CStdioFileEx读取Unicode文本

最新推荐文章于 2023-04-25 11:46:34 发布

yaoohfox

最新推荐文章于 2023-04-25 11:46:34 发布

阅读量4.8k

点赞数 1

CC 4.0 BY-SA版权

文章标签： parameters character string byte output delete

本文链接：https://blog.youkuaiyun.com/yaoohfox/article/details/4139036

本文介绍了一个扩展的 CStdioFileEx 类，该类能够自动识别并处理 ANSI 和 UNICODE 格式的文本文件。通过重写读写方法，实现了对不同编码文件的兼容。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

最近因为要读取SQL脚本文件，用CStdioFile来读取脚本文件，却在程序调试时读取不了文件。
后来看了一下文本文件格式，竟然是UNICODE格式的，原来在导出ＳＱＬ脚本的时候，选项默认的是UNICODE格式。为了同时支持ANSI和UNICODE两种格式，在Codeproject站点上找到了CStdioFileEx类的代码，但在调试运行过程中发现，在生成UNICODE版本的执行文件时，运行没有错误，但在非UNICODE版本中却出现错误，原来在代码中此部分没有考虑文件读到末尾的情况，经修改，CStdioFileEx类就可以正常使用了，在读取文本文件时，自动识别ANSI和UNICODE两种格式。
实现头文件如下：

#define nUNICODE_BOM      0xFEFF  // Unicode "byte order mark" which goes at start of file
#define sNEWLINE        _T("/r/n") // New line characters
#define sDEFAULT_UNICODE_FILLER_CHAR "#"   // Filler char used when no conversion from Unicode to local code page is possible

class CStdioFileEx: public CStdioFile
{
public:
CStdioFileEx();
CStdioFileEx( LPCTSTR lpszFileName, UINT nOpenFlags );

virtual BOOL Open( LPCTSTR lpszFileName, UINT nOpenFlags, CFileException* pError = NULL );
virtual BOOL ReadString(CString& rString);
virtual void WriteString( LPCTSTR lpsz );
bool IsFileUnicodeText() { return m_bIsUnicodeText; }
unsigned long GetCharCount();

// Additional flag to allow Unicode text writing
static const UINT modeWriteUnicode;

// static utility functions

// --------------------------------------------------------------------------------------------
//
// CStdioFileEx::GetUnicodeStringFromMultiByteString()
//
// --------------------------------------------------------------------------------------------
// Returns:    bool
// Parameters: char *  szMultiByteString  (IN) Multi-byte input string
//     wchar_t*  szUnicodeString  (OUT) Unicode output string
//     short   nUnicodeBufferSize (IN) Size of Unicode output buffer
//     UINT   nCodePage    (IN) Code page used to perform conversion
//                  Default = -1 (Get local code page).
//
// Purpose:  Gets a Unicode string from a MultiByte string.
// Notes:  None.
// Exceptions: None.
//
static bool  GetUnicodeStringFromMultiByteString(char * szMultiByteString,wchar_t* szUnicodeString,
                   short nUnicodeBufferSize,UINT nCodePage=-1);

// --------------------------------------------------------------------------------------------
//
// CStdioFileEx::GetMultiByteStringFromUnicodeString()
//
// --------------------------------------------------------------------------------------------
// Returns:    BOOL
// Parameters: wchar_t * szUnicodeString   (IN) Unicode input string
//     char*   szMultiByteString   (OUT) Multibyte output string
//     short   nMultiByteBufferSize  (IN) Multibyte buffer size
//     UINT   nCodePage     (IN) Code page used to perform conversion
//                   Default = -1 (Get local code page).
//
// Purpose:  Gets a MultiByte string from a Unicode string.
// Notes:  .
// Exceptions: None.
//
static BOOL   GetMultiByteStringFromUnicodeString(wchar_t * szUnicodeString,char* szMultiByteString,
                   short nMultiByteBufferSize,UINT nCodePage=-1);

// --------------------------------------------------------------------------------------------
//
// CStdioFileEx::IsFileUnicode()
//
// --------------------------------------------------------------------------------------------
// Returns:    bool
// Parameters: const CString& sFilePath
//
// Purpose:  Determines whether a file is Unicode by reading the first character and detecting
//     whether it's the Unicode byte marker.
// Notes:  None.
// Exceptions: None.
//
static bool IsFileUnicode(const CString& sFilePath);

protected:
UINT ProcessFlags(const CString& sFilePath, UINT& nOpenFlags);

bool m_bIsUnicodeText;
UINT m_nFlags;
};

