spark AddPartitionExec 源码

2022-10-20
浏览 (215)

spark AddPartitionExec 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/AddPartitionExec.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.execution.datasources.v2

import scala.collection.JavaConverters._

import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.analysis.{PartitionsAlreadyExistException, ResolvedPartitionSpec}
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.connector.catalog.{SupportsAtomicPartitionManagement, SupportsPartitionManagement}
import org.apache.spark.sql.errors.QueryExecutionErrors

/**
 * Physical plan node for adding partitions of table.
 */
case class AddPartitionExec(
    table: SupportsPartitionManagement,
    partSpecs: Seq[ResolvedPartitionSpec],
    ignoreIfExists: Boolean,
    refreshCache: () => Unit) extends LeafV2CommandExec {
  import DataSourceV2Implicits._

  override def output: Seq[Attribute] = Seq.empty

  override protected def run(): Seq[InternalRow] = {
    val (existsParts, notExistsParts) =
      partSpecs.partition(p => table.partitionExists(p.ident))

    if (existsParts.nonEmpty && !ignoreIfExists) {
      throw new PartitionsAlreadyExistException(
        table.name(), existsParts.map(_.ident), table.partitionSchema())
    }

    val isTableAltered = notExistsParts match {
      case Seq() => false // Nothing will be done
      case Seq(partitionSpec) =>
        val partProp = partitionSpec.location.map(loc => "location" -> loc).toMap
        table.createPartition(partitionSpec.ident, partProp.asJava)
        true
      case _ if table.isInstanceOf[SupportsAtomicPartitionManagement] =>
        val partIdents = notExistsParts.map(_.ident)
        val partProps = notExistsParts.map(_.location.map(loc => "location" -> loc).toMap)
        table.asAtomicPartitionable
          .createPartitions(
            partIdents.toArray,
            partProps.map(_.asJava).toArray)
        true
      case _ =>
        throw QueryExecutionErrors.cannotAddMultiPartitionsOnNonatomicPartitionTableError(
          table.name())
    }
    if (isTableAltered) refreshCache()
    Seq.empty
  }
}

相关信息

spark 源码目录

相关文章

spark AlterNamespaceSetPropertiesExec 源码

spark AlterTableExec 源码

spark BatchScanExec 源码

spark CacheTableExec 源码

spark ContinuousScanExec 源码

spark CreateIndexExec 源码

spark CreateNamespaceExec 源码

spark CreateTableExec 源码

spark DataSourceRDD 源码

spark DataSourceV2ScanExecBase 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/39a4089117904d5c8554f902b62d11fc

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 鸿蒙初识ArkTS语言
6、 harmony 鸿蒙ArkUI组件（ArkTS）开发常见问题
7、 flink kafka connector scan.startup.mode 的几个选项
8、 golang
9、 openharmony
10、 Vue中input框自动聚焦

Loading...