Modul:ja
Bu modulun sənədləşdirmə səhifəsi Modul:ja/doc səhifəsində yaradıla bilər
local export = {}
-- note that arrays loaded by mw.loadData cannot be directly used by mw.ustring.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.romaji_dediacritics(text)
if type(text) == "table" then
text = text.args[1]
end
return (mw.ustring.gsub(text, '.', function (char) return data.rd[char] or char end))
end
function export.hira_to_kata(text)
if type(text) == "table" then
text = text.args[1]
end
return (mw.ustring.gsub(text, '.', function (char) return data.hk[char] or char end))
end
function export.kata_to_hira(text)
if type(text) == "table" then
text = text.args[1]
end
return (mw.ustring.gsub(text, '.', function (char) return data.kh[char] or char end))
end
function export.kana_to_romaji(text, nodiacr, keepdot)
if type(text) == "table" then -- assume a frame.
text, nodiacr = text.args[1], text.args[2]
end
-- local kr_minus_period = data.kr
-- kr_minus_period["。"] = "。"
-- convert Japanese spaces to western spaces
text = mw.ustring.gsub(text, ' ', ' ')
text = mw.ustring.gsub(text, 'っ%%', 'っ')
text = mw.ustring.gsub(text, 'ッ%%', 'ッ')
-- if there is a は separated by halfwidth spaces, romanize it as " wa "
text = mw.ustring.gsub(text, ' は ', ' wa ')
-- also if it follows a space and is the last character, e.g. それでは
text = mw.ustring.gsub(text, ' は$', ' wa')
-- or " は、"
text = mw.ustring.gsub(text, ' は、', ' wa, ')
-- or " は。"
text = mw.ustring.gsub(text, ' は。', ' wa. ')
text = mw.ustring.gsub(text, ' は？', ' wa? ')
text = mw.ustring.gsub(text, ' は）', ' wa)')
-- or " '''は''' "
text = mw.ustring.gsub(text, " '''は''' ", " '''wa''' ")
-- romanize では as "dewa"
text = mw.ustring.gsub(text, ' では ', ' dewa ')
text = mw.ustring.gsub(text, ' では$', ' dewa')
text = mw.ustring.gsub(text, ' では、', ' dewa, ')
text = mw.ustring.gsub(text, ' では。', ' dewa. ')
text = mw.ustring.gsub(text, ' では？', ' dewa? ')
text = mw.ustring.gsub(text, ' では）', ' dewa)')
text = mw.ustring.gsub(text, "'''では'''", "'''dewa'''")
-- romanize で は (with space) as "de wa"
text = mw.ustring.gsub(text, "'''で は'''", "'''de wa'''")
-- same sort of thing for へ
text = mw.ustring.gsub(text, ' へ ', ' e ')
text = mw.ustring.gsub(text, " '''へ''' ", " '''e''' ")
text = mw.ustring.gsub(text, ' へ$', ' e')
text = mw.ustring.gsub(text, ' へ、', ' e, ')
text = mw.ustring.gsub(text, ' へ。', ' e. ')
text = mw.ustring.gsub(text, ' へ？', ' e?')
text = mw.ustring.gsub(text, ' へ）', ' e)')
-- dangling small tsu is romanized as nothing
text = mw.ustring.gsub(text, 'ッ。', '。')
text = mw.ustring.gsub(text, 'ッ！', '！')
text = mw.ustring.gsub(text, 'ッ」', '」')
text = mw.ustring.gsub(text, 'ッ、', '、')
-- ゝ means "repeat the previous character" and is used with hiragana, like 々 is for kanji
-- TODO: do same sort of thing for ゞ
text = mw.ustring.gsub(text, '(.)ゝ', '%1%1')
-- romanising ヶ
text = mw.ustring.gsub(text, 'ヶげつ', 'kagetsu')
text = mw.ustring.gsub(text, 'ヶ', 'ga')
-- convert hiragana to katakana
text = mw.ustring.gsub(text, '.', function (char) return data.hk[char] or char end)
-- replace katakana with romaji (?? not sure what the pattern below does ??)
