# HG changeset patch # User Jaroslav Tulach # Date 1349055647 25200 # Node ID 9f3c454e74d49b6c2f662748f85664d18d1235ab # Parent d65b3a2fbfaf1b3fb3d36bd592a92ac5cee97e0d Removing methods from Character diff -r d65b3a2fbfaf -r 9f3c454e74d4 emul/src/main/java/java/lang/Character.java --- a/emul/src/main/java/java/lang/Character.java Sun Sep 30 18:29:37 2012 -0700 +++ b/emul/src/main/java/java/lang/Character.java Sun Sep 30 18:40:47 2012 -0700 @@ -25,11 +25,6 @@ package java.lang; -import java.util.Arrays; -import java.util.Map; -import java.util.HashMap; -import java.util.Locale; - /** * The {@code Character} class wraps a value of the primitive * type {@code char} in an object. An object of type @@ -171,7 +166,6 @@ * * @since 1.1 */ - @SuppressWarnings("unchecked") public static final Class TYPE = Class.getPrimitiveClass("char"); /* @@ -636,3702 +630,6 @@ // See http://www.unicode.org/Public/UNIDATA/Blocks.txt // for the latest specification of Unicode Blocks. - /** - * A family of character subsets representing the character blocks in the - * Unicode specification. Character blocks generally define characters - * used for a specific script or purpose. A character is contained by - * at most one Unicode block. - * - * @since 1.2 - */ - public static final class UnicodeBlock extends Subset { - - private static Map map = new HashMap<>(256); - - /** - * Creates a UnicodeBlock with the given identifier name. - * This name must be the same as the block identifier. - */ - private UnicodeBlock(String idName) { - super(idName); - map.put(idName, this); - } - - /** - * Creates a UnicodeBlock with the given identifier name and - * alias name. - */ - private UnicodeBlock(String idName, String alias) { - this(idName); - map.put(alias, this); - } - - /** - * Creates a UnicodeBlock with the given identifier name and - * alias names. - */ - private UnicodeBlock(String idName, String... aliases) { - this(idName); - for (String alias : aliases) - map.put(alias, this); - } - - /** - * Constant for the "Basic Latin" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock BASIC_LATIN = - new UnicodeBlock("BASIC_LATIN", - "BASIC LATIN", - "BASICLATIN"); - - /** - * Constant for the "Latin-1 Supplement" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock LATIN_1_SUPPLEMENT = - new UnicodeBlock("LATIN_1_SUPPLEMENT", - "LATIN-1 SUPPLEMENT", - "LATIN-1SUPPLEMENT"); - - /** - * Constant for the "Latin Extended-A" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock LATIN_EXTENDED_A = - new UnicodeBlock("LATIN_EXTENDED_A", - "LATIN EXTENDED-A", - "LATINEXTENDED-A"); - - /** - * Constant for the "Latin Extended-B" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock LATIN_EXTENDED_B = - new UnicodeBlock("LATIN_EXTENDED_B", - "LATIN EXTENDED-B", - "LATINEXTENDED-B"); - - /** - * Constant for the "IPA Extensions" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock IPA_EXTENSIONS = - new UnicodeBlock("IPA_EXTENSIONS", - "IPA EXTENSIONS", - "IPAEXTENSIONS"); - - /** - * Constant for the "Spacing Modifier Letters" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock SPACING_MODIFIER_LETTERS = - new UnicodeBlock("SPACING_MODIFIER_LETTERS", - "SPACING MODIFIER LETTERS", - "SPACINGMODIFIERLETTERS"); - - /** - * Constant for the "Combining Diacritical Marks" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS = - new UnicodeBlock("COMBINING_DIACRITICAL_MARKS", - "COMBINING DIACRITICAL MARKS", - "COMBININGDIACRITICALMARKS"); - - /** - * Constant for the "Greek and Coptic" Unicode character block. - *

- * This block was previously known as the "Greek" block. - * - * @since 1.2 - */ - public static final UnicodeBlock GREEK = - new UnicodeBlock("GREEK", - "GREEK AND COPTIC", - "GREEKANDCOPTIC"); - - /** - * Constant for the "Cyrillic" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock CYRILLIC = - new UnicodeBlock("CYRILLIC"); - - /** - * Constant for the "Armenian" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ARMENIAN = - new UnicodeBlock("ARMENIAN"); - - /** - * Constant for the "Hebrew" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock HEBREW = - new UnicodeBlock("HEBREW"); - - /** - * Constant for the "Arabic" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ARABIC = - new UnicodeBlock("ARABIC"); - - /** - * Constant for the "Devanagari" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock DEVANAGARI = - new UnicodeBlock("DEVANAGARI"); - - /** - * Constant for the "Bengali" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock BENGALI = - new UnicodeBlock("BENGALI"); - - /** - * Constant for the "Gurmukhi" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock GURMUKHI = - new UnicodeBlock("GURMUKHI"); - - /** - * Constant for the "Gujarati" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock GUJARATI = - new UnicodeBlock("GUJARATI"); - - /** - * Constant for the "Oriya" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ORIYA = - new UnicodeBlock("ORIYA"); - - /** - * Constant for the "Tamil" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock TAMIL = - new UnicodeBlock("TAMIL"); - - /** - * Constant for the "Telugu" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock TELUGU = - new UnicodeBlock("TELUGU"); - - /** - * Constant for the "Kannada" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock KANNADA = - new UnicodeBlock("KANNADA"); - - /** - * Constant for the "Malayalam" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock MALAYALAM = - new UnicodeBlock("MALAYALAM"); - - /** - * Constant for the "Thai" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock THAI = - new UnicodeBlock("THAI"); - - /** - * Constant for the "Lao" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock LAO = - new UnicodeBlock("LAO"); - - /** - * Constant for the "Tibetan" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock TIBETAN = - new UnicodeBlock("TIBETAN"); - - /** - * Constant for the "Georgian" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock GEORGIAN = - new UnicodeBlock("GEORGIAN"); - - /** - * Constant for the "Hangul Jamo" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock HANGUL_JAMO = - new UnicodeBlock("HANGUL_JAMO", - "HANGUL JAMO", - "HANGULJAMO"); - - /** - * Constant for the "Latin Extended Additional" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL = - new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL", - "LATIN EXTENDED ADDITIONAL", - "LATINEXTENDEDADDITIONAL"); - - /** - * Constant for the "Greek Extended" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock GREEK_EXTENDED = - new UnicodeBlock("GREEK_EXTENDED", - "GREEK EXTENDED", - "GREEKEXTENDED"); - - /** - * Constant for the "General Punctuation" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock GENERAL_PUNCTUATION = - new UnicodeBlock("GENERAL_PUNCTUATION", - "GENERAL PUNCTUATION", - "GENERALPUNCTUATION"); - - /** - * Constant for the "Superscripts and Subscripts" Unicode character - * block. - * @since 1.2 - */ - public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS = - new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS", - "SUPERSCRIPTS AND SUBSCRIPTS", - "SUPERSCRIPTSANDSUBSCRIPTS"); - - /** - * Constant for the "Currency Symbols" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock CURRENCY_SYMBOLS = - new UnicodeBlock("CURRENCY_SYMBOLS", - "CURRENCY SYMBOLS", - "CURRENCYSYMBOLS"); - - /** - * Constant for the "Combining Diacritical Marks for Symbols" Unicode - * character block. - *

