my @bytes = unpack( "C*", $_ ); # break string into bytes

my $widec = ""; # accumulate valid utf8 bytes here
my $width = 0;  # keep track of how many bytes to accumulate

for my $b ( @bytes ) {
   if (( $b & 0xf0 ) == 0xe0 or  # high 4 bits are 1110 
       ( $b & 0xe0 ) == 0xc0 )   # high 3 bits are 110
   {
# either condition represents the start of a multibyte-char
      die "Bad byte sequence\n" if ( $width );
      $width = (( $b & 0xe0 ) == 0xe0 ) ?  3 : 2;
      $widec .= chr( $b );
   }
   elsif (( $b & 0xc0 ) == 0x80 )  # high 2 bits are 10
   {
# this should be a continuation of a multibyte-char
      die "Bad byte sequence\n" unless ( $width );
      $widec .= chr( $b );
   }
   elsif (( $b & 0x80 ) == 0 )   # this is an ascii byte
   {
# cannot occur while assembling a multibyte-char
      die "Bad byte sequence\n" if ( $width );
      $width = 1;
      $widec = chr( $b );
   }
   else {
      die "Bad byte value\n"; # all four high-bits set
   }
   if ( length( $widec ) == $width ) {
      $width = 0;
      $widec = "";
   }
}
die "Incomplete multibyte char\n" if ( $width );

# get here if the string was valid utf8