Module:Unicode data - Revision history

imported>Pppery: Add KCantonese lookup per request

2025-01-13T23:05:04Z

Add KCantonese lookup per request

← Older revision		Revision as of 23:05, 13 January 2025
Line 549:		Line 549:
	local codepoint = get_codepoint(frame.args, 2)		local codepoint = get_codepoint(frame.args, 2)
	return (func(codepoint)) -- Adjust to one result.		return (func(codepoint)) -- Adjust to one result.
			end
			end

			function p.lookup_kCantonese(codepoint)
			local data = loader[('Unihan/kCantonese/%02X'):format(floor(codepoint / 0x1000))]
			if data then
			return data[codepoint]
	end		end
	end		end

	return p		return p

imported>Trappist the monk: is_Latin(): when returning false as the first return value, also return character position of first non-Latn character as second return value; for use in {{lang}}, {{langx}}, {{transliteration}} error messaging;

2024-11-29T14:34:29Z

is_Latin(): when returning false as the first return value, also return character position of first non-Latn character as second return value; for use in {{lang}}, {{langx}}, {{transliteration}} error messaging;

← Older revision		Revision as of 14:34, 29 November 2024
Line 440:		Line 440:

	local Latn = false		local Latn = false
			local i = 0; -- indexer for use in error messages

	for codepoint in mw.ustring.gcodepoint(str) do		for codepoint in mw.ustring.gcodepoint(str) do
			i = i + 1; -- bump the indexer
	local script = lookup_script(codepoint)		local script = lookup_script(codepoint)

Line 448:		Line 450:
	elseif not (script == "Zyyy" or script == "Zinh"		elseif not (script == "Zyyy" or script == "Zinh"
	or script == "Zzzz") then		or script == "Zzzz") then
	return false		return false, i -- abandon as not Latn; identify the offending character's position
	end		end
	end		end

	return Latn		return Latn, (not Latn and i) or nil -- when <Latn> false, return offending charactor's position as second return value; nil else
	end		end

imported>Pppery: Split noncharacter per request

2024-04-21T15:21:55Z

Split noncharacter per request

← Older revision		Revision as of 15:21, 21 April 2024
Line 126:		Line 126:
	--]]		--]]

	~~-- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8~~		function p.is_noncharacter(codepoint)
	function p.~~lookup_name~~(codepoint)
	-- U+FDD0-U+FDEF and all code points ending in FFFE or FFFF are Unassigned		-- U+FDD0-U+FDEF and all code points ending in FFFE or FFFF are Unassigned
	-- (Cn) and specifically noncharacters:		-- (Cn) and specifically noncharacters:

	-- https://www.unicode.org/faq/private_use.html#nonchar4		-- https://www.unicode.org/faq/private_use.html#nonchar4
	if 0xFDD0 <= codepoint and (codepoint <= 0xFDEF		return 0xFDD0 <= codepoint and (codepoint <= 0xFDEF
	or floor(codepoint % 0x10000) >= 0xFFFE) then		or floor(codepoint % 0x10000) >= 0xFFFE)
			end

			-- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8
			function p.lookup_name(codepoint)
			if p.is_noncharacter(codepoint) then
	return ("<noncharacter-%04X>"):format(codepoint)		return ("<noncharacter-%04X>"):format(codepoint)
	end		end

imported>Pppery: Per edit request

2023-11-22T21:35:20Z

Per edit request

← Older revision		Revision as of 21:35, 22 November 2023
Line 162:		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 171:		Line 169:
	end		end
	end		end
	~~--]]~~

	local planes = {		local planes = {

imported>Drmccreedy: Add new block for Unicode v15.1

2023-09-12T16:56:59Z

Add new block for Unicode v15.1

← Older revision		Revision as of 16:56, 12 September 2023
Line 98:		Line 98:
	{ 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		{ 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

imported>Trappist the monk: +is_rtl_frame (frame) entry point to gain access to is_rtl (str) from an invoke;

2023-05-10T13:46:04Z

+is_rtl_frame (frame) entry point to gain access to is_rtl (str) from an invoke;

@@ Line 481: / Line 481: @@
 	return result
 end
 local function get_codepoint(args, arg)

imported>Drmccreedy: Update for Unicode v15.0

2022-09-17T03:28:33Z

Update for Unicode v15.0

← Older revision		Revision as of 03:28, 17 September 2022
Line 87:		Line 87:
	{ 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu		{ 0x1B170, 0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu
	{ 0x20000, 0x2A6DF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B		{ 0x20000, 0x2A6DF, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension B
	{ 0x2A700, ~~0x2B738~~, "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
	{ 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

imported>Drmccreedy: Update for Unicode 14.0

2021-09-21T18:56:34Z

Update for Unicode 14.0

← Older revision		Revision as of 18:56, 21 September 2021
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, 0x2B738, "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

imported>Drmccreedy: Unicode 13.0 release

2020-03-14T17:52:07Z

Unicode 13.0 release

imported>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";
	}		}

← 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";