Difference between revisions of "Module:Sandbox/Erutuon/UTF-8"

From blackwiki
Jump to navigation Jump to search
blackwiki>Erutuon
(highlighting non-codepoint parts of encoding)
blackwiki>Erutuon
(00-7F)
Line 40: Line 40:
  
 
local function markDigits(byteTable)
 
local function markDigits(byteTable)
local tag1 = { '<span style="color: deeppink;>', '</span>' }
+
-- ASCII
local tag2 = { '<span style="color: chocolate;>', '</span>' }
+
local tag1 = { '<span style="color: darkgray;">', '</span>' }
local last
+
-- leading bytes
 +
local tag2 = { '<span style="color: deeppink;">', '</span>' }
 +
-- continuation bytes
 +
local tag3 = { '<span style="color: chocolate;">', '</span>' }
 
local onesCount = 0
 
local onesCount = 0
 
for i, digit in ipairs(byteTable) do
 
for i, digit in ipairs(byteTable) do
 
if digit == 1 then
 
if digit == 1 then
 
onesCount = onesCount + 1
 
onesCount = onesCount + 1
last = digit
 
 
else
 
else
 
local tag
 
local tag
if onesCount > 1 then
+
-- ASCII (0x00 - 0x7F)
 +
if onesCount == 0 then
 
tag = tag1
 
tag = tag1
 +
 +
-- continuation bytes
 +
elseif onesCount == 1 then
 +
tag = tag3
 +
 +
-- leading bytes
 
else
 
else
 
tag = tag2
 
tag = tag2
Line 101: Line 110:
  
 
function p.show(frame)
 
function p.show(frame)
local str = frame.args[1] or "ᾰ̓τῑμᾰ́ζω"
+
local str = frame.args[1] or "abc πρᾶγμᾰ"
 
return printBytes(str) .. "\n" .. print(makeCharByteTables(str))
 
return printBytes(str) .. "\n" .. print(makeCharByteTables(str))
 
end
 
end
  
 
return p
 
return p

Revision as of 09:58, 17 September 2017

An experiment with printing binary digit representations of characters.

Usage

01100001 01111110 11000010 10100001 11000011 10100001 11001110 10110001 11100001 10111110 10110000 11110000 10100000 10000000 10000000

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

-- 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 markDigits(byteTable)
	-- ASCII
	local tag1 = { '<span style="color: darkgray;">', '</span>' }
	-- leading bytes
	local tag2 = { '<span style="color: deeppink;">', '</span>' }
	-- continuation bytes
	local tag3 = { '<span style="color: chocolate;">', '</span>' }
	local onesCount = 0
	for i, digit in ipairs(byteTable) do
		if digit == 1 then
			onesCount = onesCount + 1
		else
			local tag
			-- ASCII (0x00 - 0x7F)
			if onesCount == 0 then
				tag = tag1
			
			-- continuation bytes
			elseif onesCount == 1 then
				tag = tag3
			
			-- leading bytes
			else
				tag = tag2
			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)
	local output = { '{| class="wikitable"'}
	for i, char in ipairs(chars) do
		table.insert(output, "| " .. char)
	end
	table.insert(output, "|-")
	for i, byteString in ipairs(bytes) do
		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 printBytes(str) .. "\n" .. print(makeCharByteTables(str))
end

return p