spark TextOptions 源码

2022-10-20
浏览 (189)

spark TextOptions 代码

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

import java.nio.charset.{Charset, StandardCharsets}

import org.apache.spark.sql.catalyst.{DataSourceOptions, FileSourceOptions}
import org.apache.spark.sql.catalyst.util.{CaseInsensitiveMap, CompressionCodecs}

/**
 * Options for the Text data source.
 */
class TextOptions(@transient private val parameters: CaseInsensitiveMap[String])
  extends FileSourceOptions(parameters) {

  import TextOptions._

  def this(parameters: Map[String, String]) = this(CaseInsensitiveMap(parameters))

  /**
   * Compression codec to use.
   */
  val compressionCodec = parameters.get(COMPRESSION).map(CompressionCodecs.getCodecClassName)

  /**
   * wholetext - If true, read a file as a single row and not split by "\n".
   */
  val wholeText = parameters.getOrElse(WHOLETEXT, "false").toBoolean

  val encoding: Option[String] = parameters.get(ENCODING)

  val lineSeparator: Option[String] = parameters.get(LINE_SEP).map { lineSep =>
    require(lineSep.nonEmpty, s"'$LINE_SEP' cannot be an empty string.")

    lineSep
  }

  // Note that the option 'lineSep' uses a different default value in read and write.
  val lineSeparatorInRead: Option[Array[Byte]] = lineSeparator.map { lineSep =>
    lineSep.getBytes(encoding.map(Charset.forName(_)).getOrElse(StandardCharsets.UTF_8))
  }
  val lineSeparatorInWrite: Array[Byte] =
    lineSeparatorInRead.getOrElse("\n".getBytes(StandardCharsets.UTF_8))
}

private[sql] object TextOptions extends DataSourceOptions {
  val COMPRESSION = newOption("compression")
  val WHOLETEXT = newOption("wholetext")
  val ENCODING = newOption("encoding")
  val LINE_SEP = newOption("lineSep")
}

相关信息

spark 源码目录

相关文章

spark TextFileFormat 源码

spark TextOutputWriter 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/6e576aa9c0ba4ce58d71640137f688de

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...