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

local labels = {}
local handlers = {}

local m_str_utils = require("Module:string utilities")

local concat = table.concat
local full_link = require("Module:links").full_link
local insert = table.insert
local Hani_sort = require("Module:Hani-sortkey").makeSortKey
local match = m_str_utils.match
local sort = table.sort
local tag_text = require("Module:script_utilities").tag_text
local ucfirst = m_str_utils.ucfirst

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 kana_capture = "(+)"
local yomi_data = require("Module:kanjitab/data")

labels = {
	description = "{{{langname}}} adnominals, or {{ja-r|連%体%詞|れん%たい%し}}, which modify nouns, and do not conjugate or ].",
	parents = {{name = "{{{langcat}}}", raw = true}},
}

labels = {
	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 ] representation of that word. " ..
	"Wiktionary represents {{{langname}}}-language segments in three ways: in normal form (with ], if appropriate), in ] " ..
	"form (this differs from kanji form only when the segment contains kanji), and in ] form.",
	additional = "''See also'' ]",
	toc_template = "categoryTOC-hiragana",
	parents = {
		{name = "{{{langcat}}}", raw = true},
		"Category:Hiragana script characters",
	}
}

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

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

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

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

labels = {
	topright = "{{wp|Honorific speech in Japanese}}",
	description = "{{{langname}}} ]s.",
	parents = {{name = "{{{langcat}}}", raw = true}},
}

labels = {
	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 = {
	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 = {
	topright = "{{wp|Kanji}}",
	description = "{{{langname}}} symbols of the Han logographic script, which can represent sounds or convey meanings directly.",
	toc_template = "Hani-categoryTOC",
	umbrella = "Han characters",
	parents = "logograms",
}

labels = {
	description = "{{{langname}}} kanji categorized by reading.",
	parents = {{name = "kanji", sort = "reading"}},
}

labels = {
	topright = "{{wp|Makurakotoba}}",
	description = "{{{langname}}} idioms used in poetry to introduce specific words.",
	parents = {"idioms"},
}

labels = {
	description = "{{{langname}}} categories grouped with regard to the readings of the kanji with which they are spelled.",
	parents = {{name = "{{{langcat}}}", raw = true}},
}

labels = {
	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 and yomi.onyomi then
			local yomi_catname = yomi
			if yomi_catname ~= false then
				local yomi_type = yomi.type
				if yomi_type ~= "on'yomi" and yomi_type ~= cat_yomi_type then
					insert(onyomi, "]")
				end
			end
		end
		seen = 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
		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)),
						sort = yomi_catname
					})
				end
			end
			labels = label
		end
	end
end

add_yomi_category(
	"terms read with {{{yomi_catname}}}",
	"reading_category",
	"terms by reading pattern",
	"{{{langname}}} terms read with"
)

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 read with"
)

labels = {
	description = "{{{langname}}} terms where at least one ] is missing from {{tl|{{{langcode}}}-kanjitab}}.",
	hidden = true,
	can_be_empty = true,
	parents = {"entry maintenance"},
}

labels = {
	description = "{{{langname}}} terms with pronunciations that do not have a {{w|Japanese pitch accent|pitch accent}} specified.",
	additional = "Pitch accent can be specified in {{tl|{{{langcode}}}-pron}} with the {{code|=acc=}} parameter.",
	hidden = true,
	can_be_empty = true,
	parents = {"entry maintenance"},
}

labels = {
	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 = {
	topright = "{{wp|Ateji}}",
	description = "{{{langname}}} terms containing one or more ] {{mdash}} {{ja-r|当て字|あてじ}} {{mdash}} which are ] used to represent sounds rather than meanings (though meaning may have some influence on which kanji are chosen).",
	parents = {{name = "{{{langcat}}}", raw = true}},
}

labels = {
	description = "Japanese terms spelled using ], categorized using {{temp|ja-daiyouji}}.",
	parents = {"terms by etymology"},
}

