package testExperiment

//Demonstrate Lex Analyzer
//The purpose of this experiment is to make us familiar with  Lex-like Algorithem
//first let me make a introduction:
//This Analyzer is programmed by Java languange
//By useing 11 methods (including main method) ,it is concise and easy for reading

import java.io.*;
import java.util.StringTokenizer;

//Class name
public class Compiler_Simulate_Lex 
{   
	//Main method
	public static void main(String[] args)
	{
		//Set a counter
		int counter = 0;
		
        //It has 98 keywords
		String[] Keyword = {
"absolute","end","inline","procedure","type","and","external","interface","program","unit","array","file","interrupt","record","until","begin","for","label","repeat","uses","case","forward","mod","set","var","const","function","nil","shl","while","div","goto","not","shr","with","do","if","of","string","xor","downto","implementation","in","then","else","or","packed","to","ABSOLUTE","END","INLINE","PROCEDURE","TYPE","AND","EXTERNAL","INTERFACE","PROGRAM","UNIT","ARRAY","FILE","INTERRUPT","RECORD","UNTIL","BEGIN","FOR","LABEL","REPEAT","USES","CASE","FORWARD","MOD","SET","VAR","CONST","FUNCTION","NIL","SHL","WHILE","DIV","GOTO","NOT","SHR","WITH","DO","IF","OF","STRING","XOR","DOWNTO","IMPLEMENTATION","IN","THEN","ELSE","OR","PACKED","TO","WRITE","write"
				};
		
		//It has 52 alphabetas
		String Alphabeta = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ";
		
		//It has 10 numbers in all
		String Digit = "0123456789";
		
		//It has 13 identities
		String Identity = "\"\'\\<=>:+-();/";
		
		//Give a pascal program as a test
		//The total number of words is 96
		String TestPascalProgram = "program tripme ( input , output ) ; " +
				"var " +
				"x , y , c : integer ; " +
				"function add ( int a , int b ) : int " +
				"begin add = a + b ; end ; " +
				"function subtract ( int a , int b ) : int " +
				"begin subtract = a - b ; end ; " +
				"begin x = 6 ; y = 2 ; c := subtract ( a , b ) ; " +
				"write ( c ) ; c := add ( a , b ) ; " +
				"write ( c ) ; end .";
		
		
	    //show the TestProgram
		System.out.println("Here is a Pascal program for testing the Lex analyzer:");
		System.out.println("***********************************************************");
		System.out.println("program tripme (input , output);");
		System.out.println("var ");
		System.out.println("x , y , c : integer ; ");
		System.out.println("function add (int a , int b) : int ");
		System.out.println("begin add = a + b ; end ; ");
		System.out.println("function subtract (int a , int b) : int ");
		System.out.println("begin subtract = a - b ; end ; ");
		System.out.println("begin x = 6 ; y = 2 ; c := subtract (a , b) ; ");
		System.out.println("write (c) ; c := add (a , b) ; " );
		System.out.println("write (c) ; end .");
		
		
//Remind that the analyze begins.
		System.out.println("***********************************************************");
		System.out.println("");
		System.out.println("Now begin analyzing:");
		System.out.println('\r');

		//Create String[] to store TestProgram
		String[] Tokens = (String[])tokenIntoArray(TestPascalProgram).clone();
		
		//Use loop to identify program
		for(counter = 0;counter <= numberOfTokens(TestPascalProgram);counter++)
		{
			//first check whether it is a keyword and then print the result out
			System.out.print(Tokens[counter]);
			
			if(isKeyword(Tokens[counter],Keyword))
					{
				        System.out.println('\b'+": Is a keyword"+"and is located at"+
						locateKeyword(Tokens[counter],Keyword));
					}
			
			//Then Check whether it is a Alphabeta
			else if(isAlphabeta(Tokens[counter],Alphabeta))
			           {
				    
				//The process below is worthless,should be deleted
				if(locateAlphabeta(Tokens[counter],Alphabeta) > 0)
				              { 
					           System.out.print('\b'+": Is a Alphabeta"+"and is located at"
				               +locateAlphabeta(Tokens[counter],Alphabeta)+95);
				              }
				    else{}
				   
