MapReduce 单词统计案列

导包：

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>2.10.0</version>
        </dependency>

    </dependencies>

MyMapper类：

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

import java.io.IOException;

public class MyMapper extends Mapper<LongWritable, Text,Text,LongWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line=value.toString();
        String[] words = line.split(" ");
        for (String word : words) {
            context.write(new Text(word),new LongWritable(1));
        }

    }
}

MyReducer类：

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

import java.io.IOException;


public class MyReducer extends Reducer<Text, LongWritable,Text, LongWritable> {
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
        int sum=0;
        for (LongWritable value : values) {
            sum+=value.get();
        }
        context.write(key,new LongWritable(sum));
    }
}

MyJob类：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

import java.io.IOException;

public class MyDriver {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(MyDriver.class);
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        FileInputFormat.addInputPath(job,new Path("file:/home/hadoop/temp/wordcount.txt"));
        FileOutputFormat.setOutputPath(job,new Path("file:/home/hadoop/temp/wordcountRes"));

        FileSystem.get(conf).delete(new Path("file:/home/hadoop/temp/wordcountRes"),true);

        boolean b = job.waitForCompletion(true);

        System.exit(b?0:1);
    }
}