IDEA 运行 Hadoop WordCount示例

1、在本地解压hadoop安装包，然后修改系统变量，增加HADOOP_HOME及HADOOP_USER_NAME，HADOOP_USER_NAME为实际集群运行用户



2、修改项目的Pom文件

<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-jobclient</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>commons-cli</groupId>
<artifactId>commons-cli</artifactId>
<version>1.2</version>
</dependency>
</dependencies>

3、将core-site.xml、hdfs-site.xml、mapred-site.xml、yarn-site.xml、log4j.properties拷贝至resources目录

在mapred-site.xml设置

<property>
<name>mapreduce.app-submission.cross-platform</name>
<value>true</value>
</property>
<property>
<name>mapred.jar</name>
<value>E:\Projects\hadoop\HadoopExercise\target\HadoopExercise-1.0-SNAPSHOT.jar</value>
</property>

4、示例程序

Mapper

package org.zheng.demo;

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

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

public class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable> {

private final static IntWritable one = new IntWritable(1);

private Text word = new Text();

@Override
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);
}
}
}

Reducer

package org.zheng.demo;

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

import java.io.IOException;

public class IntSumReducer
extends Reducer<Text, IntWritable, Text, IntWritable> {

private IntWritable result = new IntWritable();

@Override
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);
}
}

Main

package org.zheng.demo;

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

public class WordCount {

public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
//设置RM 访问位置
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);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}

5、编辑运行选项，设置参数



6、运行