rdblue commented on code in PR #6622: URL: https://github.com/apache/iceberg/pull/6622#discussion_r1116144251
########## spark/v3.3/spark/src/test/java/org/apache/iceberg/spark/sql/TestAggregatePushDown.java: ########## @@ -0,0 +1,680 @@ +/* + * 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.sql; + +import java.math.BigDecimal; +import java.sql.Date; +import java.sql.Timestamp; +import java.util.List; +import java.util.Locale; +import java.util.Map; +import org.apache.iceberg.CatalogUtil; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.exceptions.AlreadyExistsException; +import org.apache.iceberg.hive.HiveCatalog; +import org.apache.iceberg.hive.TestHiveMetastore; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.spark.SparkCatalogTestBase; +import org.apache.iceberg.spark.SparkTestBase; +import org.apache.spark.sql.SparkSession; +import org.junit.After; +import org.junit.Assert; +import org.junit.BeforeClass; +import org.junit.Test; + +public class TestAggregatePushDown extends SparkCatalogTestBase { + + public TestAggregatePushDown( + String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + } + + @BeforeClass + public static void startMetastoreAndSpark() { + SparkTestBase.metastore = new TestHiveMetastore(); + metastore.start(); + SparkTestBase.hiveConf = metastore.hiveConf(); + + SparkTestBase.spark = + SparkSession.builder() + .master("local[2]") + .config("spark.sql.iceberg.aggregate_pushdown", "true") + .enableHiveSupport() + .getOrCreate(); + + SparkTestBase.catalog = + (HiveCatalog) + CatalogUtil.loadCatalog( + HiveCatalog.class.getName(), "hive", ImmutableMap.of(), hiveConf); + + try { + catalog.createNamespace(Namespace.of("default")); + } catch (AlreadyExistsException ignored) { + // the default namespace already exists. ignore the create error + } + } + + @After + public void removeTables() { + sql("DROP TABLE IF EXISTS %s", tableName); + } + + @Test + public void testDifferentDataTypesAggregatePushDownInPartitionedTable() { + testDifferentDataTypesAggregatePushDown(true); + } + + @Test + public void testDifferentDataTypesAggregatePushDownInNonPartitionedTable() { + testDifferentDataTypesAggregatePushDown(false); + } + + @SuppressWarnings("checkstyle:CyclomaticComplexity") + private void testDifferentDataTypesAggregatePushDown(boolean hasPartitionCol) { + String createTable; + if (hasPartitionCol) { + createTable = + "CREATE TABLE %s (id LONG, int_data INT, boolean_data BOOLEAN, float_data FLOAT, double_data DOUBLE, " + + "decimal_data DECIMAL(14, 2), binary_data binary) USING iceberg PARTITIONED BY (id)"; + } else { + createTable = + "CREATE TABLE %s (id LONG, int_data INT, boolean_data BOOLEAN, float_data FLOAT, double_data DOUBLE, " + + "decimal_data DECIMAL(14, 2), binary_data binary) USING iceberg"; + } + + sql(createTable, tableName); + sql( + "INSERT INTO TABLE %s VALUES " + + "(1, null, false, null, null, 11.11, X'1111')," + + " (1, null, true, 2.222, 2.222222, 22.22, X'2222')," + + " (2, 33, false, 3.333, 3.333333, 33.33, X'3333')," + + " (2, 44, true, null, 4.444444, 44.44, X'4444')," + + " (3, 55, false, 5.555, 5.555555, 55.55, X'5555')," + + " (3, null, true, null, 6.666666, 66.66, null) ", + tableName); + + String select = + "SELECT count(*), max(id), min(id), count(id), " + + "max(int_data), min(int_data), count(int_data), " + + "max(boolean_data), min(boolean_data), count(boolean_data), " + + "max(float_data), min(float_data), count(float_data), " + + "max(double_data), min(double_data), count(double_data), " + + "max(decimal_data), min(decimal_data), count(decimal_data), " + + "max(binary_data), min(binary_data), count(binary_data) FROM %s"; + + List<Object[]> explain = sql("EXPLAIN " + select, tableName); + String explainString = explain.get(0)[0].toString(); + boolean explainContainsPushDownAggregates = false; + if (explainString.contains("count(*)".toLowerCase(Locale.ROOT)) Review Comment: It's the explain string that needs to be lower cased in these tests as well. -- 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
