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.
]]
local data = {
["languages"] = {
["ab"] = {
["name"] = "Abkhaz",
},
["ang"] = {
-- Remove macrons, acutes, and overdots
["replacements"] = {
decompose = true,
from = { "[" .. macron .. acute .. dot .. "]" },
},
},
["ar"] = {
["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).."]"] = "",
},
},
["bal"] = {
["name"] = "Baluchi",
},
["be"] = {
["replacements"] = {
[acute] = "",
},
},
["bua"] = {
["name"] = "Buryat",
},
["cu"] = {
["name"] = "Old Church Slavonic",
},
["egy"] = {
["name"] = "Egyptian",
},
["frp"] = {
["name"] = "Franco-Provençal",
},
["goh"] = {
["replacements"] = {
decompose = true,
from = {
"[" .. macron .. circumflex .. diaeresis .. "]",
},
},
},
["got"] = {
["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",
},
},
["grc"] = {
["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",
}
},
},
["ha"] = {
-- remove tilde, grave, acute, macron, circumflex
["replacements"] = {
decompose = true,
from = { "[" .. grave .. circumflex .. macron .. acute .. tilde .. "]" },
},
},
["jbo"] = {
["type"] = "appendix",
},
["la"] = {
["replacements"] = {
decompose = true,
from = { "[" .. macron .. breve .. diaeresis .. "]" },
},
},
["lt"] = {
-- remove acute, tilde, grave
["replacements"] = {
decompose = true,
from = { "[" .. acute .. tilde .. grave .. "]" },
},
},
["moe"] = {
["name"] = "Cree",
},
["mul"] = {
["name"] = "Translingual",
},
["nci"] = {
-- 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",
},
["orv"] = {
["replacements"] = {
[U(0x484)] = "",
},
},
["ru"] = {
["replacements"] = { [acute] = "", },
},
["rw"] = {
["name"] = "Rwanda-Rundi",
},
["se"] = {
["replacements"] = {
["([đflmnŋrsšŧv])'%1"] = "%1%1",
},
},
["sh"] = {
["replacements"] = {
decompose = true,
from = { "([AaEeIiOoUuRrАаЕеИиОоУуРр])[" .. double_grave
.. grave .. invbreve .. acute .. macron .. tilde .. "]" },
to = { "%1" },
},
},
["sl"] = {
["replacements"] = {
decompose = true,
-- remove tonal orthography
from = {"ł", "[" .. grave .. acute .. macron .. double_grave .. invbreve .. circumflex .. dot_below .. "]"},
to = {"l"},
},
},
["uk"] = {
["replacements"] = { [acute] = "", }
},
["xcl"] = {
["replacements"] = {
["[՞՜՛՟]"] = "",
["և"] = "եւ",
},
},
["xgf"] = {
["replacements"] = {
["['`ʔ]"] = "ʼ",
},
},
-- Custom private-use codes which should be added to [[Module:Lang]].
-- Codes are in the format of "code-x-code"
["gem-x-proto"] = {
["type"] = "reconstructed",
},
["grk-x-proto"] = {
["name"] = "Proto-Hellenic",
["type"] = "reconstructed",
},
["ine-x-proto"] = {
["type"] = "reconstructed",
},
["sem-x-proto"] = {
["type"] = "reconstructed",
},
["sla-x-proto"] = {
["type"] = "reconstructed",
["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",
},
},
},
-- 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",
["ciw"] = "oj",
["cnr"] = "sh",
["fil"] = "tl",
["fuf"] = "ff",
["gem"] = "gem-x-proto", -- Not correct, but is commonly used.
["gmw-ecg"] = "gmw-x-ecg",
["hak"] = "zh",
["hbo"] = "he",
["hr"] = "sh",
["ine"] = "ine-x-proto", -- Not correct, but might be commonly used.
["kjv"] = "sh",
["nan"] = "zh",
["prs"] = "fa",
["rn"] = "rw",
["sli"] = "gmw-x-ecg",
["sr"] = "sh",
["src"] = "sc",
["sro"] = "sc",
["tw"] = "ak",
["wae"] = "gsw",
["wep"] = "nds-de",
["yue"] = "zh",
["xno"] = "fro",
-- Incorrect private use tags
["cel-proto"] = "cel-x-proto",
["gem-pro"] = "gem-x-proto",
["grk-pro"] = "grk-x-proto",
["ine-pro"] = "ine-x-proto",
["ine-bsl-pro"] = "ine-x-proto",
["sem-pro"] = "sem-x-proto",
["sla-pro"] = "sla-x-proto",
},
}
return data
