singhpk234 commented on code in PR #6752: URL: https://github.com/apache/iceberg/pull/6752#discussion_r1097020044
########## spark/v3.3/spark-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DropBranchExec.scala: ########## @@ -0,0 +1,50 @@ +/* + * 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.spark.sql.execution.datasources.v2 + +import org.apache.iceberg.spark.source.SparkTable +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.connector.catalog.Identifier +import org.apache.spark.sql.connector.catalog.TableCatalog + +case class DropBranchExec(catalog: TableCatalog, + ident: Identifier, + branch: String) extends LeafV2CommandExec { + + import org.apache.spark.sql.connector.catalog.CatalogV2Implicits._ + + override lazy val output: Seq[Attribute] = Nil + + override protected def run(): Seq[InternalRow] = { + catalog.loadTable(ident) match { + case iceberg: SparkTable => + iceberg.table().manageSnapshots().removeBranch(branch).commit() + case table => + throw new UnsupportedOperationException(s"Cannot create or replace branch on non-Iceberg table: $table") Review Comment: ```suggestion throw new UnsupportedOperationException(s"Cannot drop branch on non-Iceberg table: $table") ``` ########## spark/v3.3/spark-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DropBranchExec.scala: ########## @@ -0,0 +1,50 @@ +/* + * 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.spark.sql.execution.datasources.v2 + +import org.apache.iceberg.spark.source.SparkTable +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.connector.catalog.Identifier +import org.apache.spark.sql.connector.catalog.TableCatalog + +case class DropBranchExec(catalog: TableCatalog, + ident: Identifier, + branch: String) extends LeafV2CommandExec { Review Comment: [style] can we follow the indentation we do for existing operators. i.e new line should start with 4 spaces. for ex: CallExec https://github.com/apache/iceberg/blob/531a81581aed152bdbcfa8801593f26918dc1d02/spark/v3.1/spark-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/CallExec.scala#L27-L30 Here is scala style , i think spark follows https://github.com/databricks/scala-style-guide ########## spark/v3.3/spark-extensions/src/main/antlr/org.apache.spark.sql.catalyst.parser.extensions/IcebergSqlExtensions.g4: ########## @@ -74,6 +74,7 @@ statement | ALTER TABLE multipartIdentifier SET IDENTIFIER_KW FIELDS fieldList #setIdentifierFields | ALTER TABLE multipartIdentifier DROP IDENTIFIER_KW FIELDS fieldList #dropIdentifierFields | ALTER TABLE multipartIdentifier createReplaceBranchClause #createOrReplaceBranch + | ALTER TABLE multipartIdentifier DROP BRANCH identifier #dropBranch Review Comment: can we make the `#dropBranch` in one row like `#setIdentifierFields` and `#call` ```suggestion | ALTER TABLE multipartIdentifier DROP IDENTIFIER_KW FIELDS fieldList #dropIdentifierFields | ALTER TABLE multipartIdentifier createReplaceBranchClause #createOrReplaceBranch | ALTER TABLE multipartIdentifier DROP BRANCH identifier #dropBranch ``` ########## spark/v3.3/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestDropBranch.java: ########## @@ -0,0 +1,116 @@ +/* + * 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.extensions; + +import java.util.List; +import java.util.Map; +import org.apache.iceberg.AssertHelpers; +import org.apache.iceberg.SnapshotRef; +import org.apache.iceberg.Table; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.spark.SparkCatalogConfig; +import org.apache.iceberg.spark.source.SimpleRecord; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.junit.After; +import org.junit.Assert; +import org.junit.Test; +import org.junit.runners.Parameterized; + +public class TestDropBranch extends SparkExtensionsTestBase { + + @Parameterized.Parameters(name = "catalogName = {0}, implementation = {1}, config = {2}") + public static Object[][] parameters() { + return new Object[][] { + { + SparkCatalogConfig.SPARK.catalogName(), + SparkCatalogConfig.SPARK.implementation(), + SparkCatalogConfig.SPARK.properties() + } + }; + } + + public TestDropBranch(String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + } + + @After + public void removeTable() { + sql("DROP TABLE IF EXISTS %s", tableName); + } + + @Test + public void testDropBranch() throws NoSuchTableException { + sql("CREATE TABLE %s (id INT, data STRING) USING iceberg", tableName); + List<SimpleRecord> records = + ImmutableList.of(new SimpleRecord(1, "a"), new SimpleRecord(2, "b")); + Dataset<Row> df = spark.createDataFrame(records, SimpleRecord.class); + df.writeTo(tableName).append(); Review Comment: can move this in `@BeforeEach` ########## spark/v3.3/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestDropBranch.java: ########## @@ -0,0 +1,116 @@ +/* + * 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.extensions; + +import java.util.List; +import java.util.Map; +import org.apache.iceberg.AssertHelpers; +import org.apache.iceberg.SnapshotRef; +import org.apache.iceberg.Table; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.spark.SparkCatalogConfig; +import org.apache.iceberg.spark.source.SimpleRecord; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.junit.After; +import org.junit.Assert; +import org.junit.Test; +import org.junit.runners.Parameterized; + +public class TestDropBranch extends SparkExtensionsTestBase { + + @Parameterized.Parameters(name = "catalogName = {0}, implementation = {1}, config = {2}") + public static Object[][] parameters() { + return new Object[][] { + { + SparkCatalogConfig.SPARK.catalogName(), + SparkCatalogConfig.SPARK.implementation(), + SparkCatalogConfig.SPARK.properties() + } + }; + } + + public TestDropBranch(String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + } + + @After + public void removeTable() { + sql("DROP TABLE IF EXISTS %s", tableName); + } + + @Test + public void testDropBranch() throws NoSuchTableException { + sql("CREATE TABLE %s (id INT, data STRING) USING iceberg", tableName); + List<SimpleRecord> records = + ImmutableList.of(new SimpleRecord(1, "a"), new SimpleRecord(2, "b")); + Dataset<Row> df = spark.createDataFrame(records, SimpleRecord.class); + df.writeTo(tableName).append(); + + Table table = validationCatalog.loadTable(tableIdent); + String branchName = "b1"; + table.manageSnapshots().createBranch(branchName, table.currentSnapshot().snapshotId()).commit(); + SnapshotRef ref = table.refs().get(branchName); + Assert.assertEquals(table.currentSnapshot().snapshotId(), ref.snapshotId()); + + sql("ALTER TABLE %s DROP BRANCH %s", tableName, branchName); + table.refresh(); + + ref = table.refs().get(branchName); + Assert.assertEquals(null, ref); Review Comment: [minor] can use `Assert.assertNull()` -- 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
