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
| Kanji in this term |
|---|
| 懐 |
| なつ Grade: S |
| kun’yomi |
| Alternative spelling |
|---|
| 懷かしい (kyūjitai) |
| Kanji in this term | |
|---|---|
| 取 | 締 |
| と(り) Grade: 3 |
し(まり) Grade: S |
| kun’yomi | |
| Kanji in this term | |
|---|---|
| 日 | 付 |
| ひ Grade: 1 |
つ(け) > づ(け) Grade: 4 |
| kun’yomi | |
| Kanji in this term | |
|---|---|
| 関 | 係 |
| かん Grade: 4 |
けい Grade: 3 |
| kan’on | |
| Alternative spelling |
|---|
| 關係 (kyūjitai) |
| Kanji in this term | |
|---|---|
| 東 | 京 |
| とう Grade: 2 |
きょう Grade: 2 |
| kan’on | goon |
| Kanji in this term | |||
|---|---|---|---|
| 大 | 和 | 言 | 葉 |
| やまと | こと Grade: 2 |
は > ば Grade: 3 | |
| Grade: 1 | Grade: 3 | ||
| jukujikun | kun’yomi | ||
| Kanji in this term | |||
|---|---|---|---|
| 滅 | 茶 | 苦 | 茶 |
| め Grade: S (ateji) |
ちゃ Grade: 2 (ateji) |
く Grade: 3 (ateji) |
ちゃ Grade: 2 (ateji) |
| irregular | kan’yōon | goon | kan’yōon |
| Kanji in this term | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| 阿 | 弗 | 利 | 加 | 系 | 亜 | 米 | 利 | 加 | 人 |
| あ Jinmeiyō (ateji) |
ふつ > ふ Hyōgaiji (ateji) |
り Grade: 4 (ateji) |
か Grade: 4 (ateji) |
けい Grade: 6 |
あ Grade: S (ateji) |
め Grade: 2 (ateji) |
り Grade: 4 (ateji) |
か Grade: 4 (ateji) |
じん Grade: 1 |
| on’yomi | irregular | on’yomi | kan’on | kan’on | kan’on | irregular | on’yomi | kan’on | kan’on |
| Alternative spelling |
|---|
| 阿弗利加系亞米利加人 (kyūjitai) |
{{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_str_utils = require("Module:string utilities")
local m_utilities = require("Module:utilities")
local m_ja = require("Module:ja")
local show_labels = require("Module:labels").show_labels
--[=[
Other modules used: [[Module:parameters]]
]=]
local concat = table.concat
local convert_iteration_marks = require("Module:Hani").convert_iteration_marks
local find = string.find
local gsplit = m_str_utils.gsplit
local gsub = string.gsub
local insert = table.insert
local match = string.match
local remove = table.remove
local split = m_str_utils.split
local sub = string.sub
local ugsub = mw.ustring.gsub
local ulen = m_str_utils.len
local umatch = mw.ustring.match
local usub = m_str_utils.sub
local title = mw.title.getCurrentTitle()
local PAGENAME = mw.loadData("Module:headword/data").pagename
local NAMESPACE = title.nsText
local d_range = mw.loadData'Module:ja/data/range'
local kanji_grade_links = {
"[[Appendix:Japanese_glossary#kyōiku_kanji|Grade: 1]]",
"[[Appendix:Japanese_glossary#kyōiku_kanji|Grade: 2]]",
"[[Appendix:Japanese_glossary#kyōiku_kanji|Grade: 3]]",
"[[Appendix:Japanese_glossary#kyōiku_kanji|Grade: 4]]",
"[[Appendix:Japanese_glossary#kyōiku_kanji|Grade: 5]]",
"[[Appendix:Japanese_glossary#kyōiku_kanji|Grade: 6]]",
"[[Appendix:Japanese_glossary#jōyō_kanji|Grade: S]]", -- 7
"[[Appendix:Japanese_glossary#jinmeiyō_kanji|Jinmeiyō]]", -- 8
"[[Appendix:Japanese_glossary#hyōgaiji|Hyōgaiji]]" -- 9
}
-- this is the function that is called from templates
function export.show(frame)
local args = require("Module:parameters").process(frame:getParent().args, {
[1] = { list = true, allow_holes = true },
k = { list = true, allow_holes = true },
o = { list = true, allow_holes = true },
r = {},
sort = {},
yomi = {},
ateji = {},
alt = {},
alt2 = {},
kyu = { list = true },
y = {alias_of = 'yomi'},
clearright = {type = "boolean"},
pagename = {},
})
local lang_code = frame.args[1]
local lang = require("Module:languages").getByCode(lang_code)
