Module:kanjitab

The following documentation is located at Module:kanjitab/documentation. ^[edit]

Useful links: subpage list • links • transclusions • testcases • sandbox

This module generates the content of {{ja-kanjitab}}, {{ryu-kanjitab}} etc.

Testcases

{{ja-kanjitab|pagename=大和言葉|||こと|は|k4=ば|yomi=juku2,k2}}
{{ja-kanjitab|pagename=大和言葉|やまと2|こと|は|k3=ば|yomi=juku2,k2}} // "3" is # of argument, not # of kanji

---

local export = {}

local m_utilities = require("Module:utilities")
local m_ja = require("Module:ja")
--[=[
	Other modules used: [[Module:parameters]], [[Module:table]], [[Module:debug]]
]=]

local title = mw.title.getCurrentTitle()
local PAGENAME = title.text
local NAMESPACE = title.nsText

local lang = require("Module:languages").getByCode("ja")

local kanji_pattern = "㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-𯨟"

local kanji_grade_links = {
	"[[:w:Kyōiku_kanji|Grade: 1]]",
	"[[:w:Kyōiku_kanji|Grade: 2]]",
	"[[:w:Kyōiku_kanji|Grade: 3]]",
	"[[:w:Kyōiku_kanji|Grade: 4]]",
	"[[:w:Kyōiku_kanji|Grade: 5]]",
	"[[:w:Kyōiku_kanji|Grade: 6]]",
	"[[:w:Jōyō kanji|Grade: S]]",		-- 7
	"[[:w:Jinmeiyō kanji|Jinmeiyō]]",	-- 8
	"[[:w:Hyōgai kanji|Hyōgaiji]]"		-- 9
}

local function track(code)
	if type(code) == "string" then
		require("Module:debug").track("ja-kanjitab/" .. code)
	end
end

local function quote(text)
	return "“" .. text .. "”"
end

-- this is the function that is called from templates
function export.show(frame)
	local params = {
		[1] = { list = true, allow_holes = true },
		k = { list = true, allow_holes = true },
		o = { list = true, allow_holes = true },
		r = {},
		sort = {},
		yomi = {},
		ateji = {},
		alt = {},
		pagename = {},
	}
	local args, unrecognized_args = require("Module:parameters").process(frame:getParent().args, params, true)
	
	if args.pagename and NAMESPACE == "" then
		track("pagename param in mainspace")
	end
	local pagename = args.pagename or PAGENAME
	
	for key, value in pairs(unrecognized_args) do
		local additional
		if mw.ustring.sub(key, 1, 1) == "y" then
			additional =  " Perhaps you meant " .. quote("yomi") .. "?"
		end
		error(quote(key) .. " is not a recognized parameter." .. (additional or ""))
	end
	
	local categories = {}
	local cells = {}
	-- replace e.g. 時々 with 時時
	local kanji = mw.ustring.gsub(pagename, '([' .. kanji_pattern .. '])々', '%1%1')
	-- remove non-kanji characters
	kanji = mw.ustring.gsub(kanji, '[^' .. kanji_pattern .. ']', '')
		
	local kanji_length = mw.ustring.len(kanji)
	local colspan = ""
	if kanji_length > 1 then
		colspan = 'colspan="' .. kanji_length .. '" '
	end

	local table_head = [=[
{| class="wikitable kanji-table" style="text-align: center; font-size: small; float: right;"
! ]=] .. colspan .. [=[style="font-weight: normal;" | [[kanji|Kanji]] in this term
|- lang="ja" class="Jpan" style="font-size: 2em; background: white; line-height: 1em;"

