spark OrcTable 源码

2022-10-20
浏览 (125)

spark OrcTable 代码

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

import scala.collection.JavaConverters._

import org.apache.hadoop.fs.FileStatus

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.connector.write.{LogicalWriteInfo, Write, WriteBuilder}
import org.apache.spark.sql.execution.datasources.FileFormat
import org.apache.spark.sql.execution.datasources.orc.OrcUtils
import org.apache.spark.sql.execution.datasources.v2.FileTable
import org.apache.spark.sql.types._
import org.apache.spark.sql.util.CaseInsensitiveStringMap

case class OrcTable(
    name: String,
    sparkSession: SparkSession,
    options: CaseInsensitiveStringMap,
    paths: Seq[String],
    userSpecifiedSchema: Option[StructType],
    fallbackFileFormat: Class[_ <: FileFormat])
  extends FileTable(sparkSession, options, paths, userSpecifiedSchema) {

  override def newScanBuilder(options: CaseInsensitiveStringMap): OrcScanBuilder =
    new OrcScanBuilder(sparkSession, fileIndex, schema, dataSchema, options)

  override def inferSchema(files: Seq[FileStatus]): Option[StructType] =
    OrcUtils.inferSchema(sparkSession, files, options.asScala.toMap)

  override def newWriteBuilder(info: LogicalWriteInfo): WriteBuilder =
    new WriteBuilder {
      override def build(): Write = OrcWrite(paths, formatName, supportsDataType, info)
    }

  override def supportsDataType(dataType: DataType): Boolean = dataType match {
    case _: AtomicType => true

    case st: StructType => st.forall { f => supportsDataType(f.dataType) }

    case ArrayType(elementType, _) => supportsDataType(elementType)

    case MapType(keyType, valueType, _) =>
      supportsDataType(keyType) && supportsDataType(valueType)

    case udt: UserDefinedType[_] => supportsDataType(udt.sqlType)

    case _ => false
  }

  override def formatName: String = "ORC"
}

相关信息

spark 源码目录

相关文章

spark OrcDataSourceV2 源码

spark OrcPartitionReaderFactory 源码

spark OrcScan 源码

spark OrcScanBuilder 源码

spark OrcWrite 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/c06ecec87d7849d4a50ce7f14935032a

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

Loading...