* src/scan-gram.l (gram_get_lineno, gram_get_in, gram_get_out):

[bison.git] / src / parse-gram.y

diff --git a/src/parse-gram.y b/src/parse-gram.y
index 2224c85f0e1600ddfefa8cecb043476133592f9f..735a3fd730dad60424699b16a94281b487881683 100644 (file)
--- a/src/parse-gram.y
+++ b/src/parse-gram.y
@@ -1,5 +1,6 @@
-/* Bison Grammar Parser                             -*- C -*-
-   Copyright (C) 2002 Free Software Foundation, Inc.
+%{/* Bison Grammar Parser                             -*- C -*-
+
+   Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc.

 
    This file is part of Bison, the GNU Compiler Compiler.
 
 
    This file is part of Bison, the GNU Compiler Compiler.
 


@@ -15,20 +16,10 @@
 
    You should have received a copy of the GNU General Public License
    along with this program; if not, write to the Free Software
 
    You should have received a copy of the GNU General Public License
    along with this program; if not, write to the Free Software

-   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
-   02111-1307  USA
+   Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+   02110-1301  USA

 */
 
 */
 

-
-%debug
-%defines
-%locations
-%pure-parser
-// %error-verbose
-%defines
-%name-prefix="gram_"
-
-%{

 #include "system.h"
 
 #include "complain.h"
 #include "system.h"
 
 #include "complain.h"


@@ -38,15 +29,16 @@
 #include "gram.h"
 #include "muscle_tab.h"
 #include "output.h"
 #include "gram.h"
 #include "muscle_tab.h"
 #include "output.h"

+#include "quotearg.h"

 #include "reader.h"
 #include "symlist.h"
 
 #include "reader.h"
 #include "symlist.h"
 

-/* Produce verbose syntax errors.  */
-#define YYERROR_VERBOSE 1
-

 #define YYLLOC_DEFAULT(Current, Rhs, N)  (Current) = lloc_default (Rhs, N)
 static YYLTYPE lloc_default (YYLTYPE const *, int);
 
 #define YYLLOC_DEFAULT(Current, Rhs, N)  (Current) = lloc_default (Rhs, N)
 static YYLTYPE lloc_default (YYLTYPE const *, int);
 

+#define YY_LOCATION_PRINT(File, Loc) \
+          location_print (File, Loc)
+

 /* Request detailed syntax error messages, and pass them to GRAM_ERROR.
    FIXME: depends on the undocumented availability of YYLLOC.  */
 #undef  yyerror
 /* Request detailed syntax error messages, and pass them to GRAM_ERROR.
    FIXME: depends on the undocumented availability of YYLLOC.  */
 #undef  yyerror


@@ -54,10 +46,6 @@ static YYLTYPE lloc_default (YYLTYPE const *, int);
         gram_error (&yylloc, Msg)
 static void gram_error (location const *, char const *);
 
         gram_error (&yylloc, Msg)
 static void gram_error (location const *, char const *);
 

-#define YYPRINT(File, Type, Value) \
-       print_token_value (File, Type, &Value)
-static void print_token_value (FILE *, int, YYSTYPE const *);
-

 static void add_param (char const *, char *, location);
 
 symbol_class current_class = unknown_sym;
 static void add_param (char const *, char *, location);
 
 symbol_class current_class = unknown_sym;


@@ -68,6 +56,23 @@ assoc current_assoc;
 int current_prec = 0;
 %}
 
 int current_prec = 0;
 %}
 

+%debug
+%verbose
+%defines
+%locations
+%pure-parser
+%error-verbose
+%defines
+%name-prefix="gram_"
+
+%initial-action
+{
+  /* Bison's grammar can initial empty locations, hence a default
+     location is needed. */
+  @$.start.file   = @$.end.file   = current_file;
+  @$.start.line   = @$.end.line   = 1;
+  @$.start.column = @$.end.column = 0;
+}