实现文件如下：

/*static*/ const UINT CStdioFileEx::modeWriteUnicode = 0x20000; // Add this flag to write in Unicode

CStdioFileEx::CStdioFileEx(): CStdioFile()
{
m_bIsUnicodeText = false;
}

CStdioFileEx::CStdioFileEx(LPCTSTR lpszFileName,UINT nOpenFlags)
:CStdioFile(lpszFileName, ProcessFlags(lpszFileName, nOpenFlags))
{
}

BOOL CStdioFileEx::Open(LPCTSTR lpszFileName,UINT nOpenFlags,CFileException* pError /*=NULL*/)
{
// Process any Unicode stuff
ProcessFlags(lpszFileName, nOpenFlags);

return CStdioFile::Open(lpszFileName, nOpenFlags, pError);
}

BOOL CStdioFileEx::ReadString(CString& rString)
{
const int nMAX_LINE_CHARS = 4096;
BOOL   bReadData;
LPTSTR  lpsz;
int   nLen = 0; //, nMultiByteBufferLength = 0, nChars = 0;
CString  sTemp;
wchar_t*  pszUnicodeString = NULL;
char *  pszMultiByteString= NULL;

// If at position 0, discard byte-order mark before reading
if (!m_pStream || (GetPosition() == 0 && m_bIsUnicodeText))
{
  wchar_t cDummy;
//  Read(&cDummy, sizeof(_TCHAR));
  Read(&cDummy, sizeof(wchar_t));
}

// If compiled for Unicode
#ifdef _UNICODE
// Do standard stuff -- both ANSI and Unicode cases seem to work OK
bReadData = CStdioFile::ReadString(rString);
#else

if (!m_bIsUnicodeText)
{
  // Do standard stuff -- read ANSI in ANSI
  bReadData = CStdioFile::ReadString(rString);
}
else
{
  pszUnicodeString = new wchar_t[nMAX_LINE_CHARS];
  pszMultiByteString= new char[nMAX_LINE_CHARS];

// Read as Unicode, convert to ANSI

  if(fgetws(pszUnicodeString, nMAX_LINE_CHARS, m_pStream)==NULL)
  {
   bReadData=FALSE;
  }
  else
  {
   bReadData=TRUE;
   if (GetMultiByteStringFromUnicodeString(pszUnicodeString, pszMultiByteString, nMAX_LINE_CHARS))
   {
    rString = (CString)pszMultiByteString;
   }

   if (pszUnicodeString)
   {
    delete pszUnicodeString;
   }

   if (pszMultiByteString)
   {
    delete pszMultiByteString;
   }
  }
}
#endif

// Then remove end-of-line character if in Unicode text mode
if (bReadData)
{
  // Copied from FileTxt.cpp but adapted to Unicode and then adapted for end-of-line being just '/r'.
  nLen = rString.GetLength();
  if (nLen > 1 && rString.Mid(nLen-2) == sNEWLINE)
  {
   rString.GetBufferSetLength(nLen-2);
  }
  else
  {
   lpsz = rString.GetBuffer(0);
   if (nLen != 0 && (lpsz[nLen-1] == _T('/r') || lpsz[nLen-1] == _T('/n')))
   {
    rString.GetBufferSetLength(nLen-1);
   }
  }
}

return bReadData;
}

// --------------------------------------------------------------------------------------------
//
// CStdioFileEx::WriteString()
//
// --------------------------------------------------------------------------------------------
// Returns:    void
// Parameters: LPCTSTR lpsz
//
// Purpose:  Writes string to file either in Unicode or multibyte, depending on whether the caller specified the
//     CStdioFileEx::modeWriteUnicode flag. Override of base class function.
// Notes:  If writing in Unicode we need to:
//      a) Write the Byte-order-mark at the beginning of the file
//      b) Write all strings in byte-mode
//     - If we were compiled in Unicode, we need to convert Unicode to multibyte if
//      we want to write in multibyte
//     - If we were compiled in multi-byte, we need to convert multibyte to Unicode if
//      we want to write in Unicode.
// Exceptions: None.
//
void CStdioFileEx::WriteString(LPCTSTR lpsz)
{
// If writing Unicode and at the start of the file, need to write byte mark
if (m_nFlags & CStdioFileEx::modeWriteUnicode)
{
  // If at position 0, write byte-order mark before writing anything else
  if (!m_pStream || GetPosition() == 0)
  {
   wchar_t cBOM = (wchar_t)nUNICODE_BOM;
   CFile::Write(&cBOM, sizeof(wchar_t));
  }
}

