local export = {}
local find = mw.ustring.find
local length = mw.ustring.len
local trim = mw.text.trim
local split = mw.text.split
local sub, gsub = mw.ustring.sub, mw.ustring.gsub
local match, gmatch = mw.ustring.match, mw.ustring.gmatch
local to_cp, to_char = mw.ustring.codepoint, mw.ustring.char
local Jpan = require("Module:scripts").getByCode("Jpan")
local lang = require("Module:languages").getByCode("ja")
-- note that arrays loaded by mw.loadData cannot be directly used by gsub
local data = mw.loadData("Module:ja/data")
export.data = {
joyo_kanji = data.joyo_kanji,
jinmeiyo_kanji = data.jinmeiyo_kanji,
grade1 = data.grade1,
grade2 = data.grade2,
grade3 = data.grade3,
grade4 = data.grade4,
grade5 = data.grade5,
grade6 = data.grade6
}
function export.hira_to_kata(text)
if type(text) == "table" then text = text.args[1] end
return (gsub(text, '[ぁ-ゖ]', function(char) return to_char(to_cp(char) + 96) end))
end
function export.kata_to_hira(text)
if type(text) == "table" then text = text.args[1] end
return (gsub(text, '[ァ-ヶ]', function(char) return to_char(to_cp(char) - 96) end))
end
function export.fullwidth_to_halfwidth(text)
if type(text) == "table" then text = text.args[1] end
text = gsub(text, ' ', ' ')
return (gsub(text, '[！-～]', function(char) return to_char(to_cp(char) - 65248) end))
end
function export.kana_to_romaji(text, options)
-- options: no_diacritics, keep_period, hist
if type(text) == "table" then
text = text.args[1]
end
if not options then options = {} end
local tracking_has_percent = find(text, '%%')
local text_old = trim(require('Module:ja/k2r-old').kana_to_romaji(text, options.no_diacritics, options.keep_period))
-- conversions
text = gsub(text, '(%-)([はハ])$', '%1㊟㈛㊟%2') -- は as suffix and appearing at the end of string
text = gsub(text, '(%-)([はハ]) ', '%1㊟㈛㊟%2 ') -- は as suffix and appearing mid-sentence
text = gsub(text, '％', '㊟㌫㊟') -- at [[見込む]], for example; avoid collision with % used in our ruby syntax
text = gsub(text, '\'\'\'', '㊟⒝㊟')
text = gsub(text, '<u>', '㊟㋑⒰㊟')
text = gsub(text, '</u>', '㊟㋺⒰㊟')
-- avoid tampering with existing latin text: store it away
local escape = {}
local id = 0
for latin in gmatch(text, "[a-z]+") do
escape[id] = latin
text = gsub(text, latin, "㊟㊕㊕㊟" .. id .. "㊟㊕㊕㊟")
id = id + 1
end
-- special preformatting
text = gsub(text, 'ヶげつ', 'かげつ')
text = gsub(text, 'ヶ(㊟[㋑㋺⒝⒰]+㊟)げつ', 'か%1げつ') -- 「'''ヶ'''げつ」
text = gsub(text, 'ヶ', 'が')
text = gsub(text, '(.)ゝ', '%1%1')
text = gsub(text, '(.)ゞ', function(char) return mw.ustring.toNFC(char .. char .. '゙') end) -- unicode hax
-- [[Wiktionary:Grease_pit/2017/May#Formatting_for_individual_Japanese_readings]]
if options.hist then
text = gsub(text, 'づ', 'du')
text = gsub(text, 'ぢ', 'di')
text = gsub(text, 'を', 'wo')
text = gsub(text, '([やゆよわゐゑを])', '㊟⒳㊟%1')
end
text = export.hira_to_kata(text)
text = gsub(text, '.', function(char) return data.kr[char] or char end)
text = export.fullwidth_to_halfwidth(text)
if options.hist then
text = gsub(text, 'ou', 'o.u')
text = gsub(text, '([iu])㊟⒳㊟', '') -- くゐやう kwyau
text = gsub(text, '㊟⒳㊟', '') -- ゑつ wetsu
end
-- markup
text = gsub(text, '%%', '.') -- ruby "percent sign" syntax
text = gsub(text, '([ッ¤])%.', '%1') -- 「し を ぼっ.す」; 「るい%じん%えん」→「rui.jin¤.en¤」
-- 「テェェェ」→「テェーー」 (avoid funky romaji effected by the "(テュ→)teユ→tyu" line below)
text = gsub(text, '(ァ)(ァ+)', function(a,b) return a .. mw.ustring.rep('ー', length(b)) end)
text = gsub(text, '(ィ)(ィ+)', function(a,b) return a .. mw.ustring.rep('ー', length(b)) end)
text = gsub(text, '(ゥ)(ゥ+)', function(a,b) return a .. mw.ustring.rep('ー', length(b)) end)
text = gsub(text, '(ェ)(ェ+)', function(a,b) return a .. mw.ustring.rep('ー', length(b)) end)
text = gsub(text, '(ォ)(ォ+)', function(a,b) return a .. mw.ustring.rep('ー', length(b)) end)
-- (ゲェ→)geェ→gee (note that this causes things like ウゥ→ū and ギィ→gī)
text = gsub(text, '[aiueo][ァィゥェォ]', {['aァ']='aa',['iィ']='ii',['uゥ']='uu',['eェ']='ee',['oォ']='oo',})
-- (クヮ→)kuヮ→kwa
text = gsub(text, '[u]([ヮ])', {['ヮ']='wa',})
-- (クァ→)kuァ→kwa, (トァ→)toァ→twa, (ウィ→)uィ→wi
text = gsub(text, '[uo]([ァィェォ])', {['ァ']='wa',['ィ']='wi',['ェ']='we',['ォ']='wo',})
-- (ツァ→)cwa→ca
text = gsub(text, '([fvcsz])w', '%1')
-- (テュ→)teユ→tyu, (ギェ→)giェ→gye