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

local function add_grade_categories(grade, desc, wp, only_one, parent, sort)
	local grade_kanji = grade .. " kanji"
	local topright = wp and ("{{wp|%s}}"):format(ucfirst(grade_kanji)) or nil
	
	labels = {
		topright = topright,
		description = "{{{langname}}} kanji " .. desc,
		toc_template = "Hani-categoryTOC",
		parents = {{
			name = parent and (parent .. " kanji") or "kanji",
			sort = sort or grade
		}},
	}
	
	labels = {
		topright = topright,
		description = "{{{langname}}} terms spelled with " .. (only_one and "at least one " or "") .. "kanji " .. desc,
		parents = {{
			name = parent and ("terms spelled with " .. parent .. " kanji") or "terms by orthographic property",
			sort = sort or grade
		}},
	}
end

for i = 1, 6 do
	local ord = m_numeric.ones_position_ord
	add_grade_categories(
		ord .. " grade",
		"taught in the " .. ord .. " grade of elementary school, as designated by the the official list of {{ja-r|教%育 漢%字|きょう%いく かん%じ|education kanji}}.",
		false,
		false,
		"kyōiku",
		i
	)
end

add_grade_categories(
	"kyōiku",
	"on the official list of {{ja-r|教%育 漢%字|きょう%いく かん%じ|education kanji}}.",
	true,
	false,
	"jōyō"
)

add_grade_categories(
	"secondary school",
	"on the official list of {{ja-r|常%用 漢%字|じょう%よう かん%じ|regular-use characters}} that are generally taught in secondary school.",
	false,
	false,
	"jōyō"
)

add_grade_categories(
	"jōyō",
	"on the official list of {{ja-r|常%用 漢%字|じょう%よう かん%じ|regular-use characters}}.",
	true,
	false
)

add_grade_categories(
	"tōyō",
	"on the official list of {{ja-r|当%用 漢%字|とう%よう かん%じ|general-use characters}}, which was used from 1946{{ndash}}1981 until the publication of the list of {{ja-r|常%用 漢%字|じょう%よう かん%じ|regular-use characters}}.",
	true,
	false
)

add_grade_categories(
	"jinmeiyō",
	"on the official list of {{ja-r|人%名%用 漢%字|じん%めい%-よう かん%じ|kanji for use in personal names}}.",
	true,
	true
)

add_grade_categories(
	"hyōgai",
	"not included on the official list of {{ja-r|常%用 漢%字|じょう%よう かん%じ|regular-use characters}} or {{ja-r|人%名%用 漢%字|じん%めい%-よう かん%じ|kanji for use in personal names}}, known as {{ja-r|表%外 漢%字|ひょう%がい かん%じ}} or {{ja-r|表%外%字|ひょう%がい%じ|unlisted characters}}.",
	true,
	true
)

labels = {
	description = "{{{langname}}} terms with multiple pronunciations (hence multiple ] spellings).",
	parents = {{name = "{{{langcat}}}", raw = true}},
}

labels = {
	description = "{{{langname}}} categories grouped with regard to the number of morae in their kanji readings.",
	parents = {{name = "{{{langcat}}}", raw = true}},
}

labels = {
	description = "{{{langname}}} terms written as a single kanji.",
	parents = {"terms by orthographic property", {name = "character counts", sort = " "}},
}

labels = {
	breadcrumb = "Kanji missing okurigana designation",
	description = "{{{langname}}} kanji entries in which one or more kun readings entered into {{tl|{{{langcode}}}-readings}} is missing a hyphen denoting okurigana.",
	toc_template = "Hani-categoryTOC",
	hidden = true,
	can_be_empty = true,
	parents = {"entry maintenance"},
}

labels = {
	breadcrumb = "Historical",
	description = "{{{langname}}} terms categorized by whether their spellings in the {{w|historical kana orthography}} included certain individual characters.",
	parents = {{name = "terms by their individual characters", sort = " "}},
}

labels = {
	description = "{{{langname}}} verbs missing the {{code|=tr=}} parameter from their headword templates.",
	hidden = true,
	can_be_empty = true,
	parents = {"entry maintenance"},
}

labels = {
	topright = "{{wp|Yojijukugo}}",
	description = "{{{langname}}} four-] 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 Chinese {{w|chengyu}} and Korean {{w|sajaseong-eo}}.",
	umbrella = "four-character idioms",
	parents = {"idioms"},
}

