/*
 * @(#)Character.java	1.30 04/06/28
 *
 * Copyright 2004 Sun Microsystems, Inc. All rights reserved.
 * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
 */

package java.lang;
import java.util.Map;
import java.util.HashMap;
import java.util.Locale;

/**
 * The <code>Character</code> class wraps a value of the primitive
 * type <code>char</code> in an object. An object of type
 * <code>Character</code> contains a single field whose type is
 * <code>char</code>.
 * <p>
 * In addition, this class provides several methods for determining
 * a character's category (lowercase letter, digit, etc.) and for converting
 * characters from uppercase to lowercase and vice versa.
 * <p>
 * Character information is based on the Unicode Standard, version 4.0.
 * <p>
 * The methods and data of class <code>Character</code> are defined by
 * the information in the <i>UnicodeData</i> file that is part of the
 * Unicode Character Database maintained by the Unicode
 * Consortium. This file specifies various properties including name
 * and general category for every defined Unicode code point or
 * character range.
 * <p>
 * The file and its description are available from the Unicode Consortium at:
 * <ul>
 * <li><a href="http://www.unicode.org">http://www.unicode.org</a>
 * </ul>
 *
 * <h4><a name="unicode">Unicode Character Representations</a></h4>
 *
 * <p>The <code>char</code> data type (and therefore the value that a
 * <code>Character</code> object encapsulates) are based on the
 * original Unicode specification, which defined characters as
 * fixed-width 16-bit entities. The Unicode standard has since been
 * changed to allow for characters whose representation requires more
 * than 16 bits.  The range of legal <em>code point</em>s is now
 * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>.
 * (Refer to the <a
 * href="http://www.unicode.org/reports/tr27/#notation"><i>
 * definition</i></a> of the U+<i>n</i> notation in the Unicode
 * standard.)
 *
 * <p>The set of characters from U+0000 to U+FFFF is sometimes
 * referred to as the <em>Basic Multilingual Plane (BMP)</em>. <a
 * name="supplementary">Characters</a> whose code points are greater
 * than U+FFFF are called <em>supplementary character</em>s.  The Java
 * 2 platform uses the UTF-16 representation in <code>char</code>
 * arrays and in the <code>String</code> and <code>StringBuffer</code>
 * classes. In this representation, supplementary characters are
 * represented as a pair of <code>char</code> values, the first from
 * the <em>high-surrogates</em> range, (\uD800-\uDBFF), the
 * second from the <em>low-surrogates</em> range
 * (\uDC00-\uDFFF).
 *
 * <p>A <code>char</code> value, therefore, represents Basic
 * Multilingual Plane (BMP) code points, including the surrogate
 * code points, or code units of the UTF-16 encoding. An
 * <code>int</code> value represents all Unicode code points,
 * including supplementary code points. The lower (least significant)
 * 21 bits of <code>int</code> are used to represent Unicode code
 * points and the upper (most significant) 11 bits must be zero.
 * Unless otherwise specified, the behavior with respect to
 * supplementary characters and surrogate <code>char</code> values is
 * as follows:
 *
 * <ul>
 * <li>The methods that only accept a <code>char</code> value cannot support
 * supplementary characters. They treat <code>char</code> values from the
 * surrogate ranges as undefined characters. For example,
 * <code>Character.isLetter('\uD840')</code> returns <code>false</code>, even though
 * this specific value if followed by any low-surrogate value in a string
 * would represent a letter.
 *
 * <li>The methods that accept an <code>int</code> value support all
 * Unicode characters, including supplementary characters. For
 * example, <code>Character.isLetter(0x2F81A)</code> returns
 * <code>true</code> because the code point value represents a letter
 * (a CJK ideograph).
 * </ul>
 *
 * <p>In the J2SE API documentation, <em>Unicode code point</em> is
 * used for character values in the range between U+0000 and U+10FFFF,
 * and <em>Unicode code unit</em> is used for 16-bit
 * <code>char</code> values that are code units of the <em>UTF-16</em>
 * encoding. For more information on Unicode terminology, refer to the
 * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>.
 *
 * @author  Lee Boynton
 * @author  Guy Steele
 * @author  Akira Tanaka
 * @since   1.0
 */
public final
class Character extends Object implements java.io.Serializable, Comparable<Character> {
    /**
     * The minimum radix available for conversion to and from strings.
     * The constant value of this field is the smallest value permitted
     * for the radix argument in radix-conversion methods such as the
     * <code>digit</code> method, the <code>forDigit</code>
     * method, and the <code>toString</code> method of class
     * <code>Integer</code>.
     *
     * @see     java.lang.Character#digit(char, int)
     * @see     java.lang.Character#forDigit(int, int)
     * @see     java.lang.Integer#toString(int, int)
     * @see     java.lang.Integer#valueOf(java.lang.String)
     */
    public static final int MIN_RADIX = 2;

