Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/20935#discussion_r178444386
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/columnar/ColumnStatsSuite.scala
---
@@ -103,4 +119,109 @@ class ColumnStatsSuite extends SparkFunSuite {
}
}
}
+
+ def testArrayColumnStats(
+ dataType: DataType, orderable: Boolean, initialStatistics:
Array[Any]): Unit = {
+ val columnType = ColumnType(dataType)
+
+ test(s"${dataType.typeName}: empty") {
+ val objectStats = new ArrayColumnStats(dataType)
+ objectStats.collectedStatistics.zip(initialStatistics).foreach {
+ case (actual, expected) => assert(actual === expected)
+ }
+ }
+
+ test(s"${dataType.typeName}: non-empty") {
+ import org.apache.spark.sql.execution.columnar.ColumnarTestUtils._
+ val objectStats = new ArrayColumnStats(dataType)
+ val rows = Seq.fill(10)(makeRandomRow(columnType)) ++
Seq.fill(10)(makeNullRow(1))
--- End diff --
Because we don't reuse the unsafe array/row here, we don't actually test on
the copying in corresponding column statistics, can we have the test data
reusing the unsafe structures to test array and struct column statistics?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
