Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/16395#discussion_r95523768 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/Range.scala --- @@ -0,0 +1,75 @@ +/* + * 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.math.{BigDecimal => JDecimal} +import java.sql.{Date, Timestamp} + +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst.util.DateTimeUtils +import org.apache.spark.sql.types.{BooleanType, DateType, TimestampType, _} + + +/** Value range of a column. */ +trait Range + +/** For simplicity we use decimal to unify operations of numeric ranges. */ +case class NumericRange(min: JDecimal, max: JDecimal) extends Range + +/** + * This version of Spark does not have min/max for binary/string types, we define their default + * behaviors by this class. + */ +class DefaultRange extends Range + +/** This is for columns with only null values. */ +class NullRange extends Range + +object Range { + def apply(min: Option[Any], max: Option[Any], dataType: DataType): Range = dataType match { + case StringType | BinaryType => new DefaultRange() + case _ if min.isEmpty || max.isEmpty => new NullRange() + case _ => toNumericRange(min.get, max.get, dataType) + } + + /** + * For simplicity we use decimal to unify operations of numeric types, the two methods below + * are the contract of conversion. + */ + private def toNumericRange(min: Any, max: Any, dataType: DataType): NumericRange = { + dataType match { + case _: NumericType => + NumericRange(new JDecimal(min.toString), new JDecimal(max.toString)) + case BooleanType => + val min1 = if (min.asInstanceOf[Boolean]) 1 else 0 + val max1 = if (max.asInstanceOf[Boolean]) 1 else 0 + NumericRange(new JDecimal(min1), new JDecimal(max1)) + case DateType => + val min1 = DateTimeUtils.fromJavaDate(min.asInstanceOf[Date]) + val max1 = DateTimeUtils.fromJavaDate(max.asInstanceOf[Date]) + NumericRange(new JDecimal(min1), new JDecimal(max1)) + case TimestampType => + val min1 = DateTimeUtils.fromJavaTimestamp(min.asInstanceOf[Timestamp]) + val max1 = DateTimeUtils.fromJavaTimestamp(max.asInstanceOf[Timestamp]) + NumericRange(new JDecimal(min1), new JDecimal(max1)) + case _ => + throw new AnalysisException(s"Type $dataType is not castable to numeric in estimation.") --- End diff -- when we get here, is it an error in spark? if yes, we should probably throw UnsupportedOperationEception
--- 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