- * This block was previously known as "Combining Marks for Symbols". - * @since 1.2 - */ - public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS = - new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS", - "COMBINING DIACRITICAL MARKS FOR SYMBOLS", - "COMBININGDIACRITICALMARKSFORSYMBOLS", - "COMBINING MARKS FOR SYMBOLS", - "COMBININGMARKSFORSYMBOLS"); - - /** - * Constant for the "Letterlike Symbols" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock LETTERLIKE_SYMBOLS = - new UnicodeBlock("LETTERLIKE_SYMBOLS", - "LETTERLIKE SYMBOLS", - "LETTERLIKESYMBOLS"); - - /** - * Constant for the "Number Forms" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock NUMBER_FORMS = - new UnicodeBlock("NUMBER_FORMS", - "NUMBER FORMS", - "NUMBERFORMS"); - - /** - * Constant for the "Arrows" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ARROWS = - new UnicodeBlock("ARROWS"); - - /** - * Constant for the "Mathematical Operators" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock MATHEMATICAL_OPERATORS = - new UnicodeBlock("MATHEMATICAL_OPERATORS", - "MATHEMATICAL OPERATORS", - "MATHEMATICALOPERATORS"); - - /** - * Constant for the "Miscellaneous Technical" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock MISCELLANEOUS_TECHNICAL = - new UnicodeBlock("MISCELLANEOUS_TECHNICAL", - "MISCELLANEOUS TECHNICAL", - "MISCELLANEOUSTECHNICAL"); - - /** - * Constant for the "Control Pictures" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock CONTROL_PICTURES = - new UnicodeBlock("CONTROL_PICTURES", - "CONTROL PICTURES", - "CONTROLPICTURES"); - - /** - * Constant for the "Optical Character Recognition" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION = - new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION", - "OPTICAL CHARACTER RECOGNITION", - "OPTICALCHARACTERRECOGNITION"); - - /** - * Constant for the "Enclosed Alphanumerics" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ENCLOSED_ALPHANUMERICS = - new UnicodeBlock("ENCLOSED_ALPHANUMERICS", - "ENCLOSED ALPHANUMERICS", - "ENCLOSEDALPHANUMERICS"); - - /** - * Constant for the "Box Drawing" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock BOX_DRAWING = - new UnicodeBlock("BOX_DRAWING", - "BOX DRAWING", - "BOXDRAWING"); - - /** - * Constant for the "Block Elements" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock BLOCK_ELEMENTS = - new UnicodeBlock("BLOCK_ELEMENTS", - "BLOCK ELEMENTS", - "BLOCKELEMENTS"); - - /** - * Constant for the "Geometric Shapes" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock GEOMETRIC_SHAPES = - new UnicodeBlock("GEOMETRIC_SHAPES", - "GEOMETRIC SHAPES", - "GEOMETRICSHAPES"); - - /** - * Constant for the "Miscellaneous Symbols" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock MISCELLANEOUS_SYMBOLS = - new UnicodeBlock("MISCELLANEOUS_SYMBOLS", - "MISCELLANEOUS SYMBOLS", - "MISCELLANEOUSSYMBOLS"); - - /** - * Constant for the "Dingbats" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock DINGBATS = - new UnicodeBlock("DINGBATS"); - - /** - * Constant for the "CJK Symbols and Punctuation" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION = - new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION", - "CJK SYMBOLS AND PUNCTUATION", - "CJKSYMBOLSANDPUNCTUATION"); - - /** - * Constant for the "Hiragana" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock HIRAGANA = - new UnicodeBlock("HIRAGANA"); - - /** - * Constant for the "Katakana" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock KATAKANA = - new UnicodeBlock("KATAKANA"); - - /** - * Constant for the "Bopomofo" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock BOPOMOFO = - new UnicodeBlock("BOPOMOFO"); - - /** - * Constant for the "Hangul Compatibility Jamo" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO = - new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO", - "HANGUL COMPATIBILITY JAMO", - "HANGULCOMPATIBILITYJAMO"); - - /** - * Constant for the "Kanbun" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock KANBUN = - new UnicodeBlock("KANBUN"); - - /** - * Constant for the "Enclosed CJK Letters and Months" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS = - new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS", - "ENCLOSED CJK LETTERS AND MONTHS", - "ENCLOSEDCJKLETTERSANDMONTHS"); - - /** - * Constant for the "CJK Compatibility" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock CJK_COMPATIBILITY = - new UnicodeBlock("CJK_COMPATIBILITY", - "CJK COMPATIBILITY", - "CJKCOMPATIBILITY"); - - /** - * Constant for the "CJK Unified Ideographs" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS = - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS", - "CJK UNIFIED IDEOGRAPHS", - "CJKUNIFIEDIDEOGRAPHS"); - - /** - * Constant for the "Hangul Syllables" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock HANGUL_SYLLABLES = - new UnicodeBlock("HANGUL_SYLLABLES", - "HANGUL SYLLABLES", - "HANGULSYLLABLES"); - - /** - * Constant for the "Private Use Area" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock PRIVATE_USE_AREA = - new UnicodeBlock("PRIVATE_USE_AREA", - "PRIVATE USE AREA", - "PRIVATEUSEAREA"); - - /** - * Constant for the "CJK Compatibility Ideographs" Unicode character - * block. - * @since 1.2 - */ - public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS = - new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS", - "CJK COMPATIBILITY IDEOGRAPHS", - "CJKCOMPATIBILITYIDEOGRAPHS"); - - /** - * Constant for the "Alphabetic Presentation Forms" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS = - new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS", - "ALPHABETIC PRESENTATION FORMS", - "ALPHABETICPRESENTATIONFORMS"); - - /** - * Constant for the "Arabic Presentation Forms-A" Unicode character - * block. - * @since 1.2 - */ - public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A = - new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A", - "ARABIC PRESENTATION FORMS-A", - "ARABICPRESENTATIONFORMS-A"); - - /** - * Constant for the "Combining Half Marks" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock COMBINING_HALF_MARKS = - new UnicodeBlock("COMBINING_HALF_MARKS", - "COMBINING HALF MARKS", - "COMBININGHALFMARKS"); - - /** - * Constant for the "CJK Compatibility Forms" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock CJK_COMPATIBILITY_FORMS = - new UnicodeBlock("CJK_COMPATIBILITY_FORMS", - "CJK COMPATIBILITY FORMS", - "CJKCOMPATIBILITYFORMS"); - - /** - * Constant for the "Small Form Variants" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock SMALL_FORM_VARIANTS = - new UnicodeBlock("SMALL_FORM_VARIANTS", - "SMALL FORM VARIANTS", - "SMALLFORMVARIANTS"); - - /** - * Constant for the "Arabic Presentation Forms-B" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B = - new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B", - "ARABIC PRESENTATION FORMS-B", - "ARABICPRESENTATIONFORMS-B"); - - /** - * Constant for the "Halfwidth and Fullwidth Forms" Unicode character - * block. - * @since 1.2 - */ - public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS = - new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS", - "HALFWIDTH AND FULLWIDTH FORMS", - "HALFWIDTHANDFULLWIDTHFORMS"); - - /** - * Constant for the "Specials" Unicode character block. - * @since 1.2 - */ - public static final UnicodeBlock SPECIALS = - new UnicodeBlock("SPECIALS"); - - /** - * @deprecated As of J2SE 5, use {@link #HIGH_SURROGATES}, - * {@link #HIGH_PRIVATE_USE_SURROGATES}, and - * {@link #LOW_SURROGATES}. These new constants match - * the block definitions of the Unicode Standard. - * The {@link #of(char)} and {@link #of(int)} methods - * return the new constants, not SURROGATES_AREA. - */ - @Deprecated - public static final UnicodeBlock SURROGATES_AREA = - new UnicodeBlock("SURROGATES_AREA"); - - /** - * Constant for the "Syriac" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock SYRIAC = - new UnicodeBlock("SYRIAC"); - - /** - * Constant for the "Thaana" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock THAANA = - new UnicodeBlock("THAANA"); - - /** - * Constant for the "Sinhala" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock SINHALA = - new UnicodeBlock("SINHALA"); - - /** - * Constant for the "Myanmar" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock MYANMAR = - new UnicodeBlock("MYANMAR"); - - /** - * Constant for the "Ethiopic" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock ETHIOPIC = - new UnicodeBlock("ETHIOPIC"); - - /** - * Constant for the "Cherokee" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock CHEROKEE = - new UnicodeBlock("CHEROKEE"); - - /** - * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = - new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS", - "UNIFIED CANADIAN ABORIGINAL SYLLABICS", - "UNIFIEDCANADIANABORIGINALSYLLABICS"); - - /** - * Constant for the "Ogham" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock OGHAM = - new UnicodeBlock("OGHAM"); - - /** - * Constant for the "Runic" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock RUNIC = - new UnicodeBlock("RUNIC"); - - /** - * Constant for the "Khmer" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock KHMER = - new UnicodeBlock("KHMER"); - - /** - * Constant for the "Mongolian" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock MONGOLIAN = - new UnicodeBlock("MONGOLIAN"); - - /** - * Constant for the "Braille Patterns" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock BRAILLE_PATTERNS = - new UnicodeBlock("BRAILLE_PATTERNS", - "BRAILLE PATTERNS", - "BRAILLEPATTERNS"); - - /** - * Constant for the "CJK Radicals Supplement" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT = - new UnicodeBlock("CJK_RADICALS_SUPPLEMENT", - "CJK RADICALS SUPPLEMENT", - "CJKRADICALSSUPPLEMENT"); - - /** - * Constant for the "Kangxi Radicals" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock KANGXI_RADICALS = - new UnicodeBlock("KANGXI_RADICALS", - "KANGXI RADICALS", - "KANGXIRADICALS"); - - /** - * Constant for the "Ideographic Description Characters" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS = - new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS", - "IDEOGRAPHIC DESCRIPTION CHARACTERS", - "IDEOGRAPHICDESCRIPTIONCHARACTERS"); - - /** - * Constant for the "Bopomofo Extended" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock BOPOMOFO_EXTENDED = - new UnicodeBlock("BOPOMOFO_EXTENDED", - "BOPOMOFO EXTENDED", - "BOPOMOFOEXTENDED"); - - /** - * Constant for the "CJK Unified Ideographs Extension A" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A", - "CJK UNIFIED IDEOGRAPHS EXTENSION A", - "CJKUNIFIEDIDEOGRAPHSEXTENSIONA"); - - /** - * Constant for the "Yi Syllables" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock YI_SYLLABLES = - new UnicodeBlock("YI_SYLLABLES", - "YI SYLLABLES", - "YISYLLABLES"); - - /** - * Constant for the "Yi Radicals" Unicode character block. - * @since 1.4 - */ - public static final UnicodeBlock YI_RADICALS = - new UnicodeBlock("YI_RADICALS", - "YI RADICALS", - "YIRADICALS"); - - /** - * Constant for the "Cyrillic Supplementary" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY = - new UnicodeBlock("CYRILLIC_SUPPLEMENTARY", - "CYRILLIC SUPPLEMENTARY", - "CYRILLICSUPPLEMENTARY", - "CYRILLIC SUPPLEMENT", - "CYRILLICSUPPLEMENT"); - - /** - * Constant for the "Tagalog" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock TAGALOG = - new UnicodeBlock("TAGALOG"); - - /** - * Constant for the "Hanunoo" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock HANUNOO = - new UnicodeBlock("HANUNOO"); - - /** - * Constant for the "Buhid" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock BUHID = - new UnicodeBlock("BUHID"); - - /** - * Constant for the "Tagbanwa" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock TAGBANWA = - new UnicodeBlock("TAGBANWA"); - - /** - * Constant for the "Limbu" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock LIMBU = - new UnicodeBlock("LIMBU"); - - /** - * Constant for the "Tai Le" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock TAI_LE = - new UnicodeBlock("TAI_LE", - "TAI LE", - "TAILE"); - - /** - * Constant for the "Khmer Symbols" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock KHMER_SYMBOLS = - new UnicodeBlock("KHMER_SYMBOLS", - "KHMER SYMBOLS", - "KHMERSYMBOLS"); - - /** - * Constant for the "Phonetic Extensions" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock PHONETIC_EXTENSIONS = - new UnicodeBlock("PHONETIC_EXTENSIONS", - "PHONETIC EXTENSIONS", - "PHONETICEXTENSIONS"); - - /** - * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = - new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A", - "MISCELLANEOUS MATHEMATICAL SYMBOLS-A", - "MISCELLANEOUSMATHEMATICALSYMBOLS-A"); - - /** - * Constant for the "Supplemental Arrows-A" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A = - new UnicodeBlock("SUPPLEMENTAL_ARROWS_A", - "SUPPLEMENTAL ARROWS-A", - "SUPPLEMENTALARROWS-A"); - - /** - * Constant for the "Supplemental Arrows-B" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B = - new UnicodeBlock("SUPPLEMENTAL_ARROWS_B", - "SUPPLEMENTAL ARROWS-B", - "SUPPLEMENTALARROWS-B"); - - /** - * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode - * character block. - * @since 1.5 - */ - public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = - new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B", - "MISCELLANEOUS MATHEMATICAL SYMBOLS-B", - "MISCELLANEOUSMATHEMATICALSYMBOLS-B"); - - /** - * Constant for the "Supplemental Mathematical Operators" Unicode - * character block. - * @since 1.5 - */ - public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS = - new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS", - "SUPPLEMENTAL MATHEMATICAL OPERATORS", - "SUPPLEMENTALMATHEMATICALOPERATORS"); - - /** - * Constant for the "Miscellaneous Symbols and Arrows" Unicode character - * block. - * @since 1.5 - */ - public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS = - new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS", - "MISCELLANEOUS SYMBOLS AND ARROWS", - "MISCELLANEOUSSYMBOLSANDARROWS"); - - /** - * Constant for the "Katakana Phonetic Extensions" Unicode character - * block. - * @since 1.5 - */ - public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS = - new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS", - "KATAKANA PHONETIC EXTENSIONS", - "KATAKANAPHONETICEXTENSIONS"); - - /** - * Constant for the "Yijing Hexagram Symbols" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS = - new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS", - "YIJING HEXAGRAM SYMBOLS", - "YIJINGHEXAGRAMSYMBOLS"); - - /** - * Constant for the "Variation Selectors" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock VARIATION_SELECTORS = - new UnicodeBlock("VARIATION_SELECTORS", - "VARIATION SELECTORS", - "VARIATIONSELECTORS"); - - /** - * Constant for the "Linear B Syllabary" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock LINEAR_B_SYLLABARY = - new UnicodeBlock("LINEAR_B_SYLLABARY", - "LINEAR B SYLLABARY", - "LINEARBSYLLABARY"); - - /** - * Constant for the "Linear B Ideograms" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock LINEAR_B_IDEOGRAMS = - new UnicodeBlock("LINEAR_B_IDEOGRAMS", - "LINEAR B IDEOGRAMS", - "LINEARBIDEOGRAMS"); - - /** - * Constant for the "Aegean Numbers" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock AEGEAN_NUMBERS = - new UnicodeBlock("AEGEAN_NUMBERS", - "AEGEAN NUMBERS", - "AEGEANNUMBERS"); - - /** - * Constant for the "Old Italic" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock OLD_ITALIC = - new UnicodeBlock("OLD_ITALIC", - "OLD ITALIC", - "OLDITALIC"); - - /** - * Constant for the "Gothic" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock GOTHIC = - new UnicodeBlock("GOTHIC"); - - /** - * Constant for the "Ugaritic" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock UGARITIC = - new UnicodeBlock("UGARITIC"); - - /** - * Constant for the "Deseret" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock DESERET = - new UnicodeBlock("DESERET"); - - /** - * Constant for the "Shavian" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock SHAVIAN = - new UnicodeBlock("SHAVIAN"); - - /** - * Constant for the "Osmanya" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock OSMANYA = - new UnicodeBlock("OSMANYA"); - - /** - * Constant for the "Cypriot Syllabary" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock CYPRIOT_SYLLABARY = - new UnicodeBlock("CYPRIOT_SYLLABARY", - "CYPRIOT SYLLABARY", - "CYPRIOTSYLLABARY"); - - /** - * Constant for the "Byzantine Musical Symbols" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS = - new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS", - "BYZANTINE MUSICAL SYMBOLS", - "BYZANTINEMUSICALSYMBOLS"); - - /** - * Constant for the "Musical