X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/f6857bbf8c40df05d7c7324cf41ced6d1961ca89..93d133c932a4f754172cd8473bfe469975b00023:/src/reader.c?ds=inline
diff --git a/src/reader.c b/src/reader.c
index 4bbed58f..86fde7b2 100644
--- a/src/reader.c
+++ b/src/reader.c
@@ -1,42 +1,41 @@
/* Input parser for Bison
- Copyright (C) 1984, 1986, 1989, 1992, 1998, 2000, 2001, 2002, 2003,
- 2005, 2006, 2007 Free Software Foundation, Inc.
+ Copyright (C) 1984, 1986, 1989, 1992, 1998, 2000-2003, 2005-2007,
+ 2009-2012 Free Software Foundation, Inc.
This file is part of Bison, the GNU Compiler Compiler.
- Bison is free software; you can redistribute it and/or modify
+ This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2, or (at your option)
- any later version.
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
- Bison is distributed in the hope that it will be useful,
+ This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
- along with Bison; see the file COPYING. If not, write to
- the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
- Boston, MA 02110-1301, USA. */
+ along with this program. If not, see . */
#include
#include "system.h"
-#include
+#include
#include "complain.h"
#include "conflicts.h"
#include "files.h"
#include "getargs.h"
#include "gram.h"
-#include "muscle_tab.h"
+#include "muscle-tab.h"
#include "reader.h"
#include "symlist.h"
#include "symtab.h"
#include "scan-gram.h"
#include "scan-code.h"
+static void prepare_percent_define_front_end_variables (void);
static void check_and_convert_grammar (void);
static symbol_list *grammar = NULL;
@@ -69,27 +68,6 @@ grammar_start_symbol_set (symbol *sym, location loc)
}
}
-
-/*---------------------------------------------------------------------.
-| There are two prologues: one before the first %union and one after. |
-| Augment the one specified by POST. |
-`---------------------------------------------------------------------*/
-
-void
-prologue_augment (const char *prologue, location loc, bool post)
-{
- struct obstack *oout =
- !post ? &pre_prologue_obstack : &post_prologue_obstack;
-
- obstack_fgrow1 (oout, "]b4_syncline(%d, [[", loc.start.line);
- /* FIXME: Protection of M4 characters missing here. See
- output.c:escaped_output. */
- MUSCLE_OBSTACK_SGROW (oout,
- quotearg_style (c_quoting_style, loc.start.file));
- obstack_sgrow (oout, "]])[\n");
- obstack_sgrow (oout, prologue);
-}
-
/*------------------------------------------------------------------------.
@@ -150,12 +128,16 @@ record_merge_function_type (int merger, uniqstr type, location declaration_loc)
aver (merge_function != NULL && merger_find == merger);
if (merge_function->type != NULL && !UNIQSTR_EQ (merge_function->type, type))
{
- complain_at (declaration_loc,
- _("result type clash on merge function `%s': <%s> != <%s>"),
- merge_function->name, type, merge_function->type);
- complain_at (merge_function->type_declaration_location,
- _("previous declaration"));
- }
+ unsigned indent = 0;
+ complain_at_indent (declaration_loc, &indent,
+ _("result type clash on merge function %s: "
+ "<%s> != <%s>"),
+ quote (merge_function->name), type,
+ merge_function->type);
+ indent += SUB_INDENT;
+ complain_at_indent (merge_function->type_declaration_location, &indent,
+ _("previous declaration"));
+ }
merge_function->type = uniqstr_new (type);
merge_function->type_declaration_location = declaration_loc;
}
@@ -192,7 +174,7 @@ free_merger_functions (void)
static symbol_list *grammar_end = NULL;
/* Append SYM to the grammar. */
-static void
+static symbol_list *
grammar_symbol_append (symbol *sym, location loc)
{
symbol_list *p = symbol_list_sym_new (sym, loc);
@@ -208,8 +190,27 @@ grammar_symbol_append (symbol *sym, location loc)
part of it. */
if (sym)
++nritems;
+
+ return p;
+}
+
+static void
+assign_named_ref (symbol_list *p, named_ref *name)
+{
+ symbol *sym = p->content.sym;
+
+ if (name->id == sym->tag)
+ {
+ warn_at (name->loc,
+ _("duplicated symbol name for %s ignored"),
+ quote (sym->tag));
+ named_ref_free (name);
+ }
+ else
+ p->named_ref = name;
}
+
/* The rule currently being defined, and the previous rule.
