sub file_is_valid_utf8 {
  my $f = shift;
  open(F,"<:raw",$f) or return 0;
  local $/;
  my $x=<F>; 
  close F;
  return is_valid_utf8($x);
}
   
# What's passed to this routine has to be a stream of bytes, not a utf8 string in which the characters are complete utf8 characters.
# That's why you typically want to call file_is_valid_utf8 rather than calling this directly.
sub is_valid_utf8 {   
  my $x = shift;
  my $leading0     = '[\x{0}-\x{7f}]';
  my $leading10    = '[\x{80}-\x{bf}]';
  my $leading110   = '[\x{c0}-\x{df}]';
  my $leading1110  = '[\x{e0}-\x{ef}]';
  my $leading11110 = '[\x{f0}-\x{f7}]';
  my $utf8 = "($leading0|($leading110$leading10)|($leading1110$leading10$leading10)|($leading11110$leading10$leading10$leading10))*";
  return ($x=~/^$utf8$/);
}