มอดูล:category tree/poscatboiler/data/เฉพาะภาษา/jpx
- The following documentation is generated by Template:poscatboiler data submodule documentation. [edit]
- Useful links: root page • root page’s subpages • links • transclusions • testcases • sandbox
This data submodule defines part of Wiktionary's category structure.
For an introduction to the poscatboiler system and a description of how to add or modify categories, see Module:category tree/poscatboiler/data/documentation.
local export = {}
local Hira = require("Module:scripts").getByCode("Hira")
local Jpan = require("Module:scripts").getByCode("Jpan")
local kana_to_romaji = require("Module:Hrkt-translit").tr
local m_numeric = require("Module:ConvertNumeric")
local rmatch = mw.ustring.match
function export.add_labels(labels, lang)
labels["คำนามคุณศัพท์"] = {
description = "{{{langname}}} {{m|ja|連体詞||[[adnominal]], attributive|tr=れんたいし, rentaishi|sc=Jpan}}. Modifies nouns, doesn’t conjugate, and doesn’t [[predicate#Verb|predicate]].",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["adnominals"] = labels["คำนามคุณศัพท์"] -- equivalent to adjectival noun
labels["ฮิรางานะ"] = {
description = "The [[hiragana]] ([[平仮名]], [[ひらがな]]) form of " .. (lang:getCode() == "ryu" and "an" or "a") .. " {{{langname}}} word is a [[phonetic]] representation of that word. " ..
"Wiktionary represents {{{langname}}}-language segments in three ways: in normal form (with [[kanji]], if appropriate), in [[hiragana]] " ..
"form (this differs from kanji form only when the segment contains kanji), and in [[romaji]] form.",
additional = (lang:getCode() == "ja" and "สำหรับข้อมูลเพิ่มเติม ดูที่ [[วิกิพจนานุกรม:ภาษาญี่ปุ่น]]\n\n" or "") .. "''ดูเพิ่ม'' [[:หมวดหมู่:คาตากานะ{{{langcat}}}]]",
toc_template = "categoryTOC-hiragana",
parents = {
{name = "{{{langcat}}}", raw = true},
--"Category:Hiragana script characters",
}
}
labels["hiragana"] = labels["ฮิรางานะ"]
labels["ฮิรางานะในอดีต"] = {
description = "{{{langname}}} historical [[hiragana]].",
additional = "''See also'' [[:Category:{{{langname}}} historical katakana]].",
toc_template = "categoryTOC-hiragana",
parents = {
"ฮิรางานะ",
{name = "{{{langcat}}}", raw = true},
--"Category:Hiragana script characters",
}
}
labels["historical hiragana"] = labels["ฮิรางานะในอดีต"]
labels["คาตากานะ"] = {
description = "{{{langname}}} words and terms with katakana forms, sorted by conventional katakana sequence. Katakana is used primarily for transliterations of foreign words, including old Chinese Hanzi not used in [[shinjitai]].",
additional = (lang:getCode() == "ja" and "สำหรับข้อมูลเพิ่มเติม ดูที่ [[วิกิพจนานุกรม:ภาษาญี่ปุ่น]]\n\n" or "") .. "''ดูเพิ่ม'' [[:หมวดหมู่:ฮิรางานะ{{{langcat}}}]]",
toc_template = "categoryTOC-katakana",
parents = {
{name = "{{{langcat}}}", raw = true},
--"Category:Katakana script characters",
}
}
labels["katakana"] = labels["คาตากานะ"]
labels["คาตากานะในอดีต"] = {
description = "{{{langname}}} historical [[katakana]].",
additional = "''See also'' [[:Category:{{{langname}}} historical hiragana]].",
