词法分析程序设计

【实验内容】

对一个简单语言的子集编制一个一遍扫描的词法分析程序。

【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。 

 

单词符号	种别码	单词符号	种别码
begin	1	:	17
if	2	:=	18
then	3	<	20
while	4	<>	21
do	5	<=	22
end	6	>	23
letter(letter|digit)*	10	>=	24
digitdigit*	11	=	25
+	13	;	26
-	14	(	27
*	15	)	28
/	16	#	0

 

 

 

 

 

 

 

 

 

 

 

 

 

写的比较杂

public class Test {
	//存关键字和符号方便调用
	static String token[]=new String[] {"#","begin","if","then","while","do","end","null","null","null","null",
			              "null","null","+","-","*","/",":",":=","null","<","<>","<=",">",">=","=",";","(",")"};
	static Map<Integer, String> map = new HashMap<>();
	//单词种别码
	static int syn;
	//单词自身字符串
	static String tokeN;
	//指向字符位数
	static int p;
	//输入字符
	static String prog;

	public static void main(String[] args) {
		// TODO Auto-generated method stub
		//将各种单词符号和种别码匹配，map方便调用
		for(int i=0;i<29;i++) {
		map.put(i,token[i]);
		}
	
	   System.out.println("\n please input string:");
	   Scanner sc=new Scanner(System.in);
	   prog=sc.nextLine();
	   p=0;      //字符位数初值
	   
	   
	   do {
			scan();     //调用扫描函数，判断为何种单词符号
			switch(syn)
			{
			//当为标识符和数字时
			case 11:
			case 10:
				System.out.println("(11,"+tokeN+") ");
				break;
			
			case -1:
				System.out.println("error");
			    break;
			//当为关键字和和符号时
			default:
				System.out.println("("+syn+","+token[syn]+") ");
			    break;
			}
			
	   }while(syn!=0);
	   
	}
	static void scan() {
		
		//int length=prog.length();
		
		char ch = prog.charAt(p);       //取第p个字符
		while(ch==' ') {
			p++;
			ch = prog.charAt(p);
		}
		//关键字，标识符判断
		if(ch>='0' && ch<='9' || ch>='A' && ch<='z') {   
			int s1=p;
			while(ch>='0' && ch<='9' || ch>='A' && ch<='z') {
				p++;
				ch = prog.charAt(p);
			}
			tokeN=prog.substring(s1,p);
			//和关键字表比较
			if(tokeN.equals(map.get(1)))
				syn=1;
			else if(tokeN.equals(map.get(2)))
				syn=2;
			else if(tokeN.equals(map.get(3)))
				syn=3;
			else if(tokeN.equals(map.get(4)))
				syn=4;
			else if(tokeN.equals(map.get(5)))
				syn=5;
			else if(tokeN.equals(map.get(6)))
				syn=6;
			else       //非关键字，标识符
				syn=10;
				
			}	
		else          //数字判断
			if(ch>='0' && ch<='9'){
				int s1=p;
				while(ch>='0' && ch<='9') {
					p++;
					ch = prog.charAt(p);
					syn=11;
				}
				tokeN=prog.substring(s1,p);
			}
			
		else        //其他符号判断
			switch(ch)
			{
			case '+':syn=13;
				p++;break;
			case '-':syn=14;
				p++;break;
			case '*':syn=15;
				p++;break;
			case '/':syn=16;
				p++;break;
			case ':':
				p++;
				ch = prog.charAt(p);
				if(ch=='=')
					syn=18;
				else {
					syn=17;
					p--;
				}
				p++;
				break;
			case '<':
				p++;
				ch = prog.charAt(p);
				if(ch=='>')
					syn=21;
				if(ch=='=')
					syn=22;
				else {
					syn=20;
					p--;
				}
				p++;
				break;
			case '>':
				p++;
				ch = prog.charAt(p);
				if(ch=='=')
					syn=24;
				else {
					syn=23;
					p--;
				}
				p++;
				break;
			case '=':syn=25;
				p++;break;
			case ';':syn=26;
				p++;break;
			case '(':syn=27;
				p++;break;
			case ')':syn=28;
				p++;break;
			case '#':syn=0;
				p++;break;
			default:syn=-1;
				break;
			
			}
					
		
	}
	

}