几个多字节和UNICODE及UTF-8之间相互转化的函数

时间:2023-01-14 22:24:22

 做vc++开发免不了多字节UNICODE、UTF-8转来转去,下面贴出我写的几个字符转化函数

 1、 TCHAR  和CHAR转化, TCHAR 对应UNICODE和多字节下分别是WCHAR 和CHAR 函数如下:

  需要注意*dest是new出来的需要释放

//char 字符串转化为tchar字符串
void C2T(TCHAR** dest, const char* src)
{
#ifdef _UNICODE
    if (src == NULL)
    {
        return ;
    }

    size_t alen = strlen(src) + 1;
    size_t  ulen = (size_t)MultiByteToWideChar(CP_ACP, 0, src,alen,NULL, 0 )+1;

    *dest = new WCHAR[ulen];
    ::MultiByteToWideChar(CP_ACP, 0, src, alen, *dest, ulen);
#else 
    //多字节TCHAR就是 char 
    int len = strlen(src)+1;
    *dest = new char[len];
    strcpy(*dest, src);
#endif
}

2、TCHAR转化为多字节,同样要注意*dest指针释放

void T2C(char** dest, const TCHAR* src)
{
    if(src == NULL)
        return ;
#ifdef _UNICODE
    size_t len = WideCharToMultiByte(CP_ACP, 0, src, -1, NULL, 0 , NULL, NULL);
    if (len == 0)
    {
        return;
    }
    *dest = new char[len];
    WideCharToMultiByte( CP_ACP, 0, src, -1, *dest, len, NULL, NULL );
#else
    int len = _tcslen(src) + 1;
    *dest = new TCHAR[len];
    strcpy(*dest, src);
#endif
}

3、下面两个函数跟上面的有点重复但是后面会用到,也贴出来

//多字节转化为宽字节
void C2W(WCHAR** dest, const char* src)
{
    if (src == NULL)
    {
        return ;
    }

    size_t alen = strlen(src) + 1;
    size_t  ulen = (size_t)MultiByteToWideChar(CP_ACP, 0, src,alen,NULL, 0 )+1;

    *dest = new WCHAR[ulen];
    ::MultiByteToWideChar(CP_ACP, 0, src, alen, *dest, ulen);
}

//宽字节转化为多字节
void W2C(char** dest, const WCHAR *src)
{
    if(src == NULL)
        return ;
    size_t len = WideCharToMultiByte(CP_ACP, 0, src, -1, NULL, 0 , NULL, NULL);
    if (len == 0)
    {
        return;
    }
    *dest = new char[len];
    WideCharToMultiByte( CP_ACP, 0, src, -1, *dest, len, NULL, NULL );

}

4、UTF-8和多字节及宽字节之间的转化

//UNICODE可以直接转化为UTF-8 
void UnicodeToUtf8(char** dest , const WCHAR* src)
 {
      ASSERT(dest!= NULL || src != NULL);
      int len = -1;
      len = WideCharToMultiByte(CP_UTF8, 0, src, -1, 0, 0, 0, 0)+1;
      *dest = new char[len+1];
      ::WideCharToMultiByte(CP_UTF8, 0, src, -1,*dest, len, 0, 0);
 }

//多字节要先转化为宽字节在转化为UTF-8
void AnsiToUtf8(char** dest, const char* src)
 {
    ASSERT(dest!= NULL || src != NULL);
    WCHAR* pwszStr = NULL;
    C2W(&pwszStr, src);
    UnicodeToUtf8(dest, pwszStr);
    SAFE_ARRYDELETE(pwszStr);
 }

UTF-8转化为多字节或者UNICODE:

 void Utf8ToAnsi(char** dest, const char* src)
 {
     ASSERT(dest!= NULL || src != NULL);
     WCHAR* str = NULL;
     Utf8ToUnicode(&str, src);
     W2C(dest, str);
     SAFE_ARRYDELETE(str);
 }

void Utf8ToUnicode(WCHAR** dest,const char* src)
{
    ASSERT(dest!= NULL || src != NULL);
    int unicodeLen = ::MultiByteToWideChar( CP_UTF8, 0, src, -1, NULL, 0 ) + 1;  
    
    *dest = new WCHAR[unicodeLen];
    //memset(*dest, 0x0, (unicodeLen + 1)*sizeof(WCHAR));
    MultiByteToWideChar(CP_UTF8, 0, src, -1, *dest, unicodeLen);

}

 

SAFE_ARRYDELETE是一个内存是释放宏如下

#define SAFE_ARRYDELETE(x) if(NULL!=x){delete[] x;x = NULL;}

#define SAFE_DELETE(x) if(NULL!=x){delete x; x =NULL;}

 

有了以上函数基本上不同编码间可以随意转,大家也还可以对以上这些函数尽心扩展,需要注意的是上面这些函数中dest指向的指针需要释放。