]=]
	
	local yomi
	
	-- on/kun is jūbakoyomi; NOTE: these are only applicable for two-kanji compounds
	-- kun/on is yutōyomi; NOTE: these are only applicable for two-kanji compounds
	local function parse_extended_yomi(yomi, kanji_length)

	end
	
	if args.yomi then
		yomi = {}
		local extended_yomi_code = {
			o = 'on',			on = 'on',
			kanon = 'kanon',  -- kan is kan'yoon, and ko is kun+on for backward compatibility
			goon = 'goon',
			toon = 'toon',
			kan = 'kanyoon',	kanyo = 'kanyoon',		kanyoon = 'kanyoon',
			k = 'kun',			kun = 'kun',
			juku = 'jukujikun',	jukuji = 'jukujikun',	jukujikun = 'jukujikun',
			ok = "jūbakoyomi",	j = "jūbakoyomi",
			ko = "yutōyomi",	y = "yutōyomi",			yu = "yutōyomi",
			i = 'irregular',	irr = 'irregular',		irreg = 'irregular',	irregular = 'irregular',
			n = 'nanori',	nanori = 'nanori',
			[''] = '',			none = '',
		}
		for i in mw.text.gsplit(args.yomi, ',') do
			local _, _, a, b = mw.ustring.find(i, '^([a-z]*)([0-9]*)$')
			a = extended_yomi_code[a] or error("The yomi type “" .. args.yomi .. "” is not recognized.")
			b = tonumber(b) or 1
			table.insert(yomi, { a, b })
		end
		if #yomi == 1 and kanji_length > 1 then
			yomi[1][2] = kanji_length
		end
	else
		-- [[Special:WhatLinksHere/Template:tracking/ja-kanjitab/no yomi]]
		track("no yomi")
	end
	
	-- [[Special:WhatLinksHere/Template:tracking/ja-kanjitab/incorrect yutou or juubako]]
	if yomi and (yomi[1][1] == "jūbakoyomi" or yomi[1][1] == "yutōyomi") and kanji_length ~= 2 then
		track("ja-pron/incorrect yutou or juubako")
	end

	
	-- readings and okurigana are appended to this
	local sortkey = ""
	
	-- [[Special:WhatLinksHere/Template:tracking/ja-kanjitab/too many k]]
	-- [[Special:WhatLinksHere/Template:tracking/ja-kanjitab/too many o]]
	if args.k.maxindex and args.k.maxindex > args[1].maxindex then
		track("too many k")
	end
	
	if args.o.maxindex and args.o.maxindex > args[1].maxindex then
		track("too many o")
	end
	
	local yomi_type_by_kanji = {}
	if yomi then
		for i = 1, #yomi do
			for j = 1, yomi[i][2] do
				table.insert(yomi_type_by_kanji, yomi[i][1])
			end
		end
	else
		for i = 1, kanji_length do
			table.insert(yomi_type_by_kanji, '')
		end
	end
	
	-- if hiragana readings were passed,
	-- make the "spelled with ..." categories, the readings cells on the lower level and build the sort key
	-- otherwise rely on the pagename to make the original kanjitab and categories
	table.insert(cells, '|- style="background: white;"')
	for i = 1, kanji_length do
		local single_kanji = mw.ustring.sub(kanji, i, i)
		local kanji_grade = m_ja.kanji_grade(single_kanji)
		local reading = args[1][i]
		local cell = {}
		table.insert(cell, "| ")
		if reading then
			if mw.ustring.find(reading, '[ぁ-ゖ]') then
				if not mw.ustring.find(reading, '^[ぁ-ゖ]+$') then
					--[[Special:WhatLinksHere/Template:tracking/ja-kanjitab/not all hiragana]]
					track('not all hiragana')
				end
				
				-- subcategorize by reading if this is joyo kanji, don't do that for less common kanji, with exceptions
				if (kanji_grade < 8 or ('厭昌之芽昌浩智晃淳敦聡晃旭亮糊桂隘阿唖撫鼠阿耘迂寅已伊餡姦闊礙碍凱亥价謳嘔齧日臣桶抉兎鵜卯綾飴焙肋鮫頚糞軋烏痒捷辰叩橙揃嶋澤菱彦囃覗呑之乃鼠做寅樋堤槌机杖頼辿哉叢狢峯巳卍鱒仄他惚弘宏燕倦經痙圭禽僑鋸醵墟屹綺几翫癌劫膠昂鹸牽喧餐鑽瑣些渾梱坤國壕誦哨蒐杓爾梓荼楕躁綜楚闡閃撰專泄藉棲錘錐祷盪淘點顛填擲擢闖厨蛋潭腿冪碧劈焚祓弗憑誹砒婢挽拔撥剥胚播乃狼牢蓮礫醂龍榴蕾酉祐佑耶也蔓曼沫邁呆硼牡甫步矮狸苔'):find(single_kanji)) and yomi_type_by_kanji[i] ~= 'irregular' and yomi_type_by_kanji[i] ~= 'jukujikun' then
					table.insert(categories, "Japanese terms spelled with " .. single_kanji .. " read as " .. reading)
				else
					table.insert(categories, "Japanese terms spelled with " .. single_kanji)
				end
				local actual_reading = args.k[i]
				local okurigana = args.o[i]
				
