spark hbase

package com.xmgps.yfzx.sparkhbase

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

object SparkHbase extends Serializable{

  def main(args: Array[String]): Unit = {

    val conf = new SparkConf().setAppName("spark hbase").setMaster("local[1]")
      .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")

    val hbaseconfig = HBaseConfiguration.create()
    hbaseconfig.addResource("hbase-site.xml")
    hbaseconfig.set(TableInputFormat.INPUT_TABLE,"LEASE")

    val sc = SparkContext.getOrCreate(conf)

    val connection = ConnectionFactory.createConnection(hbaseconfig)
    val table = connection.getTable(TableName.valueOf("freight"))

    for (i <- 1 to 10) {

      val put = new Put(Bytes.toBytes("row0000" + i))
      put.add(Bytes.toBytes("A"),Bytes.toBytes("name"),Bytes.toBytes("value" + i))
      table.put(put)
    }

    val hrdd = sc.newAPIHadoopRDD(hbaseconfig,
      classOf[TableInputFormat],
      classOf[ImmutableBytesWritable],
      classOf[Result]
    )
    val count = hrdd.count().toInt
    println(count)

    val res = hrdd.take(count)
    for (j <- 1 until count) {
      println("j: " + j)
      val rs = res(j - 1)._2
      val kvs = rs.raw
      for (kv <- kvs)
        println("rowkey:" + new String(kv.getRow()) +
          " cf:" + new String(kv.getFamily()) +
          " column:" + new String(kv.getQualifier()) +
          " value:" + new String(kv.getValue()))
    }
  }
}