    /**
     * The maximum radix available for conversion to and from strings.
     * The constant value of this field is the largest value permitted
     * for the radix argument in radix-conversion methods such as the
     * <code>digit</code> method, the <code>forDigit</code>
     * method, and the <code>toString</code> method of class
     * <code>Integer</code>.
     *
     * @see     java.lang.Character#digit(char, int)
     * @see     java.lang.Character#forDigit(int, int)
     * @see     java.lang.Integer#toString(int, int)
     * @see     java.lang.Integer#valueOf(java.lang.String)
     */
    public static final int MAX_RADIX = 36;

    /**
     * The constant value of this field is the smallest value of type
     * <code>char</code>, <code>'\u0000'</code>.
     *
     * @since   1.0.2
     */
    public static final char   MIN_VALUE = '\u0000';

    /**
     * The constant value of this field is the largest value of type
     * <code>char</code>, <code>'\uFFFF'</code>.
     *
     * @since   1.0.2
     */
    public static final char   MAX_VALUE = '\uffff';

    /**
     * The <code>Class</code> instance representing the primitive type
     * <code>char</code>.
     *
     * @since   1.1
     */
    public static final Class<Character> TYPE = Class.getPrimitiveClass("char");

   /*
    * Normative general types
    */

   /*
    * General character types
    */

   /**
    * General category "Cn" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        UNASSIGNED                  = 0;

   /**
    * General category "Lu" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        UPPERCASE_LETTER            = 1;

   /**
    * General category "Ll" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        LOWERCASE_LETTER            = 2;

   /**
    * General category "Lt" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        TITLECASE_LETTER            = 3;

   /**
    * General category "Lm" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        MODIFIER_LETTER             = 4;

   /**
    * General category "Lo" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        OTHER_LETTER                = 5;

   /**
    * General category "Mn" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        NON_SPACING_MARK            = 6;

   /**
    * General category "Me" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        ENCLOSING_MARK              = 7;

   /**
    * General category "Mc" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        COMBINING_SPACING_MARK      = 8;

   /**
    * General category "Nd" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        DECIMAL_DIGIT_NUMBER        = 9;

   /**
    * General category "Nl" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        LETTER_NUMBER               = 10;

   /**
    * General category "No" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        OTHER_NUMBER                = 11;

   /**
    * General category "Zs" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        SPACE_SEPARATOR             = 12;

   /**
    * General category "Zl" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        LINE_SEPARATOR              = 13;

   /**
    * General category "Zp" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        PARAGRAPH_SEPARATOR         = 14;

   /**
    * General category "Cc" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        CONTROL                     = 15;

   /**
    * General category "Cf" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        FORMAT                      = 16;

   /**
    * General category "Co" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        PRIVATE_USE                 = 18;

   /**
    * General category "Cs" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        SURROGATE                   = 19;

   /**
    * General category "Pd" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        DASH_PUNCTUATION            = 20;

   /**
    * General category "Ps" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        START_PUNCTUATION           = 21;

   /**
    * General category "Pe" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        END_PUNCTUATION             = 22;

   /**
    * General category "Pc" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        CONNECTOR_PUNCTUATION       = 23;

   /**
    * General category "Po" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        OTHER_PUNCTUATION           = 24;

   /**
    * General category "Sm" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        MATH_SYMBOL                 = 25;

   /**
    * General category "Sc" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        CURRENCY_SYMBOL             = 26;

   /**
    * General category "Sk" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        MODIFIER_SYMBOL             = 27;

   /**
    * General category "So" in the Unicode specification.
    * @since   1.1
    */
    public static final byte
        OTHER_SYMBOL                = 28;

