case class CobolParameters(copybookPath: Option[String], multiCopybookPath: Seq[String], copybookContent: Option[String], sourcePaths: Seq[String], recordFormat: RecordFormat, isText: Boolean, isEbcdic: Boolean, ebcdicCodePage: String, ebcdicCodePageClass: Option[String], asciiCharset: String, fieldCodePage: Map[String, String], isUtf16BigEndian: Boolean, floatingPointFormat: FloatingPointFormat, recordStartOffset: Int, recordEndOffset: Int, recordLength: Option[Int], minimumRecordLength: Option[Int], maximumRecordLength: Option[Int], variableLengthParams: Option[VariableLengthParameters], variableSizeOccurs: Boolean, generateRecordBytes: Boolean, schemaRetentionPolicy: SchemaRetentionPolicy, stringTrimmingPolicy: StringTrimmingPolicy, allowPartialRecords: Boolean, multisegmentParams: Option[MultisegmentParameters], commentPolicy: CommentPolicy, strictSignOverpunch: Boolean, improvedNullDetection: Boolean, decodeBinaryAsHex: Boolean, dropGroupFillers: Boolean, dropValueFillers: Boolean, fillerNamingPolicy: FillerNamingPolicy, nonTerminals: Seq[String], occursMappings: Map[String, Map[String, Int]], debugFieldsPolicy: DebugFieldsPolicy, debugIgnoreFileSize: Boolean, metadataPolicy: MetadataPolicy) extends Product with Serializable
This class holds parameters for the job.
- copybookPath
String containing the path to the copybook in a given file system.
- multiCopybookPath
Sequence containing the paths to the copybooks.
- copybookContent
String containing the actual content of the copybook. Either this, the copybookPath, or multiCopybookPath parameter must be specified.
- sourcePaths
The list of source file paths.
- recordFormat
The record format (F, V, VB, D)
- isText
[deprecated by recordFormat] If true the input data consists of text files where records are separated by a line ending character
- isEbcdic
If true the input data file encoding is EBCDIC, otherwise it is ASCII
- ebcdicCodePage
Specifies what code page to use for EBCDIC to ASCII/Unicode conversions
- ebcdicCodePageClass
An optional custom code page conversion class provided by a user
- asciiCharset
A charset for ASCII data
- fieldCodePage
Specifies a mapping between a field name and the code page
- isUtf16BigEndian
If true UTF-16 is considered big-endian.
- floatingPointFormat
A format of floating-point numbers
- recordStartOffset
A number of bytes to skip at the beginning of the record before parsing a record according to a copybook
- recordEndOffset
A number of bytes to skip at the end of each record
- recordLength
Specifies the length of the record disregarding the copybook record size. Implied the file has fixed record length.
- minimumRecordLength
Minium record length for which the record is considered valid.
- maximumRecordLength
Maximum record length for which the record is considered valid.
- variableLengthParams
VariableLengthParameters containing the specifications for the consumption of variable-length Cobol records.
- variableSizeOccurs
If true, OCCURS DEPENDING ON data size will depend on the number of elements
- generateRecordBytes
Generate 'record_bytes' field containing raw bytes of the original record
- schemaRetentionPolicy
A copybook usually has a root group struct element that acts like a rowtag in XML. This can be retained in Spark schema or can be collapsed
- stringTrimmingPolicy
Specify if and how strings should be trimmed when parsed
- allowPartialRecords
If true, partial ASCII records can be parsed (in cases when LF character is missing for example)
- multisegmentParams
Parameters for reading multisegment mainframe files
- commentPolicy
A comment truncation policy
- improvedNullDetection
If true, string values that contain only zero bytes (0x0) will be considered null.
- decodeBinaryAsHex
Decode binary fields as HEX strings
- dropGroupFillers
If true the parser will drop all FILLER fields, even GROUP FILLERS that have non-FILLER nested fields
- dropValueFillers
If true the parser will drop all value FILLER fields
- nonTerminals
A list of non-terminals (GROUPS) to combine and parse as primitive fields
- debugFieldsPolicy
Specifies if debugging fields need to be added and what should they contain (false, hex, raw).
- debugIgnoreFileSize
If true the fixed length file reader won't check file size divisibility. Useful for debugging binary file / copybook mismatches.
- metadataPolicy
Specifies the policy of metadat fields to be added to the Spark schema
- Alphabetic
- By Inheritance
- CobolParameters
- Serializable
- Serializable
- Product
- Equals
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
CobolParameters(copybookPath: Option[String], multiCopybookPath: Seq[String], copybookContent: Option[String], sourcePaths: Seq[String], recordFormat: RecordFormat, isText: Boolean, isEbcdic: Boolean, ebcdicCodePage: String, ebcdicCodePageClass: Option[String], asciiCharset: String, fieldCodePage: Map[String, String], isUtf16BigEndian: Boolean, floatingPointFormat: FloatingPointFormat, recordStartOffset: Int, recordEndOffset: Int, recordLength: Option[Int], minimumRecordLength: Option[Int], maximumRecordLength: Option[Int], variableLengthParams: Option[VariableLengthParameters], variableSizeOccurs: Boolean, generateRecordBytes: Boolean, schemaRetentionPolicy: SchemaRetentionPolicy, stringTrimmingPolicy: StringTrimmingPolicy, allowPartialRecords: Boolean, multisegmentParams: Option[MultisegmentParameters], commentPolicy: CommentPolicy, strictSignOverpunch: Boolean, improvedNullDetection: Boolean, decodeBinaryAsHex: Boolean, dropGroupFillers: Boolean, dropValueFillers: Boolean, fillerNamingPolicy: FillerNamingPolicy, nonTerminals: Seq[String], occursMappings: Map[String, Map[String, Int]], debugFieldsPolicy: DebugFieldsPolicy, debugIgnoreFileSize: Boolean, metadataPolicy: MetadataPolicy)
- copybookPath
String containing the path to the copybook in a given file system.
