spark

Type Members

1. class Analyzer extends AnyRef

   

2. class Args extends ScallopConf

   

3. abstract class BaseJoin extends AnyRef

   

4. sealed trait BaseKvRdd extends AnyRef

   

5. case class BootstrapInfo(joinConf: api.Join, joinParts: Seq[JoinPartMetadata], externalParts: Seq[ExternalPartMetadata], derivations: Array[StructField], hashToSchema: Map[String, Array[StructField]]) extends Product with Serializable

   

6. class ChrononKryoRegistrator extends KryoRegistrator

   

7. class CpcSketchKryoSerializer extends Serializer[CpcSketch]

   

8. sealed trait DataRange extends AnyRef

   

9. class DummyExtensions extends (SparkSessionExtensions) ⇒ Unit

   

10. case class ExternalPartMetadata(externalPart: ExternalPart, keySchema: Array[StructField], valueSchema: Array[StructField]) extends Product with Serializable

    

11. class GroupBy extends Serializable

    

12. class GroupByUpload extends Serializable

    

13. sealed case class IncompatibleSchemaException(inconsistencies: Seq[(String, DataType, DataType)]) extends Exception with Product with Serializable

    

14. class ItemSketchSerializable extends Serializable

    

15. class ItemsSketchKryoSerializer extends Serializer[ItemSketchSerializable]

    

16. class Join extends BaseJoin

    

17. case class JoinPartMetadata(joinPart: JoinPart, keySchema: Array[StructField], valueSchema: Array[StructField], derivationDependencies: Map[StructField, Seq[StructField]]) extends Product with Serializable

    

18. case class KeyWithHash(data: Array[Any], hash: Array[Byte], hashInt: Int) extends Serializable with Product

    

19. case class KvRdd(data: RDD[(Array[Any], Array[Any])], keySchema: StructType, valueSchema: StructType)(implicit sparkSession: SparkSession) extends BaseKvRdd with Product with Serializable

    

20. class LabelJoin extends AnyRef

    

21. class LocalTableExporter extends AnyRef

    

22. class LogFlattenerJob extends Serializable

    

    Purpose of LogFlattenerJob is to unpack serialized Avro data from online requests and flatten each field (both keys and values) into individual columns and save to an offline "flattened" log table.

    Purpose of LogFlattenerJob is to unpack serialized Avro data from online requests and flatten each field (both keys and values) into individual columns and save to an offline "flattened" log table.

    Steps: 1. determine unfilled range and pull raw logs from partitioned log table 2. fetch joinCodecs for all unique schema_hash present in the logs 3. build a merged schema from all schema versions, which will be used as output schema 4. unpack each row and adhere to the output schema 5. save the schema info in the flattened log table properties (cumulatively)

23. case class LoggingSchema(keyCodec: AvroCodec, valueCodec: AvroCodec) extends Product with Serializable

    

24. case class PartitionRange(start: String, end: String)(implicit tableUtils: TableUtils) extends DataRange with Ordered[PartitionRange] with Product with Serializable

    

25. class StagingQuery extends AnyRef

    

26. case class TableUtils(sparkSession: SparkSession) extends Product with Serializable

    

27. case class TimeRange(start: Long, end: Long)(implicit tableUtils: TableUtils) extends DataRange with Product with Serializable

    

28. case class TimedKvRdd(data: RDD[(Array[Any], Array[Any], Long)], keySchema: StructType, valueSchema: StructType)(implicit sparkSession: SparkSession) extends BaseKvRdd with Product with Serializable