Packages

o

org.finra.msd.sparkcompare

SparkCompare

object SparkCompare

Contains comparison related operations

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. SparkCompare
  2. AnyRef
  3. 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. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  5. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  6. def compareAppleTables(left: AppleTable, right: AppleTable): DiffResult

    Performs schema based comparison irrespective of source data types

    Performs schema based comparison irrespective of source data types

    left

    Custom table for source1

    right

    Custom table for source2

    returns

    a pair of DataFrames, the left parameter has values in DF1 and not in DF2, the right parameter has values in DF2 but not in DF1

  7. def compareAppleTablesCount(left: AppleTable, right: AppleTable): CountResult

    Performs schema based comparison irrespective of source data types

    Performs schema based comparison irrespective of source data types

    left

    Custom table for LeftSource

    right

    Custom table for RightSource

    returns

    a pair containing the count in left and right

  8. def compareAppleTablesSaveResults(left: AppleTable, right: AppleTable, outputDirectory: String, singleFileOutput: Boolean, delimiter: String): Unit

    Performs comparison between two custom source data types that were created from the actual source data details

    Performs comparison between two custom source data types that were created from the actual source data details

    left

    Custom table for source1

    right

    Custom table for source2

    outputDirectory

    path where the comparison results have to be redirected

    singleFileOutput

    a boolean variable to denote the number of output files to be one or more than one

    delimiter

    character to use as delimiter in the files

  9. def compareAppleTablesSaveResultsWithManipulation(left: AppleTable, right: AppleTable, outputDirectory: String, singleFileOutput: Boolean, delimiter: String, excludeCols: Option[Array[String]], orderByCols: Option[Array[String]], ascOrder: Boolean): Boolean
  10. def compareFileSaveResults(file1Location: String, file2Location: String, outputDirectory: String, singleFileOutput: Boolean, delimiter: String): Unit

    Compares two data sources and stores results locally

    Compares two data sources and stores results locally

    file1Location

    path to source1 data

    file2Location

    path to source2 data

    outputDirectory

    path where the comparison results have to be redirected

    singleFileOutput

    a boolean variable to denote the number of output files to be one or more than one

    delimiter

    character to use as delimiter in the files

  11. def compareFiles(file1Location: String, file2Location: String): DiffResult

    Can compare two files whether S3 , HDFS , local file system, For example, for HDFS, "hdfs://nn1home:8020/input/war-and-peace.txt" For S3 location, "s3n://myBucket/myFile1.log"

    Can compare two files whether S3 , HDFS , local file system, For example, for HDFS, "hdfs://nn1home:8020/input/war-and-peace.txt" For S3 location, "s3n://myBucket/myFile1.log"

    file1Location

    location of file1 representing Left values

    file2Location

    location of file2 representing Right values

    returns

    a Pair of RDDs the Left parameter has values in RDD1 and not in RDD2, the Right parameter has values in RDD2 but not in RDD1

  12. def compareSchemaDataFrames(left: DataFrame, right: DataFrame): DiffResult

    left

    dataframe containing source1 data

    right

    dataframe containing source2 data

    returns

    a pair of RDDs, the left parameter has values in RDD1 and not in RDD2, the right parameter has values in RDD2 but not in RDD1

  13. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  14. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  15. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  16. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  17. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  18. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  19. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  20. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  21. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  22. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  23. def toString(): String
    Definition Classes
    AnyRef → Any
  24. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  25. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  26. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()

Inherited from AnyRef

Inherited from Any

Ungrouped