Github user hvanhovell commented on a diff in the pull request:
https://github.com/apache/spark/pull/13494#discussion_r70252043
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/OptimizeMetadataOnlyQuerySuite.scala
---
@@ -0,0 +1,153 @@
+/*
+ * 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.sql._
+import org.apache.spark.sql.catalyst.plans.logical.LocalRelation
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.test.SharedSQLContext
+
+class OptimizeMetadataOnlyQuerySuite extends QueryTest with
SharedSQLContext {
+ import testImplicits._
+
+ override def beforeAll(): Unit = {
+ super.beforeAll()
+ val data = (1 to 10).map(i => (i, s"data-$i", i % 2, if ((i % 2) == 0)
"even" else "odd"))
+ .toDF("col1", "col2", "partcol1", "partcol2")
+ data.write.partitionBy("partcol1",
"partcol2").mode("append").saveAsTable("srcpart")
+ }
+
+ override protected def afterAll(): Unit = {
+ try {
+ sql("DROP TABLE IF EXISTS srcpart")
+ } finally {
+ super.afterAll()
+ }
+ }
+
+ private def assertMetadataOnlyQuery(df: DataFrame): Unit = {
+ val localRelations = df.queryExecution.optimizedPlan.collect {
+ case l @ LocalRelation(_, _) => l
+ }
+ assert(localRelations.size == 1)
+ }
+
+ private def assertNotMetadataOnlyQuery(df: DataFrame): Unit = {
+ val localRelations = df.queryExecution.optimizedPlan.collect {
+ case l @ LocalRelation(_, _) => l
+ }
+ assert(localRelations.size == 0)
+ }
+
+ test("OptimizeMetadataOnlyQuery test: aggregate expression is partition
columns") {
--- End diff --
That is not what I mean. I all for thorough testing, however the structure
the same everywhere. You could generalize this (and improve readability), e.g.:
```scala
def testMetadataOnly(name: String, sql: String*): Unit = {
test(name) {
withSQLConf(SQLConf.OPTIMIZER_METADATA_ONLY.key -> "true") {
sqls.foreach(assertMetadataOnlyQuery(sql(_)))
}
withSQLConf(SQLConf.OPTIMIZER_METADATA_ONLY.key -> "false") {
sqls.foreach(assertNotMetadataOnlyQuery(sql(_)))
}
}
}
testMetadataOnly(
"OptimizeMetadataOnlyQuery test: aggregate expression is partition
columns",
"select partcol1 from srcpart group by partcol1",
"select partcol2 from srcpart where partcol1 = 0 group by partcol2")
```
---
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]
