com.sun.xml.bind.v2.util.EditDistance Maven / Gradle / Ivy
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
*
* Copyright (c) 1997-2017 Oracle and/or its affiliates. All rights reserved.
*
* The contents of this file are subject to the terms of either the GNU
* General Public License Version 2 only ("GPL") or the Common Development
* and Distribution License("CDDL") (collectively, the "License"). You
* may not use this file except in compliance with the License. You can
* obtain a copy of the License at
* https://oss.oracle.com/licenses/CDDL+GPL-1.1
* or LICENSE.txt. See the License for the specific
* language governing permissions and limitations under the License.
*
* When distributing the software, include this License Header Notice in each
* file and include the License file at LICENSE.txt.
*
* GPL Classpath Exception:
* Oracle designates this particular file as subject to the "Classpath"
* exception as provided by Oracle in the GPL Version 2 section of the License
* file that accompanied this code.
*
* Modifications:
* If applicable, add the following below the License Header, with the fields
* enclosed by brackets [] replaced by your own identifying information:
* "Portions Copyright [year] [name of copyright owner]"
*
* Contributor(s):
* If you wish your version of this file to be governed by only the CDDL or
* only the GPL Version 2, indicate your decision by adding "[Contributor]
* elects to include this software in this distribution under the [CDDL or GPL
* Version 2] license." If you don't indicate a single choice of license, a
* recipient has the option to distribute your version of this file under
* either the CDDL, the GPL Version 2 or to extend the choice of license to
* its licensees as provided above. However, if you add GPL Version 2 code
* and therefore, elected the GPL Version 2 license, then the option applies
* only if the new code is made subject to such option by the copyright
* holder.
*/
package com.sun.xml.bind.v2.util;
import java.util.AbstractMap;
import java.util.Arrays;
import java.util.Collection;
import java.util.WeakHashMap;
/**
* Computes the string edit distance.
*
*
* Refer to a computer science text book for the definition
* of the "string edit distance".
*
* @author
* Kohsuke Kawaguchi ([email protected])
*/
public class EditDistance {
/**
* Weak results cache to avoid additional computations.
* Because of high complexity caching is required.
*/
private static final WeakHashMap, Integer> CACHE = new WeakHashMap, Integer>();
/**
* Computes the edit distance between two strings.
*
*
* The complexity is O(nm) where n=a.length() and m=b.length().
*/
public static int editDistance( String a, String b ) {
// let's check cache
AbstractMap.SimpleEntry entry = new AbstractMap.SimpleEntry(a, b); // using this class to avoid creation of my own which will handle PAIR of values
Integer result = null;
if (CACHE.containsKey(entry))
result = CACHE.get(entry); // looks like we have it
if (result == null) {
result = new EditDistance(a, b).calc();
CACHE.put(entry, result); // cache the result
}
return result;
}
/**
* Finds the string in the group closest to
* key and returns it.
*
* @return null if group.length==0.
*/
public static String findNearest( String key, String[] group ) {
return findNearest(key, Arrays.asList(group));
}
/**
* Finds the string in the group closest to
* key and returns it.
*
* @return null if group.length==0.
*/
public static String findNearest( String key, Collection group ) {
int c = Integer.MAX_VALUE;
String r = null;
for (String s : group) {
int ed = editDistance(key,s);
if( c>ed ) {
c = ed;
r = s;
}
}
return r;
}
/** cost vector. */
private int[] cost;
/** back buffer. */
private int[] back;
/** Two strings to be compared. */
private final String a,b;
private EditDistance( String a, String b ) {
this.a=a;
this.b=b;
cost = new int[a.length()+1];
back = new int[a.length()+1]; // back buffer
for( int i=0; i<=a.length(); i++ )
cost[i] = i;
}
/**
* Swaps two buffers.
*/
private void flip() {
int[] t = cost;
cost = back;
back = t;
}
private int min(int a,int b,int c) {
return Math.min(a,Math.min(b,c));
}
private int calc() {
for( int j=0; j