Hi Community,
I'm running a basic spark job which reads from an HBase table.
I can see the job is getting complete without any error, but in output I get the empty rows.
Will appreciate any help.
Below is my code
object objectName {
def catalog = s"""{
|"table":{"namespace":"namespaceName", "name":"tableName"},
|"rowkey":"rowKeyAttribute",
|"columns":{
|"Key":{"cf":"rowkey", "col":"rowKeyAttribute", "type":"string"},
|"col1":{"cf":"cfName", "col":"col1", "type":"bigint"},
|"col2":{"cf":"cfName", "col":"col2", "type":"string"}
|}
|}""".stripMargin
def main(args: Array[String]) {
val spark = SparkSession.builder()
.appName("dummyApplication")
.getOrCreate()
val sc = spark.sparkContext
val sqlContext = spark.sqlContext
import sqlContext.implicits._
def withCatalog(cat: String): DataFrame = {
sqlContext
.read
.options(Map(HBaseTableCatalog.tableCatalog -> cat))
.format("org.apache.spark.sql.execution.datasources.hbase")
.load()
}
}