Hbase整合Mapreduce案例2 hbase数据下载至hdfs中——wordcount

目录

• 整合结构
• 准备
• 数据下载
• • pom.xml
  • Main.java
  • Reduce.java
  • Map.java
  • 操作
• 总结

整合结构

和案例1的结构差不多，Hbase移动到开头，后面跟随MR程序。

因此对于输入的K1 V1会进行一定的修改

准备

1. 在HBASE中创建表，并写入数据

create "wunaiieq:sentence","colf"

2. 系统文件上传

datain3.java

package org.wunaiieq.hbase2hdfs;

import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.util.Bytes;
import org.wunaiieq.HBaseConnection;
import org.wunaiieq.HbaseDML;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;

public class datain3 {
    public static Connection connection = HBaseConnection.connection;
    public static void main(String[] args) throws IOException {
        BufferedReader bufferedReader =new BufferedReader(
                new FileReader("/opt/module/jar/data.txt")
        );
        String line =null;
        Table table = connection.getTable(TableName.valueOf("wunaiieq", "sentence"));
        int rowkey = 1;
        while ((line=bufferedReader.readLine())!=null){
            Put put = new Put(Bytes.toBytes(rowkey));
            put.addColumn(Bytes.toBytes("colf"),Bytes.toBytes("line"),Bytes.toBytes(line));
            table.put(put);
            rowkey++;
        }
        bufferedReader.close();
    }
}

数据下载

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.hbase</groupId>
    <artifactId>hbase2hdfs</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>
        <hadoop.version>3.1.3</hadoop.version>
        <hbase.version>2.2.3</hbase.version>
    </properties>

    <dependencies>
        <!-- Hadoop Dependencies -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-api</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-streaming</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!-- HBase Dependencies -->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>${hbase.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>${hbase.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-common</artifactId>
            <version>${hbase.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-mapreduce</artifactId>
            <version>${hbase.version}</version>
        </dependency>

        <!-- Other Dependencies -->
        <dependency>
            <groupId>com.google.protobuf</groupId>
            <artifactId>protobuf-java</artifactId>
            <version>3.19.1</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.25</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
            <scope>compile</scope>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <!--声明-->
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.3.0</version>
                <!--具体配置-->
                <configuration>
                    <archive>
                        <manifest>
                            <!--jar包的执行入口-->
                            <mainClass>org.wunaiieq.hbase2hdfs.Main</mainClass>
                        </manifest>
                    </archive>
                    <descriptorRefs>
                        <!--描述符，此处为预定义的，表示创建一个包含项目所有依赖的可执行 JAR 文件;
                        允许自定义生成jar文件内容-->
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <!--执行配置-->
                <executions>
                    <execution>
                        <!--执行配置ID，可修改-->
                        <id>make-assembly</id>
                        <!--执行的生命周期-->
                        <phase>package</phase>
                        <goals>
                            <!--执行的目标，single表示创建一个分发包-->
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

Main.java

package org.wunaiieq.hbase2hdfs;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class Main {
    public static void main(String[] args) throws Exception {
        //配置文件，写在resources目录下
        Job job =Job.getInstance(new Configuration());
        //入口类
        job.setJarByClass(Main.class);
        Scan scan = new Scan();
        TableMapReduceUtil.initTableMapperJob(
               "wunaiieq:sentence",//表名
                scan,//表输入时，可以在此处进行部分设置，如选择查询的列簇，列，过滤行等等
                org.wunaiieq.hbase2hdfs.Map.class,//指定mapper类
                Text.class,//k2
                IntWritable.class,//v2
                job,
                false
        );
        job.setOutputKeyClass(Text.class);//K3
        job.setOutputValueClass(IntWritable.class);//V3
        job.setReducerClass(org.wunaiieq.hbase2hdfs.Reduce.class);
        //手动输入输出路径
        FileOutputFormat.setOutputPath(job,new Path(args[0]));




        job.waitForCompletion(true);

    }
}

Reduce.java

package org.wunaiieq.hbase2hdfs;

import org.apache.hadoop.hbase.client.Mutation;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

//                                        K3    V3     K4     V4
public class Reduce extends Reducer<Text,IntWritable,Text,IntWritable>{
    private IntWritable v4 =new IntWritable();
    private Text k4 =new Text();
    @Override
    protected void reduce(Text k3, Iterable<IntWritable> v3,Context context) throws IOException, InterruptedException {
        int sum =0;
        for (IntWritable v30:v3){
            sum+=v30.get();
        }
        v4.set(sum);
        k4=k3;
        context.write(k4,v4);
    }
}

Map.java

package org.wunaiieq.hbase2hdfs;

import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;
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;
//                                      K1   V1
public class Map extends TableMapper<Text,IntWritable> {
    private Text k2=new Text();
    private IntWritable v2 =new IntWritable(1);
    @Override
    protected void map(ImmutableBytesWritable k1, Result v1,Context context) throws IOException, InterruptedException {
        System.out.println("k1:"+k1.toString());
        //读取当前行中的colf:line数据
        byte[] data =v1.getValue(Bytes.toBytes("colf"),Bytes.toBytes("line"));
        String line =Bytes.toString(data);
        String [] words =line.split(" ");
        for (String word :words){
            k2.set(word);
            context.write(k2,v2);
        }
    }
}

操作

打包上传至linux系统中

hadoop jar hbase2hdfs-1.0-SNAPSHOT-jar-with-dependencies.jar /output/test

检查文件

hdfs dfs -cat /output/test/part-r-00000

总结

没什么特殊点，记录下这两个案例即可，只需要在MR程序中替换掉对应的Mapper和Reducer即可