标准CSV格式的介绍和分析以及解析算法实例详解

BOOL CCSV2Json::Parse() 
{ 
  BOOL bSuc = FALSE; 
  do { 
    if ( INVALID_HANDLE_VALUE == m_hFile ) { 
      break; 
    } 
    OVERLAPPED ov; 
    memset(&ov, 0, sizeof(OVERLAPPED)); 
    BYTE lpBuffer[BUFFERSIZE] = {0}; 
    DWORD dwHaveRead = 0; 
    std::string strSingle; 
    BOOL bFirstDoubleQuotes = FALSE;  // 第一个字符是否为" 
    BOOL bBeforeIsDoubleQuotes = FALSE;  
    BOOL bBeforeIsX0D = FALSE; 
    ListString Liststr; 
    BOOL bPairDoubleQuotes = FALSE; 
    while ( ReadFile(m_hFile, lpBuffer, sizeof(lpBuffer), &dwHaveRead, &ov ) ) { 
      ov.Offset += dwHaveRead; 
      for ( DWORD dwIndex = 0; dwIndex < dwHaveRead; dwIndex++ ) { 
        BYTE& by = *(lpBuffer + dwIndex); 
 
        if ( bFirstDoubleQuotes ) { 
          // 有前置" 
          if ( IsDoubleQuotes(by) ) { 
            bBeforeIsX0D = FALSE; 
            if ( bBeforeIsDoubleQuotes ) { 
              strSingle.append(1, (char)(by)); 
              bBeforeIsDoubleQuotes = FALSE; 
            } 
            else { 
              bBeforeIsDoubleQuotes = TRUE; 
            } 
          } 
          else { 
            if ( bBeforeIsDoubleQuotes ) { 
              bFirstDoubleQuotes = FALSE; 
            } 
            bBeforeIsDoubleQuotes = FALSE; 
            if ( IsCRLF( by ) ){ 
              if ( bFirstDoubleQuotes ) { 
                strSingle.append(1, (char)(by)); 
              } 
              else if (FALSE == bBeforeIsX0D) { 
                Liststr.push_back(strSingle); 
                m_Listliststr.push_back(Liststr); 
                Liststr.clear(); 
                strSingle.clear(); 
                bFirstDoubleQuotes = FALSE; 
              } 
              bBeforeIsX0D = IsX0D(by); 
            } 
            else if ( IsSep(by) ) { 
              bBeforeIsX0D = FALSE; 
              if ( bFirstDoubleQuotes ) { 
                strSingle.append(1, (char)(by)); 
              } 
              else { 
                bBeforeIsX0D = FALSE; 
                Liststr.push_back(strSingle); 
                strSingle.clear(); 
              } 
            } 
            else { 
              bBeforeIsX0D = FALSE; 
              strSingle.append(1, (char)(by)); 
            } 
          } 
        } 
        else{ 
          // 如果无前置" 
          if ( IsDoubleQuotes(by) ) { 
            bBeforeIsX0D = FALSE; 
            if ( strSingle.empty() ) { 
              // 空串，第一个是" 
              bFirstDoubleQuotes = TRUE; 
              bBeforeIsDoubleQuotes = FALSE; 
            } 
            else { 
              strSingle.append(1,(char)(by)); 
              continue; 
            } 
          } 
          else { 
            bBeforeIsDoubleQuotes = FALSE; 
            if ( IsCRLF( by ) ){ 
              if (FALSE == bBeforeIsX0D) { 
                Liststr.push_back(strSingle); 
                m_Listliststr.push_back(Liststr); 
                Liststr.clear(); 
                strSingle.clear(); 
                bFirstDoubleQuotes = FALSE; 
                bBeforeIsDoubleQuotes = FALSE; 
              } 
              else { 
                // 连续\r\n不考虑设置为新的行 
              } 
              bBeforeIsX0D = IsX0D(by); 
            } 
            else if ( IsSep(by) ) { 
              bBeforeIsX0D = FALSE; 
              Liststr.push_back(strSingle); 
              strSingle.clear(); 
            } 
            else { 
              bBeforeIsX0D = FALSE; 
              strSingle.append(1, (char)(by)); 
            } 
          } 
        } 
 
      } 
      memset(lpBuffer, 0, sizeof(lpBuffer));    
    } 
     
    if ( false == strSingle.empty() ) { 
//       while ( IsCRLF(strSingle.at(strSingle.length() - 1) ) && strSingle.length() > 0) { 
//         strSingle = strSingle.substr(0, strSingle.length() - 1 ); 
//       } 
      Liststr.push_back(strSingle); 
      m_Listliststr.push_back(Liststr); 
      Liststr.clear(); 
      strSingle.clear(); 
    } 
 
    bSuc = TRUE; 
  } while (0); 
   
  if ( NULL != m_hFile ) { 
    CloseHandle(m_hFile); 
    m_hFile = NULL; 
  } 
   
  return bSuc; 
}