[COMPILER DESIGN LAB]

COMPILER DESIGN LABORATORY

Sub. Code: 13CS306
Hrs. / Week: 03
Total Hrs: 42

LIST OF PROGRAMS

IA Marks: 50
Exam Hours: 03
Exam Marks: 50

Part A
Execute the following programs using LEX:
1.

Convert the upper case characters to lower case characters in a file.

2.

Display the ASCII values of non-printing characters which are present in a file.

3.

Count number of characters, words, lines, and spaces in a given file.

4.

Count the number of comment lines in a given C program. Also eliminate them and copy the resulting program into a
separate file.

5.

Convert an octal number to its equivalent decimal number.

6.

Recognize and count the number of identifiers in a given input file.

Execute the following programs using YACC:

1.

Recognize IF control statements and display number of levels of nesting.

2.

Recognize a valid variable name, which starts with a letter, followed by any number of letters or digits?

3.

Check whether the given string an bm (n>0, m>=0) is accepted by the grammar or not.

4.

Check for the validity of a given arithmetic expression.

5.

Evaluate an arithmetic expression involving operators +, -, and /.

6.

Check whether the given string an bn (n>0) is accepted by the grammar or not.
Part B

Execute the following programs using ANTLR:

1.

Combined grammar for implementing simple calculator.

2.

Check whether the given sentence in English is valid or not.

3.

Implement input construct in C/Java language.

4.

Write a combined grammar to implement output construct in C/Java language.

5.

Write a combined grammar to implement ASSIGNMENT construct in C++ language.

6.

Write a combined grammar to implement FOR construct in FORTRAN / C++ language.

Part C (Mini Projects)

Project#1a

Development of Lexical analyzer for C, C++, Python, FORTRAN, PASCAL or any other
programming language.

Project#1b

Development of Lexical analyzer for HTML, XML, Perl, PHP or any other scripting language.

2.

Project#2

Development of Parser / code optimizer for any programming / scripting language.

3.

Project#3

Development of Syntax directed translator / semantic analyzer for any language.

1.

5th Sem

Autonomous Scheme

1 of 22

[COMPILER DESIGN LAB]

Write a program to convert the upper case characters into lower case characters in a file.

%{
/* Lex specification to convert upper case characters to lower case. */
#include<stdio.h>
%}
%%
[A-Z]
.|\n

{putchar ( 'a' + ( yytext[0] - 'A' ) ); }

{ECHO;}

%%
int main(int argc , char **argv )
{
/* Input is taken from stdin, output is to stdout */
yylex();
return 0;
}

5th Sem

Autonomous Scheme

2 of 22

[COMPILER DESIGN LAB]

Write a program to count the number of comment lines in a given C program. Also eliminate them and copy
the resulting program into a separate file.
%{
/* Lex specification to count number of comment lines in a file and eliminate them. */
int count=0, flag=0;
%}
%%
[\t ]+
"/*"
.
"*/"
%%

{fprintf(yyout, yytext);}
{flag=1; count++ ;}
{if(flag) fprintf(yyout, " ");
else fprintf(yyout, yytext);}
{flag=0;}

int main(int argc, char **argv)

{
char sname[25], dname[25];
if(argc!=3)
{
printf("Enter the source file\n");
scanf("%s", sname);
printf("Enter the destination file\n");
scanf("%s", dname);
yyin=fopen(sname, "r");
yyout=fopen(dname, "w");
}
else
{
yyin=fopen(argv[1], "r");
yyout=fopen(argv[2], "w");
}
yylex();
printf("The number of comments are=%d\n", count);
return 0;

5th Sem

Autonomous Scheme

3 of 22

[COMPILER DESIGN LAB]

}
Write a program to display the ASCII values of non-printing characters which are present in a file.
%{
/* Lex Specification to print the ASCII values of the non-printable characters from the input
file. The input file name is passed as a command-line argument. */
#include<stdio.h>
#include<ctype.h>
/* For isprint() function */
#include<stdlib.h>
/* To store the non-printable characters found so far */
/* The size of the array is the max number of different ASCII characters possible */
int nonPrintable[256];
int arrayIndex=0, i;
%}
%%
.|\n

{/* Check if the character is non-printable or not */

if(!isprint(yytext[0]))
{
/* Check if we have already found this character */
for(i=0;i<arrayIndex;++i)
if(yytext[0]==nonPrintable[i])
break;
/* If we have not found this character before, then output it */
if(i<=arrayIndex)
{
printf("\n%5d\n", yytext[0]);
nonPrintable[arrayIndex++]=yytext[0];
}
}
}

