jnode-svn-commits Mailing List for JNode: new Java Operating System (Page 108)

SourceForge Headquarters 1320 Columbia Street Suite 310 San Diego, CA 92101 +1 (858) 422-6466

Revision: 3194
          http://jnode.svn.sourceforge.net/jnode/?rev=3194&view=rev
Author:   lsantha
Date:     2007-05-13 10:03:10 -0700 (Sun, 13 May 2007)

Log Message:
-----------
First merges of OpenJDK.

Added Paths:
-----------
    trunk/core/src/openjdk/java/java/text/
    trunk/core/src/openjdk/java/java/text/Normalizer.java

Added: trunk/core/src/openjdk/java/java/text/Normalizer.java
===================================================================

--- trunk/core/src/openjdk/java/java/text/Normalizer.java	                        (rev 0)
+++ trunk/core/src/openjdk/java/java/text/Normalizer.java	2007-05-13 17:03:10 UTC (rev 3194)
@@ -0,0 +1,183 @@
+/*
+ * Portions Copyright 2005-2006 Sun Microsystems, Inc.  All Rights Reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This code is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 only, as
+ * published by the Free Software Foundation.  Sun designates this
+ * particular file as subject to the "Classpath" exception as provided
+ * by Sun in the LICENSE file that accompanied this code.
+ *
+ * This code is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * version 2 for more details (a copy is included in the LICENSE file that
+ * accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License version
+ * 2 along with this work; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
+ * CA 95054 USA or visit www.sun.com if you need additional information or
+ * have any questions.
+ */
+
+/*
+ *******************************************************************************
+ * (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 &mdash; 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 &mdash; 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);
+    }
+}


This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.




2006	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep	Oct	Nov	Dec (97)
2007	Jan (127)	Feb (34)	Mar (16)	Apr (26)	May (55)	Jun (107)	Jul (36)	Aug (72)	Sep (90)	Oct (41)	Nov (27)	Dec (13)
2008	Jan (37)	Feb (39)	Mar (98)	Apr (115)	May (134)	Jun (120)	Jul (86)	Aug (149)	Sep (68)	Oct (66)	Nov (104)	Dec (49)
2009	Jan (131)	Feb (132)	Mar (125)	Apr (172)	May (161)	Jun (43)	Jul (47)	Aug (38)	Sep (18)	Oct (6)	Nov (1)	Dec (15)
2010	Jan (21)	Feb (8)	Mar (10)	Apr (4)	May (9)	Jun	Jul (1)	Aug	Sep	Oct (2)	Nov	Dec (4)
2011	Jan (23)	Feb (10)	Mar (13)	Apr (3)	May	Jun (19)	Jul (11)	Aug (22)	Sep	Oct (4)	Nov (2)	Dec (12)
2012	Jan (3)	Feb (4)	Mar (7)	Apr (3)	May	Jun (1)	Jul (1)	Aug (30)	Sep (3)	Oct (2)	Nov	Dec (8)
2013	Jan (3)	Feb (40)	Mar	Apr	May	Jun (1)	Jul	Aug	Sep	Oct	Nov (12)	Dec
2021	Jan	Feb	Mar	Apr	May	Jun	Jul	Aug	Sep (2)	Oct	Nov	Dec

jnode-svn-commits Mailing List for JNode: new Java Operating System (Page 108)

jnode-svn-commits — Subversion commit notifications