "Algic", --TLCHANGE spanish_name = "Álgicas", --TLCHANGE } m["art"] = { "nilikha", --TLCHANGE "constructed" 33215, "qfa-not", aliases = {"artificial", "planned"}, english_name = "constructed", --TLCHANGE } 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"] = { "Hermaniko", --TLCHANGE 21200, "ine", english_name = "Germanic", --TLCHANGE spanish_name = "Germánico", --TLCHANGE } 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"] = { "Kanlurang Hermaniko", --TLCHANGE 26721, "gem", english_name = "West Germanic", --TLCHANGE spanish_name = "Germánico occidental", --TLCHANGE } m["gmw-afr"] = { "Angglofrisyo", --TLCHANGE 5329170, "gmw-nsg", english_name = "Anglo-Frisian", --TLCHANGE spanish_name = "Anglofrisio", --TLCHANGE } m["gmw-ang"] = { "Anggliko", --TLCHANGE 1346342, "gmw-afr", protoLanguage = "ang", english_name = "Anglic", --TLCHANGE spanish_name = "Ánglico", --TLCHANGE } m["gmw-fri"] = { "Frisian", 25325, "gmw-afr", protoLanguage = "ofs", } m["gmw-frk"] = { "Mababang Franconyo", --TLCHANGE 153050, "gmw", protoLanguage = "frk", english_name = "Low Franconian", --TLCHANGE spanish_name = "Bajofranconio", --TLCHANGE } m["gmw-hgm"] = { "Mataas na Hermaniko", --TLCHANGE 52040, "gmw", protoLanguage = "goh", english_name = "High German", --TLCHANGE spanish_name = "Altogermánico", --TLCHANGE } m["gmw-ian"] = { "Irish Anglo-Norman", 120719384, "gmw-ang", protoLanguage = "enm", } m["gmw-lgm"] = { "Mababang Hermaniko", --TLCHANGE 25433, "gmw-nsg", protoLanguage = "osx", english_name = "Low German", --TLCHANGE spanish_name = "Bajogermánico", --TLCHANGE } m["gmw-nsg"] = { "Hermaniko Dagat Hilaga", --TLCHANGE 30134, "gmw", aliases = {"Ingvaeonic"}, english_name = "North Sea Germanic", spanish_name = "Germánico del mar del norte", --TLCHANGE } 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"] = { "Indoeuropeo", --TLCHANGE 19860, aliases = {"Indo-Germanic"}, english_name = "Indo-European", --TLCHANGE spanish_name = "Indoeuropeo", --TLCHANGE } 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"] = { "Italiko", --TLCHANGE 131848, "ine", english_name = "Italic", --TLCHANGE spanish_name = "Itálico", --TLCHANGE } m["itc-laf"] = { "Latino-Faliscan", 33478, "itc", aliases = {"Latinian"}, } m["itc-sbl"] = { "Osco-Umbrian", 515194, "itc", aliases = {"Sabellic", "Sabellian"}, } m["jpx"] = { "Haponiko", 33612, aliases = {"Japanese", "Japanese-Ryukyuan"}, english_name = "Japonic", --TLCHANGE spanish_name = "Japónico", --TLCHANGE } m["jpx-nry"] = { "Kahilagaang Ryukyuwense", --TLCHANGE 20862796, "jpx-ryu", english_name = "Northern Ryukyuan", --TLCHANGE } m["jpx-ryu"] = { "Ryukyuwense", --TLCHANGE 56393, "jpx", english_name = "Ryukyuan", --TLCHANGE spanish_name = "Ryukyuense", --TLCHANGE } m["jpx-sry"] = { "Katimugang Ryukyuwense", --TLCHANGE 18392243, "jpx-ryu", english_name = "Southern Ryukyuan", --TLCHANGE } 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"] = { "Kurdo", --TLCHANGE 36368, "ira-nwi", english_name = "Kurdish", --TLCHANGE spanish_name = "Kurdo", --TLCHANGE } m["kv"] = { "Komi", 36126, -- "Komi language" in Wikipedia but refers specifically to Komi-Zyrian; no Wikidata item for Komi family "urj-prm", } m["map"] = { "Awstronesyo", --TLCHANGE 49228, is_official_kwf_name = "https://kwfwikaatkultura.ph/mga-wika-ng-pilipinas/", --TLCHANGE english_name = "Austronesian", --TLCHANGE spanish_name = "Austronesio", --TLCHANGE } 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", nil, "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", 1270220, "omq-otp", } m["oto-otm"] = { "Otomi", nil, "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"] = { "Pilipino", --TLCHANGE "Philippine" 947858, "poz", english_name = "Philippine" --TLCHANGE } m["phi-kal"] = { "Kalamian", 3217466, "phi", aliases = {"Calamian"}, } m["poz"] = { "Malayo-Polinesya", --TLCHANGE 143158, "map", english_name = "Malayo-Polynesian", --TLCHANGE spanish_name = "Malayo-polinesia" --TLCHANGE } 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"] = { "Romanse", --TLCHANGE 19814, "itc", aliases = {"Romanic", "Latin", "Neolatin", "Neo-Latin"}, protoLanguage = "la", english_name = "Romance", --TLCHANGE spanish_name = "Romance", --TLCHANGE } m["roa-asl"] = { "Asturleonese", 35390, "roa-ibe", protoLanguage = "roa-ole", } m["roa-cas"] = { "Kastila", --TLCHANGE "Kastila" for castillian, "Espanyol" for spanish 71924, "roa-ibe", aliases = {"Castillian", "Castilic", "Castillic"}, protoLanguage = "osp", english_name = "Castilian", --TLCHANGE spanish_name = "Castellano", --TLCHANGE } 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"] = { "Romanse Italo-Kanluranin", --TLCHANGE 112608, "roa", aliases = {"Italo-Western"}, english_name = "Italo-Western Romance", --TLCHANGE spanish_name = "Romance italo-occidental", --TLCHANGE } 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"] = { "Iberoromanse", --TLCHANGE 749533, "roa-wes", aliases = {"Iberian Romance", "West Ibero-Romance", "Western Ibero-Romance", "West Iberian Romance", "Western Iberian Romance"}, english_name = "Ibero-Romance", --TLCHANGE spanish_name = "Iberorromance", --TLCHANGE } 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"] = { "Kanluraning Romanse", --TLCHANGE 2714388, "roa-iwr", english_name = "Western Romance", --TLCHANGE spanish_name = "Romance occidental", --TLCHANGE } --[=[ 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-Tibetano", --TLCHANGE "Sino-Tibetan" 45961, aliases = {"Trans-Himalayan"}, english_name = "Sino-Tibetan" --TLCHANGE } 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"] = { "Fino-baltiko", --TLCHANGE 33328, "urj", aliases = {"Baltic-Finnic", "Balto-Finnic", "Fennic"}, english_name = "Finnic", --TLCHANGE spanish_name = "Fino-báltico", --TLCHANGE } 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"] = { "Sinitiko", --TLCHANGE "Sinitic" 33857, "sit-sba", aliases = {"Chinese"}, protoLanguage = "och", english_name = "Sinitic", --TLCHANGE spanish_name = "Sinitico", --TLCHANGE } m["zhx-com"] = { "Min Pandalampasigan", --TLCHANGE "baybayin" is already an overloaded term (used in wiktionary in the spelling sense), so let's use "dalampasigan" instead 20667215, "zhx-min", english_name = "Coastal Min", --TLCHANGE } m["zhx-inm"] = { "Min Pang-ilaya", --TLCHANGE 20667237, "zhx-min", english_name = "Inland Min", --TLCHANGE } m["zhx-man"] = { "Mandariniko", --TLCHANGE nil, "zhx", protoLanguage = "cmn-ear", english_name = "Mandarinic", --TLCHANGE spanish_name = "Mandarinico", --TLCHANGE } m["zhx-min"] = { "Min", 56504, "zhx", } m["zhx-nan"] = { "Silanganing Min", --TLCHANGE 36495, "zhx-com", english_name = "Southern Min", --TLCHANGE } 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") nwyix4278hqddrw6psdaen8qhfw7apf 828 32622 176314 176235 2026-04-14T02:30:58Z Yivan000 4078 merge changes 176314 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}, }, english_name = "Afar", --TLCHANGE } m["ab"] = { "Abhasiyo", --TLCHANGE From spanish "abjasio" 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], "", } }, }, english_name = "Abkahz", --TLCHANGE spanish_name = "Abjasio", --TLCHANGE } m["ae"] = { "Avestiko", --TLCHANGE from Spanish "avéstico" 29572, "ira-cen", "Avst, Gujr, Deva", translit = { Avst = "Avst-translit" }, english_name = "Avestan", --TLCHANGE spanish_name = "Avéstico", --TLCHANGE } m["af"] = { "Afrikāns", --TLCHANGE the "ā" is a long vowel, since "aa" is pronounced "aɁa" 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]} } }, english_name = "Afrikaans", --TLCHANGE spanish_name = "Afrikáans", --TLCHANGE } m["ak"] = { "Akan", 28026, "alv-ctn", "Latn", } m["am"] = { "Amhariko", --TLCHANGE 28244, "sem-eth", "Ethi", translit = "Ethi-translit", english_name = "Amharic", --TLCHANGE spanish_name = "Amhárico", --TLCHANGE } m["an"] = { "Aragones", --TLCHANGE 8765, "roa-nar", "Latn", english_name = "Aragonese", --TLCHANGE spanish_name = "Aragonés", --TLCHANGE } m["ar"] = { "Arabe", --TLCHANGE 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]] is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=96", --TLCHANGE english_name = "Arabic", --TLCHANGE } m["as"] = { "Asames", --TLCHANGE 29401, "inc-bas", "as-Beng", ancestors = "inc-mas", translit = "as-translit", english_name = "Assamese", --TLCHANGE spanish_name = "Asamés", --TLCHANGE } 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]} }, }, english_name = "Avar", --TLCHANGE } m["ay"] = { "Aymara", --TLCHANGE 4627, "sai-aym", "Latn", english_name = "Aymara", --TLCHANGE spanish_name = "Aimara", --TLCHANGE } m["az"] = { "Azeri", --TLCHANGE 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]} }, }, english_name = "Azerbaijani", --TLCHANGE spanish_name = "Azerí", --TLCHANGE } m["ba"] = { "Baskir", --TLCHANGE 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]} }, english_name = "Bashkir", --TLCHANGE spanish_name = "Baskir", --TLCHANGE } m["be"] = { "Biyeloruso", --TLCHANGE 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. }, english_name = "Belarusian", --TLCHANGE spanish_name = "Bielorruso", --TLCHANGE } m["bg"] = { "Bulgaro", --TLCHANGE 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, english_name = "Bulgarian", --TLCHANGE spanish_name = "Búlgaro", --TLCHANGE } m["bh"] = { "Bihari", --TLCHANGE 135305, "inc-eas", "Deva", english_name = "Bihari", --TLCHANGE spanish_name = "Bihari", --TLCHANGE } m["bi"] = { "Bislama", 35452, "crp", "Latn", ancestors = "en", english_name = "Bislama", --TLCHANGE } 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]} }, }, english_name = "Bambara", --TLCHANGE } m["bn"] = { "Benggali", --TLCHANGE 9610, "inc-bas", "Beng, Newa", ancestors = "inc-mbn", translit = { Beng = "bn-translit" }, english_name = "Bengali", --TLCHANGE spanish_name = "Bengalí", --TLCHANGE } m["bo"] = { "Tibetano", --TLCHANGE 34271, "sit-tib", "Tibt", -- sometimes Deva? ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] english_name = "Tibetan", --TLCHANGE spanish_name = "Tibetano", --TLCHANGE } m["br"] = { "Breton", 12107, "cel-brs", "Latn", ancestors = "xbm", sort_key = { from = {"ch", "c['ʼ’]h"}, to = {"c" .. p[1], "c" .. p[2]} }, english_name = "Breton", --TLCHANGE } m["ca"] = { "Katalan", --TLCHANGE 7026, "roa-ocr", "Latn", ancestors = "roa-oca", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, standard_chars = "AaÀàBbCcÇçDdEeÉéÈèFfGgHhIiÍíÏïJjLlMmNnOoÓóÒòPpQqRrSsTtUuÚúÜüVvXxYyZz·" .. c.punc, english_name = "Catalan", --TLCHANGE spanish_name = "Catalán", --TLCHANGE } m["ce"] = { "Tsetseno", --TLCHANGE 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]} }, }, english_name = "Chechen", --TLCHANGE spanish_name = "Checheno", --TLCHANGE } m["ch"] = { "Tsamoro", --TLCHANGE 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]} }, english_name = "Chamorro", --TLCHANGE spanish_name = "Chamorro", --TLCHANGE } m["co"] = { "Korso", --TLCHANGE 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, english_name = "Corsican", --TLCHANGE spanish_name = "Corso" --TLCHANGE } m["cr"] = { "Kri", --TLCHANGE 33390, "alg", "Latn, Cans", translit = { Cans = "cr-translit" }, english_name = "Cree", --TLCHANGE spanish_name = "Cree", --TLCHANGE } m["cs"] = { "Tseko", --TLCHANGE 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, english_name = "Czech", --TLCHANGE spanish_name = "Checo", --TLCHANGE } m["cu"] = { "Lumang Simbahang Eslavo", --TLCHANGE 35499, "zls", "Cyrs, Glag, Zname", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] english_name = "Old Church Slavonic", --TLCHANGE spanish_name = "Antiguo eslavo eclesiástico" --TLCHANGE } m["cv"] = { "Tsuvasyo", --TLCHANGE 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]} }, english_name = "Chuvash", --TLCHANGE spanish_name = "Chuvasio", --TLCHANGE } m["cy"] = { "Gales", --TLCHANGE 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, english_name = "Welsh", --TLCHANGE spanish_name = "Galés", --TLCHANGE } m["da"] = { "Danes", --TLCHANGE 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, english_name = "Danish", --TLCHANGE spanish_name = "Danés", --TLCHANGE } m["de"] = { "Aleman", --TLCHANGE 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 }, is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=Alem%C3%A1n", --TLCHANGE (Spanish first before English) english_name = "German", --TLCHANGE spanish_name = "Alemán", --TLCHANGE } m["dv"] = { "Divehi", --TLCHANGE 32656, "inc-ins", "Thaa, Diak", translit = { Thaa = "dv-translit", Diak = "Diak-translit", }, ancestors = "dv-old", override_translit = true, english_name = "Dhivehi", --TLCHANGE spanish_name = "Divehi", --TLCHANGE } m["dz"] = { "Dzongkha", 33081, "sit-tib", "Tibt", ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] english_name = "Dzongkha", --TLCHANGE } 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]} }, english_name = "Ewe", --TLCHANGE } m["el"] = { "Griyego", --from Spanish "griego" 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 }, is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=Griy%C3%A9go", --TLCHANGE (Spanish first before English) english_name = "Greek", --TLCHANGE spanish_name = "Griego", --TLCHANGE } m["en"] = { "Ingles", --from Spanish "inglés" 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 }, is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=20", --TLCHANGE english_name = "English", --TLCHANGE spanish_name = "Inglés", --TLCHANGE } 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, english_name = "Esperanto", --TLCHANGE } m["es"] = { "Espanyol", --TLCHANGE this is confusing, KWF has "Espanyol", "Kastila", and "Español" as all translations of 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 }, is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=12", --TLCHANGE english_name = "Spanish", --TLCHANGE spanish_name = "Español", --TLCHANGE } m["et"] = { "Estonyo", --TLCHANGE from Spanish "estonio" 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, english_name = "Estonian", --TLCHANGE spanish_name = "Estonio", --TLCHANGE } m["eu"] = { "Euskera", --from Spanish "Euskera" 8752, "euq", "Latn", sort_key = { from = {"ç", "ñ"}, to = {"c" .. p[1], "n" .. p[1]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnÑñOoPpRrSsTtUuXxZz" .. c.punc, english_name = "Basque", --TLCHANGE spanish_name = "Euskera", --TLCHANGE } m["fa"] = { "Persa", --TLCHANGE from Spanish "persa" 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]] english_name = "Persian", --TLCHANGE spanish_name = "Persa", --TLCHANGE } m["ff"] = { "Fula", 33454, "alv-fwo", "Latn, Adlm", english_name = "Fula", --TLCHANGE } m["fi"] = { "Fines", --TLCHANGE from Spanish "finés" 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, english_name = "Finnish", --TLCHANGE spanish_name = "Finés", --TLCHANGE } m["fj"] = { "Fiyiyano", --TLCHANGE from Spanish "fiyiano" 33295, "poz-pcc", "Latn", english_name = "Fijian", --TLCHANGE spanish_name = "Fiyiano" --TLCHANGE } m["fo"] = { "Feroes", --TLCHANGE from Spanish "feroés" 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, english_name = "Faroese", --TLCHANGE spanish_name = "Feroés", --TLCHANGE } m["fr"] = { "Franses", --from Spanish "francés" 150, "roa-oil", "Latn, Brai", ancestors = "frm", sort_key = { Latn = s["roa-oil-sortkey"] }, standard_chars = { Latn = "AaÀàÂâBbCcÇçDdEeÉéÈèÊêËëFfGgHhIiÎîÏïJjLlMmNnOoÔôŒœPpQqRrSsTtUuÙùÛûÜüVvXxYyZz", Brai = c.braille, c.punc }, english_name = "French", --TLCHANGE spanish_name = "Francés", --TLCHANGE } m["fy"] = { "Kanlurang Frison",--TLCHANGE from Spanish "frisón occidental" 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, english_name = "West Frisian", --TLCHANGE spanish_name = "Frisón occidental", --TLCHANGE } m["ga"] = { "Irlandes", --from Spanish "irlandés" 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, english_name = "Irish", --TLCHANGE spanish_name = "Irlandés", --TLCHANGE } m["gd"] = { "Gaeliko Eskoses", --TLCHANGE from Spanish "Gaélico escocés" 9314, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = {remove_diacritics = c.grave .. c.acute}, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙù" .. c.punc, english_name = "Scottish Gaelic", --TLCHANGE spanish_name = "Gaélico escocés", --TLCHANGE } m["gl"] = { "Galyego", --from Spanish "gallego" 9307, "roa-gap", "Latn", sort_key = { remove_diacritics = c.acute, from = {"ñ"}, to = {"n" .. p[1]} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíÏïLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxZz" .. c.punc, english_name = "Galician", --TLCHANGE spanish_name = "Gallego", --TLCHANGE } m["gu"] = { "Guyarati", --TLCHANGE from Spanish "guyaratí" 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 = "઼"}, }, english_name = "Gujarati", --TLCHANGE spanish_name = "Guyaratí", --TLCHANGE } m["gv"] = { "Manes", --TLCHANGE from Spanish "manés" 12175, "cel-gae", "Latn", ancestors = "mga", sort_key = {remove_diacritics = c.cedilla .. "-"}, standard_chars = "AaBbCcÇçDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYy" .. c.punc, english_name = "Manx", --TLCHANGE spanish_name = "Manés", --TLCHANGE } m["ha"] = { "Hawsa", --TLCHANGE 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]} }, }, english_name = "Hausa", --TLCHANGE } m["he"] = { "Ebreo", --from Spanish "hebreo" 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) english_name = "Hebrew", --TLCHANGE spanish_name = "Hebreo", --TLCHANGE } m["hi"] = { "Hindi", 1568, "inc-hnd", "Deva, Kthi, Newa", translit = { Deva = "hi-translit" }, standard_chars = { Deva = "अआइईउऊएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषसहत्रज्ञक्षक़ख़ग़ज़झ़ड़ढ़फ़काखागाघाङाचाछाजाझाञाटाठाडाढाणाताथादाधानापाफाबाभामायारालावाशाषासाहात्राज्ञाक्षाक़ाख़ाग़ाज़ाझ़ाड़ाढ़ाफ़ाकिखिगिघिङिचिछिजिझिञिटिठिडिढिणितिथिदिधिनिपिफिबिभिमियिरिलिविशिषिसिहित्रिज्ञिक्षिक़िख़िग़िज़िझ़िड़िढ़िफ़िकीखीगीघीङीचीछीजीझीञीटीठीडीढीणीतीथीदीधीनीपीफीबीभीमीयीरीलीवीशीषीसीहीत्रीज्ञीक्षीक़ीख़ीग़ीज़ीझ़ीड़ीढ़ीफ़ीकुखुगुघुङुचुछुजुझुञुटुठुडुढुणुतुथुदुधुनुपुफुबुभुमुयुरुलुवुशुषुसुहुत्रुज्ञुक्षुक़ुख़ुग़ुज़ुझ़ुड़ुढ़ुफ़ुकूखूगूघूङूचूछूजूझूञूटूठूडूढूणूतूथूदूधूनूपूफूबूभूमूयूरूलूवूशूषूसूहूत्रूज्ञूक्षूक़ूख़ूग़ूज़ूझ़ूड़ूढ़ूफ़ूकेखेगेघेङेचेछेजेझेञेटेठेडेढेणेतेथेदेधेनेपेफेबेभेमेयेरेलेवेशेषेसेहेत्रेज्ञेक्षेक़ेख़ेग़ेज़ेझ़ेड़ेढ़ेफ़ेकैखैगैघैङैचैछैजैझैञैटैठैडैढैणैतैथैदैधैनैपैफैबैभैमैयैरैलैवैशैषैसैहैत्रैज्ञैक्षैक़ैख़ैग़ैज़ैझ़ैड़ैढ़ैफ़ैकोखोगोघोङोचोछोजोझोञोटोठोडोढोणोतोथोदोधोनोपोफोबोभोमोयोरोलोवोशोषोसोहोत्रोज्ञोक्षोक़ोख़ोग़ोज़ोझ़ोड़ोढ़ोफ़ोकौखौगौघौङौचौछौजौझौञौटौठौडौढौणौतौथौदौधौनौपौफौबौभौमौयौरौलौवौशौषौसौहौत्रौज्ञौक्षौक़ौख़ौग़ौज़ौझ़ौड़ौढ़ौफ़ौक्ख्ग्घ्ङ्च्छ्ज्झ्ञ्ट्ठ्ड्ढ्ण्त्थ्द्ध्न्प्फ्ब्भ्म्य्र्ल्व्श्ष्स्ह्त्र्ज्ञ्क्ष्क़्ख़्ग़्ज़्झ़्ड़्ढ़्फ़्।॥०१२३४५६७८९॰", c.punc }, english_name = "Hindi", --TLCHANGE } m["ho"] = { "Hiri Motu", 33617, "crp", "Latn", ancestors = "meu", english_name = "Hiri Motu", --TLCHANGE } m["ht"] = { "Kriyolyo Aityano", --from Spanish "Criollo haitiano" 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] } }, english_name = "Haitian Creole", --TLCHANGE spanish_name = "Criollo haitiano", --TLCHANGE } m["hu"] = { "Unggaro", --from Spanish "húngaro" 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 }, english_name = "Hungarian", --TLCHANGE spanish_name = "Húngaro", --TLCHANGE } m["hy"] = { "Armenyo", --from Spanish "armenio" 8785, "hyx", "Armn, Brai", ancestors = "axm", -- Armn translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Armn = { remove_diacritics = "՛՜՞՟", from = {"եւ", "^յ", "^ի", "^է", "յ̵", "ՙ", "՚"}, to = {"և", "յ", "ի", "է", "ֈ", "ʻ", "’"} }, }, sort_key = { Armn = { from = { "ու", "եւ", -- 2 chars "և" -- 1 char }, to = { "ւ", "եվ", "եվ" } }, }, english_name = "Armenian", --TLCHANGE spanish_name = "Armenio", --TLCHANGE } m["hz"] = { "Herero", 33315, "bnt-swb", "Latn", english_name = "Herero", --TLCHANGE } m["ia"] = { "Interlingguwa", --TLCHANGE 35934, "art", "Latn", english_name = "Interlingua", --TLCHANGE spanish_name = "Interlingua", --TLCHANGE } m["id"] = { "Indonesyo", --TLCHANGE 9240, "poz-mly", "Latn", ancestors = "ms", standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc, english_name = "Indonesian", --TLCHANGE spanish_name = "Indonesio", --TLCHANGE } m["ie"] = { "Interlingguwe", --TLCHANGE 35850, "art", "Latn", type = "appendix-constructed", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, english_name = "Interlingue", --TLCHANGE } 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]} }, english_name = "Igbo", --TLCHANGE } m["ii"] = { "Nuwosu", --TLCHANGE 34235, "tbq-nlo", "Yiii", translit = "ii-translit", english_name = "Nuosu", --TLCHANGE } m["ik"] = { "Iñupyak", --TLCHANGE 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] } }, english_name = "Inupiaq", --TLCHANGE spanish_name = "Iñupiaq", --TLCHANGE } m["io"] = { "Ido", 35224, "art", "Latn", english_name = "Ido", --TLCHANGE } m["is"] = { "Islandes", --TLCHANGE from Spanish "islandés" 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, english_name = "Icelandic", --TLCHANGE spanish_name = "Islandés", --TLCHANGE } m["it"] = { "Italyano", --from Spanish "italiano" 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, english_name = "Italian", --TLCHANGE spanish_name = "Italiano", --TLCHANGE } m["iu"] = { "Inuktitut", 29921, "esx-inu", "Cans, Latn", translit = { Cans = "cr-translit" }, override_translit = true, english_name = "Inuktitut", --TLCHANGE } m["ja"] = { "Hapones", --TLCHANGE 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"], is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=32", --TLCHANGE english_name = "Japanese", --TLCHANGE spanish_name = "Japonés", --TLCHANGE } m["jv"] = { "Havanes", --TLCHANGE from Spanish "javanés" 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]} }, }, english_name = "Javanese", --TLCHANGE spanish_name = "Javanés", --TLCHANGE } m["ka"] = { "Heorhiyano", --from Spanish "georgiano" 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]] english_name = "Georgian", --TLCHANGE spanish_name = "Georgiano", --TLCHANGE } m["kg"] = { "Konggo", --TLCHANGE 33702, "bnt-kng", "Latn", english_name = "Kongo", --TLCHANGE } m["ki"] = { "Kikuyu", 33587, "bnt-kka", "Latn", english_name = "Kikuyu", --TLCHANGE } m["kj"] = { "Kuwanyama", --TLCHANGE 1405077, "bnt-ova", "Latn", english_name = "Kwanyama", --TLCHANGE spanish_name = "Kuanyama", --TLCHANGE } m["kk"] = { "Kazaho", --TLCHANGE from Spanish "kazajo" 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 }, english_name = "Kazakh", --TLCHANGE spanish_name = "Kazajo", --TLCHANGE } m["kl"] = { "Groenlandes", --TLCHANGE from Spanish "groenlandés" 25355, "esx-inu", "Latn", sort_key = { from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, english_name = "Greenlandic", --TLCHANGE spanish_name = "Groenlandés" --TLCHANGE } m["km"] = { "Hemer", --TLCHANGE from Spanish "jemer" 9205, "mkh-kmr", "Khmr", ancestors = "xhm", translit = "km-translit", english_name = "Khmer", --TLCHANGE spanish_name = "Jemer", --TLCHANGE } m["kn"] = { "Kanares", --TLCHANGE from Spanish "canarés" 33673, "dra-kan", "Knda, Tutg", ancestors = "dra-mkn", -- Knda translit in [[Module:scripts/data]] english_name = "Kannada", --TLCHANGE spanish_name = "Canarés", --TLCHANGE } m["ko"] = { "Koreano", --TLCHANGE official from KWF 9176, "qfa-kor", "Kore, Brai", ancestors = "ko-ear", translit = { Kore = "ko-translit", }, -- Kore strip_diacritics in [[Module:scripts/data]] is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=41", --TLCHANGE english_name = "Korean", --TLCHANGE spanish_name = "Coreano", --TLCHANGE } 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]} }, }, english_name = "Kanuri", --TLCHANGE } m["ks"] = { "Katsemir", --TLCHANGE 33552, "inc-kas", "ks-Arab, Deva, Shrd, Latn", translit = { ["ks-Arab"] = "ks-Arab-translit", Deva = "ks-Deva-translit", -- Shrd translit in [[Module:scripts/data]] }, english_name = "Kashmiri", --TLCHANGE spanish_name = "Cachemir", --TLCHANGE } -- "kv" is treated as "koi", "kpv", see [[WT:LT]] m["kw"] = { "Korniko", --TLCHANGE from Spanish "córnico" 25289, "cel-brs", "Latn", ancestors = "cnx", sort_key = { from = {"ch"}, to = {"c" .. p[1]} }, english_name = "Cornish", --TLCHANGE spanish_name = "Córnico", --TLCHANGE } m["ky"] = { "Kirgis", --from Spanish "kirguís" 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]} }, }, english_name = "Kyrgyz", --TLCHANGE spanish_name = "Kirguís", --TLCHANGE } m["la"] = { "Latin", -- official from KWF 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 }, is_official_kwf_name = "https://kwf.gov.ph/wp-content/uploads/MMP_Full.pdf#page=114", --TLCHANGE english_name = "Latin", --TLCHANGE spanish_name = "Latín", --TLCHANGE } m["lb"] = { "Luksemburges", --TLCHANGE from Spanish "luxemburgués" 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]} }, }, english_name = "Luxembourgish", --TLCHANGE spanish_name = "Luxemburgués", --TLCHANGE } m["lg"] = { "Luganda", 33368, "bnt-nyg", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ŋ"}, to = {"n" .. p[1]} }, english_name = "Luganda", --TLCHANGE } m["li"] = { "Limburges", --from Spanish "limburgués" 102172, "gmw-frk", "Latn", ancestors = "dum", english_name = "Limburgish", --TLCHANGE spanish_name = "Limburgués", --TLCHANGE } m["ln"] = { "Linggala", --TLCHANGE 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]} }, english_name = "Lingala", --TLCHANGE } m["lo"] = { "Lao", --TLCHANGE 9211, "tai-swe", "Laoo", translit = "lo-translit", sort_key = "Laoo-sortkey", standard_chars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. c.punc, english_name = "Lao", --TLCHANGE } m["lt"] = { "Litwano", --from Spanish "lituano" 9083, "bat-eas", "Latn", ancestors = "olt", display_text = "lt-common", strip_diacritics = "lt-common", sort_key = "lt-common", standard_chars = "AaĄąBbCcČčDdEeĘęĖėFfGgHhIiĮįYyJjKkLlMmNnOoPpRrSsŠšTtUuŲųŪūVvZzŽž" .. c.punc, english_name = "Lithuanian", --TLCHANGE spanish_name = "Lituano", --TLCHANGE } m["lu"] = { "Luba-Katanga", 36157, "bnt-lub", "Latn", english_name = "Luba-Katanga", --TLCHANGE } m["lv"] = { "Leton", --from Spanish "letón" 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, english_name = "Latvian", --TLCHANGE spanish_name = "Letón", --TLCHANGE } m["mg"] = { "Malgatse", --TLCHANGE from Spanish "malgache" 7930, "poz-bre", "Latn, Arab", english_name = "Malagasy", --TLCHANGE spanish_name = "Malgache", --TLCHANGE } m["mh"] = { "Marshales", --from Spanish "marshalés" 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]} }, english_name = "Marshallese", --TLCHANGE spanish_name = "Marshalés", --TLCHANGE } m["mi"] = { "Māori", --TLCHANGE 36451, "poz-pep", "Latn", sort_key = { remove_diacritics = c.macron, from = {"ng", "wh"}, to = {"n" .. p[1], "w" .. p[1]} }, english_name = "Māori", --TLCHANGE } m["mk"] = { "Masedonyo", --from Spanish "macedonio" 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 }, english_name = "Macedonian", --TLCHANGE spanish_name = "Macedonio" --TLCHANGE } m["ml"] = { "Malayalam", 36236, "dra-mal", "Mlym", override_translit = true, -- Mlym translit in [[Module:scripts/data]] english_name = "Malayalam", --TLCHANGE } m["mn"] = { "Monggol", --from Spanish "mongol" 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 }, english_name = "Mongolian", --TLCHANGE spanish_name = "Mongol" --TLCHANGE } -- "mo" is treated as "ro", see [[WT:LT]] m["mr"] = { "Marati", --TLCHANGE 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"} }, }, english_name = "Marathi", --TLCHANGE spanish_name = "Maratí", --TLCHANGE } m["ms"] = { "Malayo", --TLCHANGE 9237, "poz-mly", "Latn, ms-Arab", ancestors = "ms-cla", standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", c.punc }, english_name = "Malay", --TLCHANGE spanish_name = "Malayo", --TLCHANGE } m["mt"] = { "Maltes", --from Spanish "maltés" 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" } }, english_name = "Maltese", --TLCHANGE spanish_name = "Maltes", --TLCHANGE } m["my"] = { "Birmano", --from Spanish "birmano" 9228, "tbq-brm", "Mymr", ancestors = "obr", translit = "my-translit", override_translit = true, sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"} }, english_name = "Burmese", --TLCHANGE spanish_name = "Birmano" --TLCHANGE } m["na"] = { "Naurwano", --TLCHANGE from Spanish "nauruano" 13307, "poz-mic", "Latn", english_name = "Nauruan", --TLCHANGE spanish_name = "Nauruano" --TLCHANGE } m["nb"] = { "Norwego Bokmål", --TLCHANGE from Spanish "noruego" 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"], english_name = "Norwegian Bokmål", --TLCHANGE } m["nd"] = { "Hilagang Ndebele", 35613, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, english_name = "Northern Ndebele", --TLCHANGE } m["ne"] = { "Nepali", 33823, "inc-pah", "Deva, Newa", translit = { Deva = "ne-translit" }, english_name = "Nepali", --TLCHANGE } m["ng"] = { "Endonga", --TLCHANGE 33900, "bnt-ova", "Latn", english_name = "Ndonga", --TLCHANGE } m["nl"] = { "Nerlandes", --TLCHANGE from Spanish "neerlandés" 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 }, english_name = "Dutch", --TLCHANGE spanish_name = "Neerlandés" --TLCHANGE } m["nn"] = { "Norwego Nynorsk", --TLCHANGE from Spanish "noruego" 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"], english_name = "Norwegian Nynorsk", --TLCHANGE } m["no"] = { "Norwego", --from Spanish "noruego" 9043, "gmq-wes", "Latn", ancestors = "gmq-mno", sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], english_name = "Norwegian", --TLCHANGE spanish_name = "Noruego" --TLCHANGE } m["nr"] = { "Katimugang Ndebele", --TLCHANGE 36785, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, english_name = "Southern Ndebele", --TLCHANGE } m["nv"] = { "Navaho", --TLCHANGE 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] } }, english_name = "Navajo", --TLCHANGE spanish_name = "Navajo", --TLCHANGE } m["ny"] = { "Tsitsewa", --TLCHANGE 33273, "bnt-nys", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ng'"}, to = {"ng"} }, english_name = "Chichewa", --TLCHANGE } m["oc"] = { "Oksitano", --from Spanish "occitano" 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]] english_name = "Occitan", --TLCHANGE spanish_name = "Occitano" --TLCHANGE } m["oj"] = { "Ojibwë", --TLCHANGE this is a schwa sound, that's why "a" and "e" are interchangable in English 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]} }, }, english_name = "Ojibwe", --TLCHANGE spanish_name = "Ojibwa", --TLCHANGE } m["om"] = { "Oromo", 33864, "cus-eas", "Latn, Ethi", english_name = "Oromo", --TLCHANGE } m["or"] = { "Oriya", --TLCHANGE 33810, "inc-eas", "Orya", ancestors = "inc-mor", translit = "or-translit", english_name = "Odia", --TLCHANGE spanish_name = "Oriya", --TLCHANGE } m["os"] = { "Osetyo", --TLCHANGE from Spanish "osetio" 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]} }, }, english_name = "Ossetian", --TLCHANGE spanish_name = "Osetio" --TLCHANGE } m["pa"] = { "Punjabi", --TLCHANGE the J is actully pronounced /dʒ/ in its origin language, so no need to convert from Spanish J to Y 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"} }, }, english_name = "Punjabi", --TLCHANGE spanish_name = "Punyabí", --TLCHANGE } 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", "ᩣ"} }, english_name = "Pali", --TLCHANGE } m["pl"] = { "Polako", --from Spanish "polaco" 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, english_name = "Polish", --TLCHANGE spanish_name = "Polaco" --TLCHANGE } m["ps"] = { "Pastun", --TLCHANGE from Spanish "pastún" 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}, english_name = "Pashto", --TLCHANGE spanish_name = "Pastún" --TLCHANGE } m["pt"] = { "Portuges", --from Spanish "portugués" 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 }, english_name = "Portuguese", --TLCHANGE spanish_name = "Portugués" --TLCHANGE } m["qu"] = { "Ketsuwa", --TLCHANGE from Spanish "quechua" 5218, "qwe", "Latn", english_name = "Quechua", --TLCHANGE spanish_name = "Quechua" --TLCHANGE } m["rm"] = { "Romantse", --TLCHANGE from Spanish "Romanche" 13199, "roa-rhe", ancestors = "rm-old", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.small_e}, english_name = "Romansch", --TLCHANGE spanish_name = "Romanche" --TLCHANGE } m["ro"] = { "Rumano", --from Spanish "rumano" 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 }, english_name = "Romanian", --TLCHANGE spanish_name = "Rumano" --TLCHANGE } m["ru"] = { "Ruso", --from Spanish "ruso" 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. }, english_name = "Russian", --TLCHANGE spanish_name = "Ruso" --TLCHANGE } m["rw"] = { "Kiñarwanda-Kirundi", --TLCHANGE 3217514, "bnt-glb", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.caron}, english_name = "Rwanda-Rundi", --TLCHANGE spanish_name = "Kiñaruanda-Kirundi" --TLCHANGE } m["sa"] = { "Sanskrit", --TLCHANGE it's "Sanskrit" according to KWF 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, --}, }, is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=S%C3%A1nskrit", --TLCHANGE english_name = "Sanskrit", --TLCHANGE } m["sc"] = { "Sardo", --TLCHANGE from Spanish "sardo" 33976, "roa-sou", "Latn", ancestors = "sc-old", english_name = "Sardinian", --TLCHANGE spanish_name = "Sardo" --TLCHANGE } m["sd"] = { "Sindi", --TLCHANGE from Spanish "sindi" 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"} }, }, english_name = "Sindhi", --TLCHANGE spanish_name = "Sindi" --TLCHANGE } m["se"] = { "Hilagang Sami", --TLCHANGE 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, english_name = "Northern Sami", --TLCHANGE } m["sg"] = { "Sanggo", --TLCHANGE 33954, "crp", "Latn", ancestors = "ngb", english_name = "Sango", --TLCHANGE spanish_name = "sango", --TLCHANGE } m["sh"] = { "Serbokroata", --TLCHANGE from Spanish "Serbocroata" 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 }, english_name = "Serbo-Croatian", --TLCHANGE spanish_name = "Serbocroata" --TLCHANGE } m["si"] = { "Singgales", --from Spanish "cingalés" 13267, "inc-ins", "Sinh", translit = "si-translit", override_translit = true, english_name = "Sinhalese", --TLCHANGE spanish_name = "Singalés" --TLCHANGE } m["sk"] = { "Eslovako", --TLCHANGE from Spanish "eslovaco" 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, english_name = "Slovak", --TLCHANGE spanish_name = "Eslovaco" --TLCHANGE } m["sl"] = { "Esloveno", --TLCHANGE from Spanish "esloveno" 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, english_name = "Slovene", --TLCHANGE spanish_name = "Esloveno" --TLCHANGE } m["sm"] = { "Samoano", --from Spanish "samoano" 34011, "poz-pnp", "Latn", english_name = "Samoan", --TLCHANGE spanish_name = "Samoano" --TLCHANGE } m["sn"] = { "Shona", 34004, "bnt-sho", "Latn", strip_diacritics = {remove_diacritics = c.acute}, english_name = "Shona", --TLCHANGE } m["so"] = { "Somali", 13275, "cus-som", "Latn, Arab, Osma", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, english_name = "Somali", --TLCHANGE } m["sq"] = { "Albanes", --from Spanish "albanés" 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 }, english_name = "Albanian", --TLCHANGE spanish_name = "Albanés" --TLCHANGE } m["ss"] = { "Suwazi", --from Spanish "suazi" 34014, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, english_name = "Swazi", --TLCHANGE spanish_name = "Suazi" --TLCHANGE } m["st"] = { "Sesoto", --TLCHANGE from Spanish "Sesoto" 34340, "bnt-sts", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, english_name = "Sotho", --TLCHANGE spanish_name = "Sesoto" --TLCHANGE } m["su"] = { "Sondanes", --TLCHANGE from Spanish "sondanés" 34002, "poz-msa", "Latn, Sund, Arab", ancestors = "osn", translit = { Sund = "Sund-translit" }, english_name = "Sundanese", --TLCHANGE spanish_name = "Sondanés" --TLCHANGE } m["sv"] = { "Suweko", --from Spanish "sueco" 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, english_name = "Swedish", --TLCHANGE spanish_name = "Sueco" --TLCHANGE } m["sw"] = { "Suwahili", --TLCHANGE from Spanish "suajili" 7838, "bnt-swh", "Latn, Arab", sort_key = { Latn = { from = {"ng'"}, to = {"ng" .. p[1]} }, }, english_name = "Swahili", --TLCHANGE spanish_name = "Suajili" --TLCHANGE } m["ta"] = { "Tamil", 5885, "dra-tam", "Taml", ancestors = "ta-mid", translit = "ta-translit", override_translit = true, english_name = "Tamil", --TLCHANGE } m["te"] = { "Telugu", 8097, "dra-tel", "Telu", translit = "te-translit", override_translit = true, english_name = "Telugu", --TLCHANGE } m["tg"] = { "Tayiko", --from Spanish "tayiko" 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]} }, }, english_name = "Tajik", --TLCHANGE spanish_name = "Tayiko", --TLCHANGE } m["th"] = { "Tailandes", --from Spanish "tailandés" 9217, "tai-swe", "Thai, Khomt, Brai", translit = { Thai = "th-translit" }, sort_key = { Thai = "Thai-sortkey" }, english_name = "Thai", --TLCHANGE spanish_name = "Tailandés", --TLCHANGE } m["ti"] = { "Tigriña", --TLCHANGE from Spanish tigriña 34124, "sem-eth", "Ethi", translit = "Ethi-translit", english_name = "Tigrinya", --TLCHANGE spanish_name = "Tigriña", --TLCHANGE } m["tk"] = { "Turkomano", --TLCHANGE from Spanish "turcomano" 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", english_name = "Turkmen", --TLCHANGE spanish_name = "Turcomano", --TLCHANGE } 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", }, is_official_kwf_name = "https://kwfwikaatkultura.ph/tagalog-2/", --TLCHANGE english_name = "Tagalog", --TLCHANGE } m["tn"] = { "Setsuwana", --TLCHANGE from Spanish "Setsuana" 34137, "bnt-sts", "Latn", english_name = "Tswana", --TLCHANGE spanish_name = "Setsuana", --TLCHANGE } m["to"] = { "Tonggano", --from Spanish "tongano" 34094, "poz-ton", "Latn", strip_diacritics = {remove_diacritics = c.acute}, sort_key = {remove_diacritics = c.macron}, english_name = "Tongan", --TLCHANGE spanish_name = "Tongano", --TLCHANGE } m["tr"] = { "Turko", --from Spanish "turco" 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, english_name = "Turkish", --TLCHANGE spanish_name = "Turco", --TLCHANGE } m["ts"] = { "Tsongga", --from Spanish "tsonga" 34327, "bnt-tsr", "Latn", english_name = "Tsonga", --TLCHANGE spanish_name = "Tsonga", --TLCHANGE } m["tt"] = { "Tartaro", --from Spanish "tártaro" 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] } }, }, english_name = "Tatar", --TLCHANGE spanish_name = "Tártaro", --TLCHANGE } -- "tw" is treated as "ak", see [[WT:LT]] m["ty"] = { "Tahityano", --TLCHANGE from Spanish "tahitiano" 34128, "poz-pep", "Latn", english_name = "Tahitian", --TLCHANGE spanish_name = "Tahitiano", --TLCHANGE } m["ug"] = { "Wigur", --TLCHANGE from Spanish "uigur" 13263, "trk-kar", "ug-Arab, Latn, Cyrl", ancestors = "chg", translit = { ["ug-Arab"] = "ug-translit", Cyrl = "ug-translit", }, override_translit = true, english_name = "Uyghur", --TLCHANGE spanish_name = "Uigur", --TLCHANGE } m["uk"] = { "Ukranyano", --from Spanish "ucraniano" 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. english_name = "Ukrainian", --TLCHANGE spanish_name = "Ucraniano", --TLCHANGE } 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, }, english_name = "Urdu", --TLCHANGE } m["uz"] = { "Uzbeko", --TLCHANGE from Spanish "uzbeko" 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", }, english_name = "Uzbek", --TLCHANGE spanish_name = "Uzbeko", --TLCHANGE } m["ve"] = { "Venda", --TLCHANGE from Spanish "venda" 32704, "bnt-bso", "Latn", english_name = "Venda", --TLCHANGE spanish_name = "Venda", --TLCHANGE } m["vi"] = { "Viyetnamita", --TLCHANGE 9199, "mkh-vie", "Latn, Hani", ancestors = "mkh-mvi", sort_key = { Latn = "vi-sortkey", Hani = "Hani-sortkey", }, english_name = "Vietnamese", --TLCHANGE spanish_name = "Vietnamita", --TLCHANGE } m["vo"] = { "Volapük", 36986, "art", "Latn", english_name = "Volapük", --TLCHANGE } m["wa"] = { "Valon", --TLCHANGE from Spanish "valón" 34219, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], english_name = "Walloon", --TLCHANGE spanish_name = "Valón", --TLCHANGE } m["wo"] = { "Wolof", --from Spanish "wólof" 34257, "alv-fwo", "Latn, Arab, Gara", english_name = "Wolof", --TLCHANGE spanish_name = "Wólof", --TLCHANGE } m["xh"] = { "Khosa", --TLCHANGE we have "kh", it is the closest to [ᵏǁʰôːsa] 13218, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, english_name = "Xhosa", --TLCHANGE spanish_name = "Xhosa", --TLCHANGE } m["yi"] = { "Yidis", --from Spanish "Yidis" 8641, "gmw-hgm", "Hebr, Latn", ancestors = "gmh", translit = { Hebr = "yi-translit", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] english_name = "Yiddish", --TLCHANGE spanish_name = "Yidis", --TLCHANGE } 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]} }, }, english_name = "Yoruba", --TLCHANGE } m["za"] = { "Zhuang", 13216, "tai", "Latn, Hani", sort_key = { Latn = "za-sortkey", Hani = "Hani-sortkey", }, english_name = "Zhuang", --TLCHANGE } m["zh"] = { "Tsino", --from Spanish "chino" 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" }, is_official_kwf_name = "https://kwfdiksiyonaryo.ph/?query=Ts%C3%ADno", --TLCHANGE english_name = "Chinese", --TLCHANGE spanish_name = "Chino", --TLCHANGE } m["zu"] = { "Zulu", --from Spanish "zulú" 10179, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, english_name = "Zulu", --TLCHANGE spanish_name = "Zulú", --TLCHANGE } return require("Module:languages").finalizeData(m, "language") p0yus3xmaqn0znu7tidsdbpcfe820ln 828 32634 176320 175584 2026-04-14T02:44:53Z Yivan000 4078 176320 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", --"Gaddang", 3438830, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/gaddang/", --TLCHANGE english_name = "Gaddang", --TLCHANGE } 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 "Gâdang", --TLCHANGE (this is the one in Paracelis, Mountain Province) 5515189, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/gaddang/", --TLCHANGE english_name = "Ga'dang", --TLCHANGE } 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", -- different from Gâdang (Paracelis, Mountain Province) 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["ggn"] = { "Eastern Gurung", 12952472, "sit-tam", "Gukh, Deva", } 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"] = { "Griyego Miseniko", --TLCHANGE 668366, "grk", "Linb", translit = "Linb-translit", english_name = "Mycenaean Greek", --TLCHANGE spanish_name = "Griego micénico", --TLCHANGE } 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"] = { "Gotiko", --TLCHANGE 35722, "gme", "Goth, Runr, Latn", translit = {Goth = "Goth-translit"}, link_tr = true, strip_diacritics = {Latn = {remove_diacritics = c.macron}}, english_name = "Gothic", --TLCHANGE spanish_name = "Gótico", --TLCHANGE } 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"] = { "Sinaunang Griyego", --TLCHANGE 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 }, english_name = "Ancient Greek", --TLCHANGE spanish_name = "Griego antiguo", --TLCHANGE } 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"] = { "Wikang Senyas ng mga Griyego", --TLCHANGE 3565084, "sgn", english_name = "Greek Sign Language", --TLCHANGE spanish_name = "Lengua de signos griego", --TLCHANGE } 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"] = { "Western 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") mlw7pi4zu6uduz67ta9wt7y09z6ut2q 828 32636 176306 175551 2026-04-13T13:08:38Z Yivan000 4078 176306 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["baa"] = { "Babatana", 2877785, "poz-ocw", "Latn", } m["bab"] = { "Bainouk-Gunyuño", 35508, "alv-bny", "Latn", } m["bac"] = { "Baduy", 3449885, "poz-msa", "Latn, Sund", ancestors = "osn", translit = { Sund = "Sund-translit" }, } m["bae"] = { "Baré", 3504087, "awd", "Latn", } m["baf"] = { "Nubaca", 36270, "nic-ymb", "Latn", } m["bag"] = { "Tuki", 36621, "nic-mba", "Latn", } m["bah"] = { "Bahamian Creole", 2669229, "crp", "Latn", ancestors = "en", } m["baj"] = { "Barakai", 3502030, "poz-cet", "Latn", } m["bal"] = { "Baluchi", 33049, "ira-nwi", "fa-Arab", } m["ban"] = { "Balines", --TLCHANGE 33070, "poz-bss", "Latn, Bali", english_name = "Balinese", --TLCHANGE spanish_name = "Balinés", --TLCHANGE } m["bao"] = { "Waimaha", 2883738, "sai-tuc", "Latn", } m["bap"] = { "Bantawa", 56500, "sit-kic", "Krai, Deva", } m["bar"] = { "Bavaro", --TLCHANGE 29540, "gmw-hgm", "Latn", ancestors = "gmh", english_name = "Bavarian", --TLCHANGE spanish_name = "Bávaro", --TLCHANGE } m["bas"] = { "Basaa", 33093, "bnt-bsa", "Latn", } m["bau"] = { "Badanchi", 11001650, "nic-jrw", "Latn", } m["bav"] = { "Babungo", 34885, "nic-rnn", "Latn", } m["baw"] = { "Bambili-Bambui", 34880, "nic-nge", "Latn", } m["bax"] = { "Bamum", 35280, "nic-nun", "Latn, Bamu", } m["bay"] = { "Batuley", 8828787, "poz", "Latn", } m["bba"] = { "Baatonum", 34889, "alv-sav", "Latn", } m["bbb"] = { "Barai", 4858206, "ngf-koi", "Latn", } m["bbc"] = { "Toba Batak", 33017, "btk", "Latn, Batk", } m["bbd"] = { "Bau", 4873415, "ngf-gum", "Latn", } m["bbe"] = { "Bangba", 34895, "nic-nke", "Latn", } m["bbf"] = { "Baibai", 56902, "paa-fas", "Latn", } m["bbg"] = { "Barama", 34884, "bnt-sir", "Latn", } m["bbh"] = { "Bugan", 3033554, "mkh-pkn", "Latn", } m["bbi"] = { "Barombi", 34985, "bnt-bsa", "Latn", } m["bbj"] = { "Ghomala'", 35271, "bai", "Latn", } m["bbk"] = { "Babanki", 34790, "nic-rnc", "Latn", } m["bbl"] = { "Bats", 33259, "cau-nkh", "Geor", -- Geor translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { remove_diacritics = c.tilde .. c.macron .. c.breve, from = {"^ნ"}, to = {"ნ"} }, } m["bbm"] = { -- name includes prefix "Babango", 34819, "bnt-bta", "Latn", } m["bbn"] = { "Uneapa", 7884126, "poz-ocw", "Latn", } m["bbo"] = { "Konabéré", 35371, "dmn-snb", "Latn", } m["bbp"] = { "West Central Banda", 7984377, "bad", "Latn", } m["bbq"] = { "Bamali", 34901, "nic-nun", "Latn", } m["bbr"] = { "Girawa", 5564185, "ngf-kok", "Latn", } m["bbs"] = { "Bakpinka", 3515061, "nic-ucr", "Latn", } m["bbt"] = { "Mburku", 3441324, "cdc-wst", "Latn", } m["bbu"] = { "Bakulung", 35580, "nic-jrn", "Latn", } m["bbv"] = { "Karnai", 6372803, "poz-ocw", "Latn", } m["bbw"] = { "Baba", 34822, "nic-nun", "Latn", } m["bbx"] = { -- cf bvb "Bubia", 34953, "nic-bds", "Latn", ancestors = "bvb", } m["bby"] = { "Befang", 34960, "nic-bds", "Latn", } m["bca"] = { "Central Bai", 12628803, "sit-bai", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bcb"] = { "Bainouk-Samik", 36390, "alv-bny", "Latn", } m["bcd"] = { "North Babar", 7054041, "poz-tim", "Latn", } m["bce"] = { "Bamenyam", 34968, "nic-nun", "Latn", } m["bcf"] = { "Bamu", 3503788, "paa-kiw", "Latn", } m["bcg"] = { "Baga Pokur", 31172660, "alv-nal", "Latn", } m["bch"] = { "Bariai", 2884502, "poz-ocw", "Latn", } m["bci"] = { "Baoule", 35107, "alv-ctn", "Latn", } m["bcj"] = { "Bardi", 3913852, "aus-nyu", "Latn", } m["bck"] = { "Bunaba", 580923, "aus-bub", "Latn", } m["bcl"] = { "Bikol Naga", --"Bikol Central", 33284, "phi", "Latn, Tglg", translit = { Tglg = "bcl-translit", }, override_translit = true, strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ, } }, sort_key = { Latn = "tl-sortkey", }, standard_chars = { Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy" .. c.punc, }, is_official_kwf_name = "https://kwfwikaatkultura.ph/bikol/", --TLCHANGE english_name = "Bikol Central", --TLCHANGE } m["bcm"] = { "Banoni", 2882857, "poz-ocw", "Latn", } m["bcn"] = { "Bibaali", 34892, "alv-mye", "Latn", } m["bco"] = { "Kaluli", 6354586, "ngf-bos", "Latn", } m["bcp"] = { "Bali", 3515074, "bnt-kbi", "Latn", } m["bcq"] = { "Bench", 35108, "omv", "Latn", } m["bcr"] = { "Babine-Witsuwit'en", 27864, "ath-nor", "Latn", } m["bcs"] = { "Kohumono", 35590, "nic-ucn", "Latn", } m["bct"] = { "Bendi", 8836662, "csu-mle", "Latn", } m["bcu"] = { "Biliau", 2874658, "poz-ocw", "Latn", } m["bcv"] = { "Shoo-Minda-Nye", 36548, "nic-jkn", "Latn", } m["bcw"] = { "Bana", 56272, "cdc-cbm", "Latn", } m["bcy"] = { "Bacama", 56274, "cdc-cbm", "Latn", } m["bcz"] = { "Bainouk-Gunyaamolo", 35506, "alv-bny", "Latn", } m["bda"] = { "Bayot", 35019, "alv-jol", "Latn", } m["bdb"] = { "Basap", 3504208, "poz-bnn", "Latn", } m["bdc"] = { "Emberá-Baudó", 11173166, "sai-chc", "Latn", } m["bdd"] = { "Bunama", 4997416, "poz-ocw", "Latn", } m["bde"] = { "Bade", 56239, "cdc-wst", "Latn", } m["bdf"] = { "Biage", 48037487, "ngf-koi", "Latn", } m["bdg"] = { "Bonggi", 2910053, "poz-bnn", "Latn", } m["bdh"] = { "Tara Baka", 2880165, "csu-bbk", "Latn", } m["bdi"] = { "Burun", 35040, "sdv-niw", "Latn", } m["bdj"] = { "Bai (South Sudan)", 34894, "nic-ser", "Latn", } m["bdk"] = { "Budukh", 35397, "cau-ssm", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["bdl"] = { "Indonesian Bajau", 2880038, "poz", "Latn", } m["bdm"] = { "Buduma", 56287, "cdc-cbm", "Latn", } m["bdn"] = { "Baldemu", 56280, "cdc-cbm", "Latn", } m["bdo"] = { "Morom", 759770, "csu-bgr", "Latn", } m["bdp"] = { "Bende", 8836490, "bnt", "Latn", } m["bdq"] = { "Bahnar", 32924, "mkh-ban", "Latn", } m["bdr"] = { "West Coast Bajau", 2880037, "poz-sbj", "Latn", } m["bds"] = { "Burunge", 56617, "cus-sou", "Latn", } m["bdt"] = { "Bokoto", 4938812, "gba-wes", "Latn", } m["bdu"] = { "Oroko", 36278, "bnt-saw", "Latn", } m["bdv"] = { "Bodo Parja", 8845881, "inc-eas", "Orya", } m["bdw"] = { "Baham", 3513309, "paa-mbi", "Latn", } m["bdx"] = { "Budong-Budong", 4985158, "poz-ssw", "Latn", } m["bdy"] = { "Bandjalang", 2980386, "aus-pam", "Latn", } m["bdz"] = { "Badeshi", 33028, "iir", "Arab, Latn", } m["bea"] = { "Beaver", 20826, "ath-nor", "Latn", } m["beb"] = { "Bebele", 34976, "bnt-btb", "Latn", } m["bec"] = { "Iceve-Maci", 35449, "nic-tvc", "Latn", } m["bed"] = { "Bedoanas", 4879330, "poz-hce", "Latn", } m["bee"] = { "Byangsi", 56904, "sit-alm", "Deva", } m["bef"] = { "Benabena", 2895638, "ngf-gor", "Latn", } m["beg"] = { "Belait", 2894198, "poz-swa", "Latn", } m["beh"] = { "Biali", 34961, "nic-eov", "Latn", } m["bei"] = { "Bekati'", 3441683, "day", "Latn", } m["bej"] = { "Beja", 33025, "cus", "Arab, Latn", strip_diacritics = { Latn = { remove_diacritics = c.acute, } }, } m["bek"] = { "Bebeli", 4878430, "poz-ocw", "Latn", } m["bem"] = { "Bemba", 33052, "bnt-sbi", "Latn", } m["beo"] = { "Beami", 3504079, "ngf-bos", "Latn", } m["bep"] = { "Besoa", 8840465, "poz-kal", "Latn", } m["beq"] = { "Beembe", 3196320, "bnt-kng", "Latn", } m["bes"] = { "Besme", 289832, "alv-kim", "Latn", } m["bet"] = { "Guiberoua Bété", 11019185, "kro-bet", "Latn", } m["beu"] = { "Blagar", 4923846, "paa-alp", "Latn", } m["bev"] = { "Daloa Bété", 11155819, "kro-bet", "Latn", } m["bew"] = { "Betawi", 33014, "crp", "Latn", ancestors = "ms", } m["bex"] = { "Jur Modo", 56682, "csu-bbk", "Latn", } m["bey"] = { "Beli (New Guinea)", 3504170, "paa-trr", "Latn", } m["bez"] = { "Kibena", 2502949, "bnt-bki", "Latn", } m["bfa"] = { "Bari", 35042, "sdv-bri", "Latn", } m["bfb"] = { "Pauri Bareli", 7155462, "inc-bhi", "Deva", } m["bfc"] = { "Panyi Bai", 12642165, "sit-nba", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bfd"] = { "Bafut", 34888, "nic-nge", "Latn", } m["bfe"] = { "Betaf", 4897329, "paa-bvi", "Latn", } m["bff"] = { "Bofi", 34914, "gba-eas", "Latn", } m["bfg"] = { "Busang Kayan", 9231909, "poz", "Latn", } m["bfh"] = { "Blafe", 12628007, "paa-ton", "Latn", } m["bfi"] = { "Wikang Senyas ng mga Britaniko", --TLCHANGE 33000, "sgn", "Latn", -- when documented english_name = "British Sign Language", --TLCHANGE spanish_name = "Lengua de signos británico", --TLCHANGE } m["bfj"] = { "Bafanji", 34890, "nic-nun", "Latn", } m["bfk"] = { "Wikang Senyas ng Ban Khor", --TLCHANGE 3441103, "sgn", english_name = "Ban Khor Sign Language", --TLCHANGE spanish_name = "Lengua de signos ban khor", --TLCHANGE } m["bfl"] = { "Banda-Ndélé", 34850, "bad-cnt", "Latn", } m["bfm"] = { "Mmen", 36132, "nic-rnc", "Latn", } m["bfn"] = { "Bunak", 35101, "paa-tap", "Latn", } m["bfo"] = { "Malba Birifor", 11150710, "nic-mre", "Latn", } m["bfp"] = { "Beba", 35050, "nic-nge", "Latn", } m["bfq"] = { "Badaga", 33205, "dra-kan", "Taml, Knda, Mlym", translit = { --Taml = "Taml-translit", }, -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["bfr"] = { "Bazigar", 8829558, "inc", } m["bfs"] = { "Southern Bai", 12952250, "sit-bai", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bft"] = { "Balti", 33086, "sit-lab", "fa-Arab, Deva, Tibt", override_translit = "Tibt", -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] strip_diacritics = { ["fa-Arab"] = { from = {"هٔ", "ٱ"}, to = {"ه", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.kashida .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, }, }, } m["bfu"] = { "Gahri", 5516952, "sit-whm", "Takr, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["bfw"] = { "Bondo", 2567942, "mun", "Orya", } m["bfx"] = { "Bantayanon", 16837866, "phi", "Latn", } m["bfy"] = { "Bagheli", 2356364, "inc-hie", "Deva", ancestors = "inc-oaw", translit = "hi-translit", } m["bfz"] = { "Mahasu Pahari", 6733460, "him", "Deva, Takr", translit = "hi-translit", } m["bga"] = { "Gwamhi-Wuri", 6707102, "nic-knn", "Latn", } m["bgb"] = { "Bobongko", 4935896, "poz-slb", "Latn", } m["bgc"] = { "Haryanvi", 33410, "inc-hiw", "Deva", translit = "hi-translit", } m["bgd"] = { "Rathwi Bareli", 7295692, "inc-bhi", "Deva", } m["bge"] = { "Bauria", 4873579, "inc-bhi", "Deva", } m["bgf"] = { "Bangandu", 34938, "gba-sou", "Latn", } m["bgg"] = { "Bugun", 3514220, "sit-khb", "Latn", } m["bgi"] = { "Klata", --"Giangan", 4842057, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/klata/", --TLCHANGE english_name = "Giangan", --TLCHANGE } m["bgj"] = { "Bangolan", 34862, "nic-nun", "Latn", } m["bgk"] = { "Bit", 2904868, "mkh-pal", "Latn", -- also Hani? } m["bgl"] = { "Bo", 8845514, "mkh-vie", } m["bgo"] = { "Baga Koga", 35695, "alv-bag", "Latn", } m["bgq"] = { "Bagri", 2426319, "raj", "Deva", } m["bgr"] = { "Bawm Chin", 56765, "tbq-kuk", "Latn", } m["bgs"] = { "Tagabawa", --"Tagabawa" 7675121, "mno", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/tagabawa/", --TLCHANGE english_name = "Tagabawa", --TLCHANGE } m["bgt"] = { "Bughotu", 2927723, "poz-sls", "Latn", } m["bgu"] = { "Mbongno", 36141, "nic-mmb", "Latn", } m["bgv"] = { "Warkay-Bipim", 4915439, "paa-yaq", "Latn", } m["bgw"] = { "Bhatri", 8841054, "inc-eas", "Deva", } m["bgx"] = { "Balkan Gagauz Turkish", 2360396, "trk-ogz", "Latn", ancestors = "trk-oat", } m["bgy"] = { "Benggoi", 4887742, "poz-cma", "Latn", } m["bgz"] = { "Banggai", 3441692, "poz-slb", "Latn", } m["bha"] = { "Bharia", 4901287, "inc", "Deva", } m["bhb"] = { "Bhili", 33229, "inc-bhi", "Deva, Gujr", translit = { Deva = "hi-translit", Gujr = "gu-translit", }, } m["bhc"] = { "Biga", 2902375, "poz-hce", "Latn", } m["bhd"] = { "Bhadrawahi", 4900565, "him", "Arab, Deva", translit = {Deva = "hi-translit"}, } m["bhe"] = { "Bhaya", 8841168, "raj", } m["bhf"] = { "Odiai", 56690, "qfa-dis", -- Papuan; no consensus; may be in the Kwomtari family, an isolate and/or distantly related to the -- Torricelli family. "Latn", } m["bhg"] = { "Binandere", 3503802, "ngf-bin", "Latn", } m["bhh"] = { "Bukhari", 56469, "ira-swi", "Cyrl, Hebr, Latn, fa-Arab", ancestors = "tg", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["bhi"] = { "Bhilali", 4901729, "inc-bhi", "Deva", } m["bhj"] = { "Bahing", 56442, "sit-kiw", "Deva, Latn", } m["bhl"] = { "Bimin", 4913743, "ngf-mok", "Latn", } m["bhm"] = { "Bathari", 2586893, "sem-sar", "Arab, Latn", } m["bhn"] = { "Bohtan Neo-Aramaic", 33230, "sem-nna", "Syrc", } m["bho"] = { "Bhojpuri", 33268, "inc-bih", "Deva, Kthi", wikimedia_codes = "bh", translit = { Deva = "bho-translit", Kthi = "bho-Kthi-translit", }, } m["bhp"] = { "Bima", 2796873, "poz-cet", "Latn", } m["bhq"] = { "South Tukang Besi", 12643975, "poz-mun", "Latn", } m["bhs"] = { "Buwal", 3515065, "cdc-cbm", "Latn", } m["bht"] = { "Bhattiyali", 4901452, "him", "Deva", } m["bhu"] = { "Bhunjia", 8841766, "inc-hal", "Deva, Orya", } m["bhv"] = { "Bahau", 3502039, "poz", "Latn", } m["bhw"] = { "Biak", 1961488, "poz-hce", "Latn", } m["bhx"] = { -- spurious? "Bhalay", 8840773, "inc", } m["bhy"] = { "Bhele", 4901671, "bnt-kbi", "Latn", } m["bhz"] = { "Bada", 4840520, "poz-kal", "Latn", } m["bia"] = { "Badimaya", 3442745, "aus-psw", "Latn", } m["bib"] = { "Bissa", 32934, "dmn-bbu", "Latn", } --- Bikaru [bic] is spurious m["bid"] = { "Bidiyo", 56258, "cdc-est", "Latn", } m["bie"] = { "Bepour", 4890914, "ngf-kum", "Latn", } m["bif"] = { "Biafada", 35099, "alv-ten", "Latn", } m["big"] = { "Biangai", 8842027, "paa-kun", "Latn", } m["bij"] = { "Kwanka", 35598, "nic-tar", "Latn", } m["bil"] = { "Bile", 34987, "nic-jrn", "Latn", } m["bim"] = { "Bimoba", 34971, "nic-grm", "Latn", } m["bin"] = { "Edo", 35375, "alv-eeo", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.grave .. c.macron .. c.dgrave}, sort_key = { from = {"ẹ", "gb", "gh", "kh", "kp", "mw", "nw", "ny", "ọ", "rh", "rr", "vb"}, to = {"e" .. p[1], "g" .. p[1], "g" .. p[2], "k" .. p[1], "k" .. p[2], "m" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "r" .. p[1], "r" .. p[1], "v" .. p[1]} }, } m["bio"] = { "Nai", 3508074, "paa-kwo", "Latn", } m["bip"] = { "Bila", 2902626, "bnt-kbi", "Latn", } m["biq"] = { "Bipi", 2904312, "poz-aay", "Latn", } m["bir"] = { "Bisorio", 8844749, "ngf-oen", "Latn", } m["bit"] = { "Berinomo", 56447, "paa-sep", "Latn", } m["biu"] = { "Biete", 4904687, "tbq-kuk", "Latn", } m["biv"] = { "Southern Birifor", 32859745, "nic-mre", "Latn", } m["biw"] = { "Kol (Cameroon)", 35582, "bnt-mka", "Latn", } m["bix"] = { "Bijori", 3450686, "mun", "Deva", } m["biy"] = { "Birhor", 3450469, "mun", "Deva", } m["biz"] = { "Baloi", 3450590, "bnt-ngn", "Latn", } m["bja"] = { "Budza", 3046889, "bnt-bun", "Latn", } m["bjb"] = { "Barngarla", 3439071, "aus-pam", "Latn", } m["bjc"] = { "Bariji", 4690919, "ngf-yar", "Latn", } m["bje"] = { "Biao-Jiao Mien", 3503800, "hmx-mie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bjf"] = { "Barzani Jewish Neo-Aramaic", 33234, "sem-nna", "Hebr", -- maybe others -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["bjg"] = { "Bidyogo", 35365, "alv-bak", "Latn", } m["bjh"] = { "Bahinemo", 56361, "paa-sep", "Latn", } m["bji"] = { "Burji", 34999, "cus-hec", "Latn, Ethi", } m["bjj"] = { "Kannauji", 2726867, "inc-hiw", "Deva", } m["bjk"] = { "Barok", 2884743, "poz-ocw", "Latn", } m["bjl"] = { "Bulu (New Guinea)", 4997162, "poz-ocw", "Latn", } m["bjm"] = { "Bajelani", 4848866, "ira-zgr", "Latn, Arab", ancestors = "hac", } m["bjn"] = { "Banjares", --TLCHANGE the J is actully pronounced /dʒ/ in its origin language, so no need to convert from Spanish J to Y 33151, "poz-mly", "Latn, Arab", english_name = "Banjarese", --TLCHANGE spanish_name = "Banjarés", --TLCHANGE } m["bjo"] = { "Mid-Southern Banda", 42303990, "bad-cnt", "Latn", } m["bjp"] = { "Fanamaket", 56704263, "poz-oce", "Latn", } m["bjr"] = { "Binumarien", 538364, "ngf-tai", "Latn", } m["bjs"] = { "Bajan", 2524014, "crp", "Latn", ancestors = "en", } m["bjt"] = { "Balanta-Ganja", 19359034, "alv-bak", "Arab, Latn", } m["bju"] = { "Busuu", 35046, "nic-fru", "Latn", } m["bjv"] = { "Bedjond", 8829831, "csu-sar", "Latn", } m["bjw"] = { "Bakwé", 34899, "kro-ekr", "Latn", } m["bjx"] = { "Itnëg Banaw", --"Banao Itneg", 12627559, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/itneg/", --TLCHANGE english_name = "Banao Itneg", --TLCHANGE } m["bjy"] = { "Bayali", 4874263, "aus-pam", "Latn", } m["bjz"] = { "Baruga", 2886189, "ngf-bin", "Latn", } m["bka"] = { "Kyak", 35653, "alv-bwj", "Latn", } m["bkc"] = { "Baka", 34905, "nic-nkb", "Latn", } m["bkd"] = { "Binukid", --"Binukid", 4914553, "mno", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/binukid/", --TLCHANGE english_name = "Binukid", --TLCHANGE } m["bkf"] = { "Beeke", 3441375, "bnt-kbi", "Latn", } m["bkg"] = { "Buraka", 35066, "nic-nkg", "Latn", } m["bkh"] = { "Bakoko", 34866, "bnt-bsa", "Latn", } m["bki"] = { "Baki", 11024697, "poz-vnc", "Latn", } m["bkj"] = { "Pande", 36263, "bnt-ngn", "Latn", } m["bkk"] = { -- written in Balti script "Brokskat", 2925988, "inc-shn", "Tibt, Arab", -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- (NOTE: formerly not present, probably an accidental omission) } m["bkl"] = { "Berik", 378743, "paa-tor", "Latn", } m["bkm"] = { "Kom (Cameroon)", 1656595, "nic-rnc", "Latn", } m["bkn"] = { "Bukitan", 3446774, "poz-bnn", "Latn", } m["bko"] = { "Kwa'", 35567, "bai", "Latn", } m["bkp"] = { "Iboko", 35089, "bnt-ngn", "Latn", } m["bkq"] = { "Bakairí", 56846, "sai-pek", "Latn", } m["bkr"] = { "Bakumpai", 3436626, "poz-brw", "Latn", } m["bks"] = { "Hilagang Sorsoganon", --TLCHANGE 16113356, "phi", "Latn", english_name = "Masbate Sorsogon", --TLCHANGE is_official_kwf_name = "https://kwfwikaatkultura.ph/ortograpiyang-sorsoganon/" --TLCHANGE } m["bkt"] = { "Boloki", 4144560, "bnt-zbi", "Latn", ancestors = "lse", } m["bku"] = { "Buhid Mangyan", --"Buhid", 1002956, "phi", "Latn, Buhd", translit = { Buhd = "bku-translit", }, override_translit = true, strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ, } }, sort_key = { Latn = "tl-sortkey", }, standard_chars = { Latn = "AaBbKkDdEeFfGgHhIiLlMmNnOoPpRrSsTtUuWwYy" .. c.punc, }, is_official_kwf_name = "https://kwfwikaatkultura.ph/buhid-mangyan/", --TLCHANGE english_name = "Buhid", --TLCHANGE } m["bkv"] = { "Bekwarra", 34954, "nic-ben", "Latn", } m["bkw"] = { "Bekwel", 34950, "bnt-bek", "Latn", } m["bkx"] = { "Baikeno", 11200640, "poz-tim", "Latn", } m["bky"] = { "Bokyi", 35087, "nic-ben", "Latn", } m["bkz"] = { "Bungku", 2928207, "poz-btk", "Latn", } m["bla"] = { "Blackfoot", 33060, "alg", "Latn, Cans", } m["blb"] = { "Bilua", 35003, "qfa-dis", -- Papuan; isolate per Glottolog, Central Solomon per Ross (2005) and Pedrós (2015) "Latn", } m["blc"] = { "Bella Coola", 977808, "sal", "Latn", } m["bld"] = { "Bolango", 3450578, "phi", "Latn", } m["ble"] = { "Balanta-Kentohe", 56789, "alv-bak", "Latn", } m["blf"] = { "Buol", 2928278, "phi", "Latn", } m["blg"] = { "Balau", 4850134, "poz-mly", "Latn", } m["blh"] = { "Kuwaa", 35579, "kro", "Latn", } m["bli"] = { "Bolia", 34910, "bnt-mon", "Latn", } m["blj"] = { "Bulungan", 9229310, "poz", "Latn", } m["blk"] = { "Pa'o Karen", 7121294, "kar", "Mymr", } m["bll"] = { "Biloxi", 2903780, "sio-ohv", "Latn", } m["blm"] = { "Beli (South Sudan)", 56821, "csu-bbk", "Latn", } m["bln"] = { "Bikol Katimugang Catanduanes", --TLCHANGE 7569754, "phi", "Latn", english_name = "Southern Catanduanes Bicolano", --TLCHANGE } m["blo"] = { "Anii", 34838, "alv-ntg", "Latn", } m["blp"] = { "Blablanga", 2905245, "poz-ocw", "Latn", } m["blq"] = { "Baluan-Pam", 2881675, "poz-aay", "Latn", } m["blr"] = { "Blang", 4925096, "mkh-pal", "Latn, Tale, Lana, Thai", sort_key = { -- FIXME: This needs to be converted into the current standardized format. from = {"[%pᪧๆ]", "[᩠ᩳ-᩿]", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "ᩈᩈ", "ᩁ", "ᩃ", "ᨦ", "%1ᨮ", "%1ᨻ", "ᩣ", "", "%2%1"} }, } m["bls"] = { "Balaesang", 4849796, "poz", "Latn", } m["blt"] = { "Tai Dam", 56407, "tai-swe", "Tavt, Latn", --translit = "Tavt-translit", sort_key = { Tavt = { from = {"[꪿ꫀ꫁ꫂ]", "([ꪵꪶꪹꪻꪼ])([ꪀ-ꪯ])"}, to = {"", "%2%1"} }, }, } m["blv"] = { "Kibala", 4939959, "bnt-kmb", "Latn", } m["blw"] = { "Balangaw", --"Balangao", 4850033, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/balangaw/", --TLCHANGE english_name = "Balangao", --TLCHANGE } m["blx"] = { "Ayta Mag-indi", --"Mag-Indi Ayta", 1931221, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/ayta-mag-indi/", --TLCHANGE english_name = "Mag-Indi Ayta", --TLCHANGE } m["bly"] = { "Notre", 11009194, "nic-wov", "Latn", } m["blz"] = { "Balantak", 4850053, "poz-slb", "Latn", } m["bma"] = { "Lame", 3913997, "nic-jrn", "Latn", } m["bmb"] = { "Bembe", 4885023, "bnt-lgb", "Latn", } m["bmc"] = { "Biem", 4904523, "poz-ocw", "Latn", } m["bmd"] = { "Baga Manduri", 35815, "alv-bag", "Latn", } m["bme"] = { "Limassa", 11004666, "nic-nkb", "Latn", } m["bmf"] = { "Bom", 35088, "alv-mel", "Latn", } m["bmg"] = { "Bamwe", 34867, "bnt-bun", "Latn", } m["bmh"] = { "Kein", 6383764, "ngf-kok", "Latn", } m["bmi"] = { "Bagirmi", 34903, "csu-bgr", "Latn", } m["bmj"] = { "Bote-Majhi", 9229570, "inc-bih", "Deva", } m["bmk"] = { "Ghayavi", 5555976, "poz-ocw", "Latn", } m["bml"] = { "Bomboli", 35055, "bnt-ngn", "Latn", } m["bmn"] = { "Bina", 8843664, "poz-ocw", "Latn", } m["bmo"] = { "Bambalang", 34868, "nic-nun", "Latn", } m["bmp"] = { "Bulgebi", 4996380, "ngf-war", "Latn", } m["bmq"] = { "Bomu", 35065, "nic-bwa", "Latn", } m["bmr"] = { "Muinane", 3027894, "sai-bor", "Latn", } m["bmt"] = { "Biao Mon", 8842159, "hmx-mie", } m["bmu"] = { "Somba-Siawari", 5000983, "ngf-kbm", "Latn", } m["bmv"] = { "Bum", 35058, "nic-rnc", "Latn", } m["bmw"] = { "Bomwali", 34984, "bnt-ndb", "Latn", } m["bmx"] = { "Baimak", 3450546, "ngf-han", "Latn", } m["bmz"] = { "Baramu", 4858315, "paa-tir", "Latn", } m["bna"] = { "Bonerate", 4941729, "poz-mun", "Latn", } m["bnb"] = { "Bookan", 4943150, "poz-san", "Latn", } m["bnd"] = { "Banda", 3504147, "poz-cma", "Latn", } m["bne"] = { "Bintauna", 4914533, "phi", "Latn", } m["bnf"] = { "Masiwang", 6783305, "poz-cma", "Latn", } m["bng"] = { "Benga", 34952, "bnt-saw", "Latn", } m["bni"] = { "Bangi", 34936, "bnt-bmo", "Latn", } m["bnj"] = { "Bangon Mangyan", --"Eastern Tawbuid", 18757427, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/bangon-mangyan/", --TLCHANGE english_name = "Eastern Tawbuid", --TLCHANGE } m["bnk"] = { "Bierebo", 2902029, "poz-vnc", "Latn", } m["bnl"] = { "Boon", 56616, "cus-eas", "Latn", } m["bnm"] = { "Batanga", 34979, "bnt-saw", "Latn", } m["bnn"] = { "Bunun", 56505, "map", "Latn", } m["bno"] = { "Asi", --"Asi", 29490, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/asi/", --TLCHANGE english_name = "Asi", --TLCHANGE } m["bnp"] = { "Bola", 4938876, "poz-ocw", "Latn", } m["bnq"] = { "Bantik", 2883521, "poz", "Latn", } m["bnr"] = { "Butmas-Tur", 2928942, "poz-vnn", "Latn", } m["bns"] = { "Bundeli", 56399, "inc-hiw", "Deva", translit = "hi-translit", } m["bnu"] = { "Bentong", 4890644, "poz-ssw", "Latn", } m["bnv"] = { "Beneraf", 4941733, "paa-tor", "Latn", } m["bnw"] = { "Bisis", 56356, "paa-sep", "Latn", } m["bnx"] = { "Bangubangu", 3438330, "bnt-lbn", "Latn", } m["bny"] = { "Bintulu", 3450775, "poz-swa", "Latn", } m["bnz"] = { "Beezen", 35083, "nic-ykb", "Latn", } m["boa"] = { "Bora", 2375468, "sai-bor", "Latn", } m["bob"] = { "Aweer", 56526, "cus-som", "Latn", } m["boe"] = { "Mundabli", 36127, "nic-beb", "Latn", } m["bof"] = { "Bolon", 3913301, "dmn-emn", "Latn", } m["bog"] = { "Wikang Senyas ng Bamako", --TLCHANGE 4853284, "sgn", english_name = "Bamako Sign Language", --TLCHANGE spanish_name = "Lengua de signos bamako", --TLCHANGE } m["boh"] = { "North Boma", 35080, "bnt-bdz", "Latn", } m["boi"] = { "Barbareño", 56391, "nai-chu", "Latn", } m["boj"] = { "Anjam", 3504136, "ngf-min", "Latn", } m["bok"] = { "Bonjo", 34942, "alv", "Latn", } m["bol"] = { "Bole", 3436680, "cdc-wst", "Latn", } m["bom"] = { "Berom", 35013, "nic-beo", "Latn", } m["bon"] = { "Bine", 4914077, "paa-etf", "Latn", } m["boo"] = { "Tiemacèwè Bozo", 12643582, "dmn-snb", "Latn", -- and others? } m["bop"] = { "Bonkiman", 4942134, "ngf-yup", "Latn", } m["boq"] = { "Bogaya", 7207578, "qfa-dis", -- Papuan; isolate per Glottolog, grouped in Duna-Pogaya family by Voorhoeve (1975), Ross (2005) and Usher (2018) "Latn", } m["bor"] = { "Borôro", 32986, "sai-mje", "Latn", } m["bot"] = { "Bongo", 2910067, "csu-bbk", "Latn", } m["bou"] = { "Bondei", 4941378, "bnt-seu", "Latn", } m["bov"] = { "Tuwuli", 36974, "alv-ktg", "Latn", } m["bow"] = { "Rema", 7311502, "paa-ton", "Latn", } m["box"] = { "Buamu", 35157, "nic-bwa", "Latn", } m["boy"] = { "Bodo (Central Africa)", 4936715, "bnt-leb", "Latn", } m["boz"] = { "Tiéyaxo Bozo", 32860401, "dmn-snb", "Latn", } m["bpa"] = { "Daakaka", 1157729, "poz-vnc", "Latn", } m["bpd"] = { "Banda-Banda", 3450674, "bad-cnt", "Latn", } m["bpe"] = { "Bauni", 105150962, "paa-pio", "Latn", } m["bpg"] = { "Bonggo", 4941860, "poz-ocw", "Latn", } m["bph"] = { "Botlikh", 56560, "cau-and", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["bpi"] = { "Bagupi", 3450697, "ngf-han", "Latn", } m["bpj"] = { "Binji", 4914403, "bnt-lbn", "Latn", } m["bpk"] = { "Orowe", 7103905, "poz-cln", "Latn", } m["bpl"] = { "Broome Pearling Lugger Pidgin", 4975277, "crp", "Latn", ancestors = "ms", } m["bpm"] = { "Biyom", 4919327, "ngf-rai", "Latn", } m["bpn"] = { "Dzao Min", 3042189, "hmx-mie", } m["bpo"] = { "Anasi", 11207813, "paa-egb", "Latn", } m["bpp"] = { "Kaure", 20526532, "paa-kko", "Latn", } m["bpq"] = { "Banda Malay", 12473442, "crp", "Latn", ancestors = "ms", } m["bpr"] = { "Koronadal Blaan", 16115430, "phi", "Latn", } m["bps"] = { "Sarangani Blaan", 16117272, "phi", "Latn", } m["bpt"] = { "Barrow Point", 2567916, "aus-pmn", "Latn", } m["bpu"] = { "Bongu", 4941930, "ngf-min", "Latn", } m["bpv"] = { "Bian Marind", 8841889, "paa-mri", "Latn", } -- bpw: Bo (Papua New Guinea): excluded in 2012 and re-evaluated in 2025 with the same conclusion; per Wikipedia: "It is -- essentially undocumented, and its status as a separate language is unconfirmed." m["bpx"] = { "Palya Bareli", 7128872, "inc-bhi", "Deva", translit = "hi-translit", } m["bpy"] = { "Bishnupriya Manipuri", 37059, "inc-bas", "Beng", ancestors = "inc-obn", } m["bpz"] = { "Bilba", 8843362, "poz-tim", "Latn", } m["bqa"] = { "Tchumbuli", 11008162, "alv-ctn", "Latn", ancestors = "ak", } m["bqb"] = { "Bagusa", 4842178, "paa-kwe", "Latn", } m["bqc"] = { "Boko", 34983, "dmn-bbu", "Latn", } m["bqd"] = { "Bung", 3436612, "nic-bdn", "Latn", } m["bqf"] = { "Baga Kaloum", 3502293, "alv-bag", "Latn", } m["bqg"] = { "Bago-Kusuntu", 34878, "nic-gne", } m["bqh"] = { "Baima", 674990, "sit-qia", } m["bqi"] = { "Bakhtiari", 257829, "ira-swi", "fa-Arab", ancestors = "pal", } m["bqj"] = { "Bandial", 34872, "alv-jol", "Latn", } m["bqk"] = { "Banda-Mbrès", 3450724, "bad-cnt", "Latn", } m["bql"] = { "Karian", 4907504, "ngf-num", "Latn", } m["bqm"] = { "Wumboko", 37051, "bnt-kpw", "Latn", } m["bqn"] = { "Wikang Senyas ng mga Bulgaro", --TLCHANGE 3438325, "sgn", english_name = "Bulgarian Sign Language", --TLCHANGE spanish_name = "Lengua de signos búlgaro", --TLCHANGE } m["bqo"] = { "Balo", 34865, "nic-grs", "Latn", } m["bqp"] = { "Busa", 35185, "dmn-bbu", "Latn", } m["bqq"] = { "Biritai", 56382, "paa-clp", "Latn", } m["bqr"] = { "Burusu", 5001028, "poz-san", "Latn", } m["bqs"] = { "Bosngun", 56838, "paa-baw", "Latn", } m["bqt"] = { "Bamukumbit", 35078, "nic-nge", "Latn", } m["bqu"] = { "Boguru", 3438444, "bnt-boa", "Latn", } m["bqv"] = { "Begbere-Ejar", 7194098, "nic-plc", "Latn", } m["bqw"] = { "Buru (Nigeria)", 1017152, "nic-bds", "Latn", } m["bqx"] = { "Baangi", 3450648, "nic-kam", "Latn", } m["bqy"] = { "Wikang Senyas ng Bengkala", --TLCHANGE "Bengkala Sign Language", 3322119, "sgn", english_name = "Bengkala Sign Language", --TLCHANGE spanish_name = "Lengua de signos bengkala", --TLCHANGE } m["bqz"] = { "Bakaka", 34855, "bnt-mne", "Latn", } m["bra"] = { "Braj", 35243, "inc-hiw", "Deva", translit = "hi-translit", } m["brb"] = { "Lave", 4957737, "mkh-ban", } m["brc"] = { "Berbice Creole Dutch", 35215, "crp", "Latn", ancestors = "nl", } m["brd"] = { "Baraamu", 56804, "sit-new", "Deva", } m["brf"] = { "Bera", 2896850, "bnt-kbi", "Latn", } m["brg"] = { "Baure", 2839722, "awd", "Latn", } m["brh"] = { "Brahui", 33202, "dra-nor", "ur-Arab, Latn", translit = {["ur-Arab"] = "ur-translit"}, strip_diacritics = { -- 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 }, } m["bri"] = { "Mokpwe", 36428, "bnt-kpw", "Latn", } m["brj"] = { "Bieria", 4904607, "poz-vnc", "Latn", } m["brk"] = { "Birgid", 56823, "nub", "Latn", } m["brl"] = { "Birwa", 3501019, "bnt-sts", "Latn", } m["brm"] = { "Barambu", 34893, "znd", "Latn", } m["brn"] = { "Boruca", 4946773, "cba", "Latn", } m["bro"] = { "Brokkat", 56605, "sit-tib", "Tibt, Latn", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["brp"] = { "Barapasi", 56995, "paa-egb", "Latn", } m["brq"] = { "Breri", 4961835, "paa-tam", "Latn", } m["brr"] = { "Birao", 2904383, "poz-sls", "Latn", } m["brs"] = { "Baras", 8827053, "poz", "Latn", } m["brt"] = { "Bitare", 34946, "nic-tvn", "Latn", } m["bru"] = { "Silanganing Bru", --TLCHANGE 16115463, "mkh-kat", "Latn, Laoo, Thai", sort_key = { Laoo = "Laoo-sortkey", Thai = "Thai-sortkey", }, english_name = "Eastern Bru", --TLCHANGE } m["brv"] = { "Kanluraning Bru", --TLCHANGE 13018531, "mkh-kat", "Latn, Laoo, Thai", sort_key = { Laoo = "Laoo-sortkey", Thai = "Thai-sortkey", }, english_name = "Western Bru", --TLCHANGE } m["brw"] = { "Bellari", 4883496, "dra-tlk", "Knda, Mlym", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["brx"] = { "Bodo (India)", 33223, "tbq-bdg", "Deva, Latn", translit = {Deva = "brx-translit"}, } m["bry"] = { "Burui", 5000976, "paa-nnd", "Latn", } m["brz"] = { "Bilbil", 4907473, "poz-ocw", "Latn", } m["bsa"] = { "Abinomn", 56648, "qfa-iso", -- Papuan "Latn", } m["bsb"] = { "Brunei Bisaya", 3450611, "poz-san", "Latn", } m["bsc"] = { "Bassari", 35098, "alv-ten", "Latn", } m["bse"] = { "Wushi", 36973, "nic-rnn", "Latn", } m["bsf"] = { "Bauchi", 34974, "nic-shi", "Latn", } m["bsg"] = { "Bashkardi", 33030, "ira-swi", "fa-Arab, Latn", } m["bsh"] = { "Kamkata-viri", 2605045, "nur-nor", "Latn, Arab", } m["bsi"] = { "Bassossi", 34940, "bnt-mne", "Latn", } m["bsj"] = { "Bangwinji", 3446631, "alv-wjk", "Latn", } m["bsk"] = { "Burushaski", 216286, "qfa-iso", "Arab", strip_diacritics = { -- 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 }, } m["bsl"] = { "Basa-Gumna", 4866150, "nic-bas", "Latn", } m["bsm"] = { "Busami", 5001255, "poz-hce", "Latn", } m["bsn"] = { "Barasana", 2883843, "sai-tuc", "Latn", } m["bso"] = { "Buso", 3441370, "cdc-est", "Latn", } m["bsp"] = { "Baga Sitemu", 36466, "alv-bag", "Latn", } m["bsq"] = { "Bassa", 34949, "kro-wkr", "Latn, Bass", } m["bsr"] = { "Bassa-Kontagora", 4866152, "nic-bas", "Latn", } m["bss"] = { "Akoose", 34806, "bnt-mne", "Latn", } m["bst"] = { "Basketo", 56531, "omv-ome", "Ethi", } m["bsu"] = { "Bahonsuai", 2879298, "poz-btk", "Latn", } m["bsv"] = { "Baga Sobané", 3450433, "alv-bag", "Latn", } m["bsw"] = { "Baiso", 56615, "cus-som", "Latn", } m["bsx"] = { "Yangkam", 36922, "nic-tar", "Latn", } m["bsy"] = { "Sabah Bisaya", 12641557, "poz-san", "Latn", } m["bta"] = { "Bata", 56254, "cdc-cbm", "Latn", } m["btc"] = { "Bati (Cameroon)", 34944, "nic-mbw", "Latn", } m["btd"] = { "Dairi Batak", 2891045, "btk", "Latn, Batk", } m["bte"] = { "Gamo-Ningi", 5520366, "nic-jer", "Latn", } m["btf"] = { "Birgit", 56302, "cdc-est", "Latn", } m["btg"] = { "Gagnoa Bété", 5005069, "kro-bet", "Latn", } m["bth"] = { "Biatah Bidayuh", 2900881, "day", "Latn", } m["bti"] = { "Burate", 56900, "paa-egb", "Latn", } m["btj"] = { "Bacanese Malay", 8828608, "poz-mly", "Latn", } m["btm"] = { "Mandailing Batak", 2891049, "btk", "Latn, Batk", } m["btn"] = { "Ratagnon Mangyan", --"Ratagnon", 13197, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/ratagnon-mangyan/", --TLCHANGE english_name = "Ratagnon", --TLCHANGE } m["bto"] = { "Rinkonada", --"Iriga Bicolano", 12633026, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/rinkonada/", --TLCHANGE english_name = "Iriga Bicolano", --TLCHANGE } m["btp"] = { "Budibud", 4985086, "poz-ocw", "Latn", } m["btq"] = { "Batek", 860315, "mkh-asl", "Latn", } m["btr"] = { "Baetora", 2878874, "poz-vnn", "Latn", } m["bts"] = { "Simalungun Batak", 2891054, "btk", "Latn, Batk", } m["btt"] = { "Bete-Bendi", 4887064, "nic-ben", "Latn", } m["btu"] = { "Batu", 34964, "nic-tvn", "Latn", } m["btv"] = { "Bateri", 3812564, "inc-koh", "Deva", } m["btw"] = { "Butwanon", --"Butuanon", 5003156, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/butwanon/", --TLCHANGE english_name = "Butuanon", --TLCHANGE } m["btx"] = { "Karo Batak", 33012, "btk", "Latn, Batk", } m["bty"] = { "Bobot", 3446788, "poz-cma", "Latn", } m["btz"] = { "Alas-Kluet Batak", 2891042, "btk", "Latn, Batk", } m["bua"] = { "Buryat", 33120, "xgn-cen", "Cyrl, Mong, Latn", wikimedia_codes = "bxr", ancestors = "cmg", translit = { Cyrl = "bua-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 = { from = {"ё", "ө", "ү", "һ"}, to = {"е" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1]} }, }, } m["bub"] = { "Bua", 32928, "alv-bua", "Latn", } m["bud"] = { "Ntcham", 36266, "nic-grm", "Latn", } m["bue"] = { "Beothuk", 56234, "qfa-unc", -- extinct since 1829, poorly attested; possibly a divergent Algonquian language "Latn", } m["buf"] = { "Bushoong", 3449964, "bnt-bsh", "Latn", } m["bug"] = { "Buginese", 33190, "poz-ssw", "Bugi, Latn", } m["buh"] = { "Younuo Bunu", 56299, "hmn", "Latn", } m["bui"] = { "Bongili", 35084, "bnt-ngn", "Latn", } m["buj"] = { "Basa-Gurmana", 6432515, "nic-bas", "Latn", } m["buk"] = { "Bukawa", 35043, "poz-ocw", "Latn", } m["bum"] = { "Bulu (Cameroon)", 35028, "bnt-btb", "Latn", } m["bun"] = { "Sherbro", 36339, "alv-mel", "Latn", } m["buo"] = { "Terei", 56831, "paa-sbo", "Latn", } m["bup"] = { "Busoa", 5002001, "poz", "Latn", } m["buq"] = { "Brem", 4960502, "ngf-nad", "Latn", } m["bus"] = { "Bokobaru", 9228931, "dmn-bbu", "Latn", } m["but"] = { "Bungain", 3450623, "paa-mar", "Latn", } m["buu"] = { "Budu", 3450207, "bnt-nya", "Latn", } m["buv"] = { "Bun", 56351, "paa-yua", "Latn", } m["buw"] = { "Bubi", 35017, "bnt-tso", "Latn", } m["bux"] = { "Boghom", 3440412, "cdc-wst", "Latn", } m["buy"] = { "Mmani", 35061, "alv-mel", "Latn", } m["bva"] = { "Barein", 56285, "cdc-est", "Latn", } m["bvb"] = { "Bube", 35110, "nic-bds", "Latn", } m["bvc"] = { "Baelelea", 2878833, "poz-sls", "Latn", } m["bvd"] = { "Baeggu", 2878850, "poz-sls", "Latn", } m["bve"] = { "Berau Malay", 3915770, "poz-mly", "Latn", } m["bvf"] = { "Boor", 56250, "cdc-est", "Latn", } m["bvg"] = { "Bonkeng", 34958, "bnt-bbo", "Latn", } m["bvh"] = { "Bure", 56294, "cdc-wst", "Latn", } m["bvi"] = { "Belanda Viri", 35247, "nic-ser", "Latn", } m["bvj"] = { "Baan", 3515067, "nic-ogo", "Latn", } m["bvk"] = { "Bukat", 4986814, "poz-bnn", "Latn", } m["bvl"] = { "Wikang Senyas ng mga Bolivyano", --TLCHANGE 1783590, "sgn", "Latn", -- when documented english_name = "Bolivian Sign Language", --TLCHANGE spanish_name = "Lengua de signos boliviano", --TLCHANGE } m["bvm"] = { "Bamunka", 34882, "nic-rnn", "Latn", } m["bvn"] = { "Buna", 3450516, "paa-mar", "Latn", } m["bvo"] = { "Bolgo", 35038, "alv-bua", "Latn", } m["bvp"] = { "Bumang", 4997235, "mkh-pal", } m["bvq"] = { "Birri", 56514, "csu-bkr", "Latn", } m["bvr"] = { "Burarra", 4998124, "aus-arn", "Latn", } m["bvt"] = { "Bati (Indonesia)", 4869253, "poz-cma", "Latn", } m["bvu"] = { "Bukit Malay", 9230148, "poz-mly", "Latn", } m["bvv"] = { "Baniva", 3515198, "awd", "Latn", } m["bvw"] = { "Boga", 56262, "cdc-cbm", "Latn", } m["bvx"] = { "Babole", 35180, "bnt-ngn", "Latn", } m["bvy"] = { "Baybayanon", 16839275, "phi", "Latn", } m["bvz"] = { "Bauzi", 56360, "paa-egb", "Latn", } m["bwa"] = { "Bwatoo", 9232446, "poz-cln", "Latn", } m["bwb"] = { "Namosi-Naitasiri-Serua", 3130290, "poz-pcc", "Latn", } m["bwc"] = { "Bwile", 3447440, "bnt-sbi", "Latn", } m["bwd"] = { "Bwaidoka", 2929111, "poz-ocw", "Latn", } m["bwe"] = { "Bwe Karen", 56994, "kar", "Mymr, Latn", } m["bwf"] = { "Boselewa", 4947229, "poz-ocw", "Latn", } m["bwg"] = { "Barwe", 8826802, "bnt-sna", "Latn", } m["bwh"] = { "Bishuo", 34973, "nic-fru", "Latn", } m["bwi"] = { "Baniwa", 3501735, "awd-nwk", "Latn", } m["bwj"] = { "Láá Láá Bwamu", 11017275, "nic-bwa", "Latn", } m["bwk"] = { "Bauwaki", 4873607, "paa-mal", "Latn", } m["bwl"] = { "Bwela", 5003678, "bnt-bun", "Latn", } m["bwm"] = { "Biwat", 56352, "paa-yua", "Latn", } m["bwn"] = { "Wunai Bunu", 56452, "hmn", } m["bwo"] = { "Shinasha", 56260, "omv-gon", "Latn", } m["bwp"] = { "Lower Mandobo", 12636155, "ngf-dum", "Latn", } m["bwq"] = { "Southern Bobo", 11001714, "dmn-snb", "Latn", } m["bwr"] = { "Bura", 56552, "cdc-cbm", "Latn", } m["bws"] = { "Bomboma", 9229429, "bnt-bun", "Latn", } m["bwt"] = { "Bafaw", 34853, "bnt-bbo", "Latn", } m["bwu"] = { "Buli (Ghana)", 35085, "nic-buk", "Latn", } m["bww"] = { "Bwa", 3515058, "bnt-bta", "Latn", } m["bwx"] = { "Bu-Nao Bunu", 56411, "hmn", "Latn", } m["bwy"] = { "Cwi Bwamu", 11150714, "nic-bwa", "Latn", } m["bwz"] = { "Bwisi", 35067, "bnt-sir", "Latn", } m["bxa"] = { "Bauro", 2892068, "poz-sls", "Latn", } m["bxb"] = { "Belanda Bor", 56678, "sdv-lon", "Latn", } m["bxc"] = { "Molengue", 13345, "bnt-kel", "Latn", } m["bxd"] = { "Pela", 57000, "tbq-brm", } m["bxe"] = { "Ongota", 36344, "qfa-unc", -- moribund, no academic consensus on classification; might be an isolate "Latn", } m["bxf"] = { "Bilur", 2903788, "poz-ocw", "Latn", } m["bxg"] = { "Bangala", 34989, "bnt-bmo", "Latn", } m["bxh"] = { "Buhutu", 4986329, "poz-ocw", "Latn", } m["bxi"] = { "Pirlatapa", 10632195, "aus-kar", "Latn", } m["bxj"] = { "Bayungu", 10427485, "aus-psw", "Latn", } m["bxk"] = { "Bukusu", 32930, "bnt-msl", "Latn", } m["bxl"] = { "Jalkunan", 11009787, "dmn-jje", "Latn", } m["bxn"] = { "Burduna", 4998313, "aus-psw", "Latn", } m["bxo"] = { "Barikanchi", 3450802, "crp", "Latn", ancestors = "ha", } m["bxp"] = { "Bebil", 34941, "bnt-btb", "Latn", } m["bxq"] = { "Beele", 56238, "cdc-wst", "Latn", } m["bxs"] = { "Busam", 35189, "nic-grs", "Latn", } m["bxv"] = { "Berakou", 56796, "csu-bgr", "Latn", } m["bxw"] = { "Banka", 3438402, "dmn-smg", "Latn", } m["bxz"] = { "Binahari", 4913840, "paa-mal", "Latn", } m["bya"] = { "Binatak", --"Palawan Batak", 3450443, "phi", "Tagb", is_official_kwf_name = "https://kwfwikaatkultura.ph/binatak/", --TLCHANGE english_name = "Palawan Batak", --TLCHANGE } m["byb"] = { "Bikya", 33257, "nic-fru", "Latn", } m["byc"] = { "Ubaghara", 36625, "nic-ucn", "Latn", } m["byd"] = { "Benyadu'", 11173588, "day", "Latn", } m["bye"] = { "Pouye", 7235814, "paa-sep", "Latn", } m["byf"] = { "Bete", 32932, "nic-ykb", "Latn", } m["byg"] = { "Baygo", 56836, "sdv-daj", "Latn", } m["byh"] = { "Bujhyal", 56317, "sit-gma", "Deva", } m["byi"] = { "Buyu", 5003401, "bnt-nyb", "Latn", } m["byj"] = { "Binawa", 4913807, "nic-kau", "Latn", } m["byk"] = { "Biao", 4902547, "qfa-tak", "Latn", -- also Hani? } m["byl"] = { "Bayono", 3503856, "paa-baa", "Latn", } m["bym"] = { "Bidyara", 8842355, "aus-pam", "Latn", } m["byn"] = { "Blin", 56491, "cus-cen", "Ethi, Latn", translit = {Ethi = "Ethi-translit"}, } m["byo"] = { "Biyo", 56848, "tbq-bka", "Latn, Hani", sort_key = {Hani = "Hani-sortkey"}, } m["byp"] = { "Bumaji", 4997234, "nic-ben", "Latn", } m["byq"] = { "Basay", 716647, "map", "Latn", } m["byr"] = { "Baruya", 3450812, "ngf-bsi", "Latn", } m["bys"] = { "Burak", 4998097, "alv-bwj", "Latn", } m["byt"] = { "Berti", 35008, "ssa-sah", "Latn", } m["byv"] = { "Medumba", 36019, "bai", "Latn", } m["byw"] = { "Belhariya", 32961, "sit-kie", "Deva", } m["byx"] = { "Qaqet", 3503009, "paa-bai", "Latn", } m["byz"] = { "Banaro", 56858, "paa-ram", "Latn", } m["bza"] = { "Bandi", 34912, "dmn-msw", "Latn", } m["bzb"] = { "Andio", 4754487, "poz-slb", "Latn", } m["bzd"] = { "Bribri", 28400, "cba", "Latn", } m["bze"] = { "Jenaama Bozo", 10950633, "dmn-snb", "Latn", } m["bzf"] = { "Boikin", 56829, "paa-ndu", "Latn", } m["bzg"] = { "Babuza", 716615, "map", "Latn", } m["bzh"] = { "Mapos Buang", 2927370, "poz-ocw", "Latn", } m["bzi"] = { "Bisu", 56852, "tbq-bis", "Latn, Thai", sort_key = {Thai = "Thai-sortkey"}, } m["bzj"] = { "Belizean Creole", 1363055, "crp", "Latn", ancestors = "en", } m["bzk"] = { "Nicaraguan Creole", 3504097, "crp", "Latn", ancestors = "en", } m["bzl"] = { -- supposedly also called "Bolano", but I can find no evidence of that "Boano (Sulawesi)", 4931258, "poz", "Latn", } m["bzm"] = { "Bolondo", 35071, "bnt-bun", "Latn", } m["bzn"] = { "Boano (Maluku)", 4931255, "poz-cma", "Latn", } m["bzo"] = { "Bozaba", 4952785, "bnt-ngn", "Latn", } m["bzp"] = { "Kemberano", 12634399, "ngf-sbh", "Latn", } m["bzq"] = { "Buli (Indonesia)", 2927952, "poz-hce", "Latn", } m["bzr"] = { "Biri", 4087011, "aus-pam", "Latn", } m["bzs"] = { "Wikang Senyas ng mga Brasileño", --TLCHANGE 3436689, "sgn", "Latn", english_name = "Brazilian Sign Language", --TLCHANGE spanish_name = "Lengua de signos brasileño", --TLCHANGE } m["bzu"] = { "Burmeso", 56746, "qfa-dis", -- isolate in Glottolog, Wurm and Foley; in East Bird's Head-Sentani fmaily by Ross "Latn", } m["bzv"] = { "Bebe", 34977, "nic-bbe", "Latn", } m["bzw"] = { "Basa", 34898, "nic-bas", "Latn", } m["bzx"] = { "Hainyaxo Bozo", 11159536, "dmn-snb", "Latn", } m["bzy"] = { "Obanliku", 36276, "nic-ben", "Latn", } m["bzz"] = { "Evant", 35259, "nic-tvc", "Latn", } return require("Module:languages").finalizeData(m, "language") j8cq6vt7d5cpkrwjc70uoo3zvbh3uu0 176307 176306 2026-04-13T13:09:54Z Yivan000 4078 176307 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["baa"] = { "Babatana", 2877785, "poz-ocw", "Latn", } m["bab"] = { "Bainouk-Gunyuño", 35508, "alv-bny", "Latn", } m["bac"] = { "Baduy", 3449885, "poz-msa", "Latn, Sund", ancestors = "osn", translit = { Sund = "Sund-translit" }, } m["bae"] = { "Baré", 3504087, "awd", "Latn", } m["baf"] = { "Nubaca", 36270, "nic-ymb", "Latn", } m["bag"] = { "Tuki", 36621, "nic-mba", "Latn", } m["bah"] = { "Bahamian Creole", 2669229, "crp", "Latn", ancestors = "en", } m["baj"] = { "Barakai", 3502030, "poz-cet", "Latn", } m["bal"] = { "Baluchi", 33049, "ira-nwi", "fa-Arab", } m["ban"] = { "Balines", --TLCHANGE 33070, "poz-bss", "Latn, Bali", english_name = "Balinese", --TLCHANGE spanish_name = "Balinés", --TLCHANGE } m["bao"] = { "Waimaha", 2883738, "sai-tuc", "Latn", } m["bap"] = { "Bantawa", 56500, "sit-kic", "Krai, Deva", } m["bar"] = { "Bavaro", --TLCHANGE 29540, "gmw-hgm", "Latn", ancestors = "gmh", english_name = "Bavarian", --TLCHANGE spanish_name = "Bávaro", --TLCHANGE } m["bas"] = { "Basaa", 33093, "bnt-bsa", "Latn", } m["bau"] = { "Badanchi", 11001650, "nic-jrw", "Latn", } m["bav"] = { "Babungo", 34885, "nic-rnn", "Latn", } m["baw"] = { "Bambili-Bambui", 34880, "nic-nge", "Latn", } m["bax"] = { "Bamum", 35280, "nic-nun", "Latn, Bamu", } m["bay"] = { "Batuley", 8828787, "poz", "Latn", } m["bba"] = { "Baatonum", 34889, "alv-sav", "Latn", } m["bbb"] = { "Barai", 4858206, "ngf-koi", "Latn", } m["bbc"] = { "Toba Batak", 33017, "btk", "Latn, Batk", } m["bbd"] = { "Bau", 4873415, "ngf-gum", "Latn", } m["bbe"] = { "Bangba", 34895, "nic-nke", "Latn", } m["bbf"] = { "Baibai", 56902, "paa-fas", "Latn", } m["bbg"] = { "Barama", 34884, "bnt-sir", "Latn", } m["bbh"] = { "Bugan", 3033554, "mkh-pkn", "Latn", } m["bbi"] = { "Barombi", 34985, "bnt-bsa", "Latn", } m["bbj"] = { "Ghomala'", 35271, "bai", "Latn", } m["bbk"] = { "Babanki", 34790, "nic-rnc", "Latn", } m["bbl"] = { "Bats", 33259, "cau-nkh", "Geor", -- Geor translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { remove_diacritics = c.tilde .. c.macron .. c.breve, from = {"^ნ"}, to = {"ნ"} }, } m["bbm"] = { -- name includes prefix "Babango", 34819, "bnt-bta", "Latn", } m["bbn"] = { "Uneapa", 7884126, "poz-ocw", "Latn", } m["bbo"] = { "Konabéré", 35371, "dmn-snb", "Latn", } m["bbp"] = { "West Central Banda", 7984377, "bad", "Latn", } m["bbq"] = { "Bamali", 34901, "nic-nun", "Latn", } m["bbr"] = { "Girawa", 5564185, "ngf-kok", "Latn", } m["bbs"] = { "Bakpinka", 3515061, "nic-ucr", "Latn", } m["bbt"] = { "Mburku", 3441324, "cdc-wst", "Latn", } m["bbu"] = { "Bakulung", 35580, "nic-jrn", "Latn", } m["bbv"] = { "Karnai", 6372803, "poz-ocw", "Latn", } m["bbw"] = { "Baba", 34822, "nic-nun", "Latn", } m["bbx"] = { -- cf bvb "Bubia", 34953, "nic-bds", "Latn", ancestors = "bvb", } m["bby"] = { "Befang", 34960, "nic-bds", "Latn", } m["bca"] = { "Central Bai", 12628803, "sit-bai", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bcb"] = { "Bainouk-Samik", 36390, "alv-bny", "Latn", } m["bcd"] = { "North Babar", 7054041, "poz-tim", "Latn", } m["bce"] = { "Bamenyam", 34968, "nic-nun", "Latn", } m["bcf"] = { "Bamu", 3503788, "paa-kiw", "Latn", } m["bcg"] = { "Baga Pokur", 31172660, "alv-nal", "Latn", } m["bch"] = { "Bariai", 2884502, "poz-ocw", "Latn", } m["bci"] = { "Baoule", 35107, "alv-ctn", "Latn", } m["bcj"] = { "Bardi", 3913852, "aus-nyu", "Latn", } m["bck"] = { "Bunaba", 580923, "aus-bub", "Latn", } m["bcl"] = { "Bikol Naga", --"Bikol Central", 33284, "phi", "Latn, Tglg", translit = { Tglg = "bcl-translit", }, override_translit = true, strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ, } }, sort_key = { Latn = "tl-sortkey", }, standard_chars = { Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy" .. c.punc, }, is_official_kwf_name = "https://kwfwikaatkultura.ph/bikol/", --TLCHANGE english_name = "Bikol Central", --TLCHANGE } m["bcm"] = { "Banoni", 2882857, "poz-ocw", "Latn", } m["bcn"] = { "Bibaali", 34892, "alv-mye", "Latn", } m["bco"] = { "Kaluli", 6354586, "ngf-bos", "Latn", } m["bcp"] = { "Bali", 3515074, "bnt-kbi", "Latn", } m["bcq"] = { "Bench", 35108, "omv", "Latn", } m["bcr"] = { "Babine-Witsuwit'en", 27864, "ath-nor", "Latn", } m["bcs"] = { "Kohumono", 35590, "nic-ucn", "Latn", } m["bct"] = { "Bendi", 8836662, "csu-mle", "Latn", } m["bcu"] = { "Biliau", 2874658, "poz-ocw", "Latn", } m["bcv"] = { "Shoo-Minda-Nye", 36548, "nic-jkn", "Latn", } m["bcw"] = { "Bana", 56272, "cdc-cbm", "Latn", } m["bcy"] = { "Bacama", 56274, "cdc-cbm", "Latn", } m["bcz"] = { "Bainouk-Gunyaamolo", 35506, "alv-bny", "Latn", } m["bda"] = { "Bayot", 35019, "alv-jol", "Latn", } m["bdb"] = { "Basap", 3504208, "poz-bnn", "Latn", } m["bdc"] = { "Emberá-Baudó", 11173166, "sai-chc", "Latn", } m["bdd"] = { "Bunama", 4997416, "poz-ocw", "Latn", } m["bde"] = { "Bade", 56239, "cdc-wst", "Latn", } m["bdf"] = { "Biage", 48037487, "ngf-koi", "Latn", } m["bdg"] = { "Bonggi", 2910053, "poz-bnn", "Latn", } m["bdh"] = { "Tara Baka", 2880165, "csu-bbk", "Latn", } m["bdi"] = { "Burun", 35040, "sdv-niw", "Latn", } m["bdj"] = { "Bai (South Sudan)", 34894, "nic-ser", "Latn", } m["bdk"] = { "Budukh", 35397, "cau-ssm", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["bdl"] = { "Indonesian Bajau", 2880038, "poz", "Latn", } m["bdm"] = { "Buduma", 56287, "cdc-cbm", "Latn", } m["bdn"] = { "Baldemu", 56280, "cdc-cbm", "Latn", } m["bdo"] = { "Morom", 759770, "csu-bgr", "Latn", } m["bdp"] = { "Bende", 8836490, "bnt", "Latn", } m["bdq"] = { "Bahnar", 32924, "mkh-ban", "Latn", } m["bdr"] = { "West Coast Bajau", 2880037, "poz-sbj", "Latn", } m["bds"] = { "Burunge", 56617, "cus-sou", "Latn", } m["bdt"] = { "Bokoto", 4938812, "gba-wes", "Latn", } m["bdu"] = { "Oroko", 36278, "bnt-saw", "Latn", } m["bdv"] = { "Bodo Parja", 8845881, "inc-eas", "Orya", } m["bdw"] = { "Baham", 3513309, "paa-mbi", "Latn", } m["bdx"] = { "Budong-Budong", 4985158, "poz-ssw", "Latn", } m["bdy"] = { "Bandjalang", 2980386, "aus-pam", "Latn", } m["bdz"] = { "Badeshi", 33028, "iir", "Arab, Latn", } m["bea"] = { "Beaver", 20826, "ath-nor", "Latn", } m["beb"] = { "Bebele", 34976, "bnt-btb", "Latn", } m["bec"] = { "Iceve-Maci", 35449, "nic-tvc", "Latn", } m["bed"] = { "Bedoanas", 4879330, "poz-hce", "Latn", } m["bee"] = { "Byangsi", 56904, "sit-alm", "Deva", } m["bef"] = { "Benabena", 2895638, "ngf-gor", "Latn", } m["beg"] = { "Belait", 2894198, "poz-swa", "Latn", } m["beh"] = { "Biali", 34961, "nic-eov", "Latn", } m["bei"] = { "Bekati'", 3441683, "day", "Latn", } m["bej"] = { "Beja", 33025, "cus", "Arab, Latn", strip_diacritics = { Latn = { remove_diacritics = c.acute, } }, } m["bek"] = { "Bebeli", 4878430, "poz-ocw", "Latn", } m["bem"] = { "Bemba", 33052, "bnt-sbi", "Latn", } m["beo"] = { "Beami", 3504079, "ngf-bos", "Latn", } m["bep"] = { "Besoa", 8840465, "poz-kal", "Latn", } m["beq"] = { "Beembe", 3196320, "bnt-kng", "Latn", } m["bes"] = { "Besme", 289832, "alv-kim", "Latn", } m["bet"] = { "Guiberoua Bété", 11019185, "kro-bet", "Latn", } m["beu"] = { "Blagar", 4923846, "paa-alp", "Latn", } m["bev"] = { "Daloa Bété", 11155819, "kro-bet", "Latn", } m["bew"] = { "Betawi", 33014, "crp", "Latn", ancestors = "ms", } m["bex"] = { "Jur Modo", 56682, "csu-bbk", "Latn", } m["bey"] = { "Beli (New Guinea)", 3504170, "paa-trr", "Latn", } m["bez"] = { "Kibena", 2502949, "bnt-bki", "Latn", } m["bfa"] = { "Bari", 35042, "sdv-bri", "Latn", } m["bfb"] = { "Pauri Bareli", 7155462, "inc-bhi", "Deva", } m["bfc"] = { "Panyi Bai", 12642165, "sit-nba", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bfd"] = { "Bafut", 34888, "nic-nge", "Latn", } m["bfe"] = { "Betaf", 4897329, "paa-bvi", "Latn", } m["bff"] = { "Bofi", 34914, "gba-eas", "Latn", } m["bfg"] = { "Busang Kayan", 9231909, "poz", "Latn", } m["bfh"] = { "Blafe", 12628007, "paa-ton", "Latn", } m["bfi"] = { "Wikang Senyas ng mga Britaniko", --TLCHANGE 33000, "sgn", "Latn", -- when documented english_name = "British Sign Language", --TLCHANGE spanish_name = "Lengua de signos británico", --TLCHANGE } m["bfj"] = { "Bafanji", 34890, "nic-nun", "Latn", } m["bfk"] = { "Wikang Senyas ng Ban Khor", --TLCHANGE 3441103, "sgn", english_name = "Ban Khor Sign Language", --TLCHANGE spanish_name = "Lengua de signos ban khor", --TLCHANGE } m["bfl"] = { "Banda-Ndélé", 34850, "bad-cnt", "Latn", } m["bfm"] = { "Mmen", 36132, "nic-rnc", "Latn", } m["bfn"] = { "Bunak", 35101, "paa-tap", "Latn", } m["bfo"] = { "Malba Birifor", 11150710, "nic-mre", "Latn", } m["bfp"] = { "Beba", 35050, "nic-nge", "Latn", } m["bfq"] = { "Badaga", 33205, "dra-kan", "Taml, Knda, Mlym", translit = { --Taml = "Taml-translit", }, -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["bfr"] = { "Bazigar", 8829558, "inc", } m["bfs"] = { "Southern Bai", 12952250, "sit-bai", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bft"] = { "Balti", 33086, "sit-lab", "fa-Arab, Deva, Tibt", override_translit = "Tibt", -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] strip_diacritics = { ["fa-Arab"] = { from = {"هٔ", "ٱ"}, to = {"ه", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.kashida .