Java 类org.apache.lucene.analysis.ngram.EdgeNGramTokenizer 实例源码

@Override
public Tokenizer create() {
    if (matcher == null) {
        return new EdgeNGramTokenizer(minGram, maxGram);
    } else {
        return new EdgeNGramTokenizer(minGram, maxGram) {
            @Override
            protected boolean isTokenChar(int chr) {
                return matcher.isTokenChar(chr);
            }
        };
    }
}

@Override
public void init(Map<String, String> args) {
  super.init(args);
  String maxArg = args.get("maxGramSize");
  maxGramSize = (maxArg != null ? Integer.parseInt(maxArg) : EdgeNGramTokenizer.DEFAULT_MAX_GRAM_SIZE);

  String minArg = args.get("minGramSize");
  minGramSize = (minArg != null ? Integer.parseInt(minArg) : EdgeNGramTokenizer.DEFAULT_MIN_GRAM_SIZE);

  side = args.get("side");
  if (side == null) {
    side = EdgeNGramTokenizer.Side.FRONT.getLabel();
  }
}

@Override
public EdgeNGramTokenizer create(Reader input) {
  return new EdgeNGramTokenizer(input, side, minGramSize, maxGramSize);
}

@Override public Object create(Random random) {
  return random.nextBoolean() 
      ? EdgeNGramTokenizer.Side.FRONT 
      : EdgeNGramTokenizer.Side.BACK;
}

@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
  return new TokenStreamComponents(new EdgeNGramTokenizer(reader, EdgeNGramTokenizer.Side.BACK,
      10, 20));
}