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
21 * positions at which the corresponding symbols are different.
22 *
23 * <p>
24 * For further explanation about the Hamming Distance, take a look at its
25 * Wikipedia page at http://en.wikipedia.org/wiki/Hamming_distance.
26 * </p>
27 *
28 * @since 1.0
29 */
30 public class HammingDistance implements EditDistance<Integer> {
31
32 /**
33 * Find the Hamming Distance between two strings with the same
34 * length.
35 *
36 * <p>The distance starts with zero, and for each occurrence of a
37 * different character in either String, it increments the distance
38 * by 1, and finally return its value.</p>
39 *
40 * <p>Since the Hamming Distance can only be calculated between strings of equal length, input of different lengths
41 * will throw IllegalArgumentException</p>
42 *
43 * <pre>
44 * distance.apply("", "") = 0
45 * distance.apply("pappa", "pappa") = 0
46 * distance.apply("1011101", "1011111") = 1
47 * distance.apply("ATCG", "ACCC") = 2
48 * distance.apply("karolin", "kerstin" = 3
49 * </pre>
50 *
51 * @param left the first CharSequence, must not be null
52 * @param right the second CharSequence, must not be null
53 * @return distance
54 * @throws IllegalArgumentException if either input is {@code null} or
55 * if they do not have the same length
56 */
57 @Override
58 public Integer apply(final CharSequence left, final CharSequence right) {
59 if (left == null || right == null) {
60 throw new IllegalArgumentException("Strings must not be null");
61 }
62
63 if (left.length() != right.length()) {
64 throw new IllegalArgumentException("Strings must have the same length");
65 }
66
67 int distance = 0;
68
69 for (int i = 0; i < left.length(); i++) {
70 if (left.charAt(i) != right.charAt(i)) {
71 distance++;
72 }
73 }
74
75 return distance;
76 }
77
78 }