   /**
    * General category "Pi" in the Unicode specification.
    * @since   1.4
    */
    public static final byte
        INITIAL_QUOTE_PUNCTUATION   = 29;

   /**
    * General category "Pf" in the Unicode specification.
    * @since   1.4
    */
    public static final byte
        FINAL_QUOTE_PUNCTUATION     = 30;

    /**
     * Error or non-char flag
     * @since 1.4
     */
     static final char CHAR_ERROR = '\uFFFF';


    /**
     * Undefined bidirectional character type. Undefined <code>char</code>
     * values have undefined directionality in the Unicode specification.
     * @since 1.4
     */
     public static final byte DIRECTIONALITY_UNDEFINED = -1;

    /**
     * Strong bidirectional character type "L" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;

    /**
     * Strong bidirectional character type "R" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;

    /**
    * Strong bidirectional character type "AL" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;

    /**
     * Weak bidirectional character type "EN" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;

    /**
     * Weak bidirectional character type "ES" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;

    /**
     * Weak bidirectional character type "ET" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;

    /**
     * Weak bidirectional character type "AN" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;

    /**
     * Weak bidirectional character type "CS" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;

    /**
     * Weak bidirectional character type "NSM" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;

    /**
     * Weak bidirectional character type "BN" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;

    /**
     * Neutral bidirectional character type "B" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;

    /**
     * Neutral bidirectional character type "S" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;

    /**
     * Neutral bidirectional character type "WS" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_WHITESPACE = 12;

    /**
     * Neutral bidirectional character type "ON" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;

    /**
     * Strong bidirectional character type "LRE" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;

    /**
     * Strong bidirectional character type "LRO" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;

    /**
     * Strong bidirectional character type "RLE" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;

    /**
     * Strong bidirectional character type "RLO" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;

    /**
     * Weak bidirectional character type "PDF" in the Unicode specification.
     * @since 1.4
     */
    public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;

    /**
     * The minimum value of a Unicode high-surrogate code unit in the
     * UTF-16 encoding. A high-surrogate is also known as a
     * <i>leading-surrogate</i>.
     *
     * @since 1.5
     */
    public static final char MIN_HIGH_SURROGATE = '\uD800';

    /**
     * The maximum value of a Unicode high-surrogate code unit in the
     * UTF-16 encoding. A high-surrogate is also known as a
     * <i>leading-surrogate</i>.
     *
     * @since 1.5
     */
    public static final char MAX_HIGH_SURROGATE = '\uDBFF';

    /**
     * The minimum value of a Unicode low-surrogate code unit in the
     * UTF-16 encoding. A low-surrogate is also known as a
     * <i>trailing-surrogate</i>.
     *
     * @since 1.5
     */
    public static final char MIN_LOW_SURROGATE  = '\uDC00';

    /**
     * The maximum value of a Unicode low-surrogate code unit in the
     * UTF-16 encoding. A low-surrogate is also known as a
     * <i>trailing-surrogate</i>.
     *
     * @since 1.5
     */
    public static final char MAX_LOW_SURROGATE  = '\uDFFF';

    /**
     * The minimum value of a Unicode surrogate code unit in the UTF-16 encoding.
     *
     * @since 1.5
     */
    public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;

    /**
     * The maximum value of a Unicode surrogate code unit in the UTF-16 encoding.
     *
     * @since 1.5
     */
    public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;

    /**
     * The minimum value of a supplementary code point.
     *
     * @since 1.5
     */
    public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;

    /**
     * The minimum value of a Unicode code point.
     * 
     * @since 1.5
     */
    public static final int MIN_CODE_POINT = 0x000000;

    /**
     * The maximum value of a Unicode code point.
     *
     * @since 1.5
     */
    public static final int MAX_CODE_POINT = 0x10ffff;


    /**
     * Instances of this class represent particular subsets of the Unicode
     * character set.  The only family of subsets defined in the
     * <code>Character</code> class is <code>{@link Character.UnicodeBlock
     * UnicodeBlock}</code>.  Other portions of the Java API may define other
     * subsets for their own purposes.
     *
     * @since 1.2
     */
    public static class Subset  {

        private String name;

