Question

怎么解决js解码base64中文乱码问题

Answer 1

最近在做一个插件开发，我用c++在插件里面把带中文的字符串用base64算法加密后推给网页的js去解码，解出来的相信大家预料到了，洋文一字不差，中文就TMD的都是乱码。
google了一下，也没找到能解决问题的方法，没办法只好自己研究了。后来发现问题原因了，编码过程肯定是没有问题的，看到前面加颜色那段字了没，就是我解出来的编码虽然是utf8，但是将中文文字进行Base64编码再解码后，重新排列编码的时候，往往就会出现乱码，UTF8页面的编码实际还是用UTF-16存储的。应该在解码后把UTF8还原为UTF-16格式。这样就能真正搞定javascript解密中文base64编码的问题了。
这里我就把js解码代码贴出来，给广大同胞：
/**
* Waitang.com
*/
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编码
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解码
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;
}

这是转换utf8到utf16的代码：

/**
* Yovae.com
*/
//utf-8转utf16
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;
}
//utf-16转utf-8
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;
}

这是c++ base64编码代码：

/**
* Yovae.com
*/
CString encode(const CString in_str)
{
const CString _base64_encode_chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
CString out_str;
unsigned char c1, c2, c3;
int i = 0;
int len = in_str.GetLength();
while ( i {
c1 = in_str[i++];
if ( i==len )
{
out_str += _base64_encode_chars[ c1>>2 ];
out_str += _base64_encode_chars[ (c1&0x3)<<4 ];
out_str += "==";
break;
}
c2 = in_str[i++];
if ( i==len )
{
out_str += _base64_encode_chars[ c1>>2 ];
out_str += _base64_encode_chars[ ((c1&0x3)<<4) | ((c2&0xF0)>>4) ];
out_str += _base64_encode_chars[ (c2&0xF)<<2 ];
out_str += "=";
break;
}

c3 = in_str[i++];
out_str += _base64_encode_chars[ c1>>2 ];
out_str += _base64_encode_chars[ ((c1&0x3)<<4) | ((c2&0xF0)>>4) ];
out_str += _base64_encode_chars[ ((c2&0xF)<<2) | ((c3&0xC0)>>6) ];
out_str += _base64_encode_chars[ c3&0x3F ];
}
return out_str;
}

Answer 2

应该在解码后把UTF8还原为UTF-16格式。这样就能真正搞定javascript解密中文base64编码的问题了。
这里我就把js解码代码贴出来，给广大同胞：

/**
* Waitang.com
*/
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编码
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解码
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;
}

这是转换utf8到utf16的代码：

/**
* Yovae.com
*/
//utf-8转utf16
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;
}
//utf-16转utf-8
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;
}

这是c++ base64编码代码：

/**
* Yovae.com
*/
CString encode(const CString in_str)
{
const CString _base64_encode_chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
CString out_str;
unsigned char c1, c2, c3;
int i = 0;
int len = in_str.GetLength();
while ( i {
c1 = in_str[i++];
if ( i==len )
{
out_str += _base64_encode_chars[ c1>>2 ];
out_str += _base64_encode_chars[ (c1&0x3)<<4 ];
out_str += "==";
break;
}
c2 = in_str[i++];
if ( i==len )
{
out_str += _base64_encode_chars[ c1>>2 ];
out_str += _base64_encode_chars[ ((c1&0x3)<<4) | ((c2&0xF0)>>4) ];
out_str += _base64_encode_chars[ (c2&0xF)<<2 ];
out_str += "=";
break;
}

c3 = in_str[i++];
out_str += _base64_encode_chars[ c1>>2 ];
out_str += _base64_encode_chars[ ((c1&0x3)<<4) | ((c2&0xF0)>>4) ];
out_str += _base64_encode_chars[ ((c2&0xF)<<2) | ((c3&0xC0)>>6) ];
out_str += _base64_encode_chars[ c3&0x3F ];
}
return out_str;
}

Answer 3

 在线加密解密工具

Answer 4

js解码后，还在乱码？ 就 可能是页面编码格式不一致