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, }, }, } m["bfu"] = { "Gahri", 5516952, "sit-whm", "Takr, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["bfw"] = { "Bondo", 2567942, "mun", "Orya", } m["bfx"] = { "Bantayanon", 16837866, "phi", "Latn", } m["bfy"] = { "Bagheli", 2356364, "inc-hie", "Deva", ancestors = "inc-oaw", translit = "hi-translit", } m["bfz"] = { "Mahasu Pahari", 6733460, "him", "Deva, Takr", translit = "hi-translit", } m["bga"] = { "Gwamhi-Wuri", 6707102, "nic-knn", "Latn", } m["bgb"] = { "Bobongko", 4935896, "poz-slb", "Latn", } m["bgc"] = { "Haryanvi", 33410, "inc-hiw", "Deva", translit = "hi-translit", } m["bgd"] = { "Rathwi Bareli", 7295692, "inc-bhi", "Deva", } m["bge"] = { "Bauria", 4873579, "inc-bhi", "Deva", } m["bgf"] = { "Bangandu", 34938, "gba-sou", "Latn", } m["bgg"] = { "Bugun", 3514220, "sit-khb", "Latn", } m["bgi"] = { "Klata", --"Giangan", 4842057, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/klata/", --TLCHANGE english_name = "Giangan", --TLCHANGE } m["bgj"] = { "Bangolan", 34862, "nic-nun", "Latn", } m["bgk"] = { "Bit", 2904868, "mkh-pal", "Latn", -- also Hani? } m["bgl"] = { "Bo", 8845514, "mkh-vie", } m["bgo"] = { "Baga Koga", 35695, "alv-bag", "Latn", } m["bgq"] = { "Bagri", 2426319, "raj", "Deva", } m["bgr"] = { "Bawm Chin", 56765, "tbq-kuk", "Latn", } m["bgs"] = { "Tagabawa", --"Tagabawa" 7675121, "mno", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/tagabawa/", --TLCHANGE english_name = "Tagabawa", --TLCHANGE } m["bgt"] = { "Bughotu", 2927723, "poz-sls", "Latn", } m["bgu"] = { "Mbongno", 36141, "nic-mmb", "Latn", } m["bgv"] = { "Warkay-Bipim", 4915439, "paa-yaq", "Latn", } m["bgw"] = { "Bhatri", 8841054, "inc-eas", "Deva", } m["bgx"] = { "Balkan Gagauz Turkish", 2360396, "trk-ogz", "Latn", ancestors = "trk-oat", } m["bgy"] = { "Benggoi", 4887742, "poz-cma", "Latn", } m["bgz"] = { "Banggai", 3441692, "poz-slb", "Latn", } m["bha"] = { "Bharia", 4901287, "inc", "Deva", } m["bhb"] = { "Bhili", 33229, "inc-bhi", "Deva, Gujr", translit = { Deva = "hi-translit", Gujr = "gu-translit", }, } m["bhc"] = { "Biga", 2902375, "poz-hce", "Latn", } m["bhd"] = { "Bhadrawahi", 4900565, "him", "Arab, Deva", translit = {Deva = "hi-translit"}, } m["bhe"] = { "Bhaya", 8841168, "raj", } m["bhf"] = { "Odiai", 56690, "qfa-dis", -- Papuan; no consensus; may be in the Kwomtari family, an isolate and/or distantly related to the -- Torricelli family. "Latn", } m["bhg"] = { "Binandere", 3503802, "ngf-bin", "Latn", } m["bhh"] = { "Bukhari", 56469, "ira-swi", "Cyrl, Hebr, Latn, fa-Arab", ancestors = "tg", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["bhi"] = { "Bhilali", 4901729, "inc-bhi", "Deva", } m["bhj"] = { "Bahing", 56442, "sit-kiw", "Deva, Latn", } m["bhl"] = { "Bimin", 4913743, "ngf-mok", "Latn", } m["bhm"] = { "Bathari", 2586893, "sem-sar", "Arab, Latn", } m["bhn"] = { "Bohtan Neo-Aramaic", 33230, "sem-nna", "Syrc", } m["bho"] = { "Bhojpuri", 33268, "inc-bih", "Deva, Kthi", wikimedia_codes = "bh", translit = { Deva = "bho-translit", Kthi = "bho-Kthi-translit", }, } m["bhp"] = { "Bima", 2796873, "poz-cet", "Latn", } m["bhq"] = { "South Tukang Besi", 12643975, "poz-mun", "Latn", } m["bhs"] = { "Buwal", 3515065, "cdc-cbm", "Latn", } m["bht"] = { "Bhattiyali", 4901452, "him", "Deva", } m["bhu"] = { "Bhunjia", 8841766, "inc-hal", "Deva, Orya", } m["bhv"] = { "Bahau", 3502039, "poz", "Latn", } m["bhw"] = { "Biak", 1961488, "poz-hce", "Latn", } m["bhx"] = { -- spurious? "Bhalay", 8840773, "inc", } m["bhy"] = { "Bhele", 4901671, "bnt-kbi", "Latn", } m["bhz"] = { "Bada", 4840520, "poz-kal", "Latn", } m["bia"] = { "Badimaya", 3442745, "aus-psw", "Latn", } m["bib"] = { "Bissa", 32934, "dmn-bbu", "Latn", } --- Bikaru [bic] is spurious m["bid"] = { "Bidiyo", 56258, "cdc-est", "Latn", } m["bie"] = { "Bepour", 4890914, "ngf-kum", "Latn", } m["bif"] = { "Biafada", 35099, "alv-ten", "Latn", } m["big"] = { "Biangai", 8842027, "paa-kun", "Latn", } m["bij"] = { "Kwanka", 35598, "nic-tar", "Latn", } m["bil"] = { "Bile", 34987, "nic-jrn", "Latn", } m["bim"] = { "Bimoba", 34971, "nic-grm", "Latn", } m["bin"] = { "Edo", 35375, "alv-eeo", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.grave .. c.macron .. c.dgrave}, sort_key = { from = {"ẹ", "gb", "gh", "kh", "kp", "mw", "nw", "ny", "ọ", "rh", "rr", "vb"}, to = {"e" .. p[1], "g" .. p[1], "g" .. p[2], "k" .. p[1], "k" .. p[2], "m" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "r" .. p[1], "r" .. p[1], "v" .. p[1]} }, } m["bio"] = { "Nai", 3508074, "paa-kwo", "Latn", } m["bip"] = { "Bila", 2902626, "bnt-kbi", "Latn", } m["biq"] = { "Bipi", 2904312, "poz-aay", "Latn", } m["bir"] = { "Bisorio", 8844749, "ngf-oen", "Latn", } m["bit"] = { "Berinomo", 56447, "paa-sep", "Latn", } m["biu"] = { "Biete", 4904687, "tbq-kuk", "Latn", } m["biv"] = { "Southern Birifor", 32859745, "nic-mre", "Latn", } m["biw"] = { "Kol (Cameroon)", 35582, "bnt-mka", "Latn", } m["bix"] = { "Bijori", 3450686, "mun", "Deva", } m["biy"] = { "Birhor", 3450469, "mun", "Deva", } m["biz"] = { "Baloi", 3450590, "bnt-ngn", "Latn", } m["bja"] = { "Budza", 3046889, "bnt-bun", "Latn", } m["bjb"] = { "Barngarla", 3439071, "aus-pam", "Latn", } m["bjc"] = { "Bariji", 4690919, "ngf-yar", "Latn", } m["bje"] = { "Biao-Jiao Mien", 3503800, "hmx-mie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["bjf"] = { "Barzani Jewish Neo-Aramaic", 33234, "sem-nna", "Hebr", -- maybe others -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["bjg"] = { "Bidyogo", 35365, "alv-bak", "Latn", } m["bjh"] = { "Bahinemo", 56361, "paa-sep", "Latn", } m["bji"] = { "Burji", 34999, "cus-hec", "Latn, Ethi", } m["bjj"] = { "Kannauji", 2726867, "inc-hiw", "Deva", } m["bjk"] = { "Barok", 2884743, "poz-ocw", "Latn", } m["bjl"] = { "Bulu (New Guinea)", 4997162, "poz-ocw", "Latn", } m["bjm"] = { "Bajelani", 4848866, "ira-zgr", "Latn, Arab", ancestors = "hac", } m["bjn"] = { "Banjares", --TLCHANGE the J is actully pronounced /dʒ/ in its origin language, so no need to convert from Spanish J to Y 33151, "poz-mly", "Latn, Arab", english_name = "Banjarese", --TLCHANGE spanish_name = "Banjarés", --TLCHANGE } m["bjo"] = { "Mid-Southern Banda", 42303990, "bad-cnt", "Latn", } m["bjp"] = { "Fanamaket", 56704263, "poz-oce", "Latn", } m["bjr"] = { "Binumarien", 538364, "ngf-tai", "Latn", } m["bjs"] = { "Bajan", 2524014, "crp", "Latn", ancestors = "en", } m["bjt"] = { "Balanta-Ganja", 19359034, "alv-bak", "Arab, Latn", } m["bju"] = { "Busuu", 35046, "nic-fru", "Latn", } m["bjv"] = { "Bedjond", 8829831, "csu-sar", "Latn", } m["bjw"] = { "Bakwé", 34899, "kro-ekr", "Latn", } m["bjx"] = { "Itnëg Banaw", --"Banao Itneg", 12627559, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/itneg/", --TLCHANGE english_name = "Banao Itneg", --TLCHANGE } m["bjy"] = { "Bayali", 4874263, "aus-pam", "Latn", } m["bjz"] = { "Baruga", 2886189, "ngf-bin", "Latn", } m["bka"] = { "Kyak", 35653, "alv-bwj", "Latn", } m["bkc"] = { "Baka", 34905, "nic-nkb", "Latn", } m["bkd"] = { "Binukid", --"Binukid", 4914553, "mno", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/binukid/", --TLCHANGE english_name = "Binukid", --TLCHANGE } m["bkf"] = { "Beeke", 3441375, "bnt-kbi", "Latn", } m["bkg"] = { "Buraka", 35066, "nic-nkg", "Latn", } m["bkh"] = { "Bakoko", 34866, "bnt-bsa", "Latn", } m["bki"] = { "Baki", 11024697, "poz-vnc", "Latn", } m["bkj"] = { "Pande", 36263, "bnt-ngn", "Latn", } m["bkk"] = { -- written in Balti script "Brokskat", 2925988, "inc-shn", "Tibt, Arab", -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- (NOTE: formerly not present, probably an accidental omission) } m["bkl"] = { "Berik", 378743, "paa-tor", "Latn", } m["bkm"] = { "Kom (Cameroon)", 1656595, "nic-rnc", "Latn", } m["bkn"] = { "Bukitan", 3446774, "poz-bnn", "Latn", } m["bko"] = { "Kwa'", 35567, "bai", "Latn", } m["bkp"] = { "Iboko", 35089, "bnt-ngn", "Latn", } m["bkq"] = { "Bakairí", 56846, "sai-pek", "Latn", } m["bkr"] = { "Bakumpai", 3436626, "poz-brw", "Latn", } m["bks"] = { "Hilagang Sorsoganon", --TLCHANGE 16113356, "phi", "Latn", english_name = "Masbate Sorsogon", --TLCHANGE is_official_kwf_name = "https://kwfwikaatkultura.ph/ortograpiyang-sorsoganon/" --TLCHANGE } m["bkt"] = { "Boloki", 4144560, "bnt-zbi", "Latn", ancestors = "lse", } m["bku"] = { "Buhid Mangyan", --"Buhid", 1002956, "phi", "Latn, Buhd", translit = { Buhd = "bku-translit", }, override_translit = true, strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ, } }, sort_key = { Latn = "tl-sortkey", }, standard_chars = { Latn = "AaBbKkDdEeFfGgHhIiLlMmNnOoPpRrSsTtUuWwYy" .. c.punc, }, is_official_kwf_name = "https://kwfwikaatkultura.ph/buhid-mangyan/", --TLCHANGE english_name = "Buhid", --TLCHANGE } m["bkv"] = { "Bekwarra", 34954, "nic-ben", "Latn", } m["bkw"] = { "Bekwel", 34950, "bnt-bek", "Latn", } m["bkx"] = { "Baikeno", 11200640, "poz-tim", "Latn", } m["bky"] = { "Bokyi", 35087, "nic-ben", "Latn", } m["bkz"] = { "Bungku", 2928207, "poz-btk", "Latn", } m["bla"] = { "Blackfoot", 33060, "alg", "Latn, Cans", } m["blb"] = { "Bilua", 35003, "qfa-dis", -- Papuan; isolate per Glottolog, Central Solomon per Ross (2005) and Pedrós (2015) "Latn", } m["blc"] = { "Bella Coola", 977808, "sal", "Latn", } m["bld"] = { "Bolango", 3450578, "phi", "Latn", } m["ble"] = { "Balanta-Kentohe", 56789, "alv-bak", "Latn", } m["blf"] = { "Buol", 2928278, "phi", "Latn", } m["blg"] = { "Balau", 4850134, "poz-mly", "Latn", } m["blh"] = { "Kuwaa", 35579, "kro", "Latn", } m["bli"] = { "Bolia", 34910, "bnt-mon", "Latn", } m["blj"] = { "Bulungan", 9229310, "poz", "Latn", } m["blk"] = { "Pa'o Karen", 7121294, "kar", "Mymr", } m["bll"] = { "Biloxi", 2903780, "sio-ohv", "Latn", } m["blm"] = { "Beli (South Sudan)", 56821, "csu-bbk", "Latn", } m["bln"] = { "Bikol Katimugang Catanduanes", --TLCHANGE 7569754, "phi", "Latn", english_name = "Southern Catanduanes Bicolano", --TLCHANGE } m["blo"] = { "Anii", 34838, "alv-ntg", "Latn", } m["blp"] = { "Blablanga", 2905245, "poz-ocw", "Latn", } m["blq"] = { "Baluan-Pam", 2881675, "poz-aay", "Latn", } m["blr"] = { "Blang", 4925096, "mkh-pal", "Latn, Tale, Lana, Thai", sort_key = { -- FIXME: This needs to be converted into the current standardized format. from = {"[%pᪧๆ]", "[᩠ᩳ-᩿]", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "ᩈᩈ", "ᩁ", "ᩃ", "ᨦ", "%1ᨮ", "%1ᨻ", "ᩣ", "", "%2%1"} }, } m["bls"] = { "Balaesang", 4849796, "poz", "Latn", } m["blt"] = { "Tai Dam", 56407, "tai-swe", "Tavt, Latn", --translit = "Tavt-translit", sort_key = { Tavt = { from = {"[꪿ꫀ꫁ꫂ]", "([ꪵꪶꪹꪻꪼ])([ꪀ-ꪯ])"}, to = {"", "%2%1"} }, }, } m["blv"] = { "Kibala", 4939959, "bnt-kmb", "Latn", } m["blw"] = { "Balangaw", --"Balangao", 4850033, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/balangaw/", --TLCHANGE english_name = "Balangao", --TLCHANGE } m["blx"] = { "Ayta Mag-indi", --"Mag-Indi Ayta", 1931221, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/ayta-mag-indi/", --TLCHANGE english_name = "Mag-Indi Ayta", --TLCHANGE } m["bly"] = { "Notre", 11009194, "nic-wov", "Latn", } m["blz"] = { "Balantak", 4850053, "poz-slb", "Latn", } m["bma"] = { "Lame", 3913997, "nic-jrn", "Latn", } m["bmb"] = { "Bembe", 4885023, "bnt-lgb", "Latn", } m["bmc"] = { "Biem", 4904523, "poz-ocw", "Latn", } m["bmd"] = { "Baga Manduri", 35815, "alv-bag", "Latn", } m["bme"] = { "Limassa", 11004666, "nic-nkb", "Latn", } m["bmf"] = { "Bom", 35088, "alv-mel", "Latn", } m["bmg"] = { "Bamwe", 34867, "bnt-bun", "Latn", } m["bmh"] = { "Kein", 6383764, "ngf-kok", "Latn", } m["bmi"] = { "Bagirmi", 34903, "csu-bgr", "Latn", } m["bmj"] = { "Bote-Majhi", 9229570, "inc-bih", "Deva", } m["bmk"] = { "Ghayavi", 5555976, "poz-ocw", "Latn", } m["bml"] = { "Bomboli", 35055, "bnt-ngn", "Latn", } m["bmn"] = { "Bina", 8843664, "poz-ocw", "Latn", } m["bmo"] = { "Bambalang", 34868, "nic-nun", "Latn", } m["bmp"] = { "Bulgebi", 4996380, "ngf-war", "Latn", } m["bmq"] = { "Bomu", 35065, "nic-bwa", "Latn", } m["bmr"] = { "Muinane", 3027894, "sai-bor", "Latn", } m["bmt"] = { "Biao Mon", 8842159, "hmx-mie", } m["bmu"] = { "Somba-Siawari", 5000983, "ngf-kbm", "Latn", } m["bmv"] = { "Bum", 35058, "nic-rnc", "Latn", } m["bmw"] = { "Bomwali", 34984, "bnt-ndb", "Latn", } m["bmx"] = { "Baimak", 3450546, "ngf-han", "Latn", } m["bmz"] = { "Baramu", 4858315, "paa-tir", "Latn", } m["bna"] = { "Bonerate", 4941729, "poz-mun", "Latn", } m["bnb"] = { "Bookan", 4943150, "poz-san", "Latn", } m["bnd"] = { "Banda", 3504147, "poz-cma", "Latn", } m["bne"] = { "Bintauna", 4914533, "phi", "Latn", } m["bnf"] = { "Masiwang", 6783305, "poz-cma", "Latn", } m["bng"] = { "Benga", 34952, "bnt-saw", "Latn", } m["bni"] = { "Bangi", 34936, "bnt-bmo", "Latn", } m["bnj"] = { "Bangon Mangyan", --"Eastern Tawbuid", 18757427, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/bangon-mangyan/", --TLCHANGE english_name = "Eastern Tawbuid", --TLCHANGE } m["bnk"] = { "Bierebo", 2902029, "poz-vnc", "Latn", } m["bnl"] = { "Boon", 56616, "cus-eas", "Latn", } m["bnm"] = { "Batanga", 34979, "bnt-saw", "Latn", } m["bnn"] = { "Bunun", 56505, "map", "Latn", } m["bno"] = { "Asi", --"Asi", 29490, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/asi/", --TLCHANGE english_name = "Asi", --TLCHANGE } m["bnp"] = { "Bola", 4938876, "poz-ocw", "Latn", } m["bnq"] = { "Bantik", 2883521, "poz", "Latn", } m["bnr"] = { "Butmas-Tur", 2928942, "poz-vnn", "Latn", } m["bns"] = { "Bundeli", 56399, "inc-hiw", "Deva", translit = "hi-translit", } m["bnu"] = { "Bentong", 4890644, "poz-ssw", "Latn", } m["bnv"] = { "Beneraf", 4941733, "paa-tor", "Latn", } m["bnw"] = { "Bisis", 56356, "paa-sep", "Latn", } m["bnx"] = { "Bangubangu", 3438330, "bnt-lbn", "Latn", } m["bny"] = { "Bintulu", 3450775, "poz-swa", "Latn", } m["bnz"] = { "Beezen", 35083, "nic-ykb", "Latn", } m["boa"] = { "Bora", 2375468, "sai-bor", "Latn", } m["bob"] = { "Aweer", 56526, "cus-som", "Latn", } m["boe"] = { "Mundabli", 36127, "nic-beb", "Latn", } m["bof"] = { "Bolon", 3913301, "dmn-emn", "Latn", } m["bog"] = { "Wikang Senyas ng Bamako", --TLCHANGE 4853284, "sgn", english_name = "Bamako Sign Language", --TLCHANGE spanish_name = "Lengua de signos bamako", --TLCHANGE } m["boh"] = { "North Boma", 35080, "bnt-bdz", "Latn", } m["boi"] = { "Barbareño", 56391, "nai-chu", "Latn", } m["boj"] = { "Anjam", 3504136, "ngf-min", "Latn", } m["bok"] = { "Bonjo", 34942, "alv", "Latn", } m["bol"] = { "Bole", 3436680, "cdc-wst", "Latn", } m["bom"] = { "Berom", 35013, "nic-beo", "Latn", } m["bon"] = { "Bine", 4914077, "paa-etf", "Latn", } m["boo"] = { "Tiemacèwè Bozo", 12643582, "dmn-snb", "Latn", -- and others? } m["bop"] = { "Bonkiman", 4942134, "ngf-yup", "Latn", } m["boq"] = { "Bogaya", 7207578, "qfa-dis", -- Papuan; isolate per Glottolog, grouped in Duna-Pogaya family by Voorhoeve (1975), Ross (2005) and Usher (2018) "Latn", } m["bor"] = { "Borôro", 32986, "sai-mje", "Latn", } m["bot"] = { "Bongo", 2910067, "csu-bbk", "Latn", } m["bou"] = { "Bondei", 4941378, "bnt-seu", "Latn", } m["bov"] = { "Tuwuli", 36974, "alv-ktg", "Latn", } m["bow"] = { "Rema", 7311502, "paa-ton", "Latn", } m["box"] = { "Buamu", 35157, "nic-bwa", "Latn", } m["boy"] = { "Bodo (Central Africa)", 4936715, "bnt-leb", "Latn", } m["boz"] = { "Tiéyaxo Bozo", 32860401, "dmn-snb", "Latn", } m["bpa"] = { "Daakaka", 1157729, "poz-vnc", "Latn", } m["bpd"] = { "Banda-Banda", 3450674, "bad-cnt", "Latn", } m["bpe"] = { "Bauni", 105150962, "paa-pio", "Latn", } m["bpg"] = { "Bonggo", 4941860, "poz-ocw", "Latn", } m["bph"] = { "Botlikh", 56560, "cau-and", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["bpi"] = { "Bagupi", 3450697, "ngf-han", "Latn", } m["bpj"] = { "Binji", 4914403, "bnt-lbn", "Latn", } m["bpk"] = { "Orowe", 7103905, "poz-cln", "Latn", } m["bpl"] = { "Broome Pearling Lugger Pidgin", 4975277, "crp", "Latn", ancestors = "ms", } m["bpm"] = { "Biyom", 4919327, "ngf-rai", "Latn", } m["bpn"] = { "Dzao Min", 3042189, "hmx-mie", } m["bpo"] = { "Anasi", 11207813, "paa-egb", "Latn", } m["bpp"] = { "Kaure", 20526532, "paa-kko", "Latn", } m["bpq"] = { "Banda Malay", 12473442, "crp", "Latn", ancestors = "ms", } m["bpr"] = { "Koronadal Blaan", 16115430, "phi", "Latn", } m["bps"] = { "Sarangani Blaan", 16117272, "phi", "Latn", } m["bpt"] = { "Barrow Point", 2567916, "aus-pmn", "Latn", } m["bpu"] = { "Bongu", 4941930, "ngf-min", "Latn", } m["bpv"] = { "Bian Marind", 8841889, "paa-mri", "Latn", } -- bpw: Bo (Papua New Guinea): excluded in 2012 and re-evaluated in 2025 with the same conclusion; per Wikipedia: "It is -- essentially undocumented, and its status as a separate language is unconfirmed." m["bpx"] = { "Palya Bareli", 7128872, "inc-bhi", "Deva", translit = "hi-translit", } m["bpy"] = { "Bishnupriya Manipuri", 37059, "inc-bas", "Beng", ancestors = "inc-obn", } m["bpz"] = { "Bilba", 8843362, "poz-tim", "Latn", } m["bqa"] = { "Tchumbuli", 11008162, "alv-ctn", "Latn", ancestors = "ak", } m["bqb"] = { "Bagusa", 4842178, "paa-kwe", "Latn", } m["bqc"] = { "Boko", 34983, "dmn-bbu", "Latn", } m["bqd"] = { "Bung", 3436612, "nic-bdn", "Latn", } m["bqf"] = { "Baga Kaloum", 3502293, "alv-bag", "Latn", } m["bqg"] = { "Bago-Kusuntu", 34878, "nic-gne", } m["bqh"] = { "Baima", 674990, "sit-qia", } m["bqi"] = { "Bakhtiari", 257829, "ira-swi", "fa-Arab", ancestors = "pal", } m["bqj"] = { "Bandial", 34872, "alv-jol", "Latn", } m["bqk"] = { "Banda-Mbrès", 3450724, "bad-cnt", "Latn", } m["bql"] = { "Karian", 4907504, "ngf-num", "Latn", } m["bqm"] = { "Wumboko", 37051, "bnt-kpw", "Latn", } m["bqn"] = { "Wikang Senyas ng mga Bulgaro", --TLCHANGE 3438325, "sgn", english_name = "Bulgarian Sign Language", --TLCHANGE spanish_name = "Lengua de signos búlgaro", --TLCHANGE } m["bqo"] = { "Balo", 34865, "nic-grs", "Latn", } m["bqp"] = { "Busa", 35185, "dmn-bbu", "Latn", } m["bqq"] = { "Biritai", 56382, "paa-clp", "Latn", } m["bqr"] = { "Burusu", 5001028, "poz-san", "Latn", } m["bqs"] = { "Bosngun", 56838, "paa-baw", "Latn", } m["bqt"] = { "Bamukumbit", 35078, "nic-nge", "Latn", } m["bqu"] = { "Boguru", 3438444, "bnt-boa", "Latn", } m["bqv"] = { "Begbere-Ejar", 7194098, "nic-plc", "Latn", } m["bqw"] = { "Buru (Nigeria)", 1017152, "nic-bds", "Latn", } m["bqx"] = { "Baangi", 3450648, "nic-kam", "Latn", } m["bqy"] = { "Wikang Senyas ng Bengkala", --TLCHANGE 3322119, "sgn", english_name = "Bengkala Sign Language", --TLCHANGE spanish_name = "Lengua de signos bengkala", --TLCHANGE } m["bqz"] = { "Bakaka", 34855, "bnt-mne", "Latn", } m["bra"] = { "Braj", 35243, "inc-hiw", "Deva", translit = "hi-translit", } m["brb"] = { "Lave", 4957737, "mkh-ban", } m["brc"] = { "Berbice Creole Dutch", 35215, "crp", "Latn", ancestors = "nl", } m["brd"] = { "Baraamu", 56804, "sit-new", "Deva", } m["brf"] = { "Bera", 2896850, "bnt-kbi", "Latn", } m["brg"] = { "Baure", 2839722, "awd", "Latn", } m["brh"] = { "Brahui", 33202, "dra-nor", "ur-Arab, Latn", translit = {["ur-Arab"] = "ur-translit"}, strip_diacritics = { -- 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 }, } m["bri"] = { "Mokpwe", 36428, "bnt-kpw", "Latn", } m["brj"] = { "Bieria", 4904607, "poz-vnc", "Latn", } m["brk"] = { "Birgid", 56823, "nub", "Latn", } m["brl"] = { "Birwa", 3501019, "bnt-sts", "Latn", } m["brm"] = { "Barambu", 34893, "znd", "Latn", } m["brn"] = { "Boruca", 4946773, "cba", "Latn", } m["bro"] = { "Brokkat", 56605, "sit-tib", "Tibt, Latn", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["brp"] = { "Barapasi", 56995, "paa-egb", "Latn", } m["brq"] = { "Breri", 4961835, "paa-tam", "Latn", } m["brr"] = { "Birao", 2904383, "poz-sls", "Latn", } m["brs"] = { "Baras", 8827053, "poz", "Latn", } m["brt"] = { "Bitare", 34946, "nic-tvn", "Latn", } m["bru"] = { "Silanganing Bru", --TLCHANGE 16115463, "mkh-kat", "Latn, Laoo, Thai", sort_key = { Laoo = "Laoo-sortkey", Thai = "Thai-sortkey", }, english_name = "Eastern Bru", --TLCHANGE } m["brv"] = { "Kanluraning Bru", --TLCHANGE 13018531, "mkh-kat", "Latn, Laoo, Thai", sort_key = { Laoo = "Laoo-sortkey", Thai = "Thai-sortkey", }, english_name = "Western Bru", --TLCHANGE } m["brw"] = { "Bellari", 4883496, "dra-tlk", "Knda, Mlym", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["brx"] = { "Bodo (India)", 33223, "tbq-bdg", "Deva, Latn", translit = {Deva = "brx-translit"}, } m["bry"] = { "Burui", 5000976, "paa-nnd", "Latn", } m["brz"] = { "Bilbil", 4907473, "poz-ocw", "Latn", } m["bsa"] = { "Abinomn", 56648, "qfa-iso", -- Papuan "Latn", } m["bsb"] = { "Brunei Bisaya", 3450611, "poz-san", "Latn", } m["bsc"] = { "Bassari", 35098, "alv-ten", "Latn", } m["bse"] = { "Wushi", 36973, "nic-rnn", "Latn", } m["bsf"] = { "Bauchi", 34974, "nic-shi", "Latn", } m["bsg"] = { "Bashkardi", 33030, "ira-swi", "fa-Arab, Latn", } m["bsh"] = { "Kamkata-viri", 2605045, "nur-nor", "Latn, Arab", } m["bsi"] = { "Bassossi", 34940, "bnt-mne", "Latn", } m["bsj"] = { "Bangwinji", 3446631, "alv-wjk", "Latn", } m["bsk"] = { "Burushaski", 216286, "qfa-iso", "Arab", strip_diacritics = { -- 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 }, } m["bsl"] = { "Basa-Gumna", 4866150, "nic-bas", "Latn", } m["bsm"] = { "Busami", 5001255, "poz-hce", "Latn", } m["bsn"] = { "Barasana", 2883843, "sai-tuc", "Latn", } m["bso"] = { "Buso", 3441370, "cdc-est", "Latn", } m["bsp"] = { "Baga Sitemu", 36466, "alv-bag", "Latn", } m["bsq"] = { "Bassa", 34949, "kro-wkr", "Latn, Bass", } m["bsr"] = { "Bassa-Kontagora", 4866152, "nic-bas", "Latn", } m["bss"] = { "Akoose", 34806, "bnt-mne", "Latn", } m["bst"] = { "Basketo", 56531, "omv-ome", "Ethi", } m["bsu"] = { "Bahonsuai", 2879298, "poz-btk", "Latn", } m["bsv"] = { "Baga Sobané", 3450433, "alv-bag", "Latn", } m["bsw"] = { "Baiso", 56615, "cus-som", "Latn", } m["bsx"] = { "Yangkam", 36922, "nic-tar", "Latn", } m["bsy"] = { "Sabah Bisaya", 12641557, "poz-san", "Latn", } m["bta"] = { "Bata", 56254, "cdc-cbm", "Latn", } m["btc"] = { "Bati (Cameroon)", 34944, "nic-mbw", "Latn", } m["btd"] = { "Dairi Batak", 2891045, "btk", "Latn, Batk", } m["bte"] = { "Gamo-Ningi", 5520366, "nic-jer", "Latn", } m["btf"] = { "Birgit", 56302, "cdc-est", "Latn", } m["btg"] = { "Gagnoa Bété", 5005069, "kro-bet", "Latn", } m["bth"] = { "Biatah Bidayuh", 2900881, "day", "Latn", } m["bti"] = { "Burate", 56900, "paa-egb", "Latn", } m["btj"] = { "Bacanese Malay", 8828608, "poz-mly", "Latn", } m["btm"] = { "Mandailing Batak", 2891049, "btk", "Latn, Batk", } m["btn"] = { "Ratagnon Mangyan", --"Ratagnon", 13197, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/ratagnon-mangyan/", --TLCHANGE english_name = "Ratagnon", --TLCHANGE } m["bto"] = { "Rinkonada", --"Iriga Bicolano", 12633026, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/rinkonada/", --TLCHANGE english_name = "Iriga Bicolano", --TLCHANGE } m["btp"] = { "Budibud", 4985086, "poz-ocw", "Latn", } m["btq"] = { "Batek", 860315, "mkh-asl", "Latn", } m["btr"] = { "Baetora", 2878874, "poz-vnn", "Latn", } m["bts"] = { "Simalungun Batak", 2891054, "btk", "Latn, Batk", } m["btt"] = { "Bete-Bendi", 4887064, "nic-ben", "Latn", } m["btu"] = { "Batu", 34964, "nic-tvn", "Latn", } m["btv"] = { "Bateri", 3812564, "inc-koh", "Deva", } m["btw"] = { "Butwanon", --"Butuanon", 5003156, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/butwanon/", --TLCHANGE english_name = "Butuanon", --TLCHANGE } m["btx"] = { "Karo Batak", 33012, "btk", "Latn, Batk", } m["bty"] = { "Bobot", 3446788, "poz-cma", "Latn", } m["btz"] = { "Alas-Kluet Batak", 2891042, "btk", "Latn, Batk", } m["bua"] = { "Buryat", 33120, "xgn-cen", "Cyrl, Mong, Latn", wikimedia_codes = "bxr", ancestors = "cmg", translit = { Cyrl = "bua-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 = { from = {"ё", "ө", "ү", "һ"}, to = {"е" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1]} }, }, } m["bub"] = { "Bua", 32928, "alv-bua", "Latn", } m["bud"] = { "Ntcham", 36266, "nic-grm", "Latn", } m["bue"] = { "Beothuk", 56234, "qfa-unc", -- extinct since 1829, poorly attested; possibly a divergent Algonquian language "Latn", } m["buf"] = { "Bushoong", 3449964, "bnt-bsh", "Latn", } m["bug"] = { "Buginese", 33190, "poz-ssw", "Bugi, Latn", } m["buh"] = { "Younuo Bunu", 56299, "hmn", "Latn", } m["bui"] = { "Bongili", 35084, "bnt-ngn", "Latn", } m["buj"] = { "Basa-Gurmana", 6432515, "nic-bas", "Latn", } m["buk"] = { "Bukawa", 35043, "poz-ocw", "Latn", } m["bum"] = { "Bulu (Cameroon)", 35028, "bnt-btb", "Latn", } m["bun"] = { "Sherbro", 36339, "alv-mel", "Latn", } m["buo"] = { "Terei", 56831, "paa-sbo", "Latn", } m["bup"] = { "Busoa", 5002001, "poz", "Latn", } m["buq"] = { "Brem", 4960502, "ngf-nad", "Latn", } m["bus"] = { "Bokobaru", 9228931, "dmn-bbu", "Latn", } m["but"] = { "Bungain", 3450623, "paa-mar", "Latn", } m["buu"] = { "Budu", 3450207, "bnt-nya", "Latn", } m["buv"] = { "Bun", 56351, "paa-yua", "Latn", } m["buw"] = { "Bubi", 35017, "bnt-tso", "Latn", } m["bux"] = { "Boghom", 3440412, "cdc-wst", "Latn", } m["buy"] = { "Mmani", 35061, "alv-mel", "Latn", } m["bva"] = { "Barein", 56285, "cdc-est", "Latn", } m["bvb"] = { "Bube", 35110, "nic-bds", "Latn", } m["bvc"] = { "Baelelea", 2878833, "poz-sls", "Latn", } m["bvd"] = { "Baeggu", 2878850, "poz-sls", "Latn", } m["bve"] = { "Berau Malay", 3915770, "poz-mly", "Latn", } m["bvf"] = { "Boor", 56250, "cdc-est", "Latn", } m["bvg"] = { "Bonkeng", 34958, "bnt-bbo", "Latn", } m["bvh"] = { "Bure", 