MapReduce案例WordCount

所需的 pom 依赖：

    
        org.apache.hadoop
        hadoop-client
        2.7.3
    
    
        org.apache.hadoop
        hadoop-common
        2.7.3
    
    
        org.apache.hadoop
        hadoop-hdfs
        2.7.3
    

      17       1

<dependencies>

2

    <dependency>

3

        <groupId>org.apache.hadoopgroupId>

4

        <artifactId>hadoop-clientartifactId>

5

        <version>2.7.3version>

6

    dependency>

7

    <dependency>

8

        <groupId>org.apache.hadoopgroupId>

9

        <artifactId>hadoop-commonartifactId>

10

        <version>2.7.3version>

11

    dependency>

12

    <dependency>

13

        <groupId>org.apache.hadoopgroupId>

14

        <artifactId>hadoop-hdfsartifactId>

15

        <version>2.7.3version>

16

    dependency>

17

dependencies>

   

Mapper 实现：

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper {

    private Text k = new Text();
    private LongWritable v = new LongWritable();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        // 分词
        String[] words = line.split(" ");
        // 输出
        for (String word : words) {
            k.set(word);
            v.set(1L);
            context.write(k, v);
        }
    }
}

              1

import java.io.IOException;

2

import org.apache.hadoop.io.LongWritable;

3

import org.apache.hadoop.io.Text;

    4

import org.apache.hadoop.mapreduce.Mapper;

5

6

public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

7

8

    private Text k = new Text();

9

    private LongWritable v = new LongWritable();

10

11

    @Override

12

    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

13

        String line = value.toString();

14

        // 分词

15

        String[] words = line.split(" ");

16

        // 输出

17

        for (String word : words) {

18

            k.set(word);

19

            v.set(1L);

20

            context.write(k, v);

21

        }

22

    }

23

}

   

Reducer 实现：

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer {

    private LongWritable value = new LongWritable();

    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        long sum = 0;
        // 计数
        for (LongWritable v : values) {
            sum += v.get();
        }
        // 输出
        value.set(sum);
        context.write(key, value);
    }
}

      22       1

import java.io.IOException;

2

3

import org.apache.hadoop.io.LongWritable;

4

import org.apache.hadoop.io.Text;

5

import org.apache.hadoop.mapreduce.Reducer;

6

7

public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable> {

8

9

    private LongWritable value = new LongWritable();

10

11

    @Override

12

    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

13

        long sum = 0;

14

        // 计数

15

        for (LongWritable v : values) {

16

            sum += v.get();

17

        }

18

        // 输出

19

        value.set(sum);

20

        context.write(key, value);

21

    }

22

}

   

Driver 实现：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class Driver {

    public static void main(String[] args) throws Exception {
        args = new String[]{"D:/EclipseWorkspace/mapreducetop10/hello.txt",
            "D:/EclipseWorkspace/mapreducetop10/output"};

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 指明程序的入口
        job.setJarByClass(Driver.class);

        // 指明mapper
        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        // 指明reducer
        job.setReducerClass(WordCountReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        // 指明任务的输入输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 启动任务
        job.waitForCompletion(true);
    }
}

      37       1

import org.apache.hadoop.conf.Configuration;

2

import org.apache.hadoop.fs.Path;

3

import org.apache.hadoop.io.LongWritable;

4

import org.apache.hadoop.io.Text;

5

import org.apache.hadoop.mapreduce.Job;

6

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

7

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

8

9

public class Driver {

10

11

    public static void main(String[] args) throws Exception {

12

        args = new String[]{"D:/EclipseWorkspace/mapreducetop10/hello.txt",

13

            "D:/EclipseWorkspace/mapreducetop10/output"};

14

15

        Configuration conf = new Configuration();

16

        Job job = Job.getInstance(conf);

17

        // 指明程序的入口

18

        job.setJarByClass(Driver.class);

19

20

        // 指明mapper

21

        job.setMapperClass(WordCountMapper.class);

22

        job.setMapOutputKeyClass(Text.class);

23

        job.setMapOutputValueClass(LongWritable.class);

24

25

        // 指明reducer

26

        job.setReducerClass(WordCountReducer.class);

27

        job.setOutputKeyClass(Text.class);

28

        job.setOutputValueClass(LongWritable.class);

29

30

        // 指明任务的输入输出路径

31

        FileInputFormat.setInputPaths(job, new Path(args[0]));

32

        FileOutputFormat.setOutputPath(job, new Path(args[1]));

33

34

        // 启动任务

35

        job.waitForCompletion(true);

36

    }

37

}

   

WordCount执行过程：（图示）