Professional Documents
Culture Documents
COMPILER DESIGN-R21
COMPILER DESIGN-R21
LIST OF EXPERIMENTS
1. Using the LEX tool, Develop a lexical analyzer to recognize a few patterns in C. (Ex.
identifiers, constants, comments, operators etc.). Create a symbol table, while
recognizing
identifiers.
2. Implement a Lexical Analyzer using LEX Tool
3. Generate YACC specification for a few syntactic categories.
a. Program to recognize a valid arithmetic expression that uses operator +, -, * and /.
b. Program to recognize a valid variable which starts with a letter followed by any
number of letters or digits.
c. Program to recognize a valid control structures syntax of C language (For loop,
while loop, if-else, if-else-if, switch-case, etc.).
d. Implementation of calculator using LEX and YACC
4. Generate three address code for a simple program using LEX and YACC.
5. Implement type checking using Lex and Yacc.
6. Implement simple code optimization techniques (Constant folding, Strength
reduction and Algebraic transformation)
7. Implement back-end of the compiler for which the three address code is given as
input and the 8086 assembly language code is produced as output.
30 PERIODS
TOTAL: 75 PERIODS
PROGRAM:
#include<string.h>
#include<ctype.h>
#include<stdio.h>
void keyword(char str[10])
{
if(strcmp("for",str)==0||strcmp("while",str)==0||strcmp("do",str)==0||
strcmp("int",str)==0||strcmp("float",str)==0||strcmp("char",str)==0||
strcmp("double",str)==0||strcmp("static",str)==0||strcmp("switch",str)==0||
strcmp("case",str)==0)
printf("\n%s is a keyword",str);
else
printf("\n%s is an identifier",str);
}
main()
{
FILE *f1,*f2,*f3;
char c,str[10],st1[10];
int num[100],lineno=0,tokenvalue=0,i=0,j=0,k=0;
printf("\nEnter the c program");/*gets(st1);*/
f1=fopen("input","w");
while((c=getchar())!=EOF)
putc(c,f1);
fclose(f1);
f1=fopen("input","r");
f2=fopen("identifier","w");
f3=fopen("specialchar","w");
while((c=getc(f1))!=EOF)
{
if(isdigit(c))
{
tokenvalue=c-'0';
c=getc(f1);
while(isdigit(c))
{
tokenvalue*=10+c-'0';
c=getc(f1);
}
num[i++]=tokenvalue;
ungetc(c,f1);
}
else
if(isalpha(c))
{
putc(c,f2);
c=getc(f1);
while(isdigit(c)||isalpha(c)||c=='_'||c=='$')
{
putc(c,f2);
c=getc(f1);
}
putc(' ',f2);
ungetc(c,f1);
}
else
if(c==' '||c=='\t')
printf(" ");
else
if(c=='\n')
lineno++;
else
putc(c,f3);
}
fclose(f2);
fclose(f3);
fclose(f1);
printf("\nThe no's in the program are");
for(j=0;j<i;j++)
printf("%d",num[j]);
printf("\n");
f2=fopen("identifier","r");
k=0;
printf("The keywords and identifiersare:");
while((c=getc(f2))!=EOF)
{
if(c!=' ')
str[k++]=c;
else
{
str[k]='\0';
keyword(str);
k=0;
}
}
fclose(f2);
f3=fopen("specialchar","r");
printf("\nSpecial characters are");
while((c=getc(f3))!=EOF)
printf("%c",c);
printf("\n");
fclose(f3);
printf("Total no. of lines are:%d",lineno);
}
RESULT:
Thus the C program for lexical analyzer to recognize few patterns is implemented
and executed successfully.
ALGORITHM:
1. Start the program.
2. Declare necessary variables and creates token representation using Regular.
3. Print the pre processor or directives, keywords by analysis of the input
program.
4. In the program check whether there are arguments.
5. Declare a file and open it as read mode.
6. Read the file and if any taken in source program matches with RE that all
returned as
integer value.
