Packages

c

com.jnpersson.kmers.input

FastaTextInput

class FastaTextInput extends HadoopInputReader[Array[String]]

Reader for fasta records that are potentially multiline, but small enough to fit into a single string. Huge sequences are best processed with the fastdoop.IndexedFastaFormat instead (.fna files) Supports compression via Spark's text reader.

Linear Supertypes
HadoopInputReader[Array[String]], InputReader, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. FastaTextInput
  2. HadoopInputReader
  3. InputReader
  4. AnyRef
  5. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

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
    Definition Classes
    HadoopInputReader
  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 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
    FastaTextInput → HadoopInputReader → InputReader
  11. 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
  12. def getSequenceTitles: Dataset[SeqTitle]

    Sequence titles in this file

    Sequence titles in this file

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

Inherited from InputReader

Inherited from AnyRef

Inherited from Any

Ungrouped