mosche commented on code in PR #24543:
URL: https://github.com/apache/beam/pull/24543#discussion_r1051898910
##########
runners/spark/3/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/batch/DoFnMapPartitionsFactory.java:
##########
@@ -17,91 +17,171 @@
*/
package org.apache.beam.runners.spark.structuredstreaming.translation.batch;
-import static java.util.stream.Collectors.toCollection;
-import static java.util.stream.Collectors.toMap;
import static
org.apache.beam.runners.spark.structuredstreaming.translation.utils.ScalaInterop.scalaIterator;
-import static
org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Lists.newArrayListWithCapacity;
+import static
org.apache.beam.runners.spark.structuredstreaming.translation.utils.ScalaInterop.tuple;
+import static org.apache.beam.sdk.util.Preconditions.checkStateNotNull;
import java.io.Serializable;
import java.util.ArrayDeque;
+import java.util.ArrayList;
+import java.util.Collections;
import java.util.Deque;
import java.util.List;
import java.util.Map;
import java.util.function.Supplier;
import org.apache.beam.runners.core.DoFnRunner;
import org.apache.beam.runners.core.DoFnRunners;
-import org.apache.beam.runners.core.DoFnRunners.OutputManager;
import org.apache.beam.runners.core.SideInputReader;
+import org.apache.beam.runners.core.construction.ParDoTranslation;
import
org.apache.beam.runners.spark.structuredstreaming.metrics.MetricsAccumulator;
import
org.apache.beam.runners.spark.structuredstreaming.translation.batch.functions.CachedSideInputReader;
import
org.apache.beam.runners.spark.structuredstreaming.translation.batch.functions.NoOpStepContext;
-import
org.apache.beam.runners.spark.structuredstreaming.translation.utils.ScalaInterop.Fun1;
-import
org.apache.beam.runners.spark.structuredstreaming.translation.utils.ScalaInterop.Fun2;
import org.apache.beam.sdk.coders.Coder;
import org.apache.beam.sdk.options.PipelineOptions;
+import org.apache.beam.sdk.runners.AppliedPTransform;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.DoFnSchemaInformation;
+import org.apache.beam.sdk.transforms.ParDo.MultiOutput;
import org.apache.beam.sdk.transforms.reflect.DoFnInvokers;
import org.apache.beam.sdk.util.WindowedValue;
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.v26_0_jre.com.google.common.collect.AbstractIterator;
-import org.apache.spark.api.java.function.MapPartitionsFunction;
+import org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Maps;
import org.checkerframework.checker.nullness.qual.NonNull;
+import scala.Function1;
+import scala.Tuple2;
import scala.collection.Iterator;
/**
- * Encapsulates a {@link DoFn} inside a Spark {@link
- * org.apache.spark.api.java.function.MapPartitionsFunction}.
+ * Abstract factory to create a {@link DoFnPartitionIt DoFn partition
iterator} using a customizable
+ * {@link DoFnRunners.OutputManager}.
*/
-class DoFnMapPartitionsFactory<InT, OutT> implements Serializable {
+abstract class DoFnMapPartitionsFactory<InT, FnOutT, OutT extends @NonNull
Object>
+ implements Function1<Iterator<WindowedValue<InT>>, Iterator<OutT>>,
Serializable {
private final String stepName;
-
- private final DoFn<InT, OutT> doFn;
+ private final DoFn<? super InT, FnOutT> doFn;
Review Comment:
`? super IntT` is a left over, removed 👍
--
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]
