path: root/cpp/cexp.y

/* Parse C expressions for CCCP.
   Copyright (C) 1986 Free Software Foundation.

		       NO WARRANTY

  BECAUSE THIS PROGRAM IS LICENSED FREE OF CHARGE, WE PROVIDE ABSOLUTELY
NO WARRANTY, TO THE EXTENT PERMITTED BY APPLICABLE STATE LAW.  EXCEPT
WHEN OTHERWISE STATED IN WRITING, FREE SOFTWARE FOUNDATION, INC,
RICHARD M. STALLMAN AND/OR OTHER PARTIES PROVIDE THIS PROGRAM "AS IS"
WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY
AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE PROGRAM PROVE
DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR
CORRECTION.

 IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW WILL RICHARD M.
STALLMAN, THE FREE SOFTWARE FOUNDATION, INC., AND/OR ANY OTHER PARTY
WHO MAY MODIFY AND REDISTRIBUTE THIS PROGRAM AS PERMITTED BELOW, BE
LIABLE TO YOU FOR DAMAGES, INCLUDING ANY LOST PROFITS, LOST MONIES, OR
OTHER SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR
DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY THIRD PARTIES OR
A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS) THIS
PROGRAM, EVEN IF YOU HAVE BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES, OR FOR ANY CLAIM BY ANY OTHER PARTY.

		GENERAL PUBLIC LICENSE TO COPY

  1. You may copy and distribute verbatim copies of this source file
as you receive it, in any medium, provided that you conspicuously
and appropriately publish on each copy a valid copyright notice
"Copyright (C) 1986 Free Software Foundation"; and include
following the copyright notice a verbatim copy of the above disclaimer
of warranty and of this License.

  2. You may modify your copy or copies of this source file or
any portion of it, and copy and distribute such modifications under
the terms of Paragraph 1 above, provided that you also do the following:

    a) cause the modified files to carry prominent notices stating
    that you changed the files and the date of any change; and

    b) cause the whole of any work that you distribute or publish,
    that in whole or in part contains or is a derivative of this
    program or any part thereof, to be licensed at no charge to all
    third parties on terms identical to those contained in this
    License Agreement (except that you may choose to grant more extensive
    warranty protection to some or all third parties, at your option).

    c) You may charge a distribution fee for the physical act of
    transferring a copy, and you may at your option offer warranty
    protection in exchange for a fee.

Mere aggregation of another unrelated program with this program (or its
derivative) on a volume of a storage or distribution medium does not bring
the other program under the scope of these terms.

  3. You may copy and distribute this program (or a portion or derivative
of it, under Paragraph 2) in object code or executable form under the terms
of Paragraphs 1 and 2 above provided that you also do one of the following:

    a) accompany it with the complete corresponding machine-readable
    source code, which must be distributed under the terms of
    Paragraphs 1 and 2 above; or,

    b) accompany it with a written offer, valid for at least three
    years, to give any third party free (except for a nominal
    shipping charge) a complete machine-readable copy of the
    corresponding source code, to be distributed under the terms of
    Paragraphs 1 and 2 above; or,

    c) accompany it with the information you received as to where the
    corresponding source code may be obtained.  (This alternative is
    allowed only for noncommercial distribution and only if you
    received the program in object code or executable form alone.)

For an executable file, complete source code means all the source code for
all modules it contains; but, as a special exception, it need not include
source code for modules which are standard libraries that accompany the
operating system on which the executable file runs.

  4. You may not copy, sublicense, distribute or transfer this program
except as expressly provided under this License Agreement.  Any attempt
otherwise to copy, sublicense, distribute or transfer this program is void and
your rights to use the program under this License agreement shall be
automatically terminated.  However, parties who have received computer
software programs from you with this License Agreement will not have
their licenses terminated so long as such parties remain in full compliance.

 In other words, you are welcome to use, share and improve this program.
 You are forbidden to forbid anyone else to use, share and improve
 what you give them.   Help stamp out software-hoarding!

