X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Fregex_internal.c;h=f679f87eaa4b49ca0ed2ce1910247028502c3c7c;hb=fa1db0dd22768f09a507674a30beb5b8a87bb35f;hp=27c3d3f03ed844845ba47ad52e71cbf4e9499f8c;hpb=1602f0afed21be664fcf5c42d59db07cc22c56d6;p=gnulib.git diff --git a/lib/regex_internal.c b/lib/regex_internal.c index 27c3d3f03..f679f87ea 100644 --- a/lib/regex_internal.c +++ b/lib/regex_internal.c @@ -1,21 +1,21 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2012 Free Software Foundation, Inc. + Copyright (C) 2002-2013 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa . - 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 GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. - This program is distributed in the hope that it will be useful, + The GNU C Library 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. + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. - 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, see + . */ static void re_string_construct_common (const char *str, Idx len, re_string_t *pstr, @@ -134,9 +134,9 @@ re_string_realloc_buffers (re_string_t *pstr, Idx new_buf_len) { wint_t *new_wcs; - /* Avoid overflow. */ - size_t max_object_size = MAX (sizeof (wint_t), sizeof (Idx)); - if (BE (SIZE_MAX / max_object_size < new_buf_len, 0)) + /* Avoid overflow in realloc. */ + const size_t max_object_size = MAX (sizeof (wint_t), sizeof (Idx)); + if (BE (MIN (IDX_MAX, SIZE_MAX / max_object_size) < new_buf_len, 0)) return REG_ESPACE; new_wcs = re_realloc (pstr->wcs, wint_t, new_buf_len); @@ -236,13 +236,8 @@ build_wcs_buffer (re_string_t *pstr) else p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx; mbclen = __mbrtowc (&wc, p, remain_len, &pstr->cur_state); - if (BE (mbclen == (size_t) -2, 0)) - { - /* The buffer doesn't have enough space, finish to build. */ - pstr->cur_state = prev_st; - break; - } - else if (BE (mbclen == (size_t) -1 || mbclen == 0, 0)) + if (BE (mbclen == (size_t) -1 || mbclen == 0 + || (mbclen == (size_t) -2 && pstr->bufs_len >= pstr->len), 0)) { /* We treat these cases as a singlebyte character. */ mbclen = 1; @@ -251,6 +246,12 @@ build_wcs_buffer (re_string_t *pstr) wc = pstr->trans[wc]; pstr->cur_state = prev_st; } + else if (BE (mbclen == (size_t) -2, 0)) + { + /* The buffer doesn't have enough space, finish to build. */ + pstr->cur_state = prev_st; + break; + } /* Write wide character and padding. */ pstr->wcs[byte_idx++] = wc; @@ -333,9 +334,11 @@ build_wcs_upper_buffer (re_string_t *pstr) for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) pstr->wcs[byte_idx++] = WEOF; } - else if (mbclen == (size_t) -1 || mbclen == 0) + else if (mbclen == (size_t) -1 || mbclen == 0 + || (mbclen == (size_t) -2 && pstr->bufs_len >= pstr->len)) { - /* It is an invalid character or '\0'. Just use the byte. */ + /* It is an invalid character, an incomplete character + at the end of the string, or '\0'. Just use the byte. */ int ch = pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; pstr->mbs[byte_idx] = ch; /* And also cast it to wide char. */ @@ -448,7 +451,8 @@ build_wcs_upper_buffer (re_string_t *pstr) for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) pstr->wcs[byte_idx++] = WEOF; } - else if (mbclen == (size_t) -1 || mbclen == 0) + else if (mbclen == (size_t) -1 || mbclen == 0 + || (mbclen == (size_t) -2 && pstr->bufs_len >= pstr->len)) { /* It is an invalid character or '\0'. Just use the byte. */ int ch = pstr->raw_mbs[pstr->raw_mbs_idx + src_idx]; @@ -495,8 +499,7 @@ re_string_skip_chars (re_string_t *pstr, Idx new_raw_idx, wint_t *last_wc) rawbuf_idx < new_raw_idx;) { wchar_t wc2; - Idx remain_len; - remain_len = pstr->len - rawbuf_idx; + Idx remain_len = pstr->raw_len - rawbuf_idx; prev_st = pstr->cur_state; mbclen = __mbrtowc (&wc2, (const char *) pstr->raw_mbs + rawbuf_idx, remain_len, &pstr->cur_state); @@ -732,21 +735,21 @@ re_string_reconstruct (re_string_t *pstr, Idx idx, int eflags) mbstate_t cur_state; wchar_t wc2; Idx mlen = raw + pstr->len - p; + unsigned char buf[6]; size_t mbclen; -#if 0 /* dead code: buf is set but never used */ - unsigned char buf[6]; + const unsigned char *pp = p; if (BE (pstr->trans != NULL, 0)) { int i = mlen < 6 ? mlen : 