#! perl
use Unicode::Normalize; # for the NFKD function
use strict;
use warnings;

my ($FOO, $BAR, $BAZ) = qw(FOO BAR BAZ);
# uses system default encoding for INFILE; say
# '<:encoding(iso-8859-1)' to explicitly use iso-latin-1
open(INFILE, '<', 'test1.txt');
while (<INFILE>)
{
  chomp;
  my ($category, $fornom, $surnom, $pass, @rest) = split;
  die "Extra crud at the end of the line: @rest" if (@rest);
  my ($squashed_fornom) = NFKD($fornom)     # NFKD separates accented letters
                                            # into letters + combining mark
  $squashed_fornom =~ s/\pM//g;             # remove marks
  $squashed_fornom = lc($squashed_fornom);  # lowercase
  my ($squashed_surnom) = NFKD($surnom);
  $squashed_surnom =~ s/\pM//g;
  $squashed_surnom = lc($squashed_surnom);
  print "$squashed_fornom $squashed_surnom";
  print "|$pass|$fornom $surnom|$FOO|$BAR|$BAZ|$FOO $fornom $surnom\n";
}