Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/8464#discussion_r38080354
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/local/LocalNodeTest.scala
---
@@ -0,0 +1,192 @@
+/*
+* 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.local
+
+import scala.util.control.NonFatal
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.sql.catalyst.{CatalystTypeConverters, InternalRow}
+import org.apache.spark.sql.catalyst.util._
+import org.apache.spark.sql.{DataFrame, Row}
+import org.apache.spark.sql.types.StructType
+
+class LocalNodeTest extends SparkFunSuite {
+
+ /**
+ * Runs the LocalNode and makes sure the answer matches the expected
result.
+ * @param input the input data to be used.
+ * @param nodeFunction a function which accepts the input LocalNode and
uses it to instantiate
+ * the local physical operator that's being tested.
+ * @param expectedAnswer the expected result in a [[Seq]] of [[Row]]s.
+ * @param sortAnswers if true, the answers will be sorted by their
toString representations prior
+ * to being compared.
+ */
+ protected def checkAnswer(
+ input: DataFrame,
+ nodeFunction: LocalNode => LocalNode,
+ expectedAnswer: Seq[Row],
+ sortAnswers: Boolean = true): Unit = {
+ doCheckAnswer(
+ input :: Nil,
+ nodes => nodeFunction(nodes.head),
+ expectedAnswer,
+ sortAnswers)
+ }
+
+ /**
+ * Runs the LocalNode and makes sure the answer matches the expected
result.
+ * @param left the left input data to be used.
+ * @param right the right input data to be used.
+ * @param nodeFunction a function which accepts the input LocalNode and
uses it to instantiate
+ * the local physical operator that's being tested.
+ * @param expectedAnswer the expected result in a [[Seq]] of [[Row]]s.
+ * @param sortAnswers if true, the answers will be sorted by their
toString representations prior
+ * to being compared.
+ */
+ protected def checkAnswer2(
+ left: DataFrame,
+ right: DataFrame,
+ nodeFunction: (LocalNode, LocalNode) => LocalNode,
+ expectedAnswer: Seq[Row],
+ sortAnswers: Boolean = true): Unit = {
+ doCheckAnswer(
+ left :: right :: Nil,
+ nodes => nodeFunction(nodes(0), nodes(1)),
+ expectedAnswer,
+ sortAnswers)
+ }
+
+ /**
+ * Runs the `LocalNode`s and makes sure the answer matches the expected
result.
+ * @param input the input data to be used.
+ * @param nodeFunction a function which accepts a sequence of input
`LocalNode`s and uses them to
+ * instantiate the local physical operator that's
being tested.
+ * @param expectedAnswer the expected result in a [[Seq]] of [[Row]]s.
+ * @param sortAnswers if true, the answers will be sorted by their
toString representations prior
+ * to being compared.
+ */
+ protected def doCheckAnswer(
+ input: Seq[DataFrame],
+ nodeFunction: Seq[LocalNode] => LocalNode,
+ expectedAnswer: Seq[Row],
+ sortAnswers: Boolean = true): Unit = {
+ LocalNodeTest.checkAnswer(
+ input.map(dataFrameToSeqScanNode), nodeFunction, expectedAnswer,
sortAnswers) match {
+ case Some(errorMessage) => fail(errorMessage)
+ case None =>
+ }
+ }
+
+ protected def dataFrameToSeqScanNode(df: DataFrame): SeqScanNode = {
+ val output = df.queryExecution.sparkPlan.output
+ val converter =
+
CatalystTypeConverters.createToCatalystConverter(StructType.fromAttributes(output))
+ new SeqScanNode(
+ output,
+ df.collect().map(r => converter(r).asInstanceOf[InternalRow]))
--- End diff --
Cool. Fixed it.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
