spark JDBCScan 源码

2022-10-20
浏览 (205)

spark JDBCScan 代码

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

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Row, SQLContext}
import org.apache.spark.sql.connector.expressions.filter.Predicate
import org.apache.spark.sql.connector.read.V1Scan
import org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation
import org.apache.spark.sql.execution.datasources.v2.TableSampleInfo
import org.apache.spark.sql.sources.{BaseRelation, TableScan}
import org.apache.spark.sql.types.StructType

case class JDBCScan(
    relation: JDBCRelation,
    prunedSchema: StructType,
    pushedPredicates: Array[Predicate],
    pushedAggregateColumn: Array[String] = Array(),
    groupByColumns: Option[Array[String]],
    tableSample: Option[TableSampleInfo],
    pushedLimit: Int,
    sortOrders: Array[String],
    pushedOffset: Int) extends V1Scan {

  override def readSchema(): StructType = prunedSchema

  override def toV1TableScan[T <: BaseRelation with TableScan](context: SQLContext): T = {
    new BaseRelation with TableScan {
      override def sqlContext: SQLContext = context
      override def schema: StructType = prunedSchema
      override def needConversion: Boolean = relation.needConversion
      override def buildScan(): RDD[Row] = {
        val columnList = if (groupByColumns.isEmpty) {
          prunedSchema.map(_.name).toArray
        } else {
          pushedAggregateColumn
        }
        relation.buildScan(columnList, prunedSchema, pushedPredicates, groupByColumns, tableSample,
          pushedLimit, sortOrders, pushedOffset)
      }
    }.asInstanceOf[T]
  }

  override def description(): String = {
    val (aggString, groupByString) = if (groupByColumns.nonEmpty) {
      val groupByColumnsLength = groupByColumns.get.length
      (seqToString(pushedAggregateColumn.drop(groupByColumnsLength)),
        seqToString(pushedAggregateColumn.take(groupByColumnsLength)))
    } else {
      ("[]", "[]")
    }
    super.description()  + ", prunedSchema: " + seqToString(prunedSchema) +
      ", PushedPredicates: " + seqToString(pushedPredicates) +
      ", PushedAggregates: " + aggString + ", PushedGroupBy: " + groupByString
  }

  private def seqToString(seq: Seq[Any]): String = seq.mkString("[", ", ", "]")
}

相关信息

spark 源码目录

相关文章

spark JDBCScanBuilder 源码

spark JDBCTable 源码

spark JDBCTableCatalog 源码

spark JDBCWriteBuilder 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/84dd190236654226972a657451771fb1

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...