Dependencies
- com.ibm.icu/icu4j/62.1
- java/11
- org.apache.lucene/lucene-analyzers-common/8.2.0
- org.apache.lucene/lucene-core/8.2.0
Declarations
-
org
-
apache
-
lucene
-
analysis
-
icu
- ICUFoldingFilter
- ICUFoldingFilterFactory
-
ICUNormalizer2CharFilter
- normalizer: Normalizer2
- inputBuffer: StringBuilder
- resultBuffer: StringBuilder
- inputFinished: boolean
- afterQuickCheckYes: boolean
- checkedInputBoundary: int
- charCount: int
- ICUNormalizer2CharFilter(Reader): void
- ICUNormalizer2CharFilter(Reader, Normalizer2): void
- ICUNormalizer2CharFilter(Reader, Normalizer2, int): void
- read(char[], int, int): int
- tmpBuffer: CharacterBuffer
- readInputToBuffer(): void
- readAndNormalizeFromInput(): int
- readFromInputWhileSpanQuickCheckYes(): int
- readFromIoNormalizeUptoBoundary(): int
- normalizeInputUpto(int): int
- recordOffsetDiff(int, int): void
- outputFromResultBuffer(char[], int, int): int
- ICUNormalizer2CharFilterFactory
- ICUNormalizer2Filter
- ICUNormalizer2FilterFactory
-
ICUTransformFilter
- transform: Transliterator
- position: Position
- termAtt: CharTermAttribute
- replaceableAttribute: ReplaceableTermAttribute
- ICUTransformFilter(TokenStream, Transliterator): void
- incrementToken(): boolean
-
ReplaceableTermAttribute
- buffer: char[]
- length: int
- token: CharTermAttribute
- setText(CharTermAttribute): void
- char32At(int): int
- charAt(int): char
- copy(int, int, int): void
- getChars(int, int, char[], int): void
- hasMetaData(): boolean
- length(): int
- replace(int, int, String): void
- replace(int, int, char[], int, int): void
- shiftForReplace(int, int, int): int
- ICUTransformFilterFactory
-
segmentation
-
BreakIteratorWrapper
- start: int
- textIterator: CharArrayIterator
- rbbi: RuleBasedBreakIterator
- text: char[]
- status: int
- BreakIteratorWrapper(RuleBasedBreakIterator): void
- current(): int
- getRuleStatus(): int
- next(): int
- calcStatus(int, int): int
- EMOJI_RK: UnicodeSet
- EMOJI: UnicodeSet
- isEmoji(int, int): boolean
- setText(char[], int, int): void
-
CharArrayIterator
- array: char[]
- start: int
- index: int
- length: int
- limit: int
- getText(): char[]
- getStart(): int
- getLength(): int
- setText(char[], int, int): void
- current(): char
- first(): char
- getBeginIndex(): int
- getEndIndex(): int
- getIndex(): int
- last(): char
- next(): char
- previous(): char
- setIndex(int): char
- clone(): CharArrayIterator
-
CompositeBreakIterator
- config: ICUTokenizerConfig
- wordBreakers: BreakIteratorWrapper[]
- rbbi: BreakIteratorWrapper
- scriptIterator: ScriptIterator
- text: char[]
- CompositeBreakIterator(ICUTokenizerConfig): void
- next(): int
- current(): int
- getRuleStatus(): int
- getScriptCode(): int
- setText(char[], int, int): void
- getBreakIterator(int): BreakIteratorWrapper
-
DefaultICUTokenizerConfig
- WORD_IDEO: String
- WORD_HIRAGANA: String
- WORD_KATAKANA: String
- WORD_HANGUL: String
- WORD_LETTER: String
- WORD_NUMBER: String
- WORD_EMOJI: String
- cjkBreakIterator: BreakIterator
- defaultBreakIterator: RuleBasedBreakIterator
- myanmarSyllableIterator: RuleBasedBreakIterator
- cjkAsWords: boolean
- myanmarAsWords: boolean
- DefaultICUTokenizerConfig(boolean, boolean): void
- combineCJ(): boolean
- getBreakIterator(int): RuleBasedBreakIterator
- getType(int, int): String
- readBreakIterator(String): RuleBasedBreakIterator
-
ICUTokenizer
- reset(): void
- IOBUFFER: int
- buffer: char[]
- length: int
- usableLength: int
- offset: int
- breaker: CompositeBreakIterator
- config: ICUTokenizerConfig
- offsetAtt: OffsetAttribute
- termAtt: CharTermAttribute
- typeAtt: TypeAttribute
- scriptAtt: ScriptAttribute
- ICUTokenizer(): void
- ICUTokenizer(ICUTokenizerConfig): void
- ICUTokenizer(AttributeFactory, ICUTokenizerConfig): void
- incrementToken(): boolean
- end(): void
- findSafeEnd(): int
- refill(): void
- read(Reader, char[], int, int): int
- incrementTokenBuffer(): boolean
- ICUTokenizerConfig
- ICUTokenizerFactory
-
ScriptIterator
- text: char[]
- start: int
- limit: int
- index: int
- scriptStart: int
- scriptLimit: int
- scriptCode: int
- combineCJ: boolean
- ScriptIterator(boolean): void
- getScriptStart(): int
- getScriptLimit(): int
- getScriptCode(): int
- next(): boolean
- isSameScript(int, int): boolean
- setText(char[], int, int): void
- basicLatin: int[]
- static class initializer
- getScript(int): int
-
BreakIteratorWrapper
- tokenattributes
-
icu
- collation
-
analysis
-
lucene
-
apache