rdblue commented on a change in pull request #1947: URL: https://github.com/apache/iceberg/pull/1947#discussion_r559831987
########## File path: spark3-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/MergeIntoExec.scala ########## @@ -0,0 +1,139 @@ +/* + * 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.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.catalyst.expressions.BasePredicate +import org.apache.spark.sql.catalyst.expressions.Expression +import org.apache.spark.sql.catalyst.expressions.UnsafeProjection +import org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate +import org.apache.spark.sql.catalyst.plans.logical.MergeIntoParams +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.execution.UnaryExecNode + +case class MergeIntoExec( + mergeIntoParams: MergeIntoParams, + @transient targetRelation: DataSourceV2Relation, + override val child: SparkPlan) extends UnaryExecNode { + + override def output: Seq[Attribute] = targetRelation.output + + protected override def doExecute(): RDD[InternalRow] = { + child.execute().mapPartitions { + processPartition(mergeIntoParams, _) + } + } + + private def generateProjection(exprs: Seq[Expression], attrs: Seq[Attribute]): UnsafeProjection = { + UnsafeProjection.create(exprs, attrs) + } + + private def generatePredicate(expr: Expression, attrs: Seq[Attribute]): BasePredicate = { + GeneratePredicate.generate(expr, attrs) + } + + def applyProjection( + actions: Seq[(BasePredicate, UnsafeProjection)], + projectTargetCols: UnsafeProjection, + projectDeleteRow: UnsafeProjection, + inputRow: InternalRow, + targetRowNotPresent: Boolean): InternalRow = { + + /** + * Find the first combination where the predicate evaluates to true. + * In case when there are overlapping condition in the MATCHED + * clauses, for the first one that satisfies the predicate, the + * corresponding action is applied. For example: + * + * WHEN MATCHED AND id > 1 AND id < 10 UPDATE * + * WHEN MATCHED AND id = 5 OR id = 21 DELETE + * + * In above case, when id = 5, it applies both that matched predicates. In this + * case the first one we see is applied. + */ Review comment: Style: this is a doc comment because it starts with `/**`. Usually, multi-line comments in code would use `// ` on each line. ---------------------------------------------------------------- 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: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