Symbols" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock MUSICAL_SYMBOLS = - new UnicodeBlock("MUSICAL_SYMBOLS", - "MUSICAL SYMBOLS", - "MUSICALSYMBOLS"); - - /** - * Constant for the "Tai Xuan Jing Symbols" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS = - new UnicodeBlock("TAI_XUAN_JING_SYMBOLS", - "TAI XUAN JING SYMBOLS", - "TAIXUANJINGSYMBOLS"); - - /** - * Constant for the "Mathematical Alphanumeric Symbols" Unicode - * character block. - * @since 1.5 - */ - public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS = - new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS", - "MATHEMATICAL ALPHANUMERIC SYMBOLS", - "MATHEMATICALALPHANUMERICSYMBOLS"); - - /** - * Constant for the "CJK Unified Ideographs Extension B" Unicode - * character block. - * @since 1.5 - */ - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B", - "CJK UNIFIED IDEOGRAPHS EXTENSION B", - "CJKUNIFIEDIDEOGRAPHSEXTENSIONB"); - - /** - * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = - new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT", - "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT", - "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT"); - - /** - * Constant for the "Tags" Unicode character block. - * @since 1.5 - */ - public static final UnicodeBlock TAGS = - new UnicodeBlock("TAGS"); - - /** - * Constant for the "Variation Selectors Supplement" Unicode character - * block. - * @since 1.5 - */ - public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT = - new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT", - "VARIATION SELECTORS SUPPLEMENT", - "VARIATIONSELECTORSSUPPLEMENT"); - - /** - * Constant for the "Supplementary Private Use Area-A" Unicode character - * block. - * @since 1.5 - */ - public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A = - new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A", - "SUPPLEMENTARY PRIVATE USE AREA-A", - "SUPPLEMENTARYPRIVATEUSEAREA-A"); - - /** - * Constant for the "Supplementary Private Use Area-B" Unicode character - * block. - * @since 1.5 - */ - public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B = - new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B", - "SUPPLEMENTARY PRIVATE USE AREA-B", - "SUPPLEMENTARYPRIVATEUSEAREA-B"); - - /** - * Constant for the "High Surrogates" Unicode character block. - * This block represents codepoint values in the high surrogate - * range: U+D800 through U+DB7F - * - * @since 1.5 - */ - public static final UnicodeBlock HIGH_SURROGATES = - new UnicodeBlock("HIGH_SURROGATES", - "HIGH SURROGATES", - "HIGHSURROGATES"); - - /** - * Constant for the "High Private Use Surrogates" Unicode character - * block. - * This block represents codepoint values in the private use high - * surrogate range: U+DB80 through U+DBFF - * - * @since 1.5 - */ - public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES = - new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES", - "HIGH PRIVATE USE SURROGATES", - "HIGHPRIVATEUSESURROGATES"); - - /** - * Constant for the "Low Surrogates" Unicode character block. - * This block represents codepoint values in the low surrogate - * range: U+DC00 through U+DFFF - * - * @since 1.5 - */ - public static final UnicodeBlock LOW_SURROGATES = - new UnicodeBlock("LOW_SURROGATES", - "LOW SURROGATES", - "LOWSURROGATES"); - - /** - * Constant for the "Arabic Supplement" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock ARABIC_SUPPLEMENT = - new UnicodeBlock("ARABIC_SUPPLEMENT", - "ARABIC SUPPLEMENT", - "ARABICSUPPLEMENT"); - - /** - * Constant for the "NKo" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock NKO = - new UnicodeBlock("NKO"); - - /** - * Constant for the "Samaritan" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock SAMARITAN = - new UnicodeBlock("SAMARITAN"); - - /** - * Constant for the "Mandaic" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock MANDAIC = - new UnicodeBlock("MANDAIC"); - - /** - * Constant for the "Ethiopic Supplement" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock ETHIOPIC_SUPPLEMENT = - new UnicodeBlock("ETHIOPIC_SUPPLEMENT", - "ETHIOPIC SUPPLEMENT", - "ETHIOPICSUPPLEMENT"); - - /** - * Constant for the "Unified Canadian Aboriginal Syllabics Extended" - * Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = - new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED", - "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED", - "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED"); - - /** - * Constant for the "New Tai Lue" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock NEW_TAI_LUE = - new UnicodeBlock("NEW_TAI_LUE", - "NEW TAI LUE", - "NEWTAILUE"); - - /** - * Constant for the "Buginese" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock BUGINESE = - new UnicodeBlock("BUGINESE"); - - /** - * Constant for the "Tai Tham" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock TAI_THAM = - new UnicodeBlock("TAI_THAM", - "TAI THAM", - "TAITHAM"); - - /** - * Constant for the "Balinese" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock BALINESE = - new UnicodeBlock("BALINESE"); - - /** - * Constant for the "Sundanese" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock SUNDANESE = - new UnicodeBlock("SUNDANESE"); - - /** - * Constant for the "Batak" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock BATAK = - new UnicodeBlock("BATAK"); - - /** - * Constant for the "Lepcha" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock LEPCHA = - new UnicodeBlock("LEPCHA"); - - /** - * Constant for the "Ol Chiki" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock OL_CHIKI = - new UnicodeBlock("OL_CHIKI", - "OL CHIKI", - "OLCHIKI"); - - /** - * Constant for the "Vedic Extensions" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock VEDIC_EXTENSIONS = - new UnicodeBlock("VEDIC_EXTENSIONS", - "VEDIC EXTENSIONS", - "VEDICEXTENSIONS"); - - /** - * Constant for the "Phonetic Extensions Supplement" Unicode character - * block. - * @since 1.7 - */ - public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT = - new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT", - "PHONETIC EXTENSIONS SUPPLEMENT", - "PHONETICEXTENSIONSSUPPLEMENT"); - - /** - * Constant for the "Combining Diacritical Marks Supplement" Unicode - * character block. - * @since 1.7 - */ - public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = - new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT", - "COMBINING DIACRITICAL MARKS SUPPLEMENT", - "COMBININGDIACRITICALMARKSSUPPLEMENT"); - - /** - * Constant for the "Glagolitic" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock GLAGOLITIC = - new UnicodeBlock("GLAGOLITIC"); - - /** - * Constant for the "Latin Extended-C" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock LATIN_EXTENDED_C = - new UnicodeBlock("LATIN_EXTENDED_C", - "LATIN EXTENDED-C", - "LATINEXTENDED-C"); - - /** - * Constant for the "Coptic" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock COPTIC = - new UnicodeBlock("COPTIC"); - - /** - * Constant for the "Georgian Supplement" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock GEORGIAN_SUPPLEMENT = - new UnicodeBlock("GEORGIAN_SUPPLEMENT", - "GEORGIAN SUPPLEMENT", - "GEORGIANSUPPLEMENT"); - - /** - * Constant for the "Tifinagh" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock TIFINAGH = - new UnicodeBlock("TIFINAGH"); - - /** - * Constant for the "Ethiopic Extended" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock ETHIOPIC_EXTENDED = - new UnicodeBlock("ETHIOPIC_EXTENDED", - "ETHIOPIC EXTENDED", - "ETHIOPICEXTENDED"); - - /** - * Constant for the "Cyrillic Extended-A" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock CYRILLIC_EXTENDED_A = - new UnicodeBlock("CYRILLIC_EXTENDED_A", - "CYRILLIC EXTENDED-A", - "CYRILLICEXTENDED-A"); - - /** - * Constant for the "Supplemental Punctuation" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION = - new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION", - "SUPPLEMENTAL PUNCTUATION", - "SUPPLEMENTALPUNCTUATION"); - - /** - * Constant for the "CJK Strokes" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock CJK_STROKES = - new UnicodeBlock("CJK_STROKES", - "CJK STROKES", - "CJKSTROKES"); - - /** - * Constant for the "Lisu" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock LISU = - new UnicodeBlock("LISU"); - - /** - * Constant for the "Vai" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock VAI = - new UnicodeBlock("VAI"); - - /** - * Constant for the "Cyrillic Extended-B" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock CYRILLIC_EXTENDED_B = - new UnicodeBlock("CYRILLIC_EXTENDED_B", - "CYRILLIC EXTENDED-B", - "CYRILLICEXTENDED-B"); - - /** - * Constant for the "Bamum" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock BAMUM = - new UnicodeBlock("BAMUM"); - - /** - * Constant for the "Modifier Tone Letters" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock MODIFIER_TONE_LETTERS = - new UnicodeBlock("MODIFIER_TONE_LETTERS", - "MODIFIER TONE LETTERS", - "MODIFIERTONELETTERS"); - - /** - * Constant for the "Latin Extended-D" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock LATIN_EXTENDED_D = - new UnicodeBlock("LATIN_EXTENDED_D", - "LATIN EXTENDED-D", - "LATINEXTENDED-D"); - - /** - * Constant for the "Syloti Nagri" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock SYLOTI_NAGRI = - new UnicodeBlock("SYLOTI_NAGRI", - "SYLOTI NAGRI", - "SYLOTINAGRI"); - - /** - * Constant for the "Common Indic Number Forms" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS = - new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS", - "COMMON INDIC NUMBER FORMS", - "COMMONINDICNUMBERFORMS"); - - /** - * Constant for the "Phags-pa" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock PHAGS_PA = - new UnicodeBlock("PHAGS_PA", - "PHAGS-PA"); - - /** - * Constant for the "Saurashtra" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock SAURASHTRA = - new UnicodeBlock("SAURASHTRA"); - - /** - * Constant for the "Devanagari Extended" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock DEVANAGARI_EXTENDED = - new UnicodeBlock("DEVANAGARI_EXTENDED", - "DEVANAGARI EXTENDED", - "DEVANAGARIEXTENDED"); - - /** - * Constant for the "Kayah Li" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock KAYAH_LI = - new UnicodeBlock("KAYAH_LI", - "KAYAH LI", - "KAYAHLI"); - - /** - * Constant for the "Rejang" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock REJANG = - new UnicodeBlock("REJANG"); - - /** - * Constant for the "Hangul Jamo Extended-A" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A = - new UnicodeBlock("HANGUL_JAMO_EXTENDED_A", - "HANGUL JAMO EXTENDED-A", - "HANGULJAMOEXTENDED-A"); - - /** - * Constant for the "Javanese" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock JAVANESE = - new UnicodeBlock("JAVANESE"); - - /** - * Constant for the "Cham" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock CHAM = - new UnicodeBlock("CHAM"); - - /** - * Constant for the "Myanmar Extended-A" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock MYANMAR_EXTENDED_A = - new UnicodeBlock("MYANMAR_EXTENDED_A", - "MYANMAR EXTENDED-A", - "MYANMAREXTENDED-A"); - - /** - * Constant for the "Tai Viet" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock TAI_VIET = - new UnicodeBlock("TAI_VIET", - "TAI VIET", - "TAIVIET"); - - /** - * Constant for the "Ethiopic Extended-A" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock ETHIOPIC_EXTENDED_A = - new UnicodeBlock("ETHIOPIC_EXTENDED_A", - "ETHIOPIC EXTENDED-A", - "ETHIOPICEXTENDED-A"); - - /** - * Constant for the "Meetei Mayek" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock MEETEI_MAYEK = - new UnicodeBlock("MEETEI_MAYEK", - "MEETEI MAYEK", - "MEETEIMAYEK"); - - /** - * Constant for the "Hangul Jamo Extended-B" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B = - new UnicodeBlock("HANGUL_JAMO_EXTENDED_B", - "HANGUL JAMO EXTENDED-B", - "HANGULJAMOEXTENDED-B"); - - /** - * Constant for the "Vertical Forms" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock VERTICAL_FORMS = - new UnicodeBlock("VERTICAL_FORMS", - "VERTICAL FORMS", - "VERTICALFORMS"); - - /** - * Constant for the "Ancient Greek Numbers" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock ANCIENT_GREEK_NUMBERS = - new UnicodeBlock("ANCIENT_GREEK_NUMBERS", - "ANCIENT GREEK NUMBERS", - "ANCIENTGREEKNUMBERS"); - - /** - * Constant for the "Ancient Symbols" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock ANCIENT_SYMBOLS = - new UnicodeBlock("ANCIENT_SYMBOLS", - "ANCIENT SYMBOLS", - "ANCIENTSYMBOLS"); - - /** - * Constant for the "Phaistos Disc" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock PHAISTOS_DISC = - new UnicodeBlock("PHAISTOS_DISC", - "PHAISTOS DISC", - "PHAISTOSDISC"); - - /** - * Constant for the "Lycian" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock LYCIAN = - new UnicodeBlock("LYCIAN"); - - /** - * Constant for the "Carian" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock CARIAN = - new UnicodeBlock("CARIAN"); - - /** - * Constant for the "Old Persian" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock OLD_PERSIAN = - new UnicodeBlock("OLD_PERSIAN", - "OLD PERSIAN", - "OLDPERSIAN"); - - /** - * Constant for the "Imperial Aramaic" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock IMPERIAL_ARAMAIC = - new UnicodeBlock("IMPERIAL_ARAMAIC", - "IMPERIAL ARAMAIC", - "IMPERIALARAMAIC"); - - /** - * Constant for the "Phoenician" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock PHOENICIAN = - new UnicodeBlock("PHOENICIAN"); - - /** - * Constant for the "Lydian" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock LYDIAN = - new UnicodeBlock("LYDIAN"); - - /** - * Constant for the "Kharoshthi" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock KHAROSHTHI = - new UnicodeBlock("KHAROSHTHI"); - - /** - * Constant for the "Old South Arabian" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock OLD_SOUTH_ARABIAN = - new UnicodeBlock("OLD_SOUTH_ARABIAN", - "OLD SOUTH ARABIAN", - "OLDSOUTHARABIAN"); - - /** - * Constant for the "Avestan" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock AVESTAN = - new UnicodeBlock("AVESTAN"); - - /** - * Constant for the "Inscriptional Parthian" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN = - new UnicodeBlock("INSCRIPTIONAL_PARTHIAN", - "INSCRIPTIONAL PARTHIAN", - "INSCRIPTIONALPARTHIAN"); - - /** - * Constant for the "Inscriptional Pahlavi" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI = - new UnicodeBlock("INSCRIPTIONAL_PAHLAVI", - "INSCRIPTIONAL PAHLAVI", - "INSCRIPTIONALPAHLAVI"); - - /** - * Constant for the "Old Turkic" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock OLD_TURKIC = - new UnicodeBlock("OLD_TURKIC", - "OLD TURKIC", - "OLDTURKIC"); - - /** - * Constant for the "Rumi Numeral Symbols" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS = - new UnicodeBlock("RUMI_NUMERAL_SYMBOLS", - "RUMI NUMERAL SYMBOLS", - "RUMINUMERALSYMBOLS"); - - /** - * Constant for the "Brahmi" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock BRAHMI = - new UnicodeBlock("BRAHMI"); - - /** - * Constant for the "Kaithi" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock KAITHI = - new UnicodeBlock("KAITHI"); - - /** - * Constant for the "Cuneiform" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock CUNEIFORM = - new UnicodeBlock("CUNEIFORM"); - - /** - * Constant for the "Cuneiform Numbers and Punctuation" Unicode - * character block. - * @since 1.7 - */ - public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION = - new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION", - "CUNEIFORM NUMBERS AND PUNCTUATION", - "CUNEIFORMNUMBERSANDPUNCTUATION"); - - /** - * Constant for the "Egyptian Hieroglyphs" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS = - new UnicodeBlock("EGYPTIAN_HIEROGLYPHS", - "EGYPTIAN HIEROGLYPHS", - "EGYPTIANHIEROGLYPHS"); - - /** - * Constant for the "Bamum Supplement" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock BAMUM_SUPPLEMENT = - new UnicodeBlock("BAMUM_SUPPLEMENT", - "BAMUM SUPPLEMENT", - "BAMUMSUPPLEMENT"); - - /** - * Constant for the "Kana Supplement" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock KANA_SUPPLEMENT = - new UnicodeBlock("KANA_SUPPLEMENT", - "KANA SUPPLEMENT", - "KANASUPPLEMENT"); - - /** - * Constant for the "Ancient Greek Musical Notation" Unicode character - * block. - * @since 1.7 - */ - public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION = - new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION", - "ANCIENT GREEK MUSICAL NOTATION", - "ANCIENTGREEKMUSICALNOTATION"); - - /** - * Constant for the "Counting Rod Numerals" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock COUNTING_ROD_NUMERALS = - new UnicodeBlock("COUNTING_ROD_NUMERALS", - "COUNTING ROD NUMERALS", - "COUNTINGRODNUMERALS"); - - /** - * Constant