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 caron        = U(0x30C) 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"] = "Abkhaz", }, ["ang"] = { ["name"] = "Old English", ["article"] = {"Old English"}, -- ["scripts"] = {"Latn"}, -- Remove macrons, acutes, and overdots ["replacements"] = { decompose = true, from = { "[" .. macron .. acute .. dot .. "]" }, }, }, ["ar"] = { ["name"] = "Arabic", ["article"] = "Arabic language", -- ["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"] = "Avar" }, ["be"] = { ["article"] = "Belarusian language", -- ["scripts"] = { "Cyrl" }, ["replacements"] = { [acute] = "", }, }, ["bn"] = { ["name"] = "Bengali", ["article"] = "Bengali language", -- ["scripts"] = { "Beng" }, }, ["bua"] = { ["name"] = "Buryat", }, ["cel-pro"] = { ["name"] = "Proto-Celtic", ["Wikipedia_code"] = "cel-x-proto", }, ["cu"] = { ["name"] = "Old Church Slavonic", ["article"] = "Old Church Slavonic", -- ["scripts"] = { "Cyrs" }, }, ["de"] = { ["name"] = "German", ["article"] = "German language", -- ["scripts"] = { "Latn" }, --[[ ["replacements"] = { ["ae"]    = "ä", ["oe"]    = "ö", ["ue"]    = "ü", ["A[Ee]"] = "Ä", ["O[Ee]"] = "Ö", ["U[Ee]"] = "Ü", }, ]] }, ["en"] = { ["name"] = "English", ["article"] = "English language", -- ["scripts"] = { "Latn" }, }, ["es"] = { ["name"] = "Spanish", ["article"] = "Spanish language", -- ["scripts"] = { "Latn" }, }, ["egy"] = { ["name"] = "Egyptian", }, ["fr"] = { ["name"] = "French", ["article"] = "French language", -- ["scripts"] = { "Latn" }, }, ["frm"] = { ["name"] = "Middle French", ["article"] = "Middle French", -- ["scripts"] = { "Latn" }, }, ["frp"] = { ["name"] = "Franco-Provençal", }, ["ff"] = { ["name"] = "Fula", }, ["gem-pro"] = { ["name"] = "Proto-Germanic", ["article"] = "Proto-Germanic language", -- ["scripts"] = { "Latn" }, ["type"] = "reconstructed", ["replacements"] = {}, ["Wikipedia_code"] = "gem-x-proto", }, ["gml"] = { ["name"] = "Middle Low German", }, ["gmw-ecg"] = { ["name"] = "East Central German", }, ["goh"] = { ["replacements"] = { decompose = true, from = { "[" .. macron .. circumflex .. diaeresis .. "]", }, }, }, ["got"] = { ["name"] = "Gothic", ["article"] = "Gothic language", -- ["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"] = "Alemannic German", }, ["grc"] = { ["name"] = "Ancient Greek", ["article"] = "Ancient Greek", -- ["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"] = "Proto-Hellenic", ["Wikipedia_name"] = "Proto-Greek", ["article"] = "Proto-Greek language", -- ["scripts"] = { "Latn" }, ["type"] = "reconstructed", ["replacements"] = {}, }, ["ha"] = { ["name"] = "Hausa", -- remove tilde, grave, acute, macron, circumflex ["replacements"] = { decompose = true, from = { "[" .. grave .. circumflex .. macron .. acute .. tilde .. "]" }, }, }, ["hi"] = { ["name"] = "Hindi", ["article"] = "Hindi", -- ["scripts"] = { "Deva" }, }, ["ine-bsl-pro"] = { ["name"] = "Proto-Balto-Slavic", ["article"] = "Proto-Balto-Slavic language", ["type"] = "reconstructed", }, ["ine-pro"] = { ["name"] = "Proto-Indo-European", ["article"] = "Proto-Indo-European