Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/20851#discussion_r176317120
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilterSuite.scala
---
@@ -313,6 +315,48 @@ class ParquetFilterSuite extends QueryTest with
ParquetTest with SharedSQLContex
}
}
+ test("filter pushdown - date") {
+ implicit class StringToDate(s: String) {
+ def date: Date = Date.valueOf(s)
+ }
+
+ val data = Seq("2018-03-18", "2018-03-19", "2018-03-20", "2018-03-21")
+
+ withParquetDataFrame(data.map(i => Tuple1(i.date))) { implicit df =>
+ checkFilterPredicate('_1.isNull, classOf[Eq[_]], Seq.empty[Row])
+ checkFilterPredicate('_1.isNotNull, classOf[NotEq[_]], data.map(i =>
Row.apply(i.date)))
+
+ checkFilterPredicate('_1 === "2018-03-18".date, classOf[Eq[_]],
"2018-03-18".date)
+ checkFilterPredicate('_1 <=> "2018-03-18".date, classOf[Eq[_]],
"2018-03-18".date)
+ checkFilterPredicate('_1 =!= "2018-03-18".date, classOf[NotEq[_]],
+ Seq("2018-03-19", "2018-03-20", "2018-03-21").map(i =>
Row.apply(i.date)))
+
+ checkFilterPredicate('_1 < "2018-03-19".date, classOf[Lt[_]],
"2018-03-18".date)
+ checkFilterPredicate('_1 > "2018-03-20".date, classOf[Gt[_]],
"2018-03-21".date)
+ checkFilterPredicate('_1 <= "2018-03-18".date, classOf[LtEq[_]],
"2018-03-18".date)
+ checkFilterPredicate('_1 >= "2018-03-21".date, classOf[GtEq[_]],
"2018-03-21".date)
+
+ checkFilterPredicate(
+ Literal("2018-03-18".date) === '_1, classOf[Eq[_]],
"2018-03-18".date)
+ checkFilterPredicate(
+ Literal("2018-03-18".date) <=> '_1, classOf[Eq[_]],
"2018-03-18".date)
+ checkFilterPredicate(
+ Literal("2018-03-19".date) > '_1, classOf[Lt[_]],
"2018-03-18".date)
+ checkFilterPredicate(
+ Literal("2018-03-20".date) < '_1, classOf[Gt[_]],
"2018-03-21".date)
+ checkFilterPredicate(
+ Literal("2018-03-18".date) >= '_1, classOf[LtEq[_]],
"2018-03-18".date)
+ checkFilterPredicate(
+ Literal("2018-03-21".date) <= '_1, classOf[GtEq[_]],
"2018-03-21".date)
+
+ checkFilterPredicate(!('_1 < "2018-03-21".date), classOf[GtEq[_]],
"2018-03-21".date)
+ checkFilterPredicate(
+ '_1 < "2018-03-19".date || '_1 > "2018-03-20".date,
+ classOf[Operators.Or],
+ Seq(Row("2018-03-18".date), Row("2018-03-21".date)))
+ }
--- End diff --
This is different from what @HyukjinKwon gave you. :)
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