text = gsub(text, '[aiueo]([ャュェョ])', {['ャ']='ya',['ュ']='yu',['ェ']='ye',['ョ']='yo',})
-- (ジュ→)jyu→ju
text = gsub(text, '([xjq])y', '%1')
-- (ティ→)teィ→ti (essentially forget about the vowel in between)
text = gsub(text, '[aiueo]([ァィゥェォ])', {['ァ']='a',['ィ']='i',['ゥ']='u',['ェ']='e',['ォ']='o',})
-- chouonpu and sokuon
while find(text, '[aiueo]ー') or find(text, 'ッ *[bcdfghjklmnpqrstvwxyz]') or find(text, 'ッ㊟[㋑㋺⒝⒰]+㊟[bcdfghjklmnpqrstvwxyz]') do
text = gsub(text, '([aiueo])ー', '%1%1')
text = gsub(text, 'ッ( *)([bcdfghjklmnpqrstvwxyz])', '%2%1%2')
text = gsub(text, 'ッ(㊟[㋑㋺⒝⒰]+㊟)([bcdfghjklmnpqrstvwxyz])', '%2%1%2')
end
-- deal with leftover sokuon not used as geminate
text = gsub(text, 'ッ', 'h')
-- (ん→)n¤
text = gsub(text, '¤([aiueoy])', "'%1")
text = gsub(text, '¤', '')
-- は
text = gsub(text, "([^a-z.㊟])ha([^a-z.㊟])", "%1wa%2")
text = gsub(text, "([^a-z.㊟])ha$", "%1wa")
text = gsub(text, "^ha([^a-z.㊟])", "wa%1")
-- へ
text = gsub(text, "([^a-z.㊟])he([^a-z.㊟])", "%1e%2")
text = gsub(text, "([^a-z.㊟])he$", "%1e")
text = gsub(text, "^he([^a-z.㊟])", "e%1")
-- change only when
-- ① not flanked by a-z or a period ("^sore wa nani$", "^hyappou no .he hitotsu$")
-- ② at the end of the string and not preceded by a-z or a period ("^are wa$")
-- ③ at the beginning of the string and not followed by a-z or a period ("^he ikou$") [not sure this is actually necessary, but I suppose it is consistent with ②]
-- this also means that "^ha$" becomes "ha"
-- period can be used next to the kana (either side) to force the "dumb" romanization (i.e. "ha", "he")
-- fix sh, ch, ts
text = gsub(text, '([xqc]*)([xqc])', function(geminate,main)
--「めちゃ」→「mecha」
--「めっちゃ」→「metcha」
--「めっっちゃ」→「mettcha」
local corresp_geminate_form = {['x']='s',['q']='t',['c']='t'}
local corresp_main = {['x']='sh',['q']='ch',['c']='ts'}
return (geminate and mw.ustring.rep(corresp_geminate_form[main], length(geminate))) .. corresp_main[main]
end
)
-- macrons
if not options.no_diacritics then
text = gsub(text, 'oo', 'ō')
text = gsub(text, 'aa', 'ā')
text = gsub(text, 'ee', 'ē')
text = gsub(text, 'ou', 'ō')
text = gsub(text, 'uu', 'ū')
text = gsub(text, 'ii', 'ī')
end
-- remove markup and convert real periods
if not options.keep_period then
text = gsub(text, '%.', '')
text = gsub(text, '。', '◆.◇')
end
--
text = gsub(text, '◇◆', '')
text = gsub(text, '◆◇', '')
text = gsub(text, ' *◆ *', '')
text = gsub(text, ' *◇ *', ' ')
-- restore latin text
text = gsub(text, "㊟㊕㊕㊟(%d+)㊟㊕㊕㊟", function(id) return escape[tonumber(id)] end)
-- clean up spaces
text = trim(text)
text = gsub(text, ' +', ' ')
-- uppercase markup
text = gsub(text, "(%^)(㊟⒝㊟)", "%2%1") -- move ^ to an effective position if placed before bold markup
text = gsub(text, "(%^)( )", "%2%1") -- same but with spaces
text = gsub(text, '%^(.)', mw.ustring.upper) -- uppercase conversion
-- clean up spaces again
text = gsub(text, ' +', ' ')
-- conversions
text = gsub(text, '㊟⒝㊟', '\'\'\'')
text = gsub(text, '㊟㋑⒰㊟', '<u>')
text = gsub(text, '㊟㋺⒰㊟', '</u>')
text = gsub(text, '㊟㈛㊟', '')
text = gsub(text, '㊟㌫㊟', '%')
-- comparison with old kana_to_romaji() code
text_old = gsub(text_old, '%(ba%)', ' (ba)') -- avoid flooding the tracking template with na-adjectives. ← this really should be looked at though
text_old = gsub(text_old, ' ”', '”') -- and spacing around quotation marks
if text ~= text_old then
if mw.ustring.lower(text) == mw.ustring.lower(text_old) then
require('Module:debug').track('ja/k2r diff caps')
elseif find(text_old, 'ッ') then
require('Module:debug').track('ja/k2r diff w xtu')
elseif tracking_has_percent then
require('Module:debug').track('ja/k2r diff pc')
else
require('Module:debug').track('ja/k2r diff')
end
mw.log('new]' .. text .. '[')
mw.log('old]' .. text_old .. '[')
end
if find(text, '[ぁ-ー]') then
require('Module:debug').track('ja/k2r failure')
end
return text
end
-- removes spaces and hyphens from input
-- intended to be used when checking manual romaji to allow the
-- insertion of spaces or hyphens in manual romaji without appearing "wrong"
function export.rm_spaces_hyphens(f)
local text = type(f) == 'table' and f.args[1] or f
text = gsub(text, ' ', '')
text = gsub(text, '-', '')
text = gsub(text, '%.', '')
text = gsub(text, ' ', '')
text = gsub(text, '\'', '')
return text
end
function export.romaji_to_kata(f)
