hadoop - Iterable 在 mapreduce Reduce Task 中不起作用

Question

大家好，我是 hadoop 的新手，我正在努力解决与 reducer 相关的问题。我有一个简单的 wordcount 程序，它没有返回预期的输出

预期输出:

这 1

哈多普 2

输出:

这 1

hadoop 1

hadoop 1

wordcount程序代码

package in.edureka.mapreduce;

import org.apache.hadoop.conf.Configuration;
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.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.mapreduce.lib.output.TextOutputFormat;

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

public class WordCount {

public static class Map extends Mapper<LongWritable, Text, Text, IntWritable>{

    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        StringTokenizer tokenizer = new StringTokenizer(value.toString());
        while (tokenizer.hasMoreTokens()){
            String token = tokenizer.nextToken();
            context.write(new Text(token), new IntWritable(1));
        }
    }
}

public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable>{


    public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for(IntWritable v: values){
            sum+=v.get();
        }
        context.write(key, new IntWritable(sum));
    }
}


public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    Configuration conf = new Configuration();   
    Job job = new Job(conf, "WordCount Programme");

    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

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

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    Path outputpath = new Path(args[1]);
    //Path outputpath = new Path(args[1]);

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));


    outputpath.getFileSystem(conf).delete(outputpath);

    System.setProperty("hadoop.home.dir", System.getProperty("user.home"));

    System.exit(job.waitForCompletion(true)? 0 : 1);
}
}

Answer 1

我不确定您的代码有什么问题，但我从文档 (https://hadoop.apache.org/docs/stable/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html#Example:_WordCount_v1.0) 中获取了以下内容

它按预期工作。

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.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;

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 void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.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);
  }
}