[boost] 1.40 regex

Subject: [boost] 1.40 regex
From: Jonathan Brannan (kickace_at_[hidden])
Date: 2009-09-03 15:54:45

I have code that comes out clean in 1.39 (as unit-test and under
valgrind), but under 1.40 it's not clean in valgrind and it crashes
when run normally (malloc(): memory corruption).  I'm trying to write
a reproducer that is smaller than what I have, but incase something
pops out at someone (or can point me where my code might be wrong),
here is the valgrind output:

Running 16 test cases...
==25074== Invalid write of size 8
==25074==    at 0x4E7D4A8:
boost::shared_ptr<boost::re_detail::named_subexpressions_base<char>
>::shared_ptr() (shared_ptr.hpp:182)
==25074==    by 0x4E813C1:
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
cons
t*, std::string> > >
>::match_results(std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > > const&) (match_results.hpp:77)
==25074==    by 0x5811371:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator
<char const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::construct_init(boost::basic_regex<char, boost::regex_traits<char,
boost::cpp_rege
x_traits<char> > > const&, boost::regex_constants::_match_flags)
(perl_matcher_common.hpp:73)
==25074==    by 0x4E856D2:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator
<char const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::perl_matcher(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::_
_normal_iterator<char const*, std::string>,
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_i
terator<char const*, std::string> > > >&, boost::basic_regex<char,
boost::regex_traits<char, boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags, _
_gnu_cxx::__normal_iterator<char const*, std::string>) (perl_matcher.hpp:366)
==25074==    by 0x4E8583A: bool
boost::regex_search<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > >(__gnu_cxx::__normal_iterator<char
const*, std::string>, __gnu_cxx::__normal_iterat
or<char const*, std::string>,
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
c
onst*, std::string> > > >&, boost::basic_regex<char,
boost::regex_traits<char, boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags, __gnu_cxx::__no
rmal_iterator<char const*, std::string>) (regex_search.hpp:55)
==25074==    by 0x4E85BEF:
boost::regex_token_iterator_implementation<__gnu_cxx::__normal_iterator<char
const*, std::string>, char, boost::regex_traits<char, boost::cpp_regex
_traits<char> > >::init(__gnu_cxx::__normal_iterator<char const*,
std::string>) (regex_token_iterator.hpp:109)
==25074==    by 0x4E8AC07:
boost::regex_token_iterator<__gnu_cxx::__normal_iterator<char const*,
std::string>, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
 >::regex_token_iterator(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::__normal_iterator<char const*, std::string>,
boost::basic_regex<char, boost::regex
_traits<char, boost::cpp_regex_traits<char> > > const&, int,
boost::regex_constants::_match_flags) (regex_token_iterator.hpp:200)
==25074==    by 0x45D99C:
application_ut_suite::test_logon::test_method()
(application_ut.cpp:139)
==25074==  Address 0x6a64588 is 0 bytes after a block of size 56 alloc'd
==25074==    at 0x4C2506C: operator new(unsigned long) (in
/usr/lib64/valgrind/amd64-linux/vgpreload_memcheck.so)
==25074==    by 0x5811362:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator
<char const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::construct_init(boost::basic_regex<char, boost::regex_traits<char,
boost::cpp_rege
x_traits<char> > > const&, boost::regex_constants::_match_flags)
(perl_matcher_common.hpp:73)
==25074==    by 0x4E856D2:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator
<char const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::perl_matcher(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::_
_normal_iterator<char const*, std::string>,
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_i
terator<char const*, std::string> > > >&, boost::basic_regex<char,
boost::regex_traits<char, boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags, _
_gnu_cxx::__normal_iterator<char const*, std::string>) (perl_matcher.hpp:366)
==25074==    by 0x4E8583A: bool
boost::regex_search<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > >(__gnu_cxx::__normal_iterator<char
const*, std::string>, __gnu_cxx::__normal_iterat
or<char const*, std::string>,
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
c
onst*, std::string> > > >&, boost::basic_regex<char,
boost::regex_traits<char, boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags, __gnu_cxx::__no
rmal_iterator<char const*, std::string>) (regex_search.hpp:55)
==25074==    by 0x4E85BEF:
boost::regex_token_iterator_implementation<__gnu_cxx::__normal_iterator<char
const*, std::string>, char, boost::regex_traits<char, boost::cpp_regex
_traits<char> > >::init(__gnu_cxx::__normal_iterator<char const*,
std::string>) (regex_token_iterator.hpp:109)
==25074==    by 0x4E8AC07:
boost::regex_token_iterator<__gnu_cxx::__normal_iterator<char const*,
