rdblue commented on code in PR #6622: URL: https://github.com/apache/iceberg/pull/6622#discussion_r1103896313
########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkAggregates.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 + * 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.util.Map; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.Expression.Operation; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.spark.SparkUtil; +import org.apache.spark.sql.connector.expressions.NamedReference; +import org.apache.spark.sql.connector.expressions.aggregate.AggregateFunc; +import org.apache.spark.sql.connector.expressions.aggregate.Count; +import org.apache.spark.sql.connector.expressions.aggregate.CountStar; +import org.apache.spark.sql.connector.expressions.aggregate.Max; +import org.apache.spark.sql.connector.expressions.aggregate.Min; + +public class SparkAggregates { + + private SparkAggregates() {} + + private static final Map<Class<? extends AggregateFunc>, Operation> AGGREGATES = + ImmutableMap.<Class<? extends AggregateFunc>, Operation>builder() + .put(Count.class, Operation.COUNT) + .put(CountStar.class, Operation.COUNT_STAR) + .put(Max.class, Operation.MAX) + .put(Min.class, Operation.MIN) + .build(); + + public static Expression convert(AggregateFunc aggregate) { + Operation op = AGGREGATES.get(aggregate.getClass()); + if (op != null) { + switch (op) { + case COUNT: + Count countAgg = (Count) aggregate; + assert (countAgg.column() instanceof NamedReference); + return Expressions.count(SparkUtil.toColumnName((NamedReference) countAgg.column())); + case COUNT_STAR: + return Expressions.countStar(); + case MAX: + Max maxAgg = (Max) aggregate; + assert (maxAgg.column() instanceof NamedReference); + return Expressions.max(SparkUtil.toColumnName((NamedReference) maxAgg.column())); + case MIN: + Min minAgg = (Min) aggregate; + assert (minAgg.column() instanceof NamedReference); + return Expressions.min(SparkUtil.toColumnName((NamedReference) minAgg.column())); + } + } + throw new UnsupportedOperationException("Invalid aggregate: " + aggregate); Review Comment: We can't assume that the aggregate is invalid just because it isn't supported. Instead, this should state that the aggregate is unsupported. Most of the time when we have a situation like this, we will return `null` to signal that conversion failed, which is not an exceptional case. When the caller receives a null back, it can then handle the situation by logging that agg pushdown was not possible, and returning `false` to Spark so that Spark will read the data and aggregate itself. -- 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-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
