[GitHub] [spark] dongjoon-hyun commented on a diff in pull request #35789: [SPARK-32268][SQL] Row-level Runtime Filtering

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

dongjoon-hyun commented on code in PR #35789:
URL: https://github.com/apache/spark/pull/35789#discussion_r889832491


##########
sql/core/src/test/scala/org/apache/spark/sql/BloomFilterAggregateQuerySuite.scala:
##########
@@ -0,0 +1,215 @@
+/*
+ * 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
+
+import org.apache.spark.sql.catalyst.FunctionIdentifier
+import org.apache.spark.sql.catalyst.analysis.FunctionRegistry
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.expressions.aggregate.BloomFilterAggregate
+import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec
+import org.apache.spark.sql.execution.aggregate.BaseAggregateExec
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.test.SharedSparkSession
+
+/**
+ * Query tests for the Bloom filter aggregate and filter function.
+ */
+class BloomFilterAggregateQuerySuite extends QueryTest with SharedSparkSession {
+  import testImplicits._
+
+  val funcId_bloom_filter_agg = new FunctionIdentifier("bloom_filter_agg")
+  val funcId_might_contain = new FunctionIdentifier("might_contain")
+
+  // Register 'bloom_filter_agg' to builtin.
+  FunctionRegistry.builtin.registerFunction(funcId_bloom_filter_agg,
+    new ExpressionInfo(classOf[BloomFilterAggregate].getName, "bloom_filter_agg"),
+    (children: Seq[Expression]) => children.size match {
+      case 1 => new BloomFilterAggregate(children.head)
+      case 2 => new BloomFilterAggregate(children.head, children(1))
+      case 3 => new BloomFilterAggregate(children.head, children(1), children(2))
+    })
+
+  // Register 'might_contain' to builtin.
+  FunctionRegistry.builtin.registerFunction(funcId_might_contain,
+    new ExpressionInfo(classOf[BloomFilterMightContain].getName, "might_contain"),
+    (children: Seq[Expression]) => BloomFilterMightContain(children.head, children(1)))
+
+  override def afterAll(): Unit = {
+    FunctionRegistry.builtin.dropFunction(funcId_bloom_filter_agg)
+    FunctionRegistry.builtin.dropFunction(funcId_might_contain)
+    super.afterAll()
+  }
+
+  test("Test bloom_filter_agg and might_contain") {

Review Comment:
   During Apache Spark 3.3.0 RC5 testing, I hit a failure of this test case and filed a JIRA
   - https://issues.apache.org/jira/browse/SPARK-39386



-- 
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.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

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