ocamlyacc with friendly dollar-symbols

[Thierry Bravier <thierry.bravier@dassault-aviation.fr>]

Dear ocamlers,

Here is a small extension to ocamlyacc.

It comes as a short patch to file reader.c in the standard
distribution of ocamlyacc.

This extension provides two features:

1/ # line "file.mly" generated in file.ml

   This is useful when the ML code written in the header or trailer
   or in the semantic actions cannot compile: the error message now
   reports the problem in the source not in the generated code.

2/ In semantic actions, dollar-number values are still there ( ie $1 );
   they are now completed by dollar-symbol values ( ie $expr ).

   This convenience makes code clearer and more robust relatively to
   grammar evolutions.

   The syntax is easy:
      `$symbol' refers to `symbol' in the right hand side of the rule
         provided there is only one occurence of `symbol' which is
         most often true and is checked.
      `$symbol#i' (where i is a positive integer literal) refers to the
         i-th occurrence of `symbol' in the rule.
      `$i' (where i is a positive integer literal) still refers to the
         i-th symbol of the rule.

   BUG: Error messages should be adapted to the new
`$symbol#i'/`$symbol'
   feature.

   SEE ALSO: This feature is provided in SML/NJ .grm syntax (equivalent
   of .mly files) and can also be found in camlp4 (where semantic values
   can even be named with free identifiers).

   EXAMPLE:
   Here is the modified calc parser from the ocaml user manual:
   /* File parser.mly */
   %token <int> INT
   %token PLUS MINUS TIMES DIV
   %token LPAREN RPAREN
   %token EOL
   %left PLUS MINUS        /* lowest precedence */
   %left TIMES DIV         /* medium precedence */
   %nonassoc UMINUS        /* highest precedence */
   %start main             /* the entry point */
   %type <int> main
   %%
   main:
       expr EOL                { $expr }
   ;
   expr:
       INT                     { $INT }
     | LPAREN expr RPAREN      { $expr }
     | expr PLUS expr          { $expr#1 + $expr#2 }
     | expr MINUS expr         { $expr#1 - $expr#2 }
     | expr TIMES expr         { $expr#1 * $expr#2 }
     | expr DIV expr           { $expr#1 / $expr#2 }
     | MINUS expr %prec UMINUS { - $expr }
   ;

Hope you find it useful.

Thierry Bravier              Dassault Aviation - DGT / DPR / DESA
78, Quai Marcel Dassault       F-92214 Saint-Cloud Cedex - France
Telephone : (33) 01 47 11 53 07   Telecopie : (33) 01 47 11 52 83
E-Mail :              mailto:thierry.bravier@dassault-aviation.fr

Here is a diff output of the modified reader.c file from version
/* $Id: reader.c,v 1.13 1997/11/13 09:57:52 xleroy Exp $ */
in the 1.06 distribution.

By default both features are enabled, they can be switched off by
compiling with -DNO_SOURCE_LOCATION and/or -DNO_DOLLAR_IDENT.

% diff -C 1 reader.distrib.c reader.c
*** reader.distrib.c    Thu Nov 13 10:57:52 1997
--- reader.c    Fri Dec 12 14:31:43 1997
***************
*** 49,51 ****
--- 49,55 ----
  
+ #ifndef NO_SOURCE_LOCATION
+ char line_format[] = "\n# %d \"%s\"\n";
+ #else
  char line_format[] = "(* Line %d, file %s *)\n";
+ #endif
  
***************
*** 322,323 ****
--- 326,330 ----
  
+ #ifndef NO_SOURCE_LOCATION
+     fprintf(f, line_format, lineno+1, input_file_name);
+ #endif
      if (*cptr == '\n')
***************
*** 1187,1189 ****
--- 1194,1276 ----
  
+ #ifndef NO_DOLLAR_IDENT
+ int
+ get_ident(int n)
+ {
+     register int c = *cptr;
+     char *t_cptr = cptr;
  
+     if (IS_IDENT(c))
+     {
+       cinc = 0;
+       for (;;) {
+           if (IS_IDENT(c)) {
+             cachec(c);
+           } else
+             break;
+           c = *++cptr;
+       }
+       cachec(NUL);
+       {
+         int sharp;
+         char *ident = MALLOC(strlen (cache) + 1);
+         strcpy(ident, cache);
+         if (cptr[0] == '#' && isdigit(cptr[1])) {
+           register int c;
+           ++cptr;
+           sharp = 0;
+           for (c = *cptr; isdigit(c); c = *++cptr)
+             sharp = 10*sharp + (c - '0');
+         } else {
+           sharp = 0;
+         }
+         {
+           int i;
+           bucket *item = 0;
+           if (sharp) {
+             int s = 0;
+             for (i = 1; i <= n; i++) {
+               item = pitem[nitems + i - n - 1];
+               if (!strcmp (ident, item->name)) {
+                 if (++s == sharp) {
+                               /* found sharp-th ident occurrence */
+                   break;
+                 }
+               }
+             }
+           } else {
+             int found = 0;
+             for (i = 1; i <= n; i++) {
+               item = pitem[nitems + i - n - 1];
+               if (!strcmp (ident, item->name)) {
+                 if (found) {
+                               /* more than one name matches ident:
error */
+                   found = 0;
+                   break;
+                 } else {
+                               /* first time a name matches ident */
+                   found = i;
+                 }
+               }
+             }
+             if (found) {
+               i = found;
+               item = pitem[nitems + i - n - 1];
+             } else {
+               i = 0;
+             }
+           }
+             if (i <= 0 || i > n)
+               unknown_rhs(i);
+             if (item->class == TERM && !item->tag)
+               illegal_token_ref(i, item->name);
+           FREE (ident);
+           return i;
+         }
+       }
+     }
+     syntax_error(lineno, line, t_cptr);
+     /*NOTREACHED*/
+     return 0;
+ }
+ #endif
  void copy_action(void)
***************
*** 1190,1191 ****
--- 1277,1281 ----
  {
+ #ifndef NO_SOURCE_LOCATION
+     int start_column = cptr - line + 1;
+ #endif
      register int c;
***************
*** 1227,1228 ****
--- 1317,1327 ----
      fprintf(f, "\tObj.repr((");
+ #ifndef NO_SOURCE_LOCATION
+     fprintf(f, line_format, lineno+1, input_file_name);
+     {
+       int i;
+       for (i = 0; i < start_column; i++) {
+       fprintf(f, " ");
+       }
+     }
+ #endif
  
***************
*** 1248,1249 ****
--- 1347,1356 ----
        }
+ #ifndef NO_DOLLAR_IDENT
+       if (isalnum(cptr[1]))
+       {
+           ++cptr;
+             fprintf(f, "dollar__%d", get_ident (n));
+           goto loop;
+       }
+ #endif
      }
-- 
Thierry Bravier                     Dassault Aviation - DGT / DPR / DESA
78, Quai Marcel Dassault              F-92214 Saint-Cloud Cedex - France
Telephone : (33) 01 47 11 53 07          Telecopie : (33) 01 47 11 52 83
E-Mail :                     mailto:thierry.bravier@dassault-aviation.fr