CURRENT_RULE points to the first LHS of the current rule, while
PREVIOUS_RULE_END points to the *end* of the previous rule (NULL). */
@@ -222,12 +223,19 @@ static symbol_list *previous_rule_end = NULL;
`----------------------------------------------*/
void
-grammar_current_rule_begin (symbol *lhs, location loc)
+grammar_current_rule_begin (symbol *lhs, location loc,
+ named_ref *lhs_name)
{
+ symbol_list* p;
+
/* Start a new rule and record its lhs. */
++nrules;
previous_rule_end = grammar_end;
- grammar_symbol_append (lhs, loc);
+
+ p = grammar_symbol_append (lhs, loc);
+ if (lhs_name)
+ assign_named_ref (p, named_ref_copy (lhs_name));
+
current_rule = grammar_end;
/* Mark the rule's lhs as a nonterminal if not already so. */
@@ -245,22 +253,25 @@ grammar_current_rule_begin (symbol *lhs, location loc)
/*----------------------------------------------------------------------.
| A symbol should be used if either: |
| 1. It has a destructor. |
-| 2. --warnings=midrule-values and the symbol is a mid-rule symbol |
-| (i.e., the generated LHS replacing a mid-rule action) that was |
-| assigned to or used, as in "exp: { $$ = 1; } { $$ = $1; }". |
+| 2. The symbol is a mid-rule symbol (i.e., the generated LHS |
+| replacing a mid-rule action) that was assigned to or used, as in |
+| "exp: { $$ = 1; } { $$ = $1; }". |
`----------------------------------------------------------------------*/
static bool
-symbol_should_be_used (symbol_list const *s)
+symbol_should_be_used (symbol_list const *s, bool *midrule_warning)
{
- if (symbol_destructor_get (s->content.sym))
+ if (symbol_destructor_get (s->content.sym)->code)
return true;
- if (warnings_flag & warnings_midrule_values)
- return ((s->midrule && s->midrule->action_props.is_value_used)
- || (s->midrule_parent_rule
- && symbol_list_n_get (s->midrule_parent_rule,
- s->midrule_parent_rhs_index)
- ->action_props.is_value_used));
+ if ((s->midrule && s->midrule->action_props.is_value_used)
+ || (s->midrule_parent_rule
+ && symbol_list_n_get (s->midrule_parent_rule,
+ s->midrule_parent_rhs_index)
+ ->action_props.is_value_used))
+ {
+ *midrule_warning = true;
+ return true;
+ }
return false;
}
@@ -304,17 +315,31 @@ grammar_rule_check (const symbol_list *r)
symbol_list const *l = r;
int n = 0;
for (; l && l->content.sym; l = l->next, ++n)
- if (! (l->action_props.is_value_used
- || !symbol_should_be_used (l)
- /* The default action, $$ = $1, `uses' both. */
- || (!r->action_props.code && (n == 0 || n == 1))))
- {
- if (n)
- warn_at (r->location, _("unused value: $%d"), n);
- else
- warn_at (r->location, _("unset value: $$"));
- }
+ {
+ bool midrule_warning = false;
+ if (!l->action_props.is_value_used
+ && symbol_should_be_used (l, &midrule_warning)
+ /* The default action, $$ = $1, `uses' both. */
+ && (r->action_props.code || (n != 0 && n != 1)))
+ {
+ void (*warn_at_ptr)(location, char const*, ...) =
+ midrule_warning ? midrule_value_at : warn_at;
+ if (n)
+ warn_at_ptr (r->location, _("unused value: $%d"), n);
+ else
+ warn_at_ptr (r->location, _("unset value: $$"));
+ }
+ }
}
+
+ /* See comments in grammar_current_rule_prec_set for how POSIX
+ mandates this complaint. It's only for identifiers, so skip
+ it for char literals and strings, which are always tokens. */
+ if (r->ruleprec
+ && r->ruleprec->tag[0] != '\'' && r->ruleprec->tag[0] != '"'
+ && !r->ruleprec->declared && !r->ruleprec->prec)
