[SPARK-12244][SPARK-12245][STREAMING] Rename trackStateByKey to mapWithState and change tracking function signature #10224
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -28,7 +28,7 @@ import org.apache.spark.{HashPartitioner, Partitioner} | |
| /** | ||
| * :: Experimental :: | ||
| * Abstract class representing all the specifications of the DStream transformation | ||
| * `mapWithState` 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 | ||
|
|
@@ -37,42 +37,47 @@ import org.apache.spark.{HashPartitioner, Partitioner} | |
| * | ||
| * Example in Scala: | ||
| * {{{ | ||
| * def mappingFunction(data: Option[ValueType], wrappedState: State[StateType]): MappedType = { | ||
| * ... | ||
| * } | ||
| * | ||
| * val spec = StateSpec.function(mappingFunction).numPartitions(10) | ||
| * | ||
| * val mapWithStateDStream = keyValueDStream.mapWithState[StateType, MappedType](spec) | ||
| * }}} | ||
| * | ||
| * Example in Java: | ||
| * {{{ | ||
| * StateSpec<KeyType, ValueType, StateType, MappedType> spec = | ||
| * StateSpec.<KeyType, ValueType, StateType, MappedType>function(mappingFunction) | ||
| * .numPartition(10); | ||
| * | ||
| * JavaMapWithStateDStream<KeyType, ValueType, StateType, MappedType> mapWithStateDStream = | ||
| * javaPairDStream.<StateType, MappedType>mapWithState(spec); | ||
| * }}} | ||
| * | ||
| * @tparam KeyType Class of the state key | ||
| * @tparam ValueType Class of the state value | ||
| * @tparam StateType Class of the state data | ||
| * @tparam MappedType Class of the mapped elements | ||
| */ | ||
| @Experimental | ||
| sealed abstract class StateSpec[KeyType, ValueType, StateType, MappedType] extends Serializable { | ||
|
|
||
| /** Set the RDD containing the initial states that will be used by `mapWithState` */ | ||
| def initialState(rdd: RDD[(KeyType, StateType)]): this.type | ||
|
|
||
| /** Set the RDD containing the initial states that will be used by `mapWithState` */ | ||
| def initialState(javaPairRDD: JavaPairRDD[KeyType, StateType]): this.type | ||
|
|
||
| /** | ||
| * Set the number of partitions by which the state RDDs generated by `mapWithState` | ||
| * will be partitioned. Hash partitioning will be used. | ||
| */ | ||
| def numPartitions(numPartitions: Int): this.type | ||
|
|
||
| /** | ||
| * Set the partitioner by which the state RDDs generated by `mapWithState` will be | ||
| * be partitioned. | ||
| */ | ||
| def partitioner(partitioner: Partitioner): this.type | ||
|
|
@@ -91,113 +96,114 @@ sealed abstract class StateSpec[KeyType, ValueType, StateType, EmittedType] exte | |
| /** | ||
| * :: Experimental :: | ||
| * Builder object for creating instances of [[org.apache.spark.streaming.StateSpec StateSpec]] | ||
| * that is used for specifying the parameters of the DStream transformation `mapWithState` | ||
| * that is used for specifying the parameters of the DStream transformation | ||
| * `mapWithState` 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: | ||
| * {{{ | ||
| * def mappingFunction(data: Option[ValueType], wrappedState: State[StateType]): MappedType = { | ||
| * ... | ||
| * } | ||
| * | ||
| * val spec = StateSpec.function(mappingFunction).numPartitions(10) | ||
|
Member
There was a problem hiding this comment. I remember this line cannot be put here because the compiler cannot infer
Contributor
Author
There was a problem hiding this comment. I am modifying the signature of the function to have the key. See jira SPARK-12245. So then this should not be a problem. |
||
| * | ||
| * val mapWithStateDStream = keyValueDStream.mapWithState[StateType, MappedType](spec) | ||
| * }}} | ||
| * | ||
| * Example in Java: | ||
| * {{{ | ||
| * StateSpec<KeyType, ValueType, StateType, MappedType> spec = | ||
| * StateSpec.<KeyType, ValueType, StateType, MappedType>function(mappingFunction) | ||
| * .numPartition(10); | ||
| * | ||
| * JavaMapWithStateDStream<KeyType, ValueType, StateType, MappedType> mapWithStateDStream = | ||
| * javaPairDStream.<StateType, MappedType>mapWithState(spec); | ||
| * }}} | ||
| */ | ||
| @Experimental | ||
| object StateSpec { | ||
| /** | ||
