spark CSVWrite 源码

2022-10-20
浏览 (193)

spark CSVWrite 代码

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

import org.apache.hadoop.mapreduce.{Job, TaskAttemptContext}

import org.apache.spark.sql.catalyst.csv.CSVOptions
import org.apache.spark.sql.catalyst.util.CompressionCodecs
import org.apache.spark.sql.connector.write.LogicalWriteInfo
import org.apache.spark.sql.execution.datasources.{CodecStreams, OutputWriter, OutputWriterFactory}
import org.apache.spark.sql.execution.datasources.csv.CsvOutputWriter
import org.apache.spark.sql.execution.datasources.v2.FileWrite
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{DataType, StructType}

case class CSVWrite(
    paths: Seq[String],
    formatName: String,
    supportsDataType: DataType => Boolean,
    info: LogicalWriteInfo) extends FileWrite {
  override def prepareWrite(
      sqlConf: SQLConf,
      job: Job,
      options: Map[String, String],
      dataSchema: StructType): OutputWriterFactory = {
    val conf = job.getConfiguration
    val csvOptions = new CSVOptions(
      options,
      columnPruning = sqlConf.csvColumnPruning,
      sqlConf.sessionLocalTimeZone)
    csvOptions.compressionCodec.foreach { codec =>
      CompressionCodecs.setCodecConfiguration(conf, codec)
    }

    new OutputWriterFactory {
      override def newInstance(
          path: String,
          dataSchema: StructType,
          context: TaskAttemptContext): OutputWriter = {
        new CsvOutputWriter(path, dataSchema, context, csvOptions)
      }

      override def getFileExtension(context: TaskAttemptContext): String = {
        ".csv" + CodecStreams.getCompressionExtension(context)
      }
    }
  }
}

相关信息

spark 源码目录

相关文章

spark CSVDataSourceV2 源码

spark CSVPartitionReaderFactory 源码

spark CSVScan 源码

spark CSVScanBuilder 源码

spark CSVTable 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/a30a8bb7caa541d0a9801039a0de1072

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...