compilecode.cpp

我的简易编译器终于在花了近20个工作日后完成了。按照设计是做成一个FormulaEx.dll

// CompileCode.cpp: implementation of the CCompileCode class.
//
//////////////////////////////////////////////////////////////////////
/*
 * Generated by MyEclipse Struts
 * 
 * Written by Yang Huaisheng 
 * Homepage: http://codefan.spaces.live.com
 * version 0.01
 * create at 2006-04-30
 * 
 *  Distribute freely, except: don't remove my name from the source or
 *  documentation (don't take credit for my work), mark your changes (don't
 *  get me blamed for your possible bugs), don't alter or remove this
 *  notice.
 *  No warrantee of any kind, express or implied, is included with this
 *  software; use at your own risk, responsibility for damages (if any) to
 *  anyone resulting from the use of this software rests entirely with the
 *  user.
 * 
 *  Send bug reports, bug fixes, enhancements, requests, flames, etc. to
 *     [e-mail]
 *  
 */

#include "stdafx.h"
#include "..\HEADER\CompileCode.h"
#include "..\Interface\ConstDef.h"
#include "..\..\Formule\Calc\RegularOpt.h"

#ifdef _DEBUG
#undef THIS_FILE
static char THIS_FILE[]=__FILE__;
#define new DEBUG_NEW
#endif
//////////////////////////////////////////////////////////////////////
// CSZGetWord:: Construction/Destruction
//////////////////////////////////////////////////////////////////////

#define MAKE_CONTINUE_TAG(n) (-4 - (n))
#define IS_CONTINUE_TAG(n) ((n) <= -4)
#define GET_CONTINUE_TAG(n) (4 - (n))

CSZGetWord::CSZGetWord()
{
	m_szSource = NULL;
	m_nSourceLen = 0;
	m_nCmpPos = 0;
	m_bAcceptOpt = FALSE;
	m_nCurLine = 0;
	m_nCurLineBeginPos = 0;
}
CSZGetWord::~CSZGetWord()
{
}
inline int	CSZGetWord::GetCurPos()
{
	return m_nCmpPos;
}
inline bool CSZGetWord::IsEnd()
{
	return m_nCmpPos>=m_nSourceLen;
}

inline void CSZGetWord::NewLine()
{
	m_nCurLine ++;
	m_nCurLineBeginPos = m_nCmpPos;
}
inline int  CSZGetWord::GetCurLine()
{
	return m_nCurLine;
}
inline int  CSZGetWord::GetCurPosInLine()
{
	return m_nCmpPos - m_nCurLineBeginPos;
}

void CSZGetWord::Reset()
{
	m_nCmpPos=0;
	m_nCurLine = 0;
	m_nCurLineBeginPos = 0;
}

void CSZGetWord::SetSource(LPCTSTR szSou, int nL)
{
	Reset();
	m_nCmpPos = 0;
	m_bAcceptOpt = FALSE;
	m_szSource = szSou;
	if(nL<0)
		m_nSourceLen = strlen(szSou);
	else
		m_nSourceLen = nL;
}

void CSZGetWord::TrimSpace()
{
	while((m_nCmpPos < m_nSourceLen ) && 
			( 
		         (m_szSource[m_nCmpPos]==' ') ||
				 (m_szSource[m_nCmpPos]==9)   ||
				 (m_szSource[m_nCmpPos]==13)  ||
				 (m_szSource[m_nCmpPos]==10) 
			) 
		)
	{
		if(m_szSource[m_nCmpPos] == 13) 
			NewLine();
		m_nCmpPos++;
	}
}

void CSZGetWord::TrimComment()
{

	if(m_nCmpPos > m_nSourceLen-1) return;
	char ch  = m_szSource[m_nCmpPos];
	char ch2 = m_szSource[m_nCmpPos+1];
	// 判断是否是注释语句
	while((ch == '/') && (ch2 == '/' || ch2 == '*')) {
		m_nCmpPos+=2;
		if( ch2 == '/'){ //单行注释
			m_nCmpPos++;
			while( ( m_nCmpPos <m_nSourceLen ) && (m_szSource[m_nCmpPos] !=13))
				m_nCmpPos++;
			NewLine();
			m_nCmpPos++;
		}else if(ch2 == '*')
		{ // 多行注释
			m_nCmpPos++;
			while( ( m_nCmpPos <m_nSourceLen-1 ) && 
					(
				        (m_szSource[m_nCmpPos] !='*')  ||
						(m_szSource[m_nCmpPos+1] !='/')
					) 
				)
			{
				if(m_szSource[m_nCmpPos] == 13)
					NewLine();
				m_nCmpPos++;
			}
			m_nCmpPos+=2;
		}
		TrimSpace();
		if(m_nCmpPos > m_nSourceLen-1) return;

		ch  = m_szSource[m_nCmpPos];
		ch2 = m_szSource[m_nCmpPos+1];
	}

}

CString CSZGetWord::GetAWord()
{
	TrimSpace();
	TrimComment();
	if( m_nCmpPos >= m_nSourceLen)
		return CString("");// KEY_UNKNOW;//m_iPreIsn = KEY_UNKNOW;

	char ch = m_szSource[m_nCmpPos++];

	int optenable = m_bAcceptOpt;

	m_bAcceptOpt = FALSE;

