Github user ron8hu commented on a diff in the pull request: https://github.com/apache/spark/pull/15637#discussion_r86411252 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/MapAggregate.scala --- @@ -0,0 +1,332 @@ +/* + * 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.expressions.aggregate + +import java.nio.ByteBuffer + +import scala.collection.immutable.TreeMap +import scala.collection.mutable + +import com.google.common.primitives.{Doubles, Ints, Longs} + +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.analysis.TypeCheckResult +import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{TypeCheckFailure, TypeCheckSuccess} +import org.apache.spark.sql.catalyst.expressions.{Expression, ExpressionDescription} +import org.apache.spark.sql.catalyst.util.ArrayBasedMapData +import org.apache.spark.sql.types.{DataType, _} +import org.apache.spark.unsafe.types.UTF8String + +/** + * The MapAggregate function for a column returns: + * 1. null if no non-null value exists. + * 2. (distinct non-null value, frequency) pairs of equi-width histogram when the number of + * distinct non-null values is less than or equal to the specified maximum number of bins. + * 3. an empty map otherwise. + * + * @param child child expression that can produce column value with `child.eval(inputRow)` + * @param numBinsExpression The maximum number of bins. + */ +@ExpressionDescription( + usage = + """ + _FUNC_(col, numBins) - Returns 1. null if no non-null value exists. + 2. (distinct non-null value, frequency) pairs of equi-width histogram when the number of + distinct non-null values is less than or equal to the specified maximum number of bins. + 3. an empty map otherwise. + """) +case class MapAggregate( + child: Expression, + numBinsExpression: Expression, + override val mutableAggBufferOffset: Int, + override val inputAggBufferOffset: Int) extends TypedImperativeAggregate[MapDigest] { + + def this(child: Expression, numBinsExpression: Expression) = { + this(child, numBinsExpression, 0, 0) + } + + // Mark as lazy so that numBinsExpression is not evaluated during tree transformation. + private lazy val numBins: Int = numBinsExpression.eval().asInstanceOf[Int] + + override def inputTypes: Seq[AbstractDataType] = { + Seq(TypeCollection(NumericType, TimestampType, DateType, StringType), IntegerType) --- End diff -- In today's software development environment, speed is an important factor. One of the agile development methodology principles is to avoid over design. The over design can slow down the development and divert an engineer's attention on the unimportant cases. Since we develop MapAggregate.scala for CBO, let's focus on CBO's need. There is no need to develop NDV and histogram for binary data type. For Boolean data type, we already have number of trues and number of falses defined in ColumnStat. I think wxhfy's code is doing fine here.
--- 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