当前位置: 首页>>代码示例>>Scala>>正文


Scala FileStatus类代码示例

本文整理汇总了Scala中org.apache.hadoop.fs.FileStatus的典型用法代码示例。如果您正苦于以下问题:Scala FileStatus类的具体用法?Scala FileStatus怎么用?Scala FileStatus使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。


在下文中一共展示了FileStatus类的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Scala代码示例。

示例1: HdfsUtils

//设置package包名称以及导入依赖的类
package yamrcraft.etlite.utils

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

import scala.collection.mutable

object HdfsUtils {

  def renameFiles(fromBase: Path, toBase: Path, fs: FileSystem) = {
    if (fs.exists(fromBase)) {
      val filesToMove = listFiles(fromBase, fs)
      println("files to move:")
      filesToMove foreach (p => println("+++" + p.toString))
      filesToMove foreach { file =>
        val relPath = relativize(fromBase, file)
        val toPath = new Path(toBase, relPath)
        fs.mkdirs(toPath.getParent)
        fs.rename(file, toPath)
        println(" file renamed to: " + toPath.toString)
      }
    }
  }

  def relativize(base: Path, files: List[Path]) = {
    files map (file => new Path(base.toUri.relativize(file.toUri).getPath))
  }

  def relativize(base: Path, file: Path): Path = {
    new Path(base.toUri.relativize(file.toUri).getPath)
  }

  def listFiles(path: Path, fs: FileSystem): List[Path] = {
    val statusList = mutable.MutableList[FileStatus]()
    traverse(path, statusList, fs)
    statusList.map(status => new Path(status.getPath.toUri.getPath)).toList
  }

  private def traverse(path: Path, list: mutable.MutableList[FileStatus], fs: FileSystem): Unit = {
    fs.listStatus(path) foreach { status =>
      if (!status.isDirectory) {
        list += status
      } else {
        traverse(status.getPath, list, fs)
      }
    }
  }

} 
开发者ID:yamrcraft,项目名称:etl-light,代码行数:49,代码来源:HdfsUtils.scala

示例2: DefaultSource

//设置package包名称以及导入依赖的类
package pl.jborkowskijmartin.spark.mf

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.FileStatus
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.execution.datasources.{FileFormat, OutputWriterFactory, PartitionedFile}
import org.apache.spark.sql.sources.Filter
import org.apache.spark.sql.types.{StringType, StructField, StructType}
import org.apache.spark.unsafe.types.UTF8String


class DefaultSource extends FileFormat {
  override def inferSchema(sparkSession: SparkSession, options: Map[String, String], files: Seq[FileStatus]):
  Option[StructType] = {
    println(">>>InferSchema")
    Some(StructType(
      StructField("line", StringType, nullable = true) :: Nil
    ))
  }

  override def prepareWrite(sparkSession: SparkSession, job: Job, options: Map[String, String], dataSchema: StructType):
  OutputWriterFactory = {
    println(">>> prepareWrite")
    null
  }

  override def buildReader(sparkSession: SparkSession, dataSchema: StructType, partitionSchema: StructType,
                           requiredSchema: StructType, filters: Seq[Filter], options: Map[String, String],
                           hadoopConf: Configuration): (PartitionedFile) => Iterator[InternalRow] = {
    pf => Iterator(InternalRow(UTF8String.fromString("hello")))
  }
} 
开发者ID:jborkowski,项目名称:plugin-for-jacek,代码行数:35,代码来源:DefaultSource.scala


注:本文中的org.apache.hadoop.fs.FileStatus类示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。