hadoop小Demo

关于Maven的使用就不再啰嗦了，网上很多，并且这么多年变化也不大，这里仅介绍怎么搭建Hadoop的开发环境。

1. 首先创建工程

mvn archetype:generate -DgroupId=my.hadoopstudy -DartifactId=hadoopstudy -DarchetypeArtifactId=maven-archetype-quickstart -DinteractiveMode=false

2. 然后在pom.xml文件里添加hadoop的依赖包hadoop-common, hadoop-client, hadoop-hdfs，添加后的pom.xml文件如下

<project xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://maven.apache.org/POM/4.0.0"
		 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
	<modelVersion>4.0.0</modelVersion>
	<groupId>my.hadoopstudy</groupId>
	<artifactId>hadoopstudy</artifactId>
	<packaging>jar</packaging>
	<version>1.0-SNAPSHOT</version>
	<name>hadoopstudy</name>
	<url>http://maven.apache.org</url>

	<dependencies>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-common</artifactId>
			<version>2.5.1</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-hdfs</artifactId>
			<version>2.5.1</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-client</artifactId>
			<version>2.5.1</version>
		</dependency>

		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>3.8.1</version>
			<scope>test</scope>
		</dependency>
	</dependencies>
</project>

3. 测试3.1 首先我们可以测试一下hdfs的开发，这里假定使用上一篇Hadoop文章中的hadoop集群，类代码如下

package my.hadoopstudy.dfs;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;

import java.io.InputStream;
import java.net.URI;

public class Test {
	public static void main(String[] args) throws Exception {
		String uri = "hdfs://9.111.254.189:9000/";
		Configuration config = new Configuration();
		FileSystem fs = FileSystem.get(URI.create(uri), config);

		// 列出hdfs上/user/fkong/目录下的所有文件和目录
		FileStatus[] statuses = fs.listStatus(new Path("/user/fkong"));
		for (FileStatus status : statuses) {
			System.out.println(status);
		}

		// 在hdfs的/user/fkong目录下创建一个文件，并写入一行文本
		FSDataOutputStream os = fs.create(new Path("/user/fkong/test.log"));
		os.write("Hello World!".getBytes());
		os.flush();
		os.close();

		// 显示在hdfs的/user/fkong下指定文件的内容
		InputStream is = fs.open(new Path("/user/fkong/test.log"));
		IOUtils.copyBytes(is, System.out, 1024, true);
	}
}

3.2 测试MapReduce作业测试代码比较简单，如下：

package my.hadoopstudy.mapreduce;

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;
import org.apache.hadoop.util.GenericOptionsParser;

import java.io.IOException;

public class EventCount {

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

		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
			int idx = value.toString().indexOf(" ");
			if (idx > 0) {
				String e = value.toString().substring(0, idx);
				event.set(e);
				context.write(event, one);
			}
		}
	}

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

		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);
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
		if (otherArgs.length < 2) {
			System.err.println("Usage: EventCount <in> <out>");
			System.exit(2);
		}
		Job job = Job.getInstance(conf, "event count");
		job.setJarByClass(EventCount.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(otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}

运行“mvn package”命令产生jar包hadoopstudy-1.0-SNAPSHOT.jar，并将jar文件复制到hadoop安装目录下

这里假定我们需要分析几个日志文件中的Event信息来统计各种Event个数，所以创建一下目录和文件

/tmp/input/event.log.1
/tmp/input/event.log.2
/tmp/input/event.log.3

因为这里只是要做一个列子，所以每个文件内容可以都一样，假如内容如下

JOB_NEW ...
JOB_NEW ...
JOB_FINISH ...
JOB_NEW ...
JOB_FINISH ...

然后把这些文件复制到HDFS上

$ bin/hdfs dfs -put /tmp/input /user/fkong/input

运行mapreduce作业

$ bin/hadoop jar hadoopstudy-1.0-SNAPSHOT.jar my.hadoopstudy.mapreduce.EventCount /user/fkong/input /user/fkong/output

查看执行结果

$ bin/hdfs dfs -cat /user/fkong/output/part-r-00000