Windows下搭建环境测试Mapreduce--集群测试

需要配置Windows下的hadoop环境，大家可以去参考我的另一篇文章

Windows下HDFS的环境准备——HDFS相关的客户端操作_你可以自己看的博客-CSDN博客

创建Maven工程

设置Maven配置

导包

<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>

添加日志配置文件log4j.properties

log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

编写Mapper类

package com.gk.mapreduce.wordcount;

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;

/**
 * create with IntelliJ IDEA
 *
 * @Project :MapreduceDemo
 * @Package :com.gk.mapreduce.wordcount
 * @ClassName :
 * @CreateTime :2022/3/816:28
 * @Version :1.0
 * @Author :锦林
 * @Email :836658031@qq.com
 * <p>
 * 参数解释：KEYIN,传入参数key类型 LongWritable
 * VALUEIN,传入参数value类型 Text
 * KEYOUT,传出参数key类型 Text
 * VALUEOUT 传出参数value类型 IntWritable
 **/
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    private Text outK = new Text();
    private IntWritable outV = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 1 获取一行
        String line = value.toString();

        // 2 切割
        String[] words = line.split(" ");

        // 3 输出
        for (String word : words) {

            outK.set(word);
            context.write(outK, outV);
        }
    }
}

编写Reduce类

package com.gk.mapreduce.wordcount;

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

import java.io.IOException;

/**
 * create with IntelliJ IDEA
 *
 * @Project :MapreduceDemo
 * @Package :com.gk.mapreduce.wordcount
 * @ClassName :
 * @CreateTime :2022/3/816:29
 * @Version :1.0
 * @Author :锦林
 * @Email :836658031@qq.com
 * <p>
 * 参数解释：KEYIN,传入参数key类型 Text
 * VALUEIN,传入参数value类型 IntWritable
 * KEYOUT,传出参数key类型 Text
 * VALUEOUT 传出参数value类型 IntWritable
 **/
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    private IntWritable value = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        int sum = 0;

        // 遍历读取值
        for (IntWritable value : values) {

            // 1.累加求和
            sum += value.get();
        }

        // 2.输出
        value.set(sum);
        context.write(key,value);
    }
}

创建Driver类

package com.gk.mapreduce.wordcount;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

/**
 * create with IntelliJ IDEA
 *
 * @Project :MapreduceDemo
 * @Package :com.gk.mapreduce.wordcount
 * @ClassName :
 * @CreateTime :2022/3/816:29
 * @Version :1.0
 * @Author :锦林
 * @Email :836658031@qq.com
 **/
public class WordCountDriver {

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

        // 1.获取配置信息以及获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2.关联Driver程序的jar包
        job.setJarByClass(WordCountDriver.class);

        // 3.关联Mapper和reducer的Jar
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4.设置Mapper输出的k，y类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5.设置最终输出k，v类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6.设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path("E:\\SGG-Hadoop\\wcInput"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\SGG-Hadoop\\wcOutput"));

        // 7.提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);
    }
}

然后执行WordCountDriver下的main方法

显示已经执行成功了

现在我们去看一下输出文件

已经成功统计出输入文件中单词的次数了

现在我们把这个代码打包上传到集群去试一下，在这之前我们先去修改一些东西

首先，在pom.xml文件下添加如下代码，当然，其实这些代码可以不加，含义是打包的时候将依赖包一并打入进jar包中，我们的hadoop集群中是有相关jar包的，所以可以不需要

<build>
    <plugins>
    <plugin>
    <artifactId>maven-compiler-plugin</artifactId>
        <version>3.6.1</version>
        <configuration>
            <source>1.8</source>
            <target>1.8</target>
        </configuration>
    </plugin>
        <plugin>
            <artifactId>maven-assembly-plugin</artifactId>
            <configuration>
                <descriptorRefs>
                    <descriptorRef>jar-with-dependencies</descriptorRef>
                </descriptorRefs>
            </configuration>
            <executions>
                <execution>
                    <id>make-assembly</id>
                    <phase>package</phase>
                    <goals>
                        <goal>single</goal>
                    </goals>
                </execution>
            </executions>
        </plugin>
    </plugins>
    </build>

然后复制一份一模一样的代码出来，但是文件夹变了