วิกิพจนานุกรม

มอดูล:Unicode data

The following documentation is located at มอดูล:Unicode data/documentation. [edit]
Useful links: subpage list • links • transclusions • testcases • sandbox (diff)

This module is used for accessing the Unicode character database (version 16.0), derived from files in the Unicode Character Database (UCD).

Functions

แก้ไข

All of these functions can only be used in a module. For template-invokable functions, see Module:Unicode data/templates.

lookup_name
Look up the name of a code point. Used by Module:character info, Module:character list, Module:also, and Module:mul-domino def.
lookup_image
Look up the image for a code point. Used by Module:character info and Module:character list.
enum_blocks
Used in a for in loop in Module:character list to iterate through the array of block ranges.
lookup_plane
Returns the name of the plane to which a code point belongs. Unused.
get_block_range
Given a block name, returns the range of code points included in the block. Used by Module:character list.
is_valid_pagename
Given a string, returns true or false depending on whether the string can be used as a page title.
add_dotted_circle
Given a string, places a dotted circle before every combining character in the string. Used by Module:grc-utilities.
lookup_script
Given a code point, returns the Unicode script code, using Module:Unicode data/scripts.
get_entry_title
Returns the title for the entry on a character, which is a subpage of Unsupported titles for characters that cannot appear in pagenames. See Manual:Page title on the MediaWiki website for more information. Used by Module:character info and Module:character list.

The following functions relate to a code point's General Category. They receive a code point and return two values: a boolean (which expresses whether the code point fulfills the condition) and a string describing the General Category, if the character is in the General Categories of Separator (Z) or Other (C), or the string "assigned". They use Module:Unicode data/control.

is_assigned
Checks whether a code point's General Category is not Cn (Other, unassigned). Used by Module:character list.
is_printable
Checks whether a code point is printable: that its General Category is not "Other" (C), "Separator, line" (Zl), or "Separator, paragraph" (Zp). Used by Module:character info and Module:character list.
is_whitespace
Checks whether a code point's General Category is Zs ("Separator, space"). Used by Module:character list and Module:links/print data.

Data modules

แก้ไข

The data used by functions in this module is found on subpages.

The name and image data modules (Module:Unicode data/names/xxx and Module:Unicode data/images/xxx) were compiled from UnicodeData.txt. Each one contains, at maximum, code points U+xxx000 to U+xxxFFF. The names in the following ranges, however, are auto-generated by this base module and do not require separate name modules:

BMP: 0000–001F (C0 control characters), 007F–009F (DEL and C1 control characters), 3400–4DBF (CJK),
4E00–9FFF (CJK), AC00–D7A3 (Hangul), D800–DFFF (surrogates), E000–F8FF (private use), F900–FAFF (CJK)
SMP: 17000–18AFF (Tangut), 18B00–18CD5 (Khitan), 18D00–18D08 (Tangut), 1B170–1B2FB (Nüshu)
Planes 2–3 (CJK)
Plane 14: E0100–E01EF (variation selectors)
Planes 15–16 (private use)

ข้อผิดพลาดสคริปต์: ไม่มีมอดูล "User:Erutuon/Unicode"

Updating

แก้ไข

When each Unicode version is released, several submodules, and sometimes the name rules in the main module, need to be updated. The name, block, control character, and combining character category modules were constructed by the scripts given in User:Kephir/Unicode; the script and General Category modules were generated by modules on Wikipedia. Most of the name rules are given in chapter 4, section 4.8 (Name) of the Unicode Core Specification, others were manually added and at each Unicode version the ranges of characters that they apply to may need to be expanded.

Module:Unicode data/Hangul and the Hangul Syllable name rule never need to be updated.

After these modules have been updated, the version number in Module:character list needs to be updated as well.

แก้ไข

The Unicode database is released by Unicode Inc. under the following terms:

Copyright © 1991-2022 Unicode, Inc. All rights reserved. Distributed under the Terms of Use in https://www.unicode.org/copyright.html.

Permission is hereby granted, free of charge, to any person obtaining a copy of the Unicode data files and any associated documentation (the "Data Files") or Unicode software and any associated documentation (the "Software") to deal in the Data Files or Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, and/or sell copies of the Data Files or Software, and to permit persons to whom the Data Files or Software are furnished to do so, provided that either (a) this copyright and permission notice appear with all copies of the Data Files or Software, or (b) this copyright and permission notice appear in associated Documentation.

THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE DATA FILES OR SOFTWARE.

Except as contained in this notice, the name of a copyright holder shall not be used in advertising or otherwise to promote the sale, use or other dealings in these Data Files or Software without prior written authorization of the copyright holder. 

