< prev index next >

src/java.base/share/classes/java/text/Normalizer.java

Print this page
rev 57619 : imported patch 8174270
   1 /*
   2  * Copyright (c) 2005, 2019, 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} 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} 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 &mdash; 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>


   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  * (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 jdk.internal.icu.text.NormalizerBase;
  41 
  42 /**
  43  * This class provides the method {@code normalize} 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} 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 &mdash; 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>


< prev index next >