rdblue commented on code in PR #7050: URL: https://github.com/apache/iceberg/pull/7050#discussion_r1133142216
########## spark/v3.3/spark/src/test/java/org/apache/iceberg/spark/sql/TestPartitionedWritesToWAPBranch.java: ########## @@ -0,0 +1,118 @@ +/* + * 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.Map; +import java.util.UUID; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.spark.SparkSessionProperties; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.assertj.core.api.Assertions; +import org.junit.After; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Test; + +public class TestPartitionedWritesToWAPBranch extends PartitionedWritesTestBase { + + private static final String BRANCH = "test"; + + public TestPartitionedWritesToWAPBranch( + String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + } + + @Before + @Override + public void createTables() { + spark.conf().set(SparkSessionProperties.WAP_BRANCH, BRANCH); + sql( + "CREATE TABLE %s (id bigint, data string) USING iceberg PARTITIONED BY (truncate(id, 3)) OPTIONS (%s = 'true')", + tableName, TableProperties.WRITE_AUDIT_PUBLISH_ENABLED); + sql("INSERT INTO %s VALUES (1, 'a'), (2, 'b'), (3, 'c')", tableName); + } + + @After + @Override + public void removeTables() { + super.removeTables(); + spark.conf().unset(SparkSessionProperties.WAP_BRANCH); + spark.conf().unset(SparkSessionProperties.WAP_ID); + } + + @Override + protected String commitTarget() { + return tableName; + } + + @Override + protected String selectTarget() { + return String.format("%s VERSION AS OF '%s'", tableName, BRANCH); + } + + // commit target in WAP is just the table name + // should use table + branch name instead for read Review Comment: I don't agree with this. I think it has to read the branch if it exists. For example, a DELETE command is going to modify the state of a branch if it exists, and it could exist because branch WAP supports multiple writes. That means the reads for both the delete itself and any dynamic pruning must read the branch if it exists and main if it doesn't. -- 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]