-- this is hackish, but we're using the period to indicate morpheme boundaries to prevent macrons
-- from forming across them, so we'll remove the ASCII periods used for markup but not the Japanese periods
-- convert the Japanese periods at the end
--table.remove(kr_minus_period, "。")
text = mw.ustring.gsub(text, '.[ィェォャュョァヮゥ゜]?ェ?',
function (char)
if char == "。" then
return char
else
return data.kr[char] or char
end
end)
-- replace long vowel mark with the vowel that comes before
text = mw.ustring.gsub(text, '([aeiou])ー', '%1%1')
-- add vowels with diacritics
if not nodiacr then
text = mw.ustring.gsub(text, 'oo', 'ō')
text = mw.ustring.gsub(text, 'aa', 'ā')
text = mw.ustring.gsub(text, 'ee', 'ē')
text = mw.ustring.gsub(text, 'ou', 'ō')
text = mw.ustring.gsub(text, 'uu', 'ū')
text = mw.ustring.gsub(text, 'ii', 'ī')
end
if not keepdot then
-- if input had spaces, keep them
-- if the input string had periods, then remove them now
text = mw.ustring.gsub(text, '%.', '')
-- now that markup periods are gone, convert the Japanese periods to western periods
text = mw.ustring.gsub(text, "。", ". ")
end
-- romanize sokuon or geminate consonants
-- text = mw.ustring.gsub(text, '^ッ', '')
-- double the previous consonant letter if there is a small tsu
text = mw.ustring.gsub(text, 'ッ([kstpgdbjzrfh])', '%1%1')
text = mw.ustring.gsub(text, 'ッ\'\'\'([kstpgdbjzrfh])', '%1\'\'\'%1')
-- replace ッc with tc
text = mw.ustring.gsub(text, 'ッc', 'tc')
text = mw.ustring.gsub(text, 'ッ\'\'\'c', 't\'\'\'c')
-- if small tsu comes at the end, just throw it away
text = mw.ustring.gsub(text, 'ッ$', '')
-- the @ is used to determine when to insert an opostrophe after ん or ン
-- (all is kata at that point)
-- insert apostrophe when ン is followed by a vowel or
-- y, which corresponds to the cases んや (n'ya) んゆ (n'yu) and んよ (n'yo)
text = mw.ustring.gsub(text, "@([aeiouāēīōūy])", "'%1")
-- remove @
text = mw.ustring.gsub(text, "@", "")
-- capitalize any letter following a ^ symbol
text = mw.ustring.gsub(text, "%^%l", mw.ustring.upper)
-- remove ^
text = mw.ustring.gsub(text, "%^", "")
-- remove %
text = mw.ustring.gsub(text, '%%', '')
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 = f.args[1]
text = mw.ustring.gsub(text, ' ', '')
text = mw.ustring.gsub(text, '-', '')
text = mw.ustring.gsub(text, '%.', '')
text = mw.ustring.gsub(text, ' ', '')
text = mw.ustring.gsub(text, '\'', '')
return text
end
function export.romaji_to_kata(f)
local text = f.args[1]
text = mw.ustring.gsub(text, '.', function (char) return data.rd[char] or char end)
text = mw.ustring.gsub(text, 'kk', 'ッk')
text = mw.ustring.gsub(text, 'ss', 'ッs')
text = mw.ustring.gsub(text, 'tt', 'ッt')
text = mw.ustring.gsub(text, 'pp', 'ッp')
text = mw.ustring.gsub(text, 'bb', 'ッb')
text = mw.ustring.gsub(text, 'dd', 'ッd')
text = mw.ustring.gsub(text, 'gg', 'ッg')
text = mw.ustring.gsub(text, 'jj', 'ッj')
text = mw.ustring.gsub(text, 'tc', 'ッc')
text = mw.ustring.gsub(text, 'tsyu', 'ツュ')
text = mw.ustring.gsub(text, 'ts[uoiea]', {['tsu']='ツ',['tso']='ツォ',['tsi']='ツィ',['tse']='ツェ',['tsa']='ツァ'})
text = mw.ustring.gsub(text, 'sh[uoiea]', {['shu']='シュ',['sho']='ショ',['shi']='シ',['she']='シェ',['sha']='シャ'})
text = mw.ustring.gsub(text, 'ch[uoiea]', {['chu']='チュ',['cho']='チョ',['chi']='チ',['che']='チェ',['cha']='チャ'})
text = mw.ustring.gsub(text, "n[uoiea']?", {['nu']='ヌ',['no']='ノ',['ni']='ニ',['ne']='ネ',['na']='ナ',['n']='ン',["n'"]='ン'})
text = mw.ustring.gsub(text, '[wvtrpsmlkjhgfdbzy][yw]?[uoiea]', function (char) return data.rk[char] or char end)
text = mw.ustring.gsub(text, 'u', 'ウ')
text = mw.ustring.gsub(text, 'o', 'オ')
text = mw.ustring.gsub(text, 'i', 'イ')
text = mw.ustring.gsub(text, 'e', 'エ')
text = mw.ustring.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 mw.ustring.match(text, '[ぁ-ゖ]') then
table.insert(script, 'Hira')
end
-- TODO: there are two kanas. This should insert Kata.
