diff options
Diffstat (limited to 'libjava/java/lang/Character.java')
| -rw-r--r-- | libjava/java/lang/Character.java | 204 |
1 files changed, 204 insertions, 0 deletions
diff --git a/libjava/java/lang/Character.java b/libjava/java/lang/Character.java index 2695b04..cdb3957 100644 --- a/libjava/java/lang/Character.java +++ b/libjava/java/lang/Character.java @@ -284,4 +284,208 @@ public final class Character implements Serializable, Comparable // Private data. private char value; + + public static class Subset + { + protected Subset (String name) + { + this.name = name; + } + + public final boolean equals (Object obj) + { + return obj == this; + } + + public final int hashCode () + { + return super.hashCode (); + } + + public final String toString () + { + return name; + } + + // Name of this subset. + private String name; + } + + public static final class UnicodeBlock extends Subset + { + private UnicodeBlock (String name, char start, char end) + { + super (name); + this.start = start; + this.end = end; + } + + public static UnicodeBlock of (char c) + { + // A special case we need. + if (c == '\uFEFF') + return SPECIALS; + + // Do a binary search to find the correct subset. + int hi = blocks.length; + int lo = 0; + while (hi > lo) + { + int mid = (hi + lo) / 2; + UnicodeBlock ub = blocks[mid]; + if (c < ub.start) + hi = mid; + else if (c > ub.end) + lo = mid; + else + return ub; + } + + return null; + } + + // Start and end characters. + private char start, end; + + // Everything from here to the end of UnicodeBlock is + // automatically generated by the blocks.pl script. + public static final UnicodeBlock BASIC_LATIN = new UnicodeBlock ("Basic Latin", '\u0000', '\u007F'); + public static final UnicodeBlock LATIN_1_SUPPLEMENT = new UnicodeBlock ("Latin-1 Supplement", '\u0080', '\u00FF'); + public static final UnicodeBlock LATIN_EXTENDED_A = new UnicodeBlock ("Latin Extended-A", '\u0100', '\u017F'); + public static final UnicodeBlock LATIN_EXTENDED_B = new UnicodeBlock ("Latin Extended-B", '\u0180', '\u024F'); + public static final UnicodeBlock IPA_EXTENSIONS = new UnicodeBlock ("IPA Extensions", '\u0250', '\u02AF'); + public static final UnicodeBlock SPACING_MODIFIER_LETTERS = new UnicodeBlock ("Spacing Modifier Letters", '\u02B0', '\u02FF'); + public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS = new UnicodeBlock ("Combining Diacritical Marks", '\u0300', '\u036F'); + public static final UnicodeBlock GREEK = new UnicodeBlock ("Greek", '\u0370', '\u03FF'); + public static final UnicodeBlock CYRILLIC = new UnicodeBlock ("Cyrillic", '\u0400', '\u04FF'); + public static final UnicodeBlock ARMENIAN = new UnicodeBlock ("Armenian", '\u0530', '\u058F'); + public static final UnicodeBlock HEBREW = new UnicodeBlock ("Hebrew", '\u0590', '\u05FF'); + public static final UnicodeBlock ARABIC = new UnicodeBlock ("Arabic", '\u0600', '\u06FF'); + public static final UnicodeBlock DEVANAGARI = new UnicodeBlock ("Devanagari", '\u0900', '\u097F'); + public static final UnicodeBlock BENGALI = new UnicodeBlock ("Bengali", '\u0980', '\u09FF'); + public static final UnicodeBlock GURMUKHI = new UnicodeBlock ("Gurmukhi", '\u0A00', '\u0A7F'); + public static final UnicodeBlock GUJARATI = new UnicodeBlock ("Gujarati", '\u0A80', '\u0AFF'); + public static final UnicodeBlock ORIYA = new UnicodeBlock ("Oriya", '\u0B00', '\u0B7F'); + public static final UnicodeBlock TAMIL = new UnicodeBlock ("Tamil", '\u0B80', '\u0BFF'); + public static final UnicodeBlock TELUGU = new UnicodeBlock ("Telugu", '\u0C00', '\u0C7F'); + public static final UnicodeBlock KANNADA = new UnicodeBlock ("Kannada", '\u0C80', '\u0CFF'); + public static final UnicodeBlock MALAYALAM = new UnicodeBlock ("Malayalam", '\u0D00', '\u0D7F'); + public static final UnicodeBlock THAI = new UnicodeBlock ("Thai", '\u0E00', '\u0E7F'); + public static final UnicodeBlock LAO = new UnicodeBlock ("Lao", '\u0E80', '\u0EFF'); + public static final UnicodeBlock TIBETAN = new UnicodeBlock ("Tibetan", '\u0F00', '\u0FBF'); + public static final UnicodeBlock GEORGIAN = new UnicodeBlock ("Georgian", '\u10A0', '\u10FF'); + public static final UnicodeBlock HANGUL_JAMO = new UnicodeBlock ("Hangul Jamo", '\u1100', '\u11FF'); + public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL = new UnicodeBlock ("Latin Extended Additional", '\u1E00', '\u1EFF'); + public static final UnicodeBlock GREEK_EXTENDED = new UnicodeBlock ("Greek Extended", '\u1F00', '\u1FFF'); + public static final UnicodeBlock GENERAL_PUNCTUATION = new UnicodeBlock ("General Punctuation", '\u2000', '\u206F'); + public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS = new UnicodeBlock ("Superscripts and Subscripts", '\u2070', '\u209F'); + public static final UnicodeBlock CURRENCY_SYMBOLS = new UnicodeBlock ("Currency Symbols", '\u20A0', '\u20CF'); + public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS = new UnicodeBlock ("Combining Marks for Symbols", '\u20D0', '\u20FF'); + public static final UnicodeBlock LETTERLIKE_SYMBOLS = new UnicodeBlock ("Letterlike Symbols", '\u2100', '\u214F'); + public static final UnicodeBlock NUMBER_FORMS = new UnicodeBlock ("Number Forms", '\u2150', '\u218F'); + public static final UnicodeBlock ARROWS = new UnicodeBlock ("Arrows", '\u2190', '\u21FF'); + public static final UnicodeBlock MATHEMATICAL_OPERATORS = new UnicodeBlock ("Mathematical Operators", '\u2200', '\u22FF'); + public static final UnicodeBlock MISCELLANEOUS_TECHNICAL = new UnicodeBlock ("Miscellaneous Technical", '\u2300', '\u23FF'); + public static final UnicodeBlock CONTROL_PICTURES = new UnicodeBlock ("Control Pictures", '\u2400', '\u243F'); + public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION = new UnicodeBlock ("Optical Character Recognition", '\u2440', '\u245F'); + public static final UnicodeBlock ENCLOSED_ALPHANUMERICS = new UnicodeBlock ("Enclosed Alphanumerics", '\u2460', '\u24FF'); + public static final UnicodeBlock BOX_DRAWING = new UnicodeBlock ("Box Drawing", '\u2500', '\u257F'); + public static final UnicodeBlock BLOCK_ELEMENTS = new UnicodeBlock ("Block Elements", '\u2580', '\u259F'); + public static final UnicodeBlock GEOMETRIC_SHAPES = new UnicodeBlock ("Geometric Shapes", '\u25A0', '\u25FF'); + public static final UnicodeBlock MISCELLANEOUS_SYMBOLS = new UnicodeBlock ("Miscellaneous Symbols", '\u2600', '\u26FF'); + public static final UnicodeBlock DINGBATS = new UnicodeBlock ("Dingbats", '\u2700', '\u27BF'); + public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION = new UnicodeBlock ("CJK Symbols and Punctuation", '\u3000', '\u303F'); + public static final UnicodeBlock HIRAGANA = new UnicodeBlock ("Hiragana", '\u3040', '\u309F'); + public