2

我正在尝试使用 setMapOutputKeyClass、setMapOutputValueClass、setMapKeyClass和 配置不同的映射器和减速器输出类型setMapValueClass。但是，即使在我调用了这些函数之后，我仍然会在运行时收到错误消息。

这是我的代码：

package org.myorg;

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class Sort {

    public static class Map extends MapReduceBase 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 static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, LongWritable> {
      public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, LongWritable> output, Reporter reporter) throws IOException {
        int sum = 0;
        while (values.hasNext()) {
          sum += values.next().get();
        }
        output.collect(key, new LongWritable(sum));
      }
    }

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

      conf.setMapperClass(Map.class);
      conf.setCombinerClass(Reduce.class);
      conf.setReducerClass(Reduce.class);

      conf.setInputFormat(TextInputFormat.class);
      conf.setOutputFormat(TextOutputFormat.class);

      FileInputFormat.setInputPaths(conf, new Path(args[0]));
      FileOutputFormat.setOutputPath(conf, new Path(args[1]));

      conf.setMapOutputKeyClass(Text.class);
      conf.setMapOutputValueClass(IntWritable.class);
      conf.setOutputKeyClass(Text.class);
      conf.setOutputValueClass(LongWritable.class);

      JobClient.runJob(conf);
    }
}

我得到的错误信息：

java.lang.Exception: java.io.IOException: wrong value class: class org.apache.hadoop.io.LongWritable is not class org.apache.hadoop.io.IntWritable
at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:354)
Caused by: java.io.IOException: wrong value class: class org.apache.hadoop.io.LongWritable is not class org.apache.hadoop.io.IntWritable
at org.apache.hadoop.mapred.IFile$Writer.append(IFile.java:168)
at org.apache.hadoop.mapred.Task$CombineOutputCollector.collect(Task.java:1160)
at org.myorg.Sort$Reduce.reduce(Sort.java:34)
at org.myorg.Sort$Reduce.reduce(Sort.java:28)
at org.apache.hadoop.mapred.Task$OldCombinerRunner.combine(Task.java:1436)
at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.sortAndSpill(MapTask.java:1441)
at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.flush(MapTask.java:1303)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:431)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:366)
at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:223)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:724)
13/10/12 14:08:11 INFO mapred.JobClient:  map 0% reduce 0%
13/10/12 14:08:11 INFO mapred.JobClient: Job complete: job_local599611407_0001
13/10/12 14:08:11 INFO mapred.JobClient: Counters: 0
13/10/12 14:08:11 INFO mapred.JobClient: Job Failed: NA
Exception in thread "main" java.io.IOException: Job failed!
at org.apache.hadoop.mapred.JobClient.runJob(JobClient.java:1357)
at org.myorg.Sort.main(Sort.java:57)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.hadoop.util.RunJar.main(RunJar.java:160)

我做错什么了吗？谢谢你的帮助！

4

1 回答 1

5

注释掉下面的行，程序应该可以工作。这是对问题所在的解释。

conf.setCombinerClass(Reduce.class);

编写输入和输出类型相同的reducer 的另一种解决方案。在这种情况下，reducer 类也可以用作组合器类。

于 2013-10-12T08:15:18.707 回答