外国的一个blog上摘录的，原文如下：

Recently I’ve been doing some work on a PHP script that has to process a bunch of XML files (in this case they’re imsmanifest files) however a few of them weren’t being parsed successfully.

The problem was soon quite clear, some of the files had been encoded using UTF-16 which wasn’t playing nicely with PHP. To solve this I’ve written a function that attempts to detect if a string is encoded using UTF-16 (little endian or big endian) and then converts it to a slightly more PHP friendly UTF-8. All the complicated stuff is copied from these JavaScript functions for converting between UTF-8 and UTF-16.


PHP:

function utf16_to_utf8($str) {
    $c0 = ord($str[0]);
    $c1 = ord($str[1]);

    if ($c0 == 0xFE && $c1 == 0xFF) {
        $be = true;
    } else if ($c0 == 0xFF && $c1 == 0xFE) {
        $be = false;
    } else {
        return $str;
    }

    $str = substr($str, 2);
    $len = strlen($str);
    $dec = '';
    for ($i = 0; $i < $len; $i += 2) {
        $c = ($be) ? ord($str[$i]) << 8 | ord($str[$i + 1]) : 
                ord($str[$i + 1]) << 8 | ord($str[$i]);
        if ($c >= 0x0001 && $c <= 0x007F) {
            $dec .= chr($c);
        } else if ($c > 0x07FF) {
            $dec .= chr(0xE0 | (($c >> 12) & 0x0F));
            $dec .= chr(0x80 | (($c >>  6) & 0x3F));
            $dec .= chr(0x80 | (($c >>  0) & 0x3F));
        } else {
            $dec .= chr(0xC0 | (($c >>  6) & 0x1F));
            $dec .= chr(0x80 | (($c >>  0) & 0x3F));
        }
    }
    return $dec;
}

JavaScript:

/* 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;
}

原文地址：
http://www.moddular.org/log/utf16-to-utf8