winscp/libs/mfc/source/strex.cpp

// This is a part of the Microsoft Foundation Classes C++ library.
// Copyright (C) 1992-1998 Microsoft Corporation
// All rights reserved.
//
// This source code is only intended as a supplement to the
// Microsoft Foundation Classes Reference and related
// electronic documentation provided with the library.
// See these sources for detailed information regarding the
// Microsoft Foundation Classes product.

#include "stdafx.h"
// WINSCP
#include <algorithm>
#define max std::max
#define min std::min

//////////////////////////////////////////////////////////////////////////////
// More sophisticated construction

CString::CString(LPCTSTR lpch, int nLength)
{
	Init();
	if (nLength != 0)
	{
		ASSERT(AfxIsValidAddress(lpch, nLength, FALSE));
		AllocBuffer(nLength);
		memcpy(m_pchData, lpch, nLength*sizeof(TCHAR));
	}
}

/////////////////////////////////////////////////////////////////////////////
// Special conversion constructors

CString::CString(LPCSTR lpsz, int nLength)
{
	Init();
	if (nLength != 0)
	{
		AllocBuffer(nLength);
		int n = ::MultiByteToWideChar(CP_ACP, 0, lpsz, nLength, m_pchData, nLength+1);
		ReleaseBuffer(n >= 0 ? n : -1);
	}
}

//////////////////////////////////////////////////////////////////////////////
// Assignment operators

const CString& CString::operator=(TCHAR ch)
{
	AssignCopy(1, &ch);
	return *this;
}

//////////////////////////////////////////////////////////////////////////////
// less common string expressions

CString AFXAPI operator+(const CString& string1, TCHAR ch)
{
	CString s;
	s.ConcatCopy(string1.GetData()->nDataLength, string1.m_pchData, 1, &ch);
	return s;
}

CString AFXAPI operator+(TCHAR ch, const CString& string)
{
	CString s;
	s.ConcatCopy(1, &ch, string.GetData()->nDataLength, string.m_pchData);
	return s;
}

//////////////////////////////////////////////////////////////////////////////
// Advanced manipulation

int CString::Delete(int nIndex, int nCount /* = 1 */)
{
	if (nIndex < 0)
		nIndex = 0;
	int nNewLength = GetData()->nDataLength;
	if (nCount > 0 && nIndex < nNewLength)
	{
		CopyBeforeWrite();
		int nBytesToCopy = nNewLength - (nIndex + nCount) + 1;

		memcpy(m_pchData + nIndex,
			m_pchData + nIndex + nCount, nBytesToCopy * sizeof(TCHAR));
		GetData()->nDataLength = nNewLength - nCount;
	}

	return nNewLength;
}

int CString::Replace(TCHAR chOld, TCHAR chNew)
{
	int nCount = 0;

	// short-circuit the nop case
	if (chOld != chNew)
	{
		// otherwise modify each character that matches in the string
		CopyBeforeWrite();
		LPTSTR psz = m_pchData;
		LPTSTR pszEnd = psz + GetData()->nDataLength;
		while (psz < pszEnd)
		{
			// replace instances of the specified character only
			if (*psz == chOld)
			{
				*psz = chNew;
				nCount++;
			}
			psz = _tcsinc(psz);
		}
	}
	return nCount;
}

int CString::Replace(LPCTSTR lpszOld, LPCTSTR lpszNew)
{
	// can't have empty or NULL lpszOld

	int nSourceLen = SafeStrlen(lpszOld);
	if (nSourceLen == 0)
		return 0;
	int nReplacementLen = SafeStrlen(lpszNew);

	// loop once to figure out the size of the result string
	int nCount = 0;
	LPTSTR lpszStart = m_pchData;
	LPTSTR lpszEnd = m_pchData + GetData()->nDataLength;
	LPTSTR lpszTarget;
	while (lpszStart < lpszEnd)
	{
		while ((lpszTarget = _tcsstr(lpszStart, lpszOld)) != NULL)
		{
			nCount++;
			lpszStart = lpszTarget + nSourceLen;
		}
		lpszStart += lstrlen(lpszStart) + 1;
	}

	// if any changes were made, make them
	if (nCount > 0)
	{
		CopyBeforeWrite();

		// if the buffer is too small, just
		//   allocate a new buffer (slow but sure)
		int nOldLength = GetData()->nDataLength;
		int nNewLength =  nOldLength + (nReplacementLen-nSourceLen)*nCount;
		if (GetData()->nAllocLength < nNewLength || GetData()->nRefs > 1)
		{
			CStringData* pOldData = GetData();
			LPTSTR pstr = m_pchData;
			AllocBuffer(nNewLength);
			memcpy(m_pchData, pstr, pOldData->nDataLength*sizeof(TCHAR));
			CString::Release(pOldData);
		}
		// else, we just do it in-place
		lpszStart = m_pchData;
		lpszEnd = m_pchData + GetData()->nDataLength;