local lang_name = lang:getCanonicalName()
if args.pagename and NAMESPACE == "" then
require'Module:debug'.track'kanjitab/pagename param in mainspace'
end
local pagename = args.pagename or PAGENAME
local categories = {}
local cells = {}
-- extract kanji and non-kanji
local kanji = {}
local non_kanji = {}
-- 々 and 〻
pagename = convert_iteration_marks(pagename)
local kanji_border = 1
ugsub(pagename, '()([' .. d_range.kanji .. '々〻])()', function(p1, w1, p2)
insert(non_kanji, usub(pagename, kanji_border, p1 - 1))
kanji_border = p2
insert(kanji, w1)
end)
insert(non_kanji, usub(pagename, kanji_border))
-- kyujitai
local kyu = args.kyu
if kyu[1] == '-' then
kyu = {}
elseif kyu[1] == nil then
local form_kyu = {non_kanji[1]}
local kyu_data = mw.loadData('Module:ja/data/kyu')
local has_kyu, has_kyu_nonsupple, has_shin = false, false, false
for i, v in ipairs(kanji) do
local v_kyu = match(kyu_data[1], v .. "(%S*)%s")
if v_kyu == nil then
insert(form_kyu, v)
elseif v_kyu == '' then
has_shin = true
break
elseif v_kyu:sub(1, 1) == '&' then
has_kyu = true
insert(form_kyu, v_kyu)
else
has_kyu, has_kyu_nonsupple = true, true
insert(form_kyu, v_kyu)
end
insert(form_kyu, non_kanji[i + 1])
end
if not has_shin and has_kyu then
kyu[1] = (has_kyu_nonsupple and '' or pagename .. '|') .. concat(form_kyu)
end
if find(pagename, "弁") then
require'Module:debug'.track'kanjitab/ambiguous kyujitai for 弁'
kyu[1] = 'which 弁?'
end
end
-- process readings
local readings = {}
local readings_actual = {}
local reading_length_total = 0
for i = 1, args[1].maxindex do
local reading_kana, reading_length = match(args[1][i] or "", "^(%D*)(%d*)$")
reading_kana = reading_kana ~= "" and reading_kana or nil
reading_length = reading_kana and tonumber(reading_length) or 1
insert(readings, {reading_kana, reading_length})
reading_length_total = reading_length_total + reading_length
end
if reading_length_total > #kanji then
error('Readings for ' .. reading_length_total .. ' kanji are given, but this word has only ' .. #kanji .. ' kanji.')
else
for i = reading_length_total + 1, #kanji do insert(readings, {nil, 1}) end
end
local table_head = [=[
{| class="wikitable kanji-table" style="text-align: center; font-size: small; float: right;]=] .. (args.clearright and ' clear:right;' or '') .. [=["
! ]=] .. (#kanji > 1 and 'colspan="' .. #kanji .. '" ' or '') .. [=[style="font-weight: normal;" | [[Appendix:Japanese_glossary#kanji|Kanji]] in this term
|- lang="]=] .. lang_code .. [=[" class="Jpan" style="font-size: 2em; background: white; line-height: 1em;"
]=]
local yomi
-- on/kun is jūbakoyomi; NOTE: these are only applicable for two-kanji compounds
-- kun/on is yutōyomi; NOTE: these are only applicable for two-kanji compounds
if args.yomi then
yomi = {}
local extended_yomi_code = {
o = 'on', on = 'on',
kanon = 'kanon', -- kan is kan'yoon, and ko is kun+on for backward compatibility
goon = 'goon',
soon = 'soon',
toon = 'toon',
kan = 'kanyoon', kanyo = 'kanyoon', kanyoon = 'kanyoon',
k = 'kun', kun = 'kun',
juku = 'jukujikun', jukuji = 'jukujikun', jukujikun = 'jukujikun',
ok = "jūbakoyomi", j = "jūbakoyomi",
ko = "yutōyomi", y = "yutōyomi", yu = "yutōyomi",
i = 'irregular', irr = 'irregular', irreg = 'irregular', irregular = 'irregular',
n = 'nanori', nanori = 'nanori',
[''] = '', none = '',
}
for i in gsplit(args.yomi, ',') do
local a, b = match(i, "^(%l*)(%d*)$")
a = extended_yomi_code[a] or error("The yomi type “" .. args.yomi .. "” is not recognized.")
