character.java

gcc的组建

                         "Mathematical Alphanumeric Symbols");

    /**
     * CJK Unified Ideographs Extension B.
     * 0x20000 - 0x2A6DF.
     * @since 1.5
     */
    public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B
      = new UnicodeBlock(0x20000, 0x2A6DF,
                         "CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B", 
                         "CJK Unified Ideographs Extension B");

    /**
     * CJK Compatibility Ideographs Supplement.
     * 0x2F800 - 0x2FA1F.
     * @since 1.5
     */
    public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT
      = new UnicodeBlock(0x2F800, 0x2FA1F,
                         "CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT", 
                         "CJK Compatibility Ideographs Supplement");

    /**
     * Tags.
     * 0xE0000 - 0xE007F.
     * @since 1.5
     */
    public static final UnicodeBlock TAGS
      = new UnicodeBlock(0xE0000, 0xE007F,
                         "TAGS", 
                         "Tags");

    /**
     * Variation Selectors Supplement.
     * 0xE0100 - 0xE01EF.
     * @since 1.5
     */
    public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT
      = new UnicodeBlock(0xE0100, 0xE01EF,
                         "VARIATION_SELECTORS_SUPPLEMENT", 
                         "Variation Selectors Supplement");

    /**
     * Supplementary Private Use Area-A.
     * 0xF0000 - 0xFFFFF.
     * @since 1.5
     */
    public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A
      = new UnicodeBlock(0xF0000, 0xFFFFF,
                         "SUPPLEMENTARY_PRIVATE_USE_AREA_A", 
                         "Supplementary Private Use Area-A");

    /**
     * Supplementary Private Use Area-B.
     * 0x100000 - 0x10FFFF.
     * @since 1.5
     */
    public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B
      = new UnicodeBlock(0x100000, 0x10FFFF,
                         "SUPPLEMENTARY_PRIVATE_USE_AREA_B", 
                         "Supplementary Private Use Area-B");

    /**
     * Surrogates Area.
     * 'D800' - 'DFFF'.
     * @deprecated As of 1.5, the three areas, 
     * <a href="#HIGH_SURROGATES">HIGH_SURROGATES</a>,
     * <a href="#HIGH_PRIVATE_USE_SURROGATES">HIGH_PRIVATE_USE_SURROGATES</a>
     * and <a href="#LOW_SURROGATES">LOW_SURROGATES</a>, as defined
     * by the Unicode standard, should be used in preference to
     * this.  These are also returned from calls to <code>of(int)</code>
     * and <code>of(char)</code>.
     */
    public static final UnicodeBlock SURROGATES_AREA
      = new UnicodeBlock(0xD800, 0xDFFF,
                         "SURROGATES_AREA",
             "Surrogates Area");

