Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/9256#discussion_r44199760
--- Diff:
streaming/src/main/scala/org/apache/spark/streaming/StateSpec.scala ---
@@ -0,0 +1,181 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.streaming
+
+import scala.reflect.ClassTag
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.api.java.JavaPairRDD
+import org.apache.spark.rdd.RDD
+import org.apache.spark.{HashPartitioner, Partitioner}
+
+
+/**
+ * :: Experimental ::
+ * Abstract class representing all the specifications of the DStream
transformation
+ * `trackStateByKey` operation of a
+ * [[org.apache.spark.streaming.dstream.PairDStreamFunctions pair
DStream]] (Scala) or a
+ * [[org.apache.spark.streaming.api.java.JavaPairDStream JavaPairDStream]]
(Java).
+ * Use the [[org.apache.spark.streaming.StateSpec StateSpec.apply()]] or
+ * [[org.apache.spark.streaming.StateSpec StateSpec.create()]] to create
instances of
+ * this class.
+ *
+ * Example in Scala:
+ * {{{
+ * val spec = StateSpec(trackingFunction).numPartitions(10)
+ *
+ * val emittedRecordDStream =
keyValueDStream.trackStateByKey[StateType, EmittedDataType](spec)
+ * }}}
+ *
+ * Example in Java:
+ * {{{
+ * StateStateSpec[StateType, EmittedDataType] spec =
+ * StateStateSpec.create[StateType,
EmittedDataType](trackingFunction).numPartition(10);
+ *
+ * JavaDStream[EmittedDataType] emittedRecordDStream =
+ * javaPairDStream.trackStateByKey[StateType, EmittedDataType](spec);
+ * }}}
+ */
+@Experimental
+sealed abstract class StateSpec[K, V, S, T] extends Serializable {
+
+ /** Set the RDD containing the initial states that will be used by
`trackStateByKey`*/
+ def initialState(rdd: RDD[(K, S)]): this.type
+
+ /** Set the RDD containing the initial states that will be used by
`trackStateByKey`*/
+ def initialState(javaPairRDD: JavaPairRDD[K, S]): this.type
+
+ /**
+ * Set the number of partitions by which the state RDDs generated by
`trackStateByKey`
+ * will be partitioned. Hash partitioning will be used on the
+ */
+ def numPartitions(numPartitions: Int): this.type
+
+ /**
+ * Set the partitioner by which the state RDDs generated by
`trackStateByKey` will be
+ * be partitioned.
+ */
+ def partitioner(partitioner: Partitioner): this.type
+
+ /**
+ * Set the duration after which the state of an idle key will be
removed. A key and its state is
+ * considered idle if it has not received any data for at least the
given duration. The state
+ * tracking function will be called one final time on the idle states
that are going to be
+ * removed; [[org.apache.spark.streaming.State State.isTimingOut()]] set
+ * to `true` in that call.
+ */
+ def timeout(idleDuration: Duration): this.type
+}
+
+
+/**
+ * :: Experimental ::
+ * Builder object for creating instances of
[[org.apache.spark.streaming.StateSpec StateSpec]]
+ * that is used for specifying the parameters of the DStream transformation
+ * `trackStateByKey` operation of a
+ * [[org.apache.spark.streaming.dstream.PairDStreamFunctions pair
DStream]] (Scala) or a
+ * [[org.apache.spark.streaming.api.java.JavaPairDStream JavaPairDStream]]
(Java).
+ *
+ * Example in Scala:
+ * {{{
+ * val spec = StateSpec(trackingFunction).numPartitions(10)
+ *
+ * val emittedRecordDStream =
keyValueDStream.trackStateByKey[StateType, EmittedDataType](spec)
+ * }}}
+ *
+ * Example in Java:
+ * {{{
+ * StateStateSpec[StateType, EmittedDataType] spec =
+ * StateStateSpec.create[StateType,
EmittedDataType](trackingFunction).numPartition(10);
+ *
+ * JavaDStream[EmittedDataType] emittedRecordDStream =
+ * javaPairDStream.trackStateByKey[StateType, EmittedDataType](spec);
+ * }}}
+ */
+@Experimental
+object StateSpec {
+ /**
+ *
+ * @param trackingFunction
+ * @tparam KeyType Class of keys
+ * @tparam ValueType
+ * @tparam StateType
+ * @tparam EmittedType
+ * @return
+ */
+ def apply[KeyType, ValueType, StateType, EmittedType](
+ trackingFunction: (KeyType, Option[ValueType], State[StateType]) =>
Option[EmittedType]
+ ): StateSpec[KeyType, ValueType, StateType, EmittedType] = {
+ new StateSpecImpl[KeyType, ValueType, StateType,
EmittedType](trackingFunction)
+ }
+
+ def create[KeyType, ValueType, StateType, EmittedType](
+ trackingFunction: (KeyType, Option[ValueType], State[StateType]) =>
Option[EmittedType]
+ ): StateSpec[KeyType, ValueType, StateType, EmittedType] = {
+ apply(trackingFunction)
+ }
+}
+
+
+/** Internal implementation of [[org.apache.spark.streaming.StateSpec]]
interface. */
+private[streaming]
+case class StateSpecImpl[K, V, S: ClassTag, T: ClassTag](
--- End diff --
Oh crap, yes, I should remove them here too.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