	CString sCurWord(ch);
	switch(ch){
		case '.': 
			if(m_szSource[m_nCmpPos] == '.' && m_szSource[m_nCmpPos+1] == '.'){
				m_nCmpPos += 2;
				sCurWord = "...";
				return sCurWord;
			}	 
			break;//m_iPreIsn = BS_DOT ; return BS_DOT ;
		case ',': 
		case ';': 
		case ':': 
		case '[': 
		case ']': 
		case '(': 
		case ')': 
		case '{': 
		case '}': 
		case '@': 
		case '%': 
		case '#': 
			return sCurWord;
		case '*': 
		case '/': 
		case '=':
		case '>':
		case '<':
		case '!':
			if(m_szSource[m_nCmpPos] == '=') {
				m_nCmpPos ++;
				sCurWord += "=";
			}
			return sCurWord;
		case '+': 
			if(m_szSource[m_nCmpPos] == '=') {
				m_nCmpPos ++;
				sCurWord += "=";
				return sCurWord;
			} 
			if(m_szSource[m_nCmpPos] == '+') {
				m_nCmpPos ++;
				sCurWord += "+";
				m_bAcceptOpt = TRUE;
				return sCurWord;
			}
			if( optenable )
				return sCurWord;
			return sCurWord;
		case '-':
			if(m_szSource[m_nCmpPos] == '=') {
				m_nCmpPos ++;
				sCurWord += "=";
				return sCurWord;
			} 
			if(m_szSource[m_nCmpPos] == '-') {
				m_nCmpPos ++;
				sCurWord += "-";
				m_bAcceptOpt = TRUE;
				return sCurWord;
			}
			if( optenable )
				return sCurWord; //{ m_iPreIsn = OP_ADD ; return OP_ADD ;}
			break;
		case '&': 
			if(m_szSource[m_nCmpPos] == '&') {
				m_nCmpPos ++;
				sCurWord += "&";
			}
			return sCurWord;
		case '|': 
			if(m_szSource[m_nCmpPos] == '|') {
				m_nCmpPos ++;
				sCurWord += "|";
			}
			return sCurWord;
		default:
			break;
	}

	m_bAcceptOpt = TRUE;

	if(((ch>='a')&&(ch<='z'))||((ch>='A')&&(ch<='Z'))||(ch=='_')){
		ch = m_szSource[m_nCmpPos++];
		while( (m_nCmpPos<m_nSourceLen) && 
					( ((ch>='a')&&(ch<='z')) ||((ch>='A')&&(ch<='Z')) || (ch=='_') ||
					  ((ch>='0')&&(ch<='9')) ) )
		{
			sCurWord += ch;
			ch = m_szSource[m_nCmpPos++];
		}
		m_nCmpPos--;
		return sCurWord;//return  GEN_SIGN;
	}
	bool bHasDot = ch == '.';
	if(((ch>='0')&&(ch<='9'))||(ch=='.')||(ch=='+')||(ch=='-')){ // const 
		ch = m_szSource[m_nCmpPos++];
		if((ch=='+')||(ch=='-')){
			while((m_nCmpPos<m_nSourceLen) && 
				  (ch == ' ' || ch == 9) )
			{
				ch = m_szSource[m_nCmpPos++];
			}
		}

		while( (m_nCmpPos<m_nSourceLen) &&( (ch=='.') || ((ch>='0')&&(ch<='9')) ) )
		{
			if(ch=='.'){
				if(bHasDot)
					break;
				bHasDot = true;
			}
			sCurWord += ch;
			ch = m_szSource[m_nCmpPos++];
		}
		m_nCmpPos--;
		return sCurWord;//m_iPreIsn = GEN_CTNUM;return GEN_CTNUM;
	}

	if(ch == '"'){ //String
		for( ch = m_szSource[m_nCmpPos++]; 
				( ch != '"')&&(m_nCmpPos < m_nSourceLen) ; 
				ch = m_szSource[m_nCmpPos++])
		{
			if(ch == 13){
				NewLine();
				break;
			}
			if(ch == '\\' && m_nCmpPos < m_nSourceLen ){
				ch = m_szSource[m_nCmpPos++];
				switch(ch){
				case 'r':
				case 'R':
					ch = 13;
					break;
				case 'n':
				case 'N':
					ch = 10;
					break;
				case 't':
				case 'T':
					ch = 9;
					break;
				}
				// 分析转义符
			}
			sCurWord += ch;
		}
		sCurWord += '"';
		return sCurWord;
	}

