hebmorph/org.gnit.lucenekmp.analysis.he/StreamLemmatizer

StreamLemmatizer

class StreamLemmatizer : Lemmatizer

Constructors

StreamLemmatizer

constructor(input: Reader, dict: DictHebMorph)

constructor(input: Reader, dict: DictHebMorph, specialTokenizationCases: DictRadix<Byte>?)

Functions

fun getEndOffset(): Int

getLemmatizeNextToken

fun getLemmatizeNextToken(nextToken: Reference<String>, retTokens: MutableList<Token>): Int

fun getStartOffset(): Int

fun isLegalPrefix(str: String): Boolean

fun lemmatize(word: String): MutableList<HebrewToken>

fun lemmatize(word: String, ret: MutableList<HebrewToken>): MutableList<HebrewToken>

lemmatizeTolerant

fun lemmatizeTolerant(word: String): MutableList<HebrewToken>

fun lemmatizeTolerant(word: String, ret: MutableList<HebrewToken>): MutableList<HebrewToken>

fun reset(input: Reader)

setSuffixForExactMatch

fun setSuffixForExactMatch(suffixForExactMatch: Char?)

tryStrippingPrefix

fun tryStrippingPrefix(word: String): String