[GitHub] [iceberg] rdblue commented on a change in pull request #3865: Flink: ArrayBatchRecords for a batch of records for a single file; RecordAndPosi…

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

rdblue commented on a change in pull request #3865:
URL: https://github.com/apache/iceberg/pull/3865#discussion_r799656225



##########
File path: flink/v1.14/flink/src/main/java/org/apache/iceberg/flink/source/reader/ArrayBatchRecords.java
##########
@@ -0,0 +1,158 @@
+/*
+ * 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.iceberg.flink.source.reader;
+
+import java.util.Collections;
+import java.util.Set;
+import javax.annotation.Nullable;
+import org.apache.flink.annotation.VisibleForTesting;
+import org.apache.flink.connector.base.source.reader.RecordsWithSplitIds;
+import org.apache.flink.connector.file.src.util.Pool;
+import org.apache.flink.table.data.RowData;
+import org.apache.iceberg.flink.source.DataIterator;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+
+/**
+ * {@link RecordsWithSplitIds} is used to pass a batch of records from fetcher to source reader.
+ * Batching is to improve the efficiency for records handover.
+ *
+ * {@link RecordsWithSplitIds} interface can encapsulate batches from multiple splits.
+ * This is the case for Kafka source where fetchers can retrieve records from multiple
+ * Kafka partitions at the same time.
+ *
+ * For file-based sources like Iceberg, readers always read one split/file at a time.
+ * Hence, we will only have a batch of records for one split here.
+ *
+ * This class uses array to store a batch of records from the same file (with the same fileOffset).
+ */
+class ArrayBatchRecords<T> implements RecordsWithSplitIds<RecordAndPosition<T>> {
+  @Nullable
+  private String splitId;
+  @Nullable
+  private final Pool.Recycler<T[]> recycler;
+  @Nullable
+  private final T[] records;
+  private final int numberOfRecords;
+  private final Set<String> finishedSplits;
+  private final RecordAndPosition<T> recordAndPosition;
+
+  // point to current read position within the records array
+  private int position;
+
+  private ArrayBatchRecords(
+      @Nullable String splitId, @Nullable Pool.Recycler<T[]> recycler, @Nullable T[] records,
+      int numberOfRecords, int fileOffset, long startingRecordOffset, Set<String> finishedSplits) {
+    Preconditions.checkArgument(numberOfRecords >= 0, "numberOfRecords can't be negative");
+    Preconditions.checkArgument(fileOffset >= 0, "fileOffset can't be negative");
+    Preconditions.checkArgument(startingRecordOffset >= 0, "numberOfRecords can't be negative");
+
+    this.splitId = splitId;
+    this.recycler = recycler;
+    this.records = records;
+    this.numberOfRecords = numberOfRecords;
+    this.finishedSplits = Preconditions.checkNotNull(finishedSplits, "finishedSplits can be empty but not null");
+    this.recordAndPosition = new RecordAndPosition<>();
+
+    recordAndPosition.set(null, fileOffset, startingRecordOffset);
+    this.position = 0;
+  }
+
+  @Nullable
+  @Override
+  public String nextSplit() {
+    String nextSplit = this.splitId;
+    // set the splitId to null to indicate no more splits
+    // this class only contains record for one split
+    this.splitId = null;
+    return nextSplit;
+  }
+
+  @Nullable
+  @Override
+  public RecordAndPosition<T> nextRecordFromSplit() {
+    if (position < numberOfRecords) {
+      recordAndPosition.record(records[position++]);

Review comment:
       Can you increment/decrement on a separate line? We don't use the return value of ++ because it is hard to reason about.




-- 
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: issues-unsubscribe@iceberg.apache.org

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



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org