/* YACC parser for C expressions, for GDB.
- Copyright (C) 1986, 1989, 1990, 1991 Free Software Foundation, Inc.
+ Copyright (C) 1986, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997,
+ 1998, 1999, 2000, 2003, 2004, 2006, 2007 Free Software Foundation, Inc.
This file is part of GDB.
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., 675 Mass Ave, Cambridge, MA 02139, USA. */
+Foundation, Inc., 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA. */
/* Parse a C expression from text in a string,
and return the result as a struct expression pointer.
See expression.h for the details of the format.
What is important here is that it can be built up sequentially
during the process of parsing; the lower levels of the tree always
- come first in the result. */
+ come first in the result.
+
+ Note that malloc's and realloc's in this file are transformed to
+ xmalloc and xrealloc respectively by the same sed command in the
+ makefile that remaps any other malloc/realloc inserted by the parser
+ generator. Doing this with #defines and trying to control the interaction
+ with include files (<malloc.h> and <stdlib.h> for example) just became
+ too messy, particularly when such includes can be inserted at random
+ times by the parser generator. */
%{
-#include <stdio.h>
-#include <string.h>
#include "defs.h"
-#include "param.h"
-#include "symtab.h"
-#include "frame.h"
+#include "gdb_string.h"
+#include <ctype.h>
#include "expression.h"
-#include "parser-defs.h"
#include "value.h"
+#include "parser-defs.h"
#include "language.h"
-
-/* These MUST be included in any grammar file!!!!
- Please choose unique names! */
+#include "c-lang.h"
+#include "bfd.h" /* Required by objfiles.h. */
+#include "symfile.h" /* Required by objfiles.h. */
+#include "objfiles.h" /* For have_full_symbols and have_partial_symbols */
+#include "charset.h"
+#include "block.h"
+#include "cp-support.h"
+
+/* Remap normal yacc parser interface names (yyparse, yylex, yyerror, etc),
+ as well as gratuitiously global symbol names, so we can have multiple
+ yacc generated parsers in gdb. Note that these are only the variables
+ produced by yacc. If other parser generators (bison, byacc, etc) produce
+ additional global names that conflict at link time, then those parser
+ generators need to be fixed instead of adding those names to this list. */
+
+#define yymaxdepth c_maxdepth
#define yyparse c_parse
#define yylex c_lex
#define yyerror c_error
#define yyps c_ps
#define yypv c_pv
#define yys c_s
+#define yy_yys c_yys
#define yystate c_state
#define yytmp c_tmp
#define yyv c_v
+#define yy_yyv c_yyv
#define yyval c_val
#define yylloc c_lloc
+#define yyreds c_reds /* With YYDEBUG defined */
+#define yytoks c_toks /* With YYDEBUG defined */
+#define yyname c_name /* With YYDEBUG defined */
+#define yyrule c_rule /* With YYDEBUG defined */
+#define yylhs c_yylhs
+#define yylen c_yylen
+#define yydefred c_yydefred
+#define yydgoto c_yydgoto
+#define yysindex c_yysindex
+#define yyrindex c_yyrindex
+#define yygindex c_yygindex
+#define yytable c_yytable
+#define yycheck c_yycheck
+
+#ifndef YYDEBUG
+#define YYDEBUG 1 /* Default to yydebug support */
+#endif
-/* Forward decls */
-void yyerror ();
-static int parse_number ();
-int yyparse ();
+#define YYFPRINTF parser_fprintf
-/* #define YYDEBUG 1 */
+int yyparse (void);
+
+static int yylex (void);
+
+void yyerror (char *);
%}
%union
{
LONGEST lval;
- unsigned LONGEST ulval;
- double dval;
+ struct {
+ LONGEST val;
+ struct type *type;
+ } typed_val_int;
+ struct {
+ DOUBLEST dval;
+ struct type *type;
+ } typed_val_float;
struct symbol *sym;
struct type *tval;
struct stoken sval;
int *ivec;
}
-%type <voidval> exp exp1 type_exp start variable
-%type <tval> type typebase
+%{
+/* YYSTYPE gets defined by %union */
+static int parse_number (char *, int, int, YYSTYPE *);
+%}
+
+%type <voidval> exp exp1 type_exp start variable qualified_name lcurly
+%type <lval> rcurly
+%type <tval> type typebase qualified_type
%type <tvec> nonempty_typelist
/* %type <bval> block */
%type <tval> ptype
%type <lval> array_mod
-%token <lval> INT CHAR
-%token <ulval> UINT
-%token <dval> FLOAT
+%token <typed_val_int> INT
+%token <typed_val_float> FLOAT
/* Both NAME and TYPENAME tokens represent symbols in the input,
and both convey their data as strings.
/* A NAME_OR_INT is a symbol which is not known in the symbol table,
but which would parse as a valid number in the current input radix.
E.g. "c" when input_radix==16. Depending on the parse, it will be
- turned into a name or into a number. NAME_OR_UINT ditto. */
+ turned into a name or into a number. */
-%token <ssym> NAME_OR_INT NAME_OR_UINT
+%token <ssym> NAME_OR_INT
-%token STRUCT UNION ENUM SIZEOF UNSIGNED COLONCOLON
+%token STRUCT CLASS UNION ENUM SIZEOF UNSIGNED COLONCOLON
+%token TEMPLATE
%token ERROR
/* Special type cases, put in to allow the parser to distinguish different
legal basetypes. */
-%token SIGNED LONG SHORT INT_KEYWORD
-
-%token <lval> LAST REGNAME
+%token SIGNED_KEYWORD LONG SHORT INT_KEYWORD CONST_KEYWORD VOLATILE_KEYWORD DOUBLE_KEYWORD
-%token <ivar> VARIABLE
+%token <voidval> VARIABLE
%token <opcode> ASSIGN_MODIFY
/* C++ */
-%token THIS
+%token TRUEKEYWORD
+%token FALSEKEYWORD
+
%left ','
%left ABOVE_COMMA
%right '=' ASSIGN_MODIFY
%right '?'
-%left OR
-%left AND
+%left OROR
+%left ANDAND
%left '|'
%left '^'
%left '&'
%right UNARY INCREMENT DECREMENT
%right ARROW '.' '[' '('
%token <ssym> BLOCKNAME
+%token <bval> FILENAME
%type <bval> block
%left COLONCOLON
+
\f
%%
/* Expressions, not including the comma operator. */
exp : '*' exp %prec UNARY
{ write_exp_elt_opcode (UNOP_IND); }
+ ;
exp : '&' exp %prec UNARY
{ write_exp_elt_opcode (UNOP_ADDR); }
+ ;
exp : '-' exp %prec UNARY
{ write_exp_elt_opcode (UNOP_NEG); }
;
+exp : '+' exp %prec UNARY
+ { write_exp_elt_opcode (UNOP_PLUS); }
+ ;
+
exp : '!' exp %prec UNARY
- { write_exp_elt_opcode (UNOP_ZEROP); }
+ { write_exp_elt_opcode (UNOP_LOGICAL_NOT); }
;
exp : '~' exp %prec UNARY
- { write_exp_elt_opcode (UNOP_LOGNOT); }
+ { write_exp_elt_opcode (UNOP_COMPLEMENT); }
;
exp : INCREMENT exp %prec UNARY
write_exp_elt_opcode (STRUCTOP_PTR); }
;
+exp : exp ARROW qualified_name
+ { /* exp->type::name becomes exp->*(&type::name) */
+ /* Note: this doesn't work if name is a
+ static member! FIXME */
+ write_exp_elt_opcode (UNOP_ADDR);
+ write_exp_elt_opcode (STRUCTOP_MPTR); }
+ ;
+
exp : exp ARROW '*' exp
{ write_exp_elt_opcode (STRUCTOP_MPTR); }
;
write_exp_elt_opcode (STRUCTOP_STRUCT); }
;
+exp : exp '.' qualified_name
+ { /* exp.type::name becomes exp.*(&type::name) */
+ /* Note: this doesn't work if name is a
+ static member! FIXME */
+ write_exp_elt_opcode (UNOP_ADDR);
+ write_exp_elt_opcode (STRUCTOP_MEMBER); }
+ ;
+
exp : exp '.' '*' exp
{ write_exp_elt_opcode (STRUCTOP_MEMBER); }
;
write_exp_elt_opcode (OP_FUNCALL); }
;
+lcurly : '{'
+ { start_arglist (); }
+ ;
+
arglist :
;
{ arglist_len++; }
;
-exp : '{' type '}' exp %prec UNARY
+rcurly : '}'
+ { $$ = end_arglist () - 1; }
+ ;
+exp : lcurly arglist rcurly %prec ARROW
+ { write_exp_elt_opcode (OP_ARRAY);
+ write_exp_elt_longcst ((LONGEST) 0);
+ write_exp_elt_longcst ((LONGEST) $3);
+ write_exp_elt_opcode (OP_ARRAY); }
+ ;
+
+exp : lcurly type rcurly exp %prec UNARY
{ write_exp_elt_opcode (UNOP_MEMVAL);
write_exp_elt_type ($2);
write_exp_elt_opcode (UNOP_MEMVAL); }
;
exp : exp '&' exp
- { write_exp_elt_opcode (BINOP_LOGAND); }
+ { write_exp_elt_opcode (BINOP_BITWISE_AND); }
;
exp : exp '^' exp
- { write_exp_elt_opcode (BINOP_LOGXOR); }
+ { write_exp_elt_opcode (BINOP_BITWISE_XOR); }
;
exp : exp '|' exp
- { write_exp_elt_opcode (BINOP_LOGIOR); }
+ { write_exp_elt_opcode (BINOP_BITWISE_IOR); }
;
-exp : exp AND exp
- { write_exp_elt_opcode (BINOP_AND); }
+exp : exp ANDAND exp
+ { write_exp_elt_opcode (BINOP_LOGICAL_AND); }
;
-exp : exp OR exp
- { write_exp_elt_opcode (BINOP_OR); }
+exp : exp OROR exp
+ { write_exp_elt_opcode (BINOP_LOGICAL_OR); }
;
exp : exp '?' exp ':' exp %prec '?'