%%
int main(int argc, char **argv)
{
/* Check if the arguments are OK */
if(argc!=2)
{
fprintf(stderr, "Usage: %s filename\n", argv[0]);
exit(1);
}
/* Open the file on yyin */
yyin=fopen(argv[1], "r");
if(!yyin)
{
fprintf(stderr, "Could not open %s\n", argv[1]);
exit(1);
}

5th Sem

Autonomous Scheme

4 of 22

[COMPILER DESIGN LAB]

/* Call the lexer */

printf("The following non-printable ASCIIs were found in the file --\n");
yylex();
/* Close the file */
fclose(yyin);
return 0;
}

5th Sem

Autonomous Scheme

5 of 22

[COMPILER DESIGN LAB]

Write a program to convert an octal number to its equivalent decimal number.
%{
/* Lex specification to convert an octal number to its equivalent decimal number. */
#include<stdio.h>
int octal=0, decimal=0;
int valid=0;
%}
%%
[0-7]+

{valid=1; octal=atoi(yytext);}

[\n]

{;}

{valid=0;}

%%
yywrap()
{
if(valid)
{
decimal=octalToDecimal(octal);
printf("Decimal Equivalent is: %d", decimal);
}
else
{
printf("Invalid Number");
}
}
int octalToDecimal(int n)
{
int digit=0, sum=0, i=0;
while(n)
{
digit=n%10;
sum+=digit*power(8, i);
n=n/10;
i++;
}
return sum;
}
int power(int a, int n)
{
int i=0, tempsum=1;
for(i=0; i<n; i ++)
tempsum=tempsum*a;
return tempsum;
}

5th Sem

Autonomous Scheme

6 of 22

[COMPILER DESIGN LAB]

int main()
{
printf("Enter the octal number :");
yylex();
return 0;
}

5th Sem

Autonomous Scheme

7 of 22

[COMPILER DESIGN LAB]

Write a program to count number of characters, words, lines, and spaces in a given file.
%{
/* Lex specification to count spaces, lines, words, characters. */
int nword=0,nline=0,nchar=0,nspace=0;
%}
%%
[a-zA-Z0-9]+ {nword++;nchar+=yyleng;}
[ ]+
{nspace++;}
\n
{nline++;}
.
{nchar++;}
%%
int main(int argc, char **argv)
{
char sname[25];
if(argc!=2)
{
printf("Enter the source file\n");
scanf("%s", sname);
yyin=fopen(sname, "r");
}
else
yyin=fopen(argv[1], "r");
yylex();
printf("Number
printf("Number
printf("Number
printf("Number
return 0;

of
of
of
of

words=%d\n", nword);
characters=%d\n", nchar);
spaces=%d\n", nspace);
lines=%d\n", nline);

5th Sem

Autonomous Scheme

8 of 22

[COMPILER DESIGN LAB]

Write a program to recognize and count the number of identifiers in a given input file.
%{
/* Lex specification to count identifiers in a file. */
int flag=0,id=0;
%}
%%
int|long|float|double|char

{flag=1;}

[,]

{
if(flag)
id++;
}

[;]

{
if(flag)
{
id++;
flag=0;
}
}

{;}

%%
int main(int argc, char
{
char *source;
if(argc>1)
{

**argv)

yyin=fopen(argv[1], "r");
if(!yyin)
{
printf("Error in opening the file %s\n", argv[1]);
exit(0);
}
}
else
{
printf("Enter source\n");
scanf("%s", source);
yyin=fopen(source, "r");
if(!yyin)
{
printf("Error in opening the file %s\n", source);
exit(0);
}
}
yylex();
printf("Number of identifiers=%d\n", id);
return 0;
}

5th Sem

Autonomous Scheme

9 of 22

[COMPILER DESIGN LAB]

Write a program to check for the validity of a given arithmetic expression.
%{
/* Yacc specification to test the validity of a simple expression. */
#include <stdio.h>
%}
%token NUMBER
%left '+' '-'
%left '*' '/'
%%
lines:
|lines '\n'
|lines exp '\n'
{printf("\nValid expression\n");}
;
exp:'-' exp
|exp '+' exp
|exp '-' exp
|exp '*' exp
|exp '/' exp
|'(' exp ')'
|NUMBER
;
%%
yyerror()
{
printf("\nError");
exit(0);
}
yylex()
{
char ch;
ch=getchar();
if(isdigit(ch))
{
ungetc(ch, stdin);
scanf("%d", &yylval);
return NUMBER;
}
return ch;
}
int main()
{
printf("Enter an expression");
yyparse();
return 0;

