How to use

getLengthSortedValues

method

in

org.datacleaner.reference.DictionaryConnection

private String capitalizeWordsByDictionaries(final String value) {
  final String preparedString = UCharacter.toTitleCase(value, BreakIterator.getWordInstance());
  for (final DictionaryConnection allWordsDictionaryConnection : allWordsDictionaryConnections) {
    final Iterator<String> lengthSortedValues = allWordsDictionaryConnection.getLengthSortedValues();
    while (lengthSortedValues.hasNext()) {
      final String candidate = lengthSortedValues.next();
      if (candidate.equalsIgnoreCase(value)) {
        return candidate;
      }
    }
  }
  return getAllWords(preparedString).stream().map(this::capitalizeWordByDictionaries)
      .collect(Collectors.joining());
}

@Override
public Iterator<String> getLengthSortedValues() {
  return _dictionary.loadIntoMemory(_datastoreConnection).openConnection(null).getLengthSortedValues();
}

@Initialize
public void init() {
  _dictionaryConnection = _dictionary.openConnection(_configuration);
  multiWordDictionaryPatterns = new LinkedHashMap<>();
  final Iterator<String> allValues = _dictionaryConnection.getLengthSortedValues();
  while (allValues.hasNext()) {
    final String value = allValues.next();
    if (!StringUtils.isSingleWord(value)) {
      final Pattern pattern;
      if (_dictionary.isCaseSensitive()) {
        pattern = Pattern.compile("\\b" + Pattern.quote(value) + "\\b");
      } else {
        pattern = Pattern.compile("\\b" + Pattern.quote(value.toLowerCase()) + "\\b");
      }
      multiWordDictionaryPatterns.put(value, pattern);
    }
  }
}