com.elixir.hadoop.Chromo.FragmentCoverage.java Source code

Introduction

Here is the source code for com.elixir.hadoop.Chromo.FragmentCoverage.java

Source

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package com.elixir.hadoop.Chromo;

import java.io.IOException;
//import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
//import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

import com.elixir.hadoop.FragmentCoverage.CoverageMapper;
import com.elixir.hadoop.FragmentCoverage.IntSumReducer;

public class FragmentCoverage {

    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "position");
        job.setJarByClass(FragmentCoverage.class);

        job.setMapperClass(CoverageMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setNumReduceTasks(5);
        job.setMapOutputKeyClass(com.elixir.hadoop.Chromo.SecondrySort.IntPair.class);
        //job.setSpeculativeExecution(true);
        job.setPartitionerClass(ChromoPartitioner.class);
        job.setGroupingComparatorClass(com.elixir.hadoop.Chromo.SecondrySort.FirstGroupingComparator.class);
        job.setReducerClass(IntSumReducer.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);
        //   job.setOutputFormatClass(Text.class);

        for (int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}