 
 /* Only NUMBERS have a value.  */
 %union
 
 /* Only NUMBERS have a value.  */
 %union


@@ -108,25 +113,31 @@ int current_prec = 0;
 `----------------------*/
 
 %token
 `----------------------*/
 
 %token

-  PERCENT_DEBUG         "%debug"
-  PERCENT_DEFINE        "%define"
-  PERCENT_DEFINES       "%defines"
-  PERCENT_ERROR_VERBOSE "%error-verbose"
-  PERCENT_EXPECT        "%expect"
-  PERCENT_FILE_PREFIX   "%file-prefix"
-  PERCENT_GLR_PARSER    "%glr-parser"
-  PERCENT_LEX_PARAM     "%lex-param {...}"
-  PERCENT_LOCATIONS     "%locations"
-  PERCENT_NAME_PREFIX   "%name-prefix"
-  PERCENT_NO_LINES      "%no-lines"
-  PERCENT_OUTPUT        "%output"
-  PERCENT_PARSE_PARAM   "%parse-param {...}"
-  PERCENT_PURE_PARSER   "%pure-parser"
-  PERCENT_SKELETON      "%skeleton"
-  PERCENT_START         "%start"
-  PERCENT_TOKEN_TABLE   "%token-table"
-  PERCENT_VERBOSE       "%verbose"
-  PERCENT_YACC          "%yacc"
+  PERCENT_DEBUG           "%debug"
+  PERCENT_DEFAULT_PREC    "%default-prec"
+  PERCENT_DEFINE          "%define"
+  PERCENT_DEFINES         "%defines"
+  PERCENT_ERROR_VERBOSE   "%error-verbose"
+  PERCENT_EXPECT          "%expect"
+  PERCENT_EXPECT_RR      "%expect-rr"
+  PERCENT_FILE_PREFIX     "%file-prefix"
+  PERCENT_GLR_PARSER      "%glr-parser"
+  PERCENT_INITIAL_ACTION  "%initial-action {...}"
+  PERCENT_LEX_PARAM       "%lex-param {...}"
+  PERCENT_LOCATIONS       "%locations"
+  PERCENT_NAME_PREFIX     "%name-prefix"
+  PERCENT_NO_DEFAULT_PREC "%no-default-prec"
+  PERCENT_NO_LINES        "%no-lines"
+  PERCENT_NONDETERMINISTIC_PARSER
+                          "%nondeterministic-parser"
+  PERCENT_OUTPUT          "%output"
+  PERCENT_PARSE_PARAM     "%parse-param {...}"
+  PERCENT_PURE_PARSER     "%pure-parser"
+  PERCENT_SKELETON        "%skeleton"
+  PERCENT_START           "%start"
+  PERCENT_TOKEN_TABLE     "%token-table"
+  PERCENT_VERBOSE         "%verbose"
+  PERCENT_YACC            "%yacc"

 ;
 
 %token TYPE            "type"
 ;
 
 %token TYPE            "type"


@@ -143,6 +154,18 @@ int current_prec = 0;
 
 %type <chars> STRING string_content
              "%destructor {...}"
 
 %type <chars> STRING string_content
              "%destructor {...}"

+             "%initial-action {...}"
+             "%lex-param {...}"
+             "%parse-param {...}"
+             "%printer {...}"
+             "%union {...}"
+             BRACED_CODE action
+             PROLOGUE EPILOGUE
+%printer { fprintf (stderr, "\"%s\"", $$); }
+              STRING string_content
+%printer { fprintf (stderr, "{\n%s\n}", $$); }
+             "%destructor {...}"
+             "%initial-action {...}"

              "%lex-param {...}"
              "%parse-param {...}"
              "%printer {...}"
              "%lex-param {...}"
              "%parse-param {...}"
              "%printer {...}"


@@ -150,8 +173,13 @@ int current_prec = 0;
              BRACED_CODE action
              PROLOGUE EPILOGUE
 %type <uniqstr> TYPE
              BRACED_CODE action
              PROLOGUE EPILOGUE
 %type <uniqstr> TYPE

