You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@iceberg.apache.org by GitBox <gi...@apache.org> on 2023/01/18 18:49:56 UTC
[GitHub] [iceberg] amogh-jahagirdar commented on a diff in pull request #6617: Spark: Spark SQL Extensions for create branch
amogh-jahagirdar commented on code in PR #6617:
URL: https://github.com/apache/iceberg/pull/6617#discussion_r1073943012
##########
spark/v3.3/spark-extensions/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/CreateBranch.scala:
##########
@@ -0,0 +1,34 @@
+/*
+ * 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.catalyst.plans.logical
+
+import org.apache.spark.sql.catalyst.expressions.Attribute
+
+case class CreateBranch(table: Seq[String], branch: String, snapshotId: Option[Long], numSnapshots: Option[Long],
+ snapshotRetain: Option[Long], snapshotRefRetain: Option[Long]) extends LeafCommand {
+
+ import org.apache.spark.sql.connector.catalog.CatalogV2Implicits._
+
+ override lazy val output: Seq[Attribute] = Nil
+
+ override def simpleString(maxFields: Int): String = {
+ s"Create branch:${branch} for table:${table.quoted} "
Review Comment:
Nit: spacing in the message
`"Create branch: ${branch} for table: ${table.quoted}"`
##########
spark/v3.3/spark-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/CreateBranchExec.scala:
##########
@@ -0,0 +1,61 @@
+/*
+ * 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.catalyst.plans.logical.CreateBranch
+import org.apache.spark.sql.connector.catalog.Identifier
+import org.apache.spark.sql.connector.catalog.TableCatalog
+
+case class CreateBranchExec(
+ catalog: TableCatalog,
+ ident: Identifier,
+ createBranch: CreateBranch) 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 =>
+
+ val snapshotId = createBranch.snapshotId.getOrElse(iceberg.table.currentSnapshot().snapshotId())
+ iceberg.table.manageSnapshots()
+ .createBranch(createBranch.branch, snapshotId)
+ .setMinSnapshotsToKeep(createBranch.branch, createBranch.numSnapshots.getOrElse(1L).toInt)
+ // 5 days
+ .setMaxSnapshotAgeMs(createBranch.branch, createBranch.snapshotRetain.getOrElse(5 * 24 * 60 * 60 * 1000L))
+ .setMaxRefAgeMs(createBranch.branch, createBranch.snapshotRefRetain.getOrElse(Long.MaxValue))
+ .commit()
+
+ case table =>
+ throw new UnsupportedOperationException(s"Cannot add branch to non-Iceberg table: $table")
Review Comment:
I think this case will be common for all the reference based operations. We may want to see about extracting to a common parent. Not needed at this point, but we may revisit in later DDL implementations.
##########
spark/v3.3/spark-extensions/src/main/antlr/org.apache.spark.sql.catalyst.parser.extensions/IcebergSqlExtensions.g4:
##########
@@ -73,6 +73,13 @@ statement
| ALTER TABLE multipartIdentifier WRITE writeSpec #setWriteDistributionAndOrdering
| ALTER TABLE multipartIdentifier SET IDENTIFIER_KW FIELDS fieldList #setIdentifierFields
| ALTER TABLE multipartIdentifier DROP IDENTIFIER_KW FIELDS fieldList #dropIdentifierFields
+ | ALTER TABLE multipartIdentifier CREATE BRANCH identifier (AS OF VERSION snapshotId)? (snapshotRetentionClause)? (RETAIN snapshotRefRetain snapshotRefRetainTimeUnit)? #createBranch
Review Comment:
Agreed, after re-reading the syntax I felt this way too. `RETAIN` should be close to the actual branch clause so that association of what the clauses is responsible for (the retention of the reference itself) is there.
--
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-unsubscribe@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org