在前端開發中,我們時常需要對資料進行編碼與解碼,Base64 與 UTF8 就是最常見的兩種。本文將從原理出發,並附上可直接使用的 JavaScript 實作,幫助你徹底搞懂它們的運作方式。
Base64 的核心思想是:把每 3 個 8 位元組(3×8=24 位元)重新切分成 4 個 6 位元組(4×6=24 位元),再在前面補兩個 0,湊成 4 個完整的 8 位元組。由於 6 位元最多只能表示 64 種組合,因此正好對應到 64 個可列印字元。若原始資料長度不是 3 的倍數,就用 0 補齊,並以「=」作為填充符號,所以編碼後的結果末尾常會出現 1 到 2 個「=」。
這份實作在編碼前會先把 Unicode 字串轉為 ANSI(雙位元組)碼,處理底層位元運算後再進行 Base64 轉換,因此能正確處理中文等非 ASCII 字元:
var base64 = (function(){
var keyStr = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
return {
"encode64": encode64,
"decode64": decode64
}
function encode64(input)
{
input = strUnicode2Ansi(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;
}
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 strAnsi2Unicode(output);
}
// UnicodeChr() 與 AnsicodeChr() 在此提供完整的 Unicode ↔ GB2312 對照碼表,
// 皆為以逗號分隔的十六進位碼位字串,用於 UnicodeToAnsi / AnsiToUnicode 的查表轉換。
// 由於對照表篇幅龐大(涵蓋數千個中日韓字元與符號),此處省略其內容,
// 實作時直接放入完整的對照碼表即可。
function UnicodeToAnsi(chrCode)
{
var chrHex=chrCode.toString(16);
chrHex="000"+chrHex.toUpperCase();
chrHex=chrHex.substr(chrHex.length-4);
var i=UnicodeChr().indexOf(chrHex);
if(i!=-1)
{
chrHex=AnsicodeChr().substr(i,4);
}
return parseInt(chrHex,16)
}
function AnsiToUnicode(chrCode)
{
var chrHex=chrCode.toString(16);
chrHex="000"+chrHex.toUpperCase();
chrHex=chrHex.substr(chrHex.length-4);
var i=AnsicodeChr().indexOf(chrHex);
if(i!=-1)
{
chrHex=UnicodeChr().substr(i,4);
}
return parseInt(chrHex,16)
}
function strUnicode2Ansi(asContents)
{
var len1=asContents.length;
var temp="";
for(var i=0;i<len1;i++)
{
var varasc=asContents.charCodeAt(i);
if(varasc<0)
varasc+=65536;
if(varasc>127)
varasc=UnicodeToAnsi(varasc);
if(varasc>255)
{
var varlow=varasc & 65280;
varlow=varlow>>8;
var varhigh=varasc & 255;
temp+=String.fromCharCode(varlow)+String.fromCharCode(varhigh);
}
else
{
temp+=String.fromCharCode(varasc);
}
}
return temp;
}
function strAnsi2Unicode(asContents)
{
var len1=asContents.length;
var temp="";
var chrcode;
for(var i=0;i<len1;i++)
{
var varasc=asContents.charCodeAt(i);
if(varasc>127)
{
chrcode=AnsiToUnicode((varasc<<8)+asContents.charCodeAt(++i));
}
else
{
chrcode=varasc;
}
temp+=String.fromCharCode(chrcode);
}
return temp;
}
}());
測試方式很簡單,一行就能驗證中文的編解碼:
var str = base64.encode64("這是測試");
alert(base64.decode64(str));
這份實作把 Base64 編解碼與 UTF16↔UTF8 的轉換拆開,使用時先以 utf16to8 轉碼,再做 Base64 編碼;解碼時則反向操作。這種組合能避免中文亂碼:
var base64EncodeChars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
var base64DecodeChars = new Array(
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,
-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,62,-1,-1,-1,63,
52,53,54,55,56,57,58,59,60,61,-1,-1,-1,-1,-1,-1,
-1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,