exp : INT
{ write_exp_elt_opcode (OP_LONG);
- if ($1 == (int) $1 || $1 == (unsigned int) $1)
- write_exp_elt_type (builtin_type_int);
- else
- write_exp_elt_type (BUILTIN_TYPE_LONGEST);
- write_exp_elt_longcst ((LONGEST) $1);
+ write_exp_elt_type ($1.type);
+ write_exp_elt_longcst ((LONGEST)($1.val));
write_exp_elt_opcode (OP_LONG); }
;
{ YYSTYPE val;
parse_number ($1.stoken.ptr, $1.stoken.length, 0, &val);
write_exp_elt_opcode (OP_LONG);
- if (val.lval == (int) val.lval ||
- val.lval == (unsigned int) val.lval)
- write_exp_elt_type (builtin_type_int);
- else
- write_exp_elt_type (BUILTIN_TYPE_LONGEST);
- write_exp_elt_longcst (val.lval);
- write_exp_elt_opcode (OP_LONG); }
- ;
-
-exp : UINT
- {
- write_exp_elt_opcode (OP_LONG);
- if ($1 == (unsigned int) $1)
- write_exp_elt_type (builtin_type_unsigned_int);
- else
- write_exp_elt_type (BUILTIN_TYPE_UNSIGNED_LONGEST);
- write_exp_elt_longcst ((LONGEST) $1);
+ write_exp_elt_type (val.typed_val_int.type);
+ write_exp_elt_longcst ((LONGEST)val.typed_val_int.val);
write_exp_elt_opcode (OP_LONG);
}
;
-exp : NAME_OR_UINT
- { YYSTYPE val;
- parse_number ($1.stoken.ptr, $1.stoken.length, 0, &val);
- write_exp_elt_opcode (OP_LONG);
- if (val.ulval == (unsigned int) val.ulval)
- write_exp_elt_type (builtin_type_unsigned_int);
- else
- write_exp_elt_type (BUILTIN_TYPE_UNSIGNED_LONGEST);
- write_exp_elt_longcst ((LONGEST)val.ulval);
- write_exp_elt_opcode (OP_LONG);
- }
- ;
-
-exp : CHAR
- { write_exp_elt_opcode (OP_LONG);
- write_exp_elt_type (builtin_type_char);
- write_exp_elt_longcst ((LONGEST) $1);
- write_exp_elt_opcode (OP_LONG); }
- ;
exp : FLOAT
{ write_exp_elt_opcode (OP_DOUBLE);
- write_exp_elt_type (builtin_type_double);
- write_exp_elt_dblcst ($1);
+ write_exp_elt_type ($1.type);
+ write_exp_elt_dblcst ($1.dval);
write_exp_elt_opcode (OP_DOUBLE); }
;
exp : variable
;
-exp : LAST
- { write_exp_elt_opcode (OP_LAST);
- write_exp_elt_longcst ((LONGEST) $1);
- write_exp_elt_opcode (OP_LAST); }
- ;
-
-exp : REGNAME
- { write_exp_elt_opcode (OP_REGISTER);
- write_exp_elt_longcst ((LONGEST) $1);
- write_exp_elt_opcode (OP_REGISTER); }
- ;
-
exp : VARIABLE
- { write_exp_elt_opcode (OP_INTERNALVAR);
- write_exp_elt_intern ($1);
- write_exp_elt_opcode (OP_INTERNALVAR); }
+ /* Already written by write_dollar_variable. */
;
exp : SIZEOF '(' type ')' %prec UNARY
{ write_exp_elt_opcode (OP_LONG);
- write_exp_elt_type (builtin_type_int);
+ write_exp_elt_type (builtin_type (current_gdbarch)->builtin_int);
+ CHECK_TYPEDEF ($3);
write_exp_elt_longcst ((LONGEST) TYPE_LENGTH ($3));
write_exp_elt_opcode (OP_LONG); }
;
exp : STRING
- { write_exp_elt_opcode (OP_STRING);
- write_exp_string ($1);
- write_exp_elt_opcode (OP_STRING); }
+ { /* C strings are converted into array constants with
+ an explicit null byte added at the end. Thus
+ the array upper bound is the string length.
+ There is no such thing in C as a completely empty
+ string. */
+ char *sp = $1.ptr; int count = $1.length;
+ while (count-- > 0)
+ {
+ write_exp_elt_opcode (OP_LONG);
+ write_exp_elt_type (builtin_type (current_gdbarch)->builtin_char);
+ write_exp_elt_longcst ((LONGEST)(*sp++));
+ write_exp_elt_opcode (OP_LONG);
+ }
+ write_exp_elt_opcode (OP_LONG);
+ write_exp_elt_type (builtin_type (current_gdbarch)->builtin_char);
+ write_exp_elt_longcst ((LONGEST)'\0');
+ write_exp_elt_opcode (OP_LONG);
+ write_exp_elt_opcode (OP_ARRAY);
+ write_exp_elt_longcst ((LONGEST) 0);
+ write_exp_elt_longcst ((LONGEST) ($1.length));
+ write_exp_elt_opcode (OP_ARRAY); }
;
/* C++. */
-exp : THIS
- { write_exp_elt_opcode (OP_THIS);
- write_exp_elt_opcode (OP_THIS); }
+exp : TRUEKEYWORD
+ { write_exp_elt_opcode (OP_LONG);
+ write_exp_elt_type (builtin_type (current_gdbarch)->builtin_bool);
+ write_exp_elt_longcst ((LONGEST) 1);
+ write_exp_elt_opcode (OP_LONG); }
+ ;
+
+exp : FALSEKEYWORD
+ { write_exp_elt_opcode (OP_LONG);
+ write_exp_elt_type (builtin_type (current_gdbarch)->builtin_bool);
+ write_exp_elt_longcst ((LONGEST) 0);
+ write_exp_elt_opcode (OP_LONG); }
;
/* end of C++. */
block : BLOCKNAME
{
- if ($1.sym != 0)
- $$ = SYMBOL_BLOCK_VALUE ($1.sym);
+ if ($1.sym)
+ $$ = SYMBOL_BLOCK_VALUE ($1.sym);
else
- {
- struct symtab *tem =
- lookup_symtab (copy_name ($1.stoken));
- if (tem)
- $$ = BLOCKVECTOR_BLOCK
- (BLOCKVECTOR (tem), STATIC_BLOCK);
- else
- error ("No file or function \"%s\".",
- copy_name ($1.stoken));
- }
+ error ("No file or function \"%s\".",
+ copy_name ($1.stoken));
+ }
+ | FILENAME
+ {
+ $$ = $1;
}
;
block : block COLONCOLON name
{ struct symbol *tem
= lookup_symbol (copy_name ($3), $1,
- VAR_NAMESPACE, 0, NULL);
+ VAR_DOMAIN, (int *) NULL,
+ (struct symtab **) NULL);
if (!tem || SYMBOL_CLASS (tem) != LOC_BLOCK)
error ("No function \"%s\" in specified context.",
copy_name ($3));
variable: block COLONCOLON name
{ struct symbol *sym;
sym = lookup_symbol (copy_name ($3), $1,
- VAR_NAMESPACE, 0, NULL);
+ VAR_DOMAIN, (int *) NULL,
+ (struct symtab **) NULL);
if (sym == 0)
error ("No symbol \"%s\" in specified context.",
copy_name ($3));
write_exp_elt_opcode (OP_VAR_VALUE);
+ /* block_found is set by lookup_symbol. */
+ write_exp_elt_block (block_found);
write_exp_elt_sym (sym);
write_exp_elt_opcode (OP_VAR_VALUE); }
;
-variable: typebase COLONCOLON name
+qualified_name: typebase COLONCOLON name
{
struct type *type = $1;
if (TYPE_CODE (type) != TYPE_CODE_STRUCT
- && TYPE_CODE (type) != TYPE_CODE_UNION)
+ && TYPE_CODE (type) != TYPE_CODE_UNION
+ && TYPE_CODE (type) != TYPE_CODE_NAMESPACE)
error ("`%s' is not defined as an aggregate type.",
TYPE_NAME (type));
| typebase COLONCOLON '~' name
{
struct type *type = $1;
+ struct stoken tmp_token;
if (TYPE_CODE (type) != TYPE_CODE_STRUCT
- && TYPE_CODE (type) != TYPE_CODE_UNION)
+ && TYPE_CODE (type) != TYPE_CODE_UNION
+ && TYPE_CODE (type) != TYPE_CODE_NAMESPACE)
error ("`%s' is not defined as an aggregate type.",
TYPE_NAME (type));
- if (strcmp (type_name_no_tag (type), $4.ptr))
- error ("invalid destructor `%s::~%s'",
- type_name_no_tag (type), $4.ptr);
+ tmp_token.ptr = (char*) alloca ($4.length + 2);
+ tmp_token.length = $4.length + 1;
+ tmp_token.ptr[0] = '~';
+ memcpy (tmp_token.ptr+1, $4.ptr, $4.length);
+ tmp_token.ptr[tmp_token.length] = 0;