56294, "cdc-wst", "Latn", } m["bvi"] = { "Belanda Viri", 35247, "nic-ser", "Latn", } m["bvj"] = { "Baan", 3515067, "nic-ogo", "Latn", } m["bvk"] = { "Bukat", 4986814, "poz-bnn", "Latn", } m["bvl"] = { "Wikang Senyas ng mga Bolivyano", --TLCHANGE 1783590, "sgn", "Latn", -- when documented english_name = "Bolivian Sign Language", --TLCHANGE spanish_name = "Lengua de signos boliviano", --TLCHANGE } m["bvm"] = { "Bamunka", 34882, "nic-rnn", "Latn", } m["bvn"] = { "Buna", 3450516, "paa-mar", "Latn", } m["bvo"] = { "Bolgo", 35038, "alv-bua", "Latn", } m["bvp"] = { "Bumang", 4997235, "mkh-pal", } m["bvq"] = { "Birri", 56514, "csu-bkr", "Latn", } m["bvr"] = { "Burarra", 4998124, "aus-arn", "Latn", } m["bvt"] = { "Bati (Indonesia)", 4869253, "poz-cma", "Latn", } m["bvu"] = { "Bukit Malay", 9230148, "poz-mly", "Latn", } m["bvv"] = { "Baniva", 3515198, "awd", "Latn", } m["bvw"] = { "Boga", 56262, "cdc-cbm", "Latn", } m["bvx"] = { "Babole", 35180, "bnt-ngn", "Latn", } m["bvy"] = { "Baybayanon", 16839275, "phi", "Latn", } m["bvz"] = { "Bauzi", 56360, "paa-egb", "Latn", } m["bwa"] = { "Bwatoo", 9232446, "poz-cln", "Latn", } m["bwb"] = { "Namosi-Naitasiri-Serua", 3130290, "poz-pcc", "Latn", } m["bwc"] = { "Bwile", 3447440, "bnt-sbi", "Latn", } m["bwd"] = { "Bwaidoka", 2929111, "poz-ocw", "Latn", } m["bwe"] = { "Bwe Karen", 56994, "kar", "Mymr, Latn", } m["bwf"] = { "Boselewa", 4947229, "poz-ocw", "Latn", } m["bwg"] = { "Barwe", 8826802, "bnt-sna", "Latn", } m["bwh"] = { "Bishuo", 34973, "nic-fru", "Latn", } m["bwi"] = { "Baniwa", 3501735, "awd-nwk", "Latn", } m["bwj"] = { "Láá Láá Bwamu", 11017275, "nic-bwa", "Latn", } m["bwk"] = { "Bauwaki", 4873607, "paa-mal", "Latn", } m["bwl"] = { "Bwela", 5003678, "bnt-bun", "Latn", } m["bwm"] = { "Biwat", 56352, "paa-yua", "Latn", } m["bwn"] = { "Wunai Bunu", 56452, "hmn", } m["bwo"] = { "Shinasha", 56260, "omv-gon", "Latn", } m["bwp"] = { "Lower Mandobo", 12636155, "ngf-dum", "Latn", } m["bwq"] = { "Southern Bobo", 11001714, "dmn-snb", "Latn", } m["bwr"] = { "Bura", 56552, "cdc-cbm", "Latn", } m["bws"] = { "Bomboma", 9229429, "bnt-bun", "Latn", } m["bwt"] = { "Bafaw", 34853, "bnt-bbo", "Latn", } m["bwu"] = { "Buli (Ghana)", 35085, "nic-buk", "Latn", } m["bww"] = { "Bwa", 3515058, "bnt-bta", "Latn", } m["bwx"] = { "Bu-Nao Bunu", 56411, "hmn", "Latn", } m["bwy"] = { "Cwi Bwamu", 11150714, "nic-bwa", "Latn", } m["bwz"] = { "Bwisi", 35067, "bnt-sir", "Latn", } m["bxa"] = { "Bauro", 2892068, "poz-sls", "Latn", } m["bxb"] = { "Belanda Bor", 56678, "sdv-lon", "Latn", } m["bxc"] = { "Molengue", 13345, "bnt-kel", "Latn", } m["bxd"] = { "Pela", 57000, "tbq-brm", } m["bxe"] = { "Ongota", 36344, "qfa-unc", -- moribund, no academic consensus on classification; might be an isolate "Latn", } m["bxf"] = { "Bilur", 2903788, "poz-ocw", "Latn", } m["bxg"] = { "Bangala", 34989, "bnt-bmo", "Latn", } m["bxh"] = { "Buhutu", 4986329, "poz-ocw", "Latn", } m["bxi"] = { "Pirlatapa", 10632195, "aus-kar", "Latn", } m["bxj"] = { "Bayungu", 10427485, "aus-psw", "Latn", } m["bxk"] = { "Bukusu", 32930, "bnt-msl", "Latn", } m["bxl"] = { "Jalkunan", 11009787, "dmn-jje", "Latn", } m["bxn"] = { "Burduna", 4998313, "aus-psw", "Latn", } m["bxo"] = { "Barikanchi", 3450802, "crp", "Latn", ancestors = "ha", } m["bxp"] = { "Bebil", 34941, "bnt-btb", "Latn", } m["bxq"] = { "Beele", 56238, "cdc-wst", "Latn", } m["bxs"] = { "Busam", 35189, "nic-grs", "Latn", } m["bxv"] = { "Berakou", 56796, "csu-bgr", "Latn", } m["bxw"] = { "Banka", 3438402, "dmn-smg", "Latn", } m["bxz"] = { "Binahari", 4913840, "paa-mal", "Latn", } m["bya"] = { "Binatak", --"Palawan Batak", 3450443, "phi", "Tagb", is_official_kwf_name = "https://kwfwikaatkultura.ph/binatak/", --TLCHANGE english_name = "Palawan Batak", --TLCHANGE } m["byb"] = { "Bikya", 33257, "nic-fru", "Latn", } m["byc"] = { "Ubaghara", 36625, "nic-ucn", "Latn", } m["byd"] = { "Benyadu'", 11173588, "day", "Latn", } m["bye"] = { "Pouye", 7235814, "paa-sep", "Latn", } m["byf"] = { "Bete", 32932, "nic-ykb", "Latn", } m["byg"] = { "Baygo", 56836, "sdv-daj", "Latn", } m["byh"] = { "Bujhyal", 56317, "sit-gma", "Deva", } m["byi"] = { "Buyu", 5003401, "bnt-nyb", "Latn", } m["byj"] = { "Binawa", 4913807, "nic-kau", "Latn", } m["byk"] = { "Biao", 4902547, "qfa-tak", "Latn", -- also Hani? } m["byl"] = { "Bayono", 3503856, "paa-baa", "Latn", } m["bym"] = { "Bidyara", 8842355, "aus-pam", "Latn", } m["byn"] = { "Blin", 56491, "cus-cen", "Ethi, Latn", translit = {Ethi = "Ethi-translit"}, } m["byo"] = { "Biyo", 56848, "tbq-bka", "Latn, Hani", sort_key = {Hani = "Hani-sortkey"}, } m["byp"] = { "Bumaji", 4997234, "nic-ben", "Latn", } m["byq"] = { "Basay", 716647, "map", "Latn", } m["byr"] = { "Baruya", 3450812, "ngf-bsi", "Latn", } m["bys"] = { "Burak", 4998097, "alv-bwj", "Latn", } m["byt"] = { "Berti", 35008, "ssa-sah", "Latn", } m["byv"] = { "Medumba", 36019, "bai", "Latn", } m["byw"] = { "Belhariya", 32961, "sit-kie", "Deva", } m["byx"] = { "Qaqet", 3503009, "paa-bai", "Latn", } m["byz"] = { "Banaro", 56858, "paa-ram", "Latn", } m["bza"] = { "Bandi", 34912, "dmn-msw", "Latn", } m["bzb"] = { "Andio", 4754487, "poz-slb", "Latn", } m["bzd"] = { "Bribri", 28400, "cba", "Latn", } m["bze"] = { "Jenaama Bozo", 10950633, "dmn-snb", "Latn", } m["bzf"] = { "Boikin", 56829, "paa-ndu", "Latn", } m["bzg"] = { "Babuza", 716615, "map", "Latn", } m["bzh"] = { "Mapos Buang", 2927370, "poz-ocw", "Latn", } m["bzi"] = { "Bisu", 56852, "tbq-bis", "Latn, Thai", sort_key = {Thai = "Thai-sortkey"}, } m["bzj"] = { "Belizean Creole", 1363055, "crp", "Latn", ancestors = "en", } m["bzk"] = { "Nicaraguan Creole", 3504097, "crp", "Latn", ancestors = "en", } m["bzl"] = { -- supposedly also called "Bolano", but I can find no evidence of that "Boano (Sulawesi)", 4931258, "poz", "Latn", } m["bzm"] = { "Bolondo", 35071, "bnt-bun", "Latn", } m["bzn"] = { "Boano (Maluku)", 4931255, "poz-cma", "Latn", } m["bzo"] = { "Bozaba", 4952785, "bnt-ngn", "Latn", } m["bzp"] = { "Kemberano", 12634399, "ngf-sbh", "Latn", } m["bzq"] = { "Buli (Indonesia)", 2927952, "poz-hce", "Latn", } m["bzr"] = { "Biri", 4087011, "aus-pam", "Latn", } m["bzs"] = { "Wikang Senyas ng mga Brasileño", --TLCHANGE 3436689, "sgn", "Latn", english_name = "Brazilian Sign Language", --TLCHANGE spanish_name = "Lengua de signos brasileño", --TLCHANGE } m["bzu"] = { "Burmeso", 56746, "qfa-dis", -- isolate in Glottolog, Wurm and Foley; in East Bird's Head-Sentani fmaily by Ross "Latn", } m["bzv"] = { "Bebe", 34977, "nic-bbe", "Latn", } m["bzw"] = { "Basa", 34898, "nic-bas", "Latn", } m["bzx"] = { "Hainyaxo Bozo", 11159536, "dmn-snb", "Latn", } m["bzy"] = { "Obanliku", 36276, "nic-ben", "Latn", } m["bzz"] = { "Evant", 35259, "nic-tvc", "Latn", } return require("Module:languages").finalizeData(m, "language") 3q19i9kmm0iz5v21y47s3muzthpix92 828 32640 176305 175522 2026-04-13T12:44:01Z Yivan000 4078 176305 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["aaa"] = { "Ghotuo", 35463, "alv-yek", "Latn", } m["aab"] = { "Alumu-Tesu", 35034, "nic-alu", "Latn", } m["aac"] = { "Ari", 1811224, "ngf-gsu", "Latn", } m["aad"] = { "Amal", 56708, "paa-sep", "Latn", } -- "aae" is treated as "sq", see [[WT:LT]] m["aaf"] = { "Aranadan", 3507928, "dra-mal", "Mlym", -- Mlym translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["aag"] = { "Ambrak", 4741706, "paa-pal", "Latn", } m["aah"] = { "Abu'", 4670715, "paa-ara", "Latn", } m["aai"] = { "Arifama-Miniafia", 4790560, "poz-ocw", "Latn", } m["aak"] = { "Ankave", 3446690, "ngf-ata", "Latn", } m["aal"] = { "Afade", 56434, "cdc-cbm", "Latn", } m["aan"] = { "Anambé", 3507873, "tup-gua", "Latn", } m["aap"] = { "Arára (Pará)", 56807, "sai-pek", "Latn", } m["aaq"] = { "Penobscot", 3515185, "alg-abp", "Latn", } m["aas"] = { "Aasax", 56620, "cus-sou", "Latn", } -- "aat" is treated as "sq", see [[WT:LT]] m["aau"] = { "Abau", 3073568, "paa-sep", "Latn", } m["aaw"] = { "Solong", 7558834, "poz-ocw", "Latn", } m["aax"] = { "Upper Mandobo", 12636156, "ngf-dum", "Latn", } m["aaz"] = { "Amarasi", 4740192, "poz-tim", "Latn", } m["aba"] = { "Abé", 34833, "alv-lag", "Latn", } m["abb"] = { "Bankon", 34860, "bnt-bsa", "Latn", } m["abc"] = { "Ayta Ambala", --"Ambala Ayta", 3448896, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/ayta-ambala/", --TLCHANGE english_name = "Ambala Ayta", } m["abd"] = { "Manide", --"Camarines Norte Agta", 3399682, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/manide/", --TLCHANGE english_name = "Camarines Norte Agta", } m["abe"] = { "Abenaki", 17502788, "alg-abp", "Latn", } m["abf"] = { "Abai Sungai", 4663287, "poz-san", "Latn", } m["abg"] = { "Abaga", 3507954, "ngf-kya", "Latn", } m["abh"] = { "Arabe Tajiki", --TLCHANGE 56833, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Tajiki Arabic", --TLCHANGE } m["abi"] = { "Abidji", 34781, "alv-lag", "Latn", } m["abj"] = { "Aka-Bea", 2356391, "qfa-ads", "Latn", } m["abl"] = { "Abung", 49215, "poz-lgx", "Latn", } m["abm"] = { "Abanyom", 7502, "nic-eko", "Latn", } m["abn"] = { "Abua", 34835, "nic-cde", "Latn", } m["abo"] = { "Abon", 35121, "nic-tvn", "Latn", } m["abp"] = { "Abellen", --"Abenlen Ayta" 3436621, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/abellen/", --TLCHANGE english_name = "Abenlen Ayta", --TLCHANGE } m["abq"] = { "Abaza", 27567, "cau-abz", "Cyrl, Latn", translit = { Cyrl = "abq-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 = { "гъв", "гъь", "гӏв", "джв", "джь", "къв", "къь", "кӏв", "кӏь", "хъв", "хӏв", "чӏв", -- 3 chars "гв", "гъ", "гь", "гӏ", "дж", "дз", "ё", "жв", "жь", "кв", "къ", "кь", "кӏ", "ль", "лӏ", "пӏ", "тл", "тш", "тӏ", "фӏ", "хв", "хъ", "хь", "хӏ", "цӏ", "чв", "чӏ", "шв", "шӏ" -- 2 chars }, to = { "г" .. p[3], "г" .. p[4], "г" .. p[7], "д" .. p[2], "д" .. p[3], "к" .. p[3], "к" .. p[4], "к" .. p[7], "к" .. p[8], "х" .. p[3], "х" .. p[6], "ч" .. p[3], "г" .. p[1], "г" .. p[2], "г" .. p[5], "г" .. p[6], "д" .. p[1], "д" .. p[4], "е" .. p[1], "ж" .. p[1], "ж" .. p[2], "к" .. p[1], "к" .. p[2], "к" .. p[5], "к" .. p[6], "л" .. p[1], "л" .. p[2], "п" .. p[1], "т" .. p[1], "т" .. p[2], "т" .. p[3], "ф" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[4], "х" .. p[5], "ц" .. p[1], "ч" .. p[1], "ч" .. p[2], "ш" .. p[1], "ш" .. p[2] } }, }, } -- "abr" Abron is treated as "ak" Akan, see [[WT:LT]] m["abs"] = { "Ambonese Malay", 3124354, "crp", "Latn", ancestors = "ms", } m["abt"] = { "Ambulas", 3508015, "paa-nnd", "Latn", } m["abu"] = { "Abure", 34767, "alv-ptn", "Latn", } m["abv"] = { "Arabe Baharna", --TLCHANGE 56576, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Baharna Arabic", --TLCHANGE } m["abw"] = { "Pal", 7126121, "ngf-omo", "Latn", } m["abx"] = { "Inabaknon", --"Inabaknon", 2820163, "poz-sbj", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/inabaknon/", --TLCHANGE english_name = "Inabaknon", --TLCHANGE } m["aby"] = { "Aneme Wake", 3508107, "ngf-yar", "Latn", } m["abz"] = { "Abui", 2822110, "paa-alp", "Latn", } m["aca"] = { "Achagua", 2822982, "awd", "Latn", } m["acb"] = { "Áncá", 11130787, "nic-mom", "Latn", } m["acd"] = { "Gikyode", 35256, "alv-gng", "Latn", } m["ace"] = { "Atsenes", --TLCHANGE 27683, "cmc", "Latn, ms-Arab", standard_chars = { Latn = "AaBbCcDdEeÉéÈèËëFfGgHhIiJjKkLlMmNnOoÔôÖöPpQqRrSsTtUuVvWwXxYyZz", -- current orthography (not yet add Arab) c.punc }, english_name = "Acehnese", --TLCHANGE english_name = "Achenés", --TLCHANGE } m["ach"] = { "Acholi", 34926, "sdv-los", "Latn", } m["aci"] = { "Aka-Cari", 2670418, "qfa-adn", "Latn", } m["ack"] = { "Aka-Kora", 3433680, "qfa-adn", "Latn", } m["acl"] = { "Akar-Bale", 3436825, "qfa-ads", "Latn", } m["acm"] = { "Arabe Iraqi", --TLCHANGE 56232, "sem-arb", "Arab, Hebr", strip_diacritics = { Arab = "ar-stripdiacritics", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] english_name = "Iraqi Arabic", --TLCHANGE } m["acn"] = { "Achang", 56582, "tbq-brm", "Latn", } m["acp"] = { "Eastern Acipa", 5329945, "nic-kmk", "Latn", } m["acr"] = { "Achi", 34774, "myn", "Latn", } m["acs"] = { "Acroá", 2829146, "sai-cje", "Latn", } m["acu"] = { "Achuar", 2823170, "sai-jiv", "Latn", } m["acv"] = { "Achumawi", 56661, "nai-pal", "Latn", } m["acw"] = { "Arabe Hijazi", --TLCHANGE 56608, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Hijazi Arabic", --TLCHANGE } m["acx"] = { "Arabe Omani", --TLCHANGE 56630, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Omani Arabic", --TLCHANGE } m["acy"] = { "Arabe Tsipriyota", --TLCHANGE 56416, "sem-arb", "Latn, Grek", ancestors = "acm", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.breve}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Latn = "AaBbCcDdΔδEeFfGgĠġĊċIiJjKkLlMmNnOoPpΘθRrSsTtUuVvWwXxYyZzŞş", c.punc }, english_name = "Cypriot Arabic", --TLCHANGE spanish_name = "Árabe chipriota" --TLCHANGE } m["acz"] = { "Acheron", 34769, "alv-tal", "Latn", } m["ada"] = { "Adangme", 35141, "alv-gda", "Latn", } m["adb"] = { "Atauran", 125421255, "poz-cet", "Latn", } m["add"] = { "Dzodinka", 35266, "nic-nka", "Latn", } m["ade"] = { "Adele", 27740, "alv-ntg", "Latn", } m["adf"] = { "Arabe Dhofari", --TLCHANGE 56565, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Dhofari Arabic", --TLCHANGE spanish_name = "Árabe dhofarí" --TLCHANGE } m["adg"] = { "Andegerebinha", 3508123, "aus-rnd", "Latn", } m["adh"] = { "Adhola", 1971400, "sdv-los", "Latn", } m["adi"] = { "Adi", 56440, "sit-tan", "Latn", } m["adj"] = { "Adioukrou", 34738, "alv-lag", "Latn", } m["adl"] = { "Galo", 2857892, "sit-tan", "Latn", } m["adn"] = { "Adang", 3398276, "paa-alp", "Latn", } m["ado"] = { "Abu", 56659, "paa-por", "Latn", } m["adp"] = { "Adap", 3512402, "sit-tib", "Tibt", ancestors = "dz", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["adq"] = { "Adangbe", 34730, "alv-gda", "Latn", ancestors = "ada", } m["adr"] = { "Adonara", 4684505, "poz-cet", "Latn", } m["ads"] = { "Wikang Senyas ng mga Adamorobe", --TLCHANGE 27709, "sgn", "Latn", -- when documented english_name = "Adamorobe Sign Language", --TLCHANGE } m["adt"] = { "Adnyamathanha", 2225391, "aus-psw", "Latn", } m["adu"] = { "Aduge", 34734, "alv-nwd", "Latn", ancestors = "opa", } m["adw"] = { "Amondawa", 12626847, "tup-gua", "Latn", } m["ady"] = { "Adyghe", 27776, "cau-cir", "Cyrl, Latn, Arab", translit = { Cyrl = "cau-cir-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 = { "кхъу", "къӏу", -- 4 chars "гъу", "джу", "дзу", "жъу", "къу", "кхъ", "къӏ", "кӏу", "кӏь", "лъу", "лӏу", "пӏу", "сӏу", "тӏу", "фӏу", "хъу", "цӏу", "чъу", "чӏу", "шъу", "шӏу", "щӏу", -- 3 chars "гу", "гъ", "гь", "дж", "дз", "ё", "жъ", "жь", "ку", "къ", "кь", "кӏ", "лъ", "ль", "лӏ", "пӏ", "сӏ", "тӏ", "фӏ", "ху", "хъ", "хь", "цу", "цӏ", "чу", "чъ", "чӏ", "шъ", "шӏ", "щӏ", "ӏу", "ӏь" -- 2 chars }, to = { "к" .. p[5], "к" .. p[7], "г" .. p[3], "д" .. p[2], "д" .. p[4], "ж" .. p[2], "к" .. p[3], "к" .. p[4], "к" .. p[6], "к" .. p[10], "к" .. p[11], "л" .. p[2], "л" .. p[5], "п" .. p[2], "с" .. p[2], "т" .. p[2], "ф" .. p[2], "х" .. p[3], "ц" .. p[3], "ч" .. p[3], "ч" .. p[5], "ш" .. p[2], "ш" .. p[4], "щ" .. p[2], "г" .. p[1], "г" .. p[2], "г" .. p[4], "д" .. p[1], "д" .. p[3], "е" .. p[1], "ж" .. p[1], "ж" .. p[3], "к" .. p[1], "к" .. p[2], "к" .. p[8], "к" .. p[9], "л" .. p[1], "л" .. p[3], "л" .. p[4], "п" .. p[1], "с" .. p[1], "т" .. p[1], "ф" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[4], "ц" .. p[1], "ц" .. p[2], "ч" .. p[1], "ч" .. p[2], "ч" .. p[4], "ш" .. p[1], "ш" .. p[3], "щ" .. p[1], "ӏ" .. p[1], "ӏ" .. p[2] } }, }, } m["adz"] = { "Adzera", 3327445, "poz-ocw", "Latn", } m["aea"] = { "Areba", 3509129, "aus-pam", "Latn", } m["aeb"] = { "Arabe Tunesino", --TLCHANGE 56240, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Tunisian Arabic", --TLCHANGE spanish_name = "Árabe tunecino" --TLCHANGE } m["aed"] = { "Wikang Senyas ng mga Arhentino", --TLCHANGE 3322073, "sgn", "Latn", -- when documented english_name = "Argentine Sign Language", --TLCHANGE spanish_name = "Lengua de signos argentino", --TLCHANGE } m["aee"] = { "Northeast Pashayi", 12642198, "inc-pas", "fa-Arab, Latn", } m["aek"] = { "Haeke", 5638166, "poz-cln", "Latn", } m["ael"] = { "Ambele", 34818, "nic-grf", "Latn", } m["aem"] = { "Arem", 3507920, "mkh-vie", "Latn", } m["aen"] = { "Wikang Senyas ng mga Armenyo", --TLCHANGE 3446604, "sgn", english_name = "Armenian Sign Language", --TLCHANGE spanish_name = "Lengua de signos armenio", --TLCHANGE } m["aeq"] = { "Aer", 3246741, "inc-wes", "Arab", } m["aer"] = { "Eastern Arrernte", 10728232, "aus-rnd", "Latn", } m["aes"] = { "Alsea", 2395641, nil, "Latn", } m["aeu"] = { "Akeu", 4700657, "tbq-sil", "Latn", } m["aew"] = { "Ambakich", 56642, "paa-eke", "Latn", } m["aey"] = { "Amele", 3508025, "ngf-gum", "Latn", } m["aez"] = { "Aeka", 16110528, "ngf-oro", "Latn", } m["afb"] = { "Arabe Golpo", --TLCHANGE 56385, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Gulf Arabic", --TLCHANGE spanish_name = "Árabe del Golfo" --TLCHANGE } m["afd"] = { "Andai", 4753480, "paa-arf", "Latn", } m["afe"] = { "Putukwam", 3914930, "nic-ben", "Latn", } m["afg"] = { "Wikang Senyas ng mga Afgano", --TLCHANGE 4689093, "sgn", english_name = "Afghan Sign Language", --TLCHANGE spanish_name = "Lengua de signos afgano", --TLCHANGE } m["afh"] = { "Afrihili", 384707, "art", "Latn", type = "appendix-constructed", } m["afi"] = { "Akrukay", 57003, "paa-tam", "Latn", } m["afk"] = { "Nanubae", 6964416, "paa-arf", "Latn", } m["afn"] = { "Defaka", 35174, "nic", "Latn", } m["afo"] = { "Eloyi", 3914066, "nic-plt", "Latn", } m["afp"] = { "Tapei", 16887371, "paa-arf", "Latn", } m["afs"] = { "Afro-Seminole Creole", 27867, "crp", "Latn", ancestors = "en", } m["aft"] = { "Afitti", 3400829, "sdv-nyi", "Latn", } m["afu"] = { "Awutu", 34847, "alv-gng", "Latn", } m["afz"] = { "Obokuitai", 7075258, "paa-clp", "Latn", } m["aga"] = { "Aguano", 3331203, nil, "Latn", } m["agb"] = { "Legbo", 35584, "nic-uce", "Latn", } m["agc"] = { "Agatu", 34732, "alv-ido", "Latn", } m["agd"] = { "Agarabi", 3399642, "ngf-gau", "Latn", } m["age"] = { "Angal", 10951553, "ngf-ank", "Latn", } m["agf"] = { "Arguni", 12473346, "poz-cet", "Latn", } m["agg"] = { "Angor", 3508100, "paa-sng", "Latn", } m["agh"] = { "Ngelima", 7022266, "bnt-bta", "Latn", } m["agi"] = { "Agariya", 663586, "mun", "Deva", } m["agj"] = { "Argobba", 29292, "sem-eth", "Ethi", } m["agk"] = { "Agta Isarog", --"Isarog Agta", 6078982, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/agta-isarog/", --TLCHANGE english_name = "Isarog Agta", --TLCHANGE } m["agl"] = { "Fembe", 372927, "ngf-est", "Latn", } m["agm"] = { "Angaataha", 3508001, "ngf-ang", "Latn", } m["agn"] = { "Agutaynën", --"Agutaynen", 3399717, "phi-kal", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/agutaynen/", --TLCHANGE english_name = "Agutaynen", } m["ago"] = { "Tainae", 7676186, "ngf-taa", "Latn", } m["agq"] = { "Aghem", 34737, "nic-rnw", "Latn", } m["agr"] = { "Aguaruna", 1526530, "sai-jiv", "Latn", } m["ags"] = { "Esimbi", 35260, "nic-bds", "Latn", } m["agt"] = { "Pannon", --"Central Cagayan Agta", 5017296, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/pannon/", --TLCHANGE english_name = "Central Cagayan Agta", --TLCHANGE } m["agu"] = { "Aguacateca", 35091, "myn", "Latn", } m["agv"] = { "Hatang Kaye", --"Remontado Agta", 3508085, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/hatang-kaye/", --TLCHANGE english_name = "Remontado Agta", --TLCHANGE } m["agw"] = { "Kahua", 3191906, "poz-sls", "Latn", } m["agx"] = { "Aghul", 36498, "cau-esm", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = s["cau-Cyrl-displaytext"], strip_diacritics = s["cau-Cyrl-stripdiacritics"], sort_key = { from = {"аь", "гъ", "гь", "гӏ", "дж", "ё", "къ", "кь", "кӏ", "оь", "пӏ", "тӏ", "уь", "хъ", "хь", "хӏ", "цӏ", "чӏ"}, to = {"а" .. p[1], "г" .. p[1], "г" .. p[2], "г" .. p[3], "д" .. 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], "х" .. p[3], "ц" .. p[1], "ч" .. p[1]} }, } m["agy"] = { "Kabulowan", --"Southern Alta", 7569611, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/kabulowan/", --TLCHANGE english_name = "Southern Alta", --TLCHANGE } m["agz"] = { "Agta Iriga", --"Mount Iriga Agta", 6921432, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/agta-iriga/", --TLCHANGE english_name = "Mount Iriga Agta", --TLCHANGE } m["aha"] = { "Ahanta", 34729, "alv-ctn", "Latn", } m["ahb"] = { "Axamb", 2874710, "poz-vnc", "Latn", } m["ahg"] = { "Qimant", 35663, "cus-cen", "Latn", } m["ahh"] = { "Aghu", 3436645, "ngf-awy", "Latn", } m["ahi"] = { "Tiagba", 3400073, "kro-aiz", "Latn", } m["ahk"] = { "Akha", 56643, "tbq-han", "Latn, Mymr, Thai", sort_key = { Thai = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"} }, }, } m["ahl"] = { "Igo", 35412, "alv-ktg", "Latn", } m["ahm"] = { "Mobu", 35967, "kro-aiz", "Latn", } m["ahn"] = { "Àhàn", 34723, "alv-aah", "Latn", } m["aho"] = { "Ahom", 34778, "tai-swe", "Ahom", translit = "Ahom-translit", } m["ahp"] = { "Apro", 34810, "alv-kwa", "Latn", } m["ahr"] = { "Ahirani", 15549890, "raj", "Deva", translit = "mr-translit", } m["ahs"] = { "Ashe", 34823, "nic-plc", "Latn", } m["aht"] = { "Ahtna", 21058, "ath-nor", "Latn", } m["aia"] = { "Arosi", 2863483, "poz-sls", "Latn", } m["aib"] = { "Äynu", 27927, "qfa-mix", "Arab, Latn", ancestors = "ug, fa" } m["aic"] = { "Ainbai", 3332149, "paa-bew", "Latn", } m["aid"] = { "Alngith", 3279409, "aus-pmn", "Latn", } m["aie"] = { "Amara", 2841180, "poz-ocw", "Latn", } m["aif"] = { "Agi", 3331491, "paa-wpa", "Latn", } m["aig"] = { "Antigua and Barbuda Creole English", 3244184, "crp", "Latn", ancestors = "en", } m["aih"] = { "Ai-Cham", 2827749, "qfa-kms", "Latn, Hani", sort_key = { Hani = "Hani-sortkey" }, } m["aii"] = { "Assyrian Neo-Aramaic", 29440, "sem-nna", "Syrc", translit = "aii-translit", strip_diacritics = "Syrc-stripdiacritics", } m["aij"] = { "Lishanid Noshan", 3436467, "sem-nna", "Hebr", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["aik"] = { "Ake", 34808, "nic-pls", "Latn", } m["ail"] = { "Aimele", 3327418, "ngf-bos", "Latn", } m["aim"] = { "Aimol", 4697175, "tbq-kuk", "Latn, Beng", } m["ain"] = { "Ainu", 27969, "qfa-ain", "Kana, Latn, Cyrl", sort_key = { Kana = "Kana-sortkey" }, } m["aio"] = { "Aiton", 3399725, "tai-swe", "Mymr", translit = "aio-phk-translit", display_text = s["aio-displaytext"], strip_diacritics = s["aio-stripdiacritics"], } m["aip"] = { "Burumakok", 5000984, "ngf-wok", "Latn", } m["air"] = { "Airoran", 3321131, "paa-saa", "Latn", } m["ait"] = { "Arikem", 3446679, "tup", "Latn", } m["aiw"] = { "Aari", 7495, "omv-aro", "Latn", } m["aix"] = { "Aighon", 3504287, "poz-ocw", "Latn", } m["aiy"] = { "Ali", 34814, "gba-eas", "Latn", } m["aja"] = { "Aja (East Africa)", 3237491, "csu-bkr", "Latn", } m["ajg"] = { "Aja (West Africa)", 35035, "alv-gbe", "Latn", } m["aji"] = { "Ajië", 2828867, "poz-cln", "Latn", } m["ajn"] = { "Andajin", 16111302, "aus-wor", "Latn", } m["ajp"] = { "Arabe Timog Levantino", --TLCHANGE 55633582, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "South Levantine Arabic", --TLCHANGE spanish_name = "Árabe levantino del sur" --TLCHANGE } m["ajw"] = { "Ajawa", 56645, "cdc-wst", "Latn", } m["ajz"] = { "Amri Karbi", 3508092, "tbq-kuk", "Latn", ancestors = "mjw", } m["akb"] = { "Angkola Batak", 2640686, "btk", "Latn, Batk", } m["akc"] = { "Mpur", 3327139, "qfa-iso", -- Papuan; based on Palmer (2018), Ethnologue and Glottolog "Latn", } m["akd"] = { "Ukpet-Ehom", 36618, "nic-ucr", "Latn", } m["ake"] = { "Akawaio", 28059, "sai-pem", "Latn", } m["akf"] = { "Akpa", 34801, "alv-ido", "Latn", } m["akg"] = { "Anakalangu", 4750964, "poz-cet", "Latn", } m["akh"] = { "Angal Heneng", 10950354, "ngf-ank", "Latn", } m["aki"] = { "Aiome", 56735, "paa-aia", "Latn", } m["akj"] = { "Jeru", 2919121, "qfa-adn", "Latn, Deva", } m["akk"] = { "Akadyo", --TLCHANGE 35518, "sem-eas", "Xsux, Latn", english_name = "Akkadian", --TLCHANGE spanish_name = "Acadio", --TLCHANGE } m["akl"] = { "Aklanon", --"Aklanon", 8773, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/aklanon/", --TLCHANGE english_name = "Aklanon", --TLCHANGE } m["akm"] = { "Aka-Bo", 35361, "qfa-adn", "Latn", } m["ako"] = { "Akurio", 56650, "sai-tar", "Latn", } m["akp"] = { "Siwu", 36470, "alv-ntg", "Latn", } m["akq"] = { "Ak", 56654, "paa-sep", "Latn", } m["akr"] = { "Araki", 2699882, "poz-vnn", "Latn", } m["aks"] = { "Akaselem", 34817, "nic-grm", "Latn", } m["akt"] = { "Akolet", 3330162, "poz-ocw", "Latn", } m["aku"] = { "Akum", 34799, "nic-ykb", "Latn", } m["akv"] = { "Akhvakh", 56423, "cau-and", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = s["cau-Cyrl-displaytext"], strip_diacritics = s["cau-Cyrl-stripdiacritics"], } m["akw"] = { "Akwa", 34802, "bnt-mbo", "Latn", } m["akx"] = { "Aka-Kede", 3436816, "qfa-adc", "Latn", } m["aky"] = { "Aka-Kol", 3436784, "qfa-adc", "Latn", } m["akz"] = { "Alabama", 1815020, "nai-mus", "Latn", } m["ala"] = { "Alago", 34813, "alv-ido", "Latn", } m["alc"] = { "Kawésqar", 56544, "aqa", "Latn", } m["ald"] = { "Alladian", 34837, "alv-lag", "Latn", } m["ale"] = { "Aleut", 27210, "esx", "Latn, Cyrl", } m["alf"] = { "Alege", 34815, "nic-ben", "Latn", } m["alh"] = { "Alawa", 2147917, "aus-gun", "Latn", } m["ali"] = { "Amaimon", 3327427, "ngf-mad", "Latn", } m["alj"] = { "Alangan Mangyan", --"Alangan", 3327423, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/alangan-mangyan/", --TLCHANGE english_name = "Alangan", --TLCHANGE } m["alk"] = { "Alak", 2714690, "mkh", "Latn", } m["all"] = { "Allar", 3393634, "dra-mal", "Mlym", -- Mlym translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } -- "aln" is treated as "sq", see [[WT:LT]] m["alm"] = { "Amblong", 11022615, "poz-vnn", "Latn", } m["alo"] = { "Larike-Wakasihu", 3217929, "poz-cma", "Latn", } m["alp"] = { "Alune", 3327367, "poz-cet", "Latn", } m["alq"] = { "Algonquin", 28092, "alg", "Latn, Cans", ancestors = "oj", } m["alr"] = { "Alutor", 28213, "qfa-ckn", "Cyrl", strip_diacritics = { from = {"['’]"}, to = {"ʼ"} }, sort_key = { from = {"вʼ", "гʼ", "ғ", "ә", "ё", "ӄ", "ӈ"}, to = {"в" .. p[1], "г" .. p[1], "г" .. p[2], "е" .. p[1], "е" .. p[2], "к" .. p[1], "н" .. p[1]} }, } m["alt"] = { "Southern Altai", 1991779, "trk-kkp", "Cyrl", translit = "Altai-translit", sort_key = { from = {"ј", "ё", "ҥ", "ӧ", "ӱ"}, to = {"д" .. p[1], "е" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]} }, } m["alu"] = { "'Are'are", 5160, "poz-sls", "Latn", } m["alw"] = { "Alaba", 56652, "cus-hec", "Latn", } m["alx"] = { "Amol", 3504260, "paa-pal", "Latn", } m["aly"] = { "Alyawarr", 3327389, "aus-rnd", "Latn", } m["alz"] = { "Alur", 56507, "sdv-los", "Latn", } m["ama"] = { "Amanayé", 3508053, "tup-gua", "Latn", } m["amb"] = { "Ambo", 3450142, "nic-tvn", "Latn", } m["amc"] = { "Amahuaca", 2669150, "sai-pan", "Latn", } m["ame"] = { "Yanesha'", 3088540, "awd", "Latn", } m["amf"] = { "Hamer-Banna", 35764, "omv-aro", "Latn, Ethi", sort_key = "amf-utilities" } m["amg"] = { "Amurdag", 3360016, "aus-wdj", "Latn", } m["ami"] = { "Amis", 35132, "map", "Latn", } m["amj"] = { "Amdang", 28335, "ssa-fur", "Latn", } m["amk"] = { "Ambai", 1875885, "poz-hce", "Latn", } m["aml"] = { "War-Jaintia", 56321, "aav-khs", "Latn", } m["amm"] = { "Ama", 3446626, "paa-lma", "Latn", } m["amn"] = { "Amanab", 3327399, "paa-war", "Latn", } m["amo"] = { "Amo", 34826, "nic-kne", "Latn", } m["amp"] = { "Alamblak", 56688, "paa-sep", "Latn", } m["amq"] = { "Amahai", 3327384, "poz-cma", "Latn", } m["amr"] = { "Amarakaeri", 35128, "sai-har", "Latn", } m["ams"] = { "Southern Amami Ōshima", 2840986, "jpx-nry", "Jpan", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["amt"] = { "Amto", 56517, "paa-amu", "Latn", } m["amu"] = { "Guerrero Amuzgo", 3501942, "omq", "Latn", } m["amv"] = { "Ambelau", 2669214, "poz-cma", "Latn", } m["amw"] = { "Western Neo-Aramaic", 34226, "sem-arw", "Armi, Syrc, Latn", strip_diacritics = { Syrc = "Syrc-stripdiacritics" }, } m["amx"] = { "Anmatyerre", 10412317, "aus-rnd", "Latn", } m["amy"] = { "Ami", 10408315, "aus-dal", "Latn", } m["amz"] = { "Atampaya", 3446651, "aus-pam", "Latn", } m["ana"] = { "Andaqui", 2846078, nil, "Latn", } m["anb"] = { "Andoa", 2846171, "sai-zap", "Latn", } m["anc"] = { "Ngas", 35999, "cdc-wst", "Latn", } m["and"] = { "Ansus", 3513300, "poz-hce", "Latn", } m["ane"] = { "Xârâcùù", 3571097, "poz-cln", "Latn", } m["anf"] = { "Animere", 34783, "alv-ktg", "Latn", } m["ang"] = { "Old English", 42365, "gmw-ang", "Latn, Runr", translit = { Runr = "Runr-translit" }, strip_diacritics = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron .. c.breve .. c.dotabove .. c.diaer .. c.dotbelow, from = {"[Ƿƿ]"}, to = {{ ["Ƿ"] = "W", ["ƿ"] = "w", }}, }, }, sort_key = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron .. c.breve .. c.dotabove .. c.diaer .. c.dotbelow, from = {"[æƀꝺðꝼᵹȝłœꞃꞅꞇþꝥꝧƿ]"}, to = {{ ["æ"] = "ae", ["ƀ"] = "b", ["ꝺ"] = "d", ["ð"] = "d" .. p[1], ["ꝼ"] = "f", ["ᵹ"] = "g", ["ȝ"] = "g" .. p[1], ["ł"] = "l", ["œ"] = "oe", ["ꞃ"] = "r", ["ꞅ"] = "s", ["ꞇ"] = "t", ["þ"] = "t" .. p[1], ["ꝥ"] = "t" .. p[1], ["ꝧ"] = "t" .. p[1], ["ƿ"] = "w", }}, }, }, standard_chars = { Latn = "AaÆæBbCcDdÐðEeFfGgHhIiLlMmNnOoŒœPpRrSsTtÞþUuWwXxYy", c.punc, }, } m["anh"] = { "Nend", 6991554, "ngf-wso", "Latn", } m["ani"] = { "Andi", 34849, "cau-and", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = s["cau-Cyrl-displaytext"], strip_diacritics = s["cau-Cyrl-stripdiacritics"], } m["anj"] = { "Anor", 56458, "paa-aia", "Latn", } m["ank"] = { "Goemai", 35272, "cdc-wst", "Latn", } m["anl"] = { "Anu", 4777679, "sit-mru", "Latn", } m["anm"] = { "Anāl", 56235, "tbq-kuk", "Latn", } m["ann"] = { "Obolo", 36614, "nic-lcr", "Latn", } m["ano"] = { "Andoque", 2669225, "qfa-iso", "Latn", } m["anp"] = { "Angika", 28378, "inc-bih", "Deva, Kthi", translit = { Deva = "hi-translit", Kthi = "bho-Kthi-translit", }, } m["anq"] = { "Jarawa", 2475526, "qfa-ong", "Latn", } m["anr"] = { "Andh", 4754314, "inc-sou", "Deva", } m["ans"] = { "Anserma", 3446613, "sai-chc", "Latn", } m["ant"] = { "Antakarinya", 921304, "aus-psw", "Latn", } m["anu"] = { "Anuak", 56677, "sdv-lon", "Latn", } m["anv"] = { "Denya", 35187, "nic-mam", "Latn", } m["anw"] = { "Anaang", 2845320, "nic-ief", "Latn", } m["anx"] = { "Andra-Hus", 2846195, "poz-aay", "Latn", } m["any"] = { "Anyi", 28395, "alv-ctn", "Latn", } m["anz"] = { "Anem", 56512, "qfa-dis", -- Papuan; might be an isolate or in a putative West New Britain family "Latn", } m["aoa"] = { "Angolar", 34994, "crp", "Latn", ancestors = "pt", } m["aob"] = { "Abom", 3446647, "qfa-dis", -- Papuan; possibly a divergent Tirio language (Anim family), or a top-level TNG node "Latn", } m["aoc"] = { "Pemon", 10729616, "sai-pem", "Latn", } m["aod"] = { "Andarum", 3507888, "paa-ata", "Latn", } m["aoe"] = { "Angal Enen", 10951638, "ngf-ank", "Latn", } m["aof"] = { "Bragat", 3507977, "paa-pal", "Latn", } m["aog"] = { "Angoram", 56366, -- cf 6754745 for merged dialect "paa-lse", "Latn", } m["aoi"] = { "Anindilyakwa", 2714654, "aus-arn", "Latn", } m["aoj"] = { "Mufian", 3507881, "paa-ara", "Latn", } m["aok"] = { "Arhö", 4790086, "poz-cln", "Latn", } m["aol"] = { "Alorese", 3332062, "poz", "Latn", } m["aom"] = { "Ömie", 8078975, "ngf-koi", "Latn", } m["aon"] = { "Bumbita Arapesh", 3508044, "paa-ara", "Latn", } m["aor"] = { "Aore", 12627129, "poz-vnn", "Latn", } m["aos"] = { "Taikat", 7676018, "paa-taa", "Latn", } m["aot"] = { "Atong (India)", 5646, "tbq-bdg", "Latn, Beng", } m["aou"] = { "A'ou", 16109994, "gio", "Latn", -- also Hani? } m["aox"] = { "Atorada", 3507932, "awd", "Latn", } m["aoz"] = { "Uab Meto", 3441962, "poz-tim", "Latn", } m["apb"] = { "Sa'a", 36294, "poz-sls", "Latn", } m["apc"] = { "Arabe Hilagang Levantino", --TLCHANGE 22809485, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "North Levantine Arabic", --TLCHANGE spanish_name = "Árabe levantino del norte" --TLCHANGE } m["apd"] = { "Arabe Sudanes", --TLCHANGE 56573, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Sudanese Arabic", --TLCHANGE spanish_name = "Árabe sudanés" --TLCHANGE } m["ape"] = { "Bukiyip", 3507895, "paa-ara", "Latn", } m["apf"] = { "Pahanan Agta", --"Pahanan Agta" 7135432, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/pahanan-agta/", --TLCHANGE english_name = "Pahanan Agta" --TLCHANGE } m["apg"] = { "Ampanang", 4748035, "poz", "Latn", } m["aph"] = { "Athpare", 3449126, "sit-kie", "Deva, Latn", } m["api"] = { "Apiaká", 3507941, "tup-gua", "Latn", } m["apj"] = { "Jicarilla", 28277, "apa", "Latn", } m["apk"] = { "Plains Apache", 27861, "apa", "Latn", } m["apl"] = { "Lipan", 28269, "apa", "Latn", } m["apm"] = { "Chiricahua", 13368, "apa", "Latn", } m["apn"] = { "Apinayé", 2858311, "sai-nje", "Latn", } m["apo"] = { "Ambul", 12627135, "poz-ocw", "Latn", } m["app"] = { "Apma", 2669188, "poz-vnn", "Latn", } m["apq"] = { "A-Pucikwar", 28466, "qfa-adc", "Latn", } m["apr"] = { "Arop-Lokep", 2863482, "poz-ocw", "Latn", } m["aps"] = { "Arop-Sissano", 12627242, "poz-ocw", "Latn", } m["apt"] = { "Apatani", 56306, "sit-tan", "Latn", } m["apu"] = { "Apurinã", 2859081, "awd", "Latn", } m["apv"] = { "Alapmunte", 16110782, "sai-nmk", "Latn", } m["apw"] = { "Western Apache", 28060, "apa", "Latn", } m["apx"] = { "Aputai", 12473343, "poz-tim", "Latn", } m["apy"] = { "Apalaí", 2736980, "sai-gui", "Latn", } m["apz"] = { "Safeyoka", 7398693, "ngf-woj", "Latn", } m["aqc"] = { "Archi", 34915, "cau-lzg", "Cyrl", translit = "cau-nec-translit", override_translit = true, display_text = s["cau-Cyrl-displaytext"], strip_diacritics = s["cau-Cyrl-stripdiacritics"], sort_key = { from = { "ккъӏв", "ххьӏв", -- 5 chars "гъӏв", "ёоӏ", "ккъӏ", "ккъв", "къӏв", "ллъв", "ххьӏ", "хъӏв", "хьӏв", "ццӏв", "ччӏв", -- 4 chars "ааӏ", "гӏв", "гъӏ", "гъв", "гьв", "ееӏ", "ёӏ", "ёо", "ииӏ", "кӏв", "ккв", "ккъ", "къӏ", "къв", "кьв", "лӏв", "ллъ", "лъв", "льв", "ооӏ", "пӏв", "ппв", "ссв", "тӏв", "ттв", "ууӏ", "хӏв", "ххв", "хъӏ", "хъв", "хьӏ", "цӏв", "ццӏ", "ццв", "чӏв", "ччӏ", "ээӏ", "юуӏ", "яаӏ", -- 3 chars "аӏ", "аа", "гӏ", "гв", "гъ", "гь", "дв", "еӏ", "ее", "ё", "жв", "зв", "иӏ", "ии", "кӏ", "кв", "кк", "къ", "кь", "лӏ", "лв", "лъ", "ль", "оӏ", "оо", "пӏ", "пв", "пп", "св", "сс", "тӏ", "тв", "тт", "уӏ", "уу", "фв", "хӏ", "хв", "хх", "хъ", "цӏ", "цв", "цц", "чӏ", "чв", "шв", "щв", "эӏ", "ээ", "юӏ", "юу", "яӏ", "яа" -- 2 chars }, to = { "к" .. p[8], "х" .. p[7], "г" .. p[6], "е" .. p[7], "к" .. p[7], "к" .. p[9], "к" .. p[12], "л" .. p[5], "х" .. p[6], "х" .. p[10], "х" .. p[13], "ц" .. p[6], "ч" .. p[5], "а" .. p[3], "г" .. p[2], "г" .. p[5], "г" .. p[7], "г" .. p[9], "е" .. p[3], "е" .. p[5], "е" .. p[6], "и" .. p[3], "к" .. p[2], "к" .. p[5], "к" .. p[6], "к" .. p[11], "к" .. p[13], "к" .. p[15], "л" .. p[2], "л" .. p[4], "л" .. p[7], "л" .. p[9], "о" .. p[3], "п" .. p[2], "п" .. p[5], "с" .. p[3], "т" .. p[2], "т" .. p[5], "у" .. p[3], "х" .. p[2], "х" .. p[5], "х" .. p[9], "х" .. p[11], "х" .. p[12], "ц" .. p[2], "ц" .. p[5], "ц" .. p[7], "ч" .. p[2], "ч" .. p[4], "э" .. p[3], "ю" .. p[3], "я" .. p[3], "а" .. p[1], "а" .. p[2], "г" .. p[1], "г" .. p[3], "г" .. p[4], "г" .. p[8], "д" .. p[1], "е" .. p[1], "е" .. p[2], "е" .. p[4], "ж" .. p[1], "з" .. p[1], "и" .. p[1], "и" .. p[2], "к" .. p[1], "к" .. p[3], "к" .. p[4], "к" .. p[10], "к" .. p[14], "л" .. p[1], "л" .. p[3], "л" .. p[6], "л" .. p[8], "о" .. p[1], "о" .. p[2], "п" .. p[1], "п" .. p[3], "п" .. p[4], "с" .. p[1], "с" .. p[2], "т" .. p[1], "т" .. p[3], "т" .. p[4], "у" .. p[1], "у" .. p[2], "ф" .. p[1], "х" .. p[1], "х" .. p[3], "х" .. p[4], "х" .. p[8], "ц" .. p[1], "ц" .. p[3], "ц" .. p[4], "ч" .. p[1], "ч" .. p[3], "ш" .. p[1], "щ" .. p[1], "э" .. p[1], "э" .. p[2], "ю" .. p[1], "ю" .. p[2], "я" .. p[1], "я" .. p[2] } }, } m["aqd"] = { "Ampari Dogon", 4748057, "nic-dgw", "Latn", } m["aqg"] = { "Arigidi", 34829, "alv-von", "Latn", } m["aqm"] = { "Atohwaim", 11732297, "paa-kay", "Latn", } m["aqn"] = { "Alta", --TLCHANGE 7058116, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/alta/", --TLCHANGE english_name = "Northern Alta", --TLCHANGE } m["aqp"] = { "Atakapa", 10975683, "qfa-iso", "Latn", } m["aqr"] = { "Arhâ", 4790085, "poz-cln", "Latn", } m["aqt"] = { "Angaité", 15736037, "sai-mas", "Latn", } m["aqz"] = { "Akuntsu", 4701960, "tup", "Latn", } m["arc"] = { "Arameas", --TLCHANGE 28602, "sem-ara", "Hebr, Armi, Syrc, Palm, Nbat, Phnx, Mand, Samr, Hatr, Elym", translit = { Armi = "Armi-translit", Palm = "Palm-translit", }, strip_diacritics = { -- The first three were added by [[User:Wikitiki89]] in 2015 for use with Syriac, which has diacritics that look -- like a diaeresis (syāmē) and macrons above and below (mṭalqānā); see Wikipedia [[w:Syriac alphabet]]. But -- I don't know if they are actually represented using these diacritics. Syrc = {remove_diacritics = c.macron .. c.diaer .. c.macronbelow .. u(0x0730) .. "-" .. u(0x0748)}, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- Samr strip_diacritics, sort_key in [[Module:scripts/data]]; previously no sort_key for Samr, presumably a mistake -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) english_name = "Aramaic", --TLCHANGE spanish_name = "Arameas", --TLCHANGE } m["ard"] = { "Arabana", 3507959, "aus-kar", "Latn", } m["are"] = { "Western Arrernte", 12645549, "aus-rnd", "Latn", } m["arh"] = { "Arhuaco", 2640621, "cba", "Latn", } m["ari"] = { "Arikara", 56539, "cdd", "Latn", strip_diacritics = {remove_diacritics = c.acute}, } m["arj"] = { "Arapaso", 9627356, "sai-tuc", "Latn", } m["ark"] = { "Arikapú", 3446640, "sai-mje", "Latn", } m["arl"] = { "Arabela", 2591221, "sai-zap", "Latn", } m["arn"] = { "Mapudungun", 33730, "sai-ara", "Latn", } m["aro"] = { "Araona", 958414, "sai-tac", "Latn", } m["arp"] = { "Arapaho", 56417, "alg-ara", "Latn", } m["arq"] = { "Arabe Arhelino", --TLCHANGE 56499, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Algerian Arabic", --TLCHANGE spanish_name = "Árabe argelino" --TLCHANGE } m["arr"] = { "Arara-Karo", 35539, "tup", "Latn", } m["ars"] = { "Arabe Neyedi", --TLCHANGE 56574, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Najdi Arabic", --TLCHANGE spanish_name = "Árabe neyedí" --TLCHANGE } m["aru"] = { "Arua", 2746221, "auf", "Latn", } m["arv"] = { "Arbore", 56883, "cus-eas", "Latn", } m["arw"] = { "Lokono", 2655664, "awd-taa", "Latn", } m["arx"] = { "Aruá", 3507907, "tup", "Latn", } m["ary"] = { "Arabe Maroki", --TLCHANGE 56426, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Moroccan Arabic", --TLCHANGE spanish_name = "Árabe marroquí" --TLCHANGE } m["arz"] = { "Arabe Ehipsiyo", --TLCHANGE 29919, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Egyptian Arabic", --TLCHANGE spanish_name = "Árabe egipcio" --TLCHANGE } m["asa"] = { "Pare", 36403, "bnt-par", "Latn", } m["asb"] = { "Assiniboine", 2591288, "sio-dkt", "Latn", } m["asc"] = { "Casuarina Coast Asmat", 11732046, "ngf-asm", "Latn", } m["ase"] = { "Wikang Senyas ng mga Amerikano", --TLCHANGE 14759, "sgn", "Sgnw", english_name = "American Sign Language", --TLCHANGE spanish_name = "Lengua de signos americano", --TLCHANGE } m["asf"] = { "Auslan", 29525, "sgn", "Latn", -- when documented } m["asg"] = { "Cishingini", 35199, "nic-kam", "Latn", } m["ash"] = { "Abishira", 2871740, "qfa-dis", -- extinct, poorly documented; isolate or in a proposed Tequiraca-Canichana family by Kaufman (1994) "Latn", } m["asi"] = { "Buruwai", 5001031, "ngf-sab", "Latn", } m["asj"] = { "Nsari", 36418, "nic-bbe", "Latn", } m["ask"] = { "Ashkun", 29379, "nur-sou", "Arab, Latn", } m["asl"] = { "Asilulu", 12473347, "poz-cma", "Latn", } m["asn"] = { "Xingú Asuriní", 8044571, "tup-gua", "Latn", } m["aso"] = { "Dano", 5220979, "ngf-gah", "Latn", } m["asp"] = { "Wikang Senyas ng mga Arhelino", --TLCHANGE 3135421, "sgn", english_name = "Algerian Sign Language", --TLCHANGE spanish_name = "Lengua de signos argelino", --TLCHANGE } m["asq"] = { "Wikang Senyas ng mga Awstriyako", --TLCHANGE 36668, "sgn", "Latn", -- when documented english_name = "Austrian Sign Language", --TLCHANGE spanish_name = "Lengua de signos austriaco", --TLCHANGE } m["asr"] = { "Asuri", 3504321, "mun", "Latn", -- when documented } m["ass"] = { "Ipulo", 35408, "nic-tvc", "Latn", } m["ast"] = { "Asturyano", --TLCHANGE 29507, "roa-asl", "Latn", english_name = "Asturian", --TLCHANGE spanish_name = "Asturiano", --TLCHANGE } m["asu"] = { "Tocantins Asurini", 32041490, "tup-gua", "Latn", } m["asv"] = { "Asoa", 56296, "csu-maa", "Latn", } m["asw"] = { "Wikang Senyas ng mga Katutubong Awstralyano", --TLCHANGE 955216, "sgn", "Latn", -- when documented english_name = "Australian Aboriginal Sign Language", --TLCHANGE spanish_name = "Lengua de signos aborigen australiano", --TLCHANGE } m["asx"] = { "Muratayak", 11732766, "ngf-war", "Latn", } m["asy"] = { "Yaosakor Asmat", 16113158, "ngf-asm", "Latn", } m["asz"] = { "As", 2866218, "poz-hce", "Latn", } m["ata"] = { "Pele-Ata", 56511, "qfa-dis", -- Papuan; possibly in a putative West New Britain family, or an isolate "Latn", } m["atb"] = { "Zaiwa", 56594, "tbq-brm", "Latn, Lisu", -- also Hani? -- Lisu translit, sort_key in [[Module:scripts/data]] } m["atc"] = { "Atsahuaca", 4817730, "sai-pan", "Latn", } m["atd"] = { "Manobo Ata", --"Ata Manobo", 12627315, "mno", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/manobo-ata/", --TLCHANGE english_name = "Ata Manobo", --TLCHANGE } m["ate"] = { "Atemble", 4813055, "ngf-wso", "Latn", } m["atg"] = { "Okpela", 7082551, "alv-yek", "Latn", } m["ati"] = { "Attié", 34844, "alv-lag", "Latn", } m["atj"] = { "Atikamekw", 56590, "alg", "Latn", ancestors = "cr", } m["atk"] = { "Inete", --"Ati", 3217458, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/inete/", --TLCHANGE english_name = "Ati", --TLCHANGE } m["atl"] = { "Agta Iraya", --"Mount Iraya Agta", 6921430, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/agta-iraya/", --TLCHANGE english_name = "Mount Iraya Agta", --TLCHANGE } m["atm"] = { "Inata", --"Ata", 4812603, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/inata/", --TLCHANGE english_name = "Ata", --TLCHANGE } m["ato"] = { "Atong (Cameroon)", 34824, "nic-grs", "Latn", } m["atp"] = { "Atta Pudtol", --"Pudtol Atta", 12640726, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/atta/", --TLCHANGE english_name = "Pudtol Atta", --TLCHANGE } m["atq"] = { "Aralle-Tabulahan", 4783889, "poz-ssw", "Latn", } m["atr"] = { "Waimiri-Atroari", 56865, "sai-car", "Latn", } m["ats"] = { "Gros Ventre", 56628, "alg-ara", "Latn", } m["att"] = { "Atta Pamplona", --TLCHANGE 12639245, "phi", "Latn", english_name = "Pamplona Atta", --TLCHANGE } m["atu"] = { "Reel", 7306882, "sdv-dnu", "Latn", } m["atv"] = { "Northern Altai", 2640863, "trk-ssb", "Cyrl", translit = "Altai-translit", } m["atw"] = { "Atsugewi", 56718, "nai-pal", "Latn", } m["atx"] = { "Arutani", 56609, nil, "Latn", } m["aty"] = { "Aneityum", 2379113, "poz-vns", "Latn", } m["atz"] = { "Arta", --"Arta", 3508067, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/arta/", --TLCHANGE english_name = "Arta", --TLCHANGE } m["aua"] = { "Asumboa", 4811870, "poz-tem", "Latn", } m["aub"] = { "Alugu", 12626798, "tbq-urp", "Latn", -- also Hani? } m["auc"] = { "Huaorani", 758570, "qfa-iso", "Latn", } m["aud"] = { "Anuta", 35326, "poz-pnp", "Latn", } m["aug"] = { "Aguna", 34733, "alv-gbe", "Latn", } m["auh"] = { "Aushi", 2872082, "bnt-sbi", "Latn", } m["aui"] = { "Anuki", 3508132, "poz-ocw", "Latn", } m["auj"] = { "Awjila", 56398, "ber", "Latn, Arab, Tfng", } m["auk"] = { "Heyo", 3504295, "paa-hya", "Latn", } m["aul"] = { "Aulua", 427300, "poz-vnc", "Latn", } m["aum"] = { "Asu", 34798, "alv-ngb", "Latn", } m["aun"] = { "Molmo One", 12637224, "paa-trr", "Latn", } m["auo"] = { "Auyokawa", 56247, "cdc-wst", "Latn", } m["aup"] = { "Makayam", 6738863, "paa-tir", "Latn", } m["auq"] = { "Anus", 23855, "poz-ocw", "Latn", } m["aur"] = { "Aruek", 3504279, "paa-kom", "Latn", } m["aut"] = { "Austral", 2669261, "poz-pep", "Latn", } m["auu"] = { "Auye", 4827334, "ngf-pan", "Latn", } m["auw"] = { "Awyi", 3513326, "paa-taa", "Latn", } m["aux"] = { "Aurá", 3507995, "tup-gua", "Latn", } m["auy"] = { "Auyana", 2873211, "ngf-gau", "Latn", } m["auz"] = { "Arabe Uzbeki", --TLCHANGE 3399507, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Uzbeki Arabic", --TLCHANGE, } m["avb"] = { "Avau", 12627412, "poz-ocw", "Latn", } m["avd"] = { "Alviri-Vidari", 3327357, "xme", "fa-Arab", ancestors = "xme-mid", } m["avi"] = { "Avikam", 34840, "alv-lag", "Latn", } m["avk"] = { "Kotava", 1377116, "art", "Latn", type = "appendix-constructed", } m["avm"] = { "Angkamuthi", 62603022, "aus-pmn", "Latn", } m["avn"] = { "Avatime", 34796, "alv-ktg", "Latn", } m["avo"] = { "Agavotaguerra", 3508007, "awd", "Latn", } m["avs"] = { "Aushiri", 3409318, "sai-zap", "Latn", } m["avt"] = { "Au", 3446608, "paa-wap", "Latn", } m["avu"] = { "Avokaya", 56685, "csu-mma", "Latn", } m["avv"] = { "Avá-Canoeiro", 4829584, "tup-gua", "Latn", } m["awa"] = { "Awadhi", 29579, "inc-hie", "Deva, Kthi, fa-Arab", ancestors = "inc-oaw", translit = { Deva = "hi-translit" }, } m["awb"] = { "Awa (New Guinea)", 2874650, "ngf-gau", "Latn", } m["awc"] = { "Cicipu", 35193, "nic-kam", "Latn", } m["awe"] = { "Awetí", 4830038, "tup", "Latn", } m["awg"] = { "Anguthimri", 4764288, "aus-pam", "Latn", } m["awh"] = { "Awbono", 3446684, "paa-baa", "Latn", } m["awi"] = { "Aekyom", 3399691, "paa-kae", "Latn", } m["awk"] = { "Awabakal", 3449138, "aus-pam", "Latn", } m["awm"] = { "Arawum", 4784537, "ngf-rai", "Latn", } m["awn"] = { "Awngi", 34934, "cus-cen", "Ethi", } m["awo"] = { "Awak", 3446643, "alv-wjk", "Latn", } m["awr"] = { "Awera", 56379, "paa-flp", "Latn", } m["aws"] = { "South Awyu", 12633986, "ngf-awy", "Latn", } m["awt"] = { "Araweté", 4784535, "tup-gua", "Latn", } m["awu"] = { "Central Awyu", 12628801, "ngf-awy", "Latn", } m["awv"] = { "Jair Awyu", 16110177, "ngf-awy", "Latn", } m["aww"] = { "Awun", 56369, "paa-sep", "Latn", } m["awx"] = { "Awara", 2874670, "ngf-waa", "Latn", } m["awy"] = { "Edera Awyu", 12630425, "ngf-awy", "Latn", } m["axb"] = { "Abipón", 11252539, "sai-guc", "Latn", } m["axe"] = { "Ayerrerenge", 16112737, "aus-pam", "Latn", } m["axg"] = { "Arára (Mato Grosso)", 3446660, nil, "Latn", } m["axk"] = { "Aka (Central Africa)", 11010149, "bnt-ngn", "Latn", } m["axl"] = { "Lower Southern Aranda", 6693295, "aus-rnd", "Latn", } m["axm"] = { "Middle Armenian", 4438498, "hyx", "Armn", ancestors = "xcl", -- Armn translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { remove_diacritics = "՞՜՛՟", from = {"եւ", "ՙ", "՚"}, to = {"և", "ʻ", "’"} } } m["axx"] = { "Xârâgurè", 8045635, "poz-cln", "Latn", } m["aya"] = { "Awar", 56876, "paa-baw", "Latn", } m["ayb"] = { "Ayizo", 34841, "alv-pph", "Latn", } m["ayd"] = { "Ayabadhu", 3509164, "aus-pmn", "Latn", } m["aye"] = { "Ayere", 34788, "alv-aah", "Latn", } m["ayg"] = { "Nyanga (Togo)", 35446, "alv-gng", "Latn", } m["ayi"] = { "Leyigha", 3914492, "nic-uce", "Latn", } m["ayk"] = { "Akuku", 3450179, "alv-nwd", "Latn", } m["ayl"] = { "Arabe Libyo", --TLCHANGE 56503, "sem-arb", "Arab", strip_diacritics = "ar-stripdiacritics", english_name = "Libyan Arabic", --TLCHANGE spanish_name = "Árabe libio", --TLCHANGE } m["ayn"] = { "Arabe Yemeni", --TLCHANGE 1686766, "sem-arb", "Arab, Hebr", strip_diacritics = { Arab = "ar-stripdiacritics", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] english_name = "Yemeni Arabic", --TLCHANGE spanish_name = "Árabe yemení" --TLCHANGE } m["ayo"] = { "Ayoreo", 56634, "sai-zam", "Latn", } m["ayp"] = { "Arabe Hilagang Mesopotamiko", --TLCHANGE 56577, "sem-arb", "Arab", ancestors = "acm", strip_diacritics = "ar-stripdiacritics", english_name = "North Mesopotamian Arabic", --TLCHANGE spanish_name = "Árabe mesopotámico del norte", --TLCHANGE } m["ayq"] = { "Ayi", 56449, "paa-sep", "Latn", } m["ays"] = { "Ayta Sorsogon", --TLCHANGE 7563752, "phi", "Latn", english_name = "Sorsogon Ayta", --TLCHANGE } m["ayt"] = { "Ayta Magbukun", --"Bataan Ayta", 4921648, "phi", "Latn", is_official_kwf_name = "https://kwfwikaatkultura.ph/ayta-magbukun/", --TLCHANGE english_name = "Bataan Ayta", } m["ayu"] = { "Ayu", 34786, "alv", "Latn", } -- ayy deleted and removed from ISO; per the removal request, "no linguistic data exists for any [Ayta] language that the -- ancestors of this group might have once spoken. And thus, there is no evidence that this group ever had a language -- distinct from any other Philippine language." [Lobel] m["ayz"] = { "Maybrat", 4830892, "paa-may", -- either an isolate; grouped with Abun and the West Bird's Head family; or in the putative West Papuan family "Latn", } m["aza"] = { "Azha", 4832486, "tbq-axi", "Latn", } m["azd"] = { "Eastern Durango Nahuatl", 16115449, "azc-dur", "Latn", } m["azg"] = { "San Pedro Amuzgos Amuzgo", 35092, "omq", "Latn", } m["azm"] = { "Ipalapa Amuzgo", 12633013, "omq", "Latn", } m["azn"] = { "Western Durango Nahuatl", 12645553, "azc-dur", "Latn", } m["azo"] = { "Awing", 34856, "nic-nge", "Latn", } m["azt"] = { "Atta Faire", --TLCHANGE 12630884, "phi", "Latn", english_name = "Faire Atta", --TLCHANGE } m["azz"] = { "Highland Puebla Nahuatl", 12953754, "azc-nah", "Latn", } return require("Module:languages").finalizeData(m, "language") hkj1ag6227wlvfd6kaqu7skjn0ybsp7 828 32643 176304 175574 2026-04-13T12:28:57Z Yivan000 4078 176304 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["faa"] = { "Fasu", 3446687, "qfa-dis", -- Papuan; isolate or in the proposed Kutubuan family "Latn", } m["fab"] = { "Annobonese", 34992, "crp", "Latn", ancestors = "pt", } m["fad"] = { "Wagi", 7959569, "ngf-han", "Latn", } m["faf"] = { "Fagani", 3063759, "poz-sls", "Latn", } m["fag"] = { "Finongan", 3450761, "ngf-era", "Latn", } m["fah"] = { "Baissa Fali", 3446632, "nic-bco", "Latn", } m["fai"] = { "Faiwol", 3501773, "ngf-mok", "Latn", } m["faj"] = { "Kursav", 976953, "ngf-eso", "Latn", } m["fak"] = { "Fang (Beboid)", 5433811, "nic-beb", "Latn", } m["fal"] = { "Timog Fali", --TLCHANGE 15637351, "alv-fli", "Latn", english_name = "South Fali", --TLCHANGE } m["fam"] = { "Fam", 35290, "nic-mmb", "Latn", } m["fan"] = { "Fang (Bantu)", 33484, "bnt-btb", "Latn", } m["fap"] = { "Palor", 36318, "alv-cng", "Latn", } m["far"] = { "Fataleka", 3067168, "poz-sls", "Latn", } -- "fat" is treated as "ak", see [[WT:LT]] m["fau"] = { "Fayu", 5439113, "paa-wlp", "Latn", } m["fax"] = { "Fala", 300402, "roa-gap", "Latn", } m["fay"] = { "Southwestern Fars", 5228140, "ira-swi", "Arab", } m["faz"] = { "Northwestern Fars", 7060307, "ira-swi", } m["fbl"] = { "Bikol Kanlurang Albay", --TLCHANGE 18603801, "phi", "Latn", english_name = "West Albay Bikol", --TLCHANGE } m["fcs"] = { "Wikang Senyas ng mga Kebekes", --TLCHANGE 13193, "sgn", "Latn", -- when documented english_name = "Quebec Sign Language", --TLCHANGE spanish_name = "Lengua de signos quebequés", --TLCHANGE } m["fer"] = { "Feroge", 35287, "nic-ser", "Latn", } m["ffi"] = { "Foia Foia", 8564176, "paa-wig", "Latn", } -- "ffm" is treated as "ff", see [[WT:LT]] m["fgr"] = { "Fongoro", 3437645, "csu", "Latn", } m["fia"] = { "Nobiin", 36503, "nub", "Latn, Arab, Copt", ancestors = "onw", translit = { Copt = "Copt-translit", }, sort_key = { Copt = "Copt-sortkey", }, } m["fie"] = { "Fyer", 56273, "cdc-wst", "Latn", } m["fif"] = { "Faifi", 85760309, "sem-cen", -- conservatively putting undifferentiated sem-cen, there's debate over if it's OSA or Arabic "Arab", -- or IPA/Latn; mostly it is unwritten -- ancestors = "sem-srb", if one accepts the view that like Razihi it is sem-osa } -- "fil" is treated as "tl", see [[WT:LT]] m["fip"] = { "Fipa", 667747, "bnt-mwi", "Latn", } m["fir"] = { "Firan", 3915847, "nic-plc", "Latn", } m["fit"] = { "Meänkieli", 13357, "urj-fin", "Latn", ancestors = "fi", } m["fiw"] = { "Fiwaga", 5456292, "ngf-eku", "Latn", } m["fkk"] = { "Kirya-Konzel", 6416310, "cdc-cbm", "Latn", } m["fkv"] = { "Kven", 165795, "urj-fin", "Latn", ancestors = "fi", } m["fla"] = { "Montana Salish", 3111983, "sal", "Latn", } m["flh"] = { "Foau", 5463819, "paa-elp", "Latn", } m["fli"] = { "Fali", 56244, "cdc-cbm", "Latn", } m["fll"] = { "Hilagang Fali", --TLCHANGE 12952419, "alv-fli", "Latn", english_name = "North Fali", --TLCHANGE } m["fln"] = { "Flinders Island", 3915702, "aus-pmn", "Latn", } m["flr"] = { "Fuliiru", 7166821, "bnt-shh", "Latn", } m["fly"] = { "Tsotsitaal", 12643960, "crp", "Latn", ancestors = "af", } m["fmp"] = { "Fe'fe'", 35276, "bai", "Latn", } m["fmu"] = { "Far Western Muria", 42589412, "dra-mur", "Deva", } m["fng"] = { "Fanagalo", 35727, "crp", "Latn", ancestors = "zu", } m["fni"] = { "Fania", 317642, "alv-bua", "Latn", } m["fod"] = { "Foodo", 5465566, "alv-gng", "Latn", } m["foi"] = { "Foi", 5464146, "ngf-eku", "Latn", } m["fom"] = { "Foma", 5464911, "bnt-ske", "Latn", ancestors = "khy", } m["fon"] = { "Fon", 33291, "alv-gbe", "Latn", } m["for"] = { "Fore", 3077126, "ngf-fgi", "Latn", } m["fos"] = { "Siraya", 716604, "map", "Latn", } m["fpe"] = { "Pichinglis", 35288, "crp", "Latn", ancestors = "en", } m["fqs"] = { "Fas", 56320, "paa-fas", "Latn", } -- "frc" is treated as "fr" (or as etymology-only), see [[WT:LT]] m["frd"] = { "Fordata", 5468035, "poz-cet", "Latn", } m["frm"] = { "Middle French", 1473289, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["fro"] = { "Old French", 35222, "roa-oil", "Latn, Hebr", sort_key = { Latn = s["roa-oil-sortkey"], }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["frp"] = { "Franco-Provençal", 15087, "roa-grh", "Latn", ancestors = "frp-old", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.cedilla .. "'", from = {"æ", "œ"}, to = {"ae", "oe"} }, } m["frq"] = { "Forak", 5467173, "ngf-war", "Latn", } m["frr"] = { "North Frisian", 28224, "gmw-fri", "Latn", } -- "frs" is not used, see [[WT:LT]] m["frt"] = { "Fortsenal", 2666835, "poz-vnn", "Latn", } m["fse"] = { "Wikang Senyas ng mga Fines", --TLCHANGE 33225, "sgn", "Latn", -- when documented english_name = "Finnish Sign Language", --TLCHANGE } m["fsl"] = { "Wikang Senyas ng mga Franses", --TLCHANGE 33302, "sgn-fsl", "Latn", -- when documented english_name = "French Sign Language", --TLCHANGE } m["fss"] = { "Wikang Senyas ng mga Franses-Suweko", --TLCHANGE 5450448, "sgn", "Latn", -- when documented english_name = "Finnish-Swedish Sign Language", --TLCHANGE } -- "fub" is treated as "ff", see [[WT:LT]] -- "fuc" is treated as "ff", see [[WT:LT]] m["fud"] = { "East Futuna", 35334, "poz-pnp", "Latn", } -- "fue" is treated as "ff", see [[WT:LT]] -- "fuf" is treated as "ff", see [[WT:LT]] -- "fuh" is treated as "ff", see [[WT:LT]] -- "fui" is treated as "ff", see [[WT:LT]] m["fuj"] = { "Ko", 35693, "alv-hei", "Latn", } m["fum"] = { "Fum", 11011870, "nic-nka", "Latn", } m["fun"] = { "Fulniô", 774441, "qfa-iso", "Latn", } -- "fuq" is treated as "ff", see [[WT:LT]] m["fur"] = { "Friulian", 33441, "roa-rhe", ancestors = "fur-old", "Latn", } m["fut"] = { "Futuna-Aniwa", 3064409, "poz-pnp", "Latn", } m["fuu"] = { "Furu", 3441160, "csu-bkr", "Latn", } -- "fuv" is treated as "ff", see [[WT:LT]] m["fuy"] = { "Fuyug", 3073472, "qfa-dis", -- Papuan; isolate per Glottolog and Usher (2020), only tentatively retained in putative Goilalan family -- within TNG by Ross (2005) "Latn", } m["fvr"] = { "Fur", 33364, "ssa-fur", "Latn", } m["fwa"] = { "Fwâi", 3091331, "poz-cln", "Latn", } m["fwe"] = { "Fwe", 5511159, "bnt-bot", "Latn", } return require("Module:languages").finalizeData(m, "language") cl9tpujal6pzcyshh6tlfvqgmbk1rjl 14 33699 176310 175423 2026-04-13T15:10:15Z Yivan000 4078 176310 wikitext text/x-wiki {{auto cat|english_name=Places in Quezon, Philippines}} i5p3mtab8hjsgo98l0tdshmsgca0ngi 4 34189 176329 166336 2026-04-14T11:48:00Z CommonsDelinker 49 Replacing Logo_for_the_beta_feature_FileExporter.svg with [[File:Logo_for_FileExporter.svg]] (by [[:c:User:CommonsDelinker|CommonsDelinker]] because: [[:c:COM:FR|File renamed]]: [[:c:COM:FR#FR3|Criterion 3]] (obvious error) · Has been a default feature si 176329 wikitext text/x-wiki == FileExporter beta feature == <div class="plainlinks mw-content-ltr" lang="en" dir="ltr"> [[File:Logo for FileExporter.svg|thumb|Coming soon: the beta feature [[m:WMDE_Technical_Wishes/Move_files_to_Commons|FileExporter]]]] A new beta feature will soon be released on all wikis: The [[m:WMDE_Technical_Wishes/Move_files_to_Commons|FileExporter]]. It allows exports of files from a local wiki to Wikimedia Commons, including their file history and page history. Which files can be exported is defined by each wiki's community: '''Please check your wiki's [[m:WMDE_Technical_Wishes/Move_files_to_Commons/Configuration file documentation|configuration file]]''' if you want to use this feature. The FileExporter has already been a beta feature on [https://www.mediawiki.org mediawiki.org], [https://meta.wikimedia.org meta.wikimedia], deWP, faWP, arWP, koWP and on [https://wikisource.org wikisource.org]. After some functionality was added, it's now becoming a beta feature on all wikis. Deployment is planned for January 16. More information can be found [[m:WMDE_Technical_Wishes/Move_files_to_Commons|on the project page]]. As always, feedback is highly appreciated. If you want to test the FileExporter, please activate it in your [[Special:Preferences#mw-prefsection-betafeatures|user preferences]]. The best place for feedback is the [[mw:Help_talk:Extension:FileImporter|central talk page]]. Thank you from Wikimedia Deutschland's [[m:WMDE Technical Wishes|Technical Wishes project]]. </div> [[User:Johanna Strodt (WMDE)|Johanna Strodt (WMDE)]] 09:41, 14 Enero 2019 (UTC) <!-- Message sent by User:Johanna Strodt (WMDE)@metawiki using the list at https://meta.wikimedia.org/w/index.php?title=WMDE_Technical_Wishes/Technical_Wishes_News_list_all_village_pumps&oldid=18782700 --> == No editing for 30 minutes on 17 January == <div lang="en" dir="ltr" class="mw-content-ltr">You will '''not be able to edit''' the wikis for up to 30 minutes on '''[https://www.timeanddate.com/worldclock/fixedtime.html?iso=20190117T07 17 January 07:00 UTC]'''. This is because of a database problem that has to be fixed immediately. You can still read the wikis. Some wikis are not affected. They don't get this message. You can see which wikis are '''not''' affected [[:m:User:Johan (WMF)/201901ReadOnlyPage|on this page]]. Most wikis are affected. The time you can not edit might be shorter than 30 minutes. /[[User:Johan (WMF)|Johan (WMF)]]</div> 18:55, 16 Enero 2019 (UTC) <!