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 * An edit distance algorithm based on the length of the longest common subsequence between two strings.
21 *
22 * <p>
23 * This code is directly based upon the implementation in {@link LongestCommonSubsequence}.
24 * </p>
25 *
26 * <p>
27 * For reference see: <a href="https://en.wikipedia.org/wiki/Longest_common_subsequence_problem">
28 * https://en.wikipedia.org/wiki/Longest_common_subsequence_problem</a>.
29 * </p>
30 *
31 * <p>For further reading see:</p>
32 *
33 * <p>Lothaire, M. <i>Applied combinatorics on words</i>. New York: Cambridge U Press, 2005. <b>12-13</b></p>
34 *
35 * @since 1.0
36 */
37 public class LongestCommonSubsequenceDistance implements EditDistance<Integer> {
38
39 private final LongestCommonSubsequence longestCommonSubsequence = new LongestCommonSubsequence();
40
41 /**
42 * Calculates an edit distance between two <code>CharSequence</code>'s <code>left</code> and
43 * <code>right</code> as: <code>left.length() + right.length() - 2 * LCS(left, right)</code>, where
44 * <code>LCS</code> is given in {@link LongestCommonSubsequence#apply(CharSequence, CharSequence)}.
45 *
46 * @param left first character sequence
47 * @param right second character sequence
48 * @return distance
49 * @throws IllegalArgumentException
50 * if either String input {@code null}
51 */
52 @Override
53 public Integer apply(final CharSequence left, final CharSequence right) {
54 // Quick return for invalid inputs
55 if (left == null || right == null) {
56 throw new IllegalArgumentException("Inputs must not be null");
57 }
58 return left.length() + right.length() - 2 * longestCommonSubsequence.apply(left, right);
59 }
60
61 }