static final UnicodeBlock KATAKANA = new UnicodeBlock ("Katakana", '\u30A0', '\u30FF'); + public static final UnicodeBlock BOPOMOFO = new UnicodeBlock ("Bopomofo", '\u3100', '\u312F'); + public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO = new UnicodeBlock ("Hangul Compatibility Jamo", '\u3130', '\u318F'); + public static final UnicodeBlock KANBUN = new UnicodeBlock ("Kanbun", '\u3190', '\u319F'); + public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS = new UnicodeBlock ("Enclosed CJK Letters and Months", '\u3200', '\u32FF'); + public static final UnicodeBlock CJK_COMPATIBILITY = new UnicodeBlock ("CJK Compatibility", '\u3300', '\u33FF'); + public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS = new UnicodeBlock ("CJK Unified Ideographs", '\u4E00', '\u9FFF'); + public static final UnicodeBlock HANGUL_SYLLABLES = new UnicodeBlock ("Hangul Syllables", '\uAC00', '\uD7A3'); + public static final UnicodeBlock HIGH_SURROGATES = new UnicodeBlock ("High Surrogates", '\uD800', '\uDB7F'); + public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES = new UnicodeBlock ("High Private Use Surrogates", '\uDB80', '\uDBFF'); + public static final UnicodeBlock LOW_SURROGATES = new UnicodeBlock ("Low Surrogates", '\uDC00', '\uDFFF'); + public static final UnicodeBlock PRIVATE_USE = new UnicodeBlock ("Private Use", '\uE000', '\uF8FF'); + public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS = new UnicodeBlock ("CJK Compatibility Ideographs", '\uF900', '\uFAFF'); + public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS = new UnicodeBlock ("Alphabetic Presentation Forms", '\uFB00', '\uFB4F'); + public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A = new UnicodeBlock ("Arabic Presentation Forms-A", '\uFB50', '\uFDFF'); + public static final UnicodeBlock COMBINING_HALF_MARKS = new UnicodeBlock ("Combining Half Marks", '\uFE20', '\uFE2F'); + public static final UnicodeBlock CJK_COMPATIBILITY_FORMS = new UnicodeBlock ("CJK Compatibility Forms", '\uFE30', '\uFE4F'); + public static final UnicodeBlock SMALL_FORM_VARIANTS = new UnicodeBlock ("Small Form Variants", '\uFE50', '\uFE6F'); + public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B = new UnicodeBlock ("Arabic Presentation Forms-B", '\uFE70', '\uFEFE'); + public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS = new UnicodeBlock ("Halfwidth and Fullwidth Forms", '\uFF00', '\uFFEF'); + public static final UnicodeBlock SPECIALS = new UnicodeBlock ("Specials", '\uFFF0', '\uFFFD'); + private static final UnicodeBlock[] blocks = { + BASIC_LATIN, + LATIN_1_SUPPLEMENT, + LATIN_EXTENDED_A, + LATIN_EXTENDED_B, + IPA_EXTENSIONS, + SPACING_MODIFIER_LETTERS, + COMBINING_DIACRITICAL_MARKS, + GREEK, + CYRILLIC, + ARMENIAN, + HEBREW, + ARABIC, + DEVANAGARI, + BENGALI, + GURMUKHI, + GUJARATI, + ORIYA, + TAMIL, + TELUGU, + KANNADA, + MALAYALAM, + THAI, + LAO, + TIBETAN, + GEORGIAN, + HANGUL_JAMO, + 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, + CJK_SYMBOLS_AND_PUNCTUATION, + HIRAGANA, + KATAKANA, + BOPOMOFO, + HANGUL_COMPATIBILITY_JAMO, + KANBUN, + ENCLOSED_CJK_LETTERS_AND_MONTHS, + CJK_COMPATIBILITY, + CJK_UNIFIED_IDEOGRAPHS, + HANGUL_SYLLABLES, + HIGH_SURROGATES, + HIGH_PRIVATE_USE_SURROGATES, + LOW_SURROGATES, + PRIVATE_USE, + 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 + }; + } } |