1.

Write a c program to identify different types of tokens in a given program

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

// Returns 'true' if the character is a DELIMITER.

bool isDelimiter(char ch)
{
if (ch == ' ' || ch == '+' || ch == '-' || ch == '*' ||
ch == '/' || ch == ',' || ch == ';' || ch == '>' ||
ch == '<' || ch == '=' || ch == '(' || ch == ')' ||
ch == '[' || ch == ']' || ch == '{' || ch == '}')
return (true);
return (false);
}

// Returns 'true' if the character is an OPERATOR.

bool isOperator(char ch)
{
if (ch == '+' || ch == '-' || ch == '*' ||
ch == '/' || ch == '>' || ch == '<' ||
ch == '=')
return (true);
return (false);
}

// Returns 'true' if the string is a VALID IDENTIFIER.

bool validIdentifier(char* str)
{
if (str[0] == '0' || str[0] == '1' || str[0] == '2' ||
str[0] == '3' || str[0] == '4' || str[0] == '5' ||
str[0] == '6' || str[0] == '7' || str[0] == '8' ||
str[0] == '9' || isDelimiter(str[0]) == true)
return (false);
return (true);
}

// Returns 'true' if the string is a KEYWORD.

bool isKeyword(char* str)
{
if (!strcmp(str, "if") || !strcmp(str, "else") ||
!strcmp(str, "while") || !strcmp(str, "do") ||
!strcmp(str, "break") ||
!strcmp(str, "continue") || !strcmp(str, "int")
|| !strcmp(str, "double") || !strcmp(str, "float")
|| !strcmp(str, "return") || !strcmp(str, "char")
|| !strcmp(str, "case") || !strcmp(str, "char")
|| !strcmp(str, "sizeof") || !strcmp(str, "long")
|| !strcmp(str, "short") || !strcmp(str, "typedef")
|| !strcmp(str, "switch") || !strcmp(str, "unsigned")
 || !strcmp(str, "void") || !strcmp(str, "static")
|| !strcmp(str, "struct") || !strcmp(str, "goto"))
return (true);
return (false);
}

// Returns 'true' if the string is an INTEGER.

bool isInteger(char* str)
{
int i, len = strlen(str);

if (len == 0)
return (false);
for (i = 0; i < len; i++) {
if (str[i] != '0' && str[i] != '1' && str[i] != '2'
&& str[i] != '3' && str[i] != '4' && str[i] != '5'
&& str[i] != '6' && str[i] != '7' && str[i] != '8'
&& str[i] != '9' || (str[i] == '-' && i > 0))
return (false);
}
return (true);
}

// Returns 'true' if the string is a REAL NUMBER.

bool isRealNumber(char* str)
{
int i, len = strlen(str);
bool hasDecimal = false;

if (len == 0)
return (false);
for (i = 0; i < len; i++) {
if (str[i] != '0' && str[i] != '1' && str[i] != '2'
&& str[i] != '3' && str[i] != '4' && str[i] != '5'
&& str[i] != '6' && str[i] != '7' && str[i] != '8'
&& str[i] != '9' && str[i] != '.' ||
(str[i] == '-' && i > 0))
return (false);
if (str[i] == '.')
hasDecimal = true;
}
return (hasDecimal);
}

// Extracts the SUBSTRING.

char* subString(char* str, int left, int right)
{
int i;
char* subStr = (char*)malloc(
sizeof(char) * (right - left + 2));
 for (i = left; i <= right; i++)
subStr[i - left] = str[i];
subStr[right - left + 1] = '\0';
return (subStr);
}

// Parsing the input STRING.

void parse(char* str)
{
int left = 0, right = 0;
int len = strlen(str);

while (right <= len && left <= right) {

if (isDelimiter(str[right]) == false)
right++;

if (isDelimiter(str[right]) == true && left == right) {

if (isOperator(str[right]) == true)
printf("'%c' IS AN OPERATOR\n", str[right]);

right++;
left = right;
} else if (isDelimiter(str[right]) == true && left != right
|| (right == len && left != right)) {
char* subStr = subString(str, left, right - 1);

if (isKeyword(subStr) == true)
printf("'%s' IS A KEYWORD\n", subStr);

else if (isInteger(subStr) == true)

printf("'%s' IS AN INTEGER\n", subStr);

else if (isRealNumber(subStr) == true)

printf("'%s' IS A REAL NUMBER\n", subStr);

else if (validIdentifier(subStr) == true

&& isDelimiter(str[right - 1]) == false)
printf("'%s' IS A VALID IDENTIFIER\n", subStr);

else if (validIdentifier(subStr) == false

&& isDelimiter(str[right - 1]) == false)
printf("'%s' IS NOT A VALID IDENTIFIER\n", subStr);
left = right;
}
}
return;
}

