/* utf-8 utf-16 convertion library.
*
/* copyright (c) 1999 masanao izumo iz@onicos.co.jp>
* 2007 ma bingyao andot@ujn.edu.cn>
* version: 2.1
* lastmodified: feb 25, 2007
* this library is free. you can redistribute it and/or modify it.
*/
/*
* interfaces:
* utf8 = utf16to8(utf16);
* utf16 = utf16to8(utf8);
*/
function utf16to8(str) {
if (str.match(/^[\x00-\x7f]*$/) != null) {
return str;
}
var out, i, j, len, c, c2;
out = [];
len = str.length;
for (i = 0, j = 0; i c = str.charcodeat(i);
if (c out[j] = str.charat(i);
}
else if (c out[j] = string.fromcharcode(0xc0 | (c >>> 6),
0x80 | (c & 0x3f));
}
else if (c || c > 0xdfff) {
out[j] = string.fromcharcode(0xe0 | (c >>> 12),
0x80 | ((c >>> 6) & 0x3f),
0x80 | (c & 0x3f));
}
else {
if (++i c2 = str.charcodeat(i);
if (c && 0xdc00 && c2 c = ((c & 0x03ff) 10 | (c2 & 0x03ff)) + 0x010000;
if (0x010000 && c out[j] = string.fromcharcode(0xf0 | ((c >>> 18) & 0x3f),
0x80 | ((c >>> 12) & 0x3f),
0x80 | ((c >>> 6) & 0x3f),
0x80 | (c & 0x3f));
}
else {
out[j] = '?';
}
}
else {
i--;
out[j] = '?';
}
}
else {
i--;
out[j] = '?';
}
}
}
return out.join('');
}
function utf8to16(str) {
if ((str.match(/^[\x00-\x7f]*$/) != null) ||
(str.match(/^[\x00-\xff]*$/) == null)) {
return str;
}
var out, i, j, len, c, c2, c3, c4, s;
out = [];
len = str.length;
i = j = 0;
while (i c = str.charcodeat(i++);
switch (c >> 4) {
case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
// 0xxx xxxx
out[j++] = str.charat(i - 1);
break;
case 12: case 13:
// 110x xxxx 10xx xxxx
c2 = str.charcodeat(i++);
out[j++] = string.fromcharcode(((c & 0x1f) 6) |
(c2 & 0x3f));
break;
case 14:
// 1110 xxxx 10xx xxxx 10xx xxxx
c2 = str.charcodeat(i++);
c3 = str.charcodeat(i++);
out[j++] = string.fromcharcode(((c & 0x0f) 12) |
((c2 & 0x3f) 6) |
(c3 & 0x3f));
break;
case 15:
switch (c & 0xf) {
case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
// 1111 0xxx 10xx xxxx 10xx xxxx 10xx xxxx
c2 = str.charcodeat(i++);
c3 = str.charcodeat(i++);
c4 = str.charcodeat(i++);
s = ((c & 0x07) 18) |
((c2 & 0x3f) 12) |
((c3 & 0x3f) 6) |
(c4 & 0x3f) - 0x10000;
if (0 && s out[j] = string.fromcharcode(((s >>> 10) & 0x03ff) | 0xd800,
(s & 0x03ff) | 0xdc00);
}
else {
out[j] = '?';
}
break;
case 8: case 9: case 10: case 11:
// 1111 10xx 10xx xxxx 10xx xxxx 10xx xxxx 10xx xxxx
i+=4;
out[j] = '?';
break;
case 12: case 13:
// 1111 110x 10xx xxxx 10xx xxxx 10xx xxxx 10xx xxxx 10xx xxxx
i+=5;
out[j] = '?';
break;
}
}
j++;
}
return out.join('');
}