Sware at 21:33, 16 November 2025

2025-11-16T21:33:18Z

← Older revision		Revision as of 21:33, 16 November 2025
Line 1:		Line 1:
			local math_module = "Module:math"

	local char = string.char		local char = string.char
	local ~~concat~~ = ~~table~~.~~concat~~		local error = error
			local format = string.format
			local pcall = pcall
			local select = select
	local tonumber = tonumber		local tonumber = tonumber
			local type = type

			local function to_hex(...)
			to_hex = require(math_module).to_hex
			return to_hex(...)
			end

	local function ~~err~~(cp)		local function codepoint_err(cp, i)
	error(~~"Codepoint " ..~~ cp .. " ~~is out of range: codepoints must be~~ between 0x0 and 0x10FFFF.", 2)		-- Throw error: to_hex can only return integers, so only show the bad value
			-- if it can be converted into something that looks like a codepoint.
			local success, result = pcall(to_hex, cp, true)
			error(format(
			"bad argument #%d to 'string/char' (codepoint between 0x0 and 0x10FFFF expected%s)",
			i, success and "; got " .. result or ""),
			i + 3)
	end		end

	local function utf8_char(cp)		local function utf8_char(n, i, v, ...)
	cp = tonumber(cp)		local cp = tonumber(v)
	if cp ~~< 0~~ then		if cp == nil then
	~~err~~("~~-0x" ..~~ ("%X")~~:format~~(-cp ~~+ 1)~~)		error(format("bad argument #%d to 'char' (number expected; got %s)", i, type(v)), i + 2)
			elseif cp < 0 then
			codepoint_err(cp, i)
	elseif cp < 0x80 then		elseif cp < 0x80 then
	return ~~char~~(cp)		if i == n then
			return cp
			end
			return cp, utf8_char(n, i + 1, ...)
	elseif cp < 0x800 then		elseif cp < 0x800 then
	return ~~char(~~		if i == n then
	0xC0 + cp / 0x40,		return 0xC0 + cp / 0x40,
	0x80 + cp % 0x40		0x80 + cp % 0x40
	)		end
			return 0xC0 + cp / 0x40,
			0x80 + cp % 0x40,
			utf8_char(n, i + 1, ...)
	elseif cp < 0x10000 then		elseif cp < 0x10000 then
	~~if cp >= 0xD800 and cp < 0xE000 then~~		-- Don't return "?" for surrogates, like mw.ustring.char does, as they
	return "?" -- mw.ustring.char ~~returns "?" for surrogates~~.		-- have legitimate uses (e.g. in JSON).
			if i == n then
			return 0xE0 + cp / 0x1000,
			0x80 + cp / 0x40 % 0x40,
			0x80 + cp % 0x40
	end		end
	return ~~char(~~		return 0xE0 + cp / 0x1000,
	0xE0 + cp / 0x1000,
	0x80 + cp / 0x40 % 0x40,		0x80 + cp / 0x40 % 0x40,
	0x80 + cp % 0x40		0x80 + cp % 0x40,
	)		utf8_char(n, i + 1, ...)
	elseif cp < 0x110000 then		elseif cp < 0x110000 then
	return ~~char(~~		if i == n then
	0xF0 + cp / 0x40000,		return 0xF0 + cp / 0x40000,
			0x80 + cp / 0x1000 % 0x40,
			0x80 + cp / 0x40 % 0x40,
			0x80 + cp % 0x40
			end
			return 0xF0 + cp / 0x40000,
	0x80 + cp / 0x1000 % 0x40,		0x80 + cp / 0x1000 % 0x40,
	0x80 + cp / 0x40 % 0x40,		0x80 + cp / 0x40 % 0x40,
	0x80 + cp % 0x40		0x80 + cp % 0x40,
	)		utf8_char(n, i + 1, ...)
	end		end
	~~err("0x" .. ("%X"):format~~(cp))		codepoint_err(cp, i)
	end		end

	return function(~~cp,~~ ...)		return function(...)
	if ... =~~= nil~~ then		local n = select("#", ...)
	return utf8_char(~~cp)~~		if n ~= 0 then
	~~end~~		return char(utf8_char(n, 1, ...))
	~~local ret = {cp~~, ...}
	~~for i = 1, #ret do~~
	~~ret[i] = utf8_char(ret[i]~~)
	end		end
	~~return concat(ret)~~
	end		end

Sware: Created page with "local char = string.char local concat = table.concat local tonumber = tonumber local function err(cp) error("Codepoint " .. cp .. " is out of range: codepoints must be between 0x0 and 0x10FFFF.", 2) end local function utf8_char(cp) cp = tonumber(cp) if cp < 0 then err("-0x" .. ("%X"):format(-cp + 1)) elseif cp < 0x80 then return char(cp) elseif cp < 0x800 then return char( 0xC0 + cp / 0x40, 0x80 + cp % 0x40 ) elseif cp < 0x10000 then if cp >= 0xD8..."

2024-07-02T22:33:44Z

Created page with "local char = string.char local concat = table.concat local tonumber = tonumber local function err(cp) error("Codepoint " .. cp .. " is out of range: codepoints must be between 0x0 and 0x10FFFF.", 2) end local function utf8_char(cp) cp = tonumber(cp) if cp < 0 then err("-0x" .. ("%X"):format(-cp + 1)) elseif cp < 0x80 then return char(cp) elseif cp < 0x800 then return char( 0xC0 + cp / 0x40, 0x80 + cp % 0x40 ) elseif cp < 0x10000 then if cp >= 0xD8..."

New page

local char = string.char
local concat = table.concat
local tonumber = tonumber

local function err(cp)
error("Codepoint " .. cp .. " is out of range: codepoints must be between 0x0 and 0x10FFFF.", 2)
end

local function utf8_char(cp)
cp = tonumber(cp)
if cp < 0 then
err("-0x" .. ("%X"):format(-cp + 1))
elseif cp < 0x80 then
return char(cp)
elseif cp < 0x800 then
return char(
0xC0 + cp / 0x40,
0x80 + cp % 0x40
)
elseif cp < 0x10000 then
if cp >= 0xD800 and cp < 0xE000 then
return "?" -- mw.ustring.char returns "?" for surrogates.
end
return char(
0xE0 + cp / 0x1000,
0x80 + cp / 0x40 % 0x40,
0x80 + cp % 0x40
)
elseif cp < 0x110000 then
return char(
0xF0 + cp / 0x40000,
0x80 + cp / 0x1000 % 0x40,
0x80 + cp / 0x40 % 0x40,
0x80 + cp % 0x40
)
end
err("0x" .. ("%X"):format(cp))
end

return function(cp, ...)
if ... == nil then
return utf8_char(cp)
end
local ret = {cp, ...}
for i = 1, #ret do
ret[i] = utf8_char(ret[i])
end
return concat(ret)
end

Module:string/char - Revision history

Sware at 21:33, 16 November 2025