【Spark】Spark之读取Hbase数据库表并写入文件

import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.client.{HBaseAdmin, 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 HbaseUtils {
  def main(args: Array[String]): Unit = {

    val conf = new SparkConf().setAppName("HbaseTest").setMaster("local")
    val sc = new SparkContext(conf)
    val tableName = "mkd_sdata:u_user_info"
    val hbaseConfig = HBaseConfiguration.create()
    hbaseConfig.set(TableInputFormat.INPUT_TABLE, tableName)
    val admin = new HBaseAdmin(hbaseConfig)

    val hbaseRDD = sc.newAPIHadoopRDD(hbaseConfig,
      classOf[TableInputFormat],
      classOf[ImmutableBytesWritable],
      classOf[Result])

    val count = hbaseRDD.count()

    println("------------------:"+count)

    val resultRDD = hbaseRDD.map { result => {
        val key = Bytes.toString(result._2.getRow)
        val userId = Bytes.toString(result._2.getValue("base".getBytes, "user_id".getBytes))
        val mobile = Bytes.toString(result._2.getValue("base".getBytes, "mobile".getBytes))
        println("key:" + key + "\t userId:" + userId + "\t mobile:" + mobile)
        (userId, mobile)
      }
    }
    resultRDD.saveAsTextFile("file:///e:/outs")
    sc.stop()
    admin.close()

  }
}