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     * Creates a new instance.
049     */
050    public JaroWinklerDistance() {
051        // empty
052    }
053
054    /**
055     * Computes the Jaro Winkler Distance between two character sequences.
056     *
057     * <pre>
058     * distance.apply(null, null)          = IllegalArgumentException
059     * distance.apply("foo", null)         = IllegalArgumentException
060     * distance.apply(null, "foo")         = IllegalArgumentException
061     * distance.apply("", "")              = 0.0
062     * distance.apply("foo", "foo")        = 0.0
063     * distance.apply("foo", "foo ")       = 0.06
064     * distance.apply("foo", "foo  ")      = 0.09
065     * distance.apply("foo", " foo ")      = 0.13
066     * distance.apply("foo", "  foo")      = 0.49
067     * distance.apply("", "a")             = 1.0
068     * distance.apply("aaapppp", "")       = 1.0
069     * distance.apply("frog", "fog")       = 0.07
070     * distance.apply("fly", "ant")        = 1.0
071     * distance.apply("elephant", "hippo") = 0.56
072     * distance.apply("hippo", "elephant") = 0.56
073     * distance.apply("hippo", "zzzzzzzz") = 1.0
074     * distance.apply("hello", "hallo")    = 0.12
075     * distance.apply("ABC Corporation", "ABC Corp") = 0.09
076     * distance.apply("D N H Enterprises Inc", "D &amp; H Enterprises, Inc.") = 0.05
077     * distance.apply("My Gym Children's Fitness Center", "My Gym. Childrens Fitness") = 0.08
078     * distance.apply("PENNSYLVANIA", "PENNCISYLVNIA") = 0.12
079     * </pre>
080     *
081     * @param left the first input, must not be null.
082     * @param right the second input, must not be null.
083     * @return result distance.
084     * @throws IllegalArgumentException if either CharSequence input is {@code null}
085     */
086    @Override
087    public Double apply(final CharSequence left, final CharSequence right) {
088        return apply(SimilarityInput.input(left), SimilarityInput.input(right));
089    }
090
091    /**
092     * Computes the Jaro Winkler Distance between two character sequences.
093     *
094     * <pre>
095     * distance.apply(null, null)          = IllegalArgumentException
096     * distance.apply("foo", null)         = IllegalArgumentException
097     * distance.apply(null, "foo")         = IllegalArgumentException
098     * distance.apply("", "")              = 0.0
099     * distance.apply("foo", "foo")        = 0.0
100     * distance.apply("foo", "foo ")       = 0.06
101     * distance.apply("foo", "foo  ")      = 0.09
102     * distance.apply("foo", " foo ")      = 0.13
103     * distance.apply("foo", "  foo")      = 0.49
104     * distance.apply("", "a")             = 1.0
105     * distance.apply("aaapppp", "")       = 1.0
106     * distance.apply("frog", "fog")       = 0.07
107     * distance.apply("fly", "ant")        = 1.0
108     * distance.apply("elephant", "hippo") = 0.56
109     * distance.apply("hippo", "elephant") = 0.56
110     * distance.apply("hippo", "zzzzzzzz") = 1.0
111     * distance.apply("hello", "hallo")    = 0.12
112     * distance.apply("ABC Corporation", "ABC Corp") = 0.09
113     * distance.apply("D N H Enterprises Inc", "D &amp; H Enterprises, Inc.") = 0.05
114     * distance.apply("My Gym Children's Fitness Center", "My Gym. Childrens Fitness") = 0.08
115     * distance.apply("PENNSYLVANIA", "PENNCISYLVNIA") = 0.12
116     * </pre>
117     *
118     * @param <E> The type of similarity score unit.
119     * @param left the first input, must not be null.
120     * @param right the second input, must not be null.
121     * @return result distance.
122     * @throws IllegalArgumentException if either CharSequence input is {@code null}.
123     * @since 1.13.0
124     */
125    public <E> Double apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
126        if (left == null || right == null) {
127            throw new IllegalArgumentException("CharSequences must not be null");
128        }
129        return 1 - JaroWinklerSimilarity.INSTANCE.apply(left, right);
130    }
131}