Character class wraps a value of the primitive
* type char in an object. An object of type
* Character contains a single field whose type is
* char.
* * In addition, this class provides several methods for determining * a character's category (lowercase letter, digit, etc.) and for converting * characters from uppercase to lowercase and vice versa. *
* Character information is based on the Unicode Standard, version 4.0. *
* The methods and data of class Character are defined by
* the information in the UnicodeData file that is part of the
* Unicode Character Database maintained by the Unicode
* Consortium. This file specifies various properties including name
* and general category for every defined Unicode code point or
* character range.
*
* The file and its description are available from the Unicode Consortium at: *
* *The char data type (and therefore the value that a
* Character object encapsulates) are based on the
* original Unicode specification, which defined characters as
* fixed-width 16-bit entities. The Unicode standard has since been
* changed to allow for characters whose representation requires more
* than 16 bits. The range of legal code points is now
* U+0000 to U+10FFFF, known as Unicode scalar value.
* (Refer to the
* definition of the U+n notation in the Unicode
* standard.)
*
*
The set of characters from U+0000 to U+FFFF is sometimes
* referred to as the Basic Multilingual Plane (BMP). Characters whose code points are greater
* than U+FFFF are called supplementary characters. The Java
* 2 platform uses the UTF-16 representation in char
* arrays and in the String and StringBuffer
* classes. In this representation, supplementary characters are
* represented as a pair of char values, the first from
* the high-surrogates range, (\uD800-\uDBFF), the
* second from the low-surrogates range
* (\uDC00-\uDFFF).
*
*
A char value, therefore, represents Basic
* Multilingual Plane (BMP) code points, including the surrogate
* code points, or code units of the UTF-16 encoding. An
* int value represents all Unicode code points,
* including supplementary code points. The lower (least significant)
* 21 bits of int are used to represent Unicode code
* points and the upper (most significant) 11 bits must be zero.
* Unless otherwise specified, the behavior with respect to
* supplementary characters and surrogate char values is
* as follows:
*
*
char value cannot support
* supplementary characters. They treat char values from the
* surrogate ranges as undefined characters. For example,
* Character.isLetter('\uD840') returns false, even though
* this specific value if followed by any low-surrogate value in a string
* would represent a letter.
*
* int value support all
* Unicode characters, including supplementary characters. For
* example, Character.isLetter(0x2F81A) returns
* true because the code point value represents a letter
* (a CJK ideograph).
* In the Java SE API documentation, Unicode code point is
* used for character values in the range between U+0000 and U+10FFFF,
* and Unicode code unit is used for 16-bit
*
* 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", new String[] {"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", new String[] { "Letterlike Symbols", "LetterlikeSymbols"});
/**
* Constant for the "Number Forms" Unicode character block.
* @since 1.2
*/
public static final UnicodeBlock NUMBER_FORMS =
new UnicodeBlock("NUMBER_FORMS", new String[] {"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", new String[] {"Mathematical Operators",
"MathematicalOperators"});
/**
* Constant for the "Miscellaneous Technical" Unicode character block.
* @since 1.2
*/
public static final UnicodeBlock MISCELLANEOUS_TECHNICAL =
new UnicodeBlock("MISCELLANEOUS_TECHNICAL", new String[] {"Miscellaneous Technical",
"MiscellaneousTechnical"});
/**
* Constant for the "Control Pictures" Unicode character block.
* @since 1.2
*/
public static final UnicodeBlock CONTROL_PICTURES =
new UnicodeBlock("CONTROL_PICTURES", new String[] {"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", new String[] {"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", new String[] {"Enclosed Alphanumerics",
"EnclosedAlphanumerics"});
/**
* Constant for the "Box Drawing" Unicode character block.
* @since 1.2
*/
public static final UnicodeBlock BOX_DRAWING =
new UnicodeBlock("BOX_DRAWING", new String[] {"Box Drawing", "BoxDrawing"});
/**
* Constant for the "Block Elements" Unicode character block.
* @since 1.2
*/
public static final UnicodeBlock BLOCK_ELEMENTS =
new UnicodeBlock("BLOCK_ELEMENTS", new String[] {"Block Elements", "BlockElements"});
/**
* Constant for the "Geometric Shapes" Unicode character block.
* @since 1.2
*/
public static final UnicodeBlock GEOMETRIC_SHAPES =
new UnicodeBlock("GEOMETRIC_SHAPES", new String[] {"Geometric Shapes", "GeometricShapes"});
/**
* Constant for the "Miscellaneous Symbols" Unicode character block.