-- FIXME: Only works for 0 through 19.
local word_to_number = {}
for k, v in pairs(m_numeric.ones_position) do
	word_to_number = k
end

local periods = {
	historical = true,
	ancient = true,
}

local function get_period_text_and_reading_type_link(period, reading_type)
	if period and not periods 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 then
		return nil, reading_type
	end

	local reading_type_link = "]"
	return period_text, reading_type_link
end

local function get_sc(str)
	return match(str:gsub("+", ""), "") and Jpan or Hira
end
		
local function get_tagged_reading(reading, lang)
	return tag_text(reading, lang, get_sc(reading))
end

local function get_reading_link(reading, lang, period, link)
	local hist = periods
	reading = reading:gsub("+", "")
	return full_link({
		lang = lang,
		sc = get_sc(reading),
		term = link or reading:gsub("・", ""),
		-- If we have okurigana, demarcate furigana.
		alt = reading:gsub("^(.-)・", "<span style=\"border-top:1px solid;position:relative;padding:1px;\">%1<span style=\"position:absolute;top:0;bottom:67%%;right:0%%;border-right:1px solid;\"></span></span>"),
		tr = kana_to_romaji((reading:gsub("・", ".")), lang:getCode(), nil, {keep_dot = true, hist = hist})
			:gsub("^(.-)%.", "<u>%1</u>"),
		pos = reading:find("・", 1, true) and get_tagged_reading((reading:gsub("^.-・", "～")), lang) or nil
	}, "term")
end

local function is_on_subtype(reading_type)
	return reading_type:find(".on$")
end

insert(handlers, function(data)
	local number = data.label:match("^terms with (%d*) kanji$")
	if not number then
		return
	end
	return {
		description = "{{{langname}}} terms containing exactly " .. number .. " kanji.",
		breadcrumb = number,
		parents = {{
			name = "character counts",
			sort = ("#%03d"):format(number)
		}}
	}
end)


insert(handlers, function(data)
	local label_pref, kana = data.label:match("^(terms historically spelled with )" .. kana_capture .. "$")
	
	if not kana then
		return
	end
	
	local lang = data.lang
	
	return {
		description = "{{{langname}}} terms spelled with " .. get_reading_link(kana, lang, "historical") .. " in the {{w|historical kana orthography}}.",
		displaytitle = "{{{langname}}} " .. label_pref .. get_tagged_reading(kana, lang),
		breadcrumb = "historical",
		parents = {
			{name = "terms spelled with " .. kana, sort = " "},
			{name = "terms by the individual characters in their historical spellings", sort = lang:makeSortKey(kana)}
		},
	}
end)


insert(handlers, function(data)
	local count, plural = data.label:match("^kanji readings with (.+) mora(e?)$")
	
	-- Make sure 'one' goes with singular and other numbers with plural.
	if not count or (count == "one") ~= (plural == "") then
		return
	end
	
	local num = word_to_number
	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)


insert(handlers, function(data)
	local label_pref, period, reading_type, reading = match(data.label, "^(kanji with (-) ?(+) reading )" .. kana_capture .. "$")
	
	if not period then
		return
	end
	
	period = period ~= "" and period or nil
	local period_text, reading_type_link = get_period_text_and_reading_type_link(period, reading_type)
	
	if not reading_type_link then
		return
	end
	
	local lang = data.lang
	
	-- Compute parents.
	local parents, breadcrumb = {}
	if reading:find("・", 1, true) then
		local okurigana = reading:match("・(.*)")
		insert(parents, {
			name = "kanji with " .. (period_text or "") .. reading_type .. " reading " .. reading:match("(.-)・"),
			-- Sort by okurigana, since all coordinate categories will have the same furigana.
			sort = (lang:makeSortKey(okurigana))
		})
		breadcrumb = "～" .. okurigana
	else
		insert(parents, {
			name = "kanji by " .. (period_text or "") .. reading_type .. " reading",
			sort = (lang:makeSortKey(reading))
		})
		breadcrumb = reading
	end
	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
	
	return {
		description = "{{{langname}}} ] with the " .. (period_text or "") .. reading_type_link .. " reading " ..
			get_reading_link(reading, lang, period or reading_type) .. ".",
		displaytitle = "{{{langname}}} " .. label_pref .. get_tagged_reading(reading, lang),
		breadcrumb = get_tagged_reading(breadcrumb, lang),
		parents = parents,
	}
end)

insert(handlers, function(data)
	local period, reading_type = match(data.label, "^kanji by (-) ?(+) reading$")
	
	if not period then
		return
	end
	
	period = period ~= "" and period or nil
	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}}} ] categorized by " .. (period_text or "") .. reading_type_link .. " reading."
	return {
		description = description,
		breadcrumb = (period_text or "") .. reading_type,
		parents = parents,
	}
end)


insert(handlers, function(data)
	local label_pref, reading = match(data.label, "^(kanji read as )" .. kana_capture .. "$")
	
