spark SaveIntoDataSourceCommand 源码

2022-10-20
浏览 (227)

spark SaveIntoDataSourceCommand 代码

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

import scala.util.control.NonFatal

import org.apache.spark.sql.{Dataset, Row, SaveMode, SparkSession}
import org.apache.spark.sql.catalyst.plans.QueryPlan
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.command.LeafRunnableCommand
import org.apache.spark.sql.sources.CreatableRelationProvider

/**
 * Saves the results of `query` in to a data source.
 *
 * Note that this command is different from [[InsertIntoDataSourceCommand]]. This command will call
 * `CreatableRelationProvider.createRelation` to write out the data, while
 * [[InsertIntoDataSourceCommand]] calls `InsertableRelation.insert`. Ideally these 2 data source
 * interfaces should do the same thing, but as we've already published these 2 interfaces and the
 * implementations may have different logic, we have to keep these 2 different commands.
 */
case class SaveIntoDataSourceCommand(
    query: LogicalPlan,
    dataSource: CreatableRelationProvider,
    options: Map[String, String],
    mode: SaveMode) extends LeafRunnableCommand {

  override def innerChildren: Seq[QueryPlan[_]] = Seq(query)

  override def run(sparkSession: SparkSession): Seq[Row] = {
    val relation = dataSource.createRelation(
      sparkSession.sqlContext, mode, options, Dataset.ofRows(sparkSession, query))

    try {
      val logicalRelation = LogicalRelation(relation, relation.schema.toAttributes, None, false)
      sparkSession.sharedState.cacheManager.recacheByPlan(sparkSession, logicalRelation)
    } catch {
      case NonFatal(_) =>
        // some data source can not support return a valid relation, e.g. `KafkaSourceProvider`
    }

    Seq.empty[Row]
  }

  override def simpleString(maxFields: Int): String = {
    val redacted = conf.redactOptions(options)
    s"SaveIntoDataSourceCommand ${dataSource}, ${redacted}, ${mode}"
  }

  // Override `clone` since the default implementation will turn `CaseInsensitiveMap` to a normal
  // map.
  override def clone(): LogicalPlan = {
    SaveIntoDataSourceCommand(query.clone(), dataSource, options, mode)
  }
}

相关信息

spark 源码目录

相关文章

spark AggregatePushDownUtils 源码

spark ApplyCharTypePadding 源码

spark BasicWriteStatsTracker 源码

spark BucketingUtils 源码

spark CatalogFileIndex 源码

spark CodecStreams 源码

spark DataSource 源码

spark DataSourceStrategy 源码

spark DataSourceUtils 源码

spark DaysWritable 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/68d93ad90d224ccbb971d9a003b719e7

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...