1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165
/* * @(#)Normalizer.java 1.1 05/05/13 * * Portions Copyright 2006 Sun Microsystems, Inc. All rights reserved. * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms. */ /* ******************************************************************************* * (C) Copyright IBM Corp. 1996-2005 - All Rights Reserved * * * * The original version of this source code and documentation is copyrighted * * and owned by IBM, These materials are provided under terms of a License * * Agreement between IBM and Sun. This technology is protected by multiple * * US and International patents. This notice and attribution to IBM may not * * to removed. * ******************************************************************************* */ package java.text; import sun.text.normalizer.NormalizerBase; import sun.text.normalizer.NormalizerImpl; /** * This class provides the method <code>normalize</code> which transforms Unicode * text into an equivalent composed or decomposed form, allowing for easier * sorting and searching of text. * The <code>normalize</code> method supports the standard normalization forms * described in * <a href="http://www.unicode.org/unicode/reports/tr15/tr15-23.html"> * Unicode Standard Annex #15 — Unicode Normalization Forms</a>. * <p> * Characters with accents or other adornments can be encoded in * several different ways in Unicode. For example, take the character A-acute. * In Unicode, this can be encoded as a single character (the "composed" form): * * <p><pre> * U+00C1 LATIN CAPITAL LETTER A WITH ACUTE</pre> * </p> * * or as two separate characters (the "decomposed" form): * * <p><pre> * U+0041 LATIN CAPITAL LETTER A * U+0301 COMBINING ACUTE ACCENT</pre> * </p> * * To a user of your program, however, both of these sequences should be * treated as the same "user-level" character "A with acute accent". When you * are searching or comparing text, you must ensure that these two sequences are * treated as equivalent. In addition, you must handle characters with more than * one accent. Sometimes the order of a character's combining accents is * significant, while in other cases accent sequences in different orders are * really equivalent. * <p> * Similarly, the string "ffi" can be encoded as three separate letters: * * <p><pre> * U+0066 LATIN SMALL LETTER F * U+0066 LATIN SMALL LETTER F * U+0069 LATIN SMALL LETTER I</pre> * </p> * * or as the single character * * <p><pre> * U+FB03 LATIN SMALL LIGATURE FFI</pre> * </p> * * The ffi ligature is not a distinct semantic character, and strictly speaking * it shouldn't be in Unicode at all, but it was included for compatibility * with existing character sets that already provided it. The Unicode standard * identifies such characters by giving them "compatibility" decompositions * into the corresponding semantic characters. When sorting and searching, you * will often want to use these mappings. * <p> * The <code>normalize</code> method helps solve these problems by transforming * text into the canonical composed and decomposed forms as shown in the first * example above. In addition, you can have it perform compatibility * decompositions so that you can treat compatibility characters the same as * their equivalents. * Finally, the <code>normalize</code> method rearranges accents into the * proper canonical order, so that you do not have to worry about accent * rearrangement on your own. * <p> * The W3C generally recommends to exchange texts in NFC. * Note also that most legacy character encodings use only precomposed forms and * often do not encode any combining marks by themselves. For conversion to such * character encodings the Unicode text needs to be normalized to NFC. * For more usage examples, see the Unicode Standard Annex. * * @since 1.6 */ public final class Normalizer { private Normalizer() {}; /** * This enum provides constants of the four Unicode normalization forms * that are described in * <a href="http://www.unicode.org/unicode/reports/tr15/tr15-23.html"> * Unicode Standard Annex #15 — Unicode Normalization Forms</a> * and two methods to access them. * * @since 1.6 */ public static enum Form { /** * Canonical decomposition. */ NFD, /** * Canonical decomposition, followed by canonical composition. */ NFC, /** * Compatibility decomposition. */ NFKD, /** * Compatibility decomposition, followed by canonical composition. */ NFKC } /** * Normalize a sequence of char values. * The sequence will be normalized according to the specified normalization * from. * @param src The sequence of char values to normalize. * @param form The normalization form; one of * {@link java.text.Normalizer.Form#NFC}, * {@link java.text.Normalizer.Form#NFD}, * {@link java.text.Normalizer.Form#NFKC}, * {@link java.text.Normalizer.Form#NFKD} * @return The normalized String * @throws NullPointerException If <code>src</code> or <code>form</code> * is null. */ public static String normalize(CharSequence src, Form form) { return NormalizerBase.normalize(src.toString(), form); } /** * Determines if the given sequence of char values is normalized. * @param src The sequence of char values to be checked. * @param form The normalization form; one of * {@link java.text.Normalizer.Form#NFC}, * {@link java.text.Normalizer.Form#NFD}, * {@link java.text.Normalizer.Form#NFKC}, * {@link java.text.Normalizer.Form#NFKD} * @return true if the sequence of char values is normalized; * false otherwise. * @throws NullPointerException If <code>src</code> or <code>form</code> * is null. */ public static boolean isNormalized(CharSequence src, Form form) { return NormalizerBase.isNormalized(src.toString(), form); } }