if mw.ustring.match(text, '[ァ-ヺー]') then
table.insert(script, 'Kana')
end
-- 一 is unicode 4e00, previously used 丁 is 4e01
if mw.ustring.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 mw.ustring.match(text, '[a-zA-ZāēīōūĀĒĪŌŪａ-ｚＡ-Ｚ]') then
table.insert(script, 'Romaji')
end
if mw.ustring.match(text, '[0-9０-９]') then
table.insert(script, 'Number')
end
if mw.ustring.match(text, '[〆々]') then
table.insert(script, 'Abbreviation')
end
return table.concat(script, '+')
end
-- accepts the entry name, extracts the kanji, and
-- puts the kanji inside {{ja-kanji|}} and returns it
function export.extract_kanji(f)
local text = f.args[1]
local len = 1
local result = ''
text = mw.ustring.gsub(mw.ustring.gsub(text, ".", function (char) return data.ky[char] or char end), ".", function (char) return data.hy[char] or char end)
text = mw.ustring.gsub(text,' ','')
len = mw.ustring.len(text)
if text ~= '' then
result = '{{ja-kanjitab'
-- for i = 1, len, 1 do
-- char = mw.ustring.sub(text,i,i)
-- result = (result .. '|' .. char)
-- end
result = (result .. '}}')
end
return result
end
-- returns the number of kanji in this term
function export.count_kanji(f)
local text = f.args[1]
local len = 1
-- replace 時々 with 時時
text = mw.ustring.gsub(text, '([㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-])々', '%1%1')
-- See w:Template:CJK_ideographs_in_Unicode (U+3400 - U+4DB5, U+4E00 - U+9FCC, U+F900 (escaped to avoid normalisation) - U+FAD9 (escaped to avoid normalisation), U+20000 - U+2FA1F)
text = mw.ustring.gsub(text, '[^㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-]', '')
len = mw.ustring.len(text)
return len
end
-- used within other functions but >> no longer necessary <<
-- returns a hidx-style hiragana sort key attached to |hidx=,
-- e.g. |hidx=はつぐん' when given ばつぐん
function export.hidx(f)
local text = f.args[1]
local textsub = ''
local convertedten = ''
local result = ''
local len = 1
local kyreplace = ''
kyreplace = mw.ustring.gsub(text,'.',function (char) return data.ky[char] or char end)
if kyreplace == '' then
result = ('|' .. 'hidx' .. '=')
end
text = mw.ustring.gsub(text,'.',function (char) return data.kh[char] or char end)
if mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.dakuten[char] or char end) == '' then
if kyreplace == '' then else result = ('|' .. 'hidx' .. '=') end
len = mw.ustring.len(text)
textsub = mw.ustring.sub(text,2,len)
convertedten = mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.tenconv[char] or char end)
result = (result .. convertedten .. textsub .. "'")
else
if mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.handakuten[char] or char end) == '' then
if kyreplace == '' then else result = ('|' .. 'hidx' .. '=') end
len = mw.ustring.len(text)
textsub = mw.ustring.sub(text,2,len)
convertedten = mw.ustring.gsub(mw.ustring.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
-- 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 = mw.ustring.gsub(text, '.', function (char) return data.kh[char] or char end)
-- remove all of the small hiragana such as ょ except small tsu
text = mw.ustring.gsub(text,'.',function (char) return data.nonmora_to_empty[char] or char end)
-- remove zero-width spaces
text = mw.ustring.gsub(text, '', '')
-- return number of characters, which should be the number of morae
return mw.ustring.len(text)
end
-- accepts: any mix of kana
-- returns: a hiragana sort key designed for WMF software (hidx of old)
-- this is like hidx above but doesn't return |hidx=sortkey,
-- just the sort key itself, but unlike hidx above, 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
