View source for Module:zh-han

local m_str_utils = require("Module:string utilities")

local codepoint = m_str_utils.codepoint
local find = m_str_utils.find
local get_section = require("Module:pages").get_section
local gsub = m_str_utils.gsub
local sub = m_str_utils.sub

local m_links = require("Module:links")
local m_script_utils = require("Module:script utilities")

local export = {}

local PAGENAME = mw.loadData("Module:headword/data").pagename

local cangjie = {
	A = "日", B = "月", C = "金", D = "木", E = "水", F = "火", G = "土", H = "竹", I = "戈", J = "十", K = "大", L = "中", M = "一", N = "弓", O = "人", P = "心", Q = "手", R = "口", S = "尸", T = "廿", U = "山", V = "女", W = "田", X = "難", Y = "卜", Z = "重"
}

local radicals = {
	"一","丨","丶","丿","乙","亅",
	"二","亠","人","儿","入","八","冂","冖","冫","几","凵","刀","力","勹","匕","匚","匸","十","卜","卩","厂","厶","又",
	"口","囗","土","士","夂","夊","夕","大","女","子","宀","寸","小","尢","尸","屮","山","巛","工","己","巾","干","幺","广","廴","廾","弋","弓","彐","彡","彳",
	"心","戈","戶","手","支","攴","文","斗","斤","方","无","日","曰","月","木","欠","止","歹","殳","毋","比","毛","氏","气","水","火","爪","父","爻","爿","片","牙","牛","犬",
	"玄","玉","瓜","瓦","甘","生","用","田","疋","疒","癶","白","皮","皿","目","矛","矢","石","示","禸","禾","穴","立",
	"竹","米","糸","缶","网","羊","羽","老","而","耒","耳","聿","肉","臣","自","至","臼","舌","舛","舟","艮","色","艸","虍","虫","血","行","衣","襾",
	"見","角","言","谷","豆","豕","豸","貝","赤","走","足","身","車","辛","辰","辵","邑","酉","釆","里",
	"金","長","門","阜","隶","隹","雨","靑","非",
	"面","革","韋","韭","音","頁","風","飛","食","首","香",
	"馬","骨","高","髟","鬥","鬯","鬲","鬼",
	"魚","鳥","鹵","鹿","麥","麻",
	"黃","黍","黑","黹",
	"黽","鼎","鼓","鼠",
	"鼻","齊",
	"齒",
	"龍","龜",
	"龠"
}

local simplified_radical = {
	['讠']='言',['门']='門',['饣']='食',['飞']='飛',['马']='馬',['见']='見',['贝']='貝',['纟']='糸',['车']='車',['长']='長',['韦']='韋',['风']='風',['钅']='金',['鸟']='鳥',['竜']='龍',['龙']='龍',['页']='頁',['斉']='齊',['齐']='齊',['麦']='麥',['亀']='龜',['龟']='龜',['鱼']='魚',['黾']='黽',['鼡']='鼠',['歯']='齒',['齿']='齒',['卤']='鹵',['𬺞']='龜',['丬']='爿',['黒']='黑',['黄']='黃',
}

local codes = {
	c = 'simplified Chinese', m = 'mainland China',
	j = 'Japanese', k = 'Korean'
}

-- Letters in "as" or "sn" parameter names follow these criteria:
-- There must be 1 or 2 of them.
-- They must be c, m, j, or k.
-- They must be in the order [cm]jk.
local function validate_letters(letters)
	local letter_count = #letters
	return letter_count == 3 and (letters == 'mjk' or letters == 'cjk')
		or letter_count == 2 and (letters == 'jk' or letters == 'cj' or letters == 'mj')
		or letter_count == 1 and codes[letters]
end

local function mul_link(term)
	return m_links.full_link({lang = require('Module:languages').getByCode('zh'), term = term.."//", tr="-"})
end

local function radical(name,number,variant)
	number = number or 1
	local padleft = ("%03d"):format(number)
	local text = '<div class="noprint" style="border:solid #aaa 1px;margin:0;font-size:74%;background:#f9f3f6;width:120px;padding:3px;spacing:0;text-align:center;float:right"><div style="float:left">[[Image:Commons-logo.svg|24px|none|link=Commons:Category:Radical ' .. padleft .. ']]</div>[[Commons:Category:Radical ' .. padleft .. "-0|See images of <br>'''Radical " .. number .. " <big>" .. ((name and name ~= '') and PAGENAME or '※') .. "</big>''']]</div>"
	if name == PAGENAME or (variant and variant ~= '') then
		text = text .. '[[Category:Han character radicals| ]]'
	else
		text = text .. '[[Category:Han char without var| ]]'
	end
	return text
end

