Bug#373937: libstdc++6: codecvt locale facet is broken

[Roger Leigh <rleigh@debian.org>]

Package: libstdc++6
Version: 4.1.1-5
Severity: important

The attached source file (UTF-8 encoded) demonstrates that codecvt
is broken for the simplest of transformations (UTF-8 to UCS-4).
This is pretty basic, and the underlying gconf stuff works correctly,
so the bug is either in libstdc++6 or somewhere inline in the headers.

$ ./wide
wide: ../iconv/loop.c:425: utf8_internal_loop_single: Assertion `inptr -
bytebuf > (state->__count & 7)' failed.
Aborted

While running:
(gdb) bt
#0  0x0fcc672c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#1  0x0fe0425c in ?? () from /lib/tls/libc.so.6
#2  0x0ffa6ef8 in std::codecvt<wchar_t, char, __mbstate_t>::do_in ()
   from /usr/lib/libstdc++.so.6
#3  0x100016b4 in std::__codecvt_abstract_base<wchar_t, char, __mbstate_t>::in
    (this=0x100290b8, __state=@0x7fa405a8, __from=0x10013014 "fffä%G�%@237»",
    __from_end=0x1001301d "", __from_next=@0x7fa405b0, __to=0x7fa405bc,
    __to_end=0x7fa406fc, __to_next=@0x7fa405b4)
    at /usr/lib/gcc/powerpc-linux-gnu/4.1.2/../../../../include/c++/4.1.2/bits/codecvt.h:204
#4  0x10001244 in to_wide_string (str=@0x7fa40758, locale=@0x7fa40738)
    at wide.cc:22
#5  0x10001544 in main () at wide.cc:59

After aborting:
wide: ../iconv/loop.c:425: utf8_internal_loop_single: Assertion `inptr - bytebuf > (state->__count & 7)' failed.

Program received signal SIGABRT, Aborted.
0x0fcd67bc in raise () from /lib/tls/libc.so.6
(gdb) bt
#0  0x0fcd67bc in raise () from /lib/tls/libc.so.6
#1  0x0fcd82c0 in abort () from /lib/tls/libc.so.6
#2  0x0fcce768 in __assert_fail () from /lib/tls/libc.so.6
#3  0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#4  0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#5  0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#6  0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#7  0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#8  0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#9  0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#10 0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
#11 0x0fcc6c7c in __gconv_transform_utf8_internal () from /lib/tls/libc.so.6
Previous frame inner to this frame (corrupt stack?)


Regards,
Roger

-- System Information:
Debian Release: testing/unstable
  APT prefers unstable
  APT policy: (990, 'unstable')
Architecture: powerpc (ppc)
Shell:  /bin/sh linked to /bin/bash
Kernel: Linux 2.6.16.17
Locale: LANG=en_GB.UTF8, LC_CTYPE=en_GB.UTF8 (charmap=UTF-8)

Versions of packages libstdc++6 depends on:
ii  gcc-4.1-base                  4.1.1-5    The GNU Compiler Collection (base 
ii  libc6                         2.3.6-15   GNU C Library: Shared libraries
ii  libgcc1                       1:4.1.1-5  GCC support library

libstdc++6 recommends no packages.

-- no debconf information

#include <iostream>
#include <locale>
#include <string>

std::wstring
to_wide_string (std::string const& str,
		std::locale        locale)
{
  typedef std::codecvt<wchar_t, char, mbstate_t> codecvt_type;
  codecvt_type const& cvt = std::use_facet<codecvt_type>(locale);
  mbstate_t state;
  const char *cbegin = str.data(), *cend = str.data() + str.size(), *cnext;
  wchar_t *wcnext;
  wchar_t wcbuf[80];
  std::wstring ret;

  while (1)
    {
      std::codecvt_base::result res =
	cvt.in(state,
	       cbegin, cend, cnext,
	       wcbuf, wcbuf + (sizeof(wcbuf) / sizeof(wcbuf[0])), wcnext);

      if (res == std::codecvt_base::ok || std::codecvt_base::partial)
	{
	  std::cout << "1" << std::endl;
	  ret += std::wstring(wcbuf, wcnext);
	  if (cend == cnext)
	    break;
	}
      else if (res == std::codecvt_base::noconv)
	{
	  std::cout << "2" << std::endl;
	  ret += std::wstring(cbegin, cend);
	  break;
	}
      else if (res == std::codecvt_base::error)
	{
	  std::cout << "3" << std::endl;
	  break;
	}
      else
	break;

      std::cout << "4" << std::endl;
      cbegin = cnext;
    }

  return ret;
}

int main()
{
  std::locale::global(std::locale(""));
  std::cout.imbue(std::locale());
  std::wcerr.imbue(std::locale());

  std::string foo = "fffäß»";
  std::wstring wfoo = to_wide_string(foo, std::wcerr.getloc());

  std::cout << foo;
  std::wcerr << wfoo;

  return 0;
}