[GitHub] [iceberg] flyrain commented on a diff in pull request #6345: Spark 3.3: Choose readers based on task types

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

flyrain commented on code in PR #6345:
URL: https://github.com/apache/iceberg/pull/6345#discussion_r1038590250


##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkPartitionReaderFactory.java:
##########
@@ -0,0 +1,80 @@
+/*
+ * 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.spark.source;
+
+import org.apache.iceberg.ChangelogScanTask;
+import org.apache.iceberg.FileScanTask;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.connector.read.InputPartition;
+import org.apache.spark.sql.connector.read.PartitionReader;
+import org.apache.spark.sql.connector.read.PartitionReaderFactory;
+import org.apache.spark.sql.vectorized.ColumnarBatch;
+
+class SparkPartitionReaderFactory implements PartitionReaderFactory {
+  private final int batchSize;
+
+  SparkPartitionReaderFactory(int batchSize) {
+    this.batchSize = batchSize;
+  }
+
+  @Override
+  public PartitionReader<InternalRow> createReader(InputPartition inputPartition) {
+    Preconditions.checkArgument(
+        inputPartition instanceof SparkInputPartition,
+        "Unknown input partition type: %s",
+        inputPartition.getClass().getName());
+
+    SparkInputPartition partition = (SparkInputPartition) inputPartition;
+
+    if (partition.allTasksOfType(FileScanTask.class)) {
+      return new RowDataReader(partition);
+
+    } else if (partition.allTasksOfType(ChangelogScanTask.class)) {
+      return new ChangelogRowReader(partition);
+
+    } else {
+      throw new UnsupportedOperationException(
+          "Unsupported task group for row-based reads: " + partition.taskGroup());
+    }
+  }
+
+  @Override
+  public PartitionReader<ColumnarBatch> createColumnarReader(InputPartition inputPartition) {
+    Preconditions.checkArgument(
+        inputPartition instanceof SparkInputPartition,
+        "Unknown input partition type: %s",
+        inputPartition.getClass().getName());
+
+    SparkInputPartition partition = (SparkInputPartition) inputPartition;
+
+    if (partition.allTasksOfType(FileScanTask.class)) {
+      return new BatchDataReader(partition, batchSize);
+
+    } else {
+      throw new UnsupportedOperationException(
+          "Unsupported task group for batch reads: " + partition.taskGroup());
+    }
+  }
+
+  @Override
+  public boolean supportColumnarReads(InputPartition inputPartition) {
+    return batchSize > 1;

Review Comment:
   How about add methods `vectorized(boolean).batchSize(int)`? It would be more code, but cleaner logically.



-- 
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