final case class DelimitedFileSourceConfig(id: ID, description: Option[NonEmptyString], path: URI, schema: Option[ID], persist: Option[StorageLevel], delimiter: NonEmptyString = ",", quote: NonEmptyString = "\"", escape: NonEmptyString = "\\", header: Boolean = false, windowBy: StreamWindowing = ProcessingTime, options: Seq[SparkParam] = Seq.empty, keyFields: Seq[NonEmptyString] = Seq.empty, metadata: Seq[SparkParam] = Seq.empty) extends FileSourceConfig with DelimitedFileConfig with Product with Serializable
Delimited file source configuration
- id
Source ID
- description
Source description
- path
Path to file
- schema
Schema ID (only if header = false)
- persist
Spark storage level in order to persist dataframe during job execution.
- delimiter
Column delimiter (default: ,)
- quote
Quotation symbol (default: ")
- escape
Escape symbol (default: \)
- header
Boolean flag indicating whether schema should be read from file header (default: false)
- windowBy
Source of timestamp used to build windows. Applicable only for streaming jobs! Default: processingTime - uses current timestamp at the moment when Spark processes row. Other options are:
- eventTime - uses column with name 'timestamp' (column must be of TimestampType).
- customTime(columnName) - uses arbitrary user-defined column (column must be of TimestampType)
- options
List of additional spark options required to read the source (if any)
- keyFields
Sequence of key fields (columns that identify data row)
- metadata
List of metadata parameters specific to this source
- Alphabetic
- By Inheritance
- DelimitedFileSourceConfig
- Product
- Equals
- DelimitedFileConfig
- FileConfig
- FileSourceConfig
- SourceConfig
- JobConfigEntity
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
DelimitedFileSourceConfig(id: ID, description: Option[NonEmptyString], path: URI, schema: Option[ID], persist: Option[StorageLevel], delimiter: NonEmptyString = ",", quote: NonEmptyString = "\"", escape: NonEmptyString = "\\", header: Boolean = false, windowBy: StreamWindowing = ProcessingTime, options: Seq[SparkParam] = Seq.empty, keyFields: Seq[NonEmptyString] = Seq.empty, metadata: Seq[SparkParam] = Seq.empty)
- id
Source ID
- description
Source description
- path
Path to file
- schema
Schema ID (only if header = false)
- persist
Spark storage level in order to persist dataframe during job execution.
- delimiter
Column delimiter (default: ,)
- quote
Quotation symbol (default: ")
- escape
Escape symbol (default: \)
- header
Boolean flag indicating whether schema should be read from file header (default: false)
- windowBy
Source of timestamp used to build windows. Applicable only for streaming jobs! Default: processingTime - uses current timestamp at the moment when Spark processes row. Other options are:
- eventTime - uses column with name 'timestamp' (column must be of TimestampType).
- customTime(columnName) - uses arbitrary user-defined column (column must be of TimestampType)
- options
List of additional spark options required to read the source (if any)
- keyFields
Sequence of key fields (columns that identify data row)
- metadata
List of metadata parameters specific to this source
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()
-
val
delimiter: NonEmptyString
- Definition Classes
- DelimitedFileSourceConfig → DelimitedFileConfig
-
val
description: Option[NonEmptyString]
- Definition Classes
- DelimitedFileSourceConfig → JobConfigEntity
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
val
escape: NonEmptyString
- Definition Classes
- DelimitedFileSourceConfig → DelimitedFileConfig
-
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()
-
val
header: Boolean
- Definition Classes
- DelimitedFileSourceConfig → DelimitedFileConfig
-
val
id: ID
- Definition Classes
- DelimitedFileSourceConfig → JobConfigEntity
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
val
keyFields: Seq[NonEmptyString]
- Definition Classes
- DelimitedFileSourceConfig → SourceConfig
-
val
metadata: Seq[SparkParam]
- Definition Classes
- DelimitedFileSourceConfig → JobConfigEntity
-
val
metadataString: Option[String]
- Definition Classes
- JobConfigEntity
-
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()
- val options: Seq[SparkParam]
-
val
path: URI
- Definition Classes
- DelimitedFileSourceConfig → FileConfig
-
val
persist: Option[StorageLevel]
- Definition Classes
- DelimitedFileSourceConfig → SourceConfig
-
val
quote: NonEmptyString
- Definition Classes
- DelimitedFileSourceConfig → DelimitedFileConfig
-
val
schema: Option[ID]
- Definition Classes
- DelimitedFileSourceConfig → FileConfig
-
val
streamable: Boolean
- Definition Classes
- DelimitedFileSourceConfig → SourceConfig
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
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()
-
val
windowBy: StreamWindowing
- Definition Classes
- DelimitedFileSourceConfig → FileSourceConfig