Module:Unicode data - Revision history

ZooWiki: 1 revision imported

2023-11-28T20:43:59Z

1 revision imported

← Older revision	Revision as of 20:43, 28 November 2023
(No difference)

History of zoophilia>Pppery: Per edit request

2023-11-22T21:35:20Z

Per edit request

← Older revision		Revision as of 21:35, 22 November 2023
Line 62:		Line 62:
	{ 0x7F, 0x9F, "<control-%04X>" }, -- DEL and C1 control characters		{ 0x7F, 0x9F, "<control-%04X>" }, -- DEL and C1 control characters
	{ 0x3400, 0x4DBF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension A		{ 0x3400, 0x4DBF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension A
	{ 0x4E00, ~~0x9FFC~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph		{ 0x4E00, 0x9FFF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph
	{ 0xAC00, 0xD7A3, function (codepoint) -- Hangul Syllables		{ 0xAC00, 0xD7A3, function (codepoint) -- Hangul Syllables
	local Hangul_data = loader.Hangul		local Hangul_data = loader.Hangul
Line 86:		Line 86:
	{ 0x18D00, 0x18D08, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph Supplement		{ 0x18D00, 0x18D08, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph Supplement
	{ 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu		{ 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu
	{ 0x20000, ~~0x2A6DD~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B		{ 0x20000, 0x2A6DF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B
	{ 0x2A700, ~~0x2B734~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C		{ 0x2A700, 0x2B739, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C
	{ 0x2B740, 0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D		{ 0x2B740, 0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D
	{ 0x2B820, 0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E		{ 0x2B820, 0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E
Line 97:		Line 97:
	end},		end},
	{ 0x30000, 0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G		{ 0x30000, 0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G
			{ 0x31350, 0x323AF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension H
			{ 0x2EBF0, 0x2EE5D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension I
	{ 0xF0000, 0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use		{ 0xF0000, 0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use
	{ 0x100000, 0x10FFFD, "<private-use-%04X>" } -- Plane 16 Private Use		{ 0x100000, 0x10FFFD, "<private-use-%04X>" } -- Plane 16 Private Use
Line 160:		Line 162:
	end		end

	~~--[[~~
	~~-- No image data modules on Wikipedia yet.~~
	function p.lookup_image(codepoint)		function p.lookup_image(codepoint)
	local data = loader[('images/%03X'):format(codepoint / 0x1000)]		local data = loader[('images/%03X'):format(codepoint / 0x1000)]
Line 169:		Line 169:
	end		end
	end		end
	~~--]]~~

	local planes = {		local planes = {
Line 480:		Line 479:
	return result		return result
	end		end


			--[[--------------------------< I S _ R T L _ F R A M E >------------------------------------------------------

			external entry from an {{#invoke:}} to determine if a string of text is rtl. Strips html and html-like tags so
			that those tags don't corrupt the is-rtl-is-not-rtl determination; this added for the cases where the rtl text
			has <br /> tags.

			]]

			function p.is_rtl_frame (frame)
			local str = frame.args[1]; -- get the string from the {{#invoke:}} frame
			str = str:gsub ('%b<>', ''); -- strip any html and html-like tags
			return p.is_rtl (str); -- return if whatever remains rtl; false else
			end


	local function get_codepoint(args, arg)		local function get_codepoint(args, arg)

Ookami: 57 revisions imported

2020-09-03T04:42:35Z

57 revisions imported

← Older revision	Revision as of 04:42, 3 September 2020
(No difference)

DogMike: Created page with "local p = {} local floor = math.floor local function errorf(level, ...) if type(level) == "number" then return error(string.format(...), level + 1) else -- level is actu..."

2020-09-01T20:49:15Z

Created page with "local p = {} local floor = math.floor local function errorf(level, ...) if type(level) == "number" then return error(string.format(...), level + 1) else -- level is actu..."

