Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/7482#discussion_r34945641
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/rowFormatConverters.scala
---
@@ -0,0 +1,107 @@
+/*
+ * 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
+
+import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.rules.Rule
+
+/**
+ * :: DeveloperApi ::
+ * Converts Java-object-based rows into [[UnsafeRow]]s.
+ */
+@DeveloperApi
+case class ConvertToUnsafe(child: SparkPlan) extends UnaryNode {
+ override def output: Seq[Attribute] = child.output
+ override def outputsUnsafeRows: Boolean = true
+ override def canProcessUnsafeRows: Boolean = false
+ override def canProcessSafeRows: Boolean = true
+ override protected def doExecute(): RDD[InternalRow] = {
+ child.execute().mapPartitions { iter =>
+ val convertToUnsafe = UnsafeProjection.create(child.schema)
+ iter.map(convertToUnsafe)
+ }
+ }
+}
+
+/**
+ * :: DeveloperApi ::
+ * Converts [[UnsafeRow]]s back into Java-object-based rows.
+ */
+@DeveloperApi
+case class ConvertToSafe(child: SparkPlan) extends UnaryNode {
+ override def output: Seq[Attribute] = child.output
+ override def outputsUnsafeRows: Boolean = false
+ override def canProcessUnsafeRows: Boolean = true
+ override def canProcessSafeRows: Boolean = false
+ override protected def doExecute(): RDD[InternalRow] = {
+ child.execute().mapPartitions { iter =>
+ val convertToSafe =
FromUnsafeProjection(child.output.map(_.dataType))
+ iter.map(convertToSafe)
+ }
+ }
+}
+
+private[sql] object EnsureRowFormats extends Rule[SparkPlan] {
+
+ private def onlyHandlesSafeRows(operator: SparkPlan): Boolean =
+ operator.canProcessSafeRows && !operator.canProcessUnsafeRows
+
+ private def onlyHandlesUnsafeRows(operator: SparkPlan): Boolean =
+ operator.canProcessUnsafeRows && !operator.canProcessSafeRows
+
+ private def handlesBothSafeAndUnsafeRows(operator: SparkPlan): Boolean =
+ operator.canProcessSafeRows && operator.canProcessUnsafeRows
+
+ override def apply(operator: SparkPlan): SparkPlan =
operator.transformUp {
+ case operator: SparkPlan if onlyHandlesSafeRows(operator) =>
+ if (operator.children.exists(_.outputsUnsafeRows)) {
+ operator.withNewChildren {
+ operator.children.map {
+ c => if (c.outputsUnsafeRows) ConvertToSafe(c) else c
+ }
+ }
+ } else {
+ operator
+ }
+ case operator: SparkPlan if onlyHandlesUnsafeRows(operator) =>
+ if (operator.children.exists(!_.outputsUnsafeRows)) {
+ operator.withNewChildren {
+ operator.children.map {
+ c => if (!c.outputsUnsafeRows) ConvertToUnsafe(c) else c
+ }
+ }
+ } else {
+ operator
+ }
+ case operator: SparkPlan if handlesBothSafeAndUnsafeRows(operator) =>
+ if (operator.children.map(_.outputsUnsafeRows).toSet.size != 1) {
+ // If this operator's children produce both unsafe and safe rows,
then convert everything
+ // to safe rows
+ operator.withNewChildren {
--- End diff --
Yeah, I think so. I think that choosing to resolve this type of conflict
in favor of UnsafeRow should be fine: if unsafe operators are disabled via a
feature flag, then the plan shouldn't contain any operators which claim to
output unsafe rows so this branch will never be triggered.
I'll update this patch to change this logic.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