toc_template = "categoryTOC-katakana",
parents = {
"คาตากานะ",
{name = "{{{langcat}}}", raw = true},
--"Category:Katakana script characters",
}
}
labels["historical hiragana"] = labels["คาตากานะในอดีต"]
labels["ศัพท์ที่สะกดด้วยคานะผสม"] = {
description = "{{{langname}}} terms which combine [[hiragana]] and [[katakana]] characters, potentially with [[kanji]] too.",
parents = {
{name = "{{{langcat}}}", raw = true},
"ฮิรางานะ",
"คาตากานะ",
},
}
labels["terms spelled with mixed kana"] = labels["ศัพท์ที่สะกดด้วยคานะผสม"]
labels["honorifics"] = {
topright = "{{wikipedia|Honorific speech in Japanese}}",
description = "{{{langname}}} [[honorific]]s.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["humble language"] = {
description = "{{{langname}}} humble terms, or {{ja-r|謙譲語|けんじょうご}}, which is a type of honorific speech in {{{langname}}} that lowers the speaker in relation to the listener.",
parents = "honorifics",
}
labels["respectful language"] = {
description = "{{{langname}}} respectful terms, or {{ja-r|尊敬語|そんけいご}}, which is a type of honorific speech in {{{langname}}} that elevates the listener in relation to the speaker.",
parents = "honorifics",
}
labels["คันจิแบ่งตามการออกเสียง"] = {
description = "{{{langname}}} kanji categorized by reading.",
parents = {{name = "อักษรจีน", sort = "reading"}},
}
labels["kanji by reading"] = labels["คันจิแบ่งตามการออกเสียง"]
labels["makurakotoba"] = {
topright = "{{wikipedia|Makurakotoba}}",
description = "{{{langname}}} idioms used in poetry to introduce specific words.",
parents = {"idioms"},
}
labels["ศัพท์แบ่งตามการออกเสียงคันจิ"] = {
description = "{{{langname}}} categories grouped with regard to the readings of the kanji with which they are spelled.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["terms by kanji readings"] = labels["ศัพท์แบ่งตามการออกเสียงคันจิ"]
labels["ศัพท์แบ่งตามรูปแบบการออกเสียง"] = {
description = "{{{langname}}} categories with terms grouped by their reading patterns.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["terms by reading pattern"] = labels["ศัพท์แบ่งตามรูปแบบการออกเสียง"]
for reading_pattern, link in pairs {
["จูกูจิกุง"] = "{{ja-r|熟字訓|じゅくじくん}}",
["จูบาโกโยมิ"] = "{{ja-r|重%箱%読み|じゅう%ばこ%よみ}}, a reading pattern in {{{langname}}} compounds where kanji read with ''on'yomi'' are followed by kanji read with ''kun'yomi''",
["คุนโยมิ"] = "{{ja-r|訓読み|くんよみ}}",
["นาโนริ"] = "{{ja-r|名乗り|なのり}}",
["อนโยมิ"] = "{{ja-r|音%読み|おん%よみ}}",
["ยูโตโยมิ"] = "{{ja-r|湯%桶%読み|ゆ%とう%よみ}}, a reading pattern in {{{langname}}} compounds where kanji read with ''kun'yomi'' are followed by kanji read with ''on'yomi''",
} do
labels["ศัพท์ที่ออกเสียง" .. reading_pattern] = {
description = "{{{langname}}} terms exhibiting " .. link .. ".",
breadcrumb = reading_pattern,
parents = {{name = "ศัพท์แบ่งตามรูปแบบการออกเสียง", sort = reading_pattern}},
}
end
labels["ศัพท์แบ่งตามชนิดการออกเสียงคันจิ"] = {
description = "{{{langname}}} categories with terms grouped with regard to the types of readings of the kanji with which " ..