for the "Mahjong Tiles" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock MAHJONG_TILES = - new UnicodeBlock("MAHJONG_TILES", - "MAHJONG TILES", - "MAHJONGTILES"); - - /** - * Constant for the "Domino Tiles" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock DOMINO_TILES = - new UnicodeBlock("DOMINO_TILES", - "DOMINO TILES", - "DOMINOTILES"); - - /** - * Constant for the "Playing Cards" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock PLAYING_CARDS = - new UnicodeBlock("PLAYING_CARDS", - "PLAYING CARDS", - "PLAYINGCARDS"); - - /** - * Constant for the "Enclosed Alphanumeric Supplement" Unicode character - * block. - * @since 1.7 - */ - public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT = - new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT", - "ENCLOSED ALPHANUMERIC SUPPLEMENT", - "ENCLOSEDALPHANUMERICSUPPLEMENT"); - - /** - * Constant for the "Enclosed Ideographic Supplement" Unicode character - * block. - * @since 1.7 - */ - public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = - new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT", - "ENCLOSED IDEOGRAPHIC SUPPLEMENT", - "ENCLOSEDIDEOGRAPHICSUPPLEMENT"); - - /** - * Constant for the "Miscellaneous Symbols And Pictographs" Unicode - * character block. - * @since 1.7 - */ - public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = - new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS", - "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS", - "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS"); - - /** - * Constant for the "Emoticons" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock EMOTICONS = - new UnicodeBlock("EMOTICONS"); - - /** - * Constant for the "Transport And Map Symbols" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS = - new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS", - "TRANSPORT AND MAP SYMBOLS", - "TRANSPORTANDMAPSYMBOLS"); - - /** - * Constant for the "Alchemical Symbols" Unicode character block. - * @since 1.7 - */ - public static final UnicodeBlock ALCHEMICAL_SYMBOLS = - new UnicodeBlock("ALCHEMICAL_SYMBOLS", - "ALCHEMICAL SYMBOLS", - "ALCHEMICALSYMBOLS"); - - /** - * Constant for the "CJK Unified Ideographs Extension C" Unicode - * character block. - * @since 1.7 - */ - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C", - "CJK UNIFIED IDEOGRAPHS EXTENSION C", - "CJKUNIFIEDIDEOGRAPHSEXTENSIONC"); - - /** - * Constant for the "CJK Unified Ideographs Extension D" Unicode - * character block. - * @since 1.7 - */ - public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = - new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D", - "CJK UNIFIED IDEOGRAPHS EXTENSION D", - "CJKUNIFIEDIDEOGRAPHSEXTENSIOND"); - - private static final int blockStarts[] = { - 0x0000, // 0000..007F; Basic Latin - 0x0080, // 0080..00FF; Latin-1 Supplement - 0x0100, // 0100..017F; Latin Extended-A - 0x0180, // 0180..024F; Latin Extended-B - 0x0250, // 0250..02AF; IPA Extensions - 0x02B0, // 02B0..02FF; Spacing Modifier Letters - 0x0300, // 0300..036F; Combining Diacritical Marks - 0x0370, // 0370..03FF; Greek and Coptic - 0x0400, // 0400..04FF; Cyrillic - 0x0500, // 0500..052F; Cyrillic Supplement - 0x0530, // 0530..058F; Armenian - 0x0590, // 0590..05FF; Hebrew - 0x0600, // 0600..06FF; Arabic - 0x0700, // 0700..074F; Syriac - 0x0750, // 0750..077F; Arabic Supplement - 0x0780, // 0780..07BF; Thaana - 0x07C0, // 07C0..07FF; NKo - 0x0800, // 0800..083F; Samaritan - 0x0840, // 0840..085F; Mandaic - 0x0860, // unassigned - 0x0900, // 0900..097F; Devanagari - 0x0980, // 0980..09FF; Bengali - 0x0A00, // 0A00..0A7F; Gurmukhi - 0x0A80, // 0A80..0AFF; Gujarati - 0x0B00, // 0B00..0B7F; Oriya - 0x0B80, // 0B80..0BFF; Tamil - 0x0C00, // 0C00..0C7F; Telugu - 0x0C80, // 0C80..0CFF; Kannada - 0x0D00, // 0D00..0D7F; Malayalam - 0x0D80, // 0D80..0DFF; Sinhala - 0x0E00, // 0E00..0E7F; Thai - 0x0E80, // 0E80..0EFF; Lao - 0x0F00, // 0F00..0FFF; Tibetan - 0x1000, // 1000..109F; Myanmar - 0x10A0, // 10A0..10FF; Georgian - 0x1100, // 1100..11FF; Hangul Jamo - 0x1200, // 1200..137F; Ethiopic - 0x1380, // 1380..139F; Ethiopic Supplement - 0x13A0, // 13A0..13FF; Cherokee - 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics - 0x1680, // 1680..169F; Ogham - 0x16A0, // 16A0..16FF; Runic - 0x1700, // 1700..171F; Tagalog - 0x1720, // 1720..173F; Hanunoo - 0x1740, // 1740..175F; Buhid - 0x1760, // 1760..177F; Tagbanwa - 0x1780, // 1780..17FF; Khmer - 0x1800, // 1800..18AF; Mongolian - 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended - 0x1900, // 1900..194F; Limbu - 0x1950, // 1950..197F; Tai Le - 0x1980, // 1980..19DF; New Tai Lue - 0x19E0, // 19E0..19FF; Khmer Symbols - 0x1A00, // 1A00..1A1F; Buginese - 0x1A20, // 1A20..1AAF; Tai Tham - 0x1AB0, // unassigned - 0x1B00, // 1B00..1B7F; Balinese - 0x1B80, // 1B80..1BBF; Sundanese - 0x1BC0, // 1BC0..1BFF; Batak - 0x1C00, // 1C00..1C4F; Lepcha - 0x1C50, // 1C50..1C7F; Ol Chiki - 0x1C80, // unassigned - 0x1CD0, // 1CD0..1CFF; Vedic Extensions - 0x1D00, // 1D00..1D7F; Phonetic Extensions - 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement - 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement - 0x1E00, // 1E00..1EFF; Latin Extended Additional - 0x1F00, // 1F00..1FFF; Greek Extended - 0x2000, // 2000..206F; General Punctuation - 0x2070, // 2070..209F; Superscripts and Subscripts - 0x20A0, // 20A0..20CF; Currency Symbols - 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols - 0x2100, // 2100..214F; Letterlike Symbols - 0x2150, // 2150..218F; Number Forms - 0x2190, // 2190..21FF; Arrows - 0x2200, // 2200..22FF; Mathematical Operators - 0x2300, // 2300..23FF; Miscellaneous Technical - 0x2400, // 2400..243F; Control Pictures - 0x2440, // 2440..245F; Optical Character Recognition - 0x2460, // 2460..24FF; Enclosed Alphanumerics - 0x2500, // 2500..257F; Box Drawing - 0x2580, // 2580..259F; Block Elements - 0x25A0, // 25A0..25FF; Geometric Shapes - 0x2600, // 2600..26FF; Miscellaneous Symbols - 0x2700, // 2700..27BF; Dingbats - 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A - 0x27F0, // 27F0..27FF; Supplemental Arrows-A - 0x2800, // 2800..28FF; Braille Patterns - 0x2900, // 2900..297F; Supplemental Arrows-B - 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B - 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators - 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows - 0x2C00, // 2C00..2C5F; Glagolitic - 0x2C60, // 2C60..2C7F; Latin Extended-C - 0x2C80, // 2C80..2CFF; Coptic - 0x2D00, // 2D00..2D2F; Georgian Supplement - 0x2D30, // 2D30..2D7F; Tifinagh - 0x2D80, // 2D80..2DDF; Ethiopic Extended - 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A - 0x2E00, // 2E00..2E7F; Supplemental Punctuation - 0x2E80, // 2E80..2EFF; CJK Radicals Supplement - 0x2F00, // 2F00..2FDF; Kangxi Radicals - 0x2FE0, // unassigned - 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters - 0x3000, // 3000..303F; CJK Symbols and Punctuation - 0x3040, // 3040..309F; Hiragana - 0x30A0, // 30A0..30FF; Katakana - 0x3100, // 3100..312F; Bopomofo - 0x3130, // 3130..318F; Hangul Compatibility Jamo - 0x3190, // 3190..319F; Kanbun - 0x31A0, // 31A0..31BF; Bopomofo Extended - 0x31C0, // 31C0..31EF; CJK Strokes - 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions - 0x3200, // 3200..32FF; Enclosed CJK Letters and Months - 0x3300, // 3300..33FF; CJK Compatibility - 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A - 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols - 0x4E00, // 4E00..9FFF; CJK Unified Ideographs - 0xA000, // A000..A48F; Yi Syllables - 0xA490, // A490..A4CF; Yi Radicals - 0xA4D0, // A4D0..A4FF; Lisu - 0xA500, // A500..A63F; Vai - 0xA640, // A640..A69F; Cyrillic Extended-B - 0xA6A0, // A6A0..A6FF; Bamum - 0xA700, // A700..A71F; Modifier Tone Letters - 0xA720, // A720..A7FF; Latin Extended-D - 0xA800, // A800..A82F; Syloti Nagri - 0xA830, // A830..A83F; Common Indic Number Forms - 0xA840, // A840..A87F; Phags-pa - 0xA880, // A880..A8DF; Saurashtra - 0xA8E0, // A8E0..A8FF; Devanagari Extended - 0xA900, // A900..A92F; Kayah Li - 0xA930, // A930..A95F; Rejang - 0xA960, // A960..A97F; Hangul Jamo Extended-A - 0xA980, // A980..A9DF; Javanese - 0xA9E0, // unassigned - 0xAA00, // AA00..AA5F; Cham - 0xAA60, // AA60..AA7F; Myanmar Extended-A - 0xAA80, // AA80..AADF; Tai Viet - 0xAAE0, // unassigned - 0xAB00, // AB00..AB2F; Ethiopic Extended-A - 0xAB30, // unassigned - 0xABC0, // ABC0..ABFF; Meetei Mayek - 0xAC00, // AC00..D7AF; Hangul Syllables - 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B - 0xD800, // D800..DB7F; High Surrogates - 0xDB80, // DB80..DBFF; High Private Use Surrogates - 0xDC00, // DC00..DFFF; Low Surrogates - 0xE000, // E000..F8FF; Private Use Area - 0xF900, // F900..FAFF; CJK Compatibility Ideographs - 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms - 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A - 0xFE00, // FE00..FE0F; Variation Selectors - 0xFE10, // FE10..FE1F; Vertical Forms - 0xFE20, // FE20..FE2F; Combining Half Marks - 0xFE30, // FE30..FE4F; CJK Compatibility Forms - 0xFE50, // FE50..FE6F; Small Form Variants - 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B - 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms - 0xFFF0, // FFF0..FFFF; Specials - 0x10000, // 10000..1007F; Linear B Syllabary - 0x10080, // 10080..100FF; Linear B Ideograms - 0x10100, // 10100..1013F; Aegean Numbers - 0x10140, // 10140..1018F; Ancient Greek Numbers - 0x10190, // 10190..101CF; Ancient Symbols - 0x101D0, // 101D0..101FF; Phaistos Disc - 0x10200, // unassigned - 0x10280, // 10280..1029F; Lycian - 0x102A0, // 102A0..102DF; Carian - 0x102E0, // unassigned - 0x10300, // 10300..1032F; Old Italic - 0x10330, // 10330..1034F; Gothic - 0x10350, // unassigned - 0x10380, // 10380..1039F; Ugaritic - 0x103A0, // 103A0..103DF; Old Persian - 0x103E0, // unassigned - 0x10400, // 10400..1044F; Deseret - 0x10450, // 10450..1047F; Shavian - 0x10480, // 10480..104AF; Osmanya - 0x104B0, // unassigned - 0x10800, // 10800..1083F; Cypriot Syllabary - 0x10840, // 10840..1085F; Imperial Aramaic - 0x10860, // unassigned - 0x10900, // 10900..1091F; Phoenician - 0x10920, // 10920..1093F; Lydian - 0x10940, // unassigned - 0x10A00, // 10A00..10A5F; Kharoshthi - 0x10A60, // 10A60..10A7F; Old South Arabian - 0x10A80, // unassigned - 0x10B00, // 10B00..10B3F; Avestan - 0x10B40, // 10B40..10B5F; Inscriptional Parthian - 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi - 0x10B80, // unassigned - 0x10C00, // 10C00..10C4F; Old Turkic - 0x10C50, // unassigned - 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols - 0x10E80, // unassigned - 0x11000, // 11000..1107F; Brahmi - 0x11080, // 11080..110CF; Kaithi - 0x110D0, // unassigned - 0x12000, // 12000..123FF; Cuneiform - 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation - 0x12480, // unassigned - 0x13000, // 13000..1342F; Egyptian Hieroglyphs - 0x13430, // unassigned - 0x16800, // 16800..16A3F; Bamum Supplement - 0x16A40, // unassigned - 0x1B000, // 1B000..1B0FF; Kana Supplement - 0x1B100, // unassigned - 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols - 0x1D100, // 1D100..1D1FF; Musical Symbols - 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation - 0x1D250, // unassigned - 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols - 0x1D360, // 1D360..1D37F; Counting Rod Numerals - 0x1D380, // unassigned - 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols - 0x1D800, // unassigned - 0x1F000, // 1F000..1F02F; Mahjong Tiles - 0x1F030, // 1F030..1F09F; Domino Tiles - 0x1F0A0, // 1F0A0..1F0FF; Playing Cards - 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement - 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement - 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols And Pictographs - 0x1F600, // 1F600..1F64F; Emoticons - 0x1F650, // unassigned - 0x1F680, // 1F680..1F6FF; Transport And Map Symbols - 0x1F700, // 1F700..1F77F; Alchemical Symbols - 0x1F780, // unassigned - 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B - 0x2A6E0, // unassigned - 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C - 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D - 0x2B820, // unassigned - 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement - 0x2FA20, // unassigned - 0xE0000, // E0000..E007F; Tags - 0xE0080, // unassigned - 0xE0100, // E0100..E01EF; Variation Selectors Supplement - 0xE01F0, // unassigned - 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A - 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B - }; - - 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, - CYRILLIC_SUPPLEMENTARY, - ARMENIAN, - HEBREW, - ARABIC, - SYRIAC, - ARABIC_SUPPLEMENT, - THAANA, - NKO, - SAMARITAN, - MANDAIC, - null, - DEVANAGARI, - BENGALI, - GURMUKHI, - GUJARATI, - ORIYA, - TAMIL, - TELUGU, - KANNADA, - MALAYALAM, - SINHALA, - THAI, - LAO, - TIBETAN, - MYANMAR, - GEORGIAN, - HANGUL_JAMO, - ETHIOPIC, - ETHIOPIC_SUPPLEMENT, - CHEROKEE, - UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS, - OGHAM, - RUNIC, - TAGALOG, - HANUNOO, - BUHID, - TAGBANWA, - KHMER, - MONGOLIAN, - UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED, - LIMBU, - TAI_LE, - NEW_TAI_LUE, - KHMER_SYMBOLS, - BUGINESE, - TAI_THAM, - null, - BALINESE, - SUNDANESE, - BATAK, - LEPCHA, - OL_CHIKI, - null, - VEDIC_EXTENSIONS, - PHONETIC_EXTENSIONS, - PHONETIC_EXTENSIONS_SUPPLEMENT, - COMBINING_DIACRITICAL_MARKS_SUPPLEMENT, - 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, - MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A, - SUPPLEMENTAL_ARROWS_A, - BRAILLE_PATTERNS, - SUPPLEMENTAL_ARROWS_B, - MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B, - SUPPLEMENTAL_MATHEMATICAL_OPERATORS, - MISCELLANEOUS_SYMBOLS_AND_ARROWS, - GLAGOLITIC, - LATIN_EXTENDED_C, - COPTIC, - GEORGIAN_SUPPLEMENT, - TIFINAGH, - ETHIOPIC_EXTENDED, - CYRILLIC_EXTENDED_A, - SUPPLEMENTAL_PUNCTUATION, - CJK_RADICALS_SUPPLEMENT, - KANGXI_RADICALS, - null, - IDEOGRAPHIC_DESCRIPTION_CHARACTERS, - CJK_SYMBOLS_AND_PUNCTUATION, - HIRAGANA, - KATAKANA, - BOPOMOFO, - HANGUL_COMPATIBILITY_JAMO, - KANBUN, - BOPOMOFO_EXTENDED, - CJK_STROKES, - KATAKANA_PHONETIC_EXTENSIONS, - ENCLOSED_CJK_LETTERS_AND_MONTHS, - CJK_COMPATIBILITY, - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A, - YIJING_HEXAGRAM_SYMBOLS, - CJK_UNIFIED_IDEOGRAPHS, - YI_SYLLABLES, - YI_RADICALS, - LISU, - VAI, - CYRILLIC_EXTENDED_B, - BAMUM, - MODIFIER_TONE_LETTERS, - LATIN_EXTENDED_D, - SYLOTI_NAGRI, - COMMON_INDIC_NUMBER_FORMS, - PHAGS_PA, - SAURASHTRA, - DEVANAGARI_EXTENDED, - KAYAH_LI, - REJANG, - HANGUL_JAMO_EXTENDED_A, - JAVANESE, - null, - CHAM, - MYANMAR_EXTENDED_A, - TAI_VIET, - null, - ETHIOPIC_EXTENDED_A, - null, - MEETEI_MAYEK, - HANGUL_SYLLABLES, - HANGUL_JAMO_EXTENDED_B, - HIGH_SURROGATES, - HIGH_PRIVATE_USE_SURROGATES, - LOW_SURROGATES, - PRIVATE_USE_AREA, - CJK_COMPATIBILITY_IDEOGRAPHS, - ALPHABETIC_PRESENTATION_FORMS, - ARABIC_PRESENTATION_FORMS_A, - VARIATION_SELECTORS, - VERTICAL_FORMS, - COMBINING_HALF_MARKS, - CJK_COMPATIBILITY_FORMS, - SMALL_FORM_VARIANTS, - ARABIC_PRESENTATION_FORMS_B, - HALFWIDTH_AND_FULLWIDTH_FORMS, - SPECIALS, - LINEAR_B_SYLLABARY, - LINEAR_B_IDEOGRAMS, - AEGEAN_NUMBERS, - ANCIENT_GREEK_NUMBERS, - ANCIENT_SYMBOLS, - PHAISTOS_DISC, - null, - LYCIAN, - CARIAN, - null, - OLD_ITALIC, - GOTHIC, - null, - UGARITIC, - OLD_PERSIAN, - null, - DESERET, - SHAVIAN, - OSMANYA, - null, - CYPRIOT_SYLLABARY, - IMPERIAL_ARAMAIC, - null, - PHOENICIAN, - LYDIAN, - null, - KHAROSHTHI, - OLD_SOUTH_ARABIAN, - null, - AVESTAN, - INSCRIPTIONAL_PARTHIAN, - INSCRIPTIONAL_PAHLAVI, - null, - OLD_TURKIC, - null, - RUMI_NUMERAL_SYMBOLS, - null, - BRAHMI, - KAITHI, - null, - CUNEIFORM, - CUNEIFORM_NUMBERS_AND_PUNCTUATION, - null, - EGYPTIAN_HIEROGLYPHS, - null, - BAMUM_SUPPLEMENT, - null, - KANA_SUPPLEMENT, - null, - BYZANTINE_MUSICAL_SYMBOLS, - MUSICAL_SYMBOLS, - ANCIENT_GREEK_MUSICAL_NOTATION, - null, - TAI_XUAN_JING_SYMBOLS, - COUNTING_ROD_NUMERALS, - null, - MATHEMATICAL_ALPHANUMERIC_SYMBOLS, - null, - MAHJONG_TILES, - DOMINO_TILES, - PLAYING_CARDS, - ENCLOSED_ALPHANUMERIC_SUPPLEMENT, - ENCLOSED_IDEOGRAPHIC_SUPPLEMENT, - MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS, - EMOTICONS, - null, - TRANSPORT_AND_MAP_SYMBOLS, - ALCHEMICAL_SYMBOLS, - null, - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B, - null, - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C, - CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D, - null, - CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT, - null, - TAGS, - null, - VARIATION_SELECTORS_SUPPLEMENT, - null, - SUPPLEMENTARY_PRIVATE_USE_AREA_A, - SUPPLEMENTARY_PRIVATE_USE_AREA_B - }; - - - /** - * Returns the object representing the Unicode block containing the - * given character, or {@code null} if the character is not a - * member of a defined block. - * - *

