Java 类org.apache.lucene.analysis.compound.CompoundWordTokenFilterBase 实例源码

@Override
public void init(Map<String, String> args) {
  super.init(args);
  assureMatchVersion();
  dictFile = args.get("dictionary");
  if (args.containsKey("encoding"))
    encoding = args.get("encoding");
  hypFile = args.get("hyphenator");
  if (null == hypFile) {
    throw new IllegalArgumentException("Missing required parameter: hyphenator");
  }

  minWordSize = getInt("minWordSize", CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE);
  minSubwordSize = getInt("minSubwordSize", CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE);
  maxSubwordSize = getInt("maxSubwordSize", CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE);
  onlyLongestMatch = getBoolean("onlyLongestMatch", false);
}

public AbstractCompoundWordTokenFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);

    minWordSize = settings.getAsInt("min_word_size", CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE);
    minSubwordSize = settings.getAsInt("min_subword_size", CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE);
    maxSubwordSize = settings.getAsInt("max_subword_size", CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE);
    onlyLongestMatch = settings
        .getAsBooleanLenientForPreEs6Indices(indexSettings.getIndexVersionCreated(), "only_longest_match", false, deprecationLogger);
    wordList = Analysis.getWordSet(env, indexSettings.getIndexVersionCreated(), settings, "word_list");
    if (wordList == null) {
        throw new IllegalArgumentException("word_list must be provided for [" + name + "], either as a path to a file, or directly");
    }
}

public AbstractCompoundWordTokenFilterFactory(Index index, Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
    super(index, indexSettings, name, settings);

    minWordSize = settings.getAsInt("min_word_size", CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE);
    minSubwordSize = settings.getAsInt("min_subword_size", CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE);
    maxSubwordSize = settings.getAsInt("max_subword_size", CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE);
    onlyLongestMatch = settings.getAsBoolean("only_longest_match", false);
    wordList = Analysis.getWordSet(env, settings, "word_list");
    if (wordList == null) {
        throw new IllegalArgumentException("word_list must be provided for [" + name + "], either as a path to a file, or directly");
    }
}