b = tonumber(b) or 1
insert(yomi, { a, b })
-- If the on'yomi is not specified as goon/kanon/toon/soon, only 'on'
if a == 'on' then
require'Module:debug'.track'kanjitab/unspecified on'
end
if (a == "jūbakoyomi" or a == "yutōyomi") and #kanji ~= 2 then
error'yutou or juubako is only applicable to 二字熟語'
end
end
if #yomi == 1 and #kanji > 1 then
yomi[1][2] = #kanji
end
elseif #kanji > 0 then
require'Module:debug'.track'kanjitab/no yomi'
end
if args.k.maxindex and args.k.maxindex > args[1].maxindex then
error'kanjitab/too many k'
end
if args.o.maxindex and args.o.maxindex > args[1].maxindex then
error'kanjitab/too many o'
end
local yomi_type_by_kanji = {}
if yomi then
for i = 1, #yomi do
for j = 1, yomi[i][2] do
insert(yomi_type_by_kanji, yomi[i][1])
end
end
else
for i = 1, #kanji do
insert(yomi_type_by_kanji, '')
end
end
local is_ateji = {}
if args.ateji then
local ateji = args.ateji
local cat_ateji = false
if ateji == 'y' then
for i = 1, #kanji do
is_ateji[i] = true
end
cat_ateji = true
else
for i in gsplit(ateji, ';') do
gsub(i, '^(%d+)$', function(a)
is_ateji[tonumber(a)] = true
cat_ateji = true
end)
gsub(i, '^(%d+),(%d+)$', function (a, b)
for j = tonumber(a), tonumber(b) do
is_ateji[j] = true
end
cat_ateji = true
end)
end
end
if cat_ateji then insert(categories, lang_name .. " terms spelled with ateji") 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
local cells_above = {}
local cells_below = {}
local kanji_pos = 1
for i, reading in ipairs(readings) do
local reading_kana, reading_length = reading[1], reading[2]
local cell = {}
if reading_length <= 1 then
insert(cell, '| rowspan="2" | ')
else
insert(cell, '| colspan ="' .. reading_length .. '" | ')
end
-- display reading, actual reading and okurigana
if reading_kana then
if reading_kana ~= "" and umatch(reading_kana, "[^" .. d_range.kana .. "]") then
require'Module:debug'.track'kanjitab/not all kana'
end
local actual_reading = args.k[i]
local okurigana = args.o[i]
local okurigana_text = okurigana and "(" .. okurigana .. ")" or ""
local actual_reading_text = actual_reading and " > " .. actual_reading .. okurigana_text or ""
local text = reading_kana .. okurigana_text .. actual_reading_text
readings_actual[i] = {(actual_reading or reading_kana) .. (okurigana or ''), reading_length}
insert(cell, '<span class="Jpan" lang="' .. lang_code .. '">' .. text .. '</span>')
if reading_length <= 1 then insert(cell, '<br/>') end
else
readings_actual[i] = {nil, 1}
end
-- display kanji grade, categorize
for j = kanji_pos, kanji_pos + reading_length - 1 do
local single_kanji = kanji[j]
local kanji_grade = m_ja.kanji_grade(single_kanji)
local ateji_text = is_ateji[j] and '<br/><small>([[Appendix:Japanese glossary#ateji|ateji]])</small>' or ''
if reading_kana then
-- subcategorize by reading if this is joyo kanji, not doing that for less common kanji, with exceptions
if (kanji_grade < 8 or find("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", single_kanji)) and yomi_type_by_kanji[j] ~= "irregular" and yomi_type_by_kanji[j] ~= "jukujikun" and reading_length == 1 then
insert(categories, lang_name .. " terms spelled with " .. single_kanji .. " read as " .. reading_kana)
else
insert(categories, lang_name .. " terms spelled with " .. single_kanji)
end
else
if yomi_type_by_kanji[j] ~= 'irregular' and yomi_type_by_kanji[j] ~= 'jukujikun' then
require'Module:debug'.track'kanjitab/no reading'
