spark1.0.2读取hbase（CDH0.96.1）上的数据

libraryDependencies +=  "org.apache.spark" % "spark-core_2.10" % "1.0.2" % "provided"

libraryDependencies +=  "org.apache.spark" % "spark-streaming_2.10" % "1.0.2" % "provided"

libraryDependencies +=  "org.apache.hbase" % "hbase-common" %"0.96.1.1-hadoop2" % "provided"

libraryDependencies +=  "org.apache.hbase" % "hbase-client" % "0.96.1.1-hadoop2" % "provided"

libraryDependencies +=  "org.apache.hbase" % "hbase-server" % "0.96.1.1-hadoop2" % "provided"

package cn.rcz.bigdata
import org.apache.spark.SparkContext
import org.apache.spark._
import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.HTableDescriptor
import org.apache.hadoop.hbase.client.HBaseAdmin
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.HColumnDescriptor
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.hbase.client.Put
import org.apache.hadoop.hbase.client.HTable
import org.apache.hadoop.hbase.client.Result
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.client.Delete

/**
 * Created by ptbx on 2015/4/7.
 */
import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.SparkContext._

    object Test01 extends Serializable{
      def main(args: Array[String]) {
     /*   if (args.length != 2) {
          System.err.println("Usage: LogAnalyzer <input> <output>")
          System.exit(1)
        }*/
        val sc = new SparkContext("spark://master:7077", "SparkHBase01")

        val conf = HBaseConfiguration.create()
        conf.set("hbase.zookeeper.property.clientPort", "2181")
        conf.set("hbase.zookeeper.quorum", "master")
        conf.set("hbase.master", "master:60000")
        conf.addResource("/home/hadoop/hbase-0.96.1.1-cdh5.0.2/conf/hbase-site.xml")
        conf.set(TableInputFormat.INPUT_TABLE, "carInfo")

        val admin = new HBaseAdmin(conf)
        if (!admin.isTableAvailable("messInfo")) {
          print("Table Not Exists! Create Table")
          val tableDesc = new HTableDescriptor("messInfo")
          tableDesc.addFamily(new HColumnDescriptor("messInfo".getBytes()))
          admin.createTable(tableDesc)
        }


        val hbaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat],
          classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
          classOf[org.apache.hadoop.hbase.client.Result])

        val count = hbaseRDD.count()
        println("HBase RDD Count:" + count)
        hbaseRDD.cache()

        val res = hbaseRDD.take(count.toInt)
        for (j <- 1 until count.toInt) {
          println("j: " + j)
          var rs = res(j - 1)._2
          var 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()))
        }
        System.exit(0)

    }
  }

sh spark-submit  --class cn.szkj.bigdata.Test01 --master local[3]  /home/hadoop/work.jar