// DRIVER FUNCTION
int main()
{
 // maximum length of string is 100 here
char str[100] = "int a = b + 1c; ";

parse(str); // calling the parse function

return (0);
}

Output
'int' IS A KEYWORD
'a' IS A VALID IDENTIFIER
'=' IS AN OPERATOR
'b' IS A VALID IDENTIFIER
'+' IS AN OPERATOR
'1c' IS NOT A VALID IDENTIFIER

2. Write a lex program to implement a lexical analyser using lex tool

3. write a c program to simulate lexical analyzer to validate a given input string
#include<stdio.h>
void main()
{
char s[5];
//clrscr();
printf("\n Enter any operator:");
gets(s);
switch(s[0])
{
case'>': if(s[1]=='=')
printf("\n Greater than or equal");
else
printf("\n Greater than");
break;
case'<': if(s[1]=='=')
printf("\n Less than or equal");
else
printf("\nLess than");
break;
case'=': if(s[1]=='=')
printf("\nEqual to");
else
printf("\nAssignment");
break;
case'!': if(s[1]=='=')
printf("\nNot Equal");
else
printf("\n Bit Not");
break;
case'&': if(s[1]=='&')
printf("\nLogical AND");
else
printf("\n Bitwise AND");
 break;
case'|': if(s[1]=='|')
printf("\nLogical OR");
else
printf("\nBitwise OR");
break;
case'+': printf("\n Addition");
break;
case'-': printf("\nSubstraction");
break;
case'*': printf("\nMultiplication");
break;
case'/': printf("\nDivision");
break;
case'%': printf("Modulus");
break;
default: printf("\n Not a operator");
}
//getch();
}

Output
Enter any operator:*
Multiplication

4. write a c program to implement the brute force technique of top down parsing
#include<stdio.h>
//#include<conio.h>
#include<iostream.h>
void main()
{
int a[30];
//clrscr();
int min=10000,temp=0,i,lev,n,noofc,z;
printf("please enter how many number");
cin>>n;
for(i=0;i<n;i++)
a[i]=0;
cout<<"enter value of root";
cin>>a[0];
for(i=1;i<=n/2;i++)
{
cout<<"please enter no of child of parent with value"<<a[i-1]<<":";
cin>>noofc;
for(int j=1;j<=noofc;j++)
{z=(i)*2+j-2;
cout<<"please enter value of child";
cin>>a[z];
}
}
 Output

5.write a c program to implement a recursvie descent parser

#include<stdio.h>
#include<string.h>
int E(),Edash(),T(),Tdash(),F();
char *ip;
char string[50];
int main()
{
printf("Enter the string\n");
scanf("%s",string);
ip=string;
printf("\n\nInput\tAction\n--------------------------------\n");

if(E() && ip=="\0"){

printf("\n--------------------------------\n");
printf("\n String is successfully parsed\n");
}
else{
printf("\n--------------------------------\n");
printf("Error in parsing String\n");
}
}
int E()
{
printf("%s\tE->TE' \n",ip);
if(T())
{
if(Edash())
{
return 1;
}
else
return 0;
}
else
return 0;
}
int Edash()
{
if(*ip=='+')
{
printf("%s\tE'->+TE' \n",ip);
ip++;
if(T())
{
if(Edash())
{
return 1;
}
else
return 0;
}
else
return 0;
}
else
{
printf("%s\tE'->^ \n",ip);
return 1;
}
}
int T()
{
printf("%s\tT->FT' \n",ip);
if(F())
{

if(Tdash())
{
return 1;
}
else
return 0;
}
else
return 0;
}
int Tdash()
{
if(*ip=='*')
{
printf("%s\tT'->*FT' \n",ip);
ip++;
if(F())
{
if(Tdash())
{
return 1;
}
else
return 0;
}
else
return 0;
}
else
{
printf("%s\tT'->^ \n",ip);
return 1;
}
}
int F()
{
if(*ip=='(')
{
printf("%s\tF->(E) \n",ip);
ip++;
if(E())
{
if(*ip==')')
{
ip++;
return 0;
}
else
return 0;
}
else
return 0;
}

else if(*ip=='i')
{
ip++;
printf("%s\tF->id \n",ip);
return 1;
}
else
return 0;
}

