# A MR creates an ascending list of unique article names and at the same time an ascending list of unique words.
#
# rm -rf step-8-out-sol; perl step-8-solution.pl -c 2 -r 2 /home/straka/wiki/cs-text-medium/ step-8-out-sol
# less step-8-out-sol/part-*

package My::Mapper;
use Moose;
with 'Hadoop::Mapper';

sub map {
  my ($self, $key, $value, $context) = @_;

  $context->write($key, 0);
  foreach my $word (split /\W/, $value) {
    next if not length $word;
    $context->write($word, 1);
  }
}

package My::Partitioner;
use Moose;
with 'Hadoop::Partitioner';

sub getPartition {
  my ($self, $key, $value, $partitions) = @_;

  return $value;
}

package My::Reducer;
use Moose;
with 'Hadoop::Reducer';

sub reduce {
  my ($self, $key, $values, $context) = @_;

  $context->write($key);
}

package main;
use Hadoop::Runner;

my $runner = Hadoop::Runner->new(
  mapper => My::Mapper->new(),
  partitioner => My::Partitioner->new(),
  reducer => My::Reducer->new(),
  input_format => 'KeyValueTextInputFormat');

$runner->run();