text = mw.ustring.gsub(text, '[ %-%.]', '')
text = mw.ustring.gsub(text,'.',function (char) return data.kh[char] or char end)
-- 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 mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.dakuten[char] or char end) == '' then
len = mw.ustring.len(text)
textsub = mw.ustring.sub(text,2,len)
convertedten = mw.ustring.gsub(mw.ustring.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 mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.handakuten[char] or char end) == '' then
len = mw.ustring.len(text)
textsub = mw.ustring.sub(text,2,len)
convertedten = mw.ustring.gsub(mw.ustring.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 = mw.ustring.gsub(text,key,value)
end
return text
end
-- returns 'yes' if the string contains kana (not exactly is kana)
-- returns 'no' otherwise, including if string is empty
function export.is_kana(f)
local text = f.args[1]
if mw.ustring.match(text, '[ぁ-ゖ]') then
return 'yes'
end
if mw.ustring.match(text, '[ァ-ヺ]') then
return 'yes'
end
return 'no'
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(text) == 'table' and f.args[1] or f
local textsub = ''
local convertedten = ''
local result = ''
local len = 1
local kyreplace = ''
kyreplace = mw.ustring.gsub(text,'.',function (char) return data.ky[char] or char end)
if kyreplace == '' then
result = ('|' .. 'sort' .. '=')
end
text = mw.ustring.gsub(text,'.',function (char) return data.kh[char] or char end)
if mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.dakuten[char] or char end) == '' then
if kyreplace == '' then else result = ('|' .. 'sort' .. '=') end
len = mw.ustring.len(text)
textsub = mw.ustring.sub(text,2,len)
convertedten = mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.tenconv[char] or char end)
result = (result .. convertedten .. textsub .. "'")
else
if mw.ustring.gsub(mw.ustring.sub(text,1,1),'.',function (char) return data.handakuten[char] or char end) == '' then
if kyreplace == '' then else result = ('|' .. 'sort' .. '=') end
len = mw.ustring.len(text)
textsub = mw.ustring.sub(text,2,len)
convertedten = mw.ustring.gsub(mw.ustring.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 mw.ustring.sub(f.args[1],1,(mw.ustring.len(f.args[1])-1))
end
-- this generates links to categories of the form
-- Category:Japanese terms spelled with (kanji)
-- which was previously done in Template:ja-kanjitab
-- but depended on the editor entering the right kanji
function export.spelled_with_kanji()
local PAGENAME = mw.title.getCurrentTitle().text
--PAGENAME = f.args["pagename"]
local cats = {}
local c = ''
-- remove non-kanji characters
-- technically 々 is not a kanji, but we want a category for it, so leave it in
PAGENAME = mw.ustring.gsub(PAGENAME, '[^㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-]', '')
local uniquekanji = ""
for k in mw.ustring.gmatch(PAGENAME,".") do
if not mw.ustring.find(uniquekanji,k) then uniquekanji = (uniquekanji .. k) end
end
for i = 1, mw.ustring.len(uniquekanji) do
local c = mw.ustring.sub(uniquekanji,i,i)
table.insert(cats, '[[Category:Japanese terms spelled with ')
table.insert(cats, c)
--table.insert(cats, '|')
--table.insert(cats, sortkey)
table.insert(cats, ']]')
--table.insert(cats, "\n")
--table.insert(cats, '</nowiki>')
end
return table.concat(cats, '')
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 = mw.ustring.gsub(term, '%[%[([^|%]]+)%]%]', '[[%1|%1]]')
-- remove links from kana
kana = mw.ustring.gsub(kana, '%[%[([^|%]]+)%]%]', '%1')
kana = mw.ustring.gsub(kana, '%[%[[^%]]+|([^%]]+)%]%]', '%1')
-- build up pattern
-- escape the magic characters in the term
