maropu commented on a change in pull request #29792: URL: https://github.com/apache/spark/pull/29792#discussion_r502238470
########## File path: sql/core/src/test/scala/org/apache/spark/sql/UnwrapCastInComparisonEndToEndSuite.scala ########## @@ -0,0 +1,165 @@ +/* + * 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 + +import org.apache.spark.sql.catalyst.expressions.IntegralLiteralTestUtils.{negativeInt, positiveInt} +import org.apache.spark.sql.test.SharedSparkSession +import org.apache.spark.sql.types.Decimal + +class UnwrapCastInComparisonEndToEndSuite extends QueryTest with SharedSparkSession { Review comment: Could you add these end-2-end tests in `SQLQueryTestSuite` instead of making a new suite? ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala ########## @@ -35,18 +35,32 @@ import org.apache.spark.sql.types._ * to be optimized away later and pushed down to data sources. * * Currently this only handles cases where: - * 1). `fromType` (of `fromExp`) and `toType` are of integral types (i.e., byte, short, int and - * long) + * 1). `fromType` (of `fromExp`) and `toType` are of numeric types (i.e., short, int, float, + * decimal, etc) * 2). `fromType` can be safely coerced to `toType` without precision loss (e.g., short to int, * int to long, but not long to int) * * If the above conditions are satisfied, the rule checks to see if the literal `value` is within * range `(min, max)`, where `min` and `max` are the minimum and maximum value of `fromType`, - * respectively. If this is true then it means we can safely cast `value` to `fromType` and thus + * respectively. If this is true then it means we may safely cast `value` to `fromType` and thus * able to move the cast to the literal side. That is: * * `cast(fromExp, toType) op value` ==> `fromExp op cast(value, fromType)` * + * Note there are some exceptions to the above: if casting from `value` to `fromType` causes + * rounding up or down, the above conversion will no longer be valid. Instead, the rule does the + * following: + * + * if casting `value` to `fromType` causes rounding up: + * - `cast(fromExp, toType) > value` ==> `fromExp >= cast(value, fromType)` + * - `cast(fromExp, toType) >= value` ==> `fromExp >= cast(value, fromType)` + * - `cast(fromExp, toType) === value` ==> if(isnull(fromExp), null, false) + * - `cast(fromExp, toType) <=> value` ==> false (if `fromExp` is deterministic) + * - `cast(fromExp, toType) <= value` ==> `fromExp < cast(value, fromType)` + * - `cast(fromExp, toType) < value` ==> `fromExp < cast(value, fromType)` + * + * Similarly for the case when casting `value` to `fromType` causes rounding down. Review comment: nit: wrong indent. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UnwrapCastInBinaryComparison.scala ########## @@ -200,25 +248,27 @@ object UnwrapCastInBinaryComparison extends Rule[LogicalPlan] { /** * Check if the input `fromExp` can be safely cast to `toType` without any loss of precision, * i.e., the conversion is injective. Note this only handles the case when both sides are of - * integral type. + * numeric type. */ private def canImplicitlyCast( fromExp: Expression, toType: DataType, literalType: DataType): Boolean = { toType.sameType(literalType) && !fromExp.foldable && - fromExp.dataType.isInstanceOf[IntegralType] && - toType.isInstanceOf[IntegralType] && + fromExp.dataType.isInstanceOf[NumericType] && + toType.isInstanceOf[NumericType] && Cast.canUpCast(fromExp.dataType, toType) } - private def getRange(dt: DataType): (Any, Any) = dt match { - case ByteType => (Byte.MinValue, Byte.MaxValue) - case ShortType => (Short.MinValue, Short.MaxValue) - case IntegerType => (Int.MinValue, Int.MaxValue) - case LongType => (Long.MinValue, Long.MaxValue) - case other => throw new IllegalArgumentException(s"Unsupported type: ${other.catalogString}") + private def getRange(dt: DataType): Option[(Any, Any)] = dt match { + case ByteType => Some((Byte.MinValue, Byte.MaxValue)) + case ShortType => Some((Short.MinValue, Short.MaxValue)) + case IntegerType => Some((Int.MinValue, Int.MaxValue)) + case LongType => Some((Long.MinValue, Long.MaxValue)) + case FloatType => Some((Float.NegativeInfinity, Float.NaN)) + case DoubleType => Some((Double.NegativeInfinity, Double.NaN)) Review comment: Looks it does not have any test for this code path, so could you add some tests for it. (NOTE: I think `byte`, `int`, and `long` are not tested in `UnwrapCastInBinaryComparisonSuite`, too) ---------------------------------------------------------------- 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: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