 Adapted from expread.y of GDB by Paul Rubin, July 1986.

/* Parse a C expression from text in a string  */
   
%{
#include <setjmp.h>
/* #define YYDEBUG 1 */

  static int yylex ();
  static yyerror ();
  int expression_value;

  static jmp_buf parse_return_error;

  /* some external tables of character types */
  extern unsigned char is_idstart[], is_idchar[];

%}

%union {
  long lval;
  int voidval;
  char *sval;
}

%type <lval> exp exp1 start
%token <lval> INT CHAR
%token <sval> NAME
%token <lval> ERROR

%left ','
%left OR
%left AND
%left '|'
%left '^'
%left '&'
%left EQUAL NOTEQUAL
%left '<' '>' LEQ GEQ
%left LSH RSH
%left '+' '-'
%left '*' '/' '%'
%right UNARY

%%

start   :	exp1
		{ expression_value = $1; }
	;

/* Expressions, including the comma operator.  */
exp1	:	exp
	|	exp1 ',' exp
			{ $$ = $3; }
	;

/* Expressions, not including the comma operator.  */
exp	:	'-' exp    %prec UNARY
			{ $$ = - $2; }
	|	'!' exp    %prec UNARY
			{ $$ = ! $2; }
	|	'~' exp    %prec UNARY
			{ $$ = ~ $2; }
	|	'(' exp1 ')'
			{ $$ = $2; }
	;

/* Binary operators in order of decreasing precedence.  */
exp	:	exp '*' exp
			{ $$ = $1 * $3; }
	|	exp '/' exp
			{ $$ = $1 / $3; }
	|	exp '%' exp
			{ $$ = $1 % $3; }
	|	exp '+' exp
			{ $$ = $1 + $3; }
	|	exp '-' exp
			{ $$ = $1 - $3; }
	|	exp LSH exp
			{ $$ = $1 << $3; }
	|	exp RSH exp
			{ $$ = $1 >> $3; }
	|	exp EQUAL exp
			{ $$ = ($1 == $3); }
	|	exp NOTEQUAL exp
			{ $$ = ($1 != $3); }
	|	exp LEQ exp
			{ $$ = ($1 <= $3); }
	|	exp GEQ exp
			{ $$ = ($1 >= $3); }
	|	exp '<' exp
			{ $$ = ($1 < $3); }
	|	exp '>' exp
			{ $$ = ($1 > $3); }
	|	exp '&' exp
			{ $$ = ($1 & $3); }
	|	exp '^' exp
			{ $$ = ($1 ^ $3); }
	|	exp '|' exp
			{ $$ = ($1 | $3); }
	|	exp AND exp
			{ $$ = ($1 && $3); }
	|	exp OR exp
			{ $$ = ($1 || $3); }
	|	exp '?' exp ':' exp
			{ $$ = $1 ? $3 : $5; }
	|	INT
			{ $$ = yylval.lval; }
	|	CHAR
			{ $$ = yylval.lval; }
	|	NAME
			{ $$ = 0; }
	;
%%

/* During parsing of a C expression, the pointer to the next character
   is in this variable.  */

static char *lexptr;

/* Take care of parsing a number (anything that starts with a digit).
   Set yylval and return the token type; update lexptr.
   LEN is the number of characters in it.  */

/* maybe needs to actually deal with floating point numbers */

static int
parse_number (olen)
     int olen;
{
  register char *p = lexptr;
  register long n = 0;
  register int c;
  register int base = 10;
  register len = olen;
  char *err_copy;

  extern double atof ();

  for (c = 0; c < len; c++)
    if (p[c] == '.') {
      /* It's a float since it contains a point.  */
      yyerror ("floating point numbers not allowed in #if expressions");
      return ERROR;
      
