eu.interedition.collatex.matching.EditDistanceTokenComparator Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of collatex-core Show documentation

A Java library for collating textual sources, for example, to produce an apparatus.

There is a newer version: 1.7.1

/*
 * Copyright (c) 2015 The Interedition Development Group.
 *
 * This file is part of CollateX.
 *
 * CollateX 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.
 *
 * CollateX 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 CollateX.  If not, see .
 */

package eu.interedition.collatex.matching;

import eu.interedition.collatex.Token;
import eu.interedition.collatex.simple.SimpleToken;

import java.util.Comparator;

public class EditDistanceTokenComparator implements Comparator {

    private final int threshold;

    public EditDistanceTokenComparator() {
        this(1);
    }

    public EditDistanceTokenComparator(int threshold) {
        this.threshold = threshold;
    }

    @Override
    public int compare(Token base, Token witness) {
        final String baseContent = ((SimpleToken) base).getNormalized();
        final String witnessContent = ((SimpleToken) witness).getNormalized();
        return (EditDistance.compute(baseContent, witnessContent) <= threshold) ? 0 : -1;
    }
}