Mòideal:Language/name

(deasbaireachd⧼tpt-languages-separator⧽⧼tpt-languages-separator⧽eachdraidh⧼tpt-languages-separator⧽ceanglaichean⧼tpt-languages-separator⧽doc⧼tpt-languages-separator⧽bogsa-gainmhich⧼tpt-languages-separator⧽cùisean deuchainn)

This module converts ISO 639 codes and language tags into their equivalent language names (descriptions). It has three modes: simple (strict), fuzzy and formal. In simple, the whole tag needs to be an exact match; in fuzzy, only the base ISO 639 code needs to be an exact match. For example, if there's no mn-Cyrl tag in the list, but there's mn, simple will not be able to find a match, whereas fuzzy will. Finally, in formal, the script will attempt to properly decode the tag by language, script (writing system) and region and print its name in full. Here's how the three modes will handle zh and zh-Hans-CN:

{{#invoke:Language/name|simple|code=zh}}	→	Chinese
{{#invoke:Language/name|simple|code=zh-Hans-CN}}	→
{{#invoke:Language/name|fuzzy|code=zh-Hans-CN}}	→	Chinese
{{#invoke:Language/name|formal|code=zh-Hans-CN}}	→	Chinese (Han (Simplified variant), China)

{{ISO 639 name}} and Mòideal:Language/text use fuzzy. Input is case-insensitive. If input is omitted, this module with return an error; if no match is found, it'll return an empty string that can be used with #if constructs in wikicode, e.g. {{#if:{{ISO 639 name|{{{1}}}}}| ... }}.

Data is pulled from /data.

For info on language tags, see BCP 47, the IANA Language Subtag Registry, Richard Ishida's Language Subtag Lookup and the IETF language tag article here on Wikipedia.

Faic cuideachd - Also see

• Special:PrefixIndex/Module:Language/

---

local getArgs = require("Module:Arguments").getArgs
local p, e = {}, {}

local function __compile(...)
	local r,i = "",0
	for _, v in ipairs(arg) do
		i = i + 1
		if i == 1 then
			r = v[1]
		elseif i == 2 then
			r = r .. " (" .. v[1]
		else
			r =  r .. ", " .. v[1]
		end
	end
	if i > 1 then
		r = r .. ")"
	end
	return r
end

function e.simple(args, data)
	return __compile(data.lang[args.code])
end

function e.fuzzy(args, data)
	-- split lang code at '-', starting from the end, one dash at a time
	-- and try to find a match; break from loop when we do
	repeat
		if data.lang[args.code] then
			break
		end
		args.code = args.code:gsub("-[^-]*$", "")
	until not args.code:match("-")

	return __compile(data.lang[args.code])
end

function e.formal(args, data)
	-- split the whole lang code up at every '-' and stick the bits in an array
	local bits = {}; for match in args.code:gmatch("[^-]+") do
		bits[#bits+1] = match
	end

	-- if length of the 2nd array item is 4, assume it's a script code,
	-- otherwise a region code
	if bits[2] and #bits[2] == 4 then
		return __compile(data.lang[bits[1]],
						 data.script[bits[2]],
						 data.region[bits[3]]
						)
	else
		return __compile(data.lang[bits[1]],
						 data.region[bits[2]]
						)
	end
end

for function_name in pairs(e) do
	p[function_name] = function (frame)
		local args = getArgs(frame)
		local data = mw.loadData("Module:Language/name/data")

		args.code = args.code:lower()

		-- if dataset=iana, discard wp language table
		if args.dataset == "iana" then
			data.lang = data.lang_iana
		end

		return e[function_name](args, data)
	end
end

return p