1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * http://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.text.similarity;
18
19 /**
20 * Measures the Jaccard distance of two sets of character sequence. Jaccard
21 * distance is the dissimilarity between two sets. Its the complementary of
22 * Jaccard similarity.
23 *
24 * <p>
25 * For further explanation about Jaccard Distance, refer
26 * https://en.wikipedia.org/wiki/Jaccard_index
27 * </p>
28 *
29 * @since 1.0
30 */
31 public class JaccardDistance implements EditDistance<Double> {
32
33 private final JaccardSimilarity jaccardSimilarity = new JaccardSimilarity();
34
35 /**
36 * Calculates Jaccard distance of two set character sequence passed as
37 * input. Calculates Jaccard similarity and returns the complement of it.
38 *
39 * @param left first character sequence
40 * @param right second character sequence
41 * @return index
42 * @throws IllegalArgumentException
43 * if either String input {@code null}
44 */
45 @Override
46 public Double apply(CharSequence left, CharSequence right) {
47 if (left == null || right == null) {
48 throw new IllegalArgumentException("Input cannot be null");
49 }
50 return Math.round((1 - jaccardSimilarity.apply(left, right)) * 100d) / 100d;
51 }
52 }