c

com.ebiznext.comet.job.ingest

XmlIngestionJob

class XmlIngestionJob extends IngestionJob

Main class to XML file If your json contains only one level simple attribute aka. kind of dsv but in json format please use SIMPLE_JSON instead. It's way faster

Linear Supertypes
IngestionJob, SparkJob, JobBase, StrictLogging, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. XmlIngestionJob
  2. IngestionJob
  3. SparkJob
  4. JobBase
  5. StrictLogging
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new XmlIngestionJob(domain: Domain, schema: Schema, types: List[Type], path: List[Path], storageHandler: StorageHandler, schemaHandler: SchemaHandler, options: Map[String, String])(implicit settings: Settings)

    domain

    : Input Dataset Domain

    schema

    : Input Dataset Schema

    types

    : List of globally defined types

    path

    : Input dataset path

    storageHandler

    : Storage Handler

Type Members

  1. type JdbcConfigName = String
    Definition Classes
    JobBase

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 analyze(fullTableName: String): Any
    Attributes
    protected
    Definition Classes
    SparkJob
  5. def applyIgnore(dfIn: DataFrame): Dataset[Row]
    Attributes
    protected
    Definition Classes
    IngestionJob
  6. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  7. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  8. def createSparkViews(views: Views, sqlParameters: Map[String, String]): Unit
    Attributes
    protected
    Definition Classes
    SparkJob
  9. val domain: Domain
    Definition Classes
    XmlIngestionJob → IngestionJob
  10. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  11. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  12. lazy val extension: String
    Definition Classes
    IngestionJob
  13. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  14. val flatRowValidator: GenericRowValidator
    Attributes
    protected
    Definition Classes
    IngestionJob
  15. lazy val format: String
    Definition Classes
    IngestionJob
  16. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  17. def getWriteMode(): WriteMode
    Definition Classes
    IngestionJob
  18. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  19. def ingest(dataset: DataFrame): (RDD[_], RDD[_])

    Where the magic happen

    Where the magic happen

    dataset

    input dataset as a RDD of string

    Attributes
    protected
    Definition Classes
    XmlIngestionJob → IngestionJob
  20. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  21. def loadDataSet(): Try[DataFrame]

    load the json as an RDD of String

    load the json as an RDD of String

    returns

    Spark Dataframe loaded using metadata options

    Attributes
    protected
    Definition Classes
    XmlIngestionJob → IngestionJob
  22. val logger: Logger
    Attributes
    protected
    Definition Classes
    StrictLogging
  23. lazy val metadata: Metadata

    Merged metadata

    Merged metadata

    Definition Classes
    IngestionJob
  24. def name: String
    Definition Classes
    XmlIngestionJob → JobBase
  25. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  26. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  27. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  28. val now: Timestamp
    Definition Classes
    IngestionJob
  29. val options: Map[String, String]
    Definition Classes
    XmlIngestionJob → IngestionJob
  30. def parseViewDefinition(valueWithEnv: String): (SinkType, Option[JdbcConfigName], String)

    valueWithEnv

    in the form [SinkType:[configName:]]viewName

    returns

    (SinkType, configName, viewName)

    Attributes
    protected
    Definition Classes
    JobBase
  31. def partitionDataset(dataset: DataFrame, partition: List[String]): DataFrame
    Attributes
    protected
    Definition Classes
    SparkJob
  32. def partitionedDatasetWriter(dataset: DataFrame, partition: List[String]): DataFrameWriter[Row]

    Partition a dataset using dataset columns.

    Partition a dataset using dataset columns. To partition the dataset using the ingestion time, use the reserved column names :

    • comet_date
    • comet_year
    • comet_month
    • comet_day
    • comet_hour
    • comet_minute These columns are renamed to "date", "year", "month", "day", "hour", "minute" in the dataset and their values is set to the current date/time.
    dataset

    : Input dataset

    partition

    : list of columns to use for partitioning.

    returns

    The Spark session used to run this job

    Attributes
    protected
    Definition Classes
    SparkJob
  33. val path: List[Path]
    Definition Classes
    XmlIngestionJob → IngestionJob
  34. def registerUdf(udf: String): Unit
    Attributes
    protected
    Definition Classes
    SparkJob
  35. def reorderAttributes(dataFrame: DataFrame): List[Attribute]
    Definition Classes
    IngestionJob
  36. def run(): Try[JobResult]

    Main entry point as required by the Spark Job interface

    Main entry point as required by the Spark Job interface

    returns

    : Spark Session used for the job

    Definition Classes
    IngestionJob → JobBase
  37. def saveAccepted(dataframe: DataFrame): (DataFrame, Path)

    Merge new and existing dataset if required Save using overwrite / Append mode

    Merge new and existing dataset if required Save using overwrite / Append mode

    Attributes
    protected
    Definition Classes
    IngestionJob
  38. def saveRejected(rejectedRDD: RDD[String]): Try[Path]
    Attributes
    protected
    Definition Classes
    IngestionJob
  39. val schema: Schema
    Definition Classes
    XmlIngestionJob → IngestionJob
  40. val schemaHandler: SchemaHandler
    Definition Classes
    XmlIngestionJob → IngestionJob
  41. lazy val schemaSparkType: StructType
  42. lazy val session: SparkSession
    Definition Classes
    SparkJob
  43. implicit val settings: Settings
    Definition Classes
    XmlIngestionJob → JobBase
  44. lazy val sparkEnv: SparkEnv
    Definition Classes
    SparkJob
  45. val storageHandler: StorageHandler
    Definition Classes
    XmlIngestionJob → IngestionJob
  46. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  47. def toString(): String
    Definition Classes
    AnyRef → Any
  48. val treeRowValidator: GenericRowValidator
    Attributes
    protected
    Definition Classes
    IngestionJob
  49. val types: List[Type]
    Definition Classes
    XmlIngestionJob → IngestionJob
  50. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  51. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  52. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()

Inherited from IngestionJob

Inherited from SparkJob

Inherited from JobBase

Inherited from StrictLogging

Inherited from AnyRef

Inherited from Any

Ungrouped