Spark Structured Streaming with Hbase integration

Question

We are doing streaming on kafka data which being collected from MySQL. Now once all the analytics has been done i want to save my data directly to Hbase. I have through the

Answer 1

1- add these libraries to your project :

      "org.apache.hbase" % "hbase-client" % "2.0.1"
      "org.apache.hbase" % "hbase-common" % "2.0.1"

2- add this trait to your code :

   import java.util.concurrent.ExecutorService
   import org.apache.hadoop.hbase.client.{Connection, ConnectionFactory, Put, Table}
   import org.apache.hadoop.hbase.security.User
   import org.apache.hadoop.hbase.{HBaseConfiguration, TableName}
   import org.apache.spark.sql.ForeachWriter

   trait HBaseForeachWriter[RECORD] extends ForeachWriter[RECORD] {

     val tableName: String
     val hbaseConfResources: Seq[String]

     def pool: Option[ExecutorService] = None

     def user: Option[User] = None

     private var hTable: Table = _
     private var connection: Connection = _


     override def open(partitionId: Long, version: Long): Boolean = {
       connection = createConnection()
       hTable = getHTable(connection)
       true
     }

     def createConnection(): Connection = {
       val hbaseConfig = HBaseConfiguration.create()
       hbaseConfResources.foreach(hbaseConfig.addResource)
       ConnectionFactory.createConnection(hbaseConfig, pool.orNull,                      user.orNull)

     }

     def getHTable(connection: Connection): Table = {
       connection.getTable(TableName.valueOf(tableName))
     }

     override def process(record: RECORD): Unit = {
       val put = toPut(record)
       hTable.put(put)
     }

     override def close(errorOrNull: Throwable): Unit = {
       hTable.close()
       connection.close()
     }

     def toPut(record: RECORD): Put

   }

3- use it for your logic :

    val ds = .... //anyDataset[WhatEverYourDataType]

    val query = ds.writeStream
           .foreach(new HBaseForeachWriter[WhatEverYourDataType] {
                            override val tableName: String = "hbase-table-name"
                            //your cluster files, i assume here it is in resources  
                            override val hbaseConfResources: Seq[String] = Seq("core-site.xml", "hbase-site.xml") 

                            override def toPut(record: WhatEverYourDataType): Put = {
                              val key = .....
                              val columnFamaliyName : String = ....
                              val columnName : String = ....
                              val columnValue = ....

                              val p = new Put(Bytes.toBytes(key))
                              //Add columns ... 
                   p.addColumn(Bytes.toBytes(columnFamaliyName),
                               Bytes.toBytes(columnName), 
                               Bytes.toBytes(columnValue))

                              p
                            }

                          }
           ).start()

         query.awaitTermination()