Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/15047#discussion_r78331887 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveHash.scala --- @@ -0,0 +1,145 @@ +/* + * 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.hive + +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.util.{ArrayData, MapData} +import org.apache.spark.sql.types._ +import org.apache.spark.unsafe.Platform +import org.apache.spark.unsafe.types.UTF8String + +/** + * Simulates Hive's hashing function at + * org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils#hashcode() in Hive + * + * We should use this hash function for both shuffle and bucket of Hive tables, so that + * we can guarantee shuffle and bucketing have same data distribution + * + * TODO: Support Decimal and date related types + */ +@ExpressionDescription( + usage = "_FUNC_(a1, a2, ...) - Returns a hash value of the arguments.") +case class HiveHash(children: Seq[Expression], seed: Int) extends HashExpression[Int] { + def this(arguments: Seq[Expression]) = this(arguments, 42) + + override def dataType: DataType = IntegerType + + override def prettyName: String = "hive-hash" + + override protected def hasherClassName: String = classOf[HiveHash].getName + + override protected def computeHash(value: Any, dataType: DataType, seed: Int): Int = { + HiveHashFunction.hash(value, dataType, seed).toInt + } +} + +object HiveHashFunction extends InterpretedHashFunction { + override protected def hashInt(i: Int, seed: Long): Long = { + HiveHasher.hashInt(i, seed.toInt) + } + + override protected def hashLong(l: Long, seed: Long): Long = { + HiveHasher.hashLong(l, seed.toInt) + } + + override protected def hashUnsafeBytes(base: AnyRef, offset: Long, len: Int, seed: Long): Long = { + HiveHasher.hashUnsafeBytes(base, offset, len, seed.toInt) + } + + override def hash(value: Any, dataType: DataType, seed: Long): Long = { + value match { + case s: UTF8String => + val bytes = s.getBytes + var result: Int = 0 + var i = 0 + while (i < bytes.length) { + result = (result * 31) + bytes(i).toInt + i += 1 + } + result + + + case array: ArrayData => + val elementType = dataType match { + case udt: UserDefinedType[_] => udt.sqlType.asInstanceOf[ArrayType].elementType --- End diff -- the caller of `hash` guarantees the value matches the data type. So in this branch, if the value is `ArrayData`, the data type must be `ArrayType` or UDT of `ArrayType`
--- 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