7. Print the token identified using YYdex() function.
8. Stop the program
PROGRAM:
%{
%}
identifier[a-zA-Z][a-zA-Z0-9]*
%%
#.* {printf("\n%s is a preprocessor directive",yytext);}
int |
float |
char |
double |
while |
do |
if |
break |
continue |
void |
switch |
return |
else |
goto {printf("\n%s is a keyword",yytext);}
{identifier}\( {printf("\n function %s",yytext);}
\{ {printf("\nblock begins");}
\} {printf("\nblock ends");}
\( {printf("\n");ECHO;}
{identifier}(\[[0-9]*\])* {printf("\n%s is an identifier",yytext);}
\".*\" {printf("\n %s is a string ",yytext);}
[0-9]+ {printf("\n%s is a number",yytext);
}
\<= |
\>= |
\< |
\> |
\== {printf("\n %s is a relational operator",yytext);}
\= |
\+ |
\- |
\/ |
\& |
% {printf("\n %s is a operator",yytext);}
.|
\n;
%%
int main(int argc,char **argv)
{
FILE *file;
file=fopen("inp.c","r");
if(!file)
{
printf("could not open the file!!!");
exit(0);
}
yyin=file;
yylex();
printf("\n\n");
return(0);
}
int yywrap()
{
return 1;
}
OUTPUT:
void is a keyword
function main(
block begins
int is a keyword
a is an identifier
b is an identifier
c is an identifier
function printf(
"enter the value for a,b" is a string
function scanf(
"%d%d" is a string
& is a operator
a is an identifier
& is a operator
b is an identifier
c is an identifier
= is a operator
a is an identifier
+ is a operator
b is an identifier
function printf(
"the value of c:%d" is a string
& is a operator
c is an identifier
block ends
RESULT:
Thus the program to implement lexical analyzer using lex tool is executed and
implemented successfully.
3. GENERATE YACC SPECIFICATION FOR A FEW SYNTACTIC
CATEGORIES
ALGORITHM:
$ lex exp.l
$ yacc –d exp.y
$ cc lex.yy.c y.tab.c –ll –ly
$ ./a.out
PROGRAM:
Yacc<Exp.y>
%token NUMBER ID NL
%left '+' '-'
%left '*' '/'
%%
Lex<Exp.L>
%{
#include “y.tab.h”
%}
%%
[0-9]+ { return NUMBER; }
[a-zA-Z][a-zA-Z0-9_]* { return ID; }
\n { return NL ;}
. { return yytext[0]; }
%%
RESULT:
Thus the program for validating arithmetic expressions using Yacc is implemented
and executed successfully.
B) PROGRAM TO RECOGNIZE A VALID VARIABLE WHICH
STARTS WITH A LETTER FOLLOWED BY ANY NUMBER OF
LETTERS OR DIGITS.
PROGRAM:
Yacc<Let.Y>
%{
#include “y.tab.h”
%}
%%
[a-zA-Z] { return LETTER ;}
[0-9] { return DIGIT ; }
[\n] { return NL ;}
[_] { return UND; }
. { return yytext[0]; }
%%
RESULT:
Thus the program is executed successfully.
C. PROGRAM TO RECOGNIZE A VALID CONTROL STRUCTURES SYNTAX
OF C LANGUAGE (FOR LOOP,WHILE LOOP, IF-ELSE, IF-ELSE-IF, SWITCH-
CASE, ETC.).
D) IMPLEMENTATION OF CALCULATOR USING LEX AND YACC
PROGRAM:
Lex<Cal.L>
%{
#include"y.tab.h"
#include<math.h>
%}
%%
([0-9]+|([0-9]*\.[0-9]+)([eE][-+]?[0-9]+)?) {yylval.dval=atof(yytext);return
NUMBER;}
log |
LOG {return LOG;}
In {return nLOG;}
sin |
SIN {return SINE;}
cos |
COS {return COS;}
tan |
TAN {return TAN;}
mem {return MEM;}
[\t];
\$ return 0;
\n|. return yytext[0];
%%
Yacc<Cal.Y>
%{
double memvar;
%}
%union
{
double dval;
}
%token<dval>NUMBER
%token<dval>MEM
%token LOG SINE nLOG COS TAN
%left '-' '+'
%left '*' '/'
%right '^'
%left LOG SINE nLOG COS TAN
%nonassoc UMINUS
%type<dval>expression
%%
start:statement'\n'
|start statement'\n'
;
statement:MEM'='expression {memvar=$3;}
| expression{printf("Answer=%g\n",$1);}
;
expression:expression'+'expression {$$=$1+$3;}
| expression '-' expression {$$=$1-$3;}
| expression '*' expression {$$=$1*$3;}
| expression '/' expression
{
if($3==0)
yyerror("divide by zero");
else
$$=$1/$3;
}
|expression'^'expression {$$=pow($1,$3);}
;
expression:'-'expression %prec UMINUS{$$=-$2;}
|'('expression')'{$$=$2;}
|LOG expression {$$=log($2)/log(10);}
|nLOG expression {$$=log($2);}
|SINE expression {$$=sin($2*3.14/180);}
|COS expression {$$=cos($2*3.14/180);}
|TAN expression {$$=tan($2*3.14/180);}
|NUMBER {$$=$1;}
|MEM {$$=memvar;}
;
%%
main()
{
printf("Enter the expression");
yyparse();}
int yyerror(char *error)
{
printf("%s\n",error);
}
OUTPUT:
RESULT:
Thus the program to implement calculator using LEX and YACC tool is executed
successfully and output is verified.
