* NEWS, data/c++-skel.m4, data/c++.m4, data/c-skel.m4, data/c.m4,

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

diff --git a/src/parse-gram.y b/src/parse-gram.y
index a6b8f3b14435ffb9870cc3c0c5a16883b7fe8315..4d463a9160876c80ec004e66d43980bea89befdf 100644 (file)
--- a/src/parse-gram.y
+++ b/src/parse-gram.y
@@ -1,5 +1,7 @@
-/* Bison Grammar Parser                             -*- C -*-
-   Copyright (C) 2002 Free Software Foundation, Inc.
+%{/* Bison Grammar Parser                             -*- C -*-
+
+   Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007 Free Software Foundation,
+   Inc.

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


@@ -15,89 +17,98 @@
 
    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"

 
 

-%debug
-%defines
-%locations
-%pure-parser
-// %error-verbose
-%defines
-%name-prefix="gram_"
+#include <strverscmp.h>

 
 

-%{
-#include "system.h"

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

-#include "muscle_tab.h"
+#include "conflicts.h"

 #include "files.h"
 #include "getargs.h"
 #include "files.h"
 #include "getargs.h"

-#include "output.h"
-#include "symlist.h"

 #include "gram.h"
 #include "gram.h"

+#include "muscle_tab.h"
+#include "quotearg.h"

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

-#include "conflicts.h"
+#include "symlist.h"
+#include "scan-gram.h"
+#include "scan-code.h"
+
+#define YYLLOC_DEFAULT(Current, Rhs, N)  (Current) = lloc_default (Rhs, N)
+static YYLTYPE lloc_default (YYLTYPE const *, int);

 
 

-/* Produce verbose parse errors.  */
-#define YYERROR_VERBOSE 1
-#define YYLLOC_DEFAULT(Current, Rhs, N)                        \
-do {                                                   \
-  if (N)                                               \
-  {                                                    \
-    Current.first_column  = Rhs[1].first_column;       \
-    Current.first_line    = Rhs[1].first_line;         \
-    Current.last_column   = Rhs[N].last_column;                \
-    Current.last_line     = Rhs[N].last_line;          \
-  }                                                    \
-  else                                                 \
-  {                                                    \
-    Current = Rhs[0];                                  \
-  }                                                    \
-} while (0)
-
-/* Pass the control structure to YYPARSE and YYLEX. */
-#define YYPARSE_PARAM gram_control
-#define YYLEX_PARAM gram_control
-/* YYPARSE receives GRAM_CONTROL as a void *.  Provide a
-   correctly typed access to it.  */
-#define yycontrol ((gram_control_t *) gram_control)
-
-/* Request detailed parse error messages, and pass them to
-   GRAM_ERROR. */
+#define YY_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) \
 #undef  yyerror
 #define yyerror(Msg) \

-        gram_error (yycontrol, &yylloc, Msg)
-
-#define YYPRINT(File, Type, Value) \
-        yyprint (File, Type, &Value)
-static void yyprint (FILE *file, int type, const yystype *value);
-
-symbol_class current_class = unknown_sym;
-char *current_type = 0;
-symbol_t *current_lhs;
-location_t current_lhs_location;
-associativity current_assoc;
-int current_prec = 0;
-braced_code_t current_braced_code = action_braced_code;
+       gram_error (&yylloc, Msg)
+static void gram_error (location const *, char const *);
+
+static char const *char_name (char);
+
+/** Add a lex-param or a parse-param.
+ *
+ * \param type  \a lex_param or \a parse_param
+ * \param decl  the formal argument
+ * \param loc   the location in the source.
+ */
+static void add_param (char const *type, char *decl, location loc);
+
+
+static symbol_class current_class = unknown_sym;
+static uniqstr current_type = NULL;
+static symbol *current_lhs;
+static location current_lhs_location;
+static int current_prec = 0;
+
+#define YYTYPE_INT16 int_fast16_t
+#define YYTYPE_INT8 int_fast8_t
+#define YYTYPE_UINT16 uint_fast16_t
+#define YYTYPE_UINT8 uint_fast8_t

 %}
 
 %}
 

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

 
 

-/* Only NUMBERS have a value.  */

 %union
 {
 %union
 {

-  symbol_t *symbol;
-  symbol_list_t *list;
+  symbol *symbol;
+  symbol_list *list;

   int integer;
   int integer;

