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 * The hamming distance between two strings of equal length is the number of positions at which the corresponding symbols are different.
21 *
22 * <p>
23 * For further explanation about the Hamming Distance, take a look at its Wikipedia page at https://en.wikipedia.org/wiki/Hamming_distance.
24 * </p>
25 *
26 * @since 1.0
27 */
28 public class HammingDistance implements EditDistance<Integer> {
29
30 /**
31 * Computes the Hamming Distance between two strings with the same length.
32 *
33 * <p>
34 * 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
35 * value.
36 * </p>
37 *
38 * <p>
39 * Since the Hamming Distance can only be calculated between strings of equal length, input of different lengths will throw IllegalArgumentException
40 * </p>
41 *
42 * <pre>
43 * distance.apply("", "") = 0
44 * distance.apply("pappa", "pappa") = 0
45 * distance.apply("1011101", "1011111") = 1
46 * distance.apply("ATCG", "ACCC") = 2
47 * distance.apply("karolin", "kerstin" = 3
48 * </pre>
49 *
50 * @param left the first input, must not be null.
51 * @param right the second input, must not be null.
52 * @return distance.
53 * @throws IllegalArgumentException if either input is {@code null} or if they do not have the same length.
54 */
55 @Override
56 public Integer apply(final CharSequence left, final CharSequence right) {
57 return apply(SimilarityInput.input(left), SimilarityInput.input(right));
58 }
59
60 /**
61 * Computes the Hamming Distance between two strings with the same length.
62 *
63 * <p>
64 * 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
65 * value.
66 * </p>
67 * <p>
68 * Since the Hamming Distance can only be calculated between strings of equal length, input of different lengths will throw IllegalArgumentException
69 * </p>
70 *
71 * <pre>
72 * distance.apply("", "") = 0
73 * distance.apply("pappa", "pappa") = 0
74 * distance.apply("1011101", "1011111") = 1
75 * distance.apply("ATCG", "ACCC") = 2
76 * distance.apply("karolin", "kerstin" = 3
77 * </pre>
78 *
79 * @param <E> The type of similarity score unit.
80 * @param left the first input, must not be null.
81 * @param right the second input, must not be null.
82 * @return distance.
83 * @throws IllegalArgumentException if either input is {@code null} or if they do not have the same length.
84 * @since 1.13.0
85 */
86 public <E> Integer apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
87 if (left == null || right == null) {
88 throw new IllegalArgumentException("SimilarityInput must not be null");
89 }
90 if (left.length() != right.length()) {
91 throw new IllegalArgumentException("SimilarityInput must have the same length");
92 }
93 int distance = 0;
94 for (int i = 0; i < left.length(); i++) {
95 if (!left.at(i).equals(right.at(i))) {
96 distance++;
97 }
98 }
99 return distance;
100 }
101
102 }