Hadoop wordcount源码

1.写完计数程序打包成jar
只要class文件即可
2.上传到node1上
3.hadoop jar wordcount.jar com.hadoop.mr.WordCount

hdfs dfs -ls /data/output
hdfs dfs -cat /data/output/part-r-00000
也可以把内容copy到当前的目录
hdfs dfs -get /data/output/* ./

package com.hadoop.mr.count;

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 void main(String[] args) throws Exception {
		Configuration configuration = new Configuration(true);
		
		
		Job job = Job.getInstance(configuration);
		job.setJarByClass(WordCount.class);
    
    job.setJobName("wordcount");
    
    Path input = new Path("/data/test3.txt");
    FileInputFormat.addInputPath(job, input);
    Path output = new Path("/data/output2");
    FileOutputFormat.setOutputPath(job, output);
    
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    
    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    // Submit the job, then poll for progress until the job is complete
    job.waitForCompletion(true);

	}

	
	
}
class MyMapper 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);
    }
  }

}
class MyReducer 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);
  }

}