        /**
         * Constructs a new <code>Subset</code> instance.
         *
         * @exception NullPointerException if name is <code>null</code>
         * @param  name  The name of this subset
         */
        protected Subset(String name) {
            if (name == null) {
                throw new NullPointerException("name");
            }
            this.name = name;
        }

        /**
         * Compares two <code>Subset</code> objects for equality.
         * This method returns <code>true</code> if and only if
         * <code>this</code> and the argument refer to the same
         * object; since this method is <code>final</code>, this
         * guarantee holds for all subclasses.
         */
        public final boolean equals(Object obj) {
            return (this == obj);
        }

        /**
         * Returns the standard hash code as defined by the
         * <code>{@link Object#hashCode}</code> method.  This method
         * is <code>final</code> in order to ensure that the
         * <code>equals</code> and <code>hashCode</code> methods will
         * be consistent in all subclasses.
         */
        public final int hashCode() {
            return super.hashCode();
        }

        /**
         * Returns the name of this subset.
         */
        public final String toString() {
            return name;
        }
    }

    /**
     * A family of character subsets representing the character blocks in the
     * Unicode specification. Character blocks generally define characters
     * used for a specific script or purpose. A character is contained by
     * at most one Unicode block.
     *
     * @since 1.2
     */
    public static final class UnicodeBlock extends Subset {

        private static Map map = new HashMap();

        /**
         * Create a UnicodeBlock with the given identifier name. 
         * This name must be the same as the block identifier.
         */
        private UnicodeBlock(String idName) {
            super(idName);
            map.put(idName.toUpperCase(Locale.US), this);
        }

        /**
         * Create a UnicodeBlock with the given identifier name and
         * alias name.
         */
        private UnicodeBlock(String idName, String alias) {
            this(idName);
            map.put(alias.toUpperCase(Locale.US), this);
        }

        /** 
         * Create a UnicodeBlock with the given identifier name and 
         * alias names.
         */
        private UnicodeBlock(String idName, String[] aliasName) {
            this(idName);
            if (aliasName != null) {
                for(int x=0; x<aliasName.length; ++x) {
                    map.put(aliasName[x].toUpperCase(Locale.US), this);
                }
            }
        }

        /**
         * Constant for the "Basic Latin" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock  BASIC_LATIN = 
            new UnicodeBlock("BASIC_LATIN", new String[] {"Basic Latin", "BasicLatin" });

        /**
         * Constant for the "Latin-1 Supplement" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock LATIN_1_SUPPLEMENT =
            new UnicodeBlock("LATIN_1_SUPPLEMENT", new String[]{ "Latin-1 Supplement", "Latin-1Supplement"});

        /**
         * Constant for the "Latin Extended-A" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock LATIN_EXTENDED_A = 
            new UnicodeBlock("LATIN_EXTENDED_A", new String[]{ "Latin Extended-A", "LatinExtended-A"});

        /**
         * Constant for the "Latin Extended-B" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock LATIN_EXTENDED_B = 
            new UnicodeBlock("LATIN_EXTENDED_B", new String[] {"Latin Extended-B", "LatinExtended-B"});

        /**
         * Constant for the "IPA Extensions" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock IPA_EXTENSIONS = 
            new UnicodeBlock("IPA_EXTENSIONS", new String[] {"IPA Extensions", "IPAExtensions"});

        /**
         * Constant for the "Spacing Modifier Letters" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock SPACING_MODIFIER_LETTERS = 
            new UnicodeBlock("SPACING_MODIFIER_LETTERS", new String[] { "Spacing Modifier Letters",
                                                                        "SpacingModifierLetters"});

        /**
         * Constant for the "Combining Diacritical Marks" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS = 
            new UnicodeBlock("COMBINING_DIACRITICAL_MARKS", new String[] {"Combining Diacritical Marks",
                                                                          "CombiningDiacriticalMarks" });

        /**
         * Constant for the "Greek and Coptic" Unicode character block.
         * <p>
         * This block was previously known as the "Greek" block.
         *
         * @since 1.2
         */
        public static final UnicodeBlock GREEK 
            = new UnicodeBlock("GREEK", new String[] {"Greek and Coptic", "GreekandCoptic"});

        /**
         * Constant for the "Cyrillic" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CYRILLIC = 
            new UnicodeBlock("CYRILLIC");

