[GitHub] [iceberg] rdblue commented on a change in pull request #1947: [WIP] Spark MERGE INTO Support (copy-on-write implementation)

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

rdblue commented on a change in pull request #1947:
URL: https://github.com/apache/iceberg/pull/1947#discussion_r545516120



##########
File path: spark3-extensions/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteMergeInto.scala
##########
@@ -0,0 +1,164 @@
+/*
+ * 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.optimizer
+
+import java.util.UUID
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.{AnalysisException, SparkSession}
+import org.apache.spark.sql.catalyst.encoders.RowEncoder
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.plans.{FullOuter, Inner, JoinType}
+import org.apache.spark.sql.catalyst.plans.logical._
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.connector.catalog.Table
+import org.apache.spark.sql.connector.iceberg.read.SupportsFileFilter
+import org.apache.spark.sql.connector.iceberg.write.MergeBuilder
+import org.apache.spark.sql.connector.write.{LogicalWriteInfo, LogicalWriteInfoImpl}
+import org.apache.spark.sql.execution.datasources.v2.{DataSourceV2Relation, DataSourceV2ScanRelation}
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types._
+import org.apache.spark.sql.util.CaseInsensitiveStringMap
+
+object RewriteMergeInto extends Rule[LogicalPlan]
+  with PredicateHelper
+  with Logging  {
+  val ROW_ID_COL = "_row_id_"
+  val FILE_NAME_COL = "_file_name_"
+  val SOURCE_ROW_PRESENT_COL = "_source_row_present_"
+  val TARGET_ROW_PRESENT_COL = "_target_row_present_"
+
+  import org.apache.spark.sql.execution.datasources.v2.ExtendedDataSourceV2Implicits._
+
+  override def apply(plan: LogicalPlan): LogicalPlan = {
+    plan resolveOperators {
+      // rewrite all operations that require reading the table to delete records
+      case MergeIntoTable(target: DataSourceV2Relation,
+                          source: LogicalPlan, cond, actions, notActions) =>
+        // Find the files in target that matches the JOIN condition from source.
+        val targetOutputCols = target.output
+        val newProjectCols = target.output ++ Seq(Alias(InputFileName(), FILE_NAME_COL)())
+        val newTargetTable = Project(newProjectCols, target)

Review comment:
       It would be helpful to group some of these plan nodes into sections, like in `RewriteDelete` where methods like `buildFileFilterPlan` and `buildScanPlan` give good context for what plans are being constructed and how they will be used.




----------------------------------------------------------------
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.

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