Module:Unicode data/sandbox - Revision history

Northern Moonlight at 03:43, 1 January 2025

2025-01-01T03:43:32Z

← Previous revision		Revision as of 03:43, 1 January 2025
Line 553:		Line 553:

	function p.lookup_kCantonese(codepoint)		function p.lookup_kCantonese(codepoint)
	local data = loader[('Unihan/kCantonese/%02X'):format(floor(codepoint / ~~0x10000~~))]		local data = loader[('Unihan/kCantonese/%02X'):format(floor(codepoint / 0x1000))]
	if data then		if data then
	return data[codepoint]		return data[codepoint]

2025-01-01T03:41:20Z

← Previous revision		Revision as of 03:41, 1 January 2025
Line 552:		Line 552:
	end		end

	p.lookup_kCantonese ~~= memo_lookup~~(		function p.lookup_kCantonese(codepoint)
	"Unihan/kCantonese",		local data = loader[('Unihan/kCantonese/%02X'):format(floor(codepoint / 0x10000))]
			if data then
	function (codepoint, cantonese)
	return ~~cantonese~~		return data[codepoint]
	end		end
			end
	)

	return p		return p

2025-01-01T03:37:23Z

test

← Previous revision		Revision as of 03:37, 1 January 2025
Line 551:		Line 551:
	end		end
	end		end

			p.lookup_kCantonese = memo_lookup(
			"Unihan/kCantonese",
			function (codepoint, cantonese)
			return cantonese
			end
			)

	return p		return p

2025-01-01T03:15:33Z

sync

← Previous revision		Revision as of 03:15, 1 January 2025
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, 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

2024-04-21T15:20:45Z

Fix

← Previous revision		Revision as of 15:20, 21 April 2024
Line 137:		Line 137:
	-- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8		-- https://www.unicode.org/versions/Unicode11.0.0/ch04.pdf, section 4.8
	function p.lookup_name(codepoint)		function p.lookup_name(codepoint)
	if is_noncharacter(codepoint) then		if p.is_noncharacter(codepoint) then
	return ("<noncharacter-%04X>"):format(codepoint)		return ("<noncharacter-%04X>"):format(codepoint)

	end		end

2024-04-21T15:20:29Z

Split noncharacter

← Previous revision		Revision as of 15:20, 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 is_noncharacter(codepoint) then
	return ("<noncharacter-%04X>"):format(codepoint)		return ("<noncharacter-%04X>"):format(codepoint)

	end		end

2023-11-20T21:13:02Z

← Previous revision		Revision as of 21:13, 20 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 = {

2023-11-20T21:12:24Z

@@ Line 87: / Line 87: @@
 	{  0x1B170,  0x1B2FB, "NUSHU CHARACTER-%04X" }, -- Nushu
 	{  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
 	{  0x2B820,  0x2CEA1, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension E
@@ Line 97: / Line 97: @@
 	end},
 	{  0x30000,  0x3134A, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension G
 	{  0xF0000,  0xFFFFD, "<private-use-%04X>" }, -- Plane 15 Private Use
 	{ 0x100000, 0x10FFFD, "<private-use-%04X>" }  -- Plane 16 Private Use
@@ Line 344: / Line 346: @@
 	end,
 )
 function p.add_dotted_circle(str)
@@ Line 490: / Line 482: @@
 	return result
 end
 local function get_codepoint(args, arg)

2022-06-01T06:47:20Z

← Previous revision		Revision as of 06:47, 1 June 2022
Line 345:		Line 345:
	0)		0)

	-- Same data as is_combining, but return combining_class not T/F conversion		-- TEST 1Jun2022 Same data as is_combining, but return combining_class not T/F conversion
	-- Return blank for none		-- Return blank for none
	-- Per https://www.unicode.org/reports/tr44/#Canonical_Combining_Class_Values		-- Per https://www.unicode.org/reports/tr44/#Canonical_Combining_Class_Values
	p.~~lookup_combining~~ = memo_lookup(		p.lookup_combiningclass = memo_lookup(
	"combining",		"combining",
	function (codepoint, combining_class)		function (codepoint, combining_class)
	return combining_class ~~and combining_class ~= 0 or ''~~		return combining_class
	end,		end,
	99)		99)

2022-06-01T06:37:13Z

p.lookup_combining

@@ Line 344: / Line 344: @@
 	end,
 )
 function p.add_dotted_circle(str)