Note: This method cannot handle - * supplementary - * characters. To support all Unicode characters, including - * supplementary characters, use the {@link #of(int)} method. - * - * @param c The character in question - * @return The {@code UnicodeBlock} instance representing the - * Unicode block of which this character is a member, or - * {@code null} if the character is not a member of any - * Unicode block - */ - public static UnicodeBlock of(char c) { - return of((int)c); - } - - /** - * Returns the object representing the Unicode block - * containing the given character (Unicode code point), or - * {@code null} if the character is not a member of a - * defined block. - * - * @param codePoint the character (Unicode code point) in question. - * @return The {@code UnicodeBlock} instance representing the - * Unicode block of which this character is a member, or - * {@code null} if the character is not a member of any - * Unicode block - * @exception IllegalArgumentException if the specified - * {@code codePoint} is an invalid Unicode code point. - * @see Character#isValidCodePoint(int) - * @since 1.5 - */ - public static UnicodeBlock of(int codePoint) { - if (!isValidCodePoint(codePoint)) { - throw new IllegalArgumentException(); - } - - int top, bottom, current; - bottom = 0; - top = blockStarts.length; - current = top/2; - - // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom] - while (top - bottom > 1) { - if (codePoint >= blockStarts[current]) { - bottom = current; - } else { - top = current; - } - current = (top + bottom) / 2; - } - return blocks[current]; - } - - /** - * Returns the UnicodeBlock with the given name. Block - * names are determined by The Unicode Standard. The file - * Blocks-<version>.txt defines blocks for a particular - * version of the standard. The {@link Character} class specifies - * the version of the standard that it supports. - *

