实验1 词法分析程序设计

【实验要求】

1、待分析的简单语言的词法

1) 关键字

begin if then while do end

2) 运算符和界符

:= + - * / < <= > >= <> = ; ( ) #

3) 其他单词是标识符(ID)和整形常数(NUM)，通过以下正规式定义：

ID=letter(letter|digit)*

NUM=digitdigit*

4) 空格由空白、制表符和换行符组成。空格一般用来分隔ID、NUM、运算符、界符和关键字，词法分析阶段通常被忽略。

2、各种单词符号对应的种别编码

3、词法分析程序的功能

输入：所给文法的源程序字符串

输出：二元组（syn,token或sum）构成的序列。

syn为单词种别码；

token为存放的单词自身字符串；

sum为整形常数。

例如：对源程序begin x:=9;if x>0 then x:=2*x+1/3;end# 经词法分析后输出如下序列：

（1，begin）(10,’x’) (18,:=) (11,9) (26,;) (2,if)……

#include <iostream>
#include <cstring>
using namespace std;

char prog[800];	//存储程序 
char token[10];	//存储单词字符串
char ch;	//当前字符 
int syn;	//单词种别码 
int sum;	//整型常数 
int p;	//prog指针
int m;	//token指针
int n; 
//关键字 
const char * rwtab[6] = {"begin", "if", "then", "while", "do", "end"};

bool isLetter(char ch);	//判断是否为字母 
bool isDigit(char ch);	//判断是否为数字 
void scanner();			//扫描分析器 

bool isLetter(char ch){
	if ((ch <= 'z' && ch >='a') || (ch <'Z' && ch >= 'A')){
		return true;
	}
	else{
		return false;
	}
}

bool isDigit(char ch){
	if(ch >= '0' && ch <= '9'){
		return true;
	}
	else{
		return false;
	}
	
} 

void scanner(){
	//清空token 
	for (n = 0 ; n < 8; n++){
		token[n] = NULL;
	}
	m = 0; 
	
	//获取下一个有效字符 
	ch = prog[p];
	while(ch == ' '){
		p++;
		ch = prog[p];
	}
	
	if(isDigit(ch)){
		//字符为数字 
		sum = 0;
		while (isDigit(ch)){
			sum = sum * 10 + ch - '0';	//str转换为数值类型
			p++;
			ch = prog[p]; 
			syn = 11;
		}
	}
	//字符为字符串 
	else if(isLetter(ch)){
		while(isDigit(ch) || isLetter(ch)){
			token[m] = ch;
			m++;
			p++;
			ch = prog[p];
		}
		token[m] = '\0';
		m++; 
		syn = 10;
		for(n = 0; n < 6; n++){
			if(strcmp(token, rwtab[n]) == 0){
				syn = n + 1;
				break;	
			}
		}
	}
	else{
 	    switch (ch){
 			case '<':
 				syn = 20;
 				m = 0;
 				token[m] = ch;
 				m++;
 				p++;
 				ch = prog[p];
	            if (ch == '>') {
	                syn = 21;
					token[m] = ch;
					m++;
	 				p++;
	 				ch = prog[p];					
	            }
	            else if (ch == '=') {
	                syn = 22;
					token[m++] = ch;
					m++;
					p++;
 					ch = prog[p];
	        	}
	            break;
	        
			case '>':
				syn = 23;
	            m = 0;
	            token[m++] = ch;
	            p++;
	            ch = prog[p];    
	            if (ch == '=') {
	            	syn = 24;
	                token[m] = ch;
	                m++;
	                p++;
            		ch = prog[p];
	            }
	            break;
	            
	        case ':':
	        	syn = 17;
	            m = 0;
	            token[m] = ch;
	            m++;
	            p++;
	            ch = prog[p];    
	            if (ch == '=') {
	            	syn = 18;
	                token[m] = ch;
	                m++;
	                p++;
	                ch = prog[p];
	            }
	            break;
	            
	        case '+':
	            syn = 13;
	            token[0] = ch;
				p++;
            	ch = prog[p];
	            break;
	            
	        case '-':
	            syn = 14;
	            token[0] = ch;
	            p++;
            	ch = prog[p];
				break;
	            
	        case '*':
	            syn = 15;
	            token[0] = ch;
	            p++;
            	ch = prog[p];
	            break;
	            
	        case '/':
	            syn = 16;
	            token[0] = ch;
	            p++;
            	ch = prog[p];
	            break;

	        case '=':
	            syn = 25;
	            token[0] = ch;
	            p++;
            	ch = prog[p];
	            break;
	            
	        case ';':
	            syn = 26;
	            token[0] = ch;
	            p++;
            	ch = prog[p];
	            break;
	            
	        case '(':
	            syn = 27;
	            token[0] = ch;
	            p++;
            	ch = prog[p];
	            break;
	            
	        case ')':
	            syn = 28;
	            token[0] = ch;
	            p++;
            	ch = prog[p];
	            break;
	            
	        case '#':
	            syn = 0;
	            token[0] = ch;
	            break;
	        default:
	        	syn = -1;
	        	break;        	
	        }
	} 

}

int main(int argc, char** argv) {

	cout << "please input string: \n" << endl;
	
	p = 0;
	char str;
	
	//获取程序 
	do{
		str = getchar();
		prog[p] = str;
		p++;	
	}while(str != '#');
	
	p = 0;
	ch = prog[p];

	//开始分析 
	do{
		scanner();
		switch(syn){
			case 11:
				cout << "(" << syn << "," << sum << ")" << endl;
				break;
			case -1:
				cout << "error" << endl;
				break;
			default:
				cout << "("<< syn << "," << token << ")" <<endl;
		}
	}while(syn != 0);
	
    system("pause");

	return 0;
}

气人的编译器！！！