《UTF-8与GB2312之间的互换》的改进

 

 在UTF-8,与UNICODE之间转换的时候，用二进制运算，代替了字符串的转换。

UTF-8一个汉字，用3个字节，而UNICODE用2个字节。

 

对应关系如下：

UTF-8编码： [1,1,1,0,A5,A6,A7,A8], [1,0,B3,B4,B5,B6,B7,B8], [1,0,C3,C4,C5,C6,C7,C8];

对应的UNICODE编码：[A5,A6,A7,A8,B3,B4,B5,B6], [B7,B8,C3,C4,C5,C6,C7,C8] 。

因此我们只需进行位操作，即可达到目的；

 

如： // 把UTF-8转换成Unicode

void CChineseCodeLib::UTF_8ToUnicode(WCHAR* pOut,char *pText)

 {

    char* uchar = (char *)pOut;

     uchar = ((pText[0] & 0x0F) << 4) + ((pText >> 2) & 0x0F);

     uchar[0] = ((pText & 0x03) << 6) + (pText & 0x3F); return;

}

 

// Unicode 转换成UTF-8

void CChineseCodeLib::UnicodeToUTF_8(char* pOut,WCHAR* pText)

{

 // 注意 WCHAR高低字的顺序,低字节在前，高字节在后

    char* pchar = (char *)pText;

    pOut[0] = (0xE0 | ((pchar & 0xF0) >> 4));

    pOut = (0x80 | ((pchar & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);

    pOut = (0x80 | (pchar[0] & 0x3F)); return;

}

 

// 把Unicode 转换成 GB2312

void CChineseCodeLib::UnicodeToGB2312(char* pOut,unsigned short uData)

{

    WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL);

    return;

}

 

// GB2312 转换成 Unicode

 void CChineseCodeLib::Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer)

{

    ::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);

    return;

}

 

//GB2312 转为 UTF-8

void CChineseCodeLib::GB2312ToUTF_8(string& pOut,char *pText, int pLen)

{

     char buf; char* rst = new char[pLen + (pLen >> 2) + 2];

     memset(buf,0,4); memset(rst,0,pLen + (pLen >> 2) + 2);

     int i = 0;

    int j = 0;

     while(i < pLen)

     {

        //如果是英文直接复制就可以

        if( *(pText + i) >= 0)

                 { rst[j++] = pText[i++]; }

        else

                 { WCHAR pbuffer; Gb2312ToUnicode(&pbuffer,pText+i);

                    UnicodeToUTF_8(buf,&pbuffer);

                     unsigned short int tmp = 0;

                     tmp = rst[j] = buf[0];

                     tmp = rst[j+1] = buf;

                     tmp = rst[j+2] = buf;

                     j += 3; i += 2;

                  }

        }

        rst[j] = ''/0'';

        //返回结果

         pOut = rst;

        delete []rst;

        return;

}

 

 //UTF-8 转为 GB2312

void CChineseCodeLib::UTF_8ToGB2312(string &pOut, char *pText, int pLen)

{

    char * newBuf = new char[pLen];

     char Ctemp; memset(Ctemp,0,4);

    int i =0;

    int j = 0;

    while(i < pLen)

    {

        if(pText[i] > 0)

            { newBuf[j++] = pText[i++]; }

        else

            {

                WCHAR Wtemp;

                UTF_8ToUnicode(&Wtemp,pText + i);

                UnicodeToGB2312(Ctemp,Wtemp);

                newBuf[j] = Ctemp[0];

                newBuf[j + 1] = Ctemp; i += 3; j += 2;

             }

    }

    newBuf[j] = ''/0'';

    pOut = newBuf;

    delete []newBuf;.

     return;

 } 代码在WIN2K,VC++60 下编译，测试通过.