pattern = mw.ustring.gsub(term, '%[%[[^%]]+|([^%]]+)%]%]', '%1')
pattern = require("Module:utilities").pattern_escape(pattern)
pattern = mw.ustring.gsub(pattern, "[%[%]]+", " *")
kana = mw.ustring.gsub(kana, "[%[%]]+", '')
pattern = mw.ustring.gsub(pattern, " *('+) *", "%1")
kana = mw.ustring.gsub(kana, " *('+) *", "%1")
pattern = mw.ustring.gsub(pattern, " +", " ")
kana = mw.ustring.gsub(kana, " +", " ")
-- remove periods and caret signs and hyphens
pattern = mw.ustring.gsub(pattern, '%%[%.%^%-]', '')
kana = mw.ustring.gsub(kana, '[%.%^%-]', '')
-- in order to make a pattern that will find the ruby,
-- replace every unbroken string of kanji with a sub-pattern
pattern = mw.ustring.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 = mw.ustring.gsub(term, '%]', '%]') -- escape the "]" character so that it cannot appear, example becomes [[歌う|歌った%]%]
term = mw.ustring.gsub(term, kanji_pattern .. '+', function(text)
count = count + 1
table.insert(replaced, text)
return '[' .. count .. ']'
end) -- example becomes [[[1]う|[2]った%]%]
-- remove spaces
for i,val in ipairs(replaced) do replaced[i] = mw.ustring.gsub(val, ' ', '') end
while mw.ustring.match(term, '%[%[[^|]*%[[0-9]+%][^|]*|') do
term = mw.ustring.gsub(term, '(%[%[[^|]*)%[([0-9]+)%]([^|]*|)', 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 mw.ustring.match(kana, pattern) == nil then kana = mw.ustring.gsub(kana, ' ', '') end
local ruby = { mw.ustring.match(kana, pattern) }
-- local ruby = {}
-- for c in mw.ustring.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 mw.ustring.gmatch(term, '%[([0-9]+)%]') do table.insert(kanji_segments, replaced[tonumber(c)]) end
for i = 1, #kanji_segments do
table.insert(ruby_markup, "<ruby>" .. kanji_segments[i] .. "<rp> (</rp><rt>" .. ruby[i] .. "</rt><rp>) </rp></ruby>")
end
count = 0
term = mw.ustring.gsub(term, '%[[0-9]+%]', function()
count = count + 1
return ruby_markup[count]
end)
term = mw.ustring.gsub(term, '%%%]', ']')
term = mw.ustring.gsub(term, '%%', '')
term = mw.ustring.gsub(term, ' ', '')
--done
return '<span style="font-size: 1.2em">' .. term .. '</span>'
end
-- replaces the code in Template:ja-readings which accepted kanji readings
-- and displayed them in a consistent format
function export.readings(frame)
-- only do this if this entry is a kanji page and not some user's page
local PAGENAME = mw.title.getCurrentTitle().text
if mw.ustring.match(PAGENAME, "[㐀-䶵一-鿌\239\164\128-\239\171\153𠀀-]") then
local args = frame:getParent().args
local goon = args["goon"] or ""
local kanon = args["kanon"] or ""
local toon = args["toon"] or ""
local soon = args["soon"] or ""
local kanyoon = args["kanyoon"] or ""
local on = args["on"] or ""
local kun = args["kun"] or ""
local nanori = args["nanori"] or ""
local nazuke = args["nazuke"] or ""
local nadzuke = args["nadzuke"] or ""
-- my new field for the actual reading of the _kanji_, not the entire word (which may not even
-- be written with that kanji) which is what "kun" presently has
local corekun = args["corekun"] or ""
-- this holds the finished product composed of wikilinks to be displayed
-- in the Readings section under the Kanji section
local links = {}
if goon ~= "" then table.insert(links, "* '''[[呉音|Goon]]''': " .. goon) end
if kanon ~= "" then table.insert(links, "* '''[[漢音|Kan’on]]''': " .. kanon) end
if toon ~= "" then table.insert(links, "* '''[[唐音|Tōon]]''': " .. toon) end
if soon ~= "" then table.insert(links, "* '''[[宋音|Sōon]]''': " .. soon) end
if kanyoon ~= "" then table.insert(links, "* '''[[慣用音|Kan’yōon]]''': " .. kanyoon) end
if on ~= "" then
if goon == "" and kanon == "" and toon == "" and soon == "" and kanyoon == "" then
