模組:Category tree/poscatboiler/data/lang-specific/jpx
- 下列說明文檔位於Module:Category tree/poscatboiler/data/lang-specific/jpx/doc。[編輯]
- 相關链接：根頁面 • 根頁面的子頁面 • 链入 • 嵌入包含 • 測試用例 • 沙盒 (差異)
參見：Module:category tree/poscatboiler/data/lang-specific/doc
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
local reading_types_chinese = {
["goon"] = "吳音",
["kan'on"] = "漢音",
["kan'yōon"] = "慣用音",
["kun"] = "訓讀",
["nanori"] = "名乘",
["on"] = "音讀",
["tōon"] = "唐音",
["sōon"] = "宋音",
}
function export.add_labels(labels, lang)
labels["連體詞"] = {
description = "{{{langname}}} {{m|ja|連体詞|tr=れんたいし, rentaishi}}。用來修飾名詞、沒有活用且不做謂語的詞類。",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["平假名"] = {
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 "For more information, see [[Wiktionary:Japanese language]].\n\n" or "") .. "''See also'' [[:Category:{{{langname}}}片假名]]",
toc_template = "categoryTOC-hiragana",
parents = {
{name = "{{{langcat}}}", raw = true},
"Category:平假名字元",
}
}
labels["歷史平假名"] = {
description = "{{{langname}}}在歷史上曾使用的平假名形式。",
additional = "參見[[:Category:{{{langname}}}歷史片假名]]。",
toc_template = "categoryTOC-hiragana",
parents = {
"平假名",
{name = "{{{langcat}}}", raw = true},
"Category:平假名字元",
}
}
labels["片假名"] = {
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 "For more information, see [[Wiktionary:Japanese language]].\n\n" or "") .. "''See also'' [[:Category:{{{langname}}}平假名]]",
toc_template = "categoryTOC-katakana",
parents = {
{name = "{{{langcat}}}", raw = true},
"Category:片假名字元",
}
}
labels["歷史片假名"] = {
description = "{{{langname}}}在歷史上曾使用的片假名形式。",
additional = "參見[[:Category:{{{langname}}}歷史平假名]]。",
toc_template = "categoryTOC-katakana",
parents = {
"片假名",
{name = "{{{langcat}}}", raw = true},
"Category:片假名字元",
}
}
labels["參雜假名的用語拼寫"] = {
description = "{{{langname}}}中同時使用[[平假名]]和[[片假名]]（有時還包括[[漢字]]）的詞彙。",
parents = {
{name = "{{{langcat}}}", raw = true},
"hiragana",
"katakana",
},
}
labels["敬語"] = {
intro = "{{wikipedia|Honorific speech in Japanese}}",
description = "{{{langname}}} [[honorific]]s.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["謙讓語"] = {
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 = "敬語",
}
labels["尊敬語"] = {
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 = "敬語",
}
labels["依讀音分類的漢字"] = {
description = "依讀音分類的{{{langname}}}漢字。",
parents = {{name = "漢字", sort = "讀音"}},
}
labels["枕詞"] = {
intro = "{{wikipedia|枕詞}}",
description = "{{{langname}}} idioms used in poetry to introduce specific words.",
parents = {"idioms"},
}
labels["依漢字讀音分類的詞"] = {
description = "{{{langname}}} categories grouped with regard to the readings of the kanji with which they are spelled.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["依讀音規則分類的詞"] = {
description = "{{{langname}}} categories with terms grouped by their reading patterns.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
for reading_pattern, link in pairs {
["熟字訓"] = "{{ja-r|熟字訓|じゅくじくん}}",
["重箱讀法"] = "{{ja-r|重%箱%読み|じゅう%ばこ%よみ}}（在詞的前半部用音讀，後半部用訓讀）",
["訓讀"] = "{{ja-r|訓読み|くんよみ}}",
["名乘"] = "{{ja-r|名乗り|なのり}}",
["音讀"] = "{{ja-r|音%読み|おん%よみ}}",
["湯桶讀法"] = "{{ja-r|湯%桶%読み|ゆ%とう%よみ}}（在詞的前半部用訓讀，後半部用音讀）",
} do
labels["使用" .. reading_pattern .. "的詞"] = {
description = "顯示{{{langname}}}中使用" .. link .. "的詞語。",
breadcrumb = reading_pattern,
parents = {{name = "依讀音規則分類的詞", sort = reading_pattern}},
}
end
labels["依漢字讀法分類的詞"] = {
description = "按漢字讀法分類的{{{langname}}}分類。主要分為漢語由來（音讀）和{{{langname}}}自身由來（訓讀）。",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["未指定是否及物的動詞"] = {
description = "在標題行模板中缺失<code>tr=</code>參數的{{{langname}}}動詞。",
hidden = true,
can_be_empty = true,
parents = {"詞條維護"},
}
labels["四字成語"] = {
intro = "{{wikipedia|四字成語}}",
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:
* [[:Category:有漢字使用吳音的{{{langname}}}詞]]
* [[:Category:有漢字使用慣用音的{{{langname}}}詞]]
* [[:Category:有漢字使用漢音的{{{langname}}}詞]]
* [[:Category:有漢字使用唐音的{{{langname}}}詞]]
]=]
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 {
["吳音"] = "a {{ja-r|呉%音|ご%おん}} reading" .. on_desc,
["漢音"] = "a {{ja-r|漢%音|かん%おん}} reading" .. on_desc,
["慣用音"] = "a {{ja-l|慣用音|かんようおん|kan'yōon}} reading" .. on_desc,
