Lexical Analyzer in C and C++

Here you will get program to implement lexical analyzer in C and C++.

Compiler is responsible for converting high level language in machine language. There are several phases involved in this and lexical analysis is the first phase.

Lexical analyzer reads the characters from source code and convert it into tokens.

Different tokens or lexemes are:

• Keywords
• Identifiers
• Operators
• Constants

Take below example.

c = a + b;

After lexical analysis a symbol table is generated as given below.

Now below I have given implementation of very simple lexical analyzer which reads source code from file and then generate tokens.

Program for Lexical Analyzer in C

#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<ctype.h>

int isKeyword(char buffer[]){
	char keywords[32][10] = {"auto","break","case","char","const","continue","default",
							"do","double","else","enum","extern","float","for","goto",
							"if","int","long","register","return","short","signed",
							"sizeof","static","struct","switch","typedef","union",
							"unsigned","void","volatile","while"};
	int i, flag = 0;
	
	for(i = 0; i < 32; ++i){
		if(strcmp(keywords[i], buffer) == 0){
			flag = 1;
			break;
		}
	}
	
	return flag;
}

int main(){
	char ch, buffer[15], operators[] = "+-*/%=";
	FILE *fp;
	int i,j=0;
	
	fp = fopen("program.txt","r");
	
	if(fp == NULL){
		printf("error while opening the file\n");
		exit(0);
	}
	
	while((ch = fgetc(fp)) != EOF){
   		for(i = 0; i < 6; ++i){
   			if(ch == operators[i])
   				printf("%c is operator\n", ch);
   		}
   		
   		if(isalnum(ch)){
   			buffer[j++] = ch;
   		}
   		else if((ch == ' ' || ch == '\n') && (j != 0)){
   				buffer[j] = '\0';
   				j = 0;
   				   				
   				if(isKeyword(buffer) == 1)
   					printf("%s is keyword\n", buffer);
   				else
   					printf("%s is indentifier\n", buffer);
   		}
   		
	}
	
	fclose(fp);
	
	return 0;
}

Program for Lexical Analyzer in C++

#include<iostream>
#include<fstream>
#include<stdlib.h>
#include<string.h>
#include<ctype.h>

using namespace std;

int isKeyword(char buffer[]){
	char keywords[32][10] = {"auto","break","case","char","const","continue","default",
							"do","double","else","enum","extern","float","for","goto",
							"if","int","long","register","return","short","signed",
							"sizeof","static","struct","switch","typedef","union",
							"unsigned","void","volatile","while"};
	int i, flag = 0;
	
	for(i = 0; i < 32; ++i){
		if(strcmp(keywords[i], buffer) == 0){
			flag = 1;
			break;
		}
	}
	
	return flag;
}

int main(){
	char ch, buffer[15], operators[] = "+-*/%=";
	ifstream fin("program.txt");
	int i,j=0;
	
	if(!fin.is_open()){
		cout<<"error while opening the file\n";
		exit(0);
	}
	
	while(!fin.eof()){
   		ch = fin.get();
   		
		for(i = 0; i < 6; ++i){
   			if(ch == operators[i])
   				cout<<ch<<" is operator\n";
   		}
   		
   		if(isalnum(ch)){
   			buffer[j++] = ch;
   		}
   		else if((ch == ' ' || ch == '\n') && (j != 0)){
   				buffer[j] = '\0';
   				j = 0;
   				   				
   				if(isKeyword(buffer) == 1)
   					cout<<buffer<<" is keyword\n";
   				else
   					cout<<buffer<<" is indentifier\n";
   		}
   		
	}
	
	fin.close();
	
	return 0;
}

Output

The source code present in file is shown in above image.

Comment below if you have any queries regarding above program for lexical analyzer in C and C++.

The post Lexical Analyzer in C and C++ appeared first on The Crazy Programmer.