-  char *string;
-  associativity assoc;
+  char const *chars;
+  char *code;
+  assoc assoc;
+  uniqstr uniqstr;
+  unsigned char character;

 };
 
 };
 

-/* Define the tokens together with there human representation. */
-%token GRAM_EOF 0 "end of string"
-%token STRING CHARACTER
-%token INT
+/* Define the tokens together with their human representation.  */
+%token GRAM_EOF 0 "end of file"
+%token STRING     "string"
+%token INT        "integer"

 
 %token PERCENT_TOKEN       "%token"
 %token PERCENT_NTERM       "%nterm"
 
 %token PERCENT_TOKEN       "%token"
 %token PERCENT_NTERM       "%nterm"


@@ -106,62 +117,97 @@ braced_code_t current_braced_code = action_braced_code;
 %token PERCENT_DESTRUCTOR  "%destructor"
 %token PERCENT_PRINTER     "%printer"
 
 %token PERCENT_DESTRUCTOR  "%destructor"
 %token PERCENT_PRINTER     "%printer"
 

-%token PERCENT_UNION       "%union"
-

 %token PERCENT_LEFT        "%left"
 %token PERCENT_RIGHT       "%right"
 %token PERCENT_NONASSOC    "%nonassoc"
 
 %token PERCENT_LEFT        "%left"
 %token PERCENT_RIGHT       "%right"
 %token PERCENT_NONASSOC    "%nonassoc"
 

-%token PERCENT_EXPECT "%expect"
-%token PERCENT_START "%start"
-%token PERCENT_PREC     "%prec"
-%token PERCENT_DPREC    "%dprec"
-%token PERCENT_MERGE    "%merge"
-%token PERCENT_VERBOSE  "%verbose"
-%token PERCENT_ERROR_VERBOSE "%error-verbose"
-
-%token PERCENT_OUTPUT "%output"
-%token PERCENT_FILE_PREFIX "%file-prefix"
-%token PERCENT_NAME_PREFIX "%name-prefix"
-
-%token PERCENT_DEFINE "%define"
-%token PERCENT_PURE_PARSER "%pure-parser"
-%token PERCENT_GLR_PARSER "%glr-parser"
-
-%token PERCENT_DEFINES "%defines"
-
-%token PERCENT_YACC "%yacc"
-
-%token PERCENT_DEBUG "%debug"
-%token PERCENT_LOCATIONS "%locations"
-%token PERCENT_NO_LINES "%no-lines"
-%token PERCENT_SKELETON "%skeleton"
-%token PERCENT_TOKEN_TABLE "%token-table"
-
-%token TYPE
-%token EQUAL "="
-%token SEMICOLON ";"
-%token COLON ":"
-%token PIPE "|"
-%token ID "identifier"
+%token PERCENT_PREC          "%prec"
+%token PERCENT_DPREC         "%dprec"
+%token PERCENT_MERGE         "%merge"
+
+
+/*----------------------.
+| Global Declarations.  |
+`----------------------*/
+
+%token
+  PERCENT_CODE            "%code"
+  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_LANGUAGE        "%language"
+  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_PUSH_PARSER     "%push-parser"
+  PERCENT_PUSH_PULL_PARSER
+                          "%push-pull-parser"
+  PERCENT_REQUIRE        "%require"
+  PERCENT_SKELETON        "%skeleton"
+  PERCENT_START           "%start"
+  PERCENT_TOKEN_TABLE     "%token-table"
+  PERCENT_VERBOSE         "%verbose"
+  PERCENT_YACC            "%yacc"
+;
+
+%token BRACED_CODE     "{...}"
+%token CHAR            "char"
+%token EPILOGUE        "epilogue"
+%token EQUAL           "="
+%token ID              "identifier"
+%token ID_COLON        "identifier:"

 %token PERCENT_PERCENT "%%"
 %token PERCENT_PERCENT "%%"

