common/org.gnit.lucenekmp.analysis.miscellaneous/DelimitedTermFrequencyTokenFilter

DelimitedTermFrequencyTokenFilter

class DelimitedTermFrequencyTokenFilter(input: TokenStream, delimiter: Char = DEFAULT_DELIMITER) : TokenFilter

Characters before the delimiter are the "token", the textual integer after is the term frequency. To use this TokenFilter the field must be indexed with but no positions or offsets.

For example, if the delimiter is '|', then for the string "foo|5", "foo" is the token and "5" is a term frequency. If there is no delimiter, the TokenFilter does not modify the term frequency.

Note make sure your Tokenizer doesn't split on the delimiter, or this won't work

Constructors

DelimitedTermFrequencyTokenFilter

constructor(input: TokenStream, delimiter: Char = DEFAULT_DELIMITER)

Types

object Companion

Properties

attributeClassesIterator

val attributeClassesIterator: Iterator<Any>

attributeFactory

val attributeFactory: AttributeFactory

attributeImplsIterator

val attributeImplsIterator: Iterator<AttributeImpl>

Functions

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

addAttributeImpl

fun addAttributeImpl(att: AttributeImpl)

fun captureState(): AttributeSource.State?

clearAttributes

fun clearAttributes()

cloneAttributes

fun cloneAttributes(): AttributeSource

open override fun close()

fun copyTo(target: AttributeSource)

open override fun end()

fun endAttributes()

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

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

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

fun hasAttributes(): Boolean

open override fun hashCode(): Int

open override fun incrementToken(): Boolean

reflectAsString

fun reflectAsString(prependAttClass: Boolean): String

fun reflectWith(reflector: AttributeReflector)

removeAllAttributes

fun removeAllAttributes()

open override fun reset()

fun restoreState(state: AttributeSource.State?)

open override fun toString(): String

open override fun unwrap(): TokenStream