"they are spelled, broadly those of Chinese origin (''on'' readings) and those of {{{langname}}} origin (''kun'' readings).",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["terms by kanji reading type"] = labels["ศัพท์แบ่งตามชนิดการออกเสียงคันจิ"]
labels["verbs without transitivity"] = {
description = "{{{langname}}} verbs missing the <code>tr=</code> parameter in the headword template.",
hidden = true,
can_be_empty = true,
parents = {"entry maintenance"},
}
labels["yojijukugo"] = {
topright = "{{wikipedia|Yojijukugo}}",
description = "{{{langname}}} four-[[kanji]] compound terms with idiomatic meanings, typically derived from Classical Chinese, Buddhist scripture or traditional Japanese proverbs.",
additional = "Compare [[w:Chengyu|chengyu]] in Sinitic languages.",
parents = {"idioms"},
}
local on_continuation = [=[
Categories of terms with more specific types of ''on'' readings can be found in the following categories:
* [[:หมวดหมู่:ศัพท์{{{langname}}}ที่สะกดด้วยคันจิออกเสียงแบบโกอง]]
* [[:หมวดหมู่:ศัพท์{{{langname}}}ที่สะกดด้วยคันจิออกเสียงแบบคันโยอง]]
* [[:หมวดหมู่:ศัพท์{{{langname}}}ที่สะกดด้วยคันจิออกเสียงแบบคังอง]]
* [[:หมวดหมู่:ศัพท์{{{langname}}}ที่สะกดด้วยคันจิออกเสียงแบบโทอง]]
]=]
local on_desc = ", which is a type of {{ja-r|音%読み|おん%よみ}} or {{ja-r|音|おん}} reading"
for reading_type, reading_desc in pairs {
["โกอง"] = "a {{ja-r|呉%音|ご%おん}} reading" .. on_desc,
["คังอง"] = "a {{ja-r|漢%音|かん%おん}} reading" .. on_desc,
["คันโยอง"] = "a {{ja-l|慣用音|かんようおん|kan'yōon}} reading" .. on_desc,
["คุง"] = "a {{ja-r|訓%読み|くん%よみ}} or {{ja-r|訓|くん}} reading",
["นาโนริ"] = "a {{ja-r|名%乗り|な%のり}} reading, which is a type of reading used for people and places",
["อง"] = "an {{ja-r|音%読み|おん%よみ}} or {{ja-r|音|おん}} reading",
["โทอง"] = "a {{ja-r|唐%音|とう%おん}} reading" .. on_desc,
["โซอง"] = "a {{ja-r|宋%音|そう%おん}} reading" .. on_desc,
} do
labels["ศัพท์ที่สะกดด้วยคันจิออกเสียงแบบ" .. reading_type] = {
description = "{{{langname}}} categories with terms that are spelled with one or more kanji which exhibit " .. reading_desc .. ".",
additional = reading_type == "อง" and on_continuation,
breadcrumb = reading_type,
parents = {{name = "ศัพท์แบ่งตามชนิดการออกเสียงคันจิ", sort = reading_pattern}},
}
end
labels["ศัพท์ที่สะกดด้วยอาเตจิ"] = {
topright = "{{wikipedia|Ateji}}",
description = "{{{langname}}} terms containing one or more [[Appendix:Japanese glossary#ateji|ateji]] ({{m|ja|当て字}}), which are [[kanji]] used to represent sounds rather than meanings (though meaning may have some influence on which kanji are chosen).",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["terms spelled with ateji"] = labels["ศัพท์ที่สะกดด้วยอาเตจิ"]
labels["ศัพท์ที่สะกดด้วยไดโยจิ"] = {
description = "Japanese terms spelled using [[Appendix:Japanese glossary#daiyouji|daiyōji]], categorized using {{temp|ja-daiyouji}}.",
parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["terms spelled with daiyōji"] = labels["ศัพท์ที่สะกดด้วยไดโยจิ"]
labels["ศัพท์ที่สะกดด้วยจูกูจิกุง"] = {
description = "{{{langname}}} terms containing one or more [[Appendix:Japanese glossary#jukujikun|jukujikun]] ({{m|ja|熟字訓}}), which are [[kanji]] used to represent meanings rather than sounds.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["terms spelled with jukujikun"] = labels["ศัพท์ที่สะกดด้วยจูกูจิกุง"]
labels["terms spelled with jōyō kanji"] = {
topright = "{{wikipedia|Jōyō kanji}}",
description = "{{{langname}}} terms spelled with at least one kanji, where all kanji in the terms are included on the official list of jōyō kanji.",
additional = "See also [[:Category:{{{langname}}} terms spelled with non-jōyō kanji]].",
parents = {{name = "terms by orthographic property", sort = "jōyō"}},
}
labels["terms spelled with non-jōyō kanji"] = {
topright = "{{wikipedia|Jōyō kanji}}",
description = "{{{langname}}} terms spelled with at least one kanji not included in the official list of jōyō kanji.",
