1 /* 2 * Copyright (C) 2014 The Android Open Source Project 3 * Copyright (c) 2005, 2013, Oracle and/or its affiliates. All rights reserved. 4 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 5 * 6 * This code is free software; you can redistribute it and/or modify it 7 * under the terms of the GNU General Public License version 2 only, as 8 * published by the Free Software Foundation. Oracle designates this 9 * particular file as subject to the "Classpath" exception as provided 10 * by Oracle in the LICENSE file that accompanied this code. 11 * 12 * This code is distributed in the hope that it will be useful, but WITHOUT 13 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 14 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 15 * version 2 for more details (a copy is included in the LICENSE file that 16 * accompanied this code). 17 * 18 * You should have received a copy of the GNU General Public License version 19 * 2 along with this work; if not, write to the Free Software Foundation, 20 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 21 * 22 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 23 * or visit www.oracle.com if you need additional information or have any 24 * questions. 25 */ 26 27 /* 28 ******************************************************************************* 29 * (C) Copyright IBM Corp. 1996-2005 - All Rights Reserved * 30 * * 31 * The original version of this source code and documentation is copyrighted * 32 * and owned by IBM, These materials are provided under terms of a License * 33 * Agreement between IBM and Sun. This technology is protected by multiple * 34 * US and International patents. This notice and attribution to IBM may not * 35 * to removed. * 36 ******************************************************************************* 37 */ 38 39 package java.text; 40 41 /** 42 * This class provides the method <code>normalize</code> which transforms Unicode 43 * text into an equivalent composed or decomposed form, allowing for easier 44 * sorting and searching of text. 45 * The <code>normalize</code> method supports the standard normalization forms 46 * described in 47 * <a href="http://www.unicode.org/unicode/reports/tr15/tr15-23.html"> 48 * Unicode Standard Annex #15 — Unicode Normalization Forms</a>. 49 * <p> 50 * Characters with accents or other adornments can be encoded in 51 * several different ways in Unicode. For example, take the character A-acute. 52 * In Unicode, this can be encoded as a single character (the "composed" form): 53 * 54 * <pre> 55 * U+00C1 LATIN CAPITAL LETTER A WITH ACUTE</pre> 56 * 57 * or as two separate characters (the "decomposed" form): 58 * 59 * <pre> 60 * U+0041 LATIN CAPITAL LETTER A 61 * U+0301 COMBINING ACUTE ACCENT</pre> 62 * 63 * To a user of your program, however, both of these sequences should be 64 * treated as the same "user-level" character "A with acute accent". When you 65 * are searching or comparing text, you must ensure that these two sequences are 66 * treated as equivalent. In addition, you must handle characters with more than 67 * one accent. Sometimes the order of a character's combining accents is 68 * significant, while in other cases accent sequences in different orders are 69 * really equivalent. 70 * <p> 71 * Similarly, the string "ffi" can be encoded as three separate letters: 72 * 73 * <pre> 74 * U+0066 LATIN SMALL LETTER F 75 * U+0066 LATIN SMALL LETTER F 76 * U+0069 LATIN SMALL LETTER I</pre> 77 * 78 * or as the single character 79 * 80 * <pre> 81 * U+FB03 LATIN SMALL LIGATURE FFI</pre> 82 * 83 * The ffi ligature is not a distinct semantic character, and strictly speaking 84 * it shouldn't be in Unicode at all, but it was included for compatibility 85 * with existing character sets that already provided it. The Unicode standard 86 * identifies such characters by giving them "compatibility" decompositions 87 * into the corresponding semantic characters. When sorting and searching, you 88 * will often want to use these mappings. 89 * <p> 90 * The <code>normalize</code> method helps solve these problems by transforming 91 * text into the canonical composed and decomposed forms as shown in the first 92 * example above. In addition, you can have it perform compatibility 93 * decompositions so that you can treat compatibility characters the same as 94 * their equivalents. 95 * Finally, the <code>normalize</code> method rearranges accents into the 96 * proper canonical order, so that you do not have to worry about accent 97 * rearrangement on your own. 98 * <p> 99 * The W3C generally recommends to exchange texts in NFC. 100 * Note also that most legacy character encodings use only precomposed forms and 101 * often do not encode any combining marks by themselves. For conversion to such 102 * character encodings the Unicode text needs to be normalized to NFC. 103 * For more usage examples, see the Unicode Standard Annex. 104 * 105 * @since 1.6 106 */ 107 public final class Normalizer { 108 Normalizer()109 private Normalizer() { 110 } 111 112 /** 113 * This enum provides constants of the four Unicode normalization forms 114 * that are described in 115 * <a href="http://www.unicode.org/unicode/reports/tr15/tr15-23.html"> 116 * Unicode Standard Annex #15 — Unicode Normalization Forms</a> 117 * and two methods to access them. 118 * 119 * @since 1.6 120 */ 121 public enum Form { 122 123 /** 124 * Canonical decomposition. 125 */ 126 NFD(android.icu.text.Normalizer.NFD), 127 128 /** 129 * Canonical decomposition, followed by canonical composition. 130 */ 131 NFC(android.icu.text.Normalizer.NFC), 132 133 /** 134 * Compatibility decomposition. 135 */ 136 NFKD(android.icu.text.Normalizer.NFKD), 137 138 /** 139 * Compatibility decomposition, followed by canonical composition. 140 */ 141 NFKC(android.icu.text.Normalizer.NFKC); 142 143 private final android.icu.text.Normalizer.Mode icuMode; 144 Form(android.icu.text.Normalizer.Mode icuMode)145 Form(android.icu.text.Normalizer.Mode icuMode) { 146 this.icuMode = icuMode; 147 } 148 } 149 150 /** 151 * Normalize a sequence of char values. 152 * The sequence will be normalized according to the specified normalization 153 * from. 154 * 155 * @param src The sequence of char values to normalize. 156 * @param form The normalization form; one of 157 * {@link java.text.Normalizer.Form#NFC}, 158 * {@link java.text.Normalizer.Form#NFD}, 159 * {@link java.text.Normalizer.Form#NFKC}, 160 * {@link java.text.Normalizer.Form#NFKD} 161 * @return The normalized String 162 * @throws NullPointerException If <code>src</code> or <code>form</code> 163 * is null. 164 */ normalize(CharSequence src, Form form)165 public static String normalize(CharSequence src, Form form) { 166 return android.icu.text.Normalizer.normalize(src.toString(), form.icuMode); 167 } 168 169 /** 170 * Determines if the given sequence of char values is normalized. 171 * 172 * @param src The sequence of char values to be checked. 173 * @param form The normalization form; one of 174 * {@link java.text.Normalizer.Form#NFC}, 175 * {@link java.text.Normalizer.Form#NFD}, 176 * {@link java.text.Normalizer.Form#NFKC}, 177 * {@link java.text.Normalizer.Form#NFKD} 178 * @return true if the sequence of char values is normalized; 179 * false otherwise. 180 * @throws NullPointerException If <code>src</code> or <code>form</code> 181 * is null. 182 */ isNormalized(CharSequence src, Form form)183 public static boolean isNormalized(CharSequence src, Form form) { 184 return android.icu.text.Normalizer.isNormalized(src.toString(), form.icuMode, 0); 185 } 186 } 187