L008Linux和androidNDK之base64编码的C语言实现

从android源码中找出来的一个c语言版,base64的实现,亲测可用。

原来的函数名定义的太难理解了,重新定义了一下

int base64EnCode(unsigned char const *src, size_t srclength, char *target, size_t targsize);
int base64DeCode(char const *src, unsigned char *target, size_t targsize);

如下是源码:

#include <sys/cdefs.h>
#include <sys/types.h>
#include <sys/param.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <arpa/nameser.h>

#include <assert.h>
#include <ctype.h>
#ifdef ANDROID_CHANGES
#include "resolv_private.h"
#else
#include <resolv.h>
#endif
#include <stdio.h>

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

static const char Base64[] =
    "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static const char Pad64 = '=';

/* (From RFC1521 and draft-ietf-dnssec-secext-03.txt)
   The following encoding technique is taken from RFC 1521 by Borenstein
   and Freed.  It is reproduced here in a slightly edited form for
   convenience.

   A 65-character subset of US-ASCII is used, enabling 6 bits to be
   represented per printable character. (The extra 65th character, "=",
   is used to signify a special processing function.)

   The encoding process represents 24-bit groups of input bits as output
   strings of 4 encoded characters. Proceeding from left to right, a
   24-bit input group is formed by concatenating 3 8-bit input groups.
   These 24 bits are then treated as 4 concatenated 6-bit groups, each
   of which is translated into a single digit in the base64 alphabet.

   Each 6-bit group is used as an index into an array of 64 printable
   characters. The character referenced by the index is placed in the
   output string.

                         Table 1: The Base64 Alphabet

      Value Encoding  Value Encoding  Value Encoding  Value Encoding
          0 A            17 R            34 i            51 z
          1 B            18 S            35 j            52 0
          2 C            19 T            36 k            53 1
          3 D            20 U            37 l            54 2
          4 E            21 V            38 m            55 3
          5 F            22 W            39 n            56 4
          6 G            23 X            40 o            57 5
          7 H            24 Y            41 p            58 6
          8 I            25 Z            42 q            59 7
          9 J            26 a            43 r            60 8
         10 K            27 b            44 s            61 9
         11 L            28 c            45 t            62 +
         12 M            29 d            46 u            63 /
         13 N            30 e            47 v
         14 O            31 f            48 w         (pad) =
         15 P            32 g            49 x
         16 Q            33 h            50 y

   Special processing is performed if fewer than 24 bits are available
   at the end of the data being encoded.  A full encoding quantum is
   always completed at the end of a quantity.  When fewer than 24 input
   bits are available in an input group, zero bits are added (on the
   right) to form an integral number of 6-bit groups.  Padding at the
   end of the data is performed using the '=' character.

   Since all base64 input is an integral number of octets, only the
         -------------------------------------------------
   following cases can arise:

       (1) the final quantum of encoding input is an integral
           multiple of 24 bits; here, the final unit of encoded
       output will be an integral multiple of 4 characters
       with no "=" padding,
       (2) the final quantum of encoding input is exactly 8 bits;
           here, the final unit of encoded output will be two
       characters followed by two "=" padding characters, or
       (3) the final quantum of encoding input is exactly 16 bits;
           here, the final unit of encoded output will be three
       characters followed by one "=" padding character.
   */



int base64EnCode(unsigned char const *src, size_t srclength, char *target, size_t targsize)
{
    size_t datalength = 0;
    unsigned char input[3] = { 0, 0, 0 };  /* make compiler happy */
    unsigned char output[4];
    size_t i;

    assert(src != NULL);
    assert(target != NULL);

    while (2 < srclength) {
        input[0] = *src++;
        input[1] = *src++;
        input[2] = *src++;
        srclength -= 3;

        output[0] = (u_int32_t)input[0] >> 2;
        output[1] = ((u_int32_t)(input[0] & 0x03) << 4) +
            ((u_int32_t)input[1] >> 4);
        output[2] = ((u_int32_t)(input[1] & 0x0f) << 2) +
            ((u_int32_t)input[2] >> 6);
        output[3] = input[2] & 0x3f;
        assert(output[0] < 64);
        assert(output[1] < 64);
        assert(output[2] < 64);
        assert(output[3] < 64);

        if (datalength + 4 > targsize)
            return (-1);
        target[datalength++] = Base64[output[0]];
        target[datalength++] = Base64[output[1]];
        target[datalength++] = Base64[output[2]];
        target[datalength++] = Base64[output[3]];
    }

    /* Now we worry about padding. */
    if (0 != srclength) {
        /* Get what's left. */
        input[0] = input[1] = input[2] = '\0';
        for (i = 0; i < srclength; i++)
            input[i] = *src++;

        output[0] = (u_int32_t)input[0] >> 2;
        output[1] = ((u_int32_t)(input[0] & 0x03) << 4) +
            ((u_int32_t)input[1] >> 4);
        output[2] = ((u_int32_t)(input[1] & 0x0f) << 2) +
            ((u_int32_t)input[2] >> 6);
        assert(output[0] < 64);
        assert(output[1] < 64);
        assert(output[2] < 64);

        if (datalength + 4 > targsize)
            return (-1);
        target[datalength++] = Base64[output[0]];
        target[datalength++] = Base64[output[1]];
        if (srclength == 1)
            target[datalength++] = Pad64;
        else
            target[datalength++] = Base64[output[2]];
        target[datalength++] = Pad64;
    }
    if (datalength >= targsize)
        return (-1);
    target[datalength] = '\0';  /* Returned value doesn't count \0. */
    return (datalength);
}

