wikt>Shlyst: unify Japanese's what_categorizes_msg Module:category tree/fam/jpx/what-categorizes-msg

2026-04-11T01:46:26Z

unify Japanese's what_categorizes_msg Module:category tree/fam/jpx/what-categorizes-msg

New page

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 = "([-" .. require("Module:ja/data/range").kana .. "・]+)"
local yomi_data = require("Module:kanjitab/data")

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 = "''See also'' [[:Category:{{{langname}}} katakana]]",
toc_template = "Hira-categoryTOC",
toc_template_full = "Hira-categoryTOC/full",
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 = "Hira-categoryTOC",
toc_template_full = "Hira-categoryTOC/full",
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 = "''See also'' [[:Category:{{{langname}}} hiragana]]",
toc_template = "Kana-categoryTOC",
toc_template_full = "Kana-categoryTOC/full",
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 = "Kana-categoryTOC",
toc_template_full = "Kana-categoryTOC/full",
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["kanji"] = {
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["kanji by reading"] = {
description = "{{{langname}}} kanji categorized by reading.",
parents = {{name = "kanji", sort = "reading"}},
}

labels["makurakotoba"] = {
topright = "{{wp|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}},
}

labels["terms by number of kanji"] = {
description = "{{{langname}}} terms categorized by number of kanji.",
parents = {"terms by orthographic property"},
}

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 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["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 with IPA pronunciation with pitch accent"] = {
description = "{{{langname}}} terms with pronunciations that have {{w|Japanese pitch accent|pitch accent}} specified.",
additional = "Pitch accent can be specified in {{tl|{{{langcode}}}-pron}} with the {{code|=acc=}} parameter.",
can_be_empty = true,
parents = {"entry maintenance", "pitch accent"},
}

labels["terms with IPA pronunciation missing pitch accent"] = {
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["pitch accent"] = {
description = "{{{langname}}} terms regarding {{w|Japanese pitch accent|pitch accent}} pronunciation.",
can_be_empty = true,
parents = {{name = "{{{langcat}}}", raw = true}},
}

labels["terms with Heiban pitch accent (Tōkyō)"] = {
description = "{{{langname}}} terms with pronunciations that are (Tōkyō) [[平板型|Heiban]] {{w|Japanese pitch accent|pitch accent}}.",
can_be_empty = true,
parents = {"pitch accent"}
}

labels["terms with Atamadaka pitch accent (Tōkyō)"] = {
description = "{{{langname}}} terms with pronunciations that are (Tōkyō) [[頭高型|Atamadaka]] {{w|Japanese pitch accent|pitch accent}}.",
can_be_empty = true,
parents = {"pitch accent"}
}

labels["terms with Nakadaka pitch accent (Tōkyō)"] = {
description = "{{{langname}}} terms with pronunciations that are (Tōkyō) [[中高型|Nakadaka]] {{w|Japanese pitch accent|pitch accent}}.",
can_be_empty = true,
parents = {"pitch accent"}
}

labels["terms with Odaka pitch accent (Tōkyō)"] = {
description = "{{{langname}}} terms with pronunciations that are (Tōkyō) [[尾高型|Odaka]] {{w|Japanese pitch accent|pitch accent}}.",
can_be_empty = true,
parents = {"pitch accent"}
}

labels["terms with complex pitch accent (Tōkyō)"] = {
description = "{{{langname}}} terms with pronunciations that are (Tōkyō) complex {{w|Japanese pitch accent|pitch accent}}, as in having more than one {{m|ja|アクセント句}}.",
can_be_empty = true,
parents = {"pitch accent"}
}

labels["pitch accent deaccenting before の"] = {
description = "{{{langname}}} terms with {{w|Japanese pitch accent|pitch accent}} pronunciations that have exceptional deaccenting or lack thereof before の ({{ja-deaccenting-before-no}}).",
can_be_empty = true,
parents = {"pitch accent"}
}

labels["terms with Odaka pitch accent not deaccented before の (Tōkyō)"] = {
description = "{{{langname}}} terms with pronunciations that are (Tōkyō) [[尾高型|Odaka]] {{w|Japanese pitch accent|pitch accent}} and do not become deaccented before の ({{ja-deaccenting-before-no}}).",
can_be_empty = true,
parents = {"pitch accent deaccenting before の"}
}

labels["terms with Nakadaka pitch accent deaccented before の (Tōkyō)"] = {
description = "{{{langname}}} terms with pronunciations that are (Tōkyō) [[中高型|Nakadaka]] {{w|Japanese pitch accent|pitch accent}} and become deaccented before の ({{ja-deaccenting-before-no}}).",
can_be_empty = true,
parents = {"pitch accent deaccenting before の"}
}

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 = "{{wp|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}},
}

