java - MapReduce 排序程序中的 NullPointerException

Question

我知道 SortComparator 用于按键对映射输出进行排序。我编写了自定义 SortComparator 以更好地理解 MapReduce 框架。这是我的带有自定义 SortComparator 类的 WordCount 类。

package bananas;

import java.io.FileWriter;
import java.io.IOException;
import java.util.StringTokenizer;

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.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount {


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

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());

      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);

      }
    }
  }

  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();    
    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
                       ) throws IOException, InterruptedException {


      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }

      result.set(sum);
      context.write(key, result);
    }
  }

  public static class MyPartitoner extends Partitioner<Text, IntWritable>{

    @Override
    public int getPartition(Text key, IntWritable value, int numPartitions) {


        return Math.abs(key.hashCode()) % numPartitions;
    }  
  }

  public static class MySortComparator2 extends WritableComparator{

      protected MySortComparator2() {
          super();
          }

      @SuppressWarnings({ "rawtypes" })
    @Override
      public int compare(WritableComparable w1,WritableComparable w2){

          return 0;
      }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setSortComparatorClass(MySortComparator2.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(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

但是当我执行这个时我得到了这个错误

Error: java.lang.NullPointerException
    at org.apache.hadoop.io.WritableComparator.compare(WritableComparator.java:157)
    at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.compare(MapTask.java:1265)
    at org.apache.hadoop.util.QuickSort.fix(QuickSort.java:35)
    at org.apache.hadoop.util.QuickSort.sortInternal(QuickSort.java:87)
    at org.apache.hadoop.util.QuickSort.sort(QuickSort.java:63)
    at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.sortAndSpill(MapTask.java:1593)
    at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.flush(MapTask.java:1482)
    at org.apache.hadoop.mapred.MapTask$NewOutputCollector.close(MapTask.java:720)
    at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:790)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
    at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:163)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:415)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628)
    at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158) 

我的自定义 SortComparator 类看起来不错。映射完成后，MySortComparator2 的比较方法应该接收“文本”键作为输入，因为我返回 0，所以不会进行排序。这是我期望看到/观察到的。我遵循了这些教程

http://codingjunkie.net/secondary-sort/

http://blog.zaloni.com/secondary-sorting-in-hadoop

http://www.bigdataspeak.com/2013/02/hadoop-how-to-do-secondary-sort-on_25.html

提前致谢 我希望能得到一些帮助。

Answer 1

实际上，MySortComparator2 构造函数存在问题。代码应该看起来像

protected MySortComparator2() {
      super(Text.class, true);
}

其中第一个参数是您的键类，第二个参数的值确保 WritableComparator 以 WritableComparator.compare(byte[] b1, int s1, int l1, byte [] b2, int s2, int l2) 可以调用 MySortComparator2.compare(WritableComparable a, WritableComparable b)