From 4d8384337fec423e2aa433a2b2cf18c3f2831a83 Mon Sep 17 00:00:00 2001 From: Tim Shen Date: Thu, 23 Oct 2014 03:15:52 +0000 Subject: [PATCH] re PR libstdc++/63497 (std::regex can't handle [^class] correctly and cause runtime crash) PR libstdc++/63497 include/bits/regex_executor.h (_Executor::_M_word_boundary): Remove unused parameter. include/bits/regex_executor.tcc (_Executor::_M_dfs, _Executor::_M_word_boundary): Avoid dereferecing _M_current at _M_end or other invalid position. From-SVN: r216572 --- libstdc++-v3/ChangeLog | 9 +++++ libstdc++-v3/include/bits/regex_executor.h | 2 +- libstdc++-v3/include/bits/regex_executor.tcc | 39 +++++++++++--------- 3 files changed, 31 insertions(+), 19 deletions(-) diff --git a/libstdc++-v3/ChangeLog b/libstdc++-v3/ChangeLog index 9d1b1e5981c..4b1240d7e1a 100644 --- a/libstdc++-v3/ChangeLog +++ b/libstdc++-v3/ChangeLog @@ -1,3 +1,12 @@ +2014-10-23 Tim Shen + + PR libstdc++/63497 + include/bits/regex_executor.h (_Executor::_M_word_boundary): Remove + unused parameter. + include/bits/regex_executor.tcc (_Executor::_M_dfs, + _Executor::_M_word_boundary): Avoid dereferecing _M_current at _M_end + or other invalid position. + 2014-10-21 Joern Rennecke * testsuite/util/io/prog_bar.cc: Qualify size_t. diff --git a/libstdc++-v3/include/bits/regex_executor.h b/libstdc++-v3/include/bits/regex_executor.h index cd9e55d9689..b26992c9a4b 100644 --- a/libstdc++-v3/include/bits/regex_executor.h +++ b/libstdc++-v3/include/bits/regex_executor.h @@ -145,7 +145,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION } bool - _M_word_boundary(_State<_TraitsT> __state) const; + _M_word_boundary() const; bool _M_lookahead(_State<_TraitsT> __state); diff --git a/libstdc++-v3/include/bits/regex_executor.tcc b/libstdc++-v3/include/bits/regex_executor.tcc index 5eab85265a5..38d4781b0c5 100644 --- a/libstdc++-v3/include/bits/regex_executor.tcc +++ b/libstdc++-v3/include/bits/regex_executor.tcc @@ -274,7 +274,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION _M_dfs(__match_mode, __state._M_next); break; case _S_opcode_word_boundary: - if (_M_word_boundary(__state) == !__state._M_neg) + if (_M_word_boundary() == !__state._M_neg) _M_dfs(__match_mode, __state._M_next); break; // Here __state._M_alt offers a single start node for a sub-NFA. @@ -284,9 +284,11 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION _M_dfs(__match_mode, __state._M_next); break; case _S_opcode_match: + if (_M_current == _M_end) + break; if (__dfs_mode) { - if (_M_current != _M_end && __state._M_matches(*_M_current)) + if (__state._M_matches(*_M_current)) { ++_M_current; _M_dfs(__match_mode, __state._M_next); @@ -407,25 +409,26 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION template bool _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>:: - _M_word_boundary(_State<_TraitsT>) const + _M_word_boundary() const { - // By definition. - bool __ans = false; - auto __pre = _M_current; - --__pre; - if (!(_M_at_begin() && _M_at_end())) + bool __left_is_word = false; + if (_M_current != _M_begin + || (_M_flags & regex_constants::match_prev_avail)) { - if (_M_at_begin()) - __ans = _M_is_word(*_M_current) - && !(_M_flags & regex_constants::match_not_bow); - else if (_M_at_end()) - __ans = _M_is_word(*__pre) - && !(_M_flags & regex_constants::match_not_eow); - else - __ans = _M_is_word(*_M_current) - != _M_is_word(*__pre); + auto __prev = _M_current; + if (_M_is_word(*std::prev(__prev))) + __left_is_word = true; } - return __ans; + bool __right_is_word = + _M_current != _M_end && _M_is_word(*_M_current); + + if (__left_is_word == __right_is_word) + return false; + if (__left_is_word && !(_M_flags & regex_constants::match_not_eow)) + return true; + if (__right_is_word && !(_M_flags & regex_constants::match_not_bow)) + return true; + return false; } _GLIBCXX_END_NAMESPACE_VERSION -- 2.30.2