local text = type(f) == 'table' and f.args[1] or f
text = gsub(text, '.', function (char) return data.rd[char] or char end)
text = gsub(text, 'kk', 'ッk')
text = gsub(text, 'ss', 'ッs')
text = gsub(text, 'tt', 'ッt')
text = gsub(text, 'pp', 'ッp')
text = gsub(text, 'bb', 'ッb')
text = gsub(text, 'dd', 'ッd')
text = gsub(text, 'gg', 'ッg')
text = gsub(text, 'jj', 'ッj')
text = gsub(text, 'tc', 'ッc')
text = gsub(text, 'tsyu', 'ツュ')
text = gsub(text, 'ts[uoiea]', {['tsu']='ツ',['tso']='ツォ',['tsi']='ツィ',['tse']='ツェ',['tsa']='ツァ'})
text = gsub(text, 'sh[uoiea]', {['shu']='シュ',['sho']='ショ',['shi']='シ',['she']='シェ',['sha']='シャ'})
text = gsub(text, 'ch[uoiea]', {['chu']='チュ',['cho']='チョ',['chi']='チ',['che']='チェ',['cha']='チャ'})
text = gsub(text, "n[uoiea']?", {['nu']='ヌ',['no']='ノ',['ni']='ニ',['ne']='ネ',['na']='ナ',['n']='ン',["n'"]='ン'})
text = gsub(text, '[wvtrpsmlkjhgfdbzy][yw]?[uoiea]', function (char) return data.rk[char] or char end)
text = gsub(text, 'u', 'ウ')
text = gsub(text, 'o', 'オ')
text = gsub(text, 'i', 'イ')
text = gsub(text, 'e', 'エ')
text = gsub(text, 'a', 'ア')
return text
end
-- expects: any mix of kanji and kana
-- determines the script types used
-- e.g. given イギリス人, it returns Kana+Hani
function export.script(f)
text, script = type(f) == 'table' and f.args[1] or f, {}
if match(text, '[ぁ-ゖ]') then
table.insert(script, 'Hira')
end
-- TODO: there are two kanas. This should insert Kata.
if match(text, '[ァ-ヺー]') then
table.insert(script, 'Kana')
end
-- 一 is unicode 4e00, previously used 丁 is 4e01
if match(text, '[㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-]') then
table.insert(script, 'Hani')
end
-- matching %a should have worked but matched the end of every string
if match(text, '[a-zA-ZāēīōūĀĒĪŌŪａ-ｚＡ-Ｚ]') then
table.insert(script, 'Romaji')
end
if match(text, '[0-9０-９]') then
table.insert(script, 'Number')
end
if match(text, '[〆々]') then
table.insert(script, 'Abbreviation')
end
return table.concat(script, '+')
end
-- when counting morae, most small hiragana belong to the previous mora,
-- so for purposes of counting them, they can be removed and the characters
-- can be counted to get the number of morae. The exception is small tsu,
-- so data.nonmora_to_empty maps all small hiragana except small tsu.
function export.count_morae(text)
if type(text) == "table" then
text = text.args[1]
end
-- convert kata to hira (hira is untouched)
text = export.kata_to_hira(text)
-- remove all of the small hiragana such as ょ except small tsu
text = gsub(text,'.',function (char) return data.nonmora_to_empty[char] or char end)
-- remove zero-width spaces
text = gsub(text, '', '')
-- return number of characters, which should be the number of morae
return length(text)
end
-- accepts: any mix of kana
-- returns: a hiragana sort key designed for WMF software
-- this is like sort() but doesn't return |sort=sortkey,
-- just the sort key itself, but unlike sort(), this
-- replaces the long vowel mark with its vowel
function export.jsort(text)
if type(text) == "table" then
text = text.args[1]
end
local textsub = ''
local convertedten = ''
local result = ''
local len = 1
-- remove western spaces, hyphens, and periods
-- diff=41967612: also remove caret
text = gsub(text, '[ %-%.%^]', '')
text = export.kata_to_hira(text)
-- if the first character has dakuten, replace it with the corresponding
-- character without dakuten and add an apostrophe to the end, e.g.
-- がす > かす'
if gsub(sub(text,1,1),'.',function (char) return data.dakuten[char] or char end) == '' then
len = length(text)
textsub = sub(text,2,len)
convertedten = gsub(sub(text,1,1),'.',function (char) return data.tenconv[char] or char end)
text = (convertedten .. textsub .. "'")
else
-- similar thing but with handuken and two apostrophes, e.g. ぱす -> はす''
if gsub(sub(text,1,1),'.',function (char) return data.handakuten[char] or char end) == '' then
len = length(text)
textsub = sub(text,2,len)
convertedten = gsub(sub(text,1,1),'.',function (char) return data.tenconv[char] or char end)
text = (convertedten .. textsub .. "''")
end
end
-- replace the long vowel mark with the vowel that it stands for
for key,value in pairs(data.longvowels) do
text = gsub(text,key,value)
end
return text
end
-- returns a sort key with |sort= in front, e.g.
