/* utf.js - utf-8 <=> utf-16 convertion
 *
 * copyright (c) 1999 masanao izumo <iz@onicos.co.jp>
 * version: 1.0
 * lastmodified: dec 25 1999
 * this library is free.  you can redistribute it and/or modify it.
 */

/*
 * interfaces:
 * utf8 = utf16to8(utf16);
 * utf16 = utf16to8(utf8);
 */

function utf16to8(str) {
    var out, i, len, c;

    out = "";
    len = str.length;
    for(i = 0; i < len; i++) {
	c = str.charcodeat(i);
	if ((c >= 0x0001) && (c <= 0x007f)) {
	    out += str.charat(i);
	} else if (c > 0x07ff) {
	    out += string.fromcharcode(0xe0 | ((c >> 12) & 0x0f));
	    out += string.fromcharcode(0x80 | ((c >>  6) & 0x3f));
	    out += string.fromcharcode(0x80 | ((c >>  0) & 0x3f));
	} else {
	    out += string.fromcharcode(0xc0 | ((c >>  6) & 0x1f));
	    out += string.fromcharcode(0x80 | ((c >>  0) & 0x3f));
	}
    }
    return out;
}

function utf8to16(str) {
    var out, i, len, c;
    var char2, char3;

    out = "";
    len = str.length;
    i = 0;
    while(i < len) {
	c = str.charcodeat(i++);
	switch(c >> 4)
	{ 
	  case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
	    // 0xxxxxxx
	    out += str.charat(i-1);
	    break;
	  case 12: case 13:
	    // 110x xxxx   10xx xxxx
	    char2 = str.charcodeat(i++);
	    out += string.fromcharcode(((c & 0x1f) << 6) | (char2 & 0x3f));
	    break;
	  case 14:
	    // 1110 xxxx  10xx xxxx  10xx xxxx
	    char2 = str.charcodeat(i++);
	    char3 = str.charcodeat(i++);
	    out += string.fromcharcode(((c & 0x0f) << 12) |
					   ((char2 & 0x3f) << 6) |
					   ((char3 & 0x3f) << 0));
	    break;
	}
    }

    return out;
}