| * Create a [[org.apache.spark.streaming.StateSpec StateSpec]] for setting all the specifications | ||
| * of the `mapWithState` operation on a | ||
| * [[org.apache.spark.streaming.dstream.PairDStreamFunctions pair DStream]]. | ||
| * | ||
| * @param mappingFunction The function applied on every data item to manage the associated state | ||
| * and generate the mapped data | ||
| * @tparam KeyType Class of the keys | ||
| * @tparam ValueType Class of the values | ||
| * @tparam StateType Class of the states data | ||
| * @tparam MappedType Class of the mapped data | ||
| */ | ||
| def function[KeyType, ValueType, StateType, MappedType]( | ||
| mappingFunction: (Time, KeyType, Option[ValueType], State[StateType]) => Option[MappedType] | ||
| ): StateSpec[KeyType, ValueType, StateType, MappedType] = { | ||
| ClosureCleaner.clean(mappingFunction, checkSerializable = true) | ||
| new StateSpecImpl(mappingFunction) | ||
| } | ||
|
|
||
| /** | ||
| * Create a [[org.apache.spark.streaming.StateSpec StateSpec]] for setting all the specifications | ||
| * of the `mapWithState` operation on a | ||
| * [[org.apache.spark.streaming.dstream.PairDStreamFunctions pair DStream]]. | ||
| * | ||
| * @param mappingFunction The function applied on every data item to manage the associated state | ||
| * and generate the mapped data | ||
| * @tparam ValueType Class of the values | ||
| * @tparam StateType Class of the states data | ||
| * @tparam MappedType Class of the mapped data | ||
| */ | ||
| def function[KeyType, ValueType, StateType, MappedType]( | ||
| mappingFunction: (Option[ValueType], State[StateType]) => MappedType | ||
| ): StateSpec[KeyType, ValueType, StateType, MappedType] = { | ||
| ClosureCleaner.clean(mappingFunction, checkSerializable = true) | ||
| val wrappedFunction = | ||
| (time: Time, key: Any, value: Option[ValueType], state: State[StateType]) => { | ||
| Some(mappingFunction(value, state)) | ||
| } | ||
| new StateSpecImpl(wrappedFunction) | ||
| } | ||
|
|
||
| /** | ||
| * Create a [[org.apache.spark.streaming.StateSpec StateSpec]] for setting all | ||
| * the specifications of the `mapWithState` operation on a | ||
| * [[org.apache.spark.streaming.api.java.JavaPairDStream JavaPairDStream]]. | ||
| * | ||
| * @param mappingFunction The function applied on every data item to manage the associated | ||
| * state and generate the mapped data | ||
| * @tparam KeyType Class of the keys | ||
| * @tparam ValueType Class of the values | ||
| * @tparam StateType Class of the states data | ||
| * @tparam MappedType Class of the mapped data | ||
| */ | ||
| def function[KeyType, ValueType, StateType, MappedType](mappingFunction: | ||
| JFunction4[Time, KeyType, Optional[ValueType], State[StateType], Optional[MappedType]]): | ||
| StateSpec[KeyType, ValueType, StateType, MappedType] = { | ||
| val trackingFunc = (time: Time, k: KeyType, v: Option[ValueType], s: State[StateType]) => { | ||
| val t = mappingFunction.call(time, k, JavaUtils.optionToOptional(v), s) | ||
| Option(t.orNull) | ||
| } | ||
| StateSpec.function(trackingFunc) | ||
| } | ||
|
|
||
| /** | ||
| * Create a [[org.apache.spark.streaming.StateSpec StateSpec]] for setting all the specifications | ||
| * of the `mapWithState` operation on a | ||
| * [[org.apache.spark.streaming.api.java.JavaPairDStream JavaPairDStream]]. | ||
| * | ||
| * @param mappingFunction The function applied on every data item to manage the associated | ||
| * state and generate the mapped data | ||
| * @tparam ValueType Class of the values | ||
| * @tparam StateType Class of the states data | ||
| * @tparam MappedType Class of the mapped data | ||
| */ | ||
| def function[KeyType, ValueType, StateType, MappedType]( | ||
| mappingFunction: JFunction2[Optional[ValueType], State[StateType], MappedType]): | ||
| StateSpec[KeyType, ValueType, StateType, MappedType] = { | ||
| val trackingFunc = (v: Option[ValueType], s: State[StateType]) => { | ||
| mappingFunction.call(Optional.fromNullable(v.get), s) | ||
| } | ||
| StateSpec.function(trackingFunc) | ||
| } | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: the method name
testTrackStateByAPIshould be renamed totestMapWithStateAPI