function export.simp(frame)
	local args = frame:getParent().args
	
	local trad = args[1] or ''
	if trad == '' then
		trad = mw.loadData("Module:zh/data/st")[PAGENAME] or PAGENAME
	end
	
	local nocap = args['nocap'] or ''
	local alt = args['a'] or ''
	local from = {args['f'] or '',args['f2'] or ''}
	local to = {args['t'] or '',args['t2'] or ''}
	if from[1] == '' and to[1] ~= '' then from[1] = trad end
	local text = {}
	local result = ''
	result = (nocap == '' and 'S' or 's') .. 'implified from ' .. mul_link(trad)
	if alt ~= '' then
		result = result .. ' and ' .. mul_link(alt)
	end
	for i=1,2 do
		if from[i] ~= '' then
			if to[i] == '' then
				table.insert(text,mul_link(from[i]) .. " → a component which cannot be displayed independently")
			elseif to[i] == ' ' or to[i] == '&nbsp;' then
				table.insert(text,'elimination of ' .. mul_link(from[i]))
			else
				table.insert(text,mul_link(from[i]) .. ' → ' .. mul_link(to[i]))
			end
		end
	end
	if #text > 0 then
		result = result .. ' (' .. table.concat(text,' and '):gsub('and elimination of','and') .. ')'
	end
	return result
end

-- NOTE: added 2023 Nov as a sanity check for {{Han ref}}
function export.cp()
	return string.format('%.4X', codepoint(PAGENAME))
end

do
	local function check_translingual_only()
		for _, sec in pairs(mw.loadData("Module:headword/data").page.L2_sections) do
			if sec ~= "Translingual" then
				return
			end
		end
		require('Module:debug').track('zh-han/translingual-only character')
	end
	
	function export.character(frame)
		local args = {}
		for arg, val in pairs(frame:getParent().args) do -- Set empty args to nil.
			if val ~= '' then
				args[arg] = val
			end
		end
		if radicals[tonumber(args['rn'])] ~= (simplified_radical[args['rad']] or args['rad']) then
			error('Radical number (rn) and radical (rad) do not match')
		end
		local text = { insert = table.insert }
		local categories = { insert = table.insert }
		local as = tostring(tonumber(args['as'] or '-1'))
		if as == '0' then
			text:insert(radical(args['rad'], args['rn'], (args['var'] or '')))
		end
		
