xushiyan commented on a change in pull request #3741:
URL: https://github.com/apache/hudi/pull/3741#discussion_r732348357
##########
File path:
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/compact/HoodieCompactor.java
##########
@@ -18,39 +18,276 @@
package org.apache.hudi.table.action.compact;
+import org.apache.hudi.avro.HoodieAvroUtils;
+import org.apache.hudi.avro.model.HoodieCompactionOperation;
import org.apache.hudi.avro.model.HoodieCompactionPlan;
+import org.apache.hudi.client.AbstractHoodieWriteClient;
+import org.apache.hudi.client.WriteStatus;
+import org.apache.hudi.common.data.HoodieAccumulator;
+import org.apache.hudi.common.data.HoodieData;
import org.apache.hudi.common.engine.HoodieEngineContext;
+import org.apache.hudi.common.engine.TaskContextSupplier;
+import org.apache.hudi.common.fs.FSUtils;
+import org.apache.hudi.common.model.CompactionOperation;
+import org.apache.hudi.common.model.HoodieBaseFile;
import org.apache.hudi.common.model.HoodieFileGroupId;
+import org.apache.hudi.common.model.HoodieLogFile;
import org.apache.hudi.common.model.HoodieRecordPayload;
+import org.apache.hudi.common.model.HoodieTableType;
+import org.apache.hudi.common.model.HoodieWriteStat.RuntimeStats;
+import org.apache.hudi.common.table.HoodieTableMetaClient;
+import org.apache.hudi.common.table.TableSchemaResolver;
+import org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner;
+import org.apache.hudi.common.table.timeline.HoodieActiveTimeline;
+import org.apache.hudi.common.table.timeline.HoodieInstant;
+import org.apache.hudi.common.table.timeline.HoodieTimeline;
+import org.apache.hudi.common.table.view.TableFileSystemView.SliceView;
+import org.apache.hudi.common.util.CollectionUtils;
+import org.apache.hudi.common.util.CompactionUtils;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.ValidationUtils;
+import org.apache.hudi.common.util.collection.Pair;
import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.io.IOUtils;
+import org.apache.hudi.table.HoodieDataCompactionHandler;
import org.apache.hudi.table.HoodieTable;
+import org.apache.hudi.table.action.compact.strategy.CompactionStrategy;
+
+import org.apache.avro.Schema;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
import java.io.IOException;
import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Iterator;
+import java.util.List;
import java.util.Set;
+import java.util.stream.StreamSupport;
+
+import static java.util.stream.Collectors.toList;
/**
* A HoodieCompactor runs compaction on a hoodie table.
*/
-public interface HoodieCompactor<T extends HoodieRecordPayload, I, K, O>
extends Serializable {
+public abstract class HoodieCompactor<T extends HoodieRecordPayload, I, K, O>
implements Serializable {
Review comment:
@vinothchandar @yihua Now when we introduce a new abstraction, can we
also work towards the goal to remove avro dependency? as in decoupling it from
`HoodieRecordPayload`
--
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]