Github user wzhfy commented on a diff in the pull request: https://github.com/apache/spark/pull/15090#discussion_r79329457 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/Statistics.scala --- @@ -32,19 +34,70 @@ package org.apache.spark.sql.catalyst.plans.logical * @param sizeInBytes Physical size in bytes. For leaf operators this defaults to 1, otherwise it * defaults to the product of children's `sizeInBytes`. * @param rowCount Estimated number of rows. + * @param basicColStats Basic column-level statistics. * @param isBroadcastable If true, output is small enough to be used in a broadcast join. */ case class Statistics( sizeInBytes: BigInt, rowCount: Option[BigInt] = None, + basicColStats: Map[String, BasicColStats] = Map.empty, isBroadcastable: Boolean = false) { + override def toString: String = "Statistics(" + simpleString + ")" /** Readable string representation for the Statistics. */ def simpleString: String = { Seq(s"sizeInBytes=$sizeInBytes", if (rowCount.isDefined) s"rowCount=${rowCount.get}" else "", + if (basicColStats.nonEmpty) s"basicColStats=$basicColStats" else "", s"isBroadcastable=$isBroadcastable" - ).filter(_.nonEmpty).mkString("", ", ", "") + ).filter(_.nonEmpty).mkString(", ") + } +} + +case class BasicColStats( --- End diff -- @viirya thanks for the advice.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org