001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.text.similarity;
018
019/**
020 * Measures the Jaro-Winkler distance of two character sequences.
021 * It is the complementary of Jaro-Winkler similarity.
022 *
023 * @since 1.0
024 */
025public class JaroWinklerDistance implements EditDistance<Double> {
026
027    /**
028     * @deprecated Deprecated as of 1.7. This constant will be removed in 2.0.
029     */
030    @Deprecated
031    public static final int INDEX_NOT_FOUND = -1;
032
033    /**
034     * Computes the Jaro-Winkler string matches, half transpositions, prefix array.
035     *
036     * @param first the first string to be matched.
037     * @param second the second string to be matched.
038     * @return array containing: matches, half transpositions, and prefix
039     * @deprecated Deprecated as of 1.7. This method will be removed in 2.0, and moved to a Jaro Winkler similarity
040     *             class. TODO see TEXT-104.
041     */
042    @Deprecated
043    protected static int[] matches(final CharSequence first, final CharSequence second) {
044        return JaroWinklerSimilarity.matches(first, second);
045    }
046
047    /**
048     * Computes the Jaro Winkler Distance between two character sequences.
049     *
050     * <pre>
051     * distance.apply(null, null)          = IllegalArgumentException
052     * distance.apply("foo", null)         = IllegalArgumentException
053     * distance.apply(null, "foo")         = IllegalArgumentException
054     * distance.apply("", "")              = 0.0
055     * distance.apply("foo", "foo")        = 0.0
056     * distance.apply("foo", "foo ")       = 0.06
057     * distance.apply("foo", "foo  ")      = 0.09
058     * distance.apply("foo", " foo ")      = 0.13
059     * distance.apply("foo", "  foo")      = 0.49
060     * distance.apply("", "a")             = 1.0
061     * distance.apply("aaapppp", "")       = 1.0
062     * distance.apply("frog", "fog")       = 0.07
063     * distance.apply("fly", "ant")        = 1.0
064     * distance.apply("elephant", "hippo") = 0.56
065     * distance.apply("hippo", "elephant") = 0.56
066     * distance.apply("hippo", "zzzzzzzz") = 1.0
067     * distance.apply("hello", "hallo")    = 0.12
068     * distance.apply("ABC Corporation", "ABC Corp") = 0.09
069     * distance.apply("D N H Enterprises Inc", "D &amp; H Enterprises, Inc.") = 0.05
070     * distance.apply("My Gym Children's Fitness Center", "My Gym. Childrens Fitness") = 0.08
071     * distance.apply("PENNSYLVANIA", "PENNCISYLVNIA") = 0.12
072     * </pre>
073     *
074     * @param left the first input, must not be null.
075     * @param right the second input, must not be null.
076     * @return result distance.
077     * @throws IllegalArgumentException if either CharSequence input is {@code null}
078     */
079    @Override
080    public Double apply(final CharSequence left, final CharSequence right) {
081        return apply(SimilarityInput.input(left), SimilarityInput.input(right));
082    }
083
084    /**
085     * Computes the Jaro Winkler Distance between two character sequences.
086     *
087     * <pre>
088     * distance.apply(null, null)          = IllegalArgumentException
089     * distance.apply("foo", null)         = IllegalArgumentException
090     * distance.apply(null, "foo")         = IllegalArgumentException
091     * distance.apply("", "")              = 0.0
092     * distance.apply("foo", "foo")        = 0.0
093     * distance.apply("foo", "foo ")       = 0.06
094     * distance.apply("foo", "foo  ")      = 0.09
095     * distance.apply("foo", " foo ")      = 0.13
096     * distance.apply("foo", "  foo")      = 0.49
097     * distance.apply("", "a")             = 1.0
098     * distance.apply("aaapppp", "")       = 1.0
099     * distance.apply("frog", "fog")       = 0.07
100     * distance.apply("fly", "ant")        = 1.0
101     * distance.apply("elephant", "hippo") = 0.56
102     * distance.apply("hippo", "elephant") = 0.56
103     * distance.apply("hippo", "zzzzzzzz") = 1.0
104     * distance.apply("hello", "hallo")    = 0.12
105     * distance.apply("ABC Corporation", "ABC Corp") = 0.09
106     * distance.apply("D N H Enterprises Inc", "D &amp; H Enterprises, Inc.") = 0.05
107     * distance.apply("My Gym Children's Fitness Center", "My Gym. Childrens Fitness") = 0.08
108     * distance.apply("PENNSYLVANIA", "PENNCISYLVNIA") = 0.12
109     * </pre>
110     *
111     * @param <E> The type of similarity score unit.
112     * @param left the first input, must not be null.
113     * @param right the second input, must not be null.
114     * @return result distance.
115     * @throws IllegalArgumentException if either CharSequence input is {@code null}.
116     * @since 1.13.0
117     */
118    public <E> Double apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
119        if (left == null || right == null) {
120            throw new IllegalArgumentException("CharSequences must not be null");
121        }
122        return 1 - JaroWinklerSimilarity.INSTANCE.apply(left, right);
123    }
124}