How to write yacc grammar rules to identify function definitions vs function calls? - flex-lexer

I have started learning about YACC, and I have executed a few examples of simple toy programs. But I have never seen a practical example that demonstrates how to build a compiler that identifies and implements function definitions and function calls, array implementation and so on, nor has it been easy to find an example using Google search. Can someone please provide one example of how to generate the tree using YACC? C or C++ is fine.
Thanks in advance!

Let's parse this code with yacc.
file test contains valid C code that we want to parse.
int main (int c, int b) {
int a;
while ( 1 ) {
int d;
}
}
A lex file c.l
alpha [a-zA-Z]
digit [0-9]
%%
[ \t] ;
[ \n] { yylineno = yylineno + 1;}
int return INT;
float return FLOAT;
char return CHAR;
void return VOID;
double return DOUBLE;
for return FOR;
while return WHILE;
if return IF;
else return ELSE;
printf return PRINTF;
struct return STRUCT;
^"#include ".+ ;
{digit}+ return NUM;
{alpha}({alpha}|{digit})* return ID;
"<=" return LE;
">=" return GE;
"==" return EQ;
"!=" return NE;
">" return GT;
"<" return LT;
"." return DOT;
\/\/.* ;
\/\*(.*\n)*.*\*\/ ;
. return yytext[0];
%%
file c.y for input to YACC:
%{
#include <stdio.h>
#include <stdlib.h>
extern FILE *fp;
%}
%token INT FLOAT CHAR DOUBLE VOID
%token FOR WHILE
%token IF ELSE PRINTF
%token STRUCT
%token NUM ID
%token INCLUDE
%token DOT
%right '='
%left AND OR
%left '<' '>' LE GE EQ NE LT GT
%%
start: Function
| Declaration
;
/* Declaration block */
Declaration: Type Assignment ';'
| Assignment ';'
| FunctionCall ';'
| ArrayUsage ';'
| Type ArrayUsage ';'
| StructStmt ';'
| error
;
/* Assignment block */
Assignment: ID '=' Assignment
| ID '=' FunctionCall
| ID '=' ArrayUsage
| ArrayUsage '=' Assignment
| ID ',' Assignment
| NUM ',' Assignment
| ID '+' Assignment
| ID '-' Assignment
| ID '*' Assignment
| ID '/' Assignment
| NUM '+' Assignment
| NUM '-' Assignment
| NUM '*' Assignment
| NUM '/' Assignment
| '\'' Assignment '\''
| '(' Assignment ')'
| '-' '(' Assignment ')'
| '-' NUM
| '-' ID
| NUM
| ID
;
/* Function Call Block */
FunctionCall : ID'('')'
| ID'('Assignment')'
;
/* Array Usage */
ArrayUsage : ID'['Assignment']'
;
/* Function block */
Function: Type ID '(' ArgListOpt ')' CompoundStmt
;
ArgListOpt: ArgList
|
;
ArgList: ArgList ',' Arg
| Arg
;
Arg: Type ID
;
CompoundStmt: '{' StmtList '}'
;
StmtList: StmtList Stmt
|
;
Stmt: WhileStmt
| Declaration
| ForStmt
| IfStmt
| PrintFunc
| ';'
;
/* Type Identifier block */
Type: INT
| FLOAT
| CHAR
| DOUBLE
| VOID
;
/* Loop Blocks */
WhileStmt: WHILE '(' Expr ')' Stmt
| WHILE '(' Expr ')' CompoundStmt
;
/* For Block */
ForStmt: FOR '(' Expr ';' Expr ';' Expr ')' Stmt
| FOR '(' Expr ';' Expr ';' Expr ')' CompoundStmt
| FOR '(' Expr ')' Stmt
| FOR '(' Expr ')' CompoundStmt
;
/* IfStmt Block */
IfStmt : IF '(' Expr ')'
Stmt
;
/* Struct Statement */
StructStmt : STRUCT ID '{' Type Assignment '}'
;
/* Print Function */
PrintFunc : PRINTF '(' Expr ')' ';'
;
/*Expression Block*/
Expr:
| Expr LE Expr
| Expr GE Expr
| Expr NE Expr
| Expr EQ Expr
| Expr GT Expr
| Expr LT Expr
| Assignment
| ArrayUsage
;
%%
#include"lex.yy.c"
#include<ctype.h>
int count=0;
int main(int argc, char *argv[])
{
yyin = fopen(argv[1], "r");
if(!yyparse())
printf("\nParsing complete\n");
else
printf("\nParsing failed\n");
fclose(yyin);
return 0;
}
yyerror(char *s) {
printf("%d : %s %s\n", yylineno, s, yytext );
}
A Makefile to put it together. I use flex-lexer and bison but the example will also work with lex and yacc.
miniC: c.l c.y
bison c.y
flex c.l
gcc c.tab.c -ll -ly
Compile and parse the test code:
$ make
bison c.y
flex c.l
gcc c.tab.c -ll -ly
c.tab.c: In function ‘yyparse’:
c.tab.c:1273:16: warning: implicit declaration of function ‘yylex’ [-Wimplicit-function-declaration]
yychar = yylex ();
^
c.tab.c:1402:7: warning: implicit declaration of function ‘yyerror’ [-Wimplicit-function-declaration]
yyerror (YY_("syntax error"));
^
c.y: At top level:
c.y:155:1: warning: return type defaults to ‘int’ [-Wimplicit-int]
yyerror(char *s) {
^
$ ls
a.out c.l CMakeLists.txt c.tab.c c.y lex.yy.c Makefile README.md test
$ ./a.out test
Parsing complete
For reading resources I can recommend the books Modern Compiler Implementation in C by Andrew Appel and the flex/bison book by John Levine.

Related

Parser (Yacc) seems like it ignores tokens in grammar

Parsing the c-like example code, i have the following issue. Its like some tokens, like identifiers, are ignored by grammar, causing a non-reason syntax error.
Parser code :
%{
#include <stdio.h>
#include <stdlib.h>
int yylex();
void yyerror (char const *);
%}
%token T_MAINCLASS T_ID T_PUBLIC T_STATIC T_VOID T_MAIN T_PRINTLN T_INT T_FLOAT T_FOR T_WHILE T_IF T_ELSE T_EQUAL T_SMALLER T_BIGGER T_NOTEQUAL T_NUM T_STRING
%left '(' ')'
%left '+' '-'
%left '*' '/'
%left '{' '}'
%left ';' ','
%left '<' '>'
%%
PROGRAM : T_MAINCLASS T_ID '{' T_PUBLIC T_STATIC T_VOID T_MAIN '(' ')' COMP_STMT '}'
;
COMP_STMT : '{' STMT_LIST '}'
;
STMT_LIST : /* nothing */
| STMT_LIST STMT
;
STMT : ASSIGN_STMT
| FOR_STMT
| WHILE_STMT
| IF_STMT
| COMP_STMT
| DECLARATION
| NULL_STMT
| T_PRINTLN '(' EXPR ')' ';'
;
DECLARATION : TYPE ID_LIST ';'
;
TYPE : T_INT
| T_FLOAT
;
ID_LIST : T_ID ',' ID_LIST
|
;
NULL_STMT : ';'
;
ASSIGN_STMT : ASSIGN_EXPR ';'
;
ASSIGN_EXPR : T_ID '=' EXPR
;
EXPR : ASSIGN_EXPR
| RVAL
;
FOR_STMT : T_FOR '(' OPASSIGN_EXPR ';' OPBOOL_EXPR ';' OPASSIGN_EXPR ')' STMT
;
OPASSIGN_EXPR : /* nothing */
| ASSIGN_EXPR
;
OPBOOL_EXPR : /* nothing */
| BOOL_EXPR
;
WHILE_STMT : T_WHILE '(' BOOL_EXPR ')' STMT
;
IF_STMT : T_IF '(' BOOL_EXPR ')' STMT ELSE_PART
;
ELSE_PART : /* nothing */
| T_ELSE STMT
;
BOOL_EXPR : EXPR C_OP EXPR
;
C_OP : T_EQUAL | '<' | '>' | T_SMALLER | T_BIGGER | T_NOTEQUAL
;
RVAL : RVAL '+' TERM
| RVAL '-' TERM
| TERM
;
TERM : TERM '*' FACTOR
| TERM '/' FACTOR
| FACTOR
;
FACTOR : '(' EXPR ')'
| T_ID
| T_NUM
;
%%
void yyerror (const char * msg)
{
fprintf(stderr, "C-like : %s\n", msg);
exit(1);
}
int main ()
{
if(!yyparse()){
printf("Compiled !!!\n");
}
}
Part of Lexical Scanner code :
{Empty}+ { printf("EMPTY ") ; /* nothing */ }
"mainclass" { printf("MAINCLASS ") ; return T_MAINCLASS ; }
"public" { printf("PUBLIC ") ; return T_PUBLIC; }
"static" { printf("STATIC ") ; return T_STATIC ; }
"void" { printf("VOID ") ; return T_VOID ; }
"main" { printf("MAIN ") ; return T_MAIN ; }
"println" { printf("PRINTLN ") ; return T_PRINTLN ; }
"int" { printf("INT ") ; return T_INT ; }
"float" { printf("FLOAT ") ; return T_FLOAT ; }
"for" { printf("FOR ") ; return T_FOR ; }
"while" { printf("WHILE ") ; return T_WHILE ; }
"if" { printf("IF ") ; return T_IF ; }
"else" { printf("ELSE ") ; return T_ELSE ; }
"==" { printf("EQUAL ") ; return T_EQUAL ; }
"<=" { printf("SMALLER ") ; return T_SMALLER ; }
">=" { printf("BIGGER ") ; return T_BIGGER ; }
"!=" { printf("NOTEQUAL ") ; return T_NOTEQUAL ; }
{id} { printf("ID ") ; return T_ID ; }
{num} { printf("NUM ") ; return T_NUM ; }
{string} { printf("STRING ") ; return T_STRING ; }
