字符串UTF-8和GBK之间的转换以及判定

一、判定字符串是否是UTF-8的编码

bool is_str_utf8(const char* str)
{
    unsigned int nBytes = ;//UFT8可用1-6个字节编码,ASCII用一个字节
    unsigned char chr = *str;
    bool bAllAscii = true;

    for (unsigned int i = ; str[i] != '\0'; ++i)
    {
        chr = *(str + i);
        //判断是否ASCII编码,如果不是,说明有可能是UTF8,ASCII用7位编码,最高位标记为0,0xxxxxxx
        if (nBytes ==  && (chr & 0x80) != )
        {
            bAllAscii = false;
        }

        if (nBytes == )
        {
            //如果不是ASCII码,应该是多字节符,计算字节数
            if (chr >= 0x80)
            {
                if (chr >= 0xFC && chr <= 0xFD)
                {
                    nBytes = ;
                }
                else if (chr >= 0xF8)
                {
                    nBytes = ;
                }
                else if (chr >= 0xF0)
                {
                    nBytes = ;
                }
                else if (chr >= 0xE0)
                {
                    nBytes = ;
                }
                else if (chr >= 0xC0)
                {
                    nBytes = ;
                }
                else
                {
                    return false;
                }
                nBytes--;
            }
        }
        else
        {
            //多字节符的非首字节,应为 10xxxxxx
            if ((chr & 0xC0) != 0x80)
            {
                return false;
            }
            //减到为零为止
            nBytes--;
        }
    }

    //违返UTF8编码规则
    if (nBytes != )
    {
        return false;
    }

    if (bAllAscii)
    { //如果全部都是ASCII, 也是UTF8
        return true;
    }

    return true;
}

二、判定字符串是否是GBk的编码

bool is_str_gbk(const char* str)
{
    unsigned int nBytes = ;//GBK可用1-2个字节编码,中文两个 ,英文一个
    unsigned char chr = *str;
    bool bAllAscii = true; //如果全部都是ASCII,  

    for (unsigned int i = ; str[i] != '\0'; ++i)
    {
        chr = *(str + i);
        if ((chr & 0x80) !=  && nBytes == )
        {// 判断是否ASCII编码,如果不是,说明有可能是GBK
            bAllAscii = false;
        }

        if (nBytes == )
        {
            if (chr >= 0x80)
            {
                if (chr >= 0x81 && chr <= 0xFE)
                {
                    nBytes = +;
                }
                else
                {
                    return false;
                }
                nBytes--;
            }
        }
        else
        {
            if (chr < 0x40 || chr>0xFE)
            {
                return false;
            }
            nBytes--;
        }//else end
    }

    if (nBytes != )
    {    //违返规则
        return false;
    }

    if (bAllAscii)
    { //如果全部都是ASCII, 也是GBK
        return true;
    }

    return true;
}

三、字符串由GBk编码转换成UTF-8编码

void ConvertGBKToUtf8(CString &strGBK)
 {
  int len=MultiByteToWideChar(CP_ACP, , (LPCTSTR)strGBK, -, NULL,);
  wchar_t * wszUtf8 = new wchar_t [len];
  memset(wszUtf8, , len);
  MultiByteToWideChar(CP_ACP, , (LPCTSTR)strGBK, -, wszUtf8, len);
  len = WideCharToMultiByte(CP_UTF8, , wszUtf8, -, NULL, , NULL, NULL);
  char *szUtf8=new char[len + ];
  memset(szUtf8, , len + );
  WideCharToMultiByte (CP_UTF8, , wszUtf8, -, szUtf8, len, NULL,NULL);
  strGBK = szUtf8;
  delete[] szUtf8;
  delete[] wszUtf8;
 }

string GBKToUTF8(const char* strGBK)
{
    int len = MultiByteToWideChar(CP_ACP, , strGBK, -, NULL, );
    wchar_t* wstr = new wchar_t[len+];
    memset(wstr, , len+);
    MultiByteToWideChar(CP_ACP, , strGBK, -, wstr, len);
    len = WideCharToMultiByte(CP_UTF8, , wstr, -, NULL, , NULL, NULL);
    char* str = new char[len+];
    memset(str, , len+);
    WideCharToMultiByte(CP_UTF8, , wstr, -, str, len, NULL, NULL);
    string strTemp = str;
    if(wstr) delete[] wstr;
    if(str) delete[] str;
    return strTemp;
}  

四、字符串由UTF-8编码转换成GBk编码

string UtfToGbk(const char* utf8)
{
    int len = MultiByteToWideChar(CP_UTF8, , utf8, -, NULL, );
    wchar_t* wstr = new wchar_t[len+];
    memset(wstr, , len+);
    MultiByteToWideChar(CP_UTF8, , utf8, -, wstr, len);
    len = WideCharToMultiByte(CP_ACP, , wstr, -, NULL, , NULL, NULL);
    char* str = new char[len+];
    memset(str, , len+);
    WideCharToMultiByte(CP_ACP, , wstr, -, str, len, NULL, NULL);
    if(wstr) delete[] wstr;
    return str;
}

bool Utf82gbk(std::string &gbkStr, std::string &srcStr)
{

    //首先先将utf-8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 false;
    }

    int unicodeLen=mbstowcs(NULL,srcStr.c_str(),);//计算转换后的长度
    if(unicodeLen<=)
    {
        printf("Can not Transfer!!!\n");
        return false;
    }
    wchar_t *unicodeStr=(wchar_t *)calloc(sizeof(wchar_t),unicodeLen+);
    mbstowcs(unicodeStr,srcStr.c_str(),srcStr.size());//将gbk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 false;
    }
    int gbkLen = wcstombs(NULL,unicodeStr,);//计算转换后的长度
    if(gbkLen<=)
    {
        printf("Can not Transfer!!!\n");
        return false;
    }
    char gbkbuf[*];
    wcstombs(gbkbuf,unicodeStr,gbkLen);
    gbkbuf[gbkLen]=;//添加结束符
    gbkStr = gbkbuf;
    free(unicodeStr);
    return true;
}

string UTF8ToGBK(const std::string& strUTF8)
{
    int len = MultiByteToWideChar(CP_UTF8, , strUTF8.c_str(), -, NULL, );
    WCHAR* wszGBK = new WCHAR[len+];
    memset(wszGBK, , len *  + );
    MultiByteToWideChar(CP_UTF8, , (LPCSTR)(LPCTSTR)strUTF8.c_str(), -, wszGBK, len);    

    len = WideCharToMultiByte(CP_ACP, , wszGBK, -, NULL, , NULL, NULL);
    char *szGBK = new char[len + ];
    memset(szGBK, , len + );
    WideCharToMultiByte(CP_ACP,, wszGBK, -, szGBK, len, NULL, NULL);
    std::string strTemp(szGBK);
    delete[]szGBK;
    delete[]wszGBK;
    return strTemp;
}