Hbase索引的建立实现代码

Hbase索引主要是用于提高Hbase中表数据的访问速度，有效的避免全表扫描。
简单的讲：将经常被查询的列作为行健，行健作为列键重新构造一张表，即可实现根据列值快速地定位相关数据所在的行，这就是索引。
下面是图片展示：

我自己写了实现代码不过和这图还是有不同，我定义的列是name,sex,tel，这些都不是重点啦。下面给大家讲讲具体的过程：
1，在tableMap过程：
我们拿到名字，和行健。
2，在tableReduce过程：
将拿到的名字做行健，行健做列，插入到Hbase中就可以哒。
代码展示：
建立母表：
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 CreateHbaseTable {

    public static void main(String[] args) throws IOException {
        Admin admin = null;
        Connection con = null;
            Configuration conf = HBaseConfiguration.create();// 获取hbase配置文件
            conf.set("hbase.zookeeper.quorum", "192.168.61.128");
            con = ConnectionFactory.createConnection(conf);
            admin=con.getAdmin();//获得管理员

            TableName tn=TableName.valueOf("workerinfo");
            HTableDescriptor htd=new HTableDescriptor(tn);//创建表结构
            HColumnDescriptor hcd=new HColumnDescriptor("info");
            htd.addFamily(hcd);
            admin.createTable(htd);//创建表

            //向表中添加数据
            Table table=con.getTable(tn);
            for(int i=0;i<5;i++){
                Put put=new Put((i+"").getBytes());
                put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("zhangsan"+i))
                .addColumn(Bytes.toBytes("info"), Bytes.toBytes("sex"), Bytes.toBytes("man"))
                .addColumn(Bytes.toBytes("info"), Bytes.toBytes("tel"), Bytes.toBytes("0000"+i));
                table.put(put);
            }
    }
}

建立索引：

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 CreateHbaseIndex2 {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        conf = HBaseConfiguration.create(conf);
        conf.set("hbase.zookeeper.quorum", "192.168.61.128");

        Job job = Job.getInstance(conf, "HbaseIndex");
        job.setJarByClass(CreateHbaseIndex2.class);
        Scan scan=new Scan();
        scan.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"));

        TableMapReduceUtil.initTableMapperJob("workerinfo", scan, HbaseIndexMap.class, 
                ImmutableBytesWritable.class, ImmutableBytesWritable.class,job);
        TableMapReduceUtil.initTableReducerJob("HbaseIndex", HbaseIndexReduce.class, job);

        checkTable(conf);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

    private static class HbaseIndexMap 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){
                //name作为Key  行健作为值
                context.write(new ImmutableBytesWritable(CellUtil.cloneValue(cell)), new ImmutableBytesWritable(CellUtil.cloneRow(cell)));

            }
        }
    }

    private static class HbaseIndexReduce extends TableReducer<ImmutableBytesWritable, ImmutableBytesWritable, ImmutableBytesWritable>{
        @Override
        protected void reduce(ImmutableBytesWritable key, Iterable<ImmutableBytesWritable> values,
                Reducer<ImmutableBytesWritable, ImmutableBytesWritable, ImmutableBytesWritable, Mutation>.Context context)
                        throws IOException, InterruptedException {
            Put put=new Put(key.get());
            for (ImmutableBytesWritable v : values) {
                put.addColumn("oldrowkey".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("HbaseIndex");
        if (!admin.tableExists(tn)){
            HTableDescriptor htd = new HTableDescriptor(tn);
            HColumnDescriptor hcd = new HColumnDescriptor("oldrowkey".getBytes());
            htd.addFamily(hcd);
            admin.createTable(htd);
            System.out.println("表不存在，新创建表成功....");
        }
    }


}