For associating token numbers with token names for "yacc.c", don't use

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

diff --git a/src/parse-gram.y b/src/parse-gram.y
index 6016cea74810e21eaed1bf63a2a1aa1f5ea48831..a0c708b3e416edfebb9c85a6e5009d37a3e1c7bf 100644 (file)
--- a/src/parse-gram.y
+++ b/src/parse-gram.y
@@ -1,6 +1,6 @@
 %{/* Bison Grammar Parser                             -*- C -*-
 
 %{/* Bison Grammar Parser                             -*- C -*-
 

-   Copyright (C) 2002, 2003, 2004 Free Software Foundation, Inc.
+   Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc.

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


@@ -16,10 +16,11 @@
 
    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

 */
 
 */
 

+#include <config.h>

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


@@ -28,38 +29,52 @@
 #include "getargs.h"
 #include "gram.h"
 #include "muscle_tab.h"
 #include "getargs.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"

+#include "scan-gram.h"
+#include "scan-code.h"
+#include "strverscmp.h"

 
 #define YYLLOC_DEFAULT(Current, Rhs, N)  (Current) = lloc_default (Rhs, N)
 static YYLTYPE lloc_default (YYLTYPE const *, int);
 
 #define YY_LOCATION_PRINT(File, Loc) \
 
 #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)
+         location_print (File, Loc)
+
+static void version_check (location const *loc, char const *version);

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

-        gram_error (&yylloc, Msg)
+       gram_error (&yylloc, Msg)

 static void gram_error (location const *, char const *);
 
 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);
 
 static void add_param (char const *, char *, location);
 

-symbol_class current_class = unknown_sym;
-uniqstr current_type = 0;
-symbol *current_lhs;
-location current_lhs_location;
-assoc current_assoc;
-int current_prec = 0;
+static symbol_class current_class = unknown_sym;
+static uniqstr current_type = 0;
+static symbol *current_lhs;
+static location current_lhs_location;
+static int current_prec = 0;
+
+#ifdef UINT_FAST8_MAX
+# define YYTYPE_UINT8 uint_fast8_t
+#endif
+#ifdef INT_FAST8_MAX
+# define YYTYPE_INT8 int_fast8_t
+#endif
+#ifdef UINT_FAST16_MAX
+# define YYTYPE_UINT16 uint_fast16_t
+#endif
+#ifdef INT_FAST16_MAX
+# define YYTYPE_INT16 int_fast16_t
+#endif

 %}
 
 %debug
 %}
 
 %debug

+%verbose

 %defines
 %locations
 %pure-parser
 %defines
 %locations
 %pure-parser


@@ -71,9 +86,8 @@ int current_prec = 0;
 {
   /* Bison's grammar can initial empty locations, hence a default
      location is needed. */
 {
   /* 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;
+  boundary_set (&@$.start, current_file, 1, 0);
+  boundary_set (&@$.end, current_file, 1, 0);

 }
 
 /* Only NUMBERS have a value.  */
 }
 
 /* Only NUMBERS have a value.  */


@@ -96,8 +110,8 @@ int current_prec = 0;
 %token PERCENT_NTERM       "%nterm"
 
 %token PERCENT_TYPE        "%type"
 %token PERCENT_NTERM       "%nterm"
 
 %token PERCENT_TYPE        "%type"

-%token PERCENT_DESTRUCTOR  "%destructor {...}"
-%token PERCENT_PRINTER     "%printer {...}"
+%token PERCENT_DESTRUCTOR  "%destructor"
+%token PERCENT_PRINTER     "%printer"

 
 %token PERCENT_UNION       "%union {...}"
 
 
 %token PERCENT_UNION       "%union {...}"
 


@@ -124,17 +138,18 @@ int current_prec = 0;
   PERCENT_EXPECT_RR      "%expect-rr"
   PERCENT_FILE_PREFIX     "%file-prefix"
   PERCENT_GLR_PARSER      "%glr-parser"
   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_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
   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"
+                         "%nondeterministic-parser"

   PERCENT_OUTPUT          "%output"
   PERCENT_OUTPUT          "%output"

-  PERCENT_PARSE_PARAM     "%parse-param {...}"
+  PERCENT_PARSE_PARAM     "%parse-param"

   PERCENT_PURE_PARSER     "%pure-parser"
   PERCENT_PURE_PARSER     "%pure-parser"

+  PERCENT_REQUIRE        "%require"

   PERCENT_SKELETON        "%skeleton"
   PERCENT_START           "%start"
   PERCENT_TOKEN_TABLE     "%token-table"
   PERCENT_SKELETON        "%skeleton"
   PERCENT_START           "%start"
   PERCENT_TOKEN_TABLE     "%token-table"


@@ -153,19 +168,24 @@ int current_prec = 0;
 %token EPILOGUE        "epilogue"
 %token BRACED_CODE     "{...}"
 
 %token EPILOGUE        "epilogue"
 %token BRACED_CODE     "{...}"
 

-

 %type <chars> STRING string_content
 %type <chars> STRING string_content

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

              "%union {...}"
              "%union {...}"

