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 * Copyright (C) 2000-2014, International Business Machines Corporation and
29 * others. All Rights Reserved.
30 *******************************************************************************
31 */
32 package sun.text.normalizer;
33
34 import java.text.CharacterIterator;
35 import java.text.Normalizer;
36
37 /**
38 * Unicode Normalization
39 *
40 * <h2>Unicode normalization API</h2>
41 *
42 * <code>normalize</code> transforms Unicode text into an equivalent composed or
43 * decomposed form, allowing for easier sorting and searching of text.
44 * <code>normalize</code> supports the standard normalization forms described in
45 * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode">
46 * Unicode Standard Annex #15 — Unicode Normalization Forms</a>.
47 *
48 * Characters with accents or other adornments can be encoded in
49 * several different ways in Unicode. For example, take the character A-acute.
50 * In Unicode, this can be encoded as a single character (the
51 * "composed" form):
52 *
|
1 /*
2 * Copyright (c) 2005, 2020, 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 * Copyright (C) 2000-2014, International Business Machines Corporation and
29 * others. All Rights Reserved.
30 *******************************************************************************
31 */
32 package jdk.internal.icu.text;
33
34 import jdk.internal.icu.impl.Norm2AllModes;
35
36 import java.text.CharacterIterator;
37 import java.text.Normalizer;
38
39 /**
40 * Unicode Normalization
41 *
42 * <h2>Unicode normalization API</h2>
43 *
44 * <code>normalize</code> transforms Unicode text into an equivalent composed or
45 * decomposed form, allowing for easier sorting and searching of text.
46 * <code>normalize</code> supports the standard normalization forms described in
47 * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode">
48 * Unicode Standard Annex #15 — Unicode Normalization Forms</a>.
49 *
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
53 * "composed" form):
54 *
|