case class HmtToken(analysis: Cite2Urn, sourceUrn: CtsUrn, editionUrn: CtsUrn, lang: String = "grc", readings: Vector[Reading], lexicalCategory: LexicalCategory, lexicalDisambiguation: Cite2Urn = ..., alternateReading: Option[AlternateReading] = None, discourse: DiscourseCategory = DirectVoice, externalSource: Option[CtsUrn] = None, errors: ArrayBuffer[String] = ArrayBuffer.empty[String]) extends Product with Serializable
A fully documented, semantically distinct token.
The model of this token supports the ORCA model of
aligned text analysis. The analysis
member is a CITE2
URN representing this token as an ORCA analysis. The sourceUrn
member is a CTS URN with subreference index identifying
the specific string of text analyzed. TheeditionUrn
member is a CTS URN for this token in an analytical exemplar.
The other members of the HmtToken provide the analytical
data for this token.
- analysis
CITE URN for this token analysis.
- sourceUrn
URN for this token in the analyzed text
- editionUrn
URN for this token in an analytical exemplar when promoted to an edition
- lang
3-letter language code for the language code of this token, or a descriptive string if no ISO code defined for this language
- readings
All org.homermultitext.edmodel.Readings belonging to this token
- lexicalCategory
lexical category of this token
- lexicalDisambiguation
URN for automated method to disambiguate tokens of a given type, or manually disambiguated URN for named entity values
- alternateReading
optional org.homermultitext.edmodel.AlternateReadings belonging to this token
- discourse
category of discourse of this token
- externalSource
URN of source this token is quoted from
- errors
list of error messages (hopefully empty)
- Alphabetic
- By Inheritance
- HmtToken
- Serializable
- Serializable
- Product
- Equals
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
HmtToken(analysis: Cite2Urn, sourceUrn: CtsUrn, editionUrn: CtsUrn, lang: String = "grc", readings: Vector[Reading], lexicalCategory: LexicalCategory, lexicalDisambiguation: Cite2Urn = ..., alternateReading: Option[AlternateReading] = None, discourse: DiscourseCategory = DirectVoice, externalSource: Option[CtsUrn] = None, errors: ArrayBuffer[String] = ArrayBuffer.empty[String])
create a token
create a token
- analysis
CITE URN for this token analysis.
- sourceUrn
URN for this token in the analyzed text
- editionUrn
URN for this token in an analytical exemplar when promoted to an edition
- lang
3-letter language code for the language code of this token, or a descriptive string if no ISO code defined for this language
- readings
All org.homermultitext.edmodel.Readings belonging to this token
- lexicalCategory
lexical category of this token
- lexicalDisambiguation
URN for automated method to disambiguate tokens of a given type, or manually disambiguated URN for named entity values
- alternateReading
optional org.homermultitext.edmodel.AlternateReadings belonging to this token
- discourse
category of discourse of this token
- externalSource
URN of source this token is quoted from
- errors
list of error messages (hopefully empty)
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
- def altString: String
- def alternateMatch(s: String, accent: Boolean = true): Boolean
- var alternateReading: Option[AlternateReading]
- var analysis: Cite2Urn
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @native() @throws( ... )
-
def
columnString: String
Format a string representation as one value per line, including labels.
-
def
columnString(withLabels: Boolean): String
Format a string representation as one value per line, either with or without labels.
Format a string representation as one value per line, either with or without labels.
- withLabels
include labels if true
- def debug: String
-
def
diplomaticMatch(s: String, accent: Boolean = true): Boolean
True if diplomatic reading matches a String.
True if diplomatic reading matches a String. Comparison is based on Unicode NFC forms of the strings.
- var discourse: DiscourseCategory
- var editionUrn: CtsUrn
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
errorReport(separator: String = "\t"): String
Format human-readable report of errors encountered reading this token.
Format human-readable report of errors encountered reading this token.
- separator
String to use as structural delimiter in report.
- var errors: ArrayBuffer[String]
- var externalSource: Option[CtsUrn]
-
def
finalize(): Unit
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
hasAlternate: Boolean
True if token has an alternate reading of any kind.
-
def
hasScribalCorrection: Boolean
True if scribe offers a correction for this token.
-
def
hasScribalMultiform: Boolean
True if scribe offers a variant reading (multiform) for this token.
-
def
isAbbreviation: Boolean
True is token is abbreviated in diplomatic reading.
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- var lang: String
- def leidenDiplomatic: String
- def leidenFull: String
-
def
lexMatch(urn: Cite2Urn): Boolean
True if value for lexical disambiguation of this token matches a give URN.
True if value for lexical disambiguation of this token matches a give URN.
- urn
The URN to compare.
- var lexicalCategory: LexicalCategory
- var lexicalDisambiguation: Cite2Urn
-
var
listSeparator: String
String value separating multiple items within a single property in string representation of the object as a single row
-
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()
- def orcaColumn: String
-
var
propertySeparator: String
String value separating properties in string representation of the object as a single row
-
def
readWithAlternate: String
Collect alternate reading for this token.
Collect alternate reading for this token. Strings are normalized to Unicode form NFC.
-
def
readWithDiplomatic: String
Collect clear diplomatic readings for this token.
-
def
readWithScribal: String
Collect scribal text, adding corrections to diplomatic readings.
- var readings: Vector[Reading]
-
def
rowString: String
Format a string representation as a single line of delimited text usng
propertySeparator
value as the delimiter, andlistSeparator
as a secondary delimiter for lists within a single property. - def scribalMatch(s: String, accent: Boolean = true): Boolean
- var sourceUrn: CtsUrn
- def stringMatch(s: String, readingType: String = "diplomatic"): Boolean
-
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
- @native() @throws( ... )