Module:Unicode data/derived core properties - Revision history

Drmccreedy: Update for Unicode 14.0

2021-09-21T18:22:34Z

Update for Unicode 14.0

← Previous revision		Revision as of 18:22, 21 September 2021
Line 14:		Line 14:
	{ 0x0115F, 0x01160 },		{ 0x0115F, 0x01160 },
	{ 0x017B4, 0x017B5 },		{ 0x017B4, 0x017B5 },
	{ 0x0180B, ~~0x0180E~~ },		{ 0x0180B, 0x0180F },
	{ 0x0200B, 0x0200F },		{ 0x0200B, 0x0200F },
	{ 0x0202A, 0x0202E },		{ 0x0202A, 0x0202E },

Drmccreedy: condense range

2019-09-17T21:10:51Z

condense range

← Previous revision		Revision as of 21:10, 17 September 2019
Line 9:		Line 9:
	[0x0FEFF] = true,		[0x0FEFF] = true,
	[0x0FFA0] = true,		[0x0FFA0] = true,
	[0xE0000] = true,
	[0xE0001] = true,
	},		},

Line 24:		Line 22:
	{ 0x1BCA0, 0x1BCA3 },		{ 0x1BCA0, 0x1BCA3 },
	{ 0x1D173, 0x1D17A },		{ 0x1D173, 0x1D17A },
	{ ~~0xE0002~~, 0xE0FFF },		{ 0xE0000, 0xE0FFF },
	},		},
	}		}

Erutuon: I prefer underscores to camel case, and that's the convention in most of the Unicode data modules

2019-09-16T09:46:37Z

I prefer underscores to camel case, and that's the convention in most of the Unicode data modules

← Previous revision		Revision as of 09:46, 16 September 2019
Line 1:		Line 1:
	local data = {}		local data = {}

	data.~~defaultIgnorable~~ = {		data.default_ignorable = {
	singles = {		singles = {
	[0x000AD] = true,		[0x000AD] = true,

Erutuon: replace with output

2019-09-16T09:44:39Z

replace with output

@@ Line 1: / Line 1: @@
 local data = {}
 data.defaultIgnorable = {
 	singles = {
 	},
 	ranges = {
 	},
+}
 return data

Erutuon: generate "default ignorable" data table

2019-09-16T09:41:12Z

generate "default ignorable" data table

New page

local p = {}

function p.show(frame)
local page = frame.args[1] or "User:Erutuon/Unicode/DerivedCoreProperties.txt"
local text = assert(mw.title.new(page):getContent())
local defaultIgnorable = text
:match("Derived Property: Default_Ignorable_Code_Point.-(%f[^\n]%x%x%x%x.-)%s*\n# Total code points")
local singles, ranges = {}, {}
for codePoint1, codePoint2 in defaultIgnorable:gmatch("%f[^\n%z](%x+)%.?%.?(%x*)") do
codePoint1, codePoint2 = tonumber(codePoint1, 16), tonumber(codePoint2, 16)
local lastRange = ranges[#ranges]
if lastRange and lastRange[2] == codePoint1 - 1 then
lastRange[2] = codePoint2 or codePoint1
else
if not codePoint2 then
singles[codePoint1] = true
else
table.insert(ranges, { codePoint1, codePoint2 })
end
end
end

local template = [[
local data = {}

data.defaultIgnorable = {
singles = {
...
},

ranges = {
...
},
}

return data
]]

local Array = require "Module:array"
local printedRanges = Array()
for _, range in ipairs(ranges) do
local low, high, script_code = unpack(range)
printedRanges:insert(('\t\t{ 0x%05X, 0x%05X },'):format(low, high))
end

local printedSingles = Array()
for codepoint in require 'Module:TableTools'.sortedPairs(singles) do
printedSingles:insert(('\t\t[0x%05X] = true,'):format(codepoint))
end

local data = template
:gsub('%.%.%.', printedSingles:concat('\n'), 1)
:gsub('%.%.%.', printedRanges:concat('\n'), 1)

return mw.getCurrentFrame():extensionTag{
name = "syntaxhighlight",
content = data,
args = { lang = "lua" }
}
end

return p