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; 018 019/** 020 * Measures the Jaccard distance of two sets of character sequence. Jaccard 021 * distance is the dissimilarity between two sets. Its the complementary of 022 * Jaccard similarity. 023 * 024 * <p> 025 * For further explanation about Jaccard Distance, refer 026 * https://en.wikipedia.org/wiki/Jaccard_index 027 * </p> 028 * 029 * @since 1.0 030 */ 031public class JaccardDistance implements EditDistance<Double> { 032 033 private final JaccardSimilarity jaccardSimilarity = new JaccardSimilarity(); 034 035 /** 036 * Calculates Jaccard distance of two set character sequence passed as 037 * input. Calculates Jaccard similarity and returns the complement of it. 038 * 039 * @param left first character sequence 040 * @param right second character sequence 041 * @return index 042 * @throws IllegalArgumentException 043 * if either String input {@code null} 044 */ 045 @Override 046 public Double apply(CharSequence left, CharSequence right) { 047 if (left == null || right == null) { 048 throw new IllegalArgumentException("Input cannot be null"); 049 } 050 return Math.round((1 - jaccardSimilarity.apply(left, right)) * 100d) / 100d; 051 } 052}