Output
Enter the string
compilerdesign
Input Action
--------------------------------
compilerdesign E->TE'
compilerdesign T->FT'

--------------------------------
Error in parsing String

6.write a c program to compute the first and follow sets for the given grammar
#include<stdio.h>
#include<ctype.h>
#include<string.h>

// Functions to calculate Follow

void followfirst(char, int, int);
void follow(char c);

// Function to calculate First

void findfirst(char, int, int);

int count, n = 0;

// Stores the final result

// of the First Sets
char calc_first[10][100];

// Stores the final result

// of the Follow Sets
char calc_follow[10][100];
int m = 0;

// Stores the production rules

char production[10][10];
char f[10], first[10];
int k;
char ck;
int e;

int main(int argc, char **argv)

{
int jm = 0;
int km = 0;
int i, choice;
char c, ch;
count = 8;

// The Input grammar

strcpy(production[0], "E=TR");
strcpy(production[1], "R=+TR");
strcpy(production[2], "R=#");
strcpy(production[3], "T=FY");
strcpy(production[4], "Y=*FY");
strcpy(production[5], "Y=#");
strcpy(production[6], "F=(E)");
strcpy(production[7], "F=i");

int kay;
char done[count];
int ptr = -1;

// Initializing the calc_first array

for(k = 0; k < count; k++) {
for(kay = 0; kay < 100; kay++) {
calc_first[k][kay] = '!';
}
}
int point1 = 0, point2, xxx;

for(k = 0; k < count; k++)

{
c = production[k][0];
point2 = 0;
xxx = 0;

// Checking if First of c has

// already been calculated
for(kay = 0; kay <= ptr; kay++)
if(c == done[kay])
xxx = 1;

if (xxx == 1)
continue;

// Function call
findfirst(c, 0, 0);
ptr += 1;

// Adding c to the calculated list

done[ptr] = c;
printf("\n First(%c) = { ", c);
calc_first[point1][point2++] = c;

// Printing the First Sets of the grammar

for(i = 0 + jm; i < n; i++) {
int lark = 0, chk = 0;

for(lark = 0; lark < point2; lark++) {

if (first[i] == calc_first[point1][lark])
{
chk = 1;
break;
}
 }
if(chk == 0)
{
printf("%c, ", first[i]);
calc_first[point1][point2++] = first[i];
}
}
printf("}\n");
jm = n;
point1++;
}
printf("\n");
printf("-----------------------------------------------\n\n");
char donee[count];
ptr = -1;

// Initializing the calc_follow array

for(k = 0; k < count; k++) {
for(kay = 0; kay < 100; kay++) {
calc_follow[k][kay] = '!';
}
}
point1 = 0;
int land = 0;
for(e = 0; e < count; e++)
{
ck = production[e][0];
point2 = 0;
xxx = 0;

// Checking if Follow of ck
// has already been calculated
for(kay = 0; kay <= ptr; kay++)
if(ck == donee[kay])
xxx = 1;

if (xxx == 1)
continue;
land += 1;

// Function call
follow(ck);
ptr += 1;

// Adding ck to the calculated list

donee[ptr] = ck;
printf(" Follow(%c) = { ", ck);
calc_follow[point1][point2++] = ck;

// Printing the Follow Sets of the grammar

for(i = 0 + km; i < m; i++) {
 int lark = 0, chk = 0;
for(lark = 0; lark < point2; lark++)
{
if (f[i] == calc_follow[point1][lark])
{
chk = 1;
break;
}
}
if(chk == 0)
{
printf("%c, ", f[i]);
calc_follow[point1][point2++] = f[i];
}
}
printf(" }\n\n");
km = m;
point1++;
}
}

void follow(char c)
{
int i, j;