		// loop again to actually do the work
		while (lpszStart < lpszEnd)
		{
			while ( (lpszTarget = _tcsstr(lpszStart, lpszOld)) != NULL)
			{
				int nBalance = nOldLength - (lpszTarget - m_pchData + nSourceLen);
				memmove(lpszTarget + nReplacementLen, lpszTarget + nSourceLen,
					nBalance * sizeof(TCHAR));
				memcpy(lpszTarget, lpszNew, nReplacementLen*sizeof(TCHAR));
				lpszStart = lpszTarget + nReplacementLen;
				lpszStart[nBalance] = '\0';
				nOldLength += (nReplacementLen - nSourceLen);
			}
			lpszStart += lstrlen(lpszStart) + 1;
		}
		ASSERT(m_pchData[nNewLength] == '\0');
		GetData()->nDataLength = nNewLength;
	}

	return nCount;
}

//////////////////////////////////////////////////////////////////////////////
// Very simple sub-string extraction

CString CString::Mid(int nFirst) const
{
	return Mid(nFirst, GetData()->nDataLength - nFirst);
}

CString CString::Mid(int nFirst, int nCount) const
{
	// out-of-bounds requests return sensible things
	if (nFirst < 0)
		nFirst = 0;
	if (nCount < 0)
		nCount = 0;

	if (nFirst + nCount > GetData()->nDataLength)
		nCount = GetData()->nDataLength - nFirst;
	if (nFirst > GetData()->nDataLength)
		nCount = 0;

	ASSERT(nFirst >= 0);
	ASSERT(nFirst + nCount <= GetData()->nDataLength);

	// optimize case of returning entire string
	if (nFirst == 0 && nFirst + nCount == GetData()->nDataLength)
		return *this;

	CString dest;
	AllocCopy(dest, nCount, nFirst, 0);
	return dest;
}

CString CString::Right(int nCount) const
{
	if (nCount < 0)
		nCount = 0;
	if (nCount >= GetData()->nDataLength)
		return *this;

	CString dest;
	AllocCopy(dest, nCount, GetData()->nDataLength-nCount, 0);
	return dest;
}

CString CString::Left(int nCount) const
{
	if (nCount < 0)
		nCount = 0;
	if (nCount >= GetData()->nDataLength)
		return *this;

	CString dest;
	AllocCopy(dest, nCount, 0, 0);
	return dest;
}

//////////////////////////////////////////////////////////////////////////////
// Finding

int CString::ReverseFind(TCHAR ch) const
{
	// find last single character
	LPTSTR lpsz = _tcsrchr(m_pchData, (_TUCHAR) ch);

	// return -1 if not found, distance from beginning otherwise
	return (lpsz == NULL) ? -1 : (int)(lpsz - m_pchData);
}

// find a sub-string (like strstr)
int CString::Find(LPCTSTR lpszSub) const
{
	return Find(lpszSub, 0);
}

int CString::Find(LPCTSTR lpszSub, int nStart) const
{
	ASSERT(AfxIsValidString(lpszSub));

	int nLength = GetData()->nDataLength;
	if (nStart > nLength)
		return -1;

	// find first matching substring
	LPTSTR lpsz = _tcsstr(m_pchData + nStart, lpszSub);

	// return -1 for not found, distance from beginning otherwise
	return (lpsz == NULL) ? -1 : (int)(lpsz - m_pchData);
}


/////////////////////////////////////////////////////////////////////////////
// CString formatting

#define TCHAR_ARG   TCHAR
#define WCHAR_ARG   WCHAR
#define CHAR_ARG    char

#ifdef _X86_
	#define DOUBLE_ARG  _AFX_DOUBLE
#else
	#define DOUBLE_ARG  double
#endif

#define FORCE_ANSI      0x10000
#define FORCE_UNICODE   0x20000
#define FORCE_INT64     0x40000
#define _tclen(__a)         (1)

void CString::FormatV(LPCTSTR lpszFormat, va_list argList)
{
	ASSERT(AfxIsValidString(lpszFormat));

	va_list argListSave = argList;

	// make a guess at the maximum length of the resulting string
	int nMaxLen = 0;
	for (LPCTSTR lpsz = lpszFormat; *lpsz != '\0'; lpsz = _tcsinc(lpsz))
	{
		// handle '%' character, but watch out for '%%'
		if (*lpsz != '%' || *(lpsz = _tcsinc(lpsz)) == '%')
		{
			nMaxLen += _tclen(lpsz);
			continue;
		}

		int nItemLen = 0;