+ /* Check for valid destructor name. */
+ destructor_name_p (tmp_token.ptr, type);
write_exp_elt_opcode (OP_SCOPE);
write_exp_elt_type (type);
- write_exp_string ($4);
+ write_exp_string (tmp_token);
write_exp_elt_opcode (OP_SCOPE);
- write_exp_elt_opcode (UNOP_LOGNOT);
}
+ ;
+
+variable: qualified_name
| COLONCOLON name
{
char *name = copy_name ($2);
struct symbol *sym;
- int i;
+ struct minimal_symbol *msymbol;
sym =
- lookup_symbol (name, 0, VAR_NAMESPACE, 0, NULL);
+ lookup_symbol (name, (const struct block *) NULL,
+ VAR_DOMAIN, (int *) NULL,
+ (struct symtab **) NULL);
if (sym)
{
write_exp_elt_opcode (OP_VAR_VALUE);
+ write_exp_elt_block (NULL);
write_exp_elt_sym (sym);
write_exp_elt_opcode (OP_VAR_VALUE);
break;
}
- for (i = 0; i < misc_function_count; i++)
- if (!strcmp (misc_function_vector[i].name, name))
- break;
- if (i < misc_function_count)
+ msymbol = lookup_minimal_symbol (name, NULL, NULL);
+ if (msymbol != NULL)
{
- enum misc_function_type mft =
- misc_function_vector[i].type;
-
- write_exp_elt_opcode (OP_LONG);
- write_exp_elt_type (builtin_type_int);
- write_exp_elt_longcst ((LONGEST) misc_function_vector[i].address);
- write_exp_elt_opcode (OP_LONG);
- write_exp_elt_opcode (UNOP_MEMVAL);
- if (mft == mf_data || mft == mf_bss)
- write_exp_elt_type (builtin_type_int);
- else if (mft == mf_text)
- write_exp_elt_type (lookup_function_type (builtin_type_int));
- else
- write_exp_elt_type (builtin_type_char);
- write_exp_elt_opcode (UNOP_MEMVAL);
+ write_exp_msymbol (msymbol,
+ lookup_function_type (builtin_type (current_gdbarch)->builtin_int),
+ builtin_type (current_gdbarch)->builtin_int);
}
else
- if (symtab_list == 0
- && partial_symtab_list == 0)
+ if (!have_full_symbols () && !have_partial_symbols ())
error ("No symbol table is loaded. Use the \"file\" command.");
else
error ("No symbol \"%s\" in current context.", name);
if (sym)
{
- switch (SYMBOL_CLASS (sym))
+ if (symbol_read_needs_frame (sym))
{
- case LOC_REGISTER:
- case LOC_ARG:
- case LOC_REF_ARG:
- case LOC_REGPARM:
- case LOC_LOCAL:
- case LOC_LOCAL_ARG:
if (innermost_block == 0 ||
contained_in (block_found,
innermost_block))
innermost_block = block_found;
- case LOC_UNDEF:
- case LOC_CONST:
- case LOC_STATIC:
- case LOC_TYPEDEF:
- case LOC_LABEL:
- case LOC_BLOCK:
- case LOC_CONST_BYTES:
-
- /* In this case the expression can
- be evaluated regardless of what
- frame we are in, so there is no
- need to check for the
- innermost_block. These cases are
- listed so that gcc -Wall will
- report types that may not have
- been considered. */
-
- break;
}
+
write_exp_elt_opcode (OP_VAR_VALUE);
+ /* We want to use the selected frame, not
+ another more inner frame which happens to
+ be in the same block. */
+ write_exp_elt_block (NULL);
write_exp_elt_sym (sym);
write_exp_elt_opcode (OP_VAR_VALUE);
}
}
else
{
- register int i;
- register char *arg = copy_name ($1.stoken);
-
- /* FIXME, this search is linear! At least
- optimize the strcmp with a 1-char cmp... */
- for (i = 0; i < misc_function_count; i++)
- if (!strcmp (misc_function_vector[i].name, arg))
- break;
+ struct minimal_symbol *msymbol;
+ char *arg = copy_name ($1.stoken);
- if (i < misc_function_count)
+ msymbol =
+ lookup_minimal_symbol (arg, NULL, NULL);
+ if (msymbol != NULL)
{
- enum misc_function_type mft =
- misc_function_vector[i].type;
-
- write_exp_elt_opcode (OP_LONG);
- write_exp_elt_type (builtin_type_int);
- write_exp_elt_longcst ((LONGEST) misc_function_vector[i].address);
- write_exp_elt_opcode (OP_LONG);
- write_exp_elt_opcode (UNOP_MEMVAL);
- if (mft == mf_data || mft == mf_bss)
- write_exp_elt_type (builtin_type_int);
- else if (mft == mf_text)
- write_exp_elt_type (lookup_function_type (builtin_type_int));
- else
- write_exp_elt_type (builtin_type_char);
- write_exp_elt_opcode (UNOP_MEMVAL);
+ write_exp_msymbol (msymbol,
+ lookup_function_type (builtin_type (current_gdbarch)->builtin_int),
+ builtin_type (current_gdbarch)->builtin_int);
}
- else if (symtab_list == 0
- && partial_symtab_list == 0)
+ else if (!have_full_symbols () && !have_partial_symbols ())
error ("No symbol table is loaded. Use the \"file\" command.");
else
error ("No symbol \"%s\" in current context.",
}
;
-
-ptype : typebase
- | typebase abs_decl
- {
- /* This is where the interesting stuff happens. */
- int done = 0;
- int array_size;
- struct type *follow_type = $1;
-
- while (!done)
- switch (pop_type ())
- {
- case tp_end:
- done = 1;
- break;
- case tp_pointer:
- follow_type = lookup_pointer_type (follow_type);
- break;
- case tp_reference:
- follow_type = lookup_reference_type (follow_type);
- break;
- case tp_array:
- array_size = pop_type_int ();
- if (array_size != -1)
- follow_type = create_array_type (follow_type,
- array_size);
- else
- follow_type = lookup_pointer_type (follow_type);
- break;
- case tp_function:
- follow_type = lookup_function_type (follow_type);
- break;
- }
- $$ = follow_type;
+space_identifier : '@' NAME
+ { push_type_address_space (copy_name ($2.stoken));
+ push_type (tp_space_identifier);
}
;
+const_or_volatile: const_or_volatile_noopt
+ |
+ ;
+
+cv_with_space_id : const_or_volatile space_identifier const_or_volatile
+ ;
+
+const_or_volatile_or_space_identifier_noopt: cv_with_space_id
+ | const_or_volatile_noopt
+ ;
+
+const_or_volatile_or_space_identifier:
+ const_or_volatile_or_space_identifier_noopt
+ |
+ ;
+
abs_decl: '*'
{ push_type (tp_pointer); $$ = 0; }
| '*' abs_decl
push_type (tp_array);
$$ = 0;
}
+
| direct_abs_decl func_mod
{ push_type (tp_function); }
| func_mod
array_mod: '[' ']'
{ $$ = -1; }
| '[' INT ']'
- { $$ = $2; }
+ { $$ = $2.val; }
;
func_mod: '(' ')'
{ $$ = 0; }
+ | '(' nonempty_typelist ')'
+ { free ($2); $$ = 0; }
;
+/* We used to try to recognize pointer to member types here, but
+ that didn't work (shift/reduce conflicts meant that these rules never
+ got executed). The problem is that
+ int (foo::bar::baz::bizzle)
+ is a function type but
+ int (foo::bar::baz::bizzle::*)
+ is a pointer to member type. Stroustrup loses again! */
+
type : ptype
- | typebase COLONCOLON '*'
- { $$ = lookup_member_type (builtin_type_int, $1); }
- | type '(' typebase COLONCOLON '*' ')'
- { $$ = lookup_member_type ($1, $3); }
