character.java

gcc的组建

     * Runic.
     * '\u16A0' - '\u16FF'.
     * @since 1.4
     */
    public static final UnicodeBlock RUNIC
      = new UnicodeBlock('\u16A0', '\u16FF',
                         "RUNIC");

    /**
     * Khmer.
     * '\u1780' - '\u17FF'.
     * @since 1.4
     */
    public static final UnicodeBlock KHMER
      = new UnicodeBlock('\u1780', '\u17FF',
                         "KHMER");

    /**
     * Mongolian.
     * '\u1800' - '\u18AF'.
     * @since 1.4
     */
    public static final UnicodeBlock MONGOLIAN
      = new UnicodeBlock('\u1800', '\u18AF',
                         "MONGOLIAN");

    /**
     * Latin Extended Additional.
     * '\u1E00' - '\u1EFF'.
     */
    public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL
      = new UnicodeBlock('\u1E00', '\u1EFF',
                         "LATIN_EXTENDED_ADDITIONAL");

    /**
     * Greek Extended.
     * '\u1F00' - '\u1FFF'.
     */
    public static final UnicodeBlock GREEK_EXTENDED
      = new UnicodeBlock('\u1F00', '\u1FFF',
                         "GREEK_EXTENDED");

    /**
     * General Punctuation.
     * '\u2000' - '\u206F'.
     */
    public static final UnicodeBlock GENERAL_PUNCTUATION
      = new UnicodeBlock('\u2000', '\u206F',
                         "GENERAL_PUNCTUATION");

    /**
     * Superscripts and Subscripts.
     * '\u2070' - '\u209F'.
     */
    public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS
      = new UnicodeBlock('\u2070', '\u209F',
                         "SUPERSCRIPTS_AND_SUBSCRIPTS");

    /**
     * Currency Symbols.
     * '\u20A0' - '\u20CF'.
     */
    public static final UnicodeBlock CURRENCY_SYMBOLS
      = new UnicodeBlock('\u20A0', '\u20CF',
                         "CURRENCY_SYMBOLS");

    /**
     * Combining Marks for Symbols.
     * '\u20D0' - '\u20FF'.
     */
    public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS
      = new UnicodeBlock('\u20D0', '\u20FF',
                         "COMBINING_MARKS_FOR_SYMBOLS");

    /**
     * Letterlike Symbols.
     * '\u2100' - '\u214F'.
     */
    public static final UnicodeBlock LETTERLIKE_SYMBOLS
      = new UnicodeBlock('\u2100', '\u214F',
                         "LETTERLIKE_SYMBOLS");

    /**
     * Number Forms.
     * '\u2150' - '\u218F'.
     */
    public static final UnicodeBlock NUMBER_FORMS
      = new UnicodeBlock('\u2150', '\u218F',
                         "NUMBER_FORMS");

    /**
     * Arrows.
     * '\u2190' - '\u21FF'.
     */
    public static final UnicodeBlock ARROWS
      = new UnicodeBlock('\u2190', '\u21FF',
                         "ARROWS");

    /**
     * Mathematical Operators.
     * '\u2200' - '\u22FF'.
     */
    public static final UnicodeBlock MATHEMATICAL_OPERATORS
      = new UnicodeBlock('\u2200', '\u22FF',
                         "MATHEMATICAL_OPERATORS");

    /**
     * Miscellaneous Technical.
     * '\u2300' - '\u23FF'.
     */
    public static final UnicodeBlock MISCELLANEOUS_TECHNICAL
      = new UnicodeBlock('\u2300', '\u23FF',
                         "MISCELLANEOUS_TECHNICAL");

    /**
     * Control Pictures.
     * '\u2400' - '\u243F'.
     */
    public static final UnicodeBlock CONTROL_PICTURES
      = new UnicodeBlock('\u2400', '\u243F',
                         "CONTROL_PICTURES");

    /**
     * Optical Character Recognition.
     * '\u2440' - '\u245F'.
     */
    public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION
      = new UnicodeBlock('\u2440', '\u245F',
                         "OPTICAL_CHARACTER_RECOGNITION");

    /**
     * Enclosed Alphanumerics.
     * '\u2460' - '\u24FF'.
     */
    public static final UnicodeBlock ENCLOSED_ALPHANUMERICS
      = new UnicodeBlock('\u2460', '\u24FF',
                         "ENCLOSED_ALPHANUMERICS");