+ warn_at (r->location, _("token for %%prec is not defined: %s"),
+ r->ruleprec->tag);
}
@@ -351,6 +376,9 @@ grammar_midrule_action (void)
symbol *dummy = dummy_symbol_get (dummy_location);
symbol_list *midrule = symbol_list_sym_new (dummy, dummy_location);
+ /* Remember named_ref of previous action. */
+ named_ref *action_name = current_rule->action_props.named_ref;
+
/* Make a new rule, whose body is empty, before the current one, so
that the action just read can belong to it. */
++nrules;
@@ -360,7 +388,7 @@ grammar_midrule_action (void)
code_props_rule_action_init (&midrule->action_props,
current_rule->action_props.code,
current_rule->action_props.location,
- midrule);
+ midrule, 0);
code_props_none_init (¤t_rule->action_props);
if (previous_rule_end)
@@ -376,7 +404,8 @@ grammar_midrule_action (void)
/* Insert the dummy nonterminal replacing the midrule action into
the current rule. Bind it to its dedicated rule. */
- grammar_current_rule_symbol_append (dummy, dummy_location);
+ grammar_current_rule_symbol_append (dummy, dummy_location,
+ action_name);
grammar_end->midrule = midrule;
midrule->midrule_parent_rule = current_rule;
midrule->midrule_parent_rhs_index = symbol_list_length (current_rule->next);
@@ -387,6 +416,16 @@ grammar_midrule_action (void)
void
grammar_current_rule_prec_set (symbol *precsym, location loc)
{
+ /* POSIX says that any identifier is a nonterminal if it does not
+ appear on the LHS of a grammar rule and is not defined by %token
+ or by one of the directives that assigns precedence to a token. We
+ ignore this here because the only kind of identifier that POSIX
+ allows to follow a %prec is a token and because assuming it's a
+ token now can produce more logical error messages. Nevertheless,
+ grammar_rule_check does obey what we believe is the real intent of
+ POSIX here: that an error be reported for any identifier that
+ appears after %prec but that is not defined separately as a
+ token. */
symbol_class_set (precsym, token_sym, loc, false);
if (current_rule->ruleprec)
complain_at (loc, _("only one %s allowed per rule"), "%prec");
@@ -425,24 +464,29 @@ grammar_current_rule_merge_set (uniqstr name, location loc)
action as a mid-rule action. */
void
-grammar_current_rule_symbol_append (symbol *sym, location loc)
+grammar_current_rule_symbol_append (symbol *sym, location loc,
+ named_ref *name)
{
+ symbol_list *p;
if (current_rule->action_props.code)
grammar_midrule_action ();
- grammar_symbol_append (sym, loc);
+ p = grammar_symbol_append (sym, loc);
+ if (name)
+ assign_named_ref(p, name);
}
/* Attach an ACTION to the current rule. */
void
-grammar_current_rule_action_append (const char *action, location loc)
+grammar_current_rule_action_append (const char *action, location loc,
+ named_ref *name)
{
if (current_rule->action_props.code)
grammar_midrule_action ();
/* After all symbol declarations have been parsed, packgram invokes
code_props_translate_code. */
code_props_rule_action_init (¤t_rule->action_props, action, loc,
- current_rule);
+ current_rule, name);
}
@@ -465,20 +509,6 @@ packgram (void)
rules = xnmalloc (nrules, sizeof *rules);
- /* Before invoking grammar_rule_check on any rule, make sure all actions have
- already been scanned in order to set `used' flags. Otherwise, checking
- that a midrule's $$ should be set will not always work properly because
