merge.MergeSameData.java Source code

Introduction

Here is the source code for merge.MergeSameData.java

Source

package merge;
/*
 * ============================================================
 * The SSE USTC Software License
 * 
 * StatisticsTotalDataNum.java
 * 2014925
 * 
 * Copyright (c) 2006 China Payment and Remittance Service Co.,Ltd        
 * All rights reserved.
 * ============================================================
 */

/**
 *  ??
 * <p>
 * date           author            email                 notes<br />
 * ----------------------------------------------------------------<br />
 *2014925                 starqiu@mail.ustc.edu.cn       <br /></p>
 *
 */
import java.io.IOException;

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.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 comm.IntSumReducer;

public class MergeSameData {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private final static Text fixKey = new Text("totalDataNum");

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String[] row = value.toString().split(",");
            String sep = "\t";
            context.write(new Text(row[0] + sep + row[1] + sep + row[5]), one);
        }
    }

    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: StatisticsTotalDataNum <in> <out>");
            System.exit(2);

        }

        Job job = new Job(conf, "Statistics Total Data Num");
        job.setJarByClass(MergeSameData.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);

    }

}