    /**
     * Box Drawing.
     * '\u2500' - '\u257F'.
     */
    public static final UnicodeBlock BOX_DRAWING
      = new UnicodeBlock('\u2500', '\u257F',
                         "BOX_DRAWING");

    /**
     * Block Elements.
     * '\u2580' - '\u259F'.
     */
    public static final UnicodeBlock BLOCK_ELEMENTS
      = new UnicodeBlock('\u2580', '\u259F',
                         "BLOCK_ELEMENTS");

    /**
     * Geometric Shapes.
     * '\u25A0' - '\u25FF'.
     */
    public static final UnicodeBlock GEOMETRIC_SHAPES
      = new UnicodeBlock('\u25A0', '\u25FF',
                         "GEOMETRIC_SHAPES");

    /**
     * Miscellaneous Symbols.
     * '\u2600' - '\u26FF'.
     */
    public static final UnicodeBlock MISCELLANEOUS_SYMBOLS
      = new UnicodeBlock('\u2600', '\u26FF',
                         "MISCELLANEOUS_SYMBOLS");

    /**
     * Dingbats.
     * '\u2700' - '\u27BF'.
     */
    public static final UnicodeBlock DINGBATS
      = new UnicodeBlock('\u2700', '\u27BF',
                         "DINGBATS");

    /**
     * Braille Patterns.
     * '\u2800' - '\u28FF'.
     * @since 1.4
     */
    public static final UnicodeBlock BRAILLE_PATTERNS
      = new UnicodeBlock('\u2800', '\u28FF',
                         "BRAILLE_PATTERNS");

    /**
     * CJK Radicals Supplement.
     * '\u2E80' - '\u2EFF'.
     * @since 1.4
     */
    public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT
      = new UnicodeBlock('\u2E80', '\u2EFF',
                         "CJK_RADICALS_SUPPLEMENT");

    /**
     * Kangxi Radicals.
     * '\u2F00' - '\u2FDF'.
     * @since 1.4
     */
    public static final UnicodeBlock KANGXI_RADICALS
      = new UnicodeBlock('\u2F00', '\u2FDF',
                         "KANGXI_RADICALS");

    /**
     * Ideographic Description Characters.
     * '\u2FF0' - '\u2FFF'.
     * @since 1.4
     */
    public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS
      = new UnicodeBlock('\u2FF0', '\u2FFF',
                         "IDEOGRAPHIC_DESCRIPTION_CHARACTERS");

    /**
     * CJK Symbols and Punctuation.
     * '\u3000' - '\u303F'.
     */
    public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION
      = new UnicodeBlock('\u3000', '\u303F',
                         "CJK_SYMBOLS_AND_PUNCTUATION");

    /**
     * Hiragana.
     * '\u3040' - '\u309F'.
     */
    public static final UnicodeBlock HIRAGANA
      = new UnicodeBlock('\u3040', '\u309F',
                         "HIRAGANA");

    /**
     * Katakana.
     * '\u30A0' - '\u30FF'.
     */
    public static final UnicodeBlock KATAKANA
      = new UnicodeBlock('\u30A0', '\u30FF',
                         "KATAKANA");

    /**
     * Bopomofo.
     * '\u3100' - '\u312F'.
     */
    public static final UnicodeBlock BOPOMOFO
      = new UnicodeBlock('\u3100', '\u312F',
                         "BOPOMOFO");

    /**
     * Hangul Compatibility Jamo.
     * '\u3130' - '\u318F'.
     */
    public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO
      = new UnicodeBlock('\u3130', '\u318F',
                         "HANGUL_COMPATIBILITY_JAMO");

    /**
     * Kanbun.
     * '\u3190' - '\u319F'.
     */
    public static final UnicodeBlock KANBUN
      = new UnicodeBlock('\u3190', '\u319F',
                         "KANBUN");

    /**
     * Bopomofo Extended.
     * '\u31A0' - '\u31BF'.
     * @since 1.4
     */
    public static final UnicodeBlock BOPOMOFO_EXTENDED
      = new UnicodeBlock('\u31A0', '\u31BF',
                         "BOPOMOFO_EXTENDED");

    /**
     * Enclosed CJK Letters and Months.
     * '\u3200' - '\u32FF'.
     */
    public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS
      = new UnicodeBlock('\u3200', '\u32FF',
                         "ENCLOSED_CJK_LETTERS_AND_MONTHS");

    /**
     * CJK Compatibility.
     * '\u3300' - '\u33FF'.
     */
    public static final UnicodeBlock CJK_COMPATIBILITY
      = new UnicodeBlock('\u3300', '\u33FF',
                         "CJK_COMPATIBILITY");