-- |sort=はつぐん' if given ばつぐん
function export.sort(f)
local text = type(f) == 'table' and f.args[1] or f
local textsub = ''
local convertedten = ''
local result = ''
local len = 1
local kyreplace = ''
kyreplace = gsub(text,'[ァ-ヺ]', '')
if kyreplace == '' then
result = ('|' .. 'sort' .. '=')
end
text = export.kata_to_hira(text)
if gsub(sub(text,1,1),'.',function (char) return data.dakuten[char] or char end) == '' then
if kyreplace == '' then else result = ('|' .. 'sort' .. '=') end
len = length(text)
textsub = sub(text,2,len)
convertedten = gsub(sub(text,1,1),'.',function (char) return data.tenconv[char] or char end)
result = (result .. convertedten .. textsub .. "'")
else
if gsub(sub(text,1,1),'.',function (char) return data.handakuten[char] or char end) == '' then
if kyreplace == '' then else result = ('|' .. 'sort' .. '=') end
len = length(text)
textsub = sub(text,2,len)
convertedten = gsub(sub(text,1,1),'.',function (char) return data.tenconv[char] or char end)
result = (result .. convertedten .. textsub .. "''")
else
if kyreplace == '' then
result = (result .. text)
end
end
end
return result
end
-- returns the "stem" of a verb or -i adjective, that is the term minus the final character
function export.definal(f)
return sub(f.args[1],1,(length(f.args[1])-1))
end
-- see also Template:JAruby
-- meant to be called from another module
function export.add_ruby_backend(term, kana, from_ja_link)
local pattern = ""
-- holds the whole segments of markup enclosed in <ruby>...</ruby>
local ruby_markup = {}
-- range of kana: '[ぁ-ゖァ-ヺ]'
-- nonkana: [^ぁ-ゖァ-ヺ]
local kanji_pattern = "[々㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-０-９]"
-- links without pipes will fail
term = gsub(term, '%[%[([^|%]]+)%]%]', '[[%1|%1]]')
-- remove links from kana
kana = gsub(kana, '%[%[([^|%]]+)%]%]', '%1')
kana = gsub(kana, '%[%[[^%]]+|([^%]]+)%]%]', '%1')
-- build up pattern
-- escape the magic characters in the term
pattern = gsub(term, '%[%[[^%]]+|([^%]]+)%]%]', '%1')
pattern = require("Module:string").pattern_escape(pattern)
pattern = gsub(pattern, "[%[%]]+", " *")
kana = gsub(kana, "[%[%]]+", '')
pattern = gsub(pattern, " *('+) *", "%1")
kana = gsub(kana, " *('+) *", "%1")
pattern = gsub(pattern, " +", " ")
kana = gsub(kana, " +", " ")
-- remove periods and caret signs and hyphens
pattern = gsub(pattern, '%%[%.%^%-]', '')
kana = gsub(kana, '[%.%^%-]', '')
-- in order to make a pattern that will find the ruby,
-- replace every unbroken string of kanji with a sub-pattern
pattern = gsub(pattern, kanji_pattern .. '+', '(.+)')
-- get a pattern like
-- (.+)ばか(.+)ばか(.+)ばかばかばああか(.+) when given 超ばか猿超ばか猿超ばかばかばああか猿
-- it turns out we need to keep the spaces sometimes
-- so that kana don't "leak" in ambiguous cases like 捨すてて撤退 where it's not clear if it's
-- す, てったい or すて, ったい. only solution now is to put spaces in the "term" param
-- if they fall between kana
-- build up term (e.g. [[歌う|歌った]])
local replaced = {}
local count = 0
term = gsub(term, '%]', '%]') -- escape the "]" character so that it cannot appear, example becomes [[歌う|歌った%]%]
term = gsub(term, kanji_pattern .. '+', function(text)
count = count + 1
-- remove spaces
text = gsub(text, ' ', '')
table.insert(replaced, text)
return '[' .. count .. ']'
end) -- example becomes [[[1]う|[2]った%]%]
while match(term, '%[%[[^|]*%[%d+%][^|]*|') do
term = gsub(
term,
'(%[%[[^|]*)%[(%d+)%]([^|]*|)',
function(a,b,c)
return a .. replaced[tonumber(b)] .. c
end
)
end
-- example becomes [[歌う|[2]った%]%]
-- apply that pattern to the kana to collect the rubies
-- if this fails, try it without spaces
if match(kana, pattern) == nil then kana = gsub(kana, ' ', '') end
local ruby = { match(kana, pattern) }
-- local ruby = {}
-- for c in gmatch(kana, pattern) do table.insert(ruby, c) end
-- find the kanji strings again and combine them with their ruby to make the <ruby> markup
local kanji_segments = {}
for c in gmatch(term, '%[(%d+)%]') do
table.insert(kanji_segments, replaced[tonumber(c)])
end
for i = 1, #kanji_segments do
if not ruby[i] then
error('No ruby for kanji segment "' .. kanji_segments[i] .. '".')
end
table.insert(ruby_markup, "<ruby>" .. kanji_segments[i] .. "<rp> (</rp><rt>" .. ruby[i] .. "</rt><rp>) </rp></ruby>")
end
count = 0
term = gsub(term, '%[%d+%]', function()
count = count + 1
return ruby_markup[count]
end)
term = gsub(term, '%%%]', ']')
term = gsub(term, '%%', '')
term = gsub(term, ' ', '')
--done
return '<span style="font-size: 1.2em">' .. term .. '</span>'
end
-- do the work of Template:ja-kanji
function export.kanji(frame)
local PAGENAME = mw.title.getCurrentTitle().text
-- only do this if this entry is a kanji page and not some user's page
if match(PAGENAME, "[㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-]") then
local args = frame:getParent().args
local grade = args["grade"] or ""
local rs = args["rs"] or ""
local style = args["style"] or ""
local shin = args["shin"] or ""
local kyu = args["kyu"] or ""
local head = args["head"] or ""
local wikitext = {}
local categories = {}
local catsort = (rs ~= "") and rs or PAGENAME