language", -- ["scripts"] = { "Latn" }, ["type"] = "reconstructed", ["replacements"] = {}, ["Wikipedia_code"] = "ine-x-proto", }, ["ja"] = { ["name"] = "Japanese", ["article"] = "Japanese language", -- ["scripts"] = { "Jpan" }, }, ["jbo"] = { -- Lojban ["type"] = "appendix", }, ["la"] = { ["name"] = "Latin", ["article"] = "Latin", -- ["scripts"] = { "Latn" }, ["replacements"] = { -- Remove macrons, breves, and diaereses. decompose = true, from = { "[" .. macron .. breve .. diaeresis .. "]" }, }, }, ["lt"] = { ["name"] = "Lithuanian", -- remove acute, tilde, grave ["replacements"] = { decompose = true, from = { "[" .. acute .. tilde .. grave .. "]" }, }, }, ["moe"] = { ["name"] = "Cree", }, ["mul"] = { ["name"] = "Translingual", ["article"] = "", -- ["scripts"] = { "" }, }, ["nci"] = { ["name"] = "Classical Nahuatl", ["article"] = "Classical Nahuatl", -- ["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"] = "German Low German", }, ["oge"] = { ["name"] = "Old Georgian", -- ["scripts"] = { "Geor", "Geok", }, }, ["oj"] = { ["name"] = "Ojibwe", }, ["orv"] = { ["name"] = "Old East Slavic", ["article"] = "Old East Slavic", -- ["scripts"] = { "Cyrs" }, ["replacements"] = { [U(0x484)] = "", }, }, ["osx"] = { ["name"] = "Old Saxon", }, ["pt"] = { ["name"] = "Portuguese", ["article"] = "Portuguese language", -- ["scripts"] = { "Latn" }, }, ["pa"] = { ["name"] = "Punjabi", ["article"] = "Punjabi language", -- ["scripts"] = { "Guru", "Arab", }, }, ["ru"] = { ["name"] = "Russian", ["article"] = "Russian language", -- ["scripts"] = { "Cyrl" }, ["replacements"] = { [acute] = "", }, }, ["rw"] = { ["name"] = "Rwanda-Rundi", }, ["se"] = { ["replacements"] = { ["([đflmnŋrsšŧv])'%1"] = "%1%1", }, }, ["sem-pro"] = { ["name"] = "Proto-Semitic", ["article"] = "Proto-Semitic", ["type"] = "reconstructed", }, ["sh"] = { ["article"] = "Serbo-Croatian language", -- ["scripts"] = { "Latn", "Cyrl" }, ["replacements"] = { decompose = true, from =  { "([AaEeIiOoUuRrАаЕеИиОоУуРр])[" .. double_grave .. grave .. invbreve .. acute .. macron .. tilde .. "]" }, to   = { "%1" }, }, }, ["sl"] = { ["name"] = "Slovene", ["replacements"] = { decompose = true, -- remove tonal orthography from = {"ł", "[" .. grave .. acute .. macron .. double_grave .. invbreve .. circumflex .. dot_below .. "]"}, to = {"l"}, }, }, ["sla-pro"] = { ["name"] = "Proto-Slavic", -- 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"] = "Ukrainian language", -- ["scripts"] = { "Cyrl" }, ["replacements"] = { [acute] = "", } }, ["ur"] = { ["name"] = "Urdu", ["article"] = "Urdu", -- ["scripts"] = { "Arab" }, }, ["zh"] = { ["name"] = "Chinese", ["article"] = "Chinese language", -- ["scripts"] = { "Hani" }, }, ["xcl"] = { ["name"] = "Old Armenian", ["article"] = "Classical Armenian", -- ["scripts"] = { "Armn" }, ["replacements"] = { ["[՞՜՛՟]"] = "", ["և"] = "եւ", }, }, ["xgf"] = { ["name"] = "Tongva", -- not ISO name "Gabrielino-Fernandeño" ["article"] = "Tongva language", ["replacements"] = { ["['`ʔ]"] = "ʼ", }, }, ["xvn"] = { ["name"] = "Vandalic", ["article"] = "Vandalic language", -- ["scripts"] = { "Latn" }, }, ["yua"] = { ["name"] = "Yucatec Maya", ["article"] = "Yucatec Maya language", -- ["scripts"] = { "" }, }, --[[ [""] = { ["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