case class VariableLengthParameters(isRecordSequence: Boolean, bdw: Option[Bdw], isRdwBigEndian: Boolean, isRdwPartRecLength: Boolean, rdwAdjustment: Int, recordHeaderParser: Option[String], recordExtractor: Option[String], rhpAdditionalInfo: Option[String], reAdditionalInfo: String, recordLengthField: String, fileStartOffset: Int, fileEndOffset: Int, generateRecordId: Boolean, isUsingIndex: Boolean, inputSplitRecords: Option[Int], inputSplitSizeMB: Option[Int], improveLocality: Boolean, optimizeAllocation: Boolean, inputFileNameColumn: String, occursMappings: Map[String, Map[String, Int]]) extends Product with Serializable
This class holds the parameters currently used for parsing variable-length records.
- isRecordSequence
Does input files have 4 byte record length headers
- bdw
Block descriptor word (if specified), for FB and VB record formats
- isRdwBigEndian
Is RDW big endian? It may depend on flavor of mainframe and/or mainframe to PC transfer method
- isRdwPartRecLength
Does RDW count itself as part of record length itself
- rdwAdjustment
Controls a mismatch between RDW and record length
- recordHeaderParser
An optional custom record header parser for non-standard RDWs
- recordExtractor
An optional custom raw record parser class non-standard record types
- rhpAdditionalInfo
An optional additional option string passed to a custom record header parser
- reAdditionalInfo
An optional additional option string passed to a custom record extractor
- recordLengthField
A field that stores record length
- fileStartOffset
A number of bytes to skip at the beginning of each file
- fileEndOffset
A number of bytes to skip at the end of each file
- generateRecordId
Generate a sequential record number for each record to be able to retain the order of the original data
- isUsingIndex
Is indexing input file before processing is requested
- inputSplitRecords
The number of records to include in each partition. Notice mainframe records may have variable size, inputSplitMB is the recommended option
- inputSplitSizeMB
A partition size to target. In certain circumstances this size may not be exactly that, but the library will do the best effort to target that size
- improveLocality
Tries to improve locality by extracting preferred locations for variable-length records
- optimizeAllocation
Optimizes cluster usage in case of optimization for locality in the presence of new nodes (nodes that do not contain any blocks of the files being processed)
- inputFileNameColumn
A column name to add to the dataframe. The column will contain input file name for each record similar to 'input_file_name()' function
- Alphabetic
- By Inheritance
- VariableLengthParameters
- Serializable
- Serializable
- Product
- Equals
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
VariableLengthParameters(isRecordSequence: Boolean, bdw: Option[Bdw], isRdwBigEndian: Boolean, isRdwPartRecLength: Boolean, rdwAdjustment: Int, recordHeaderParser: Option[String], recordExtractor: Option[String], rhpAdditionalInfo: Option[String], reAdditionalInfo: String, recordLengthField: String, fileStartOffset: Int, fileEndOffset: Int, generateRecordId: Boolean, isUsingIndex: Boolean, inputSplitRecords: Option[Int], inputSplitSizeMB: Option[Int], improveLocality: Boolean, optimizeAllocation: Boolean, inputFileNameColumn: String, occursMappings: Map[String, Map[String, Int]])
- isRecordSequence
Does input files have 4 byte record length headers
- bdw
Block descriptor word (if specified), for FB and VB record formats
- isRdwBigEndian
Is RDW big endian? It may depend on flavor of mainframe and/or mainframe to PC transfer method
- isRdwPartRecLength
Does RDW count itself as part of record length itself
- rdwAdjustment
Controls a mismatch between RDW and record length
- recordHeaderParser
An optional custom record header parser for non-standard RDWs
- recordExtractor
An optional custom raw record parser class non-standard record types
- rhpAdditionalInfo
An optional additional option string passed to a custom record header parser
- reAdditionalInfo
An optional additional option string passed to a custom record extractor
- recordLengthField
A field that stores record length
- fileStartOffset
A number of bytes to skip at the beginning of each file
- fileEndOffset
A number of bytes to skip at the end of each file
- generateRecordId
Generate a sequential record number for each record to be able to retain the order of the original data
- isUsingIndex
Is indexing input file before processing is requested
- inputSplitRecords
The number of records to include in each partition. Notice mainframe records may have variable size, inputSplitMB is the recommended option
- inputSplitSizeMB
A partition size to target. In certain circumstances this size may not be exactly that, but the library will do the best effort to target that size
- improveLocality
Tries to improve locality by extracting preferred locations for variable-length records
- optimizeAllocation
Optimizes cluster usage in case of optimization for locality in the presence of new nodes (nodes that do not contain any blocks of the files being processed)
- inputFileNameColumn
A column name to add to the dataframe. The column will contain input file name for each record similar to 'input_file_name()' function
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
- val bdw: Option[Bdw]
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- val fileEndOffset: Int
- val fileStartOffset: Int
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
- val generateRecordId: Boolean
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- val improveLocality: Boolean
- val inputFileNameColumn: String
- val inputSplitRecords: Option[Int]
- val inputSplitSizeMB: Option[Int]
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val isRdwBigEndian: Boolean
- val isRdwPartRecLength: Boolean
- val isRecordSequence: Boolean
- val isUsingIndex: Boolean
-
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 occursMappings: Map[String, Map[String, Int]]
- val optimizeAllocation: Boolean
- val rdwAdjustment: Int
- val reAdditionalInfo: String
- val recordExtractor: Option[String]
- val recordHeaderParser: Option[String]
- val recordLengthField: String
- val rhpAdditionalInfo: Option[String]
-
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()