1 /*
2 * Copyright (c) 2005, 2015, Oracle and/or its affiliates. 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. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle 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 Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * 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
42 /**
43 * This class provides the method <code>normalize</code> which transforms Unicode
44 * text into an equivalent composed or decomposed form, allowing for easier
45 * sorting and searching of text.
46 * The <code>normalize</code> method supports the standard normalization forms
47 * described in
48 * <a href="http://www.unicode.org/unicode/reports/tr15/tr15-23.html">
49 * Unicode Standard Annex #15 — Unicode Normalization Forms</a>.
50 * <p>
51 * Characters with accents or other adornments can be encoded in
52 * several different ways in Unicode. For example, take the character A-acute.
53 * In Unicode, this can be encoded as a single character (the "composed" form):
54 *
55 * <pre>
56 * U+00C1 LATIN CAPITAL LETTER A WITH ACUTE</pre>
57 *
58 * or as two separate characters (the "decomposed" form):
59 *
60 * <pre>
61 * U+0041 LATIN CAPITAL LETTER A
62 * U+0301 COMBINING ACUTE ACCENT</pre>
63 *
64 * To a user of your program, however, both of these sequences should be
65 * treated as the same "user-level" character "A with acute accent". When you
66 * are searching or comparing text, you must ensure that these two sequences are
67 * treated as equivalent. In addition, you must handle characters with more than
68 * one accent. Sometimes the order of a character's combining accents is
69 * significant, while in other cases accent sequences in different orders are
70 * really equivalent.
71 * <p>
72 * Similarly, the string "ffi" can be encoded as three separate letters:
73 *
74 * <pre>
75 * U+0066 LATIN SMALL LETTER F
76 * U+0066 LATIN SMALL LETTER F
77 * U+0069 LATIN SMALL LETTER I</pre>
78 *
79 * or as the single character
80 *
81 * <pre>
82 * U+FB03 LATIN SMALL LIGATURE FFI</pre>
83 *
84 * The ffi ligature is not a distinct semantic character, and strictly speaking
85 * it shouldn't be in Unicode at all, but it was included for compatibility
86 * with existing character sets that already provided it. The Unicode standard
87 * identifies such characters by giving them "compatibility" decompositions
88 * into the corresponding semantic characters. When sorting and searching, you
89 * will often want to use these mappings.
90 * <p>
91 * The <code>normalize</code> method helps solve these problems by transforming
92 * text into the canonical composed and decomposed forms as shown in the first
93 * example above. In addition, you can have it perform compatibility
94 * decompositions so that you can treat compatibility characters the same as
95 * their equivalents.
96 * Finally, the <code>normalize</code> method rearranges accents into the
97 * proper canonical order, so that you do not have to worry about accent
98 * rearrangement on your own.
99 * <p>
100 * The W3C generally recommends to exchange texts in NFC.
101 * Note also that most legacy character encodings use only precomposed forms and
102 * often do not encode any combining marks by themselves. For conversion to such
103 * character encodings the Unicode text needs to be normalized to NFC.
104 * For more usage examples, see the Unicode Standard Annex.
105 *
106 * @since 1.6
107 */
108 public final class Normalizer {
109
110 private Normalizer() {};
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 static enum Form {
122
123 /**
124 * Canonical decomposition.
125 */
126 NFD,
127
128 /**
129 * Canonical decomposition, followed by canonical composition.
130 */
131 NFC,
132
133 /**
134 * Compatibility decomposition.
135 */
136 NFKD,
137
138 /**
139 * Compatibility decomposition, followed by canonical composition.
140 */
141 NFKC
142 }
143
144 /**
145 * Normalize a sequence of char values.
146 * The sequence will be normalized according to the specified normalization
147 * from.
148 * @param src The sequence of char values to normalize.
149 * @param form The normalization form; one of
150 * {@link java.text.Normalizer.Form#NFC},
151 * {@link java.text.Normalizer.Form#NFD},
152 * {@link java.text.Normalizer.Form#NFKC},
153 * {@link java.text.Normalizer.Form#NFKD}
154 * @return The normalized String
155 * @throws NullPointerException If <code>src</code> or <code>form</code>
156 * is null.
157 */
158 public static String normalize(CharSequence src, Form form) {
159 return NormalizerBase.normalize(src.toString(), form);
160 }
161
162 /**
163 * Determines if the given sequence of char values is normalized.
164 * @param src The sequence of char values to be checked.
165 * @param form The normalization form; one of
166 * {@link java.text.Normalizer.Form#NFC},
167 * {@link java.text.Normalizer.Form#NFD},
168 * {@link java.text.Normalizer.Form#NFKC},
169 * {@link java.text.Normalizer.Form#NFKD}
170 * @return true if the sequence of char values is normalized;
171 * false otherwise.
172 * @throws NullPointerException If <code>src</code> or <code>form</code>
173 * is null.
174 */
175 public static boolean isNormalized(CharSequence src, Form form) {
176 return NormalizerBase.isNormalized(src.toString(), form);
177 }
178 }
179