-- display the kanji itself at the top at 275% size
table.insert(wikitext, '<div><span lang="ja" class="Jpan" style="font-size:275%; line-height: 100%;">' .. (args["head"] or PAGENAME) .. '</span></div>')
-- display information for the grade
-- if grade was not specified, determine it now
if grade == "" then
local joyo_kanji_pattern = ('[' .. data.joyo_kanji .. ']')
local jinmeiyo_kanji_pattern = ('[' .. data.jinmeiyo_kanji .. ']')
if match(PAGENAME, joyo_kanji_pattern) then grade = "c"
elseif match(PAGENAME, jinmeiyo_kanji_pattern) then grade = "n"
else
grade = "uc"
end
end
table.insert(wikitext, "(''")
if grade == "1" then table.insert(wikitext, "[[w:Kyōiku kanji|grade 1 “Kyōiku” kanji]]")
elseif grade == "2" then table.insert(wikitext, "[[w:Kyōiku kanji|grade 2 “Kyōiku” kanji]]")
elseif grade == "3" then table.insert(wikitext, "[[w:Kyōiku kanji|grade 3 “Kyōiku” kanji]]")
elseif grade == "4" then table.insert(wikitext, "[[w:Kyōiku kanji|grade 4 “Kyōiku” kanji]]")
elseif grade == "5" then table.insert(wikitext, "[[w:Kyōiku kanji|grade 5 “Kyōiku” kanji]]")
elseif grade == "6" then table.insert(wikitext, "[[w:Kyōiku kanji|grade 6 “Kyōiku” kanji]]")
elseif grade == "7" or grade == "c" then table.insert(wikitext, "[[w:Jōyō kanji|common “Jōyō” kanji]]")
elseif grade == "8" or grade == "n" then table.insert(wikitext, "[[w:Jinmeiyō kanji|“Jinmeiyō” kanji used for names]]")
elseif grade == "9" or grade == "uc" then table.insert(wikitext, "[[w:Hyōgai kanji|uncommon “Hyōgai” kanji]]")
elseif grade == "0" or grade == "r" then table.insert(wikitext, "[[w:Radical_(Chinese_character)|Radical]]")
else
table.insert(categories, "[[Category:Japanese terms needing attention/kanji grade]]")
end
-- if style was indicated, mention that and provide link to corresponding kanji
-- (link to shinjitai if this is kyujitai, link to kyujitai if this is shinjitai)
if style == "s" then
table.insert(wikitext, ", ")
if kyu == "" then
table.insert(wikitext, "[[shinjitai]] kanji")
else
table.insert(wikitext, '[[shinjitai]] kanji, [[kyūjitai]] form <span lang="ja" class="Jpan">[[' .. kyu .. '#Japanese|' .. kyu .. ']]</span>')
end
elseif style == "ky" then
table.insert(wikitext, ", ")
if shin == "" then
table.insert(wikitext, "[[kyūjitai]] kanji")
else
table.insert(wikitext, '[[kyūjitai]] kanji, [[shinjitai]] form <span lang="ja" class="Jpan">[[' .. shin .. '#Japanese|' .. shin .. "]]</span>")
end
end
table.insert(wikitext, "'')")
-- add categories
table.insert(categories, "[[Category:Japanese Han characters|" .. catsort .. "]]")
if grade == "1" then table.insert(categories, "[[Category:Grade 1 kanji|" .. catsort .. "]]")
elseif grade == "2" then table.insert(categories, "[[Category:Grade 2 kanji|" .. catsort .. "]]")
elseif grade == "3" then table.insert(categories, "[[Category:Grade 3 kanji|" .. catsort .. "]]")
elseif grade == "4" then table.insert(categories, "[[Category:Grade 4 kanji|" .. catsort .. "]]")
elseif grade == "5" then table.insert(categories, "[[Category:Grade 5 kanji|" .. catsort .. "]]")
elseif grade == "6" then table.insert(categories, "[[Category:Grade 6 kanji|" .. catsort .. "]]")
elseif grade == "7" or grade == "c" then table.insert(categories, "[[Category:Common kanji|" .. catsort .. "]]")
elseif grade == "8" or grade == "n" then table.insert(categories, "[[Category:Kanji used for names|" .. catsort .. "]]")
elseif grade == "9" or grade == "uc" then table.insert(categories, "[[Category:Uncommon kanji|" .. catsort .. "]]")
elseif grade == "0" or grade == "r" then table.insert(categories, "[[Category:CJKV radicals| ]]")
end
-- error category
if rs == "" then table.insert(categories, "[[Category:Japanese terms needing attention/radical and strokes]]") end
return table.concat(wikitext, "") .. table.concat(categories, "\n")
end
end
local grade1_pattern = ('[' .. data.grade1 .. ']')
local grade2_pattern = ('[' .. data.grade2 .. ']')
local grade3_pattern = ('[' .. data.grade3 .. ']')
local grade4_pattern = ('[' .. data.grade4 .. ']')
local grade5_pattern = ('[' .. data.grade5 .. ']')
local grade6_pattern = ('[' .. data.grade6 .. ']')
local secondary_pattern = ('[' .. data.secondary .. ']')
local jinmeiyo_kanji_pattern = ('[' .. data.jinmeiyo_kanji .. ']')
local hyogaiji_pattern = ('[^' .. data.joyo_kanji .. data.jinmeiyo_kanji .. ']')
function export.kanji_grade(kanji)
if type(kanji) == "table" then
kanji = kanji.args[1]
end
if match(kanji, hyogaiji_pattern) then return 9
elseif match(kanji, jinmeiyo_kanji_pattern) then return 8
elseif match(kanji, secondary_pattern) then return 7
elseif match(kanji, grade6_pattern) then return 6
elseif match(kanji, grade5_pattern) then return 5
elseif match(kanji, grade4_pattern) then return 4
elseif match(kanji, grade3_pattern) then return 3
elseif match(kanji, grade2_pattern) then return 2
elseif match(kanji, grade1_pattern) then return 1
end
return false
end
function export.new(frame)
local args = frame:getParent().args
local result = "==Japanese=="
if args["defs"] then
result = result .. "\n{{DEFAULTSORT:" .. args["defs"] .. "}}"
end
if args["wp"] then