end
insert(categories, lang_name .. " terms spelled with " .. single_kanji)
end
if reading_length <= 1 then
insert(cell, "<small>" .. kanji_grade_links[kanji_grade] .. "</small>" .. ateji_text)
else
insert(cells_below, "| <small>" .. kanji_grade_links[kanji_grade] .. "</small>" .. ateji_text)
end
end
insert(cells_above, concat(cell))
kanji_pos = kanji_pos + reading_length
end
insert(cells, '|- style="background: white;"')
if #cells_below > 0 then
insert(cells, concat(cells_above, '\n'))
insert(cells, '|- style="background: white;"')
insert(cells, concat(cells_below, '\n'))
else
for i, v in ipairs(cells_above) do
cells_above[i] = gsub(v, "| rowspan=\"2\" | ", "| ")
end
insert(cells, concat(cells_above, '\n'))
end
local yomi_info = {
["on"] = {
text = "on’yomi",
entry = "Appendix:Japanese_glossary#on'yomi",
category = lang_name .. " terms read with on'yomi",
},
["kanon"] = {
text = "kan’on",
entry = "Appendix:Japanese_glossary#kan'on",
category = lang_name .. " terms read with on'yomi",
},
["goon"] = {
text = "goon",
entry = "Appendix:Japanese_glossary#goon",
category = lang_name .. " terms read with on'yomi",
},
["soon"] = {
text = "sōon",
entry = "Appendix:Japanese_glossary#tōon",
category = lang_name .. " terms read with on'yomi",
},
["toon"] = {
text = "tōon",
entry = "Appendix:Japanese_glossary#tōon",
category = lang_name .. " terms read with on'yomi",
},
["kun"] = {
text = "kun’yomi",
entry = "Appendix:Japanese_glossary#kun'yomi",
category = lang_name .. " terms read with kun'yomi",
},
["nanori"] = {
text = "nanori",
entry = "Appendix:Japanese_glossary#nanori",
category = lang_name .. " terms read with nanori",
},
["yutōyomi"] = {
text = "yutōyomi",
entry = "Appendix:Japanese_glossary#yutōyomi",
category = lang_name .. " terms read with yutōyomi",
},
["jūbakoyomi"] = {
text = "jūbakoyomi",
entry = "Appendix:Japanese_glossary#jūbakoyomi",
category = lang_name .. " terms read with jūbakoyomi",
},
["jukujikun"] = {
text = "jukujikun",
entry = "Appendix:Japanese_glossary#jukujikun",
category = lang_name .. " terms read with jukujikun",
},
["irregular"] = {
text = "''irregular''",
category = lang_name .. " terms with irregular kanji readings",
},
["kanyoon"] = {
text = "kan’yōon",
entry = "Appendix:Japanese_glossary#kan'yoon",
category = lang_name .. " terms read with kan'yōon",
},
}
local rendaku = args.r
if rendaku then
insert(categories, lang_name .. " terms with rendaku")
end
if yomi then
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
insert(cells, '| colspan="' .. i[2] .. '" |' .. text)
end
local is_onyomi = { on = true, kanon = true, goon = true, soon = 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
insert(categories, yomi_info.on.category)
elseif yomi[1][1] == 'jūbakoyomi' or yomi[1][1] == 'yutōyomi' then
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
insert(categories, yomi_info[yomi[1][1]].category)
elseif #yomi == 2 and yomi[1][2] == 1 and yomi[2][2] == 1 and ulen(pagename) == 2 then
if is_onyomi[yomi[1][1]] and yomi[2][1] == 'kun' then
insert(categories, yomi_info["jūbakoyomi"].category)
elseif yomi[1][1] == 'kun' and is_onyomi[yomi[2][1]] then
insert(categories, yomi_info["yutōyomi"].category)
end
end
end
end
local kanji_table
if #kanji > 0 then
kanji_table = table_head
for _, v in ipairs(kanji) do
kanji_table = kanji_table .. '| style="padding: 0.5em;" | [[' .. v .. '#' .. lang_name .. '|' .. v .. ']]\n'
