character.java

gcc的组建

      BLOCK_ELEMENTS,
      GEOMETRIC_SHAPES,
      MISCELLANEOUS_SYMBOLS,
      DINGBATS,
      BRAILLE_PATTERNS,
      CJK_RADICALS_SUPPLEMENT,
      KANGXI_RADICALS,
      IDEOGRAPHIC_DESCRIPTION_CHARACTERS,
      CJK_SYMBOLS_AND_PUNCTUATION,
      HIRAGANA,
      KATAKANA,
      BOPOMOFO,
      HANGUL_COMPATIBILITY_JAMO,
      KANBUN,
      BOPOMOFO_EXTENDED,
      ENCLOSED_CJK_LETTERS_AND_MONTHS,
      CJK_COMPATIBILITY,
      CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A,
      CJK_UNIFIED_IDEOGRAPHS,
      YI_SYLLABLES,
      YI_RADICALS,
      HANGUL_SYLLABLES,
      SURROGATES_AREA,
      PRIVATE_USE_AREA,
      CJK_COMPATIBILITY_IDEOGRAPHS,
      ALPHABETIC_PRESENTATION_FORMS,
      ARABIC_PRESENTATION_FORMS_A,
      COMBINING_HALF_MARKS,
      CJK_COMPATIBILITY_FORMS,
      SMALL_FORM_VARIANTS,
      ARABIC_PRESENTATION_FORMS_B,
      HALFWIDTH_AND_FULLWIDTH_FORMS,
      SPECIALS,
    };
  } // 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;

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

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

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

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

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

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

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

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

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

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

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

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

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

  /**
   * Strong bidirectional character type "WS".
   *
   * @since 1.4
   */
  public static final byte DIRECTIONALITY_WHITESPACE = 12;

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

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

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

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

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

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

  /**
   * Stores unicode block offset lookup table. Exploit package visibility of
   * String.value to avoid copying the array.
   * @see #readChar(char)
   * @see CharData#BLOCKS
   */
  private static final char[] blocks = String.zeroBasedStringValue(CharData.BLOCKS);

  /**
   * Stores unicode attribute offset lookup table. Exploit package visibility
   * of String.value to avoid copying the array.
   * @see CharData#DATA
   */
  private static final char[] data = String.zeroBasedStringValue(CharData.DATA);

  /**
   * Stores unicode numeric value attribute table. Exploit package visibility
   * of String.value to avoid copying the array.
   * @see CharData#NUM_VALUE
   */
  private static final char[] numValue
	  = String.zeroBasedStringValue(CharData.NUM_VALUE);

  /**