UTF8和UTF16互相转换脚本

UTF8和UTF16互相转换脚本.md

/* utf.js - UTF-8 <=> UTF-16 convertion
 * Copyright (C) 1999 Masanao Izumo <[email protected]>
 * Version: 1.0
 * LastModified: Dec 25 1999
 * This library is free.  You can redistribute it and/or modify it.
 * Reference http://suflow.iteye.com/blog/1687396
 */

/*
 * Interfaces:
 * utf8 = utf16to8(utf16);
 */
function utf16to8(str){
  var i, 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;
}

/*
 * Interfaces:
 * utf16 = utf8to16(utf8);
 */
function utf8to16(str){
  var c, char2, char3,
    i = 0, out = '',
    len = str.length;

  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;
}