spark OrcWrite 源码

2022-10-20
浏览 (206)

spark OrcWrite 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcWrite.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 org.apache.hadoop.mapred.JobConf
import org.apache.hadoop.mapreduce.{Job, TaskAttemptContext}
import org.apache.orc.OrcConf.{COMPRESS, MAPRED_OUTPUT_SCHEMA}
import org.apache.orc.mapred.OrcStruct

import org.apache.spark.sql.connector.write.LogicalWriteInfo
import org.apache.spark.sql.execution.datasources.{OutputWriter, OutputWriterFactory}
import org.apache.spark.sql.execution.datasources.orc.{OrcOptions, OrcOutputWriter, OrcUtils}
import org.apache.spark.sql.execution.datasources.v2.FileWrite
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types._

case class OrcWrite(
    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 orcOptions = new OrcOptions(options, sqlConf)

    val conf = job.getConfiguration

    conf.set(MAPRED_OUTPUT_SCHEMA.getAttribute, OrcUtils.getOrcSchemaString(dataSchema))

    conf.set(COMPRESS.getAttribute, orcOptions.compressionCodec)

    conf.asInstanceOf[JobConf]
      .setOutputFormat(classOf[org.apache.orc.mapred.OrcOutputFormat[OrcStruct]])

    val batchSize = sqlConf.orcVectorizedWriterBatchSize

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

      override def getFileExtension(context: TaskAttemptContext): String = {
        val compressionExtension: String = {
          val name = context.getConfiguration.get(COMPRESS.getAttribute)
          OrcUtils.extensionsForCompressionCodecNames.getOrElse(name, "")
        }

        compressionExtension + ".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 OrcTable 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/13ccdb329cd84ee7946330d39dc7b42f

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...