		// handle '%' character with format
		int nWidth = 0;
		for (; *lpsz != '\0'; lpsz = _tcsinc(lpsz))
		{
			// check for valid flags
			if (*lpsz == '#')
				nMaxLen += 2;   // for '0x'
			else if (*lpsz == '*')
				nWidth = va_arg(argList, int);
			else if (*lpsz == '-' || *lpsz == '+' || *lpsz == '0' ||
				*lpsz == ' ')
				;
			else // hit non-flag character
				break;
		}
		// get width and skip it
		if (nWidth == 0)
		{
			// width indicated by
			nWidth = _ttoi(lpsz);
			for (; *lpsz != '\0' && _istdigit(*lpsz); lpsz = _tcsinc(lpsz))
				;
		}
		ASSERT(nWidth >= 0);

		int nPrecision = 0;
		if (*lpsz == '.')
		{
			// skip past '.' separator (width.precision)
			lpsz = _tcsinc(lpsz);

			// get precision and skip it
			if (*lpsz == '*')
			{
				nPrecision = va_arg(argList, int);
				lpsz = _tcsinc(lpsz);
			}
			else
			{
				nPrecision = _ttoi(lpsz);
				for (; *lpsz != '\0' && _istdigit(*lpsz); lpsz = _tcsinc(lpsz))
					;
			}
			ASSERT(nPrecision >= 0);
		}

		// should be on type modifier or specifier
		int nModifier = 0;
		if (_tcsncmp(lpsz, _T("I64"), 3) == 0)
		{
			lpsz += 3;
			nModifier = FORCE_INT64;
#if !defined(_X86_) && !defined(_ALPHA_)
			// __int64 is only available on X86 and ALPHA platforms
			ASSERT(FALSE);
#endif
		}
		else
		{
			switch (*lpsz)
			{
			// modifiers that affect size
			case 'h':
				nModifier = FORCE_ANSI;
				lpsz = _tcsinc(lpsz);
				break;
			case 'l':
				nModifier = FORCE_UNICODE;
				lpsz = _tcsinc(lpsz);
				break;

			// modifiers that do not affect size
			case 'F':
			case 'N':
			case 'L':
				lpsz = _tcsinc(lpsz);
				break;
			}
		}

		// now should be on specifier
		switch (*lpsz | nModifier)
		{
		// single characters
		case 'c':
		case 'C':
			nItemLen = 2;
			va_arg(argList, TCHAR_ARG);
			break;
		case 'c'|FORCE_ANSI:
		case 'C'|FORCE_ANSI:
			nItemLen = 2;
			va_arg(argList, CHAR_ARG);
			break;
		case 'c'|FORCE_UNICODE:
		case 'C'|FORCE_UNICODE:
			nItemLen = 2;
			va_arg(argList, WCHAR_ARG);
			break;

		// strings
		case 's':
			{
				LPCTSTR pstrNextArg = va_arg(argList, LPCTSTR);
				if (pstrNextArg == NULL)
				   nItemLen = 6;  // "(null)"
				else
				{
				   nItemLen = lstrlen(pstrNextArg);
				   nItemLen = max(1, nItemLen);
				}
			}
			break;

		case 'S':
			{
				LPCSTR pstrNextArg = va_arg(argList, LPCSTR);
				if (pstrNextArg == NULL)
				   nItemLen = 6; // "(null)"
				else
				{
				   nItemLen = lstrlenA(pstrNextArg);
				   nItemLen = max(1, nItemLen);
				}
			}
			break;

		case 's'|FORCE_ANSI:
		case 'S'|FORCE_ANSI:
			{
				LPCSTR pstrNextArg = va_arg(argList, LPCSTR);
				if (pstrNextArg == NULL)
				   nItemLen = 6; // "(null)"
				else
				{
				   nItemLen = lstrlenA(pstrNextArg);
				   nItemLen = max(1, nItemLen);
				}
			}
			break;

		case 's'|FORCE_UNICODE:
		case 'S'|FORCE_UNICODE:
			{
				LPWSTR pstrNextArg = va_arg(argList, LPWSTR);
				if (pstrNextArg == NULL)
				   nItemLen = 6; // "(null)"
				else
				{
				   nItemLen = wcslen(pstrNextArg);
				   nItemLen = max(1, nItemLen);
				}
			}
			break;
		}