-%token PROLOGUE EPILOGUE
-%token BRACED_CODE
+%token PIPE            "|"
+%token PROLOGUE        "%{...%}"
+%token SEMICOLON       ";"
+%token TYPE            "type"
+%token TYPE_TAG_ANY    "<*>"
+%token TYPE_TAG_NONE   "<>"
+
+%type <character> CHAR
+%printer { fputs (char_name ($$), stderr); } CHAR
+
+/* braceless is not to be used for rule or symbol actions, as it
+   calls code_props_plain_init.  */
+%type <chars> STRING "%{...%}" EPILOGUE braceless content.opt
+%type <code> "{...}"
+%printer { fputs (quotearg_style (c_quoting_style, $$), stderr); }
+        STRING
+%printer { fprintf (stderr, "{\n%s\n}", $$); }
+        braceless content.opt "{...}" "%{...%}" EPILOGUE
+
+%type <uniqstr> TYPE ID ID_COLON variable
+%printer { fprintf (stderr, "<%s>", $$); } TYPE
+%printer { fputs ($$, stderr); } ID variable
+%printer { fprintf (stderr, "%s:", $$); } ID_COLON

 
 

-%type <string> CHARACTER TYPE STRING string_content
-               BRACED_CODE PROLOGUE EPILOGUE epilogue.opt action

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

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

 %type <assoc> precedence_declarator
 %type <assoc> precedence_declarator

-%type <list>  symbols.1
+%type <list>  symbols.1 generic_symlist generic_symlist_item

 %%
 
 input:
 %%
 
 input:

-  declarations "%%" grammar epilogue.opt
-    {
-      yycontrol->errcode = 0;
-      epilogue_set ($4, @4);
-    }
+  prologue_declarations "%%" grammar epilogue.opt

 ;
 
 
 ;
 
 


@@ -169,30 +215,82 @@ input:
        | Declarations: before the first %%.  |
        `------------------------------------*/
 
        | Declarations: before the first %%.  |
        `------------------------------------*/
 

-declarations:
+prologue_declarations:

   /* Nothing */
   /* Nothing */

-| declarations declaration semi_colon.opt
+| prologue_declarations prologue_declaration

 ;
 
 ;
 

-declaration:
+prologue_declaration:

   grammar_declaration
   grammar_declaration

-| PROLOGUE                                 { prologue_augment ($1, @1); }
-| "%debug"                                 { debug_flag = 1; }
-| "%define" string_content string_content  { muscle_insert ($2, $3); }
-| "%defines"                               { defines_flag = 1; }
-| "%error-verbose"                         { error_verbose = 1; }
-| "%expect" INT                            { expected_conflicts = $2; }
-| "%file-prefix" "=" string_content        { spec_file_prefix = $3; }
-| "%locations"                             { locations_flag = 1; }
-| "%name-prefix" "=" string_content        { spec_name_prefix = $3; }
-| "%no-lines"                              { no_lines_flag = 1; }
-| "%output" "=" string_content             { spec_outfile = $3; }
-| "%pure-parser"                           { pure_parser = 1; }
-| "%glr-parser"                           { glr_parser = 1; }
-| "%skeleton" string_content               { skeleton = $2; }
-| "%token-table"                           { token_table_flag = 1; }
-| "%verbose"                               { report_flag = 1; }
-| "%yacc"                                  { yacc_flag = 1; }
+| "%{...%}"
+    {
+      code_props plain_code;
+      code_props_plain_init (&plain_code, $1, @1);
+      code_props_translate_code (&plain_code);
+      gram_scanner_last_string_free ();
+      muscle_code_grow (union_seen ? "post_prologue" : "pre_prologue",
+                        plain_code.code, @1);
+      code_scanner_last_string_free ();
+    }
+| "%debug"                         { debug_flag = true; }
+| "%define" variable content.opt
+    {
+      char const name_prefix[] = "percent_define(";
+      size_t length = strlen ($2);
+      char *name = xmalloc (sizeof name_prefix + length + 1);
+      strcpy (name, name_prefix);
+      strcpy (name + sizeof name_prefix - 1, $2);
+      strcpy (name + sizeof name_prefix - 1 + length, ")");
+      if (muscle_find_const (name))
+        warn_at (@2, _("%s `%s' redefined"), "%define variable", $2);
+      MUSCLE_INSERT_STRING (uniqstr_new (name), $3);
+      free (name);
+      muscle_grow_user_name_list ("percent_define_user_variables", $2, @2);
+    }
+| "%defines"                       { defines_flag = true; }
+| "%defines" STRING
+    {
+      defines_flag = true;
+      spec_defines_file = xstrdup ($2);
+    }
+| "%error-verbose"                 { error_verbose = true; }
+| "%expect" INT                    { expected_sr_conflicts = $2; }
+| "%expect-rr" INT                { expected_rr_conflicts = $2; }
+| "%file-prefix" STRING            { spec_file_prefix = $2; }
+| "%file-prefix" "=" STRING        { spec_file_prefix = $3; } /* deprecated */
+| "%glr-parser"
+    {
+      nondeterministic_parser = true;
+      glr_parser = true;
+    }
+| "%initial-action" "{...}"
+    {
+      code_props action;
+      code_props_symbol_action_init (&action, $2, @2);
+      code_props_translate_code (&action);
+      gram_scanner_last_string_free ();
+      muscle_code_grow ("initial_action", action.code, @2);
+      code_scanner_last_string_free ();
+    }
+| "%language" STRING           { language_argmatch ($2, 1, &@1); }
+| "%lex-param" "{...}"         { add_param ("lex_param", $2, @2); }
+| "%locations"                  { locations_flag = true; }
+| "%name-prefix" STRING         { spec_name_prefix = $2; }
+| "%name-prefix" "=" STRING     { spec_name_prefix = $3; } /* deprecated */
+| "%no-lines"                   { no_lines_flag = true; }
+| "%nondeterministic-parser"   { nondeterministic_parser = true; }
+| "%output" STRING              { spec_outfile = $2; }
+| "%output" "=" STRING          { spec_outfile = $3; }  /* deprecated */
+| "%parse-param" "{...}"       { add_param ("parse_param", $2, @2); }
+| "%pure-parser"                { pure_parser = true; }
+| "%push-parser"                { push_parser = true; pull_parser = false; }
+| "%push-pull-parser"           { push_parser = true; pull_parser = true; }
+| "%require" STRING             { version_check (&@2, $2); }
+| "%skeleton" STRING            { skeleton_arg ($2, 1, &@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:


@@ -202,34 +300,72 @@ grammar_declaration:
     {
       grammar_start_symbol_set ($2, @2);
     }
     {
       grammar_start_symbol_set ($2, @2);
     }

-| "%union" BRACED_CODE
+| "%destructor" "{...}" generic_symlist

     {
     {

-      typed = 1;
-      MUSCLE_INSERT_INT ("stype_line", @2.first_line);
-      muscle_insert ("stype", $2);
+      symbol_list *list;
+      for (list = $3; list; list = list->next)
+       symbol_list_destructor_set (list, $2, @2);
+      symbol_list_free ($3);

     }
     }

-| "%destructor"
-    { current_braced_code = destructor_braced_code; }
-  BRACED_CODE symbols.1
+| "%printer" "{...}" generic_symlist

     {
     {

-      symbol_list_t *list;
-      for (list = $4; list; list = list->next)
-       symbol_destructor_set (list->sym, $3, @3);
-      symbol_list_free ($4);
-      current_braced_code = action_braced_code;
+      symbol_list *list;
+      for (list = $3; list; list = list->next)
+       symbol_list_printer_set (list, $2, @2);
+      symbol_list_free ($3);

     }
     }

-| "%printer"
-    { current_braced_code = printer_braced_code; }
-  BRACED_CODE symbols.1
+| "%default-prec"
+    {
+      default_prec = true;
+    }
+| "%no-default-prec"
+    {
+      default_prec = false;
+    }
+| "%code" braceless
+    {
+      muscle_code_grow ("percent_code_unqualified", $2, @2);
+      code_scanner_last_string_free ();
+    }
+| "%code" ID braceless
+    {
+      char const name_prefix[] = "percent_code(";
+      size_t length = strlen ($2);
+      char *name = xmalloc (sizeof name_prefix + length + 1);
+      strcpy (name, name_prefix);
+      strcpy (name + sizeof name_prefix - 1, $2);
+      strcpy (name + sizeof name_prefix - 1 + length, ")");
+      muscle_code_grow (uniqstr_new (name), $3, @3);
+      free (name);
+      code_scanner_last_string_free ();
+      muscle_grow_user_name_list ("percent_code_user_qualifiers", $2, @2);
+    }
+;
+
+
+/*----------*
+ | %union.  |
+ *----------*/
+
+%token PERCENT_UNION "%union";
+
+union_name:
+  /* Nothing. */ {}
+| ID             { muscle_code_grow ("union_name", $1, @1); }
+;
+
+grammar_declaration:
+  "%union" union_name braceless

