用idea初测MapReduce框架

最新推荐文章于 2024-06-12 19:56:03 发布

原创最新推荐文章于 2024-06-12 19:56:03 发布 · 1.6k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#MapReduce #hadoop

hadoop 同时被 2 个专栏收录

4 篇文章

订阅专栏

MapReduce

4 篇文章

订阅专栏

本文详细介绍了一个基于Hadoop的WordCount实现过程，包括Maven配置、MapReduce编程及作业执行。通过具体代码示例，展示了如何进行文本的单词计数。

先配置pom文件

<?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.czxy</groupId>
    <artifactId>sadas</artifactId>

    <version>1.0-SNAPSHOT</version>
    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-client</artifactId>
            <version>2.6.0-mr1-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-common</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-hdfs</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-mapreduce-client-core</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>RELEASE</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <minimizeJar>true</minimizeJar>
                        </configuration>
                    </execution>
                </executions>
            </plugin>

        </plugins>
    </build>
</project>

编写三个java代码

WordCountMap

package com.czxy;

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

import java.io.IOException;

public class WordCountMap extends Mapper<LongWritable,Text,Text,LongWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
  
        //1. 将value 从test转为string
        String datas = value.toString();
        //2. 切分数据
        String[] s = datas.split(",");
        //3. 遍历输出
        for (String data : s) {
            //输出
            context.write(new Text(data),new LongWritable(1));
        }

    }
}

WordCountReduce

package com.czxy;

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

import java.io.IOException;

public class WordCountReduce extends Reducer<Text, LongWritable,Text,LongWritable> {
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
      
        long sum = 0;
        for (LongWritable value : values) {
            sum += value.get();
        }

        context.write(key,new LongWritable(sum));
    }
}

WordCountDriver

package com.czxy;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCountDriver extends Configured implements Tool {

    //执行job
    public static void main(String[] args) throws Exception {
        ToolRunner.run(new WordCountDriver(), args);
    }

    @Override
    public int run(String[] args) throws Exception {
        //将已经编写好的map reduce 添加到计算框架
        //1. 实例一个 job
        Job job = Job.getInstance(new Configuration(), "WordCount34");
        //2. 使用 job 设置读取数据 （数据类型 ，数据路径）
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, new Path("C:\\a.txt"));
        //3. 使用 job 设置map 类（map输入的类型）
        job.setMapperClass(WordCountMap.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        //4. 使用 job 设置reduce 类 （输入的类型）
        job.setReducerClass(WordCountReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        //5. 使用 job 设置数据输出的路径
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job, new Path("C:\\BBB2"));
        //6.返回代码执行状态编号
        return job.waitForCompletion(true) ? 0 : 1;
    }
}