    /**
     * The defined subsets.
     */
    private static final UnicodeBlock sets[] = {
      BASIC_LATIN,
      LATIN_1_SUPPLEMENT,
      LATIN_EXTENDED_A,
      LATIN_EXTENDED_B,
      IPA_EXTENSIONS,
      SPACING_MODIFIER_LETTERS,
      COMBINING_DIACRITICAL_MARKS,
      GREEK,
      CYRILLIC,
      CYRILLIC_SUPPLEMENTARY,
      ARMENIAN,
      HEBREW,
      ARABIC,
      SYRIAC,
      THAANA,
      DEVANAGARI,
      BENGALI,
      GURMUKHI,
      GUJARATI,
      ORIYA,
      TAMIL,
      TELUGU,
      KANNADA,
      MALAYALAM,
      SINHALA,
      THAI,
      LAO,
      TIBETAN,
      MYANMAR,
      GEORGIAN,
      HANGUL_JAMO,
      ETHIOPIC,
      CHEROKEE,
      UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS,
      OGHAM,
      RUNIC,
      TAGALOG,
      HANUNOO,
      BUHID,
      TAGBANWA,
      KHMER,
      MONGOLIAN,
      LIMBU,
      TAI_LE,
      KHMER_SYMBOLS,
      PHONETIC_EXTENSIONS,
      LATIN_EXTENDED_ADDITIONAL,
      GREEK_EXTENDED,
      GENERAL_PUNCTUATION,
      SUPERSCRIPTS_AND_SUBSCRIPTS,
      CURRENCY_SYMBOLS,
      COMBINING_MARKS_FOR_SYMBOLS,
      LETTERLIKE_SYMBOLS,
      NUMBER_FORMS,
      ARROWS,
      MATHEMATICAL_OPERATORS,
      MISCELLANEOUS_TECHNICAL,
      CONTROL_PICTURES,
      OPTICAL_CHARACTER_RECOGNITION,
      ENCLOSED_ALPHANUMERICS,
      BOX_DRAWING,
      BLOCK_ELEMENTS,
      GEOMETRIC_SHAPES,
      MISCELLANEOUS_SYMBOLS,
      DINGBATS,
      MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A,
      SUPPLEMENTAL_ARROWS_A,
      BRAILLE_PATTERNS,
      SUPPLEMENTAL_ARROWS_B,
      MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B,
      SUPPLEMENTAL_MATHEMATICAL_OPERATORS,
      MISCELLANEOUS_SYMBOLS_AND_ARROWS,
      CJK_RADICALS_SUPPLEMENT,
      KANGXI_RADICALS,
      IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
      CJK_SYMBOLS_AND_PUNCTUATION,
      HIRAGANA,
      KATAKANA,
      BOPOMOFO,
      HANGUL_COMPATIBILITY_JAMO,
      KANBUN,
      BOPOMOFO_EXTENDED,
      KATAKANA_PHONETIC_EXTENSIONS,
      ENCLOSED_CJK_LETTERS_AND_MONTHS,
      CJK_COMPATIBILITY,
      CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
      YIJING_HEXAGRAM_SYMBOLS,
      CJK_UNIFIED_IDEOGRAPHS,
      YI_SYLLABLES,
      YI_RADICALS,
      HANGUL_SYLLABLES,
      HIGH_SURROGATES,
      HIGH_PRIVATE_USE_SURROGATES,
      LOW_SURROGATES,
      PRIVATE_USE_AREA,
      CJK_COMPATIBILITY_IDEOGRAPHS,
      ALPHABETIC_PRESENTATION_FORMS,
      ARABIC_PRESENTATION_FORMS_A,
      VARIATION_SELECTORS,
      COMBINING_HALF_MARKS,
      CJK_COMPATIBILITY_FORMS,
      SMALL_FORM_VARIANTS,
      ARABIC_PRESENTATION_FORMS_B,
      HALFWIDTH_AND_FULLWIDTH_FORMS,
      SPECIALS,
      LINEAR_B_SYLLABARY,
      LINEAR_B_IDEOGRAMS,
      AEGEAN_NUMBERS,
      OLD_ITALIC,
      GOTHIC,
      UGARITIC,
      DESERET,
      SHAVIAN,
      OSMANYA,
      CYPRIOT_SYLLABARY,
      BYZANTINE_MUSICAL_SYMBOLS,
      MUSICAL_SYMBOLS,
      TAI_XUAN_JING_SYMBOLS,
      MATHEMATICAL_ALPHANUMERIC_SYMBOLS,
      CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
      CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT,
      TAGS,
      VARIATION_SELECTORS_SUPPLEMENT,
      SUPPLEMENTARY_PRIVATE_USE_AREA_A,
      SUPPLEMENTARY_PRIVATE_USE_AREA_B,
    };
  } // class UnicodeBlock

  /**
   * The immutable value of this Character.
   *
   * @serial the value of this Character
   */
  private final char value;

  /**
   * Compatible with JDK 1.0+.
   */
  private static final long serialVersionUID = 3786198910865385080L;

  /**
   * Smallest value allowed for radix arguments in Java. This value is 2.
   *
   * @see #digit(char, int)
   * @see #forDigit(int, int)
   * @see Integer#toString(int, int)
   * @see Integer#valueOf(String)
   */
  public static final int MIN_RADIX = 2;

  /**
   * Largest value allowed for radix arguments in Java. This value is 36.
   *
   * @see #digit(char, int)
   * @see #forDigit(int, int)
   * @see Integer#toString(int, int)
   * @see Integer#valueOf(String)
   */
  public static final int MAX_RADIX = 36;

  /**
   * The minimum value the char data type can hold.
   * This value is <code>'\\u0000'</code>.
   */
  public static final char MIN_VALUE = '\u0000';

  /**
   * The maximum value the char data type can hold.
   * This value is <code>'\\uFFFF'</code>.
   */
  public static final char MAX_VALUE = '\uFFFF';

  /**
   * Class object representing the primitive char data type.
   *
   * @since 1.1
   */
  public static final Class TYPE = VMClassLoader.getPrimitiveClass('C');

  /**
   * The number of bits needed to represent a <code>char</code>.
   * @since 1.5
   */
  public static final int SIZE = 16;

  // This caches some Character values, and is used by boxing
  // conversions via valueOf().  We must cache at least 0..127;
  // this constant controls how much we actually cache.
  private static final int MAX_CACHE = 127;
  private static Character[] charCache = new Character[MAX_CACHE + 1];

