#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<ctype.h>
 
// Function to check if a string is a keyword
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"
    };
 
    for(int i = 0; i < 32; ++i)
    {
        if(strcmp(keywords[i], buffer) == 0)
        {
            return 1; // Keyword found
        }
    }
    return 0; // Not a keyword
}
 
// Function to check if a character is an operator
int isOperator(char ch)
{
    char op[] = {'+', '-', '*', '/', '%', '='};
    for(int i = 0; i < 6; i++)
    {
        if(ch == op[i])
        {
            return 1; // Operator found
        }
    }
    return 0; // Not an operator
}
 
// Function to check if a character is a symbol
int isSymbol(char ch)
{
    char sy[] = {',', ';', '(', ')', '{', '}'};
    for(int i = 0; i < 6; i++)
    {
        if(ch == sy[i])
        {
            return 1; // Symbol found
        }
    }
    return 0; // Not a symbol
}
 
int main()
{
    char ch, buffer[15],token=0;
    FILE *fp;
    int j = 0;
 
    // Open the file in read mode
    fp = fopen("NUB.txt", "r");
    if(fp == NULL)
    {
        printf("Error while opening the file\n");
        exit(0);
    }
 
    printf("Lexical Analysis:\n\n");
    while((ch = fgetc(fp)) != EOF)
    {
        // Check for alphanumeric characters
        if(isalnum(ch))
        {
            buffer[j++] = ch; // Add to buffer
        }
        else
        {
            if(j != 0) // Process the buffer if it contains something
            {
                token++;
                buffer[j] = '\0'; // Null-terminate the string
                j = 0;
 
                if(isKeyword(buffer))
                    printf("%s is a keyword\n", buffer);
                else
                    printf("%s is an identifier\n", buffer);
            }
 
            // Check for operators
            if(isOperator(ch))
            {
                token++;
                printf("%c is an operator\n", ch);
            }
            // Check for symbols
            else if(isSymbol(ch))
            {
                token++;
                printf("%c is a symbol\n", ch);
            }
        }
    }
    printf("Total Token: %d \n\n",token);
    fclose(fp); // Close the file
    return 0;
}
 

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