Modul:Language/data

local U = mw.ustring.char-- Diacritics, from the [[Combining Diacritical Marks]] block.local grave        = U(0x300)local acute        = U(0x301)local circumflex   = U(0x302)local tilde        = U(0x303)local macron       = U(0x304)local breve        = U(0x306)local dot          = U(0x307)local diaeresis    = U(0x308)local double_acute = U(0x30B)local double_grave = U(0x30F)local invbreve     = U(0x311)local dot_below    = U(0x323)local undertie     = U(0x35C)--[[This is a table of Wiktionary language codes with data belonging to them.Name is the "canonical name" used on Wiktionary.Article is the Wikipedia article.Script is the ISO 15924 code.]]local data = {["languages"] = {["ab"] = {["name"] = "abhaščina",},["ang"] = {["name"] = "stara angleščina",["article"] = {"stara angleščina"},-- ["scripts"] = {"Latn"},-- Remove macrons, acutes, and overdots["replacements"] = {decompose = true,from = { "[" .. macron .. acute .. dot .. "]" },},},["ar"] = {["name"] = "arabščina",["article"] = "arabščina",-- ["scripts"] = { "Arab" },["direction"] = "rtl", -- Should be in the script data module.["replacements"] = {-- ālif with wasla is replaced by ālif;[U(0x0671)] = U(0x0627),-- taṭwīl, fatḥatan, ḍammatan, kasratan,-- fatḥa, ḍamma, kasra,-- shadda, sukūn, and superscript (dagger) ālif are removed.["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)..U(0x064E)..U(0x064F)..U(0x0650)..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",},},["av"] = {["name"] = "avarščina"},["be"] = {["article"] = "beloruščina",-- ["scripts"] = { "Cyrl" },["replacements"] = { [acute] = "", },},["bn"] = {["name"] = "bengalščina",["article"] = "bengalščina",-- ["scripts"] = { "Beng" },},["bua"] = {["name"] = "burjatščina",},["cel-pro"] = {["name"] = "prakeltščina",["Wikipedia_code"] = "cel-x-proto",},["cu"] = {["name"] = "starocerkvena slovanščina",["article"] = "starocerkvena slovanščina",-- ["scripts"] = { "Cyrs" },},["de"] = {["name"] = "nemščina",["article"] = "nemščina",-- ["scripts"] = { "Latn" },--[[["replacements"] = {["ae"]    = "ä",["oe"]    = "ö",["ue"]    = "ü",["A[Ee]"] = "Ä",["O[Ee]"] = "Ö",["U[Ee]"] = "Ü",},]]},["en"] = {["name"] = "angleščina",["article"] = "angleščina",-- ["scripts"] = { "Latn" },},["es"] = {["name"] = "španščina",["article"] = "španščina",-- ["scripts"] = { "Latn" },},["egy"] = {["name"] = "egipščanščina",},["fr"] = {["name"] = "francoščina",["article"] = "francoščina",-- ["scripts"] = { "Latn" },},["frm"] = {["name"] = "srednja francoščina",["article"] = "srednja francoščina",-- ["scripts"] = { "Latn" },},["frp"] = {["name"] = "frankoprovansalščina",},["ff"] = {["name"] = "fulščina",},["gem-pro"] = {["name"] = "pragermanščina",["article"] = "pragermanščina",-- ["scripts"] = { "Latn" },["type"] = "reconstructed",["replacements"] = {},["Wikipedia_code"] = "gem-x-proto",},["gmw-ecg"] = {["name"] = "East Central German",},["got"] = {["name"] = "gotščina",["article"] = "gotščina",-- ["scripts"] = { "Goth" },["replacements"] = {-- Latin