		-- Creating headword with [[Module:headword]] ensures that page title is script-tagged with Hani (generic Han).
		-- This assumes that {{Han char}} is only used in Translingual sections.
		local mul = require("Module:languages").getByCode("mul")
		local Hani = require("Module:scripts").getByCode("Hani")
		local sort_key = args['rad'] .. args['as'] .. PAGENAME
		text:insert(
			require("Module:headword").full_headword{
				lang = mul,
				sc = Hani,
				heads = { args['head'] },
				categories = {},
				pos_category = "symbols",
				sort_key = sort_key,
			}
		)
		text:insert(" (''[[Kangxi radical]] " .. (args['rn'] or '') .. ", '' [[Appendix:Chinese radical/" .. (args['rad'] or '') .. '|' .. (args['rad'] or ' ') .. ']]+' .. as)
		if args['asj'] then
			text:insert(" ''in Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asj']) .. " ''in Japanese''")
		end
		if args['asc'] then
			text:insert(" ''in traditional Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asc']) .. " ''in simplified Chinese''")
		end
		if args['ask'] then
			text:insert(" ''in Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['ask']) .. " ''in Korean''")
		end
		if args['asjk'] then
			text:insert(" ''in Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asjk']) .. " ''in Japanese and Korean''")
		end
		if args['asj+'] then
			text:insert(" ''in Chinese and Korean'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asj+']) .. " ''in Japanese''")
		end
		if args['ask+'] then
			text:insert(" ''in Chinese and Japanese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['ask+']) .. " ''in Korean''")
		end
		if args['asc+'] then
			text:insert(" ''in traditional Chinese and Japanese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asc+']) .. " ''in simplified Chinese''")
		end
		if args['asc++'] then
			text:insert(" ''in traditional Chinese, Japanese and Korean'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asc++']) .. " ''in simplified Chinese''")
		end
		if args['ascj'] then
			text:insert(" ''in traditional Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['ascj']) .. " ''in simplified Chinese and Japanese''")
		end
		if args['ascj+'] then
			text:insert(" ''in traditional Chinese and Korean'', " .. (args['rad'] or '') .. '+' .. tonumber(args['ascj+']) .. " ''in simplified Chinese and Japanese''")
		end
		if args['asm'] then
			text:insert(" ''in traditional Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asm']) .. " ''in mainland China''")
		end
		if args['asmj'] then
			text:insert(" ''in traditional Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asmj']) .. " ''in mainland China and Japanese''")
		end
		if args['asmj+'] then
			text:insert(" ''in traditional Chinese and Korean'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asmj+']) .. " ''in mainland China and Japanese''")
		end
		if args['asm+'] then
			text:insert(" ''in traditional Chinese and Japanese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asm+']) .. " ''in mainland China''")
		end
		if args['asm++'] then
			text:insert(" ''in traditional Chinese, Japanese and Korean'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asm++']) .. " ''in mainland China''")
		end
		if args['ascjk'] then
			text:insert(" ''in traditional Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['ascjk']) .. " ''in simplified Chinese, Japanese and Korean''")
		end
		if args['asmjk'] then
			text:insert(" ''in traditional Chinese'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asmjk']) .. " ''in mainland China, Japanese and Korean''")
		end
		if args['asmjk+'] then
			text:insert(" ''in traditional Chinese (Taiwan)'', " .. (args['rad'] or '') .. '+' .. tonumber(args['asmjk+']) .. " ''in Chinese (mainland China, Hong Kong), Japanese and Korean''")
		end
		text:insert(", " .. (args['sn'] or '') .. " stroke")
		-- To do: fix handling of multiple additional stroke numbers;
		-- search query:
		-- hastemplate:"Module:zh-han" insource:/\|sn[cmjk][cmjk]?\+*=[^|]+\|sn[cmjk][cmjk]?\+*=[^|]+/
		if args['sn'] ~= '1' then
			text:insert('s')
		end
		if args['snj'] then
			text:insert(" ''in Chinese''")
		end
		if args['snc'] then
			text:insert(" ''in traditional Chinese''")
		end
		if args['snk'] then
			text:insert(" ''in Chinese''")
		end
		if args['snjk'] then
			text:insert(" ''in Chinese''")
		end
		if args['snj+'] then
			text:insert(" ''in Chinese and Korean''")
		end
		if args['snk+'] then
			text:insert(" ''in Chinese and Japanese''")
		end
		if args['snc+'] then
			text:insert(" ''in traditional Chinese and Japanese''")
		end
		if args['snc++'] then
			text:insert(" ''in traditional Chinese, Japanese and Korean''")
		end
		if args['sncj'] then
			text:insert(" ''in traditional Chinese''")
		end
		if args['sncj+'] then
			text:insert(" ''in traditional Chinese and Korean''")
		end
		if args['snm'] then
			text:insert(" ''in traditional Chinese''")
		end
		if args['snmj'] then
			text:insert(" ''in traditional Chinese''")
		end
		if args['snmj+'] then
			text:insert(" ''in traditional Chinese and Korean''")
		end
		if args['snm+'] then
			text:insert(" ''in traditional Chinese and Japanese''")
		end
		if args['snm++'] then
			text:insert(" ''in traditional Chinese, Japanese and Korean''")
		end
		if args['sncjk'] then
			text:insert(" ''in traditional Chinese''")
		end
		if args['snmjk'] then
			text:insert(" ''in traditional Chinese''")
		end
		if args['snmjk+'] then
			text:insert(" ''in traditional Chinese (Taiwan)''")
		end
		
		-- Find parameters specifying additional stroke numbers and add notes for
		-- them.
		for param_name, value in pairs(args) do
			if type(param_name) == "string" then
				local letters = param_name:match("^sn(%l+)%+*$")
				if letters then
					if validate_letters(letters) then
						if value and value ~= '' then
							local label = {}
							for letter in letters:gmatch(".") do
								table.insert(label, codes[letter]) -- Already checked that letters are valid.
							end
							label = table.concat(label, " and ")
							
							text:insert(", " .. value .. " stroke")
							if value ~= '1' then
								text:insert('s')
							end
							text:insert(" ''in " .. label .. "''")
						end
					else
						require("Module:debug").track('zh-han/incorrect stroke number parameter')
						-- return error("Unrecognized stroke number parameter name " .. param_name .. ".")
					end
				end
			end
		end
		
