JonasJ-ap commented on code in PR #6449: URL: https://github.com/apache/iceberg/pull/6449#discussion_r1084793195
########## delta-lake/src/integration/java/org/apache/iceberg/delta/TestSnapshotDeltaLakeTable.java: ########## @@ -0,0 +1,468 @@ +/* + * 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.delta; + +import io.delta.standalone.DeltaLog; +import io.delta.standalone.Operation; +import io.delta.standalone.OptimisticTransaction; +import io.delta.standalone.actions.AddFile; +import io.delta.standalone.actions.RemoveFile; +import io.delta.standalone.exceptions.DeltaConcurrentModificationException; +import java.io.File; +import java.io.IOException; +import java.net.URI; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import org.apache.iceberg.Table; +import org.apache.iceberg.catalog.TableIdentifier; +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.Spark3Util; +import org.apache.iceberg.spark.SparkSessionCatalog; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SQLContext; +import org.apache.spark.sql.SaveMode; +import org.apache.spark.sql.connector.catalog.CatalogPlugin; +import org.apache.spark.sql.delta.catalog.DeltaCatalog; +import org.assertj.core.api.Assertions; +import org.junit.After; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestSnapshotDeltaLakeTable extends SparkDeltaLakeSnapshotTestBase { + private static final String row1 = + "{\"name\":\"Michael\",\"addresses\":[{\"city\":\"SanJose\",\"state\":\"CA\"},{\"city\":\"Sandiago\",\"state\":\"CA\"}]," + + "\"address_nested\":{\"current\":{\"state\":\"NY\",\"city\":\"NewYork\"},\"previous\":{\"state\":\"NJ\",\"city\":\"Newark\"}}," + + "\"properties\":{\"hair\":\"brown\",\"eye\":\"black\"},\"secondProp\":{\"height\":\"6\"},\"subjects\":[[\"Java\",\"Scala\",\"C++\"]," + + "[\"Spark\",\"Java\"]],\"id\":1,\"magic_number\":1.123123123123}"; + private static final String row2 = + "{\"name\":\"Test\",\"addresses\":[{\"city\":\"SanJos123123e\",\"state\":\"CA\"},{\"city\":\"Sand12312iago\",\"state\":\"CA\"}]," + + "\"address_nested\":{\"current\":{\"state\":\"N12Y\",\"city\":\"NewY1231ork\"}},\"properties\":{\"hair\":\"brown\",\"eye\":\"black\"}," + + "\"secondProp\":{\"height\":\"6\"},\"subjects\":[[\"Java\",\"Scala\",\"C++\"],[\"Spark\",\"Java\"]],\"id\":2,\"magic_number\":2.123123123123}"; + private static final String row3 = + "{\"name\":\"Test\",\"addresses\":[{\"city\":\"SanJose\",\"state\":\"CA\"},{\"city\":\"Sandiago\",\"state\":\"CA\"}]," + + "\"properties\":{\"hair\":\"brown\",\"eye\":\"black\"},\"secondProp\":{\"height\":\"6\"},\"subjects\":" + + "[[\"Java\",\"Scala\",\"C++\"],[\"Spark\",\"Java\"]],\"id\":3,\"magic_number\":3.123123123123}"; + private static final String row4 = + "{\"name\":\"John\",\"addresses\":[{\"city\":\"LA\",\"state\":\"CA\"},{\"city\":\"Sandiago\",\"state\":\"CA\"}]," + + "\"address_nested\":{\"current\":{\"state\":\"NY\",\"city\":\"NewYork\"},\"previous\":{\"state\":\"NJ123\"}}," + + "\"properties\":{\"hair\":\"b12rown\",\"eye\":\"bla3221ck\"},\"secondProp\":{\"height\":\"633\"},\"subjects\":" + + "[[\"Spark\",\"Java\"]],\"id\":4,\"magic_number\":4.123123123123}"; + private static final String row5 = + "{\"name\":\"Jonas\",\"addresses\":[{\"city\":\"Pittsburgh\",\"state\":\"PA\"},{\"city\":\"Sandiago\",\"state\":\"CA\"}]," + + "\"address_nested\":{\"current\":{\"state\":\"PA\",\"city\":\"Haha\"},\"previous\":{\"state\":\"NJ\"}}," + + "\"properties\":{\"hair\":\"black\",\"eye\":\"black\"},\"secondProp\":{\"height\":\"7\"},\"subjects\":[[\"Java\",\"Scala\",\"C++\"]," + + "[\"Spark\",\"Java\"]],\"id\":5,\"magic_number\":5.123123123123}"; + private static final String SNAPSHOT_SOURCE_PROP = "snapshot_source"; + private static final String DELTA_SOURCE_VALUE = "delta"; + private static final String ORIGINAL_LOCATION_PROP = "original_location"; + private static final String NAMESPACE = "delta_conversion_test"; + private static final String defaultSparkCatalog = "spark_catalog"; + private static final String icebergCatalogName = "iceberg_hive"; + private String partitionedIdentifier; + private String unpartitionedIdentifier; + private String externalDataFilesIdentifier; + private final String partitionedTableName = "partitioned_table"; + private final String unpartitionedTableName = "unpartitioned_table"; + private final String externalDataFilesTableName = "external_data_files_table"; + private String partitionedLocation; + private String unpartitionedLocation; + private String newIcebergTableLocation; + private String externalDataFilesTableLocation; + + @Parameterized.Parameters(name = "Catalog Name {0} - Options {2}") + public static Object[][] parameters() { + return new Object[][] { + new Object[] { + icebergCatalogName, + SparkSessionCatalog.class.getName(), + ImmutableMap.of( + "type", + "hive", + "default-namespace", + "default", + "parquet-enabled", + "true", + "cache-enabled", + "false" // Spark will delete tables using v1, leaving the cache out of sync + ) + } + }; + } + + @Rule public TemporaryFolder temp1 = new TemporaryFolder(); + @Rule public TemporaryFolder temp2 = new TemporaryFolder(); + @Rule public TemporaryFolder temp3 = new TemporaryFolder(); + @Rule public TemporaryFolder temp4 = new TemporaryFolder(); + + public TestSnapshotDeltaLakeTable( + String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + spark.conf().set("spark.sql.catalog." + defaultSparkCatalog, DeltaCatalog.class.getName()); + } + + /** + * The test hardcode a nested dataframe to test the snapshot feature. The schema of created + * dataframe is: + * + * <pre> + * root + * |-- address_nested: struct (nullable = true) Review Comment: Agree. Thank you for pointing this out. I added another dataframe which includes all data types that delta lake supports (and also supported by iceberg). I will discuss details below -- 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