-             BRACED_CODE action

              PROLOGUE EPILOGUE
 %type <uniqstr> TYPE
              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
 %%


@@ -186,31 +206,38 @@ declarations:
 
 declaration:
   grammar_declaration
 
 declaration:
   grammar_declaration

-| PROLOGUE                                 { prologue_augment ($1, @1); }
+| PROLOGUE                         { prologue_augment (translate_code ($1, @1),
+                                                      @1); }

 | "%debug"                                 { debug_flag = true; }
 | "%debug"                                 { debug_flag = true; }

+| "%define" string_content
+    {
+      static char one[] = "1";
+      muscle_insert ($2, one);
+    }

 | "%define" string_content string_content  { muscle_insert ($2, $3); }
 | "%defines"                               { defines_flag = true; }
 | "%error-verbose"                         { error_verbose = true; }
 | "%expect" INT                            { expected_sr_conflicts = $2; }
 | "%define" string_content string_content  { muscle_insert ($2, $3); }
 | "%defines"                               { defines_flag = true; }
 | "%error-verbose"                         { error_verbose = true; }
 | "%expect" INT                            { expected_sr_conflicts = $2; }

-| "%expect-rr" INT                        { expected_rr_conflicts = $2; }
+| "%expect-rr" INT                        { expected_rr_conflicts = $2; }

 | "%file-prefix" "=" string_content        { spec_file_prefix = $3; }
 | "%glr-parser"
 | "%file-prefix" "=" string_content        { spec_file_prefix = $3; }
 | "%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); }
+    {
+      nondeterministic_parser = true;
+      glr_parser = true;
+    }
+| "%initial-action" "{...}"
+    {
+      muscle_code_grow ("initial_action", translate_symbol_action ($2, @2), @2);
+    }
+| "%lex-param" "{...}"                    { add_param ("lex_param", $2, @2); }

 | "%locations"                             { locations_flag = true; }
 | "%name-prefix" "=" string_content        { spec_name_prefix = $3; }
 | "%no-lines"                              { no_lines_flag = true; }
 | "%locations"                             { locations_flag = true; }
 | "%name-prefix" "=" string_content        { spec_name_prefix = $3; }
 | "%no-lines"                              { no_lines_flag = true; }

-| "%nondeterministic-parser"              { nondeterministic_parser = 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); }
+| "%parse-param" "{...}"                  { add_param ("parse_param", $2, @2); }

 | "%pure-parser"                           { pure_parser = true; }
 | "%pure-parser"                           { pure_parser = true; }

+| "%require" string_content                { version_check (&@2, $2); }

 | "%skeleton" string_content               { skeleton = $2; }
 | "%token-table"                           { token_table_flag = true; }
 | "%verbose"                               { report_flag = report_states; }
 | "%skeleton" string_content               { skeleton = $2; }
 | "%token-table"                           { token_table_flag = true; }
 | "%verbose"                               { report_flag = report_states; }


@@ -227,23 +254,35 @@ grammar_declaration:
     }
 | "%union {...}"
     {
     }
 | "%union {...}"
     {

+      char const *body = $1;
+
+      if (typed)
+       {
+         /* Concatenate the union bodies, turning the first one's
+            trailing '}' into '\n', and omitting the second one's '{'.  */
+         char *code = muscle_find ("stype");
+         code[strlen (code) - 1] = '\n';
+         body++;
+       }
+

       typed = true;
       typed = true;

-      MUSCLE_INSERT_INT ("stype_line", @1.start.line);
-      muscle_insert ("stype", $1);
+      muscle_code_grow ("stype", body, @1);

     }
     }

-| "%destructor {...}" symbols.1
+| "%destructor" "{...}" symbols.1

     {
       symbol_list *list;
     {
       symbol_list *list;

-      for (list = $2; list; list = list->next)
-       symbol_destructor_set (list->sym, $1, @1);
-      symbol_list_free ($2);
+      const char *action = translate_symbol_action ($2, @2);
+      for (list = $3; list; list = list->next)
+       symbol_destructor_set (list->sym, action, @2);
+      symbol_list_free ($3);

     }
     }

-| "%printer {...}" symbols.1
+| "%printer" "{...}" symbols.1

     {
       symbol_list *list;
     {
       symbol_list *list;

-      for (list = $2; list; list = list->next)
-       symbol_printer_set (list->sym, $1, list->location);
-      symbol_list_free ($2);
+      const char *action = translate_symbol_action ($2, @2);
+      for (list = $3; list; list = list->next)
+       symbol_printer_set (list->sym, action, @2);
+      symbol_list_free ($3);

     }
 | "%default-prec"
     {
     }
 | "%default-prec"
     {


@@ -302,7 +341,6 @@ type.opt:
 ;
 
 /* One or more nonterminals to be %typed. */
 ;
 
 /* One or more nonterminals to be %typed. */

-

 symbols.1:
   symbol            { $$ = symbol_list_new ($1, @1); }
 | symbols.1 symbol  { $$ = symbol_list_prepend ($1, $2, @2); }
 symbols.1:
   symbol            { $$ = symbol_list_new ($1, @1); }
 | symbols.1 symbol  { $$ = symbol_list_prepend ($1, $2, @2); }