additional = "See also [[:Category:{{{langname}}} terms spelled with jōyō kanji]].",
parents = {{name = "terms by orthographic property", sort = "non-jōyō"}},
}
for _, non_joyo_type in ipairs {"hyōgaiji", "jinmeiyō"} do
labels["terms spelled with " .. non_joyo_type .. " kanji"] = {
description = "{{{langname}}} terms spelled with " .. non_joyo_type .. " kanji.",
parents = {{name = "terms spelled with non-jōyō kanji", sort = non_joyo_type}},
}
end
for i = 1, 6 do
local ord = m_numeric.ones_position_ord[i]
labels["terms spelled with " .. ord .. " grade kanji"] = {
description = "{{{langname}}} terms spelled with " .. ord .. " grade kanji.",
parents = {{name = "terms spelled with jōyō kanji", sort = i}},
}
end
labels["terms spelled with secondary school kanji"] = {
description = "{{{langname}}} terms spelled with secondary school kanji.",
parents = {{name = "terms spelled with jōyō kanji", sort = "secondary school"}},
}
labels["terms with multiple readings"] = {
description = "{{{langname}}} terms with multiple pronunciations (hence multiple [[kana]] spellings).",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["คันจิแบ่งตามจำนวนหน่วยออกเสียง"] = {
description = "{{{langname}}} categories grouped with regard to the number of morae in their kanji readings.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["kanji readings by number of morae"] = labels["คันจิแบ่งตามจำนวนหน่วยออกเสียง"]
labels["single-kanji terms"] = {
description = "{{{langname}}} terms written as a single kanji.",
parents = {"terms by orthographic property", {name = "character counts", sort = " "}},
}
end
function export.add_handlers(handlers, lang, m_lang)
-- FIXME: Only works for 0 through 19.
local word_to_number = {}
for k, v in pairs(m_numeric.ones_position) do
word_to_number[v] = k
end
local kana_capture = "([-ぁ-ー𛀁𛀆]+)"
local periods = {
historical = true,
ancient = true,
}
local function get_period_text_and_reading_type_link(period, reading_type)
period = period ~= "" and period or nil
if period and not periods[period] then
return nil
end
local period_text = period and period .. " " or nil
-- Allow periods (historical or ancient) by themselves; they will parse as reading types.
if not period and periods[reading_type] then
return nil, reading_type
end
local reading_type_link = "[[ภาคผนวก:อภิธานศัพท์ภาษาญี่ปุ่น#" .. reading_type .. "|" .. reading_type .. "]]"
return period_text, reading_type_link
end
local function get_sc(str)
return mw.ustring.match(str:gsub('[%z\1-\127]', ''), '[^' .. Hira:getCharacters() .. ']') and Jpan or Hira
end
local function get_tagged_reading(reading)
return require("Module:script utilities").tag_text(reading, lang, get_sc(reading))
end
local function get_reading_link(reading, historical, link)
local display = reading:gsub('[%.%- ]', '')
return require("Module:links").full_link({
lang = lang,
sc = get_sc(reading),
term = link or display,
alt = display,
tr = kana_to_romaji((reading:gsub('%-', '')), lang:getCode(), nil, {hist = historical}),
}, 'term')
end
local function is_on_subtype(reading_type)
return reading_type:find(".อง$")
end
table.insert(handlers, function(data)
local count, plural = data.label:match("^terms written with (.+) Han script character(s?)$")
if count then
-- Make sure 'one' goes with singular and other numbers with plural.
if (count == "one") ~= (plural == "") then
return nil
end
local num = word_to_number[count]
if not num then
return nil
end
return {
description = "{{{langname}}} terms written with " .. count .. " Han script character" .. plural .. " (also known as [[kanji]]).",
breadcrumb = num,
parents = {{name = "character counts", sort = num}},
}
end
end)
table.insert(handlers, function(data)
--local count, plural = data.label:match("^kanji readings with (.+) mora(e?)$")
local count = data.label:match("^คันจิที่ออกเสียง (.+) หน่วย$") -- count ใช้ตัวเลขเพื่อความสะดวก
if count then
--[[ Make sure 'one' goes with singular and other numbers with plural.