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

local cp = m_str_utils.codepoint
local gcodepoint = m_str_utils.gcodepoint
local gsub = string.gsub
local u = m_str_utils.char

local export = {}
local udata = mw.loadData("Module:Unicode data/data")

local floor = math.floor

local function errorf(first_arg, ...)
	if type(first_arg) == "number" then
		return error(string.format(...), first_arg + 1)
	else
		return error(string.format(first_arg, ...), 2)
	end
end

local function binary_range_search(codepoint, ranges)
	local low, mid, high
	low, high = 1, ranges.length or require "Module:table".length(ranges)
	while low <= high do
		mid = floor((low + high) / 2)
		local range = ranges[mid]
		if codepoint < range[1] then
			high = mid - 1
		elseif codepoint <= range[2] then
			return range, mid
		else
			low = mid + 1
		end
	end
	return nil, mid
end
export.binary_range_search = binary_range_search

local function linear_range_search(codepoint, ranges)
	for i, range in ipairs(ranges) do
		if codepoint < range[1] then
			break
		elseif codepoint <= range[2] then
			return range
		end
	end
end

-- Load a module by indexing "loader" with the name of the module minus the
-- "Module:Unicode data/" part. For instance, loader.blocks returns
-- [[Module:Unicode data/blocks]]. If a module cannot be loaded, false will be
-- returned.
local loader = setmetatable({}, {
	__index = function (self, key)
		local success, data = pcall(mw.loadData, "Module:Unicode data/" .. key)
		if not success then
			data = false
		end
		self[key] = data
		return data
	end
})

-- For the algorithm used to generate Hangul Syllable names,
-- see "Hangul Syllable Name Generation" in section 3.12 of the
-- Unicode Specification:
-- https://www.unicode.org/versions/latest/ch03.pdf
-- For most of the name rules given here, see the subsection
-- "Unicode Name Property" in section 4.8 (Name) and the table 4-8
-- (Name Derivation Rule Prefix Strings):
-- https://www.unicode.org/versions/latest/ch04.pdf
local name_hooks = {
	{   0x0000,   0x001F, "<control-%04X>" }, -- C0 control characters
	{   0x007F,   0x009F, "<control-%04X>" }, -- DEL and C1 control characters
	{   0x3400,   0x4DBF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension A
	{   0x4E00,   0x9FFF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph
	{   0xAC00,   0xD7A3, function (codepoint) -- Hangul Syllables
		local Hangul_data = loader.Hangul
		local syllable_index = codepoint - 0xAC00

		return ("HANGUL SYLLABLE %s%s%s"):format(
			Hangul_data.leads[floor(syllable_index / Hangul_data.final_count)],
			Hangul_data.vowels[floor((syllable_index % Hangul_data.final_count)
				/ Hangul_data.trail_count)],
			Hangul_data.trails[syllable_index % Hangul_data.trail_count]
		)
	end },
	-- High Surrogates, High Private Use Surrogates, Low Surrogates
	{   0xD800,   0xDFFF, "<surrogate-%04X>" },
	{   0xE000,   0xF8FF, "<private-use-%04X>" }, -- Private Use
	-- CJK Compatibility Ideographs
	{   0xF900,   0xFA6D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
	{   0xFA70,   0xFAD9, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
	{   0xFDD0,   0xFDEF, "<noncharacter-%04X>" },
	{   0xFE00,   0xFE0F, function (codepoint) -- Variation Selectors Supplement
		return ("VARIATION SELECTOR-%d"):format(codepoint - 0xFE00 + 1)
	end},
    {  0x13460,  0x143FA, "EGYPTIAN HIEROGLYPH-%04X" }, -- Egyptian Hieroglyphs Extended-A
	{  0x17000,  0x187F7, "TANGUT IDEOGRAPH-%04X" }, -- Tangut
	{  0x18800,  0x18AFF, function (codepoint)
		return ("TANGUT COMPONENT-%03d"):format(codepoint - 0x187FF)
	end },
	{  0x18B00,  0x18CD5, "KHITAN SMALL SCRIPT CHARACTER-%04X" }, -- Khitan Small Script
	{  0x18CFF,  0x18CFF, "KHITAN SMALL SCRIPT CHARACTER-%04X" },
	{  0x18D00,  0x18D08, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Supplement
	{  0x1B170,  0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu
	{  0x20000,  0x2A6DF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B
	{  0x2A700,  0x2B739, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C
	{  0x2B740,  0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D
	{  0x2B820,  0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E
	{  0x2CEB0,  0x2EBE0, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension F
	{  0x2EBF0,  0x2EE5D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension I
	-- CJK Compatibility Ideographs Supplement (Supplementary Ideographic Plane)
	{  0x2F800,  0x2FA1D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
	{  0x30000,  0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G
	{  0x31350,  0x323AF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension H
	{  0xE0100,  0xE01EF, function (codepoint) -- Variation Selectors Supplement
		return ("VARIATION SELECTOR-%d"):format(codepoint - 0xE0100 + 17)
	end},
	{  0xF0000,  0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use
	{ 0x100000, 0x10FFFD, "<private-use-%04X>" }, -- Plane 16 Private Use
}
name_hooks.length = #name_hooks
--[[ Add another - in this line to test the code point ordering in name_hooks.
local i = 1
local function print_it(a, b, c)
	if type(c) == "string" then
		mw.log(c:format(a), c:format(b))
	else
		mw.log(c(a), c(b))
	end
end
while true do
	local first, second = name_hooks[i], name_hooks[i + 1]
	if not (first and second) then break end
	local message
	if not (first[1] < first[2] and first[2] < second[1] and second[1] < second[2]) then
		message = "Bad name label ordering at index " .. i .. ":"
	elseif second[1] == first[2] + 1 and second[3] == first[3] then
		message = "Name hooks can be merged at index " .. i .. ":"
	end
	if message then
		mw.log(message)
		print_it(unpack(first))
		print_it(unpack(second))
	end
	i = i + 1
end
--]]

