com.jbw.mutioutputformat.PatitionByStation.java Source code

Introduction

Here is the source code for com.jbw.mutioutputformat.PatitionByStation.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package com.jbw.mutioutputformat;

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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.mapreduce.lib.output.MultipleOutputs;
import org.apache.hadoop.mrunit.internal.output.MockMultipleOutputs;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 *
 * @author alvin
 */
public class PatitionByStation extends Configured implements Tool {

    static class StationMapper extends Mapper<LongWritable, Text, Text, Text> {

        private final YearTempParser parse = new YearTempParser();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            parse.parse(value);
            if (parse.isValid()) {
                context.write(new Text(parse.getStation()), value);
            }
        }
    }

    static class StationReducer extends Reducer<Text, Text, NullWritable, Text> {

        private MultipleOutputs multipleOutputs = null;

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            multipleOutputs = new MockMultipleOutputs(context);
        }

        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context)
                throws IOException, InterruptedException {
            for (Text t : values) {
                multipleOutputs.write(NullWritable.get(), t, "");
            }
        }

        @Override
        protected void cleanup(Context context) throws IOException, InterruptedException {
            multipleOutputs.close();
        }

    }

    @Override
    public int run(String[] strings) throws Exception {
        Configuration conf = getConf();
        Path input = new Path(conf.get("input"));
        Path output = new Path(conf.get("output"));
        Job job = Job.getInstance();
        job.setJarByClass(PatitionByStation.class);
        job.setJobName("papapa");
        job.setMapperClass(StationMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setReducerClass(StationReducer.class);
        job.setOutputKeyClass(NullWritable.class);
        FileInputFormat.addInputPath(job, input);
        FileOutputFormat.setOutputPath(job, output);
        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        System.exit(ToolRunner.run(new PatitionByStation(), args));
    }
}