@@ -316,24 +354,24 @@ symbol_def:
      }
 | ID
      {
      }
 | ID
      {

-       symbol_class_set ($1, current_class, @1);
+       symbol_class_set ($1, current_class, @1, true);

        symbol_type_set ($1, current_type, @1);
      }
 | ID INT
     {
        symbol_type_set ($1, current_type, @1);
      }
 | ID INT
     {

-      symbol_class_set ($1, current_class, @1);
+      symbol_class_set ($1, current_class, @1, true);

       symbol_type_set ($1, current_type, @1);
       symbol_user_token_number_set ($1, $2, @2);
     }
 | ID string_as_id
     {
       symbol_type_set ($1, current_type, @1);
       symbol_user_token_number_set ($1, $2, @2);
     }
 | ID string_as_id
     {

-      symbol_class_set ($1, current_class, @1);
+      symbol_class_set ($1, current_class, @1, true);

       symbol_type_set ($1, current_type, @1);
       symbol_make_alias ($1, $2, @$);
     }
 | ID INT string_as_id
     {
       symbol_type_set ($1, current_type, @1);
       symbol_make_alias ($1, $2, @$);
     }
 | ID INT string_as_id
     {

-      symbol_class_set ($1, current_class, @1);
+      symbol_class_set ($1, current_class, @1, true);

       symbol_type_set ($1, current_type, @1);
       symbol_user_token_number_set ($1, $2, @2);
       symbol_make_alias ($1, $3, @$);
       symbol_type_set ($1, current_type, @1);
       symbol_user_token_number_set ($1, $2, @2);
       symbol_make_alias ($1, $3, @$);


@@ -361,10 +399,6 @@ grammar:
 rules_or_grammar_declaration:
   rules
 | grammar_declaration ";"
 rules_or_grammar_declaration:
   rules
 | grammar_declaration ";"

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

 | error ";"
     {
       yyerrok;
 | error ";"
     {
       yyerrok;


@@ -376,18 +410,19 @@ rules:
 ;
 
 rhses.1:
 ;
 
 rhses.1:

-  rhs                { grammar_rule_end (@1); }
-| rhses.1 "|" rhs    { grammar_rule_end (@3); }
+  rhs                { grammar_current_rule_end (@1); }
+| rhses.1 "|" rhs    { grammar_current_rule_end (@3); }

 | rhses.1 ";"
 ;
 
 rhs:
   /* Nothing.  */
 | rhses.1 ";"
 ;
 
 rhs:
   /* Nothing.  */

-    { grammar_rule_begin (current_lhs, current_lhs_location); }
+    { grammar_current_rule_begin (current_lhs, current_lhs_location); }

 | rhs symbol
     { grammar_current_rule_symbol_append ($2, @2); }
 | rhs symbol
     { grammar_current_rule_symbol_append ($2, @2); }

-| rhs action
-    { grammar_current_rule_action_append ($2, @2); }
+| rhs "{...}"
+    { grammar_current_rule_action_append (gram_last_string,
+                                         gram_last_braced_code_loc); }

 | rhs "%prec" symbol
     { grammar_current_rule_prec_set ($3, @3); }
 | rhs "%dprec" INT
 | rhs "%prec" symbol
     { grammar_current_rule_prec_set ($3, @3); }
 | rhs "%dprec" INT


@@ -401,35 +436,28 @@ symbol:
 | string_as_id    { $$ = $1; }
 ;
 
 | string_as_id    { $$ = $1; }
 ;
 

-action:
-  BRACED_CODE
-   { $$ = $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
     {

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

     }
 ;
 
     }
 ;
 

-/* 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
     {

-      muscle_code_grow ("epilogue", $2, @2);
-      scanner_last_string_free ();
+      muscle_code_grow ("epilogue", translate_code ($2, @2), @2);
+      gram_scanner_last_string_free ();

     }
 ;
 
     }
 ;
 


@@ -514,49 +542,17 @@ add_param (char const *type, char *decl, location loc)
       free (name);
     }
 
       free (name);
     }
 

-  scanner_last_string_free ();
+  gram_scanner_last_string_free ();

 }
 
 }
 

-/*----------------------------------------------------.
-| When debugging the parser, display tokens' values.  |
-`----------------------------------------------------*/
-

 static void
 static void

-print_token_value (FILE *file, int type, YYSTYPE const *value)
+version_check (location const *loc, char const *version)

 {
 {

-  fputc (' ', file);
-  switch (type)
+  if (strverscmp (version, PACKAGE_VERSION) > 0)

     {
     {

-    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;
+      complain_at (*loc, "require bison %s, but have %s",
+                  version, PACKAGE_VERSION);
+      exit (63);

     }
 }
 
     }
 }
 


@@ -569,5 +565,5 @@ gram_error (location const *loc, char const *msg)
 char const *
 token_name (int type)
 {
 char const *
 token_name (int type)
 {

-  return yytname[type];
+  return yytname[YYTRANSLATE (type)];

 }
 }