模組:Category tree/poscatboiler/data/characters
此數據子模塊定義了維基詞典分類結構的一部分。
關於poscatboiler系統的介紹以及如何添加或更改分類，請參見Module:category tree/poscatboiler/data/documentation。
local raw_categories = {}
local handlers = {}
local ulen = mw.ustring.len
local uupper = mw.ustring.upper
local ulower = mw.ustring.lower
local rfind = mw.ustring.find
-----------------------------------------------------------------------------
-- --
-- RAW CATEGORIES --
-- --
-----------------------------------------------------------------------------
raw_categories["Terms by their individual characters subcategories by language"] = {
description = "Umbrella categories covering terms categorized by unusual characters contained in them.",
additional = "{{{umbrella_meta_msg}}}",
parents = {
"綜合元分類",
{name = "按漢字分類的詞", is_label = true, sort = " "},
},
}
raw_categories["字元子分類"] = {
description = "Umbrella categories covering terms categorized by unusual characters contained in them.",
additional = "{{{umbrella_meta_msg}}}",
parents = {
"綜合元分類",
{name = "依字元分類的詞", is_label = true, sort = " "},
},
}
-----------------------------------------------------------------------------
-- --
-- HANDLERS --
-- --
-----------------------------------------------------------------------------
-- If char is a combining character, returns a version with a dotted circle before it.
function add_dotted_circle(char, combining)
return combining and "◌" .. char or char
end
table.insert(handlers, function(data)
-- NOTE: The "character" in the title may actually be a description such as
-- "gershayim". In that case, char= is specified as a parameter indicating the
-- actual character.
local titlechar = data.label:match("^帶「(.+)」的詞$")
if not titlechar then
return nil
end
local params = {
["char"] = {},
["sort"] = {},
-- Not sure what used to be done with the following parameters.
["context"] = {},
["context2"] = {},
}
local args = require("Module:parameters").process(data.args, params)
if titlechar == "數字" then
local sortkey = args.sort or "#"
return {
description = "含有一個或多個數字的{{{langname}}}詞。",
parents = {{name = "依字元分類的詞", sort = sortkey }},
breadcrumb = "數字",
umbrella = {
breadcrumb = "數字",
parents = {{name = "字元子分類", sort = " " .. sortkey }}
},
}, true
end
local char = args.char or titlechar
local titlechar_is_desc = args.char and args.char ~= titlechar
if titlechar_is_desc then
require("Module:debug").track("poscatboiler-characters/titlechar_is_desc")
end
local lang = data.lang or require("Module:languages").getByCode("mul")
local combining = ulen(char) == 1 and require("Module:Unicode_data").is_combining(mw.ustring.codepoint(char))
local upper = uupper(char)
if char ~= upper and ulen(char) == 1 then
-- We want uppercase characters; but unless we're careful, we run into an issue with
-- [[Category:English terms spelled with ı]] due to the weird behavior of this character,
-- which has standard I as its uppercase equivalent.
local standard_chars = lang:getStandardCharacters()
if standard_chars and not rfind(upper, "[" .. standard_chars .. "]") then
error("Category titles should use uppercase characters: '" .. data.label .. "'")
end
end
-- Compute description.
-- If the letter has a lowercase form, show it.
local character = require("Module:links").full_link(
{
term = char,
alt = combining and add_dotted_circle(char, true) or nil,
lang = lang,
tr = combining and "-" or nil,
},
"term"
)
if ulower(char) ~= char then
character = "大寫" .. character .. "或小寫" ..
require("Module:links").full_link(
{
term = ulower(char),
lang = lang
},
"term"
)
end
if titlechar_is_desc then
character = character .. " (" .. titlechar .. ")"
end
local description = "帶「" .. character .. "」的{{{langname}}}詞。"
-- Set tagged character for displaytitle and breadcrumb.
local tagged_titlechar = not titlechar_is_desc and
require("Module:script utilities").tag_text(titlechar, lang, nil, "term") or nil
local tagged_char = titlechar_is_desc and titlechar or
require("Module:script utilities").tag_text(add_dotted_circle(char, combining), lang, nil, "term")
-- Compute sort key.
