文本文件的编码格式识别功能 (UTF-8,ANSI,UTF-16)

代码:

enum ENCODETYPE
{
    UNKNOW,
    ANSI,
    UTF8,
    UTF16
    };
ENCODETYPE TellEncodeType(BYTE* pBuf,int bufLen)
{
ENCODETYPE filetype=UNKNOW;

if (pBuf[0]==0xFF && pBuf[1]==0xFE
    || pBuf[0]==0xFE && pBuf[1]==0xFF)
    filetype=UTF16;
else
{
    int    utf8Nums=0;    //符合UTF8编码的字符个数,非Ansi部分
    int count=0;
    while(count         {
        int i=0;
        while( i             {
            if (pBuf[count+i]>0xC0)
            {
                if (pBuf[count+i+1]<0x80 || pBuf[count+i+1]>0xC0)
                {
                    filetype=ANSI;
                    break;
                }
                else
                {
                    /*
                    The transformation table for UTF-8 is presented below:
                    UNICODE                 UTF-8
                    00000000 - 0000007F     0xxxxxxx
                    00000080 - 000007FF     110xxxxx 10xxxxxx
                    00000800 - 0000FFFF     1110xxxx 10xxxxxx 10xxxxxx                          //0xE0
                    00010000 - 001FFFFF     11110xxx 10xxxxxx 10xxxxxx 10xxxxxx                 //0xF0
                    00200000 - 03FFFFFF      111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx        //0xF8
                    04000000 - 7FFFFFFF     1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx   //0xFC
                    */

                    BYTE *tC;//target Char to 识别

                    int utfStrLen=0;
                    //是否为正确的UTF8格式
                    tC=pBuf+count+i;

                    if (tC[0]<=0xF0)//<4字节
                        if(tC[0]>0xE0)    utfStrLen=3;
                        else              utfStrLen=2;   
                    else if (tC[0]>=0xFC) utfStrLen=6;
                    else if(tC[0]>=0xF8)  utfStrLen=5;
                    else                  utfStrLen=4;

                    int k=1;
                    while(k                         {
                        if (!(tC[k] & 0x80 && !(tC[k]& 0x40) ))//前二位为10
                        {
                            filetype=ANSI;
                            break;
                        }

                        k++;
                    }

                    if (k==utfStrLen)
                        utf8Nums++;
                    if (utf8Nums==10)
                        filetype=UTF8;
                }
            }

            i++;
        }//while( i
        ++count;
    }//while(count
}//else


return filetype;
}

调用例子

 LRESULT OnOpenFile(WORD /*wNotifyCode*/, WORD /*wID*/, HWND /*hWndCtl*/, BOOL& /*bHandled*/)
{
    //const TCHAR szFilter[]=_T("playlist files(*.pl)\0*.pl\0");
    CFileDialog dlg(TRUE,NULL,NULL,OFN_FILEMUSTEXIST|OFN_DONTADDTORECENT,NULL,m_hWnd);
    if(dlg.DoModal()!=IDOK)return 0;

    LPTSTR filepath=dlg.m_ofn.lpstrFile;

    ENCODETYPE filetype=UNKNOW;
    BYTE * pBuf;
    FILE * pFile;
    pFile = _tfopen( filepath, _T("rb") );
    if (pFile!=NULL)
    {
        //get the file size
        fseek(pFile,0,SEEK_END);
        int filesize=ftell(pFile);
        pBuf=(BYTE*)malloc(filesize);

        fseek(pFile,0,SEEK_SET);
        fread(pBuf,1,filesize,pFile);

        filetype=TellEncodeType(pBuf,filesize);
        fclose (pFile);
    }
    return 0;
}

你可能感兴趣的:(文本文件的编码格式识别功能 (UTF-8,ANSI,UTF-16))