std::string>, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
 >::regex_token_iterator(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::__normal_iterator<char const*, std::string>,
boost::basic_regex<char, boost::regex
_traits<char, boost::cpp_regex_traits<char> > > const&, int,
boost::regex_constants::_match_flags) (regex_token_iterator.hpp:200)
==25074==    by 0x442E4F: application_ut_suite::(anonymous
namespace)::Test_Setup::Test_Setup(std::istream&, unsigned long)
(application_ut.cpp:96)
==25074==    by 0x45D99C:
application_ut_suite::test_logon::test_method()
(application_ut.cpp:139)
==25074==    by 0x45F620:
_ZN20application_ut_suiteL18test_logon_invokerEv
(application_ut.cpp:133)
==25074==
==25074== Invalid write of size 8
==25074==    at 0x46CE8A: boost::detail::shared_count::shared_count()
(shared_count.hpp:71)
==25074==:regex_traits<char, boost::cpp_regex_traits<char> > > const&,
int, boost::regex_constants::_match_flags)
(regex_token_iterator.hpp:200)
==25074==    by 0x442E4F: application_ut_suite::(anonymous
namespace)::Test_Setup::Test_Setup(std::istream&, unsigned long)
(application_ut.cpp:96)
==25074==  Address 0x6a64590 is 8 bytes after a block of size 56 alloc'd
==25074==    at 0x4C2506C: operator new(unsigned long) (in
/usr/lib64/valgrind/amd64-linux/vgpreload_memcheck.so)
==25074==    by 0x5811362:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::construct_init(boost::basic_regex<char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags) (perl_matcher_common.hpp:73)
==25074==    by 0x4E856D2:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::perl_matcher(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::__normal_iterator<char const*, std::string>,
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::_cxx::__normal_iterator<char const*, std::string>,
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > > >&, boost::basic_regex<char,
boost::regex_traits<char, boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags,
__gnu_cxx::__normal_iterator<char const*, std::string>)
(regex_search.hpp:55)
==25074==    by 0x4E85BEF:
boost::regex_token_iterator_implementation<__gnu_cxx::__normal_iterator<char
const*, std::string>, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::init(__gnu_cxx::__normal_iterator<char const*, std::string>)
(regex_token_iterator.hpp:109)
==25074==    by 0x4E8AC07:
boost::regex_token_iterator<__gnu_cxx::__normal_iterator<char const*,
std::string>, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::regex_token_iterator(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::__normal_iterator<char const*, std::string>,
boost::basic_regex<char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > > const&, int,
boost::regex_constants::_match_flags) (regex_token_iterator.hpp:200)
==25074==    by 0x442E4F: application_ut_suite::(anonymous
namespace)::Test_Setup::Test_Setup(std::istream&, unsigned long)
(application_ut.cpp:96)
==25074==    by 0x45D99C:
application_ut_suite::test_logon::test_method()
(application_ut.cpp:139)
==250ub_match<__gnu_cxx::__normal_iterator<char const*, std::string> >
>, boost::regex_traits<char, boost::cpp_regex_traits<char> >
>::construct_init(boost::basic_regex<char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags) (perl_matcher_common.hpp:73)
==25074==    by 0x4E856D2:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::perl_matcher(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::__normal_iterator<char const*, std::string>,
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > > >&, boost::basic_regex<char,
boost::regex_traits<char, boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags,
__gnu_cxx::__normal_iterator<char const*, std::string>)
(perl_matcher.hpp:366)
==25074==    by 0x4E8583A: bool
boost::regex_search<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > >(__gnu_cxx::__normal_iterator<char
const*, std::string>, __gnu_cxx::__normal_iterator<char const*,
std::string>, boost::match_results<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > > >&, boost::basic_regex<char,
boost::regex_traits<char, boost::cpp_regex_traits<char> > > const&,
boost::regex_constants::_match_flags,
__gnu_cxx::__normal_iterator<char const*, std::string>)
(regex_search.hpp:55)
==25074==    by 0x4E85BEF:
boost::regex_token_iterator_implementation<__gnu_cxx::__normal_iterator<char
const*, std::string>, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::init(__gnu_cxx::__normal_iterator<char const*,
snstants::_match_flags) (regex_token_iterator.hpp:200)
==25074==    by 0x442E4F: application_ut_suite::(anonymous
namespace)::Test_Setup::Test_Setup(std::istream&, unsigned long)
(application_ut.cpp:96)
==25074==    by 0x45D99C:
application_ut_suite::test_logon::test_method()
(application_ut.cpp:139)
==25074==    by 0x45F620:
_ZN20application_ut_suiteL18test_logon_invokerEv
(application_ut.cpp:133)
==25074==  Address 0x6a64598 is not stack'd, malloc'd or (recently) free'd
**25074** new/new[] failed and should throw an exception, but Valgrind
   cannot throw exceptions and so is aborting instead.  Sorry.
