Wanted: YACC Grammer for C/C++

James Buchanan james at sparrmsuucp
Fri May 19 23:37:50 AEST 1989


In article <18416 at cup.portal.com>, src at cup.portal.com (Steve R Calwas) writes:
> I am looking for a public domain or inexpensive YACC grammer definition for
> C and/or C++.  LEX definitions of same are also desired.  Anyone having
> information about sources for these would be much appreciated.  E-mail or
> post.  (For example, is a YACC grammer for C a part of the ANSI committee's
> output?)  Thanks for any help.

Here's the LEX file. Again this is written by some anonymous Guru rumoured
to be involved with the ANSI C committee. 

************ CUT HERE scan.l ***********
D			[0-9]
L			[a-zA-Z_]
H			[a-fA-F0-9]
E			[Ee][+-]?{D}+
FS			(f|F|l|L)
IS			(u|U|l|L)*

%{
#include <stdio.h>
#include "y.tab.h"

void count();
%}

%%
"/*"			{ comment(); }

"auto"			{ count(); return(AUTO); }
"break"			{ count(); return(BREAK); }
"case"			{ count(); return(CASE); }
"char"			{ count(); return(CHAR); }
"const"			{ count(); return(CONST); }
"continue"		{ count(); return(CONTINUE); }
"default"		{ count(); return(DEFAULT); }
"do"			{ count(); return(DO); }
"double"		{ count(); return(DOUBLE); }
"else"			{ count(); return(ELSE); }
"enum"			{ count(); return(ENUM); }
"extern"		{ count(); return(EXTERN); }
"float"			{ count(); return(FLOAT); }
"for"			{ count(); return(FOR); }
"goto"			{ count(); return(GOTO); }
"if"			{ count(); return(IF); }
"int"			{ count(); return(INT); }
"long"			{ count(); return(LONG); }
"register"		{ count(); return(REGISTER); }
"return"		{ count(); return(RETURN); }
"short"			{ count(); return(SHORT); }
"signed"		{ count(); return(SIGNED); }
"sizeof"		{ count(); return(SIZEOF); }
"static"		{ count(); return(STATIC); }
"struct"		{ count(); return(STRUCT); }
"switch"		{ count(); return(SWITCH); }
"typedef"		{ count(); return(TYPEDEF); }
"union"			{ count(); return(UNION); }
"unsigned"		{ count(); return(UNSIGNED); }
"void"			{ count(); return(VOID); }
"volatile"		{ count(); return(VOLATILE); }
"while"			{ count(); return(WHILE); }

{L}({L}|{D})*		{ count(); return(check_type()); }

0[xX]{H}+{IS}?		{ count(); return(CONSTANT); }
0[xX]{H}+{IS}?		{ count(); return(CONSTANT); }
0{D}+{IS}?		{ count(); return(CONSTANT); }
0{D}+{IS}?		{ count(); return(CONSTANT); }
{D}+{IS}?		{ count(); return(CONSTANT); }
{D}+{IS}?		{ count(); return(CONSTANT); }
'(\\.|[^\\'])+'		{ count(); return(CONSTANT); }

{D}+{E}{FS}?		{ count(); return(CONSTANT); }
{D}*"."{D}+({E})?{FS}?	{ count(); return(CONSTANT); }
{D}+"."{D}*({E})?{FS}?	{ count(); return(CONSTANT); }

\"(\\.|[^\\"])*\"	{ count(); return(STRING_LITERAL); }

">>="			{ count(); return(RIGHT_ASSIGN); }
"<<="			{ count(); return(LEFT_ASSIGN); }
"+="			{ count(); return(ADD_ASSIGN); }
"-="			{ count(); return(SUB_ASSIGN); }
"*="			{ count(); return(MUL_ASSIGN); }
"/="			{ count(); return(DIV_ASSIGN); }
"%="			{ count(); return(MOD_ASSIGN); }
"&="			{ count(); return(AND_ASSIGN); }
"^="			{ count(); return(XOR_ASSIGN); }
"|="			{ count(); return(OR_ASSIGN); }
">>"			{ count(); return(RIGHT_OP); }
"<<"			{ count(); return(LEFT_OP); }
"++"			{ count(); return(INC_OP); }
"--"			{ count(); return(DEC_OP); }
"->"			{ count(); return(PTR_OP); }
"&&"			{ count(); return(AND_OP); }
"||"			{ count(); return(OR_OP); }
"<="			{ count(); return(LE_OP); }
">="			{ count(); return(GE_OP); }
"=="			{ count(); return(EQ_OP); }
"!="			{ count(); return(NE_OP); }
";"			{ count(); return(';'); }
"{"			{ count(); return('{'); }
"}"			{ count(); return('}'); }
","			{ count(); return(','); }
":"			{ count(); return(':'); }
"="			{ count(); return('='); }
"("			{ count(); return('('); }
")"			{ count(); return(')'); }
"["			{ count(); return('['); }
"]"			{ count(); return(']'); }
"."			{ count(); return('.'); }
"&"			{ count(); return('&'); }
"!"			{ count(); return('!'); }
"~"			{ count(); return('~'); }
"-"			{ count(); return('-'); }
"+"			{ count(); return('+'); }
"*"			{ count(); return('*'); }
"/"			{ count(); return('/'); }
"%"			{ count(); return('%'); }
"<"			{ count(); return('<'); }
">"			{ count(); return('>'); }
"^"			{ count(); return('^'); }
"|"			{ count(); return('|'); }
"?"			{ count(); return('?'); }

[ \t\v\n\f]		{ count(); }
.			{ /* ignore bad characters */ }

%%

yywrap()
{
	return(1);
}

comment()
{
	char c, c1;

loop:
	while ((c = input()) != '*' && c != 0)
		putchar(c);

	if ((c1 = input()) != '/' && c != 0)
	{
		unput(c1);
		goto loop;
	}

	if (c != 0)
		putchar(c1);
}

int column = 0;

void count()
{
	int i;

	for (i = 0; yytext[i] != '\0'; i++)
		if (yytext[i] == '\n')
			column = 0;
		else if (yytext[i] == '\t')
			column += 8 - (column % 8);
		else
			column++;

	ECHO;
}

int check_type()
{
/*
* pseudo code --- this is what it should check
*
*	if (yytext == type_name)
*		return(TYPE_NAME);
*
*	return(IDENTIFIER);
*/

/*
*	it actually will only return IDENTIFIER
*/

	return(IDENTIFIER);
}
*****************


   
p.s. We've been having some trouble with the address our mailer
     deamon is putting on our e-mail. The correct address is
     the one below, if the header says comething different,
     please ignore it.
    
    James Buchanan				james at sparrms.UUCP
    Spar Aerospace Ltd		
    1700 Ormont Drive				(416) 745-9680
    Weston, Ontario, CANADA  M9L 2W7



More information about the Comp.lang.c mailing list