wordanalyse.cpp

一个支持中文的类C语言编译器

// WordAnalyse.cpp: implementation of the CWordAnalyse class.
//
//////////////////////////////////////////////////////////////////////

#include "stdafx.h"
//#include "Compiler.h"
#include "WordAnalyse.h"
#include "assert.h"

#ifdef _DEBUG
#undef THIS_FILE
static char THIS_FILE[]=__FILE__;
#define new DEBUG_NEW
#endif

//////////////////////////////////////////////////////////////////////
// Construction/Destruction
//////////////////////////////////////////////////////////////////////
//基本字表的初始化工作
CTwoDim CWordAnalyse::Table_BaseWord[SIZE_TB]={
	{CTwoDim($IF,"if")},///////////////////
	{CTwoDim($ELSE,"else")},
	{CTwoDim($WHILE,"while")},
	{CTwoDim($SIGN,"\0")},////////////////////副作用？？？
	{CTwoDim($PLUS,"+")},
	{CTwoDim($MINUS,"-")},
	{CTwoDim($STAR,"*")},
	{CTwoDim($DIVIDE,"/")},
	{CTwoDim($AND,"&")},
	{CTwoDim($OR,"|")},
	{CTwoDim($LOW,"<")},
	{CTwoDim($LARGE,">")},
	{CTwoDim($EQU,"=")},
	{CTwoDim($NOT,"!")},
	{CTwoDim($LPAR,"(")},
	{CTwoDim($RPAR,")")},
	{CTwoDim($LBP,"{")},
	{CTwoDim($RBP,"}")},
	{CTwoDim($QUOT,"\"")},
	{CTwoDim($DOTCO,";")},
	{CTwoDim($COMMA,",")},
	{CTwoDim($DOT,".")},
	{CTwoDim($FCONST,(double)0)},//////////////
	{CTwoDim($ICONST,(long)0)},///////////////
	{CTwoDim($SCONST,"\0")},
	{CTwoDim($DAND,"&&")},
	{CTwoDim($DOR,"||")},
	{CTwoDim($LOEQ,"<=")},
	{CTwoDim($LAEQ,">=")},
	{CTwoDim($DEQ,"==")},
	{CTwoDim($NEQ,"!=")}};
CWordAnalyse::CWordAnalyse(CEdit * pctrEdit,const CString& strEdit)
{
	this->m_pctrEdit=pctrEdit;
	this->m_sOriginalResource=strEdit;//原始程序
	this->m_ptStr=NULL;//指针
	
	this->m_sWord.Empty();
	this->m_sChar.Empty();
	this->m_sBuffRes.Empty();
	//	this->m_ptstrEndOfFile=NULL;
	this->m_piPointer=0;
	
}
	
CWordAnalyse::~CWordAnalyse()
{
	
}
	
	//如果即将读取的字符是文件尾结束符，则指针无动作
	//（仍指向文件尾NULL,而整型指针无效（=getlenth()）），char='\000'
	//否则，读取该位置字符，指针后移
bool CWordAnalyse::GetChar()
{
	
	this->m_sChar.Empty();//清空字符
	VERIFY(this->m_ptStr!=NULL);
	if(*this->m_ptStr!='\000'&&this->m_piPointer<this->m_sBuffRes.GetLength()){
		if(IsDBCSLeadByteEx(0,*m_ptStr)){
			this->m_sChar=this->m_ptStr[0];
			this->m_sChar=this->m_sChar+this->m_ptStr[1];
			this->m_piPointer+=2;
		}
		else{
			this->m_sChar=this->m_ptStr[0];
			this->m_piPointer++;
		}
		this->m_ptStr=CharNext(this->m_ptStr);//指针后移一个“单元字符”
	}
	else{
		this->m_sChar='\000';
		return false;
	}
	
	VERIFY(this->m_sChar.GetLength()<=2);
	return true;
	
}

//
bool CWordAnalyse::GetNBC()
{
	
	while(m_sChar=='\040'||m_sChar=='\r'||m_sChar=='\n'){
		VERIFY(this->m_sChar.GetLength()==1);
		if(!this->GetChar()) return false;
	}
	return true;
	