/* ****************
	 yylval.dval = atof (p);
	 lexptr += len;
	 return FLOAT;
		 ****************  */
    }
  
  if (len >= 3 && (!strncmp (p, "0x", 2) || !strncmp (p, "0X", 2))) {
    p += 2;
    base = 16;
    len -= 2;
  }
  else if (*p == '0')
    base = 8;
  
  while (len-- > 0) {
    c = *p++;
    n *= base;
    if (c >= '0' && c <= '9')
      n += c - '0';
    else {
      if (c >= 'A' && c <= 'Z') c += 'a' - 'A';
      if (base == 16 && c >= 'a' && c <= 'f')
	n += c - 'a' + 10;
      else if (len == 0 && c == 'l')
	;
      else {
	yyerror ("Invalid number in #if expression");
	return ERROR;
      }
    }
  }

  lexptr = p;
  yylval.lval = n;
  return INT;
}

struct token {
  char *operator;
  int token;
};

#define NULL 0

static struct token tokentab2[] = {
  {"&&", AND},
  {"||", OR},
  {"<<", LSH},
  {">>", RSH},
  {"==", EQUAL},
  {"!=", NOTEQUAL},
  {"<=", LEQ},
  {">=", GEQ},
  {NULL, ERROR}
};

/* Read one token, getting characters through lexptr.  */

static int
yylex ()
{
  register int c;
  register int namelen;
  register char *tokstart;
  register struct token *toktab;

 retry:

  tokstart = lexptr;
  c = *tokstart;
  /* See if it is a special token of length 2.  */
  for (toktab = tokentab2; toktab->operator != NULL; toktab++)
    if (c == *toktab->operator && tokstart[1] == toktab->operator[1]) {
      lexptr += 2;
      return toktab->token;
    }

  switch (c) {
  case 0:
    return 0;
    
  case ' ':
  case '\t':
  case '\n':
    lexptr++;
    goto retry;
    
  case '\'':
    lexptr++;
    c = *lexptr++;
    if (c == '\\')
      c = parse_escape (&lexptr);
    yylval.lval = c;
    c = *lexptr++;
    if (c != '\'') {
      yyerror ("Invalid character constant in #if");
      return ERROR;
    }
    
    return CHAR;

  case '/':			/* possible comment */
    if (*lexptr != '*')
      return c;
    for (;;) {
      while (*lexptr != '\0') {
	if (*lexptr++ == '*' && *lexptr == '/') {
	  lexptr++;
	  goto retry;
	}
      }
    }

    /* some of these chars are invalid in constant expressions;
       maybe do something about them later */
  case '+':
  case '-':
  case '*':
  case '%':
  case '|':
  case '&':
  case '^':
  case '~':
  case '!':
  case '@':
  case '<':
  case '>':
  case '(':
  case ')':
  case '[':
  case ']':
  case '.':
  case '?':
  case ':':
  case '=':
  case '{':
  case '}':
  case ',':
    lexptr++;
    return c;
    
  case '"':
    yyerror ("double quoted strings not allowed in #if expressions");
    return ERROR;
  }
  if (c >= '0' && c <= '9') {
    /* It's a number */
    for (namelen = 0;
	 c = tokstart[namelen], is_idchar[c] || c == '.'; 
	 namelen++)
      ;
    return parse_number (namelen);
  }
  
  if (!is_idstart[c]) {
    yyerror ("Invalid token in expression");
    return ERROR;
  }
  
  /* It is a name.  See how long it is.  */
  
  for (namelen = 0; is_idchar[tokstart[namelen]]; namelen++)
    ;
  
  lexptr += namelen;
  return NAME;
}


/* Parse a C escape sequence.  STRING_PTR points to a variable
   containing a pointer to the string to parse.  That pointer
   is updated past the characters we use.  The value of the
   escape sequence is returned.

   A negative value means the sequence \ newline was seen,
   which is supposed to be equivalent to nothing at all.

   If \ is followed by a null character, we return a negative
   value and leave the string pointer pointing at the null character.

