HPE Ezmeral Data Fabric Database Binary Connector for Apache Spark Integration with Basic Spark

This example shows how HBaseContext can be used to do a foreachPartition on an RDD in Scala:

val sc = new SparkContext("local", "test")
val config = new HbaseConfiguration()
...
val hbaseContext = new HBaseContext(sc, config)

rdd.hbaseForeachPartition(hbaseContext, (it, conn) => {
 val bufferedMutator = conn.getBufferedMutator(TableName.valueOf("/apps/my_table"))
 it.foreach((putRecord) => {
	val put = new Put(putRecord._1)
	putRecord._2.foreach((putValue) => 
		put.addColumn(putValue._1,
		putValue._2, putValue._3))
	bufferedMutator.mutate(put)
 })
 bufferedMutator.flush()
 bufferedMutator.close()
})
Here is the same example implemented in Java:
JavaSparkContext jsc = new JavaSparkContext(sparkConf);

try {
  List<byte[]> list = new ArrayList<>();
  list.add(Bytes.toBytes("1"));
  ...
  list.add(Bytes.toBytes("5"));

  JavaRDD<byte[]> rdd = jsc.parallelize(list);
  Configuration conf = HBaseConfiguration.create();
  JavaHBaseContext hbaseContext = new JavaHBaseContext(jsc, conf);

  hbaseContext.foreachPartition(
	rdd,
	new VoidFunction<Tuple2<Iterator<byte[]>, Connection>>() {
   public void call(Tuple2<Iterator<byte[]>, Connection> t) throws Exception {
	Table table = t._2().getTable(TableName.valueOf(tableName));
	BufferedMutator mutator = t._2().getBufferedMutator(TableName.valueOf(tableName));
    while (t._1().hasNext()) {
      byte[] b = t._1().next();
      Result r = table.get(new Get(b));
      if (r.getExists()) {
       mutator.mutate(new Put(b));
      }
    }

    mutator.flush();
    mutator.close();
    table.close();
   }
  });
} finally {
  jsc.stop();
}