* @since 1.2
*/
public static final UnicodeBlock MISCELLANEOUS_SYMBOLS =
new UnicodeBlock("MISCELLANEOUS_SYMBOLS", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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",
new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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",
new String[] {"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",
new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"Yi Syllables", "YiSyllables"});
/**
* Constant for the "Yi Radicals" Unicode character block.
* @since 1.4
*/
public static final UnicodeBlock YI_RADICALS =
new UnicodeBlock("YI_RADICALS", new String[] {"Yi Radicals", "YiRadicals"});
/**
* Constant for the "Cyrillic Supplementary" Unicode character block.
* @since 1.5
*/
public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY =
new UnicodeBlock("CYRILLIC_SUPPLEMENTARY",
new String[] {"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", new String[] {"Tai Le", "TaiLe"});
/**
* Constant for the "Khmer Symbols" Unicode character block.
* @since 1.5
*/
public static final UnicodeBlock KHMER_SYMBOLS =
new UnicodeBlock("KHMER_SYMBOLS", new String[] {"Khmer Symbols", "KhmerSymbols"});
/**
* Constant for the "Phonetic Extensions" Unicode character block.
* @since 1.5
*/
public static final UnicodeBlock PHONETIC_EXTENSIONS =
new UnicodeBlock("PHONETIC_EXTENSIONS", new String[] {"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",
new String[]{"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", new String[] {"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", new String[] {"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",
new String[] {"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",
new String[]{"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"Aegean Numbers", "AegeanNumbers"});
/**
* Constant for the "Old Italic" Unicode character block.
* @since 1.5
*/
public static final UnicodeBlock OLD_ITALIC =
new UnicodeBlock("OLD_ITALIC", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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", new String[] {"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",
new String[] {"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",
new String[] {"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",
new String[]{"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", new String[] {"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",
new String[] {"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",
new String[] {"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: 0xD800 through 0xDB7F
*
* @since 1.5
*/
public static final UnicodeBlock HIGH_SURROGATES =
new UnicodeBlock("HIGH_SURROGATES", new String[] {"High Surrogates", "HighSurrogates"});
/**
* Constant for the "High Private Use Surrogates" Unicode character block.
* This block represents codepoint values in the high surrogate
* range: 0xDB80 through 0xDBFF
*
* @since 1.5
*/
public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES =
new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES", new String[] { "High Private Use Surrogates",
"HighPrivateUseSurrogates"});
/**
* Constant for the "Low Surrogates" Unicode character block.
* This block represents codepoint values in the high surrogate
* range: 0xDC00 through 0xDFFF
*
* @since 1.5
*/
public static final UnicodeBlock LOW_SURROGATES =
new UnicodeBlock("LOW_SURROGATES", new String[] {"Low Surrogates", "LowSurrogates"});
/**
* Constant for the "Arabic Supplement" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock ARABIC_SUPPLEMENT =
new UnicodeBlock("ARABIC_SUPPLEMENT",
new String[] { "Arabic Supplement",
"ArabicSupplement"});
/**
* Constant for the "NKo" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock NKO = new UnicodeBlock("NKO");
/**
* Constant for the "Ethiopic Supplement" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock ETHIOPIC_SUPPLEMENT =
new UnicodeBlock("ETHIOPIC_SUPPLEMENT",
new String[] { "Ethiopic Supplement",
"EthiopicSupplement"});
/**
* 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 String[] { "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 "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 "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",
new String[] { "Ol Chiki",
"OlChiki"});
/**
* Constant for the "Phonetic Extensions Supplement" Unicode character
* block.