["訓讀"] = "a {{ja-r|訓%読み|くん%よみ}} or {{ja-r|訓|くん}} reading",
["名乘"] = "a {{ja-r|名%乗り|な%のり}} reading, which is a type of reading used for people and places",
["音讀"] = "an {{ja-r|音%読み|おん%よみ}} or {{ja-r|音|おん}} reading",
["唐音"] = "a {{ja-r|唐%音|とう%おん}} reading" .. on_desc,
["宋音"] = "a {{ja-r|宋%音|そう%おん}} reading" .. on_desc,
} do
labels["有漢字使用" .. reading_type .. "的詞"] = {
description = "{{{langname}}} categories with terms that are spelled with one or more kanji which exhibit " .. reading_desc .. ".",
additional = reading_type == "on" and on_continuation,
breadcrumb = reading_type,
parents = {{name = "依漢字讀法分類的詞", sort = reading_pattern}},
}
end
labels["有借字的詞"] = {
intro = "{{wikipedia|借字 (日語)|借字}}",
description = "使用{{m|ja|当て字}}（借字）的{{{langname}}}詞。",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["有代用字的詞"] = {
description = "使用代用字的{{{langname}}}詞，依據{{temp|ja-daiyouji}}形成的分類。",
parents = {"詞源"},
}
labels["有熟字訓的詞"] = {
description = "使用{{m|ja|熟字訓}}的{{{langname}}}詞。",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["有常用漢字的詞"] = {
intro = "{{wikipedia|常用漢字}}",
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 = "依正字法屬性分類的詞", sort = "jōyō"}},
}
labels["有表外漢字的詞"] = {
intro = "{{wikipedia|表外漢字}}",
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 = "依正字法屬性分類的詞", 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 = "有表外漢字的詞", 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["有中學漢字的詞"] = {
description = "{{{langname}}} terms spelled with secondary school kanji.",
parents = {{name = "有常用漢字的詞", sort = "secondary school"}},
}
labels["有多個讀音的詞"] = {
description = "{{{langname}}} terms with multiple pronunciations (hence multiple [[kana]] spellings).",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["依漢字音拍數分類的詞"] = {
description = "{{{langname}}} categories grouped with regard to the number of morae in their kanji readings.",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["單漢字詞"] = {
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 = {
['歷史假名遣'] = true,
['古日語'] = true,
}
local function separate_period_reading_type(text)
if not text then return nil, nil end
for k, v in pairs(periods) do
matched = string.find(text, k)
if matched then
text = text:gsub(k, "")
if text == "" then return "", k end
return k, text
end
end
return "", text
end
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 = "[[Appendix:日語術語#" .. 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)
return require("Module:links").full_link({
lang = lang,
sc = get_sc(reading),
term = reading:gsub('[%.%- ]', ''),
tr = kana_to_romaji((reading:gsub('%-', '')), lang:getCode(), nil, {hist = historical})
}, 'term')
end
local function is_on_subtype(reading_type)
return reading_type:find(".音$")
end
table.insert(handlers, function(data)
local count, plural = data.label:match("^terms written with (.+) Han script character(s?)$")
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 = data.label:match("^讀作(.)個音拍的漢字$")
if count then
local num = count
if not num then
return nil
end
return {
description = "含有".. count .."個音拍的{{{langname}}}漢字讀法。",
breadcrumb = num,
parents = {{name = "依漢字音拍數分類的詞", sort = num}},
}
end
end)
table.insert(handlers, function(data)
local label_pref, reading = rmatch(data.label, "^(讀作「" .. kana_capture .. "」的漢字)$")
if reading then
local parents = {{name = "依讀音分類的漢字", sort = (data.lang:makeSortKey(reading))}}
local tagged_reading = get_tagged_reading(reading)
return {
description = "讀作「" .. get_reading_link(reading, period_text) .. "」的{{{langname}}}漢字。",
displaytitle = "讀作「" .. tagged_reading .. "」的{{{langname}}}漢字",
breadcrumb = tagged_reading,
parents = parents,
}
end
end)
table.insert(handlers, function(data)
local label_pref, period_plus_reading_type, reading = rmatch(data.label, "^(([一-鿌]*)讀作「" .. kana_capture .. "」的漢字)$")
if period_plus_reading_type then
local period, reading_type = separate_period_reading_type(period_plus_reading_type)
local period_text, reading_type_link = get_period_text_and_reading_type_link(period, reading_type)
if not reading_type_link then
return nil
end
-- Compute parents.