local name_range_cache

local function generate_name(data, codepoint)
	if type(data) == "string" then
		return data:format(codepoint)
	else
		return data(codepoint)
	end
end

--[[
-- Checks that the code point is a number and in range.
-- Does not check whether code point is an integer.
-- Not used
local function check_codepoint(funcName, argIdx, val)
	require 'libraryUtil'.checkType(funcName, argIdx, val, 'number')
	if codepoint < 0 or 0x10FFFF < codepoint then
		errorf("Codepoint %04X out of range", codepoint)
	end
end
--]]

-- https://www.unicode.org/versions/latest/ch04.pdf, section 4.8
function export.lookup_name(codepoint)
	-- U+FDD0-U+FDEF and all code points ending in FFFE or FFFF are Unassigned
	-- (Cn) and specifically noncharacters:
	-- https://www.unicode.org/faq/private_use.html#nonchar4
	if codepoint >= 0xFFFE and floor(codepoint % 0x10000) >= 0xFFFE then
		return ("<noncharacter-%04X>"):format(codepoint)
	end

	if name_range_cache -- Check if previously used "name hook" applies to this code point.
			and codepoint >= name_range_cache[1]
			and codepoint <= name_range_cache[2] then
		return generate_name(name_range_cache[3], codepoint)
	end
	
	local range = binary_range_search(codepoint, name_hooks)
	if range then
		name_range_cache = range
		return generate_name(range[3], codepoint)
	end

	local data = loader[('names/%03X'):format(codepoint / 0x1000)]
	
	if data and data[codepoint] then
		return data[codepoint]
	
	-- Unassigned (Cn) consists of noncharacters and reserved characters.
	-- The character has been established not to be a noncharacter,
	-- and if it were assigned, its name would already been retrieved,
	-- so it must be reserved.
	else
		return ("<reserved-%04X>"):format(codepoint)
	end
end

function export.lookup_image(codepoint)
	local data = loader[('images/%03X'):format(codepoint / 0x1000)]
	
	if data then
		return data[codepoint]
	end
end

function export.lookup_image_emoji(codepoint)
	local data = loader[('emoji_images/%03X'):format(codepoint / 0x1000)]
	
	if data then
		return data[codepoint]
	end
end

-- Load [[Module:Unicode data/blocks]] if needed and assign it to this variable.
local blocks

local function block_iter(blocks, i)
	i = i + 1
	local data = blocks[i]
	if data then
		 -- Unpack doesn't work on tables loaded with mw.loadData.
		return i, data[3], data[1], data[2]
	end
end

-- An ipairs-type iterator generator for the list of blocks.
function export.enum_blocks()
	local blocks = loader.blocks
	return block_iter, blocks, 0
end

function export.get_block_range(name)
	for i, block in ipairs(loader.blocks) do
		if block[3] == name then
			return block[1], block[2]
		end
	end
end

function export.lookup_plane(codepoint)
	local i = floor(codepoint / 0x10000)
	return udata.planes[i] or ("Plane %u"):format(i)
end

function export.lookup_block(codepoint)
	local blocks = loader.blocks
	local range = binary_range_search(codepoint, blocks)
	if range then
		return range[3]
	else
		return "No Block"
	end
end

function export.get_block_info(name)
	for i, block in ipairs(loader.blocks) do
		if block[3] == name then
			return block
		end
	end
end

function export.is_valid_pagename(pagename)
	local has_nonws = false

	for codepoint in gcodepoint(pagename) do
		if (codepoint == 0x0023) -- #
		or (codepoint == 0x005B) -- [
		or (codepoint == 0x005D) -- ]
		or (codepoint == 0x007B) -- {
		or (codepoint == 0x007C) -- |
		or (codepoint == 0x007D) -- }
		or (codepoint == 0x180E) -- MONGOLIAN VOWEL SEPARATOR
		or ((codepoint >= 0x2000) and (codepoint <= 0x200A)) -- spaces in General Punctuation block
		or (codepoint == 0xFFFD) -- REPLACEMENT CHARACTER
		then
			return false
		end

