0% found this document useful (0 votes)
29 views

CD LabManual

The document contains details of experiments conducted on lexical analysis. Experiment 1 involves writing programs to count characters in a string, validate usernames and passwords, and identify comments. Experiment 2 focuses on programs that recognize strings ending in "ab", simulate a lexical analyzer to validate operators, and design a lexical analyzer to identify keywords and identifiers. Experiment 3 studies Lexical Analyzer Generators like LEX and Flex.

Uploaded by

Youtube GsG
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
29 views

CD LabManual

The document contains details of experiments conducted on lexical analysis. Experiment 1 involves writing programs to count characters in a string, validate usernames and passwords, and identify comments. Experiment 2 focuses on programs that recognize strings ending in "ab", simulate a lexical analyzer to validate operators, and design a lexical analyzer to identify keywords and identifiers. Experiment 3 studies Lexical Analyzer Generators like LEX and Flex.

Uploaded by

Youtube GsG
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 38

Index

Srno Experiment Title Date of


Performance

1 a) Program to count digits, vowels, consonant and symbols in


C.
b) Program to check validation of User Name and Password*
in C.
c) Write a program to identify whether a given line is a
comment or not.
2 a) Write a C program to recognize strings end with ‘ab’
b) Write a C program to simulate lexical analyzer for
validating operators
c) Design a lexical analyzer to identify from given pattern is
keyword or identifier.
d)Program to implement Lexical Analyzer.
3 To Study about Lexical Analyzer Generator(LEX) and
Flex(Fast Lexical Analyzer)
4 Implement following programs using Lex.
a) Create a Lexer to take input from text file and count no of
characters, no. of lines & no. of words.
b) Write a Lex program to count number of vowels and
consonants in a given input string.
c)Write a Lex program to print out all numbers from the given
file.
d) Write a Lex program which adds line numbers to the given
file and display the same onto the standard output.
e) Write a Lex program to printout all HTML tags in file.
5 a) Write a Lex program to count the number of comment
lines in a given C program. Also eliminate them and copy
that program into separate file.

b) Write a Lex program to print keywords, identifiers,


operators, numbers in a given C program.
6 Program to implement Recursive Descent Parsing in C.

7 a) To Study about Yet Another Compiler-Compiler(YACC).


b) Create Yacc and Lex specification files to recognizes
arithmetic expressions involving +, -, * and / .
c) Create Yacc and Lex specification files are used to
generate a calculator which accepts integer and float type
arguments.

Pratical-1
a) Program to count digits, vowels, consonant and symbols in C.

Code:-
#include <stdio.h>
int main() {

char line[150];
int vowels, consonant, digit, symbol;

// initialize all variables to 0


vowels = consonant = digit = symbol = 0;

// get full line of string input


printf("Enter a line of string: ");
fgets(line, sizeof(line), stdin);

// loop through each character of the string


for (int i = 0; line[i] != '\0'; ++i) {

// convert character to lowercase


line[i] = tolower(line[i]);

// check if the character is a vowel


if (line[i] == 'a' || line[i] == 'e' || line[i] == 'i' ||
line[i] == 'o' || line[i] == 'u') {

// increment value of vowels by 1


++vowels;
}

// if it is not a vowel and if it is an alphabet, it is a consonant


else if ((line[i] >= 'a' && line[i] <= 'z')) {
++consonant;
}

// check if the character is a digit


else if (line[i] >= '0' && line[i] <= '9') {
++digit;
}

else {
++symbol;
}
}

printf("Vowels: %d", vowels);


printf("\nConsonants: %d", consonant);
printf("\nDigits: %d", digit);
printf("\n symbol: %d", symbol);

return 0;
}

Output:-

b) Program to check validation of User Name and Password* in C.

