mirror of https://github.com/bjc/prosody
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
45 lines
1.4 KiB
45 lines
1.4 KiB
-- Prosody IM
|
|
-- Copyright (C) 2008-2010 Matthew Wild
|
|
-- Copyright (C) 2008-2010 Waqas Hussain
|
|
--
|
|
-- This project is MIT/X11 licensed. Please see the
|
|
-- COPYING file in the source package for more information.
|
|
--
|
|
|
|
|
|
--- WARNING! ---
|
|
-- This file contains a mix of encodings below.
|
|
-- Many editors will unquestioningly convert these for you.
|
|
-- Please be careful :( (I recommend Scite)
|
|
---------------------------------
|
|
|
|
local gmatch = string.gmatch;
|
|
local t_concat, t_insert = table.concat, table.insert;
|
|
local to_byte, to_char = string.byte, string.char;
|
|
|
|
local function _latin1toutf8(str)
|
|
if not str then return str; end
|
|
local p = {};
|
|
for ch in gmatch(str, ".") do
|
|
ch = to_byte(ch);
|
|
if (ch < 0x80) then
|
|
t_insert(p, to_char(ch));
|
|
elseif (ch < 0xC0) then
|
|
t_insert(p, to_char(0xC2, ch));
|
|
else
|
|
t_insert(p, to_char(0xC3, ch - 64));
|
|
end
|
|
end
|
|
return t_concat(p);
|
|
end
|
|
|
|
function latin1toutf8()
|
|
local function assert_utf8(latin, utf8)
|
|
assert_equal(_latin1toutf8(latin), utf8, "Incorrect UTF8 from Latin1: "..tostring(latin));
|
|
end
|
|
|
|
assert_utf8("", "")
|
|
assert_utf8("test", "test")
|
|
assert_utf8(nil, nil)
|
|
assert_utf8("foobar.råkat.se", "foobar.rÃ¥kat.se")
|
|
end
|
|
|