package Hadoop::Runner;
use Moose;
 
has 'mapper' => (does => 'Hadoop::Mapper', required => 1);
has 'reducer' => (does => 'Hadoop::Reducer');
has 'combiner' => (does => 'Hadoop::Reducer');
has 'partitioner' => (does => 'Hadoop::Partitioner');
 
has 'input_format' => (isa => 'InputFormat', default => 'TextInputFormat');
has 'output_format' => (isa => 'OutputFormat', default => 'TextOutputFormat');
has 'output_compression' => (isa => 'Bool', default => 0);
 
has 'hadoop_prefix' => (isa => 'Str', default => '/SGE/HADOOP/active');
has 'keep_env' => (isa => 'ArrayRef[Str]', default => sub { ["PERLLIB", "PERL5LIB"] });
 
sub run();

• mapper – a Hadoop::Mapper to use
• reducer – an optional Hadoop::Reducer to use
• combiner – an optional Hadoop::Reducer to use as combiner
• partitioner – an optional Hadoop::Partitioner to use
• input_format – one of TextInputFormat, KeyValueTextInputFormat, SequenceFileInputFormat
• output_format – one of TextOutputFormat, SequenceFileOutputFormat
• output_compression – Bool flag controlling the compression of output
• hadoop_prefix – the prefix of Hadoop instalation. Default value is fine in UFAL cluster.
• keep_env – which environment variables are preserved when running perl mappers, reducers, combiners and partitioners

package Hadoop::Mapper;
use Moose::Role;
 
requires 'map';
 
sub setup() { 1; }
sub cleanup { 1;}

• sub map($self, $key, $value, $context) – executed for every (key, value) input pair. The variable '$content' has following methods:
  • $content->write($key, $value) – output the ($key, $value) pair
  • $content->counter($group, $name, $increment) – increases the counter $name in the group $group by $increment