Update copyright.

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

diff --git a/src/parse-gram.y b/src/parse-gram.y
index 8af3e88501c802e8b7f8b0569a9666712eee3ac3..a638cb06b19a6d3082f3af486a297c4373eb0290 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.
 


@@ -15,84 +16,73 @@
 
    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 "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 "output.h"
+#include "quotearg.h"

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

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

 
 

-/* Produce verbose syntax 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)
+#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.
 
 /* Request detailed syntax error messages, and pass them to GRAM_ERROR.

-   FIXME: depends on the undocumented availability of YYLLOC.t */
+   FIXME: depends on the undocumented availability of YYLLOC.  */

 #undef  yyerror
 #define yyerror(Msg) \
         gram_error (&yylloc, Msg)
 #undef  yyerror
 #define yyerror(Msg) \
         gram_error (&yylloc, Msg)

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

 
 

-#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;
-struniq_t current_type = 0;
-symbol_t *current_lhs;
-location_t current_lhs_location;
-assoc_t current_assoc;
-int current_prec = 0;
-braced_code_t current_braced_code = action_braced_code;
+static symbol_class current_class = unknown_sym;
+static uniqstr current_type = 0;
+symbol *current_lhs;
+location current_lhs_location;
+assoc current_assoc;
+static 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
 {

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

   int integer;
   int integer;

-  char *string;
-  assoc_t assoc;
-  struniq_t struniq;
+  char *chars;
+  assoc assoc;
+  uniqstr uniqstr;

 };
 
 /* Define the tokens together with their human representation.  */
 };
 
 /* Define the tokens together with their human representation.  */


@@ -104,10 +94,10 @@ braced_code_t current_braced_code = action_braced_code;
 %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 {...}"

 
 %token PERCENT_LEFT        "%left"
 %token PERCENT_RIGHT       "%right"
 
 %token PERCENT_LEFT        "%left"
 %token PERCENT_RIGHT       "%right"


@@ -123,55 +113,79 @@ braced_code_t current_braced_code = action_braced_code;
 `----------------------*/
 
 %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 EQUAL           "="
 %token SEMICOLON       ";"
 ;
 
 %token TYPE            "type"
 %token EQUAL           "="
 %token SEMICOLON       ";"

-%token COLON           ":"
-%token COMMA           ","

 %token PIPE            "|"
 %token ID              "identifier"
 %token PIPE            "|"
 %token ID              "identifier"

+%token ID_COLON        "identifier:"

 %token PERCENT_PERCENT "%%"
 %token PROLOGUE        "%{...%}"
 %token EPILOGUE        "epilogue"
 %token BRACED_CODE     "{...}"
 
 
 %token PERCENT_PERCENT "%%"
 %token PROLOGUE        "%{...%}"
 %token EPILOGUE        "epilogue"
 %token BRACED_CODE     "{...}"
 
 

-%type <string> STRING string_content
-               BRACED_CODE code_content action
-               PROLOGUE EPILOGUE
-%type <struniq> TYPE
+%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 {...}"
+             "%union {...}"
+             BRACED_CODE action
+             PROLOGUE EPILOGUE
+%type <uniqstr> TYPE
+%printer { fprintf (stderr, "<%s>", $$); } TYPE

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

+%printer { fprintf (stderr, "%d", $$); } INT

 %type <symbol> ID symbol string_as_id
 %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
 %%
 
 input:
   declarations "%%" grammar epilogue.opt
 %type <assoc> precedence_declarator
 %type <list>  symbols.1
 %%
 
 input:
   declarations "%%" grammar epilogue.opt

-    {
-      yycontrol->errcode = 0;
-    }

 ;
 
 
 ;
 
 


@@ -181,38 +195,41 @@ input:
 
 declarations:
   /* Nothing */
 
 declarations:
   /* Nothing */

-| declarations declaration semi_colon.opt
+| declarations declaration

 ;
 
 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; }
-| "%lex-param" code_content "," code_content
-                           {
-                            muscle_pair_list_grow ("lex_param", $2, $4);
-                            scanner_last_string_free ();
-                          }
-| "%locations"                             { locations_flag = 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); }
+| "%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" code_content "," code_content
-                           {
-                            muscle_pair_list_grow ("parse_param", $2, $4);
-                            scanner_last_string_free ();
-                          }
-| "%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:


@@ -222,31 +239,33 @@ grammar_declaration:
     {
       grammar_start_symbol_set ($2, @2);
     }
     {
       grammar_start_symbol_set ($2, @2);
     }

-| "%union" BRACED_CODE
+| "%union {...}"
+    {
+      typed = true;
+      MUSCLE_INSERT_INT ("stype_line", @1.start.line);
+      muscle_insert ("stype", $1);
+    }
+| "%destructor {...}" symbols.1
+    {
+      symbol_list *list;
+      for (list = $2; list; list = list->next)
+       symbol_destructor_set (list->sym, $1, @1);
+      symbol_list_free ($2);
+    }
+| "%printer {...}" symbols.1

     {
     {

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

     }
     }

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

     {
     {

-      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;
+      default_prec = true;

     }
     }

-| "%printer"
-    { current_braced_code = printer_braced_code; }
-  BRACED_CODE symbols.1
+| "%no-default-prec"

     {
     {

-      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;
+      default_prec = false;

     }
 ;
 
     }
 ;
 


@@ -263,7 +282,7 @@ symbol_declaration:
     }
 | "%type" TYPE symbols.1
     {
     }
 | "%type" TYPE symbols.1
     {

-      symbol_list_t *list;
+      symbol_list *list;

       for (list = $3; list; list = list->next)
        symbol_type_set (list->sym, $2, @2);
       symbol_list_free ($3);
       for (list = $3; list; list = list->next)
        symbol_type_set (list->sym, $2, @2);
       symbol_list_free ($3);


@@ -273,7 +292,7 @@ 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)
        {


@@ -338,9 +357,7 @@ symbol_def:
 /* 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

-    {;}

 ;
 
 
 ;
 
 


@@ -354,8 +371,7 @@ 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 ";"


@@ -370,13 +386,13 @@ 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:
   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:


@@ -401,91 +417,126 @@ 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 ($$) - 1] = '\0';
-    };
-
-
-/* A BRACED_CODE used for its contents.  Strip the braces. */
-code_content:
-  BRACED_CODE
-    {
-      $$ = $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 ();
     }
 ;
 

-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 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->struniq);
-      break;
-
-    case BRACED_CODE:
-    case PROLOGUE:
-    case EPILOGUE:
-      fprintf (file, " = {{ %s }}", value->string);
-      break;
-
-    default:
-      fprintf (file, "unknown token type");
-      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);

     }
     }

+
+  scanner_last_string_free ();
+}
+
+static void
+gram_error (location const *loc, char const *msg)
+{
+  complain_at (*loc, "%s", msg);

 }
 
 }
 

-void
-gram_error (location_t *yylloc, const char *msg)
+char const *
+token_name (int type)

 {
 {

-  complain_at (*yylloc, "%s", msg);
+  return yytname[type];

 }
 }