echauchot commented on a change in pull request #15267:
URL: https://github.com/apache/beam/pull/15267#discussion_r683327242
##########
File path:
runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/batch/GroupByKeyTranslatorBatch.java
##########
@@ -17,74 +17,143 @@
*/
package org.apache.beam.runners.spark.structuredstreaming.translation.batch;
-import java.io.Serializable;
-import org.apache.beam.runners.core.InMemoryStateInternals;
-import org.apache.beam.runners.core.StateInternals;
-import org.apache.beam.runners.core.StateInternalsFactory;
-import org.apache.beam.runners.core.SystemReduceFn;
-import
org.apache.beam.runners.spark.structuredstreaming.translation.AbstractTranslationContext;
+import java.util.ArrayList;
+import java.util.List;
import
org.apache.beam.runners.spark.structuredstreaming.translation.TransformTranslator;
-import
org.apache.beam.runners.spark.structuredstreaming.translation.batch.functions.GroupAlsoByWindowViaOutputBufferFn;
+import
org.apache.beam.runners.spark.structuredstreaming.translation.AbstractTranslationContext;
import
org.apache.beam.runners.spark.structuredstreaming.translation.helpers.EncoderHelpers;
import
org.apache.beam.runners.spark.structuredstreaming.translation.helpers.KVHelpers;
+import org.apache.beam.sdk.coders.CannotProvideCoderException;
import org.apache.beam.sdk.coders.Coder;
-import org.apache.beam.sdk.coders.IterableCoder;
+import org.apache.beam.sdk.coders.CoderRegistry;
import org.apache.beam.sdk.coders.KvCoder;
+import org.apache.beam.sdk.coders.ListCoder;
+import org.apache.beam.sdk.transforms.Combine;
+import org.apache.beam.sdk.transforms.GroupByKey;
import org.apache.beam.sdk.transforms.PTransform;
+import org.apache.beam.sdk.transforms.windowing.BoundedWindow;
import org.apache.beam.sdk.util.WindowedValue;
import org.apache.beam.sdk.values.KV;
import org.apache.beam.sdk.values.PCollection;
import org.apache.beam.sdk.values.WindowingStrategy;
+import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.KeyValueGroupedDataset;
+import scala.Tuple2;
class GroupByKeyTranslatorBatch<K, V>
- implements TransformTranslator<
- PTransform<PCollection<KV<K, V>>, PCollection<KV<K, Iterable<V>>>>> {
+ implements TransformTranslator<
+ PTransform<PCollection<KV<K, V>>, PCollection<KV<K, Iterable<V>>>>> {
+ /**
+ * Combiner that combines {@code T}s into a single {@code List<T>}
containing all inputs.
+ *
+ * <p>For internal use to translate {@link GroupByKey}. For a large {@link
PCollection} this is
+ * expected to crash!
+ *
+ * <p>This is copied from the dataflow runner code.
Review comment:
well, just checked it is in more places than that I tracked the
extraction in [this](https://issues.apache.org/jira/browse/BEAM-12727) ticket,
I'll address it in this PR
--
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]