result = result .. "\n{{wp|lang=ja" .. (args["wp"] ~= "y" and "|" .. args["wp"] or "") .. "}}"
end
wp_count = 2
while args["wp" .. wp_count] do
result = result .. "\n{{wp|lang=ja|" .. args["wp" .. wp_count] .. "}}"
wp_count = wp_count + 1
end
if args["swp"] then
result = result .. "\n{{swp|lang=ja" .. (args["swp"] ~= "y" and "|" .. args["swp"] or "") .. "}}"
end
swp_count = 2
while args["swp" .. swp_count] do
result = result .. "\n{{swp|lang=ja|" .. args["swp" .. swp_count] .. "}}"
swp_count = swp_count + 1
end
pagename = mw.title.getCurrentTitle().text
text = args[1] ~= "" and args[1] or pagename
text = gsub(text, "%-", "|")
local function make_tab(original, yomi)
output_text = ""
original = gsub(original, " ", "|")
original = gsub(original, "%.", "|")
original = gsub(original, "%^", "")
if match(original, "<") then
for word in gmatch(original, "<([^>]+)>") do
output_text = output_text .. "|" .. word
end
yomi = yomi or "k"
else
output_text = gsub(original, ">([1-9])", "|k%1=")
output_text = match(output_text, "|") and "|" .. output_text or false
end
yomi = yomi or "o"
return "\n{{ja-kanjitab" .. (output_text or "") .. "|yomi=" .. yomi .. (yomi == "irr" and "" or sortkey or "") .. "}}", yomi
end
if match(pagename, "[㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-]") then
to_add, yomi = make_tab(text, args["yomi"])
result = result .. to_add
end
if match(text, "<") then
text = gsub(text, "[<>]", "")
else
text = gsub(text, "^[^>|]+>%d+([^>|]+)", "%1")
text = gsub(text, "|[^>|]+>%d+([^>|]+)", "%1")
text = gsub(text, "([あかがさざただなはばぱまやらわ])|(あ)", "%1.%2")
text = gsub(text, "([いきぎしじちぢにひびぴみり])|(い)", "%1.%2")
text = gsub(text, "([うくぐすずつづぬふむゆる])|(う)", "%1.%2")
text = gsub(text, "([えけげせぜてでねへめれ])|([えい])", "%1.%2")
text = gsub(text, "([おこごそぞとどのほぼぽもよろ])|([おう])", "%1.%2")
text = gsub(text, "|", "")
end
local function other(class, title, args)
local code, i = "", 2
if args[class] then
code = code .. "\n\n===" .. title .. "===\n* {{ja-l|" .. args[class] .. "}}"
while args[class .. i] do
code = code .. "\n* {{ja-l|" .. args[class .. i] .. "}}"
i = i + 1
end
end
code = gsub(code, "{{ja%-l\|([^%|%}]+)[:：]", "{{ja-r|%1|") -- change something like "{{ja-l|辞典:じてん}}" to "{{ja-r|辞典|じてん}}"
code = gsub(code, "{{ja%-l\|([ぁ-ー ^%%.]+)}}", "{{ja-r|%1}}") -- change something like "{{ja-l|じてん}}" to "{{ja-r|じてん}}"
return code
end
result = result .. other("alt", "Alternative forms", args)
sortkey = export.script(text) == "Kana" and export.sort(text) or false
if sortkey and sortkey == "|sort=" .. text then
sortkey = false
end
if args["d"] or args["e"] or args["we1"] or args["b"] or args["lb"] or args["co1"] or args["et"] or args["pr1"] or args["su1"] then
result = result .. "\n\n===Etymology===\n"
if args["we1"] then
result = result .. "{{waei|" .. args["we1"] .. (args["we2"] and "|" .. args["we2"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"
else
if args["pr1"] then
result = result .. "{{pre|ja|" .. args["pr1"] .. "|" .. args["pr2"] .. (args["defs"] and "" or sortkey or "") .. (args["tr1"] and "|tr1=" .. args["tr1"] or "") .. (args["tr2"] and "|tr2=" .. args["tr2"] or "") .. (args["pos1"] and "|pos1=" .. args["pos1"] or "") .. (args["pos2"] and "|pos2=" .. args["pos2"] or "") .. (args["t1"] and "|t1=" .. args["t1"] or "") .. (args["t2"] and "|t2=" .. args["t2"] or "") .. "}}"
else
if args["su1"] then
result = result .. "{{suf|ja|" .. args["su1"] .. "|" .. args["su2"] .. (args["defs"] and "" or sortkey or "") .. (args["tr1"] and "|tr1=" .. args["tr1"] or "") .. (args["tr2"] and "|tr2=" .. args["tr2"] or "") .. (args["pos1"] and "|pos1=" .. args["pos1"] or "") .. (args["pos2"] and "|pos2=" .. args["pos2"] or "") .. (args["t1"] and "|t1=" .. args["t1"] or "") .. (args["t2"] and "|t2=" .. args["t2"] or "") .. "}}"
else
if args["co1"] then
result = result .. "{{com|ja|" .. args["co1"] .. "|" .. args["co2"] .. (args["co3"] and "|" .. args["co3"] or "") .. (args["co4"] and "|" .. args["co4"] or "") .. (args["co5"] and "|" .. args["co5"] or "") .. (args["co6"] and "|" .. args["co6"] or "") .. (args["tr1"] and "|tr1=" .. args["tr1"] or "") .. (args["tr2"] and "|tr2=" .. args["tr2"] or "") .. (args["tr3"] and "|tr3=" .. args["tr3"] or "") .. (args["tr4"] and "|tr4=" .. args["tr4"] or "") .. (args["tr5"] and "|tr5=" .. args["tr5"] or "") .. (args["tr6"] and "|tr6=" .. args["tr6"] or "") .. (args["pos1"] and "|pos1=" .. args["pos1"] or "") .. (args["pos2"] and "|pos2=" .. args["pos2"] or "") .. (args["pos3"] and "|pos3=" .. args["pos3"] or "") .. (args["pos4"] and "|pos4=" .. args["pos4"] or "") .. (args["pos5"] and "|pos5=" .. args["pos5"] or "") .. (args["pos6"] and "|pos6=" .. args["pos6"] or "") .. (args["t1"] and "|t1=" .. args["t1"] or "") .. (args["t2"] and "|t2=" .. args["t2"] or "") .. (args["t3"] and "|t3=" .. args["t3"] or "") .. (args["t4"] and "|t4=" .. args["t4"] or "") .. (args["t5"] and "|t5=" .. args["t5"] or "") .. (args["t6"] and "|t6=" .. args["t6"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"
else
if args["et"] then
