MapReduce实现WordCount

通过WordCount案例来更好地理解MapReduce的map、reduce实现过程。

1、构建maven项目

2、添加maven依赖

这里使用的hadoop版本是hadoop-2.6.0-cdh5.7.0

<modelVersion>4.0.0</modelVersion>
<groupId>com.xxx</groupId>
<artifactId>mapreduce-app</artifactId>
<version>0.0.1-SNAPSHOT</version>
<packaging>jar</packaging>
<name>mapreduce-app</name>
<url>http://maven.apache.org</url>

<repositories>
    <repository>
        <id>cloudera</id>
        <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
    </repository>
</repositories>

<properties>
    <hadoop.version>2.6.0-cdh5.7.0</hadoop.version>
</properties>

<dependencies>
    <!-- hadoop -->
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>${hadoop.version}</version>
    </dependency>

    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>${hadoop.version}</version>
    </dependency>

    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>${hadoop.version}</version>
    </dependency>
</dependencies>

3、java实现mapreduce

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 MyMapper extends Mapper<Object, Text, Text, IntWritable>{
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        @Override
        protected 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);
            }
        }
    }

    public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
        private IntWritable result = new IntWritable();

        @Override
        protected 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);
        }
    }



    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(MyMapper.class);
        job.setCombinerClass(MyReducer.class);
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true)?0:1);
    }

}

4、使用maven命令打jar包

E:\workspace\mapreduce-app>mvn clean install

5、rz上传jar包到服务器

6、创建hdfs输入文件

# 创建输入文件目录
hadoop fs -mkdir -p /data/map-reduce/wordcount/input
# 生成输入文件
hadoop fs -put 1.log /data/map-reduce/wordcount/input/
hadoop fs -put 2.log /data/map-reduce/wordcount/input/

文件1.log内容如下：

[hadoop@hadoop001 hadoop]$ cat 1.log 
aaaaaaaa
bbbb
cc
2341
xxxxxxx
www.baidu.com
java
hadoop
java 

文件2.log内容如下：

[hadoop@hadoop001 hadoop]$ cat 2.log 
aaaaa
test
java
hadoop

7、非第一次执行，删除输出文件目录

hadoop fs -rmr /data/map-reduce/wordcount/output

8、执行jar包

bin/hadoop jar mapreduce-app.jar com.xxx.WordCount /data/map-reduce/wordcount/input /data/map-reduce/wordcount/output

9、查看输出结果

hadoop fs -cat /data/map-reduce/wordcount/output/part-r-00000