编译原理小作业词法分析程序

  1 import java.io.IOException;
  2 import java.util.Arrays;
  3 import java.util.HashMap;
  4 import java.util.Map;
  5 
  6 class Code{
  7     public static final int BEGINSY = 1;
  8     public static final int ENDSY = 2;
  9     public static final int IFSY = 3;
 10     public static final int THENSY = 4;
 11     public static final int ELSE = 5;
 12     public static final int IDSY = 20;
 13     public static final int INTSY = 21;
 14     public static final int PLUSY = 22;
 15     public static final int MINUSSY = 23;
 16     public static final int STARSY = 24;
 17     public static final int DIVISY = 25;
 18     public static final int LPARSY = 26;
 19     public static final int RPARSY = 27;
 20     public static final int COMMASY = 28;
 21     public static final int SEMISY = 29;
 22     public static final int COLONSY = 30;
 23     public static final int ASSIGNSY = 31;
 24     public static final int EQUSY = 32;
 25     public static Map<String, Integer> map = new HashMap<String, Integer>();
 26     // map to find the id of reserved.
 27     private static final String[] reserved = {"BEGIN", "END", "IF", "THEN", "ELSE"};
 28     public static void addReserv(){
 29         map.put("BEGIN", BEGINSY);
 30         map.put("END", ENDSY);
 31         map.put("IF", IFSY);
 32         map.put("THEN", THENSY);
 33         map.put("ELSE", ELSE);
 34     }
 35     public static boolean isReserv(String s){
 36         return Arrays.asList(reserved).contains(s);
 37     }
 38 }
 39 
 40 
 41 public class Word {
 42     private static String token = "";
 43     private static char lastC = 0;
 44     
 45     public static void main(String[] args) {
 46         char c=‘ ‘;//c is a char
 47         Code.addReserv();
 48         do {
 49             if(lastC==0){
 50                 do{//erase the blank character.
 51                     try {
 52                         c = (char)System.in.read();
 53                     } catch (IOException e) {e.printStackTrace();}
 54                 }while(c==‘ ‘||c==‘\t‘);
 55             }else{
 56                 c = lastC;//withdraw
 57             }
 58             int tmp = getsym(c);
 59             if(tmp!=-1&&tmp!=0)
 60                 System.out.println(tmp);
 61         } while (c!=-1);
 62     }
 63     
 64     private static int getsym(char c){
 65         lastC = 0;//give lastC a constant value to test whether it is altered.
 66         if(Character.isLetter(c)){// if c is a letter then link them together.
 67             token = "";
 68             do{
 69                 token += c;
 70                 try {
 71                     c = (char)System.in.read();
 72                 } catch (IOException e) {e.printStackTrace();}
 73             }while(Character.isDigit(c)||Character.isLetter(c));
 74             lastC = c;//use lastC to withdraw;
 75             System.out.print(token+"\t");
 76             return Code.isReserv(token)? Code.map.get(token).intValue() : Code.IDSY;
 77             //judge if token is reserved or Identifier.
 78         }else if(Character.isDigit(c)){// if c is digit then link them together
 79             token = "";
 80             do{
 81                 token += c;
 82                 try {
 83                     c = (char)System.in.read();
 84                 } catch (IOException e) {e.printStackTrace();}
 85             }while(Character.isDigit(c));
 86             lastC = c;//use lastC to withdraw;
 87             System.out.print(token+"\t");
 88             return Code.INTSY;
 89         }else if(c==‘:‘){
 90             try {
 91                 c = (char)System.in.read();
 92             } catch (IOException e) {e.printStackTrace();}
 93             if(c==‘=‘){
 94                 System.out.print(":=\t");
 95                 return Code.ASSIGNSY;
 96             }else{
 97                 System.out.print(":\t");
 98                 lastC = c;//use lastC to withdraw;
 99                 return Code.COLONSY;
100             }
101         }else if(c==‘+‘){
102             System.out.print("+\t");
103             return Code.PLUSY;
104         }else if(c==‘-‘){
105             System.out.print("-\t");
106             return Code.MINUSSY;
107         }else if(c==‘*‘){
108             System.out.print("*\t");
109             return Code.STARSY;
110         }else if(c==‘(‘){
111             System.out.print("(\t");
112             return Code.LPARSY;
113         }else if(c==‘)‘){
114             System.out.print(")\t");
115             return Code.RPARSY;
116         }else if(c==‘,‘){
117             System.out.print(",\t");
118             return Code.COMMASY;
119         }else if(c==‘;‘){
120             System.out.print(";\t");
121             return Code.SEMISY;
122         }else if(c==‘=‘){
123             System.out.print("=\t");
124             return Code.EQUSY;
125         }else if(c==‘/‘){
126             try {
127                 c = (char)System.in.read();
128             } catch (IOException e) {e.printStackTrace();}
129             if(c!=‘*‘){
130                 System.out.print("/\t");
131                 lastC = c;//use lastC to withdraw;
132                 return Code.DIVISY;
133             }else{//handle with the comments.
134                 do{
135                     do{
136                         try {
137                             c = (char)System.in.read();
138                         } catch (IOException e) {e.printStackTrace();}
139                     }while(c!=‘*‘);
140                     do{
141                         try {
142                             c = (char)System.in.read();
143                         } catch (IOException e) {e.printStackTrace();}
144                         if(c==‘/‘)    return 0;
145                     }while(c==‘*‘);
146                 }while(c!=‘*‘);
147             }
148         }
149         return -1;//-1 means wrong;
150     }
151     
152     
153 }