利用MultipleOutputs控制reduce输出路径

package com.mr.test;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapred.lib.MultipleOutputs;

public class WordCount {
    public static class MyMap implements
            Mapper<LongWritable, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        
        public void map(LongWritable key, Text value,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                output.collect(word, one);
            }
        }
		public void configure(JobConf arg0) {
			
		}
		public void close() throws IOException {
			// TODO Auto-generated method stub
		}
    }

    public static class MyReduce implements
            Reducer<Text, IntWritable, Text, IntWritable> {
    	private MultipleOutputs mos;
    	private JobConf jobconf;
        public void reduce(Text key, Iterator<IntWritable> values,
                OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            mos.getCollector(key.toString(), reporter).collect(key, new IntWritable(sum));
//            mos.getCollector(key.toString(),"test", reporter).collect(key, new IntWritable(sum));
        }

		public void configure(JobConf jobconf) {
			mos = new MultipleOutputs(jobconf);
			this.jobconf = jobconf;
		}

		public void close() throws IOException {
			mos.close();
		}
    }

    public static void main(String[] args) throws Exception {
        JobConf conf = new JobConf(WordCount.class);
        conf.setJobName("wordcount");

        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(MyMap.class);
        conf.setCombinerClass(MyReduce.class);
        conf.setReducerClass(MyReduce.class);

        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);
		System.out.println("args1:"+args[0]);
		System.out.println("args2:"+args[1]);
        FileInputFormat.setInputPaths(conf, new Path(args[0]));
        FileOutputFormat.setOutputPath(conf, new Path(args[1]));
        MultipleOutputs.addNamedOutput(conf, "test1", TextOutputFormat.class,
        		 LongWritable.class, Text.class);
        MultipleOutputs.addNamedOutput(conf, "test2", TextOutputFormat.class,
       		 LongWritable.class, Text.class);
        MultipleOutputs.addNamedOutput(conf, "test3", TextOutputFormat.class,
       		 LongWritable.class, Text.class);
        MultipleOutputs.addNamedOutput(conf, "test4", TextOutputFormat.class,
       		 LongWritable.class, Text.class);
        MultipleOutputs.addNamedOutput(conf, "test5", TextOutputFormat.class,
       		 LongWritable.class, Text.class);
        JobClient.runJob(conf);
    }
}


input.txt:

test1
test2
test3
test4
test5

output:

-rw-r--r--   2 test supergroup          0 2014-04-20 11:23 /chukwa/output/0419-10/_SUCCESS
drwxr-xr-x   - test supergroup          0 2014-04-20 11:23 /chukwa/output/0419-10/_logs
-rw-r--r--   2 test supergroup         42 2014-04-20 11:23 /chukwa/output/0419-10/part-00000.lzo
-rw-r--r--   2 test supergroup         58 2014-04-20 11:23 /chukwa/output/0419-10/test1-m-00000.lzo
-rw-r--r--   2 test supergroup         58 2014-04-20 11:23 /chukwa/output/0419-10/test2-m-00000.lzo
-rw-r--r--   2 test supergroup         58 2014-04-20 11:23 /chukwa/output/0419-10/test3-m-00000.lzo
-rw-r--r--   2test supergroup         58 2014-04-20 11:23 /chukwa/output/0419-10/test4-m-00001.lzo
-rw-r--r--   2 test supergroup         58 2014-04-20 11:23 /chukwa/output/0419-10/test5-m-00001.lzo


  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
实现Reduce输出结果的全排序,需要在Reducer中进行一定的修改。以下是一个基本的MapReduce全排序的代码示例: Mapper函数: ``` public static class SortMapper extends Mapper<Object, Text, IntWritable, IntWritable>{ private IntWritable num = new IntWritable(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); num.set(Integer.parseInt(line)); context.write(num, new IntWritable(1)); } } ``` Reducer函数: ``` public static class SortReducer extends Reducer<IntWritable,IntWritable,IntWritable,IntWritable> { public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { for (IntWritable value : values) { context.write(key, new IntWritable(1)); } } } ``` 驱动函数: ``` public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "sort"); job.setJarByClass(Sort.class); job.setMapperClass(SortMapper.class); job.setReducerClass(SortReducer.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(IntWritable.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setNumReduceTasks(1); // 设置Reduce任务数为1,确保全局排序 System.exit(job.waitForCompletion(true) ? 0 : 1); } ``` 在这个示例中,Mapper函数与之前的示例相同。在Reducer函数中,我们直接输出键值对,因为它们已经按照键进行了排序。在驱动函数中,我们设置了Reduce任务数为1,以确保全局排序。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值