Module:Unicode convert - Revision history

GKFX: Add fromUTF8 function

2021-04-11T13:12:30Z

Add fromUTF8 function

@@ Line 1: / Line 1: @@
 local p = {}
 p.getUTF8 = function (frame)
@@ Line 30: / Line 34: @@
 		bit32.rshift(codepoint, 10) + 0xD800,
 		bit32.band(codepoint, 0x3FF) + 0xDC00)
 end

MusikBot II: Protected "Module:Unicode convert": High-risk template or module (more info) ([Edit=Require autoconfirmed or confirmed access] (indefinite))

2021-04-10T17:59:47Z

Protected "Module:Unicode convert": High-risk template or module (more info) ([Edit=Require autoconfirmed or confirmed access] (indefinite))

← Previous revision	Revision as of 17:59, 10 April 2021
(No difference)

GKFX: Remove lowercase hex option - it is unused

2021-04-10T15:43:06Z

Remove lowercase hex option - it is unused

← Previous revision		Revision as of 15:43, 10 April 2021
Line 4:		Line 4:
	local ch = mw.ustring.char(tonumber(frame.args[1] or '0', 16) or 0)		local ch = mw.ustring.char(tonumber(frame.args[1] or '0', 16) or 0)
	local bytes = {mw.ustring.byte(ch, 1, -1)}		local bytes = {mw.ustring.byte(ch, 1, -1)}
	local format = ({ ~~-- TODO reduce the number of options.~~		local format = ({
	['10'] = '%d',		['10'] = '%d',
	dec = '%d',		dec = '%d'
	LChex = '%02x',
	LC16 = '%02x',
	['Lower Case Hex'] = '%02x',
	['Lower Case 16'] = '%02x'
	})[frame.args['base']] or '%02X'		})[frame.args['base']] or '%02X'
	for i = 1, #bytes do		for i = 1, #bytes do
Line 22:		Line 18:
	local format = ({ -- TODO reduce the number of options.		local format = ({ -- TODO reduce the number of options.
	['10'] = '%d',		['10'] = '%d',
	dec = '%d',		dec = '%d'
	LChex = '%04x',
	LC16 = '%04x',
	['Lower Case Hex'] = '%04x',
	['Lower Case 16'] = '%04x'
	})[frame.args['base']] or '%04X'		})[frame.args['base']] or '%04X'
	if codepoint <= 0xFFFF then -- NB this also returns lone surrogate characters		if codepoint <= 0xFFFF then -- NB this also returns lone surrogate characters

GKFX: Better match originals in case of no input

2021-04-10T09:15:29Z

Better match originals in case of no input

← Previous revision		Revision as of 09:15, 10 April 2021
Line 2:		Line 2:

	p.getUTF8 = function (frame)		p.getUTF8 = function (frame)
	local ch = mw.ustring.char(tonumber(frame.args[1], 16))		local ch = mw.ustring.char(tonumber(frame.args[1] or '0', 16) or 0)
	local bytes = {mw.ustring.byte(ch, 1, -1)}		local bytes = {mw.ustring.byte(ch, 1, -1)}
	local format = ({ -- TODO reduce the number of options.		local format = ({ -- TODO reduce the number of options.
Line 19:		Line 19:

	p.getUTF16 = function (frame)		p.getUTF16 = function (frame)
	local codepoint = tonumber(frame.args[1], 16)		local codepoint = tonumber(frame.args[1] or '0', 16) or 0
	local format = ({ -- TODO reduce the number of options.		local format = ({ -- TODO reduce the number of options.
	['10'] = '%d',		['10'] = '%d',

GKFX: Create a module to replace Template:UTF-8 and Template:UTF-16

2021-04-09T19:28:14Z

Create a module to replace Template:UTF-8 and Template:UTF-16

New page

local p = {}

p.getUTF8 = function (frame)
local ch = mw.ustring.char(tonumber(frame.args[1], 16))
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], 16)
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