* @since 1.7
*/
public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT =
new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT",
new String[] { "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",
new String[] { "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",
new String[] { "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",
new String[] { "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",
new String[] { "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",
new String[] { "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",
new String[] { "Supplemental Punctuation",
"SupplementalPunctuation"});
/**
* Constant for the "CJK Strokes" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock CJK_STROKES =
new UnicodeBlock("CJK_STROKES",
new String[] { "CJK Strokes",
"CJKStrokes"});
/**
* 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",
new String[] { "Cyrillic Extended-B",
"CyrillicExtended-B"});
/**
* Constant for the "Modifier Tone Letters" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock MODIFIER_TONE_LETTERS =
new UnicodeBlock("MODIFIER_TONE_LETTERS",
new String[] { "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",
new String[] { "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",
new String[] { "Syloti Nagri",
"SylotiNagri"});
/**
* Constant for the "Phags-pa" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock PHAGS_PA =
new UnicodeBlock("PHAGS_PA", new String[] { "Phags-pa"});
/**
* Constant for the "Saurashtra" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock SAURASHTRA =
new UnicodeBlock("SAURASHTRA");
/**
* Constant for the "Kayah Li" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock KAYAH_LI =
new UnicodeBlock("KAYAH_LI",
new String[] { "Kayah Li",
"KayahLi"});
/**
* Constant for the "Rejang" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock REJANG = new UnicodeBlock("REJANG");
/**
* Constant for the "Cham" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock CHAM = new UnicodeBlock("CHAM");
/**
* Constant for the "Vertical Forms" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock VERTICAL_FORMS =
new UnicodeBlock("VERTICAL_FORMS",
new String[] { "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",
new String[] { "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",
new String[] { "Ancient Symbols",
"AncientSymbols"});
/**
* Constant for the "Phaistos Disc" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock PHAISTOS_DISC =
new UnicodeBlock("PHAISTOS_DISC",
new String[] { "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",
new String[] { "Old Persian",
"OldPersian"});
/**
* 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 "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",
new String[] { "Cuneiform Numbers and Punctuation",
"CuneiformNumbersandPunctuation"});
/**
* 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",
new String[] { "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",
new String[] { "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",
new String[] { "Mahjong Tiles",
"MahjongTiles"});
/**
* Constant for the "Domino Tiles" Unicode character block.
* @since 1.7
*/
public static final UnicodeBlock DOMINO_TILES =
new UnicodeBlock("DOMINO_TILES",
new String[] { "Domino Tiles",
"DominoTiles"});
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; Syria
0x0750, // 0750..077F; Arabic Supplement
0x0780, // 0780..07BF; Thaana
0x07C0, // 07C0..07FF; NKo
0x0800, // 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, // unassigned
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, // unassigned
0x1B00, // 1B00..1B7F; Balinese
0x1B80, // 1B80..1BBF; Sundanese
0x1BC0, // unassigned
0x1C00, // 1C00..1C4F; Lepcha
0x1C50, // 1C50..1C7F; Ol Chiki
0x1C80, // unassigned
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 Ideograph
0xA000, // A000..A48F; Yi Syllables
0xA490, // A490..A4CF; Yi Radicals
0xA4D0, // unassigned
0xA500, // A500..A63F; Vai
0xA640, // A640..A69F; Cyrillic Extended-B
0xA6A0, // unassigned
0xA700, // A700..A71F; Modifier Tone Letters
0xA720, // A720..A7FF; Latin Extended-D
0xA800, // A800..A82F; Syloti Nagri
0xA830, // unassigned
0xA840, // A840..A87F; Phags-pa
0xA880, // A880..A8DF; Saurashtra
0xA8E0, // unassigned
0xA900, // A900..A92F; Kayah Li
0xA930, // A930..A95F; Rejang
0xA960, // unassigned
0xAA00, // AA00..AA5F; Cham
0xAA60, // unassigned
0xAC00, // AC00..D7AF; Hangul Syllables
0xD7B0, // unassigned
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; Desere
0x10450, // 10450..1047F; Shavian
0x10480, // 10480..104AF; Osmanya
0x104B0, // unassigned
0x10800, // 10800..1083F; Cypriot Syllabary
0x10840, // unassigned
0x10900, // 10900..1091F; Phoenician
0x10920, // 10920..1093F; Lydian
0x10940, // unassigned
0x10A00, // 10A00..10A5F; Kharoshthi
0x10A60, // unassigned
0x12000, // 12000..123FF; Cuneiform
0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation
0x12480, // 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, // unassigned
0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B
0x2A6E0, // 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,
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,
null,
LIMBU,
TAI_LE,
NEW_TAI_LUE,
KHMER_SYMBOLS,
BUGINESE,
null,
BALINESE,
SUNDANESE,
null,
LEPCHA,
OL_CHIKI,
null,
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,
null,
VAI,
CYRILLIC_EXTENDED_B,
null,
MODIFIER_TONE_LETTERS,
LATIN_EXTENDED_D,
SYLOTI_NAGRI,
null,
PHAGS_PA,
SAURASHTRA,
null,
KAYAH_LI,
REJANG,
null,
CHAM,
null,
HANGUL_SYLLABLES,
null,
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,
null,
PHOENICIAN,
LYDIAN,
null,
KHAROSHTHI,
null,
CUNEIFORM,
CUNEIFORM_NUMBERS_AND_PUNCTUATION,
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,
null,
CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B,
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 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
* This method accepts block names in the following forms:
*
* If the Unicode Standard changes block names, both the previous and
* current names will be accepted.
