spark MetadataLogFileIndex 源码

2022-10-20
浏览 (227)

spark MetadataLogFileIndex 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/MetadataLogFileIndex.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.streaming

import scala.collection.mutable

import org.apache.hadoop.fs.{FileStatus, Path}

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.execution.datasources._
import org.apache.spark.sql.types.StructType


/**
 * A [[FileIndex]] that generates the list of files to processing by reading them from the
 * metadata log files generated by the [[FileStreamSink]].
 *
 * @param userSpecifiedSchema an optional user specified schema that will be use to provide
 *                            types for the discovered partitions
 */
class MetadataLogFileIndex(
    sparkSession: SparkSession,
    path: Path,
    parameters: Map[String, String],
    userSpecifiedSchema: Option[StructType])
  extends PartitioningAwareFileIndex(sparkSession, parameters, userSpecifiedSchema) {

  private val metadataDirectory = {
    val metadataDir = new Path(path, FileStreamSink.metadataDir)
    val fs = metadataDir.getFileSystem(sparkSession.sessionState.newHadoopConf())
    FileStreamSink.checkEscapedMetadataPath(fs, metadataDir, sparkSession.sessionState.conf)
    metadataDir
  }

  logInfo(s"Reading streaming file log from $metadataDirectory")
  private val metadataLog =
    new FileStreamSinkLog(FileStreamSinkLog.VERSION, sparkSession, metadataDirectory.toString)
  private val allFilesFromLog = metadataLog.allFiles().map(_.toFileStatus).filterNot(_.isDirectory)
  private var cachedPartitionSpec: PartitionSpec = _

  override protected val leafFiles: mutable.LinkedHashMap[Path, FileStatus] = {
    new mutable.LinkedHashMap ++= allFilesFromLog.map(f => f.getPath -> f)
  }

  override protected val leafDirToChildrenFiles: Map[Path, Array[FileStatus]] = {
    allFilesFromLog.groupBy(_.getPath.getParent)
  }

  override def rootPaths: Seq[Path] = path :: Nil

  override def refresh(): Unit = { }

  override def partitionSpec(): PartitionSpec = {
    if (cachedPartitionSpec == null) {
      cachedPartitionSpec = inferPartitioning()
    }
    cachedPartitionSpec
  }
}

相关信息

spark 源码目录

相关文章

spark AvailableNowDataStreamWrapper 源码

spark AvailableNowMicroBatchStreamWrapper 源码

spark AvailableNowSourceWrapper 源码

spark CheckpointFileManager 源码

spark CommitLog 源码

spark CompactibleFileStreamLog 源码

spark ContinuousRecordEndpoint 源码

spark EventTimeWatermarkExec 源码

spark FileStreamOptions 源码

spark FileStreamSink 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://m.seaxiang.com/blog/cbba2c80a26d4d67b22973cb732b9456

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

Loading...