Spark读取HBase的小Demo

package HBase

import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.client.Result
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.hadoop.hbase.util.Bytes

object SparkReadHBase {
  /**
    * 此demo可以获取HBase中所有数据并转化成RDD
    * @param args
    */
  def main(args: Array[String]): Unit = {

    val conf: SparkConf = new SparkConf()
      .setAppName("HBaseTest")
      .setMaster("local[*]")

    val sc = new SparkContext(conf)

    val tablename = "myspace:test"
    val hbaseconf = HBaseConfiguration.create()
    //设置zookeeper集群地址,
    hbaseconf.set("hbase.zookeeper.quorum","tianxiang01,tianxiang03,tianxiang04,tianxiang05")
    //设置zookeeper连接端口,默认是2181
    hbaseconf.set("hbase.zookeeper.property.clientPort","2181")
    hbaseconf.set(TableInputFormat.INPUT_TABLE,tablename)

    //读取数据并转化成RDD
    val HBaseRDD = sc.newAPIHadoopRDD(
      hbaseconf,
      classOf[TableInputFormat],
      classOf[ImmutableBytesWritable],
      classOf[Result]
    )

     val count = HBaseRDD.count()
      println(count) // 1

      HBaseRDD.foreach{
        case (_,result) => {
          val key = Bytes.toString(result.getRow)
          val ziduan = Bytes.toString(result.getValue("ziduan".getBytes(),"ziduan".getBytes))
          println(key+" "+ziduan) // 1  12.19
        }
      }
  }
}