15,16,17,18,19,20,21,22,23,24,25,-1,-1,-1,-1,-1,
-1,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,
41,42,43,44,45,46,47,48,49,50,51,-1,-1,-1,-1,-1
);
/**
* base64 編碼
* @param {Object} str
*/
function base64encode(str){
var out, i, len;
var c1, c2, c3;
len = str.length;
i = 0;
out = "";
while (i < len) {
c1 = str.charCodeAt(i++) & 0xff;
if (i == len) {
out += base64EncodeChars.charAt(c1 >> 2);
out += base64EncodeChars.charAt((c1 & 0x3) << 4);
out += "==";
break;
}
c2 = str.charCodeAt(i++);
if (i == len) {
out += base64EncodeChars.charAt(c1 >> 2);
out += base64EncodeChars.charAt(((c1 & 0x3) << 4) | ((c2 & 0xF0) >> 4));
out += base64EncodeChars.charAt((c2 & 0xF) << 2);
out += "=";
break;
}
c3 = str.charCodeAt(i++);
out += base64EncodeChars.charAt(c1 >> 2);
out += base64EncodeChars.charAt(((c1 & 0x3) << 4) | ((c2 & 0xF0) >> 4));
out += base64EncodeChars.charAt(((c2 & 0xF) << 2) | ((c3 & 0xC0) >> 6));
out += base64EncodeChars.charAt(c3 & 0x3F);
}
return out;
}
/**
* base64 解碼
* @param {Object} str
*/
function base64decode(str){
var c1, c2, c3, c4;
var i, len, out;
len = str.length;
i = 0;
out = "";
while (i < len) {
/* c1 */
do {
c1 = base64DecodeChars[str.charCodeAt(i++) & 0xff];
}
while (i < len && c1 == -1);
if (c1 == -1)
break;
/* c2 */
do {
c2 = base64DecodeChars[str.charCodeAt(i++) & 0xff];
}
while (i < len && c2 == -1);
if (c2 == -1)
break;
out += String.fromCharCode((c1 << 2) | ((c2 & 0x30) >> 4));
/* c3 */
do {
c3 = str.charCodeAt(i++) & 0xff;
if (c3 == 61)
return out;
c3 = base64DecodeChars[c3];
}
while (i < len && c3 == -1);
if (c3 == -1)
break;
out += String.fromCharCode(((c2 & 0XF) << 4) | ((c3 & 0x3C) >> 2));
/* c4 */
do {
c4 = str.charCodeAt(i++) & 0xff;
if (c4 == 61)
return out;
c4 = base64DecodeChars[c4];
}
while (i < len && c4 == -1);
if (c4 == -1)
break;
out += String.fromCharCode(((c3 & 0x03) << 6) | c4);
}
return out;
}
/**
* utf16 轉 utf8
* @param {Object} str
*/
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;
}
/**
* utf8 轉 utf16
* @param {Object} str
*/
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;
}
使用時,只要先轉 UTF8 再編碼即可正確處理中文:
var output = base64encode(utf16to8(source));
var decode = utf8to16(base64decode(output));
除了上面的位元運算寫法,實務上也常看到以 \\u 轉義序列表示的 UTF8 編解碼,做法簡潔,適合處理需要以 \\uXXXX 形式呈現的場景:
function encodeUTF8(str){
var temp = "", rs = "";
for( var i=0 , len = str.length; i < len; i++ ){
temp = str.charCodeAt(i).toString(16);
rs += "\\u" + new Array(5 - temp.length).join("0") + temp;
}
return rs;
}
function decodeUTF8(str){
return str.replace(/(\u)(\w{4}|\w{2})/gi, function($0, $1, $2){
return String.fromCharCode(parseInt($2, 16));
});
}
以上就是本文的全部內容。搞懂 Base64 的位元切分原理、UTF8 的字節編碼規則,再搭配可直接複用的程式碼,相信能幫助你更從容地處理 JavaScript 中的編碼與解碼需求。