        /**
         * Constant for the "Armenian" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ARMENIAN = 
            new UnicodeBlock("ARMENIAN");

        /**
         * Constant for the "Hebrew" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock HEBREW = 
            new UnicodeBlock("HEBREW");

        /**
         * Constant for the "Arabic" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ARABIC = 
            new UnicodeBlock("ARABIC");

        /**
         * Constant for the "Devanagari" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock DEVANAGARI = 
            new UnicodeBlock("DEVANAGARI");

        /**
         * Constant for the "Bengali" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock BENGALI =
            new UnicodeBlock("BENGALI");

        /**
         * Constant for the "Gurmukhi" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock GURMUKHI = 
            new UnicodeBlock("GURMUKHI");

        /**
         * Constant for the "Gujarati" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock GUJARATI = 
            new UnicodeBlock("GUJARATI");

        /**
         * Constant for the "Oriya" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ORIYA = 
            new UnicodeBlock("ORIYA");

        /**
         * Constant for the "Tamil" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock TAMIL = 
            new UnicodeBlock("TAMIL");

        /**
         * Constant for the "Telugu" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock TELUGU = 
            new UnicodeBlock("TELUGU");

        /**
         * Constant for the "Kannada" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock KANNADA = 
            new UnicodeBlock("KANNADA");

        /**
         * Constant for the "Malayalam" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock MALAYALAM =
            new UnicodeBlock("MALAYALAM");

        /**
         * Constant for the "Thai" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock THAI = 
            new UnicodeBlock("THAI");

        /**
         * Constant for the "Lao" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock LAO = 
            new UnicodeBlock("LAO");

        /**
         * Constant for the "Tibetan" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock TIBETAN = 
            new UnicodeBlock("TIBETAN");

        /**
         * Constant for the "Georgian" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock GEORGIAN =
            new UnicodeBlock("GEORGIAN");

        /**
         * Constant for the "Hangul Jamo" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock HANGUL_JAMO = 
            new UnicodeBlock("HANGUL_JAMO", new String[] {"Hangul Jamo", "HangulJamo"});

        /**
         * Constant for the "Latin Extended Additional" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL = 
            new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL", new String[] {"Latin Extended Additional",
                                                                        "LatinExtendedAdditional"});

        /**
         * Constant for the "Greek Extended" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock GREEK_EXTENDED = 
            new UnicodeBlock("GREEK_EXTENDED", new String[] {"Greek Extended", "GreekExtended"});

        /**
         * Constant for the "General Punctuation" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock GENERAL_PUNCTUATION = 
            new UnicodeBlock("GENERAL_PUNCTUATION", new String[] {"General Punctuation", "GeneralPunctuation"});

        /**
         * Constant for the "Superscripts and Subscripts" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS = 
            new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS", new String[] {"Superscripts and Subscripts",
                                                                          "SuperscriptsandSubscripts" });

        /**
         * Constant for the "Currency Symbols" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CURRENCY_SYMBOLS = 
            new UnicodeBlock("CURRENCY_SYMBOLS", new String[] { "Currency Symbols", "CurrencySymbols"});

        /**
         * Constant for the "Combining Diacritical Marks for Symbols" Unicode character block.
         * <p>
         * This block was previously known as "Combining Marks for Symbols".
         * @since 1.2
         */
        public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS = 
            new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS", new String[] {"Combining Diacritical Marks for Symbols",
                                                                                                                                                  "CombiningDiacriticalMarksforSymbols",
                                                                          "Combining Marks for Symbols",
                                                                          "CombiningMarksforSymbols" });

        /**
         * Constant for the "Letterlike Symbols" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock LETTERLIKE_SYMBOLS = 
            new UnicodeBlock("LETTERLIKE_SYMBOLS", new String[] { "Letterlike Symbols", "LetterlikeSymbols"});

        /**
         * Constant for the "Number Forms" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock NUMBER_FORMS = 
            new UnicodeBlock("NUMBER_FORMS", new String[] {"Number Forms", "NumberForms"});

        /**
         * Constant for the "Arrows" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ARROWS = 
            new UnicodeBlock("ARROWS");