result = result .. "{{cal|ja|" .. ((args["el"] and "etyl lang=" .. args["el"]) or "etyl lang=en") .. "|etyl term=" .. args["et"] .. (args["nocap"] and "|nocap=" .. args["nocap"] or "") .. (args["ca1"] and "|" .. args["ca1"] or "") .. (args["ca2"] and "|" .. args["ca2"] or "") .. (args["ca3"] and "|" .. args["ca3"] or "") .. (args["ca4"] and "|" .. args["ca4"] or "") .. (args["ca5"] and "|" .. args["ca5"] or "") .. (args["ca6"] and "|" .. args["ca6"] or "") .. (args["tr1"] and "|tr1=" .. args["tr1"] or "") .. (args["tr2"] and "|tr2=" .. args["tr2"] or "") .. (args["tr3"] and "|tr3=" .. args["tr3"] or "") .. (args["tr4"] and "|tr4=" .. args["tr4"] or "") .. (args["tr5"] and "|tr5=" .. args["tr5"] or "") .. (args["tr6"] and "|tr6=" .. args["tr6"] or "") .. (args["pos1"] and "|pos1=" .. args["pos1"] or "") .. (args["pos2"] and "|pos2=" .. args["pos2"] or "") .. (args["pos3"] and "|pos3=" .. args["pos3"] or "") .. (args["pos4"] and "|pos4=" .. args["pos4"] or "") .. (args["pos5"] and "|pos5=" .. args["pos5"] or "") .. (args["pos6"] and "|pos6=" .. args["pos6"] or "") .. (args["t1"] and "|t1=" .. args["t1"] or "") .. (args["t2"] and "|t2=" .. args["t2"] or "") .. (args["t3"] and "|t3=" .. args["t3"] or "") .. (args["t4"] and "|t4=" .. args["t4"] or "") .. (args["t5"] and "|t5=" .. args["t5"] or "") .. (args["t6"] and "|t6=" .. args["t6"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"
else
if args["b"] then
result = result .. "{{bor|ja|" .. (args["bl"] or "en") .. (args["b"] and "|" .. args["b"] or "") .. (args["tr"] and "|tr=" .. args["tr"] or "") .. (args["t"] and "||" .. args["t"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"
else
if args["lb"] then
result = result .. "{{lbor|ja|" .. (args["lbl"] or "grc") .. (args["lb"] and "|" .. args["lb"] or "") .. (args["tr"] and "|tr=" .. args["tr"] or "") .. (args["t"] and "||" .. args["t"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"
else
result = result .. (args["e"] or
("From {{der|ja|" .. (args["dl"] or "en") .. (args["d"] and "|" .. args["d"] or "") .. (args["tr"] and "|tr=" .. args["tr"] or "") .. (args["t"] and "||" .. args["t"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"))
end
end
end
end
end
end
end
end
if not args["nop"] then
result = result .. "\n\n===Pronunciation===\n{{ja-pron" .. (args[1] ~= "" and "|" .. gsub(text, '%^', '') or "")
if args["y"] == "n" then
result = result .. ""
else if args["y"] and args["y"] ~= "n" then
result = result .. "|y=" .. args["y"]
else if yomi then
if yomi == "irr" then
result = result .. "|y=i"
else
result = result .. "|y=" .. yomi
end
end
end
end
result = result .. (args["acc"] and "|acc=" .. args["acc"] or "") .. (args["acc2"] and "|acc2=" .. args["acc2"] or "") .. (args["acc3"] and "|acc3=" .. args["acc3"] or "") .. (args["acc4"] and "|acc4=" .. args["acc4"] or "") .. (args["acc_ref"] and "|acc_ref=" .. args["acc_ref"] or "") .. (args["acc2_ref"] and "|acc2_ref=" .. args["acc2_ref"] or "") .. (args["acc3_ref"] and "|acc3_ref=" .. args["acc3_ref"] or "") .. (args["acc4_ref"] and "|acc4_ref=" .. args["acc4_ref"] or "") .. (args["dev"] and "|dev=" .. args["dev"] or "") .. "}}" .. (args["hmp"] and "\n* {{hmp|lang=ja|" .. args["hmp"] .. (args["hmp2"] and "|" .. args["hmp2"] or "") .. (args["hmp3"] and "|" .. args["hmp3"] or "") .. (args["hmp4"] and "|" .. args["hmp4"] or "") .. (args["hmp5"] and "|" .. args["hmp5"] or "") .. (args["hmp6"] and "|" .. args["hmp6"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}" or "")
end
local pos = args[2] ~= "" and args[2] or "n"
local pos_table = {
[""] = { "Noun", "noun", true },
["n"] = { "Noun", "noun", true },
["s"] = { "Noun", "noun", true, "Verb", "verb-suru" },
["noun"] = { "Noun", "noun", true },
["suru"] = { "Noun", "noun", true, "Verb", "verb-suru" },
["an"] = { "Adjective", "adj", true, "Noun", "noun" },
["anoun"] = { "Adjective", "adj", true, "Noun", "noun" },
["v"] = { "Verb", "verb", true },
["verb"] = { "Verb", "verb", true },
["vform"] = { "Verb", "verb form", true },
["verb form"] = { "Verb", "verb form", true },
["a"] = { "Adjective", "adj", true },
["adj"] = { "Adjective", "adj", true },
["adjective"] = { "Adjective", "adj", true },
["adv"] = { "Adverb", "adverb", false },
["adverb"] = { "Adverb", "adverb", false },
["pron"] = { "Pronoun", "pronoun", false },
["pronoun"] = { "Pronoun", "pronoun", false },
["pn"] = { "Proper noun", "proper", false },
["propn"] = { "Proper noun", "proper", false },
["proper"] = { "Proper noun", "proper", false },
["proper noun"] = { "Proper noun", "proper", false },
["ph"] = { "Phrase", "phrase", true },
["phrase"] = { "Phrase", "phrase", true },
["interjection"] = { "Interjection", "interjection", false },
["intj"] = { "Interjection", "interjection", false },
["conj"] = { "Conjunction", "conjunction", false },
["part"] = { "Particle", "particle", false },
["prep"] = { "Preposition", "preposition", false },
["suf"] = { "Suffix", "suffix", false },
["suffix"] = { "Suffix", "suffix", false },
["pref"] = { "Prefix", "prefix", false },
["prefix"] = { "Prefix", "prefix", false },
["prov"] = { "Proverb", "proverb", false },
}
result = result .. "\n\n===" .. pos_table[pos][1] .. "===\n{{ja-" ..