← Older revision	Revision as of 20:49, 1 September 2020
(No difference)

meta>Drmccreedy: Unicode 13.0 release

2020-03-14T17:52:07Z

Unicode 13.0 release

meta>Drmccreedy: fix plane numbers per http://unicode.org/L2/L2003/03376-n2662-roadmaps.html

2019-09-14T21:16:48Z

fix plane numbers per http://unicode.org/L2/L2003/03376-n2662-roadmaps.html

← Older revision		Revision as of 21:16, 14 September 2019
Line 173:		Line 173:
	[ 1] = "Supplementary Multilingual Plane";		[ 1] = "Supplementary Multilingual Plane";
	[ 2] = "Supplementary Ideographic Plane";		[ 2] = "Supplementary Ideographic Plane";
	[13] = "Supplementary Special-purpose Plane";		[14] = "Supplementary Special-purpose Plane";
	[14] = "Supplementary Private Use Area-A";		[15] = "Supplementary Private Use Area-A";
	[15] = "Supplementary Private Use Area-B";		[16] = "Supplementary Private Use Area-B";
	}		}

meta>Pppery: Module:Table has been renamed to Module:TableTools

2019-02-19T21:34:25Z

Module:Table has been renamed to Module:TableTools

← Older revision		Revision as of 21:34, 19 February 2019
Line 13:		Line 13:
	local function binary_range_search(codepoint, ranges)		local function binary_range_search(codepoint, ranges)
	local low, mid, high		local low, mid, high
	low, high = 1, ranges.length or require "Module:~~Table~~".length(ranges)		low, high = 1, ranges.length or require "Module:TableTools".length(ranges)
	while low <= high do		while low <= high do
	mid = floor((low + high) / 2)		mid = floor((low + high) / 2)

meta>MusikAnimal: Protected "Module:Unicode data": High-risk Lua module ([Edit=Require template editor access] (indefinite) [Move=Require template editor access] (indefinite))

2019-01-24T21:02:39Z

Protected "Module:Unicode data": High-risk Lua module ([Edit=Require template editor access] (indefinite) [Move=Require template editor access] (indefinite))

← Older revision	Revision as of 21:02, 24 January 2019
(No difference)

meta>Erutuon: have is_rtl decode HTML character references; check type because mw.text.decode doesn't; best not to repeat notes

2018-09-22T21:14:58Z

have is_rtl decode HTML character references; check type because mw.text.decode doesn't; best not to repeat notes

← Older revision		Revision as of 21:14, 22 September 2018
Line 389:		Line 389:

	function p.get_best_script(str)		function p.get_best_script(str)
			-- Check type of argument, because mw.text.decode coerces numbers to strings!
			require "libraryUtil".checkType("get_best_script", 1, str, "string")

	-- Convert HTML character references (including named character references,		-- Convert HTML character references (including named character references,
	-- or character entities) to characters.		-- or character entities) to characters.
Line 411:		Line 414:

	function p.is_Latin(str)		function p.is_Latin(str)
	~~-- Convert HTML character references~~ (~~including named character references~~,		require "libraryUtil".checkType("get_best_script", 1, str, "string")
	~~-- or character entities~~) ~~to characters.~~
	str = mw.text.decode(str, true)		str = mw.text.decode(str, true)

Line 449:		Line 451:
	-- scripts, or characters of ignorable scripts.		-- scripts, or characters of ignorable scripts.
	function p.is_rtl(str)		function p.is_rtl(str)
			require "libraryUtil".checkType("get_best_script", 1, str, "string")
			str = mw.text.decode(str, true)

	-- Search for the leading bytes that introduce the UTF-8 encoding of the		-- Search for the leading bytes that introduce the UTF-8 encoding of the
	-- code points U+0580-U+10FFFF. If they are not found, the string can only		-- code points U+0580-U+10FFFF. If they are not found, the string can only
Line 514:		Line 519:

	-- is_Latin and is_valid_pagename take strings.		-- is_Latin and is_valid_pagename take strings.
	if func == p.is_Latin or func == p.is_valid_pagename then		if func == p.is_Latin or func == p.is_valid_pagename or func == p.is_rtl then
	return (func(frame.args[2]))		return (func(frame.args[2]))
	else -- The rest take code points.		else -- The rest take code points.

meta>Erutuon: have is_Latin and get_best_script interpret HTML character references

