hadoop 2.x 简单实现wordCount

标签：

简单实现hadoop程序，包括：hadoop2.x的实现写法

import org.apache.hadoop.conf.Configured;

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;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

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

/**
* Created by dell on 2016/7/3.
*/
public class WordCount extends Configured implements Tool {

public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable();
    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.hasMoreElements()) {
        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);
    }
}
@Override
public int run(String[] args) throws Exception {
     Job job = Job.getInstance(getConf());
     job.setJarByClass(WordCount.class);
     job.setMapperClass(TokenizerMapper.class);
     job.setCombinerClass(IntSumReducer.class);
     job.setReducerClass(IntSumReducer.class);
     job.setNumReduceTasks(Integer.parseInt(args[2])); //设置reducer个数
     job.setOutputKeyClass(Text.class);
     job.setOutputValueClass(IntWritable.class);
     FileInputFormat.addInputPath(job,new Path(args[0]));
     FileOutputFormat.setOutputPath(job,new Path(args[1]));
     job.waitForCompletion(true);
     return 0;
}
    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(),new WordCount(),args);
        System.exit(res);
    }
}

hadoop 2.x 简单实现wordCount

标签：

原文地址：http://www.cnblogs.com/yyy-blog/p/5638958.html