{punct} { printf("PUNCT ") ; return yytext[0] ; }
<<EOF>> { printf("EOF ") ; return T_EOF; }
. { yyerror("lexical error"); exit(1); }
Example :
mainclass Example {
public static void main ( )
{
int c;
float x, sum, mo;
c=0;
x=3.5;
sum=0.0;
while (c<5)
{
sum=sum+x;
c=c+1;
x=x+1.5;
}
mo=sum/5;
println (mo);
}
}
Running all this stuff it showed up this output:
C-like : syntax error
MAINCLASS EMPTY ID
It seems like id is in wrong position although in grammar we have:
PROGRAM : T_MAINCLASS T_ID '{' T_PUBLIC T_STATIC T_VOID T_MAIN '(' ')' COMP_STMT '}'
Based on the "solution" proposed in OP's self answer, it's pretty clear that the original problem was that the generated header used to compile the scanner was not the same as the header generated by bison/yacc from the parser specification.
The generated header includes definitions of all the token types as small integers; in order for the scanner to communicate with the parser, it must identify each token with the correct token type. So the parser generator (bison/yacc) produces a header based on the parser specification (the .y file), and that header must be #included into the generated scanner so that scanner actions can used symbolic token type names.
If the scanner was compiled with a header file generated from some previous version of the parser specification, it is quite possible that the token numbers no longer correspond with what the parser is expecting.
The easiest way to avoid this problem is to use a build system like make, which will automatically recompile the scanner if necessary.
The easiest way to detect this problem is to use bison's built-in trace facility. Enabling tracing requires only a couple of lines of code, and saves you from having to scatter printf statements throughout your scanner and parser. The bison trace will show you exactly what is going on, so not only is it less work than adding printfs, it is also more precise. In particular, it reports every token which is passed to the parser (and, with a little more effort, you can get it to report the semantic values of those tokens as well). So if the parser is getting the wrong token code, you'll see that right away.
After many potential helpful changes, parser worked by changing the order of these tokens.
From
%token T_MAINCLASS T_ID T_PUBLIC T_STATIC T_VOID T_MAIN T_PRINTLN T_INT T_FLOAT T_FOR T_WHILE T_IF T_ELSE T_EQUAL T_SMALLER T_BIGGER T_NOTEQUAL T_NUM T_STRING
TO
%token T_MAINCLASS T_PUBLIC T_STATIC T_VOID T_MAIN T_PRINTLN T_INT T_FLOAT T_FOR T_WHILE T_IF T_EQUAL T_ID T_NUM T_SMALLER T_BIGGER T_NOTEQUAL T_ELSE T_STRING
It looked like that the reading element was else but lexer normaly returned an id. Somehow this modification was the solution.