- | type '(' typebase COLONCOLON '*' ')' '(' ')'
- { $$ = lookup_member_type
- (lookup_function_type ($1), $3); }
- | type '(' typebase COLONCOLON '*' ')' '(' nonempty_typelist ')'
- { $$ = lookup_member_type
- (lookup_function_type ($1), $3);
- free ($8); }
- ;
-
-typebase
+ ;
+
+typebase /* Implements (approximately): (type-qualifier)* type-specifier */
: TYPENAME
{ $$ = $1.type; }
| INT_KEYWORD
- { $$ = builtin_type_int; }
+ { $$ = builtin_type (current_gdbarch)->builtin_int; }
| LONG
- { $$ = builtin_type_long; }
+ { $$ = builtin_type (current_gdbarch)->builtin_long; }
| SHORT
- { $$ = builtin_type_short; }
+ { $$ = builtin_type (current_gdbarch)->builtin_short; }
| LONG INT_KEYWORD
- { $$ = builtin_type_long; }
+ { $$ = builtin_type (current_gdbarch)->builtin_long; }
+ | LONG SIGNED_KEYWORD INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_long; }
+ | LONG SIGNED_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_long; }
+ | SIGNED_KEYWORD LONG INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_long; }
| UNSIGNED LONG INT_KEYWORD
- { $$ = builtin_type_unsigned_long; }
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_long; }
+ | LONG UNSIGNED INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_long; }
+ | LONG UNSIGNED
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_long; }
| LONG LONG
- { $$ = builtin_type_long_long; }
+ { $$ = builtin_type (current_gdbarch)->builtin_long_long; }
| LONG LONG INT_KEYWORD
- { $$ = builtin_type_long_long; }
+ { $$ = builtin_type (current_gdbarch)->builtin_long_long; }
+ | LONG LONG SIGNED_KEYWORD INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_long_long; }
+ | LONG LONG SIGNED_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_long_long; }
+ | SIGNED_KEYWORD LONG LONG
+ { $$ = builtin_type (current_gdbarch)->builtin_long_long; }
+ | SIGNED_KEYWORD LONG LONG INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_long_long; }
| UNSIGNED LONG LONG
- { $$ = builtin_type_unsigned_long_long; }
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_long_long; }
| UNSIGNED LONG LONG INT_KEYWORD
- { $$ = builtin_type_unsigned_long_long; }
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_long_long; }
+ | LONG LONG UNSIGNED
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_long_long; }
+ | LONG LONG UNSIGNED INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_long_long; }
| SHORT INT_KEYWORD
- { $$ = builtin_type_short; }
+ { $$ = builtin_type (current_gdbarch)->builtin_short; }
+ | SHORT SIGNED_KEYWORD INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_short; }
+ | SHORT SIGNED_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_short; }
| UNSIGNED SHORT INT_KEYWORD
- { $$ = builtin_type_unsigned_short; }
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_short; }
+ | SHORT UNSIGNED
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_short; }
+ | SHORT UNSIGNED INT_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_short; }
+ | DOUBLE_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_double; }
+ | LONG DOUBLE_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_long_double; }
| STRUCT name
{ $$ = lookup_struct (copy_name ($2),
expression_context_block); }
+ | CLASS name
+ { $$ = lookup_struct (copy_name ($2),
+ expression_context_block); }
| UNION name
{ $$ = lookup_union (copy_name ($2),
expression_context_block); }
| UNSIGNED typename
{ $$ = lookup_unsigned_typename (TYPE_NAME($2.type)); }
| UNSIGNED
- { $$ = builtin_type_unsigned_int; }
- | SIGNED typename
- { $$ = $2.type; }
- | SIGNED
- { $$ = builtin_type_int; }
+ { $$ = builtin_type (current_gdbarch)->builtin_unsigned_int; }
+ | SIGNED_KEYWORD typename
+ { $$ = lookup_signed_typename (TYPE_NAME($2.type)); }
+ | SIGNED_KEYWORD
+ { $$ = builtin_type (current_gdbarch)->builtin_int; }
+ /* It appears that this rule for templates is never
+ reduced; template recognition happens by lookahead
+ in the token processing code in yylex. */
+ | TEMPLATE name '<' type '>'
+ { $$ = lookup_template_type(copy_name($2), $4,
+ expression_context_block);
+ }
+ | const_or_volatile_or_space_identifier_noopt typebase
+ { $$ = follow_types ($2); }
+ | typebase const_or_volatile_or_space_identifier_noopt
+ { $$ = follow_types ($1); }
+ | qualified_type
+ ;
+
+/* FIXME: carlton/2003-09-25: This next bit leads to lots of
+ reduce-reduce conflicts, because the parser doesn't know whether or
+ not to use qualified_name or qualified_type: the rules are
+ identical. If the parser is parsing 'A::B::x', then, when it sees
+ the second '::', it knows that the expression to the left of it has
+ to be a type, so it uses qualified_type. But if it is parsing just
+ 'A::B', then it doesn't have any way of knowing which rule to use,
+ so there's a reduce-reduce conflict; it picks qualified_name, since
+ that occurs earlier in this file than qualified_type.
+
+ There's no good way to fix this with the grammar as it stands; as
+ far as I can tell, some of the problems arise from ambiguities that
+ GDB introduces ('start' can be either an expression or a type), but
+ some of it is inherent to the nature of C++ (you want to treat the
+ input "(FOO)" fairly differently depending on whether FOO is an
+ expression or a type, and if FOO is a complex expression, this can
+ be hard to determine at the right time). Fortunately, it works
+ pretty well in most cases. For example, if you do 'ptype A::B',
+ where A::B is a nested type, then the parser will mistakenly
+ misidentify it as an expression; but evaluate_subexp will get
+ called with 'noside' set to EVAL_AVOID_SIDE_EFFECTS, and everything
+ will work out anyways. But there are situations where the parser
+ will get confused: the most common one that I've run into is when
+ you want to do
+
+ print *((A::B *) x)"
+
+ where the parser doesn't realize that A::B has to be a type until
+ it hits the first right paren, at which point it's too late. (The
+ workaround is to type "print *(('A::B' *) x)" instead.) (And
+ another solution is to fix our symbol-handling code so that the
+ user never wants to type something like that in the first place,
+ because we get all the types right without the user's help!)