+%printer { fprintf (stderr, "<%s>", $$); } TYPE

 %type <integer> INT
 %type <integer> INT

-%type <symbol> ID ID_COLON symbol string_as_id
+%printer { fprintf (stderr, "%d", $$); } INT
+%type <symbol> ID symbol string_as_id
+%printer { fprintf (stderr, "%s", $$->tag); } ID symbol string_as_id
+%type <symbol> ID_COLON
+%printer { fprintf (stderr, "%s:", $$->tag); } ID_COLON

 %type <assoc> precedence_declarator
 %type <list>  symbols.1
 %%
 %type <assoc> precedence_declarator
 %type <list>  symbols.1
 %%


@@ -173,25 +201,35 @@ declarations:
 declaration:
   grammar_declaration
 | PROLOGUE                                 { prologue_augment ($1, @1); }
 declaration:
   grammar_declaration
 | PROLOGUE                                 { prologue_augment ($1, @1); }

-| "%debug"                                 { debug_flag = 1; }
+| "%debug"                                 { debug_flag = true; }

 | "%define" string_content string_content  { muscle_insert ($2, $3); }
 | "%define" string_content string_content  { muscle_insert ($2, $3); }

-| "%defines"                               { defines_flag = 1; }
-| "%error-verbose"                         { error_verbose = 1; }
-| "%expect" INT                            { expected_conflicts = $2; }
+| "%defines"                               { defines_flag = true; }
+| "%error-verbose"                         { error_verbose = true; }
+| "%expect" INT                            { expected_sr_conflicts = $2; }
+| "%expect-rr" INT                        { expected_rr_conflicts = $2; }

 | "%file-prefix" "=" string_content        { spec_file_prefix = $3; }
 | "%file-prefix" "=" string_content        { spec_file_prefix = $3; }

-| "%glr-parser"                           { glr_parser = 1; }
+| "%glr-parser"
+  {
+    nondeterministic_parser = true;
+    glr_parser = true;
+  }
+| "%initial-action {...}"
+  {
+    muscle_code_grow ("initial_action", $1, @1);
+  }

 | "%lex-param {...}"                      { add_param ("lex_param", $1, @1); }
 | "%lex-param {...}"                      { add_param ("lex_param", $1, @1); }

-| "%locations"                             { locations_flag = 1; }
+| "%locations"                             { locations_flag = true; }

 | "%name-prefix" "=" string_content        { spec_name_prefix = $3; }
 | "%name-prefix" "=" string_content        { spec_name_prefix = $3; }

-| "%no-lines"                              { no_lines_flag = 1; }
+| "%no-lines"                              { no_lines_flag = true; }
+| "%nondeterministic-parser"              { nondeterministic_parser = true; }

 | "%output" "=" string_content             { spec_outfile = $3; }
 | "%output" "=" string_content             { spec_outfile = $3; }

-| "%parse-param {...}"                  { add_param ("parse_param", $1, @1); }
-| "%pure-parser"                           { pure_parser = 1; }
+| "%parse-param {...}"                    { add_param ("parse_param", $1, @1); }
+| "%pure-parser"                           { pure_parser = true; }

 | "%skeleton" string_content               { skeleton = $2; }
 | "%skeleton" string_content               { skeleton = $2; }

-| "%token-table"                           { token_table_flag = 1; }
-| "%verbose"                               { report_flag = 1; }
-| "%yacc"                                  { yacc_flag = 1; }
-| ";"
+| "%token-table"                           { token_table_flag = true; }
+| "%verbose"                               { report_flag = report_states; }
+| "%yacc"                                  { yacc_flag = true; }
+| /*FIXME: Err?  What is this horror doing here? */ ";"

 ;
 
 grammar_declaration:
 ;
 
 grammar_declaration:


@@ -203,7 +241,7 @@ grammar_declaration:
     }
 | "%union {...}"
     {
     }
 | "%union {...}"
     {

-      typed = 1;
+      typed = true;

       MUSCLE_INSERT_INT ("stype_line", @1.start.line);
       muscle_insert ("stype", $1);
     }
       MUSCLE_INSERT_INT ("stype_line", @1.start.line);
       muscle_insert ("stype", $1);
     }