Bison nonassociative precedence rule

I am trying to enforce some parsing errors by defining a non-associative precedence.
Here is part of my grammar file:
Comparison :
Value ComparisonOp Value
{
$2->Left($1);
$2->Right($3);
$$ = $2;
}
;
Expressions like 1 = 2 should parse, but expressions like 1 = 2 = 3 are not allowed in the grammar. To accommodate this, I tried to make my operator non associative as follows:
%nonassoc NONASSOCIATIVE
.
.(rest of the grammar)
.
Comparison :
Value ComparisonOp Value %prec NONASSOCIATIVE
{
$2->Left($1);
$2->Right($3);
$$ = $2;
}
;
1 = 2 = 3 still passes, Could someone please tell me what I am doing wrong?
You need to set the associativity of the ComparisonOp token(s). Either
%nonassoc ComparisonOp NONASSOCIATIVE
if ComparisonOp is a token or something like
%nonassoc '=' '<' '>' NOT_EQUAL GREATOR_OR_EQUAL LESS_OR_EQUAL NONASSOCIATIVE
if you have mulitple tokens and ComparisonOp is a rule that expands to any of them
As a concrete example, the following works exactly like you are requesting:
%{
#include <stdio.h>
#include <ctype.h>
int yylex();
void yyerror(const char *);
%}
%nonassoc '=' '<' '>' CMPOP
%left '+' '-' ADDOP
%left '*' '/' '%' MULOP
%token VALUE
%%
expr: expr cmp_op expr %prec CMPOP
| expr add_op expr %prec ADDOP
| expr mul_op expr %prec MULOP
| VALUE
| '(' expr ')'
;
cmp_op: '=' | '<' | '>' | '<' '=' | '>' '=' | '<' '>' ;
add_op: '+' | '-' ;
mul_op: '*' | '/' | '%' ;
%%
int main() { return yyparse(); }
int yylex() {
int ch;
while(isspace(ch = getchar()));
if (isdigit(ch)) return VALUE;
return ch;
}
void yyerror(const char *err) { fprintf(stderr, "%s\n", err); }
so if you are having other problems, try posting an MVCE that shows the actual problem you are having...

Removing ambiguity in bison

I am writing a simple parser in bison. The parser checks whether a program has any syntax errors with respect to my following grammar:
%{
#include <stdio.h>
void yyerror (const char *s) /* Called by yyparse on error */
{
printf ("%s\n", s);
}
%}
%token tNUM tINT tREAL tIDENT tINTTYPE tREALTYPE tINTMATRIXTYPE
%token tREALMATRIXTYPE tINTVECTORTYPE tREALVECTORTYPE tTRANSPOSE
%token tIF tENDIF tDOTPROD tEQ tNE tGTE tLTE tGT tLT tOR tAND
%left "(" ")" "[" "]"
%left "<" "<=" ">" ">="
%right "="
%left "+" "-"
%left "*" "/"
%left "||"
%left "&&"
%left "==" "!="
%% /* Grammar rules and actions follow */
prog: stmtlst ;
stmtlst: stmt | stmt stmtlst ;
stmt: decl | asgn | if;
decl: type vars "=" expr ";" ;
type: tINTTYPE | tINTVECTORTYPE | tINTMATRIXTYPE | tREALTYPE | tREALVECTORTYPE
| tREALMATRIXTYPE ;
vars: tIDENT | tIDENT "," vars ;
asgn: tIDENT "=" expr ";" ;
if: tIF "(" bool ")" stmtlst tENDIF ;
expr: tIDENT | tINT | tREAL | vectorLit | matrixLit | expr "+" expr| expr "-" expr
| expr "*" expr | expr "/" expr| expr tDOTPROD expr | transpose ;
transpose: tTRANSPOSE "(" expr ")" ;
vectorLit: "[" row "]" ;
matrixLit: "[" row ";" rows "]" ;
row: value | value "," row ;
rows: row | row ";" rows ;
value: tINT | tREAL | tIDENT ;
bool: comp | bool tAND bool | bool tOR bool ;
comp: expr relation expr ;
relation: tGT | tLT | tGTE | tLTE | tNE | tEQ ;
%%
int main ()
{
if (yyparse()) {
// parse error
printf("ERROR\n");
return 1;
}
else {
// successful parsing
printf("OK\n");
return 0;
}
}
The code may look long and complicated, but i think what i am going to ask does not need the full code, but in any case i preferred to write the code. I am sure my grammar is correct, but ambiguous. When i try to create the executable of the program by writing "bison -d filename.y", i get an error saying that conflicts: 13 shift/reduce. I defined the precedence of the operators at the beginning of this file, and i tried a lot of combinations of these precedences, but i still get this error. How can i remove this ambiguity? Thank you
tOR, tAND, and tDOTPROD need to have their precedence specified as well.

