Question

我正在尝试为wordcount运行hadoop单个单元程序，我在Windows 10 64位和Cygwin上执行此操作，这是我正在使用的程序：

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);
   }
}

我的类路径如下：

~/hadoop-1.2.1/bin/hadoop jar WordCount.jar hadoop.ProcessUnits input_dir output_dir

当我尝试编译程序时收到以下错误消息：

    Exception in thread "main" java.lang.ClassNotFoundException: hadoop.ProcessUnits
    at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
    at java.lang.Class.forName0(Native Method)
    at java.lang.Class.forName(Class.java:348)
    at org.apache.hadoop.util.RunJar.main(RunJar.java:153)

Answer 1

问题是hadoop.ProcessUnits应指向您要运行的mainClass。您的班级名为WordCount，因此它应该类似于：

$ hadoop jar WordCount.jar <PACKAGE>.WordCount input_dir output_dir

您的代码不包含软件包名称，因此我替换了<PACKAGE>

在Hadoop中找不到类的异常

1 个答案: