Module:Unicode data - Revision history

Marie: 1 revision imported

2026-03-05T07:14:32Z

1 revision imported

← Older revision		Revision as of 02:14, 5 March 2026
(No difference)

wikipedia>Drmccreedy: Add Khitan Small Script (which was omitted so showed as "reserved" in the Unichar template), condense contiguous ranges

2025-09-16T02:46:49Z

Add Khitan Small Script (which was omitted so showed as "reserved" in the Unichar template), condense contiguous ranges

← Older revision		Revision as of 21:46, 15 September 2025
Line 58:		Line 58:
	-- Unicode Specification:		-- Unicode Specification:
	-- https://www.unicode.org/versions/Unicode11.0.0/ch03.pdf		-- https://www.unicode.org/versions/Unicode11.0.0/ch03.pdf
		+	-- binary_range_search assumes these are ordered by codepoint. Do not place them in a random order!
	local name_hooks = {		local name_hooks = {
	{ 0x00, 0x1F, "<control-%04X>" }, -- C0 control characters		{ 0x00, 0x1F, "<control-%04X>" }, -- C0 control characters
Line 77:		Line 78:
	{ 0xD800, 0xDFFF, "<surrogate-%04X>" },		{ 0xD800, 0xDFFF, "<surrogate-%04X>" },
	{ 0xE000, 0xF8FF, "<private-use-%04X>" }, -- Private Use		{ 0xE000, 0xF8FF, "<private-use-%04X>" }, -- Private Use
		+
	-- CJK Compatibility Ideographs		-- CJK Compatibility Ideographs
	{ 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~~, ~~0x187F7~~, ~~"TANGUT~~ ~~IDEOGRAPH-%04X" },~~ -- ~~Tangut~~ ~~Ideograph~~	+	{ 0xFE00, 0xFE0F, function (codepoint) -- Variation Selectors
		+	return ("VARIATION SELECTOR-%d"):format(codepoint - 0xFE00 + 1)
		+	end},
		+	{ 0x13460, 0x143FA, "EGYPTIAN HIEROGLYPH-%04X" }, -- Egyptian Hieroglyphs Extended-A
		⚫	{ 0x17000, 0x187FF, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph
	{ 0x18800, 0x18AFF, 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~~	+	{ 0x18B00, 0x18CD5, "KHITAN SMALL SCRIPT CHARACTER-%04X" }, -- Khitan Small Script
		+	{ 0x18CFF, 0x18CFF, "KHITAN SMALL SCRIPT CHARACTER-%04X" }, -- Khitan Small Script
		⚫	{ 0x18D00, 0x18D1E, "TANGUT IDEOGRAPH-%04X" }, -- Tangut Ideograph Supplement
		+	{ 0x18D80, 0x18DF2, function (codepoint)
		+	return ("TANGUT COMPONENT-%03d"):format(codepoint - 0x18A7F)
		+	end },
	{ 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, ~~0x2B739~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C	+	{ 0x2A700, 0x2B81D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension C, D
−	{ ~~0x2B740~~, ~~0x2B81D~~, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension D	+	{ 0x2B820, 0x2CEAD, "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
		⚫	{ 0x2EBF0, 0x2EE5D, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension I
−	-- CJK Compatibility Ideographs Supplement (Supplementary Ideographic Plane)
−	{ 0x2F800, 0x2FA1D, "CJK COMPATIBILITY IDEOGRAPH-%04X" },	+	{ 0x2F800, 0x2FA1D, "CJK COMPATIBILITY IDEOGRAPH-%04X" }, -- CJK Compatibility Ideographs Supplement (Supplementary Ideographic Plane)
		⚫	{ 0x30000, 0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G
		+	{ 0x31350, 0x33479, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension H, J
	{ 0xE0100, 0xE01EF, function (codepoint) -- Variation Selectors Supplement		{ 0xE0100, 0xE01EF, function (codepoint) -- Variation Selectors Supplement
	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~~
⚫	{ ~~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 440:		Line 449:

	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 459:
	elseif not (script == "Zyyy" or script == "Zinh"		elseif not (script == "Zyyy" or script == "Zinh"
	or script == "Zzzz") then		or script == "Zzzz") then
		+	return false, i -- abandon as not Latn; identify the offending character's position
−	return false
	end		end
	end		end

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

Line 547:		Line 558:
	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

Rox: 1 revision imported

2024-08-23T18:30:51Z

1 revision imported

← Older revision		Revision as of 13:30, 23 August 2024
(No difference)

Wikipedia>Pppery: Split noncharacter per request

2024-04-21T15:21:55Z

Split noncharacter per request

← Older revision		Revision as of 10:21, 21 April 2024
Line 126:		Line 126:
	--]]		--]]

		⚫	function p.is_noncharacter(codepoint)
⚫	-- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8
⚫	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
Line 162:		Line 167:
	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 174:
	end		end
	end		end
−	--]]

	local planes = {		local planes = {

Rox: 1 revision imported

2023-11-18T23:38:59Z

1 revision imported

← Older revision		Revision as of 18:38, 18 November 2023
(No difference)

Wikipedia>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 11:56, 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

Rox: 1 revision imported

2023-08-23T11:08:06Z

1 revision imported

← Older revision		Revision as of 06:08, 23 August 2023
(No difference)

Wikipedia>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)

Rox: 1 revision imported

2022-11-13T17:42:10Z

1 revision imported

← Older revision		Revision as of 12:42, 13 November 2022
(No difference)

Wikipedia>Drmccreedy: Update for Unicode v15.0

2022-09-17T03:28:33Z

Update for Unicode v15.0

← Older revision		Revision as of 22:28, 16 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