mirror of
https://git.savannah.gnu.org/git/bison.git
synced 2026-03-09 20:33:03 +00:00
This patch contains more fixes to prefer signed to unsigned integer types, as modern tools like 'gcc -fsanitize=undefined' can check for signed integer overflow but not unsigned overflow. * NEWS: Document the API change. * boostrap.conf (gnulib_modules): Add intprops. * data/skeletons/glr.c: Include stddef.h and stdint.h, since this skeleton can assume C99 or later. (YYSIZEMAX): Now signed, and the minimum of SIZE_MAX and PTRDIFF_MAX. (yybool) [!__cplusplus]: Now signed (which is how bool behaves). (YYTRANSLATE): Avoid use of unsigned, and make the macro safe even for values greater than UINT_MAX. (yytnamerr, struct yyGLRState, struct yyGLRStateSet, struct yyGLRStack) (yyaddDeferredAction, yyinitStateSet, yyinitGLRStack) (yyexpandGLRStack, yymarkStackDeleted, yyremoveDeletes) (yyglrShift, yyglrShiftDefer, yy_reduce_print, yydoAction) (yyglrReduce, yysplitStack, yyreportTree, yycompressStack) (yyprocessOneStack, yyreportSyntaxError, yyrecoverSyntaxError) (yyparse, yy_yypstack, yypstack, yypdumpstack): * tests/input.at (Torturing the Scanner): Prefer ptrdiff_t to size_t. * data/skeletons/c++.m4 (b4_yytranslate_define): * src/AnnotationList.c (AnnotationList__computePredecessorAnnotations): * src/AnnotationList.h (AnnotationIndex): * src/InadequacyList.h (InadequacyListNodeCount): * src/closure.c (closure_new): * src/complain.c (error_message, complains, complain_indent) (complain_args, duplicate_directive, duplicate_rule_directive): * src/gram.c (nritems, ritem_print, grammar_dump): * src/ielr.c (ielr_compute_ritem_sees_lookahead_set) (ielr_item_has_lookahead, ielr_compute_annotation_lists) (ielr_compute_lookaheads): * src/location.c (columns, boundary_print, location_print): * src/muscle-tab.c (muscle_percent_define_insert) (muscle_percent_define_check_values): * src/output.c (prepare_rules, prepare_actions): * src/parse-gram.y (id, handle_require): * src/reader.c (record_merge_function_type, packgram): * src/reduce.c (nuseless_productions, nuseless_nonterminals) (inaccessable_symbols): * src/relation.c (relation_print): * src/scan-code.l (variant, variant_table_size, variant_count) (variant_add, get_at_spec, show_sub_message, show_sub_messages) (parse_ref): * src/scan-gram.l (<SC_ESCAPED_STRING,SC_ESCAPED_CHARACTER>) (scan_integer, convert_ucn_to_byte, handle_syncline): * src/scan-skel.l (at_complain): * src/symtab.c (complain_symbol_redeclared) (complain_semantic_type_redeclared, complain_class_redeclared) (symbol_class_set, complain_user_token_number_redeclared): * src/tables.c (conflict_tos, conflrow, conflict_table) (conflict_list, save_row, pack_vector): * tests/local.at (AT_YYLEX_DEFINE(c)): Prefer signed to unsigned integer. * data/skeletons/lalr1.cc (yy_lac_check_): * tests/actions.at (_AT_CHECK_PRINTER_AND_DESTRUCTOR): * tests/local.at (AT_YYLEX_DEFINE(c)): Omit now-unnecessary casts. * data/skeletons/location.cc (b4_location_define): * doc/bison.texi (Mfcalc Lexer, C++ position, C++ location): Prefer int to unsigned for line and column numbers. Change example to abort explicitly on memory exhaustion, and fix an off-by-one bug that led to undefined behavior. * data/skeletons/stack.hh (stack::operator[]): Also allow ptrdiff_t indexes. (stack::pop, slice::slice, slice::operator[]): Index arg is now ptrdiff_t, not int. (stack::ssize): New method. (slice::range_): Now ptrdiff_t, not int. * data/skeletons/yacc.c (b4_state_num_type): Remove. All uses replaced by b4_int_type. (YY_CONVERT_INT_BEGIN, YY_CONVERT_INT_END): New macros. (yylac, yyparse): Use them around conversions that -Wconversion would give false alarms about. Omit unnecessary casts. (yy_stack_print): Use int rather than unsigned, and omit a cast that doesn’t seem to be needed here any more. * examples/c++/variant.yy (yylex): * examples/c++/variant-11.yy (yylex): Omit no-longer-needed conversions to unsigned. * src/InadequacyList.c (InadequacyList__new_conflict): Don’t assume *node_count is unsigned. * src/output.c (muscle_insert_unsigned_table): Remove; no longer used.