5th Sem

Autonomous Scheme

10 of 22

[COMPILER DESIGN LAB]

}Write a program to recognize IF control statements and display number of levels of nesting.
%{
/* Yacc specification to recognize IF control statements and display number of levels of
nesting. */
#include<stdio.h>
%}
%token IF COND OB CB
%%
lines :
| lines ifstmt;
ifstmt: IF COND OB lines CB;
%%
yyerror()
{
printf(\nInvalid IF structure.);
exit(0);
}
int main(int argc, char **argv)
{
extern int maxlevel;
extern FILE *yyin;
char source[30];
if(argc==1)
{
printf(\nEnter the source file name : );
scanf(%s, source);
yyin=fopen(source, r);
}
else
yyin=fopen(argv[1], r);
yyparse();
printf(\nValid IF structure);
printf(\nDeapth of the structure = %d\n, maxlevel);
return 0;
}

5th Sem

Autonomous Scheme

11 of 22

[COMPILER DESIGN LAB]

Write a program to recognize IF control statements and display number of levels of nesting.
%{
/* Lex specification to recognize IF control statement and display number of levels of
nesting. */
#include"y.tab.h"
int level=0,maxlevel=0,flag=0,flag1=0,flag2=0,flag3=0;
%}
%%
[ \n\t]*"if"[ \n\t]*
[ \n\t]*"(".*")"[ \n\t]*
[ \n\t]*"{"[ \n\t]*

[ \n\t]*"}" [ \n\t]*

5th Sem

{flag=1;flag1=1;flag2=1;return IF;}
{if(flag==1) {flag=0;return COND;}}
{if((flag1==1)&&(flag2==1))
{flag2==0; level++;
if(maxlevel<level)
{maxlevel=level;}
return OB;}
else
flag3=1;}
{if((flag1==1)&&(flag3==0))
{level--; if(level==0)
{flag1=0;}
return CB;}
else flag3=0;}

Autonomous Scheme

12 of 22

[COMPILER DESIGN LAB]

%%Write a program to evaluate an arithmetic expression involving operators +, -, *, and /.
%{
/* Yacc specification to evaluate an arithmetic expression involving operators +, -, *,
and /. */
#include<stdio.h>
%}
%token DIGIT, IDENTIFIERS
%left '*' '/'
%left '+' '-'
%right UMINUS
%%
lines:
|lines '\n'
|lines exp '\n'
{ printf("\nValid expression\n");}
;
exp:'-' exp
|exp '+' exp
|exp '-' exp
|exp '*' exp
|exp '/' exp
|'(' exp ')'
|NUMBER
|IDENTIFIER
;
%%
yyerror()
{
printf("\nError");
exit(0);
}
yylex()
{
int ch;
while((ch=getchar())==' ');
if(isdigit(ch))
return NUMBER;
else if(isalpha(ch))
return IDENTIFIER;
else
return ch;
}
int main()
{
printf("Enter an expression\n");
yyparse();
return 0;

5th Sem

Autonomous Scheme

13 of 22

[COMPILER DESIGN LAB]

}Write a program to recognize a valid variable name, which starts with a letter, followed by any number
of letters or digits.
%{
/* Yacc specification to recognize a valid variable name. */
#include<stdio.h>
%}
%token letter digit
%%
start:
|letter A '\n'
|letter ;
A :letter A
|digit A
|letter
|digit ;
%%
yyerror()
{
printf("The variable is not in valid format\n");
exit(1);
}
yylex()
{
int ch;
ch=getchar();
if(isalpha(ch) && islower(ch))
return letter;
else if(isdigit(ch))
return digit;
else
return ch;
}
int main()
{
printf("Enter the variable\n");
yyparse();
printf("Valid variable\n");
return 0;

5th Sem

Autonomous Scheme

14 of 22

[COMPILER DESIGN LAB]

n

}Write a program to check whether the given string a b (n>0) is accepted by the grammar or not.
%{
n

/* Yacc specification to recognize the given string a b (n>=0) is accepted by the

grammar or not. */
#include <stdio.h>
%}
%token A B
%%
s:A s B
|A B
|
;
%%
yyerror()
{
printf("The string does not belong to the grammar provided\n");
exit(1);
}
int yylex()
{
int ch;
ch=getchar();
if(ch=='a')
return A;
else if(ch=='b')
return B;
else if(ch=='\n')
return 0;
else
return ch;
}
int main()
{
printf("Enter the expression\n");
yyparse();
printf("The string is a part of the defined grammar\n");
return 0;
}