			           }
			
			//And then check whether it is a Digit
			else if(isDigit(Tokens[counter],Digit))
			{
				System.out.println('\b'+": Is a digit"+"and is located at"+
						locateDigit(Tokens[counter],Digit)+95+52);
			}
			
			//Finally check whether it is a Identity
			else if(isIdentity(Tokens[counter],Identity))
			{
				System.out.println('\b'+": Is a identity and is located at"+
						locateIdentity(Tokens[counter],Identity)+95+52+10);
			}
		}
		
		System.out.println("Analysis completed successfully");
	}
	
	//Give a method to create a way,analyzing the Array of Tokens 
	//that whether it is a keyword
	public static boolean isKeyword(String Token, String[] keyword)
	{
		int i = 0;
		while(keyword[i] != Token)
		{
			i=i+1;
		}
		if(i>97) return false;
		else return true;
	}
	
	//A method to analyze Tokens wheteher it is a Alphabeta.
	public static boolean isAlphabeta(String Token, String alphabeta)
	{
		int i = 0;
		while(Token.charAt(0) != alphabeta.charAt(i))
		{
			i++;
		}
	
		if(i>51) return false;
		else return true;
	}
	
    //A method to analyze Tokens wheteher it is a digit.
	public static boolean isDigit(String Token, String digit)
	{
		int i = 0;
		while(Token.charAt(0) != digit.charAt(i))
		{
			i++;
		}
		if(i>9) return false;
		else return true;
	}
	
    //A method to analyze Tokens wheteher it is a identity
	public static boolean isIdentity(String Token, String identity)
	{
		int i = 0;
		while(Token.charAt(0) != identity.charAt(i))
		{
			i++;
		}
		if(i>12) return false;
		else return true;
	}
	
	//Make the testprogram into tokens and then store in an array
	public static String[] tokenIntoArray(String s)
	{
		//make a counter to limit the process of copy
		int counter = 0; 
		
		 //Make an Array to store Tokens.
		String[] Tokens = new String[98];
		
		StringTokenizer Words = new StringTokenizer(s);
		
		//Clone Tokens to Array
		while(Words.hasMoreElements())
		{
			Tokens[counter] = Words.nextToken();
			counter++;
		}
		
		return Tokens;
	}
	
	//Count the number of token
	public static int numberOfTokens(String s)
	{
		StringTokenizer Words = new StringTokenizer(s);
		return Words.countTokens();
	}
	
	//get the number in string
	public static int locateKeyword(String Token, String[] keyword)
	{
		int i = 0;
		while(keyword[i] != Token)
		{
			i++;
		}
		if (i <=95) return i;
		else return -1;
	}
	
	//get the number in string
	public static int locateAlphabeta(String Token, String alphabeta)
	{
		int i = 0;
		while(Token.charAt(0)!= alphabeta.charAt(i))
		{
			i++;
		}
		if(i<=51) return i;
		else return -1;
		
	}
	
	//get the number in string
	public static int locateDigit(String Token, String digit)
	{
		int i = 0;
		while(Token.charAt(0) != digit.charAt(i))
		{
			i++;
		}
		if(i<=9) return i;
		else return -1;
	}
	
	//get the number in string
	public static int locateIdentity(String Token, String identity)
	{
		int i = 0;
		while(Token.charAt(0) != identity.charAt(i))
		{
			i++;
		}
		if(i<=12) return i;
		else return -1;
	}
}
class MyInput 
{
	public static String readString()
	{
		BufferedReader br = new BufferedReader(new InputStreamReader(System.in),1);
		String string = " ";
		try
		{
			string = br.readLine();
		}
		catch(IOException ex)
		{
			System.out.println(ex);
		}
		return string;
	}
	
	public static int readInt()
	{
		return Integer.parseInt(readString());
	}
	
	public static double readDouble()
	{
		return Double.parseDouble(readString());
	}