local sortkey =
args.sort or lang:makeSortKey(char)
if sortkey == "" then
sortkey = char
end
return {
description = description,
displaytitle = not titlechar_is_desc and "帶「" .. tagged_titlechar .. "」的{{{langname}}}詞" or nil,
parents = {{name = "依字元分類的詞", sort = sortkey }},
breadcrumb = tagged_char,
umbrella = {
displaytitle = not titlechar_is_desc and "帶「" .. tagged_titlechar .. "」的詞" or nil,
breadcrumb = tagged_char,
parents = {{name = "字元子分類", sort = " " .. sortkey }}
} or false,
}, true
end)
table.insert(handlers, function(data)
-- NOTE: The "character" in the title may actually be a description such as
-- "gershayim". In that case, char= is specified as a parameter indicating the
-- actual character.
local titlechar = data.label:match("^寫作「(.+)」的詞$")
if not titlechar then
return nil
end
if string.find(titlechar, "讀作") ~= nil then ----------TEMP WORKAROUND
return nil
end
local ja_ryu = data.lang and (data.lang:getCode() == "ja" or data.lang:getCode() == "ryu")
-- If Japanese or Okinawan, only fire on a single kanji character.
if ja_ryu and (titlechar:find("[A-Za-z]") or ulen(titlechar) > 1) then
return nil
end
local params = {
["char"] = {},
["sort"] = {},
-- Not sure what used to be done with the following parameters.
["context"] = {},
["context2"] = {},
}
local args = require("Module:parameters").process(data.args, params)
local char = args.char or titlechar
local titlechar_is_desc = args.char and args.char ~= titlechar
if titlechar_is_desc then
require("Module:debug").track("poscatboiler-characters/titlechar_is_desc")
end
local lang = data.lang or require("Module:languages").getByCode("mul")
local combining = ulen(char) == 1 and require("Module:Unicode_data").is_combining(mw.ustring.codepoint(char))
local upper = uupper(char)
if char ~= upper and ulen(char) == 1 then
-- We want uppercase characters; but unless we're careful, we run into an issue with
-- [[Category:English terms spelled with ı]] due to the weird behavior of this character,
-- which has standard I as its uppercase equivalent.
local standard_chars = lang:getStandardCharacters()
if standard_chars and not rfind(upper, "[" .. standard_chars .. "]") then
error("Category titles should use uppercase characters: '" .. data.label .. "'")
end
end
-- Compute description.
-- If the letter has a lowercase form, show it.
local character = require("Module:links").full_link(
{
term = char,
alt = combining and add_dotted_circle(char, true) or nil,
lang = lang,
tr = combining and "-" or nil,
},
"term"
)
if ulower(char) ~= char then
character = "upper case " .. character .. " or lower case " ..
require("Module:links").full_link(
{
term = ulower(char),
lang = lang
},
"term"
)
end
if titlechar_is_desc then
character = character .. " (" .. titlechar .. ")"
end
local description = "含有漢字「" .. character .. "」的{{{langname}}}詞彙。"
-- Set tagged character for displaytitle and breadcrumb.
local tagged_titlechar = not titlechar_is_desc and
require("Module:script utilities").tag_text(titlechar, lang, nil, "term") or nil
local tagged_char = titlechar_is_desc and titlechar or
require("Module:script utilities").tag_text(add_dotted_circle(char, combining), lang, nil, "term")
-- Compute sort key.
local sortkey =
args.sort or
ja_ryu and ulen(char) == 1 and require("Module:zh-sortkey").makeSortKey(char, lang:getCode()) or
lang:makeSortKey(char)
if sortkey == "" then
sortkey = char
end
return {
description = description,
displaytitle = not titlechar_is_desc and "寫作「" .. mw.text.encode(tagged_titlechar, titlechar) .. "」的{{{langname}}}詞" or nil,
parents = {{name = "按漢字分類的詞", sort = sortkey }},
breadcrumb = "-{" .. tagged_char .. "}-",
umbrella = not ja_ryu and {
displaytitle = not titlechar_is_desc and "Terms spelled with " .. tagged_titlechar .. " by language" or nil,
breadcrumb = tagged_char,
parents = {{name = "Terms by their individual characters subcategories by language", sort = " " .. sortkey }}
} or false,
}, true
end)
return {RAW_CATEGORIES = raw_categories, HANDLERS = handlers}