Java 类org.apache.lucene.analysis.en.EnglishMinimalStemFilter 实例源码

@Override
public List<Annotation> annotate(String text) throws Exception {
    text = SimpleTokenizer.format(text);
    Analyzer analyser = new EnglishAnalyzer(Version.LUCENE_47, CharArraySet.EMPTY_SET);
    TokenFilter filter = new EnglishMinimalStemFilter(analyser.tokenStream("text", new StringReader(text)));
    List<Annotation> out = Lists.newArrayList();
    while (filter.incrementToken()) {
        CharTermAttribute az = filter.getAttribute(CharTermAttribute.class);
        OffsetAttribute o = filter.getAttribute(OffsetAttribute.class);
        String token = text.substring(o.startOffset(), o.endOffset());
        String lemma = az.toString();
        Annotation t = new Annotation();
        t.setForm(token);
        t.setLemma(lemma);
        out.add(t);
    }
    if (out.size() == 0) {
        log.debug("Input string is empty");
    }
    filter.close();
    analyser.close();
    return out;
}

@Override
public TokenStream create(TokenStream input) {
  return new EnglishMinimalStemFilter(input);
}

@Override
public TokenStream create(TokenStream input) {
  return new EnglishMinimalStemFilter(input);
}

@Override
public TokenStream create(TokenStream input) {
  return new EnglishMinimalStemFilter(input);
}

@Override
public TokenStream create(TokenStream input) {
  return new EnglishMinimalStemFilter(input);
}

@Override
public TokenStream create(TokenStream input) {
  return new EnglishMinimalStemFilter(input);
}

@Override
public TokenStream create(TokenStream input) {
  return new EnglishMinimalStemFilter(input);
}

@Override
public TokenStream create(TokenStream input) {
  return new EnglishMinimalStemFilter(input);
}