- * This method accepts block names in the following forms: - *

    - *
  1. Canonical block names as defined by the Unicode Standard. - * For example, the standard defines a "Basic Latin" block. Therefore, this - * method accepts "Basic Latin" as a valid block name. The documentation of - * each UnicodeBlock provides the canonical name. - *
  2. Canonical block names with all spaces removed. For example, "BasicLatin" - * is a valid block name for the "Basic Latin" block. - *
  3. The text representation of each constant UnicodeBlock identifier. - * For example, this method will return the {@link #BASIC_LATIN} block if - * provided with the "BASIC_LATIN" name. This form replaces all spaces and - * hyphens in the canonical name with underscores. - *
- * Finally, character case is ignored for all of the valid block name forms. - * For example, "BASIC_LATIN" and "basic_latin" are both valid block names. - * The en_US locale's case mapping rules are used to provide case-insensitive - * string comparisons for block name validation. - *

- * If the Unicode Standard changes block names, both the previous and - * current names will be accepted. - * - * @param blockName A {@code UnicodeBlock} name. - * @return The {@code UnicodeBlock} instance identified - * by {@code blockName} - * @throws IllegalArgumentException if {@code blockName} is an - * invalid name - * @throws NullPointerException if {@code blockName} is null - * @since 1.5 - */ - public static final UnicodeBlock forName(String blockName) { - UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US)); - if (block == null) { - throw new IllegalArgumentException(); - } - return block; - } - } - - - /** - * A family of character subsets representing the character scripts - * defined in the - * Unicode Standard Annex #24: Script Names. Every Unicode - * character is assigned to a single Unicode script, either a specific - * script, such as {@link Character.UnicodeScript#LATIN Latin}, or - * one of the following three special values, - * {@link Character.UnicodeScript#INHERITED Inherited}, - * {@link Character.UnicodeScript#COMMON Common} or - * {@link Character.UnicodeScript#UNKNOWN Unknown}. - * - * @since 1.7 - */ - public static enum UnicodeScript { - /** - * Unicode script "Common". - */ - COMMON, - - /** - * Unicode script "Latin". - */ - LATIN, - - /** - * Unicode script "Greek". - */ - GREEK, - - /** - * Unicode script "Cyrillic". - */ - CYRILLIC, - - /** - * Unicode script "Armenian". - */ - ARMENIAN, - - /** - * Unicode script "Hebrew". - */ - HEBREW, - - /** - * Unicode script "Arabic". - */ - ARABIC, - - /** - * Unicode script "Syriac". - */ - SYRIAC, - - /** - * Unicode script "Thaana". - */ - THAANA, - - /** - * Unicode script "Devanagari". - */ - DEVANAGARI, - - /** - * Unicode script "Bengali". - */ - BENGALI, - - /** - * Unicode script "Gurmukhi". - */ - GURMUKHI, - - /** - * Unicode script "Gujarati". - */ - GUJARATI, - - /** - * Unicode script "Oriya". - */ - ORIYA, - - /** - * Unicode script "Tamil". - */ - TAMIL, - - /** - * Unicode script "Telugu". - */ - TELUGU, - - /** - * Unicode script "Kannada". - */ - KANNADA, - - /** - * Unicode script "Malayalam". - */ - MALAYALAM, - - /** - * Unicode script "Sinhala". - */ - SINHALA, - - /** - * Unicode script "Thai". - */ - THAI, - - /** - * Unicode script "Lao". - */ - LAO, - - /** - * Unicode script "Tibetan". - */ - TIBETAN, - - /** - * Unicode script "Myanmar". - */ - MYANMAR, - - /** - * Unicode script "Georgian". - */ - GEORGIAN, - - /** - * Unicode script "Hangul". - */ - HANGUL, - - /** - * Unicode script "Ethiopic". - */ - ETHIOPIC, - - /** - * Unicode script "Cherokee". - */ - CHEROKEE, - - /** - * Unicode script "Canadian_Aboriginal". - */ - CANADIAN_ABORIGINAL, - - /** - * Unicode script "Ogham". - */ - OGHAM, - - /** - * Unicode script "Runic". - */ - RUNIC, - - /** - * Unicode script "Khmer". - */ - KHMER, - - /** - * Unicode script "Mongolian". - */ - MONGOLIAN, - - /** - * Unicode script "Hiragana". - */ - HIRAGANA, - - /** - * Unicode script "Katakana". - */ - KATAKANA, - - /** - * Unicode script "Bopomofo". - */ - BOPOMOFO, - - /** - * Unicode script "Han". - */ - HAN, - - /** - * Unicode script "Yi". - */ - YI, - - /** - * Unicode script "Old_Italic". - */ - OLD_ITALIC, - - /** - * Unicode script "Gothic". - */ - GOTHIC, - - /** - * Unicode script "Deseret". - */ - DESERET, - - /** - * Unicode script "Inherited". - */ - INHERITED, - - /** - * Unicode script "Tagalog". - */ - TAGALOG, - - /** - * Unicode script "Hanunoo". - */ - HANUNOO, - - /** - * Unicode script "Buhid". - */ - BUHID, - - /** - * Unicode script "Tagbanwa". - */ - TAGBANWA, - - /** - * Unicode script "Limbu". - */ - LIMBU, - - /** - * Unicode script "Tai_Le". - */ - TAI_LE, - - /** - * Unicode script "Linear_B". - */ - LINEAR_B, - - /** - * Unicode script "Ugaritic". - */ - UGARITIC, - - /** - * Unicode script "Shavian". - */ - SHAVIAN, - - /** - * Unicode script "Osmanya". - */ - OSMANYA, - - /** - * Unicode script "Cypriot". - */ - CYPRIOT, - - /** - * Unicode script "Braille". - */ - BRAILLE, - - /** - * Unicode script "Buginese". - */ - BUGINESE, - - /** - * Unicode script "Coptic". - */ - COPTIC, - - /** - * Unicode script "New_Tai_Lue". - */ - NEW_TAI_LUE, - - /** - * Unicode script "Glagolitic". - */ - GLAGOLITIC, - - /** - * Unicode script "Tifinagh". - */ - TIFINAGH, - - /** - * Unicode script "Syloti_Nagri". - */ - SYLOTI_NAGRI, - - /** - * Unicode script "Old_Persian". - */ - OLD_PERSIAN, - - /** - * Unicode script "Kharoshthi". - */ - KHAROSHTHI, - - /** - * Unicode script "Balinese". - */ - BALINESE, - - /** - * Unicode script "Cuneiform". - */ - CUNEIFORM, - - /** - * Unicode script "Phoenician". - */ - PHOENICIAN, - - /** - * Unicode script "Phags_Pa". - */ - PHAGS_PA, - - /** - * Unicode script "Nko". - */ - NKO, - - /** - * Unicode script "Sundanese". - */ - SUNDANESE, - - /** - * Unicode script "Batak". - */ - BATAK, - - /** - * Unicode script "Lepcha". - */ - LEPCHA, - - /** - * Unicode script "Ol_Chiki". - */ - OL_CHIKI, - - /** - * Unicode script "Vai". - */ - VAI, - - /** - * Unicode script "Saurashtra". - */ - SAURASHTRA, - - /** - * Unicode script "Kayah_Li". - */ - KAYAH_LI, - - /** - * Unicode script "Rejang". - */ - REJANG, - - /** - * Unicode script "Lycian". - */ - LYCIAN, - - /** - * Unicode script "Carian". - */ - CARIAN, - - /** - * Unicode script "Lydian". - */ - LYDIAN, - - /** - * Unicode script "Cham". - */ - CHAM, - - /** - * Unicode script "Tai_Tham". - */ - TAI_THAM, - - /** - * Unicode script "Tai_Viet". - */ - TAI_VIET, - - /** - * Unicode script "Avestan". - */ - AVESTAN, - - /** - * Unicode script "Egyptian_Hieroglyphs". - */ - EGYPTIAN_HIEROGLYPHS, - - /** - * Unicode script "Samaritan". - */ - SAMARITAN, - - /** - * Unicode script "Mandaic". - */ - MANDAIC, - - /** - * Unicode script "Lisu". - */ - LISU, - - /** - * Unicode script "Bamum". - */ - BAMUM, - - /** - * Unicode script "Javanese". - */ - JAVANESE, - - /** - * Unicode script "Meetei_Mayek". - */ - MEETEI_MAYEK, - - /** - * Unicode script "Imperial_Aramaic". - */ - IMPERIAL_ARAMAIC, - - /** - * Unicode script "Old_South_Arabian". - */ - OLD_SOUTH_ARABIAN, - - /** - * Unicode script "Inscriptional_Parthian". - */ - INSCRIPTIONAL_PARTHIAN, - - /** - * Unicode script "Inscriptional_Pahlavi". - */ - INSCRIPTIONAL_PAHLAVI, - - /** - * Unicode script "Old_Turkic". - */ - OLD_TURKIC, - - /** - * Unicode script "Brahmi". - */ - BRAHMI, - - /** - * Unicode script "Kaithi". - */ - KAITHI, - - /** - * Unicode script "Unknown". - */ - UNKNOWN; - - private static final int[] scriptStarts = { - 0x0000, // 0000..0040; COMMON - 0x0041, // 0041..005A; LATIN - 0x005B, // 005B..0060; COMMON - 0x0061, // 0061..007A; LATIN - 0x007B, // 007B..00A9; COMMON - 0x00AA, // 00AA..00AA; LATIN - 0x00AB, // 00AB..00B9; COMMON - 0x00BA, // 00BA..00BA; LATIN - 0x00BB, // 00BB..00BF; COMMON - 0x00C0, // 00C0..00D6; LATIN - 0x00D7, // 00D7..00D7; COMMON - 0x00D8, // 00D8..00F6; LATIN - 0x00F7, // 00F7..00F7; COMMON - 0x00F8, // 00F8..02B8; LATIN - 0x02B9, // 02B9..02DF; COMMON - 0x02E0, // 02E0..02E4; LATIN - 0x02E5, // 02E5..02E9; COMMON - 0x02EA, // 02EA..02EB; BOPOMOFO - 0x02EC, // 02EC..02FF; COMMON - 0x0300, // 0300..036F; INHERITED - 0x0370, // 0370..0373; GREEK - 0x0374, // 0374..0374; COMMON - 0x0375, // 0375..037D; GREEK - 0x037E, // 037E..0383; COMMON - 0x0384, // 0384..0384; GREEK - 0x0385, // 0385..0385; COMMON - 0x0386, // 0386..0386; GREEK - 0x0387, // 0387..0387; COMMON - 0x0388, // 0388..03E1; GREEK - 0x03E2, // 03E2..03EF; COPTIC - 0x03F0, // 03F0..03FF; GREEK - 0x0400, // 0400..0484; CYRILLIC - 0x0485, // 0485..0486; INHERITED - 0x0487, // 0487..0530; CYRILLIC - 0x0531, // 0531..0588; ARMENIAN - 0x0589, // 0589..0589; COMMON - 0x058A, // 058A..0590; ARMENIAN - 0x0591, // 0591..05FF; HEBREW - 0x0600, // 0600..060B; ARABIC - 0x060C, // 060C..060C; COMMON - 0x060D, // 060D..061A; ARABIC - 0x061B, // 061B..061D; COMMON - 0x061E, // 061E..061E; ARABIC - 0x061F, // 061F..061F; COMMON - 0x0620, // 0620..063F; ARABIC - 0x0640, // 0640..0640; COMMON - 0x0641, // 0641..064A; ARABIC - 0x064B, // 064B..0655; INHERITED - 0x0656, // 0656..065E; ARABIC - 0x065F, // 065F..065F; INHERITED - 0x0660, // 0660..0669; COMMON - 0x066A, // 066A..066F; ARABIC - 0x0670, // 0670..0670; INHERITED - 0x0671, // 0671..06DC; ARABIC - 0x06DD, // 06DD..06DD; COMMON - 0x06DE, // 06DE..06FF; ARABIC - 0x0700, // 0700..074F; SYRIAC - 0x0750, // 0750..077F; ARABIC - 0x0780, // 0780..07BF; THAANA - 0x07C0, // 07C0..07FF; NKO - 0x0800, // 0800..083F; SAMARITAN - 0x0840, // 0840..08FF; MANDAIC - 0x0900, // 0900..0950; DEVANAGARI - 0x0951, // 0951..0952; INHERITED - 0x0953, // 0953..0963; DEVANAGARI - 0x0964, // 0964..0965; COMMON - 0x0966, // 0966..096F; DEVANAGARI - 0x0970, // 0970..0970; COMMON - 0x0971, // 0971..0980; DEVANAGARI - 0x0981, // 0981..0A00; BENGALI - 0x0A01, // 0A01..0A80; GURMUKHI - 0x0A81, // 0A81..0B00; GUJARATI - 0x0B01, // 0B01..0B81; ORIYA - 0x0B82, // 0B82..0C00; TAMIL - 0x0C01, // 0C01..0C81; TELUGU - 0x0C82, // 0C82..0CF0; KANNADA - 0x0D02, // 0D02..0D81; MALAYALAM - 0x0D82, // 0D82..0E00; SINHALA - 0x0E01, // 0E01..0E3E; THAI - 0x0E3F, // 0E3F..0E3F; COMMON - 0x0E40, // 0E40..0E80; THAI - 0x0E81, // 0E81..0EFF; LAO - 0x0F00, // 0F00..0FD4; TIBETAN - 0x0FD5, // 0FD5..0FD8; COMMON - 0x0FD9, // 0FD9..0FFF; TIBETAN - 0x1000, // 1000..109F; MYANMAR - 0x10A0, // 10A0..10FA; GEORGIAN - 0x10FB, // 10FB..10FB; COMMON - 0x10FC, // 10FC..10FF; GEORGIAN - 0x1100, // 1100..11FF; HANGUL - 0x1200, // 1200..139F; ETHIOPIC - 0x13A0, // 13A0..13FF; CHEROKEE - 0x1400, // 1400..167F; CANADIAN_ABORIGINAL - 0x1680, // 1680..169F; OGHAM - 0x16A0, // 16A0..16EA; RUNIC - 0x16EB, // 16EB..16ED; COMMON - 0x16EE, // 16EE..16FF; RUNIC - 0x1700, // 1700..171F; TAGALOG - 0x1720, // 1720..1734; HANUNOO - 0x1735, // 1735..173F; COMMON - 0x1740, // 1740..175F; BUHID - 0x1760, // 1760..177F; TAGBANWA - 0x1780, // 1780..17FF; KHMER - 0x1800, // 1800..1801; MONGOLIAN - 0x1802, // 1802..1803; COMMON - 0x1804, // 1804..1804; MONGOLIAN - 0x1805, // 1805..1805; COMMON - 0x1806, // 1806..18AF; MONGOLIAN - 0x18B0, // 18B0..18FF; CANADIAN_ABORIGINAL - 0x1900, // 1900..194F; LIMBU - 0x1950, // 1950..197F; TAI_LE - 0x1980, // 1980..19DF; NEW_TAI_LUE - 0x19E0, // 19E0..19FF; KHMER - 0x1A00, // 1A00..1A1F; BUGINESE - 0x1A20, // 1A20..1AFF; TAI_THAM - 0x1B00, // 1B00..1B7F; BALINESE - 0x1B80, // 1B80..1BBF; SUNDANESE - 0x1BC0, // 1BC0..1BFF; BATAK - 0x1C00, // 1C00..1C4F; LEPCHA - 0x1C50, // 1C50..1CCF; OL_CHIKI - 0x1CD0, // 1CD0..1CD2; INHERITED - 0x1CD3, // 1CD3..1CD3; COMMON - 0x1CD4, // 1CD4..1CE0; INHERITED - 0x1CE1, // 1CE1..1CE1; COMMON - 0x1CE2, // 1CE2..1CE8; INHERITED - 0x1CE9, // 1CE9..1CEC; COMMON - 0x1CED, // 1CED..1CED; INHERITED - 0x1CEE, // 1CEE..1CFF; COMMON - 0x1D00, // 1D00..1D25; LATIN - 0x1D26, // 1D26..1D2A; GREEK - 0x1D2B, // 1D2B..1D2B; CYRILLIC - 0x1D2C, // 1D2C..1D5C; LATIN - 0x1D5D, // 1D5D..1D61; GREEK - 0x1D62, // 1D62..1D65; LATIN - 0x1D66, // 1D66..1D6A; GREEK - 0x1D6B, // 1D6B..1D77; LATIN - 0x1D78, // 1D78..1D78; CYRILLIC - 0x1D79, // 1D79..1DBE; LATIN - 0x1DBF, // 1DBF..1DBF; GREEK - 0x1DC0, // 1DC0..1DFF; INHERITED - 0x1E00, // 1E00..1EFF; LATIN - 0x1F00, // 1F00..1FFF; GREEK - 0x2000, // 2000..200B; COMMON - 0x200C, // 200C..200D; INHERITED - 0x200E, // 200E..2070; COMMON - 0x2071, // 2071..2073; LATIN - 0x2074, // 2074..207E; COMMON - 0x207F, // 207F..207F; LATIN - 0x2080, // 2080..208F; COMMON - 0x2090, // 2090..209F; LATIN - 0x20A0, // 20A0..20CF; COMMON - 0x20D0, // 20D0..20FF; INHERITED - 0x2100, // 2100..2125; COMMON - 0x2126, // 2126..2126; GREEK - 0x2127, // 2127..2129; COMMON - 0x212A, // 212A..212B; LATIN - 0x212C, // 212C..2131; COMMON - 0x2132, // 2132..2132; LATIN - 0x2133, // 2133..214D; COMMON - 0x214E, // 214E..214E; LATIN - 0x214F, // 214F..215F; COMMON - 0x2160, // 2160..2188; LATIN - 0x2189, // 2189..27FF; COMMON - 0x2800, // 2800..28FF; BRAILLE - 0x2900, // 2900..2BFF; COMMON - 0x2C00, // 2C00..2C5F; GLAGOLITIC - 0x2C60, // 2C60..2C7F; LATIN - 0x2C80, // 2C80..2CFF; COPTIC - 0x2D00, // 2D00..2D2F; GEORGIAN - 0x2D30, // 2D30..2D7F; TIFINAGH - 0x2D80, // 2D80..2DDF; ETHIOPIC - 0x2DE0, // 2DE0..2DFF; CYRILLIC - 0x2E00, // 2E00..2E7F; COMMON - 0x2E80, // 2E80..2FEF; HAN - 0x2FF0, // 2FF0..3004; COMMON - 0x3005, // 3005..3005; HAN - 0x3006, // 3006..3006; COMMON - 0x3007, // 3007..3007; HAN - 0x3008, // 3008..3020; COMMON - 0x3021, // 3021..3029; HAN - 0x302A, // 302A..302D; INHERITED - 0x302E, // 302E..302F; HANGUL - 0x3030, // 3030..3037; COMMON - 0x3038, // 3038..303B; HAN - 0x303C, // 303C..3040; COMMON - 0x3041, // 3041..3098; HIRAGANA - 0x3099, // 3099..309A; INHERITED - 0x309B, // 309B..309C; COMMON - 0x309D, // 309D..309F; HIRAGANA - 0x30A0, // 30A0..30A0; COMMON - 0x30A1, // 30A1..30FA; KATAKANA - 0x30FB, // 30FB..30FC; COMMON - 0x30FD, // 30FD..3104; KATAKANA - 0x3105, // 3105..3130; BOPOMOFO - 0x3131, // 3131..318F; HANGUL - 0x3190, // 3190..319F; COMMON - 0x31A0, // 31A0..31BF; BOPOMOFO - 0x31C0, // 31C0..31EF; COMMON - 0x31F0, // 31F0..31FF; KATAKANA - 0x3200, // 3200..321F; HANGUL - 0x3220, // 3220..325F; COMMON - 0x3260, // 3260..327E; HANGUL - 0x327F, // 327F..32CF; COMMON - 0x32D0, // 32D0..3357; KATAKANA - 0x3358, // 3358..33FF; COMMON - 0x3400, // 3400..4DBF; HAN - 0x4DC0, // 4DC0..4DFF; COMMON - 0x4E00, // 4E00..9FFF; HAN - 0xA000, // A000..A4CF; YI - 0xA4D0, // A4D0..A4FF; LISU - 0xA500, // A500..A63F; VAI - 0xA640, // A640..A69F; CYRILLIC - 0xA6A0, // A6A0..A6FF; BAMUM - 0xA700, // A700..A721; COMMON - 0xA722, // A722..A787; LATIN - 0xA788, // A788..A78A; COMMON - 0xA78B, // A78B..A7FF; LATIN - 0xA800, // A800..A82F; SYLOTI_NAGRI - 0xA830, // A830..A83F; COMMON - 0xA840, // A840..A87F; PHAGS_PA - 0xA880, // A880..A8DF; SAURASHTRA - 0xA8E0, // A8E0..A8FF; DEVANAGARI - 0xA900, // A900..A92F; KAYAH_LI - 0xA930, // A930..A95F; REJANG - 0xA960, // A960..A97F; HANGUL - 0xA980, // A980..A9FF; JAVANESE - 0xAA00, // AA00..AA5F; CHAM - 0xAA60, // AA60..AA7F; MYANMAR - 0xAA80, // AA80..AB00; TAI_VIET - 0xAB01, // AB01..ABBF; ETHIOPIC - 0xABC0, // ABC0..ABFF; MEETEI_MAYEK - 0xAC00, // AC00..D7FB; HANGUL - 0xD7FC, // D7FC..F8FF; UNKNOWN - 0xF900, // F900..FAFF; HAN - 0xFB00, // FB00..FB12; LATIN - 0xFB13, // FB13..FB1C; ARMENIAN - 0xFB1D, // FB1D..FB4F; HEBREW - 0xFB50, // FB50..FD3D; ARABIC - 0xFD3E, // FD3E..FD4F; COMMON - 0xFD50, // FD50..FDFC; ARABIC - 0xFDFD, // FDFD..FDFF; COMMON - 0xFE00, // FE00..FE0F; INHERITED - 0xFE10, // FE10..FE1F; COMMON - 0xFE20, // FE20..FE2F; INHERITED - 0xFE30, // FE30..FE6F; COMMON - 0xFE70, // FE70..FEFE; ARABIC - 0xFEFF, // FEFF..FF20; COMMON - 0xFF21, // FF21..FF3A; LATIN - 0xFF3B, // FF3B..FF40; COMMON - 0xFF41, // FF41..FF5A; LATIN - 0xFF5B, // FF5B..FF65; COMMON - 0xFF66, // FF66..FF6F; KATAKANA - 0xFF70, // FF70..FF70; COMMON - 0xFF71, // FF71..FF9D; KATAKANA - 0xFF9E, // FF9E..FF9F; COMMON - 0xFFA0, // FFA0..FFDF; HANGUL - 0xFFE0, // FFE0..FFFF; COMMON - 0x10000, // 10000..100FF; LINEAR_B - 0x10100, // 10100..1013F; COMMON - 0x10140, // 10140..1018F; GREEK - 0x10190, // 10190..101FC; COMMON - 0x101FD, // 101FD..1027F; INHERITED - 0x10280, // 10280..1029F; LYCIAN - 0x102A0, // 102A0..102FF; CARIAN - 0x10300, // 10300..1032F; OLD_ITALIC - 0x10330, // 10330..1037F; GOTHIC - 0x10380, // 10380..1039F; UGARITIC - 0x103A0, // 103A0..103FF; OLD_PERSIAN - 0x10400, // 10400..1044F; DESERET - 0x10450, // 10450..1047F; SHAVIAN - 0x10480, // 10480..107FF; OSMANYA - 0x10800, // 10800..1083F; CYPRIOT - 0x10840, // 10840..108FF; IMPERIAL_ARAMAIC - 0x10900, // 10900..1091F; PHOENICIAN - 0x10920, // 10920..109FF; LYDIAN - 0x10A00, // 10A00..10A5F; KHAROSHTHI - 0x10A60, // 10A60..10AFF; OLD_SOUTH_ARABIAN - 0x10B00, // 10B00..10B3F; AVESTAN - 0x10B40, // 10B40..10B5F; INSCRIPTIONAL_PARTHIAN - 0x10B60, // 10B60..10BFF; INSCRIPTIONAL_PAHLAVI - 0x10C00, // 10C00..10E5F; OLD_TURKIC - 0x10E60, // 10E60..10FFF; ARABIC - 0x11000, // 11000..1107F; BRAHMI - 0x11080, // 11080..11FFF; KAITHI - 0x12000, // 12000..12FFF; CUNEIFORM - 0x13000, // 13000..167FF; EGYPTIAN_HIEROGLYPHS - 0x16800, // 16800..16A38; BAMUM - 0x1B000, // 1B000..1B000; KATAKANA - 0x1B001, // 1B001..1CFFF; HIRAGANA - 0x1D000, // 1D000..1D166; COMMON - 0x1D167, // 1D167..1D169; INHERITED - 0x1D16A, // 1D16A..1D17A; COMMON - 0x1D17B, // 1D17B..1D182; INHERITED - 0x1D183, // 1D183..1D184; COMMON - 0x1D185, // 1D185..1D18B; INHERITED - 0x1D18C, // 1D18C..1D1A9; COMMON - 0x1D1AA, // 1D1AA..1D1AD; INHERITED - 0x1D1AE, // 1D1AE..1D1FF; COMMON - 0x1D200, // 1D200..1D2FF; GREEK - 0x1D300, // 1D300..1F1FF; COMMON - 0x1F200, // 1F200..1F200; HIRAGANA - 0x1F201, // 1F210..1FFFF; COMMON - 0x20000, // 20000..E0000; HAN - 0xE0001, // E0001..E00FF; COMMON - 0xE0100, // E0100..E01EF; INHERITED - 0xE01F0 // E01F0..10FFFF; UNKNOWN - - }; - - private static final UnicodeScript[] scripts = { - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - BOPOMOFO, - COMMON, - INHERITED, - GREEK, - COMMON, - GREEK, - COMMON, - GREEK, - COMMON, - GREEK, - COMMON, - GREEK, - COPTIC, - GREEK, - CYRILLIC, - INHERITED, - CYRILLIC, - ARMENIAN, - COMMON, - ARMENIAN, - HEBREW, - ARABIC, - COMMON, - ARABIC, - COMMON, - ARABIC, - COMMON, - ARABIC, - COMMON, - ARABIC, - INHERITED, - ARABIC, - INHERITED, - COMMON, - ARABIC, - INHERITED, - ARABIC, - COMMON, - ARABIC, - SYRIAC, - ARABIC, - THAANA, - NKO, - SAMARITAN, - MANDAIC, - DEVANAGARI, - INHERITED, - DEVANAGARI, - COMMON, - DEVANAGARI, - COMMON, - DEVANAGARI, - BENGALI, - GURMUKHI, - GUJARATI, - ORIYA, - TAMIL, - TELUGU, - KANNADA, - MALAYALAM, - SINHALA, - THAI, - COMMON, - THAI, - LAO, - TIBETAN, - COMMON, - TIBETAN, - MYANMAR, - GEORGIAN, - COMMON, - GEORGIAN, - HANGUL, - ETHIOPIC, - CHEROKEE, - CANADIAN_ABORIGINAL, - OGHAM, - RUNIC, - COMMON, - RUNIC, - TAGALOG, - HANUNOO, - COMMON, - BUHID, - TAGBANWA, - KHMER, - MONGOLIAN, - COMMON, - MONGOLIAN, - COMMON, - MONGOLIAN, - CANADIAN_ABORIGINAL, - LIMBU, - TAI_LE, - NEW_TAI_LUE, - KHMER, - BUGINESE, - TAI_THAM, - BALINESE, - SUNDANESE, - BATAK, - LEPCHA, - OL_CHIKI, - INHERITED, - COMMON, - INHERITED, - COMMON, - INHERITED, - COMMON, - INHERITED, - COMMON, - LATIN, - GREEK, - CYRILLIC, - LATIN, - GREEK, - LATIN, - GREEK, - LATIN, - CYRILLIC, - LATIN, - GREEK, - INHERITED, - LATIN, - GREEK, - COMMON, - INHERITED, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - INHERITED, - COMMON, - GREEK, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - BRAILLE, - COMMON, - GLAGOLITIC, - LATIN, - COPTIC, - GEORGIAN, - TIFINAGH, - ETHIOPIC, - CYRILLIC, - COMMON, - HAN, - COMMON, - HAN, - COMMON, - HAN, - COMMON, - HAN, - INHERITED, - HANGUL, - COMMON, - HAN, - COMMON, - HIRAGANA, - INHERITED, - COMMON, - HIRAGANA, - COMMON, - KATAKANA, - COMMON, - KATAKANA, - BOPOMOFO, - HANGUL, - COMMON, - BOPOMOFO, - COMMON, - KATAKANA, - HANGUL, - COMMON, - HANGUL, - COMMON, - KATAKANA, - COMMON, - HAN, - COMMON, - HAN, - YI, - LISU, - VAI, - CYRILLIC, - BAMUM, - COMMON, - LATIN, - COMMON, - LATIN, - SYLOTI_NAGRI, - COMMON, - PHAGS_PA, - SAURASHTRA, - DEVANAGARI, - KAYAH_LI, - REJANG, - HANGUL, - JAVANESE, - CHAM, - MYANMAR, - TAI_VIET, - ETHIOPIC, - MEETEI_MAYEK, - HANGUL, - UNKNOWN, - HAN, - LATIN, - ARMENIAN, - HEBREW, - ARABIC, - COMMON, - ARABIC, - COMMON, - INHERITED, - COMMON, - INHERITED, - COMMON, - ARABIC, - COMMON, - LATIN, - COMMON, - LATIN, - COMMON, - KATAKANA, - COMMON, - KATAKANA, - COMMON, - HANGUL, - COMMON, - LINEAR_B, - COMMON, - GREEK, - COMMON, - INHERITED, - LYCIAN, - CARIAN, - OLD_ITALIC, - GOTHIC, - UGARITIC, - OLD_PERSIAN, - DESERET, - SHAVIAN, - OSMANYA, - CYPRIOT, - IMPERIAL_ARAMAIC, - PHOENICIAN, - LYDIAN, - KHAROSHTHI, - OLD_SOUTH_ARABIAN, - AVESTAN, - INSCRIPTIONAL_PARTHIAN, - INSCRIPTIONAL_PAHLAVI, - OLD_TURKIC, - ARABIC, - BRAHMI, - KAITHI, - CUNEIFORM, - EGYPTIAN_HIEROGLYPHS, - BAMUM, - KATAKANA, - HIRAGANA, - COMMON, - INHERITED, - COMMON, - INHERITED, - COMMON, - INHERITED, - COMMON, - INHERITED, - COMMON, - GREEK, - COMMON, - HIRAGANA, - COMMON, - HAN, - COMMON, - INHERITED, - UNKNOWN - }; - - private static HashMap aliases; - static { - aliases = new HashMap<>(128); - aliases.put("ARAB", ARABIC); - aliases.put("ARMI", IMPERIAL_ARAMAIC); - aliases.put("ARMN", ARMENIAN); - aliases.put("AVST", AVESTAN); - aliases.put("BALI", BALINESE); - aliases.put("BAMU", BAMUM); - aliases.put("BATK", BATAK); - aliases.put("BENG", BENGALI); - aliases.put("BOPO", BOPOMOFO); - aliases.put("BRAI", BRAILLE); - aliases.put("BRAH", BRAHMI); - aliases.put("BUGI", BUGINESE); - aliases.put("BUHD", BUHID); - aliases.put("CANS", CANADIAN_ABORIGINAL); - aliases.put("CARI", CARIAN); - aliases.put("CHAM", CHAM); - aliases.put("CHER", CHEROKEE); - aliases.put("COPT", COPTIC); - aliases.put("CPRT", CYPRIOT); - aliases.put("CYRL", CYRILLIC); - aliases.put("DEVA", DEVANAGARI); - aliases.put("DSRT", DESERET); - aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS); - aliases.put("ETHI", ETHIOPIC); - aliases.put("GEOR", GEORGIAN); - aliases.put("GLAG", GLAGOLITIC); - aliases.put("GOTH", GOTHIC); - aliases.put("GREK", GREEK); - aliases.put("GUJR", GUJARATI); - aliases.put("GURU", GURMUKHI); - aliases.put("HANG", HANGUL); - aliases.put("HANI", HAN); - aliases.put("HANO", HANUNOO); - aliases.put("HEBR", HEBREW); - aliases.put("HIRA", HIRAGANA); - // it appears we don't have the KATAKANA_OR_HIRAGANA - //aliases.put("HRKT", KATAKANA_OR_HIRAGANA); - aliases.put("ITAL", OLD_ITALIC); - aliases.put("JAVA", JAVANESE); - aliases.put("KALI", KAYAH_LI); - aliases.put("KANA", KATAKANA); - aliases.put("KHAR", KHAROSHTHI); - aliases.put("KHMR", KHMER); - aliases.put("KNDA", KANNADA); - aliases.put("KTHI", KAITHI); - aliases.put("LANA", TAI_THAM); - aliases.put("LAOO", LAO); - aliases.put("LATN", LATIN); - aliases.put("LEPC", LEPCHA); - aliases.put("LIMB", LIMBU); - aliases.put("LINB", LINEAR_B); - aliases.put("LISU", LISU); - aliases.put("LYCI", LYCIAN); - aliases.put("LYDI", LYDIAN); - aliases.put("MAND", MANDAIC); - aliases.put("MLYM", MALAYALAM); - aliases.put("MONG", MONGOLIAN); - aliases.put("MTEI", MEETEI_MAYEK); - aliases.put("MYMR", MYANMAR); - aliases.put("NKOO", NKO); - aliases.put("OGAM", OGHAM); - aliases.put("OLCK", OL_CHIKI); - aliases.put("ORKH", OLD_TURKIC); - aliases.put("ORYA", ORIYA); - aliases.put("OSMA", OSMANYA); - aliases.put("PHAG", PHAGS_PA); - aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI); - aliases.put("PHNX", PHOENICIAN); - aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN); - aliases.put("RJNG", REJANG); - aliases.put("RUNR", RUNIC); - aliases.put("SAMR", SAMARITAN); - aliases.put("SARB", OLD_SOUTH_ARABIAN); - aliases.put("SAUR", SAURASHTRA); - aliases.put("SHAW", SHAVIAN); - aliases.put("SINH", SINHALA); - aliases.put("SUND", SUNDANESE); - aliases.put("SYLO", SYLOTI_NAGRI); - aliases.put("SYRC", SYRIAC); - aliases.put("TAGB", TAGBANWA); - aliases.put("TALE", TAI_LE); - aliases.put("TALU", NEW_TAI_LUE); - aliases.put("TAML", TAMIL); - aliases.put("TAVT", TAI_VIET); - aliases.put("TELU", TELUGU); - aliases.put("TFNG", TIFINAGH); - aliases.put("TGLG", TAGALOG); - aliases.put("THAA", THAANA); - aliases.put("THAI", THAI); - aliases.put("TIBT", TIBETAN); - aliases.put("UGAR", UGARITIC); - aliases.put("VAII", VAI); - aliases.put("XPEO", OLD_PERSIAN); - aliases.put("XSUX", CUNEIFORM); - aliases.put("YIII", YI); - aliases.put("ZINH", INHERITED); - aliases.put("ZYYY", COMMON); - aliases.put("ZZZZ", UNKNOWN); - } - - /** - * Returns the enum constant representing the Unicode script of which - * the given character (Unicode code point) is assigned to. - * - * @param codePoint the character (Unicode code point) in question. - * @return The {@code UnicodeScript} constant representing the - * Unicode script of which this character is assigned to. - * - * @exception IllegalArgumentException if the specified - * {@code codePoint} is an invalid Unicode code point. - * @see Character#isValidCodePoint(int) - * - */ - public static UnicodeScript of(int codePoint) { - if (!isValidCodePoint(codePoint)) - throw new IllegalArgumentException(); - int type = getType(codePoint); - // leave SURROGATE and PRIVATE_USE for table lookup - if (type == UNASSIGNED) - return UNKNOWN; - int index = Arrays.binarySearch(scriptStarts, codePoint); - if (index < 0) - index = -index - 2; - return scripts[index]; - } - - /** - * Returns the UnicodeScript constant with the given Unicode script - * name or the script name alias. Script names and their aliases are - * determined by The Unicode Standard. The files Scripts<version>.txt - * and PropertyValueAliases<version>.txt define script names - * and the script name aliases for a particular version of the - * standard. The {@link Character} class specifies the version of - * the standard that it supports. - *

