nori/org.gnit.lucenekmp.analysis.ko.dict/TokenInfoDictionary

TokenInfoDictionary

class TokenInfoDictionary : BinaryDictionary<TokenInfoMorphData>

Binary dictionary implementation for a known-word dictionary model: Words are encoded into an FST mapping to a list of wordIDs.

Constructors

TokenInfoDictionary

constructor(targetMapFile: Path, posDictFile: Path, dictFile: Path, fstFile: Path)

Create a TokenInfoDictionary from an external resource path.

Types

object Companion

Functions

fun getFST(): TokenInfoFST

open fun getLeftId(morphId: Int): Int

getMorphAttributes

open override fun getMorphAttributes(): TokenInfoMorphData

open fun getRightId(morphId: Int): Int

open fun getWordCost(morphId: Int): Int

fun lookupWordIds(sourceId: Int, ref: IntsRef)