Module:Wikt-lang/data/sandbox

Module documentation[view] [edit] [history] [purge]

The redirects table in Module:Wikt-lang/data connects Wikipedia language codes to the corresponding code used on the English Wiktionary. wikt:Wiktionary:Language treatment records this relationship for ISO codes. For instance, all of bs (Bosnian), hr (Croatian), sr (Serbian), cnr (Montenegrin), kjv (Kajkavian) are placed under the header for sh (Serbo-Croatian) in Wiktionary entries. See for instance wikt:kaj#Serbo-Croatian, the word that Kajkavian is named after. The subsumed codes should still be used in language-tagging on Wikipedia.

The above documentation is transcluded from Module:Wikt-lang/data/doc. (edit | history)
Editors can experiment in this module's sandbox (edit | diff) and testcases (create) pages.
Add categories to the /doc subpage. Subpages of this module.

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