Hadoop专栏（四）使用idea操作MapReduce（代码篇）

写在前面：

mapreduce 任务的提交方式
1. 打成JAR包，上传Linux，hadoop jar 执行
2. 嵌入某个应用程序：IDE 直接提交
3. local模式，在Windows上本地执行

以下代码，先使用IDEA直接提交，再打包成jar包后上传Linux执行

一、编写word count代码

注：依赖下载的jar包的配置文件pom.xml放在文末

1.驱动程序WordCountDriver.class

package cn.kgc.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 javax.security.auth.login.AppConfigurationEntry;
import java.io.IOException;


public class WordCountDriver {
    public static void main(String[] args) throws InterruptedException, IOException, ClassNotFoundException {
        //1.获取配置信息以及封装任务
        Configuration conf=new Configuration();
        Job job=Job.getInstance(conf);
        //2.设置jar加载路径
        job.setJarByClass(WordCountDriver.class);
        //3.设置map和reduce类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        //4.设置map输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputKeyClass(IntWritable.class);
        //5.设置最终的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //6.设置输入和输出路径
        FileInputFormat.setInputPaths(job,new Path("D:\\IDEA_project\\Hadoop_day1201\\data\\hello.txt"));
        FileOutputFormat.setOutputPath(job,new Path("D:\\IDEA_project\\Hadoop_day1201\\data\\output"));
        //7.提交任务执行代码
        boolean result=job.waitForCompletion(true);
        System.exit(result?0:1);
        //o正常退出
        //1或者-1  异常退出
    }
}

2.Map类WordCountMapper.java

package cn.kgc.wordcount;


import com.amazonaws.services.dynamodbv2.xspec.L;
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;

/**
 * <KEYIN,VALEIN,KEYOUT,VALUEOUT>
 * 输入的key(0,helloworld
 * 输入的value       helloworld
 * 输出的key   (hello,1)    hello
 * 输出的value               1
 */
public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    Text k = new Text();
    IntWritable v = new IntWritable(1);

protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {
        //1.获取一行内容，并转换成字符串操作
        String line = value.toString();
        //2.按空格进行切割
        String[] words = line.split(" ");
        // 3.输出(word,1)
        for (String word : words) {
            k.set(word);
            context.write(k,v);
        }
        }
}

3.Reducer类WordCountReducer.java

package cn.kgc.wordcount;

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

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, IntWritable,Text, LongWritable>{
    int sum;
    LongWritable v=new LongWritable();
    @Override
    protected void reduce(Text key,Iterable<IntWritable> value,Context context) throws IOException, InterruptedException {
        //1.对输入的Interator类型进行累加求和
        sum=0;
        for (IntWritable count : value) {
            sum+=count.get();
        }
        //2.输出（word,总次数）
        v.set(sum);
        context.write(key,v);
    }
    }

4.运行代码
运行Driver类

二、在idea中将项目打包

步骤如图所示

三、在虚拟机中操作

1.打开hdfs和yarn

cd /opt/install/hadoop
sbin/start-dfs.sh
sbin/start-yarn.sh

2.执行jar包

hadoop jar hadoop_day1202-1.0-SNAPSHOT.jar cn.kgc.wordcount WordCountDriver /wcinput /wcoutput2

3.在文件系统中查看

4.在虚拟机中查看

hdfs dfs -cat /wcoutput2/part-r-00000

附录：

配置文件pom.xml

<?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>cn.kgc</groupId>
    <artifactId>Hadoop</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-auth</artifactId>
            <version>2.6.0-cdh5.14.2</version>
        </dependency>
    </dependencies>
    <build>
        <pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
            <plugins>
                <plugin>
                    <artifactId>maven-assembly-plugin</artifactId>
                    <executions>
                        <execution>
                            <phase>package</phase>
                            <goals>
                                <goal>single</goal>
                            </goals>
                        </execution>
                    </executions>
                    <configuration>
                        <descriptorRefs>
                            <descriptorRef>jar-with-dependencies</descriptorRef>
                        </descriptorRefs>
                    </configuration>
                </plugin>
            </plugins>
        </pluginManagement>
    </build>
    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
</project>