4) GENERATE 3 ADDRESS CODE FOR A SIMPLE PROGRAM USING LEX AND
YACC
lex.l
%{
#include<stdio.h>
#include"y.tab.h"
int k=1;
%}
%%
[0-9]+ {
yylval.dval=yytext[0];
return NUM;
}
\n {return 0;}
. {return yytext[0];}
%%
main()
{
yyparse();
return 0;
}
yacc.y
%{
#include<stdio.h>
int aaa;
%}
%union{
char dval;
}
%%
statement : E {printf("\nt = %c \n",$1);}
;
E : E '+' E
{
char word[]="t";
char *test=gencode(word,$1,'+',$3);
$$=test;
}
| E '-' E
{
char word[]="t";
char *test=gencode(word,$1,'-',$3);
$$=test;
}
| E '%' E
{
char word[]="t";
char *test=gencode(word,$1,'%',$3);
$$=test;
}
| E '*' E
{
char word[]="t";
char *test=gencode(word,$1,'*',$3);
$$=test;
}
| E '/' E
{
char word[]="t";
char *test=gencode(word,$1,'/',$3);
$$=test;
}
| '(' E ')'
{
$$=$2;
}
| NUM
{
$$=$1;
}
;
%%
Problem: getting garbage value in output
Expected output for expression (2+3)*5 should be like:
t1= 2 + 3
t2= t1 * 5
Obtained output:
t1= 2 + 3
t2= garbage value * 5
RESULT:
Thus the program to implement 3 address code using LEX and YACC tool is
executed successfully and output is verified.
5. IMPLEMENT TYPE CHECKING USING LEX AND YACC.
PROGRAM:
Lex<Cal.L>
%{
#include"y.tab.h"
#include<math.h>
%}
%%
([0-9]+|([0-9]*\.[0-9]+)([eE][-+]?[0-9]+)?) {yylval.dval=atof(yytext);return
NUMBER;}
log |
LOG {return LOG;}
In {return nLOG;}
sin |
SIN {return SINE;}
cos |
COS {return COS;}
tan |
TAN {return TAN;}
mem {return MEM;}
[\t];
\$ return 0;
\n|. return yytext[0];
%%
Yacc<Cal.Y>
%{
double memvar;
%}
%union
{
double dval;
}
%token<dval>NUMBER
%token<dval>MEM
%token LOG SINE nLOG COS TAN
%left '-' '+'
%left '*' '/'
%right '^'
%left LOG SINE nLOG COS TAN
%nonassoc UMINUS
%type<dval>expression
%%
start:statement'\n'
|start statement'\n'
;
statement:MEM'='expression {memvar=$3;}
| expression{printf("Answer=%g\n",$1);}
;
expression:expression'+'expression {$$=$1+$3;}
| expression '-' expression {$$=$1-$3;}
| expression '*' expression {$$=$1*$3;}
| expression '/' expression
{
if($3==0)
yyerror("divide by zero");
else
$$=$1/$3;
}
|expression'^'expression {$$=pow($1,$3);}
;
expression:'-'expression %prec UMINUS{$$=-$2;}
|'('expression')'{$$=$2;}
|LOG expression {$$=log($2)/log(10);}
|nLOG expression {$$=log($2);}
|SINE expression {$$=sin($2*3.14/180);}
|COS expression {$$=cos($2*3.14/180);}
|TAN expression {$$=tan($2*3.14/180);}
|NUMBER {$$=$1;}
|MEM {$$=memvar;}
;
%%
main()
{
printf("Enter the expression");
yyparse();}
int yyerror(char *error)
{
printf("%s\n",error);
}
OUTPUT:
RESULT:
Thus the program to implement calculator using LEX and YACC tool is executed
successfully and output is verified.
6. IMPLEMENT SIMPLE CODE OPTIMIZATION TECHNIQUES (CONSTANT
FOLDING, STRENGTH REDUCTION AND ALGEBRAIC TRANSFORMATION)
AIM:
To write a C program to implement Code Optimization Techniques.
