extra/org.gnit.lucenekmp.analysis.uz/UzbekTokenizer

UzbekTokenizer

Tokenizer for Uzbek.

Uzbek Latin orthography uses apostrophe-like marks in letters such as o' and g', so this tokenizer keeps apostrophe variants inside adjacent letter runs.

Constructors

UzbekTokenizer

constructor()

Properties

attributeClassesIterator

val attributeClassesIterator: Iterator<Any>

attributeFactory

val attributeFactory: AttributeFactory

attributeImplsIterator

val attributeImplsIterator: Iterator<AttributeImpl>

Functions

addAttribute

fun <T : Attribute> addAttribute(attClass: KClass<T>): T

addAttributeImpl

fun addAttributeImpl(att: AttributeImpl)

captureState

fun captureState(): AttributeSource.State?

clearAttributes

fun clearAttributes()

cloneAttributes

fun cloneAttributes(): AttributeSource

open override fun close()

copyTo

fun copyTo(target: AttributeSource)

end

open override fun end()

endAttributes

fun endAttributes()

equals

open operator override fun equals(obj: Any?): Boolean

getAttribute

fun <T : Attribute> getAttribute(attClass: KClass<T>): T?

hasAttribute

fun hasAttribute(attClass: KClass<out Attribute>): Boolean

hasAttributes

fun hasAttributes(): Boolean

hashCode

open override fun hashCode(): Int

incrementToken

open override fun incrementToken(): Boolean

reflectAsString

fun reflectAsString(prependAttClass: Boolean): String

reflectWith

fun reflectWith(reflector: AttributeReflector)

removeAllAttributes

fun removeAllAttributes()

reset

open override fun reset()

restoreState

fun restoreState(state: AttributeSource.State?)

setReader

fun setReader(input: Reader)

toString

open override fun toString(): String