Mercurial > gnulib
diff lib/regcomp.c @ 6171:5862ee08bfc1
* lib/regcomp.c (re_compile_fastmap_iter, init_dfa, init_word_char):
(optimize_subexps, lower_subexp):
Don't assume 1<<31 has defined behavior on hosts with 32-bit int,
since the signed shift might overflow. Use 1u<<31 instead.
* lib/regex_internal.h (bitset_set, bitset_clear, bitset_contain):
Likewise.
* lib/regexec.c (check_dst_limits_calc_pos_1):
(check_subexp_matching_top): Likewise.
* lib/regcomp.c (optimize_subexps, lower_subexp):
Use CHAR_BIT rather than 8, for clarity.
* lib/regexec.c (check_dst_limits_calc_pos_1):
(check_subexp_matching_top): Likewise.
* lib/regcomp.c (init_dfa): Make table_size unsigned, so that we don't
have to worry about portability issues when shifting it left.
Remove no-longer-needed test for table_size > 0.
* lib/regcomp.c (parse_sub_exp): Do not shift more bits than there are
in a word, as the resulting behavior is undefined.
* lib/regexec.c (check_dst_limits_calc_pos_1): Likewise;
in one case, a <= should have been an <, and in another case the
whole test was missing.
* lib/regex_internal.h (BYTE_BITS): Remove. All uses changed to
the standard name CHAR_BIT.
* lib/regexec.c (match_ctx_add_entry): Don't assume that ~0 == -1;
this is not true on one's complement and signed-magnitude hosts.
| author | Paul Eggert <eggert@cs.ucla.edu> |
|---|---|
| date | Wed, 31 Aug 2005 19:38:13 +0000 |
| parents | a10e4460ad4c |
| children | 6039b763ad3c |
line wrap: on
line diff
--- a/lib/regcomp.c Wed Aug 31 18:08:34 2005 +0000 +++ b/lib/regcomp.c Wed Aug 31 19:38:13 2005 +0000 @@ -336,7 +336,7 @@ int i, j, ch; for (i = 0, ch = 0; i < BITSET_UINTS; ++i) for (j = 0; j < UINT_BITS; ++j, ++ch) - if (dfa->nodes[node].opr.sbcset[i] & (1 << j)) + if (dfa->nodes[node].opr.sbcset[i] & (1u << j)) re_set_fastmap (fastmap, icase, ch); } #ifdef RE_ENABLE_I18N @@ -798,7 +798,7 @@ static reg_errcode_t init_dfa (re_dfa_t *dfa, int pat_len) { - int table_size; + unsigned int table_size; #ifndef _LIBC char *codeset_name; #endif @@ -812,7 +812,7 @@ dfa->nodes = re_malloc (re_token_t, dfa->nodes_alloc); /* table_size = 2 ^ ceil(log pat_len) */ - for (table_size = 1; table_size > 0; table_size <<= 1) + for (table_size = 1; ; table_size <<= 1) if (table_size > pat_len) break; @@ -872,7 +872,7 @@ { wint_t wch = __btowc (ch); if (wch != WEOF) - dfa->sb_char[i] |= 1 << j; + dfa->sb_char[i] |= 1u << j; # ifndef _LIBC if (isascii (ch) && wch != ch) dfa->map_notascii = 1; @@ -899,7 +899,7 @@ for (i = 0, ch = 0; i < BITSET_UINTS; ++i) for (j = 0; j < UINT_BITS; ++j, ++ch) if (isalnum (ch) || ch == '_') - dfa->word_char[i] |= 1 << j; + dfa->word_char[i] |= 1u << j; } /* Free the work area which are only used while compiling. */ @@ -1222,8 +1222,8 @@ node->left->parent = node; dfa->subexp_map[other_idx] = dfa->subexp_map[node->token.opr.idx]; - if (other_idx < 8 * sizeof (dfa->used_bkref_map)) - dfa->used_bkref_map &= ~(1 << other_idx); + if (other_idx < CHAR_BIT * sizeof dfa->used_bkref_map) + dfa->used_bkref_map &= ~(1u << other_idx); } return REG_NOERROR; @@ -1266,8 +1266,8 @@ very common, so we do not lose much. An example that triggers this case is the sed "script" /\(\)/x. */ && node->left != NULL - && (node->token.opr.idx >= 8 * sizeof (dfa->used_bkref_map) - || !(dfa->used_bkref_map & (1 << node->token.opr.idx)))) + && (node->token.opr.idx >= CHAR_BIT * sizeof dfa->used_bkref_map + || !(dfa->used_bkref_map & (1u << node->token.opr.idx)))) return node->left; /* Convert the SUBEXP node to the concatenation of an @@ -2380,7 +2380,9 @@ if (BE (*err != REG_NOERROR, 0)) return NULL; } - dfa->completed_bkref_map |= 1 << cur_nsub; + + if (cur_nsub <= '9' - '1') + dfa->completed_bkref_map |= 1 << cur_nsub; tree = create_tree (dfa, tree, NULL, SUBEXP); if (BE (tree == NULL, 0))