*
* @param blockName A This method returns This method returns This method doesn't validate the specified character to be a
* valid Unicode code point. The caller must validate the
* character value using {@link #isValidCodePoint(int) isValidCodePoint}
* if necessary.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return 2 if the character is a valid supplementary character; 1 otherwise.
* @see #isSupplementaryCodePoint(int)
* @since 1.5
*/
public static int charCount(int codePoint) {
return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT? 2 : 1;
}
/**
* Converts the specified surrogate pair to its supplementary code
* point value. This method does not validate the specified
* surrogate pair. The caller must validate it using {@link
* #isSurrogatePair(char, char) isSurrogatePair} if necessary.
*
* @param high the high-surrogate code unit
* @param low the low-surrogate code unit
* @return the supplementary code point composed from the
* specified surrogate pair.
* @since 1.5
*/
public static int toCodePoint(char high, char low) {
return ((high - MIN_HIGH_SURROGATE) << 10)
+ (low - MIN_LOW_SURROGATE) + MIN_SUPPLEMENTARY_CODE_POINT;
}
/**
* Returns the code point at the given index of the
*
* A character is lowercase if its general category type, provided
* by
* The following are examples of lowercase characters:
* Many other Unicode characters are lowercase too.
*
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isLowerCase(int)} method.
*
* @param ch the character to be tested.
* @return
* A character is lowercase if its general category type, provided
* by {@link Character#getType getType(codePoint)}, is
*
* The following are examples of lowercase characters:
* Many other Unicode characters are lowercase too.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return
* A character is uppercase if its general category type, provided by
*
* The following are examples of uppercase characters:
* Many other Unicode characters are uppercase too.
*
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isUpperCase(int)} method.
*
* @param ch the character to be tested.
* @return
* A character is uppercase if its general category type, provided by
* {@link Character#getType(int) getType(codePoint)}, is
* The following are examples of uppercase characters:
* Many other Unicode characters are uppercase too.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return
* A character is a titlecase character if its general
* category type, provided by
* Some characters look like pairs of Latin letters. For example, there
* is an uppercase letter that looks like "LJ" and has a corresponding
* lowercase letter that looks like "lj". A third form, which looks like "Lj",
* is the appropriate form to use when rendering a word in lowercase
* with initial capitals, as for a book title.
*
* These are some of the Unicode characters for which this method returns
* Many other Unicode characters are titlecase too.
*
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isTitleCase(int)} method.
*
* @param ch the character to be tested.
* @return
* A character is a titlecase character if its general
* category type, provided by {@link Character#getType(int) getType(codePoint)},
* is
* Some characters look like pairs of Latin letters. For example, there
* is an uppercase letter that looks like "LJ" and has a corresponding
* lowercase letter that looks like "lj". A third form, which looks like "Lj",
* is the appropriate form to use when rendering a word in lowercase
* with initial capitals, as for a book title.
*
* These are some of the Unicode characters for which this method returns
* Many other Unicode characters are titlecase too.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return
* A character is a digit if its general category type, provided
* by
* Some Unicode character ranges that contain digits:
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isDigit(int)} method.
*
* @param ch the character to be tested.
* @return
* A character is a digit if its general category type, provided
* by {@link Character#getType(int) getType(codePoint)}, is
*
* Some Unicode character ranges that contain digits:
*
* A character is defined if at least one of the following is true:
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isDefined(int)} method.
*
* @param ch the character to be tested
* @return
* A character is defined if at least one of the following is true:
*
* A character is considered to be a letter if its general
* category type, provided by Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isLetter(int)} method.
*
* @param ch the character to be tested.
* @return
* A character is considered to be a letter if its general
* category type, provided by {@link Character#getType(int) getType(codePoint)},
* is any of the following:
*
* A character is considered to be a letter or digit if either
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isLetterOrDigit(int)} method.
*
* @param ch the character to be tested.
