J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Portions Copyright 2005-2006 Sun Microsystems, Inc. All Rights Reserved. |
| 3 | * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. |
| 4 | * |
| 5 | * This code is free software; you can redistribute it and/or modify it |
| 6 | * under the terms of the GNU General Public License version 2 only, as |
| 7 | * published by the Free Software Foundation. Sun designates this |
| 8 | * particular file as subject to the "Classpath" exception as provided |
| 9 | * by Sun in the LICENSE file that accompanied this code. |
| 10 | * |
| 11 | * This code is distributed in the hope that it will be useful, but WITHOUT |
| 12 | * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or |
| 13 | * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
| 14 | * version 2 for more details (a copy is included in the LICENSE file that |
| 15 | * accompanied this code). |
| 16 | * |
| 17 | * You should have received a copy of the GNU General Public License version |
| 18 | * 2 along with this work; if not, write to the Free Software Foundation, |
| 19 | * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. |
| 20 | * |
| 21 | * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 22 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 23 | * have any questions. |
| 24 | */ |
| 25 | |
| 26 | /* |
| 27 | ******************************************************************************* |
| 28 | * (C) Copyright IBM Corp. 1996-2005 - All Rights Reserved * |
| 29 | * * |
| 30 | * The original version of this source code and documentation is copyrighted * |
| 31 | * and owned by IBM, These materials are provided under terms of a License * |
| 32 | * Agreement between IBM and Sun. This technology is protected by multiple * |
| 33 | * US and International patents. This notice and attribution to IBM may not * |
| 34 | * to removed. * |
| 35 | ******************************************************************************* |
| 36 | */ |
| 37 | |
| 38 | package java.text; |
| 39 | |
| 40 | import sun.text.normalizer.NormalizerBase; |
| 41 | import sun.text.normalizer.NormalizerImpl; |
| 42 | |
| 43 | /** |
| 44 | * This class provides the method <code>normalize</code> which transforms Unicode |
| 45 | * text into an equivalent composed or decomposed form, allowing for easier |
| 46 | * sorting and searching of text. |
| 47 | * The <code>normalize</code> method supports the standard normalization forms |
| 48 | * described in |
| 49 | * <a href="http://www.unicode.org/unicode/reports/tr15/tr15-23.html"> |
| 50 | * Unicode Standard Annex #15 — Unicode Normalization Forms</a>. |
| 51 | * <p> |
| 52 | * Characters with accents or other adornments can be encoded in |
| 53 | * several different ways in Unicode. For example, take the character A-acute. |
| 54 | * In Unicode, this can be encoded as a single character (the "composed" form): |
| 55 | * |
| 56 | * <p><pre> |
| 57 | * U+00C1 LATIN CAPITAL LETTER A WITH ACUTE</pre> |
| 58 | * </p> |
| 59 | * |
| 60 | * or as two separate characters (the "decomposed" form): |
| 61 | * |
| 62 | * <p><pre> |
| 63 | * U+0041 LATIN CAPITAL LETTER A |
| 64 | * U+0301 COMBINING ACUTE ACCENT</pre> |
| 65 | * </p> |
| 66 | * |
| 67 | * To a user of your program, however, both of these sequences should be |
| 68 | * treated as the same "user-level" character "A with acute accent". When you |
| 69 | * are searching or comparing text, you must ensure that these two sequences are |
| 70 | * treated as equivalent. In addition, you must handle characters with more than |
| 71 | * one accent. Sometimes the order of a character's combining accents is |
| 72 | * significant, while in other cases accent sequences in different orders are |
| 73 | * really equivalent. |
| 74 | * <p> |
| 75 | * Similarly, the string "ffi" can be encoded as three separate letters: |
| 76 | * |
| 77 | * <p><pre> |
| 78 | * U+0066 LATIN SMALL LETTER F |
| 79 | * U+0066 LATIN SMALL LETTER F |
| 80 | * U+0069 LATIN SMALL LETTER I</pre> |
| 81 | * </p> |
| 82 | * |
| 83 | * or as the single character |
| 84 | * |
| 85 | * <p><pre> |
| 86 | * U+FB03 LATIN SMALL LIGATURE FFI</pre> |