2018-09-22T20:50:08Z

have is_Latin and get_best_script interpret HTML character references

← Older revision		Revision as of 20:50, 22 September 2018
Line 389:		Line 389:

	function p.get_best_script(str)		function p.get_best_script(str)
			-- Convert HTML character references (including named character references,
			-- or character entities) to characters.
			str = mw.text.decode(str, true)

	local scripts = {}		local scripts = {}
	for codepoint in mw.ustring.gcodepoint(str) do		for codepoint in mw.ustring.gcodepoint(str) do
Line 407:		Line 411:

	function p.is_Latin(str)		function p.is_Latin(str)
			-- Convert HTML character references (including named character references,
			-- or character entities) to characters.
			str = mw.text.decode(str, true)

	-- Search for the leading bytes that introduce the UTF-8 encoding of the		-- Search for the leading bytes that introduce the UTF-8 encoding of the
	-- code points U+0340-U+10FFFF. If they are not found and there is at least		-- code points U+0340-U+10FFFF. If they are not found and there is at least

← Older revision		Revision as of 17:52, 14 March 2020
Line 61:		Line 61:
	{ 0x00, 0x1F, "<control-%04X>" }, -- C0 control characters		{ 0x00, 0x1F, "<control-%04X>" }, -- C0 control characters
	{ 0x7F, 0x9F, "<control-%04X>" }, -- DEL and C1 control characters		{ 0x7F, 0x9F, "<control-%04X>" }, -- DEL and C1 control characters
	{ 0x3400, ~~0x4DB5~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension A		{ 0x3400, 0x4DBF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension A
	{ 0x4E00, ~~0x9FEF~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph		{ 0x4E00, 0x9FFC, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph
	{ 0xAC00, 0xD7A3, function (codepoint) -- Hangul Syllables		{ 0xAC00, 0xD7A3, function (codepoint) -- Hangul Syllables
	local Hangul_data = loader.Hangul		local Hangul_data = loader.Hangul
Line 80:		Line 80:
	{ 0xF900, 0xFA6D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },		{ 0xF900, 0xFA6D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
	{ 0xFA70, 0xFAD9, "CJK COMPATIBILITY IDEOGRAPH-%04X" },		{ 0xFA70, 0xFAD9, "CJK COMPATIBILITY IDEOGRAPH-%04X" },
	{ 0x17000, ~~0x187F1~~, "TANGUT IDEOGRAPH-%04X" }, -- Tangut		{ 0x17000, 0x187F7, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph
	{ 0x18800, ~~0x18AF2~~, function (codepoint)		{ 0x18800, 0x18AFF, function (codepoint)
	return ("TANGUT COMPONENT-%03d"):format(codepoint - 0x187FF)		return ("TANGUT COMPONENT-%03d"):format(codepoint - 0x187FF)
	end },		end },
			{ 0x18D00, 0x18D08, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph Supplement
	{ 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu		{ 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu
	{ 0x20000, ~~0x2A6D6~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B		{ 0x20000, 0x2A6DD, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B
	{ 0x2A700, 0x2B734, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C		{ 0x2A700, 0x2B734, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C
	{ ~~0x2A740~~, 0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D		{ 0x2B740, 0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D
	{ 0x2B820, 0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E		{ 0x2B820, 0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E
	{ 0x2CEB0, 0x2EBE0, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension F		{ 0x2CEB0, 0x2EBE0, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension F
Line 95:		Line 96:
	return ("VARIATION SELECTOR-%d"):format(codepoint - 0xE0100 + 17)		return ("VARIATION SELECTOR-%d"):format(codepoint - 0xE0100 + 17)
	end},		end},
			{ 0x30000, 0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G
	{ 0xF0000, 0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use		{ 0xF0000, 0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use
	{ 0x100000, 0x10FFFD, "<private-use-%04X>" } -- Plane 16 Private Use		{ 0x100000, 0x10FFFD, "<private-use-%04X>" } -- Plane 16 Private Use
Line 173:		Line 175:
	[ 1] = "Supplementary Multilingual Plane";		[ 1] = "Supplementary Multilingual Plane";
	[ 2] = "Supplementary Ideographic Plane";		[ 2] = "Supplementary Ideographic Plane";
			[ 3] = "Tertiary Ideographic Plane";
	[14] = "Supplementary Special-purpose Plane";		[14] = "Supplementary Special-purpose Plane";
	[15] = "Supplementary Private Use Area-A";		[15] = "Supplementary Private Use Area-A";