local parents = {
{name = "依" .. (period_text or "") .. reading_type .. "分類的漢字", sort = (data.lang:makeSortKey(reading))}
}
if is_on_subtype(reading_type) then
table.insert(parents, {name = (period_text or "") .. "音讀讀作「" .. reading .. "」的漢字", sort = reading_type})
elseif period_text then
table.insert(parents, {name = period_text .. "讀作「" .. reading .. "」的漢字", sort = reading_type})
end
if not period_text then
table.insert(parents, {name = "讀作「" .. reading .. "」的漢字", sort = reading_type})
end
local tagged_reading = get_tagged_reading(reading)
return {
description = (period_text or "") .. reading_type_link .. "讀法讀作「" .. get_reading_link(reading, period_text) .. "」的{{{langname}}}[[漢字]]。",
displaytitle = (period or "") .. reading_type .. "讀作「".. tagged_reading .. "」的{{{langname}}}漢字",
breadcrumb = tagged_reading,
parents = parents,
}
end
end)
table.insert(handlers, function(data)
local matched = rmatch(data.label, "^依([一-鿌]*)分類的漢字$")
local period, reading_type = separate_period_reading_type(matched)
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 = "依" .. (period_text or "") .. "音讀分類的漢字", sort = reading_type} or
period_text and {name = "依" .. reading_type .. "分類的漢字", sort = period} or
{name = "依讀音分類的漢字", sort = reading_type}
}
if period_text then
table.insert(parents, {name = "依" .. period_text .. "分類的漢字", sort = reading_type})
end
-- Compute description.
local description = "依照" .. (period_text or "") .. reading_type_link .. "進行分類的{{{langname}}}[[漢字]]。"
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, "^(讀作「" .. kana_capture .. "」的詞)$")
if reading then
-- Compute parents.
local sort_key = (data.lang:makeSortKey(reading))
local mora_count = m_lang.count_morae(reading)
local parents = {
{name = "依漢字讀音分類的詞", sort = sort_key},
{name = "讀作" .. mora_count .. "個音拍的漢字", sort = sort_key},
{name = "讀作「" .. reading .. "」的漢字", sort = " "},
}
local tagged_reading = get_tagged_reading(reading)
return {
description = "讀法為" .. get_reading_link(reading) ..
"的{{{langname}}}詞條（不考慮任何發音變化）。",
displaytitle = "讀作「" .. tagged_reading .. "」的{{{langname}}}詞",
breadcrumb = tagged_reading,
parents = parents,
}
end
end)
table.insert(handlers, function(data)
local kanji, reading = rmatch(data.label, "^寫作「(.)」讀作「" .. kana_capture .. "」的詞$")
if not kanji then
return nil
end
local params = {
[4] = {list = true},
}
local args = require("Module:parameters").process(data.args, params)
if #args[4] == 0 then
error("對於形如「寫作『？』讀作『？』的" .. data.lang:getCanonicalName() ..
"詞」的分類，請指明至少一種讀法（例如kun表示訓讀，on表示音讀），分別填入1=、2=、3=等。")
end
local reading_types = {}
for _, reading_type in ipairs(args[4]) do
table.insert(reading_types, reading_types_chinese[reading_type])
end
reading_types = mw.text.listToText(reading_types, "、", "或")
local parents = {
{name = "寫作「" .. kanji.. "」的詞", 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 = "讀作「" .. reading.. "」的詞", sort = kanji},
}
for _, reading_type in ipairs(args[4]) do
table.insert(parents, {name = "有漢字使用" .. reading_types_chinese[reading_type] .. "的詞", sort = (data.lang:makeSortKey(reading))})
end
local tagged_kanji = get_tagged_reading(kanji)
local tagged_reading = get_tagged_reading(reading)
return {
description = "含有漢字「{{l|{{{langcode}}}|" .. kanji .. "}}」且採用" ..
reading_types .. "讀作「" .. get_reading_link(reading) .. "」的{{{langname}}}詞語。",
displaytitle = "寫作「" .. tagged_kanji .. "」讀作「" .. tagged_reading .. "」的{{{langname}}}詞",
breadcrumb = "讀作「" .. tagged_reading .. "」",
parents = parents,
}, true
end)
table.insert(handlers, function(data)
local kanji, daiyoji = rmatch(data.label, "^使用「(.)」作為代用字代替「(.)」的詞")
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("對於形如使用『？』作為代用字代替『？』的" .. data.lang:getCanonicalName() ..
"詞」的分類，請指明至少一種代用字用法，在sort=填入代用字的發音")
end
local tagged_kanji = get_tagged_reading(kanji)
local tagged_daiyoji = get_tagged_reading(daiyoji)
return {
description = "採用代用字「{{l|{{{langcode}}}|" .. kanji .. "}}」来代替「{{l|{{{langcode}}}|" .. daiyoji .. "}}」的{{{langname}}}詞語。",
displaytitle = "使用「" .. tagged_kanji .. "」作為代用字代替「" .. tagged_daiyoji .. "」的{{{langname}}}詞",
breadcrumb = "使用「" .. tagged_kanji .. "」代替「" .. tagged_daiyoji .. "」的詞",
parents = {{name = "有代用字的詞", sort = args.sort}},
}, true
end)
end
return export