Packages

abstract class HadoopInputReader[R <: AnyRef] extends InputReader

A sequence input converter that reads data from one file using a specific Hadoop format, making the result available as Dataset[InputFragment]

Linear Supertypes
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. HadoopInputReader
  2. InputReader
  3. AnyRef
  4. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new HadoopInputReader(file: String)(implicit spark: SparkSession)

    file

    the file to read

Abstract Value Members

  1. abstract def getFragments(): Dataset[InputFragment]

    Read sequence data as fragments from the input source

    Read sequence data as fragments from the input source

    Attributes
    protected[input]
    Definition Classes
    HadoopInputReaderInputReader
  2. abstract def getSequenceTitles: Dataset[SeqTitle]

    Sequence titles in this file

    Sequence titles in this file

    Definition Classes
    InputReader
  3. abstract def loadFile(input: String): RDD[R]
    Attributes
    protected

Concrete 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() @IntrinsicCandidate()
  6. val conf: Configuration
    Attributes
    protected
  7. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  8. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @IntrinsicCandidate()
  10. def getInputFragments(withAmbiguous: Boolean, sampleFraction: Option[Double]): Dataset[InputFragment]

    Load sequence fragments from the source

    Load sequence fragments from the source

    withAmbiguous

    Whether to remove ambiguous characters and whitespace

    Definition Classes
    InputReader
  11. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @IntrinsicCandidate()
  12. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  13. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  14. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @IntrinsicCandidate()
  15. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @IntrinsicCandidate()
  16. def rdd: RDD[R]
    Attributes
    protected
  17. val sc: SparkContext
    Definition Classes
    InputReader
  18. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  19. def toString(): String
    Definition Classes
    AnyRef → Any
  20. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  21. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  22. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Deprecated Value Members

  1. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] ) @Deprecated
    Deprecated

Inherited from InputReader

Inherited from AnyRef

Inherited from Any

Ungrouped