hebmorph/org.gnit.lucenekmp.analysis.he

Package-level declarations

Types

class AddSuffixTokenFilter(input: TokenStream, suffix: Char) : TokenFilter

class BasicLemmaFilter : LemmaFilterBase

BasicLemmaFilter will only filter collections with more than one lemma. For them, any lemma scored below 0.7 is probably a result of some heavy toleration, and will be ignored.

DescFlag

enum DescFlag : Enum<DescFlag>

Created by Egozy on 28/12/2014.

DictHebMorph

class DictHebMorph

HebMorphTokenizer

class HebMorphTokenizer(input: Reader, hebrewPrefixes: MutableMap<String, Int>, specialCases: DictRadix<Byte>? = null)

HebrewAnalyzer

abstract class HebrewAnalyzer : Analyzer

HebrewCharacters

object HebrewCharacters

HebrewExactAnalyzer

class HebrewExactAnalyzer : HebrewAnalyzer

HebrewIndexingAnalyzer

class HebrewIndexingAnalyzer : HebrewAnalyzer

HebrewLegacyIndexingAnalyzer

class HebrewLegacyIndexingAnalyzer : HebrewAnalyzer

HebrewLegacyQueryAnalyzer

class HebrewLegacyQueryAnalyzer : HebrewAnalyzer

HebrewLemmatizerTokenFilter

class HebrewLemmatizerTokenFilter : TokenFilter

HebrewPosAttribute

interface HebrewPosAttribute : Attribute

Reflects the Hebrew Part-of-Speech as detected by HebMorph

HebrewPosAttributeImpl

class HebrewPosAttributeImpl : AttributeImpl, HebrewPosAttribute

HebrewQueryAnalyzer

class HebrewQueryAnalyzer : HebrewAnalyzer

HebrewQueryLightAnalyzer

class HebrewQueryLightAnalyzer : HebrewAnalyzer

HebrewToken

class HebrewToken : Token, Comparable<Token>

HebrewTokenizer

class HebrewTokenizer : Tokenizer

Tokenizes a given stream using HebMorph's Tokenizer, removes prefixes where possible, and tags Tokens with appropriate types where possible

HebrewTokenTypeAttribute

interface HebrewTokenTypeAttribute : Attribute

This attribute is used to pass info on tokens as parsed and identified by the HebMorph tokenizer

HebrewTokenTypeAttributeImpl

class HebrewTokenTypeAttributeImpl : AttributeImpl, HebrewTokenTypeAttribute

HebrewUtils

object HebrewUtils

HSpellDictionaryLoader

class HSpellDictionaryLoader

IgnoreOriginalTokenFilter

class IgnoreOriginalTokenFilter(input: TokenStream) : FilteringTokenFilter

LemmaFilterBase

abstract class LemmaFilterBase

Lemmatizer

open class Lemmatizer(dictHeb: DictHebMorph)

LookupTolerators

object LookupTolerators

MarkHebrewTokensFilter

class MarkHebrewTokensFilter(input: TokenStream) : TokenFilter

MorphData

class MorphData

NiqqudFilter

class NiqqudFilter(input: TokenStream) : TokenFilter

PrefixType

enum PrefixType : Enum<PrefixType>

Reference

class Reference<T>(var ref: T)

StreamLemmasFilter

class StreamLemmasFilter : Tokenizer

StreamLemmatizer

class StreamLemmatizer : Lemmatizer

Token

open class Token(text: String, isNumeric: Boolean = false)

WordType

enum WordType : Enum<WordType>