-- Message sent by User:Johan (WMF)@metawiki using the list at https://meta.wikimedia.org/w/index.php?title=User:Johan_(WMF)/201901ReadOnly/Targets8&oldid=18789240 --> rmrp3ofv3shdtcr1np8lrhxnslfgi1k 828 34553 176326 169574 2026-04-14T04:04:22Z Yivan000 4078 176326 Scribunto text/plain local raw_categories = {} local raw_handlers = {} local concat = table.concat local insert = table.insert ----------------------------------------------------------------------------- -- -- -- RAW CATEGORIES -- -- -- ----------------------------------------------------------------------------- raw_categories["Lahat ng pamilya ng wika"] = { --TLCHANGE "All language families" topright = "{{commonscat|Languages by family}}\n{{wp|Language family,List of language families}}", description = "This category lists all [[language family|language families]].", parents = {"Pangkalahatan"}, --TLCHANGE "Fundamental" english_name = "All language families" --TLCHANGE } raw_categories["Wika ayon sa pamilya"] = { --TLCHANGE "Languages by family" topright = "{{commonscat|Languages by family}}\n{{wp|Language family,List of language families}}", description = "This category contains all languages categorized hierarchically according to the [[language family]] they belong to.", additional = "Only top-level language families are shown here. For a full list of all language families, see [[:Category:All language families]] or [[Wiktionary:List of families]].", parents = { {name = "Lahat ng wika", sort = " "}, --TLCHANGE {name = "Lahat ng pamilya ng wika", sort = " "}, --TLCHANGE }, english_name = "Languages by family", --TLCHANGE } raw_categories["Unassigned languages"] = { description = "Languages that have not yet been assigned to any family by Wiktionary editors, usually due to oversight.", additional = [=[This should be distinguished from: * [[:Category:Unclassifiable languages]] (languages that cannot be confidently assigned to any family, typically because the language is extinct or unresearched and has little available data on it); * [[:Category:Language isolates]] (where there is general agreement that the language has no relatives); and * [[:Category:Languages of disputed affiliation]] (languages where there is no consensus concerning which family, if any, they belong to).]=], parents = { {name = "Wika ayon sa pamilya", sort = "*"}, --TLCHANGE {name = "Languages by family", sort = "*"}, "All language families", }, } ----------------------------------------------------------------------------- -- -- -- RAW HANDLERS -- -- -- ----------------------------------------------------------------------------- local function family_is_not_a_family(fam) if not fam then return false elseif fam:getCode() == "qfa-not" then return true else return family_is_not_a_family(fam:getFamily()) end end local function family_has_no_category(fam) local famcode = fam:getCode() if famcode == "paa" then return false -- Papuan languages are not a family but have a category elseif famcode == "qfa-iso" or famcode == "qfa-not" then return true else local parfam = fam:getFamily() if parfam and parfam:getCode() == "qfa-not" then -- Constructed languages, sign languages, etc.; no category for them return true end end return false end -- Currently all Papuan families begin with "paa" or "ngf", local function family_is_papuan(fam) local famcode = fam:getCode() return famcode ~= "paa" and (famcode:find("^paa") or famcode:find("^ngf")) end local function infobox(fam) local ret = {} insert(ret, "<table class=\"wikitable\">\n") insert(ret, "<tr>\n<th colspan=\"2\" class=\"plainlinks\"><small>[//tl.wiktionary.org/w/index.php?title=Module:families/data&action=edit I-edit ang datos ng pamilya]</small></th>\n</tr>\n") --TLCHANGE --TLCHANGE ADD KWF OFFICIAL STATUS INDICATOR insert(ret, "<tr>\n<th>Canonical name</th><td>" .. fam:getCanonicalName() .. "</td>\n</tr>\n") if (fam:getData().is_official_kwf_name) then insert(ret, "<tr>\n<th>Opisyal na pangalan</th><td>" .. fam:getCanonicalName() .. "<br/><span style='font-size: 0.7em'>(''ayon sa [[File:Komisyon sa Wikang Filipino (KWF).svg|20px]] [" .. fam:getData().is_official_kwf_name .. " Komisyon sa Wikang Filipino]'')</span></td>\n</tr>\n") else insert(ret, "<tr>\n<th>Kilalang pangalan</th><td>" .. fam:getCanonicalName() .. "<p style='font-size: 0.7em'>(''walang opisyal na pangalan ang [[File:Komisyon sa Wikang Filipino (KWF).svg|20px]] Komisyon sa Wikang Filipino sa pamilyang ito'')</p></td>\n</tr>\n") end local otherNames = fam:getOtherNames() if otherNames then local names = {} for _, name in ipairs(otherNames) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Ibang pangalan</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") --TLCHANGE end end local aliases = fam:getAliases() if aliases then local names = {} for _, name in ipairs(aliases) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Alyas</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") --TLCHANGE end end local varieties = fam:getVarieties() if varieties then local names = {} for _, name in ipairs(varieties) do if type(name) == "string" then insert(names, "<li>" .. name .. "</li>") else assert(type(name) == "table") local first_var local subvars = {} for i, var in ipairs(name) do if i == 1 then first_var = var else insert(subvars, "<li>" .. var .. "</li>") end end if #subvars > 0 then insert(names, "<li><dl><dt>" .. first_var .. "</dt>\n<dd><ul>" .. concat(subvars, "\n") .. "</ul></dd></dl></li>") elseif first_var then insert(names, "<li>" .. first_var .. "</li>") end end end if #names > 0 then insert(ret, "<tr>\n<th>Varieties</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end insert(ret, "<tr>\n<th>[[Wiktionary:Families|Family code]]</th><td><code>" .. fam:getCode() .. "</code></td>\n</tr>\n") insert(ret, "<tr>\n<th>[[w:Proto-language|Common ancestor]]</th><td>") local protoLanguage = fam:getProtoLanguage() if protoLanguage then insert(ret, "[[:Category:" .. protoLanguage:getCategoryName() .. "|" .. protoLanguage:getCanonicalName() .. "]]") else insert(ret, "none") end insert(ret, "</td>\n") insert(ret, "\n</tr>\n") local parent = fam:getFamily() if not parent then insert(ret, "<tr>\n<th>[[Wiktionary:Families|Parent family]]</th>\n<td>") insert(ret, "unassigned") elseif parent:getCode() == "qfa-not" then insert(ret, "<tr>\n<th>[[Wiktionary:Families|Parent family]]</th>\n<td>") insert(ret, "not a family") else local chain = {} while parent do if family_has_no_category(parent) then break end insert(chain, "[[:Category:" .. parent:getCategoryName() .. "|" .. parent:getCanonicalName() .. "]]") parent = parent:getFamily() end if #chain == 0 then insert(ret, "<tr>\n<th>[[Wiktionary:Families|Parent family]]</th>\n<td>") insert(ret, "no parents") else insert(ret, "<tr>\n<th>[[Wiktionary:Families|Parent famil" .. (#chain == 1 and "y" or "ies") .. "]]</th>\n<td>") for i = #chain, 1, -1 do insert(ret, "<ul><li>" .. chain[i]) end insert(ret, string.rep("</li></ul>", #chain)) end end insert(ret, "</td>\n</tr>\n") if fam:getWikidataItem() and mw.wikibase then local link = '[' .. mw.wikibase.getEntityUrl(fam:getWikidataItem()) .. ' ' .. fam:getWikidataItem() .. ']' insert(ret, "<tr><th>Wikidata</th><td>" .. link .. "</td></tr>") end insert(ret, "</table>") return concat(ret) end local function NavFrame_for_family_tree(content, title) return '<div class="NavFrame"><div class="NavHead">' .. (title or '{{{title}}}') .. '</div>' .. '<div class="NavContent" style="text-align: left; font-size: calc(1em / 0.95); padding: 0.3em">' .. content .. '</div></div>' end local additional_information = { ["qfa-dis"] = "These are languages where there is no consensus concerning which family, if any, they belong to.", ["qfa-iso"] = "These are languages where there is general agreement that the language has no known relatives.", ["qfa-mix"] = "A [[mixed language]] is a language which is composed of two different languages.", ["qfa-unc"] = "These are languages that cannot be confidently assigned to a family due to lack of sufficient linguistic data. " .. "They are also commonly called {{w|unclassified language|unclassified languages}}, but this is ambiguous between " .. "languages that cannot be classified (due to insufficient data) and those that merely have not been classified " .. "(due to insufficient research).", } local preceding_information = { ["qfa-dis"] = "{{also|Category:Unclassifiable languages|Category:Unassigned languages|Category:Language isolates}}", ["qfa-iso"] = "{{also|Category:Languages of disputed affiliation|Category:Unclassifiable languages|Category:Unassigned languages}}", ["qfa-unc"] = "{{also|Category:Languages of disputed affiliation|Category:Unassigned languages|Category:Language isolates}}", ["qfa-mix"] = "{{also|Category:Creole or pidgin languages}}", ["crp"] = "{{also|Category:Mixed languages}}", } local specially_named_families = { ["Languages of disputed affiliation"] = "qfa-dis", ["Language isolates"] = "qfa-iso", } local specially_named_family_sort_keys = { ["Languages of disputed affiliation"] = "Disputed affiliation", ["Language isolates"] = "Isolate", } insert(raw_handlers, function(data) local family = require("Module:families").getByCategoryName(data.category) if not family then local special_code = specially_named_families[data.category] if special_code then family = require("Module:families").getByCode(special_code) if not family then error(("Internal error: Family code '%s' is an invalid family code."):format(special_code)) end end end if not family then return nil end local parent_fam = family:getFamily() local first_parent, parent_sort_key, first_parent_sort_key if not parent_fam or family_is_not_a_family(parent_fam) then first_parent = "Wika ayon sa pamilya" --TLCHANGE "Languages by family" parent_sort_key = specially_named_family_sort_keys[data.category] first_parent_sort_key = "*" .. (parent_sort_key or "") else first_parent = parent_fam:getCategoryName() first_parent_sort_key = family:getCanonicalName() --TLCHANGE add this end local description, additional = "", "" local topright local preceding = preceding_information[family:getCode()] local additional_preface = additional_information[family:getCode()] if additional_preface then additional_preface = additional_preface .. "\n\n" else additional_preface = "" end if family_is_not_a_family(family) then additional_preface = additional_preface .. "This is a pseudo-family, used for grouping purposes but not forming a linguistically valid [[clade]] " .. "(i.e. a set of linguistically related languages descending from a common parent).\n\n" .. "Impormasyon patungkol sa pamilyang ito:\n\n" --TLCHANGE "Information about this family:\n\n" else additional_preface = "Impormasyon patungkol sa " .. family:getCanonicalName() .. ":\n\n" --TLCHANGE "Information about " end if not data.called_from_inside then topright = {} local wikipedia_art = family:getWikipediaArticle("noCategoryFallback") if wikipedia_art then insert(topright, "{{wp|" .. wikipedia_art .. "}}") end local commons_cat = family:getCommonsCategory() if commons_cat then insert(topright, "{{commonscat|" .. commons_cat:gsub("^Category:", "") .. "}}") end topright = #topright > 0 and concat(topright, "\n") or nil --TLCHANGE "This is the main category of the '''" .. family:getDisplayForm() .. "'''." description = "Ito ang pangunahing kategorya ng mga wikang '''" .. family:getCanonicalName() .. "'''." additional = additional_preface .. infobox(family) end local ok, tree_of_descendants = pcall( require("Module:family tree").print_children, family:getCode(), { protolanguage_under_family = true, must_have_descendants = true }) if ok then if tree_of_descendants then additional = additional .. NavFrame_for_family_tree( tree_of_descendants, "Puno ng pamilya") --TLCHANGE "Family tree" else additional = additional .. "\n\n" .. ucfirst(family:getCanonicalName()) .. " has no descendants or varieties listed in Wiktionary's language data modules." end else mw.log("error while generating tree: " .. tostring(tree_of_descendants)) end local parents = { {name = first_parent, sort = first_parent_sort_key}, {name = "Lahat ng pamilya ng wika", sort = parent_sort_key}, --TLCHANGE "All language families" } if parent_fam and parent_fam:getCode() == "sgn" then insert(parents, "All sign languages") end if family_is_papuan(family) then insert(parents, "Papuan languages") end return { preceding = preceding, topright = topright, description = description, additional = additional, parents = parents, breadcrumb = family:getCanonicalName(), can_be_empty = true, english_name = require("Module:string utilities").ucfirst(family:getData().english_name or family:getCanonicalName()) .. " languages" --TLCHANGE } end) return {RAW_CATEGORIES = raw_categories, RAW_HANDLERS = raw_handlers} c5wd61i1kn4kna7wt6ocuv9qw9hb3k9 828 35258 176308 168950 2026-04-13T15:07:44Z Yivan000 4078 176308 Scribunto text/plain local labels = {} labels["Classical"] = { aliases = {"classical"}, display = "classical norm", Wikipedia = "Occitan language#Writing system", } labels["Auvergne"] = { aliases = {"Auvergnat", "Auvernhat"}, Wikipedia = "Auvergnat", plain_categories = "Auvergnat", } labels["Gascony"] = { aliases = {"Gascon"}, Wikipedia = "Gascon language", plain_categories = "Gaskon", --TLCHANGE "Gascon", } labels["Béarn"] = { aliases = {"Béarnese"}, Wikipedia = "Béarnese dialect", plain_categories = "Gaskon", --TLCHANGE "Gascon", } labels["Guardiol"] = { display = "[[Guardiol]]", Wikipedia = "Guardia Piemontese", plain_categories = true, } labels["Languedoc"] = { aliases = {"Languedocian", "Languedocien"}, Wikipedia = "Languedocien dialect", plain_categories = "Languedocien", } labels["Limousin"] = { aliases = {"Lemosin"}, Wikipedia = "Limousin dialect", plain_categories = true, } labels["Mistralian"] = { Wikipedia = "Mistralian norm", regional_categories = true, } labels["Provençal"] = { aliases = {"Provencal", "Provence"}, Wikipedia = "Provençal dialect", plain_categories = true, } labels["Vivaro-Alpine"] = { Wikipedia = "Vivaro-Alpine dialect", plain_categories = true, } labels["Niçard"] = { aliases = {"Nicard"}, Wikipedia = "Niçard dialect", } return require("Module:labels").finalize_data(labels) nlm4yovwft9q0sio02d3ily2ybczg15 14 36860 176302 171913 2026-04-13T12:14:51Z Yivan000 4078 Inilipat ni Yivan000 ang pahinang [[Kategorya:Tagalog na salitang may pagbigkas na audio]] sa [[Kategorya:Tagalog na salitang may pagbigkas na awdiyo]] nang walang iniwang redirect 171913 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 14 37651 176303 175705 2026-04-13T12:18:42Z Yivan000 4078 176303 wikitext text/x-wiki {{auto cat|Pilipinas|english_name=Philippine Sign Language}} lg8rrfnegflhrvxev78em6za5xxgvcy 14 37900 176311 2026-04-13T15:11:10Z Yivan000 4078 Nilikha ang pahina na may '{{auto cat}}' 176311 wikitext text/x-wiki {{auto cat}} eomzlm5v4j7ond1phrju7cnue91g5qx 176312 176311 2026-04-13T15:11:35Z Yivan000 4078 176312 wikitext text/x-wiki {{auto cat|english_name=tl:Quezon, Philippines}} bly57gm1d2wg9sfqb4dzj0ckn5t34bn 828 37901 176315 2026-04-14T02:32:56Z Yivan000 4078 Nilikha ang pahina na may 'local export = {} local gsub = mw.ustring.gsub local u = require("Module:string/char") local con_cls = "([ကၵငꩡꩬၺတထꩫဒပၸမဗယꩺလဝꩭဢ])" local med_cls = "([ျြၞ]?)" local tt1 = { -- consonants ["က"] = "k", ["ၵ"] = "kh", ["င"] = "ṅ", ["ꩡ"] = "c", ["ꩬ"] = "s", ["ၺ"] = "ñ", ["တ"] = "t", ["ထ"] = "th", ["ꩫ"] = "n", ["ဒ"] = "d", ["ပ"] = "p", ["ၸ"] = "ph", ["မ"] = "m", ["ဗ"] = "b", ["ယ"] = "y"...' 176315 Scribunto text/plain local export = {} local gsub = mw.ustring.gsub local u = require("Module:string/char") local con_cls = "([ကၵငꩡꩬၺတထꩫဒပၸမဗယꩺလဝꩭဢ])" local med_cls = "([ျြၞ]?)" local tt1 = { -- consonants ["က"] = "k", ["ၵ"] = "kh", ["င"] = "ṅ", ["ꩡ"] = "c", ["ꩬ"] = "s", ["ၺ"] = "ñ", ["တ"] = "t", ["ထ"] = "th", ["ꩫ"] = "n", ["ဒ"] = "d", ["ပ"] = "p", ["ၸ"] = "ph", ["မ"] = "m", ["ဗ"] = "b", ["ယ"] = "y", ["ꩺ"] = "r", ["လ"] = "l", ["ဝ"] = "w", ["ꩭ"] = "h", ["ဢ"] = "ʼ", -- medials ["ျ"] = "y", ["ြ"] = "r", ["ၞ"] = "w", -- dependent vowels and diacritics (excluding front type) ["္"] = "", ["ႜ"] = "a", ["ႃ"] = "ā", ["ိ"] = "i", ["ီ"] = "ī", ["ု"] = "u", ["ူ"] = "ū", ["ွ"] = "o", ["်"] = "", ["ႝ"] = "y", ["ေ"] = "e", ["ံ"] = "ṃ", -- punctuation marks ["၊"] = ",", ["။"] = ".", ["꩷"] = "!", -- numerals ["꩸"] = "1", ["꩹"] = "2", ["၀"] = "0", ["၁"] = "1", ["၂"] = "2", ["၃"] = "3", ["၄"] = "4", ["၅"] = "5", ["၆"] = "6", ["၇"] = "7", ["၈"] = "8", ["၉"] = "9", -- zero-width space (display it if it hides in a word) [u(0x200B)] = "‼", } function export.tr(text, lang, sc) if type(text) == "table" then -- called directly from a template text = text.args[1] end text = gsub(text, u(0xFE00), "") -- remove VS01 text = gsub(text, "ေ".."ႃ", "ō") text = gsub(text, "ိ".."ု", "ü") text = gsub(text, "ွ".."်", "aw") text = gsub(text, "ၞ".."်", "aü") text = gsub(text, con_cls .. med_cls .. con_cls .. "်", "%1%2a%3") text = gsub(text, con_cls .. med_cls .. "([ႝံ])", "%1%2a%3") text = gsub(text, ".", tt1) return text end return export 0s1izt0uuxcmdrk8nbzj2jn6wq6uvsl 828 37902 176316 2026-04-14T02:33:38Z Yivan000 4078 Nilikha ang pahina na may 'local export = {} local U = require("Module:string/char") local rsub = mw.ustring.gsub local rmatch = mw.ustring.match local unpack = unpack or table.unpack -- Lua 5.2 compatibility local hbasa = U(0x73C) local rwaha = U(0x73F) local zlama_angular = U(0x739) local zlama_horizontal = U(0x738) local pthaha = U(0x732) local zqapha = U(0x735) local diacritic_vowels = hbasa .. rwaha .. zlama_angular .. zlama_horizontal .. pthaha .. zqapha local diacritic_vowels_cap...' 176316 Scribunto text/plain local export = {} local U = require("Module:string/char") local rsub = mw.ustring.gsub local rmatch = mw.ustring.match local unpack = unpack or table.unpack -- Lua 5.2 compatibility local hbasa = U(0x73C) local rwaha = U(0x73F) local zlama_angular = U(0x739) local zlama_horizontal = U(0x738) local pthaha = U(0x732) local zqapha = U(0x735) local diacritic_vowels = hbasa .. rwaha .. zlama_angular .. zlama_horizontal .. pthaha .. zqapha local diacritic_vowels_capture = "([" .. diacritic_vowels .. "])" local talqana_above = U(0x747) local combining_diaeresis = U(0x308) -- we declare consonants representing vowels (matres lectionis) as constants to mitigate differences in how mixing -- right-to-left and left-to-right characters in the same line appears in an IDE vs wiktionary. Since matres is used in -- concatenation via the .. operator, "ܘ" .. "ܐ" on wiktionary would render as "ܐ" .. "ܘ" in an IDE local alaph = U(0x710) local waw = U(0x718) local yudh = U(0x71D) local combining_tilde_below = U(0x330) local combining_tilde_above = U(0x303) local combining_macron_below = U(0x331) local combining_macron = U(0x304) local qushshaya = U(0x741) local rukkakha = U(0x742) local combining_breve_below = U(0x32E) local combining_dot_below = U(0x323) local combining_dot_above = U(0x307) local glottal_stop = 'ˀ' local pharyngeal = 'ˁ' -- constants for transliterated snippets which are used in later substitutions local TR_SECOND_PERSON_MASC_SUFFIX = 'ōḵ' local TR_THIRD_PERSON_FEM_SUFFIX = 'ōh' local TR_WAW_PLUS_RVASA = 'ū' local TR_WAW_PLUS_RVASA_SHORT = 'u' local tt_transpose_punc = { -- left/right single/double quotes ["“"] = "”", ["”"] = "“", ["‘"] = "’", ["’"] = "‘", ["؟"] = "?", -- question mark ["«"] = '“', -- quotation mark ["»"] = '”', -- quotation mark ["،"] = ",", -- comma ["؛"] = ";", -- semicolon } local tt_transpose_punc_keys = '' for key, _ in pairs(tt_transpose_punc) do tt_transpose_punc_keys = tt_transpose_punc_keys .. key end local fix = { { diacritic_vowels_capture .. qushshaya, qushshaya .. "%1"}, -- under the hood mw uses uses NFC which preempts the following two substitutions... -- feel free to uncomment if there's a test case which can be added that requires them to be uncommented -- https://www.mediawiki.org/wiki/Unicode_normalization_considerations -- { diacritic_vowels_capture .. rukkakha, rukkakha .. "%1"}, -- { diacritic_vowels_capture .. combining_tilde_below, combining_tilde_below .. "%1" }, -- partition punctuation marks so "starts with" and "ends with" substitutions work {"([".. tt_transpose_punc_keys .. "()!.:\"'])", "#%1#"}, } local tt = { ["ܦ"] = "p", ["ܒ"] = "b", ["ܬ"] = "t", ["ܛ"] = "ṭ", ["ܕ"] = "d", ["ܟ"] = "k", ["ܓ"] = "g", ["ܩ"] = "q", ["ܣ"] = "s", ["ܨ"] = "ṣ", ["ܙ"] = "z", ["ܫ"] = "š", ["ܚ"] = "ḥ", ["ܥ"] = pharyngeal, ["ܗ"] = "h", ["ܡ"] = "m", ["ܢ"] = "n", ["ܪ"] = "r", ["ܠ"] = "l", } -- local tt_keys = '' -- for key, _ in pairs(tt) do tt_keys = tt_keys .. key end local tt_values = '' for _, value in pairs(tt) do tt_values = tt_values .. value end local mhagjana_capture = "([" .. rsub('ܗܠܡܢܥܪ', ".", tt) .. alaph .. yudh .. waw .. "])" local marhetana_capture = "([" .. rsub('ܦܒܬܛܕܟܓܩܣܨܙܫܚ', ".", tt) .. "])" -- https://r12a.github.io/scripts/syrc/aii.html#single_letter_words local bdul = 'ܒܕܘܠ' local bdul_capture = '([' .. bdul .. '])' local bdul_capture2 = '([' .. bdul .. '])([' .. bdul .. '])' -- local alphabet = '' -- for letter, _ in pairs(tt) do alphabet = alphabet .. letter end -- alphabet = alphabet .. yudh .. waw .. alaph -- local alphabet_capture = '([' .. alphabet .. '])' local tt_next = { [waw] = "w", [yudh] = "y", [zlama_angular] = "ē", [zlama_horizontal] = "i", [pthaha] = "a", [zqapha] = "ā" } local glides = alaph .. yudh .. waw -- unvoweled, original values of matres lectionis (consonants representing vowels) local consonants_minus_glides = tt_values .. "cžfḇṯḏḵḡ" local consonants_minus_glides_cg = "([" .. consonants_minus_glides .. "])" local consonants_minus_glides_cg_2 = "([" .. consonants_minus_glides .. "y])" local consonants_capture = "([" .. glides .. consonants_minus_glides .. "])" -- local consonants_capture_minus_alaph = "([" .. yudh .. waw .. consonants_minus_glides .. "])" local vowels_w = TR_WAW_PLUS_RVASA_SHORT .. TR_WAW_PLUS_RVASA .. "ō" local vowels_y = "eiēī" local vowels = vowels_y .. vowels_w .. "aā" local consonants_and_vowels_capture = "([" .. glides .. consonants_minus_glides .. vowels .. "])" local genitive_endings = {"ܐ", "ܝܼ", "ܘܼܟ݂", "ܵܟ݂ܝ", "ܹܗ", "ܵܗ̇", "ܘܼܗܝ" , "ܘܼܗ̇" , "ܲܢ", "ܲܘܟ݂ܘܿܢ", "ܗܘܿܢ", "ܲܝܗܘܿܢ" , "ܹ̈ܐ" , "ܹܐ" , "ܲܝ" , "ܲܝ̈" , "ܲܬ݂" , "ܵܬ݂̈" , "ܵܬ݂" , "ܝܼ̈", "ܘܼ̈ܟ݂", "ܵܟ݂ܝ̈", "ܘܼ̈ܗܝ" , "ܘܼ̈ܗ̇" , "ܲܢ̈", "ܲܘ̈ܟ݂ܘܿܢ", "ܲܝܗ̈ܘܿܢ"} -- per "No alternation (the | operator)" https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns -- lua doesn't provide support to check if a word contains this, or that, or other via (this|that|other) -- this means we can't simply check if the word ends in any of the possible masculine genitive endings with a capture group like -- local genitive_endings_capture = "(" .. table.concat(genitive_endings,"|") .. ")" local genitive_endings_special_cases = { ["ܒܵܬ"] = "bātt", ["ܚܘܼܒ"] = "ḥubb", ["ܓܘܼܕ"] = "gudd", ["ܓܘܼܕܵܢ"] = "guddān", ["ܦܘܼܡ"] = "pumm", ["ܪܘܼܙ"] = "ruzz", ["ܐܸܣܦܘܼܓ"] = "ispugg", ["ܐܸܛܪܘܼܓ"] = "iṭrugg", ["ܐܸܛܪ̈ܘܼܓ"] = "iṭrugg", ["ܣܘܼܪܵܝ"] = "sūrāy", ["ܣܘܼܪ̈ܵܝ"] = "sūrāy", ["#ܨܘܼܪ"] = "#ṣūr", ["ܨܘܼܪ̈ܵܬ݂"] = "ṣūrāṯ", ["ܨܘܼܪ̈ܝܵܬ݂"] = "ṣūryāṯ", ["ܓܘܼܬ"] = "gutt", } -- due to runtime performance concerns, we should strive to limit special cases to only the most common terms for which the transliterator is way off local special_cases = { -- { aii_text, aii_translit_output } -- -- the # symbol pads the start and end of a word, consider the follow examples -- #float# only float matches -- #float words starting with float like float or floats match -- float# words ending with float like float or afloat match -- float words containing float like float, floats, afloat and refloats match {"#ܒܗ" .. combining_dot_above .. "ܝ#", "#b-ay#"}, {"ܗ" .. combining_dot_above .. "ܝ#", "aya#"}, {"ܗ" .. combining_dot_above .. "ܘ#", "awa#"}, {"ܡ" .. combining_dot_above .. "ܢ#", "man#"}, {"ܡ" .. combining_dot_below .. "ܢ#", "min#"}, -- commenting this out for now until test cases can be added for it {waw .. hbasa .. "ܟ݂#", TR_SECOND_PERSON_MASC_SUFFIX .. "#"}, {waw .. hbasa .. combining_diaeresis .. "ܟ݂#", TR_SECOND_PERSON_MASC_SUFFIX .. "#"}, {"ܟ̰ܵܐܝ", "čāy"}, {"ܒܵܐܝ", "bāy"}, {"ܝܼܫܘܿܥ#", "īšōˁ#"}, -- starts with vowel but not silent alaph -- "to be" without inital khwasa, ì {"#ܝܘܸܢ#", "#ìwen#"}, {"#ܝܘܵܢ#", "#ìwān#"}, {"#ܝܘܲܚ#", "#ìwaḥ#"}, {"#ܝܘܸܬ#", "#ìwet#"}, {"#ܝܘܵܬܝ#", "#ìwāt#"}, {"#ܝܬܘܿܢ#", "#ìtōn#"}, {"#ܝܠܹܗ#", "#ìlēh#"}, {"#ܝܠܵܗ̇#", "#ìlāh#"}, {"#ܝܢܵܐ#", "#ìnā#"}, {"#ܝܗ݇ܘܵܐ#", "#ìwā#"}, {"#ܝܗ݇ܘܵܬ݇#", "#ìwā#"}, {"#ܝܗ݇ܘܵܘ#", "#ìwā#"}, -- "to be" with inital khwasa, ī {"ܝܼܘܸܢ#", "īwen#"}, {"ܝܼܘܵܢ", "īwān"}, {"ܝܼܘܸܬ#", "īwet#"}, {"ܝܼܘܵܬܝ#", "īwāt#"}, {"ܝܼܠܹܗ#", "īlēh#"}, {"ܝܼܠܵܗ̇#", "īlāh#"}, {"ܝܼܘܲܚ#", "īwaḥ#"}, {"ܝܼܬܘܿܢ#", "ītōn#"}, {"ܝܼܢܵܐ#", "īnā#"}, -- "to be" blends {"ܝܼܗ݇ܘܵܐ#", "īwā#"}, {"ܝܼܗ݇ܘܵܘ#", "īwā#"}, -- "to be" imperative forms -- following substitutions starting with '#w' are to pre-empt 'w-' prefixing rule {"#ܗ݇ܘܝܼ", "#wī"}, {"#ܗ݇ܘܹܝܡܘܼܢ#", "#wēmūn#"}, -- "to be" past particles {"#ܗ݇ܘܵܐ#", "#wā#"}, {"#ܗ݇ܘܵܘ#", "#wā#"}, {"#ܗ݇ܘܹܐ#", "#wē#"}, -- "of" (fixed expressions) {"#ܕܝܵܡܵܐ#", "#d-yāmā#"}, {"#ܕܠܵܐ#", "#d-lā#"}, {"#ܕܕܸܒ݂ܫܵܐ#", "#d-diḇšā#"}, {"#ܕܲܕܡܵܐ#", "#da-dmā#"}, -- "to" (fixed expressions) {"ܠܒܲܪܵܐ#" , "l-barrā#"}, {"ܠܓܲܘܵܐ#", "l-gawwā#"}, {"ܠܒܲܪ#" , "l-bar#"}, {"ܠܓܲܘ#", "l-gaw#"}, {"#ܠܡܵܐ#" , "#lemā#"}, -- "clitic demonstrative pronouns" {"ܒܗܵܢܵܐ#", "b-hānā#"}, {"ܒܗܵܕ݂ܹܐ", "b-hāḏē"}, {"ܒܗܸܢܘܿܢ#", "b-hinnōn#"}, {"ܒܗܸܢܹܝܢ", "b-hinnēn"}, {"ܕܗܵܢܵܐ#", "d-hānā#"}, {"ܕܗܵܕ݂ܹܐ", "d-hāḏē"}, {"ܕܗܸܢܘܿܢ#", "d-hinnōn#"}, {"ܕܗܸܢܹܝܢ", "d-hinnēn"}, {"ܠܗܵܢܵܐ#", "l-hānā#"}, {"ܠܗܵܕ݂ܹܐ", "l-hāḏē"}, {"ܠܗܸܢܘܿܢ#", "l-hinnōn#"}, {"ܠܗܸܢܹܝܢ", "l-hinnēn"}, {"ܘܗܵܢܵܐ#", "w-hānā#"}, {"ܘܗܵܕ݂ܹܐ", "w-hāḏē"}, {"ܘܗܸܢܘܿܢ#", "w-hinnōn#"}, {"ܘܗܸܢܹܝܢ", "w-hinnēn"}, -- "per" (fixed expressions with time) {"ܒܕܲܩܝܼܩܵܐ#", "b-daqqīqā#"}, {"ܒܪܦܵܦܵܐ#", "b-rpāpā#"}, {"ܒܫܵܥܬ݂ܵܐ#", "b-šāˁṯa#"}, {"ܒܫܵܥܲܬ݂#", "b-šāˁaṯ#"}, {"ܒܝܵܘܡܵܐ#", "b-yāwmā#"}, {"ܒܝܘܿܡ#", "b-yōm#"}, {"ܒܫܵܒ݂ܘܿܥܵܐ#", "b-šāḇōˁā#"}, {"ܒܡܸܬ݂ܚܵܐ#", "b-miṯḥā#"}, {"ܒܝܲܪܚܵܐ#", "b-yarḥā#"}, {"ܒܝܼܪܲܚ#", "b-yraḥ#"}, {"ܒܫܹܢ݇ܬܵܐ#", "b-šētā#"}, {"ܒܫܹܢ݇ܬ#", "b-šēt#"}, {"ܒܫܢܲܝ̈#", "b-šnay#"}, {"ܒܫܢܲܬ݂#", "b-šnaṯ#"}, {"ܒܕܵܘܪܵܐ#", "b-dāwrā#"}, {"ܒܠܲܝܠܹܐ#", "b-laylē#"}, {"ܒܨܲܦܪܵܐ#", "b-ṣaprā#"}, {"ܒܪܲܡܫܵܐ#", "b-ramšā#"}, -- adverbs with clitics (fixed expressions) {"ܠܩܘܼܪܒܵܐ#", "l-qurbā#"}, {"ܒܩܘܼܪܒܵܐ#", "b-qurbā#"}, {"ܒܚܲܪܬܵܐ#", "b-ḥartā#"}, {"ܒܟܠ#", "b-kul#"}, {"ܕܗܵܘܝܵܐ#", "d-hāwyā#"}, {"ܕܟܹܐ#", "d-kē#"}, {"ܠܩܘܼܪܒܵܐ ܕ", "l-qurbā d-" .. ""}, {"ܒܡܸܬ݂ܚܵܐ ܕ", "b-miṯḥā d-" .. ""}, -- "all", "each", "every" {"ܟܠ#", "kul#"}, {"ܟܠܵܢ#", "kullān#"}, {"ܟܠܘܼܟ݂#", "kullōḵ#"}, {"ܟܠܵܟ݂ܝ#", "kullāḵ#"}, {"ܟܠܹܗ#", "kullēh#"}, {"ܟܠܵܗ̇#", "kullāh#"}, {"ܟܠܘܿܗ̇#", "kullōh#"}, {"ܟܠܘܼܗܝ#", "kullūh#"}, {"ܟܠܘܼܗ̇#", "kullōh#"}, {"ܟܠܲܢ#", "kullan#"}, {"ܟܠܲܘܟ݂ܘܿܢ#", "kullawḵōn#"}, {"ܟܠܵܝܗܝ#", "kullāyh#"}, {"ܟܠܗܘܿܢ#", "kullhōn#"}, {"ܟܠܵܢܵܐܝܼܬ#", "kullānāˀīt#"}, {"ܟܠܵܢܵܐܝܼܬ݂#", "kullānāˀīṯ#"}, {"ܟܠܵܢܵܝ", "kullānāy"}, {"ܟܘܿܠܵܝ", "kollāy"}, {"ܟܠܚܲܕ݇#", "kulḥa#"}, {"ܟܠܚܕ݂ܵܐ#", "kulḥḏā#"}, {"ܟܠܫܲܢ݇ܬ#", "kulšat#"}, -- "classical because" {"ܡܸܛܠ#", "miṭṭul#"}, {"ܡܸܛܠܬ", "miṭṭult"}, {"ܡܸܛܠܵܐܝܼܬ݂#", "miṭṭullāˀīṯ#"}, -- "houses" {"ܒܵܬܹ̈ܐ#", "bāttē#"}, {"ܒܵܬܲܝ̈#", "bāttay#"}, {"ܒܵܬܲܢ̈#", "bāttan#"}, {"ܒܵܬܘܼ̈ܟ݂#", "bāttōḵ#"}, {"ܒܵܬܲܝ̈ܗܘܿܢ#", "bāttayhōn#"}, -- masc sing construct state rvasa {"ܓܘܼܕ#", "gud#"}, {"ܦܘܼܡ#", "pum#"}, {"ܐܸܛܪܘܼܓ#", "iṭrug#"}, {"ܐܸܣܦܘܼܓ#", "ispug#"}, -- countries and nationalities {"ܒܸܠܓܝܵܐ#" , "belgyā#"}, {"ܒܸܠܓܝܼܩܵܝ", "belgīqāy"}, {"ܣܹܝܫܸܠܝܼܣ#" , "sēšellīs#"}, {"ܣܹܝܫܸܠ#", "sēšel#"}, {"ܣܹܝܫܸܠܵܝ", "sēšellāy"}, -- popular slang terms {"ܝܲܐܠܵܗ#", "yallāh#"}, {"ܘܲܐܠܵܗ#", "wallāh#"}, -- feminine imperative forms {"ܙܹܠ݇ܝ#", "zē#"}, {"ܬܵܐܝ#", "tā#"}, } function export.tr(text, lang, sc) text = rsub(text, " | ", "# | #") text = "##" .. rsub(text, " ", "# #") .. "##" text = rsub(text, "ـ", "") for _, sub in ipairs(fix) do text = rsub(text, unpack(sub)) end -- Special cases -- print(text) for _, sub in ipairs(special_cases) do text = rsub(text, unpack(sub)) end -- print(text) -- for every special case, apply substitutions for every masc genitive ending for aii_prefix, aii_prefix_corrected_tr in pairs(genitive_endings_special_cases) do for _, masc_genitive_ending in ipairs(genitive_endings) do text = rsub(text, aii_prefix .. '(' .. masc_genitive_ending .. ')' .. '#', aii_prefix_corrected_tr .. '%1#' ) end end -- Ignore siyameh text = rsub(text, combining_diaeresis, "") text = rsub(text, "ܙ" .. combining_tilde_below, "ž") text = rsub(text, "ܟ" .. combining_tilde_below, "č") text = rsub(text, "ܓ" .. combining_tilde_below, "j") text = rsub(text, "ܫ" .. combining_tilde_below, "ž") text = rsub(text, "ܙ" .. combining_tilde_above, "ž") text = rsub(text, "ܟ" .. combining_tilde_above, "č") text = rsub(text, "ܨ" .. combining_tilde_above, "ḍ") text = rsub(text, "ܫ" .. combining_tilde_above, "ž") text = rsub(text, "ܒ" .. combining_breve_below, "v") text = rsub(text, "ܦ" .. combining_breve_below, "f") text = rsub(text, "ܦ" .. qushshaya, "p") -- needs a test case text = rsub(text, "ܒ" .. qushshaya, "b") text = rsub(text, "ܬ" .. qushshaya, "t") text = rsub(text, "ܕ" .. qushshaya, "d") text = rsub(text, "ܟ" .. qushshaya, "k") text = rsub(text, "ܓ" .. qushshaya, "g") text = rsub(text, "ܒ" .. rukkakha, "ḇ") text = rsub(text, "ܬ" .. rukkakha, "ṯ") text = rsub(text, "ܕ" .. rukkakha, "ḏ") text = rsub(text, "ܟ" .. rukkakha, "ḵ") text = rsub(text, "ܓ" .. rukkakha, "ḡ") -- this covers b-, d-, w-, l- prefixing for words starting with an alaph -- https://r12a.github.io/scripts/syrc/aii.html#standalone -- and ALL special_cases starting with initial_translit_char local initial_translit_char = 'aī' -- accounts for substituted special cases starting with vowel sound local initial_char_capture = "([" .. alaph .. initial_translit_char .. "])" text = rsub(text, "#" .. bdul_capture2 .. initial_char_capture, "#%1-%2-%3") text = rsub(text, "#" .. bdul_capture .. initial_char_capture, "#%1-%2") text = rsub(text, waw .. hbasa .. "ܗ" .. combining_dot_above .. "#", TR_THIRD_PERSON_FEM_SUFFIX .. "#") text = rsub(text, yudh .. hbasa, "ī") text = rsub(text, waw .. rwaha, "ō") text = rsub(text, waw .. hbasa, TR_WAW_PLUS_RVASA) text = rsub(text, ".", tt_transpose_punc) text = rsub(text, ".", tt) text = rsub(text, "#" .. alaph .. "#", "#".. glottal_stop .."