Module:Sandbox/Erutuon/UTF-8

From blackwiki
< Module:Sandbox‎ | Erutuon
Revision as of 05:36, 18 September 2017 by blackwiki>Erutuon (for what do not belong to any of the categories (and may be invalid?))
Jump to navigation Jump to search

An experiment with printing binary digit representations of characters.

Usage

a ~ ¡ á α 𠀀
01100001 01111110 11000010 10100001 11000011 10100001 11001110 10110001 11100001 10111110 10110000 11110000 10100000 10000000 10000000



local p = {}

local bit = require("bit32")
local band = bit.band
local rshift = bit.rshift

function table.forEach(t, func)
	for i, item in ipairs(t) do
		func(item)
	end
end

local function setMt(arr)
	setmetatable(arr, { __index =  table })
end

-- Converts a string representing a number in binary base to a Lua number.
local function binary(stringBinary)
	return tonumber(stringBinary, 2)
end

-- Find the digit at a certain position in a byte.
local function digitAt(number, index)
	if type(number) == "string" then
		number = binary(number)
	end
	return band(rshift(number, 8 - index), 1)
end

-- Returns a table containing bits in a byte, from highest to lowest.
local function getBits(byte)
	local t = {}
	for bit = 8, 1, -1 do
		t[bit] = band(byte, 1)
		byte = rshift(byte, 1)
	end
	return t
end

-- mw.log(table.concat(getBits(rshift(binary("11100001"), 8 - 3))))

-- Do something to each byte in a string; put the result in a table.
local function iterBytes(str, func)
	local out = {}
	for i = 1, #str do
		table.insert(out, func(string.byte(str, i)))
	end
	return out
end

local function makeTag(color)
	return { '<span style="color: ' .. color .. ';">', '</span>' }
end

-- Find leading digits marking ASCII, leading bytes, or continuation bytes,
-- else tag byte as red.
local function markDigits(byteTable)
	local onesCount = 0
	for i, digit in ipairs(byteTable) do
		if digit == 1 then
			onesCount = onesCount + 1
			if onesCount > 4 then
				local tag = makeTag("red")
				table.insert(byteTable, #byteTable, tag[2])
				table.insert(byteTable, 1, tag[1])
			end
		else
			local tag
			-- ASCII (0x00 - 0x7F)
			if onesCount == 0 then
				tag = makeTag("darkgray")
			
			-- continuation bytes
			elseif onesCount == 1 then
				tag = makeTag("chocolate")
			
			-- leading bytes
			else
				tag = makeTag("deeppink")
			end
			table.insert(byteTable, i + 1, tag[2])
			table.insert(byteTable, 1, tag[1])
			return byteTable
		end
	end
	return byteTable
end

local function printBytes(str)
	return table.concat(
		iterBytes(
			str,
			function(byte)
				return table.concat(markDigits(getBits(byte)))
			end
		),
		" "
	)
end

local function makeCharByteTables(str)
	local chars = {}
	local bytes = {}
	local uLen = mw.ustring.len(str)
	for i = 1, uLen do
		local char = mw.ustring.sub(str, i, i)
		table.insert(chars, char)
		table.insert(bytes, printBytes(char))
	end
	return chars, bytes
end

local function print(chars, bytes)
	setMt(chars)
	setMt(bytes)
	local output = { '{| class="wikitable"'}
	chars:forEach(
		function(char)
			table.insert(output, "| " .. char)
		end
	)
	table.insert(output, "|-")
	bytes:forEach(
		function(byteString)
			table.insert(output, "| <code>" .. byteString .. "<code>")
		end
	)
	table.insert(output, "|}")
	return table.concat(output, "\n")
end

function p.show(frame)
	local str = frame.args[1] or "abc πρᾶγμᾰ"
	return print(makeCharByteTables(str))
end

return p