Skip to content

[SPARK-27421][SQL] Fix filter for int column and value class java.lang.String when pruning partition column #30380

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wangyum wants to merge 3 commits into from
Closed

[SPARK-27421][SQL] Fix filter for int column and value class java.lang.String when pruning partition column #30380

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
585250f
RuntimeException when querying a view on a partitioned parquet table
wangyum Nov 15, 2020
eb95783
Merge remote-tracking branch 'upstream/master' into SPARK-27421
wangyum Nov 16, 2020
9e796ab
Address comments
wangyum Nov 16, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveShim.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -729,7 +729,7 @@ private[client] class Shim_v0_13 extends Shim_v0_12 {
def unapply(expr: Expression): Option[Attribute] = {
expr match {
case attr: Attribute => Some(attr)
case Cast(child @ AtomicType(), dt: AtomicType, _)
case Cast(child @ IntegralType(), dt: IntegralType, _)
if Cast.canUpCast(child.dataType.asInstanceOf[AtomicType], dt) => unapply(child)
case _ => None
}
Expand Down
9 changes: 8 additions & 1 deletion sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HivePartitionFilteringSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.catalyst.catalog._
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.types.{BooleanType, IntegerType, LongType, StructType}
import org.apache.spark.sql.types.{BooleanType, IntegerType, LongType, StringType, StructType}
import org.apache.spark.util.Utils

class HivePartitionFilteringSuite(version: String)
Expand Down Expand Up @@ -290,6 +290,13 @@ class HivePartitionFilteringSuite(version: String)
(20170101 to 20170103, 0 to 4, Seq("ab", "bb")) :: Nil)
}

test("getPartitionsByFilter: chunk in ('ab', 'ba') and ((cast(ds as string)>'20170102')") {
val day = (20170101 to 20170103, 0 to 4, Seq("ab", "ba"))
testMetastorePartitionFiltering(
attr("chunk").in("ab", "ba") && (attr("ds").cast(StringType) > "20170102"),
Copy link
Member

@dongjoon-hyun dongjoon-hyun Nov 15, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What happens for 20170102.1234?

Copy link
Member Author

@wangyum wangyum Nov 16, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It is the same because we didn't pruning it:

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HivePartitionFilteringSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HivePartitionFilteringSuite.scala
index 7e10d49..6b976d9 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HivePartitionFilteringSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HivePartitionFilteringSuite.scala
@@ -28,7 +28,7 @@ import org.apache.spark.sql.catalyst.TableIdentifier
 import org.apache.spark.sql.catalyst.catalog._
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.expressions._
-import org.apache.spark.sql.types.{BooleanType, IntegerType, LongType, StructType}
+import org.apache.spark.sql.types.{BooleanType, IntegerType, LongType, StringType, StructType}
 import org.apache.spark.util.Utils

 class HivePartitionFilteringSuite(version: String)
@@ -272,6 +272,15 @@ class HivePartitionFilteringSuite(version: String)
       day1 :: day2 :: Nil)
   }

+
+  test("getPartitionsByFilter: chunk in ('ab', 'ba') and " +
+    "((cast(ds as string)='20170101') or (cast(ds as string)='20170102'))") {
+    val day = (20170101 to 20170103, 0 to 4, Seq("ab", "ba"))
+    testMetastorePartitionFiltering(attr("chunk").in("ab", "ba") &&
+      (attr("ds").cast(StringType) > "20170102.1234"),
+      day :: Nil)
+  }
+

day :: Nil)
}

private def testMetastorePartitionFiltering(
filterExpr: Expression,
expectedDs: Seq[Int],
Expand Down