[GitHub] [spark] rdblue commented on a change in pull request #35395: [SPARK-38085][SQL] DataSource V2: Handle DELETE commands for group-based sources

[GitBox <gi...@apache.org>]

rdblue commented on a change in pull request #35395:
URL: https://github.com/apache/spark/pull/35395#discussion_r810698505



##########
File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/RewriteDeleteFromTable.scala
##########
@@ -0,0 +1,84 @@
+/*
+ * 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.analysis
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.expressions.{EqualNullSafe, Expression, Literal, Not}
+import org.apache.spark.sql.catalyst.plans.logical.{DeleteFromTable, Filter, LogicalPlan, ReplaceData}
+import org.apache.spark.sql.connector.catalog.{SupportsDelete, SupportsRowLevelOperations}
+import org.apache.spark.sql.connector.write.RowLevelOperation.Command.DELETE
+import org.apache.spark.sql.connector.write.RowLevelOperationTable
+import org.apache.spark.sql.execution.datasources.v2.DataSourceV2Relation
+
+/**
+ * Assigns a rewrite plan for v2 tables that support rewriting data to handle DELETE statements.
+ *
+ * If a table implements [[SupportsDelete]] and [[SupportsRowLevelOperations]], this rule assigns
+ * a rewrite plan but the optimizer will check whether this particular DELETE statement can be
+ * handled by simply passing delete filters to the connector. If yes, the optimizer will then
+ * discard the rewrite plan.
+ */
+object RewriteDeleteFromTable extends RewriteRowLevelCommand {
+
+  override def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators {
+    case d @ DeleteFromTable(aliasedTable, cond, None) if d.resolved =>
+      EliminateSubqueryAliases(aliasedTable) match {
+        case r @ DataSourceV2Relation(tbl: SupportsRowLevelOperations, _, _, _, _) =>
+          val operation = buildRowLevelOperation(tbl, DELETE)
+          val table = RowLevelOperationTable(tbl, operation)
+          val deleteCond = cond.getOrElse(Literal.TrueLiteral)

Review comment:
       Can we match `Some(cond)` to avoid needing to do this? You could also have a rule above that matches None with `SupportsDelete` or `SupportsTruncate` to avoid the case where this is `true`.




-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org