if (count == "one") ~= (plural == "") then
return nil
end
local num = word_to_number[count]
if not num then
return nil
end
--]]
return {
description = "{{{langname}}} kanji readings containing " .. count .. " mora.",
breadcrumb = num,
parents = {{name = "คันจิแบ่งตามจำนวนหน่วยออกเสียง", sort = num}},
}
end
end)
table.insert(handlers, function(data)
local label_pref, period, reading_type, reading = rmatch(data.label, "^(kanji with ([a-z]-) ?([%a']+) reading )" .. kana_capture .. "$")
if period then
local period_text, reading_type_link = get_period_text_and_reading_type_link(period, reading_type)
if not reading_type_link then
return nil
end
-- Compute parents.
local parents = {
{name = "kanji by " .. (period_text or "") .. reading_type .. " reading", sort = (data.lang:makeSortKey(reading))}
}
if is_on_subtype(reading_type) then
table.insert(parents, {name = "kanji with " .. (period_text or "") .. "on reading " .. reading, sort = reading_type})
elseif period_text then
table.insert(parents, {name = "kanji with " .. period_text .. "reading " .. reading, sort = reading_type})
end
if not period_text then
table.insert(parents, {name = "kanji read as " .. reading, sort = reading_type})
end
local tagged_reading = get_tagged_reading(reading)
return {
description = "{{{langname}}} [[kanji]] with the " .. (period_text or "") .. reading_type_link .. " reading " ..
get_reading_link(reading, period_text) .. ".",
displaytitle = "{{{langname}}} " .. label_pref .. tagged_reading,
breadcrumb = tagged_reading,
parents = parents,
}
end
end)
table.insert(handlers, function(data)
local period, reading_type = rmatch(data.label, "^kanji by ([a-z]-) ?([%a']+) reading$")
if period then
local period_text, reading_type_link = get_period_text_and_reading_type_link(period, reading_type)
if not reading_type_link then
return nil
end
-- Compute parents.
local parents = {
is_on_subtype(reading_type) and {name = "kanji by " .. (period_text or "") .. "on reading", sort = reading_type} or
period_text and {name = "kanji by " .. reading_type .. " reading", sort = period} or
{name = "คันจิแบ่งตามการออกเสียง", sort = reading_type}
}
if period_text then
table.insert(parents, {name = "kanji by " .. period_text .. "reading", sort = reading_type})
end
-- Compute description.
local description = "{{{langname}}} [[kanji]] categorized by " .. (period_text or "") .. reading_type_link .. " reading."
return {
description = description,
breadcrumb = (period_text or "") .. reading_type,
parents = parents,
}
end
end)
table.insert(handlers, function(data)
local label_pref, reading = rmatch(data.label, "^(คันจิที่ออกเสียง )" .. kana_capture .. "$")
if reading then
local params = {
["histconsol"] = {},
}
local args = require("Module:parameters").process(data.args, params)
local parents = {{name = "คันจิแบ่งตามการออกเสียง", sort = (data.lang:makeSortKey(reading))}}
local addl
local period_text
if args.histconsol then
period_text = "historical"
addl = ("This is a [[Wikipedia:Historical kana orthography|historical]] [[Wikipedia:Kanazukai|reading]], now " ..
"consolidated with the [[Wikipedia:Modern kana usage|modern reading]] of " ..
get_reading_link(args.histconsol, nil, ("Category:Japanese kanji read as %s"):format(args.histconsol)) .. ".")
end
local tagged_reading = get_tagged_reading(reading)
return {
description = "คันจิ{{{langcat}}}ที่ออกเสียง " .. get_reading_link(reading, period_text),
displaytitle = "{{{langname}}} " .. label_pref .. tagged_reading,
breadcrumb = tagged_reading,
parents = parents,
}, true
end
end)
table.insert(handlers, function(data)
local label_pref, reading = rmatch(data.label, "^(ศัพท์ที่สะกดด้วยคันจิออกเสียง )" .. kana_capture .. "$")
if reading then
-- Compute parents.
local sort_key = (data.lang:makeSortKey(reading))
local mora_count = m_lang.count_morae(reading)
--local mora_count_words = m_numeric.spell_number(tostring(mora_count))
local parents = {
{name = "ศัพท์แบ่งตามการออกเสียงคันจิ", sort = sort_key},
--{name = "kanji readings with " .. mora_count_words .. " mora" .. (mora_count > 1 and "e" or ""), sort = sort_key},
{name = "คันจิที่ออกเสียง " .. mora_count .. " หน่วย", sort = sort_key},
{name = "คันจิที่ออกเสียง " .. reading, sort = " "},
}
local tagged_reading = get_tagged_reading(reading)
return {
description = "{{{langname}}} terms that contain kanji that exhibit a reading of " .. get_reading_link(reading) ..