==25074==    at 0x4C22E23: (within
/usr/lib64/valgrind/amd64-linux/vgpreload_memcheck.so)
==25074==    by 0x4C250C8: operator new(unsigned long) (in
/usr/lib64/valgrind/amd64-linux/vgpreload_memcheck.so)
==25074==    by 0x4E84680:
__gnu_cxx::new_allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >::allocate(unsigned long, void const*)
(new_allocator.h:92)
==25074==    by 0x4E846AF:
std::_Vector_base<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> >,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > > >::_M_allocate(unsigned long)
(stl_vector.h:144)
==25074==    by 0x4E8A4AE:
std::vector<boost::sub_match<__gnu_cxx::__normal_iterator<char const*,
std::string> >,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*tor.tcc:395)
==25074==    by 0x4E8A61E:
std::vector<boost::sub_match<__gnu_cxx::__normal_iterator<char const*,
std::string> >,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >
>::insert(__gnu_cxx::__normal_iterator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> >*,
std::vector<boost::sub_match<__gnu_cxx::__normal_iterator<char const*,
std::string> >,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > > > >, unsigned long,
boost::sub_match<__gnu_cxx::__normal_iterator<char const*,
std::string> > const&) (stl_vector.h:792)
==25074==    by 0x4E8A73B:
boost::match_results<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > > >::set_size(unsigned long,
__gnu_cxx::__normal_iterator<char const*, std::string>,
__gnu_cxx::__normal_iterator<char const*, std::string>)
(match_results.hpp:399)
==25074==    by 0x4E8B1BF:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> > >::find_imp()
(perl_matcher_common.hpp:263)
==25074==    by 0x5810D0A:
boost::re_detail::perl_matcher<__gnu_cxx::__normal_iterator<char
const*, std::string>,
std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, boost::regex_traits<char,
boost::cpp_regex_traits<char> > >::find()
(perl_matcher_common.hpp:229)
==25074==    by 0x4E85846: bool
boost::regex_search<__gnu_cxx::__normal_iterator<char const*,
std::string>, std::allocator<boost::sub_match<__gnu_cxx::__normal_iterator<char
const*, std::string> > >, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > >(__gnu_cxx::__normal_iterator<char
const*, std::string>, __gnu_cxx::__normal_iterator<char const*,
std::string>, boost::match_results<__gnu_cxx::__normal_iterator<char
const*, std::string>, std::allocator<boost:::regex_traits<char,
boost::cpp_regex_traits<char> >
>::init(__gnu_cxx::__normal_iterator<char const*, std::string>)
(regex_token_iterator.hpp:109)
==25074==    by 0x4E8AC07:
boost::regex_token_iterator<__gnu_cxx::__normal_iterator<char const*,
std::string>, char, boost::regex_traits<char,
boost::cpp_regex_traits<char> >
>::regex_token_iterator(__gnu_cxx::__normal_iterator<char const*,
std::string>, __gnu_cxx::__normal_iterator<char const*, std::string>,
boost::basic_regex<char, boost::regex_traits<char,
boost::cpp_regex_traits<char> > > const&, int,
boost::regex_constants::_match_flags) (regex_token_iterator.hpp:200)
==25074==
==25074== ERROR SUMMARY: 3 errors from 3 contexts (suppressed: 3 from 1)
==25074== malloc/free: in use at exit: 64,694 bytes in 500 blocks.
==25074== malloc/free: 590 allocs, 89 frees, 103,110 bytes allocated.
==25074== For counts of detected errors, rerun with: -v
==25074== searching for pointers to 500 not-freed blocks.
==25074== checked 402,856 bytes.
==25074==
==25074== LEAK SUMMARY:
==25074==    definitely lost: 0 bytes in 0 blocks.
==25074==      possibly lost: 7,480 bytes in 190 blocks.
==25074==    still reachable: 57,214 bytes in 310 blocks.
==25074==         suppressed: 0 bytes in 0 blocks.
==25074== Rerun with --leak-check=full to see details of leaked memory.