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 * The hamming distance between two strings of equal length is the number of 021 * positions at which the corresponding symbols are different. 022 * 023 * <p> 024 * For further explanation about the Hamming Distance, take a look at its 025 * Wikipedia page at https://en.wikipedia.org/wiki/Hamming_distance. 026 * </p> 027 * 028 * @since 1.0 029 */ 030public class HammingDistance implements EditDistance<Integer> { 031 032 /** 033 * Find the Hamming Distance between two strings with the same 034 * length. 035 * 036 * <p>The distance starts with zero, and for each occurrence of a 037 * different character in either String, it increments the distance 038 * by 1, and finally return its value.</p> 039 * 040 * <p>Since the Hamming Distance can only be calculated between strings of equal length, input of different lengths 041 * will throw IllegalArgumentException</p> 042 * 043 * <pre> 044 * distance.apply("", "") = 0 045 * distance.apply("pappa", "pappa") = 0 046 * distance.apply("1011101", "1011111") = 1 047 * distance.apply("ATCG", "ACCC") = 2 048 * distance.apply("karolin", "kerstin" = 3 049 * </pre> 050 * 051 * @param left the first CharSequence, must not be null 052 * @param right the second CharSequence, must not be null 053 * @return distance 054 * @throws IllegalArgumentException if either input is {@code null} or 055 * if they do not have the same length 056 */ 057 @Override 058 public Integer apply(final CharSequence left, final CharSequence right) { 059 if (left == null || right == null) { 060 throw new IllegalArgumentException("CharSequences must not be null"); 061 } 062 063 if (left.length() != right.length()) { 064 throw new IllegalArgumentException("CharSequences must have the same length"); 065 } 066 067 int distance = 0; 068 069 for (int i = 0; i < left.length(); i++) { 070 if (left.charAt(i) != right.charAt(i)) { 071 distance++; 072 } 073 } 074 075 return distance; 076 } 077 078}