Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/17148#discussion_r104492007 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala --- @@ -249,17 +265,19 @@ case class FilterEstimation(plan: Filter, catalystConf: CatalystConf) extends Lo attr: Attribute, literal: Literal, update: Boolean): Option[Double] = { + if (!colStatsMap.contains(attr)) { + logDebug("[CBO] No statistics for " + attr) + return None + } + attr.dataType match { - case _: NumericType | DateType | TimestampType => + case _: NumericType | DateType | TimestampType | BooleanType => evaluateBinaryForNumeric(op, attr, literal, update) case StringType | BinaryType => // TODO: It is difficult to support other binary comparisons for String/Binary // type without min/max and advanced statistics like histogram. logDebug("[CBO] No range comparison statistics for String/Binary type " + attr) None - case _ => --- End diff -- we can't remove this, we may still hit unsupported type like array, map, etc.
--- 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