6; while (--i >= 0) buf[i] = pstr->trans[p[i]]; + pp = buf; } -#endif /* XXX Don't use mbrtowc, we know which conversion to use (UTF-8 -> UCS4). */ memset (&cur_state, 0, sizeof (cur_state)); - mbclen = __mbrtowc (&wc2, (const char *) p, mlen, + mbclen = __mbrtowc (&wc2, (const char *) pp, mlen, &cur_state); if (raw + offset - p <= mbclen && mbclen < (size_t) -2) @@ -831,7 +834,7 @@ re_string_reconstruct (re_string_t *pstr, Idx idx, int eflags) } static unsigned char -internal_function __attribute ((pure)) +internal_function __attribute__ ((pure)) re_string_peek_byte_case (const re_string_t *pstr, Idx idx) { int ch; @@ -868,7 +871,7 @@ re_string_peek_byte_case (const re_string_t *pstr, Idx idx) } static unsigned char -internal_function __attribute ((pure)) +internal_function re_string_fetch_byte_case (re_string_t *pstr) { if (BE (!pstr->mbs_allocated, 1)) @@ -971,7 +974,7 @@ re_node_set_alloc (re_node_set *set, Idx size) set->alloc = size; set->nelem = 0; set->elems = re_malloc (Idx, size); - if (BE (set->elems == NULL, 0)) + if (BE (set->elems == NULL, 0) && (MALLOC_0_IS_NONNULL || size != 0)) return REG_ESPACE; return REG_NOERROR; } @@ -1351,7 +1354,7 @@ re_node_set_insert_last (re_node_set *set, Idx elem) Return true if SET1 and SET2 are equivalent. */ static bool -internal_function __attribute ((pure)) +internal_function __attribute__ ((pure)) re_node_set_compare (const re_node_set *set1, const re_node_set *set2) { Idx i; @@ -1366,7 +1369,7 @@ re_node_set_compare (const re_node_set *set1, const re_node_set *set2) /* Return (idx + 1) if SET contains the element ELEM, return 0 otherwise. */ static Idx -internal_function __attribute ((pure)) +internal_function __attribute__ ((pure)) re_node_set_contains (const re_node_set *set, Idx elem) { __re_size_t idx, right, mid; @@ -1412,13 +1415,12 @@ re_dfa_add_node (re_dfa_t *dfa, re_token_t token) Idx *new_nexts, *new_indices; re_node_set *new_edests, *new_eclosures; re_token_t *new_nodes; - size_t max_object_size = - MAX (sizeof (re_token_t), - MAX (sizeof (re_node_set), - sizeof (Idx))); - /* Avoid overflows. */ - if (BE (SIZE_MAX / 2 / max_object_size < dfa->nodes_alloc, 0)) + /* Avoid overflows in realloc. */ + const size_t max_object_size = MAX (sizeof (re_token_t), + MAX (sizeof (re_node_set), + sizeof (Idx))); + if (BE (MIN (IDX_MAX, SIZE_MAX / max_object_size) < new_nodes_alloc, 0)) return REG_MISSING; new_nodes = re_realloc (dfa->nodes, re_token_t, new_nodes_alloc); @@ -1441,11 +1443,9 @@ re_dfa_add_node (re_dfa_t *dfa, re_token_t token) dfa->nodes[dfa->nodes_len] = token; dfa->nodes[dfa->nodes_len].constraint = 0; #ifdef RE_ENABLE_I18N - { - int type = token.type; dfa->nodes[dfa->nodes_len].accept_mb = - (type == OP_PERIOD && dfa->mb_cur_max > 1) || type == COMPLEX_BRACKET; - } + ((token.type == OP_PERIOD && dfa->mb_cur_max > 1) + || token.type == COMPLEX_BRACKET); #endif dfa->nexts[dfa->nodes_len] = REG_MISSING; re_node_set_init_empty (dfa->edests + dfa->nodes_len); @@ -1453,7 +1453,7 @@ re_dfa_add_node (re_dfa_t *dfa, re_token_t token) return dfa->nodes_len++; } -static inline re_hashval_t +static re_hashval_t internal_function calc_state_hash (const re_node_set *nodes, unsigned int context) { @@ -1550,7 +1550,7 @@ re_acquire_state_context (reg_errcode_t *err, const re_dfa_t *dfa, && re_node_set_compare (state->entrance_nodes, nodes)) return state; } - /* There are no appropriate state in `dfa', create the new one. */ + /* There are no appropriate state in 'dfa', create the new one. */ new_state = create_cd_newstate (dfa, nodes, context, hash); if (BE (new_state == NULL, 0)) *err = REG_ESPACE; @@ -1579,7 +1579,7 @@ register_state (const re_dfa_t *dfa, re_dfastate_t *newstate, { Idx elem = newstate->nodes.elems[i]; if (!IS_EPSILON_NODE (dfa->nodes[elem].type)) - if (BE (! re_node_set_insert_last (&newstate->non_eps_nodes, elem), 0)) + if (! re_node_set_insert_last (&newstate->non_eps_nodes, elem)) return REG_ESPACE; } @@ -1614,7 +1614,7 @@ free_state (re_dfastate_t *state) re_free (state); } -/* Create the new state which is independ of contexts. +/* Create the new state which is independent of contexts. Return the new state if succeeded, otherwise return NULL. */ static re_dfastate_t *