@@ -221,6 +259,14 @@ grammar_declaration:
        symbol_printer_set (list->sym, $1, list->location);
       symbol_list_free ($2);
     }
        symbol_printer_set (list->sym, $1, list->location);
       symbol_list_free ($2);
     }

+| "%default-prec"
+    {
+      default_prec = true;
+    }
+| "%no-default-prec"
+    {
+      default_prec = false;
+    }

 ;
 
 symbol_declaration:
 ;
 
 symbol_declaration:


@@ -328,7 +374,7 @@ grammar:
    body of the grammar.  */
 rules_or_grammar_declaration:
   rules
    body of the grammar.  */
 rules_or_grammar_declaration:
   rules

-| grammar_declaration
+| grammar_declaration ";"

     {
       if (yacc_flag)
        complain_at (@$, _("POSIX forbids declarations in the grammar"));
     {
       if (yacc_flag)
        complain_at (@$, _("POSIX forbids declarations in the grammar"));


@@ -337,7 +383,6 @@ rules_or_grammar_declaration:
     {
       yyerrok;
     }
     {
       yyerrok;
     }

-| ";"

 ;
 
 rules:
 ;
 
 rules:


@@ -347,6 +392,7 @@ rules:
 rhses.1:
   rhs                { grammar_rule_end (@1); }
 | rhses.1 "|" rhs    { grammar_rule_end (@3); }
 rhses.1:
   rhs                { grammar_rule_end (@1); }
 | rhses.1 "|" rhs    { grammar_rule_end (@3); }

+| rhses.1 ";"

 ;
 
 rhs:
 ;
 
 rhs:


@@ -371,32 +417,30 @@ symbol:
 
 action:
   BRACED_CODE
 
 action:
   BRACED_CODE

-   { $$ = $1; }
+    { $$ = $1; }

 ;
 
 ;
 

-/* A string used as an ID: we have to keep the quotes. */
+/* A string used as an ID: quote it.  */

 string_as_id:
   STRING
     {
 string_as_id:
   STRING
     {

-      $$ = symbol_get ($1, @1);
+      $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1);

       symbol_class_set ($$, token_sym, @1);
     }
 ;
 
       symbol_class_set ($$, token_sym, @1);
     }
 ;
 

-/* A string used for its contents.  Strip the quotes. */
+/* A string used for its contents.  Don't quote it.  */

 string_content:
   STRING
 string_content:
   STRING

-    {
-      $$ = $1 + 1;
-      $$[strlen ($$) - 1] = '\0';
-    };
+    { $$ = $1; }
+;

 
 
 epilogue.opt:
   /* Nothing.  */
 | "%%" EPILOGUE
     {
 
 
 epilogue.opt:
   /* Nothing.  */
 | "%%" EPILOGUE
     {

-      epilogue_augment ($2, @2);
+      muscle_code_grow ("epilogue", $2, @2);

       scanner_last_string_free ();
     }
 ;
       scanner_last_string_free ();
     }
 ;


@@ -413,24 +457,24 @@ static YYLTYPE
 lloc_default (YYLTYPE const *rhs, int n)
 {
   int i;
 lloc_default (YYLTYPE const *rhs, int n)
 {
   int i;

-  int j;
-  YYLTYPE r;
-  r.start = r.end = rhs[n].end;
+  YYLTYPE loc;
+
+  /* SGI MIPSpro 7.4.1m miscompiles "loc.start = loc.end = rhs[n].end;".
+     The bug is fixed in 7.4.2m, but play it safe for now.  */
+  loc.start = rhs[n].end;
+  loc.end = rhs[n].end;

 
 

+  /* Ignore empty nonterminals the start of the the right-hand side.
+     Do not bother to ignore them at the end of the right-hand side,
+     since empty nonterminals have the same end as their predecessors.  */

   for (i = 1; i <= n; i++)
     if (! equal_boundaries (rhs[i].start, rhs[i].end))
       {
   for (i = 1; i <= n; i++)
     if (! equal_boundaries (rhs[i].start, rhs[i].end))
       {

