spark V2Aggregator 源码

2022-10-20
浏览 (218)

spark V2Aggregator 代码

文件路径：/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/V2Aggregator.scala

/*
 * 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.io.{ByteArrayInputStream, ByteArrayOutputStream, ObjectInputStream, ObjectOutputStream}

import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.{Expression, ImplicitCastInputTypes, UnsafeProjection}
import org.apache.spark.sql.connector.catalog.functions.{AggregateFunction => V2AggregateFunction}
import org.apache.spark.sql.types.{AbstractDataType, DataType}

case class V2Aggregator[BUF <: java.io.Serializable, OUT](
    aggrFunc: V2AggregateFunction[BUF, OUT],
    children: Seq[Expression],
    mutableAggBufferOffset: Int = 0,
    inputAggBufferOffset: Int = 0)
  extends TypedImperativeAggregate[BUF] with ImplicitCastInputTypes {

  private[this] lazy val inputProjection = UnsafeProjection.create(children)

  override def nullable: Boolean = aggrFunc.isResultNullable
  override def dataType: DataType = aggrFunc.resultType()
  override def inputTypes: Seq[AbstractDataType] = aggrFunc.inputTypes().toSeq
  override def createAggregationBuffer(): BUF = aggrFunc.newAggregationState()

  override def update(buffer: BUF, input: InternalRow): BUF = {
    aggrFunc.update(buffer, inputProjection(input))
  }

  override def merge(buffer: BUF, input: BUF): BUF = aggrFunc.merge(buffer, input)

  override def eval(buffer: BUF): Any = {
    aggrFunc.produceResult(buffer)
  }

  override def serialize(buffer: BUF): Array[Byte] = {
    val bos = new ByteArrayOutputStream()
    val out = new ObjectOutputStream(bos)
    out.writeObject(buffer)
    out.close()
    bos.toByteArray
  }

  override def deserialize(bytes: Array[Byte]): BUF = {
    val in = new ObjectInputStream(new ByteArrayInputStream(bytes))
    in.readObject().asInstanceOf[BUF]
  }

  def withNewMutableAggBufferOffset(newMutableAggBufferOffset: Int): V2Aggregator[BUF, OUT] =
    copy(mutableAggBufferOffset = newMutableAggBufferOffset)

  def withNewInputAggBufferOffset(newInputAggBufferOffset: Int): V2Aggregator[BUF, OUT] =
    copy(inputAggBufferOffset = newInputAggBufferOffset)

  override protected def withNewChildrenInternal(newChildren: IndexedSeq[Expression]): Expression =
    copy(children = newChildren)
}

相关信息

spark 源码目录

相关文章

spark AnyValue 源码

spark ApproxCountDistinctForIntervals 源码

spark ApproximatePercentile 源码

spark Average 源码

spark BloomFilterAggregate 源码

spark CentralMomentAgg 源码

spark Corr 源码

spark Count 源码

spark CountIf 源码

spark CountMinSketchAgg 源码

0 赞

所属分类： 前端技术
本文标签：
版权声明： 原创文章如转载，请注明本文链接: https://www.seaxiang.com/blog/ea950cd414fb421780e2c120ce287f5a

热门推荐

1、直接访问google.com
2、 - 优质文章
3、 gate.io
4、 harmony 鸿蒙hdc使用指导
5、 harmony 鸿蒙ArkUI组件（ArkTS）开发常见问题
6、 harmony 鸿蒙初识ArkTS语言
7、 golang
8、 flink kafka connector scan.startup.mode 的几个选项
9、 openharmony
10、 Vue中input框自动聚焦

Loading...