HdfsUtils

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

4. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

5. def backupFiles(fs: FileSystem)(filesToBackup: Seq[Path], backupParentDir: Path, dataPath: Path): Try[Path]

   

   Create a new directory inside backupParentDir, called "backup_{randomUUID}".

   Create a new directory inside backupParentDir, called "backup_{randomUUID}". Each of the files inside filesToBackup will be copied in this directory, also maintaining the eventual HDFS partitioning. The new file path is created by removing the base directory (that is dataPath) from the file path, and replacing it with the path of the backup directory. Example: filesToBackup = ["/user/data/p1=a/p2=b/file.parquet"] backupParentDir = "/user" dataPath = "/user/data"

   • This function creates: backupDir = "/user/backup_123'
   • then it copies the file into this directory, replacing the prefix "/user/data" with "/user/backup_123": "/user/backup_123/p1=a/p2=b/file.parquet"

   filesToBackup

   Files that should be copied in the backup directory

   backupParentDir

   Base path where to create the backup directory

   dataPath

   Path containing the data that will be backup

   returns

   Path of the newly created backup directory

6. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

7. def deletePath(fs: FileSystem)(sourcePath: Path): Try[Unit]

   

8. final def eq(arg0: AnyRef): Boolean

   

   Definition Classes

   AnyRef

9. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

10. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

11. def findPartitionColumns(uri: String): List[(String, String)]

    

12. def foldIterator[T, B](iterator: RemoteIterator[T], acc: Try[B])(f: (B, T) ⇒ B)(exitPath: (B) ⇒ Boolean): Try[B]

    

13. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

14. def getRawModelPathToToLoad(rawModel: RawModel, sc: SparkContext): String

    

15. def getRawModelPathToWrite(rawModel: RawModel): String

    

16. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

17. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

18. val logger: WaspLogger

    

    Attributes

    protected

    Definition Classes

    Logging

19. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

20. final def notify(): Unit

    

    Definition Classes

    AnyRef

21. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

22. def readRawModel(rawModel: RawModel, spark: SparkSession): Try[DataFrame]

    

23. def replacePathPrefix(filePath: Path, prefixPathToChange: Path, newPrefix: Path): Path

    

24. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

25. def toString(): String

    

    Definition Classes

    AnyRef → Any

26. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

27. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

28. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

29. def writeRawModel(rawModel: RawModel, df: DataFrame): Try[Unit]