A hello world example about connecting Scala to HBase

build.sbt

name := "ScalaHBase"

version := "1.0"

scalaVersion := "2.11.8"

resolvers ++= Seq(
  "Hadoop Releases" at "https://repository.cloudera.com/content/repositories/releases/"
)

libraryDependencies ++= Seq(
  "com.google.guava" % "guava" % "15.0",
  "org.apache.hadoop" % "hadoop-common" % "2.6.0",
  "org.apache.hadoop" % "hadoop-mapred" % "0.22.0",
  "org.apache.hbase" % "hbase-common" % "1.0.0",
  "org.apache.hbase" % "hbase-client" % "1.0.0"
)

dependencyOverrides += "com.google.guava" % "guava" % "15.0"


assemblyMergeStrategy in assembly := {
  case PathList("javax", "servlet", xs @ _*) => MergeStrategy.last
  case PathList("javax", "activation", xs @ _*) => MergeStrategy.last
  case PathList("org", "apache", xs @ _*) => MergeStrategy.last
  case PathList("com", "google", xs @ _*) => MergeStrategy.first
  case PathList("com", "yammer", xs @ _*) => MergeStrategy.last
  case "about.html" => MergeStrategy.rename
  case "plugin.properties" => MergeStrategy.last
  case "log4j.properties" => MergeStrategy.last
  case x =>
    val oldStrategy = (assemblyMergeStrategy in assembly).value
    oldStrategy(x)
}

ScalaHBaseExample.scala

//CHECK ishassan/build.sbt as well
import org.apache.hadoop.hbase.client._
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.hbase.{CellUtil, HBaseConfiguration, TableName}
import org.apache.hadoop.conf.Configuration
import scala.collection.JavaConverters._

object ScalaHBaseExample extends App{

  def printRow(result : Result) = {
    val cells = result.rawCells();
    print( Bytes.toString(result.getRow) + " : " )
    for(cell <- cells){
      val col_name = Bytes.toString(CellUtil.cloneQualifier(cell))
      val col_value = Bytes.toString(CellUtil.cloneValue(cell))
      print("(%s,%s) ".format(col_name, col_value))
    }
    println()
  }

  val conf : Configuration = HBaseConfiguration.create()
  /*
  From http://hbase.apache.org/0.94/book/zookeeper.html
  A distributed Apache HBase (TM) installation depends on a running ZooKeeper cluster. All participating nodes and clients
  need to be able to access the running ZooKeeper ensemble. Apache HBase by default manages a ZooKeeper "cluster" for you.
  It will start and stop the ZooKeeper ensemble as part of the HBase start/stop process. You can also manage the ZooKeeper
  ensemble independent of HBase and just point HBase at the cluster it should use. To toggle HBase management of ZooKeeper,
  use the HBASE_MANAGES_ZK variable in conf/hbase-env.sh. This variable, which defaults to true, tells HBase whether to
  start/stop the ZooKeeper ensemble servers as part of HBase start/stop.
  */
  val ZOOKEEPER_QUORUM = "WRITE THE ZOOKEEPER CLUSTER THAT HBASE SHOULD USE"
  conf.set("hbase.zookeeper.quorum", ZOOKEEPER_QUORUM);

  val connection = ConnectionFactory.createConnection(conf)
  val table = connection.getTable(TableName.valueOf( Bytes.toBytes("emostafa:test_table") ) )

  // Put example
  var put = new Put(Bytes.toBytes("row1"))
  put.addColumn(Bytes.toBytes("d"), Bytes.toBytes("test_column_name"), Bytes.toBytes("test_value"))
  put.addColumn(Bytes.toBytes("d"), Bytes.toBytes("test_column_name2"), Bytes.toBytes("test_value2"))
  table.put(put)

  // Get example
  println("Get Example:")
  var get = new Get(Bytes.toBytes("row1"))
  var result = table.get(get)
  printRow(result)

  //Scan example
  println("\nScan Example:")
  var scan = table.getScanner(new Scan())
  scan.asScala.foreach(result => {
      printRow(result)
  })
  
  table.close()
  connection.close()
}