[GitHub] [spark] c21 commented on a change in pull request #29804: [SPARK-32859][SQL] Introduce physical rule to decide bucketing dynamically

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

c21 commented on a change in pull request #29804:
URL: https://github.com/apache/spark/pull/29804#discussion_r497898501



##########
File path: sql/core/src/test/scala/org/apache/spark/sql/sources/DisableUnnecessaryBucketedScanSuite.scala
##########
@@ -0,0 +1,221 @@
+/*
+ * 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.sources
+
+import org.apache.spark.sql.QueryTest
+import org.apache.spark.sql.execution.FileSourceScanExec
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.internal.StaticSQLConf.CATALOG_IMPLEMENTATION
+import org.apache.spark.sql.test.{SharedSparkSession, SQLTestUtils}
+
+class DisableUnnecessaryBucketedScanWithoutHiveSupportSuite
+  extends DisableUnnecessaryBucketedScanSuite
+  with SharedSparkSession {
+
+  protected override def beforeAll(): Unit = {
+    super.beforeAll()
+    assert(spark.sparkContext.conf.get(CATALOG_IMPLEMENTATION) == "in-memory")
+  }
+}
+
+abstract class DisableUnnecessaryBucketedScanSuite extends QueryTest with SQLTestUtils {
+  import testImplicits._
+
+  private lazy val df1 =
+    (0 until 50).map(i => (i % 5, i % 13, i.toString)).toDF("i", "j", "k").as("df1")
+  private lazy val df2 =
+    (0 until 50).map(i => (i % 7, i % 11, i.toString)).toDF("i", "j", "k").as("df2")
+
+  private def checkDisableBucketedScan(
+      query: String,
+      expectedNumScanWithAutoScanEnabled: Int,
+      expectedNumScanWithAutoScanDisabled: Int): Unit = {
+
+    def checkNumBucketedScan(query: String, expectedNumBucketedScan: Int): Unit = {
+      val plan = sql(query).queryExecution.executedPlan
+      val bucketedScan = plan.collect { case s: FileSourceScanExec if s.bucketedScan => s }
+      assert(bucketedScan.length == expectedNumBucketedScan)
+    }
+
+    withSQLConf(SQLConf.AUTO_BUCKETED_SCAN_ENABLED.key -> "true") {
+      checkNumBucketedScan(query, expectedNumScanWithAutoScanEnabled)
+      val result = sql(query).collect()
+
+      withSQLConf(SQLConf.AUTO_BUCKETED_SCAN_ENABLED.key -> "false") {
+        checkNumBucketedScan(query, expectedNumScanWithAutoScanDisabled)
+        checkAnswer(sql(query), result)
+      }
+    }
+  }
+
+  test("SPARK-32859: disable unnecessary bucketed table scan - basic test") {
+    withTable("t1", "t2", "t3", "t4") {

Review comment:
       @viirya - yes, this is typo, will remove.




----------------------------------------------------------------
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: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org