libiconv字符编码处理及判断字符串是否为utf8代码,C/C++代码库,德仔网

代码语言
代码分类
【C/C++】 libiconv字符编码处理及判断字符串是否为utf8
作者:珍灵 / 发布于2018/3/26/ 827
#include <stdio.h>
#include <string.h>
#include <iconv.h>
#include <stdlib.h>

#include <stdbool.h> 


bool IsUTF8(const void* pBuffer, long size)  
{  
        bool IsUTF8 = true;  
        unsigned char* start = (unsigned char*)pBuffer;  
        unsigned char* end = (unsigned char*)pBuffer + size;  
        while (start < end)  
        {  
                if (*start < 0x80) // (10000000): 值小于0x80的为ASCII字符    
                {  
                        start++;  
                }  
                else if (*start < (0xC0)) // (11000000): 值介于0x80与0xC0之间的为无效UTF-8字符    
                {  
                        IsUTF8 = false;  
                        break;  
                }  
                else if (*start < (0xE0)) // (11100000): 此范围内为2字节UTF-8字符    
                {  
                        if (start >= end - 1)  
                        {  
                                break;  
                        }  

                        if ((start[1] & (0xC0)) != 0x80)  
                        {  
                                IsUTF8 = false;  
                                break;  
                        }  

                        start += 2;  
                }  
                else if (*start < (0xF0)) // (11110000): 此范围内为3字节UTF-8字符    
                {  
                        if (start >= end - 2)  
                        {  
                                break;  
                        }  

                        if ((start[1] & (0xC0)) != 0x80 || (start[2] & (0xC0)) != 0x80)  
                        {  
                                IsUTF8 = false;  
                                break;  
                        }  

                        start += 3;  
                }  
                else  
                {  
                        IsUTF8 = false;  
                        break;  
                }  
        }  

        return IsUTF8;  
}  

int ChangeCode( const char* pFromCode,
                const char* pToCode,
                const char* pInBuf,
                size_t* iInLen,
                char* pOutBuf,
                size_t* iOutLen );

int main( int argc, char* argv[] )
{
        char sInBuf[100];
        char sOutBuf[100];
        size_t iInLen = 0;
        size_t iOutLen = 100;
        int iRet;


        //char *orign_str = "0xe4b881e4baae";
        char *orign_str = "0xC0D6CAD3";
        int pos = 0;

        char str[100] = {0};
        orign_str = orign_str+2;
        for(;;pos++) {
                if(pos>99 || orign_str[2*pos] == 0 || orign_str[2*pos+1] == 0)
                        break;

                sscanf(orign_str+2*pos, "%2x", &str[pos]);
        }

        if(IsUTF8(str, strlen(str))){
                printf("UTF-8, str=[%s]\n", str);
                printf("\n");
        }else{
                strcpy( sInBuf, str);
                memset( sOutBuf, 0x00, 100 );
                iInLen = strlen( sInBuf );
                iRet = ChangeCode( "GBK", "UTF-8", sInBuf, &iInLen, sOutBuf, &iOutLen );

                printf("Gbk  dddddddddd %s\n",sOutBuf);
        }
        return 0;
}

int ChangeCode( const char* pFromCode,
                const char* pToCode,
                const char* pInBuf,
                size_t* iInLen,
                char* pOutBuf,
                size_t* iOutLen )
{
        int iRet;
        iconv_t hIconv = iconv_open( pToCode, pFromCode );
        if ( -1 == (int)hIconv )
        {
                return -1;
        }
        iRet = iconv( hIconv, (const char**)(&pInBuf), iInLen, (char**)(&pOutBuf), iOutLen );
        iconv_close( hIconv );
        return iRet;
}
试试其它关键字
同语言下
可能有用的
珍灵贡献的其它代码(6)