编写简单的Mapreduce程序并部署在Hadoop2.2.0上运行

2022-01-17 00:44:27

今天主要来说说怎么在Hadoop2.2.0分布式上面运行写好的 Mapreduce 程序。

可以在eclipse写好程序，export或用fatjar打包成jar文件。

先给出这个程序所依赖的Maven包：

<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>Temperature</groupId>

  <artifactId>Temperature</artifactId>

  <version>0.0.1-SNAPSHOT</version>

  <build>

    <sourceDirectory>src</sourceDirectory>

    <plugins>

      <plugin>

        <artifactId>maven-compiler-plugin</artifactId>

        <version>3.1</version>

        <configuration>

          <source>1.7</source>

          <target>1.7</target>

        </configuration>

      </plugin>

    </plugins>

  </build>

  <dependencies>

  <dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-mapreduce-client-core</artifactId>

      <version>2.2.0</version>

  </dependency>

  <dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-common</artifactId>

      <version>2.2.0</version>

  </dependency>

  <dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-mapreduce-client-common</artifactId>

      <version>2.2.0</version>

  </dependency>

  <dependency>

      <groupId>org.apache.hadoop</groupId>

      <artifactId>hadoop-mapreduce-client-jobclient</artifactId>

      <version>2.2.0</version>

  </dependency>

  </dependencies>

</project>

好了，现在给出程序，代码如下：

Mapper

package org.ccnt.mr;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapred.MapReduceBase;

import org.apache.hadoop.mapred.Mapper;

import org.apache.hadoop.mapred.OutputCollector;

import org.apache.hadoop.mapred.Reporter;

public class Map extends MapReduceBase implements

        Mapper<LongWritable, Text, Text, IntWritable> {

    private static final int MISSING = 9999;

    @Override

    public void map(LongWritable key, Text value,

            OutputCollector<Text, IntWritable> output, Reporter reporter)

            throws IOException {

        String line = value.toString();

        String year = line.substring(15, 19);

        int airTemperature;

        if (line.charAt(87) == '+')

            airTemperature = Integer.parseInt(line.substring(88, 92));

        else

            airTemperature = Integer.parseInt(line.substring(87, 92));

        String quality = line.substring(92, 93);

        if (airTemperature != MISSING && quality.matches("[01459]")) {

            output.collect(new Text(year), new IntWritable(airTemperature));

        }

    }

}

Reducer：

package org.ccnt.mr;

import java.io.IOException;

import java.util.Iterator;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapred.MapReduceBase;

import org.apache.hadoop.mapred.OutputCollector;

import org.apache.hadoop.mapred.Reducer;

import org.apache.hadoop.mapred.Reporter;

public class Reduce extends MapReduceBase implements

        Reducer<Text, IntWritable, Text, IntWritable> {

    @Override

    public void reduce(Text key, Iterator<IntWritable> values,

            OutputCollector<Text, IntWritable> output, Reporter reporter)

            throws IOException {

        int maxValue = Integer.MIN_VALUE;

        while (values.hasNext()) {

            maxValue = Math.max(maxValue, values.next().get());

        }

        output.collect(key, new IntWritable(maxValue));

    }

}

Main

package org.ccnt.mr;

import java.io.IOException;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapred.FileInputFormat;

import org.apache.hadoop.mapred.FileOutputFormat;

import org.apache.hadoop.mapred.JobClient;

import org.apache.hadoop.mapred.JobConf;

public class MaxTemperature {

    public static void main(String[] args) throws IOException {

        System.out.println(args.length);

        for (String string : args) {

            System.out.println(string);

        }

        if (args.length != 2) {

            System.err.println("Error");

            System.exit(1);

        }

        JobConf conf = new JobConf(MaxTemperature.class);

        conf.setJobName("Max Temperature");

        FileInputFormat.addInputPath(conf, new Path(args[0]));

        FileOutputFormat.setOutputPath(conf, new Path(args[1]));

        conf.setMapperClass(Map.class);

        conf.setReducerClass(Reduce.class);

        conf.setOutputKeyClass(Text.class);

        conf.setOutputValueClass(IntWritable.class);

        JobClient.runJob(conf);

    }

}

将上面的程序编译和打包成jar文件，然后开始在Hadoop2.2.0（本文假定用户都部署好了Hadoop2.2.0）上面部署了。下面主要讲讲如何去部署：
首先，启动Hadoop2.2.0，命令如下：

sbin/start-dfs.sh

sbin/start-yarn.sh

打包编译jar文件有两种方式：

1）直接用export导出jar包，生成默认的MANIFEST.MF文件，不需要写main方法所在的类

使用的命令：

bin/hadoop jar ~/Downlowd/MaxTemperature.jar org.ccnt.mr.MaxTemperature input/data.txt result

2）用Fat jar工具导出jar包，不需要导出依赖的（hadoop环境有），其实也就是MANIFEST.MF文件有了main方法所在的类。

bin/hadoop jar ~/Download/Temperature input/data.txt result2

结果是一样的。

附程序测试的数据的下载地址：http://pan.baidu.com/s/1iSacM

Reference：

[原]编写简单的Mapreduce程序并部署在Hadoop2.2.0上运行

码农公寓

[原]编写简单的Mapreduce程序并部署在Hadoop2.2.0上运行

相关文章