Remove >3 bytes characters

clear-utf8.pl

#!/usr/bin/env perl
use strict;
use warnings;
use open qw( :encoding(UTF-8) :std );
use English qw( -no_match_vars );

while ( my $line = <> ) {
    my $count = $line =~ s{
        [\N{U+07FF}-\N{U+7FFFFFF}]
    } [?]xg;
    if ($count) {
        print {*STDERR} "Bad $count symbols in file $ARGV, line $INPUT_LINE_NUMBER\n";
    }
    print $line;
}