mosesdecoder/scripts/tokenizer/lowercase.perl

#!/usr/bin/env perl
#
# This file is part of moses.  Its use is licensed under the GNU Lesser General
# Public License version 2.1 or, at your option, any later version.

use warnings;
use strict;

while (@ARGV) {
    $_ = shift;
    /^-b$/ && ($| = 1, next); # not buffered (flush each line)
}

binmode(STDIN, ":utf8");
binmode(STDOUT, ":utf8");

while(<STDIN>) {
  print lc($_);
}