Module:category tree/poscatboiler/data/lang-specific/jpx

The following documentation is generated by Module:documentation. ^[edit]

Useful links: root page • root page’s subpages • links • transclusions • testcases • sandbox

This module handles generating the descriptions and categorization for Japonic category pages of the format "Japonic LABEL" where LABEL can be any text. Examples are Category:Bulgarian conjugation 2.1 verbs and Category:Russian velar-stem neuter-form nouns. This module is part of the poscatboiler system, which is a general framework for generating the descriptions and categorization of category pages.

For more information, see Module:category tree/poscatboiler/data/lang-specific/documentation.

NOTE: If you add a new language-specific module, you must add the language code to the list at the top of Module:category tree/poscatboiler/data/lang-specific in order for the module to be recognized.

---

local export = {}

local concat = table.concat
local insert = table.insert
local Hani_sort = require("Module:Hani-sortkey").makeSortKey
local sort = table.sort

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 yomi_data = require("Module:kanjitab/data")


function export.add_labels(labels, lang)
	labels["adnominals"] = {
		description = "{{{langname}}} adnominals, or {{ja-r|連%体%詞|れん%たい%し}}, which modify nouns, and do not conjugate or [[predicate#Verb|predicate]].",
		parents = {{name = "{{{langcat}}}", raw = true}},
	}

	labels["hiragana"] = {
		description = "{{{langname}}} terms with hiragana {{mdash}} {{ja-r|平%仮%名|ひら%が%な}} {{mdash}} forms, sorted by conventional hiragana sequence. The hiragana form 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}}} katakana]]",
		toc_template = "categoryTOC-hiragana",
		parents = {
			{name = "{{{langcat}}}", raw = true},
			"Category:Hiragana script characters",
		}
	}

	labels["historical hiragana"] = {
		description = "{{{langname}}} historical [[hiragana]].",
		additional = "''See also'' [[:Category:{{{langname}}} historical katakana]].",
		toc_template = "categoryTOC-hiragana",
		parents = {
			"hiragana",
			{name = "{{{langcat}}}", raw = true},
			"Category:Hiragana script characters",
		}
	}

	labels["katakana"] = {
		description = "{{{langname}}} terms with katakana {{mdash}} {{ja-r|片%仮%名|かた%か%な}} {{mdash}} 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}}} hiragana]]",
		toc_template = "categoryTOC-katakana",
		parents = {
			{name = "{{{langcat}}}", raw = true},
			"Category:Katakana script characters",
		}
	}

	labels["historical katakana"] = {
		description = "{{{langname}}} historical [[katakana]].",
		additional = "''See also'' [[:Category:{{{langname}}} historical hiragana]].",
		toc_template = "categoryTOC-katakana",
		parents = {
			"katakana",
			{name = "{{{langcat}}}", raw = true},
			"Category:Katakana script characters",
		}
	}

	labels["terms spelled with mixed kana"] = {
		description = "{{{langname}}} terms which combine [[hiragana]] and [[katakana]] characters, potentially with [[kanji]] too.",
		parents = {
			{name = "{{{langcat}}}", raw = true},
			"hiragana",
			"katakana",
		},
	}

	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 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 that elevates the listener in relation to the speaker.",
		parents = "honorifics",
	}

	labels["kanji by reading"] = {
		description = "{{{langname}}} kanji categorized by reading.",
		parents = {{name = "Han characters", sort = "reading"}},
	}
	
	labels["makurakotoba"] = {
		topright = "{{wikipedia|Makurakotoba}}",
		description = "{{{langname}}} idioms used in poetry to introduce specific words.",
		parents = {"idioms"},
	}

	labels["terms by kanji readings"] = {
		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 reading pattern"] = {
		description = "{{{langname}}} categories with terms grouped by their reading patterns.",
		parents = {{name = "{{{langcat}}}", raw = true}},
	}
	