	if not reading then
		return
	end
	
	local args = require("Module:parameters").process(data.args, {
		 = true,
	})
	local lang = data.lang
	
	local parents, breadcrumb = {}
	if reading:find("・", 1, true) then
		local okurigana = reading:match("・(.*)")
		insert(parents, {
			name = "kanji read as " .. reading:match("(.-)・"),
			-- Sort by okurigana, since all coordinate categories will have the same furigana.
			sort = (lang:makeSortKey(okurigana))
		})
		breadcrumb = "～" .. okurigana
	else
		insert(parents, {
			name = "kanji by reading",
			sort = (lang:makeSortKey(reading))
		})
		breadcrumb = reading
	end
	
	local addl
	local period_text
	if args.histconsol then
		period_text = "historical"
		addl = ("This is a ] ], now " ..
		"consolidated with the ] of " ..
		get_reading_link(args.histconsol, lang, nil, ("Category:Japanese kanji read as %s"):format(args.histconsol)) .. ".")
	end
	
	return {
		description = "{{{langname}}} ] read as " .. get_reading_link(reading, lang, period_text) .. ".",
		additional = addl,
		displaytitle = "{{{langname}}} " .. label_pref .. get_tagged_reading(reading, lang),
		breadcrumb = get_tagged_reading(breadcrumb, lang),
		parents = parents,
	}, true
end)


insert(handlers, function(data)
	local label_pref, reading = match(data.label, "^(terms spelled with kanji read as )" .. kana_capture .. "$")
	
	if not reading then
		return
	end
	
	-- Compute parents.
	local lang = data.lang
	local sort_key = (lang:makeSortKey(reading))
	local mora_count = require("Module:ja").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, lang)
	return {
		description = "{{{langname}}} terms that contain kanji that exhibit a reading of " .. get_reading_link(reading, lang) ..
		" in those terms prior to any sound changes.",
		displaytitle = "{{{langname}}} " .. label_pref .. tagged_reading,
		breadcrumb = tagged_reading,
		parents = parents,
	}
end)


insert(handlers, function(data)
	local kanji, reading = match(data.label, "^terms spelled with (.) read as " .. kana_capture .. "$")
	
	if not kanji then
		return nil
	end
	
	local args = require("Module:parameters").process(data.args, {
		 = {list = true},
	})
	local lang = data.lang
	
	if #args == 0 then
		error("For categories of the form \"" .. lang:getCanonicalName() ..
			" terms spelled with KANJI read as READING\", at least one reading type (e.g. <code>kun</code> or <code>on</code>) must be specified using <code>1=</code>, <code>2=</code>, <code>3=</code>, etc.")
	end
	local yomi_types, parents = {}, {}
	for _, yomi, category in ipairs(args) do
		local yomi_data = yomi_data
		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, yomi_data.link)
		insert(parents, {
			name = "terms spelled with kanji with " .. category .. " readings",
			sort = (lang:makeSortKey(reading))
		})
	end
	
	insert(parents, 1, {name = "terms spelled with " .. kanji, sort = (lang:makeSortKey(reading))})
	insert(parents, 2, {name = "terms spelled with kanji read as " .. reading, sort = Hani_sort(kanji)})
	
	yomi_types = (#yomi_types > 1 and "one of " or "") .. "its " ..
		require("Module:table").serialCommaJoin(yomi_types, {conj = "or"}) ..
		" reading" .. (#yomi_types > 1 and "s" or "")
	
	local tagged_kanji = get_tagged_reading(kanji, lang)
	local tagged_reading = get_tagged_reading(reading, lang)
	return {
		description = "{{{langname}}} terms spelled with {{l|{{{langcode}}}|" .. kanji .. "}} with " ..
			yomi_types .. " of " .. get_reading_link(reading, lang) .. ".",
		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 = match(data.label, "^terms with (.) replaced by daiyōji (.)$")
	
	if not kanji then
		return nil
	end
	
	local args = require("Module:parameters").process(data.args, {
		 = true,
	})
	local lang = data.lang
	
	if not args.sort then
		error("For categories of the form \"" .. 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, lang)
	local tagged_daiyoji = get_tagged_reading(daiyoji, lang)
	return {
		description = "{{{langname}}} terms with {{l|{{{langcode}}}|" .. kanji .. "}} replaced by ] {{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)

return {LABELS = labels, HANDLERS = handlers}