Hadoop序列化——电话流量 案列

1.创建maven工程

在pom.xml文件中添加如下依赖 

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

        <!--    安装java测试框架-->
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.13.2</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.slf4j/slf4j-nop -->
        <!--    安装日志框架-->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-nop</artifactId>
            <version>1.7.35</version>
        </dependency>
    </dependencies>

    <!--maven打jar包要用的依赖插件（不把依赖框架一起打包）-->
    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <!--当你想要把依赖一起打包时加上下面的代码-->
<!--            <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>
2.在项目的resources目录下，创建一个文件，命名为 log4j.properties ，在文中填入以下内容

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

3.自定义一个类实现Writable接口

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/*
 * 1.定义类实现Writable接口
 * 2.重写空参构造
 * 3.重写序列方法和反序列方法
 * 4.重写toString方法
 * */
public class FlowBean implements Writable {

    private long upFlow;//上行流量
    private long downFlow;//下行流量
    private long sumFlow;//总流量


    //空参构造函数
    public FlowBean() {
    }

    public long getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public long getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(long downFlow) {
        this.downFlow = downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow() {
        this.sumFlow = this.downFlow + this.upFlow;
    }

    //序列方法
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);

    }


    //这里要注意：序列方法和反序列方法里的参数位置一定要一致
    //反序列方法
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }

    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }
}

4.Map类

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

import java.io.IOException;

/*
 * 输入的key: 一行，所以是 LongWritable 类型
 * 输入的value: 电话号码，所以是 Text 类型
 * 输出的key: 电话号码，所以是 Text 类型
 * 输出的value: 总流量，所以是 FlowBean 对象 (这里FlowBean类是我们定义好的)
* */
public class FlowMapper extends Mapper<LongWritable, Text, Text, FlowBean> {

    //定义key输出类型
    Text outK = new Text();

    //定义value输出类型
    FlowBean outV = new FlowBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        //1.获取一行,并转为String类型
        String line = key.toString();

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

        //3.抓取想要的数据
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];

        //4.封装


        outK.set(phone);
        outV.setUpFlow(Long.parseLong(up));
        outV.setDownFlow(Long.parseLong(up));
        outV.setSumFlow();

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

5.Reduce类

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

import java.io.IOException;

public class FlowReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
    FlowBean outV = new FlowBean();

    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {

        long sumUp = 0;
        long sumDown = 0;

        //1.遍历集合进行累加
        for (FlowBean value : values){
            sumUp = value.getUpFlow();
            sumDown = value.getDownFlow();
        }

        //2.封装
        outV.setUpFlow(sumUp);
        outV.setDownFlow(sumDown);
        outV.setSumFlow();

        //3.输出
        context.write(key, outV);

    }
}

6.Driver类

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 FlowDriver {

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

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

        //2.设置jar
        job.setJarByClass(FlowDriver.class);

        //3.关联Mapper和Reduce
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //4.设置 Mapper的kv 输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);

        //5.设置 数据最终的kv 输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //6.设置输入和输出的路径
        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);
    }
}

最后打jar包，传到linux上的hadoop文件下，运行代码如下：

hadoop jar         包名     Driver类的路径      输入路径        输出路径