+
+ Perhaps we could fix this by making the lexer smarter. Some of
+ this functionality used to be in the lexer, but in a way that
+ worked even less well than the current solution: that attempt
+ involved having the parser sometimes handle '::' and having the
+ lexer sometimes handle it, and without a clear division of
+ responsibility, it quickly degenerated into a big mess. Probably
+ the eventual correct solution will give more of a role to the lexer
+ (ideally via code that is shared between the lexer and
+ decode_line_1), but I'm not holding my breath waiting for somebody
+ to get around to cleaning this up... */
+
+qualified_type: typebase COLONCOLON name
+ {
+ struct type *type = $1;
+ struct type *new_type;
+ char *ncopy = alloca ($3.length + 1);
+
+ memcpy (ncopy, $3.ptr, $3.length);
+ ncopy[$3.length] = '\0';
+
+ if (TYPE_CODE (type) != TYPE_CODE_STRUCT
+ && TYPE_CODE (type) != TYPE_CODE_UNION
+ && TYPE_CODE (type) != TYPE_CODE_NAMESPACE)
+ error ("`%s' is not defined as an aggregate type.",
+ TYPE_NAME (type));
+
+ new_type = cp_lookup_nested_type (type, ncopy,
+ expression_context_block);
+ if (new_type == NULL)
+ error ("No type \"%s\" within class or namespace \"%s\".",
+ ncopy, TYPE_NAME (type));
+
+ $$ = new_type;
+ }
;
typename: TYPENAME
{
$$.stoken.ptr = "int";
$$.stoken.length = 3;
- $$.type = builtin_type_int;
+ $$.type = builtin_type (current_gdbarch)->builtin_int;
}
| LONG
{
$$.stoken.ptr = "long";
$$.stoken.length = 4;
- $$.type = builtin_type_long;
+ $$.type = builtin_type (current_gdbarch)->builtin_long;
}
| SHORT
{
$$.stoken.ptr = "short";
$$.stoken.length = 5;
- $$.type = builtin_type_short;
+ $$.type = builtin_type (current_gdbarch)->builtin_short;
}
;
nonempty_typelist
: type
- { $$ = (struct type **)xmalloc (sizeof (struct type *) * 2);
- $$[0] = (struct type *)0;
+ { $$ = (struct type **) malloc (sizeof (struct type *) * 2);
+ $<ivec>$[0] = 1; /* Number of types in vector */
$$[1] = $1;
}
| nonempty_typelist ',' type
- { int len = sizeof (struct type *) * ++($<ivec>1[0]);
- $$ = (struct type **)xrealloc ($1, len);
+ { int len = sizeof (struct type *) * (++($<ivec>1[0]) + 1);
+ $$ = (struct type **) realloc ((char *) $1, len);
$$[$<ivec>$[0]] = $3;
}
;
+ptype : typebase
+ | ptype const_or_volatile_or_space_identifier abs_decl const_or_volatile_or_space_identifier
+ { $$ = follow_types ($1); }
+ ;
+
+const_and_volatile: CONST_KEYWORD VOLATILE_KEYWORD
+ | VOLATILE_KEYWORD CONST_KEYWORD
+ ;
+
+const_or_volatile_noopt: const_and_volatile
+ { push_type (tp_const);
+ push_type (tp_volatile);
+ }
+ | CONST_KEYWORD
+ { push_type (tp_const); }
+ | VOLATILE_KEYWORD
+ { push_type (tp_volatile); }
+ ;
+
name : NAME { $$ = $1.stoken; }
| BLOCKNAME { $$ = $1.stoken; }
| TYPENAME { $$ = $1.stoken; }
| NAME_OR_INT { $$ = $1.stoken; }
- | NAME_OR_UINT { $$ = $1.stoken; }
;
name_not_typename : NAME
=exp) or just an exp. If name_not_typename was ever used in an lvalue
context where only a name could occur, this might be useful.
| NAME_OR_INT
- | NAME_OR_UINT
*/
;
static int
parse_number (p, len, parsed_float, putithere)
- register char *p;
- register int len;
+ char *p;
+ int len;
int parsed_float;
YYSTYPE *putithere;
{
- register LONGEST n = 0;
- register LONGEST prevn = 0;
- register int i;
- register int c;
- register int base = input_radix;
+ /* FIXME: Shouldn't these be unsigned? We don't deal with negative values
+ here, and we do kind of silly things like cast to unsigned. */
+ LONGEST n = 0;
+ LONGEST prevn = 0;
+ ULONGEST un;
+
+ int i = 0;
+ int c;
+ int base = input_radix;
int unsigned_p = 0;
- extern double atof ();
+ /* Number of "L" suffixes encountered. */
+ int long_p = 0;
+
+ /* We have found a "L" or "U" suffix. */
+ int found_suffix = 0;
+
+ ULONGEST high_bit;
+ struct type *signed_type;
+ struct type *unsigned_type;
if (parsed_float)
{
/* It's a float since it contains a point or an exponent. */
- putithere->dval = atof (p);
+ char *s = malloc (len);
+ int num = 0; /* number of tokens scanned by scanf */
+ char saved_char = p[len];
+
+ p[len] = 0; /* null-terminate the token */
+ num = sscanf (p, DOUBLEST_SCAN_FORMAT "%s",
+ &putithere->typed_val_float.dval, s);
+ p[len] = saved_char; /* restore the input stream */
+
+ if (num == 1)
+ putithere->typed_val_float.type =
+ builtin_type (current_gdbarch)->builtin_double;
+
+ if (num == 2 )
+ {
+ /* See if it has any float suffix: 'f' for float, 'l' for long
+ double. */
+ if (!strcasecmp (s, "f"))
+ putithere->typed_val_float.type =
+ builtin_type (current_gdbarch)->builtin_float;
+ else if (!strcasecmp (s, "l"))
+ putithere->typed_val_float.type =
+ builtin_type (current_gdbarch)->builtin_long_double;
+ else
+ return ERROR;
+ }
+
return FLOAT;
}
if (c != 'l' && c != 'u')
n *= base;
if (c >= '0' && c <= '9')
- n += i = c - '0';
+ {
+ if (found_suffix)
+ return ERROR;
+ n += i = c - '0';
+ }
else
{
if (base > 10 && c >= 'a' && c <= 'f')
- n += i = c - 'a' + 10;
- else if (len == 0 && c == 'l')
- ;
- else if (len == 0 && c == 'u')
- unsigned_p = 1;
+ {
+ if (found_suffix)
+ return ERROR;
+ n += i = c - 'a' + 10;
+ }
+ else if (c == 'l')
+ {
+ ++long_p;
+ found_suffix = 1;
+ }
+ else if (c == 'u')
+ {
+ unsigned_p = 1;
+ found_suffix = 1;
+ }
else
return ERROR; /* Char not a digit */
}
if (i >= base)
return ERROR; /* Invalid digit in this base */
- if(!unsigned_p && (prevn >= n))
- unsigned_p=1; /* Try something unsigned */
- /* Don't do the range check if n==i and i==0, since that special
- case will give an overflow error. */
- if(RANGE_CHECK && n!=0)
- {
- if((unsigned_p && (unsigned)prevn >= (unsigned)n))
- range_error("Overflow on numeric constant.");
- }
- prevn=n;
+
+ /* Portably test for overflow (only works for nonzero values, so make
+ a second check for zero). FIXME: Can't we just make n and prevn
+ unsigned and avoid this? */
+ if (c != 'l' && c != 'u' && (prevn >= n) && n != 0)
+ unsigned_p = 1; /* Try something unsigned */
+
+ /* Portably test for unsigned overflow.
+ FIXME: This check is wrong; for example it doesn't find overflow
+ on 0x123456789 when LONGEST is 32 bits. */
+ if (c != 'l' && c != 'u' && n != 0)
+ {
+ if ((unsigned_p && (ULONGEST) prevn >= (ULONGEST) n))
+ error ("Numeric constant too large.");
+ }
+ prevn = n;
}
- if (unsigned_p)
+ /* An integer constant is an int, a long, or a long long. An L
+ suffix forces it to be long; an LL suffix forces it to be long
+ long. If not forced to a larger size, it gets the first type of
+ the above that it fits in. To figure out whether it fits, we
+ shift it right and see whether anything remains. Note that we
+ can't shift sizeof (LONGEST) * HOST_CHAR_BIT bits or more in one
+ operation, because many compilers will warn about such a shift
+ (which always produces a zero result). Sometimes gdbarch_int_bit
+ or gdbarch_long_bit will be that big, sometimes not. To deal with
+ the case where it is we just always shift the value more than
+ once, with fewer bits each time. */
+
+ un = (ULONGEST)n >> 2;
+ if (long_p == 0
+ && (un >> (gdbarch_int_bit (current_gdbarch) - 2)) == 0)
+ {
+ high_bit = ((ULONGEST)1) << (gdbarch_int_bit (current_gdbarch) - 1);
+
+ /* A large decimal (not hex or octal) constant (between INT_MAX
+ and UINT_MAX) is a long or unsigned long, according to ANSI,
+ never an unsigned int, but this code treats it as unsigned
+ int. This probably should be fixed. GCC gives a warning on
+ such constants. */
+
+ unsigned_type = builtin_type (current_gdbarch)->builtin_unsigned_int;
+ signed_type = builtin_type (current_gdbarch)->builtin_int;
+ }
+ else if (long_p <= 1
+ && (un >> (gdbarch_long_bit (current_gdbarch) - 2)) == 0)
{
- putithere->ulval = n;
- return UINT;
+ high_bit = ((ULONGEST)1) << (gdbarch_long_bit (current_gdbarch) - 1);
+ unsigned_type = builtin_type (current_gdbarch)->builtin_unsigned_long;
+ signed_type = builtin_type (current_gdbarch)->builtin_long;
}
else
{
- putithere->lval = n;
- return INT;
+ int shift;
+ if (sizeof (ULONGEST) * HOST_CHAR_BIT
+ < gdbarch_long_long_bit (current_gdbarch))
+ /* A long long does not fit in a LONGEST. */
+ shift = (sizeof (ULONGEST) * HOST_CHAR_BIT - 1);
+ else
+ shift = (gdbarch_long_long_bit (current_gdbarch) - 1);
+ high_bit = (ULONGEST) 1 << shift;
+ unsigned_type = builtin_type (current_gdbarch)->builtin_unsigned_long_long;
+ signed_type = builtin_type (current_gdbarch)->builtin_long_long;
}
+
+ putithere->typed_val_int.val = n;
+
+ /* If the high bit of the worked out type is set then this number
+ has to be unsigned. */
+
+ if (unsigned_p || (n & high_bit))
+ {
+ putithere->typed_val_int.type = unsigned_type;
+ }
+ else
+ {
+ putithere->typed_val_int.type = signed_type;
+ }
+
+ return INT;
}
struct token
enum exp_opcode opcode;
};
-const static struct token tokentab3[] =
+static const struct token tokentab3[] =
{
{">>=", ASSIGN_MODIFY, BINOP_RSH},
{"<<=", ASSIGN_MODIFY, BINOP_LSH}
};
-const static struct token tokentab2[] =
+static const struct token tokentab2[] =
{
{"+=", ASSIGN_MODIFY, BINOP_ADD},
{"-=", ASSIGN_MODIFY, BINOP_SUB},
{"*=", ASSIGN_MODIFY, BINOP_MUL},
{"/=", ASSIGN_MODIFY, BINOP_DIV},
{"%=", ASSIGN_MODIFY, BINOP_REM},
- {"|=", ASSIGN_MODIFY, BINOP_LOGIOR},
- {"&=", ASSIGN_MODIFY, BINOP_LOGAND},
- {"^=", ASSIGN_MODIFY, BINOP_LOGXOR},
+ {"|=", ASSIGN_MODIFY, BINOP_BITWISE_IOR},
+ {"&=", ASSIGN_MODIFY, BINOP_BITWISE_AND},
+ {"^=", ASSIGN_MODIFY, BINOP_BITWISE_XOR},
{"++", INCREMENT, BINOP_END},
{"--", DECREMENT, BINOP_END},
{"->", ARROW, BINOP_END},
- {"&&", AND, BINOP_END},
- {"||", OR, BINOP_END},
+ {"&&", ANDAND, BINOP_END},
+ {"||", OROR, BINOP_END},
{"::", COLONCOLON, BINOP_END},
{"<<", LSH, BINOP_END},
{">>", RSH, BINOP_END},
/* Read one token, getting characters through lexptr. */
-int
+static int
yylex ()
{
- register int c;
- register int namelen;
- register unsigned i;
- register char *tokstart;
-
+ int c;
+ int namelen;
+ unsigned int i;
+ char *tokstart;
+ char *tokptr;
+ int tempbufindex;
+ static char *tempbuf;
+ static int tempbufsize;
+ char * token_string = NULL;
+ int class_prefix = 0;
+
retry:
+ /* Check if this is a macro invocation that we need to expand. */
+ if (! scanning_macro_expansion ())
+ {
+ char *expanded = macro_expand_next (&lexptr,
+ expression_macro_lookup_func,
+ expression_macro_lookup_baton);
+
+ if (expanded)
+ scan_macro_expansion (expanded);
+ }
+
+ prev_lexptr = lexptr;
+
tokstart = lexptr;
/* See if it is a special token of length 3. */
for (i = 0; i < sizeof tokentab3 / sizeof tokentab3[0]; i++)
- if (!strncmp (tokstart, tokentab3[i].operator, 3))
+ if (strncmp (tokstart, tokentab3[i].operator, 3) == 0)
{
lexptr += 3;
yylval.opcode = tokentab3[i].opcode;
/* See if it is a special token of length 2. */
for (i = 0; i < sizeof tokentab2 / sizeof tokentab2[0]; i++)
- if (!strncmp (tokstart, tokentab2[i].operator, 2))
+ if (strncmp (tokstart, tokentab2[i].operator, 2) == 0)
{
lexptr += 2;
yylval.opcode = tokentab2[i].opcode;
switch (c = *tokstart)
{
case 0:
- return 0;
+ /* If we were just scanning the result of a macro expansion,
+ then we need to resume scanning the original text.
+ Otherwise, we were already scanning the original text, and
+ we're really done. */
+ if (scanning_macro_expansion ())
+ {
+ finished_macro_expansion ();
+ goto retry;
+ }
+ else
+ return 0;
case ' ':
case '\t':
goto retry;
case '\'':
+ /* We either have a character constant ('0' or '\177' for example)
+ or we have a quoted symbol reference ('foo(int,int)' in C++
+ for example). */
lexptr++;
c = *lexptr++;
if (c == '\\')
c = parse_escape (&lexptr);
- yylval.lval = c;
+ else if (c == '\'')
+ error ("Empty character constant.");
+ else if (! host_char_to_target (c, &c))
+ {
+ int toklen = lexptr - tokstart + 1;
+ char *tok = alloca (toklen + 1);
+ memcpy (tok, tokstart, toklen);
+ tok[toklen] = '\0';
+ error ("There is no character corresponding to %s in the target "
+ "character set `%s'.", tok, target_charset ());
+ }
+
+ yylval.typed_val_int.val = c;
+ yylval.typed_val_int.type = builtin_type (current_gdbarch)->builtin_char;
+
c = *lexptr++;
if (c != '\'')
- error ("Invalid character constant.");
- return CHAR;
+ {
+ namelen = skip_quoted (tokstart) - tokstart;
+ if (namelen > 2)
+ {
+ lexptr = tokstart + namelen;
+ if (lexptr[-1] != '\'')
+ error ("Unmatched single quote.");
+ namelen -= 2;
+ tokstart++;
+ goto tryname;
+ }
+ error ("Invalid character constant.");
+ }
+ return INT;
case '(':
paren_depth++;
return c;
case ',':
- if (comma_terminates && paren_depth == 0)
+ if (comma_terminates
+ && paren_depth == 0
+ && ! scanning_macro_expansion ())
return 0;
lexptr++;
return c;
{
/* It's a number. */
int got_dot = 0, got_e = 0, toktype;
- register char *p = tokstart;
+ char *p = tokstart;
int hex = input_radix > 10;
if (c == '0' && (p[1] == 'x' || p[1] == 'X'))
for (;; ++p)
{
+ /* This test includes !hex because 'e' is a valid hex digit
+ and thus does not indicate a floating point number when
+ the radix is hex. */
if (!hex && !got_e && (*p == 'e' || *p == 'E'))
got_dot = got_e = 1;
- else if (!hex && !got_dot && *p == '.')
+ /* This test does not include !hex, because a '.' always indicates
+ a decimal floating point number regardless of the radix. */
+ else if (!got_dot && *p == '.')
got_dot = 1;
else if (got_e && (p[-1] == 'e' || p[-1] == 'E')
&& (*p == '-' || *p == '+'))
{
char *err_copy = (char *) alloca (p - tokstart + 1);
- bcopy (tokstart, err_copy, p - tokstart);
+ memcpy (err_copy, tokstart, p - tokstart);
err_copy[p - tokstart] = 0;
error ("Invalid number \"%s\".", err_copy);
}
return c;
case '"':
- for (namelen = 1; (c = tokstart[namelen]) != '"'; namelen++)
- if (c == '\\')
+
+ /* Build the gdb internal form of the input string in tempbuf,
+ translating any standard C escape forms seen. Note that the
+ buffer is null byte terminated *only* for the convenience of
+ debugging gdb itself and printing the buffer contents when
+ the buffer contains no embedded nulls. Gdb does not depend
+ upon the buffer being null byte terminated, it uses the length
+ string instead. This allows gdb to handle C strings (as well
+ as strings in other languages) with embedded null bytes */
+
+ tokptr = ++tokstart;
+ tempbufindex = 0;
+
+ do {
+ char *char_start_pos = tokptr;
+
+ /* Grow the static temp buffer if necessary, including allocating
+ the first one on demand. */
+ if (tempbufindex + 1 >= tempbufsize)
{
- c = tokstart[++namelen];
- if (c >= '0' && c <= '9')
+ tempbuf = (char *) realloc (tempbuf, tempbufsize += 64);
+ }
+ switch (*tokptr)
+ {
+ case '\0':
+ case '"':
+ /* Do nothing, loop will terminate. */
+ break;
+ case '\\':
+ tokptr++;
+ c = parse_escape (&tokptr);
+ if (c == -1)
{
- c = tokstart[++namelen];
- if (c >= '0' && c <= '9')
- c = tokstart[++namelen];
+ continue;
}
+ tempbuf[tempbufindex++] = c;
+ break;
+ default:
+ c = *tokptr++;
+ if (! host_char_to_target (c, &c))
+ {
+ int len = tokptr - char_start_pos;
+ char *copy = alloca (len + 1);
+ memcpy (copy, char_start_pos, len);
+ copy[len] = '\0';
+
+ error ("There is no character corresponding to `%s' "
+ "in the target character set `%s'.",
+ copy, target_charset ());
+ }
+ tempbuf[tempbufindex++] = c;
+ break;
}
- yylval.sval.ptr = tokstart + 1;
- yylval.sval.length = namelen - 1;
- lexptr += namelen + 1;
- return STRING;
+ } while ((*tokptr != '"') && (*tokptr != '\0'));
+ if (*tokptr++ != '"')
+ {
+ error ("Unterminated string in expression.");
+ }
+ tempbuf[tempbufindex] = '\0'; /* See note above */
+ yylval.sval.ptr = tempbuf;
+ yylval.sval.length = tempbufindex;
+ lexptr = tokptr;
+ return (STRING);
}
if (!(c == '_' || c == '$'
namelen = 0;
for (c = tokstart[namelen];
(c == '_' || c == '$' || (c >= '0' && c <= '9')
- || (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z'));
- c = tokstart[++namelen])
- ;
+ || (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || c == '<');)
+ {
+ /* Template parameter lists are part of the name.