236 lines
6.5 KiB
C
236 lines
6.5 KiB
C
/* Closures for Bison
|
||
|
||
Copyright (C) 1984, 1989, 2000-2002, 2004-2005, 2007, 2009-2015,
|
||
2018-2019 Free Software Foundation, Inc.
|
||
|
||
This file is part of Bison, the GNU Compiler Compiler.
|
||
|
||
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 3 of the License, or
|
||
(at your option) any later version.
|
||
|
||
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 this program. If not, see <http://www.gnu.org/licenses/>. */
|
||
|
||
#include <config.h>
|
||
#include "system.h"
|
||
|
||
#include <bitset.h>
|
||
#include <bitsetv.h>
|
||
|
||
#include "closure.h"
|
||
#include "derives.h"
|
||
#include "getargs.h"
|
||
#include "gram.h"
|
||
#include "reader.h"
|
||
#include "symtab.h"
|
||
|
||
/* NITEMSET is the size of the array ITEMSET. */
|
||
item_number *itemset;
|
||
size_t nitemset;
|
||
|
||
/* RULESET contains a bit for each rule. CLOSURE sets the bits for
|
||
all rules which could potentially describe the next input to be
|
||
read. */
|
||
static bitset ruleset;
|
||
|
||
/* internal data. See comments before set_fderives and set_firsts. */
|
||
static bitsetv fderives = NULL;
|
||
static bitsetv firsts = NULL;
|
||
|
||
/* Retrieve the FDERIVES/FIRSTS sets of the nonterminals numbered Var. */
|
||
#define FDERIVES(Var) fderives[(Var) - ntokens]
|
||
#define FIRSTS(Var) firsts[(Var) - ntokens]
|
||
|
||
|
||
/*-----------------.
|
||
| Debugging code. |
|
||
`-----------------*/
|
||
|
||
static void
|
||
closure_print (char const *title, item_number const *array, size_t size)
|
||
{
|
||
fprintf (stderr, "Closure: %s\n", title);
|
||
for (size_t i = 0; i < size; ++i)
|
||
{
|
||
fprintf (stderr, " %2d: .", array[i]);
|
||
item_number *rp;
|
||
for (rp = &ritem[array[i]]; *rp >= 0; ++rp)
|
||
fprintf (stderr, " %s", symbols[*rp]->tag);
|
||
fprintf (stderr, " (rule %d)\n", -*rp - 1);
|
||
}
|
||
fputs ("\n\n", stderr);
|
||
}
|
||
|
||
|
||
static void
|
||
print_firsts (void)
|
||
{
|
||
fprintf (stderr, "FIRSTS\n");
|
||
for (symbol_number i = ntokens; i < nsyms; ++i)
|
||
{
|
||
fprintf (stderr, " %s firsts\n", symbols[i]->tag);
|
||
bitset_iterator iter;
|
||
symbol_number j;
|
||
BITSET_FOR_EACH (iter, FIRSTS (i), j, 0)
|
||
fprintf (stderr, " %s\n", symbols[j + ntokens]->tag);
|
||
}
|
||
fprintf (stderr, "\n\n");
|
||
}
|
||
|
||
|
||
static void
|
||
print_fderives (void)
|
||
{
|
||
fprintf (stderr, "FDERIVES\n");
|
||
for (symbol_number i = ntokens; i < nsyms; ++i)
|
||
{
|
||
fprintf (stderr, " %s derives\n", symbols[i]->tag);
|
||
bitset_iterator iter;
|
||
rule_number r;
|
||
BITSET_FOR_EACH (iter, FDERIVES (i), r, 0)
|
||
{
|
||
fprintf (stderr, " %3d ", r);
|
||
rule_rhs_print (&rules[r], stderr);
|
||
fprintf (stderr, "\n");
|
||
}
|
||
}
|
||
fprintf (stderr, "\n\n");
|
||
}
|
||
|
||
/*------------------------------------------------------------------.
