#!/usr/bin/perl

# expect as input file named "file" with these contents:
# $ hexdump file
# 00000000  e9 e9 6e 0a

use Getopt::Std;
use IO::File;
use Text::CSV_XS;
use Encode;
binmode(STDOUT, ":utf8");

# -c = use CSV_XS instead of simple IO
# -f = force utf8 flag on
getopts('cf');

my $io = IO::File->new();
$io->open("file", "<:raw:encoding(cp1252)")  ||
         die("$0: open inputfile: $!\n");
my $csvin = Text::CSV_XS->new({ 'binary' => 1 });

if ($opt_c)  {
    $cols = $csvin->getline($io);
    $s = $$cols[0];
} else {
    $s = <$io>;
    chomp($s);
}

Encode::_utf8_on($s)  if ($opt_f);

print "[$s] ", utf8::is_utf8($s) ? "Is UTF8" : "NOT utf8",
    " ", utf8::valid($s) ? "Is valid" : "NOT valid";
print "\nLENGTH: ", length($s), "  SUBSTR3: [", substr($s,0,3), "]",
    "  SPLIT: [", join(" ", split(//, $s)), "]\n";