大数据之HBase_MR

官方HBase-MapReduce

查看HBase的MapReduce任务的所需的依赖
bin/hbase mapredcp

执行环境变量的导入
$ export HBASE_HOME=/opt/module/hbase-1.3.1
$ export HADOOP_CLASSPATH = ``${HBASE_HOME}/bin/hbase mapredcp `

运行官方的MapReduce任务
– 案例一：统计Student表中有多少行数据
==$ /opt/module/hadoop-2.8.4/bin/yarn jar lib/hbase-server-1.3.1.jar rowcounter ns_ct:calllog=

案例二：使用MapReduce将本地数据导入到HBase

(1) 在本地创建一个tsv格式的文件：city.tsv，自己建表用\t分割数据
1001 BeiJing China
1002 New York TUS
1003 ShangHai China
尖叫提示：上面的这个数据不要从word中直接复制，有格式错误

(2) 创建HBase表
hbase(main):001:0> create ‘city’,'cf’

(3) 在HDFS中创建input_fruit文件夹并上传city.tsv文件
$ /opt/module/hadoop-2.8.4/bin/hdfs dfs -mkdir /hbase_test/
$ /opt/module/hadoop-2.8.4/bin/hdfs dfs -put city.tsv /hbase_test/

(4) 执行MapReduce到HBase的fruit表中
$ /opt/module/hadoop-2.8.4/bin/yarn jar lib/hbase-server-1.3.1.jar importtsv
-Dimporttsv.columns=HBASE_ROW_KEY,cf:name,cf:countries city
hdfs://bigdata11:9000/hbase_test

(5) 使用scan命令查看导入后的结果
base(main):001:0> scan 'city’

HBase2HBase

目标：将city表中的一部分数据，通过MR迁入到city_mr表中。
分步实现：
(1) 构建HBaseMapper类，用于读取city表中的数据

public class HBaseMapper extends TableMapper<ImmutableBytesWritable, Put> {
    @Override
    protected void map(ImmutableBytesWritable key, Result value, Context context) throws IOException, InterruptedException {
        //将city的name和color提取出来，相当于将每一行数据读取出来放入到Put对象中。
        Put put = new Put(key.get());
        //遍历添加column行
        for (Cell cell : value.rawCells()){
            //添加/克隆列族:cf
            if ("cf".equals(Bytes.toString(CellUtil.cloneFamily(cell)))){
                //添加/克隆列：name
                if ("name".equals(Bytes.toString(CellUtil.cloneQualifier(cell)))){
                    //将该列cell加入到put对象中
                    put.add(cell);
                }
            }
        }
        //将从fruit读取到的每行数据写入到context中作为map的输出
        context.write(key,put);
    }
}

2) 构建HBaseReduce类，用于将读取到的fruit表中的数据写入到city_mr表中

public class HBaseReduce extends TableReducer<ImmutableBytesWritable, Put, NullWritable> {
    @Override
    protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context) throws IOException, InterruptedException {
        //将map获取的数据写入到对应的文件中
        for (Put put : values){

            context.write(NullWritable.get(),put);
        }
    }
}

3) 构建 CityToCity_mr extends Configured implements Tool用于组装运行Job任务

public class CityToCity_mr extends Configured implements Tool {
    public int run(String[] strings) throws Exception {

        //获取配置文件
        Configuration conf = this.getConf();
        //创建job任务
        Job job = Job.getInstance(conf,getClass().getSimpleName());
        job.setJarByClass(CityToCity_mr.class);

        //创建扫描器
        Scan scan = new Scan();

        //设置Mapper，注意导入的是mapreduce包下的，不是mapred包下的，后者是老版本
        TableMapReduceUtil.initTableMapperJob(
                //读数据的表
                "City",
                //扫描器
                scan,
                //设置map类
                HBaseMapper.class,
                //设置输出数据类型
                ImmutableBytesWritable.class,
                Put.class,
                //配置job
                job
        );

        //配置Reduce
        TableMapReduceUtil.initTableReducerJob(
                //将数据写到City_mr中
                "city_mr",
                //设置Reduce类
                HBaseReduce.class,
                //配置给job任务
                job
        );
        //设置Reduce数量，最少1个
        job.setNumReduceTasks(1);

        boolean status = job.waitForCompletion(true);

        if (status){
            return 0;
        }else {
            return 1;
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = HBaseConfiguration.create();
        int status = ToolRunner.run(conf, new CityToCity_mr(), args);
        System.exit(status);

    }
}

打包运行任务
尖叫提示：运行任务前，如果待数据导入的表不存在，则需要提前创建之。

---

HDFS2HBase

目标：实现将HDFS中的数据写入到HBase表中。
分步实现：
构建HDFS2HBaseMapper于读取HDFS中的文件数据

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class HDFS2HBaseMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        //从HDFS中读取数据
        String lineValue = value.toString();
        //读取出来的每行数据使用\t进行分割，存于String数组
        String[] values = lineValue.split("\t");

        //根据数据中值的含义进行取值 1001    apple   red
        String rowkey = values[0];
        String name = values[1];
        String color = values[2];

        //初始化rowkey
        ImmutableBytesWritable immutableBytesWritable = new ImmutableBytesWritable(Bytes.toBytes(rowkey));

        //初始化put
        Put put = new Put(Bytes.toBytes(rowkey));

        //参数分别：列蔟，列，值
        put.add(Bytes.toBytes("info"),Bytes.toBytes("name"),Bytes.toBytes("name"));
        put.add(Bytes.toBytes("info"),Bytes.toBytes("color"),Bytes.toBytes("color"));

        context.write(immutableBytesWritable,put);
    }

}

构建HDFS2HBaseReduce类

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 java.io.IOException;

public class HDFS2HBaseReduce extends TableReducer<ImmutableBytesWritable, Put, NullWritable> {

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

        //读出来的每一行数据写入到 fruit_hdfs 表中
        for (Put put : values){
            context.write(NullWritable.get(),put);
        }
    }
}

创建HDFS2HBase组装Job

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.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;

public class HDFS2HBase extends Configured implements Tool {
    public int run(String[] strings) throws Exception {

        String args = "hdfs://bigdata11:9000/input_fruit/fruit.tsv";

        //得到Configuration
        Configuration conf = this.getConf();

        //创建job任务
        Job job = Job.getInstance(conf, getClass().getSimpleName());
        job.setJarByClass(HDFS2HBase.class);
        Path path = new Path(args);
        FileInputFormat.addInputPath(job,path);

        //设置Mapper
        job.setMapperClass(HBaseMapper.class);
        job.setMapOutputKeyClass(ImmutableBytesWritable.class);
        job.setMapOutputValueClass(Put.class);

        //设置Reduce
        TableMapReduceUtil.initTableReducerJob("fruit_hdfs",HBaseReduce.class,job);
        //设置Reduce个数
        job.setNumReduceTasks(1);

        boolean isSuccess = job.waitForCompletion(true);
        if (!isSuccess){
            throw new IOException("Job running with error");
        }
        return isSuccess? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = HBaseConfiguration.create();
        int status = ToolRunner.run(conf, new HDFS2HBase(), args);
        System.exit(status);
    }
}

打包运行
尖叫提示：运行任务前，如果待数据导入的表不存在，则需要提前创建之。