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[grade_kanji] = {
topright = topright,
description = "{{{langname}}} kanji " .. desc,
toc_template = "Hani-categoryTOC",
parents = {{
name = parent and (parent .. " kanji") or "kanji",
sort = sort or grade
}},
}

labels["terms spelled with " .. grade_kanji] = {
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[i]
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["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 = "terms with 1 kanji", sort = " "},
},
}

labels["kanji with kun readings missing okurigana designation"] = {
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["terms by the individual characters in their historical spellings"] = {
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["verbs without transitivity"] = {
description = "{{{langname}}} verbs missing the {{code|=tr=}} parameter from their headword templates.",
hidden = true,
can_be_empty = true,
parents = {"entry maintenance"},
}

labels["yojijukugo"] = {
topright = "{{wp|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 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[v] = 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[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 match(str:gsub("[%s%p]+", ""), "[^" .. Hira:getCharacters() .. "]") 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[period]
reading = reading:gsub("[%.%-%s]+", "")
return full_link({
lang = lang,
sc = get_sc(reading),
term = link or reading:gsub("・", ""),
-- If we have okurigana, demarcate furigana.
alt = reading:gsub("^(.-)・", "%1"),
tr = kana_to_romaji((reading:gsub("・", ".")), lang:getCode(), nil, {keep_dot = true, hist = hist})
:gsub("^(.-)%.", "%1"),
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 n =data.label:match("^terms with ([1-9]%d*) kanji$")
if not n then
return
end
local sortkey = require("Module:category tree").numeral_sortkey(n, 2097152)
return {
breadcrumb = n,
description = ("{{{langname}}} terms containing exactly %d kanji."):format(n),
-- TODO: implement this using the same mechanism used to implement parents (i.e. avoiding the need for raw categories).
-- umbrella = {
-- breadcrumb = ("%d kanji"):format(n),
-- parents = {{name = "terms by number of kanji subcategories by language", sort = sortkey}},
-- },
parents = {{name = ("terms by number of kanji"), sort = sortkey}}
}
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)}
},
umbrella = false,
}
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[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}},
umbrella = false,
}
end)

insert(handlers, function(data)
local label_pref, period, reading_type, reading = match(data.label, "^(kanji with ([a-z]-) ?([%a']+) 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}}} [[kanji]] 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,
umbrella = false,
}
end)

insert(handlers, function(data)
local period, reading_type = match(data.label, "^kanji by ([a-z]-) ?([%a']+) 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}}} [[kanji]] categorized by " .. (period_text or "") .. reading_type_link .. " reading."
return {
description = description,
breadcrumb = (period_text or "") .. reading_type,
parents = parents,
umbrella = false,
}
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, {
["histconsol"] = 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 [[Wikipedia:Historical kana orthography|historical]] [[Wikipedia:Kanazukai|reading]], now " ..
"consolidated with the [[Wikipedia:Modern kana usage|modern reading]] of " ..
get_reading_link(args.histconsol, lang, nil, ("Category:Japanese kanji read as %s"):format(args.histconsol)) .. ".")
end

return {
description = "{{{langname}}} [[kanji]] 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,
umbrella = false,
}, 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,
umbrella = false,
}
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, {
[1] = {list = true},
})
local lang = data.lang

if #args[1] == 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[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, 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,
umbrella = false,
}, true
end)

insert(handlers, function(data)
local affix, kanji, reading = data.label:match("^terms ([a-z]+fix)ed with (.+) read as " .. kana_capture .. "$")

if not affix or not kanji or not reading then
return nil
end

local args = require("Module:parameters").process(data.args, {
[1] = {list = true},
})
local lang = data.lang

if #args[1] == 0 then
error("For categories of the form \"" .. lang:getCanonicalName() ..
" terms AFFIXed 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 = {}
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, yomi_data.link)
end

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 description = "{{{langname}}} terms " .. affix .. "ed with {{l|{{{langcode}}}|" .. kanji .. "}} with " ..
yomi_types .. " of " .. get_reading_link(reading, lang) .. "."
local what_categorizes_msg =
require("Module:category tree/fam/jpx/what-categorizes-msg")
.get_what_categorizes_msg(kanji, reading, affix)
if what_categorizes_msg then
description = description .. "\n\n" .. what_categorizes_msg
end

local parents = {}
table.insert(parents, {name = "terms " .. affix .. "ed with " .. kanji, sort = (lang:makeSortKey(reading))})
if mw.title.new("Category:" .. lang:getCanonicalName() .. " terms spelled with " .. kanji .. " read as " .. reading).exists then
table.insert(parents, {name = "terms spelled with " .. kanji .. " read as " .. reading, sort = (lang:makeSortKey(reading)), args=data.args})
end

local tagged_kanji = get_tagged_reading(kanji, lang)
local tagged_reading = get_tagged_reading(reading, lang)
return {
description = description,
displaytitle = "{{{langname}}} terms " .. affix .. "ed with " .. tagged_kanji .. " read as " .. tagged_reading,
breadcrumb = "read as " .. reading,
parents = parents,
umbrella = false,
}, 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, {
["sort"] = 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 [[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}},
umbrella = false,
}, true
end)

return {LABELS = labels, HANDLERS = handlers}

Module:category tree/fam/jpx - Revision history

Sware: 1 revision imported

wikt>Shlyst: unify Japanese's what_categorizes_msg Module:category tree/fam/jpx/what-categorizes-msg

← Older revision	Revision as of 11:22, 21 April 2026
(No difference)