ALGORITHM:
PROGRAM:
#include<stdio.h>
#include<conio.h>
#include<string.h>
struct op
{
char l;
char r[20];
}
op[10],pr[10];
void main()
{
int a,i,k,j,n,z=0,m,q;
char *p,*l;
char temp,t;
char *tem;
clrscr();
printf("Enter the Number of Values:");
scanf("%d",&n);
for(i=0;i<n;i++)
{
printf("left: ");
op[i].l=getche();
printf("\tright: ");
scanf("%s",op[i].r);
}
printf("Intermediate Code\n") ;
for(i=0;i<n;i++)
{
printf("%c=",op[i].l);
printf("%s\n",op[i].r);
}
for(i=0;i<n-1;i++)
{
temp=op[i].l;
for(j=0;j<n;j++)
{
p=strchr(op[j].r,temp);
if(p)
{
pr[z].l=op[i].l;
strcpy(pr[z].r,op[i].r);
z++; }}}
pr[z].l=op[n-1].l;
strcpy(pr[z].r,op[n-1].r);
z++;
printf("nAfter Dead Code Eliminationn");
for(k=0;k<z;k++) {
printf("%ct=",pr[k].l);
printf("%sn",pr[k].r);
}
for(m=0;m<z;m++) {
tem=pr[m].r;
for(j=m+1;j<z;j++) {
p=strstr(tem,pr[j].r);
if(p) {
t=pr[j].l;
pr[j].l=pr[m].l;
for(i=0;i<z;i++) {
l=strchr(pr[i].r,t) ;
if(l) {
a=l-pr[i].r;
printf("pos: %d",a);
pr[i].r[a]=pr[m].l; }}}}}
printf("Eliminate Common Expression\n");
for(i=0;i<z;i++)
{
printf("%c\t=",pr[i].l);
printf("%s\n",pr[i].r);
}
for(i=0;i<z;i++)
{
for(j=i+1;j<z;j++)
{
q=strcmp(pr[i].r,pr[j].r);
if((pr[i].l==pr[j].l)&&!q)
{
pr[i].l='\0';
strcpy(pr[i].r,'\0');
}
}
}
printf("Optimized Code\n");
for(i=0;i<z;i++)
{
if(pr[i].l!='\0')
{
printf("%c=",pr[i].l);
printf("%s\n",pr[i].r);
}
}
getch();
}
RESULT:
Thus the program for code optimization is implemented and executed
successfully, and the output is verified.
7. IMPLEMENT BACK-END OF THE COMPILER FOR WHICH THE THREE
ADDRESS CODE IS GIVEN AS INPUT AND THE 8086 ASSEMBLY LANGUAGE
CODE IS PRODUCED AS OUTPUT.
AIM:
To write a C program to implement Simple Code Generator.
ALGORITHM:
1. Start
2. Get address code sequence.
3. Determine current location of 3 using address (for 1st operand).
4. If current location not already exist generate move (B,O).
5. Update address of A(for 2nd operand).
6. If current value of B and () is null,exist.
7. If they generate operator () A,3 ADPR.
8. Store the move instruction in memory
9. Stop
PROGRAM:
#include<stdio.h>
#include<conio.h>
#include<string.h>
#include<ctype.h>
#include<graphics.h>
typedef struct
{
char var[10];
int alive;
}
regist;
regist preg[10];
void substring(char exp[],int st,int end)
{
int i,j=0;
char dup[10]="";
for(i=st;i<end;i++)
dup[j++]=exp[i];
dup[j]='0';
strcpy(exp,dup);
}
int getregister(char var[])
{
int i;
for(i=0;i<10;i++)
{
if(preg[i].alive==0)
{
strcpy(preg[i].var,var);
break;
}
}
return(i);
}
void getvar(char exp[],char v[])
{
int i,j=0;
char var[10]="";
for(i=0;exp[i]!='\0';i++)
if(isalpha(exp[i]))
var[j++]=exp[i];
else
break;
strcpy(v,var);
}
void main()
{
char basic[10][10],var[10][10],fstr[10],op;
int i,j,k,reg,vc,flag=0;
clrscr();
printf("\nEnter the Three Address Code:\n");
for(i=0;;i++)
{
gets(basic[i]);
if(strcmp(basic[i],"exit")==0)
break;
}
printf("\nThe Equivalent Assembly Code is:\n");
for(j=0;j<i;j++)
{
getvar(basic[j],var[vc++]);
strcpy(fstr,var[vc-1]);
substring(basic[j],strlen(var[vc-1])+1,strlen(basic[j]));
getvar(basic[j],var[vc++]);
reg=getregister(var[vc-1]);
if(preg[reg].alive==0)
{
printf("\nMov R%d,%s",reg,var[vc-1]);
preg[reg].alive=1;
}
op=basic[j][strlen(var[vc-1])];
substring(basic[j],strlen(var[vc-1])+1,strlen(basic[j]));
getvar(basic[j],var[vc++]);
switch(op)
{
case '+': printf("\nAdd"); break;
case '-': printf("\nSub"); break;
case '*': printf("\nMul"); break;
case '/': printf("\nDiv"); break;
}
flag=1;
for(k=0;k<=reg;k++)
{
if(strcmp(preg[k].var,var[vc-1])==0)
{
printf("R%d, R%d",k,reg);
preg[k].alive=0;
flag=0;
break;
}
}
if(flag)
{
printf(" %s,R%d",var[vc-1],reg);
printf("\nMov %s,R%d",fstr,reg);
}
strcpy(preg[reg].var,var[vc-3]);
getch();
}
}
INPUT & OUTPUT:
RESULT:
Thus the program to implement simple code generator is executed successfully
and the output is verified.