// Adding "$" to the follow

// set of the start symbol
if(production[0][0] == c) {
f[m++] = '$';
}
for(i = 0; i < 10; i++)
{
for(j = 2;j < 10; j++)
{
if(production[i][j] == c)
{
if(production[i][j+1] != '\0')
{
// Calculate the first of the next
// Non-Terminal in the production
followfirst(production[i][j+1], i, (j+2));
}

if(production[i][j+1]=='\0' && c!=production[i][0])

{
// Calculate the follow of the Non-Terminal
// in the L.H.S. of the production
follow(production[i][0]);
}
}
}
 }
}

void findfirst(char c, int q1, int q2)

{
int j;

// The case where we

// encounter a Terminal
if(!(isupper(c))) {
first[n++] = c;
}
for(j = 0; j < count; j++)
{
if(production[j][0] == c)
{
if(production[j][2] == '#')
{
if(production[q1][q2] == '\0')
first[n++] = '#';
else if(production[q1][q2] != '\0'
&& (q1 != 0 || q2 != 0))
{
// Recursion to calculate First of New
// Non-Terminal we encounter after epsilon
findfirst(production[q1][q2], q1, (q2+1));
}
else
first[n++] = '#';
}
else if(!isupper(production[j][2]))
{
first[n++] = production[j][2];
}
else
{
// Recursion to calculate First of
// New Non-Terminal we encounter
// at the beginning
findfirst(production[j][2], j, 3);
}
}
}
}

void followfirst(char c, int c1, int c2)

{
int k;

// The case where we encounter

// a Terminal
 if(!(isupper(c)))
f[m++] = c;
else
{
int i = 0, j = 1;
for(i = 0; i < count; i++)
{
if(calc_first[i][0] == c)
break;
}

//Including the First set of the

// Non-Terminal in the Follow of
// the original query
while(calc_first[i][j] != '!')
{
if(calc_first[i][j] != '#')
{
f[m++] = calc_first[i][j];
}
else
{
if(production[c1][c2] == '\0')
{
// Case where we reach the
// end of a production
follow(production[c1][0]);
}
else
{
// Recursion to the next symbol
// in case we encounter a "#"
followfirst(production[c1][c2], c1, c2+1);
}
}
j++;
}
}
}

Output
First(E) = { (, i, }

First(R) = { +, #, }

First(T) = { (, i, }

First(Y) = { *, #, }

First(F) = { (, i, }
-----------------------------------------------

Follow(E) = { $, ), }

Follow(R) = { $, ), }

Follow(T) = { +, $, ), }

Follow(Y) = { +, $, ), }

Follow(F) = { *, +, $, ), }

7.write a c program for eliminating the left recursion and left factoring of a given grammar

Remove left factoring of grammar

#include<iostream.h>
#include<stdio.h>
#include<conio.h>
#include<string.h>

//Structure Declaration

struct production
{
char lf;
char rt[10];
int prod_rear;
int fl;
};
struct production prodn[20],prodn_new[20]; //Creation of object

//Variables Declaration

int b=-1,d,f,q,n,m=0,c=0;
char terminal[20],nonterm[20],alpha[10],extra[10];
char epsilon='^';

//Beginning of Main Program

void main()
{
clrscr();

//Input of Special characters

cout<<"\nEnter the number of Special characters(except non-terminals): ";
cin>>q;
cout<<"Enter the special characters for your production: ";
for(int cnt=0;cnt<q;cnt++)
{
 cin>>alpha[cnt];
}

//Input of Productions

cout<<"\nEnter the number of productions: ";

cin>>n;
for(cnt=0;cnt<=n-1;cnt++)
{
cout<<"Enter the "<< cnt+1<<" production: ";
cin>>prodn[cnt].lf;
cout<<"->";
cin>>prodn[cnt].rt;
prodn[cnt].prod_rear=strlen(prodn[cnt].rt);
prodn[cnt].fl=0;
}