				sortkey = sortkey .. (actual_reading or reading) .. (okurigana or "")
				
				local reading_text = reading
				local actual_reading_text
				
				if actual_reading then
					actual_reading_text = " > " .. actual_reading
				end
				
				if okurigana then
					local okurigana_text = "(" .. okurigana .. ")"
					
					if reading_text then
						reading_text = reading_text .. okurigana_text
					end
					
					if actual_reading_text then
						actual_reading_text = actual_reading_text .. okurigana_text
					end
				end
				
				local text = reading_text .. (actual_reading_text or "")
				
				table.insert(cell, '<span class="Jpan" lang="ja">' .. text .. '</span>')
			end
		else
			-- [[Special:WhatLinksHere/Template:tracking/ja-kanjitab/no reading]]
			if yomi_type_by_kanji[i] ~= 'irregular' and yomi_type_by_kanji[i] ~= 'jukujikun' then
				track("no reading")
			end
			table.insert(categories, "Japanese terms spelled with " .. single_kanji)
		end
		
		if reading and mw.ustring.match(reading, '[ぁ-ゖ]') then
			table.insert(cell, "<br/>")
		end
		table.insert(cell, "<small>" .. kanji_grade_links[kanji_grade] .. "</small>")
		table.insert(cells, table.concat(cell))
	end
	
	local yomi_info = {
		["on"] = {
			text = "on’yomi",
			entry = "音読み",
			category = "Japanese terms read with on'yomi",
		},
		["kanon"] = {
			text = "kan’on",
			entry = "漢音",
			category = "Japanese terms read with on'yomi",
		},
		["goon"] = {
			text = "goon",
			entry = "呉音",
			category = "Japanese terms read with on'yomi",
		},
		["toon"] = {
			text = "tōon",
			entry = "唐音",
			category = "Japanese terms read with on'yomi",
		},
		["kun"] = {
			text = "kun’yomi",
			entry = "訓読み",
			category = "Japanese terms read with kun'yomi",
		},
		["nanori"] = {
			text = "nanori",
			entry = "名乗り",
			category = "Japanese terms read with nanori",
		},
		["yutōyomi"] = {
			text = "yutōyomi",
			entry = "湯桶読み",
			category = "Japanese terms read with yutōyomi",
		},
		["jūbakoyomi"] = {
			text = "jūbakoyomi",
			entry = "重箱読み",
			category = "Japanese terms read with jūbakoyomi",
		},
		["jukujikun"] = {
			text = "jukujikun",
			entry = "熟字訓",
			category = "Japanese terms read with jukujikun",
		},
		["irregular"] = {
			text = "''Irregular''",
			category = "Japanese terms with irregular kanji readings",
		},
		["kanyoon"] = {
			text = "kan’yōon",
			entry = "慣用音",
			category = "Japanese terms read with kan'yōon",
		},
	}