Code:-
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
void checkPass(char a[]);
void checkUsername(char b[]);

main()
{
char a[100], b[100];
printf("Enter your username \n");
scanf("%s",b);
printf( "Enter your password \n");
scanf("%s",a);
checkUsername(b);
checkPass(a);

}
void checkPass(char a[])
{
char c;
int len,i,flag1=0,flag2=0,flag3=0,flag4=0;
len=strlen(a);
if(len<6)
flag1=1;
else
{
for(i=0;i<len;i++)
if((a[i]>=48&&a[i]<=58))
{
flag2=0;

break;
}
else
flag2=1;

for(i=0;i<len;i++)
if((a[i]>=65&&a[i]<=90) || (a[i]>= 97 && a[i]<=122))
{
flag3=0;

break;
}
else
flag3=1;

for(i=0;i<len;i++)
if(a[i]=='@'||a[i]=='_'||a[i]=='*'||a[i]=='&'||a[i]=='$')
{
flag4=0;

break;
}
else
flag4=1;

}
if(flag1==1||flag2==1||flag3==1||flag4==1)
printf("\nWrong password\n ");
else
printf("your password is successfully validate\n");
return;
}

void checkUsername(char b[])


{
char c;
int len,i,flag1=0,flag2=0,flag3=0,flag4=0;
len=strlen(b);
if(len<4)
flag1=1;
else
{
for(i=0;i<len;i++)
if((b[i]>=48&&b[i]<=58))
{
flag2=0;
break;
}
else
flag2=1;

for(i=0;i<len;i++)
if((b[i]>=65&&b[i]<=90) || (b[i]>= 97 && b[i]<=122))
{
flag3=0;
break;
}
else
flag3=1;

for(i=0;i<len;i++)
if(b[i]=='@'||b[i]=='_'||b[i]=='*'||b[i]=='&'||b[i]=='$')
{
flag4=0;

break;
}
else
flag4=1;
}
if(flag1==1||flag2==1||flag3==1||flag4==1)
printf("\nWrong username\n");
else
printf("your username is successfully validate\n");
return;
}
Output:-

c) Write a program to identify whether a given line is a comment or not.


Code:-
#include<stdio.h>
void main()
{
char com[30];
int i=2,a=0;
printf("\n Enter comment:");
gets(com);

if(com[0]=='/')
{
if(com[1]=='/')
printf("\n It is a comment");
else if(com[1]=='*')
{
for(i=2;i<=30;i++)
{
if(com[i]=='*'&&com[i+1]=='/')
{
printf("\n It is a comment");
a=1;
break;
}
else
continue;
}
if(a==0)
printf("\n It is not a comment");
}
else
printf("\n It is not a comment");
}
else
printf("\n It is not a comment");
} Output:-

Pratical-2
a) Write a C program to recognize strings end with ‘ab’

Code:-
#include<stdio.h>
#include<string.h>
int main() {
char com[30];
int i=2,a=0, len = 0;
printf("\n Enter comment:");
gets(com);
len = strlen(com);
if((com[len-2]=='a' || com[len-2]=='A') && (com[len-1]=='b' || com[len-1]=='B'))
{
printf("\n recognize strings end with ab");
}
else{
printf("\n not recognize strings end with ab");
}
return 0;
}

Output:-

b) Write a C program to simulate lexical analyzer for validating operators


Code:-

#include<stdio.h>
#include<conio.h>
void main()
{
char s[5];

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("\n Substraction");
break;
case'*': printf("\nMultiplication");
break;
case'/': printf("\nDivision");
break;
case'%': printf("Modulus");
break;
default: printf("\n Not a operator");
}
getch();
}
Output:-

c) Design a lexical analyzer to identify from given pattern is keyword or identifier.

#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("");

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("");

else if (isRealNumber(subStr) == true)


printf("");

else if (validIdentifier(subStr) == true


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

else if (validIdentifier(subStr) == false


&&isDelimiter(str[right - 1]) == false)
printf("");
left = right;
}
}
return;
}

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

parse(str); // calling the parse function

return (0);
}
Output:-

d) Program to implement Lexical Analyzer.


