Module:Pinyin

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

This module converts Hanyu Pinyin input from the "lazy" numbers form (eg. Han4yu3 pin1yin1) to the proper form with tones marked on the correct vowels (eg. Hànyǔ pīnyīn). It implements {{Pinyin}}

Additionally, the module converts the convenient shorthand v to ü as in most Chinese pinyin IMEs, and catches the incorrect nue and lue to nüe and lüe respectively. Otherwise, the module does not check whether the input pinyin is entered correctly or not.

Also supports putting the accent on esoteric pinyin like on m, ng, and ê. (eg. ng3 gives ňg)

Usage

{{#invoke:Pinyin|pinyin|input}}

• input - The values to convert to proper pinyin form. As input, the pinyin for individual characters has to be in the form untoned pinyin + tone number with no spaces between them (eg. ma1), though there is no limitation on how many words to take as input and whether there are spaces between individual characters.

The above documentation is transcluded from Module:Pinyin/doc. (edit | history)
Editors can experiment in this module's sandbox (create | mirror) and testcases (edit | run) pages.
Subpages of this module.

local p = {}

function attachTone(a, n)
	if a == "a" then
		if n == 1 then return "ā" end
		if n == 2 then return "á" end
		if n == 3 then return "ǎ" end
		if n == 4 then return "à" end
		return a
			
	end
	
	if a == "A" then
		if n == 1 then return "Ā" end
		if n == 2 then return "Á" end
		if n == 3 then return "Ǎ" end
		if n == 4 then return "À" end
		return a
			
	end
	
	if a == "e" then
		if n == 1 then return "ē" end
		if n == 2 then return "é" end
		if n == 3 then return "ě" end
		if n == 4 then return "è" end
		return a
			
	end
	
	if a == "E" then
		if n == 1 then return "Ē" end
		if n == 2 then return "É" end
		if n == 3 then return "Ě" end
		if n == 4 then return "È" end
		return a
			
	end
	
	if a == "i" then
		if n == 1 then return "ī" end
		if n == 2 then return "í" end
		if n == 3 then return "ǐ" end
		if n == 4 then return "ì" end
		return a
			
	end
	
	if a == "O" then
		if n == 1 then return "Ō" end
		if n == 2 then return "Ó" end
		if n == 3 then return "Ŏ" end
		if n == 4 then return "Ò" end
		return a
			
	end
	
	if a == "o" then
		if n == 1 then return "ō" end
		if n == 2 then return "ó" end
		if n == 3 then return "ǒ" end
		if n == 4 then return "ò" end
		return a
			
	end
	
	if a == "u" then
		if n == 1 then return "ū" end
		if n == 2 then return "ú" end
		if n == 3 then return "ǔ" end
		if n == 4 then return "ù" end
		return a
			
	end
	
	if (a == "v") or (a == "ü") then
		if n == 1 then return "ǖ" end
		if n == 2 then return "ǘ" end
		if n == 3 then return "ǚ" end
		if n == 4 then return "ǜ" end
		return "ü"
			
	end
	
	return a
	
end




function selectVowel(chara, n)

	local A_in = string.find(chara, "A", -1)
	if A_in then
		chara[A_in] = attachTone("A", n)
		return chara
	end
	
	local a_in = string.find(chara, "a", -1)
	if a_in then
		chara[a_in] = attachTone("a", n)
		return chara
	end


	local E_in = string.find(chara, "E", -1)
	if E_in then
		chara[E_in] = attachTone("E", n)
		return chara
	end
	
	local e_in = string.find(chara, "e", -1)
	if e_in then
		chara[e_in] = attachTone("e", n)
		return chara
	end
	
	
	local i_in = string.find(chara, "i", -1)
	if i_in then
		if chara[i_in + 1] == "u" then
			chara[i_in + 1] = attachTone("u", n)
			return chara
		end
		
		chara[i_in] = attachTone("i", n)
		return chara
	end
	
	
	local O_in = string.find(chara, "O", -1)
	if O_in then
		chara[O_in] = attachTone("O", n)
		return chara
	end
	
	local o_in = string.find(chara, "o", -1)
	if o_in then
		chara[o_in] = attachTone("o", n)
		return chara
	end
	
	
	local u_in = string.find(chara, "u", -1)
	if u_in then
		chara[u_in] = attachTone("u", n)
		return chara
	end
	
	
	local v_in = string.find(chara, "v", -1)
	if v_in then
		chara[v_in] = attachTone("v", n)
		return chara
	end
	
	local umlaut_in = string.find(chara, "ü", -1)
	if umlaut_in then
		chara[umlaut_in] = attachTone("ü", n)
		return chara
	end
	
end

function p.pinyin(frame)
	return string.gsub(frame.args[1], "(%a+)(%d)", selectVowel)
end

 
return p