hadoop案例WordCount

原创
2014/02/21 11:01
阅读数 174

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();
    //TextInput默认设置是读取一行数据,map阶段是按照我们的需求将读取到的每一行进行分割。
    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
     StringTokenizer line = new StringTokenizer(value.toString());
     while(line.hasMoreTokens()){
      word.set(line.nextToken());
      context.write(word, one);
     }
    }
  }
  //在reduce阶段,是map阶段分割后的经过排序后的数据向reduce任务中copy的过程,在此过程中会有一个背景线程将相同的key值进行合并,并将其value值归并到一个类似集合的容器中,此时的逻辑就是我们要遍历这个容器中的数据,计算它的值,然后输出。
  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();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
    Job job = new Job(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(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

展开阅读全文
打赏
0
1 收藏
分享
加载中
更多评论
打赏
0 评论
1 收藏
0
分享
返回顶部
顶部