+ FIXME: This mishandles `print $a<4&&$a>3'. */
+
+ if (c == '<')
+ {
+ /* Scan ahead to get rest of the template specification. Note
+ that we look ahead only when the '<' adjoins non-whitespace
+ characters; for comparison expressions, e.g. "a < b > c",
+ there must be spaces before the '<', etc. */
+
+ char * p = find_template_name_end (tokstart + namelen);
+ if (p)
+ namelen = p - tokstart;
+ break;
+ }
+ c = tokstart[++namelen];
+ }
- /* The token "if" terminates the expression and is NOT
- removed from the input stream. */
- if (namelen == 2 && tokstart[0] == 'i' && tokstart[1] == 'f')
+ /* The token "if" terminates the expression and is NOT removed from
+ the input stream. It doesn't count if it appears in the
+ expansion of a macro. */
+ if (namelen == 2
+ && tokstart[0] == 'i'
+ && tokstart[1] == 'f'
+ && ! scanning_macro_expansion ())
{
return 0;
}
lexptr += namelen;
- /* Handle the tokens $digits; also $ (short for $0) and $$ (short for $$1)
- and $$digits (equivalent to $<-digits> if you could type that).
- Make token type LAST, and put the number (the digits) in yylval. */
+ tryname:
- if (*tokstart == '$')
- {
- register int negate = 0;
- c = 1;
- /* Double dollar means negate the number and add -1 as well.
- Thus $$ alone means -1. */
- if (namelen >= 2 && tokstart[1] == '$')
- {
- negate = 1;
- c = 2;
- }
- if (c == namelen)
- {
- /* Just dollars (one or two) */
- yylval.lval = - negate;
- return LAST;
- }
- /* Is the rest of the token digits? */
- for (; c < namelen; c++)
- if (!(tokstart[c] >= '0' && tokstart[c] <= '9'))
- break;
- if (c == namelen)
- {
- yylval.lval = atoi (tokstart + 1 + negate);
- if (negate)
- yylval.lval = - yylval.lval;
- return LAST;
- }
- }
-
- /* Handle tokens that refer to machine registers:
- $ followed by a register name. */
-
- if (*tokstart == '$') {
- for (c = 0; c < NUM_REGS; c++)
- if (namelen - 1 == strlen (reg_names[c])
- && !strncmp (tokstart + 1, reg_names[c], namelen - 1))
- {
- yylval.lval = c;
- return REGNAME;
- }
- for (c = 0; c < num_std_regs; c++)
- if (namelen - 1 == strlen (std_regs[c].name)
- && !strncmp (tokstart + 1, std_regs[c].name, namelen - 1))
- {
- yylval.lval = std_regs[c].regnum;
- return REGNAME;
- }
- }
/* Catch specific keywords. Should be done with a data structure. */
switch (namelen)
{
case 8:
- if (!strncmp (tokstart, "unsigned", 8))
+ if (strncmp (tokstart, "unsigned", 8) == 0)
return UNSIGNED;
+ if (current_language->la_language == language_cplus
+ && strncmp (tokstart, "template", 8) == 0)
+ return TEMPLATE;
+ if (strncmp (tokstart, "volatile", 8) == 0)
+ return VOLATILE_KEYWORD;
break;
case 6:
- if (!strncmp (tokstart, "struct", 6))
+ if (strncmp (tokstart, "struct", 6) == 0)
return STRUCT;
- if (!strncmp (tokstart, "signed", 6))
- return SIGNED;
- if (!strncmp (tokstart, "sizeof", 6))
+ if (strncmp (tokstart, "signed", 6) == 0)
+ return SIGNED_KEYWORD;
+ if (strncmp (tokstart, "sizeof", 6) == 0)
return SIZEOF;
+ if (strncmp (tokstart, "double", 6) == 0)
+ return DOUBLE_KEYWORD;
break;
case 5:
- if (!strncmp (tokstart, "union", 5))
+ if (current_language->la_language == language_cplus)
+ {
+ if (strncmp (tokstart, "false", 5) == 0)
+ return FALSEKEYWORD;
+ if (strncmp (tokstart, "class", 5) == 0)
+ return CLASS;
+ }
+ if (strncmp (tokstart, "union", 5) == 0)
return UNION;
- if (!strncmp (tokstart, "short", 5))
+ if (strncmp (tokstart, "short", 5) == 0)
return SHORT;
+ if (strncmp (tokstart, "const", 5) == 0)
+ return CONST_KEYWORD;
break;
case 4:
- if (!strncmp (tokstart, "enum", 4))
+ if (strncmp (tokstart, "enum", 4) == 0)
return ENUM;
- if (!strncmp (tokstart, "long", 4))
+ if (strncmp (tokstart, "long", 4) == 0)
return LONG;
- if (!strncmp (tokstart, "this", 4))
- {
- static const char this_name[] =
- { CPLUS_MARKER, 't', 'h', 'i', 's', '\0' };
-
- if (lookup_symbol (this_name, expression_context_block,
- VAR_NAMESPACE, 0, NULL))
- return THIS;
- }
+ if (current_language->la_language == language_cplus)
+ {
+ if (strncmp (tokstart, "true", 4) == 0)
+ return TRUEKEYWORD;
+ }
break;
case 3:
- if (!strncmp (tokstart, "int", 3))
+ if (strncmp (tokstart, "int", 3) == 0)
return INT_KEYWORD;
break;
default:
yylval.sval.ptr = tokstart;
yylval.sval.length = namelen;
- /* Any other names starting in $ are debugger internal variables. */
-
if (*tokstart == '$')
{
- yylval.ivar = lookup_internalvar (copy_name (yylval.sval) + 1);
+ write_dollar_variable (yylval.sval);
return VARIABLE;
}
-
+
/* Use token-type BLOCKNAME for symbols that happen to be defined as
functions or symtabs. If this is not so, then ...