}

void CWordAnalyse::Concat()
{
	this->m_sWord=this->m_sWord+this->m_sChar;
}

bool CWordAnalyse::IsLetterOrChinese()
{
	PTSTR ptStr;
	ptStr=this->m_sChar.GetBuffer(0);//TRACE("判断是否汉字或字母: %s\n",this->m_sChar);
	
	if(IsDBCSLeadByteEx(0,*ptStr)){//chinese
		return true;
	}
	
	if('A'<=this->m_sChar&&this->m_sChar<='Z'||
		'a'<=this->m_sChar&&this->m_sChar<='z'){//letter
		VERIFY(this->m_sChar.GetLength()==1);
		return true;
	}
	
	return false;
	
	
}

bool CWordAnalyse::IsDigit()
{
	PTSTR ptStr;
	ptStr=this->m_sChar.GetBuffer(0);
	
	
	
	if('0'<=this->m_sChar&&this->m_sChar<='9'){
		VERIFY(!IsDBCSLeadByteEx(0,*ptStr));
		VERIFY(this->m_sChar.GetLength()==1);
		return true;
	}
	else{
		return false;
	}
	
}

bool CWordAnalyse::Fortransact(CString &str)
{
	int lSp=0;//lSp 用作位置指示器
	int i=0;
	int j=0;
	//--------------------------------------------------------------------
	//TRACE("@@@@@@@@@@@@@@@@@@@@@@@@@2预处理前内部源程序长度为:%d\n",this->m_sBuffRes.GetLength());
	//TRACE("@@@@@@@@@@@@@@@@@@@@@@@@@2预处理前用户源程序长度为:%d\n",this->m_sOriginalResource.GetLength());
	//--------------------------------------------------------------------
	int line=0;
	bool flag=false;
	for(i=0;i<str.GetLength()-3;i++){
		flag=false;
		if(str.GetAt(i)=='/'&&str.GetAt(i+1)=='*'){
			for(line=i;line>0;line--){
				if(str.GetAt(line)=='\n'&&str.GetAt(line-1)=='\r')break;			
				if(str.GetAt(line)=='/'&&str.GetAt(line-1)=='/'){
					flag=true;//发现前面有//
					break;
				}
			}
			if(flag==true) continue;
			lSp=i+2;
			for(;lSp<str.GetLength()-1&&(!(str.GetAt(lSp)=='*'&&str.GetAt(lSp+1)=='/'));){
				lSp++;
				if(lSp>=str.GetLength()-1) break;
				
			}
			if(lSp>=str.GetLength()-1) {
				MessageBox(NULL,"找到未匹配的/*","语法错误",MB_OK|MB_ICONHAND);
				if(m_pctrEdit)
				{
					this->m_pctrEdit->SetSel(i,i+2);
					this->m_pctrEdit->SetFocus();
				}
				return false;
			}
			str.Delete(i,lSp+2-i);
			for(j=i;j<lSp+2;j++){
				str.Insert(i,' ');
			}
		}
		
	}//删除"/*...............*/"形式的注释），代之以同样数目的空白符
	
	//删除            //	
	for(i=0;i<str.GetLength()-1;i++){
		if(str.GetAt(i)=='/'&&str.GetAt(i+1)=='/'){
			lSp=i;//i指向第一个/
			for(;!(str.GetAt(lSp)=='\r'&&str.GetAt(lSp+1)=='\n')&&lSp<str.GetLength()-1;){
				lSp++;
				if(lSp>=str.GetLength()-1) break;
			}
			
			if(lSp>=str.GetLength()-1){//lSp指向文末最后一个字符
				str.Delete(i,lSp-i+1);//删除到文末
				for(j=i;j<lSp+1;j++){
					str.Insert(i,' ');//插入同样多的空格
				}
			}
			else {
				str.Delete(i,lSp-i);//删除到\r前一个字符
				for(j=i;j<lSp;j++){
					str.Insert(i,' ');//插入同样多的空格,直到回车键之前（\r）
				}
			}
		}
	}//删除"//------------"型），代之以同样数目的空白符
	
	for(i=0;i<str.GetLength();i++){
		if(str.GetAt(i)=='\t'){
			str.Delete(i,1);
			str.Insert(i,' ');
		}								
	}//删除tab字符，并代之以空白符
	
	//MessageBox(NULL,this->m_sOriginalResource,"",0);
	//
	//--------------------------------------------------------------------
	//TRACE("@@@@@@@@@@@@@@@@@@@@@@@@@2预处理后内部源程序长度为:%d\n",this->m_sBuffRes.GetLength());
	//TRACE("@@@@@@@@@@@@@@@@@@@@@@@@@2预处理后用户源程序长度为:%d\n",this->m_sOriginalResource.GetLength());
	//--------------------------------------------------------------------
	
	return true;
}

bool CWordAnalyse::OnInitWordAnalyse()
{
	this->m_sBuffRes=this->m_sOriginalResource;
	if(!this->Fortransact(this->m_sBuffRes))return false;//预处理后，m_sBuffRes将发生变化
	//	MessageBox(NULL,this->m_sBuffRes,"",0);
	//	TRACE("**********************\n");
	this->m_ptStr=this->m_sBuffRes.GetBuffer(0);
	