end
kanji_table = kanji_table .. concat(cells, '\n') .. '\n|}'
else
kanji_table = ''
end
local forms_table = ""
if args.alt == '' or args.alt == '-' then args.alt = nil end
if kyu[1] or args.alt then
local forms = {}
-- |kyu=
if kyu[1] == 'which 弁?' then
insert(forms, '<strong class="error" style="font-size:75%;">Please specify the correct kyujitai for 弁 with the parameter "kyu".</strong>[[Category:Requests for cleanup in ' .. lang_name .. ' entries]]')
remove(kyu, 1)
end
for _, form in ipairs(kyu) do
local form_linkto, form_display = match(form, "^(.+)|(.+)$")
if not form_linkto then form_linkto, form_display = form, form end
insert(forms, concat{
'<span class="Jpan" lang="' .. lang_code .. '" style="font-family:游ゴシック, HanaMinA, sans-serif; font-size:140%;">[[',
form_linkto,
form_linkto == pagename and '|' or '#' .. lang_name .. '|',
form_display,
']]</span> <small>',
show_labels {labels = {'kyūjitai'}, lang = lang, nocat = true },
'</small>',
})
end
-- |alt=
if args.alt then
for form in gsplit(args.alt, ',') do
local i_semicolon = find(form, ":")
if i_semicolon then
local altform = sub(form, 1, i_semicolon - 1)
local altlabels = split(sub(form, i_semicolon + 1), ' ')
insert(forms, concat{
'<span class="Jpan" lang="' .. lang_code .. '" style="font-size:140%">[[',
altform,
'#' .. lang_name .. '|',
altform,
']]</span> <small>',
show_labels { labels = altlabels, lang = lang, nocat = true },
'</small>',
})
else
insert(forms, concat{
'<span class="Jpan" lang="' .. lang_code .. '" style="font-size:140%">[[',
form,
'#' .. lang_name .. '|',
form,
']]</span>'
})
end
end
end
forms_table = '\n' .. [[{| class="wikitable floatright"
! style="font-weight:normal" | Alternative spelling]] .. (#forms == 1 and "" or "s") .. [[
|-
| style="text-align:center;font-size:108%" | ]] .. concat(forms, '<br>') .. '\n|}'
end
local forms_table2 = ""
if args.alt2 and args.alt2 ~= "" and args.alt2 ~= "-" then
local forms2 = {}
for form in gsplit(args.alt2, ',') do
insert(forms2, '<span class="Jpan" lang="' .. lang_code .. '">[[' .. form .. '#' .. lang_name .. '|' .. form .. ']]</span>')
end
forms_table2 = '\n' .. [[{| class="wikitable floatright"
! style="font-weight:normal" | Variant form]] .. (#forms2 == 1 and "" or "s") .. '\n' .. [[
| style="text-align:center;font-size:140%" | ]] .. concat(forms2, '<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 sortkey
if args.sort then
sortkey = args.sort
else
sortkey = {non_kanji[1]}
local id = 1
for _, v in ipairs(readings_actual) do
id = id + v[2]
insert(sortkey, (v[1] or '') .. (non_kanji[id] or ''))
end
sortkey = concat(sortkey)
end
if sortkey == "" then
sortkey = nil
else
sortkey = lang:makeSortKey(sortkey)
end
if sortkey ~= lang:makeSortKey(PAGENAME) then
require("Module:debug/track"){"kanjitab/nonstandard sortkey", "kanjitab/nonstandard sortkey/" .. lang_code}
end
return kanji_table .. forms_table .. forms_table2 .. m_utilities.format_categories(categories, lang, sortkey)
end
return export
Categories:
- Southern Amami Ōshima modules
- Language-specific utility modules
- Japanese modules
- Old Japanese modules
- Kunigami modules
- Kikai modules
- Okinawan modules
- Proto-Ryukyuan modules
- Miyako modules
- Yonaguni modules
- Northern Amami Ōshima modules
- Yaeyama modules
- Hachijō modules
- Proto-Japonic modules
- Tokunoshima modules
- Okinoerabu modules
- Yoron modules