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

1 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

词法分析器源代码

  1 package com.gxf.lexical;
  2
  3 import java.util.Scanner;
  4
  5 public class Lexical {
  6     String input = "";                                        //源程序
  7     String keyWords[] = {"int", "for"};                        //关键词
  8     int point = 0;                                            //全局指针指向源程序
  9     int syn = 0;                                            //单词种别码
 10     int sum = 0;                                            //数字的总和
 11     StringBuffer token = new StringBuffer("");                //存放单词
 12
 13     public static void main(String[] args) {
 14         Scanner scanner = new Scanner(System.in);
 15         Lexical lexical = new Lexical();
 16
 17         lexical.input = scanner.nextLine();
 18 //        System.out.println(lexical.input);//输入源程序
 19         scanner.close();
 20
 21         do{
 22             lexical.scanner();
 23             switch(lexical.syn){
 24                 case 4:
 25                     System.out.println("(" + lexical.syn + "," + lexical.sum + ")");
 26                     break;
 27                     default:
 28                         System.out.println("(" + lexical.syn + "," + lexical.token + ")");
 29                     break;
 30             }
 31         }while(lexical.syn != 17);
 32     }
 33
 34     /**
 35      * 词法分析器
 36      */
 37     public void scanner(){
 38         //将单词置为空
 39         token = new StringBuffer();
 40         while(‘ ‘ == input.charAt(point))
 41             point++;                                        //去掉空格
 42         if((input.charAt(point) >= ‘a‘ && input.charAt(point) <= ‘z‘) ||
 43                 (input.charAt(point) >= ‘A‘ && input.charAt(point) <= ‘Z‘)){//关键词或者标识符
 44             syn = 3;//种别码为3
 45             while((input.charAt(point) >= ‘a‘ && input.charAt(point) <= ‘z‘) ||
 46                     (input.charAt(point) >= ‘A‘ && input.charAt(point) <= ‘Z‘) ||
 47                     (input.charAt(point) >= ‘0‘ && input.charAt(point) <= ‘9‘)){
 48                 token.append(input.charAt(point));
 49                 point++;
 50             }
 51 //            point--;//后退一个位置
 52             for(int i = 0; i < keyWords.length; i++){
 53                 if(keyWords[i].equals(String.valueOf(token))){
 54                     syn = i + 1;//修改种别码
 55                     break;
 56                 }
 57             }
 58         }//if
 59         else if(input.charAt(point) >= ‘0‘ && input.charAt(point) <= ‘9‘){//如果是数字
 60             syn = 4;
 61             sum = 0;
 62             while(input.charAt(point) >= ‘0‘ && input.charAt(point) <= ‘9‘){
 63                 sum = sum * 10 + (input.charAt(point) - ‘0‘);
 64                 point++;
 65             }
 66             //point--;//后退一个字符
 67         }//else if
 68         else{//其他字符
 69             switch(input.charAt(point)){
 70                 case ‘>‘://大于符号
 71                     token = new StringBuffer(">");//重置token
 72                     point++;
 73                     if(input.charAt(point) == ‘=‘){
 74                         token.append("=");
 75                         syn = 10;
 76                     }else{
 77                         syn = 9;
 78                         point--;
 79                     }
 80                     point++;
 81                     break;
 82                 case ‘<‘:
 83                     token = new StringBuffer("<");
 84                     point++;
 85                     if(input.charAt(point) == ‘=‘){
 86                         token.append("=");
 87                         syn = 12;
 88                     }else{
 89                         syn = 11;
 90                         point--;
 91                     }
 92                     point++;
 93                     break;
 94                 case ‘*‘:
 95                     token = new StringBuffer("*");
 96                     syn = 5;
 97                     point++;
 98                     break;
 99                 case ‘/‘:
100                     token = new StringBuffer("/");
101                     syn = 6;
102                     point++;
103                     break;
104                 case ‘+‘:
105                     token = new StringBuffer("+");
106                     syn = 7;
107                     point++;
108                     break;
109                 case ‘-‘:
110                     token = new StringBuffer("-");
111                     syn = 8;
112                     point++;
113                     break;
114                 case ‘;‘:
115                     token = new StringBuffer(";");
116                     syn = 14;
117                     point++;
118                     break;
119                 case ‘(‘:
120                     token = new StringBuffer("(");
121                     syn = 15;
122                     point++;
123                     break;
124                 case ‘)‘:
125                     token = new StringBuffer(")");
126                     syn = 16;
127                     point++;
128                     break;
129                 case ‘#‘:
130                     token = new StringBuffer("#");
131                     syn = 17;
132                     point++;
133                     break;
134                 case ‘=‘:
135                     token = new StringBuffer("=");
136                     syn = 13;
137                     point++;
138                     break;
139             }
140
141         }
142     }
143 }

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