MapReduce编程初体验(WordCount)

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

Map类：

package itcast.demo01;

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

import java.io.IOException;

/**
 * @Author wcl09
 * @Version v 1.0
 * @Date 2019/11/12
 */
public class WordCountMap extends Mapper<LongWritable, Text, Text, LongWritable> {

@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
    //key       代码里指的是 这行数据的偏移量
    //value     数据

    //1.将value 从text转为string
    String datas = value.toString();
    //2.切分数据
    String[] splits = datas.split(",");
    //3.遍历输出
    for (String data : splits) {
        System.out.println(data);
        context.write(new Text(data), new LongWritable(1));
 	   }
   }
}

Reduce类：

package itcast.demo01;

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

import java.io.IOException;

/**
 * @Author wcl09
 * @Version v 1.0
 * @Date 2019/11/12
 */
public class WordCountReduce extends Reducer<Text, LongWritable, Text, LongWritable> {
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
        //value     输出的是相同key的数据集合
        long sum = 0;
        //遍历values
        for (LongWritable value : values) {
            sum += value.get();
        }
        //输出
        context.write(key, new LongWritable(sum));
    }
}

Driver驱动类：

package itcast.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;

/**
 * @Author wcl09
 * @Version v 1.0
 * @Date 2019/11/12
 */
public class WordCountDriver extends Configured implements Tool {

    @Override
    public int run(String[] args) throws Exception {
        //将已经编写好的Map    Reduce添加到计算框架中

        //1.实例化一个Job
        Job job = Job.getInstance(new Configuration(), "WordCount");

        //2.使用Job 设置读取数据(包括数据的路径)
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, new Path("E:\\Me\\日常\\测试代码\\a.txt"));

        //3.使用Job设置Map类(map 输出的类型)
        job.setMapperClass(WordCountMap.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //4.使用Job设置Reduce类(Reduce 输入和输出的类型)
        job.setReducerClass(WordCountReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //5.使用Job设置数据的输出路径
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job, new Path("E:\\Me\\日常\\测试代码\\b"));

        //6.返回执行状态编号
        return job.waitForCompletion(true) ? 0 : 1;
    }


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

}

pom文件配置

<?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>

结果展示：

原文件：

结果：