View Javadoc
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    *      https://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   * Scores {@link CharSequence} similarity, like a {@link String}.
21   * <p>
22   * A string similarity score is intended to have <em>some</em> of the properties of a metric, yet
23   * allowing for exceptions, like the Jaro-Winkler similarity score.
24   * </p>
25   * <p>
26   * A similarity score is the function {@code d: [X * X] -&gt; [0, INFINITY)} with the
27   * following properties:
28   * </p>
29   * <ul>
30   *     <li>{@code d(x,y) &gt;= 0}, non-negativity or separation axiom</li>
31   *     <li>{@code d(x,y) == d(y,x)}, symmetry.</li>
32   * </ul>
33   * <p>
34   * Notice, these are two of the properties that contribute to {@code d} being a metric.
35   * </p>
36   * <p>
37   * Further, this intended to be BiFunction&lt;CharSequence, CharSequence, R&gt;.
38   * The {@code apply} method accepts a pair of {@link CharSequence} parameters
39   * and returns an {@code R} type similarity score.
40   * </p>
41   *
42   * @param <R> The type of similarity score unit.
43   * @since 1.0
44   */
45  public interface SimilarityScore<R> extends ObjectSimilarityScore<CharSequence, R> {
46  
47      /**
48       * Compares two CharSequences.
49       *
50       * @param left  the "left" or "first" input.
51       * @param right the "right" or "second" input.
52       * @return The similarity score between two CharSequences.
53       */
54      @Override
55      R apply(CharSequence left, CharSequence right);
56  
57  }