dilipbiswal commented on a change in pull request #24759: [SPARK-27395][SQL] Improve EXPLAIN command URL: https://github.com/apache/spark/pull/24759#discussion_r316448199
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/ExplainUtils.scala ########## @@ -0,0 +1,237 @@ +/* + * 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.execution + +import scala.collection.mutable +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst.expressions.{Expression, PlanExpression} +import org.apache.spark.sql.catalyst.plans.QueryPlan +import org.apache.spark.sql.catalyst.trees.TreeNodeTag + +object ExplainUtils { + /** + * Given a input physical plan, performs the following tasks. + * 1. Computes the operator id for current operator and records it in the operaror + * by setting a tag. + * 2. Computes the whole stage codegen id for current operator and records it in the + * operator by setting a tag. + * 3. Generate the two part explain output for this plan. + * 1. First part explains the operator tree with each operator tagged with an unique + * identifier. + * 2. Second part explans each operator in a verbose manner. + * + * Note : This function skips over subqueries. They are handled by its caller. + * + * @param plan Input query plan to process + * @param append function used to append the explain output + * @startOperationID The start value of operation id. The subsequent operations will + * be assigned higher value. + * + * @return The last generated operation id for this input plan. This is to ensure we + * always assign incrementing unique id to each operator. + * + */ + private def processPlanSkippingSubqueries[T <: QueryPlan[T]]( + plan: => QueryPlan[T], + append: String => Unit, + startOperatorID: Int): Int = { + + // ReusedSubqueryExecs are skipped over + if (plan.isInstanceOf[BaseSubqueryExec]) { + return startOperatorID + } + + val operationIDs = new mutable.ArrayBuffer[(Int, QueryPlan[_])]() + var currentOperatorID = startOperatorID + try { + currentOperatorID = generateOperatorIDs(plan, currentOperatorID, operationIDs) + generateWholeStageCodegenIds(plan) + + QueryPlan.append( + plan, + append, + verbose = false, + addSuffix = false, + printOperatorId = true) + + append("\n") + var i: Integer = 0 + for ((opId, curPlan) <- operationIDs) { + append(curPlan.verboseStringWithOperatorId()) + } + } catch { + case e: AnalysisException => append(e.toString) + } + currentOperatorID + } + + /** + * Given a input physical plan, performs the following tasks. + * 1. Generates the explain output for the input plan excluding the subquery plans. + * 2. Generates the explain output for each subquery referenced in the plan. + */ + def processPlan[T <: QueryPlan[T]]( + plan: => QueryPlan[T], + append: String => Unit): Unit = { + try { + val subqueries = ArrayBuffer.empty[(SparkPlan, Expression, SparkPlan)] + var currentOperatorID = 0 + currentOperatorID = processPlanSkippingSubqueries(plan, append, currentOperatorID) + getSubqueries(plan, subqueries) + var i = 0 + + // Process all the subqueries in the plan. + for (sub <- subqueries) { + if (i == 0) { + append("\n===== Subqueries =====\n\n") + } + i = i + 1 Review comment: @cloud-fan actually i need that variable to print the subquery number ? I print like : ``` subquery:1 .... subquery:2 .... ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org