[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user dawidwys closed the pull request at: https://github.com/apache/flink/pull/3963 --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user dawidwys commented on a diff in the pull request: https://github.com/apache/flink/pull/3963#discussion_r118322678 --- Diff: flink-libraries/flink-cep-scala/src/main/scala/org/apache/flink/cep/scala/conditions/Context.scala --- @@ -0,0 +1,33 @@ +/* + * 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.flink.cep.scala.conditions + +import java.io.Serializable + +/** + * The context used when evaluating the {@link IterativeCondition condition}. + */ +trait Context[T] extends Serializable { + /** +* @return An { @link Iterable} over the already accepted elements +*for a given pattern. Elements are iterated in the order they were +*inserted in the pattern. +* @param name The name of the pattern. +*/ + def apply(name: String): Iterable[T] +} --- End diff -- Right I was also not really decided on that one. Of course you can change it. --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user kl0u commented on a diff in the pull request: https://github.com/apache/flink/pull/3963#discussion_r118297586 --- Diff: flink-libraries/flink-cep-scala/src/main/scala/org/apache/flink/cep/scala/conditions/Context.scala --- @@ -0,0 +1,33 @@ +/* + * 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.flink.cep.scala.conditions + +import java.io.Serializable + +/** + * The context used when evaluating the {@link IterativeCondition condition}. + */ +trait Context[T] extends Serializable { + /** +* @return An { @link Iterable} over the already accepted elements +*for a given pattern. Elements are iterated in the order they were +*inserted in the pattern. +* @param name The name of the pattern. +*/ + def apply(name: String): Iterable[T] +} --- End diff -- Why having different method names between Java and Scala? In Java this method is called `getEventsForPattern()`. We could rename both to sth like `getEventsForState()` if you agree, but I would suggest that same methods should have the same name and also, specifically for this, writing `context(stateName)` does not really seem nice. If you agree I can change it and then merge. --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user dawidwys commented on a diff in the pull request: https://github.com/apache/flink/pull/3963#discussion_r118055738 --- Diff: flink-libraries/flink-cep-scala/src/main/scala/org/apache/flink/cep/scala/PatternStream.scala --- @@ -296,25 +294,94 @@ class PatternStream[T](jPatternStream: JPatternStream[T]) { * timeout events wrapped in a [[Either]] type. */ def flatSelect[L: TypeInformation, R: TypeInformation]( - patternFlatTimeoutFunction: (mutable.Map[String, JList[T]], Long, Collector[L]) => Unit) ( - patternFlatSelectFunction: (mutable.Map[String, JList[T]], Collector[R]) => Unit) + patternFlatTimeoutFunction: (Map[String, Iterable[T]], Long, Collector[L]) => Unit) ( + patternFlatSelectFunction: (Map[String, Iterable[T]], Collector[R]) => Unit) : DataStream[Either[L, R]] = { val cleanSelectFun = cleanClosure(patternFlatSelectFunction) val cleanTimeoutFun = cleanClosure(patternFlatTimeoutFunction) val patternFlatSelectFun = new PatternFlatSelectFunction[T, R] { - override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = { -cleanSelectFun(pattern.asScala, out) + override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = +cleanSelectFun(mapToScala(pattern), out) +} + +val patternFlatTimeoutFun = new PatternFlatTimeoutFunction[T, L] { + override def timeout( +pattern: JMap[String, JList[T]], +timeoutTimestamp: Long, out: Collector[L]) + : Unit = { +cleanTimeoutFun(mapToScala(pattern), timeoutTimestamp, out) } } --- End diff -- Yes, I am also referring to those methods. :) --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user kl0u commented on a diff in the pull request: https://github.com/apache/flink/pull/3963#discussion_r118051044 --- Diff: flink-libraries/flink-cep-scala/src/main/scala/org/apache/flink/cep/scala/PatternStream.scala --- @@ -296,25 +294,94 @@ class PatternStream[T](jPatternStream: JPatternStream[T]) { * timeout events wrapped in a [[Either]] type. */ def flatSelect[L: TypeInformation, R: TypeInformation]( - patternFlatTimeoutFunction: (mutable.Map[String, JList[T]], Long, Collector[L]) => Unit) ( - patternFlatSelectFunction: (mutable.Map[String, JList[T]], Collector[R]) => Unit) + patternFlatTimeoutFunction: (Map[String, Iterable[T]], Long, Collector[L]) => Unit) ( + patternFlatSelectFunction: (Map[String, Iterable[T]], Collector[R]) => Unit) : DataStream[Either[L, R]] = { val cleanSelectFun = cleanClosure(patternFlatSelectFunction) val cleanTimeoutFun = cleanClosure(patternFlatTimeoutFunction) val patternFlatSelectFun = new