Use token-type TYPENAME for symbols that happen to be defined
int hextype;
sym = lookup_symbol (tmp, expression_context_block,
- VAR_NAMESPACE, &is_a_field_of_this, NULL);
- if ((sym && SYMBOL_CLASS (sym) == LOC_BLOCK) ||
- lookup_partial_symtab (tmp))
+ VAR_DOMAIN,
+ current_language->la_language == language_cplus
+ ? &is_a_field_of_this : (int *) NULL,
+ (struct symtab **) NULL);
+ /* Call lookup_symtab, not lookup_partial_symtab, in case there are
+ no psymtabs (coff, xcoff, or some future change to blow away the
+ psymtabs once once symbols are read). */
+ if (sym && SYMBOL_CLASS (sym) == LOC_BLOCK)
{
yylval.ssym.sym = sym;
yylval.ssym.is_a_field_of_this = is_a_field_of_this;
return BLOCKNAME;
}
+ else if (!sym)
+ { /* See if it's a file name. */
+ struct symtab *symtab;
+
+ symtab = lookup_symtab (tmp);
+
+ if (symtab)
+ {
+ yylval.bval = BLOCKVECTOR_BLOCK (BLOCKVECTOR (symtab), STATIC_BLOCK);
+ return FILENAME;
+ }
+ }
+
if (sym && SYMBOL_CLASS (sym) == LOC_TYPEDEF)
{
+ /* NOTE: carlton/2003-09-25: There used to be code here to
+ handle nested types. It didn't work very well. See the
+ comment before qualified_type for more info. */
yylval.tsym.type = SYMBOL_TYPE (sym);
return TYPENAME;
}
- if ((yylval.tsym.type = lookup_primitive_typename (tmp)) != 0)
- return TYPENAME;
+ yylval.tsym.type
+ = language_lookup_primitive_type_by_name (current_language,
+ current_gdbarch, tmp);
+ if (yylval.tsym.type != NULL)
+ return TYPENAME;
/* Input names that aren't symbols but ARE valid hex numbers,
when the input radix permits them, can be names or numbers
yylval.ssym.is_a_field_of_this = is_a_field_of_this;
return NAME_OR_INT;
}
- if (hextype == UINT)
- {
- yylval.ssym.sym = sym;
- yylval.ssym.is_a_field_of_this = is_a_field_of_this;
- return NAME_OR_UINT;
- }
}
/* Any other kind of symbol */
yyerror (msg)
char *msg;
{
- error ("Invalid syntax in expression.");
-}
-\f
-/* Table mapping opcodes into strings for printing operators
- and precedences of the operators. */
-
-const static struct op_print c_op_print_tab[] =
- {
- {",", BINOP_COMMA, PREC_COMMA, 0},
- {"=", BINOP_ASSIGN, PREC_ASSIGN, 1},
- {"||", BINOP_OR, PREC_OR, 0},
- {"&&", BINOP_AND, PREC_AND, 0},
- {"|", BINOP_LOGIOR, PREC_LOGIOR, 0},
- {"&", BINOP_LOGAND, PREC_LOGAND, 0},
- {"^", BINOP_LOGXOR, PREC_LOGXOR, 0},
- {"==", BINOP_EQUAL, PREC_EQUAL, 0},
- {"!=", BINOP_NOTEQUAL, PREC_EQUAL, 0},
- {"<=", BINOP_LEQ, PREC_ORDER, 0},
- {">=", BINOP_GEQ, PREC_ORDER, 0},
- {">", BINOP_GTR, PREC_ORDER, 0},
- {"<", BINOP_LESS, PREC_ORDER, 0},
- {">>", BINOP_RSH, PREC_SHIFT, 0},
- {"<<", BINOP_LSH, PREC_SHIFT, 0},
- {"+", BINOP_ADD, PREC_ADD, 0},
- {"-", BINOP_SUB, PREC_ADD, 0},
- {"*", BINOP_MUL, PREC_MUL, 0},
- {"/", BINOP_DIV, PREC_MUL, 0},
- {"%", BINOP_REM, PREC_MUL, 0},
- {"@", BINOP_REPEAT, PREC_REPEAT, 0},
- {"-", UNOP_NEG, PREC_PREFIX, 0},
- {"!", UNOP_ZEROP, PREC_PREFIX, 0},
- {"~", UNOP_LOGNOT, PREC_PREFIX, 0},
- {"*", UNOP_IND, PREC_PREFIX, 0},
- {"&", UNOP_ADDR, PREC_PREFIX, 0},
- {"sizeof ", UNOP_SIZEOF, PREC_PREFIX, 0},
- {"++", UNOP_PREINCREMENT, PREC_PREFIX, 0},
- {"--", UNOP_PREDECREMENT, PREC_PREFIX, 0},
- /* C++ */
- {"::", BINOP_SCOPE, PREC_PREFIX, 0},
-};
-\f
-/* These variables point to the objects
- representing the predefined C data types. */
-
-struct type *builtin_type_void;
-struct type *builtin_type_char;
-struct type *builtin_type_short;
-struct type *builtin_type_int;
-struct type *builtin_type_long;
-struct type *builtin_type_long_long;
-struct type *builtin_type_unsigned_char;
-struct type *builtin_type_unsigned_short;
-struct type *builtin_type_unsigned_int;
-struct type *builtin_type_unsigned_long;
-struct type *builtin_type_unsigned_long_long;
-struct type *builtin_type_float;
-struct type *builtin_type_double;
-struct type *builtin_type_long_double;
-struct type *builtin_type_complex;
-struct type *builtin_type_double_complex;
-
-struct type ** const (c_builtin_types[]) =
-{
- &builtin_type_int,
- &builtin_type_long,
- &builtin_type_short,
- &builtin_type_char,
- &builtin_type_float,
- &builtin_type_double,
- &builtin_type_void,
- &builtin_type_long_long,
- &builtin_type_unsigned_char,
- &builtin_type_unsigned_short,
- &builtin_type_unsigned_int,
- &builtin_type_unsigned_long,
- &builtin_type_unsigned_long_long,
- &builtin_type_long_double,
- &builtin_type_complex,
- &builtin_type_double_complex,
- 0
-};
-
-/* FIXME: Eventually do a separate defintion for C++. */
-
-const struct language_defn c_language_defn = {
- "c", /* Language name */
- language_c,
- c_builtin_types,
- range_check_off,
- type_check_off,
- c_parse,
- c_error,
- &BUILTIN_TYPE_LONGEST, /* longest signed integral type */
- &BUILTIN_TYPE_UNSIGNED_LONGEST,/* longest unsigned integral type */
- &builtin_type_double, /* longest floating point type */ /*FIXME*/
- "0x%x", "0x%", "x", /* Hex format, prefix, suffix */
- "0%o", "0%", "o", /* Octal format, prefix, suffix */
- c_op_print_tab, /* expression operators for printing */
- LANG_MAGIC
-};
+ if (prev_lexptr)
+ lexptr = prev_lexptr;
-void
-_initialize_c_exp ()
-{
- builtin_type_void =
- init_type (TYPE_CODE_VOID, 1, 0,
- "void");
- builtin_type_char =
- init_type (TYPE_CODE_INT, TARGET_CHAR_BIT / TARGET_CHAR_BIT, 0,
- "char");
- builtin_type_unsigned_char =
- init_type (TYPE_CODE_INT, TARGET_CHAR_BIT / TARGET_CHAR_BIT, 1,
- "unsigned char");
- builtin_type_short =
- init_type (TYPE_CODE_INT, TARGET_SHORT_BIT / TARGET_CHAR_BIT, 0,
- "short");
- builtin_type_unsigned_short =
- init_type (TYPE_CODE_INT, TARGET_SHORT_BIT / TARGET_CHAR_BIT, 1,
- "unsigned short");
- builtin_type_int =
- init_type (TYPE_CODE_INT, TARGET_INT_BIT / TARGET_CHAR_BIT, 0,
- "int");
- builtin_type_unsigned_int =
- init_type (TYPE_CODE_INT, TARGET_INT_BIT / TARGET_CHAR_BIT, 1,
- "unsigned int");
- builtin_type_long =
- init_type (TYPE_CODE_INT, TARGET_LONG_BIT / TARGET_CHAR_BIT, 0,
- "long");
- builtin_type_unsigned_long =
- init_type (TYPE_CODE_INT, TARGET_LONG_BIT / TARGET_CHAR_BIT, 1,
- "unsigned long");
- builtin_type_long_long =
- init_type (TYPE_CODE_INT, TARGET_LONG_LONG_BIT / TARGET_CHAR_BIT, 0,
- "long long");
- builtin_type_unsigned_long_long =
- init_type (TYPE_CODE_INT, TARGET_LONG_LONG_BIT / TARGET_CHAR_BIT, 1,
- "unsigned long long");
- builtin_type_float =
- init_type (TYPE_CODE_FLT, TARGET_FLOAT_BIT / TARGET_CHAR_BIT, 0,
- "float");
- builtin_type_double =
- init_type (TYPE_CODE_FLT, TARGET_DOUBLE_BIT / TARGET_CHAR_BIT, 0,
- "double");
- builtin_type_long_double =
- init_type (TYPE_CODE_FLT, TARGET_LONG_DOUBLE_BIT / TARGET_CHAR_BIT, 0,
- "long double");
- builtin_type_complex =
- init_type (TYPE_CODE_FLT, TARGET_COMPLEX_BIT / TARGET_CHAR_BIT, 0,
- "complex");
- builtin_type_double_complex =
- init_type (TYPE_CODE_FLT, TARGET_DOUBLE_COMPLEX_BIT / TARGET_CHAR_BIT, 0,
- "double complex");
-
- add_language (&c_language_defn);
- set_language (language_c); /* Make C the default language */
+ error ("A %s in expression, near `%s'.", (msg ? msg : "error"), lexptr);
}