- the check must forward-reference the midrule's parent rule. For the same
- reason, all the `used' flags must be set before checking whether to remove
- `$' from any midrule symbol name. */
- while (p)
- {
- code_props_translate_code (&p->action_props);
- if (p)
- p = p->next;
- }
-
- p = grammar;
while (p)
{
int rule_length = 0;
@@ -585,16 +615,13 @@ reader (void)
undeftoken->class = token_sym;
undeftoken->number = ntokens++;
- /* Initialize the obstacks. */
- obstack_init (&pre_prologue_obstack);
- obstack_init (&post_prologue_obstack);
-
gram_in = xfopen (grammar_file, "r");
gram__flex_debug = trace_flag & trace_scan;
gram_debug = trace_flag & trace_parse;
gram_scanner_initialize ();
gram_parse ();
+ prepare_percent_define_front_end_variables ();
if (! complaint_issued)
check_and_convert_grammar ();
@@ -602,6 +629,35 @@ reader (void)
xfclose (gram_in);
}
+static void
+prepare_percent_define_front_end_variables (void)
+{
+ /* Set %define front-end variable defaults. */
+ muscle_percent_define_default ("lr.keep-unreachable-states", "false");
+ {
+ char *lr_type;
+ /* IELR would be a better default, but LALR is historically the
+ default. */
+ muscle_percent_define_default ("lr.type", "lalr");
+ lr_type = muscle_percent_define_get ("lr.type");
+ if (0 != strcmp (lr_type, "canonical-lr"))
+ muscle_percent_define_default ("lr.default-reductions", "most");
+ else
+ muscle_percent_define_default ("lr.default-reductions", "accepting");
+ free (lr_type);
+ }
+
+ /* Check %define front-end variables. */
+ {
+ static char const * const values[] = {
+ "lr.type", "lalr", "ielr", "canonical-lr", NULL,
+ "lr.default-reductions", "most", "consistent", "accepting", NULL,
+ NULL
+ };
+ muscle_percent_define_check_values (values);
+ }
+}
+
/*-------------------------------------------------------------.
| Check the grammar that has just been read, and convert it to |
@@ -615,9 +671,6 @@ check_and_convert_grammar (void)
if (nrules == 0)
fatal (_("no rules in the input grammar"));
- /* Report any undefined symbols and consider them nonterminals. */
- symbols_check_defined ();
-
/* If the user did not define her ENDTOKEN, do it now. */
if (!endtoken)
{
@@ -628,6 +681,9 @@ check_and_convert_grammar (void)
endtoken->user_token_number = 0;
}
+ /* Report any undefined symbols and consider them nonterminals. */
+ symbols_check_defined ();
+
/* Find the start symbol if no %start. */
if (!start_flag)
{
@@ -668,6 +724,23 @@ check_and_convert_grammar (void)
token symbols into FDEFINES if requested. */
symbols_pack ();
+ /* Scan rule actions after invoking symbol_check_alias_consistency (in
+ symbols_pack above) so that token types are set correctly before the rule
+ action type checking.
+
+ Before invoking grammar_rule_check (in packgram below) on any rule, make
+ sure all actions have already been scanned in order to set `used' flags.
+ Otherwise, checking that a midrule's $$ should be set will not always work
+ properly because the check must forward-reference the midrule's parent
+ rule. For the same reason, all the `used' flags must be set before
+ checking whether to remove `$' from any midrule symbol name (also in
+ packgram). */
+ {
+ symbol_list *sym;
+ for (sym = grammar; sym; sym = sym->next)
+ code_props_translate_code (&sym->action_props);
+ }
+
/* Convert the grammar into the format described in gram.h. */
packgram ();