	if(ch == '\''){ //String
		for( ch = m_szSource[m_nCmpPos++]; 
				( ch != '\'') && (m_nCmpPos < m_nSourceLen) ; 
				ch = m_szSource[m_nCmpPos++] )
		{
			if(ch == 13){
				NewLine();
				break;
			}
			if(ch == '\\' && m_nCmpPos < m_nSourceLen ){
				ch = m_szSource[m_nCmpPos++];
				switch(ch){
				case 'r':
				case 'R':
					ch = 13;
					break;
				case 'n':
				case 'N':
					ch = 10;
					break;
				case 't':
				case 'T':
					ch = 9;
					break;
				}
				// 分析转义符
			}
			sCurWord += ch;
		}
		sCurWord += '\'';
		return sCurWord;
	}
	m_bAcceptOpt = optenable;
	return sCurWord;
}
//////////////////////////////////////////////////////////////////////
// CChainStack::Construction/Destruction
//////////////////////////////////////////////////////////////////////

CChainStack::CChainStack()
{
	m_nDept=0;
}

CChainStack::~CChainStack()
{

}

int CChainStack::GetDept()
{
	return m_nDept;
}
void CChainStack::Push(SJMPChain & SC)
{
	if( m_nDept >= m_Stack.GetSize() ) 
		m_Stack.SetSize(m_nDept+1);
	m_Stack[m_nDept] = SC;
	m_nDept++;
}

SJMPChain CChainStack::Pop()
{
	ASSERT(m_nDept>0);
	m_nDept--;
	return m_Stack[m_nDept];
}
PJMPCHAIN CChainStack::GetTop()
{
	//ASSERT(m_nDept>0);
	if(m_nDept ==0)
		return NULL;
	return &m_Stack[m_nDept-1];
}

PJMPCHAIN CChainStack::GetTopLoopChain()
{
	for(int i=m_nDept-1;i>=0; i--)
		if(m_Stack[i].SEN_TYPE == RES_WHILE ||
			m_Stack[i].SEN_TYPE == RES_FOR
		)
			return &m_Stack[i];
	return NULL;
}

void CChainStack::Clear()
{
	m_nDept = 0;
}

BOOL CChainStack::IsEmpty()
{
	return m_nDept == 0;
}



//////////////////////////////////////////////////////////////////////
// CCompileCode::Construction/Destruction
//////////////////////////////////////////////////////////////////////

CCompileCode::CCompileCode()
{
	m_sCurWord = "";
	m_nCurISN  = 0;
	m_bIsBack  = FALSE;
	m_CurWT = WT_UNKNOWN;
	m_pFormulaModula = NULL;
}

CCompileCode::~CCompileCode()
{

}

void CCompileCode::Reset()
{
	m_sCurWord = "";
	m_nCurISN  = 0;
	m_bIsBack  = FALSE;
	m_CurWT = WT_UNKNOWN;
	m_slErrorMsgs.RemoveAll();
	m_JMPChain.Clear();
	m_pFormulaModula->Reset();
	m_SourceCode.SetSource(m_pFormulaModula->GetSource(),m_pFormulaModula->GetSourceLen());
}

void CCompileCode::RaiseWarning(LPCTSTR sMsg)
{
	CString sStr;
	sStr.Format("Line %d Warning: %s",m_SourceCode.GetCurLine(),sMsg);
	m_slErrorMsgs.AddTail(sStr);
}

void CCompileCode::RaiseError(LPCTSTR sMsg)
{
	CString sStr;
	sStr.Format("Line %d Error: %s",m_SourceCode.GetCurLine(),sMsg);
	m_slErrorMsgs.AddTail(sStr);
}
void CCompileCode::WordMissing(LPCTSTR sWord)
{
	CString sStr;
	sStr.Format("missing \'%s\', but \'%s\' appears!",sWord,m_sCurWord );
	RaiseError(sStr);
}

void CCompileCode::WordRedefined(LPCTSTR sWord)
{
	CString sStr;
	sStr.Format("%s is redefined!",sWord);
	RaiseError(sStr);
}

#define RETURN_ISN(isn)	m_nCurISN = isn;  \
	return isn;

int	 CCompileCode::Advance()
{
	if(m_bIsBack){ // BackWord
		ASSERT(m_nCurISN);
		m_bIsBack = FALSE;
		return m_nCurISN;
	}

	m_sCurWord = m_SourceCode.GetAWord();
	if( m_sCurWord=="") 
		return KEY_UNKNOWN;

	int nISN = IsSeparator(m_sCurWord);
	if( nISN != 0) {
		m_CurWT = WT_SEPARATOR;
		RETURN_ISN(nISN);
	}

	nISN = IsOperator(m_sCurWord);
	if( nISN != 0) {
		m_CurWT = WT_OPERATOR;
		RETURN_ISN(nISN);
	}

	nISN = IsEvaluate(m_sCurWord);
	if( nISN != 0) {