final case class SanitiserConfig(standardiseCharacters: Boolean = true, cleanSpacing: Boolean = true, removeTatweel: Boolean = true, standardiseDigits: Boolean = true, standardisePunctuation: Boolean = true, removeDiacritics: Boolean = false) extends Product with Serializable
Configuration options for TextSanitiser.
- standardiseCharacters
replaces Arabic and non-standard character variants with standard Persian characters
- cleanSpacing
cleans and canonicalises whitespace, non-breaking spaces, and zero-width non-joiners
- removeTatweel
strips Kashida / Tatweel elongation characters
- standardiseDigits
converts Western ASCII and Eastern Arabic digits into Persian digits
- standardisePunctuation
normalises punctuation symbols into Persian equivalents
- removeDiacritics
strips Arabic Tashkeel (harakat) short vowel diacritics
- Alphabetic
- By Inheritance
- SanitiserConfig
- Serializable
- Product
- Equals
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
- new SanitiserConfig()
Auxiliary zero-argument constructor for seamless Java interoperability.
- new SanitiserConfig(standardiseCharacters: Boolean = true, cleanSpacing: Boolean = true, removeTatweel: Boolean = true, standardiseDigits: Boolean = true, standardisePunctuation: Boolean = true, removeDiacritics: Boolean = false)
- standardiseCharacters
replaces Arabic and non-standard character variants with standard Persian characters
- cleanSpacing
cleans and canonicalises whitespace, non-breaking spaces, and zero-width non-joiners
- removeTatweel
strips Kashida / Tatweel elongation characters
- standardiseDigits
converts Western ASCII and Eastern Arabic digits into Persian digits
- standardisePunctuation
normalises punctuation symbols into Persian equivalents
- removeDiacritics
strips Arabic Tashkeel (harakat) short vowel diacritics
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 cleanSpacing: Boolean
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @IntrinsicCandidate() @native()
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- def productElementNames: Iterator[String]
- Definition Classes
- Product
- val removeDiacritics: Boolean
- val removeTatweel: Boolean
- val standardiseCharacters: Boolean
- val standardiseDigits: Boolean
- val standardisePunctuation: Boolean
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
Deprecated Value Members
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable]) @Deprecated
- Deprecated
(Since version 9)