Difference between revisions of "Module:Unicode data/derived core properties"

From blackwiki
Jump to navigation Jump to search
blackwiki>Erutuon
(generate "default ignorable" data table)
 
blackwiki>Erutuon
(replace with output)
Line 1: Line 1:
−
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 = {}
 
local data = {}
  
 
data.defaultIgnorable = {
 
data.defaultIgnorable = {
 
singles = {
 
singles = {
−
...
+
[0x000AD] = true,
 +
[0x0034F] = true,
 +
[0x0061C] = true,
 +
[0x03164] = true,
 +
[0x0FEFF] = true,
 +
[0x0FFA0] = true,
 +
[0xE0000] = true,
 +
[0xE0001] = true,
 
},
 
},
 
 
 
ranges = {
 
ranges = {
−
...
+
{ 0x0115F, 0x01160 },
 +
{ 0x017B4, 0x017B5 },
 +
{ 0x0180B, 0x0180E },
 +
{ 0x0200B, 0x0200F },
 +
{ 0x0202A, 0x0202E },
 +
{ 0x02060, 0x0206F },
 +
{ 0x0FE00, 0x0FE0F },
 +
{ 0x0FFF0, 0x0FFF8 },
 +
{ 0x1BCA0, 0x1BCA3 },
 +
{ 0x1D173, 0x1D17A },
 +
{ 0xE0002, 0xE0FFF },
 
},
 
},
 
}
 
}
  
 
return data
 
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
 

Revision as of 09:44, 16 September 2019

Contains data for the Default_Ignorable_Code_Point property, which is used by the function is_default_ignorable in Module:Unicode data/sandbox. Generated by Module:Unicode data/derived core properties/make from DerivedCoreProperties.txt in the Unicode Character Database. 

local data = {}

data.defaultIgnorable = {
	singles = {
		[0x000AD] = true,
		[0x0034F] = true,
		[0x0061C] = true,
		[0x03164] = true,
		[0x0FEFF] = true,
		[0x0FFA0] = true,
		[0xE0000] = true,
		[0xE0001] = true,
	},
	
	ranges = {
		{ 0x0115F, 0x01160 },
		{ 0x017B4, 0x017B5 },
		{ 0x0180B, 0x0180E },
		{ 0x0200B, 0x0200F },
		{ 0x0202A, 0x0202E },
		{ 0x02060, 0x0206F },
		{ 0x0FE00, 0x0FE0F },
		{ 0x0FFF0, 0x0FFF8 },
		{ 0x1BCA0, 0x1BCA3 },
		{ 0x1D173, 0x1D17A },
		{ 0xE0002, 0xE0FFF },
	},
}

return data
Retrieved from "https://blackwiki.org/index.php?title=Module:Unicode_data/derived_core_properties&oldid=448801"