accanalyse.java

一个用java实现的词法和语法分析器

package jywhu;
import java.io.*;
import java.util.*;

public class AccAnalyse {
	private ArrayList al;
	private static int i=0;
	private static final String[] reserveWord={"if","else","while","read","write","int","real"};
	private String str;
	private static int lineCount=0;
	private int index=0;
	private String token;
	public AccAnalyse(String str){
		this.str=str;
		al=new ArrayList();
	}
	/*public ArrayList getList(){
		return al;
	}*/
	public void analyse(){
		File f=new File(str);
		try{
			if(!f.exists()){
				System.out.println("源文件不存在");
			}else{
					BufferedReader br=new BufferedReader(new FileReader(f));
					String s;
					//开始词法分析
					while((s=br.readLine())!=null){
						lineCount++;
						//过滤行字符串
						s=s.trim();
						System.out.println(lineCount + ":" + s);
						char[] c=s.toCharArray();
						while(index<c.length){
							token=" ";
							char ch=this.getChar(c);
							switch(ch){
							//此字符为字母
							case 'a':case 'b':case 'c':case 'd':case 'e':case 'f':case 'g':case 'h':case 'i':case 'j':case 'k':case 'l':
							case 'm':case 'n':case 'o':case 'p':case 'q':case 'r':case 's':case 't':case 'u':case 'v':case 'w':case 'x':
							case 'y':case 'z':case 'A':case 'B':case 'C':case 'D':case 'E':case 'F':case 'G':case 'H':case  'I':case 'J':
							case 'K':case 'L':case 'M':case 'N':case 'O':case 'P':case 'Q':
							case 'R':case 'S':case 'T':case 'U':case 'V':case  'W':case 'X':case 'Y':case 'Z':
								token=this.contact(token, ch);
								if(index==c.length){
									 //System.out.println(" " + " " + lineCount + ": " +  "ID, name=" + token );
									al.add(new Token("id",token,lineCount));
									break;
									}else{
			               ch=this.getNextChar(c);
			               while(this.isLetter(ch) || this.isDigit(ch) || ch=='_'){
			            	   token=this.contact(token, ch);
			            	   if(index==c.length)
			            		   break;
			            	   else
			            	   ch=this.getNextChar(c);
			               }
								}
			            if(index<=c.length)   this.retract();
			               //判断此字符串为标识符
			               token=token.trim();
			               if(token.charAt(token.length()-1)=='_'){
			            	   System.out.println(" " + " " + lineCount + ":" + 
							    		"[ERROR]在此行发现非法的标识符!" + " " + token);
			               }else{
			            	   //此字符串为保留字
			               if(this.isReserve(token)){
			            	   //System.out.println(" " + " " + lineCount + ": " + "reserved word:" + token);
			            	  
			            	  al.add(new Token(token,token,lineCount));
			               }else{
			            	   //System.out.println(" " + " " + lineCount + ": " +  "ID, name=" + token );
			            	   al.add(new Token("id",token,lineCount));
			               }
			               }
			               token=" ";
			               break;
			               //此字符为数字
						   case '0':case '1':case '2':case '3':case '4':case '5':case '6':case '7':case '8': case  '9':
								 token=this.contact(token, ch);
								 if(index==c.length){
									 //System.out.println(" " + " " + lineCount + ": " +  "NUM, val=" + token );
									 al.add(new Token("num",token,lineCount));
									 break;
								 }else{
					             ch=this.getNextChar(c);
					             while(this.isDigit(ch) || ch=='.'){
					            	 token=this.contact(token, ch);
					            	  if(index==c.length)
					            		  
