001    /**
002     * Copyright (c) 2000-2013 Liferay, Inc. All rights reserved.
003     *
004     * This library is free software; you can redistribute it and/or modify it under
005     * the terms of the GNU Lesser General Public License as published by the Free
006     * Software Foundation; either version 2.1 of the License, or (at your option)
007     * any later version.
008     *
009     * This library is distributed in the hope that it will be useful, but WITHOUT
010     * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
011     * FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more
012     * details.
013     */
014    
015    package com.liferay.util;
016    
017    import com.liferay.ibm.icu.text.Transliterator;
018    import com.liferay.portal.kernel.util.StringUtil;
019    
020    /**
021     * @author Brian Wing Shun Chan
022     * @author Shuyang Zhou
023     */
024    public class Normalizer {
025    
026            public static String normalizeToAscii(String s) {
027                    if (!_hasNonASCIICode(s)) {
028                            return s;
029                    }
030    
031                    String normalizedText = _transliterator.transform(s);
032    
033                    return StringUtil.replace(
034                            normalizedText, _UNICODE_TEXT, _NORMALIZED_TEXT);
035            }
036    
037            private static boolean _hasNonASCIICode(String s) {
038                    for (int i = 0; i < s.length(); i++) {
039                            if (s.charAt(i) > 127) {
040                                    return true;
041                            }
042                    }
043    
044                    return false;
045            }
046    
047            private static final String[] _NORMALIZED_TEXT = new String[] {
048                    "l", "'", "\""
049            };
050    
051            private static final String[] _UNICODE_TEXT = new String[] {
052                    "\u0142", "\u02B9", "\u02BA"
053            };
054    
055            private static Transliterator _transliterator = Transliterator.getInstance(
056                    "Greek-Latin; Cyrillic-Latin; NFD; [:Nonspacing Mark:] Remove; NFC");
057    
058    }