Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/22036#discussion_r209481430 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala --- @@ -204,6 +204,24 @@ class StatisticsCollectionSuite extends StatisticsCollectionTestBase with Shared } } + test("SPARK-25028: column stats collection for null partitioning columns") { + val table = "analyze_partition_with_null" + withTempDir { dir => + withTable(table) { + sql(s""" + |CREATE TABLE $table (name string, value string) + |USING PARQUET + |PARTITIONED BY (name) + |LOCATION '${dir.toURI}'""".stripMargin) + val df = Seq(("a", null), ("b", null)).toDF("value", "name") --- End diff -- when creating the table, we can put partition column at the end, to avoid this confusion.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org