character.java

gcc的组建

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

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

  /**
   * Stores unicode direction attribute table. Exploit package visibility
   * of String.value to avoid copying the array.
   * @see CharData#DIRECTION
   */
  // Package visible for use by String.
  static final char[] direction = String.zeroBasedStringValue(CharData.DIRECTION);

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

  /**
   * Mask for grabbing the type out of the contents of data.
   * @see CharData#DATA
   */
  private static final int TYPE_MASK = 0x1F;

  /**
   * Mask for grabbing the non-breaking space flag out of the contents of
   * data.
   * @see CharData#DATA
   */
  private static final int NO_BREAK_MASK = 0x20;

  /**
   * Mask for grabbing the mirrored directionality flag out of the contents
   * of data.
   * @see CharData#DATA
   */
  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.
   *
   * @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
   * @see CharData#DATA
   * @see CharData#SHIFT
   */
  // Package visible for use in String.
  static char readChar(char ch)
  {
    // Perform 16-bit addition to find the correct entry in data.
    return data[(char) (blocks[ch >> CharData.SHIFT] + 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()
  {
    // Package constructor avoids an array copy.
    return new String(new char[] { value }, 0, 1, true);
  }

  /**
   * 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)
  {
    // Package constructor avoids an array copy.
    return new String(new char[] { ch }, 0, 1, true);
  }

  /**
   * 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 first letter in
   * a Java identifier.  This is the combination of isJavaLetter (isLetter,
   * type of LETTER_NUMBER, currency, connecting punctuation) and digit,
   * numeric letter (like Roman numerals), combining marks, non-spacing marks,
   * or isIdentifierIgnorable.
   *
   * @param ch character to test
   * @return true if ch can follow the first letter in a Java identifier
   * @deprecated Replaced by {@link #isJavaIdentifierPart(char)}
   * @see #isJavaLetter(char)
   * @see #isJavaIdentifierStart(char)
   * @see #isJavaIdentifierPart(char)
   * @see #isLetter(char)
   * @see #isLetterOrDigit(char)
   * @see #isUnicodeIdentifierPart(char)
   * @see #isIdentifierIgnorable(char)
   */
  public static boolean isJavaLetterOrDigit(char ch)
  {
    return isJavaIdentifierPart(ch);
  }

  /**
   * 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 '_').
   * <br>
   * Java identifier start = [Lu]|[Ll]|[Lt]|[Lm]|[Lo]|[Nl]|[Sc]|[Pc]
   *
   * @param ch character to test
   * @return true if ch can start a Java identifier, else false
   * @see #isJavaIdentifierPart(char)
   * @see #isLetter(char)
   * @see #isUnicodeIdentifierStart(char)
   * @since 1.1
   */
  public static boolean isJavaIdentifierStart(char ch)
  {
    return ((1 << getType(ch))
            & ((1 << UPPERCASE_LETTER)
               | (1 << LOWERCASE_LETTER)
               | (1 << TITLECASE_LETTER)
               | (1 << MODIFIER_LETTER)
               | (1 << OTHER_LETTER)
               | (1 << LETTER_NUMBER)
               | (1 << CURRENCY_SYMBOL)
               | (1 << CONNECTOR_PUNCTUATION))) != 0;
  }

  /**
   * Determines if a character can follow the first letter in
   * a Java identifier.  This is the combination of isJavaLetter (isLetter,
   * type of LETTER_NUMBER, currency, connecting punctuation) and digit,
   * numeric letter (like Roman numerals), combining marks, non-spacing marks,
   * or isIdentifierIgnorable.
   * <br>
   * Java identifier extender =
   *   [Lu]|[Ll]|[Lt]|[Lm]|[Lo]|[Nl]|[Sc]|[Pc]|[Mn]|[Mc]|[Nd]|[Cf]
   *   |U+0000-U+0008|U+000E-U+001B|U+007F-U+009F
   *
   * @param ch character to test
   * @return true if ch can follow the first letter in a Java identifier
   * @see #isIdentifierIgnorable(char)
   * @see #isJavaIdentifierStart(char)
   * @see #isLetterOrDigit(char)
   * @see #isUnicodeIdentifierPart(char)
   * @since 1.1
   */
  public static boolean isJavaIdentifierPart(char ch)
  {
    int category = getType(ch);
    return ((1 << category)
            & ((1 << UPPERCASE_LETTER)
               | (1 << LOWERCASE_LETTER)
               | (1 << TITLECASE_LETTER)
               | (1 << MODIFIER_LETTER)
               | (1 << OTHER_LETTER)
               | (1 << NON_SPACING_MARK)
               | (1 << COMBINING_SPACING_MARK)
               | (1 << DECIMAL_DIGIT_NUMBER)
               | (1 << LETTER_NUMBER)
               | (1 << CURRENCY_SYMBOL)
               | (1 << CONNECTOR_PUNCTUATION)
               | (1 << FORMAT))) != 0
      || (category == CONTROL && isIdentifierIgnorable(ch));
  }

  /**
   * Determines if a character can start a Unicode identifier.  Only
   * letters can start a Unicode identifier, but this includes characters
   * in LETTER_NUMBER.
   * <br>
   * Unicode identifier start = [Lu]|[Ll]|[Lt]|[Lm]|[Lo]|[Nl]
   *
   * @param ch character to test
   * @return true if ch can start a Unicode identifier, else false
   * @see #isJavaIdentifierStart(char)
   * @see #isLetter(char)
   * @see #isUnicodeIdentifierPart(char)
   * @since 1.1
   */
  public static boolean isUnicodeIdentifierStart(char ch)
  {
    return ((1 << getType(ch))
            & ((1 << UPPERCASE_LETTER)