Example usage for org.apache.lucene.analysis.de GermanStemFilter GermanStemFilter

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.de GermanStemFilter GermanStemFilter.

Prototype

public GermanStemFilter(TokenStream in) 

Source Link

Document

Creates a GermanStemFilter instance

Usage

From source file:ie.cmrc.smtx.lucene.analysis.EuropeanAnalyzer.java

License:Apache License

/**
 * Returns an aggressive stemming filter suitable for the provided language
 * @param language Two-letter code of a language
 * @param input {@code org.apache.lucene.analysis.TokenStream} input to
 * filter//w  w  w  . j  a va  2 s  .c o  m
 * @return {@code org.apache.lucene.analysis.TokenStream} that filters the
 * provided {@code input}
 */
protected TokenStream getStemFilter(String language, TokenStream input) {
    String lang = language;
    if (lang != null)
        lang = lang.trim().toLowerCase();
    if (SUPPORTED_LANGUAGES.contains(lang)) {
        if (lang.equals(LANG_EN)) {
            return new PorterStemFilter(input);
        } else if (lang.equals(LANG_FR)) {
            return new SnowballFilter(input, new FrenchStemmer());
        } else if (lang.equals(LANG_ES)) {
            return new SnowballFilter(input, new SpanishStemmer());
        } else if (lang.equals(LANG_PT)) {
            return new PortugueseStemFilter(input);
        } else if (lang.equals(LANG_IT)) {
            return new SnowballFilter(input, new ItalianStemmer());
        } else if (lang.equals(LANG_DE)) {
            return new GermanStemFilter(input);
        } else if (lang.equals(LANG_NO)) {
            return new SnowballFilter(input, new NorwegianStemmer());
        }
    }
    return input;
}

---

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

License:Apache License

public GermanStemFilter create(TokenStream in) {
    return new GermanStemFilter(in);
}

---

From source file:org.crosswire.jsword.index.lucene.analysis.GermanLuceneAnalyzer.java

License:Open Source License

@Override
public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new LowerCaseTokenizer(reader);

    if (doStopWords && stopSet != null) {
        result = new StopFilter(false, result, stopSet);
    }/*from  w w  w.j a  v  a  2  s.c  om*/

    if (doStemming) {
        result = new GermanStemFilter(result);
    }

    return result;
}

---

From source file:org.crosswire.jsword.index.lucene.analysis.GermanLuceneAnalyzer.java

License:Open Source License

@Override
public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
        streams = new SavedStreams(new LowerCaseTokenizer(reader));
        if (doStopWords && stopSet != null) {
            streams.setResult(new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion),
                    streams.getResult(), stopSet));
        }//from w ww  . j a v  a 2  s.c o  m

        if (doStemming) {
            streams.setResult(new GermanStemFilter(streams.getResult()));
        }

        setPreviousTokenStream(streams);
    } else {
        streams.getSource().reset(reader);
    }
    return streams.getResult();
}

---

From source file:org.elasticsearch.analysis.common.GermanStemTokenFilterFactory.java

License:Apache License

@Override
public TokenStream create(TokenStream tokenStream) {
    return new GermanStemFilter(new SetKeywordMarkerFilter(tokenStream, exclusions));
}

---