  /**
   * Lu = Letter, Uppercase (Informative).
   *
   * @since 1.1
   */
  public static final byte UPPERCASE_LETTER = 1;

  /**
   * Ll = Letter, Lowercase (Informative).
   *
   * @since 1.1
   */
  public static final byte LOWERCASE_LETTER = 2;

  /**
   * Lt = Letter, Titlecase (Informative).
   *
   * @since 1.1
   */
  public static final byte TITLECASE_LETTER = 3;

  /**
   * Mn = Mark, Non-Spacing (Normative).
   *
   * @since 1.1
   */
  public static final byte NON_SPACING_MARK = 6;

  /**
   * Mc = Mark, Spacing Combining (Normative).
   *
   * @since 1.1
   */
  public static final byte COMBINING_SPACING_MARK = 8;

  /**
   * Me = Mark, Enclosing (Normative).
   *
   * @since 1.1
   */
  public static final byte ENCLOSING_MARK = 7;

  /**
   * Nd = Number, Decimal Digit (Normative).
   *
   * @since 1.1
   */
  public static final byte DECIMAL_DIGIT_NUMBER = 9;

  /**
   * Nl = Number, Letter (Normative).
   *
   * @since 1.1
   */
  public static final byte LETTER_NUMBER = 10;

  /**
   * No = Number, Other (Normative).
   *
   * @since 1.1
   */
  public static final byte OTHER_NUMBER = 11;

  /**
   * Zs = Separator, Space (Normative).
   *
   * @since 1.1
   */
  public static final byte SPACE_SEPARATOR = 12;

  /**
   * Zl = Separator, Line (Normative).
   *
   * @since 1.1
   */
  public static final byte LINE_SEPARATOR = 13;

  /**
   * Zp = Separator, Paragraph (Normative).
   *
   * @since 1.1
   */
  public static final byte PARAGRAPH_SEPARATOR = 14;

  /**
   * Cc = Other, Control (Normative).
   *
   * @since 1.1
   */
  public static final byte CONTROL = 15;

  /**
   * Cf = Other, Format (Normative).
   *
   * @since 1.1
   */
  public static final byte FORMAT = 16;

  /**
   * Cs = Other, Surrogate (Normative).
   *
   * @since 1.1
   */
  public static final byte SURROGATE = 19;

  /**
   * Co = Other, Private Use (Normative).
   *
   * @since 1.1
   */
  public static final byte PRIVATE_USE = 18;

  /**
   * Cn = Other, Not Assigned (Normative).
   *
   * @since 1.1
   */
  public static final byte UNASSIGNED = 0;

  /**
   * Lm = Letter, Modifier (Informative).
   *
   * @since 1.1
   */
  public static final byte MODIFIER_LETTER = 4;

  /**
   * Lo = Letter, Other (Informative).
   *
   * @since 1.1
   */
  public static final byte OTHER_LETTER = 5;

  /**
   * Pc = Punctuation, Connector (Informative).
   *
   * @since 1.1
   */
  public static final byte CONNECTOR_PUNCTUATION = 23;

  /**
   * Pd = Punctuation, Dash (Informative).
   *
   * @since 1.1
   */
  public static final byte DASH_PUNCTUATION = 20;

  /**
   * Ps = Punctuation, Open (Informative).
   *
   * @since 1.1
   */
  public static final byte START_PUNCTUATION = 21;

  /**
   * Pe = Punctuation, Close (Informative).
   *
   * @since 1.1
   */
  public static final byte END_PUNCTUATION = 22;

  /**
   * Pi = Punctuation, Initial Quote (Informative).
   *
   * @since 1.4
   */
  public static final byte INITIAL_QUOTE_PUNCTUATION = 29;

  /**
   * Pf = Punctuation, Final Quote (Informative).
   *
   * @since 1.4
   */
  public static final byte FINAL_QUOTE_PUNCTUATION = 30;

  /**
   * Po = Punctuation, Other (Informative).
   *
   * @since 1.1
   */
  public static final byte OTHER_PUNCTUATION = 24;

  /**
   * Sm = Symbol, Math (Informative).
   *
   * @since 1.1
   */
  public static final byte MATH_SYMBOL = 25;

  /**
   * Sc = Symbol, Currency (Informative).
   *
   * @since 1.1
   */
  public static final byte CURRENCY_SYMBOL = 26;

  /**
   * Sk = Symbol, Modifier (Informative).
   *
   * @since 1.1
   */
  public static final byte MODIFIER_SYMBOL = 27;

  /**
   * So = Symbol, Other (Informative).
   *
   * @since 1.1
   */
  public static final byte OTHER_SYMBOL = 28;