rdblue commented on a change in pull request #3708: URL: https://github.com/apache/iceberg/pull/3708#discussion_r766963596
########## File path: spark/v3.2/spark/src/test/java/org/apache/iceberg/spark/sql/TestPartitionedWritesAsSelect.java ########## @@ -0,0 +1,181 @@ +/* + * 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.util.List; +import java.util.Map; +import java.util.stream.IntStream; +import org.apache.iceberg.AssertHelpers; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.spark.IcebergSpark; +import org.apache.iceberg.spark.SparkCatalogTestBase; +import org.apache.iceberg.spark.SparkSessionCatalog; +import org.apache.spark.SparkException; +import org.apache.spark.sql.AnalysisException; +import org.apache.spark.sql.types.DataTypes; +import org.junit.After; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Test; +import org.junit.runners.Parameterized; + +public class TestPartitionedWritesAsSelect extends SparkCatalogTestBase { + + private final String targetTable = "target_table"; + + public TestPartitionedWritesAsSelect(String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + } + + @Parameterized.Parameters(name = "catalogName = {0}, implementation = {1}, config = {2}") + public static Object[][] parameters() { + return new Object[][]{{"spark_catalog", + SparkSessionCatalog.class.getName(), + ImmutableMap.of( + "type", "hive", + "default-namespace", "default", + "parquet-enabled", "true", + "cache-enabled", "false" + )} + }; + } + + @Before + public void createTables() { + sql("CREATE TABLE %s (id bigint, data string, category string, ts timestamp)" + + "USING iceberg", tableName); + } + + @After + public void removeTables() { + sql("DROP TABLE IF EXISTS %s", tableName); + sql("DROP TABLE IF EXISTS %s", targetTable); + } + + @Test + public void testInsertAsSelectAppend() { + insertData(3); + List<Object[]> expected = currentData(); + + sql("CREATE TABLE %s (id bigint, data string, category string, ts timestamp)" + + "USING iceberg PARTITIONED BY (days(ts), category)", targetTable); + + sql("INSERT INTO %s SELECT id, data, category, ts FROM %s ORDER BY ts,category", targetTable, tableName); + Assert.assertEquals("Should have 24 rows after insert", + 3 * 8L, scalarSql("SELECT count(*) FROM %s", targetTable)); + + assertEquals("Row data should match expected", + expected, sql("SELECT * FROM %s ORDER BY id", targetTable)); + } + + @Test + public void testInsertAsSelectWithBucket() { + insertData(3); + List<Object[]> expected = currentData(); + + sql("CREATE TABLE %s (id bigint, data string, category string, ts timestamp)" + + "USING iceberg PARTITIONED BY (bucket(8, data))", targetTable); + + IcebergSpark.registerBucketUDF(spark, "iceberg_bucket8", DataTypes.StringType, 8); + sql("INSERT INTO %s SELECT id, data, category, ts FROM %s ORDER BY iceberg_bucket8(data)", targetTable, tableName); + Assert.assertEquals("Should have 24 rows after insert", + 3 * 8L, scalarSql("SELECT count(*) FROM %s", targetTable)); + + assertEquals("Row data should match expected", + expected, sql("SELECT * FROM %s ORDER BY id", targetTable)); + } + + @Test + public void testInsertAsSelectWithTruncate() { + insertData(3); + List<Object[]> expected = currentData(); + + sql("CREATE TABLE %s (id bigint, data string, category string, ts timestamp)" + + "USING iceberg PARTITIONED BY (truncate(data, 4), truncate(id, 4))", targetTable); + + IcebergSpark.registerTruncateUDF(spark, "iceberg_truncate_string4", DataTypes.StringType, 4); + IcebergSpark.registerTruncateUDF(spark, "iceberg_truncate_long4", DataTypes.LongType, 4); + sql("INSERT INTO %s SELECT id, data, category, ts FROM %s " + + "ORDER BY iceberg_truncate_string4(data),iceberg_truncate_long4(id)", targetTable, tableName); + Assert.assertEquals("Should have 24 rows after insert", + 3 * 8L, scalarSql("SELECT count(*) FROM %s", targetTable)); + + assertEquals("Row data should match expected", + expected, sql("SELECT * FROM %s ORDER BY id", targetTable)); + } + + @Test + public void testInsertAsSelectWithBucketFailure() { + insertData(3); + + sql("CREATE TABLE %s (id bigint, data string, category string, ts timestamp)" + + "USING iceberg PARTITIONED BY (bucket(8, id))", targetTable); + AssertHelpers.assertThrows("should registered temporary function" + + "nor a permanent function registered in the database 'default'", + AnalysisException.class, + "Undefined function: 'iceberg_bucket8'", + () -> sql("INSERT INTO %s SELECT id, data, category, ts FROM %s ORDER BY iceberg_bucket8(id)", + targetTable, tableName)); + + AssertHelpers.assertThrows("should registered the bucket transform function" + + "in Spark to specify it during sort.", + SparkException.class, + "Writing job aborted", + () -> sql("INSERT INTO %s SELECT id, data, category, ts FROM %s ORDER BY id", targetTable, tableName)); + } + + @Test + public void testInsertAsSelectWithTruncateFailure() { Review comment: Why test these failure cases? I think we test these elsewhere and it doesn't make sense to fail if something gets better later. I'd remove this and the test above. -- 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]
