Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/22535#discussion_r219948634
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala
---
@@ -437,53 +436,63 @@ object DataSourceStrategy {
* @return a `Some[Filter]` if the input [[Expression]] is convertible,
otherwise a `None`.
*/
protected[sql] def translateFilter(predicate: Expression):
Option[Filter] = {
+// Recursively try to find an attribute name in top level or struct
that can be pushed down.
+def attrName(e: Expression): Option[String] = e match {
+ // In Spark and many data sources such as parquet, dots are used as
a column path delimiter;
+ // thus, we don't push down such filters.
+ case a: Attribute if !a.name.contains(".") =>
+Some(a.name)
+ case s: GetStructField if
!s.childSchema(s.ordinal).name.contains(".") =>
+attrName(s.child).map(_ + s".${s.childSchema(s.ordinal).name}")
+ case _ =>
+None
+}
+
predicate match {
- case expressions.EqualTo(a: Attribute, Literal(v, t)) =>
-Some(sources.EqualTo(a.name, convertToScala(v, t)))
- case expressions.EqualTo(Literal(v, t), a: Attribute) =>
-Some(sources.EqualTo(a.name, convertToScala(v, t)))
-
- case expressions.EqualNullSafe(a: Attribute, Literal(v, t)) =>
-Some(sources.EqualNullSafe(a.name, convertToScala(v, t)))
- case expressions.EqualNullSafe(Literal(v, t), a: Attribute) =>
-Some(sources.EqualNullSafe(a.name, convertToScala(v, t)))
-
- case expressions.GreaterThan(a: Attribute, Literal(v, t)) =>
-Some(sources.GreaterThan(a.name, convertToScala(v, t)))
- case expressions.GreaterThan(Literal(v, t), a: Attribute) =>
-Some(sources.LessThan(a.name, convertToScala(v, t)))
-
- case expressions.LessThan(a: Attribute, Literal(v, t)) =>
-Some(sources.LessThan(a.name, convertToScala(v, t)))
- case expressions.LessThan(Literal(v, t), a: Attribute) =>
-Some(sources.GreaterThan(a.name, convertToScala(v, t)))
-
- case expressions.GreaterThanOrEqual(a: Attribute, Literal(v, t)) =>
-Some(sources.GreaterThanOrEqual(a.name, convertToScala(v, t)))
- case expressions.GreaterThanOrEqual(Literal(v, t), a: Attribute) =>
-Some(sources.LessThanOrEqual(a.name, convertToScala(v, t)))
-
- case expressions.LessThanOrEqual(a: Attribute, Literal(v, t)) =>
-Some(sources.LessThanOrEqual(a.name, convertToScala(v, t)))
- case expressions.LessThanOrEqual(Literal(v, t), a: Attribute) =>
-Some(sources.GreaterThanOrEqual(a.name, convertToScala(v, t)))
-
- case expressions.InSet(a: Attribute, set) =>
-val toScala =
CatalystTypeConverters.createToScalaConverter(a.dataType)
-Some(sources.In(a.name, set.toArray.map(toScala)))
+ case expressions.EqualTo(e: Expression, Literal(v, t)) =>
--- End diff --
This PR will be a good performance improvement for Spark 2.5.0.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
