使用JS对中文字符串进行utf-8的Base64编码

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title></title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<style type="text/css">
<!--
body{
  margin:0px;
  padding:0px;
}
body,td{
  font-size:9pt;
}
-->
</style>
<script type="text/javascript">
<!--
var keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
//将Ansi编码的字符串进行Base64编码
function encode64(input) {
	var output = "";
	var chr1, chr2, chr3 = "";
	var enc1, enc2, enc3, enc4 = "";
	var i = 0;
	do {
		chr1 = input.charCodeAt(i++);
		chr2 = input.charCodeAt(i++);
		chr3 = input.charCodeAt(i++);
		enc1 = chr1 >> 2;
		enc2 = ((chr1 & 3) << 4) | (chr2 >> 4);
		enc3 = ((chr2 & 15) << 2) | (chr3 >> 6);
		enc4 = chr3 & 63;
		if (isNaN(chr2)) {
			enc3 = enc4 = 64;
		} else if (isNaN(chr3)) {
			enc4 = 64;
		}
		output = output + keyStr.charAt(enc1) + keyStr.charAt(enc2)
				+ keyStr.charAt(enc3) + keyStr.charAt(enc4);
		chr1 = chr2 = chr3 = "";
		enc1 = enc2 = enc3 = enc4 = "";
	} while (i < input.length);
	return output;
}
//将Base64编码字符串转换成Ansi编码的字符串
function decode64(input) {
	var output = "";
	var chr1, chr2, chr3 = "";
	var enc1, enc2, enc3, enc4 = "";
	var i = 0;

	if (input.length % 4 != 0) {
		return "";
	}
	var base64test = /[^A-Za-z0-9\+\/\=]/g;
	if (base64test.exec(input)) {
		return "";
	}
	do {
		enc1 = keyStr.indexOf(input.charAt(i++));
		enc2 = keyStr.indexOf(input.charAt(i++));
		enc3 = keyStr.indexOf(input.charAt(i++));
		enc4 = keyStr.indexOf(input.charAt(i++));
		chr1 = (enc1 << 2) | (enc2 >> 4);
		chr2 = ((enc2 & 15) << 4) | (enc3 >> 2);
		chr3 = ((enc3 & 3) << 6) | enc4;

		output = output + String.fromCharCode(chr1);
		if (enc3 != 64) {
			output += String.fromCharCode(chr2);
		}
		if (enc4 != 64) {
			output += String.fromCharCode(chr3);
		}
		chr1 = chr2 = chr3 = "";
		enc1 = enc2 = enc3 = enc4 = "";
	} while (i < input.length);
	return output;
}

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;
}

// 测试代码 开始
var de = encode64(utf16to8("select 用户名 from 用户"));
document.writeln(de+"<br>");
var ee = utf8to16(decode64(de))
document.writeln(ee);
// 测试代码 结束

//-->
</script>
</head>
<body>
</body>
</html>

Java代码中为什么要使用getBytes("UTF-8")呢？因为Windows和Linux环境下默认编码不同，要使你的程序在不同平台下得到相同编码，必然要指定编码

虽然Html和JS的编码都是utf-8，但JS从页面上得到的中文编码却是utf-16，所以直接对中文进行Base64编码将得到错误的结果，所以我们要先从utf-16转到utf-8再编码

使用JS对中文字符串进行utf-8的Base64编码

猜你喜欢