Module:Unicode convert: Difference between revisions

Module documentation[view] [edit] [history] [purge]

Usage

Converts Unicode character codes, always given in hexadecimal, to their UTF-8 or UTF-16 representation in upper-case hex or decimal. Can also reverse this for UTF-8. The UTF-16 form will accept and pass through unpaired surrogates e.g. {{#invoke:Unicode convert|getUTF8|D835}} → D835. The reverse function fromUTF8 accepts multiple characters, and can have both input and output set to decimal.

When using from another module, you may call these functions as e.g. unicodeConvert.getUTF8{ args = {'1F345'} }, without a proper frame object.

To find the character code of a given symbol (in decimal), use e.g. {{#invoke:ustring|codepoint|\🐱}} → 128049.

Code	Output
{{#invoke:Unicode convert|getUTF8|1F345}}	F0 9F 8D 85
{{#invoke:Unicode convert|getUTF8|1F345|base=dec}}	240 159 141 133
{{#invoke:Unicode convert|fromUTF8|F0 9F 8D 85}}
{{#invoke:Unicode convert|fromUTF8|240 159 141 133|base=dec|basein=dec}}
{{#invoke:Unicode convert|getUTF16|1F345}}	D83C DF45
{{#invoke:Unicode convert|getUTF16|1F345|base=dec}}	55356 57157

See also

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

local p = {}

p.getUTF8 = function (frame)
	local ch = mw.ustring.char(tonumber(frame.args[1] or '0', 16) or 0)
	local bytes = {mw.ustring.byte(ch, 1, -1)}
	local format = ({ -- TODO reduce the number of options.
		['10'] = '%d',
		dec = '%d',
		LChex = '%02x',
		LC16 = '%02x',
		['Lower Case Hex'] = '%02x',
		['Lower Case 16'] = '%02x'
	})[frame.args['base']] or '%02X'
	for i = 1, #bytes do
		bytes[i] = format:format(bytes[i])
	end
	return table.concat(bytes, ' ')
end

p.getUTF16 = function (frame)
	local codepoint = tonumber(frame.args[1] or '0', 16) or 0
	local format = ({ -- TODO reduce the number of options.
		['10'] = '%d',
		dec = '%d',
		LChex = '%04x',
		LC16 = '%04x',
		['Lower Case Hex'] = '%04x',
		['Lower Case 16'] = '%04x'
	})[frame.args['base']] or '%04X'
	if codepoint <= 0xFFFF then -- NB this also returns lone surrogate characters
		return format:format(codepoint)
	elseif codepoint > 0x10FFFF then -- There are no codepoints above this
		return ''
	end
	codepoint = codepoint - 0x10000
	bit32 = require('bit32')
	return (format .. ' ' .. format):format(
		bit32.rshift(codepoint, 10) + 0xD800,
		bit32.band(codepoint, 0x3FF) + 0xDC00)
end

return p