|
||
| Set FIRSTS to be an NVARS array of NVARS bitsets indicating which |
|
||
| items can represent the beginning of the input corresponding to |
|
||
| which other items. |
|
||
| |
|
||
| For example, if some rule expands symbol 5 into the sequence of |
|
||
| symbols 8 3 20, the symbol 8 can be the beginning of the data for |
|
||
| symbol 5, so the bit [8 - ntokens] in first[5 - ntokens] (= FIRST |
|
||
| (5)) is set. |
|
||
`------------------------------------------------------------------*/
|
||
|
||
static void
|
||
set_firsts (void)
|
||
{
|
||
firsts = bitsetv_create (nvars, nvars, BITSET_FIXED);
|
||
|
||
for (symbol_number i = ntokens; i < nsyms; ++i)
|
||
for (symbol_number j = 0; derives[i - ntokens][j]; ++j)
|
||
{
|
||
item_number sym = derives[i - ntokens][j]->rhs[0];
|
||
if (ISVAR (sym))
|
||
bitset_set (FIRSTS (i), sym - ntokens);
|
||
}
|
||
|
||
if (trace_flag & trace_sets)
|
||
bitsetv_matrix_dump (stderr, "RTC: Firsts Input", firsts);
|
||
bitsetv_reflexive_transitive_closure (firsts);
|
||
if (trace_flag & trace_sets)
|
||
bitsetv_matrix_dump (stderr, "RTC: Firsts Output", firsts);
|
||
|
||
if (trace_flag & trace_sets)
|
||
print_firsts ();
|
||
}
|
||
|
||
/*-------------------------------------------------------------------.
|
||
| Set FDERIVES to an NVARS by NRULES matrix of bits indicating which |
|
||
| rules can help derive the beginning of the data for each |
|
||
| nonterminal. |
|
||
| |
|
||
| For example, if symbol 5 can be derived as the sequence of symbols |
|
||
| 8 3 20, and one of the rules for deriving symbol 8 is rule 4, then |
|
||
| the [5 - NTOKENS, 4] bit in FDERIVES is set. |
|
||
`-------------------------------------------------------------------*/
|
||
|
||
static void
|
||
set_fderives (void)
|
||
{
|
||
fderives = bitsetv_create (nvars, nrules, BITSET_FIXED);
|
||
|
||
set_firsts ();
|
||
|
||
for (symbol_number i = ntokens; i < nsyms; ++i)
|
||
for (symbol_number j = ntokens; j < nsyms; ++j)
|
||
if (bitset_test (FIRSTS (i), j - ntokens))
|
||
for (rule_number k = 0; derives[j - ntokens][k]; ++k)
|
||
bitset_set (FDERIVES (i), derives[j - ntokens][k]->number);
|
||
|
||
if (trace_flag & trace_sets)
|
||
print_fderives ();
|
||
|
||
bitsetv_free (firsts);
|
||
}
|
||
|
||
|
||
|
||
void
|
||
closure_new (int n)
|
||
{
|
||
itemset = xnmalloc (n, sizeof *itemset);
|
||
|
||
ruleset = bitset_create (nrules, BITSET_FIXED);
|
||
|
||
set_fderives ();
|
||
}
|
||
|
||
|
||
|
||
void
|
||
closure (item_number const *core, size_t n)
|
||
{
|
||
if (trace_flag & trace_closure)
|
||
closure_print ("input", core, n);
|
||
|
||
bitset_zero (ruleset);
|
||
|
||
for (size_t c = 0; c < n; ++c)
|
||
if (ISVAR (ritem[core[c]]))
|
||
bitset_or (ruleset, ruleset, FDERIVES (ritem[core[c]]));
|
||
|
||
/* core is sorted on item index in ritem, which is sorted on rule number.
|
||
Compute itemset with the same sort. */
|
||
nitemset = 0;
|
||
size_t c = 0;
|
||
|
||
/* A bit index over RULESET. */
|
||
rule_number ruleno;
|
||
bitset_iterator iter;
|
||
BITSET_FOR_EACH (iter, ruleset, ruleno, 0)
|
||
{
|
||
item_number itemno = rules[ruleno].rhs - ritem;
|
||
while (c < n && core[c] < itemno)
|
||
{
|
||
itemset[nitemset] = core[c];
|
||
nitemset++;
|
||
c++;
|
||
}
|
||
itemset[nitemset] = itemno;
|
||
nitemset++;
|
||
};
|
||
|
||
while (c < n)
|
||
{
|
||
itemset[nitemset] = core[c];
|
||
nitemset++;
|
||
c++;
|
||
}
|
||
|
||
if (trace_flag & trace_closure)
|
||
closure_print ("output", itemset, nitemset);
|
||
}
|
||
|
||
|
||
void
|
||
closure_free (void)
|
||
{
|
||
free (itemset);
|
||
bitset_free (ruleset);
|
||
bitsetv_free (fderives);
|
||
}
|