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 clone(): AnyRef

   Attributes

   protected[lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... ) @native()

6.  final def eq(arg0: AnyRef): Boolean

   Definition Classes

   AnyRef

7.  def equals(arg0: Any): Boolean

   Definition Classes

   AnyRef → Any

8.  def finalize(): Unit

   Attributes

   protected[lang]

   Definition Classes

   AnyRef

   Annotations

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

9.  final def getClass(): Class[_]

   Definition Classes

   AnyRef → Any

   Annotations

   @native()

10.  def hashCode(): Int

    Definition Classes

    AnyRef → Any

    Annotations

    @native()

11.  final def isInstanceOf[T0]: Boolean

    Definition Classes

    Any

12.  final def ne(arg0: AnyRef): Boolean

    Definition Classes

    AnyRef

13.  final def notify(): Unit

    Definition Classes

    AnyRef

    Annotations

    @native()

14.  final def notifyAll(): Unit

    Definition Classes

    AnyRef

    Annotations

    @native()

15.  def read(path: String, recursive: Boolean, spark: SparkSession, sampleRatio: Double = 1, inspectZip: Boolean = true, seed: Long = 0L): DataFrame

    Read the directory of binary files from the local or remote source

    Read the directory of binary files from the local or remote source

    path

    Path to the directory

    recursive

    Recursive search flag

    returns

    DataFrame with a single column of "binaryFiles", see "columnSchema" for details

16.  def readFromPaths(df: DataFrame, pathCol: String, bytesCol: String, concurrency: Int, timeout: Int): DataFrame
    df

    the dataframe containing the paths

    pathCol

    the column name of the paths to read

    bytesCol

    the column name of the resulting bytes column

    concurrency

    the number of concurrent reads

    timeout

    in milliseconds

17.  def recursePath(fileSystem: FileSystem, path: Path, pathFilter: (FileStatus) ⇒ Boolean): Array[Path]
18.  def stream(path: String, spark: SparkSession, sampleRatio: Double = 1, inspectZip: Boolean = true, seed: Long = 0L): DataFrame

    Read the directory of binary files from the local or remote source

    Read the directory of binary files from the local or remote source

    path

    Path to the directory

    returns

    DataFrame with a single column of "binaryFiles", see "columnSchema" for details

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

    Definition Classes

    AnyRef

20.  def toString(): String

    Definition Classes

    AnyRef → Any

21.  final def wait(): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

23.  final def wait(arg0: Long): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... ) @native()