java 词法分析器

参考：http://www.cnblogs.com/yanlingyin/archive/2012/04/17/2451717.html

实现了一个简单的java词法分析器

功能：词法分析下面一段java小程序

 int sum = 0; for(int i = 1; i <= 100; i = i + 1) sum += i;#

1.程序片段中使用到的关键字、运算符和界符：

关键词：

Int for

运算符：

+ =

界符：

( ) <= #

2.单词和单词种别码设计

单词符号	种别码
Int	1
For	2
Letter(letter|digit)*	3
Digit|digit*	4
*	5
/	6
+	7
-	8
>	9
>=	10
<	11
<=	12
=	13
;	14
(	15
)	16
#	17

词法分析器源代码

 package com.gxf.lexical;

 import java.util.Scanner;

 public class Lexical {
     String input = "";                                        //源程序
     String keyWords[] = {"int", "for"};                        //关键词
     int point = 0;                                            //全局指针指向源程序
     int syn = 0;                                            //单词种别码
     int sum = 0;                                            //数字的总和
     StringBuffer token = new StringBuffer("");                //存放单词

     public static void main(String[] args) {
         Scanner scanner = new Scanner(System.in);
         Lexical lexical = new Lexical();

         lexical.input = scanner.nextLine();
 //        System.out.println(lexical.input);//输入源程序
         scanner.close();

         do{
             lexical.scanner();
             switch(lexical.syn){
                 case 4:
                     System.out.println("(" + lexical.syn + "," + lexical.sum + ")");
                     break;
                     default:
                         System.out.println("(" + lexical.syn + "," + lexical.token + ")");
                     break;
             }
         }while(lexical.syn != 17);
     }

     /**
      * 词法分析器
      */
     public void scanner(){
         //将单词置为空
         token = new StringBuffer();
         while(' ' == input.charAt(point))
             point++;                                        //去掉空格
         if((input.charAt(point) >= 'a' && input.charAt(point) <= 'z') ||
                 (input.charAt(point) >= 'A' && input.charAt(point) <= 'Z')){//关键词或者标识符
             syn = 3;//种别码为3
             while((input.charAt(point) >= 'a' && input.charAt(point) <= 'z') ||
                     (input.charAt(point) >= 'A' && input.charAt(point) <= 'Z') ||
                     (input.charAt(point) >= '0' && input.charAt(point) <= '9')){
                 token.append(input.charAt(point));
                 point++;
             }
 //            point--;//后退一个位置
             for(int i = 0; i < keyWords.length; i++){
                 if(keyWords[i].equals(String.valueOf(token))){
                     syn = i + 1;//修改种别码
                     break;
                 }
             }
         }//if
         else if(input.charAt(point) >= '0' && input.charAt(point) <= '9'){//如果是数字
             syn = 4;
             sum = 0;
             while(input.charAt(point) >= '0' && input.charAt(point) <= '9'){
                 sum = sum * 10 + (input.charAt(point) - '0');
                 point++;
             }
             //point--;//后退一个字符
         }//else if
         else{//其他字符
             switch(input.charAt(point)){
                 case '>'://大于符号
                     token = new StringBuffer(">");//重置token
                     point++;
                     if(input.charAt(point) == '='){
                         token.append("=");
                         syn = 10;
                     }else{
                         syn = 9;
                         point--;
                     }
                     point++;
                     break;
                 case '<':
                     token = new StringBuffer("<");
                     point++;
                     if(input.charAt(point) == '='){
                         token.append("=");
                         syn = 12;
                     }else{
                         syn = 11;
                         point--;
                     }
                     point++;
                     break;
                 case '*':
                     token = new StringBuffer("*");
                     syn = 5;
                     point++;
                     break;
                 case '/':
                     token = new StringBuffer("/");
                     syn = 6;
                     point++;
                     break;
                 case '+':
                     token = new StringBuffer("+");
                     syn = 7;
                     point++;
                     break;
                 case '-':
                     token = new StringBuffer("-");
                     syn = 8;
                     point++;
                     break;
                 case ';':
                     token = new StringBuffer(";");
                     syn = 14;
                     point++;
                     break;
                 case '(':
                     token = new StringBuffer("(");
                     syn = 15;
                     point++;
                     break;
                 case ')':
                     token = new StringBuffer(")");
                     syn = 16;
                     point++;
                     break;
                 case '#':
                     token = new StringBuffer("#");
                     syn = 17;
                     point++;
                     break;
                 case '=':
                     token = new StringBuffer("=");
                     syn = 13;
                     point++;
                     break;
             }    

         }
     }
 }

注意程序片段要以#号结束

其实，上面参考的博客写得还不错可以看看