Module:Unicode data/category

Module documentationviewedithistorypurge

Unicode General Category data generated by Module:Unicode data/category/make from DerivedGeneralCategory.txt and PropertyValueAliases.txt in the Unicode Character Database. The category Cn (Unassigned) is omitted because it is the default for characters not assigned to another category.

The above documentation is transcluded from Module:Unicode data/category/doc. (edit | history)
Editors can experiment in this module's sandbox (create | mirror) and testcases (create) pages.
Subpages of this module.

-- [[:commons:Data:Unicode/data/category/singles.tab]]
-- [[:commons:Data:Unicode/data/category/ranges.tab]]
-- [[:commons:Data:Unicode/data/category/names.tab]]

local function get_result()
	local write_index
	local result={}
	
	-- singles
	result.singles={}
	local data=mw.ext.data.get("Unicode/data/category/singles.tab")
	for index, cols in ipairs(data.data) do
		if cols[1] and cols[2]  then
			if cols[2] ~= "Cn" then
				result.singles[tonumber(cols[1], 16)]=cols[2]
			end
		end
	end
	
	-- ranges
	data=mw.ext.data.get("Unicode/data/category/ranges.tab")
	write_index=1
	result.ranges={}
	for index, cols in ipairs(data.data) do
		if cols[1] and cols[2] and cols[3] then
			if cols[3] ~= "Cn" then
				result.ranges[write_index]={tonumber(cols[1], 16), tonumber(cols[2], 16), cols[3]}
				write_index=write_index+1
			end
		end
	end

	-- long_names
	data=mw.ext.data.get("Unicode/data/category/names.tab")
	result.long_names={}
	for index, cols in ipairs(data.data) do
		if cols[1] and cols[2] then
			result.long_names[cols[1]]=cols[2]
		end
	end
	
	return result
end

return get_result()