public class LuceneHungarianTokenizer extends BaseTokenizer
ITokenizer.StemmingMode
DEFAULT_TOKENS_COUNT, EMPTY_STRING_LIST, EMPTY_TOKENS_LIST, shouldDelegateTokenizeExactly, TOKENIZER_DEBUG_PROVIDER
Constructor and Description |
---|
LuceneHungarianTokenizer() |
Modifier and Type | Method and Description |
---|---|
protected org.apache.lucene.analysis.TokenStream |
getTokenStream(java.lang.String strOrig,
boolean stemsAllowed,
boolean stopWordsAllowed) |
getEffectiveLanguage, getProjectLanguage, getStandardTokenStream, getSupportedLanguages, printTest, test, tokenize, tokenizeByCodePoint, tokenizeByCodePointToStrings, tokenizeToStrings, tokenizeVerbatim, tokenizeVerbatimToStrings, tokenizeWords, tokenizeWordsToStrings
protected org.apache.lucene.analysis.TokenStream getTokenStream(java.lang.String strOrig, boolean stemsAllowed, boolean stopWordsAllowed) throws java.io.IOException
getTokenStream
in class BaseTokenizer
java.io.IOException