					            		   break;
					            	   else
					            	   ch=this.getNextChar(c);
					             }
								 }
					            if(index<=c.length)  this.retract();
					             int count=0;
					             for(int i=0;i<token.length();i++){
					            	 if(token.charAt(i)=='.'){
					            		 count++;
					            	 }
					             }
					             //判断此字符串为数字
					             if(count==0){
					             //System.out.println(" " + " " + lineCount + ": " +  "NUM, val=" + token );
					            	 al.add(new Token("intNum",token,lineCount));
					             }else if(count==1){
					            	 al.add(new Token("realNum",token,lineCount));
					             }else{
					            	 System.out.println(" " + " " + lineCount + ":" + 
									    		"[ERROR]在此行发现非法的数字!" + " " + token);
					             }
					             token=" ";
					        break;
						   case '=':
							   token=this.contact(token, ch);
							   ch=this.getNextChar(c);
						       if(ch=='='){
						    	   index++;
						    	   token=this.contact(token, ch);
						    	  // System.out.println(" " + " " + lineCount + ":" + token );
						    	   al.add(new Token("relop",token,lineCount));
						       }else{
						    	   //System.out.println(" " + " " + lineCount + ":" + token );
						    	   al.add(new Token("equalop",token,lineCount));
						       }
						      this.retract();
						      token=" ";
						      break;
						   case '+':
							   token=this.contact(token, ch);
							   //System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("addop",token,lineCount));
							   token=" ";
							   break;
						   case '*':
							   token=this.contact(token, ch);
							   //System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("mulop",token,lineCount));
							   token=" ";
							   break;
						   case '(':
							   token=this.contact(token, ch);
							   //System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("leftbracket",token,lineCount));
							   token=" ";
							   break;
						   case ')':
							   token=this.contact(token, ch);
							  // System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("rightbracket",token,lineCount));
							   token=" ";
							   break;
						   case '{':
							   token=this.contact(token, ch);
							  // System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("bleftbracket",token,lineCount));
							   token=" ";
							   break;
						   case '}':
							   token=this.contact(token, ch);
							   //System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("brightbracket",token,lineCount));
							   token=" ";
							   break;
						   case '[':
							   token=this.contact(token, ch);
							   //System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("mleftbracket",token,lineCount));
							   token=" ";
							   break;
						   case ']':
							   token=this.contact(token, ch);
							  // System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("mrightbracket",token,lineCount));
							   token=" ";
							   break;
						   case '<':
							   token=this.contact(token, ch);
							   ch=this.getNextChar(c);
						       if(ch=='>'){
						    	   index++;
						    	   token=this.contact(token, ch);
						    	   //System.out.println(" " + " " + lineCount + ":" + token );
						    	   al.add(new Token("relop",token,lineCount));
						       }else{
						    	   //System.out.println(" " + " " + lineCount + ":" + token );
						    	   al.add(new Token("relop",token,lineCount));
						       }
						      this.retract();
						      token=" ";
						      break;
						   case '-':
							   token=this.contact(token, ch);
							  // System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("addop",token,lineCount));
							   token=" ";
							   break;
						   case '/':
							   token=this.contact(token, ch);
							   //System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("mulop",token,lineCount));
							   token=" ";
							   break;
						   case ',':
							   token=this.contact(token, ch);
							   //System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("comma",token,lineCount));
							   token=" ";
							   break;
						   case ';':
							   token=this.contact(token, ch);
							  // System.out.println(" " + " " + lineCount + ":" + token );
							   al.add(new Token("semicolon",token,lineCount));
							   token=" ";
							   break;
						default:
							token=this.contact(token, ch);
						    System.out.println(" " + " " + lineCount + ":" + 
						    		"[ERROR]在此行发现不能识别的单词,此行分析终止!" + " " + token);
						    token=" ";
						    break;
						}
						}
						index=0;
						}
			}
		}catch(Exception e){
			e.printStackTrace();		}
	}
	
	//得到一个字符
	public char getChar(char[] c){
		try{
			while((c[index]) == ' '){
				index++;
			}
			index++;
		}catch(Exception e){
			e.printStackTrace();
		}
		return c[index-1];
	}
	
	//得到先前字符的后一个字符
	public char getNextChar(char[] c){
		index++;
		return c[index-1];
	}
	
	public boolean isLetter(char ch){
		return Character.isLetter(ch);
	}
	
	public boolean isDigit(char ch){
		return Character.isDigit(ch);
	}
	
	//判断此字符串是否为保留字
	public boolean isReserve(String token){
		for(int i=0;i<reserveWord.length;i++){
			if(token.equals(reserveWord[i])){
				return true;
			}
		}
		return false;
	}
	
	public String contact(String token,char ch){
		String tmp=token + String.valueOf(ch);
		token=tmp;
		return token;
	}
	
	public void retract(){
		index--;
	}


	public Token getToken(){
		i=i+1;
		return (Token)al.get(i-1);
		
	}
	//判断arraylist是否操作越界
	public boolean isOut(){
		if(i<al.size())
			return true;
		else
		    return false;
	}

}
class Token implements Serializable{
	private String tokenType;
	private String token;
	private int lineno;
	public Token(String tokenType,String token,int lineno){
		this.tokenType=tokenType;
		this.token=token;
		this.lineno=lineno;
	}
	public String getTokenType(){
		return tokenType;
	}
	public String getToken(){
		return token;
	}
	public int getLineno(){
		return lineno;
	}
	
}