BOM results from the CPAN

HTML-FormatExternal
  require HTML::FormatText::Links;
  print "Links _have_html_margin(): ",
    (HTML::FormatText::Links->_have_html_margin() ? "yes" : "no"),"\n";

  require HTML::FormatText::Vilistextum;
  print "Vilistextum _have_multibyte(): ",
    (HTML::FormatText::Vilistextum->_have_multibyte() ? "yes" : "no"),"\n";
  exit 0;
}


{
  # IPC::Run in taint mode
  # $ENV{PATH} = '/bin:/usr/bin';
  my $str;
  require IPC::Run;
   IPC::Run::run(['echo','hello'], '>',\$str);
  # IPC::Run::run(['cat'], '<', \'hello', '>', \$str);
  ### $str
  exit 0;
}



{
  # taintedness of program_version()
  $ENV{PATH} = '/bin:/usr/bin';
  require HTML::FormatText::W3m;
  my $str = HTML::FormatText::W3m->program_full_version;
  require Scalar::Util;
  print "tainted ",(Scalar::Util::tainted($str) ? 'yes' : 'no'), "\n";
  exit 0;  
}




{
  # format_file() with output_wide

  require HTML::FormatText::W3m;
  my $str = HTML::FormatText::W3m->format_file
    ('devel/base.html', output_wide => 1);

  $Data::Dumper::Useqq=1;
  print Dumper(\$str);
  print "utf8 flag ",(utf8::is_utf8($str) ? 'yes' : 'no'), "\n";
  exit 0;
}


{
  # format_file() with base

  require HTML::FormatText::Elinks;
  my $str = HTML::FormatText::Elinks->format_file
    ('devel/base.html', base => 'http://localhost');
  exit 0;
}
{
  # BOM on input
  # lynx recognises automatically

  my $html = "<html><body><p>Hello world</p></body></html>\n";
  require Encode;

   $html = Encode::encode('utf-32',$html); # with BOM
  # $html = "\xFF\xFE\x00\x00" . Encode::encode('utf-32le',$html); # with BOM
  $html = ("\x20\x00\x00\x00" x 8) . $html;  # BE spaces

  print "HTML input string:\n";
  IPC::Run::run(['hd'],'<',\$html, '>','/tmp/hd.txt');
  IPC::Run::run(['cat'],'<','/tmp/hd.txt');

  require HTML::FormatText::Lynx;
  my $text = HTML::FormatText::Lynx->format_string ($html,
                                                    input_charset=>'UTF-32',
                                                    # output_charset=>'UTF-8',
                                                    output_wide => 1,
                                                    # base => 'http://localhost',
                                                   );
  print "Text output:\n";
  print $text;
  IPC::Run::run(['hd'],'<',\$text, '>','/tmp/hd.txt');
  IPC::Run::run(['cat'],'<','/tmp/hd.txt');
  for my $i (0 .. length($text)-1) {
    my $c = substr($text,$i,1);
    if (ord($c) >= 128) {
      printf "0x%X\n", ord($c);
    }
  }
  exit 0;
}




{
  # entities

  POSIX::setlocale (POSIX::LC_CTYPE(), "C");

  foreach my $class ('HTML::FormatText::Netrik',
                     'HTML::FormatText::Links',
                     'HTML::FormatText::Html2text',
                     'HTML::FormatText::Lynx',
                     'HTML::FormatText::Elinks',
                     'HTML::FormatText::W3m',
                     'HTML::FormatText::Vilistextum',
                    ) {
    print "--------------------\n$class\n";
    Module::Load::load ($class);
    my $html = "
<html>
<head>
  <meta http-equiv=Content-Type content='text/html; charset=iso-8859-1'>
</head>
<body>
<p>
  \xA2 &#9786; &#9686;
</p>
</body>
</html>";
    my $str = $class->format_string
      ($html
       # input_charset  => $input_charset,
       # output_charset => $output_charset,
      );
( run in 0.511 second using v1.01-cache-2.11-cpan-e1769b4cff6 )