(not pos_table[pos][3] and "pos|" or "") .. pos_table[pos][2] ..
(args[1] ~= "" and "|" .. text or "") ..
(args["head"] and "|head=" .. args["head"] or "") ..
(args["kyu"] and "|kyu=" .. args["kyu"] or "") ..
(args["sin"] and "|shin=" .. args["sin"] or "") ..
(args["ak"] and "|" .. args["ak"] or "") ..
(args["ak2"] and "|" .. args["ak2"] or "") ..
(args["ro"] and "|rom=" .. args["ro"] or "") ..
(args["hh"] and "|hhira=" .. args["hh"] or "") ..
(args["hk"] and "|hkata=" .. args["hk"] or "")
if pos_table[pos][1] == "Adjective" then
result = result .. "|infl=" .. (args["infl"] and args["infl"] or "na")
end
result = result .. (args["type"] and "|type=" .. args["type"] or "") .. (args["tr"] and "|tr=" .. args["tr"] or "") .. "}}"
result = result .. "\n\n# " .. (args[3] or "{{rfdef|ja}}")
if pos_table[pos][1] == "Adjective" then
result = result .. "\n\n====Inflection====\n"
if args["infl"] == "i" or args["infl"] == "い" then
result = result .. "{{ja-i" .. (args[1] ~= "" and "|" .. sub(text, 1, -2) or "") .. "}}"
else
result = result .. "{{ja-na" .. (args[1] ~= "" and "|" .. text or "") .. "}}"
end
end
if pos_table[pos][2] == "verb" then
result = result .. "\n\n====Conjugation====\n{{ja-"
penul, cons = text, text
penul, cons = sub(penul, -2, -2), sub(cons, -1, -1)
penul, cons = export.hira_to_kata(penul), export.hira_to_kata(cons)
penul, cons = gsub(penul, ".", function (char) return data.kr[char] or char end), gsub(cons, ".", function (char) return data.kr[char] or char end)
penul, cons = sub(penul, -1, -1), sub(cons, 1, 1)
if cons == "u" then
cons = ""
elseif cons == "c" then
cons = "ts"
end
if final == "る" and (penul == "i" or penul == "e") and args["type"] == 2 then
result = result .. "ichi"
else
result = result .. "go-" .. cons .. "u"
end
result = result .. (args[1] ~= "" and "|" .. sub(text, 1, -2) or "") .. "}}"
end
if pos_table[pos][4] and args[4] ~= "" then
result = result .. "\n\n===" .. pos_table[pos][4] .. "===\n{{ja-" .. pos_table[pos][5] .. (args[1] ~= "" and "|" .. text or "") ..
(args["type"] and "|type=" .. args["type"] or "") .. (args["tr"] and "|tr=" .. args["tr"] or "") .. "}}\n\n# " .. (args[4] or "{{rfdef|ja}}")
if pos_table[pos][4] == "Verb" then
result = result .. "\n\n====Conjugation====\n{{ja-suru" .. (args[1] ~= "" and "|" .. text or "") .. "}}"
end
end
result = result .. other("syn", "=Synonyms=", args)
result = result .. other("ant", "=Antonyms=", args)
result = result .. other("der", "=Derived terms=", args)
result = result .. other("rel", "=Related terms=", args)
if args["dzh"] or args["dko"] or args["dvi"] then
result = result .. "\n\n===Descendants===\n" .. (args["dzh"] and "* Chinese: {{zh-l|" .. args["dzh"] .. "}}" or "")
if args["dzh"] then
if args["dko"] or args["dvi"] then
result = result .. "\n"
end
end
result = result .. (args["dko"] and "* Korean: {{ko-l|" .. args["dko"] .. "}}" or "")
if args["dko"] then
if args["dvi"] then
result = result .. "\n"
end
end
result = result .. (args["dvi"] and "* Vietnamese: {{vi-l|" .. args["dvi"] .. "}}" or "")
end
result = result .. other("ana", "Anagrams", args)
result = result .. other("also", "See also", args)
if args["acc_ref"] or args["acc2_ref"] or args["acc3_ref"] then
result = result .. "\n\n===References===\n<references/>"
end
if args["cn"] then
result = result .. "\n\n{{cln|ja|" .. args["cn"] .. (args["cn2"] and "|" .. args["cn2"] or "") .. (args["cn3"] and "|" .. args["cn3"] or "") .. (args["cn4"] and "|" .. args["cn4"] or "") .. (args["cn5"] and "|" .. args["cn5"] or "") .. (args["cn6"] and "|" .. args["cn6"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"
end
if args["ct"] then
result = result .. (args["cn"] and "\n" or "\n\n") .. "{{C|ja|" .. args["ct"] .. (args["ct2"] and "|" .. args["ct2"] or "") .. (args["ct3"] and "|" .. args["ct3"] or "") .. (args["ct4"] and "|" .. args["ct4"] or "") .. (args["ct5"] and "|" .. args["ct5"] or "") .. (args["ct6"] and "|" .. args["ct6"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"
end
if args["k"] then
result = result .."\n\n----\n\n==Korean==\n{{ko-hanjatab}}\n\n===" .. pos_table[args["kp"] or "n"][1] ..
"===\n{{ko-" .. pos_table[args["kp"] or "n"][2] .. "|hangeul=" .. args["k"] .. (args["mr"] and "|mr=" .. args["mr"] or "") .. (args["yl"] and "|y=" .. args["yl"] or "") .. "}}" ..
"\n\n# {{hanja form of|" .. args["k"] .. "|" .. (args["kd"] or args[3]) .. "}}"
end
return result
end
return export