Code:-
#include <stdbool.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
bool isValidDelimiter(char ch) {
if (ch == ' ' || ch == '+' || ch == '-' || ch == '*' ||
ch == '/' || ch == ',' || ch == ';' || ch == '>' ||
ch == '<' || ch == '=' || ch == '(' || ch == ')' ||
ch == '[' || ch == ']' || ch == '{' || ch == '}')
return (true);
return (false);
}
bool isValidOperator(char ch){
if (ch == '+' || ch == '-' || ch == '*' ||
ch == '/' || ch == '>' || ch == '<' ||
ch == '=')
return (true);
return (false);
}
// Returns 'true' if the string is a VALID IDENTIFIER.
bool isvalidIdentifier(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' || isValidDelimiter(str[0]) == true)
return (false);
return (true);
}
bool isValidKeyword(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);
}
bool isValidInteger(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);
}
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);
}
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);
}
void detectTokens(char* str) {
int left = 0, right = 0;
int length = strlen(str);
while (right <= length && left <= right) {
if (isValidDelimiter(str[right]) == false)
right++;
if (isValidDelimiter(str[right]) == true && left == right) {
if (isValidOperator(str[right]) == true)
printf("Valid operator : '%c'\n", str[right]);
right++;
left = right;
} else if (isValidDelimiter(str[right]) == true && left != right || (right == length && left !=
right)) {
char* subStr = subString(str, left, right - 1);
if (isValidKeyword(subStr) == true)
printf("Valid keyword : '%s'\n", subStr);
else if (isValidInteger(subStr) == true)
printf("Valid Integer : '%s'\n", subStr);
else if (isRealNumber(subStr) == true)
printf("Real Number : '%s'\n", subStr);
else if (isvalidIdentifier(subStr) == true
&&isValidDelimiter(str[right - 1]) == false)
printf("Valid Identifier : '%s'\n", subStr);
else if (isvalidIdentifier(subStr) == false
&&isValidDelimiter(str[right - 1]) == false)
printf("Invalid Identifier : '%s'\n", subStr);
left = right;
}
}
return;
}
int main(){
char str[100] = "float x = a + 1b; ";
printf("The Program is : '%s' \n", str);
printf("All Tokens are : \n");
detectTokens(str);
return (0);
}
Output:-
Practical-4
a) Create a Lexer to take input from text file and count no of characters, no. of lines & no.
of words.
Code:-
%{

#include<stdio.h>

int words=0, lines=0, chars=0;

%}

%%

[a-zA-Z] chars++;
\n {++lines;++words;};
[\t' '] ++words;
%%

main(void)

{
yyin= fopen("input.txt","r");
yylex();

printf(" This File contains ...");


printf("\n\t%d chars", chars);

printf("\n\t%d lines", lines);

printf("\n\t%d words", (words+1));


}

int yywrap()
{

return(1);

}
Output:-

b) Write a Lex program to count number of vowels and consonants in a given input
string.
Code:-
%{

#include<stdio.h>

int vowels=0, consonants=0;

%}

%%

[aeiouAEIOU] vowels++;
[a-zA-Z] consonants++;

%%

main(void)

{
yyin= fopen("input1.txt","r");
yylex();

printf(" This File contains ...");

printf("\n\t%d vowels", vowels);

printf("\n\t%d consonants", consonants);

}
int yywrap()
{

return(1);

}
}
Output:-

c)Write a Lex program to print out all numbers from the given file.
Code:-
%{

#include<stdio.h>

%}

%%

([0-9]+)((.([0-9]+))[Ee][+-]?[0-9]+) { printf("%s\n", yytext); }


.|\n ;
%%

main(void)

{
yyin= fopen("input.txt","r");
yylex();

int yywrap()
{

return(1);

Output:-
d) Write a Lex program which adds line numbers to the given file and display the same onto the
standard output.
Code:-
%{
int line_number = 1;
%}

line .*

%%
{line} { fprintf(yyout,"%10d %s", line_number++, yytext); }

%%

int yywrap(){}

int main(int argc, char*argv[])


{
extern FILE *yyin;

yyin = fopen("input.txt","r");
yyout = fopen("output.txt","w");
yylex();

return 0;
}
Output:-
e) Write a Lex program to printout all HTML tags in file.
Code:-
%{
%}