//Condition for left factoring

for(int cnt1=0;cnt1<n;cnt1++)
{
for(int cnt2=cnt1+1;cnt2<n;cnt2++)
{
if(prodn[cnt1].lf==prodn[cnt2].lf)
{
cnt=0;
int p=-1;
while((prodn[cnt1].rt[cnt]!='\0')&&(prodn[cnt2].rt[cnt]!='\0'))
{
if(prodn[cnt1].rt[cnt]==prodn[cnt2].rt[cnt])
{
extra[++p]=prodn[cnt1].rt[cnt];
prodn[cnt1].fl=1;
prodn[cnt2].fl=1;
}
else
{
if(p==-1)
break;
else
{
int h=0,u=0;
prodn_new[++b].lf=prodn[cnt1].lf;
strcpy(prodn_new[b].rt,extra);
prodn_new[b].rt[p+1]=alpha[c];
prodn_new[++b].lf=alpha[c];
for(int g=cnt;g<prodn[cnt2].prod_rear;g++)
prodn_new[b].rt[h++]=prodn[cnt2].rt[g];
prodn_new[++b].lf=alpha[c];
for(g=cnt;g<=prodn[cnt1].prod_rear;g++)
prodn_new[b].rt[u++]=prodn[cnt1].rt[g];
 m=1;
break;
}
}
cnt++;
}
if((prodn[cnt1].rt[cnt]==0)&&(m==0))
{
int h=0;
prodn_new[++b].lf=prodn[cnt1].lf;
strcpy(prodn_new[b].rt,extra);
prodn_new[b].rt[p+1]=alpha[c];
prodn_new[++b].lf=alpha[c];
prodn_new[b].rt[0]=epsilon;
prodn_new[++b].lf=alpha[c];
for(int g=cnt;g<prodn[cnt2].prod_rear;g++)
prodn_new[b].rt[h++]=prodn[cnt2].rt[g];
}
if((prodn[cnt2].rt[cnt]==0)&&(m==0))
{
int h=0;
prodn_new[++b].lf=prodn[cnt1].lf;
strcpy(prodn_new[b].rt,extra);
prodn_new[b].rt[p+1]=alpha[c];
prodn_new[++b].lf=alpha[c];
prodn_new[b].rt[0]=epsilon;
prodn_new[++b].lf=alpha[c];
for(int g=cnt;g<prodn[cnt1].prod_rear;g++)
prodn_new[b].rt[h++]=prodn[cnt1].rt[g];
}
c++;
m=0;
}
}
}

//Display of Output

cout<<"\n\n********************************";
cout<<"\n AFTER LEFT FACTORING ";
cout<<"\n********************************";
cout<<endl;
for(int cnt3=0;cnt3<=b;cnt3++)
{
cout<<"Production "<<cnt3+1<<" is: ";
cout<<prodn_new[cnt3].lf;
cout<<"->";
cout<<prodn_new[cnt3].rt;
cout<<endl<<endl;
}
 for(int cnt4=0;cnt4<n;cnt4++)
{
if(prodn[cnt4].fl==0)
{
cout<<"Production "<<cnt3++<<" is: ";
cout<<prodn[cnt4].lf;
cout<<"->";
cout<<prodn[cnt4].rt;
cout<<endl<<endl;
}
}
getche();
} //end of main program
Output

Left recursion
#include<stdio.h>
#include<string.h>
void main()
{
char input[100],l[50],r[50],temp[10],tempprod[20],productions[25][50];
int i=0,j=0,flag=0,consumed=0;
printf("Enter the productions: ");
scanf("%1s->%s",l,r);
printf("%s",r);
while(sscanf(r+consumed,"%[^|]s",temp) == 1 && consumed <= strlen(r))
{
 if(temp[0] == l[0])
{
flag = 1;
sprintf(productions[i++],"%s->%s%s'\0",l,temp+1,l);
}
else
sprintf(productions[i++],"%s'->%s%s'\0",l,temp,l);
consumed += strlen(temp)+1;
}
if(flag == 1)
{
sprintf(productions[i++],"%s->ε\0",l);
printf("The productions after eliminating Left Recursion are:\n");
for(j=0;j<i;j++)
printf("%s\n",productions[j]);
}
else
printf("The Given Grammar has no Left Recursion");
}

Output
Enter the productions: E->E+E|T
E+E|TThe productions after eliminating Left Recursion are:
E->+EE'
E'->TE'
E->ε