Hbase_使用mapreduce读取hdfs上的文件到hbase

---

1.准备

文件路径：hdfs:/hbase/input/user.txt

文件格式
字段间以 \t 相隔

0007    zhangsan        18
0008    lisi    25
0009    wangwu  20

2.导入依赖

<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.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.2.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.2.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>6.14.3</version>
            <scope>test</scope>
        </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>
                    <!--    <verbal>true</verbal>-->
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.2</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*/RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

3.编写mr代码

1、main函数

package com.twy.HBaseMR3;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


public class Hdfs2HBaseTest extends Configured implements Tool {

    @Override
    public int run(String[] strings) throws Exception {
        Job job = Job.getInstance(super.getConf(), "hdfs->hbase");

        //设置输入路径
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.setInputPaths(job,new Path("hdfs://node01:8020/hbase/input"));

        //自定义mapper逻辑
        job.setMapperClass(MyHBaseMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        //定义HBase输入,reduce逻辑
        TableMapReduceUtil.initTableReducerJob("myuser2",HdfstoHbaseReducer.class,job);


        //等待结束
        boolean b = job.waitForCompletion(true);
        return b? 0:1;
    }

    public static void main(String[] args) throws Exception {
        //获取hbase配置文件
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");

        //启动job
        int run = ToolRunner.run(configuration, new Hdfs2HBaseTest(), args);

        //执行
        System.exit(run);

    }
}

2、map阶段
无需切割

 package com.twy.HBaseMR3;

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

import java.io.IOException;

public class MyHBaseMapper extends Mapper<LongWritable,Text,Text,NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //无需切割，直接输出行值
        context.write(new Text(value.toString()),NullWritable.get());
    }
}

3、reduce阶段
继承TabaleReducer

package com.twy.HBaseMR3;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;

import java.io.IOException;

public class HdfstoHbaseReducer extends TableReducer<Text,NullWritable,ImmutableBytesWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        //拿到数据，并进行切割
        String s = key.toString();

        //切割得到rowkey,列name,列age
        String[] split = s.split("\t");

        String rowkey = split[0];
        String name = split[1];
        String age = split[2];

        Put put = new Put(rowkey.getBytes());
        put.addColumn("f1".getBytes(),"name".getBytes(),name.getBytes());
        put.addColumn("f1".getBytes(),"age".getBytes(),age.getBytes());

        context.write(new ImmutableBytesWritable(rowkey.getBytes()),put);
    }
}

结果：