Example usage for org.apache.lucene.analysis.hunspell HunspellStemFilter HunspellStemFilter

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.hunspell HunspellStemFilter HunspellStemFilter.

Prototype

public HunspellStemFilter(TokenStream input, Dictionary dictionary) 

Source Link

Document

Create a HunspellStemFilter outputting all possible stems.

Usage

From source file:org.apache.solr.analysis.HunspellStemFilterFactory.java

License:Apache License

/**
 * Creates an instance of {@link org.apache.lucene.analysis.hunspell.HunspellStemFilter} that will filter the given
 * TokenStream/*w  w w. ja  va2s  .  c  o m*/
 *
 * @param tokenStream TokenStream that will be filtered
 * @return HunspellStemFilter that filters the TokenStream 
 */
public TokenStream create(TokenStream tokenStream) {
    return new HunspellStemFilter(tokenStream, dictionary);
}

---

From source file:org.elasticsearch.analysis.hunspell.cs.CzechHunspellAnalyzer.java

License:Apache License

@Override
protected TokenStreamComponents createComponents(String field) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StopFilter(source, stopwords);
    if (!this.stemExclusionTable.isEmpty()) {
        result = new SetKeywordMarkerFilter(result, stemExclusionTable);
    }//from w  ww. ja  v  a2s.  c  o m
    result = new HunspellStemFilter(result, dictionary);
    result = new LowerCaseFilter(result);
    return new TokenStreamComponents(source, result);
}

---

From source file:org.elasticsearch.analysis.hunspell.fr.FrenchHunspellAnalyzer.java

License:Apache License

@Override
protected TokenStreamComponents createComponents(String field) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new ElisionFilter(source, FrenchAnalyzer.DEFAULT_ARTICLES);
    result = new StopFilter(result, stopwords);
    if (!this.stemExclusionTable.isEmpty()) {
        result = new SetKeywordMarkerFilter(result, stemExclusionTable);
    }/*from  w  w w. j a  v  a 2 s .  c om*/
    result = new HunspellStemFilter(result, dictionary);
    result = new LowerCaseFilter(result);
    return new TokenStreamComponents(source, result);
}

---

From source file:org.omegat.tokenizer.HunspellTokenizer.java

License:Open Source License

@Override
protected TokenStream getTokenStream(final String strOrig, final boolean stemsAllowed,
        final boolean stopWordsAllowed) {
    if (stemsAllowed) {
        HunspellDictionary dictionary = getDict();
        if (dictionary == null) {
            return new StandardTokenizer(getBehavior(), new StringReader(strOrig));
        }//from   w w  w .  ja v a 2 s. c o  m

        return new HunspellStemFilter(new StandardTokenizer(getBehavior(), new StringReader(strOrig)),
                dictionary);

        /// TODO: implement stop words checks
    } else {
        return new StandardTokenizer(getBehavior(), new StringReader(strOrig));
    }
}

---