	
	VERIFY(m_ptStr!=NULL);
	return true;
}

void CWordAnalyse::Retract()
{
	VERIFY(this->m_ptStr!=NULL);
	if(IsDBCSLeadByteEx(0,*this->m_sChar.GetBuffer(0))){
		this->m_piPointer-=2;
	}
	else{
		this->m_piPointer--;
	}
	
	this->m_ptStr=CharPrev(this->m_sBuffRes.GetBuffer(0),this->m_ptStr);
	VERIFY(this->m_ptStr!=NULL);
	VERIFY(this->m_piPointer>=0);
	
	this->m_sChar.Empty();
	
}
	
void CWordAnalyse::assistant()
{
	if(!this->OnInitWordAnalyse()) return;
	//*/
	WordType result=$ILLEGALWORD;
	
	CString temp;
	while(result!=$ENDOFFILE)
	{
		result=this->Getsym().WdTp;
		
		switch(result)
		{
			case $ENDOFFILE://文件尾
				MessageBox(NULL,"文件尾","",0);
				break;
			case $SCONST://字符串型常量
				MessageBox(NULL,"字符串","",0);
				break;
			case $ILLEGALWORD:
				MessageBox(NULL,"非法","",0);
				break;
			case $IF:
				temp.Format("识别出了基本字if,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $ELSE:
				temp.Format("识别出了基本字else,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $WHILE:
				temp.Format("识别出了基本字while,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $SIGN:
				temp.Format("识别出了基本字标识符,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $PLUS:
				temp.Format("识别出了基本字+,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $MINUS:
				temp.Format("识别出了基本字-,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $STAR:
				temp.Format("识别出了基本字*,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $DIVIDE:
				temp.Format("识别出了基本字/,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $AND:
				temp.Format("识别出了基本字&,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $OR:
				temp.Format("识别出了基本字|,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $LOW:
				temp.Format("识别出了基本字<,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $LARGE:
				temp.Format("识别出了基本字>,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $EQU:
				temp.Format("识别出了基本字=,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $NOT:
				temp.Format("识别出了基本字!,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $LPAR:
				temp.Format("识别出了基本字(,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $RPAR:
				temp.Format("识别出了基本字),种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $LBP:
				temp.Format("识别出了基本字{,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $RBP:
				temp.Format("识别出了基本字},种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $DOTCO:
				temp.Format("识别出了基本字;,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $COMMA:
				temp.Format("识别出了基本字,,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $DOT:
				temp.Format("识别出了基本字.,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $FCONST:
				temp.Format("识别出了基本字 实常数,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $ICONST:
				temp.Format("识别出了基本字 整常数,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $DAND:
				temp.Format("识别出了基本字 &&,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $DOR:
				temp.Format("识别出了基本字 ||,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $LOEQ:
				temp.Format("识别出了基本字 <=,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $LAEQ:
				temp.Format("识别出了基本字 >=,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $DEQ:
				temp.Format("识别出了基本字 ==,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			case $NEQ:
				temp.Format("识别出了基本字 !=,种别码：%d",result);
				MessageBox(NULL,temp,"",0);
				break;
			default:
				MessageBox(NULL,"找到了该基本字，但暂时无法识别","",0);	
		}
	}
}

CTwoDim CWordAnalyse::Getsym()
{
	bool isNotEnd=true;//记录getchar()的执行情况
	
	WordType WType;//纪录种别编码
	CTwoDim	TDim;//构造函数已将之初始化了
	
	this->m_sWord.Empty();//每次词法分析前，m_sWord必须清空
	
	isNotEnd=this->GetChar();		
	if(isNotEnd)isNotEnd=this->GetNBC();
	if(isNotEnd){
		this->m_pPtWd.pFst_word=CharPrev(this->m_sBuffRes.GetBuffer(0),this->m_ptStr);//字头指针
		if(IsDBCSLeadByteEx(0,*m_pPtWd.pFst_word)){
			this->m_pPtWd.piFst_word=this->m_piPointer-2;//字头指针
		}
		else{
			this->m_pPtWd.piFst_word=this->m_piPointer-1;//字头指针