001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.text.similarity;
018
019import java.util.HashSet;
020import java.util.Set;
021
022/**
023 * Measures the Jaccard similarity (aka Jaccard index) of two sets of character sequence. Jaccard similarity is the size of the intersection divided by the size
024 * of the union of the two sets.
025 *
026 * <p>
027 * For further explanation about Jaccard Similarity, refer https://en.wikipedia.org/wiki/Jaccard_index
028 * </p>
029 *
030 * @since 1.0
031 */
032public class JaccardSimilarity implements SimilarityScore<Double> {
033
034    /**
035     * Singleton instance.
036     */
037    static final JaccardSimilarity INSTANCE = new JaccardSimilarity();
038
039    /**
040     * Computes the Jaccard Similarity of two set character sequence passed as input.
041     *
042     * @param left  first input sequence.
043     * @param right second input sequence.
044     * @return index.
045     * @throws IllegalArgumentException if either String input {@code null}.
046     */
047    @Override
048    public Double apply(final CharSequence left, final CharSequence right) {
049        return apply(SimilarityInput.input(left), SimilarityInput.input(right));
050    }
051
052    /**
053     * Computes the Jaccard Similarity of two character sequences passed as input. Does the calculation by identifying the union (characters in at least one of
054     * the two sets) of the two sets and intersection (characters which are present in set one which are present in set two)
055     *
056     * @param <E>   The type of similarity score unit.
057     * @param left  first input sequence.
058     * @param right second input sequence.
059     * @return index.
060     * @since 1.13.0
061     */
062    public <E> Double apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
063        if (left == null || right == null) {
064            throw new IllegalArgumentException("Input cannot be null");
065        }
066        final int leftLength = left.length();
067        final int rightLength = right.length();
068        if (leftLength == 0 && rightLength == 0) {
069            return 1d;
070        }
071        if (leftLength == 0 || rightLength == 0) {
072            return 0d;
073        }
074        final Set<E> leftSet = new HashSet<>();
075        for (int i = 0; i < leftLength; i++) {
076            leftSet.add(left.at(i));
077        }
078        final Set<E> rightSet = new HashSet<>();
079        for (int i = 0; i < rightLength; i++) {
080            rightSet.add(right.at(i));
081        }
082        final Set<E> unionSet = new HashSet<>(leftSet);
083        unionSet.addAll(rightSet);
084        final int intersectionSize = leftSet.size() + rightSet.size() - unionSet.size();
085        return 1.0d * intersectionSize / unionSet.size();
086    }
087}