        /**
         * Constant for the "Mathematical Operators" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock MATHEMATICAL_OPERATORS = 
            new UnicodeBlock("MATHEMATICAL_OPERATORS", new String[] {"Mathematical Operators",
                                                                     "MathematicalOperators"});

        /**
         * Constant for the "Miscellaneous Technical" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock MISCELLANEOUS_TECHNICAL = 
            new UnicodeBlock("MISCELLANEOUS_TECHNICAL", new String[] {"Miscellaneous Technical",
                                                                      "MiscellaneousTechnical"});

        /**
         * Constant for the "Control Pictures" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CONTROL_PICTURES = 
            new UnicodeBlock("CONTROL_PICTURES", new String[] {"Control Pictures", "ControlPictures"});

        /**
         * Constant for the "Optical Character Recognition" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION = 
            new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION", new String[] {"Optical Character Recognition", 
                                                                            "OpticalCharacterRecognition"});

        /**
         * Constant for the "Enclosed Alphanumerics" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ENCLOSED_ALPHANUMERICS = 
            new UnicodeBlock("ENCLOSED_ALPHANUMERICS", new String[] {"Enclosed Alphanumerics", 
                                                                     "EnclosedAlphanumerics"});

        /**
         * Constant for the "Box Drawing" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock BOX_DRAWING = 
            new UnicodeBlock("BOX_DRAWING", new String[] {"Box Drawing", "BoxDrawing"});

        /**
         * Constant for the "Block Elements" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock BLOCK_ELEMENTS = 
            new UnicodeBlock("BLOCK_ELEMENTS", new String[] {"Block Elements", "BlockElements"});

        /**
         * Constant for the "Geometric Shapes" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock GEOMETRIC_SHAPES = 
            new UnicodeBlock("GEOMETRIC_SHAPES", new String[] {"Geometric Shapes", "GeometricShapes"});

        /**
         * Constant for the "Miscellaneous Symbols" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock MISCELLANEOUS_SYMBOLS = 
            new UnicodeBlock("MISCELLANEOUS_SYMBOLS", new String[] {"Miscellaneous Symbols", 
                                                                    "MiscellaneousSymbols"});

        /**
         * Constant for the "Dingbats" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock DINGBATS = 
            new UnicodeBlock("DINGBATS");

        /**
         * Constant for the "CJK Symbols and Punctuation" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION = 
            new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION", new String[] {"CJK Symbols and Punctuation",
                                                                          "CJKSymbolsandPunctuation"});

        /**
         * Constant for the "Hiragana" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock HIRAGANA = 
            new UnicodeBlock("HIRAGANA");

        /**
         * Constant for the "Katakana" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock KATAKANA = 
            new UnicodeBlock("KATAKANA");

        /**
         * Constant for the "Bopomofo" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock BOPOMOFO = 
            new UnicodeBlock("BOPOMOFO");

        /**
         * Constant for the "Hangul Compatibility Jamo" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO = 
            new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO", new String[] {"Hangul Compatibility Jamo",
                                                                        "HangulCompatibilityJamo"});

        /**
         * Constant for the "Kanbun" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock KANBUN = 
            new UnicodeBlock("KANBUN");

        /**
         * Constant for the "Enclosed CJK Letters and Months" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS = 
            new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS", new String[] {"Enclosed CJK Letters and Months",
                                                                              "EnclosedCJKLettersandMonths"});

        /**
         * Constant for the "CJK Compatibility" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CJK_COMPATIBILITY = 
            new UnicodeBlock("CJK_COMPATIBILITY", new String[] {"CJK Compatibility", "CJKCompatibility"});

        /**
         * Constant for the "CJK Unified Ideographs" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS = 
            new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS", new String[] {"CJK Unified Ideographs", 
                                                                     "CJKUnifiedIdeographs"});

        /**
         * Constant for the "Hangul Syllables" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock HANGUL_SYLLABLES = 
            new UnicodeBlock("HANGUL_SYLLABLES", new String[] {"Hangul Syllables", "HangulSyllables"});

        /**
         * Constant for the "Private Use Area" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock PRIVATE_USE_AREA = 
            new UnicodeBlock("PRIVATE_USE_AREA", new String[] {"Private Use Area", "PrivateUseArea"});