// If compiled in Unicode...
#ifdef _UNICODE

// If writing Unicode, no conversion needed
if (m_nFlags & CStdioFileEx::modeWriteUnicode)
{
  // Write in byte mode
  CFile::Write(lpsz, lstrlen(lpsz) * sizeof(wchar_t));
}
// Else if we don't want to write Unicode, need to convert
else
{
  int  nChars = lstrlen(lpsz) + 1;    // Why plus 1? Because yes
  int  nBufferSize = nChars * sizeof(char);
  wchar_t* pszUnicodeString = new wchar_t[nChars];
  char * pszMultiByteString= new char[nChars];

// Copy string to Unicode buffer
lstrcpy(pszUnicodeString, lpsz);

  // Get multibyte string
  if (GetMultiByteStringFromUnicodeString(pszUnicodeString, pszMultiByteString, nBufferSize, GetACP()))
  {
   // Do standard write
   CFile::Write((const void*)pszMultiByteString, lstrlen(lpsz));
  }

  if (pszUnicodeString && pszMultiByteString)
  {
   delete [] pszUnicodeString;
   delete [] pszMultiByteString;
  }
}
// Else if *not* compiled in Unicode
#else
// If writing Unicode, need to convert
if (m_nFlags & CStdioFileEx::modeWriteUnicode)
{
  int  nChars = lstrlen(lpsz) + 1; // Why plus 1? Because yes
  int  nBufferSize = nChars * sizeof(wchar_t);
  wchar_t* pszUnicodeString = new wchar_t[nChars];
  char * pszMultiByteString= new char[nChars];

// Copy string to multibyte buffer
lstrcpy(pszMultiByteString, lpsz);

  if (GetUnicodeStringFromMultiByteString(pszMultiByteString, pszUnicodeString, nBufferSize, GetACP()))
  {
   // Write in byte mode
   CFile::Write(pszUnicodeString, lstrlen(lpsz) * sizeof(wchar_t));
  }
  else
  {
   ASSERT(false);
  }

  if (pszUnicodeString && pszMultiByteString)
  {
   delete [] pszUnicodeString;
   delete [] pszMultiByteString;
  }
}
// Else if we don't want to write Unicode, no conversion needed
else
{
  // Do standard stuff
  CStdioFile::WriteString(lpsz);
}

#endif
}

UINT CStdioFileEx::ProcessFlags(const CString& sFilePath, UINT& nOpenFlags)
{
m_bIsUnicodeText = false;

// If we have writeUnicode we must have write or writeRead as well
#ifdef _DEBUG
if (nOpenFlags & CStdioFileEx::modeWriteUnicode)
{
ASSERT(nOpenFlags & CFile::modeWrite || nOpenFlags & CFile::modeReadWrite);
}
#endif

// If reading in text mode and not creating...
if (nOpenFlags & CFile::typeText && !(m_nFlags & CFile::modeCreate) && !(m_nFlags & CFile::modeWrite ))
{
m_bIsUnicodeText = IsFileUnicode(sFilePath);

  // If it's Unicode, switch to binary mode
  if (m_bIsUnicodeText)
  {
   nOpenFlags ^= CFile::typeText;
   nOpenFlags |= CFile::typeBinary;
  }
}

m_nFlags = nOpenFlags;

return nOpenFlags;
}

// --------------------------------------------------------------------------------------------
//
// CStdioFileEx::IsFileUnicode()
//
// --------------------------------------------------------------------------------------------
// Returns:    bool
// Parameters: const CString& sFilePath
//
// Purpose:  Determines whether a file is Unicode by reading the first character and detecting
//     whether it's the Unicode byte marker.
// Notes:  None.
// Exceptions: None.
//
/*static*/ bool CStdioFileEx::IsFileUnicode(const CString& sFilePath)
{
CFile    file;
bool    bIsUnicode = false;
wchar_t   cFirstChar;
CFileException exFile;

