utf8与unicode转码问题

Question

1.如将带中文的字符串转成unicode的格式，然后如何再转回来，

注：字符串中既有英文又有中文
代码由C语言实现。

Answer 1

https://www.cnblogs.com/cfas/p/7931787.html
这个试试

/*****************************************************************************
* 将一个字符的UTF8编码转换成Unicode(UCS-2和UCS-4)编码.
*
* 参数:
*    pInput      指向输入缓冲区, 以UTF-8编码
*    Unic        指向输出缓冲区, 其保存的数据即是Unicode编码值,
*                类型为unsigned long .
*
* 返回值:
*    成功则返回该字符的UTF8编码所占用的字节数; 失败则返回0.
*
* 注意:
*     1. UTF8没有字节序问题, 但是Unicode有字节序要求;
*        字节序分为大端(Big Endian)和小端(Little Endian)两种;
*        在Intel处理器中采用小端法表示, 在此采用小端法表示. (低地址存低位)
****************************************************************************/
int enc_utf8_to_unicode_one( const /*unsigned*/ char* pInput, unsigned int length,/*unsigned*/ char *Unic )
{
    assert( pInput != NULL && Unic != NULL );

    // b1 表示UTF-8编码的pInput中的高字节, b2 表示次高字节, ...
    char b1, b2, b3, b4, b5, b6;

    int utfbytes = 0;
    unsigned char *pOutput = ( unsigned char * )Unic;
    int n = 0;
    while ( true )
    {

        //*Unic = 0x0; // 把 *Unic 初始化为全零
        utfbytes = enc_get_utf8_size( *pInput );

        switch ( utfbytes )
        {
        case 0:
            *pOutput = *pInput;
            utfbytes += 1;
            break;
        case 2:
            b1 = *pInput;
            b2 = *( pInput + 1 );
            if ( ( b2 & 0xE0 ) != 0x80 )
                return 0;
            *pOutput = ( b1 << 6 ) + ( b2 & 0x3F );
            *( pOutput + 1 ) = ( b1 >> 2 ) & 0x07;
            break;
        case 3:
            b1 = *pInput;
            b2 = *( ++pInput );
            b3 = *( ++pInput );
            if ( ( ( b2 & 0xC0 ) != 0x80 ) || ( ( b3 & 0xC0 ) != 0x80 ) )
                return 0;
            *(pOutput+n) = ( b2 << 6 ) + ( b3 & 0x3F );
            *( pOutput+n+1  ) = ( b1 << 4 ) + ( ( b2 >> 2 ) & 0x0F );
            n += 2;
            break;
        case 4:
            b1 = *pInput;
            b2 = *( pInput + 1 );
            b3 = *( pInput + 2 );
            b4 = *( pInput + 3 );
            if ( ( ( b2 & 0xC0 ) != 0x80 ) || ( ( b3 & 0xC0 ) != 0x80 )
                || ( ( b4 & 0xC0 ) != 0x80 ) )
                return 0;
            *pOutput = ( b3 << 6 ) + ( b4 & 0x3F );
            *( pOutput + 1 ) = ( b2 << 4 ) + ( ( b3 >> 2 ) & 0x0F );
            *( pOutput + 2 ) = ( ( b1 << 2 ) & 0x1C ) + ( ( b2 >> 4 ) & 0x03 );
            break;
        case 5:
            b1 = *pInput;
            b2 = *( pInput + 1 );
            b3 = *( pInput + 2 );
            b4 = *( pInput + 3 );
            b5 = *( pInput + 4 );
            if ( ( ( b2 & 0xC0 ) != 0x80 ) || ( ( b3 & 0xC0 ) != 0x80 )
                || ( ( b4 & 0xC0 ) != 0x80 ) || ( ( b5 & 0xC0 ) != 0x80 ) )
                return 0;
            *pOutput = ( b4 << 6 ) + ( b5 & 0x3F );
            *( pOutput + 1 ) = ( b3 << 4 ) + ( ( b4 >> 2 ) & 0x0F );
            *( pOutput + 2 ) = ( b2 << 2 ) + ( ( b3 >> 4 ) & 0x03 );
            *( pOutput + 3 ) = ( b1 << 6 );
            break;
        case 6:
            b1 = *pInput;
            b2 = *( pInput + 1 );
            b3 = *( pInput + 2 );
            b4 = *( pInput + 3 );
            b5 = *( pInput + 4 );
            b6 = *( pInput + 5 );
            if ( ( ( b2 & 0xC0 ) != 0x80 ) || ( ( b3 & 0xC0 ) != 0x80 )
                || ( ( b4 & 0xC0 ) != 0x80 ) || ( ( b5 & 0xC0 ) != 0x80 )
                || ( ( b6 & 0xC0 ) != 0x80 ) )
                return 0;
            *pOutput = ( b5 << 6 ) + ( b6 & 0x3F );
            *( pOutput + 1 ) = ( b5 << 4 ) + ( ( b6 >> 2 ) & 0x0F );
            *( pOutput + 2 ) = ( b3 << 2 ) + ( ( b4 >> 4 ) & 0x03 );
            *( pOutput + 3 ) = ( ( b1 << 6 ) & 0x40 ) + ( b2 & 0x3F );
            break;
        default:
            return 0;
            break;
        }
        length -= utfbytes;
        if ( length <= 0 )
            break;
        else
            ++pInput;
    }
    return utfbytes;
}
int main( int argc, char** argv )
{   
        string utf8 = CodeConverter::UnicodeToUtf8( L"成都" );
        wstring unicode = CodeConverter::Utf8ToUnicode( wsdd );
        char Unic[ 512 ] = { 0 };
        enc_utf8_to_unicode_one( wsdd.c_str(), wsdd.size(), Unic );
    }