yabola commented on code in PR #39687: URL: https://github.com/apache/spark/pull/39687#discussion_r1096491741
########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/InternalRowComparableWrapper.scala: ########## @@ -0,0 +1,88 @@ +/* + * 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.util + +import scala.collection.mutable + +import org.apache.spark.SparkException +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Expression, Murmur3HashFunction, RowOrdering} +import org.apache.spark.sql.catalyst.plans.physical.KeyGroupedPartitioning +import org.apache.spark.sql.connector.read.{HasPartitionKey, InputPartition} +import org.apache.spark.sql.types.{DataType, StructField, StructType} + +/** + * Wraps the [[InternalRow]] with the corresponding [[DataType]] to make it comparable with + * the values in [[InternalRow]]. + * It uses Spark's internal murmur hash to compute hash code from an row, and uses [[RowOrdering]] + * to perform equality checks. + * + * @param dataTypes the data types for the row + */ +class InternalRowComparableWrapper(val row: InternalRow, val dataTypes: Seq[DataType]) { + + private val structType = StructType(dataTypes.map(t => StructField("f", t))) + private val ordering = RowOrdering.createNaturalAscendingOrdering(dataTypes) + + override def hashCode(): Int = Murmur3HashFunction.hash(row, structType, 42L).toInt + + override def equals(other: Any): Boolean = { + if (!other.isInstanceOf[InternalRowComparableWrapper]) { + return false + } + val otherWrapper = other.asInstanceOf[InternalRowComparableWrapper] + if (!otherWrapper.dataTypes.equals(this.dataTypes)) { + return false + } + ordering.compare(row, otherWrapper.row) == 0 + } +} + +object InternalRowComparableWrapper { + + def apply( + partition: InputPartition, + partitionExpression: Seq[Expression]): InternalRowComparableWrapper = { + if (!partition.isInstanceOf[HasPartitionKey]) { Review Comment: Thanks , done -- 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. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