" in those terms prior to any sound changes.",
displaytitle = "{{{langname}}} " .. label_pref .. tagged_reading,
breadcrumb = tagged_reading,
parents = parents,
}
end
end)
table.insert(handlers, function(data)
local kanji, reading = rmatch(data.label, "^ศัพท์ที่สะกดด้วย (.) ออกเสียง " .. kana_capture .. "$")
if not kanji then
return nil
end
local params = {
[1] = {list = true},
}
local args = require("Module:parameters").process(data.args, params)
if #args[1] == 0 then
error("For categories of the form \"" .. data.lang:getCanonicalName() ..
" terms spelled with KANJI read as READING\", at least one reading type (e.g. \"kun\" or \"on\") must be specified using 1=, 2=, 3=, etc.")
end
local reading_types = {}
for _, reading_type in ipairs(args[1]) do
table.insert(reading_types, "<i>" .. reading_type .. "</i>")
end
reading_types = require("Module:table").serialCommaJoin(reading_types, {conj = "หรือ"})
local parents = {
{name = "ศัพท์ที่สะกดด้วย " .. kanji, sort = (data.lang:makeSortKey(reading))},
-- FIXME, using the kanji directly as the sort key is what it did before but maybe we should call [[Module:Hani-sortkey]]
-- to get the radical/stroke sort key
{name = "ศัพท์ที่สะกดด้วยคันจิออกเสียง " .. reading, sort = kanji},
}
for _, reading_type in ipairs(args[1]) do
table.insert(parents, {name = "ศัพท์ที่สะกดด้วยคันจิออกเสียงแบบ" .. reading_type, sort = (data.lang:makeSortKey(reading))})
end
local tagged_kanji = get_tagged_reading(kanji)
local tagged_reading = get_tagged_reading(reading)
return {
description = "ศัพท์{{{langcat}}}ที่สะกดด้วย {{l|{{{langcode}}}|" .. kanji .. "}} ซึ่งออกเสียงแบบ " ..
reading_types .. " ว่า " .. get_reading_link(reading),
displaytitle = "ศัพท์{{{langcat}}}ที่สะกดด้วย " .. tagged_kanji .. " ออกเสียง " .. tagged_reading,
breadcrumb = "ออกเสียง " .. tagged_reading,
parents = parents,
}, true
end)
table.insert(handlers, function(data)
local kanji, daiyoji = rmatch(data.label, "^terms with (.) replaced by daiyōji (.)$")
if not kanji then
return nil
end
local params = {
["sort"] = {},
}
local args = require("Module:parameters").process(data.args, params)
if not args.sort then
error("For categories of the form \"" .. data.lang:getCanonicalName() ..
" terms with KANJI replaced by daiyōji DAIYOJI\", the sort key must be specified using sort=")
end
local tagged_kanji = get_tagged_reading(kanji)
local tagged_daiyoji = get_tagged_reading(daiyoji)
return {
description = "{{{langname}}} terms with {{l|{{{langcode}}}|" .. kanji .. "}} replaced by [[Appendix:Japanese glossary#daiyouji|daiyōji]] {{l|{{{langcode}}}|" .. daiyoji .. "}}.",
displaytitle = "{{{langname}}} terms with " .. tagged_kanji .. " replaced by daiyōji " .. tagged_daiyoji,
breadcrumb = tagged_kanji .. " replaced by daiyōji " .. tagged_daiyoji,
parents = {{name = "ศัพท์ที่สะกดด้วยไดโยจิ", sort = args.sort}},
}, true
end)
end
return export