| 87 | * </p> |
| 88 | * |
| 89 | * The ffi ligature is not a distinct semantic character, and strictly speaking |
| 90 | * it shouldn't be in Unicode at all, but it was included for compatibility |
| 91 | * with existing character sets that already provided it. The Unicode standard |
| 92 | * identifies such characters by giving them "compatibility" decompositions |
| 93 | * into the corresponding semantic characters. When sorting and searching, you |
| 94 | * will often want to use these mappings. |
| 95 | * <p> |
| 96 | * The <code>normalize</code> method helps solve these problems by transforming |
| 97 | * text into the canonical composed and decomposed forms as shown in the first |
| 98 | * example above. In addition, you can have it perform compatibility |
| 99 | * decompositions so that you can treat compatibility characters the same as |
| 100 | * their equivalents. |
| 101 | * Finally, the <code>normalize</code> method rearranges accents into the |
| 102 | * proper canonical order, so that you do not have to worry about accent |
| 103 | * rearrangement on your own. |
| 104 | * <p> |
| 105 | * The W3C generally recommends to exchange texts in NFC. |
| 106 | * Note also that most legacy character encodings use only precomposed forms and |
| 107 | * often do not encode any combining marks by themselves. For conversion to such |
| 108 | * character encodings the Unicode text needs to be normalized to NFC. |
| 109 | * For more usage examples, see the Unicode Standard Annex. |
| 110 | * |
| 111 | * @since 1.6 |
| 112 | */ |
| 113 | public final class Normalizer { |
| 114 | |
| 115 | private Normalizer() {}; |
| 116 | |
| 117 | /** |
| 118 | * This enum provides constants of the four Unicode normalization forms |
| 119 | * that are described in |
| 120 | * <a href="http://www.unicode.org/unicode/reports/tr15/tr15-23.html"> |
| 121 | * Unicode Standard Annex #15 — Unicode Normalization Forms</a> |
| 122 | * and two methods to access them. |
| 123 | * |
| 124 | * @since 1.6 |
| 125 | */ |
| 126 | public static enum Form { |
| 127 | |
| 128 | /** |
| 129 | * Canonical decomposition. |
| 130 | */ |
| 131 | NFD, |
| 132 | |
| 133 | /** |
| 134 | * Canonical decomposition, followed by canonical composition. |
| 135 | */ |
| 136 | NFC, |
| 137 | |
| 138 | /** |
| 139 | * Compatibility decomposition. |
| 140 | */ |
| 141 | NFKD, |
| 142 | |
| 143 | /** |
| 144 | * Compatibility decomposition, followed by canonical composition. |
| 145 | */ |
| 146 | NFKC |
| 147 | } |
| 148 | |
| 149 | /** |
| 150 | * Normalize a sequence of char values. |
| 151 | * The sequence will be normalized according to the specified normalization |
| 152 | * from. |
| 153 | * @param src The sequence of char values to normalize. |
| 154 | * @param form The normalization form; one of |
| 155 | * {@link java.text.Normalizer.Form#NFC}, |
| 156 | * {@link java.text.Normalizer.Form#NFD}, |
| 157 | * {@link java.text.Normalizer.Form#NFKC}, |
| 158 | * {@link java.text.Normalizer.Form#NFKD} |
| 159 | * @return The normalized String |
| 160 | * @throws NullPointerException If <code>src</code> or <code>form</code> |
| 161 | * is null. |
| 162 | */ |
| 163 | public static String normalize(CharSequence src, Form form) { |
| 164 | return NormalizerBase.normalize(src.toString(), form); |
| 165 | } |
| 166 | |
| 167 | /** |
| 168 | * Determines if the given sequence of char values is normalized. |
| 169 | * @param src The sequence of char values to be checked. |
| 170 | * @param form The normalization form; one of |
| 171 | * {@link java.text.Normalizer.Form#NFC}, |
| 172 | * {@link java.text.Normalizer.Form#NFD}, |
| 173 | * {@link java.text.Normalizer.Form#NFKC}, |
| 174 | * {@link java.text.Normalizer.Form#NFKD} |
| 175 | * @return true if the sequence of char values is normalized; |
| 176 | * false otherwise. |
| 177 | * @throws NullPointerException If <code>src</code> or <code>form</code> |
| 178 | * is null. |
| 179 | */ |
| 180 | public static boolean isNormalized(CharSequence src, Form form) { |
| 181 | return NormalizerBase.isNormalized(src.toString(), form); |
| 182 | } |
| 183 | } |