#") text = rsub(text, consonants_capture .. mhagjana_capture .. combining_macron_below .. consonants_capture, "%1e%2%3") text = rsub(text, consonants_capture .. marhetana_capture .. combining_macron .. consonants_capture, "%1%2e%3") text = rsub(text, consonants_capture .. talqana_above, "") -- doubling consonants text = rsub(text, "([" .. zlama_horizontal .. pthaha .. "])" .. consonants_capture .. diacritic_vowels_capture, "%1%2%2%3") text = rsub(text, "([" .. zlama_horizontal .. pthaha .. "])" .. consonants_capture .. TR_THIRD_PERSON_FEM_SUFFIX , "%1%2%2" .. TR_THIRD_PERSON_FEM_SUFFIX) -- text = rsub(text, combining_dot_above, "") text = rsub(text, consonants_capture .. zlama_angular .. yudh .. consonants_capture, "%1ē%2") text = rsub(text, consonants_capture .. yudh .. consonants_capture, "%1i%2") text = rsub(text, consonants_minus_glides_cg .. yudh .. "#", "%1#") text = rsub(text, alaph .. pthaha .. waw .. "#", "aw#") -- needs a test case (impossible combination of characters?) text = rsub(text, alaph .. pthaha .. yudh .. "#", "ay#") -- needs a test case text = rsub(text, "#" .. alaph .. zlama_angular .. yudh, "#ē") -- needs a test case text = rsub(text, "#" .. alaph .. yudh, "#ī") -- needs a test case text = rsub(text, "#" .. yudh .. consonants_capture, "#%1") text = rsub(text, pthaha .. alaph .. "#", "a#") -- needs a test case text = rsub(text, zlama_angular .. alaph .. "#", "ē#") text = rsub(text, zlama_horizontal .. alaph .. "#", "i" .. glottal_stop .. "#") text = rsub(text, zlama_horizontal .. alaph .. yudh .. "#", "i" .. glottal_stop .. "#") text = rsub(text, zqapha .. alaph .. "#", "ā#") -- needs a test case text = rsub(text, alaph .. "#", "ā#") -- needs a test case text = rsub(text, "#" .. alaph, "#") text = rsub(text, alaph, glottal_stop) text = rsub(text, "#" .. waw .. consonants_and_vowels_capture, "#w-%1") text = rsub(text, ".", tt_next) -- shorten waw + rvasa text = rsub(text, TR_WAW_PLUS_RVASA .. consonants_minus_glides_cg .. consonants_minus_glides_cg_2, TR_WAW_PLUS_RVASA_SHORT .. "%1%2") text = rsub(text, "([ēīā])" .. glottal_stop .. consonants_capture, "%1%2") text = rsub(text, "([" .. vowels_w .. "])([" .. vowels .. "])", "%1w%2") -- needs a test case text = rsub(text, "([" .. vowels_y .. "])([" .. vowels .. "])", "%1y%2") text = rsub(text, pharyngeal .. pharyngeal, pharyngeal) -- needs a test case text = rsub(text, glottal_stop .. glottal_stop, glottal_stop) -- needs a test case text = rsub(text, "-" .. glottal_stop, "-") text = rsub(text, "ḇḇ", "ḇ") text = rsub(text, "ḡḡ", "ḡ") text = rsub(text, "ḏḏ", "ḏ") text = rsub(text, "ḵḵ", "ḵ") text = rsub(text, "p̄p̄", "p̄") text = rsub(text, "ṯṯ", "ṯ") text = rsub(text, "āā", "ā") -- substitutions like this are preferred to be closer to the top, but it was hard to figure out how to do that -- shorten waw + rvasa a different way from before per verbal noun of the d stem local waw_cg = "([" .. consonants_minus_glides .. "wy])" text = rsub(text, '#' .. waw_cg .. TR_WAW_PLUS_RVASA .. waw_cg .. 'ā' .. waw_cg .. 'ā#', "%1" .. TR_WAW_PLUS_RVASA_SHORT .. '%2%2ā%3ā') -- local bdul_capture = '([bdwl])' -- text = rsub(text, "#" .. bdul_capture .. "([" .. vowels .. "])", "#%1-%2") text = rsub(text, "#", "") if not rmatch(text, "([-" .. vowels .. " ])") then require("Module:debug").track("aii-translit/lacking diacritics") return nil end return text end return export owhta2gitvtmvn996fdkby9001usr7a 828 37903 176317 2026-04-14T02:34:06Z Yivan000 4078 Nilikha ang pahina na may 'export = {} local match = mw.ustring.match local str_gsub = string.gsub local function ugsub(text, regex, replacement) local out = mw.ustring.gsub(text, regex, replacement) return out end local alphabet = "ⲁⲃⲅⲇⲉⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱϣϥⳉϧϩϫϭw" local vowels = "ⲁⲉⲏⲓⲟⲩⲱ" local vowel = "[" .. vowels .. "]" local consonants = ugsub(alphabet, vowel, "") local consonant = "[" .. consonants .. "]" lo...' 176317 Scribunto text/plain export = {} local match = mw.ustring.match local str_gsub = string.gsub local function ugsub(text, regex, replacement) local out = mw.ustring.gsub(text, regex, replacement) return out end local alphabet = "ⲁⲃⲅⲇⲉⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱϣϥⳉϧϩϫϭw" local vowels = "ⲁⲉⲏⲓⲟⲩⲱ" local vowel = "[" .. vowels .. "]" local consonants = ugsub(alphabet, vowel, "") local consonant = "[" .. consonants .. "]" local replacements = { ["ⲟⲩ"] = "ⲩ", ["ⳤ"] = "ⲕⲉ", ["ⲉⲓ"] = "ⲓ", ["ϯ"] = "ⲧⲓ", ["-"] = "", ["⸗"] = "", ["ˋ"] = "", } local CopticToGreek = { ["ⲁ"] = "α", ["ⲃ"] = "β", ["ⲅ"] = "γ", ["ⲇ"] = "δ", ["ⲉ"] = "ε", ["ⲍ"] = "ζ", ["ⲏ"] = "η", ["ⲑ"] = "θ", ["ⲓ"] = "ι", ["ⲕ"] = "κ", ["ⲗ"] = "λ", ["ⲙ"] = "μ", ["ⲛ"] = "ν", ["ⲝ"] = "ξ", ["ⲟ"] = "ο", ["ⲡ"] = "π", ["ⲣ"] = "ρ", ["ⲥ"] = "σ", ["ⲧ"] = "τ", ["ⲩ"] = "υ", ["ⲫ"] = "φ", ["ⲭ"] = "χ", ["ⲯ"] = "ψ", ["ⲱ"] = "ω", } function export.makeSortKey(text, lang, sc) text = mw.ustring.lower(text) for letter, replacement in pairs(replacements) do text = str_gsub(text, letter, replacement) end local origText = text text = ugsub(text, "ⲩ(" .. vowel .. ")", "w%1") text = ugsub(text, "(" .. vowel .. ")ⲩ", "%1w") -- mw.log(origText, text) local sort = {} for word in mw.ustring.gmatch(text, "%S+") do -- Add initial vowel (if any). table.insert(sort, match(word, "^" .. vowel) ) -- Add consonants (in order). table.insert(sort, ugsub(word, vowel .. "+", "")) --[[ Add the number "1" if word ends in consonant. "1" sorts before Greek–Coptic and Coptic Unicode blocks. ]] if mw.ustring.match(word, consonant .. "$") then table.insert(sort, "1") elseif mw.ustring.match(word, vowel .. "$") then table.insert(sort, "2") end -- Get non-initial vowels (in order) by removing initial vowel and all consonants. table.insert(sort, ugsub(ugsub(word, "^" .. vowel, ""), consonant, "")) table.insert(sort, " ") end sort = table.concat(sort) sort = str_gsub(sort, "w", "ⲩ") --[[ Convert Greek-derived Coptic characters to Greek ones. Otherwise, the uniquely Coptic letters would sort first, because they were added to Unicode earlier. ϣϥⳉϧϩϫϭ ⲁⲃⲅⲇⲉⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱ ⇓ αβγδεζηθικλμνξοπρστυφχψω ϣϥⳉϧϩϫϭ ]] sort = str_gsub(sort, "[\194-\244][\128-\191]+", CopticToGreek) return mw.ustring.upper(sort) end local lang = require("Module:languages").getByCode("cop") local sc = require("Module:scripts").getByCode("Copt") local function tag(text) return require("Module:script utilities").tag_text(text, lang, sc) end function export.showSorting(frame) local terms = {} for i, term in ipairs(frame.args) do table.insert(terms, term) end local function comp(term1, term2) return export.makeSortKey(term1) < export.makeSortKey(term2) end table.sort(terms, comp) for i, term in pairs(terms) do terms[i] = "\n* " .. tag(term) .. " (<code>" .. export.makeSortKey(term) .. "</code>)" end return table.concat(terms) end return export 8o899v7yx7qyh5uiyv6wmfsrsqo8b0t 828 37904 176318 2026-04-14T02:34:29Z Yivan000 4078 Nilikha ang pahina na may 'local export = {} local chars = { ["Ⲁ"] = "A", ["ⲁ"] = "a", ["Ⲃ"] = "B", ["ⲃ"] = "b", ["Ⲅ"] = "G", ["ⲅ"] = "g", ["Ⲇ"] = "D", ["ⲇ"] = "d", ["Ⲉ"] = "E", ["ⲉ"] = "e", ["Ⲍ"] = "Z", ["ⲍ"] = "z", ["Ⲏ"] = "Ē", ["ⲏ"] = "ē", ["Ⲑ"] = "Th", ["ⲑ"] = "th", ["Ⲓ"] = "I", ["ⲓ"] = "i", ["Ⲕ"] = "K", ["ⲕ"] = "k", ["Ⲗ"] = "L", ["ⲗ"] = "l", ["Ⲙ"] = "M", ["ⲙ"] = "m", ["Ⲛ"] = "N", ["ⲛ"] = "n", ["Ⲻ"] = "N", ["ⲻ"] =...' 176318 Scribunto text/plain local export = {} local chars = { ["Ⲁ"] = "A", ["ⲁ"] = "a", ["Ⲃ"] = "B", ["ⲃ"] = "b", ["Ⲅ"] = "G", ["ⲅ"] = "g", ["Ⲇ"] = "D", ["ⲇ"] = "d", ["Ⲉ"] = "E", ["ⲉ"] = "e", ["Ⲍ"] = "Z", ["ⲍ"] = "z", ["Ⲏ"] = "Ē", ["ⲏ"] = "ē", ["Ⲑ"] = "Th", ["ⲑ"] = "th", ["Ⲓ"] = "I", ["ⲓ"] = "i", ["Ⲕ"] = "K", ["ⲕ"] = "k", ["Ⲗ"] = "L", ["ⲗ"] = "l", ["Ⲙ"] = "M", ["ⲙ"] = "m", ["Ⲛ"] = "N", ["ⲛ"] = "n", ["Ⲻ"] = "N", ["ⲻ"] = "n", ["⳯"] = "n", ["Ⲳ"] = "N", ["ⲳ"] = "n", ["Ⳟ"] = "Ŋ", ["ⳟ"] = "ŋ", ["Ⳡ"] = "Ñ", ["ⳡ"] = "ñ", ["Ⳣ"] = "W", ["ⳣ"] = "w", ["Ⲝ"] = "Ks", ["ⲝ"] = "ks", ["Ⲟ"] = "O", ["ⲟ"] = "o", ["Ⲡ"] = "P", ["ⲡ"] = "p", ["Ⲣ"] = "R", ["ⲣ"] = "r", ["Ⲥ"] = "S", ["ⲥ"] = "s", ["Ⲧ"] = "T", ["ⲧ"] = "t", ["Ⲩ"] = "U", ["ⲩ"] = "u", ["Ⲫ"] = "Ph", ["ⲫ"] = "ph", ["Ⲭ"] = "Kh", ["ⲭ"] = "kh", ["Ⲯ"] = "Ps", ["ⲯ"] = "ps", ["Ⲱ"] = "Ō", ["ⲱ"] = "ō", ["Ⲿ"] = "Ō", ["ⲿ"] = "ō", ["Ϣ"] = "Š", ["ϣ"] = "š", ["Ⳇ"] = "Š", ["ⳇ"] = "š", ["Ⳅ"] = "Š", ["ⳅ"] = "š", ["Ϥ"] = "F", ["ϥ"] = "f", ["Ϧ"] = "X", ["ϧ"] = "x", ["Ⳉ"] = "X", ["ⳉ"] = "x", ["Ⳳ"] = "X", ["ⳳ"] = "x", ["Ϩ"] = "H", ["ϩ"] = "h", ["Ⳏ"] = "h", ["ⳏ"] = "h", ["Ⳑ"] = "h", ["ⳑ"] = "h", ["Ϫ"] = "J", ["ϫ"] = "j", ["Ⳗ"] = "Č", ["ⳗ"] = "č", ["Ⳙ"] = "Č", ["ⳙ"] = "č", ["Ϭ"] = "Č", ["ϭ"] = "č", ["Ⳛ"] = "C", ["ⳛ"] = "c", ["Ⳝ"] = "Ç", ["ⳝ"] = "ç", ["Ϯ"] = "Ti", ["ϯ"] = "ti", ["Ⲹ"] = "Q", ["ⲹ"] = "q", ["Ⳋ"] = "Ç", ["ⳋ"] = "ç", ["Ⳃ"] = "Ç", ["ⳃ"] = "ç", ["Ⳓ"] = "Ḫ", ["ⳓ"] = "ḫ", ["Ⳕ"] = "ḥ", ["ⳕ"] = "ḥ", ["Ⳍ"] = "ḥ", ["ⳍ"] = "ḥ", ["Ⲵ"] = "ʿ", ["ⲵ"] = "ʿ", ["ⳤ"] = "ke", ["⳦"] = "pros", ["⳧"] = "stauros", ["⳨"] = "taur", ["⳪"] = "cōis", } function export.tr(text, lang, sc) return (mw.ustring.gsub(text, '.', chars)) end return export bjntxfxk6ezvd571ahg9dsu8ftmv6rx 828 37905 176319 2026-04-14T02:36:12Z Yivan000 4078 Nilikha ang pahina na may 'local u = require("Module:string/char") local MACRON = u(0x0304) local DOTABOVE = u(0x0307) local DOTBELOW = u(0x0323) local str_gsub, ugsub = string.gsub, mw.ustring.gsub local unpack = unpack or table.unpack -- Lua 5.2 compatibility local UTF8char = '[\1-\127\194-\244][\128-\191]*' local export = {} local tab = { ["А"]='A', ["а"]='a', ["В"]='W', ["в"]='w', ["Е"]='E', ["е"]='e', ["Ё"]='Jo', ["ё"]='jo', ["Г"]='G', ["г"]='g', ["Д"]='D', ["д"...' 176319 Scribunto text/plain local u = require("Module:string/char") local MACRON = u(0x0304) local DOTABOVE = u(0x0307) local DOTBELOW = u(0x0323) local str_gsub, ugsub = string.gsub, mw.ustring.gsub local unpack = unpack or table.unpack -- Lua 5.2 compatibility local UTF8char = '[\1-\127\194-\244][\128-\191]*' local export = {} local tab = { ["А"]='A', ["а"]='a', ["В"]='W', ["в"]='w', ["Е"]='E', ["е"]='e', ["Ё"]='Jo', ["ё"]='jo', ["Г"]='G', ["г"]='g', ["Д"]='D', ["д"]='d', ["И"]='I', ["и"]='i', ["Ӣ"]='Ī', ["ӣ"]='ī', ["Й"]='J', ["й"]='j', ["К"]='K', ["к"]='k', ["Л"]='L', ["л"]='l', ["М"]='M', ["м"]='m', ["Н"]='N', ["н"]='n', ["Ӈ"]='Ŋ', ["ӈ"]='ŋ', ["О"]='O', ["о"]='o', ["П"]='P', ["п"]='p', ["Р"]='R', ["р"]='r', ["С"]='S', ["с"]='s', ["Т"]='T', ["т"]='t', ["У"]='U', ["у"]='u', ["Ӯ"]='Ū', ["ӯ"]='ū', ["Ф"]='F', ["ф"]='f', ["Х"]='H', ["х"]='h', ["Ч"]='Ç', ["ч"]='ç', ["Ы"]='I', ["ы"]='i', ["Э"]='Ə', ["э"]='ə', ["Ю"]='Ju', ["ю"]='ju', ["Я"]='Ja', ["я"]='ja', -- non-native letters ["Б"]='B', ["б"]='b', ["Ж"]='Z', ["ж"]='z', ["З"]='Z', ["з"]='z', ["Ц"]='C', ["ц"]='c', ["Ш"]='Ş', ["ш"]='ş', ["Щ"]='Ş', ["щ"]='ş', --in literary language ш is only found in Russian words and was originally represented with s, however some dialects have ш in native words ['Ъ']='ʺ', ['ъ']='ʺ', ["Ь"]="’", ["ь"]="’" } local other = { { 'Я', 'Ja' }, { 'я', 'ja' }, { 'Ё', 'Jo' }, { 'ё', 'jo' }, { 'Ю', 'Ju' }, { 'ю', 'ju' }, -- Unfortunately the Cyrillic alphabet doesn't distinguish between ʒe and ʒə { 'Де', 'Ʒe' }, { 'де', 'ʒe' }, { 'Не', 'Ņe' }, { 'не', 'ņe' }, { 'Ди', 'Ʒi' }, { 'ди', 'ʒi' }, { 'Ни', 'Ņi' }, { 'ни', 'ņi' }, { 'Дӣ', 'Ʒī' }, { 'дӣ', 'ʒī' }, { 'Нӣ', 'Ņī' }, { 'нӣ', 'ņī' }, { 'Дj', 'Ʒ' }, { 'дj', 'ʒ' }, { 'Нj', 'Ņ' }, { 'нj', 'ņ' }, } function export.tr(text, lang, sc) for i, replacement in ipairs(other) do text = str_gsub(text, unpack(replacement)) end -- е after a vowel or at the beginning of a word becomes ye -- Again, the Cyrillic alphabet doesn't distinguish between je and jə text = ugsub(text, "([АОУЫЕИӢЪЬаӣиоуыэеъьaeiou]["..MACRON..DOTABOVE..DOTBELOW.."]?)е", "%1je") text = ugsub(text, "([АОУЫЕИӢЪЬаӣиоуыэеъьaeiou]["..MACRON..DOTABOVE..DOTBELOW.."]?)и", "%1ji") text = ugsub(text, "([АОУЫЕИӢЪЬаӣиоуыэеъьaeiou]["..MACRON..DOTABOVE..DOTBELOW.."]?)ӣ", "%1jī") text = str_gsub(text, "^Е","Je") text = str_gsub(text, "^е","je") text = ugsub(text, "([^Ѐ-ӿ])Е","%1Je") text = ugsub(text, "([^Ѐ-ӿ])е","%1je") return (str_gsub(text, UTF8char, tab)) end return export iyv9e7f8bbz2mqejzxctu452v8oy4l0 828 37906 176321 2026-04-14T02:45:19Z Yivan000 4078 Nilikha ang pahina na may '-- In the |subst= parameter, as there is not a better way, use @ to force ideogram -- reading for ambiguous characters, and use + to indicate superimposition. local export = {} local gsub = mw.ustring.gsub -- Special character to ignore formatting in replacements. Only one character -- because bolding should be ignored, but tables shouldn't. local format_char = "'-" local dig_chars = { [""] = 0, ["𐄇"] = 1, ["𐄈"] = 2, ["𐄉"] = 3, ["𐄊"] = 4, ["...' 176321 Scribunto text/plain -- In the |subst= parameter, as there is not a better way, use @ to force ideogram -- reading for ambiguous characters, and use + to indicate superimposition. local export = {} local gsub = mw.ustring.gsub -- Special character to ignore formatting in replacements. Only one character -- because bolding should be ignored, but tables shouldn't. local format_char = "'-" local dig_chars = { [""] = 0, ["𐄇"] = 1, ["𐄈"] = 2, ["𐄉"] = 3, ["𐄊"] = 4, ["𐄋"] = 5, ["𐄌"] = 6, ["𐄍"] = 7, ["𐄎"] = 8, ["𐄏"] = 9, ["𐄐"] = 10, ["𐄑"] = 20, ["𐄒"] = 30, ["𐄓"] = 40, ["𐄔"] = 50, ["𐄕"] = 60, ["𐄖"] = 70, ["𐄗"] = 80, ["𐄘"] = 90, ["𐄙"] = 100, ["𐄚"] = 200, ["𐄛"] = 300, ["𐄜"] = 400, ["𐄝"] = 500, ["𐄞"] = 600, ["𐄟"] = 700, ["𐄠"] = 800, ["𐄡"] = 900, ["𐄢"] = 1000, ["𐄣"] = 2000, ["𐄤"] = 3000, ["𐄥"] = 4000, ["𐄦"] = 5000, ["𐄧"] = 6000, ["𐄨"] = 7000, ["𐄩"] = 8000, ["𐄪"] = 9000, ["𐄫"] = 10000, ["𐄬"] = 20000, ["𐄭"] = 30000, ["𐄮"] = 40000, ["𐄯"] = 50000, ["𐄰"] = 60000, ["𐄱"] = 70000, ["𐄲"] = 80000, ["𐄳"] = 90000, } local chars = { -- SYLLABOGRAMS -- ["𐀅"] = { id = "1", tl = "da" }, ["𐀫"] = { id = "2", tl = "ro" }, ["𐀞"] = { id = "3", tl = "pa" }, ["𐀳"] = { id = "4", tl = "te" }, ["𐀵"] = { id = "5", tl = "to" }, ["𐀙"] = { id = "6", tl = "na" }, ["𐀇"] = { id = "7", tl = "di" }, ["𐀀"] = { id = "8", tl = "a" }, ["𐀮"] = { id = "9", tl = "se" }, ["𐀄"] = { id = "10", tl = "u" }, ["𐀡"] = { id = "11", tl = "po" }, ["𐀰"] = { id = "12", tl = "so" }, ["𐀕"] = { id = "13", tl = "me" }, ["𐀈"] = { id = "14", tl = "do" }, ["𐀗"] = { id = "15", tl = "mo" }, ["𐀣"] = { id = "16", tl = "qa" }, ["𐀼"] = { id = "17", tl = "za" }, ["𐁐"] = { id = "18" }, ["𐁑"] = { id = "19" }, ["𐀿"] = { id = "20", tl = "zo" }, ["𐀥"] = { id = "21", tl = "qi" }, ["𐁒"] = { id = "22" }, ["𐀘"] = { id = "23", tl = "mu" }, ["𐀚"] = { id = "24", tl = "ne" }, ["𐁀"] = { id = "25", tl = "a2" }, ["𐀬"] = { id = "26", tl = "ru" }, ["𐀩"] = { id = "27", tl = "re" }, ["𐀂"] = { id = "28", tl = "i" }, ["𐁆"] = { id = "29", tl = "pu2" }, ["𐀛"] = { id = "30", tl = "ni" }, ["𐀭"] = { id = "31", tl = "sa" }, ["𐀦"] = { id = "32", tl = "qo" }, ["𐁉"] = { id = "33", tl = "ra3" }, ["𐁓"] = { id = "34" }, -- *35 is a flipped variant of *34 ["𐀍"] = { id = "36", tl = "jo" }, ["𐀴"] = { id = "37", tl = "ti" }, ["𐀁"] = { id = "38", tl = "e" }, ["𐀠"] = { id = "39", tl = "pi" }, ["𐀹"] = { id = "40", tl = "wi" }, ["𐀯"] = { id = "41", tl = "si" }, ["𐀺"] = { id = "42", tl = "wo" }, ["𐁁"] = { id = "43", tl = "a3" }, ["𐀐"] = { id = "44", tl = "ke" }, ["𐀆"] = { id = "45", tl = "de" }, ["𐀋"] = { id = "46", tl = "je" }, ["𐁔"] = { id = "47" }, ["𐁅"] = { id = "48", tl = "nwa" }, ["𐁕"] = { id = "49" }, ["𐀢"] = { id = "50", tl = "pu" }, ["𐀉"] = { id = "51", tl = "du" }, ["𐀜"] = { id = "52", tl = "no" }, ["𐀪"] = { id = "53", tl = "ri" }, ["𐀷"] = { id = "54", tl = "wa" }, ["𐀝"] = { id = "55", tl = "nu" }, ["𐁖"] = { id = "56" }, ["𐀊"] = { id = "57", tl = "ja" }, ["𐀱"] = { id = "58", tl = "su" }, ["𐀲"] = { id = "59", tl = "ta" }, ["𐀨"] = { id = "60", tl = "ra" }, ["𐀃"] = { id = "61", tl = "o" }, ["𐁇"] = { id = "62", tl = "pte" }, ["𐁗"] = { id = "63" }, ["𐁘"] = { id = "64" }, ["𐀎"] = { id = "65", tl = "ju" }, ["𐁋"] = { id = "66", tl = "ta2" }, ["𐀑"] = { id = "67", tl = "ki" }, ["𐁊"] = { id = "68", tl = "ro2" }, ["𐀶"] = { id = "69", tl = "tu" }, ["𐀒"] = { id = "70", tl = "ko" }, ["𐁃"] = { id = "71", tl = "dwe" }, ["𐀟"] = { id = "72", tl = "pe" }, ["𐀖"] = { id = "73", tl = "mi" }, ["𐀽"] = { id = "74", tl = "ze" }, ["𐀸"] = { id = "75", tl = "we" }, ["𐁈"] = { id = "76", tl = "ra2" }, ["𐀏"] = { id = "77", tl = "ka" }, ["𐀤"] = { id = "78", tl = "qe" }, ["𐁙"] = { id = "79" }, ["𐀔"] = { id = "80", tl = "ma" }, ["𐀓"] = { id = "81", tl = "ku" }, ["𐁚"] = { id = "82" }, ["𐁛"] = { id = "83" }, -- *84 ["𐁂"] = { id = "85", tl = "au" }, ["𐁜"] = { id = "86" }, ["𐁌"] = { id = "87", tl = "twe" }, -- *88 ["𐁝"] = { id = "89" }, ["𐁄"] = { id = "90", tl = "dwo" }, ["𐁍"] = { id = "91", tl = "two" }, -- IDEOGRAMS -- ["𐂀"] = { id = "100", tl = "VIR" }, -- *101 is a variant of *100 ["𐂁"] = { id = "102", tl = "MUL" }, -- *103 is a variant of *102 ["𐂂"] = { id = "104", tl = "CERV" }, ["𐂃"] = { id = "105", tl = "EQU" }, ["𐂄"] = { id = "105f", tl = "EQU^f" }, ["𐂅"] = { id = "105m", tl = "EQU^m" }, ["@𐀥"] = { id = "106", tl = "OVIS" }, -- same as *21 ["𐂆"] = { id = "106f", tl = "OVIS^f" }, ["𐂇"] = { id = "106m", tl = "OVIS^m" }, ["@𐁒"] = { id = "107", tl = "CAP" }, -- same as *22 ["𐂈"] = { id = "107f", tl = "CAP^f" }, ["𐂉"] = { id = "107m", tl = "CAP^m" }, ["@𐁂"] = { id = "108", tl = "SUS" }, -- same as *85 ["𐂊"] = { id = "108f", tl = "SUS^f" }, ["𐂋"] = { id = "108m", tl = "SUS^m" }, ["@𐀘"] = { id = "109", tl = "BOS" }, -- same as *23 ["𐂌"] = { id = "109f", tl = "BOS^f" }, ["𐂍"] = { id = "109m", tl = "BOS^m" }, ["𐄿"] = { id = "110", tl = "Z" }, ["𐄾"] = { id = "111", tl = "V" }, ["𐄼"] = { id = "112", tl = "T" }, ["𐄽"] = { id = "113", tl = "S" }, ["𐄻"] = { id = "114", tl = "Q" }, ["𐄺"] = { id = "115", tl = "P" }, ["𐄹"] = { id = "116", tl = "N" }, ["𐄸"] = { id = "117", tl = "M" }, ["𐄷"] = { id = "118", tl = "L" }, ["𐂎"] = { id = "120", tl = "GRA" }, ["𐂏"] = { id = "121", tl = "HORD" }, ["𐂐"] = { id = "122", tl = "OLIV" }, ["𐂑"] = { id = "123", tl = "AROM" }, -- *124 is a flipped variant of *125, traditionally transliterated as PYC ["𐂒"] = { id = "125", tl = "CYP" }, -- *126 ["𐂓"] = { id = "127", tl = "ka+po" }, ["𐂔"] = { id = "128", tl = "ka+na+ko" }, ["@𐀎"] = { id = "129", tl = "FAR" }, -- same as *65 ["𐂕"] = { id = "130", tl = "OLE" }, ["𐂖"] = { id = "131", tl = "VIN" }, ["𐂗"] = { id = "132" }, ["𐂘"] = { id = "133", tl = "a+re+pa" }, -- *134 ["𐂙"] = { id = "135", tl = "me+ri", }, ["𐂚"] = { id = "140", tl = "AES" }, ["𐂛"] = { id = "141", tl = "AUR" }, ["𐂜"] = { id = "142" }, -- *143 ["@𐁉"] = { id = "144", tl = "CROC" }, -- same as *33 ["𐂝"] = { id = "145", tl = "LANA" }, ["𐂞"] = { id = "146" }, -- *147, *148, *149 ["𐂟"] = { id = "150" }, ["𐂠"] = { id = "151", tl = "CORN" }, ["𐂡"] = { id = "152" }, ["𐂢"] = { id = "153" }, ["𐂣"] = { id = "154" }, ["𐃞"] = { id = "155", vas = true }, ["𐂤"] = { id = "156", tl = "tu+ro2" }, ["𐂥"] = { id = "157" }, ["𐂦"] = { id = "158" }, ["𐂧"] = { id = "159", tl = "TELA" }, ["𐂨"] = { id = "160" }, ["𐂩"] = { id = "161" }, ["𐂪"] = { id = "162", tl = "TUN" }, ["𐂫"] = { id = "163", tl = "ARM" }, ["𐂬"] = { id = "164" }, ["𐂭"] = { id = "165" }, ["𐂮"] = { id = "166" }, ["𐂯"] = { id = "167" }, ["𐂰"] = { id = "168" }, ["𐂱"] = { id = "169" }, ["𐂲"] = { id = "170" }, ["𐂳"] = { id = "171" }, ["𐂴"] = { id = "172" }, ["𐂵"] = { id = "173", tl = "LUNA" }, ["𐂶"] = { id = "174" }, -- *175 ["𐂷"] = { id = "176", tl = "ARB" }, ["𐂸"] = { id = "177" }, ["𐂹"] = { id = "178" }, ["𐂺"] = { id = "179" }, ["𐂻"] = { id = "180" }, ["𐂼"] = { id = "181" }, ["𐂽"] = { id = "182" }, ["𐂾"] = { id = "183" }, ["𐂿"] = { id = "184" }, ["𐃀"] = { id = "185" }, -- *186, *187, *188 ["𐃁"] = { id = "189" }, ["𐃂"] = { id = "190" }, ["𐃃"] = { id = "191", tl = "GAL" }, ["𐃟"] = { id = "200", vas = true }, ["𐃠"] = { id = "201", vas = true }, ["𐃡"] = { id = "202", vas = true }, ["𐃢"] = { id = "203", vas = true }, ["𐃣"] = { id = "204", vas = true }, ["𐃤"] = { id = "205", vas = true }, ["𐃥"] = { id = "206", vas = true }, ["𐃦"] = { id = "207", vas = true }, ["𐃧"] = { id = "208", vas = true }, ["𐃨"] = { id = "209", tl = "AMPH", vas = true }, ["𐃩"] = { id = "210", vas = true }, ["𐃪"] = { id = "211", vas = true }, ["𐃫"] = { id = "212", vas = true }, ["𐃬"] = { id = "213", vas = true }, ["𐃭"] = { id = "214", vas = true }, ["𐃮"] = { id = "215", vas = true }, ["𐃯"] = { id = "216", vas = true }, ["𐃰"] = { id = "217", vas = true }, ["𐃱"] = { id = "218", vas = true }, ["𐃲"] = { id = "219", vas = true }, ["𐃄"] = { id = "220" }, ["𐃳"] = { id = "221", vas = true }, ["𐃴"] = { id = "222", vas = true }, ["𐃅"] = { id = "225", tl = "ALV" }, ["𐃵"] = { id = "226", vas = true }, ["𐃶"] = { id = "227", vas = true }, ["𐃷"] = { id = "228", vas = true }, ["𐃸"] = { id = "229", vas = true }, ["𐃆"] = { id = "230", tl = "HAS" }, ["𐃇"] = { id = "231", tl = "SAG" }, ["𐃈"] = { id = "232" }, ["𐃉"] = { id = "233", tl = "PUG" }, ["𐃊"] = { id = "234" }, -- *235 ["𐃋"] = { id = "236", tl = "GUP" }, -- *237, *238, *239 ["𐃌"] = { id = "240", tl = "BIG" }, ["𐃍"] = { id = "241", tl = "CUR" }, ["𐃎"] = { id = "242", tl = "CAPS" }, ["𐃏"] = { id = "243", tl = "ROTA" }, -- *244, variant of *243 ? ["𐃐"] = { id = "245" }, ["𐃑"] = { id = "246" }, ["𐃒"] = { id = "247", tl = "di+pte" }, ["𐃓"] = { id = "248" }, ["𐃔"] = { id = "249" }, ["𐃹"] = { id = "250", vas = true }, ["𐃕"] = { id = "251" }, ["𐃖"] = { id = "252" }, ["𐃗"] = { id = "253" }, ["𐃘"] = { id = "254", tl = "JAC" }, ["𐃙"] = { id = "255" }, ["𐃚"] = { id = "256" }, ["𐃛"] = { id = "257" }, ["𐃜"] = { id = "258" }, ["𐃝"] = { id = "259" }, ["𐃺"] = { id = "305", vas = true }, -- enwikt-original ideogram abbreviations ["@𐀭"] = { id = "31", tl = "LIN" }, -- often SA despite being an ideogram } function export.tr(text, lang, sc) -- Put a hyphen between syllabograms. for i = 1, 2 do text = gsub(text, "([𐀀-𐁝%]]"..format_char .. "[%[%]%{%}⟦⟧⟨⟩/]?" .. format_char..")([𐀀-𐁝])", "%1-%2") end -- Numerals. text = gsub(text, "[𐄇-𐄳]+", function(str) local ret, count = gsub(str, "^([𐄫-𐄳]?)([𐄢-𐄪]?)([𐄙-𐄡]?)([𐄐-𐄘]?)([𐄇-𐄏]?)$", function (u5, u4, u3, u2, u1) return dig_chars[u5] + dig_chars[u4] + dig_chars[u3] + dig_chars[u2] + dig_chars[u1] end) if count ~= 1 then error("The number " .. str .. " is weird. Are you sure?") end return ret end) -- Syllabograms and ideograms. text = gsub(text, "@?[𐀀-𐃺𐄷-𐄿]", function(x_text) x = chars[x_text] if x == nil then error("The symbol " .. x_text .. " is not recognised.") end return x.tl or ("*"..x.id..(x.vas and "^VAS" or "")) end) -- Symbols. text = gsub(text, "(𐄀 ?"..format_char.." ?%] ?"..format_char.." ?)-", "%1") text = gsub(text, " ?𐄀 ?", ", ") text = gsub(text, " ([%]%}⟧⟩]) *", "%1 ") text = gsub(text, " *([%[%{⟦⟨]) ", " %1") -- The end. return text end return export rcvckveyucas7cxzxanmunutk3vstnn 828 37907 176322 2026-04-14T02:48:29Z Yivan000 4078 Nilikha ang pahina na may 'local export = {} local toNFD = mw.ustring.toNFD local noDecompose = { ["ё"] = true, ["Ё"] = true, ["й"] = true, ["Й"] = true, } local twoChars = { ["де"] = "ʒe", ["Де"] = "Ʒe", ["ДЕ"] = "ƷE", ["дё"] = "ʒo", ["Дё"] = "Ʒo", ["ДЁ"] = "ƷO", ["ди"] = "ʒi", ["Ди"] = "Ʒi", ["ДИ"] = "ƷI", ["дю"] = "ʒu", ["Дю"] = "Ʒu", ["ДЮ"] = "ƷU", ["дя"] = "ʒa", ["Дя"] = "Ʒa", ["ДЯ"] = "ƷA", ["дь"] = "ʒ", ["Дь"] = "Ʒ",...' 176322 Scribunto text/plain local export = {} local toNFD = mw.ustring.toNFD local noDecompose = { ["ё"] = true, ["Ё"] = true, ["й"] = true, ["Й"] = true, } local twoChars = { ["де"] = "ʒe", ["Де"] = "Ʒe", ["ДЕ"] = "ƷE", ["дё"] = "ʒo", ["Дё"] = "Ʒo", ["ДЁ"] = "ƷO", ["ди"] = "ʒi", ["Ди"] = "Ʒi", ["ДИ"] = "ƷI", ["дю"] = "ʒu", ["Дю"] = "Ʒu", ["ДЮ"] = "ƷU", ["дя"] = "ʒa", ["Дя"] = "Ʒa", ["ДЯ"] = "ƷA", ["дь"] = "ʒ", ["Дь"] = "Ʒ", ["ДЬ"] = "Ʒ", ["нг"] = "ӈ", ["Нг"] = "Ӈ", ["НГ"] = "Ӈ", } local tab = { ["а"] = "a", ["А"] = "A", ["б"] = "b", ["Б"] = "B", ["в"] = "w", ["В"] = "W", ["г"] = "g", ["Г"] = "G", ["д"] = "d", ["Д"] = "D", ["е"] = "je", ["Е"] = "Je", ["ё"] = "jo", ["Ё"] = "Jo", ["ж"] = "ž", ["Ж"] = "Ž", ["з"] = "z", ["З"] = "Z", ["и"] = "i", ["И"] = "I", ["й"] = "j", ["Й"] = "J", ["к"] = "k", ["К"] = "K", ["л"] = "l", ["Л"] = "L", ["м"] = "m", ["М"] = "M", ["н"] = "n", ["Н"] = "N", ["ӈ"] = "ŋ", ["Ӈ"] = "Ŋ", ["о"] = "o", ["О"] = "O", ["п"] = "p", ["П"] = "P", ["р"] = "r", ["Р"] = "R", ["с"] = "s", ["С"] = "S", ["т"] = "t", ["Т"] = "T", ["у"] = "u", ["У"] = "U", ["ф"] = "f", ["Ф"] = "F", ["х"] = "h", ["Х"] = "H", ["ц"] = "c", ["Ц"] = "C", ["ч"] = "č", ["Ч"] = "Č", ["ш"] = "š", ["Ш"] = "Š", ["щ"] = "š", ["Щ"] = "Š", ["ъ"] = "ʺ", ["Ъ"] = "ʺ", ["ы"] = "y", ["Ы"] = "Y", ["ь"] = "ʹ", ["Ь"] = "ʹ", ["э"] = "e", ["Э"] = "E", ["ю"] = "ju", ["Ю"] = "Ju", ["я"] = "ja", ["Я"] = "Ja", } function export.tr(text, lang, sc) -- Decompose (except ё/Ё and й/Й) to simplify conversion of letters with macrons. text = text:gsub("[%z\1-\127\194-\244][\128-\191]*", function(m) if not noDecompose[m] then return toNFD(m) end end) for digraph, replacement in pairs(twoChars) do text = text:gsub(digraph, replacement) end return mw.ustring.toNFC((text:gsub("[%z\1-\127\194-\244][\128-\191]*", tab))) end return export 94a8vyaaww16gnqeope2d4mdx9iqkqj 828 37908 176323 2026-04-14T02:48:57Z Yivan000 4078 Nilikha ang pahina na may 'local u = require("Module:string/char") local export = {} local mapping1 = { ["п"] = "p", ["б"] = "b", ["т"] = "t", ["д"] = "d", ["к"] = "k", ["г"] = "g", ["ц"] = "c", ["ч"] = "č", ["с"] = "s", ["з"] = "z", ["ш"] = "š", ["ж"] = "ž", ["х"] = "x", ["м"] = "m", ["н"] = "n", ["р"] = "r", ["л"] = "l", ["в"] = "v", ["й"] = "y", ["и"] = "i", ["е"] = "e", ["э"] = "e", ["а"] = "a", ["о"] = "o", ["у"] = "u", ["ӥ"] = "ü", ["ъ"] = "...' 176323 Scribunto text/plain local u = require("Module:string/char") local export = {} local mapping1 = { ["п"] = "p", ["б"] = "b", ["т"] = "t", ["д"] = "d", ["к"] = "k", ["г"] = "g", ["ц"] = "c", ["ч"] = "č", ["с"] = "s", ["з"] = "z", ["ш"] = "š", ["ж"] = "ž", ["х"] = "x", ["м"] = "m", ["н"] = "n", ["р"] = "r", ["л"] = "l", ["в"] = "v", ["й"] = "y", ["и"] = "i", ["е"] = "e", ["э"] = "e", ["а"] = "a", ["о"] = "o", ["у"] = "u", ["ӥ"] = "ü", ["ъ"] = "ʾ", } local mapping2 = { ["пӏ"] = "p’", ["тӏ"] = "t’", ["кӏ"] = "k’", ["къ"] = "q’", ["цӏ"] = "c’", ["лӏ"] = "ƛ", ["кь"] = "ƛ’", ["чӏ"] = "c’", ["хъ"] = "q", ["лъ"] = "λ", ["гъ"] = "ġ", ["хӏ"] = "ḥ", ["гӏ"] = "a̯", ["гь"] = "h", ["кӏв"] = "k’ʷ", ["хъв"] = "qʷ", ["къв"] = "q’ʷ", ["гъв"] = "ġʷ", ["хв"] = "xʷ", } function export.tr(text, lang, sc) local str_gsub = string.gsub local UTF8_char = "[%z\1-\127\194-\244][\128-\191]*" -- Convert capital to lowercase palochka. text = str_gsub(text, u(0x4C0), u(0x4CF)) for pat, repl in pairs(mapping2) do text = str_gsub(text, pat, repl) end text = str_gsub(text, UTF8_char, mapping1) return text end return export dpo9q6i35ahmr6m3umt1z8qvanwjka0 828 37909 176324 2026-04-14T02:51:32Z Yivan000 4078 Nilikha ang pahina na may 'local u = require("Module:string/char") local export = {} local mapping1 = { ["п"] = "p", ["б"] = "b", ["т"] = "t", ["д"] = "d", ["к"] = "k", ["г"] = "g", ["ц"] = "c", ["ч"] = "č", ["с"] = "s", ["з"] = "z", ["ш"] = "š", ["ж"] = "ž", ["х"] = "x", ["м"] = "m", ["н"] = "n", ["р"] = "r", ["л"] = "l", ["в"] = "v", ["й"] = "y", ["а"] = "a", ["е"] = "e", ["э"] = "e", ["и"] = "i", ["о"] = "o", ["у"] = "u", ["ы"] = "ɨ", ["ā"]...' 176324 Scribunto text/plain local u = require("Module:string/char") local export = {} local mapping1 = { ["п"] = "p", ["б"] = "b", ["т"] = "t", ["д"] = "d", ["к"] = "k", ["г"] = "g", ["ц"] = "c", ["ч"] = "č", ["с"] = "s", ["з"] = "z", ["ш"] = "š", ["ж"] = "ž", ["х"] = "x", ["м"] = "m", ["н"] = "n", ["р"] = "r", ["л"] = "l", ["в"] = "v", ["й"] = "y", ["а"] = "a", ["е"] = "e", ["э"] = "e", ["и"] = "i", ["о"] = "o", ["у"] = "u", ["ы"] = "ɨ", ["ā"] = "ā", ["е̄"] = "ē", ["ӣ"] = "ī", ["о̄"] = "ō", ["ӯ"] = "ū", ["ы̄"] = "ɨ̄", ["ъ"] = "ʾ", } local mapping2 = { ["пӏ"] = "p’", ["тӏ"] = "t’", ["кӏ"] = "k’", ["къ"] = "q’", ["цӏ"] = "c’", ["лӏ"] = "ƛ", ["кь"] = "ƛ’", ["чӏ"] = "č’", ["хъ"] = "q", ["лъ"] = "λ", ["гъ"] = "ġ", ["хӏ"] = "ḥ", ["гӏ"] = "a̯", ["гь"] = "h", ["аᵸ"] = "ã", ["еᵸ"] = "ẽ", ["эᵸ"] = "ẽ", ["иᵸ"] = "ĩ", ["оᵸ"] = "õ", ["уᵸ"] = "ũ", ["аӏ"] = "aʿ", ["еӏ"] = "eʿ", ["иӏ"] = "iʿ", ["оӏ"] = "oʿ", ["уӏ"] = "uʿ", } function export.tr(text, lang, sc) local str_gsub = string.gsub local UTF8_char = "[%z\1-\127\194-\244][\128-\191]*" text = str_gsub(text, u(0x4C0), u(0x4CF)) for pat, repl in pairs(mapping2) do text = str_gsub(text, pat, repl) end text = str_gsub(text, UTF8_char, mapping1) return text end return export 01w56uluv1cv4lkv8fi89ri4jtn3vfu 4 37910 176328 2026-04-14T08:53:42Z Yivan000 4078 Nilikha ang pahina na may '{{main|Wiktionary:List of languages|Wiktionary:Languages}} {{shortcut|WT:LOLS|WT:LOL/S}} Nililista ng pahinang ito ang mga wikang espesyal. This page lists languages by any particular property that they may have. ==Di maaari sa pangunahing ngalan-espasyo== Hindi puwedeng gamitin ang mga ito sa mga entrada sa pangunahing ngalan-espasyo; sa Apendise o sa Rekonstruksiyon lamang. ===Mga wikang narekonstruwir=== {{#invoke:list of languages|show|type|reconstructed}}...' 176328 wikitext text/x-wiki {{main|Wiktionary:List of languages|Wiktionary:Languages}} {{shortcut|WT:LOLS|WT:LOL/S}} Nililista ng pahinang ito ang mga wikang espesyal. This page lists languages by any particular property that they may have. ==Di maaari sa pangunahing ngalan-espasyo== Hindi puwedeng gamitin ang mga ito sa mga entrada sa pangunahing ngalan-espasyo; sa Apendise o sa Rekonstruksiyon lamang. ===Mga wikang narekonstruwir=== {{#invoke:list of languages|show|type|reconstructed}} ===Mga wikang narekonstruwir na menor=== {{#invoke:list of languages|show|type|appendix-constructed}} ==With sort key or diacritic removal== These languages have the <code>sort_key</code> and/or <code>entry_name</code> value set. These properties are used to generate a sort key or an entry name, by removing diacritics and the like. {{#invoke:list of languages|show|subst}} ==Meta-codes== {{#invoke:list of languages|show|special}} ==Mga wikang pang-etimolohiya lamang== {{shortcut|WT:LOL/E}} {{#invoke:list of languages|show_etym}} [[Category:Lahat ng wika]] jfcfqxqymyqelbmkwarwsaq3xu97fey