Hadoop_MapReduc WordCount案例

新建Maven项目

在pom.xml中写入

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>org.cheetah</groupId>
    <artifactId>MapReduceDemo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-app</artifactId>
            <version>3.1.3</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-server-resourcemanager</artifactId>
            <version>3.1.3</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>

    <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>
    
</project>

在resources中创建log4j.properties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文件

WordCountMapper.java

package wordcount2;

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, VALUEIN, KEYOUT, VALUEOUT
 * 第一个：map阶段输入的k 偏移量 LongWritable
 * 第二个：map阶段输入value类型为 Text
 * 第三个：map阶段输出的key类为 Text
 * 第四个：map阶段输出的value类为 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, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {

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

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

        //3循环写出
        for (String word : words) {
            //封装
            outK.set(word);

            //写出
            context.write(outK,outV);
        }
    }
}

编写Reduce文件

WordCountReducer.java

package wordcount2;

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

import java.io.IOException;

/**
 * map的输出是reduce的输入
 * KEYIN, VALUEIN, KEYOUT, VALUEOUT
 * 第一个：reduce阶段输入的k Text
 * 第二个：reduce阶段输入value类型为 IntWritable
 * 第三个：reduce阶段输出的key类为 Text
 * 第四个：reduce阶段输出的value类为 IntWritable
 */
public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    IntWritable outV=new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        int sum=0;

        //累加
        for (IntWritable value : values) {
            sum+=value.get();
        }

        outV.set(sum);
        //写出
        context.write(key,outV);
    }
}

编写Driver文件

WordCountDriver.java

package wordcount2;

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;

public class WordCountDriver {

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

        // 1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        // 3 关联mapper和reducerWordCountMapper
        //                     WordCountMapper
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出的kV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

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

对Maven进行打包