[SPARK-34436][SQL] DPP support LIKE ANY/ALL expression

### What changes were proposed in this pull request? This pr make DPP support LIKE ANY/ALL expression: ```sql SELECT date_id, product_id FROM fact_sk f JOIN dim_store s ON f.store_id = s.store_id WHERE s.country LIKE ANY ('%D%E%', '%A%B%') ``` ### Why are the changes needed? Improve query performance. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Unit test. Closes apache#31563 from wangyum/SPARK-34436. Lead-authored-by: Yuming Wang <[email protected]> Co-authored-by: Yuming Wang <[email protected]> Signed-off-by: Wenchen Fan <[email protected]> (cherry picked from commit 4a3200b) Signed-off-by: Wenchen Fan <[email protected]>
fishcus · Jan 12, 2022 · eee08d7 · eee08d7
1 parent 6003f7c
commit eee08d7
Show file tree

Hide file tree

Showing 2 changed files with 21 additions and 0 deletions.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PartitionPruning.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PartitionPruning.scala
@@ -163,6 +163,7 @@ object PartitionPruning extends Rule[LogicalPlan] with PredicateHelper {
     case _: BinaryComparison => true
     case _: In | _: InSet => true
     case _: StringPredicate => true
+    case _: MultiLikeBase => true
     case _ => false
   }
 

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DynamicPartitionPruningSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DynamicPartitionPruningSuite.scala
@@ -1361,6 +1361,26 @@ abstract class DynamicPartitionPruningSuiteBase
       checkAnswer(df, Nil)
     }
   }
+
+  test("SPARK-34436: DPP support LIKE ANY/ALL expression") {
+    withSQLConf(SQLConf.DYNAMIC_PARTITION_PRUNING_ENABLED.key -> "true") {
+      val df = sql(
+        """
+          |SELECT date_id, product_id FROM fact_sk f
+          |JOIN dim_store s
+          |ON f.store_id = s.store_id WHERE s.country LIKE ANY ('%D%E%', '%A%B%')
+        """.stripMargin)
+
+      checkPartitionPruningPredicate(df, false, true)
+
+      checkAnswer(df,
+        Row(1030, 2) ::
+        Row(1040, 2) ::
+        Row(1050, 2) ::
+        Row(1060, 2) :: Nil
+      )
+    }
+  }
 }
 
 class DynamicPartitionPruningSuiteAEOff extends DynamicPartitionPruningSuiteBase {