diff options
author | Florian Weimer <fweimer@redhat.com> | 2018-07-10 11:18:26 +0200 |
---|---|---|
committer | Florian Weimer <fweimer@redhat.com> | 2018-07-10 11:18:26 +0200 |
commit | 7b2f4cedf044ea83f53f6b43a5bf6871eb9ce969 (patch) | |
tree | 4e579c9471bc1d2d1a799ba005023fc7a7f4440b /posix | |
parent | 4fa34da6793c442255fc003cf659c85b197ab29a (diff) | |
download | glibc-7b2f4cedf044ea83f53f6b43a5bf6871eb9ce969.zip glibc-7b2f4cedf044ea83f53f6b43a5bf6871eb9ce969.tar.gz glibc-7b2f4cedf044ea83f53f6b43a5bf6871eb9ce969.tar.bz2 |
regexec: Fix off-by-one bug in weight comparison [BZ #23036]
Each weight is prefixed by its length, and the length does not include
itself in the count. This can be seen clearly from the find_idx
function in string/strxfrm_l.c, for example. The old code behaved as if
the length itself counted, thus comparing an additional byte after the
weight, leading to spurious comparison failures and incorrect further
partitioning of character equivalence classes.
Diffstat (limited to 'posix')
-rw-r--r-- | posix/regexec.c | 43 |
1 files changed, 20 insertions, 23 deletions
diff --git a/posix/regexec.c b/posix/regexec.c index 63aef97..73644c2 100644 --- a/posix/regexec.c +++ b/posix/regexec.c @@ -3878,30 +3878,27 @@ check_node_accept_bytes (const re_dfa_t *dfa, Idx node_idx, indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTMB); int32_t idx = findidx (table, indirect, extra, &cp, elem_len); + int32_t rule = idx >> 24; + idx &= 0xffffff; if (idx > 0) - for (i = 0; i < cset->nequiv_classes; ++i) - { - int32_t equiv_class_idx = cset->equiv_classes[i]; - size_t weight_len = weights[idx & 0xffffff]; - if (weight_len == weights[equiv_class_idx & 0xffffff] - && (idx >> 24) == (equiv_class_idx >> 24)) - { - Idx cnt = 0; - - idx &= 0xffffff; - equiv_class_idx &= 0xffffff; - - while (cnt <= weight_len - && (weights[equiv_class_idx + 1 + cnt] - == weights[idx + 1 + cnt])) - ++cnt; - if (cnt > weight_len) - { - match_len = elem_len; - goto check_node_accept_bytes_match; - } - } - } + { + size_t weight_len = weights[idx]; + for (i = 0; i < cset->nequiv_classes; ++i) + { + int32_t equiv_class_idx = cset->equiv_classes[i]; + int32_t equiv_class_rule = equiv_class_idx >> 24; + equiv_class_idx &= 0xffffff; + if (weights[equiv_class_idx] == weight_len + && equiv_class_rule == rule + && memcmp (weights + idx + 1, + weights + equiv_class_idx + 1, + weight_len) == 0) + { + match_len = elem_len; + goto check_node_accept_bytes_match; + } + } + } } } else |