HBase整合MapReduce之建立HBase索引

Posted 2020-07-10 汤高

HBase索引主要用于提高Hbase中表数据的访问速度，有效的避免了全表扫描，HBase中的表根据行健被分成了多个Regions，通常一个region的一行都会包含较多的数据，如果以列值作为查询条件，就只能从第一行数据开始往下找，直到找到相关数据为止，这很低效。相反，如果将经常被查询的列作为行健、行健作为列重新构造一张表，即可实现根据列值快速定位相关数据所在的行，这就是索引。显然索引表仅需要包含一个列，所以索引表的大小和原表比起来要小得多，如图4-14给出了索引表与原表之间的关系。从图可以看出，由于索引表的单条记录所占的空间比原表要小，所以索引表的一个Region与原表相比，能包含更多条记录

假设HBase中存在一张表heroes，里面的内容如表所示，则根据列info:name构建的索引表如图4-15所示。Hbase会自动将生成的索引表加入如图4-3所示的结构中，从而提高搜索的效率

下面看代码实现

首先创建heroes表

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.util.Bytes;

public class CreateTable {

    public static void main(String[] args) {
        // 2.获得会话
        Admin admin = null;
        Connection con = null;

        try {
            // 操作hbase数据库
            // 1.建立连接
            Configuration conf = HBaseConfiguration.create(); // 获得配制文件对象
            conf.set("hbase.zookeeper.quorum", "192.168.52.140");
            con = ConnectionFactory.createConnection(conf); // 获得连接对象
            TableName tn = TableName.valueOf("heroes");

            admin = con.getAdmin();
            HTableDescriptor htd = new HTableDescriptor(tn);
            HColumnDescriptor hcd = new HColumnDescriptor("info");
            htd.addFamily(hcd);
            admin.createTable(htd);
            Table t = con.getTable(tn);
            String[] heronames = new String[] { "peter", "hiro", "sylar", "claire", "noah" };
            for (int i = 0; i < 5; i++) {
                Put put = new Put((i + "").getBytes());
                put.addColumn("info".getBytes(), "name".getBytes(), heronames[i].getBytes());
                put.addColumn("info".getBytes(), "email".getBytes(), (i + "@qq.com").getBytes());
                put.addColumn("info".getBytes(), "power".getBytes(), "Idotknow".getBytes());
                t.put(put);
            }
            admin.close();
            con.close();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

}

然后根据heroes表建立索引表

package com.tg.index;

import java.io.IOException;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Mutation;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;



public class CreateHbaseIndex {
    //map阶段，根据hbase中的数据取出行健和姓名
    public static class HbaseIndexMapper extends TableMapper<ImmutableBytesWritable, ImmutableBytesWritable>{

        @Override
        protected void map(ImmutableBytesWritable key, Result value,
                Mapper<ImmutableBytesWritable, Result, ImmutableBytesWritable, ImmutableBytesWritable>.Context context)
                        throws IOException, InterruptedException {

            List<Cell> cs = value.listCells();

            for (Cell cell : cs) {
                String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
                System.out.println("qualifier="+qualifier);
                if(qualifier.equals("name")){
                    //把名字做键  行健做值输出
                    context.write(new ImmutableBytesWritable(CellUtil.cloneValue(cell)), new ImmutableBytesWritable(CellUtil.cloneRow(cell)));
                }
            }

        }

    }
    //reduce阶段，将姓名作为键，行健作为值存入hbase
    public static class HbaseIndexReduce extends TableReducer<ImmutableBytesWritable, ImmutableBytesWritable, ImmutableBytesWritable>{

        @Override
        protected void reduce(ImmutableBytesWritable key, Iterable<ImmutableBytesWritable> value,
                Reducer<ImmutableBytesWritable, ImmutableBytesWritable, ImmutableBytesWritable, Mutation>.Context context)
                        throws IOException, InterruptedException {
            //把名字做行健
            Put put=new Put(key.get());
            //把行健做值
            for (ImmutableBytesWritable v : value) {
                put.addColumn("rowkey".getBytes(),"index".getBytes(),v.get() );
            }
            context.write(key, put);
        }

    }
    private static void checkTable(Configuration conf) throws Exception {
        Connection con = ConnectionFactory.createConnection(conf);
        Admin admin = con.getAdmin();
        TableName tn = TableName.valueOf("heroesIndex");
        if (!admin.tableExists(tn)){
            HTableDescriptor htd = new HTableDescriptor(tn);
            HColumnDescriptor hcd = new HColumnDescriptor("rowkey".getBytes());
            htd.addFamily(hcd);
            admin.createTable(htd);
            System.out.println("表不存在，新创建表成功....");
        }
    }

    public static void main(String[] args) {
        try {

            Configuration conf = new Configuration();
            conf = HBaseConfiguration.create(conf);
            conf.set("hbase.zookeeper.quorum", "192.168.52.140");

            Job job = Job.getInstance(conf, "heroes");
            job.setJarByClass(CreateHbaseIndex.class);
            Scan scan = new Scan();
            scan.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"));

            TableMapReduceUtil.initTableMapperJob("heroes", scan, HbaseIndexMapper.class, 
                    ImmutableBytesWritable.class, ImmutableBytesWritable.class,job);
            TableMapReduceUtil.initTableReducerJob("heroesIndex", HbaseIndexReduce.class, job);

            checkTable(conf);
            System.exit(job.waitForCompletion(true) ? 0 : 1);
        } catch (ClassNotFoundException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (InterruptedException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

}

heroes原表的记录如下图：

创建的索引表记录如下图：

转载请指明出处 http://blog.csdn.net/tanggao1314/article/details/51464226