hadoop 2.3.0 wordcount

最新推荐文章于 2022-04-18 12:05:41 发布

原创最新推荐文章于 2022-04-18 12:05:41 发布 · 85 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#hadoop #java #maven

java 专栏收录该内容

67 篇文章

订阅专栏

本文介绍了如何使用Maven构建一个Hadoop示例项目，并详细说明了创建类、配置Maven依赖、安装jar包、上传至Hadoop环境、创建文本文件、执行WordCount任务及查看结果的过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

新建maven项目

<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>hadoop2.3</groupId>
  <artifactId>example</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <name>hadoop示例</name>


  <properties>
  	<hadoop-version>2.3.0</hadoop-version>
  </properties>

  <dependencies>

  <dependency>
	<groupId>org.apache.hadoop</groupId>
	<artifactId>hadoop-core</artifactId>
	<version>1.2.1</version>
</dependency>

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

	<dependency>
	    <groupId>jdk.tools</groupId>
	    <artifactId>jdk.tools</artifactId>
	    <version>1.6</version>
	    <scope>system</scope>
	    <systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
	</dependency>

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


  </dependencies>
</project>

2、新建类


/**
 * 
 */
package com.xxx.example;


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

	public class MyWordcount {

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

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

	    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);
	      }
	    }
	  }

	  public static class IntSumReducer 
	       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: wordcount <in> <out>");
	      System.exit(2);
	    }
	    Job job = new Job(conf, "word count");
	    job.setJarByClass(MyWordcount.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(otherArgs[0]));
	    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
	    System.exit(job.waitForCompletion(true) ? 0 : 1);
	  }
	}

3、maven install
生成jar
example-0.0.1-SNAPSHOT.jar

4、上传到hadoop_home目录

5、创建word.txt
mkdir input

vi input/word.txt
输入文字

保存

6、执行
bin/hadoop jar example-0.0.1-SNAPSHOT.jar com.xxx.example.MyWordcount file:///data01/javaapp/hadoop-2.3.0/input/word.txt output

7、查看结果
http://192.168.1.22:50070/explorer.html

或者

bin/hadoop fs -ls -R output

bin/hadoop fs -cat output/part-**

8、删除执行结果

bin/hadoop fs -rm -r output*