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 * Interface for <a href="http://en.wikipedia.org/wiki/Edit_distance">Edit Distances</a>.
21 *
22 * <p>
23 * An edit distance is a formal metric on the Kleene closure ({@code X<sup>*</sup>}) over an
24 * alphabet ({@code X}). Note, that a <a href="https://en.wikipedia.org/wiki/Metric_(mathematics)">metric</a>
25 * on a set {@code S} is a function {@code d: [S * S] -> [0, INFINITY)} such
26 * that the following hold for {@code x,y,z} in
27 * the set {@code S}:
28 * </p>
29 * <ul>
30 * <li>{@code d(x,y) >= 0}, non-negativity or separation axiom</li>
31 * <li>{@code d(x,y) == 0}, if and only if, {@code x == y}</li>
32 * <li>{@code d(x,y) == d(y,x)}, symmetry, and</li>
33 * <li>{@code d(x,z) <= d(x,y) + d(y,z)}, the triangle inequality</li>
34 * </ul>
35 *
36 *
37 * <p>
38 * This is a BiFunction<CharSequence, CharSequence, R>.
39 * The {@code apply} method
40 * accepts a pair of {@link CharSequence} parameters
41 * and returns an {@code R} type similarity score.
42 * </p>
43 *
44 * @param <R> The type of similarity score unit used by this EditDistance.
45 * @since 1.0
46 */
47 public interface EditDistance<R> extends SimilarityScore<R> {
48
49 /**
50 * Compares two CharSequences.
51 *
52 * @param left the first CharSequence
53 * @param right the second CharSequence
54 * @return The similarity score between two CharSequences
55 */
56 @Override
57 R apply(CharSequence left, CharSequence right);
58
59 }