5th Sem

Autonomous Scheme

15 of 22

[COMPILER DESIGN LAB]

Write a combined grammar for implementing simple calculator.
grammar SimpleCalc;
options
{
language = Java;
}
tokens
{
PLUS = '+';
MINUS = '-';
MULT = '*';
DIV = '/';
}
@members
{
publicstaticvoid main(String[] args) throws Exception
{
SimpleCalcLexer lex = new SimpleCalcLexer(new ANTLRFileStream(args[0]));
CommonTokenStream tokens = new CommonTokenStream(lex);
SimpleCalcParser parser = new SimpleCalcParser(tokens);
try
{
parser.expr();
}
catch(RecognitionException e)
{
e.printStackTrace();
}
}
}
/*Parser Rules*/
expr : term((PLUS|MINUS)term)*;
term : factor((MULT|DIV)factor)*;
factor : NUMBER;
/*Lexer Rules*/
NUMBER : (DIGIT)+;
WHITESPACE : ('\t'|' '|'\n')+
fragment DIGIT : '0'..'9';

5th Sem

{$channel = HIDDEN;};

Autonomous Scheme

16 of 22

[COMPILER DESIGN LAB]

Write a combined grammar to check whether the given sentence in English is valid or not.
grammar Sentence;
options
{
language = Java;
}
tokens
{
GET = 'get';
PUT = 'put';
CHANGE = 'change';
DATA = 'data';
METADATA = 'metadata';
DEPENDENCIES = 'dependencies';
DEPENDENTS = 'dependents';
FROM = 'from';
IN = 'in';
ABOUT = 'about';
OF = 'of';
}
@members
{
publicstaticvoid main(String[] args) throws Exception
{
SentenceLexer lex = new SentenceLexer(new ANTLRFileStream(args[0]));
CommonTokenStream tokens = new CommonTokenStream(lex);
SentenceParser parser = new SentenceParser(tokens);
try
{
parser.expr();
}
catch(RecognitionException e)
{
e.printStackTrace();
}
}
}
command : sentence (NEWLINEsentence)* NEWLINE? EOF;
sentence : WS? verbWSobjectWSprepositionWStargetWS?;
verb : GET | PUT | CHANGE;
object : DATA | METADATA | DEPENDENCIES | DEPENDENTS | STATISTICS;
preposition : IN | ABOUT | OF | FROM;
target : FILE;

FILE : ('a'..'z' | 'A'..'Z' | '0'..'9' | '.')+;

NEWLINE : '\r'?'\n';
WS : (' ' | '\r' | '\n' | '\t')+ {SKIP();};

5th Sem

Autonomous Scheme

17 of 22

[COMPILER DESIGN LAB]

Write a combined grammar to implement READ construct in PASCAL language.
grammar read;
options {
language = Java;
}
tokens {
PLUS = '+';
MINUS = '-';
MULT = '*';
DIV = '/';
EQUAL = ':=';
OPENB = '(';
CLOSEB = ')';
COMMA = ',';
}
@members {
publicstaticvoid main(String[] args) throws Exception
{
readLexer lex = new readLexer(new ANTLRFileStream(args[0]));
CommonTokenStream tokens = new CommonTokenStream(lex);
readParser parser = new readParser(tokens);
try
{
parser.expr();
}
catch(RecognitionException e)
{
e.printStackTrace();
}
}
}
/* Lexer rules */

NUMBER: (DIGIT)+('\.'(DIGIT)+)?;
WS: ('\t'|' '|'\r'|'\n')+ {$channel = HIDDEN};
READ: 'read';
ID: (ALPHA)+;
fragment DIGIT: '0'..'9';
fragment ALPHA: 'a'..'z';
/* Parser rules */
read: READOPENBidlistCLOSEB;
idlist: ID (COMMAID)*;
lhs: IDEQUALexpr;
expr: term((PLUS|MINUS)term)*;
term: factor((MULT|DIV)factor)*;
factor: NUMBER|ID;

5th Sem

Autonomous Scheme

18 of 22

[COMPILER DESIGN LAB]

