MapReduce的自定义分组

package com.mengyao.hadoop.mapreduce;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;

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.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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


public class MyGroupApp extends Configured implements Tool {

    static class MyGroupMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
        
        private Text k = null;
        private LongWritable v = null;
        
        @Override
        protected void setup(
                Mapper<LongWritable, Text, Text, LongWritable>.Context context)
                throws IOException, InterruptedException {
            k = new Text();
            v = new LongWritable(1L);
        }

        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            final String[] words = value.toString().split("\t");
            for (String word : words) {
                k.set(word);
                context.write(k, v);
            }
        }
    }
    
    static class MyGroupReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
        @Override
        protected void reduce(Text key, Iterable<LongWritable> value, Context context)
                throws IOException, InterruptedException {
            long count = 0L;
            for (LongWritable item : value) {
                count += item.get();
            }
            context.write(key, new LongWritable(count));
        }
    }
    
    @Override
    public int run(String[] arg0) throws Exception {
        Configuration conf = getConf();
        conf.set("mapreduce.job.jvm.numtasks", "-1");        
        conf.set("mapreduce.map.speculative", "false");        
        conf.set("mapreduce.reduce.speculative", "false");    
        conf.set("mapreduce.map.maxattempts", "4");            
        conf.set("mapreduce.reduce.maxattempts", "4");        
        conf.set("mapreduce.map.skip.maxrecords", "0");        
        Job job = Job.getInstance(conf, MyGroupApp.class.getSimpleName());
        job.setJarByClass(MyGroupApp.class);
        job.setInputFormatClass(TextInputFormat.class);
        
        FileInputFormat.addInputPath(job, new Path(arg0[0]));
        FileOutputFormat.setOutputPath(job, new Path(arg0[1]));
        
        job.setMapperClass(MyGroupMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        
        job.setReducerClass(MyGroupReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        
        return job.waitForCompletion(true)?0:1;
    }
    
    
    public static int createJob(String[] args) {
        Configuration conf = new Configuration();
        int status = 1;
        try {
            status = ToolRunner.run(conf, new MyGroupApp(), args);
        } catch (Exception e) {
            e.printStackTrace();
            throw new RuntimeException(e);
        }
        
        return status;
    }
    
    public static void main(String[] args) throws Exception {
        //此处用ant直接编译打包上传运行，先行赋值
        args = new String[]{"/testdata/words", "/job/mapreduce/"+WordCountApp.class.getSimpleName()+"_"+new SimpleDateFormat("yyyyMMddhhMMss").format(new Date())};
        if (args.length != 2) {
            System.out.println("Usage: "+WordCountApp.class.getSimpleName()+" <in> <out>");
            System.exit(2);
        } else {
            int status = createJob(args);
            System.exit(status);
        }

    }

}