singhpk234 commented on code in PR #15368: URL: https://github.com/apache/iceberg/pull/15368#discussion_r2850791296
########## spark/v4.1/spark/src/main/java/org/apache/iceberg/spark/source/TableWithIO.java: ########## @@ -0,0 +1,286 @@ +/* + * 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.List; +import java.util.Map; +import java.util.UUID; +import java.util.function.Supplier; +import org.apache.iceberg.AppendFiles; +import org.apache.iceberg.DeleteFiles; +import org.apache.iceberg.ExpireSnapshots; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.HistoryEntry; +import org.apache.iceberg.IncrementalAppendScan; +import org.apache.iceberg.IncrementalChangelogScan; +import org.apache.iceberg.ManageSnapshots; +import org.apache.iceberg.OverwriteFiles; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.PartitionStatisticsFile; +import org.apache.iceberg.PartitionStatisticsScan; +import org.apache.iceberg.ReplacePartitions; +import org.apache.iceberg.ReplaceSortOrder; +import org.apache.iceberg.RewriteFiles; +import org.apache.iceberg.RewriteManifests; +import org.apache.iceberg.RowDelta; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.SnapshotRef; +import org.apache.iceberg.SortOrder; +import org.apache.iceberg.StatisticsFile; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.TableScan; +import org.apache.iceberg.Transaction; +import org.apache.iceberg.UpdateLocation; +import org.apache.iceberg.UpdatePartitionSpec; +import org.apache.iceberg.UpdatePartitionStatistics; +import org.apache.iceberg.UpdateProperties; +import org.apache.iceberg.UpdateSchema; +import org.apache.iceberg.UpdateStatistics; +import org.apache.iceberg.encryption.EncryptionManager; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.LocationProvider; + +/** + * This is a wrapper around {@link Table} and {@link FileIO} where the {@link FileIO} instance might + * have more specific storage credentials and should be used for a table scan + * + * @param table The table instance + * @param fileIOForScan The {@link FileIO} instance that might have more specific storage + * credentials for a table scan + */ +public record TableWithIO(Table table, Supplier<FileIO> fileIOForScan) Review Comment: should we override the name() too, i think default it goes to `toString` but i think having consistent semantics of table.name() would be nice ########## core/src/main/java/org/apache/iceberg/BaseScan.java: ########## @@ -102,7 +102,8 @@ public Table table() { return table; } - protected FileIO io() { + @Override + public FileIO io() { return table.io(); } Review Comment: are we checking these io are correctly closed ? ########## core/src/test/java/org/apache/iceberg/rest/TestRESTScanPlanning.java: ########## @@ -953,4 +957,95 @@ public void serverSupportsPlanningButNotCancellation() throws IOException { // Verify no exception was thrown - cancelPlan returns false when endpoint not supported assertThat(cancelled).isFalse(); } + + @ParameterizedTest + @EnumSource(PlanningMode.class) + void fileIOForRemotePlanningIsPropagated( + Function<TestPlanningBehavior.Builder, TestPlanningBehavior.Builder> planMode) { + RESTCatalogAdapter adapter = + Mockito.spy( + new RESTCatalogAdapter(backendCatalog) { + @Override + public <T extends RESTResponse> T execute( + HTTPRequest request, + Class<T> responseType, + Consumer<ErrorResponse> errorHandler, + Consumer<Map<String, String>> responseHeaders, + ParserContext parserContext) { + T response = + super.execute( + request, responseType, errorHandler, responseHeaders, parserContext); + return maybeAddStorageCredential(response); + } + }); + + adapter.setPlanningBehavior(planMode.apply(TestPlanningBehavior.builder()).build()); + + RESTCatalog catalog = + new RESTCatalog(SessionCatalog.SessionContext.createEmpty(), (config) -> adapter); + catalog.initialize( + "test", + ImmutableMap.of( + CatalogProperties.FILE_IO_IMPL, + "org.apache.iceberg.inmemory.InMemoryFileIO", + RESTCatalogProperties.REST_SCAN_PLANNING_ENABLED, + "true")); + + Table table = restTableFor(catalog, "file_io_propagation"); + setParserContext(table); + + assertThat(table.io().properties()).doesNotContainKey(RESTCatalogProperties.REST_SCAN_PLAN_ID); + // make sure remote scan planning is called and FileIO gets the planId + TableScan tableScan = table.newScan(); Review Comment: should we add another call for it and may be inspect the plan-id values are different ? -- 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]