PatternFlatSelectFunction[T, R] { - override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = { -cleanSelectFun(pattern.asScala, out) + override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = +cleanSelectFun(mapToScala(pattern), out) +} + +val patternFlatTimeoutFun = new PatternFlatTimeoutFunction[T, L] { + override def timeout( +pattern: JMap[String, JList[T]], +timeoutTimestamp: Long, out: Collector[L]) + : Unit = { +cleanTimeoutFun(mapToScala(pattern), timeoutTimestamp, out) } } --- End diff -- I was referring to the 2 methods that follow :) . The ones that for example use the `foreach`. --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user dawidwys commented on a diff in the pull request: https://github.com/apache/flink/pull/3963#discussion_r118050667 --- Diff: flink-libraries/flink-cep-scala/src/main/scala/org/apache/flink/cep/scala/PatternStream.scala --- @@ -296,25 +294,94 @@ class PatternStream[T](jPatternStream: JPatternStream[T]) { * timeout events wrapped in a [[Either]] type. */ def flatSelect[L: TypeInformation, R: TypeInformation]( - patternFlatTimeoutFunction: (mutable.Map[String, JList[T]], Long, Collector[L]) => Unit) ( - patternFlatSelectFunction: (mutable.Map[String, JList[T]], Collector[R]) => Unit) + patternFlatTimeoutFunction: (Map[String, Iterable[T]], Long, Collector[L]) => Unit) ( + patternFlatSelectFunction: (Map[String, Iterable[T]], Collector[R]) => Unit) : DataStream[Either[L, R]] = { val cleanSelectFun = cleanClosure(patternFlatSelectFunction) val cleanTimeoutFun = cleanClosure(patternFlatTimeoutFunction) val patternFlatSelectFun = new PatternFlatSelectFunction[T, R] { - override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = { -cleanSelectFun(pattern.asScala, out) + override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = +cleanSelectFun(mapToScala(pattern), out) +} + +val patternFlatTimeoutFun = new PatternFlatTimeoutFunction[T, L] { + override def timeout( +pattern: JMap[String, JList[T]], +timeoutTimestamp: Long, out: Collector[L]) + : Unit = { +cleanTimeoutFun(mapToScala(pattern), timeoutTimestamp, out) } } --- End diff -- This is the scala way of applying `flatFunction`. We also provide both of those alternatives for e.g. `DataStream#flatMap`. --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user kl0u commented on a diff in the pull request: https://github.com/apache/flink/pull/3963#discussion_r117989704 --- Diff: flink-libraries/flink-cep-scala/src/main/scala/org/apache/flink/cep/scala/PatternStream.scala --- @@ -296,25 +294,94 @@ class PatternStream[T](jPatternStream: JPatternStream[T]) { * timeout events wrapped in a [[Either]] type. */ def flatSelect[L: TypeInformation, R: TypeInformation]( - patternFlatTimeoutFunction: (mutable.Map[String, JList[T]], Long, Collector[L]) => Unit) ( - patternFlatSelectFunction: (mutable.Map[String, JList[T]], Collector[R]) => Unit) + patternFlatTimeoutFunction: (Map[String, Iterable[T]], Long, Collector[L]) => Unit) ( + patternFlatSelectFunction: (Map[String, Iterable[T]], Collector[R]) => Unit) : DataStream[Either[L, R]] = { val cleanSelectFun = cleanClosure(patternFlatSelectFunction) val cleanTimeoutFun = cleanClosure(patternFlatTimeoutFunction) val patternFlatSelectFun = new PatternFlatSelectFunction[T, R] { - override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = { -cleanSelectFun(pattern.asScala, out) + override def flatSelect(pattern: JMap[String, JList[T]], out: Collector[R]): Unit = +cleanSelectFun(mapToScala(pattern), out) +} + +val patternFlatTimeoutFun = new PatternFlatTimeoutFunction[T, L] { + override def timeout( +pattern: JMap[String, JList[T]], +timeoutTimestamp: Long, out: Collector[L]) + : Unit = { +cleanTimeoutFun(mapToScala(pattern), timeoutTimestamp, out) } } --- End diff -- Why are the following two methods added? --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---
[GitHub] flink pull request #3963: [FLINK-6658][cep] Use scala Collections in scala C...
Github user kl0u commented on a diff in the pull request: https://github.com/apache/flink/pull/3963#discussion_r117985885 --- Diff: flink-libraries/flink-cep-scala/src/main/scala/org/apache/flink/cep/scala/package.scala --- @@ -40,7 +44,11 @@ package object scala { private[flink] def cleanClosure[F <: AnyRef](f: F, checkSerializable: Boolean = true): F = { ClosureCleaner.clean(f, checkSerializable) -return f +f + } + + private[flink] def mapToScala[T](map: JMap[String, JList[T]]): Map[String, Iterable[T]] = { +map.asScala.mapValues(_.asScala.toIterable).toMap --- End diff -- Why not getting rid of the last `.toMap` and return a `collection.Map`? This will avoid an iteration over the elements of the `JMap` which is important given that this method will be invoked at every incoming element. From the rest, I think we are ok as the `asScala`s are just wrappers and the `.mapValues` are lazily evaluated. --- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. ---