- * Character case is ignored for all of the valid script names. - * The en_US locale's case mapping rules are used to provide - * case-insensitive string comparisons for script name validation. - *

- * - * @param scriptName A {@code UnicodeScript} name. - * @return The {@code UnicodeScript} constant identified - * by {@code scriptName} - * @throws IllegalArgumentException if {@code scriptName} is an - * invalid name - * @throws NullPointerException if {@code scriptName} is null - */ - public static final UnicodeScript forName(String scriptName) { - scriptName = scriptName.toUpperCase(Locale.ENGLISH); - //.replace(' ', '_')); - UnicodeScript sc = aliases.get(scriptName); - if (sc != null) - return sc; - return valueOf(scriptName); - } - } /** * The value of the {@code Character}. @@ -5227,40 +1525,7 @@ * @see Character#getType(char) */ public static boolean isLowerCase(char ch) { - return isLowerCase((int)ch); - } - - /** - * Determines if the specified character (Unicode code point) is a - * lowercase character. - *

- * A character is lowercase if its general category type, provided - * by {@link Character#getType getType(codePoint)}, is - * {@code LOWERCASE_LETTER}, or it has contributory property - * Other_Lowercase as defined by the Unicode Standard. - *

- * The following are examples of lowercase characters: - * 

-     * a b c d e f g h i j k l m n o p q r s t u v w x y z
-     * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
-     * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
-     * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
-     * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
-     *
- *

Many other Unicode characters are lowercase too. - * - * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character is lowercase; - * {@code false} otherwise. - * @see Character#isLowerCase(int) - * @see Character#isTitleCase(int) - * @see Character#toLowerCase(int) - * @see Character#getType(int) - * @since 1.5 - */ - public static boolean isLowerCase(int codePoint) { - return getType(codePoint) == Character.LOWERCASE_LETTER || - CharacterData.of(codePoint).isOtherLowercase(codePoint); + throw new UnsupportedOperationException(); } /** @@ -5295,38 +1560,7 @@ * @since 1.0 */ public static boolean isUpperCase(char ch) { - return isUpperCase((int)ch); - } - - /** - * Determines if the specified character (Unicode code point) is an uppercase character. - *

- * A character is uppercase if its general category type, provided by - * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER}, - * or it has contributory property Other_Uppercase as defined by the Unicode Standard. - *

- * The following are examples of uppercase characters: - * 

-     * A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
-     * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
-     * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
-     * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
-     * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
-     *
- *

Many other Unicode characters are uppercase too.

- * - * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character is uppercase; - * {@code false} otherwise. - * @see Character#isLowerCase(int) - * @see Character#isTitleCase(int) - * @see Character#toUpperCase(int) - * @see Character#getType(int) - * @since 1.5 - */ - public static boolean isUpperCase(int codePoint) { - return getType(codePoint) == Character.UPPERCASE_LETTER || - CharacterData.of(codePoint).isOtherUppercase(codePoint); + throw new UnsupportedOperationException(); } /** @@ -5663,431 +1897,11 @@ (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1) != 0; } - - /** - * Determines if the specified character is permissible as the first - * character in a Java identifier. - *

- * A character may start a Java identifier if and only if - * one of the following is true: - *

    - *
  • {@link #isLetter(char) isLetter(ch)} returns {@code true} - *
  • {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER} - *
  • {@code ch} is a currency symbol (such as {@code '$'}) - *
  • {@code ch} is a connecting punctuation character (such as {@code '_'}). - *
- * - * @param ch the character to be tested. - * @return {@code true} if the character may start a Java - * identifier; {@code false} otherwise. - * @see Character#isJavaLetterOrDigit(char) - * @see Character#isJavaIdentifierStart(char) - * @see Character#isJavaIdentifierPart(char) - * @see Character#isLetter(char) - * @see Character#isLetterOrDigit(char) - * @see Character#isUnicodeIdentifierStart(char) - * @since 1.02 - * @deprecated Replaced by isJavaIdentifierStart(char). - */ - @Deprecated - public static boolean isJavaLetter(char ch) { - return isJavaIdentifierStart(ch); + + static int getType(int x) { + throw new UnsupportedOperationException(); } - - /** - * Determines if the specified character may be part of a Java - * identifier as other than the first character. - *

- * A character may be part of a Java identifier if and only if any - * of the following are true: - *

    - *
  • it is a letter - *
  • it is a currency symbol (such as {@code '$'}) - *
  • it is a connecting punctuation character (such as {@code '_'}) - *
  • it is a digit - *
  • it is a numeric letter (such as a Roman numeral character) - *
  • it is a combining mark - *
  • it is a non-spacing mark - *
  • {@code isIdentifierIgnorable} returns - * {@code true} for the character. - *
- * - * @param ch the character to be tested. - * @return {@code true} if the character may be part of a - * Java identifier; {@code false} otherwise. - * @see Character#isJavaLetter(char) - * @see Character#isJavaIdentifierStart(char) - * @see Character#isJavaIdentifierPart(char) - * @see Character#isLetter(char) - * @see Character#isLetterOrDigit(char) - * @see Character#isUnicodeIdentifierPart(char) - * @see Character#isIdentifierIgnorable(char) - * @since 1.02 - * @deprecated Replaced by isJavaIdentifierPart(char). - */ - @Deprecated - public static boolean isJavaLetterOrDigit(char ch) { - return isJavaIdentifierPart(ch); - } - - /** - * Determines if the specified character (Unicode code point) is an alphabet. - *

- * A character is considered to be alphabetic if its general category type, - * provided by {@link Character#getType(int) getType(codePoint)}, is any of - * the following: - *

    - *
  • UPPERCASE_LETTER - *
  • LOWERCASE_LETTER - *
  • TITLECASE_LETTER - *
  • MODIFIER_LETTER - *
  • OTHER_LETTER - *
  • LETTER_NUMBER - *
- * or it has contributory property Other_Alphabetic as defined by the - * Unicode Standard. - * - * @param codePoint the character (Unicode code point) to be tested. - * @return true if the character is a Unicode alphabet - * character, false otherwise. - * @since 1.7 - */ - public static boolean isAlphabetic(int codePoint) { - return (((((1 << Character.UPPERCASE_LETTER) | - (1 << Character.LOWERCASE_LETTER) | - (1 << Character.TITLECASE_LETTER) | - (1 << Character.MODIFIER_LETTER) | - (1 << Character.OTHER_LETTER) | - (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) || - CharacterData.of(codePoint).isOtherAlphabetic(codePoint); - } - - /** - * Determines if the specified character (Unicode code point) is a CJKV - * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by - * the Unicode Standard. - * - * @param codePoint the character (Unicode code point) to be tested. - * @return true if the character is a Unicode ideograph - * character, false otherwise. - * @since 1.7 - */ - public static boolean isIdeographic(int codePoint) { - return CharacterData.of(codePoint).isIdeographic(codePoint); - } - - /** - * Determines if the specified character is - * permissible as the first character in a Java identifier. - *

- * A character may start a Java identifier if and only if - * one of the following conditions is true: - *

    - *
  • {@link #isLetter(char) isLetter(ch)} returns {@code true} - *
  • {@link #getType(char) getType(ch)} returns {@code LETTER_NUMBER} - *
  • {@code ch} is a currency symbol (such as {@code '$'}) - *
  • {@code ch} is a connecting punctuation character (such as {@code '_'}). - *
- * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #isJavaIdentifierStart(int)} method. - * - * @param ch the character to be tested. - * @return {@code true} if the character may start a Java identifier; - * {@code false} otherwise. - * @see Character#isJavaIdentifierPart(char) - * @see Character#isLetter(char) - * @see Character#isUnicodeIdentifierStart(char) - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) - * @since 1.1 - */ - public static boolean isJavaIdentifierStart(char ch) { - return isJavaIdentifierStart((int)ch); - } - - /** - * Determines if the character (Unicode code point) is - * permissible as the first character in a Java identifier. - *

- * A character may start a Java identifier if and only if - * one of the following conditions is true: - *

    - *
  • {@link #isLetter(int) isLetter(codePoint)} - * returns {@code true} - *
  • {@link #getType(int) getType(codePoint)} - * returns {@code LETTER_NUMBER} - *
  • the referenced character is a currency symbol (such as {@code '$'}) - *
  • the referenced character is a connecting punctuation character - * (such as {@code '_'}). - *
- * - * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character may start a Java identifier; - * {@code false} otherwise. - * @see Character#isJavaIdentifierPart(int) - * @see Character#isLetter(int) - * @see Character#isUnicodeIdentifierStart(int) - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) - * @since 1.5 - */ - public static boolean isJavaIdentifierStart(int codePoint) { - return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint); - } - - /** - * Determines if the specified character may be part of a Java - * identifier as other than the first character. - *

- * A character may be part of a Java identifier if any of the following - * are true: - *

    - *
  • it is a letter - *
  • it is a currency symbol (such as {@code '$'}) - *
  • it is a connecting punctuation character (such as {@code '_'}) - *
  • it is a digit - *
  • it is a numeric letter (such as a Roman numeral character) - *
  • it is a combining mark - *
  • it is a non-spacing mark - *
  • {@code isIdentifierIgnorable} returns - * {@code true} for the character - *
- * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #isJavaIdentifierPart(int)} method. - * - * @param ch the character to be tested. - * @return {@code true} if the character may be part of a - * Java identifier; {@code false} otherwise. - * @see Character#isIdentifierIgnorable(char) - * @see Character#isJavaIdentifierStart(char) - * @see Character#isLetterOrDigit(char) - * @see Character#isUnicodeIdentifierPart(char) - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) - * @since 1.1 - */ - public static boolean isJavaIdentifierPart(char ch) { - return isJavaIdentifierPart((int)ch); - } - - /** - * Determines if the character (Unicode code point) may be part of a Java - * identifier as other than the first character. - *

- * A character may be part of a Java identifier if any of the following - * are true: - *

    - *
  • it is a letter - *
  • it is a currency symbol (such as {@code '$'}) - *
  • it is a connecting punctuation character (such as {@code '_'}) - *
  • it is a digit - *
  • it is a numeric letter (such as a Roman numeral character) - *
  • it is a combining mark - *
  • it is a non-spacing mark - *
  • {@link #isIdentifierIgnorable(int) - * isIdentifierIgnorable(codePoint)} returns {@code true} for - * the character - *
- * - * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character may be part of a - * Java identifier; {@code false} otherwise. - * @see Character#isIdentifierIgnorable(int) - * @see Character#isJavaIdentifierStart(int) - * @see Character#isLetterOrDigit(int) - * @see Character#isUnicodeIdentifierPart(int) - * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) - * @since 1.5 - */ - public static boolean isJavaIdentifierPart(int codePoint) { - return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint); - } - - /** - * Determines if the specified character is permissible as the - * first character in a Unicode identifier. - *

- * A character may start a Unicode identifier if and only if - * one of the following conditions is true: - *

    - *
  • {@link #isLetter(char) isLetter(ch)} returns {@code true} - *
  • {@link #getType(char) getType(ch)} returns - * {@code LETTER_NUMBER}. - *
- * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #isUnicodeIdentifierStart(int)} method. - * - * @param ch the character to be tested. - * @return {@code true} if the character may start a Unicode - * identifier; {@code false} otherwise. - * @see Character#isJavaIdentifierStart(char) - * @see Character#isLetter(char) - * @see Character#isUnicodeIdentifierPart(char) - * @since 1.1 - */ - public static boolean isUnicodeIdentifierStart(char ch) { - return isUnicodeIdentifierStart((int)ch); - } - - /** - * Determines if the specified character (Unicode code point) is permissible as the - * first character in a Unicode identifier. - *

- * A character may start a Unicode identifier if and only if - * one of the following conditions is true: - *

    - *
  • {@link #isLetter(int) isLetter(codePoint)} - * returns {@code true} - *
  • {@link #getType(int) getType(codePoint)} - * returns {@code LETTER_NUMBER}. - *
- * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character may start a Unicode - * identifier; {@code false} otherwise. - * @see Character#isJavaIdentifierStart(int) - * @see Character#isLetter(int) - * @see Character#isUnicodeIdentifierPart(int) - * @since 1.5 - */ - public static boolean isUnicodeIdentifierStart(int codePoint) { - return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint); - } - - /** - * Determines if the specified character may be part of a Unicode - * identifier as other than the first character. - *

- * A character may be part of a Unicode identifier if and only if - * one of the following statements is true: - *

    - *
  • it is a letter - *
  • it is a connecting punctuation character (such as {@code '_'}) - *
  • it is a digit - *
  • it is a numeric letter (such as a Roman numeral character) - *
  • it is a combining mark - *
  • it is a non-spacing mark - *
  • {@code isIdentifierIgnorable} returns - * {@code true} for this character. - *
- * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #isUnicodeIdentifierPart(int)} method. - * - * @param ch the character to be tested. - * @return {@code true} if the character may be part of a - * Unicode identifier; {@code false} otherwise. - * @see Character#isIdentifierIgnorable(char) - * @see Character#isJavaIdentifierPart(char) - * @see Character#isLetterOrDigit(char) - * @see Character#isUnicodeIdentifierStart(char) - * @since 1.1 - */ - public static boolean isUnicodeIdentifierPart(char ch) { - return isUnicodeIdentifierPart((int)ch); - } - - /** - * Determines if the specified character (Unicode code point) may be part of a Unicode - * identifier as other than the first character. - *

- * A character may be part of a Unicode identifier if and only if - * one of the following statements is true: - *

    - *
  • it is a letter - *
  • it is a connecting punctuation character (such as {@code '_'}) - *
  • it is a digit - *
  • it is a numeric letter (such as a Roman numeral character) - *
  • it is a combining mark - *
  • it is a non-spacing mark - *
  • {@code isIdentifierIgnorable} returns - * {@code true} for this character. - *
- * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character may be part of a - * Unicode identifier; {@code false} otherwise. - * @see Character#isIdentifierIgnorable(int) - * @see Character#isJavaIdentifierPart(int) - * @see Character#isLetterOrDigit(int) - * @see Character#isUnicodeIdentifierStart(int) - * @since 1.5 - */ - public static boolean isUnicodeIdentifierPart(int codePoint) { - return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint); - } - - /** - * Determines if the specified character should be regarded as - * an ignorable character in a Java identifier or a Unicode identifier. - *

- * The following Unicode characters are ignorable in a Java identifier - * or a Unicode identifier: - *

    - *
  • ISO control characters that are not whitespace - *
      - *
    • {@code '\u005Cu0000'} through {@code '\u005Cu0008'} - *
    • {@code '\u005Cu000E'} through {@code '\u005Cu001B'} - *
    • {@code '\u005Cu007F'} through {@code '\u005Cu009F'} - *
    - * - *
  • all characters that have the {@code FORMAT} general - * category value - *
- * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #isIdentifierIgnorable(int)} method. - * - * @param ch the character to be tested. - * @return {@code true} if the character is an ignorable control - * character that may be part of a Java or Unicode identifier; - * {@code false} otherwise. - * @see Character#isJavaIdentifierPart(char) - * @see Character#isUnicodeIdentifierPart(char) - * @since 1.1 - */ - public static boolean isIdentifierIgnorable(char ch) { - return isIdentifierIgnorable((int)ch); - } - - /** - * Determines if the specified character (Unicode code point) should be regarded as - * an ignorable character in a Java identifier or a Unicode identifier. - *

