001/* ***** BEGIN LICENSE BLOCK *****
002 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
003 *
004 * The contents of this file are subject to the Mozilla Public License Version
005 * 1.1 (the "License"); you may not use this file except in compliance with
006 * the License. You may obtain a copy of the License at
007 * http://www.mozilla.org/MPL/
008 *
009 * Software distributed under the License is distributed on an "AS IS" basis,
010 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
011 * for the specific language governing rights and limitations under the
012 * License.
013 *
014 * The Original Code is part of dcm4che, an implementation of DICOM(TM) in
015 * Java(TM), hosted at https://github.com/gunterze/dcm4che.
016 *
017 * The Initial Developer of the Original Code is
018 * Agfa Healthcare.
019 * Portions created by the Initial Developer are Copyright (C) 2011
020 * the Initial Developer. All Rights Reserved.
021 *
022 * Contributor(s):
023 * See listed authors below.
024 *
025 * Alternatively, the contents of this file may be used under the terms of
026 * either the GNU General Public License Version 2 or later (the "GPL"), or
027 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
028 * in which case the provisions of the GPL or the LGPL are applicable instead
029 * of those above. If you wish to allow use of your version of this file only
030 * under the terms of either the GPL or the LGPL, and not to allow others to
031 * use your version of this file under the terms of the MPL, indicate your
032 * decision by deleting the provisions above and replace them with the notice
033 * and other provisions required by the GPL or the LGPL. If you do not delete
034 * the provisions above, a recipient may use your version of this file under
035 * the terms of any one of the MPL, the GPL or the LGPL.
036 *
037 * ***** END LICENSE BLOCK ***** */
038
039package org.dcm4che3.soundex;
040
041/**
042 * @author Gunter Zeilinger <gunterze@gmail.com>
043 */
044public class Soundex implements FuzzyStr {
045
046    protected static final java.lang.String MAP_6 =
047        // A BCD  E FG  H   I JKLMN  O PQRST  U V  W X  Y Z
048        "\000123\00012\001\00022455\00012623\0001\0012\0002";
049    protected static final java.lang.String MAP_9 = 
050        // A BCD  E FG  H   I JKLMN  O PQRST  U V  W X  Y Z
051        "\000136\00024\001\00043788\00015936\0002\0015\0005";
052
053    private final boolean encodeFirst;
054    private final int codeLength;
055    private final int padLength;
056    private final char[] map;
057
058    public Soundex() {
059        this(false, 4, 4, MAP_6);
060    }
061
062    public Soundex(boolean encodeFirst, int codeLength, int padLength, String map) {
063        this.encodeFirst = encodeFirst;
064        this.codeLength = codeLength;
065        this.padLength = padLength;
066        this.map = map.toCharArray();
067    }
068
069    @Override
070    public String toFuzzy(String s) {
071        if (s == null || s.length() == 0)
072            return "";
073
074        char[] in = s.toCharArray();
075        char[] out = in.length < padLength ? new char[padLength] : in;
076        int i = 0;
077        int j = 0;
078        char prevout = 0;
079        if (!encodeFirst) {
080            while (!Character.isLetter(in[i]))
081                if (++i >= in.length)
082                    return "";
083            prevout = map(out[j++] = Character.toUpperCase(in[i++]));
084        }
085
086        char curout = 0;
087        for (; i < in.length && j < codeLength; i++) {
088            curout = map(in[i]);
089            switch (curout) {
090            case '\0':
091                prevout = curout;
092            case '\1':
093                break;
094            default:
095                if (curout != prevout)
096                    out[j++] = prevout = curout;
097            }
098        }
099        while (j < padLength)
100            out[j++] = '0';
101        return new String(out, 0, j);
102    }
103
104    private char map(char c) {
105        try {
106            return map[c >= 'a' ? c - 'a' : c - 'A'];
107        } catch (IndexOutOfBoundsException e) {
108            return (c == 'ß' || c == 'Ç' || c == 'ç') ? map['c' - 'a'] : '\u0000';
109        }
110    }
111
112    public static void main(String[] args) {
113        Soundex inst = new Soundex();
114        for (String arg : args)
115            System.out.println(inst.toFuzzy(arg));
116    }
117
118}