sms信息编码

信息编码

信息编码共有三种方式，按所携带信息的大小排序可分为：7bit编码、8bit编码、UCS2编码

7bit编码

7位编码是种压缩算法，因为，ASCII码（不包括扩展ASCII），其值小于0x80，最高位bit8是0，被忽略了；而7bit编码就利用了这一位来存储数据；其编码时，依次将下一7位编码的后几位逐次移至前面，形成新的8位编码。

根据上图可得到7bit编码解码算法如下：

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

#define HIGH_8BIT_MASK(N) (0xFF << (N))
#define LOW_8BIT_MASK(N) (~HIGH_8BIT_MASK(N))

int _7bit_to_asscii(char *p_dst, unsigned char *src, int src_size)
{
    int i = 0;
    int n = 0;
    int pos = 0;
    int left = 0;
    char high_part, low_part;
    left = 8;

    if (src == NULL || p_dst == NULL)
    {
        return -1;
    }

    n = (src_size * 8) / 7;

    for (i = 0; i < n; i++)
    {
        if (8 == left)
        {
            p_dst[i] = src[pos] & LOW_8BIT_MASK(7);
            left = 1;
        }
        else if (7 == left)
        {
            p_dst[i] = (src[pos] & HIGH_8BIT_MASK(8 - left)) >> (8 - left);
            left = 8;
            pos++;
        }
        else
        {
            high_part = low_part = 0;
            low_part = (src[pos] & HIGH_8BIT_MASK(8 - left)) >> (8 - left);
            high_part = (src[pos+1] & LOW_8BIT_MASK(7 - left)) << left;
            p_dst[i] = low_part | high_part;
            left = 8 - (7 - left);
            pos++;
        }
    }

    return n;
}

int asscii_to_7bit(char *p_dst, const char *p_src, int src_size)
{
    int i = 0;
    int pos = 0;
    int left = 0;   //当前字节还能放多少个元素
    int high_part, low_part;
    char p_usrc[src_size + 1];
    memcpy(p_usrc, p_src, src_size);
    left = 8;//初始时候为8位，这是从低位开始算的
    for(i = 0; i < src_size ; i++){
        if(left == 8){
            p_dst[pos] |= p_usrc[i] << (8 - left);
            left -= 7;
        }else if(left == 7){
            p_dst[pos] |= p_usrc[i] << (8 - left);
            left = 8;
            pos++;
        }else{  //需要分割，分为两部分，一部分是 低left位, 另一部分是 高7-left位
            high_part = low_part = 0;
            low_part = p_usrc[i] & LOW_8BIT_MASK(left);
            high_part = (p_usrc[i] & HIGH_8BIT_MASK(left)) >> left;

            p_dst[pos] |= low_part << (8 - left);
            pos++;
            p_dst[pos] |= high_part;
            left = 8 - (7 - left);
        }
    }
    return ((src_size * 7 + 7) / 8);

}

8bit编码

8bit编码，顾名思义就是一个char型数据代表一个字符，所以他的编解码是一模一样的，甚至都不叫编解码，直接拿来用即可：

int decode_8bit(char *in, int in_length, char *out, int *out_length)
{
    int length = 0;

    if (in == NULL || in_length <= 0 || out == NULL || out_length == NULL)
    {
        return -1;
    }

    for (int index = 0; index < in_length; index++)
    {
        out[length++] = in[index];
    }
    *out_length = length;

    return 0;
}

int encode_8bit(char *in, int in_length, char *out, int *out_length)
{
    int length = 0;

    if (in == NULL || in_length <= 0 || out == NULL || out_length == NULL)
    {
        return -1;
    }

    for (int index = 0; index < in_length; index++)
    {
        out[length++] = in[index];
    }
    *out_length = length;

    return 0;
}

UCS2编码

UCS2就是标准的unicode编码， 它是某国际组织设计的一种文字符号编码表，包括了世界上绝大多数文字和符号，包括中文，每个字符使用2字节编码，因此叫ucs2。

对于这种标准编码有现成的函数iconv()可以使用：

#include <iconv.h>

iconv_t iconv_open(const char *tocode, const char *fromcode);
size_t iconv(iconv_t cd,
                char **inbuf, size_t *inbytesleft,
                char **outbuf, size_t *outbytesleft);
int iconv_close(iconv_t cd);

iconv_open：

tocode:目标编码；fromcode:当前编码；返回值为iconv的句柄

iconv：

cd:iconv_open获取的句柄；inbuf，inbytesleft:输入的字符串及其大小；outbuf，outbytesleft:输出的字符串及其大小

iconv_close：

cd:iconv_open获取的句柄

UCS2编码如下：

int encode_ucs2(char *in, int in_length, char *out, int *out_length)
{
    iconv_t icon_handler = 0;
    int out_buffer_length = 0;
    char *out_buffer = NULL;
    char temp = 0x00;

    if (in == NULL || in_length <= 0 || out == NULL || out_length == NULL)
    {
        return -1;
    }

    if ((icon_handler = iconv_open("ucs-2", "utf-8")) == 0)
    {
        return -1;
    }

    out_buffer_length = *out_length;
    out_buffer = out;
    if (iconv(icon_handler, &in, (size_t *)&in_length, &out_buffer, (size_t *)&out_buffer_length) == -1)
    {
        *out_length = 0;
        printf("encode_ucs2 errno = %d.", errno);
        iconv_close(icon_handler);
        return -1;
    }
    *out_length -= out_buffer_length;
    iconv_close(icon_handler);

    for (int index = 0; index < *out_length ; index += 2)
    {
        temp = out[index];
        out[index] = out[index + 1];
        out[index + 1] = temp;
    }

    return 0;
}

int decode_ucs2(char *in, int in_length, char *out, int *out_length)
{
    iconv_t icon_handler = 0;
    int out_buffer_length = 0;
    char *out_buffer = NULL;
    char temp = 0x00;

    if (in == NULL || in_length <= 0 || in_length % 2 != 0 || out == NULL || out_length == NULL)
    {
        return -1;
    }

    for (int index = 0; index < in_length; index += 2)
    {
        temp = in[index];
        in[index] = in[index + 1];
        in[index + 1] = temp;
    }

    if ((icon_handler = iconv_open("utf-8", "ucs-2")) == 0)
    {
        return -1;
    }

    out_buffer_length = *out_length;
    out_buffer = out;
    if (iconv(icon_handler, &in, (size_t *)&in_length, &out_buffer, (size_t *)&out_buffer_length) == -1)
    {
        *out_length = 0;
        printf("decode_ucs2 errno = %d.", errno);
        iconv_close(icon_handler);
        return -1;
    }
    *out_length -= out_buffer_length;
    iconv_close(icon_handler);

    return 0;
}