Packages

object OrcUtils extends Logging

Linear Supertypes
Logging, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. OrcUtils
  2. Logging
  3. AnyRef
  4. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

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. def addSparkVersionMetadata(writer: Writer): Unit

    Add a metadata specifying Spark version.

  5. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native() @HotSpotIntrinsicCandidate()
  7. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  8. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. val extensionsForCompressionCodecNames: Map[String, String]
  10. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  11. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  12. def inferSchema(sparkSession: SparkSession, files: Seq[FileStatus], options: Map[String, String]): Option[StructType]
  13. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  14. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  15. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  16. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  17. def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path]
  18. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  19. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  20. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  21. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  22. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  23. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  24. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  25. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  26. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  27. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  28. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  29. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  30. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  31. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  32. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  33. def orcResultSchemaString(canPruneCols: Boolean, dataSchema: StructType, resultSchema: StructType, partitionSchema: StructType, conf: Configuration): String

    Returns the result schema to read from ORC file.

    Returns the result schema to read from ORC file. In addition, It sets the schema string to 'orc.mapred.input.schema' so ORC reader can use later.

    canPruneCols

    Flag to decide whether pruned cols schema is send to resultSchema or to send the entire dataSchema to resultSchema.

    dataSchema

    Schema of the orc files.

    resultSchema

    Result data schema created after pruning cols.

    partitionSchema

    Schema of partitions.

    conf

    Hadoop Configuration.

    returns

    Returns the result schema as string.

  34. def orcTypeDescriptionString(dt: DataType): String

    Given a StructType object, this methods converts it to corresponding string representation in ORC.

  35. def readCatalystSchema(file: Path, conf: Configuration, ignoreCorruptFiles: Boolean): Option[StructType]
  36. def readOrcSchemasInParallel(files: Seq[FileStatus], conf: Configuration, ignoreCorruptFiles: Boolean): Seq[StructType]

    Reads ORC file schemas in multi-threaded manner, using native version of ORC.

    Reads ORC file schemas in multi-threaded manner, using native version of ORC. This is visible for testing.

  37. def readSchema(sparkSession: SparkSession, files: Seq[FileStatus], options: Map[String, String]): Option[StructType]
  38. def readSchema(file: Path, conf: Configuration, ignoreCorruptFiles: Boolean): Option[TypeDescription]
  39. def requestedColumnIds(isCaseSensitive: Boolean, dataSchema: StructType, requiredSchema: StructType, reader: Reader, conf: Configuration): Option[(Array[Int], Boolean)]

    returns

    Returns the combination of requested column ids from the given ORC file and boolean flag to find if the pruneCols is allowed or not. Requested Column id can be -1, which means the requested column doesn't exist in the ORC file. Returns None if the given ORC file is empty.

  40. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  41. def toString(): String
    Definition Classes
    AnyRef → Any
  42. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  43. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  44. 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 Logging

Inherited from AnyRef

Inherited from Any

Ungrouped