table.insert(links, "* '''[[on'yomi|On]]''': " .. on)
else
table.insert(links, "* '''[[on'yomi|On]]''' (unclassified): " .. on)
end
end
if kun ~= "" then table.insert(links, "* '''[[kun'yomi|Kun]]''': " .. kun) end
-- three names for the same thing
if nanori ~= "" then
table.insert(links, "* '''[[nanori|Nanori]]''': " .. nanori)
elseif nazuke ~= "" then
table.insert(links, "* '''[[nanori|Nanori]]''': " .. nazuke)
elseif nadzuke ~= "" then
table.insert(links, "* '''[[nanori|Nanori]]''': " .. nadzuke)
end
-- add kanji readings categories
-- range of hiragana: [ぁ-ゖ]
-- determine if this is joyo kanji (常用) or jinmeiyo kanji (人名用) or neither (表外)
local joyo_kanji_pattern = ('[' .. data.joyo_kanji .. ']')
local jinmeiyo_kanji_pattern = ('[' .. data.jinmeiyo_kanji .. ']')
local sortkey = ""
if mw.ustring.match(PAGENAME, joyo_kanji_pattern) then sortkey = "Common"
elseif mw.ustring.match(PAGENAME, jinmeiyo_kanji_pattern) then sortkey = "Names"
else
sortkey = "Uncommon"
end
local all_usable_readings = (goon .. kanon .. toon .. soon .. kanyoon .. on .. corekun)
for r in mw.ustring.gmatch(all_usable_readings, "[{%[]([ぁ-ゖ].-)[}%]]") do
table.insert(links, "[[Category:Japanese kanji read as " .. r .. "|" .. sortkey .. "]]")
end
-- readings should only be in hiragana
if mw.ustring.match(all_usable_readings, '[ァ-ヺ]') then
table.insert(links, "[[Category:Japanese kanji needing attention]]")
end
return table.concat(links, "\n")
end
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 mw.ustring.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 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 class="Jpan" style="font-size:275%; line-height: 100%;">' .. 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 mw.ustring.match(PAGENAME, joyo_kanji_pattern) then grade = "c"
elseif mw.ustring.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 mw.ustring.match(kanji, hyogaiji_pattern) then return 9
elseif mw.ustring.match(kanji, jinmeiyo_kanji_pattern) then return 8
elseif mw.ustring.match(kanji, secondary_pattern) then return 7
elseif mw.ustring.match(kanji, grade6_pattern) then return 6
elseif mw.ustring.match(kanji, grade5_pattern) then return 5
elseif mw.ustring.match(kanji, grade4_pattern) then return 4
elseif mw.ustring.match(kanji, grade3_pattern) then return 3
elseif mw.ustring.match(kanji, grade2_pattern) then return 2
elseif mw.ustring.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
if args["wp"] == "y" then
result = result .. "\n{{wikipedia|lang=ja}}"
else
result = result .. "\n{{wikipedia|lang=ja|" .. args["wp"] .. "}}"
end
end
if args["wp2"] then
result = result .. "\n{{wikipedia|lang=ja|" .. args["wp2"] .. "}}"
end
if args["wp3"] then
result = result .. "\n{{wikipedia|lang=ja|" .. args["wp3"] .. "}}"
end
if args["wp4"] then
result = result .. "\n{{wikipedia|lang=ja|" .. args["wp4"] .. "}}"
end
if args["wp5"] then
result = result .. "\n{{wikipedia|lang=ja|" .. args["wp5"] .. "}}"
end
if args["wp6"] then
result = result .. "\n{{wikipedia|lang=ja|" .. args["wp6"] .. "}}"
end
pagename = mw.title.getCurrentTitle().text
text = args[1] ~= "" and args[1] or pagename
text = mw.ustring.gsub(text, "%-", "|")
local function make_tab(original, yomi)
output_text = ""
original = mw.ustring.gsub(original, " ", "|")
if mw.ustring.match(original, "<") then
for word in mw.ustring.gmatch(original, "<([^>]+)>") do
output_text = output_text .. "|" .. word
end
yomi = "k"
else
output_text = mw.ustring.gsub(original, ">([1-9])", "|k%1=")
output_text = mw.ustring.match(output_text, "|") and "|" .. output_text or false
end
