[GitHub] [hudi] yuzhaojing commented on a diff in pull request #3599: [HUDI-2207] Support independent flink hudi clustering function

[GitBox <gi...@apache.org>]

yuzhaojing commented on code in PR #3599:
URL: https://github.com/apache/hudi/pull/3599#discussion_r878703474


##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/clustering/FlinkCustomColumnsSortPartitioner.java:
##########
@@ -0,0 +1,68 @@
+/*
+ * 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

Review Comment:
   fixed.



##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/clustering/ClusteringOperator.java:
##########
@@ -0,0 +1,327 @@
+/*
+ * 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.hudi.sink.clustering;
+
+import org.apache.hudi.avro.HoodieAvroUtils;
+import org.apache.hudi.avro.model.HoodieClusteringGroup;
+import org.apache.hudi.client.FlinkTaskContextSupplier;
+import org.apache.hudi.client.HoodieFlinkWriteClient;
+import org.apache.hudi.client.WriteStatus;
+import org.apache.hudi.client.utils.ConcatenatingIterator;
+import org.apache.hudi.common.model.ClusteringOperation;
+import org.apache.hudi.common.table.HoodieTableConfig;
+import org.apache.hudi.common.table.log.HoodieFileSliceReader;
+import org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.StringUtils;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.configuration.FlinkOptions;
+import org.apache.hudi.exception.HoodieClusteringException;
+import org.apache.hudi.exception.HoodieIOException;
+import org.apache.hudi.io.IOUtils;
+import org.apache.hudi.io.storage.HoodieFileReader;
+import org.apache.hudi.io.storage.HoodieFileReaderFactory;
+import org.apache.hudi.sink.bulk.BulkInsertWriterHelper;
+import org.apache.hudi.sink.bulk.sort.SortOperatorGen;
+import org.apache.hudi.table.HoodieFlinkTable;
+import org.apache.hudi.util.AvroToRowDataConverters;
+import org.apache.hudi.util.StreamerUtil;
+
+import org.apache.avro.Schema;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.avro.generic.GenericRecordBuilder;
+import org.apache.avro.generic.IndexedRecord;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.metrics.Gauge;
+import org.apache.flink.runtime.memory.MemoryManager;
+import org.apache.flink.streaming.api.operators.BoundedOneInput;
+import org.apache.flink.streaming.api.operators.OneInputStreamOperator;
+import org.apache.flink.streaming.runtime.streamrecord.StreamRecord;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.table.data.binary.BinaryRowData;
+import org.apache.flink.table.planner.codegen.sort.SortCodeGenerator;
+import org.apache.flink.table.runtime.generated.GeneratedNormalizedKeyComputer;
+import org.apache.flink.table.runtime.generated.GeneratedRecordComparator;
+import org.apache.flink.table.runtime.generated.NormalizedKeyComputer;
+import org.apache.flink.table.runtime.generated.RecordComparator;
+import org.apache.flink.table.runtime.operators.TableStreamOperator;
+import org.apache.flink.table.runtime.operators.sort.BinaryExternalSorter;
+import org.apache.flink.table.runtime.typeutils.AbstractRowDataSerializer;
+import org.apache.flink.table.runtime.typeutils.BinaryRowDataSerializer;
+import org.apache.flink.table.runtime.typeutils.RowDataSerializer;
+import org.apache.flink.table.runtime.util.StreamRecordCollector;
+import org.apache.flink.table.types.logical.RowType;
+import org.apache.hadoop.fs.Path;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Spliterator;
+import java.util.Spliterators;
+import java.util.stream.Collectors;
+import java.util.stream.StreamSupport;
+
+import static org.apache.hudi.table.format.FormatUtils.buildAvroRecordBySchema;
+
+/**
+ * Function to execute the actual clustering task assigned by the clustering plan task.
+ * In order to execute scalable, the input should shuffle by the clustering event {@link ClusteringPlanEvent}.
+ */
+public class ClusteringOperator extends TableStreamOperator<ClusteringCommitEvent> implements
+    OneInputStreamOperator<ClusteringPlanEvent, ClusteringCommitEvent>, BoundedOneInput {
+  private static final Logger LOG = LoggerFactory.getLogger(ClusteringOperator.class);
+
+  private final Configuration conf;
+  private final RowType rowType;
+  private int taskID;
+  private transient HoodieWriteConfig writeConfig;
+  private transient HoodieFlinkTable<?> table;
+  private transient Schema schema;
+  private transient Schema readerSchema;
+  private transient int[] requiredPos;
+  private transient AvroToRowDataConverters.AvroToRowDataConverter avroToRowDataConverter;
+  private transient HoodieFlinkWriteClient writeClient;
+  private transient BulkInsertWriterHelper writerHelper;
+  private transient String instantTime;
+
+  private GeneratedNormalizedKeyComputer gComputer;
+  private GeneratedRecordComparator gComparator;
+
+  private transient BinaryExternalSorter sorter;
+  private transient StreamRecordCollector<ClusteringCommitEvent> collector;
+  private transient BinaryRowDataSerializer binarySerializer;
+
+  public ClusteringOperator(Configuration conf, RowType rowType) {
+    this.conf = conf;
+    this.rowType = rowType;
+    this.gComputer = createSortCodeGenerator().generateNormalizedKeyComputer("SortComputer");
+    this.gComparator = createSortCodeGenerator().generateRecordComparator("SortComparator");
+  }

Review Comment:
   fixed.



-- 
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: commits-unsubscribe@hudi.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org