MapReduce的Jar包上传到集群运行

需求：

在给定的文本文件中统计输出每一个单词出现的总次数

数据格式准备如下：

创建这个文件

cd /export/servers
vim wordcount.txt

文件内容：

hello,world,hadoop
hello,hive,sqoop,flume
kitty,tom,jerry,world
hadoop

上传成功后效果

上传文件到集群

hdfs dfs -mkdir /wordcount/
hdfs dfs -put wordcount.txt /wordcount/

项目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>cn.itcast</groupId>
    <artifactId>mapreduce</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>

准备java代码

JobMain.class

package com.czxy.demo01;

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 JobMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        Job job =Job.getInstance(new Configuration(),"WordCount");

        //这一行让你的代码能在集群上跑，没有就找不到jar包
        job.setJarByClass(JobMain.class);

        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("hdfs://192.168.100.201:8020/wordcount"));
        //MapReduce程序的输入如果是一个目录，则会计算目录下所有文件
        //如果指定某文件，则只计算这个文件。
        //这里就是输入一个目录，就会计算目录下所有文件，也就是上传的那个文件。

        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(WordCountReducer.class);
        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(LongWritable.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("hdfs://192.168.100.201:8020/wordcount_out"));
        //输出的文件目录不能存在

        boolean b = job.waitForCompletion(true);
        return b?0:1;
    }

    /**
     * 程序main函数的入口类
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        Tool tool  =  new JobMain();
        int run = ToolRunner.run(configuration, tool, args);
        System.exit(run);
    }

}

WordCountMapper.class

package com.czxy.demo01;

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

public class WordCountMapper extends Mapper<LongWritable,Text,Text,LongWritable> {
    @Override
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] split = line.split(",");
        for (String word : split) {
            context.write(new Text(word),new LongWritable(1));
        }

    }
}

WordCountReducer.class

package com.czxy.demo01;

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,LongWritable,Text,LongWritable> {
    /**
     * 自定义reduce逻辑
     * 所有的key都是单词，所有的values都是单词出现的次数
     * @param key
     * @param values
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
        long count = 0;
        for (LongWritable value : values) {
            count += value.get();
        }
        context.write(key,new LongWritable(count));
    }
}

写完代码打成jar包

先clean在package

package成功后，target文件夹出现了，里面出现俩jar包

名字短的体积比较大，里面包括了运行所需要的所有jar包
名字长的体积小，里面只有核心程序。不包括运行所需要的jar包

所以，使用体积比较大的，把它先上传到集群里
复制，粘贴到桌面，改名为test.jar

然后先上传虚拟机，再上传集群

上传完毕，可以运行试试

hadoop jar test.jar com.czxy.demo01.JobMain

运行完毕，查看运行结果

运行成功，每一个单词的次数统计出来了。（需求：在给定的文本文件中统计输出每一个单词出现的总次数）
最重要的是：

job.setJarByClass(JobMain.class);

补充

Map的数量不能人为设置，reduce的数量可以人为设置。

job.setNumReduceTasks(3);

reduce数量越多，计算速度越快。

combinner的添加

ComBiner 在map端局部聚和，设置reduce的class

job.setCombinerClass(WordCountReduce.class);