twosom commented on code in PR #33267: URL: https://github.com/apache/beam/pull/33267#discussion_r1890932261
########## runners/spark/src/main/java/org/apache/beam/runners/spark/translation/streaming/StatefulStreamingParDoEvaluator.java: ########## @@ -0,0 +1,246 @@ +/* + * 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.beam.runners.spark.translation.streaming; + +import static org.apache.beam.runners.spark.translation.TranslationUtils.getBatchDuration; +import static org.apache.beam.runners.spark.translation.TranslationUtils.rejectTimers; +import static org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.Preconditions.checkArgument; +import static org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.Preconditions.checkState; + +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import org.apache.beam.runners.core.construction.SerializablePipelineOptions; +import org.apache.beam.runners.spark.coders.CoderHelpers; +import org.apache.beam.runners.spark.metrics.MetricsAccumulator; +import org.apache.beam.runners.spark.metrics.MetricsContainerStepMapAccumulator; +import org.apache.beam.runners.spark.stateful.StateAndTimers; +import org.apache.beam.runners.spark.translation.EvaluationContext; +import org.apache.beam.runners.spark.translation.SparkPCollectionView; +import org.apache.beam.runners.spark.translation.TransformEvaluator; +import org.apache.beam.runners.spark.translation.TranslationUtils; +import org.apache.beam.runners.spark.util.ByteArray; +import org.apache.beam.runners.spark.util.GlobalWatermarkHolder; +import org.apache.beam.runners.spark.util.SideInputBroadcast; +import org.apache.beam.sdk.coders.Coder; +import org.apache.beam.sdk.coders.KvCoder; +import org.apache.beam.sdk.transforms.DoFn; +import org.apache.beam.sdk.transforms.DoFnSchemaInformation; +import org.apache.beam.sdk.transforms.ParDo; +import org.apache.beam.sdk.transforms.reflect.DoFnSignature; +import org.apache.beam.sdk.transforms.reflect.DoFnSignatures; +import org.apache.beam.sdk.transforms.windowing.WindowFn; +import org.apache.beam.sdk.util.WindowedValue; +import org.apache.beam.sdk.util.construction.ParDoTranslation; +import org.apache.beam.sdk.values.KV; +import org.apache.beam.sdk.values.PCollection; +import org.apache.beam.sdk.values.PCollectionView; +import org.apache.beam.sdk.values.TupleTag; +import org.apache.beam.sdk.values.WindowingStrategy; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Iterables; +import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Iterators; +import org.apache.spark.streaming.State; +import org.apache.spark.streaming.StateSpec; +import org.apache.spark.streaming.api.java.JavaDStream; +import org.apache.spark.streaming.api.java.JavaMapWithStateDStream; +import org.apache.spark.streaming.api.java.JavaPairDStream; +import scala.Option; +import scala.Tuple2; + +/** + * A specialized evaluator for ParDo operations in Spark Streaming context that is invoked when + * stateful streaming is detected in the DoFn. + * + * <p>This class is used by {@link StreamingTransformTranslator}'s ParDo evaluator to handle + * stateful streaming operations. When a DoFn contains stateful processing logic, the translation + * process routes the execution through this evaluator instead of the standard ParDo evaluator. + * + * <p>The evaluator manages state handling and ensures proper processing semantics for streaming + * stateful operations in the Spark runner context. + * + * <p>Important: This evaluator includes validation logic that rejects DoFn implementations + * containing {@code @Timer} annotations, as timer functionality is not currently supported in the + * Spark streaming context. + */ +public class StatefulStreamingParDoEvaluator<KeyT, ValueT, OutputT> + implements TransformEvaluator<ParDo.MultiOutput<KV<KeyT, ValueT>, OutputT>> { + + @Override + public void evaluate( + ParDo.MultiOutput<KV<KeyT, ValueT>, OutputT> transform, EvaluationContext context) { + final DoFn<KV<KeyT, ValueT>, OutputT> doFn = transform.getFn(); + final DoFnSignature signature = DoFnSignatures.signatureForDoFn(doFn); + + rejectTimers(doFn); + checkArgument( + !signature.processElement().isSplittable(), Review Comment: You're right! I'll remove this redundant check in a follow-up PR since splittable and stateful are mutually exclusive by design. Thank you for catching this. 😀 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