}
?	運行結果：

Here is a Pascal program for testing the Lex analyzer:
***********************************************************
program tripme (input , output);
var 
x , y , c : integer ; 
function add (int a , int b) : int 
begin add = a + b ; end ; 
function subtract (int a , int b) : int 
begin subtract = a - b ; end ; 
begin x = 6 ; y = 2 ; c := subtract (a , b) ; 
write (c) ; c := add (a , b) ; 
write (c) ; end .
***********************************************************

Now begin analyzing:


program : Is a keyword and is located at 1
tripme : Is a Alphabeta and is located at 8
(: Is a identity and is located at 19
input : Is a Alphabeta and is located at 9
, : Is a identity and is located at 20
output : Is a Alphabeta and is located at 10
) : Is a identity and is located at 21
; : Is a identity and is located at22
var : Is a keyword and is located at 2
x : Is a Alphabeta and is located at 11
, : Is a identity and is located at 20
y : Is a Alphabeta and is located at 12
, : Is a identity and is located at 20
c : Is a Alphabeta and is located at 13
: : Is a identity and is located at 23
integer : Is a keyword and is located at 3
; : Is a identity and is located at 22
function : Is a keyword and is located at 4
add : Is a Alphabeta and is located at 14
(: Is a identity and is located at 19
int : Is a Alphabeta and is located at 15
a : Is a Alphabeta and is located at 16
, : Is a identity and is located at 20
int : Is a Alphabeta and is located at 15
b : Is a Alphabeta and is located at 24
) : Is a identity and is located at 21
: : Is a identity and is located at 23
int : Is a Alphabeta and is located 15
begin : Is a keyword and is located at 5
add : Is a Alphabeta and is located at 14
=: Is a identity and is located at 24
a : Is a Alphabeta and is located at 16
+: Is a identity and is located at 25
b : Is a Alphabeta and is located at 17
; : Is a identity and is located at 22
end : Is a keyword and is located at 6
; : Is a identity and is located at 22
function : Is a keyword and is located at 4
subtract : Is a Alphabeta and is located at 18
(: Is a identity and is located at 19
int : Is a Alphabeta and is located at 15
a : Is a Alphabeta and is located at 16
, : Is a identity and is located at 20
int : Is a Alphabeta and is located at 15
b : Is a Alphabeta and is located at 17
) : Is a identity and is located at 21
: : Is a identity and is located at 23
int : Is a Alphabeta and is located at 15
begin : Is a keyword and is located at 5
subtract : Is a Alphabeta and is located at 18
=: Is a identity and is located at 24
a : Is a Alphabeta and is located at 16
-: Is a identity and is located at 25
b : Is a Alphabeta and is located at 17
; : Is a identity and is located at 22
end : Is a keyword and is located at 6
; : Is a identity and is located at 22
begin : Is a keyword and is located at 5
x : Is a Alphabeta and is located at 11
=: Is a identity and is located at 24
6 : Is a digit and is located at 19
; : Is a identity and is located at 22
y : Is a Alphabeta and is located at 12
=: Is a identity and is located at 24
2 : Is a digit and is located at 20
; : Is a identity and is located at 22
c : Is a Alphabeta and is located at 13
:= : Is a identity and is located at 26
subtract : Is a Alphabeta and is located at 18
(: Is a identity and is located at 19
a : Is a Alphabeta and is located at 16
, : Is a identity and is located at 20
b : Is a Alphabeta and is located at 17
) : Is a identity and is located at 21
; : Is a identity and is located at 22
write : Is a keyword and is located at 7
(: Is a identity and is located at 19
c : Is a Alphabeta and is located at 13
) : Is a identity and is located at 21
; : Is a identity and is located at 22
c : Is a Alphabeta and is located at 13
:= : Is a identity and is located at 26
Add : Is a Alphabeta and is located at 14
(: Is a identity and is located at 19
a : Is a Alphabeta and is located at 16
, : Is a identity and is located at 20
b : Is a Alphabeta and is located at 17
) : Is a identity and is located at 21
; : Is a identity and is located at 22
write : Is a keyword and is located at 7
(: Is a identity and is located at 19
c : Is a Alphabeta and is located at 13
) : Is a identity and is located at 21
; : Is a identity and is located at 22
end : Is a keyword and is located at 6
. : Is a identity and is located at 27

Analysis completed successfully