Check for invalid UTF-8 in Metafilter infodump

find_invalid_utf8.pl

#!/usr/bin/env perl
use warnings;
use strict;
use feature qw/say/;
use Encode qw/decode/;
use Try::Tiny;

open my $usernames, '<', 'usernames.txt' or die $!;

while(<$usernames>) {
    s/\r?\n$//;
    my @fields = split /\t/;
    try {
        decode('UTF-8', $fields[2], Encode::FB_CROAK);
    } catch {
        (my $quoted_username = $fields[2]) =~ s/([^\x20-\x7e])/sprintf "\\x%02x", ord $1/eg;
        say "Invalid UTF-8 found in username on line $.: $quoted_username";
    }
}

output.txt

Invalid UTF-8 found in username on line 4864: \xa9
Invalid UTF-8 found in username on line 5408: pi\xf9
Invalid UTF-8 found in username on line 5497: uttar\xf2
Invalid UTF-8 found in username on line 6070: lk\xf2jhk\xf2j
Invalid UTF-8 found in username on line 6741: \xa1\xf0\xb6\xcc\xbd\xde--\xb7Q\xbb\xa1
Invalid UTF-8 found in username on line 9569: \xe1\xcc\xc5\xcb\xd3\xc5\xca\xf3\xd4\xc1\xd3\xc0\xcb\xc5\xd7\xc9\xde
Invalid UTF-8 found in username on line 9576: \xf4\xd2\xd5\xc8\xc9\xce\xe5\xd7\xc7\xc5\xce\xc9\xca\xef\xcc\xc5\xc7\xcf\xd7\xc9\xde
Invalid UTF-8 found in username on line 9578: \xfb\xd5\xd0\xcc\xd1\xcb\xe1\xce\xc1\xd4\xcf\xcc\xc9\xca\xe1\xce\xc1\xd4\xcf\xcc\xd8\xc5\xd7\xc9\xde
Invalid UTF-8 found in username on line 9580: \xf3\xd4\xc1\xce\xc9\xd3\xcc\xc1\xd7\xf1\xce\xcb\xcf\xd7\xd3\xcb\xc9\xca
Invalid UTF-8 found in username on line 9582: \xf3\xcf\xc2\xcf\xcc\xc5\xd7\xe1\xcc\xc5\xcb\xd3\xc1\xce\xc4\xd2\xf3\xc5\xd2\xc7\xc5\xc5\xd7\xc9\xde
Invalid UTF-8 found in username on line 9592: \xe1\xd2\xcd\xc5\xce\xed\xce\xc1\xc3\xc1\xcb\xc1\xce\xd1\xce
Invalid UTF-8 found in username on line 9635: \xed\xc1\xd2\xd8\xd1\xce\xe2\xc5\xcc\xc5\xce\xd8\xcb\xc9\xca
Invalid UTF-8 found in username on line 9929: \xf0\xcf\xc2\xcf\xcc\xc5\xcc\xcf\xd7\xe1\xcc\xc5\xcb\xd3\xc1\xce\xc4\xd2\xe9\xd7\xc1\xce\xcf\xd7\xc9\xde
Invalid UTF-8 found in username on line 10622: \xf7\xcf\xcc\xd8\xc4\xc5\xcd\xc1\xd2\xeb\xc9\xd3\xd3
Invalid UTF-8 found in username on line 10714: \xeb\xc9\xd3\xf3.\xe1.
Invalid UTF-8 found in username on line 11066: \xe5\xd7\xc7\xc5\xce\xc9\xca
Invalid UTF-8 found in username on line 11513: \xf3\xcf\xc2\xd1\xce\xc9\xce
Invalid UTF-8 found in username on line 11627: \xf2\xcf\xda\xd5\xcd\xce\xd9\xca\xe1\xcc\xc5\xcb\xd3\xc1\xce\xc4\xd2\xf7\xcc\xc1\xc4\xc9\xcd\xc9\xd2\xcf\xd7\xc9\xde
Invalid UTF-8 found in username on line 11875: \xe5.\xe0.\xee\xc5\xd7\xc9\xc4\xc9\xcd\xcf\xd7
Invalid UTF-8 found in username on line 12010: l\xf6wi
Invalid UTF-8 found in username on line 12288: \xae
Invalid UTF-8 found in username on line 12293: \xb7
Invalid UTF-8 found in username on line 12295: \xb91
Invalid UTF-8 found in username on line 12298: ( \xb7 )( \xb7 )
Invalid UTF-8 found in username on line 12367: \xd9
Invalid UTF-8 found in username on line 12395: Holden\xb7
Invalid UTF-8 found in username on line 12485: mick\x81
Invalid UTF-8 found in username on line 15985: Oy\xe9ah
Invalid UTF-8 found in username on line 18340: \xba\xa4\xf8,\xb8\xb8,\xf8\xa4\xba\xba\xa4\xf8,\xb8\xb8,\xf8\xa4\xba
Invalid UTF-8 found in username on line 18548: Mumle G\xe5segg
Invalid UTF-8 found in username on line 19218: Axaxaxas Ml\xf6
Invalid UTF-8 found in username on line 21287: heavy metal \xfcmlaut
Invalid UTF-8 found in username on line 21950: skj\xf8nn
Invalid UTF-8 found in username on line 22324: ND\xa2
Invalid UTF-8 found in username on line 23910: La M\xf4me Piaf
Invalid UTF-8 found in username on line 24535: umb\xfa
Invalid UTF-8 found in username on line 25649: \xae@
Invalid UTF-8 found in username on line 25944: Se\xf1or Pantalones
Invalid UTF-8 found in username on line 26212: the black rabbit of Inl\xe9
Invalid UTF-8 found in username on line 26325: \xd8
Invalid UTF-8 found in username on line 27614: Nathanial H\xf6rnblow\xe9r
Invalid UTF-8 found in username on line 27950: n\xedmwunnan
Invalid UTF-8 found in username on line 29549: Se\xf1or Grumpus
Invalid UTF-8 found in username on line 30334: Qo\xf6lio
Invalid UTF-8 found in username on line 31654: ausb\xfcrgern
Invalid UTF-8 found in username on line 31780: L'homme arm\xe9
Invalid UTF-8 found in username on line 32085: Z\xe9 Pequeno
Invalid UTF-8 found in username on line 32274: \xaebin
Invalid UTF-8 found in username on line 32385: nicolas l\xe9onard sadi carnot
Invalid UTF-8 found in username on line 33600: mathowie\xa0
Invalid UTF-8 found in username on line 56820: d\xe9soeuvr\xe9e