		if args['canj'] then
			local canj = args['canj']
			local canj_split = mw.text.split(canj,',')
			for i = 1, #canj_split do
				if canj_split[i]:match('^%u+$') then
					canj_split[i] = canj_split[i]:gsub('[%(%)]','')
					canj_split[i] = m_script_utils.tag_text(canj_split[i]:gsub('%u',cangjie), mul, Hani) .. ' ([[Appendix:Chinese Cangjie/' .. canj_split[i]:sub(1,1):lower() .. '|' .. canj_split[i] .. ']])'
				else
					return error('The value of "canj" parameter is invalid.')
				end
			end
			text:insert(", ''[[Appendix:Chinese Cangjie|cangjie input]]'' " .. table.concat(canj_split,' or '))
			if #canj_split > 1 then
				categories:insert("[[Category:Han char with multiple canj]]")
			end
		end
		if args['four'] then
			local four = args['four']
			local four_split = mw.text.split(four,',')
			for i=1,#four_split do
				if not four_split[i]:match('[<>]') then
					four_split[i] = four_split[i]:gsub('(%d)(%d%d%d)%.?(%d?)','[[Appendix:Chinese four corner/%1|%1%2<sub>%3</sub>]]')
				else
					return error('The value of "four" parameter is invalid.')
				end
			end
			text:insert(", ''[[Appendix:Chinese four corner|four-corner]]'' " .. table.concat(four_split,' or '))
			if #four_split > 1 then
				categories:insert("[[Category:Han char with multiple four]]")
			end
		end
		if args['ids'] then
			local ids = args['ids']
			local ids_split = mw.text.split(ids,',')
			for i=1, #ids_split do
				if not ids_split[i]:match('[%[%]]') then
					if find(ids_split[i], '^[⿲⿳](.)%1%1$') then
						categories:insert('[[Category:Triplicated CJKV characters]]')
					end
					if find(ids_split[i], '^[⿰⿱](.)%1$') then
						categories:insert('[[Category:Duplicated CJKV characters]]')
					end
					local before = {}
					ids_split[i] = gsub(ids_split[i], "([⺀-⻳　-〿アイウエオカキクケコサシスセソタチツテトナニヌネノハヒフヘホマミムメモヤユヨラリルレロワヰヱヲン㇀-㇣〇一-鿿㐀-䶿﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧-﨩𠀀-𪛟𪜀-𮯠𰀀-𲎯])",
						function (character)
							if not before[character] then
								before[character] = true
								return "[[" .. character .. "]]"
							else
								return character
							end
						end)
					ids_split[i] = ids_split[i]:gsub("^(.-)%f[%(%z](.*)",
						function(m1, m2)
							local m1 = m_links.embedded_language_links{term = m1, lang = mul, sc = Hani}
							m1 = m_script_utils.tag_text(m1, mul, Hani)
							local letters = {
								G = '<span class="explain" title="Mainland China">G</span>',
								H = '<span class="explain" title="Hong Κong">H</span>',
								T = '<span class="explain" title="Taiwan">T</span>',
								J = '<span class="explain" title="Japan">J</span>',
								K = '<span class="explain" title="Korea">K</span>',
								V = '<span class="explain" title="Vietnam">V</span>'
							}
							return m1 .. m2:gsub(".", letters)
						end)
				end
			end
			text:insert(", ''[[w:Chinese character description languages#Ideographic Description Sequences|composition]]'' " .. table.concat(ids_split,' or '))
			if #ids_split > 1 then
				categories:insert("[[Category:Han char with multiple ids]]")
			end
		end
		text:insert(')')
		if args['rad'] then
			if mw.title.getCurrentTitle().nsText == '' then
				categories:insert("[[Category:Han script characters|" .. sort_key .. "]]")
			end
		else
			if mw.title.getCurrentTitle().nsText == '' then
				categories:insert("[[Category:Han char without rad]]")
			end
		end
		local params_to_check = { "as", "rn", "sn", "ids", "four", "canj" }
		local sortkey = args['rad'] and "|" .. args['rad'] or ""
		for _, param in pairs(params_to_check) do
			if not args[param] or args[param] == '' then
				categories:insert("[[Category:Han char without " .. param .. sortkey .. "]]")
			end
		end
		
		if type(args['sn']) == "string" and sub(args['sn'],1,1) == '0' then
			return error('Please remove leading zeros from the "sn" parameter.')
		end
		
		check_translingual_only()
		
		if (get_section(mw.title.getCurrentTitle():getContent(), "Translingual", 2) or ""):match("%f[^%z\n\r]#[ \t]*%S") then
			categories:insert("[[Category:Translingual Han characters with definition lines " .. sortkey .. "]]")
		end
		
		return table.concat(text) .. table.concat(categories)
	end
end

return export