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 positions at which the corresponding symbols are different.
021 *
022 * <p>
023 * For further explanation about the Hamming Distance, take a look at its Wikipedia page at https://en.wikipedia.org/wiki/Hamming_distance.
024 * </p>
025 *
026 * @since 1.0
027 */
028public class HammingDistance implements EditDistance<Integer> {
029
030    /**
031     * Computes the Hamming Distance between two strings with the same length.
032     *
033     * <p>
034     * The distance starts with zero, and for each occurrence of a different character in either String, it increments the distance by 1, and finally return its
035     * value.
036     * </p>
037     *
038     * <p>
039     * Since the Hamming Distance can only be calculated between strings of equal length, input of different lengths will throw IllegalArgumentException
040     * </p>
041     *
042     * <pre>
043     * distance.apply("", "")               = 0
044     * distance.apply("pappa", "pappa")     = 0
045     * distance.apply("1011101", "1011111") = 1
046     * distance.apply("ATCG", "ACCC")       = 2
047     * distance.apply("karolin", "kerstin"  = 3
048     * </pre>
049     *
050     * @param left  the first input, must not be null.
051     * @param right the second input, must not be null.
052     * @return distance.
053     * @throws IllegalArgumentException if either input is {@code null} or if they do not have the same length.
054     */
055    @Override
056    public Integer apply(final CharSequence left, final CharSequence right) {
057        return apply(SimilarityInput.input(left), SimilarityInput.input(right));
058    }
059
060    /**
061     * Computes the Hamming Distance between two strings with the same length.
062     *
063     * <p>
064     * The distance starts with zero, and for each occurrence of a different character in either String, it increments the distance by 1, and finally return its
065     * value.
066     * </p>
067     * <p>
068     * Since the Hamming Distance can only be calculated between strings of equal length, input of different lengths will throw IllegalArgumentException
069     * </p>
070     *
071     * <pre>
072     * distance.apply("", "")               = 0
073     * distance.apply("pappa", "pappa")     = 0
074     * distance.apply("1011101", "1011111") = 1
075     * distance.apply("ATCG", "ACCC")       = 2
076     * distance.apply("karolin", "kerstin"  = 3
077     * </pre>
078     *
079     * @param <E> The type of similarity score unit.
080     * @param left  the first input, must not be null.
081     * @param right the second input, must not be null.
082     * @return distance.
083     * @throws IllegalArgumentException if either input is {@code null} or if they do not have the same length.
084     * @since 1.13.0
085     */
086    public <E> Integer apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
087        if (left == null || right == null) {
088            throw new IllegalArgumentException("SimilarityInput must not be null");
089        }
090        if (left.length() != right.length()) {
091            throw new IllegalArgumentException("SimilarityInput must have the same length");
092        }
093        int distance = 0;
094        for (int i = 0; i < left.length(); i++) {
095            if (!left.at(i).equals(right.at(i))) {
096                distance++;
097            }
098        }
099        return distance;
100    }
101
102}