   If \ is followed by 000, we return 0 and leave the string pointer
   after the zeros.  A value of 0 does not mean end of string.  */

static int
parse_escape (string_ptr)
     char **string_ptr;
{
  register int c = *(*string_ptr)++;
  switch (c)
    {
    case 'a':
      return '\a';
    case 'b':
      return '\b';
    case 'e':
      return 033;
    case 'f':
      return '\f';
    case 'n':
      return '\n';
    case 'r':
      return '\r';
    case 't':
      return '\t';
    case 'v':
      return '\v';
    case '\n':
      return -2;
    case 0:
      (*string_ptr)--;
      return 0;
    case '^':
      c = *(*string_ptr)++;
      if (c == '\\')
	c = parse_escape (string_ptr);
      if (c == '?')
	return 0177;
      return (c & 0200) | (c & 037);
      
    case '0':
    case '1':
    case '2':
    case '3':
    case '4':
    case '5':
    case '6':
    case '7':
      {
	register int i = c - '0';
	register int count = 0;
	while (++count < 3)
	  {
	    if ((c = *(*string_ptr)++) >= '0' && c <= '7')
	      {
		i *= 8;
		i += c - '0';
	      }
	    else
	      {
		(*string_ptr)--;
		break;
	      }
	  }
	return i;
      }
    default:
      return c;
    }
}

static
yyerror (s)
     char *s;
{
  error (s);
  longjmp (parse_return_error, 1);
}

/* This page contains the entry point to this file.  */

/* Parse STRING as an expression, and complain if this fails
   to use up all of the contents of STRING.  */
int
parse_c_expression (string)
     char *string;
{
  lexptr = string;
  
  if (lexptr == 0 || *lexptr == 0) {
    error ("empty #if expression");
    return 0;			/* don't include the #if group */
  }

  /* if there is some sort of scanning error, just return 0 and assume
     the parsing routine has printed an error message somewhere.
     there is surely a better thing to do than this.     */
  if (setjmp(parse_return_error))
    return 0;

  if (yyparse ())
    return 0;			/* actually this is never reached
				   the way things stand. */
  if (*lexptr)
    error ("Junk after end of expression.");

  return expression_value;	/* set by yyparse() */
}

#ifdef TEST_EXP_READER
/* main program, for testing purposes. */
main()
{
  int n;
  char buf[1024];
  extern int yydebug;
/*
  yydebug = 1;
*/
  initialize_random_junk ();

  for (;;) {
    printf("enter expression: ");
    n = 0;
    while ((buf[n] = getchar()) != '\n')
      n++;
    buf[n] = '\0';
    printf("parser returned %d\n", parse_c_expression(buf));
  }
}

/* table to tell if char can be part of a C identifier. */
char is_idchar[256];
/* table to tell if char can be first char of a c identifier. */
char is_idstart[256];
/* table to tell if c is horizontal space.  isspace() thinks that
   newline is space; this is not a good idea for this program. */
char is_hor_space[256];

/*
 * initialize random junk in the hash table and maybe other places
 */
initialize_random_junk()
{
  register int i;

  /*
   * Set up is_idchar and is_idstart tables.  These should be
   * faster than saying (is_alpha(c) || c == '_'), etc.
   * Must do set up these things before calling any routines tthat
   * refer to them.
   */
  for (i = 'a'; i <= 'z'; i++) {
    ++is_idchar[i - 'a' + 'A'];
    ++is_idchar[i];
    ++is_idstart[i - 'a' + 'A'];
    ++is_idstart[i];
  }
  for (i = '0'; i <= '9'; i++)
    ++is_idchar[i];
  ++is_idchar['_'];
  ++is_idstart['_'];

  /* horizontal space table */
  ++is_hor_space[' '];
  ++is_hor_space['\t'];
}

error (msg)
{
  printf("error: %s\n", msg);
}
#endif