linux c utf8和GBK 的转换函数

方法一:使用如下两个函数
 
mbstowcs将多字节编码转换为宽字节编码
 
wcstombs将宽字节编码转换为多字节编码
 
注意, 需要系统编码的支持, 可以通过locale -a 查看系统支持的。若不支持zh_CN.gbk, 需要安装,

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <locale.h>


/****************************************************************************** 
    * DESCRIPTION: 实现由utf8编码到gbk编码的转换 
    * Input: gbkStr,转换后的字符串;  
    * srcStr,待转换的字符串; 
    * maxGbkStrlen, gbkStr的最大长度 
    * Output: gbkStr 
    * Returns: -1,fail;>0,success


******************************************************************************/ 
int utf82gbk(char *gbkStr, const char *srcStr, int maxGbkStrlen) 
{
    if (NULL == srcStr) 
    {       
        printf("Bad Parameter\n");      
        return -1;
    }   
    //首先先将utf8编码转换为unicode编码 
    if (NULL == setlocale(LC_ALL, "zh_CN.utf8")) //设置转换为unicode前的码,当前为utf8编码           
    {
        printf("Bad Parameter\n");      
        return -1;
    }   
    int unicodeLen = mbstowcs(NULL, srcStr, 0);
    //计算转换后的长度  
    if (unicodeLen <= 0)
    {
        printf("Can not Transfer!!!\n");        
        return -1;  
    }   
    wchar_t *unicodeStr = (wchar_t *) calloc(sizeof(wchar_t), unicodeLen + 1);
    mbstowcs(unicodeStr, srcStr, strlen(srcStr)); 
    //将utf8转换为unicode   
    //将unicode编码转换为gbk编码    
    if (NULL == setlocale(LC_ALL, "zh_CN.gbk")) //设置unicode转换后的码,当前为gbk           
    {
        printf("Bad Parameter\n");
        return -1;
    }
    int gbkLen = wcstombs(NULL, unicodeStr, 0);
    //计算转换后的长度  
    if (gbkLen <= 0)
    {
        printf("Can not Transfer!!!\n");
        return -1;
    } else if (gbkLen >= maxGbkStrlen) //判断空间是否足够           
    {
        printf("Dst Str memory not enough\n");
        return -1;
    }
    wcstombs(gbkStr, unicodeStr, gbkLen);
    gbkStr[gbkLen] = 0; //添加结束符    
    free(unicodeStr);
    return gbkLen;
}
 

/****************************************************************************** 
    * function: gbk2utf8 
    * description: 实现由gbk编码到utf8编码的转换  
    *  
    * input: utfstr,转换后的字符串;  srcstr,待转换的字符串; maxutfstrlen, utfstr的最大长度 
    * output: utfstr 
    * returns: -1,fail;>0,success 
    *  
******************************************************************************/

int gbk2utf8(char *utfstr,const char *srcstr,int maxutfstrlen)  
{
    if(NULL==srcstr)
    {
        printf(" bad parameter\n");
        return -1;
    }
    //首先先将gbk编码转换为unicode编码  
    if(NULL==setlocale(LC_ALL,"zh_cn.gbk"))//设置转换为unicode前的码,当前为gbk编码  
    {
        printf("setlocale bad parameter\n");
        return -1;
    }
    int unicodelen=mbstowcs(NULL,srcstr,0);//计算转换后的长度  
    if(unicodelen<=0)
    {
        printf("can not transfer!!!\n");
        return -1;
    }
    wchar_t *unicodestr=(wchar_t *)calloc(sizeof(wchar_t),unicodelen+1);
    mbstowcs(unicodestr,srcstr,strlen(srcstr));//将gbk转换为unicode  


    //将unicode编码转换为utf8编码  
    if(NULL==setlocale(LC_ALL,"zh_cn.utf8"))//设置unicode转换后的码,当前为utf8  
    {
        printf("bad parameter\n");
        return -1;
    }
    int utflen=wcstombs(NULL,unicodestr,0);//计算转换后的长度  
    if(utflen<=0)
    {
        printf("can not transfer!!!\n");
        return -1;
    }
    else if(utflen>=maxutfstrlen)//判断空间是否足够  
    {
        printf("dst str memory not enough\n");
        return -1;
    }
    wcstombs(utfstr,unicodestr,utflen);
    utfstr[utflen]=0;//添加结束符  
    free(unicodestr);
    return utflen;
}


int main(void)
{
    char *s = "中国";
    int fd , res;
    if ((fd= open("test.txt", O_WRONLY | O_CREAT | O_TRUNC,S_IREAD | S_IWRITE)) == -1)
    {
        printf("Error opening file.\n");
        exit(1);
    }


    char bufgbk[10];

    utf82gbk(bufgbk, s, sizeof(bufgbk));
    int gbk_length = strlen(bufgbk);


    if ((res = write(fd, bufgbk, gbk_length)) != gbk_length)
    {
        printf("Error gbk writing to the file.\n");
        exit(1);
    }

    close(fd);
    return 1;
}

方法二:使用iconv函数
#include <iconv.h>
#include <stdlib.h>
#include <stdio.h>
#include <unistd.h>
#include <fcntl.h>
#include <string.h>
#include <sys/stat.h>


int code_convert(char *from_charset, char *to_charset, char *inbuf, size_t inlen,
char *outbuf, size_t outlen) {
iconv_t cd;
char **pin = &inbuf;
char **pout = &outbuf;


cd = iconv_open(to_charset, from_charset);
if (cd == 0)
return -1;
memset(outbuf, 0, outlen);
if (iconv(cd, pin, &inlen, pout, &outlen) == -1)
return -1;
iconv_close(cd);
*pout = '\0';


return 0;
}


int u2g(char *inbuf, size_t inlen, char *outbuf, size_t outlen) {
return code_convert("utf-8", "gb2312", inbuf, inlen, outbuf, outlen);
}


int g2u(char *inbuf, size_t inlen, char *outbuf, size_t outlen) {
return code_convert("gb2312", "utf-8", inbuf, inlen, outbuf, outlen);
}


int main(void) {
char *s = "中国";
int fd = open("test.txt", O_RDWR|O_CREAT, S_IRUSR | S_IWUSR);
char buf[10];
u2g(s, strlen(s), buf, sizeof(buf));
write(fd, buf, strlen(buf));
close(fd);


fd = open("test.txt2", O_RDWR|O_CREAT, S_IRUSR | S_IWUSR);
char buf2[10];
g2u(buf, strlen(buf), buf2, sizeof(buf2));
write(fd, buf2, strlen(buf2));
close(fd);
return 1;
}

猜你喜欢

转载自blog.csdn.net/wushuangge/article/details/78918953