		// adjust nItemLen for strings
		if (nItemLen != 0)
		{
			if (nPrecision != 0)
				nItemLen = min(nItemLen, nPrecision);
			nItemLen = max(nItemLen, nWidth);
		}
		else
		{
			switch (*lpsz)
			{
			// integers
			case 'd':
			case 'i':
			case 'u':
			case 'x':
			case 'X':
			case 'o':
				if (nModifier & FORCE_INT64)
					va_arg(argList, __int64);
				else
					va_arg(argList, int);
				nItemLen = 32;
				nItemLen = max(nItemLen, nWidth+nPrecision);
				break;

			case 'e':
			case 'g':
			case 'G':
				va_arg(argList, DOUBLE_ARG);
				nItemLen = 128;
				nItemLen = max(nItemLen, nWidth+nPrecision);
				break;

			case 'f':
				va_arg(argList, DOUBLE_ARG);
				nItemLen = 128; // width isn't truncated
				// 312 == strlen("-1+(309 zeroes).")
				// 309 zeroes == max precision of a double
				nItemLen = max(nItemLen, 312+nPrecision);
				break;

			case 'p':
				va_arg(argList, void*);
				nItemLen = 32;
				nItemLen = max(nItemLen, nWidth+nPrecision);
				break;

			// no output
			case 'n':
				va_arg(argList, int*);
				break;

			default:
				ASSERT(FALSE);  // unknown formatting option
			}
		}

		// adjust nMaxLen for output nItemLen
		nMaxLen += nItemLen;
	}

	GetBuffer(nMaxLen);
	VERIFY(_vstprintf(m_pchData, lpszFormat, argListSave) <= GetAllocLength());
	ReleaseBuffer();

	va_end(argListSave);
}

// formatting (using wsprintf style formatting)
void AFX_CDECL CString::Format(LPCTSTR lpszFormat, ...)
{
	ASSERT(AfxIsValidString(lpszFormat));

	va_list argList;
	va_start(argList, lpszFormat);
	FormatV(lpszFormat, argList);
	va_end(argList);
}

void AFX_CDECL CString::Format(UINT nFormatID, ...)
{
	CString strFormat;
	VERIFY(strFormat.LoadString(nFormatID) != 0);

	va_list argList;
	va_start(argList, nFormatID);
	FormatV(strFormat, argList);
	va_end(argList);
}

void CString::TrimRight(LPCTSTR lpszTargetList)
{
	// find beginning of trailing matches
	// by starting at beginning (DBCS aware)

	CopyBeforeWrite();
	LPTSTR lpsz = m_pchData;
	LPTSTR lpszLast = NULL;

	while (*lpsz != '\0')
	{
		if (_tcschr(lpszTargetList, *lpsz) != NULL)
		{
			if (lpszLast == NULL)
				lpszLast = lpsz;
		}
		else
			lpszLast = NULL;
		lpsz = _tcsinc(lpsz);
	}

	if (lpszLast != NULL)
	{
		// truncate at left-most matching character
		*lpszLast = '\0';
		GetData()->nDataLength = lpszLast - m_pchData;
	}
}

void CString::TrimRight(TCHAR chTarget)
{
	// find beginning of trailing matches
	// by starting at beginning (DBCS aware)

	CopyBeforeWrite();
	LPTSTR lpsz = m_pchData;
	LPTSTR lpszLast = NULL;

	while (*lpsz != '\0')
	{
		if (*lpsz == chTarget)
		{
			if (lpszLast == NULL)
				lpszLast = lpsz;
		}
		else
			lpszLast = NULL;
		lpsz = _tcsinc(lpsz);
	}

	if (lpszLast != NULL)
	{
		// truncate at left-most matching character
		*lpszLast = '\0';
		GetData()->nDataLength = lpszLast - m_pchData;
	}
}

void CString::TrimLeft(LPCTSTR lpszTargets)
{
	// if we're not trimming anything, we're not doing any work
	if (SafeStrlen(lpszTargets) == 0)
		return;

	CopyBeforeWrite();
	LPCTSTR lpsz = m_pchData;

	while (*lpsz != '\0')
	{
		if (_tcschr(lpszTargets, *lpsz) == NULL)
			break;
		lpsz = _tcsinc(lpsz);
	}

	if (lpsz != m_pchData)
	{
		// fix up data and length
		int nDataLength = GetData()->nDataLength - (lpsz - m_pchData);
		memmove(m_pchData, lpsz, (nDataLength+1)*sizeof(TCHAR));
		GetData()->nDataLength = nDataLength;
	}
}

void CString::TrimLeft(TCHAR chTarget)
{
	// find first non-matching character

	CopyBeforeWrite();
	LPCTSTR lpsz = m_pchData;

	while (chTarget == *lpsz)
		lpsz = _tcsinc(lpsz);

	if (lpsz != m_pchData)
	{
		// fix up data and length
		int nDataLength = GetData()->nDataLength - (lpsz - m_pchData);
		memmove(m_pchData, lpsz, (nDataLength+1)*sizeof(TCHAR));
		GetData()->nDataLength = nDataLength;
	}
}

///////////////////////////////////////////////////////////////////////////////