base64编码

作用

在互联网上传输二进制数据。在互联网上传输非可打印字符时，可能会导致乱码、不能被网关有效处理等问题，而可打印字符不会有这些问题。故将二进制字符转为可打印字符就可以了。

原理

base64就是将3个8位的数据，转为4个6位的数据。转换后的字符都是可打印字符。一般设置为"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"。当然，你可以根据自己的需求，使用别的可打印字符。

处理位数不足

如果要编码的字节不是3的倍数，就会剩余2个字节或1个字节

1. 2个字节，16位，可以用3个6位来表示，这样编码后生成3个字符，最后两位用0填充

0

0

1

2

3

4

5

6

0

0

7

8

9

10

11

12

0

0

13

14

15

16

0

0

2. 1个字节，8位，可以用2个6位表示，编码后生成2个字符，最后四位用0填充

0

0

1

2

3

4

5

6

0

0

7

8

0

0

0

0

这样还有一个问题，生成的字符要么3个，要么2个，不是4的倍数。一般，生成的字符数都对齐为4的倍数。所以，不够的我们使用'='来填充

代码

下面是参考nginx实现的base64编码和解码

#include <stdio.h>
#include <stdlib.h>
#include <string.h>


void base64_encode(u_char* dst, const u_char* src)
{
    char basis[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";

    int len = strlen((char*)src);

    while (len > 2)
    {
        *dst++ = basis[(src[0] >> 2) & 0x3f];
        *dst++ = basis[((src[0] & 3) << 4) | (src[1] >> 4)];
        *dst++ = basis[((src[1] & 0x0f) << 2) | (src[2] >> 6)];
        *dst++ = basis[src[2] & 0x3f];

        src += 3;
        len -= 3;
    }

    if (len == 1)
    {
        *dst++ = basis[src[0] >> 2];
        *dst++ = basis[(src[0] & 0x3) << 4];
        *dst++ = '=';
        *dst++ = '=';
    }

    if (len == 2)
    {
        *dst++ = basis[src[0] >> 2];
        *dst++ = basis[((src[0] & 3) << 4) | (src[1] >> 4)];
        *dst++ = basis[(src[1] & 0xf) << 2];
        *dst++ = '=';
    }
    *dst = '';
}


int base64_decode(u_char* dst, const u_char* src)
{
    static u_char   basis64[] = {
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 62, 77, 77, 77, 63,
        52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 77, 77, 77, 77, 77, 77,
        77,  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, 77, 77, 77, 77, 77,
        77, 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, 77, 77, 77, 77, 77,

        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77,
        77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77, 77
    };

    int srclen = strlen((char*)src);
    int len = 0;

    for (; len < srclen; len++)
    {
        if (src[len] == '=')
        {
            break;
        }

        if (basis64[src[len]] == 77)
        {
            return -1;
        }
    }

    if ((len >> 2) == 1)
    {
        return -1;
    }

    while (len > 3)
    {
        *dst++ = (u_char)((basis64[src[0]] << 2) | (basis64[src[1]] >> 4));
        *dst++ = (u_char)((basis64[src[1]] << 4) | (basis64[src[2]] >> 2));
        *dst++ = (u_char)((basis64[src[2]] << 6) | basis64[src[3]]);

        src += 4;
        len -= 4;
    }

    if (len > 1)
    {
        *dst++ = (u_char)((basis64[src[0]] << 2) | (basis64[src[1]] >> 4));
    }
    if (len > 2)
    {
        *dst++ = (u_char)((basis64[src[1]] << 4) | (basis64[src[2]] >> 2));
    }
    *dst = '';
}


int main(int argc, char **argv)
{
    u_char szencode[100] = {0};
    u_char szdecode[100] = {0};

    base64_encode(szencode, (u_char*)argv[1]);
    printf("%s
", szencode);

    base64_decode(szdecode, szencode);
    printf("%s
", szdecode);

    return 0;
}


./a.out 'test测试english和and中文chinese' 
dGVzdOa1i+ivlWVuZ2xpc2jlkoxhbmTkuK3mlodjaGluZXNl

test测试english和and中文chinese