spark WholeTextFileRDD 源码

2022-10-20
浏览 (367)

spark WholeTextFileRDD 代码

文件路径：/core/src/main/scala/org/apache/spark/rdd/WholeTextFileRDD.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.rdd

import org.apache.hadoop.conf.{Configurable, Configuration}
import org.apache.hadoop.io.{Text, Writable}
import org.apache.hadoop.mapreduce.InputSplit
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
import org.apache.hadoop.mapreduce.task.JobContextImpl

import org.apache.spark.{Partition, SparkContext}
import org.apache.spark.input.WholeTextFileInputFormat

/**
 * An RDD that reads a bunch of text files in, and each text file becomes one record.
 */
private[spark] class WholeTextFileRDD(
    sc : SparkContext,
    inputFormatClass: Class[_ <: WholeTextFileInputFormat],
    keyClass: Class[Text],
    valueClass: Class[Text],
    conf: Configuration,
    minPartitions: Int)
  extends NewHadoopRDD[Text, Text](sc, inputFormatClass, keyClass, valueClass, conf) {

  override def getPartitions: Array[Partition] = {
    val conf = getConf
    // setMinPartitions below will call FileInputFormat.listStatus(), which can be quite slow when
    // traversing a large number of directories and files. Parallelize it.
    conf.setIfUnset(FileInputFormat.LIST_STATUS_NUM_THREADS,
      Runtime.getRuntime.availableProcessors().toString)
    val inputFormat = inputFormatClass.getConstructor().newInstance()
    inputFormat match {
      case configurable: Configurable =>
        configurable.setConf(conf)
      case _ =>
    }
    val jobContext = new JobContextImpl(conf, jobId)
    inputFormat.setMinPartitions(jobContext, minPartitions)
    val rawSplits = inputFormat.getSplits(jobContext).toArray
    val result = new Array[Partition](rawSplits.size)
    for (i <- 0 until rawSplits.size) {
      result(i) = new NewHadoopPartition(id, i, rawSplits(i).asInstanceOf[InputSplit with Writable])
    }
    result
  }
}

相关信息

spark 源码目录

相关文章

spark AsyncRDDActions 源码

spark BinaryFileRDD 源码

spark BlockRDD 源码

spark CartesianRDD 源码

spark CheckpointRDD 源码

spark CoGroupedRDD 源码

spark CoalescedRDD 源码

spark DoubleRDDFunctions 源码

spark EmptyRDD 源码

spark HadoopRDD 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/424b61a1add846ad8450badfd3ccdc35

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...