Write a combined grammar to implement WRITE construct in PASCAL language.
grammar write;
options {
language = Java;
}
tokens {
PLUS = '+';
MINUS = '-';
MULT = '*';
DIV = '/';
EQUAL = ':=';
OPENB = '(';
CLOSEB = ')';
COMMA = ',';
}
@members {
publicstaticvoid main(String[] args) throws Exception
{
writeLexer lex = new writeLexer(new ANTLRFileStream(args[0]));
CommonTokenStream tokens = new CommonTokenStream(lex);
writeParser parser = new writeParser(tokens);
try
{
parser.expr();
}
catch(RecognitionException e)
{
e.printStackTrace();
}
}
}
/* Lexer rules */

NUMBER: (DIGIT)+('\.'(DIGIT)+)?;
WS: ('\t'|' '|'\r'|'\n')+ {$channel = HIDDEN;};
WRITE: 'write';
ID: (ALPHA)+;
fragment DIGIT: '0'..'9';
fragment ALPHA: 'a'..'z';
/* Parser rules */
//write: WS? KEY WS? OPENB WS? ID WS? COMMA WS? ID WS? CLOSEB WS?;
write: WRITEOPENBidlistCLOSEB;
idlist: ID (COMMAID)*;
lhs: IDEQUALexpr;
expr: term((PLUS|MINUS)term)*;
term: factor((MULT|DIV)factor)*;
factor: NUMBER|ID;

5th Sem

Autonomous Scheme

19 of 22

[COMPILER DESIGN LAB]

Write a combined grammar to implement ASSIGNMENT construct in PASCAL language.
grammar assign;
options {
language = Java;
}
tokens {
PLUS = '+';
MINUS = '-';
MULT = '*';
DIV = '/';
EQUAL = ':=';
OPENB = '(';
CLOSEB = ')';
COMMA = ',';
}
@members {
publicstaticvoid main(String[] args) throws Exception
{
assignLexer lex = new assignLexer(new ANTLRFileStream(args[0]));
CommonTokenStream tokens = new CommonTokenStream(lex);
assignLexer parser = new assignLexer(tokens);
try
{
parser.expr();
}
catch(RecognitionException e)
{
e.printStackTrace();
}
}
}
/* Lexer rules */

NUMBER: (DIGIT)+('\.'(DIGIT)+)?;
WS: ('\t'|' '|'\r'|'\n')+ {$channel = HIDDEN;};
ID: (ALPHA)+;
fragment DIGIT: '0'..'9';
fragment ALPHA: 'a'..'z';
/* Parser rules */
stmt: IDEQUALexpr;
expr: term((PLUS|MINUS)term)*;
term: factor((MULT|DIV)factor)*;
factor: NUMBER|ID;

5th Sem

Autonomous Scheme

20 of 22

[COMPILER DESIGN LAB]

Write a combined grammar to implement FOR construct in PASCAL language & display number of levels of
nesting.
grammar forloop;
options {
language = Java;
}
tokens {
PLUS = '+';
MINUS = '-';
MULT = '*';
DIV = '/';
EQUAL = ':=';
OPENB = '(';
CLOSEB = ')';
COMMA = ',';
SEMICOLON = ';';
}
@members {
publicstaticvoid main(String[] args) throws Exception
{
forloopLexer lex = new forloopLexer(new ANTLRFileStream(args[0]));
CommonTokenStream tokens = new CommonTokenStream(lex);
forloopParser parser = new forloopParser(tokens);
try
{
parser.expr();
}
catch(RecognitionException e)
{
e.printStackTrace();
}
}
}
/* Lexer rules */

NUMBER: (DIGIT)+('\.'(DIGIT)+)?;
WS: ('\t'|' '|'\r'|'\n')+ {$channel = HIDDEN;};
FOR: 'for';
DO: 'do';
TO: 'to';
BEGIN: 'begin';
END: 'end';
WRITE: 'write';
READ: 'read';
ID: (ALPHA)+;
fragment DIGIT: '0'..'9';
fragment ALPHA: 'a'..'z';

5th Sem

Autonomous Scheme

21 of 22

[COMPILER DESIGN LAB]

/* Parser rules */
for: FORindex_expDObody;
index_exp: IDEQUALexprTOexpr;
body: stmt | BEGINstmt_listEND;
stmt: assign | read | write | for;
stmt_list: stmt (stmt)*;
write: WRITEOPENBidlistCLOSEBSEMICOLON;
read: READOPENBidlistCLOSEBSEMICOLON;
idlist: ID (COMMAID)*;
assign: IDEQUALexprSEMICOLON;
expr: term((PLUS|MINUS)term)*;
term: factor((MULT|DIV)factor)*;
factor: NUMBER|ID;

5th Sem

Autonomous Scheme

22 of 22