Syntax Error in my grammar production with Bison

As a test file, I'm using this piece of code to see whether or not the parser is working well:
/* A test program */
void main(void){
int x;
int y;
int z;
x= 10;
y = 20;
z =x* (x+y);
}
However, I'm getting a syntax error right after the first void, and I don't quite understand why it won't even reach the parameter part. If there's any tips or see something that perhaps I'm not seeing, I'd appreciate it. I know that I have yet to solve the dangling else problem, but that shouldn't be of an issue for this test.
Here's my parser so far:
%{
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
/* external function prototypes */
extern int yylex();
extern int initLex(int , char **);
/* external global variables */
extern int yydebug;
extern int yylineno;
/* function prototypes */
void yyerror(const char *);
/* global variables */
%}
/* YYSTYPE */
/* terminals */
/* Start adding token names here */
/* Your token names must match Project 1 */
/* The file cmparser.tab.h was gets generated here */
%token TOK_ERROR
%token TOK_ELSE
%token TOK_IF
%token TOK_RETURN
%token TOK_VOID
%token TOK_INT
%token TOK_WHILE
%token TOK_PLUS
%token TOK_MINUS
%token TOK_MULT
%token TOK_DIV
%token TOK_LT
%token TOK_LE
%token TOK_GT
%token TOK_GE
%token TOK_EQ
%token TOK_NE
%token TOK_ASSIGN
%token TOK_SEMI
%token TOK_COMMA
%token TOK_LPAREN
%token TOK_RPAREN
%token TOK_LSQ
%token TOK_RSQ
%token TOK_LBRACE
%token TOK_RBRACE
%token TOK_NUM
%token TOK_ID
/* associativity and precedence */
/* specify operator precedence (taken care of by grammar) and associatity here -
-uncomment */
//%left
%left '*' '/'
%left '+' '-'
%nonassoc '<' '>' "<=" ">="
%left "==" "!="
%right '='
%nonassoc error
/* Begin your grammar specification here */
%%
Start : /* put your RHS for this rule here */
Declarations
{ printf ("Declaration.\n"); }
; /* note that the rule ends with a semicolon */
Declarations :
/* empty */
{}
| Vardeclaration Declarations
{ printf ("Var-declaration.\n");}
| Fundeclaration Declarations
{ printf ("Fun-declaration.\n");}
;
Vardeclaration :
Typespecifier TOK_ID ';'
{ printf ("Not an array.\n");}
| Typespecifier TOK_ID '[' TOK_NUM ']' ';'
{ printf ("An array.\n");}
;
Typespecifier :
TOK_INT
{ printf ("Type int.\n");}
| TOK_VOID
{ printf("Type void.\n");}
;
Fundeclaration :
Typespecifier TOK_ID '(' Params ')' Compoundstmt
{ printf ("Function Declaration.");}
;
Params :
Paramlist
| TOK_VOID
{ printf ("Void param.\n");}
;
Paramlist :
Paramlist ',' Param
| Param
;
Param :
Typespecifier TOK_ID
| Typespecifier TOK_ID '[' ']'
;
Compoundstmt :
'{' Localdeclaration Statement '}'
;
Localdeclaration :
Vardeclaration Localdeclaration
| /* empty */
;
Statement :
Expressionstmt Statement
| Compoundstmt Statement
| Selectionstmt Statement
| Iterationstmt Statement
| Returnstmt Statement
| /* empty */
;
Expressionstmt :
Expression ';'
| ';'
;
Selectionstmt :
TOK_IF '(' Expression ')' Statement
| TOK_IF '(' Expression ')' Statement TOK_ELSE Statement
;
Iterationstmt :
TOK_WHILE '(' Expression ')' Statement
;
Returnstmt :
TOK_RETURN ';'
| TOK_RETURN Expression ';'
;
Expression :
Var '=' Expression
| SimpleExpression
;
Var :
TOK_ID
| TOK_ID '[' Expression ']'
;
SimpleExpression :
AdditiveExpression Relop AdditiveExpression
| AdditiveExpression
;
Relop :
"<="
| '<'
| '>'
| ">="
| "=="
| "!="
;
AdditiveExpression :
AdditiveExpression Addop Term
| Term
;
Addop :
'+'
| '-'
;
Term :
Term Mulop Factor
| Factor
;
Mulop :
'*'
| '/'
;
Factor :
'(' Expression ')'
| Var
| Call
| TOK_NUM
;
Call :
TOK_ID '(' Args ')'
;
Args :
Arglist
| /* empty */
;
Arglist :
Arglist ',' Expression
| Expression
;
%%
void yyerror (char const *s) {
fprintf (stderr, "Line %d: %s\n", yylineno, s);
}
int main(int argc, char **argv){
initLex(argc,argv);
#ifdef YYLLEXER
while (gettok() !=0) ; //gettok returns 0 on EOF
return;
#else
yyparse();
#endif
}
Your grammar looks ok, so my best guess is that your lexer doesn't recognize the string void as TOK_VOID, but instead returns something else.
Try compiling your parser with -DYYDEBUG and setting yydebug = 1 before calling yyparse to see what its getting from the lexer.