		local printable, result = export.is_printable(codepoint)
		if not printable then
			return false
		end

		if result ~= "space-separator" then
			has_nonws = true
		end
	end

	return has_nonws
end

local function manual_unpack(what, from)
	if what[from + 1] == nil then
		return what[from]
	end
	
	local result = {}
	from = from or 1
	for i, item in ipairs(what) do
		if i >= from then
			table.insert(result, item)
		end
	end
	return unpack(result)
end

local function compare_ranges(range1, range2)
	return range1[1] < range2[1]
end

-- Creates a function to look up data in a module that contains "singles" (a
-- code point-to-data map) and "ranges" (an array containing arrays that contain
-- the low and high code points of a range and the data associated with that
-- range).
-- "loader" loads and returns the "singles" and "ranges" tables.
-- "match_func" is passed the code point and either the data or the "dots", and
-- generates the final result of the function.
-- The varargs ("dots") describes the default data to be returned if there wasn't
-- a match.
-- In case the function is used more than once, "cache" saves ranges that have
-- already been found to match, or a range whose data is the default if there
-- was no match.
local function codepoint_lookup(data_module_subpage, match_func, ...)
	local dots = { ... }
	local cache = {}
	local singles, ranges

	return function (codepoint)
		if not singles then
			local data_module = loader[data_module_subpage]
			singles, ranges = data_module.singles, data_module.ranges
		end

		if singles[codepoint] then
			return match_func(codepoint, singles[codepoint])
		end

		local range = binary_range_search(codepoint, cache)
		if range then
			return match_func(codepoint, manual_unpack(range, 3))
		end
		
		local range, index = binary_range_search(codepoint, ranges)
		if range then
			table.insert(cache, range)
			table.sort(cache, compare_ranges)
			return match_func(codepoint, manual_unpack(range, 3))
		end
		
		if ranges[index] then
			local dots_range
			if codepoint > ranges[index][2] then
				dots_range = {
					ranges[index][2] + 1,
					ranges[index + 1] and ranges[index + 1][1] - 1 or 0x10FFFF,
					unpack(dots)
				}
			else -- codepoint < range[index][1]
				dots_range = {
					ranges[index - 1] and ranges[index - 1][2] + 1 or 0,
					ranges[index][1] - 1,
					unpack(dots)
				}
			end
			table.insert(cache, dots_range)
			table.sort(cache, compare_ranges)
		end
		
		return match_func(codepoint, unpack(dots))
	end
end

-- Return a character's combining class value from [[Module:Unicode data/combining classes]],
-- or otherwise 0, which is treated as the default value.
do
	local combining
	
	function export.combining_class(ch)
		combining = combining or mw.loadData("Module:Unicode data/combining classes")
		return combining[type(ch) == "number" and u(ch) or ch] or 0
	end
end

-- FIXME: Some combining characters have a combining class of 0, so this needs rethinking.
function export.is_combining(ch)
	return export.combining_class(ch) ~= 0
end

do
	local function dotted_circle(ch)
		if export.combining_class(ch) ~= 0 then
			return "◌" .. ch
		end
	end
	
	function export.add_dotted_circle(str)
		return (gsub(str, ".[\128-\191]*", dotted_circle))
	end
end

local lookup_control = codepoint_lookup(
	"control",
	function (codepoint, ccc)
		return ccc or "assigned"
	end,
	"assigned")
export.lookup_control = lookup_control

function export.is_assigned(codepoint)
	return lookup_control(codepoint) ~= "unassigned"
end

function export.is_printable(codepoint)
	local result = lookup_control(codepoint)
	return (result == "assigned") or (result == "space-separator"), result
end

function export.is_whitespace(codepoint)
	local result = lookup_control(codepoint)
	return (result == "space-separator"), result
end

export.lookup_category = codepoint_lookup(
	"category",
	function (codepoint, category)
		return category
	end,
	"Cn"
)

function export.get_category_long_name(category)
	return loader["category"].long_names[category]
end

export.lookup_script = codepoint_lookup(
	"scripts",
	function (codepoint, script)
		return script
	end,
	"Zzzz"
)

function export.get_script_alias(script)
	return loader["scripts"].aliases[script]
end

function export.get_entry_title(codepoint)
	if udata.unsupported_title[codepoint] then
		return udata.unsupported_title[codepoint]
	end
	if lookup_control(codepoint) ~= "assigned" then
		return nil
	end
	return u(codepoint)
end

return export
เข้าถึงจาก "https://th.wiktionary.org/w/index.php?title=มอดูล:Unicode_data&oldid=2118308"