CStringW TextFormat::UTF8ToUnicode(const CString& in)
{
int len = ::UTF8ToUnicode(in,in.GetLength(),NULL,0);
CStringW out;
LPWSTR ptr = out.GetBufferSetLength(len);
::UTF8ToUnicode(in,in.GetLength(),ptr,len);
out.ReleaseBuffer(len);
return out;
}
CStringW TextFormat::Latin1ToUnicode(const CString& in)
{
CStringW text;
int len = in.GetLength();
LPWSTR textPtr = text.GetBufferSetLength(len);
for (int i = 0; i < len; i++)
textPtr[i] = (wchar_t)(unsigned char)in[i];
text.ReleaseBuffer(len);
return text;
}
BOOL CStdioFileEx::ReadWideString(CStringW& rString)
{
_ASSERTE(m_pStream);
rString = L"";// empty string without deallocating
if(m_bIsUnicodeText)
{
// If at position 0, discard byte-order mark before reading
if(GetPosition() == 0)
{
wchar_t bom;
Read(&bom, sizeof(wchar_t));
}
const int nMaxSize = 128;
LPWSTR lpsz = rString.GetBuffer(nMaxSize);
LPWSTR lpszResult;
int nLen = 0;
for (;;)
{
lpszResult = fgetws(lpsz, nMaxSize+1, m_pStream);
rString.ReleaseBuffer();
// handle error/eof case
if (lpszResult == NULL && !feof(m_pStream))
{
Afx_clearerr_s(m_pStream);
AfxThrowFileException(CFileException::genericException, _doserrno,
m_strFileName);
}
// if string is read completely or EOF
if (lpszResult == NULL || (nLen = (int)lstrlenW(lpsz)) < nMaxSize || lpsz[nLen-1] == '\n')
break;
nLen = rString.GetLength();
lpsz = rString.GetBuffer(nMaxSize + nLen) + nLen;
}
//remove crlf if exist.
nLen = rString.GetLength();
if (nLen > 1 && rString.Mid(nLen-2) == L"\r\n")
{
rString.GetBufferSetLength(nLen-2);
}
return rString.GetLength() > 0;
}
else
{
CStringA ansiString;
BOOL bRetval = ReadAnsiString(ansiString);
//setlocale(LC_ALL, "chs_chn.936");//no need
rString = ansiString;
return bRetval;
}
}
CStringW Util::String::GBKToUnicode( CStringA gbk )
{
CStringW strUnicode;
DWORD dwMinSize = 0;
dwMinSize = MultiByteToWideChar(936, NULL, gbk, gbk.GetLength(),NULL, 0);
strUnicode.GetBufferSetLength(dwMinSize);
LPWSTR lpszStr = strUnicode.GetBuffer();
INT ok = MultiByteToWideChar(936, NULL, gbk, gbk.GetLength(), lpszStr, dwMinSize);
strUnicode.ReleaseBuffer();
return strUnicode;
}
void OutputStream::PutString(LPCWSTR fmt, ...)
{
CStringW str;
va_list args;
va_start(args, fmt);
int len = _vscwprintf(fmt, args) + 1;
if(len > 0) vswprintf_s(str.GetBufferSetLength(len), len, fmt, args);
va_end(args);
LPCWSTR s = str;
while(*s) PutChar(*s++);
}
LPCWSTR StringUTF8ToWChar(LPCSTR sUTF8, CStringW &sWChar, int iChars/* = -1*/)
{
if (!sUTF8)
return NULL;
sWChar.Empty();
int iLen = MultiByteToWideChar(CP_UTF8, 0, sUTF8, iChars, NULL, 0);
if (iLen > 0) {
LPWSTR sBuf = sWChar.GetBufferSetLength(iLen);
iLen = MultiByteToWideChar(CP_UTF8, 0, sUTF8, iChars, sBuf, iLen);
sWChar.ReleaseBufferSetLength(sBuf[iLen - 1] ? iLen : iLen - 1);
return (iLen > 0) ? sWChar.GetString() : NULL;
}
return *sUTF8 != 0 ? sWChar.GetString() : NULL;
}
LPCWSTR StringCharToWChar(LPCSTR sChar, CStringW &sWChar, int iChars/* = -1*/, UINT codepage/* = CP_ACP*/)
{
if (!sChar)
return NULL;
sWChar.Empty();
int iLen = MultiByteToWideChar(codepage, 0, sChar, iChars, NULL, 0);
if (iLen > 0) {
LPWSTR sBuf = sWChar.GetBufferSetLength(iLen);
MultiByteToWideChar(codepage, 0, sChar, iChars, sBuf, iLen);
sWChar.ReleaseBufferSetLength(sBuf[iLen - 1] ? iLen : iLen - 1);
return (iLen > 0) ? sWChar.GetString() : NULL;
}
return (*sChar != 0) ? sWChar.GetString() : NULL;
}
CString TextFormat::ToXML_UTF8(const CStringW& in)
{
// First escape any characters that will cause problems in the XML
CStringW escText;
int escLen = ::EscapeXML(in,in.GetLength(),NULL,0);
LPWSTR escPtr = escText.GetBufferSetLength(escLen);
::EscapeXML(in,in.GetLength(),escPtr,escLen);
escText.ReleaseBuffer(escLen);
// Convert the escaped text to UTF-8
CString utfText;
int utfLen = ::AtlUnicodeToUTF8(escText,escText.GetLength(),NULL,0);
LPSTR utfPtr = utfText.GetBufferSetLength(utfLen);
::AtlUnicodeToUTF8(escText,escText.GetLength(),utfPtr,utfLen);
utfText.ReleaseBuffer(utfLen);
return utfText;
}