        /**
         * Constant for the "CJK Compatibility Ideographs" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS = 
            new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS", 
                             new String[] {"CJK Compatibility Ideographs",
                                           "CJKCompatibilityIdeographs"});

        /**
         * Constant for the "Alphabetic Presentation Forms" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS = 
            new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS", new String[] {"Alphabetic Presentation Forms",
                                                                            "AlphabeticPresentationForms"});

        /**
         * Constant for the "Arabic Presentation Forms-A" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A = 
            new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A", new String[] {"Arabic Presentation Forms-A",
                                                                          "ArabicPresentationForms-A"});

        /**
         * Constant for the "Combining Half Marks" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock COMBINING_HALF_MARKS = 
            new UnicodeBlock("COMBINING_HALF_MARKS", new String[] {"Combining Half Marks",
                                                                   "CombiningHalfMarks"});

        /**
         * Constant for the "CJK Compatibility Forms" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock CJK_COMPATIBILITY_FORMS = 
            new UnicodeBlock("CJK_COMPATIBILITY_FORMS", new String[] {"CJK Compatibility Forms",
                                                                      "CJKCompatibilityForms"});

        /**
         * Constant for the "Small Form Variants" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock SMALL_FORM_VARIANTS = 
            new UnicodeBlock("SMALL_FORM_VARIANTS", new String[] {"Small Form Variants", 
                                                                  "SmallFormVariants"});

        /**
         * Constant for the "Arabic Presentation Forms-B" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B = 
            new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B", new String[] {"Arabic Presentation Forms-B",
                                                                          "ArabicPresentationForms-B"});

        /**
         * Constant for the "Halfwidth and Fullwidth Forms" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS = 
            new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS", 
                             new String[] {"Halfwidth and Fullwidth Forms",
                                           "HalfwidthandFullwidthForms"});

        /**
         * Constant for the "Specials" Unicode character block.
         * @since 1.2
         */
        public static final UnicodeBlock SPECIALS = 
            new UnicodeBlock("SPECIALS");

        /**
         * @deprecated As of J2SE 5, use {@link #HIGH_SURROGATES},
         *             {@link #HIGH_PRIVATE_USE_SURROGATES}, and
         *             {@link #LOW_SURROGATES}. These new constants match 
         *             the block definitions of the Unicode Standard.
         *             The {@link #of(char)} and {@link #of(int)} methods
         *             return the new constants, not SURROGATES_AREA.
         */
        @Deprecated
        public static final UnicodeBlock SURROGATES_AREA = 
            new UnicodeBlock("SURROGATES_AREA");

        /**
         * Constant for the "Syriac" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock SYRIAC = 
            new UnicodeBlock("SYRIAC");

        /**
         * Constant for the "Thaana" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock THAANA = 
            new UnicodeBlock("THAANA");

        /** 
         * Constant for the "Sinhala" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock SINHALA = 
            new UnicodeBlock("SINHALA");

        /**
         * Constant for the "Myanmar" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock MYANMAR = 
            new UnicodeBlock("MYANMAR");

        /**
         * Constant for the "Ethiopic" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock ETHIOPIC = 
            new UnicodeBlock("ETHIOPIC");

        /**
         * Constant for the "Cherokee" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock CHEROKEE = 
            new UnicodeBlock("CHEROKEE");

        /**
         * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = 
            new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS",
                             new String[] {"Unified Canadian Aboriginal Syllabics",
                                           "UnifiedCanadianAboriginalSyllabics"});

        /**
         * Constant for the "Ogham" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock OGHAM = 
                             new UnicodeBlock("OGHAM");

        /**
         * Constant for the "Runic" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock RUNIC = 
                             new UnicodeBlock("RUNIC");

        /**
         * Constant for the "Khmer" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock KHMER = 
                             new UnicodeBlock("KHMER");

        /**
         * Constant for the "Mongolian" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock MONGOLIAN = 
                             new UnicodeBlock("MONGOLIAN");

        /**
         * Constant for the "Braille Patterns" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock BRAILLE_PATTERNS = 
            new UnicodeBlock("BRAILLE_PATTERNS", new String[] {"Braille Patterns",
                                                               "BraillePatterns"});

