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 019import org.apache.commons.lang3.Validate; 020 021/** 022 * This stores a {@link EditDistance} implementation and a {@link CharSequence} "left" string. 023 * The {@link #apply(CharSequence right)} method accepts the "right" string and invokes the 024 * comparison function for the pair of strings. 025 * 026 * <p> 027 * The following is an example which finds the most similar string: 028 * </p> 029 * <pre> 030 * EditDistance<Integer> editDistance = new LevenshteinDistance(); 031 * String target = "Apache"; 032 * EditDistanceFrom<Integer> editDistanceFrom = 033 * new EditDistanceFrom<Integer>(editDistance, target); 034 * String mostSimilar = null; 035 * Integer shortestDistance = null; 036 * 037 * for (String test : new String[] { "Appaloosa", "a patchy", "apple" }) { 038 * Integer distance = editDistanceFrom.apply(test); 039 * if (shortestDistance == null || distance < shortestDistance) { 040 * shortestDistance = distance; 041 * mostSimilar = test; 042 * } 043 * } 044 * 045 * System.out.println("The string most similar to \"" + target + "\" " 046 * + "is \"" + mostSimilar + "\" because " 047 * + "its distance is only " + shortestDistance + "."); 048 * </pre> 049 * 050 * @param <R> This is the type of similarity score used by the EditDistance function. 051 * @since 1.0 052 */ 053public class EditDistanceFrom<R> { 054 055 /** 056 * Edit distance. 057 */ 058 private final EditDistance<R> editDistance; 059 /** 060 * Left parameter used in distance function. 061 */ 062 private final CharSequence left; 063 064 /** 065 * This accepts the edit distance implementation and the "left" string. 066 * 067 * @param editDistance This may not be null. 068 * @param left This may be null here, 069 * but the EditDistance#compare(CharSequence left, CharSequence right) 070 * implementation may not accept nulls. 071 */ 072 public EditDistanceFrom(final EditDistance<R> editDistance, final CharSequence left) { 073 Validate.isTrue(editDistance != null, "The edit distance may not be null."); 074 075 this.editDistance = editDistance; 076 this.left = left; 077 } 078 079 /** 080 * This compares "left" field against the "right" parameter 081 * using the "edit distance" implementation. 082 * 083 * @param right the second CharSequence 084 * @return The similarity score between two CharSequences 085 */ 086 public R apply(final CharSequence right) { 087 return editDistance.apply(left, right); 088 } 089 090 /** 091 * Gets the edit distance. 092 * 093 * @return The edit distance 094 */ 095 public EditDistance<R> getEditDistance() { 096 return editDistance; 097 } 098 099 /** 100 * Gets the left parameter. 101 * 102 * @return The left parameter 103 */ 104 public CharSequence getLeft() { 105 return left; 106 } 107 108}