How to use

RowAnnotations

in

org.datacleaner.storage

public BooleanAnalyzer(final InputColumn<Boolean>[] columns) {
  _columns = columns;
  _annotationFactory = RowAnnotations.getDefaultFactory();
}

  @Override
  public RowAnnotationFactory createRowAnnotationFactory() {
    return RowAnnotations.getInMemoryFactory(_maxSampleSets, _maxSampleRecords);
  }
}

/**
 * Constructor used for testing and ad-hoc purposes
 *
 * @param column
 * @param groupColumn
 * @param recordUniqueValues
 */
public ValueDistributionAnalyzer(final InputColumn<?> column, final InputColumn<String> groupColumn,
    final boolean recordUniqueValues) {
  this();
  _column = column;
  _groupColumn = groupColumn;
  _recordUniqueValues = recordUniqueValues;
  _annotationFactory = RowAnnotations.getDefaultFactory();
}

public static RowAnnotationFactory getDefaultFactory() {
  return getInMemoryFactory();
}

public RowAnnotation getAnnotation() {
  if (_annotation == null) {
    // only occurs for deserialized instances
    return RowAnnotations.getDefaultFactory().createAnnotation();
  }
  return _annotation;
}

public static RowAnnotationFactory getInMemoryFactory() {
  return getInMemoryFactory(500, 500);
}

@SafeVarargs
public StringAnalyzer(final InputColumn<String>... columns) {
  _columns = columns;
  _annotationFactory = RowAnnotations.getDefaultFactory();
  init();
}

/**
 * Alternative constructor for more ad-hoc usage. Uses an in memory storage
 * mechanism with a threshold on how many rows to store.
 *
 * @param configuration
 * @param inMemoryRowThreshold
 */
public DefaultPatternFinder(final TokenizerConfiguration configuration, final int inMemoryRowThreshold) {
  super(configuration);
  _annotations = new ConcurrentHashMap<>();
  _annotationFactory = RowAnnotations.getInMemoryFactory(100, inMemoryRowThreshold);
}

@SafeVarargs
public NumberAnalyzer(final InputColumn<? extends Number>... columns) {
  this();
  _columns = columns;
  _annotationFactory = RowAnnotations.getDefaultFactory();
  init();
}