org.simmetrics.simplifiers.Simplifier Maven / Gradle / Ivy

Go to download
/*
 * SimMetrics - SimMetrics is a java library of Similarity or Distance Metrics,
 * e.g. Levenshtein Distance, that provide float based similarity measures
 * between String Data. All metrics return consistent measures rather than
 * unbounded similarity scores.
 * 
 * Copyright (C) 2014 SimMetrics authors
 * 
 * This file is part of SimMetrics. This program is free software: you can
 * redistribute it and/or modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation, either version 3 of the
 * License, or (at your option) any later version.
 * 
 * This program is distributed in the hope that it will be useful, but WITHOUT ANY
 * WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
 * A PARTICULAR PURPOSE. See the GNU General Public License for more details.
 * 
 * You should have received a copy of the GNU General Public License along with
 * SimMetrics. If not, see .
 */

package org.simmetrics.simplifiers;

import org.simmetrics.StringMetricBuilder;

/**
 * Transforms a string into a simpler form.
 * 
 * 
 * Simplification increases the effectiveness of a metric by removing noise and
 * reducing the dimensionality of the problem. The process maps a a complex
 * string such as Chilpéric II son of Childeric II to a simpler
 * format chilperic ii son of childeric ii. This allows string from
 * different sources to be compared in the same normal form.
 * 
 * 
 * A simplifier can be added onto a metric through the
 * {@link StringMetricBuilder}.
 * 
 * 
 *
 */
public interface Simplifier {

	/**
	 * Simplifiers the input string.
	 * 
	 * @param input
	 *            string to simplify
	 * @return a simplified string
	 */
	public String simplify(String input);

}