sutugin
commented
6 years ago You can write your custom sink provider, inherited from StreamSinkProvider, this is my implementation:
package HBase
import org.apache.spark.internal.Logging
import org.apache.spark.sql.execution.streaming.Sink
import org.apache.spark.sql.sources.{DataSourceRegister, StreamSinkProvider}
import org.apache.spark.sql.streaming.OutputMode
import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.sql.execution.datasources.hbase._
class HBaseSink(options: Map[String, String]) extends Sink with Logging {
// String with HBaseTableCatalog.tableCatalog
private val hBaseCatalog = options.get("hbasecat").map(_.toString).getOrElse("")
override def addBatch(batchId: Long, data: DataFrame): Unit = synchronized {
val df = data.sparkSession.createDataFrame(data.rdd, data.schema)
df.write
.options(Map(HBaseTableCatalog.tableCatalog->hBaseCatalog,
HBaseTableCatalog.newTable -> "5"))
.format("org.apache.spark.sql.execution.datasources.hbase").save()
}
}
class HBaseSinkProvider extends StreamSinkProvider with DataSourceRegister {
def createSink(
sqlContext: SQLContext,
parameters: Map[String, String],
partitionColumns: Seq[String],
outputMode: OutputMode): Sink = {
new HBaseSink(parameters)
}
def shortName(): String = "hbase"
}This is example, how to use ():
inputDF.
writeStream.
queryName("hbase writer").
format("HBase.HBaseSinkProvider").
option("checkpointLocation", checkPointProdPath).
option("hbasecat", catalog).
outputMode(OutputMode.Update()).
trigger(Trigger.ProcessingTime(30.seconds)).
start
EDALJO
hamroune
merfill
ddkongbb
swarup5s
stefcorda
vibnimit
omkarahane
631068264
Saimukunth
Hi,
I have a Spark Structured Streaming application where I'd like to write streaming data to HBase using SHC. It reads data from a location where new csv files continuously are being created. The defined catalog works for writing a DataFrame with identical data into HBase. The key components of my streaming application are a DataStreamReader and a DataStreamWriter.
When running the application I'm getting the following message:
Exception in thread "main" java.lang.UnsupportedOperationException: Data source org.apache.spark.sql.execution.datasources.hbase does not support streamed writing at org.apache.spark.sql.execution.datasources.DataSource.createSink(DataSource.scala:285) at org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:286) at my.package.SHCStreamingApplication$.main(SHCStreamingApplication.scala:153) at my.package.SHCStreamingApplication.main(SHCStreamingApplication.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:755) at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180) at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205) at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119) at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)Does anyone know a solution or way/workaround to still use the SHC for writing structured streaming data to HBase? Thanks in advance!