        /**
         * Constant for the "CJK Radicals Supplement" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT = 
             new UnicodeBlock("CJK_RADICALS_SUPPLEMENT", new String[] {"CJK Radicals Supplement",
                                                                       "CJKRadicalsSupplement"});

        /**
         * Constant for the "Kangxi Radicals" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock KANGXI_RADICALS = 
            new UnicodeBlock("KANGXI_RADICALS", new String[] {"Kangxi Radicals", "KangxiRadicals"});

        /**
         * Constant for the "Ideographic Description Characters" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS =
            new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS", new String[] {"Ideographic Description Characters",
                                                                                 "IdeographicDescriptionCharacters"});

        /**
         * Constant for the "Bopomofo Extended" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock BOPOMOFO_EXTENDED = 
            new UnicodeBlock("BOPOMOFO_EXTENDED", new String[] {"Bopomofo Extended", 
                                                                "BopomofoExtended"});

        /**
         * Constant for the "CJK Unified Ideographs Extension A" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = 
            new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A", new String[] {"CJK Unified Ideographs Extension A",
                                                                                 "CJKUnifiedIdeographsExtensionA"});

        /**
         * Constant for the "Yi Syllables" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock YI_SYLLABLES = 
            new UnicodeBlock("YI_SYLLABLES", new String[] {"Yi Syllables", "YiSyllables"});

        /**
         * Constant for the "Yi Radicals" Unicode character block.
         * @since 1.4
         */
        public static final UnicodeBlock YI_RADICALS =
            new UnicodeBlock("YI_RADICALS", new String[] {"Yi Radicals", "YiRadicals"});
        

        /**
         * Constant for the "Cyrillic Supplementary" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY = 
            new UnicodeBlock("CYRILLIC_SUPPLEMENTARY", new String[] {"Cyrillic Supplementary",
                                                                     "CyrillicSupplementary"});

        /**
         * Constant for the "Tagalog" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock TAGALOG = 
            new UnicodeBlock("TAGALOG");

        /**
         * Constant for the "Hanunoo" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock HANUNOO = 
            new UnicodeBlock("HANUNOO");

        /**
         * Constant for the "Buhid" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock BUHID = 
            new UnicodeBlock("BUHID");

        /**
         * Constant for the "Tagbanwa" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock TAGBANWA = 
            new UnicodeBlock("TAGBANWA");

        /**
         * Constant for the "Limbu" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock LIMBU = 
            new UnicodeBlock("LIMBU");

        /**
         * Constant for the "Tai Le" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock TAI_LE = 
            new UnicodeBlock("TAI_LE", new String[] {"Tai Le", "TaiLe"});

        /**
         * Constant for the "Khmer Symbols" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock KHMER_SYMBOLS = 
            new UnicodeBlock("KHMER_SYMBOLS", new String[] {"Khmer Symbols", "KhmerSymbols"});

        /**
         * Constant for the "Phonetic Extensions" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock PHONETIC_EXTENSIONS = 
            new UnicodeBlock("PHONETIC_EXTENSIONS", new String[] {"Phonetic Extensions", "PhoneticExtensions"});

        /**
         * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 
            new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A", 
                             new String[]{"Miscellaneous Mathematical Symbols-A",
                                          "MiscellaneousMathematicalSymbols-A"});

        /**
         * Constant for the "Supplemental Arrows-A" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A = 
            new UnicodeBlock("SUPPLEMENTAL_ARROWS_A", new String[] {"Supplemental Arrows-A",
                                                                    "SupplementalArrows-A"});

        /**
         * Constant for the "Supplemental Arrows-B" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B = 
            new UnicodeBlock("SUPPLEMENTAL_ARROWS_B", new String[] {"Supplemental Arrows-B",
                                                                    "SupplementalArrows-B"});

        /**
         * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B
                = new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B", 
                                   new String[] {"Miscellaneous Mathematical Symbols-B",
                                                 "MiscellaneousMathematicalSymbols-B"});

        /**
         * Constant for the "Supplemental Mathematical Operators" Unicode character block.
         * @since 1.5
         */
        public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 
            new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS", 
                             new String[]{"Supplemental Mathematical Operators",
                                          "SupplementalMathematica