Quadcap Embeddable Database

com/quadcap/util/text/Soundex.java

Go to the documentation of this file.

package com.quadcap.util.text;

/* Copyright 1997 - 2003 Quadcap Software.  All rights reserved.
 *
 * This software is distributed under the Quadcap Free Software License.
 * This software may be used or modified for any purpose, personal or
 * commercial.  Open Source redistributions are permitted.  Commercial
 * redistribution of larger works derived from, or works which bundle
 * this software requires a "Commercial Redistribution License"; see
 * http://www.quadcap.com/purchase.
 *
 * Redistributions qualify as "Open Source" under  one of the following terms:
 *   
 *    Redistributions are made at no charge beyond the reasonable cost of
 *    materials and delivery.
 *
 *    Redistributions are accompanied by a copy of the Source Code or by an
 *    irrevocable offer to provide a copy of the Source Code for up to three
 *    years at the cost of materials and delivery.  Such redistributions
 *    must allow further use, modification, and redistribution of the Source
 *    Code under substantially the same terms as this license.
 *
 * Redistributions of source code must retain the copyright notices as they
 * appear in each source code file, these license terms, and the
 * disclaimer/limitation of liability set forth as paragraph 6 below.
 *
 * Redistributions in binary form must reproduce this Copyright Notice,
 * these license terms, and the disclaimer/limitation of liability set
 * forth as paragraph 6 below, in the documentation and/or other materials
 * provided with the distribution.
 *
 * The Software is provided on an "AS IS" basis.  No warranty is
 * provided that the Software is free of defects, or fit for a
 * particular purpose.  
 *
 * Limitation of Liability. Quadcap Software shall not be liable
 * for any damages suffered by the Licensee or any third party resulting
 * from use of the Software.
 */

/**
 * SOUNDEX Utilities.
 *
 * @author Stan Bailes
 */
public class Soundex {
    static final OctetMap alpha = new OctetMap('a', 'z');
    static final OctetMap Alpha = new OctetMap('A', 'Z');
    static {
        Alpha.include('a', 'z');
    }

    /*                             ABCDEFGHIJKLMNOPQRSTUVWXYZ */
    static final String sMap =    "01230120022455012623010202";
    static final char scode(int c) {
        if (alpha.has(c)) {
            return sMap.charAt(c - 'a');
        } else {                        
            return sMap.charAt(c - 'A');
        }
    }

    public static final String soundex(String s) {
        char[] ret = new char[4];
        char last = 'x';
        int pos = 0;
        for (int i = 0; i < s.length() && pos < 4; i++) {
            int c = s.charAt(i) & 0xff;
            if (Alpha.has(c)) {
                if (pos == 0) {
                    ret[pos++] = Character.toUpperCase((char)c);
                } else {
                    char code = scode(c);
                    if (code != '0' && code != last) {
                        ret[pos++] = code;
                        last = code;
                    }
                }
            }
        }
        if (pos == 0) return "";
        while (pos < 4) ret[pos++] = '0';
        return new String(ret);
    }

    public static final int difference(String a, String b) {
        String sa = soundex(a);
        String sb = soundex(b);
        int diff = 0;
        for (int i = 0; i < 4; i++) {
            if (sa.charAt(i) == sb.charAt(i)) diff++;
        }
        return diff;
    }

    //#ifndef RELEASE
    static String[] data = {
        "blather", "blabber", "Smith", "Smyth", 
        "abcdefghijklmnopqrstuvwxyz", "a", "b", "bed", "BBD",
        "ABCDEFGHIJKLMNOPQRSTUVWXYZ", "smithers", "smothers", "brothers"
    };
    public static void main(String[] args) {
        for (int i = 0; i < data.length; i++) {
            System.out.println(soundex(data[i]) + ": " + data[i]);
        }
    }
    //#endif
}