	local function handle_onyomi_list(category, category_type, cat_yomi_type)
		local onyomi, seen = {}, {}
		for _, yomi in pairs(yomi_data) do
			if not seen[yomi] and yomi.onyomi then
				local yomi_catname = yomi[category_type]
				if yomi_catname ~= false then
					local yomi_type = yomi.type
					if yomi_type ~= "on'yomi" and yomi_type ~= cat_yomi_type then
						insert(onyomi, "[[:Category:{{{langname}}} " .. category:gsub("{{{yomi_catname}}}", yomi_catname) .. "]]")
					end
				end
			end
			seen[yomi] = true
		end
		sort(onyomi)
		return onyomi
	end
	
	local function add_yomi_category(category, category_type, parent, description)
		for _, yomi in pairs(yomi_data) do
			local yomi_catname = yomi[category_type]
			if yomi_catname ~= false then
				local yomi_type = yomi.type
				local yomi_desc = yomi.link or yomi_catname
				if yomi.description then
					yomi_desc = yomi_desc .. "; " .. yomi.description
				end
				local label = {
					description = description .. " " .. yomi_desc .. ".",
					breadcrumb = yomi_type,
					parents = {{name = parent, sort = yomi_catname}},
				}
				if yomi.onyomi then
					local onyomi = handle_onyomi_list(category, category_type, yomi_type)
					
					label.additional = "Categories of terms with " ..
						(yomi_type == "on'yomi" and "more" or "other") ..
						" specific types of on'yomi readings can be found in the following categories:\n* " .. concat(onyomi, "\n* ")
					
					if yomi_type ~= "on'yomi" then
						insert(label.parents, 1, {
							name = (category:gsub("{{{yomi_catname}}}", yomi_data.on[category_type])),
							sort = yomi_catname
						})
					end
				end
				labels[category:gsub("{{{yomi_catname}}}", yomi_catname)] = label
			end
		end
	end
	
	add_yomi_category(
		"terms read with {{{yomi_catname}}}",
		"reading_category",
		"terms by reading pattern",
		"{{{langname}}} terms exhibiting"
	)
	
	add_yomi_category(
		"terms spelled with kanji with {{{yomi_catname}}} readings",
		"kanji_category",
		"terms by kanji reading type",
		"{{{langname}}} categories with terms that are spelled with one or more kanji exhibiting"
	)
	
	labels["terms with missing yomi"] = {
		description = "{{{langname}}} terms where at least one [[Appendix:Japanese glossary#yomi|yomi]] is missing from {{tl|{{{langcode}}}-kanjitab}}.",
		hidden = true,
		can_be_empty = true,
		parents = {"entry maintenance"},
	}
	
	labels["terms by kanji reading type"] = {
		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, {{ja-r|音|おん}} readings, and those of non-Chinese origin, {{ja-r|訓|くん}} readings.",
		parents = {{name = "{{{langcat}}}", raw = true}},
	}
	
	labels["terms spelled with ateji"] = {
		topright = "{{wikipedia|Ateji}}",
		description = "{{{langname}}} terms containing one or more [[Appendix:Japanese glossary#ateji|ateji]] {{mdash}} {{ja-r|当て字|あてじ}} {{mdash}} 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 daiyōji"] = {
		description = "Japanese terms spelled using [[Appendix:Japanese glossary#daiyouji|daiyōji]], categorized using {{temp|ja-daiyouji}}.",
		parents = {"terms by etymology"},
	}

	labels["terms spelled with jukujikun"] = {
		description = "{{{langname}}} terms containing one or more [[Appendix:Japanese glossary#jukujikun|jukujikun]] {{mdash}} {{ja-r|熟%字%訓|じゅく%じ%くん}} {{mdash}} which are [[kanji]] used to represent meanings rather than sounds.",
		parents = {{name = "{{{langcat}}}", raw = true}},
	}

	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 {{ja-r|常%用 漢%字|じょう%よう かん%じ}}.",
		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 {{ja-r|常%用 漢%字|じょう%よう かん%じ}}.",
		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["kanji readings by number of morae"] = {
		description = "{{{langname}}} categories grouped with regard to the number of morae in their kanji readings.",
		parents = {{name = "{{{langcat}}}", raw = true}},
	}
	
	labels["single-kanji terms"] = {
		description = "{{{langname}}} terms written as a single kanji.",
		parents = {"terms by orthographic property", {name = "character counts", sort = " "}},
	}
	