yomi = yomi or "o"
return "\n{{ja-kanjitab" .. (output_text or "") .. "|yomi=" .. yomi .. (args["yomi"] == "irr" and "" or sortkey or "") .. "}}", yomi
end
if mw.ustring.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 mw.ustring.match(text, "<") then
text = mw.ustring.gsub(text, "[<>]", "")
else
text = mw.ustring.gsub(text, "^[^>|]+>[0-9]+([^>|]+)", "%1")
text = mw.ustring.gsub(text, "|[^>|]+>[0-9]+([^>|]+)", "%1")
text = mw.ustring.gsub(text, "([あかがさざただなはばぱまやらわ])|(あ)", "%1.%2")
text = mw.ustring.gsub(text, "([いきぎしじちぢにひびぴみり])|(い)", "%1.%2")
text = mw.ustring.gsub(text, "([うくぐすずつづぬふむゆる])|(う)", "%1.%2")
text = mw.ustring.gsub(text, "([えけげせぜてでねへめれ])|([えい])", "%1.%2")
text = mw.ustring.gsub(text, "([おこごそぞとどのほぼぽもよろ])|([おう])", "%1.%2")
text = mw.ustring.gsub(text, "|", "")
end
local function other(class, title, args)
local code = ""
if args[class] then
code = code .. "\n\n===" .. title .. "===\n* {{ja-l|" .. args[class] .. "}}"
if args[class .. "2"] then
code = code .. "\n* {{ja-l|" .. args[class .. "2"] .. "}}"
if args[class .. "3"] then
code = code .. "\n* {{ja-l|" .. args[class .. "3"] .. "}}"
if args[class .. "4"] then
code = code .. "\n* {{ja-l|" .. args[class .. "4"] .. "}}"
end
end
end
end
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["co1"] 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["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["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["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 "|t=" .. 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 "|t=" .. args["t"] or "") .. (args["defs"] and "" or sortkey or "") .. "}}"))
end
end
end
end
end
end
if not args["nop"] then
result = result .. "\n\n===Pronunciation===\n{{ja-pron" .. (args[1] ~= "" and "|" .. text or "")
if args["y"] == "n" then
result = result .. ""
else if args["y"] and args["y"] ~= "n" then
result = result .. "|y=" .. args["y"]
else
result = result .. (yomi and "|y=" .. yomi or "")
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["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["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 },
["pn"] = { "Proper noun", "proper", false },
["propn"] = { "Proper noun", "proper", false },
["proper noun"] = { "Proper noun", "proper", false },
["ph"] = { "Phrase", "phrase", true },
["phrase"] = { "Phrase", "phrase", true },
["intj"] = { "Interjection", "interjection", false },
["conj"] = { "Conjunction", "conjunction", false },
["part"] = { "Particle", "particle", false },
["prep"] = { "Preposition", "preposition", 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["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 "")
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]
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 "|" .. mw.ustring.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 = mw.ustring.sub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.sub(text, -2, -2), ".", function (char) return data.hk[char] or char end), ".", function (char) return data.kr[char] or char end), -1, -1)
cons = mw.ustring.sub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.sub(text, -1, -1), ".", function (char) return data.hk[char] or char end), ".", function (char) return data.kr[char] or char end), 1, 1)
if cons == "u" then
cons = ""
elseif cons == "t" 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 "|" .. mw.ustring.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]
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("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 .. "\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