can't find a simple error when parsing with YACC

i'm trying to make a very simple YACC parser on Pascal language which just includes integer declarations, some basic expressions and if-else statements. however, i cant find the error for hours and i'm going to be crazy soon. terminal says Error at line:0 but it is impossible!. i use flex and byacc for parser.i will be very glad if you can help me. this is my lex file as you can see;
%{
#include <stdio.h>
#include <string.h>
#include "y.tab.h"
extern int yylval;
int linenum=0;
%}
digit [0-9]
letter [A-Za-z]
%%
if return IF;
then return THEN;
else return ELSE;
for return FOR;
while return WHILE;
PROGRAM return PROGRAM_SYM;
BEGIN return BEGIN_SYM;
VAR return VAR_SYM;
END return END_SYM;
INTEGER return INTEGER_SYM;
{letter}({letter}|{digit})* return identifier;
[0-9]+ return NUMBER;
[\<][\=] return CON_LE;
[\>][\=] return CON_GE;
[\=] return CON_EQ;
[\:][\=] return ASSIGNOP;
; return semiColon;
, return comma;
\n {linenum++;}
. return (int) yytext[0];
%%
and this is my Yacc file
%{
#include <stdio.h>
#include <string.h>
#include "y.tab.h"
extern FILE *yyin;
extern int linenum;
%}
%token PROGRAM_SYM VAR_SYM BEGIN_SYM END_SYM INTEGER_SYM NUMBER
%token identifier INTEGER ASSIGNOP semiColon comma THEN
%token IF ELSE FOR WHILE
%token CON_EQ CON_LE CON_GE GE LE
%left '*' '/'
%left '+' '-'
%start program
%%
program: PROGRAM_SYM identifier semiColon VAR_SYM dec_block BEGIN_SYM statement_list END_SYM '.'
;
dec_block:
dec_list semiColon;
dec_list:
dec_list dec
|
dec
;
dec:
int_dec_list
;
int_dec_list:
int_dec_list int_dec ':' type
|
int_dec ':' type
;
int_dec:
int_dec comma identifier
|
identifier
;
type:
INTEGER_SYM
;
statement_list:
statement_list statement
|
statement
;
statement:
assignment_list
|
expression_list
|
selection_list
;
assignment_list:
assignment_list assignment
|
assignment
;
assignment:
identifier ASSIGNOP expression_list
;
expression_list:
expression_list expression semiColon
|
expression semiColon
;
expression:
'(' expression ')'
|
expression '*' expression
|
expression '/' expression
|
expression '+' expression
|
expression '-' expression
|
factor
;
factor:
identifier
|
NUMBER
;
selection_list:
selection_list selection
|
selection
;
selection:
IF '(' logical_expression ')' THEN statement_list ELSE statement_list
;
logical_expression:
logical_expression '=' expression
|
logical_expression '>' expression
|
logical_expression '<' expression
;
%%
void yyerror(char *s){
fprintf(stderr,"Error at line: %d\n",linenum);
}
int yywrap(){
return 1;
}
int main(int argc, char *argv[])
{
/* Call the lexer, then quit. */
yyin=fopen(argv[1],"r");
yyparse();
fclose(yyin);
return 0;
}
and finally i take an error at the first line when i give the input;
PROGRAM myprogram;
VAR
i:INTEGER;
i3:INTEGER;
j:INTEGER;
BEGIN
i := 3;
j := 5;
i3 := i+j*2;
i := j*20;
if(i>j)
then i3 := i+50+(45*i+(40*j));
else i3 := i+50+(45*i+(40*j))+i+50+(45*i+(30*j));
END.
For debugging grammars, YYDEBUG is your friend. Either stick #define YYDEBUG 1 in the %{..%} in the top of your .y file, or compile with -DYYDEBUG, and stick a yydebug = 1; in main before calling yyparse and you'll get a slew of info about what tokens the parser is seeing and what it is doing with them....
