lexicalforc.cpp

c语言词法分析程序的实现

#include <iostream>
#include <fstream>
#include <string>
/*姓名： 赵晓东
*学号：063372
*班级：RJ010606*/
using namespace std;



string keyWord[10] = {"else", "if", "int", "return", "void", "while"};  //关键字集合

string symbol[30] = { "+", "-", "*", "/", "<", "<=", ">", ">=","=", "==", "!=",  

						";", ",",  "(", ")", "[", "]", "{", "}", "/*", "*/" };  //专用符号集合


bool isKeyWord(string s){           //查询是否是关键字
	for(int i = 0; i < 6; i++){
		
		if(s == keyWord[i]){
			
			return true;
		}
	}
	
	return false;
}


bool isSymbol(string s){			//查询是否是专门符号
	for(int i = 0; i < 21; i++){
		if(s == symbol[i]){
			
			return true;
		}
	}
	
	return false;
}


void main(){
	cout<<"请输入源文件名："<<endl;
	string fileName;
	cin>>fileName;
	
	char token[30];
	string word;
	int i = 0, line = 1;
	
	
	ifstream infile;
	ofstream outfile;
	infile.open (fileName.c_str(), ifstream::in);
	outfile.open("out.txt",ofstream::trunc);
	
	char ch = infile.get();
	
    while (infile.good()){
		i = 0;
		
		
		if(((ch>='A')&&(ch<='Z'))||((ch>='a')&&(ch<='z')))  {         //第一个字符为字母时可能为关键字或者标示符ID    
            while(((ch>='A')&&(ch<='Z'))||((ch>='a')&&(ch<='z'))) { 
				
                token[i++]=ch;   
                ch=infile.get();  
            }
			
			if(ch >= '0'&&ch <= '9'){								//标示符中不能出现数字，否则报错
				
				
				while((ch>='0')&&(ch<='9')){
					token[i++]=ch;
					ch = infile.get();
				}
				token[i] = '\0';
				outfile<<"there is a error "<<token<<" in line "<<line<<endl;
				infile.seekg(-1L,ios::cur);						//对扫描位置回溯，判断其他的可能性
																//此种方法在本例中多次用到
			}
			else{
				token[i] = '\0';
				word = token;
				
				if(isKeyWord(word))									//判断是否是关键字
					outfile<<"KEYWORD"<<"\t\t"<<word<<endl;
				else
					
					outfile<<"ID"<<"\t\t"<<word<<endl;				//非关键字就是标示符
				
				if(ch != EOF)
					infile.seekg(-1L,ios::cur);
			} 
			
		}
        else if(ch>='0'&&ch<='9'){							//第一个字符以数字开头的序列
			while(ch>='0'&&ch<='9')   {   
                token[i++]=ch;   
                ch=infile.get();  
            }
			
			if(((ch>='A')&&(ch<='Z'))||((ch>='a')&&(ch<='z')))  {             
				while(((ch>='A')&&(ch<='Z'))||((ch>='a')&&(ch<='z'))) 	{   
					token[i++]=ch;   
					ch=infile.get();  
				}
				token[i] = '\0';
				outfile<<"there is a error "<<token<<" in line "<<line<<endl;
				infile.seekg(-1L,ios::cur);
			}
			else{
				token[i] = '\0';
				word = token;
				
				outfile<<"NUMBER"<<"\t\t"<<word<<endl;	
				
				if(ch != EOF)
					infile.seekg(-1L,ios::cur);
			}
		}
		else if((ch==' ')||(ch=='\t'))   
            ;												//遇到空格符和制表符跳过 
        else if(ch=='\n')   
            line++;  
		else if(ch=='/') {							        //跳过注释   
            ch=infile.get();    
            if(ch!='*') {                                   //以“/”开头的还可能是除号 
                outfile<<"SYMBOL"<<"\t\t"<<'/'<<endl;	
                infile.seekg(-1L,ios::cur); 
            }   
            else if(ch=='*')   
            {                 
                int count=0;   
                ch=infile.get();   
                while(count!=2)                             //寻找注释的另一半标志“*/”
                {          
                    count=0;   
                    while(ch!='*')   
						ch=infile.get();    
                    count++;   
                    ch=infile.get();    
                    if(ch=='/')   
                        count++;   
                    else   
						ch=infile.get();    
                }   
            }   
        } 
		else if(ch=='"'){                                 //消除双引号中的常量   
            outfile<<"SYMBOL"<<"\t\t"<<'"'<<endl;
			
            ch=infile.get();     
            while(ch!='"')   
                ch=infile.get();    
            outfile<<"SYMBOL"<<"\t\t"<<'"'<<endl;       //消除单引号中的常量
        }
		else if(ch=='\''){                  
            outfile<<"SYMBOL"<<"\t\t"<<'\''<<endl;			            
			
            ch=infile.get();     
            while(ch!='\'')   
                ch=infile.get();    
            outfile<<"SYMBOL"<<"\t\t"<<'\''<<endl;   
        }
		else{
			token[0]=ch;   
            ch=infile.get();							//继续读入第二个字符，判断是否是组合符号  
            if(ch!=EOF)   
            {            
                token[1]=ch; 
				token[2]='\0';
				
				word = token;
                if(!isSymbol(word))   
                {                                         //非组合符号的话检查单个符号  
                    token[1] = '\0';  
                    word = token;
                    if(!isSymbol(word))   
                    {                            
                        outfile<<"there is a error "<<word<<" in line "<<line<<endl;  
                        infile.seekg(-1L,ios::cur);  
                    }   
                    else   
                    {     
                        outfile<<"SYMBOL"<<"\t\t"<<word<<endl;    
                        infile.seekg(-1L,ios::cur); 
                    }   
                }   
                else   
                {             
					outfile<<"SYMBOL"<<"\t\t"<<word<<endl;   
                }   
            }   
            else   
            {               
                
				token[1] = '\0';
				word = token;
                if(!isSymbol(word))                
                    outfile<<"there is a error "<<word<<" in line "<<line<<endl;   
                else   
                {                           
                    outfile<<"SYMBOL"<<"\t\t"<<word<<endl;  
                }   
            }   
        }  
		
        ch=infile.get(); 
		}
		
		infile.close();
		outfile.close();
		
		
		return;
		
}