    /**
     * CJK Unified Ideographs Extension A.
     * '\u3400' - '\u4DB5'.
     * @since 1.4
     */
    public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
      = new UnicodeBlock('\u3400', '\u4DB5',
                         "CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A");

    /**
     * CJK Unified Ideographs.
     * '\u4E00' - '\u9FFF'.
     */
    public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS
      = new UnicodeBlock('\u4E00', '\u9FFF',
                         "CJK_UNIFIED_IDEOGRAPHS");

    /**
     * Yi Syllables.
     * '\uA000' - '\uA48F'.
     * @since 1.4
     */
    public static final UnicodeBlock YI_SYLLABLES
      = new UnicodeBlock('\uA000', '\uA48F',
                         "YI_SYLLABLES");

    /**
     * Yi Radicals.
     * '\uA490' - '\uA4CF'.
     * @since 1.4
     */
    public static final UnicodeBlock YI_RADICALS
      = new UnicodeBlock('\uA490', '\uA4CF',
                         "YI_RADICALS");

    /**
     * Hangul Syllables.
     * '\uAC00' - '\uD7A3'.
     */
    public static final UnicodeBlock HANGUL_SYLLABLES
      = new UnicodeBlock('\uAC00', '\uD7A3',
                         "HANGUL_SYLLABLES");

    /**
     * Surrogates Area.
     * '\uD800' - '\uDFFF'.
     */
    public static final UnicodeBlock SURROGATES_AREA
      = new UnicodeBlock('\uD800', '\uDFFF',
                         "SURROGATES_AREA");

    /**
     * Private Use Area.
     * '\uE000' - '\uF8FF'.
     */
    public static final UnicodeBlock PRIVATE_USE_AREA
      = new UnicodeBlock('\uE000', '\uF8FF',
                         "PRIVATE_USE_AREA");

    /**
     * CJK Compatibility Ideographs.
     * '\uF900' - '\uFAFF'.
     */
    public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS
      = new UnicodeBlock('\uF900', '\uFAFF',
                         "CJK_COMPATIBILITY_IDEOGRAPHS");

    /**
     * Alphabetic Presentation Forms.
     * '\uFB00' - '\uFB4F'.
     */
    public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS
      = new UnicodeBlock('\uFB00', '\uFB4F',
                         "ALPHABETIC_PRESENTATION_FORMS");

    /**
     * Arabic Presentation Forms-A.
     * '\uFB50' - '\uFDFF'.
     */
    public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A
      = new UnicodeBlock('\uFB50', '\uFDFF',
                         "ARABIC_PRESENTATION_FORMS_A");

    /**
     * Combining Half Marks.
     * '\uFE20' - '\uFE2F'.
     */
    public static final UnicodeBlock COMBINING_HALF_MARKS
      = new UnicodeBlock('\uFE20', '\uFE2F',
                         "COMBINING_HALF_MARKS");

    /**
     * CJK Compatibility Forms.
     * '\uFE30' - '\uFE4F'.
     */
    public static final UnicodeBlock CJK_COMPATIBILITY_FORMS
      = new UnicodeBlock('\uFE30', '\uFE4F',
                         "CJK_COMPATIBILITY_FORMS");

    /**
     * Small Form Variants.
     * '\uFE50' - '\uFE6F'.
     */
    public static final UnicodeBlock SMALL_FORM_VARIANTS
      = new UnicodeBlock('\uFE50', '\uFE6F',
                         "SMALL_FORM_VARIANTS");

    /**
     * Arabic Presentation Forms-B.
     * '\uFE70' - '\uFEFE'.
     */
    public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B
      = new UnicodeBlock('\uFE70', '\uFEFE',
                         "ARABIC_PRESENTATION_FORMS_B");

    /**
     * Halfwidth and Fullwidth Forms.
     * '\uFF00' - '\uFFEF'.
     */
    public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS
      = new UnicodeBlock('\uFF00', '\uFFEF',
                         "HALFWIDTH_AND_FULLWIDTH_FORMS");

    /**
     * Specials.
     * '\uFEFF', '\uFFF0' - '\uFFFD'.
     */
    public static final UnicodeBlock SPECIALS
      = new UnicodeBlock('\uFFF0', '\uFFFD',
                         "SPECIALS");

    /**
     * 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,
      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,
      KHMER,
      MONGOLIAN,
      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,