	local rendaku = args.r
	if rendaku then
		table.insert(categories, "Japanese terms with rendaku")
	end
	if yomi then
		table.insert(cells, "|-")
		for _, i in ipairs(yomi) do
			local yomi_info = yomi_info[i[1]] or { text = i[1] }
			local text
			if yomi_info.entry then
				text = "[[" .. yomi_info.entry .. "|" .. yomi_info.text .. "]]"
			else
				text = yomi_info.text
			end
			table.insert(cells, '| colspan="' .. i[2] .. '" |' .. text)
		end
		local is_onyomi = { on = true, kanon = true, goon = true, toon = true, kanyoon = true }
		-- categories
		local all_onyomi = true
		for i = 1, #yomi do
			if not is_onyomi[yomi[i][1]] then all_onyomi = false; break end
		end
		if all_onyomi then
			table.insert(categories, yomi_info.on.category)
		elseif yomi[1][1] == 'jūbakoyomi' or yomi[1][1] == 'yutōyomi' then
			table.insert(categories, yomi_info[yomi[1][1]].category)
		else
			local all_yomi_of_same_type = true
			for i = 2, #yomi do
				if yomi[i][1] ~= yomi[1][1] then all_yomi_of_same_type = false; break end
			end
			if all_yomi_of_same_type then
				table.insert(categories, yomi_info[yomi[1][1]].category)
			elseif #yomi == 2 and yomi[1][2] == 1 and yomi[2][2] == 1 and mw.ustring.len(pagename) == 2 then
				if is_onyomi[yomi[1][1]] and yomi[2][1] == 'kun' then
					table.insert(categories, yomi_info["jūbakoyomi"].category)
				elseif yomi[1][1] == 'kun' and is_onyomi[yomi[2][1]] then
					table.insert(categories, yomi_info["yutōyomi"].category)
				end
			end
		end
	end
	if args.ateji then
		local ateji = args.ateji
		local text = '[[Appendix:Japanese glossary#ateji|ateji]] (<i class="Jpan mention" lang="ja">[[当て字#Japanese|当て字]]</i>)'
		table.insert(cells, "|-")
		if ateji == 'y' then
			table.insert(cells, '| colspan="' .. kanji_length .. '" | ' .. text)
		else
			local ateji_portions = {}
			for i in mw.text.gsplit(ateji, ';') do
				if mw.ustring.match(i, '^[0-9]*$') then i = i .. ',' .. i end
				local _, _, a, b = mw.ustring.find(i, '^([0-9]*),([0-9]*)$')
				a = tonumber(a) or error("there's something wrong with the ateji parameter")
				b = tonumber(b) or error("there's something wrong with the ateji parameter")
				table.insert(ateji_portions, { a, b })
			end
			local counter = 0
			for _, i in ipairs(ateji_portions) do
				if i[1] <= counter then error("there's something wrong with the ateji parameter") end
				if i[1] > counter + 1 then
					table.insert(cells, '| style="background-color: white; border-bottom: 1px solid white;' .. ((counter == 0) and ' border-left: 1px solid white;' or '') .. '" colspan="' .. (i[1] - counter - 1) .. '" |')
				end
				if i[2] < i[1] then error("there's something wrong with the ateji parameter") end
				table.insert(cells, '| colspan="' .. (i[2] - i[1] + 1) .. '" | ' .. text)
				counter = i[2]
			end
			if counter > kanji_length then error("there's something wrong with the ateji parameter") end
			if counter < kanji_length then
				table.insert(cells, '| style="background-color: white; border-bottom: 1px solid white; border-right: 1px solid white;" colspan="' .. (kanji_length - counter) .. '" |')
			end
		end
	end

	local kanji_table = kanji_length == 0 and "" or (table_head ..
		mw.ustring.gsub(kanji, '(.)', '| style="padding: 0.5em;" | [[%1#Japanese|%1]]\n') ..
		table.concat(cells, '\n') ..
		'\n|}')
	
	local forms_table = ""
	if args.alt and args.alt ~= "" and args.alt ~= "-" then
		local forms = {}
		for form in mw.text.gsplit(args.alt, ',') do
			table.insert(forms, '<span class="Jpan" lang="ja">[[' .. form .. '#Japanese|' .. form .. ']]</span>')
		end
		forms_table = '\n' .. [[{| class="wikitable floatright"
! style="font-weight:normal" | Alternative spelling]] .. (#forms == 1 and "" or "s") .. '\n' .. [[
| style="text-align:center;font-size:140%" | ]] .. table.concat(forms, '<br>') .. '\n|}'
	end
	
	
	-- use user-provided sortkey if we got one, otherwise 
	-- use the sortkey we've already made by combining the 
	-- readings if provided, if we have neither then 
	-- default to empty string and don't sort
	local userprovided_sortkey = args.sort
	if userprovided_sortkey then
		sortkey = userprovided_sortkey
	end
	if sortkey then
		sortkey = m_ja.jsort(sortkey)
	end
	
	return (forms_table == "" and kanji_table or (kanji_table .. forms_table)) .. m_utilities.format_categories(categories, lang, sortkey)
end

return export