object SparkCompare
Contains comparison related operations
- Alphabetic
- By Inheritance
- SparkCompare
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
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
-
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
-
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
- def compareAppleTablesSaveResultsWithManipulation(left: AppleTable, right: AppleTable, outputDirectory: String, singleFileOutput: Boolean, delimiter: String, excludeCols: Option[Array[String]], orderByCols: Option[Array[String]], ascOrder: Boolean): Boolean
-
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
-
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
-
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
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()