/* skips all whitespace anywhere.
   converts characters, four at a time, starting at (or after)
   src from base - 64 numbers into three 8 bit bytes in the target area.
   it returns the number of data bytes stored at the target, or -1 on error.
 */

int base64DeCode(char const *src, unsigned char *target, size_t targsize)
{
    size_t tarindex;
    int state, ch;
    char *pos;

    assert(src != NULL);
    assert(target != NULL);

    state = 0;
    tarindex = 0;

    while ((ch = (unsigned char) *src++) != '\0') {
        if (isspace(ch))    /* Skip whitespace anywhere. */
            continue;

        if (ch == Pad64)
            break;

        pos = strchr(Base64, ch);
        if (pos == 0)       /* A non-base64 character. */
            return (-1);

        switch (state) {
        case 0:
            if (target) {
                if (tarindex >= targsize)
                    return (-1);
                target[tarindex] = (pos - Base64) << 2;
            }
            state = 1;
            break;
        case 1:
            if (target) {
                if (tarindex + 1 >= targsize)
                    return (-1);
                target[tarindex] |=
                    (u_int32_t)(pos - Base64) >> 4;
                target[tarindex+1]  = ((pos - Base64) & 0x0f)
                            << 4 ;
            }
            tarindex++;
            state = 2;
            break;
        case 2:
            if (target) {
                if (tarindex + 1 >= targsize)
                    return (-1);
                target[tarindex] |=
                    (u_int32_t)(pos - Base64) >> 2;
                target[tarindex+1] = ((pos - Base64) & 0x03)
                            << 6;
            }
            tarindex++;
            state = 3;
            break;
        case 3:
            if (target) {
                if (tarindex >= targsize)
                    return (-1);
                target[tarindex] |= (pos - Base64);
            }
            tarindex++;
            state = 0;
            break;
        default:
            abort();
        }
    }

    /*
     * We are done decoding Base-64 chars.  Let's see if we ended
     * on a byte boundary, and/or with erroneous trailing characters.
     */

    if (ch == Pad64) {      /* We got a pad char. */
        ch = *src++;        /* Skip it, get next. */
        switch (state) {
        case 0:     /* Invalid = in first position */
        case 1:     /* Invalid = in second position */
            return (-1);

        case 2:     /* Valid, means one byte of info */
            /* Skip any number of spaces. */
            for (; ch != '\0'; ch = (unsigned char) *src++)
                if (!isspace(ch))
                    break;
            /* Make sure there is another trailing = sign. */
            if (ch != Pad64)
                return (-1);
            ch = *src++;        /* Skip the = */
            /* Fall through to "single trailing =" case. */
            /* FALLTHROUGH */

        case 3:     /* Valid, means two bytes of info */
            /*
             * We know this char is an =.  Is there anything but
             * whitespace after it?
             */
            for (; ch != '\0'; ch = (unsigned char) *src++)
                if (!isspace(ch))
                    return (-1);

            /*
             * Now make sure for cases 2 and 3 that the "extra"
             * bits that slopped past the last full byte were
             * zeros.  If we don't check them, they become a
             * subliminal channel.
             */
            if (target && target[tarindex] != 0)
                return (-1);
        }
    } else {
        /*
         * We ended by seeing the end of the string.  Make sure we
         * have no partial bytes lying around.
         */
        if (state != 0)
            return (-1);
    }

    return (tarindex);
}

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

发表于

我来说两句

0 条评论
登录 后参与评论

相关文章

来自专栏java一日一条

华为加班到底有多恐怖?

“我先说一下我的吧。昨天晚上好不容易11点之前搞完上线回到家,刚开门媳妇就叫到:你TMD给我站到阳台去!”

1.3K20
来自专栏金融民工小曾

电商平台分账交易是怎么做的?

另一篇文章讲到了电商平台的“二清”模式,在实际中,很多互联网电商平台需要分账给上面的平台商户或者其他角色,如果从严格的“二清”界定上来讲部分是属于违规进行了“信...

28510
来自专栏程序员的知识天地

这些拍案惊奇的智障桥段,分明是在蔑视我作为程序员的debug

作为在网络高速发展的时代背景下成长起来的一代人,网络文学几乎伴随着我们的整个青春。

13020
来自专栏java一日一条

博君一笑

9620
来自专栏java一日一条

编程,从来都不晚:来自日本的82岁APP开发者

82岁的若宮正子第一次工作时,还是使用算盘来进行计算——而如今,她是世界上年纪最大的iPhone应用开发者之一,也是使得智能手机走入老年人生活的先驱者。

15220
来自专栏java一日一条

面试中单例模式有几种写法

纠结单例模式有几种写法有用吗?有点用,面试中经常选择其中一种或几种写法作为话头,考查设计模式和coding style的同时,还很容易扩展到其他问题。这里讲解几...

12270
来自专栏程序员的知识天地

阿里员工揭秘:很多程序员离职,在小公司当领导,只动嘴不动手!

阿里巴巴是中国知名的互联网公司,每个人或多或少的都从淘宝上购买的物品,自从1998年成立到现在,里面人才济济,里面的程序员不仅工资非常的高,不少程序员年收入竟然...

16620
来自专栏java一日一条

我的编码习惯 - 参数校验和国际化规范

今天我们说说参数校验和国际化,这些代码没有什么技术含量,却大量充斥在业务代码上,很可能业务代码只有几行,参数校验代码却有十几行,非常影响代码阅读,所以很有必要把...

12810
来自专栏java一日一条

华为、腾讯、阿里、网易员工下班时间大曝光,为什么赢不了他们

这年头,不加班都不好意思说自己是上班族的。但有一种行业的疯狂加班程度,已经逐渐成为加班领域的一颗新星——互联网行业从事者!

15030
来自专栏java一日一条

盲式出轨,上流社会边缘人士,2018朋友圈流行词,哪个词说中了你?

11830

扫码关注云+社区

领取腾讯云代金券

年度创作总结 领取年终奖励