-       r.start = rhs[i].start;
-
-       for (j = n; i < j; j--)
-         if (! equal_boundaries (rhs[j].start, rhs[j].end))
-           break;
-       r.end = rhs[j].end;
-
+       loc.start = rhs[i].start;

        break;
       }
 
        break;
       }
 

-  return r;
+  return loc;

 }
 
 
 }
 
 


@@ -440,22 +484,28 @@ lloc_default (YYLTYPE const *rhs, int n)
 static void
 add_param (char const *type, char *decl, location loc)
 {
 static void
 add_param (char const *type, char *decl, location loc)
 {

-  static char const alphanum[] =
-    "0123456789"
+  static char const alphanum[26 + 26 + 1 + 10] =

     "abcdefghijklmnopqrstuvwxyz"
     "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
     "abcdefghijklmnopqrstuvwxyz"
     "ABCDEFGHIJKLMNOPQRSTUVWXYZ"

-    "_";
-  char const *alpha = alphanum + 10;
+    "_"
+    "0123456789";

   char const *name_start = NULL;
   char *p;
 
   char const *name_start = NULL;
   char *p;
 

-  for (p = decl; *p; p++)
-    if ((p == decl || ! strchr (alphanum, p[-1])) && strchr (alpha, p[0]))
+  /* Stop on last actual character.  */
+  for (p = decl; p[1]; p++)
+    if ((p == decl
+        || ! memchr (alphanum, p[-1], sizeof alphanum))
+       && memchr (alphanum, p[0], sizeof alphanum - 10))

       name_start = p;
 
       name_start = p;
 

-  /* Strip the surrounding '{' and '}'.  */
-  decl++;
-  p[-1] = '\0';
+  /* Strip the surrounding '{' and '}', and any blanks just inside
+     the braces.  */
+  while (*--p == ' ' || *p == '\t')
+    continue;
+  p[1] = '\0';
+  while (*++decl == ' ' || *decl == '\t')
+    continue;

 
   if (! name_start)
     complain_at (loc, _("missing identifier in parameter declaration"));
 
   if (! name_start)
     complain_at (loc, _("missing identifier in parameter declaration"));


@@ -465,7 +515,7 @@ add_param (char const *type, char *decl, location loc)
       size_t name_len;
 
       for (name_len = 1;
       size_t name_len;
 
       for (name_len = 1;

-          name_start[name_len] && strchr (alphanum, name_start[name_len]);
+          memchr (alphanum, name_start[name_len], sizeof alphanum);

           name_len++)
        continue;
 
           name_len++)
        continue;
 


@@ -479,49 +529,6 @@ add_param (char const *type, char *decl, location loc)
   scanner_last_string_free ();
 }
 
   scanner_last_string_free ();
 }
 

-/*----------------------------------------------------.
-| When debugging the parser, display tokens' values.  |
-`----------------------------------------------------*/
-
-static void
-print_token_value (FILE *file, int type, YYSTYPE const *value)
-{
-  fputc (' ', file);
-  switch (type)
-    {
-    case ID:
-      fprintf (file, " = %s", value->symbol->tag);
-      break;
-
-    case INT:
-      fprintf (file, " = %d", value->integer);
-      break;
-
-    case STRING:
-      fprintf (file, " = \"%s\"", value->chars);
-      break;
-
-    case TYPE:
-      fprintf (file, " = <%s>", value->uniqstr);
-      break;
-
-    case BRACED_CODE:
-    case PERCENT_DESTRUCTOR:
-    case PERCENT_LEX_PARAM:
-    case PERCENT_PARSE_PARAM:
-    case PERCENT_PRINTER:
-    case PERCENT_UNION:
-    case PROLOGUE:
-    case EPILOGUE:
-      fprintf (file, " = {{ %s }}", value->chars);
-      break;
-
-    default:
-      fprintf (file, "unknown token type");
-      break;
-    }
-}
-

 static void
 gram_error (location const *loc, char const *msg)
 {
 static void
 gram_error (location const *loc, char const *msg)
 {