Your lexical analyzer returns blanks and tabs as tokens, but the grammar doesn't recognize them.
Add a parser rule:
[ \t\r] { }
This gets you to line 6 instead of line 0 before you run into an error. You get that error because you don't allow semicolons between declarations:
dec_block:
dec_list semiColon;
dec_list:
dec_list dec
|
dec
;
dec:
int_dec_list
;
That should probably be:
dec_block:
dec_block dec
|
dec
;
dec:
int_dec_list semiColon
;
Doing this gets you to line 14 in the input.
Incidentally, one of the first things I did was to ensure that the lexical analyzer tells me what it is doing, by modifying the rules like this:
if { printf("IF\n"); return IF; }
In long term code, I'd make that diagnostic output selectable at run-time.
You have a general problem with where you expect semicolons. It is also not clear that you should allow an expression_list in the rule for statement (or, maybe, 'not yet' — that might be appropriate when you have function calls, but allowing 3 + 2 / 4 as a 'statement' is not very helpful).
This grammar gets to the end of the input:
%{
#include <stdio.h>
#include <string.h>
#include "y.tab.h"
extern FILE *yyin;
extern int linenum;
%}
%token PROGRAM_SYM VAR_SYM BEGIN_SYM END_SYM INTEGER_SYM NUMBER
%token identifier INTEGER ASSIGNOP semiColon comma THEN
%token IF ELSE FOR WHILE
%token CON_EQ CON_LE CON_GE GE LE
%left '*' '/'
%left '+' '-'
%start program
%%
program: PROGRAM_SYM identifier semiColon VAR_SYM dec_block BEGIN_SYM statement_list END_SYM '.'
;
dec_block:
dec_block dec
|
dec
;
dec:
int_dec_list semiColon
;
int_dec_list:
int_dec_list int_dec ':' type
|
int_dec ':' type
;
int_dec:
int_dec comma identifier
|
identifier
;
type:
INTEGER_SYM
;
statement_list:
statement_list statement
|
statement
;
statement:
assignment
|
selection
;
assignment:
identifier ASSIGNOP expression semiColon
;
expression:
'(' expression ')'
|
expression '*' expression
|
expression '/' expression
|
expression '+' expression
|
expression '-' expression
|
factor
;
factor:
identifier
|
NUMBER
;
selection:
IF '(' logical_expression ')' THEN statement_list ELSE statement_list
;
logical_expression:
expression '=' expression
|
expression '>' expression
|
expression '<' expression
;
%%
void yyerror(char *s){
fprintf(stderr,"Error at line: %d\n",linenum);
}
int yywrap(){
return 1;
}
int main(int argc, char *argv[])
{
/* Call the lexer, then quit. */
yyin=fopen(argv[1],"r");
yyparse();
fclose(yyin);
return 0;
}
Key changes include removing assignment_list and expression_list, and modifying logical_expression so that the two sides of the expansion are expression, rather than the LHS being logical_expression (which then never had a primitive definition, leading to the problems with warnings).
There are still issues to resolve; the expression_list in the selection should be more restrictive to accurately reflect the grammar of Pascal. (You need a block where that could be a single statement or a BEGIN, statement list, END.)

Resources