- * The following Unicode characters are ignorable in a Java identifier - * or a Unicode identifier: - *

    - *
  • ISO control characters that are not whitespace - *
      - *
    • {@code '\u005Cu0000'} through {@code '\u005Cu0008'} - *
    • {@code '\u005Cu000E'} through {@code '\u005Cu001B'} - *
    • {@code '\u005Cu007F'} through {@code '\u005Cu009F'} - *
    - * - *
  • all characters that have the {@code FORMAT} general - * category value - *
- * - * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character is an ignorable control - * character that may be part of a Java or Unicode identifier; - * {@code false} otherwise. - * @see Character#isJavaIdentifierPart(int) - * @see Character#isUnicodeIdentifierPart(int) - * @since 1.5 - */ - public static boolean isIdentifierIgnorable(int codePoint) { - return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint); - } - + /** * Converts the character argument to lowercase using case * mapping information from the UnicodeData file. @@ -6116,36 +1930,7 @@ * @see String#toLowerCase() */ public static char toLowerCase(char ch) { - return (char)toLowerCase((int)ch); - } - - /** - * Converts the character (Unicode code point) argument to - * lowercase using case mapping information from the UnicodeData - * file. - * - *

Note that - * {@code Character.isLowerCase(Character.toLowerCase(codePoint))} - * does not always return {@code true} for some ranges of - * characters, particularly those that are symbols or ideographs. - * - *

In general, {@link String#toLowerCase()} should be used to map - * characters to lowercase. {@code String} case mapping methods - * have several benefits over {@code Character} case mapping methods. - * {@code String} case mapping methods can perform locale-sensitive - * mappings, context-sensitive mappings, and 1:M character mappings, whereas - * the {@code Character} case mapping methods cannot. - * - * @param codePoint the character (Unicode code point) to be converted. - * @return the lowercase equivalent of the character (Unicode code - * point), if any; otherwise, the character itself. - * @see Character#isLowerCase(int) - * @see String#toLowerCase() - * - * @since 1.5 - */ - public static int toLowerCase(int codePoint) { - return CharacterData.of(codePoint).toLowerCase(codePoint); + throw new UnsupportedOperationException(); } /** @@ -6176,95 +1961,7 @@ * @see String#toUpperCase() */ public static char toUpperCase(char ch) { - return (char)toUpperCase((int)ch); - } - - /** - * Converts the character (Unicode code point) argument to - * uppercase using case mapping information from the UnicodeData - * file. - * - *

Note that - * {@code Character.isUpperCase(Character.toUpperCase(codePoint))} - * does not always return {@code true} for some ranges of - * characters, particularly those that are symbols or ideographs. - * - *

In general, {@link String#toUpperCase()} should be used to map - * characters to uppercase. {@code String} case mapping methods - * have several benefits over {@code Character} case mapping methods. - * {@code String} case mapping methods can perform locale-sensitive - * mappings, context-sensitive mappings, and 1:M character mappings, whereas - * the {@code Character} case mapping methods cannot. - * - * @param codePoint the character (Unicode code point) to be converted. - * @return the uppercase equivalent of the character, if any; - * otherwise, the character itself. - * @see Character#isUpperCase(int) - * @see String#toUpperCase() - * - * @since 1.5 - */ - public static int toUpperCase(int codePoint) { - return CharacterData.of(codePoint).toUpperCase(codePoint); - } - - /** - * Converts the character argument to titlecase using case mapping - * information from the UnicodeData file. If a character has no - * explicit titlecase mapping and is not itself a titlecase char - * according to UnicodeData, then the uppercase mapping is - * returned as an equivalent titlecase mapping. If the - * {@code char} argument is already a titlecase - * {@code char}, the same {@code char} value will be - * returned. - *

- * Note that - * {@code Character.isTitleCase(Character.toTitleCase(ch))} - * does not always return {@code true} for some ranges of - * characters. - * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #toTitleCase(int)} method. - * - * @param ch the character to be converted. - * @return the titlecase equivalent of the character, if any; - * otherwise, the character itself. - * @see Character#isTitleCase(char) - * @see Character#toLowerCase(char) - * @see Character#toUpperCase(char) - * @since 1.0.2 - */ - public static char toTitleCase(char ch) { - return (char)toTitleCase((int)ch); - } - - /** - * Converts the character (Unicode code point) argument to titlecase using case mapping - * information from the UnicodeData file. If a character has no - * explicit titlecase mapping and is not itself a titlecase char - * according to UnicodeData, then the uppercase mapping is - * returned as an equivalent titlecase mapping. If the - * character argument is already a titlecase - * character, the same character value will be - * returned. - * - *

Note that - * {@code Character.isTitleCase(Character.toTitleCase(codePoint))} - * does not always return {@code true} for some ranges of - * characters. - * - * @param codePoint the character (Unicode code point) to be converted. - * @return the titlecase equivalent of the character, if any; - * otherwise, the character itself. - * @see Character#isTitleCase(int) - * @see Character#toLowerCase(int) - * @see Character#toUpperCase(int) - * @since 1.5 - */ - public static int toTitleCase(int codePoint) { - return CharacterData.of(codePoint).toTitleCase(codePoint); + throw new UnsupportedOperationException(); } /** @@ -6370,7 +2067,7 @@ * @since 1.5 */ public static int digit(int codePoint, int radix) { - return CharacterData.of(codePoint).digit(codePoint, radix); + throw new UnsupportedOperationException(); } /** @@ -6441,7 +2138,7 @@ * @since 1.5 */ public static int getNumericValue(int codePoint) { - return CharacterData.of(codePoint).getNumericValue(codePoint); + throw new UnsupportedOperationException(); } /** @@ -6479,58 +2176,6 @@ } - /** - * Determines if the specified character is a Unicode space character. - * A character is considered to be a space character if and only if - * it is specified to be a space character by the Unicode Standard. This - * method returns true if the character's general category type is any of - * the following: - *

    - *
  • {@code SPACE_SEPARATOR} - *
  • {@code LINE_SEPARATOR} - *
  • {@code PARAGRAPH_SEPARATOR} - *
- * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #isSpaceChar(int)} method. - * - * @param ch the character to be tested. - * @return {@code true} if the character is a space character; - * {@code false} otherwise. - * @see Character#isWhitespace(char) - * @since 1.1 - */ - public static boolean isSpaceChar(char ch) { - return isSpaceChar((int)ch); - } - - /** - * Determines if the specified character (Unicode code point) is a - * Unicode space character. A character is considered to be a - * space character if and only if it is specified to be a space - * character by the Unicode Standard. This method returns true if - * the character's general category type is any of the following: - * - *

    - *
  • {@link #SPACE_SEPARATOR} - *
  • {@link #LINE_SEPARATOR} - *
  • {@link #PARAGRAPH_SEPARATOR} - *
- * - * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character is a space character; - * {@code false} otherwise. - * @see Character#isWhitespace(int) - * @since 1.5 - */ - public static boolean isSpaceChar(int codePoint) { - return ((((1 << Character.SPACE_SEPARATOR) | - (1 << Character.LINE_SEPARATOR) | - (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1) - != 0; - } /** * Determines if the specified character is white space according to Java. @@ -6596,7 +2241,7 @@ * @since 1.5 */ public static boolean isWhitespace(int codePoint) { - return CharacterData.of(codePoint).isWhitespace(codePoint); + throw new UnsupportedOperationException(); } /** @@ -6646,95 +2291,6 @@ } /** - * Returns a value indicating a character's general category. - * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #getType(int)} method. - * - * @param ch the character to be tested. - * @return a value of type {@code int} representing the - * character's general category. - * @see Character#COMBINING_SPACING_MARK - * @see Character#CONNECTOR_PUNCTUATION - * @see Character#CONTROL - * @see Character#CURRENCY_SYMBOL - * @see Character#DASH_PUNCTUATION - * @see Character#DECIMAL_DIGIT_NUMBER - * @see Character#ENCLOSING_MARK - * @see Character#END_PUNCTUATION - * @see Character#FINAL_QUOTE_PUNCTUATION - * @see Character#FORMAT - * @see Character#INITIAL_QUOTE_PUNCTUATION - * @see Character#LETTER_NUMBER - * @see Character#LINE_SEPARATOR - * @see Character#LOWERCASE_LETTER - * @see Character#MATH_SYMBOL - * @see Character#MODIFIER_LETTER - * @see Character#MODIFIER_SYMBOL - * @see Character#NON_SPACING_MARK - * @see Character#OTHER_LETTER - * @see Character#OTHER_NUMBER - * @see Character#OTHER_PUNCTUATION - * @see Character#OTHER_SYMBOL - * @see Character#PARAGRAPH_SEPARATOR - * @see Character#PRIVATE_USE - * @see Character#SPACE_SEPARATOR - * @see Character#START_PUNCTUATION - * @see Character#SURROGATE - * @see Character#TITLECASE_LETTER - * @see Character#UNASSIGNED - * @see Character#UPPERCASE_LETTER - * @since 1.1 - */ - public static int getType(char ch) { - return getType((int)ch); - } - - /** - * Returns a value indicating a character's general category. - * - * @param codePoint the character (Unicode code point) to be tested. - * @return a value of type {@code int} representing the - * character's general category. - * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK - * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION - * @see Character#CONTROL CONTROL - * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL - * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION - * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER - * @see Character#ENCLOSING_MARK ENCLOSING_MARK - * @see Character#END_PUNCTUATION END_PUNCTUATION - * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION - * @see Character#FORMAT FORMAT - * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION - * @see Character#LETTER_NUMBER LETTER_NUMBER - * @see Character#LINE_SEPARATOR LINE_SEPARATOR - * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER - * @see Character#MATH_SYMBOL MATH_SYMBOL - * @see Character#MODIFIER_LETTER MODIFIER_LETTER - * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL - * @see Character#NON_SPACING_MARK NON_SPACING_MARK - * @see Character#OTHER_LETTER OTHER_LETTER - * @see Character#OTHER_NUMBER OTHER_NUMBER - * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION - * @see Character#OTHER_SYMBOL OTHER_SYMBOL - * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR - * @see Character#PRIVATE_USE PRIVATE_USE - * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR - * @see Character#START_PUNCTUATION START_PUNCTUATION - * @see Character#SURROGATE SURROGATE - * @see Character#TITLECASE_LETTER TITLECASE_LETTER - * @see Character#UNASSIGNED UNASSIGNED - * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER - * @since 1.5 - */ - public static int getType(int codePoint) { - return CharacterData.of(codePoint).getType(codePoint); - } - - /** * Determines the character representation for a specific digit in * the specified radix. If the value of {@code radix} is not a * valid radix, or the value of {@code digit} is not a valid @@ -6772,126 +2328,6 @@ } /** - * Returns the Unicode directionality property for the given - * character. Character directionality is used to calculate the - * visual ordering of text. The directionality value of undefined - * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}. - * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #getDirectionality(int)} method. - * - * @param ch {@code char} for which the directionality property - * is requested. - * @return the directionality property of the {@code char} value. - * - * @see Character#DIRECTIONALITY_UNDEFINED - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR - * @see Character#DIRECTIONALITY_ARABIC_NUMBER - * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR - * @see Character#DIRECTIONALITY_NONSPACING_MARK - * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL - * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR - * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR - * @see Character#DIRECTIONALITY_WHITESPACE - * @see Character#DIRECTIONALITY_OTHER_NEUTRALS - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE - * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT - * @since 1.4 - */ - public static byte getDirectionality(char ch) { - return getDirectionality((int)ch); - } - - /** - * Returns the Unicode directionality property for the given - * character (Unicode code point). Character directionality is - * used to calculate the visual ordering of text. The - * directionality value of undefined character is {@link - * #DIRECTIONALITY_UNDEFINED}. - * - * @param codePoint the character (Unicode code point) for which - * the directionality property is requested. - * @return the directionality property of the character. - * - * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR - * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR - * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER - * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR - * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK - * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL - * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR - * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR - * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE - * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING - * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING - * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE - * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT - * @since 1.5 - */ - public static byte getDirectionality(int codePoint) { - return CharacterData.of(codePoint).getDirectionality(codePoint); - } - - /** - * Determines whether the character is mirrored according to the - * Unicode specification. Mirrored characters should have their - * glyphs horizontally mirrored when displayed in text that is - * right-to-left. For example, {@code '\u005Cu0028'} LEFT - * PARENTHESIS is semantically defined to be an opening - * parenthesis. This will appear as a "(" in text that is - * left-to-right but as a ")" in text that is right-to-left. - * - *

Note: This method cannot handle supplementary characters. To support - * all Unicode characters, including supplementary characters, use - * the {@link #isMirrored(int)} method. - * - * @param ch {@code char} for which the mirrored property is requested - * @return {@code true} if the char is mirrored, {@code false} - * if the {@code char} is not mirrored or is not defined. - * @since 1.4 - */ - public static boolean isMirrored(char ch) { - return isMirrored((int)ch); - } - - /** - * Determines whether the specified character (Unicode code point) - * is mirrored according to the Unicode specification. Mirrored - * characters should have their glyphs horizontally mirrored when - * displayed in text that is right-to-left. For example, - * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically - * defined to be an opening parenthesis. This will appear - * as a "(" in text that is left-to-right but as a ")" in text - * that is right-to-left. - * - * @param codePoint the character (Unicode code point) to be tested. - * @return {@code true} if the character is mirrored, {@code false} - * if the character is not mirrored or is not defined. - * @since 1.5 - */ - public static boolean isMirrored(int codePoint) { - return CharacterData.of(codePoint).isMirrored(codePoint); - } - - /** * Compares two {@code Character} objects numerically. * * @param anotherCharacter the {@code Character} to be compared. @@ -6928,42 +2364,6 @@ return x - y; } - /** - * Converts the character (Unicode code point) argument to uppercase using - * information from the UnicodeData file. - *

- * - * @param codePoint the character (Unicode code point) to be converted. - * @return either the uppercase equivalent of the character, if - * any, or an error flag ({@code Character.ERROR}) - * that indicates that a 1:M {@code char} mapping exists. - * @see Character#isLowerCase(char) - * @see Character#isUpperCase(char) - * @see Character#toLowerCase(char) - * @see Character#toTitleCase(char) - * @since 1.4 - */ - static int toUpperCaseEx(int codePoint) { - assert isValidCodePoint(codePoint); - return CharacterData.of(codePoint).toUpperCaseEx(codePoint); - } - - /** - * Converts the character (Unicode code point) argument to uppercase using case - * mapping information from the SpecialCasing file in the Unicode - * specification. If a character has no explicit uppercase - * mapping, then the {@code char} itself is returned in the - * {@code char[]}. - * - * @param codePoint the character (Unicode code point) to be converted. - * @return a {@code char[]} with the uppercased character. - * @since 1.4 - */ - static char[] toUpperCaseCharArray(int codePoint) { - // As of Unicode 6.0, 1:M uppercasings only happen in the BMP. - assert isBmpCodePoint(codePoint); - return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint); - } /** * The number of bits used to represent a char value in unsigned @@ -6985,48 +2385,4 @@ return (char) (((ch & 0xFF00) >> 8) | (ch << 8)); } - /** - * Returns the Unicode name of the specified character - * {@code codePoint}, or null if the code point is - * {@link #UNASSIGNED unassigned}. - *

- * Note: if the specified character is not assigned a name by - * the UnicodeData file (part of the Unicode Character - * Database maintained by the Unicode Consortium), the returned - * name is the same as the result of expression. - * - *

{@code - * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ') - * + " " - * + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); - * - * }
- * - * @param codePoint the character (Unicode code point) - * - * @return the Unicode name of the specified character, or null if - * the code point is unassigned. - * - * @exception IllegalArgumentException if the specified - * {@code codePoint} is not a valid Unicode - * code point. - * - * @since 1.7 - */ - public static String getName(int codePoint) { - if (!isValidCodePoint(codePoint)) { - throw new IllegalArgumentException(); - } - String name = CharacterName.get(codePoint); - if (name != null) - return name; - if (getType(codePoint) == UNASSIGNED) - return null; - UnicodeBlock block = UnicodeBlock.of(codePoint); - if (block != null) - return block.toString().replace('_', ' ') + " " - + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); - // should never come here - return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); - } }