character.java

gcc的组建

  /**
   * 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;

  /**
   * Mask for grabbing the type out of the result of readChar.
   * @see #readChar(char)
   */
  private static final int TYPE_MASK = 0x1F;

  /**
   * Mask for grabbing the non-breaking space flag out of the result of
   * readChar.
   * @see #readChar(char)
   */
  private static final int NO_BREAK_MASK = 0x20;

  /**
   * Mask for grabbing the mirrored directionality flag out of the result
   * of readChar.
   * @see #readChar(char)
   */
  private static final int MIRROR_MASK = 0x40;

  /**
   * Min value for supplementary code point.
   *
   * @since 1.5
   */
  public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x10000;

  /**
   * Min value for code point.
   *
   * @since 1.5
   */
  public static final int MIN_CODE_POINT = 0; 
 
 
  /**
   * Max value for code point.
   *
   * @since 1.5
   */
  public static final int MAX_CODE_POINT = 0x010ffff;


  /**
   * Minimum high surrogate code in UTF-16 encoding.
   *
   * @since 1.5
   */
  public static final char MIN_HIGH_SURROGATE = '\ud800';

  /**
   * Maximum high surrogate code in UTF-16 encoding.
   *
   * @since 1.5
   */
  public static final char MAX_HIGH_SURROGATE = '\udbff';
 
  /**
   * Minimum low surrogate code in UTF-16 encoding.
   *
   * @since 1.5
   */
  public static final char MIN_LOW_SURROGATE = '\udc00';

  /**
   * Maximum low surrogate code in UTF-16 encoding.
   *
   * @since 1.5
   */
  public static final char MAX_LOW_SURROGATE = '\udfff';

  /**
   * Minimum surrogate code in UTF-16 encoding.
   *
   * @since 1.5
   */
  public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;

  /**
   * Maximum low surrogate code in UTF-16 encoding.
   *
   * @since 1.5
   */
  public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;

  /**
   * Grabs an attribute offset from the Unicode attribute database. The lower
   * 5 bits are the character type, the next 2 bits are flags, and the top
   * 9 bits are the offset into the attribute tables. Note that the top 9
   * bits are meaningless in this context; they are useful only in the native
   * code.
   *
   * @param ch the character to look up
   * @return the character's attribute offset and type
   * @see #TYPE_MASK
   * @see #NO_BREAK_MASK
   * @see #MIRROR_MASK
   */
  private static native char readChar(char ch);

  /**
   * Wraps up a character.
   *
   * @param value the character to wrap
   */
  public Character(char value)
  {
    this.value = value;
  }

  /**
   * Returns the character which has been wrapped by this class.
   *
   * @return the character wrapped
   */
  public char charValue()
  {
    return value;
  }

  /**
   * Returns the numerical value (unsigned) of the wrapped character.
   * Range of returned values: 0x0000-0xFFFF.
   *
   * @return the value of the wrapped character
   */
  public int hashCode()
  {
    return value;
  }

  /**
   * Determines if an object is equal to this object. This is only true for
   * another Character object wrapping the same value.
   *
   * @param o object to compare
   * @return true if o is a Character with the same value
   */
  public boolean equals(Object o)
  {
    return o instanceof Character && value == ((Character) o).value;
  }

  /**
   * Converts the wrapped character into a String.
   *
   * @return a String containing one character -- the wrapped character
   *         of this instance
   */
  public String toString()
  {
    // This assumes that String.valueOf(char) can create a single-character
    // String more efficiently than through the public API.
    return String.valueOf(value);
  }

  /**
   * Returns a String of length 1 representing the specified character.
   *
   * @param ch the character to convert
   * @return a String containing the character
   * @since 1.4
   */
  public static String toString(char ch)
  {
    // This assumes that String.valueOf(char) can create a single-character
    // String more efficiently than through the public API.
    return String.valueOf(ch);
  }

  /**
   * Determines if a character is a Unicode lowercase letter. For example,
   * <code>'a'</code> is lowercase.
   * <br>
   * lowercase = [Ll]
   *
   * @param ch character to test
   * @return true if ch is a Unicode lowercase letter, else false
   * @see #isUpperCase(char)
   * @see #isTitleCase(char)
   * @see #toLowerCase(char)
   * @see #getType(char)
   */
  public static boolean isLowerCase(char ch)
  {
    return getType(ch) == LOWERCASE_LETTER;
  }

  /**
   * Determines if a character is a Unicode uppercase letter. For example,
   * <code>'A'</code> is uppercase.
   * <br>
   * uppercase = [Lu]
   *
   * @param ch character to test
   * @return true if ch is a Unicode uppercase letter, else false
   * @see #isLowerCase(char)
   * @see #isTitleCase(char)
   * @see #toUpperCase(char)
   * @see #getType(char)
   */
  public static boolean isUpperCase(char ch)
  {
    return getType(ch) == UPPERCASE_LETTER;
  }

