Github user ron8hu commented on a diff in the pull request: https://github.com/apache/spark/pull/16395#discussion_r100941831 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala --- @@ -0,0 +1,623 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.catalyst.plans.logical.statsEstimation + +import java.sql.{Date, Timestamp} + +import scala.collection.immutable.{HashSet, Map} +import scala.collection.mutable + +import org.apache.spark.internal.Logging +import org.apache.spark.sql.catalyst.CatalystConf +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.plans.logical._ +import org.apache.spark.sql.catalyst.util.DateTimeUtils +import org.apache.spark.sql.types._ +import org.apache.spark.unsafe.types.UTF8String + +/** + * @param plan a LogicalPlan node that must be an instance of Filter + * @param catalystConf a configuration showing if CBO is enabled + */ +case class FilterEstimation(plan: Filter, catalystConf: CatalystConf) extends Logging { + + /** + * We use a mutable colStats because we need to update the corresponding ColumnStat + * for a column after we apply a predicate condition. For example, column c has + * [min, max] value as [0, 100]. In a range condition such as (c > 40 AND c <= 50), + * we need to set the column's [min, max] value to [40, 100] after we evaluate the + * first condition c > 40. We need to set the column's [min, max] value to [40, 50] + * after we evaluate the second condition c <= 50. + */ + private var mutableColStats: mutable.Map[ExprId, ColumnStat] = mutable.Map.empty + + /** + * Returns an option of Statistics for a Filter logical plan node. + * For a given compound expression condition, this method computes filter selectivity + * (or the percentage of rows meeting the filter condition), which + * is used to compute row count, size in bytes, and the updated statistics after a given + * predicated is applied. + * + * @return Option[Statistics] When there is no statistics collected, it returns None. + */ + def estimate: Option[Statistics] = { + val stats: Statistics = plan.child.stats(catalystConf) --- End diff -- Here we mean the Statistics of the current node. We first copy from its child node's statistics and then we modify it to become the output statistics of the current Filter node. I can add comments to make it clear.
--- 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