%%
"<"[^>]*> {printf("%s\n", yytext); }
.;
%%

int yywrap(){}
int main(int argc, char*argv[])
{
yyin=fopen("input.txt","r");
yylex();
return 0;
}
Output:-
Practical 5

a) Write a Lex program to count the number of comment lines in a given C program. Also
eliminate them and copy that program into separate file.
Code:
%{
#include<stdio.h>
int single=0;
int multi=0;
%}

%%
"//".*\n { ++single; fprintf(yyout,"%s", " ");}
"/*"[^*/]*"*/" { ++multi; fprintf(yyout,"%s", " ");}
. { fprintf(yyout,"%s", yytext);}
%%
int yywrap(){}
int main(int argc, int **argv)
{
extern FILE *yyin;
yyin=fopen("input.txt","r");
yyout =fopen("output.txt", "w");
yylex();
printf("\nNo of single line comment = %d ", single);
printf("\nNo of multi line comment = %d ", multi);
return 0;
}
Input File:
Output:

b) Write a Lex program to print keywords, identifiers, operators, numbers in a given C


program.
Input:-

%{

#include<stdio.h>

int con=0,num=0,c=0,space=0,vowels=0,w=0,line=0;

%}
%%

"if"|"else"|"break"|"continue"|"main"|"void"|"float"|"int"|"double"|"do"|"switch"|"for" {printf("\n
%s: Keyword",yytext);}
[A-za-z_][A-Za-z0-9_]* {printf("\n%s: Identifier",yytext);}

[0-9]* {printf("\n%s: Numbers",yytext);}

\"[^\"]\" {printf("\n%s: string constant",yytext);}

"<"|">"|"+"|"="|"-"|")"|"("|"*"|"^"|"$"|"#"|"@"|"!"|"~" {printf("\n%s: Special Character",yytext);}

[ \t\n] ;

"//". num++;

"/*"+[^"*/"]+"*/" con++;

.;

%%

main(void)
{yyin= fopen("input.txt","r");
yylex();
printf("Single Line Comment %d",num);
printf("\nMultiline comment %d",con);}
int yywrap()
{return(1);}
Output:-
Practical 6
a. Program to implement Recursive Descent Parsing in C.
Code:

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

char input[10];
int i,error;
void E();
void T();
void Eprime();
void Tprime();
void F();

main()
{
i=0;
error=0;
printf("Enter an arithmetic expression : "); // Eg: a+a*a
gets(input);
E();
if(strlen(input)==i&&error==0)
printf("\nAccepted..!!!\n");
else printf("\nRejected..!!!\n");
}

void E()
{
T();
Eprime();
}

void Eprime()
{
if(input[i]=='+')
{
i++;
T();
Eprime();
}
}

void T()
{
F();
Tprime();
}

void Tprime()
{
if(input[i]=='*')
{
i++;
F();
Tprime();
}
}

void F()
{
if(isalnum(input[i]))i++;
else if(input[i]=='(')
{
i++;
E();
if(input[i]==')')
i++;
else error=1;
}
else error=1;
}

Output:

Practical 7.
a. Create Yacc and Lex specification files to recognizes arithmetic expressions involving
+, -, * and /.

Code:

%{
#include <stdio.h>
int yylex(void);
void yyerror(char *);
%}
%token INTEGER
%%
S: S E '\n' { printf("valid \n"); }
|;
E:E '+' E ;
| E '-' E ;
|E '*' E ;
|E '/' E ;
| INTEGER ;
%%

void yyerror(char *s) {


fprintf(stderr, "%s\n", s);
}
int main() {
yyparse();
return 0;
}

Output:

b. Create Yacc and Lex specification files are used to generate a calculator which accepts
integer and float type arguments.
Code: (b.y)
%{
#include <stdio.h>
int yylex(void);
void yyerror(char *);
%}
%token INTEGER
%%
S:
S E '\n' { printf("%d\n", $2); }
|;
E:E '+' E { $$ = $1 + $3; }
| E '-' E { $$ = $1 - $3; }
|E '*' E { $$ = $1 * $3; }
|E '/' E { $$ = $1 / $3; }
| INTEGER { $$ = $1; }
%%
void yyerror(char *s) {
fprintf(stderr, "%s\n", s);
}
int main() {
yyparse();
return 0;
}

You might also like