  /**
   * Determines if a character is a Unicode titlecase letter. For example,
   * the character "Lj" (Latin capital L with small letter j) is titlecase.
   * <br>
   * titlecase = [Lt]
   *
   * @param ch character to test
   * @return true if ch is a Unicode titlecase letter, else false
   * @see #isLowerCase(char)
   * @see #isUpperCase(char)
   * @see #toTitleCase(char)
   * @see #getType(char)
   */
  public static boolean isTitleCase(char ch)
  {
    return getType(ch) == TITLECASE_LETTER;
  }

  /**
   * Determines if a character is a Unicode decimal digit. For example,
   * <code>'0'</code> is a digit.
   * <br>
   * Unicode decimal digit = [Nd]
   *
   * @param ch character to test
   * @return true if ch is a Unicode decimal digit, else false
   * @see #digit(char, int)
   * @see #forDigit(int, int)
   * @see #getType(char)
   */
  public static boolean isDigit(char ch)
  {
    return getType(ch) == DECIMAL_DIGIT_NUMBER;
  }

  /**
   * Determines if a character is part of the Unicode Standard. This is an
   * evolving standard, but covers every character in the data file.
   * <br>
   * defined = not [Cn]
   *
   * @param ch character to test
   * @return true if ch is a Unicode character, else false
   * @see #isDigit(char)
   * @see #isLetter(char)
   * @see #isLetterOrDigit(char)
   * @see #isLowerCase(char)
   * @see #isTitleCase(char)
   * @see #isUpperCase(char)
   */
  public static boolean isDefined(char ch)
  {
    return getType(ch) != UNASSIGNED;
  }

  /**
   * Determines if a character is a Unicode letter. Not all letters have case,
   * so this may return true when isLowerCase and isUpperCase return false.
   * <br>
   * letter = [Lu]|[Ll]|[Lt]|[Lm]|[Lo]
   *
   * @param ch character to test
   * @return true if ch is a Unicode letter, else false
   * @see #isDigit(char)
   * @see #isJavaIdentifierStart(char)
   * @see #isJavaLetter(char)
   * @see #isJavaLetterOrDigit(char)
   * @see #isLetterOrDigit(char)
   * @see #isLowerCase(char)
   * @see #isTitleCase(char)
   * @see #isUnicodeIdentifierStart(char)
   * @see #isUpperCase(char)
   */
  public static boolean isLetter(char ch)
  {
    return ((1 << getType(ch))
            & ((1 << UPPERCASE_LETTER)
               | (1 << LOWERCASE_LETTER)
               | (1 << TITLECASE_LETTER)
               | (1 << MODIFIER_LETTER)
               | (1 << OTHER_LETTER))) != 0;
  }

  /**
   * Determines if a character is a Unicode letter or a Unicode digit. This
   * is the combination of isLetter and isDigit.
   * <br>
   * letter or digit = [Lu]|[Ll]|[Lt]|[Lm]|[Lo]|[Nd]
   *
   * @param ch character to test
   * @return true if ch is a Unicode letter or a Unicode digit, else false
   * @see #isDigit(char)
   * @see #isJavaIdentifierPart(char)
   * @see #isJavaLetter(char)
   * @see #isJavaLetterOrDigit(char)
   * @see #isLetter(char)
   * @see #isUnicodeIdentifierPart(char)
   */
  public static boolean isLetterOrDigit(char ch)
  {
    return ((1 << getType(ch))
            & ((1 << UPPERCASE_LETTER)
               | (1 << LOWERCASE_LETTER)
               | (1 << TITLECASE_LETTER)
               | (1 << MODIFIER_LETTER)
               | (1 << OTHER_LETTER)
               | (1 << DECIMAL_DIGIT_NUMBER))) != 0;
  }

  /**
   * Determines if a character can start a Java identifier. This is the
   * combination of isLetter, any character where getType returns
   * LETTER_NUMBER, currency symbols (like '$'), and connecting punctuation
   * (like '_').
   *
   * @param ch character to test
   * @return true if ch can start a Java identifier, else false
   * @deprecated Replaced by {@link #isJavaIdentifierStart(char)}
   * @see #isJavaLetterOrDigit(char)
   * @see #isJavaIdentifierStart(char)
   * @see #isJavaIdentifierPart(char)
   * @see #isLetter(char)
   * @see #isLetterOrDigit(char)
   * @see #isUnicodeIdentifierStart(char)
   */
  public static boolean isJavaLetter(char ch)
  {
    return isJavaIdentifierStart(ch);
  }

  /**
   * Determines if a character can follow the firs