// Open file in binary mode and read first character
if (file.Open(sFilePath, CFile::typeBinary | CFile::modeRead, &exFile))
{
  // If byte is Unicode byte-order marker, let's say it's Unicode
  if (file.Read(&cFirstChar, sizeof(wchar_t)) > 0 && cFirstChar == (wchar_t)nUNICODE_BOM)
  {
   bIsUnicode = true;
  }

file.Close();
}
else
{
// Handle error here if you like
}

return bIsUnicode;
}

unsigned long CStdioFileEx::GetCharCount()
{
int nCharSize;
unsigned long nByteCount, nCharCount = 0;

if (m_pStream)
{
// Get size of chars in file
nCharSize = m_bIsUnicodeText ? sizeof(wchar_t): sizeof(char);

  // If Unicode, remove byte order mark from count
  nByteCount = (unsigned long)GetLength();

  if (m_bIsUnicodeText)
  {
   nByteCount = nByteCount - sizeof(wchar_t);
  }

// Calc chars
nCharCount = (nByteCount / nCharSize);
}

return nCharCount;
}

// --------------------------------------------------------------------------------------------
//
// CStdioFileEx::GetUnicodeStringFromMultiByteString()
//
// --------------------------------------------------------------------------------------------
// Returns:    bool
// Parameters: char *  szMultiByteString  (IN) Multi-byte input string
//     wchar_t*  szUnicodeString  (OUT) Unicode outputstring
//     short   nUnicodeBufferSize (IN) Size of Unicode output buffer
//     UINT   nCodePage    (IN) Code page used to perform conversion
//                  Default = -1 (Get local code page).
//
// Purpose:  Gets a Unicode string from a MultiByte string.
// Notes:  None.
// Exceptions: None.
//
bool CStdioFileEx::GetUnicodeStringFromMultiByteString(char * szMultiByteString, wchar_t* szUnicodeString, short nUnicodeBufferSize, UINT nCodePage)
{
bool  bOK = true;
int  nReturn = 0;
CString sErrorMsg;

if (szUnicodeString && szMultiByteString)
{
  // If no code page specified, take default for system
  if (nCodePage == -1)
  {
   nCodePage = GetACP();
  }

  try
  {
   nReturn = MultiByteToWideChar(nCodePage,MB_PRECOMPOSED,szMultiByteString,-1,szUnicodeString,nUnicodeBufferSize);

   if (nReturn == 0)
   {
    bOK = false;
   }
  }
  catch(...)
  {
   bOK = false;
  }
}
else
{
  bOK = false;
}

ASSERT(bOK);
return bOK;
}

// --------------------------------------------------------------------------------------------
//
// CStdioFileEx::GetMultiByteStringFromUnicodeString()
//
// --------------------------------------------------------------------------------------------
// Returns:    BOOL
// Parameters: wchar_t * szUnicodeString   (IN) Unicode input string
//     char*   szMultiByteString   (OUT) Multibyte output string
//     short   nMultiByteBufferSize  (IN) Multibyte buffer size
//     UINT   nCodePage     (IN) Code page used to perform conversion
//                   Default = -1 (Get local code page).
//
// Purpose:  Gets a MultiByte string from a Unicode string
// Notes:  None.
// Exceptions: None.
//
BOOL CStdioFileEx::GetMultiByteStringFromUnicodeString(wchar_t * szUnicodeString, char* szMultiByteString,
                   short nMultiByteBufferSize, UINT nCodePage)
{
BOOL   bUsedDefChar = FALSE;
BOOL   bGotIt = FALSE;

if (szUnicodeString && szMultiByteString)
{
  // If no code page specified, take default for system
  if (nCodePage == -1)
  {
   nCodePage = GetACP();
  }

  try
  {
   bGotIt = WideCharToMultiByte(nCodePage, WC_COMPOSITECHECK | WC_SEPCHARS,
       szUnicodeString,-1, szMultiByteString, nMultiByteBufferSize, sDEFAULT_UNICODE_FILLER_CHAR, &bUsedDefChar);
  }
  catch(...)
  {
   TRACE(_T("Controlled exception in WideCharToMultiByte!/n"));
  }
}

return bGotIt;
}