- multiCopybookPath
Sequence containing the paths to the copybooks.
- copybookContent
String containing the actual content of the copybook. Either this, the copybookPath, or multiCopybookPath parameter must be specified.
- sourcePaths
The list of source file paths.
- recordFormat
The record format (F, V, VB, D)
- isText
[deprecated by recordFormat] If true the input data consists of text files where records are separated by a line ending character
- isEbcdic
If true the input data file encoding is EBCDIC, otherwise it is ASCII
- ebcdicCodePage
Specifies what code page to use for EBCDIC to ASCII/Unicode conversions
- ebcdicCodePageClass
An optional custom code page conversion class provided by a user
- asciiCharset
A charset for ASCII data
- fieldCodePage
Specifies a mapping between a field name and the code page
- isUtf16BigEndian
If true UTF-16 is considered big-endian.
- floatingPointFormat
A format of floating-point numbers
- recordStartOffset
A number of bytes to skip at the beginning of the record before parsing a record according to a copybook
- recordEndOffset
A number of bytes to skip at the end of each record
- recordLength
Specifies the length of the record disregarding the copybook record size. Implied the file has fixed record length.
- minimumRecordLength
Minium record length for which the record is considered valid.
- maximumRecordLength
Maximum record length for which the record is considered valid.
- variableLengthParams
VariableLengthParameters containing the specifications for the consumption of variable-length Cobol records.
- variableSizeOccurs
If true, OCCURS DEPENDING ON data size will depend on the number of elements
- generateRecordBytes
Generate 'record_bytes' field containing raw bytes of the original record
- schemaRetentionPolicy
A copybook usually has a root group struct element that acts like a rowtag in XML. This can be retained in Spark schema or can be collapsed
- stringTrimmingPolicy
Specify if and how strings should be trimmed when parsed
- allowPartialRecords
If true, partial ASCII records can be parsed (in cases when LF character is missing for example)
- multisegmentParams
Parameters for reading multisegment mainframe files
- commentPolicy
A comment truncation policy
- improvedNullDetection
If true, string values that contain only zero bytes (0x0) will be considered null.
- decodeBinaryAsHex
Decode binary fields as HEX strings
- dropGroupFillers
If true the parser will drop all FILLER fields, even GROUP FILLERS that have non-FILLER nested fields
- dropValueFillers
If true the parser will drop all value FILLER fields
- nonTerminals
A list of non-terminals (GROUPS) to combine and parse as primitive fields
- debugFieldsPolicy
Specifies if debugging fields need to be added and what should they contain (false, hex, raw).
- debugIgnoreFileSize
If true the fixed length file reader won't check file size divisibility. Useful for debugging binary file / copybook mismatches.
- metadataPolicy
Specifies the policy of metadat fields to be added to the Spark schema
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
- val allowPartialRecords: Boolean
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
- val asciiCharset: String
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
- val commentPolicy: CommentPolicy
- val copybookContent: Option[String]
- val copybookPath: Option[String]
- val debugFieldsPolicy: DebugFieldsPolicy
- val debugIgnoreFileSize: Boolean
- val decodeBinaryAsHex: Boolean
- val dropGroupFillers: Boolean
- val dropValueFillers: Boolean
- val ebcdicCodePage: String
- val ebcdicCodePageClass: Option[String]
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- val fieldCodePage: Map[String, String]
- val fillerNamingPolicy: FillerNamingPolicy
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
- val floatingPointFormat: FloatingPointFormat
- val generateRecordBytes: Boolean
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- val improvedNullDetection: Boolean
- val isEbcdic: Boolean
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val isText: Boolean
- val isUtf16BigEndian: Boolean
- val maximumRecordLength: Option[Int]
- val metadataPolicy: MetadataPolicy
- val minimumRecordLength: Option[Int]
- val multiCopybookPath: Seq[String]
- val multisegmentParams: Option[MultisegmentParameters]
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- val nonTerminals: Seq[String]
-
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 recordEndOffset: Int
- val recordFormat: RecordFormat
- val recordLength: Option[Int]
- val recordStartOffset: Int
- val schemaRetentionPolicy: SchemaRetentionPolicy
- val sourcePaths: Seq[String]
- val strictSignOverpunch: Boolean
- val stringTrimmingPolicy: StringTrimmingPolicy
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
- val variableLengthParams: Option[VariableLengthParameters]
- val variableSizeOccurs: Boolean
-
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()