【Hadoop】MapperReduce WordCount 代码示例

MAC Idea Maven

工程 maven-archetype-profiles

pom.xml

<!--HDFS-->
      <dependency>
          <groupId>org.apache.hadoop</groupId>
          <artifactId>hadoop-common</artifactId>
          <version>2.5.1</version>
      </dependency>
      <dependency>
          <groupId>org.apache.hadoop</groupId>
          <artifactId>hadoop-hdfs</artifactId>
          <version>2.5.1</version>
      </dependency>

      <!--MapReduce-->

      <dependency>
          <groupId>org.apache.hadoop</groupId>
          <artifactId>hadoop-mapreduce-client-common</artifactId>
          <version>2.5.1</version>
      </dependency>

      <dependency>
          <groupId>org.apache.hadoop</groupId>
          <artifactId>hadoop-mapreduce-client-core</artifactId>
          <version>2.5.1</version>
      </dependency>

package com.ndz.mapreducedemo;

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);
            }

            /*
             *eg: map output:
             *        hello  1
             *        word   1
             *        hello  1
             *        hadoop 1
             */
        }
    }

    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;
            System.out.println("-----------------------------------------");
            System.out.println("key: "+key);
            for (IntWritable val : values) {
                sum += val.get();
                System.out.println("val: "+val);
            }
            result.set(sum);
            System.out.println("result: "+result.toString());
            context.write(key, result);
        }
    }


    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://172.16.152.130:8020");
        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);
       // hdfs dfs -chmod -R 777 /usr/ 必须要给权限, 否则将运行失败
        FileInputFormat.addInputPath(job, new Path("/usr/input/data/wc"));
        FileOutputFormat.setOutputPath(job, new Path("/usr/output/data/wc"));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }


}

附录：

hdfs dfs -chmod -R 777 /usr/ 
 hdfs dfs -cat /usr/output/data/wc/part-r-00000
hdfs dfs -ls -R  /usr/
hdfs dfs -rm -r  /usr/output