to Gothic since people will not want to have to copy-- and paste Gothic letters in["[AÁaáĀā]"] = "𐌰",["[Bb]"]     = "𐌱",["[Gg]"]     = "𐌲",["[Dd]"]     = "𐌳",["[EeĒē]"]   = "𐌴",["[Qq]"]     = "𐌵",["[Zz]"]     = "𐌶",["[Hh]"]     = "𐌷",["[Þþ]"]     = "𐌸",["[IiÍí]"]   = "𐌹",["[Kk]"]     = "𐌺",["[Ll]"]     = "𐌻",["[Mm]"]     = "𐌼",["[Nn]"]     = "𐌽",["[Jj]"]     = "𐌾",["[UuÚúŪū]"] = "𐌿",["[Pp]"]     = "𐍀",["[Rr]"]     = "𐍂",["[Ss]"]     = "𐍃",["[Tt]"]     = "𐍄",["[WwYy]"]   = "𐍅",["[Ff]"]     = "𐍆",["[Xx]"]     = "𐍇",["[Ƕƕ]"]    = "𐍈", -- Not sure if "hw" and "hv" can safely be converted["[OoŌō]"]   = "𐍉",},},["gsw"] = {["name"] = "alemanska nemščina",},["grc"] = {["name"] = "stara grščina",["article"] = "stara grščina",-- ["scripts"] = { "Grek" },["replacements"] = {decompose = true,from = {-- Replace variant letterforms with standard ones."ϐ", "ϵ", "ϑ", "ϰ", "ϱ", "ϲ", "ϕ",-- Remove macrons and breves."[" .. macron .. breve .. undertie .. "]"},to   = {"β", "ε", "θ", "κ", "ρ", "σ", "φ",}},},["grk-pro"] = {["name"] = "pragrščina",["Wikipedia_name"] = "pragrščina",["article"] = "pragrščina",-- ["scripts"] = { "Latn" },["type"] = "reconstructed",["replacements"] = {},},["ha"] = {["name"] = "havščina",-- remove tilde, grave, acute, macron, circumflex["replacements"] = {decompose = true,from = { "[" .. grave .. circumflex .. macron .. acute .. tilde .. "]" },},},["hi"] = {["name"] = "hindijščina",["article"] = "hindijščina",-- ["scripts"] = { "Deva" },},["ine-bsl-pro"] = {["name"] = "prabaltoslovanščina",["article"] = "prabaltoslovanščina",["type"] = "reconstructed",},["ine-pro"] = {["name"] = "praindoevropščina",["article"] = "indoevropski prajezik",-- ["scripts"] = { "Latn" },["type"] = "reconstructed",["replacements"] = {},["Wikipedia_code"] = "ine-x-proto",},["ja"] = {["name"] = "japonščina",["article"] = "japonščina",-- ["scripts"] = { "Jpan" },},["jbo"] = { -- Lojban["type"] = "appendix",},["la"] = {["name"] = "latinščina",["article"] = "latinščina",-- ["scripts"] = { "Latn" },["replacements"] = {-- Remove macrons, breves, and diaereses.decompose = true,from = { "[" .. macron .. breve .. diaeresis .. "]" },},},["lt"] = {["name"] = "litovščina",["article"] = "litovščina",-- remove acute, tilde, grave["replacements"] = {decompose = true,from = { "[" .. acute .. tilde .. grave .. "]" },},},["moe"] = {["name"] = "krijščina",["article"] = "krijščina",-- ["scripts"] = { "Latn" },},["mul"] = {["name"] = "translingvalno",["article"] = "",-- ["scripts"] = { "" },},["nci"] = {["name"] = "klasična nahuatlščina",["article"] = "klasična nahuatlščina",-- ["scripts"] = {"Latn"},-- Remove macrons, acutes, circumflexes and graves["replacements"] = {decompose = true,-- Remove macrons, acutes, circumflexes, graves, and saltillo;-- see [[Saltillo (linguistics)]].from = { "[" .. grave .. acute .. macron .. circumflex .. "Ꞌꞌʻʼ'ʔ]" },},},["nds-de"] = {["name"] = "nizka nemščina",},["oj"] = {["name"] = "anašinabščina",["article"] = "anašinabščina",-- ["scripts"] = { "Latn" },},["orv"] = {["name"] = "stara vzhodna slovanščina",["article"] = "stara vzhodna slovanščina",-- ["scripts"] = { "Cyrs" },["replacements"] = {[U(0x484)] = "",},},["pt"] = {["name"] = "portugalščina",["article"] = "portugalščina",-- ["scripts"] = { "Latn" },},["pa"] = {["name"] = "pandžabščina",["article"] = "pandžabščina",-- ["scripts"] = { "Guru", "Arab", },},["ru"] = {["name"] = "ruščina",["article"] = "ruščina",-- ["scripts"] = { "Cyrl" },["replacements"] = { [acute] = "", },},["rw"] = {["name"] = "Rwanda-Rundi",},["se"] = {["replacements"] = {["([đflmnŋrsšŧv])'%1"] = "%1%1",},},["sh"] = {["article"] = "srbohrvaščina",-- ["scripts"] = { "Latn", "Cyrl" },["replacements"] = {decompose = true,from =  { "([AaEeIiOoUuRrАаЕеИиОоУуРр])[" .. double_grave.. grave .. invbreve .. acute .. macron .. tilde .. "]" },to   = { "%1" },},},["sla-pro"] = {["name"] = "praslovanščina", -- also Common Slavic["type"] = "reconstructed",-- ["scripts"] = { "Latn" },["replacements"] = {["[ÀÁÃĀȀȂ]"] = "A",["[àáãāȁȃ]"] = "a",["[ÈÉẼĒȄȆ]"] = "E",["[èéẽēȅȇ]"] = "e",["[ÌÍĨĪȈȊ]"] = "I",["[ìíĩīȉȋ]"] = "i",["[ÒÓÕŌȌȎŐ]"] = "O", ["[òóõōȍȏő]"] = "o",["[ÙÚŨŪȔȖŰ]"] = "U",["[ùúũūȕȗű]"] = "u",["[ỲÝỸȲ]"] = "Y",["[ỳýỹȳ]"] = "y",["Ǭ"] = "Ǫ",["ǭ"] = "ǫ",["[" .. grave .. acute .. double_acute .. tilde .. macron .. double_grave .. invbreve .. "]"] = "",["ĭ"] = "ь",["ŭ"] = "ъ",},},["uk"] = {["article"] = "ukrajinščina",-- ["scripts"] = { "Cyrl" },["replacements"] = { [acute] = "", }},["ur"] = {["name"] = "urdujščina",["article"] = "urdujščina",-- ["scripts"] = { "Arab" },},["zh"] = {["name"] = "kitajščina",["article"] = "kitajščina",-- ["scripts"] = { "Hani" },},["xcl"] = {["name"] = "stara armenščina",["article"] = "klasična armenščina",-- ["scripts"] = { "Armn" },["replacements"] = {["[՞՜՛՟]"] = "",["և"] = "եւ",},},["xvn"] = {["name"] = "vandalščina",["article"] = "vandalščina",-- ["scripts"] = { "Latn" },},--[[[""] = {["name"] = "",["article"] = "",-- ["scripts"] = { "" },},[""] = {["name"] = "",["article"] = "",-- ["scripts"] = { "" },["replacements"] = {},},]]},-- Here, keys (for example, "gem") are Wikipedia language codes used in-- {{lang}}, and values (for example, "gem-pro") are the equivalent Wiktionary-- code.-- Subtags are not currently supported.["redirects"] = {["aae"] = "sq",["aiq"] = "fa",["aln"] = "sq",["als"] = "sq",["azb"] = "az",["azj"] = "az",["bgn"] = "bal",["bs"] = "sh",["bxr"] = "bua",["cel-x-proto"] = "cel-pro",["ciw"] = "oj",["cnr"] = "sh",["fil"] = "tl",["fuf"] = "ff",["gem"] = "gem-pro", -- Not correct, but is commonly used.["gem-x-proto"] = "gem-pro",["hak"] = "zh",["hbo"] = "he",["hr"] = "sh",["ine"] = "ine-pro", -- Not correct, but might be commonly used.["ine-x-proto"] = "ine-pro",["kjv"] = "sh",["nan"] = "zh",["prs"] = "fa",["rn"] = "rw",["sli"] = "gmw-ecg",["sr"] = "sh",["src"] = "sc",["sro"] = "sc",["tw"] = "ak",["wae"] = "gsw",["wep"] = "nds-de",["yue"] = "zh",["xno"] = "fro",},}return data