	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, {{ja-r|四%字 熟%語|よ%じ じゅく%ご}}, with idiomatic meanings; typically derived from Classical Chinese, Buddhist scripture or traditional Japanese proverbs.",
		additional = "Compare [[w:Chengyu|chengyu]] in Sinitic languages.",
		parents = {"idioms"},
	}
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 = "[[Appendix:Japanese glossary#" .. 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(".on$")
	end


	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)


	insert(handlers, function(data)
		local count, plural = data.label:match("^kanji readings with (.+) mora(e?)$")
		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" .. plural .. ".",
				breadcrumb = num,
				parents = {{name = "kanji readings by number of morae", sort = num}},
			}
		end
	end)


	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
				insert(parents, {name = "kanji with " .. (period_text or "") .. "on reading " .. reading, sort = reading_type})
			elseif period_text then
				insert(parents, {name = "kanji with " .. period_text .. "reading " .. reading, sort = reading_type})
			end
			if not period_text then
				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)


	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 = "kanji by reading", sort = reading_type}
			}
			if period_text then
				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)


	insert(handlers, function(data)
		local label_pref, reading = rmatch(data.label, "^(kanji read as )" .. kana_capture .. "$")
		if reading then
			local params = {
				["histconsol"] = {},
			}
			local args = require("Module:parameters").process(data.args, params)
			local parents = {{name = "kanji by reading", 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 = "{{{langname}}} [[kanji]] read as " .. get_reading_link(reading, period_text) .. ".",
				additional = addl,
				displaytitle = "{{{langname}}} " .. label_pref .. tagged_reading,
				breadcrumb = tagged_reading,
				parents = parents,
			}, true
		end
	end)


	insert(handlers, function(data)
		local label_pref, reading = rmatch(data.label, "^(terms spelled with kanji read as )" .. 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 = "terms by kanji readings", sort = sort_key},
				{name = "kanji readings with " .. mora_count_words .. " mora" .. (mora_count > 1 and "e" or ""), sort = sort_key},
				{name = "kanji read as " .. 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)


	insert(handlers, function(data)
		local kanji, reading = rmatch(data.label, "^terms spelled with (.) read as " .. 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. {{code|kun}} or {{code|on}}) must be specified using 1=, 2=, 3=, etc.")
		end
		local yomi_types, parents = {}, {}
		for _, yomi, category in ipairs(args[1]) do
			local yomi_data = yomi_data[yomi]
			if not yomi_data then
				error("The yomi type \"" .. yomi .. "\" is not recognized.")
			end
			category = yomi_data.kanji_category
			if not category then
				error("The yomi type \"" .. yomi .. "\" is not valid for this type of category.")
			end
			insert(yomi_types, "<i>" .. yomi_data.type .. "</i> reading")
			insert(parents, {
				name = "terms spelled with kanji with " .. category .. " readings",
				sort = (data.lang:makeSortKey(reading))
			})
		end
		
		yomi_types = require("Module:table").serialCommaJoin(yomi_types, {conj = "or"})
		
		insert(parents, 1, {name = "terms spelled with " .. kanji, sort = (data.lang:makeSortKey(reading))})
		insert(parents, 2, {name = "terms spelled with kanji read as " .. reading, sort = Hani_sort(kanji)})
		
		local tagged_kanji = get_tagged_reading(kanji)
		local tagged_reading = get_tagged_reading(reading)
		return {
			description = "{{{langname}}} terms spelled with {{l|{{{langcode}}}|" .. kanji .. "}} with its " ..
				yomi_types .. " of " .. get_reading_link(reading) .. ".",
			displaytitle = "{{{langname}}} terms spelled with " .. tagged_kanji .. " read as " .. tagged_reading,
			breadcrumb = "read as " .. tagged_reading,
			parents = parents,
		}, true
	end)


	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 = "terms spelled with daiyōji", sort = args.sort}},
		}, true
	end)
end


return export