spark FilePartitionReader 源码

spark FilePartitionReader 代码

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

import java.io.{FileNotFoundException, IOException}

import scala.util.control.NonFatal

import org.apache.spark.SparkUpgradeException
import org.apache.spark.internal.Logging
import org.apache.spark.rdd.InputFileBlockHolder
import org.apache.spark.sql.catalyst.FileSourceOptions
import org.apache.spark.sql.connector.read.PartitionReader
import org.apache.spark.sql.errors.QueryExecutionErrors
import org.apache.spark.sql.execution.datasources.SchemaColumnConvertNotSupportedException

class FilePartitionReader[T](
    readers: Iterator[PartitionedFileReader[T]],
    options: FileSourceOptions)
  extends PartitionReader[T] with Logging {
  private var currentReader: PartitionedFileReader[T] = null

  private def ignoreMissingFiles = options.ignoreMissingFiles
  private def ignoreCorruptFiles = options.ignoreCorruptFiles

  override def next(): Boolean = {
    if (currentReader == null) {
      if (readers.hasNext) {
        try {
          currentReader = getNextReader()
        } catch {
          case e: FileNotFoundException if ignoreMissingFiles =>
            logWarning(s"Skipped missing file.", e)
            currentReader = null
          // Throw FileNotFoundException even if `ignoreCorruptFiles` is true
          case e: FileNotFoundException if !ignoreMissingFiles =>
            throw QueryExecutionErrors.fileNotFoundError(e)
          case e @ (_: RuntimeException | _: IOException) if ignoreCorruptFiles =>
            logWarning(
              s"Skipped the rest of the content in the corrupted file.", e)
            currentReader = null
        }
      } else {
        return false
      }
    }

    // In PartitionReader.next(), the current reader proceeds to next record.
    // It might throw RuntimeException/IOException and Spark should handle these exceptions.
    val hasNext = try {
      currentReader != null && currentReader.next()
    } catch {
      case e: SchemaColumnConvertNotSupportedException =>
        throw QueryExecutionErrors.unsupportedSchemaColumnConvertError(
          currentReader.file.filePath, e.getColumn, e.getLogicalType, e.getPhysicalType, e)
      case e @ (_: RuntimeException | _: IOException) if ignoreCorruptFiles =>
        logWarning(
          s"Skipped the rest of the content in the corrupted file: $currentReader", e)
        false
      case sue: SparkUpgradeException => throw sue
      case NonFatal(e) =>
        e.getCause match {
          case sue: SparkUpgradeException => throw sue
          case _ => throw QueryExecutionErrors.cannotReadFilesError(e, currentReader.file.filePath)
        }
    }
    if (hasNext) {
      true
    } else {
      close()
      currentReader = null
      next()
    }
  }

  override def get(): T = currentReader.get()

  override def close(): Unit = {
    if (currentReader != null) {
      currentReader.close()
    }
    InputFileBlockHolder.unset()
  }

  private def getNextReader(): PartitionedFileReader[T] = {
    val reader = readers.next()
    logInfo(s"Reading file $reader")
    // Sets InputFileBlockHolder for the file block's information
    val file = reader.file
    InputFileBlockHolder.set(file.filePath, file.start, file.length)
    reader
  }
}

相关信息

spark 源码目录

相关文章

spark AddPartitionExec 源码

spark AlterNamespaceSetPropertiesExec 源码

spark AlterTableExec 源码

spark BatchScanExec 源码

spark CacheTableExec 源码

spark ContinuousScanExec 源码

spark CreateIndexExec 源码

spark CreateNamespaceExec 源码

spark CreateTableExec 源码

spark DataSourceRDD 源码