建立Maven项目
```xml
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.gosuncn</groupId>
<artifactId>MapReduce</artifactId>
<version>1.0-RELEASE</version>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.7.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.5</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>2.7.5</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>2.4</version>
<configuration>
<archive>
<manifest>
<addClasspath>true</addClasspath>
<classpathPrefix>lib/</classpathPrefix>
<mainClass>com.gosuncn.WordCountDriver</mainClass>
</manifest>
</archive>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.7.0</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
</plugins>
</build>
</project>
```
编写Mapper
```java
package com.gosuncn;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* 拆分单词
*/
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
@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 IntWritable(1));
}
}
}
```
编写Reducer
```java
package com.gosuncn;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
* 计算单词
*/
public class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int count = 0; // 计数器
for (IntWritable value : values) {
count++;
}
context.write(key, new IntWritable(count));
}
}
```
编写Driver
```java
package com.gosuncn;
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 WordCountDriver {
public static void main(String[] args) throws Exception {
Job job = Job.getInstance();
job.setJarByClass(WordCountDriver.class); // 指定Jar包运行的主类
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
/**
* 指定文件位置
*/
FileInputFormat.setInputPaths(job, "/gosuncn/input");
FileOutputFormat.setOutputPath(job, new Path("/gosuncn/output"));
// job.submit();
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
```
打包上传到服务器`Hadoop1`
```bash
hadoop fs -mkdir -p /gosuncn/input # 新建目录并制造一些假数据
```
运行jar包
```bash
hadoop jar MapReduce-1.0-RELEASE.jar
```
在`/gosuncn/output`查看结果。
