WordCount案例实操

WordCount案例实操

java代码

WordCountMapper类

package com.guodaxia.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;
 
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    //1. 定义 k - v (文本 - 数量)
    Text k = new Text();
    IntWritable v = new IntWritable(1);//必须初始为1
 
    //2，重写map方法，业务代码
    @Override
    protected void map(LongWritable key,Text value ,Context context) throws IOException, InterruptedException {
        //1.从数据源中获得一行数据
        String line = value.toString();
        //2.分割该行中的单词
        String[] words = line.split(" ");
        //3.输出
        for(String word:words){
            k.set(word);//不对v做任何操作
            context.write(k,v);//TODO
        }
    }
}

WordCountReducer类

package com.guodaxia.mapreduce.wordcount;
 
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
 
import java.io.IOException;
 
public class WordCountReducer extends Reducer<Text , IntWritable , Text ,IntWritable> {
    int sumTemp;
    IntWritable v = new IntWritable(1);//必须初始为1
    //业务逻辑代码
    @Override
    protected void reduce(Text key ,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
        //1.合并同一个word的出现次数
        sumTemp = 0;
        for (IntWritable count:values){
            sumTemp += count.get();
        }
        v.set(sumTemp);
        //2，输出
        context.write(key,v);
    }
}

WordCountDriver类

package com.guodaxia.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;
 
public class WordCountDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
 
        // 1.获得配置信息和job对象
        Configuration con = new Configuration();
        Job job = Job.getInstance(con);
        // 2.关联Driver程序的jar
        job.setJarByClass(WordCountDriver.class);
        // 3.关联Mapper和Reducer程序的jar
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        // 4.设置Mapper输出的k-v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);
    }
}

xml配置文件

<?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>guodaxia</groupId>
    <artifactId>MapReduceDemo</artifactId>
    <version>1.0-SNAPSHOT</version>
 
    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>
    <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>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
        <dependency>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-assembly-plugin</artifactId>
            <version>3.2.0</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>

resources --> 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

Maven 打包

1. 打开右置Maven --> Lifecycle -->package 等待打包完成
2. 复制项目下target的 MapReduceDemo-1.0-SNAPSHOT.jar 到桌面并命名为wc.jar

hadoop集群环节

利用xshell软件将该wc.jar复制到 Hadoop集群下的/opt/module/hadoop-3.1.3下；

启动集群；

在当前路径下创建一个input 文件，并上传到Hadoop集群上；hadoop fs -put ./input input;

复制javaDriver驱动类的全包路径（打开该wordCountDriver类，在代码里右键）；

执行程序（集群上不能有output路径！！！）

hadoop jar wc.jar 驱动包 /input /output