rdblue commented on code in PR #5872: URL: https://github.com/apache/iceberg/pull/5872#discussion_r990821042
########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkPushedDownAggregateUtil.java: ########## @@ -0,0 +1,376 @@ +/* + * 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 java.math.BigDecimal; +import java.nio.ByteBuffer; +import java.util.List; +import java.util.Locale; +import java.util.Map; +import org.apache.iceberg.MetadataTableType; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.Literal; +import org.apache.iceberg.expressions.UnboundAggregate; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.spark.SparkSchemaUtil; +import org.apache.iceberg.spark.SparkTableUtil; +import org.apache.iceberg.types.Conversions; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.types.Types; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.types.ArrayType; +import org.apache.spark.sql.types.DataType; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.Decimal; +import org.apache.spark.sql.types.DecimalType; +import org.apache.spark.sql.types.MapType; +import org.apache.spark.sql.types.Metadata; +import org.apache.spark.sql.types.StructField; +import org.apache.spark.sql.types.StructType; +import scala.collection.JavaConverters; + +/** Helper methods for working with Spark aggregate push down. */ +public class SparkPushedDownAggregateUtil { + + private SparkPushedDownAggregateUtil() {} + + // Build schema for pushed down aggregates. This schema will be used as the scan schema. + public static StructType buildSchemaForPushedDownAggregate( Review Comment: Can each `BoundAggregate` return the type it produces? It should either be the type of the underlying term or `Long`: ```java public Type type() { if (op() == COUNT || op() == COUNT_STAR) { return LongType.get(); } else { return term.type(); } } ``` With that information, you should be able to produce a schema more easily. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
