Mapreduce实例——WordCount

Mapreduce实例-WordCount是一个经典的MapReduce程序，用于统计文本中每个单词出现的次数。它的工作原理是将输入的文本划分为多个片段，每个片段由多个键值对组成，其中键是单词，值是1。然后通过Map阶段将每个片段中的单词提取出来，并将每个单词映射为键值对，其中键是单词，值是1。接下来，通过Shuffle和Sort阶段将具有相同单词的键值对聚集在一起。最后，通过Reduce阶段将相同单词的计数值进行累加，得到每个单词的总次数。

以下是一个示例代码片段，展示了WordCount程序的基本结构和关键组件：

import java.io.IOException;
import java.util.StringTokenizer;
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 {
    Job job = Job.getInstance();
    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);
  }
}