     {
     {

-      symbol_list_t *list;
-      for (list = $4; list; list = list->next)
-       symbol_printer_set (list->sym, $3, list->location);
-      symbol_list_free ($4);
-      current_braced_code = action_braced_code;
+      union_seen = true;
+      muscle_code_grow ("stype", $3, @3);
+      code_scanner_last_string_free ();

     }
 ;
 
     }
 ;
 

+
+
+

 symbol_declaration:
   "%nterm" { current_class = nterm_sym; } symbol_defs.1
     {
 symbol_declaration:
   "%nterm" { current_class = nterm_sym; } symbol_defs.1
     {


@@ -243,9 +379,10 @@ symbol_declaration:
     }
 | "%type" TYPE symbols.1
     {
     }
 | "%type" TYPE symbols.1
     {

-      symbol_list_t *list;
+      symbol_list *list;
+      tag_seen = true;

       for (list = $3; list; list = list->next)
       for (list = $3; list; list = list->next)

-       symbol_type_set (list->sym, $2, @2);
+       symbol_type_set (list->content.sym, $2, @2);

       symbol_list_free ($3);
     }
 ;
       symbol_list_free ($3);
     }
 ;


@@ -253,12 +390,12 @@ symbol_declaration:
 precedence_declaration:
   precedence_declarator type.opt symbols.1
     {
 precedence_declaration:
   precedence_declarator type.opt symbols.1
     {

-      symbol_list_t *list;
+      symbol_list *list;

       ++current_prec;
       for (list = $3; list; list = list->next)
        {
       ++current_prec;
       for (list = $3; list; list = list->next)
        {

-         symbol_type_set (list->sym, current_type, @2);
-         symbol_precedence_set (list->sym, current_prec, $1, @1);
+         symbol_type_set (list->content.sym, current_type, @2);
+         symbol_precedence_set (list->content.sym, current_prec, $1, @1);

        }
       symbol_list_free ($3);
       current_type = NULL;
        }
       symbol_list_free ($3);
       current_type = NULL;


@@ -272,15 +409,28 @@ precedence_declarator:
 ;
 
 type.opt:
 ;
 
 type.opt:

-  /* Nothing. */ { current_type = NULL;}
-| TYPE           { current_type = $1; }
+  /* Nothing. */ { current_type = NULL; }
+| TYPE           { current_type = $1; tag_seen = true; }

 ;
 
 ;
 

-/* One or more nonterminals to be %typed. */
-
+/* One or more symbols to be %typed. */

 symbols.1:
 symbols.1:

-  symbol            { $$ = symbol_list_new ($1, @1); }
-| symbols.1 symbol  { $$ = symbol_list_prepend ($1, $2, @2); }
+  symbol
+    { $$ = symbol_list_sym_new ($1, @1); }
+| symbols.1 symbol
+    { $$ = symbol_list_prepend ($1, symbol_list_sym_new ($2, @2)); }
+;
+
+generic_symlist:
+  generic_symlist_item { $$ = $1; }
+| generic_symlist generic_symlist_item { $$ = symbol_list_prepend ($1, $2); }
+;
+
+generic_symlist_item:
+  symbol            { $$ = symbol_list_sym_new ($1, @1); }
+| TYPE              { $$ = symbol_list_type_new ($1, @1); }
+| "<*>"             { $$ = symbol_list_default_tagged_new (@1); }
+| "<>"             { $$ = symbol_list_default_tagless_new (@1); }

 ;
 
 /* One token definition.  */
 ;
 
 /* One token definition.  */


@@ -288,39 +438,38 @@ symbol_def:
   TYPE
      {
        current_type = $1;
   TYPE
      {
        current_type = $1;

+       tag_seen = true;

      }
      }

-| ID
+| id

      {
      {

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

        symbol_type_set ($1, current_type, @1);
      }
        symbol_type_set ($1, current_type, @1);
      }

-| ID INT
+| 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);
     }
       symbol_type_set ($1, current_type, @1);
       symbol_user_token_number_set ($1, $2, @2);
     }

-| ID string_as_id
+| 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_type_set ($1, current_type, @1);

-      symbol_make_alias ($1, $2);
+      symbol_make_alias ($1, $2, @$);

     }
     }

-| ID INT string_as_id
+| 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_type_set ($1, current_type, @1);
       symbol_user_token_number_set ($1, $2, @2);

-      symbol_make_alias ($1, $3);
+      symbol_make_alias ($1, $3, @$);

     }
 ;
 
 /* One or more symbol definitions. */
 symbol_defs.1:
   symbol_def
     }
 ;
 
 /* One or more symbol definitions. */
 symbol_defs.1:
   symbol_def

-    {;}

 | symbol_defs.1 symbol_def
 | symbol_defs.1 symbol_def

-    {;}

 ;
 
 
 ;
 
 


@@ -334,15 +483,10 @@ grammar:
 ;
 
 /* As a Bison extension, one can use the grammar declarations in the
 ;
 
 /* As a Bison extension, one can use the grammar declarations in the

-   body of the grammar.  But to remain LALR(1), they must be ended
-   with a semi-colon.  */
+   body of the 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;


@@ -350,21 +494,21 @@ rules_or_grammar_declaration:
 ;
 
 rules:
 ;
 
 rules:

-  ID ":" { current_lhs = $1; current_lhs_location = @1; } rhses.1 ";"
-    {;}
+  id_colon { current_lhs = $1; current_lhs_location = @1; } rhses.1

 ;
 
 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.  */
 ;
 
 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
+| rhs "{...}"

     { grammar_current_rule_action_append ($2, @2); }
 | rhs "%prec" symbol
     { grammar_current_rule_prec_set ($3, @3); }
     { grammar_current_rule_action_append ($2, @2); }
 | rhs "%prec" symbol
     { grammar_current_rule_prec_set ($3, @3); }


@@ -374,93 +518,213 @@ rhs:
     { grammar_current_rule_merge_set ($3, @3); }
 ;
 
     { grammar_current_rule_merge_set ($3, @3); }
 ;
 

-symbol:
-  ID              { $$ = $1; }
-| string_as_id    { $$ = $1; }
-| CHARACTER       { $$ = symbol_get ($1, @1); }
+
+/*----------------------------*
+ | variable and content.opt.  |
+ *---------------------------*/
+
+variable:
+  ID
+  | STRING { $$ = uniqstr_new ($1); } /* deprecated and not M4-friendly */
+  ;
+
+/* Some content or "1" by default. */
+content.opt:
+  /* Nothing. */
+    {
+      static char one[] = "1";
+      $$ = one;
+    }
+| STRING

 ;
 
 ;
 

-action:
-  BRACED_CODE
-   { $$ = $1; }
+
+/*-------------*
+ | braceless.  |
+ *-------------*/
+
+braceless:
+  "{...}"
+    {
+      code_props plain_code;
+      $1[strlen ($1) - 1] = '\n';
+      code_props_plain_init (&plain_code, $1+1, @1);
+      code_props_translate_code (&plain_code);
+      gram_scanner_last_string_free ();
+      $$ = plain_code.code;
+    }

 ;
 
 ;
 

-/* A string used as an ID: we have to keep the quotes. */
-string_as_id:
-  STRING
+
+/*---------------*
+ | Identifiers.  |
+ *---------------*/
+
+/* Identifiers are returned as uniqstr values by the scanner.
+   Depending on their use, we may need to make them genuine symbols.  */
+
+id:
+  ID
+    { $$ = symbol_from_uniqstr ($1, @1); }
+| CHAR

     {
     {

-      $$ = symbol_get ($1, @1);
-      symbol_class_set ($$, token_sym, @1);
+      $$ = symbol_get (char_name ($1), @1);
+      symbol_class_set ($$, token_sym, @1, false);
+      symbol_user_token_number_set ($$, $1, @1);

     }
 ;
 
     }
 ;
 

-/* A string used for its contents.  Strip the quotes. */
-string_content:
+id_colon:
+  ID_COLON { $$ = symbol_from_uniqstr ($1, @1); }
+;
+
+
+symbol:
+  id
+| string_as_id
+;
+
+/* A string used as an ID: quote it.  */
+string_as_id:

   STRING
     {
   STRING
     {

-      $$ = $1 + 1;
-      $$[strlen ($$) - 1] = '\0';
-    };
-
+      $$ = symbol_get (quotearg_style (c_quoting_style, $1), @1);
+      symbol_class_set ($$,
+                        current_class == unknown_sym
+                        ? token_sym : current_class, @1, false);
+    }
+;

 
 epilogue.opt:
   /* Nothing.  */
 
 epilogue.opt:
   /* Nothing.  */

-    {
-      $$ = xstrdup ("");
-    }

 | "%%" EPILOGUE
     {
 | "%%" EPILOGUE
     {

-      $$ = $2;
+      code_props plain_code;
+      code_props_plain_init (&plain_code, $2, @2);
+      code_props_translate_code (&plain_code);
+      gram_scanner_last_string_free ();
+      muscle_code_grow ("epilogue", plain_code.code, @2);
+      code_scanner_last_string_free ();

     }
 ;
 
     }
 ;
 

-semi_colon.opt:
-  /* Nothing.  */
-| ";"
-;

 %%
 %%

-/*------------------------------------------------------------------.
-| When debugging the parser, display tokens' locations and values.  |
-`------------------------------------------------------------------*/
+
+
+/* Return the location of the left-hand side of a rule whose
+   right-hand side is RHS[1] ... RHS[N].  Ignore empty nonterminals in
+   the right-hand side, and return an empty location equal to the end
+   boundary of RHS[0] if the right-hand side is empty.  */
+
+static YYLTYPE
+lloc_default (YYLTYPE const *rhs, int n)
+{
+  int i;
+  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))
+      {
+       loc.start = rhs[i].start;
+       break;
+      }
+
+  return loc;
+}
+
+
+/* Add a lex-param or a parse-param (depending on TYPE) with
+   declaration DECL and location LOC.  */

 
 static void
 
 static void

-yyprint (FILE *file,
-         int type, const yystype *value)
+add_param (char const *type, char *decl, location loc)

 {
 {

-  fputc (' ', file);
-  switch (type)
+  static char const alphanum[26 + 26 + 1 + 10] =
+    "abcdefghijklmnopqrstuvwxyz"
+    "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+    "_"
+    "0123456789";
+  char const *name_start = NULL;
+  char *p;
+
+  /* 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;
+
+  /* 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"));
+  else

     {
     {

-    case CHARACTER:
-      fprintf (file, " = '%s'", value->string);
-      break;
-
-    case ID:
-      fprintf (file, " = %s", value->symbol->tag);
-      break;
-
-    case INT:
-      fprintf (file, " = %d", value->integer);
-      break;
-
-    case STRING:
-      fprintf (file, " = \"%s\"", value->string);
-      break;
-
-    case TYPE:
-      fprintf (file, " = <%s>", value->string);
-      break;
-
-    case BRACED_CODE:
-    case PROLOGUE:
-    case EPILOGUE:
-      fprintf (file, " = {{ %s }}", value->string);
-      break;
+      char *name;
+      size_t name_len;
+
+      for (name_len = 1;
+          memchr (alphanum, name_start[name_len], sizeof alphanum);
+          name_len++)
+       continue;
+
+      name = xmalloc (name_len + 1);
+      memcpy (name, name_start, name_len);
+      name[name_len] = '\0';
+      muscle_pair_list_grow (type, decl, name);
+      free (name);

     }
     }

+
+  gram_scanner_last_string_free ();

 }
 
 }
 

-void
-gram_error (gram_control_t *control ATTRIBUTE_UNUSED,
-           location_t *yylloc, const char *msg)
+
+static void
+version_check (location const *loc, char const *version)
+{
+  if (strverscmp (version, PACKAGE_VERSION) > 0)
+    {
+      complain_at (*loc, "require bison %s, but have %s",
+                  version, PACKAGE_VERSION);
+      exit (63);
+    }
+}
+
+static void
+gram_error (location const *loc, char const *msg)

 {
 {

-  complain_at (*yylloc, "%s", msg);
+  complain_at (*loc, "%s", msg);
+}
+
+char const *
+token_name (int type)
+{
+  return yytname[YYTRANSLATE (type)];
+}
+
+static char const *
+char_name (char c)
+{
+  if (c == '\'')
+    return "'\\''";
+  else
+    {
+      char buf[4];
+      buf[0] = '\''; buf[1] = c; buf[2] = '\''; buf[3] = '\0';
+      return quotearg_style (escape_quoting_style, buf);
+    }

 }
 }