* @return
* A character is considered to be a letter or digit if either
* {@link #isLetter(int) isLetter(codePoint)} or
* {@link #isDigit(int) isDigit(codePoint)} returns
*
* A character may start a Java identifier if and only if
* one of the following is true:
*
* A character may be part of a Java identifier if and only if any
* of the following are true:
*
* A character may start a Java identifier if and only if
* one of the following conditions is true:
* 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
* A character may start a Java identifier if and only if
* one of the following conditions is true:
*
* A character may be part of a Java identifier if any of the following
* are true:
* 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
* A character may be part of a Java identifier if any of the following
* are true:
*
* A character may start a Unicode identifier if and only if
* one of the following conditions is true:
* 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
* A character may start a Unicode identifier if and only if
* one of the following conditions is true:
*
* A character may be part of a Unicode identifier if and only if
* one of the following statements is true:
* 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
* A character may be part of a Unicode identifier if and only if
* one of the following statements is true:
*
* The following Unicode characters are ignorable in a Java identifier
* or a Unicode identifier:
* 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
* The following Unicode characters are ignorable in a Java identifier
* or a Unicode identifier:
*
* Note that
* In general, {@link java.lang.String#toLowerCase()} should be used to map
* characters to lowercase. Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #toLowerCase(int)} method.
*
* @param ch the character to be converted.
* @return the lowercase equivalent of the character, if any;
* otherwise, the character itself.
* @see java.lang.Character#isLowerCase(char)
* @see java.lang.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
* In general, {@link java.lang.String#toLowerCase()} should be used to map
* characters to lowercase.
* Note that
* In general, {@link java.lang.String#toUpperCase()} should be used to map
* characters to uppercase. Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #toUpperCase(int)} method.
*
* @param ch the character to be converted.
* @return the uppercase equivalent of the character, if any;
* otherwise, the character itself.
* @see java.lang.Character#isUpperCase(char)
* @see java.lang.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
* In general, {@link java.lang.String#toUpperCase()} should be used to map
* characters to uppercase.
* Note that
* 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 java.lang.Character#isTitleCase(char)
* @see java.lang.Character#toLowerCase(char)
* @see java.lang.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
*
* If the radix is not in the range Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #digit(int, int)} method.
*
* @param ch the character to be converted.
* @param radix the radix.
* @return the numeric value represented by the character in the
* specified radix.
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Character#isDigit(char)
*/
public static int digit(char ch, int radix) {
return digit((int)ch, radix);
}
/**
* Returns the numeric value of the specified character (Unicode
* code point) in the specified radix.
*
* If the radix is not in the range
* The letters A-Z in their uppercase (
* If the character does not have a numeric value, then -1 is returned.
* If the character has a numeric value that cannot be represented as a
* nonnegative integer (for example, a fractional value), then -2
* is returned.
*
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #getNumericValue(int)} method.
*
* @param ch the character to be converted.
* @return the numeric value of the character, as a nonnegative
* The letters A-Z in their uppercase (
* If the character does not have a numeric value, then -1 is returned.
* If the character has a numeric value that cannot be represented as a
* nonnegative integer (for example, a fractional value), then -2
* is returned.
*
* @param codePoint the character (Unicode code point) to be converted.
* @return the numeric value of the character, as a nonnegative 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 Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isWhitespace(int)} method.
*
* @param ch the character to be tested.
* @return
*
* @param codePoint the character (Unicode code point) to be tested.
* @return Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isISOControl(int)} method.
*
* @param ch the character to be tested.
* @return 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
* The
* If the digit is less than 10, then
* Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #getDirectionality(int)} method.
*
* @param ch Note: This method cannot handle supplementary characters. To support
* all Unicode characters, including supplementary characters, use
* the {@link #isMirrored(int)} method.
*
* @param ch
*
* @param codePoint the character (Unicode code point) to be converted.
* @return either the uppercase equivalent of the character, if
* any, or an error flag (char values that are code units of the UTF-16
* encoding. For more information on Unicode terminology, refer to the
* Unicode Glossary.
*
* @author Lee Boynton
* @author Guy Steele
* @author Akira Tanaka
* @since 1.0
*/
public final
class Character extends Object implements java.io.Serializable, Comparabledigit method, the forDigit
* method, and the toString method of class
* Integer.
*
* @see java.lang.Character#digit(char, int)
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Integer#toString(int, int)
* @see java.lang.Integer#valueOf(java.lang.String)
*/
public static final int MIN_RADIX = 2;
/**
* The maximum radix available for conversion to and from strings.
* The constant value of this field is the largest value permitted
* for the radix argument in radix-conversion methods such as the
* digit method, the forDigit
* method, and the toString method of class
* Integer.
*
* @see java.lang.Character#digit(char, int)
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Integer#toString(int, int)
* @see java.lang.Integer#valueOf(java.lang.String)
*/
public static final int MAX_RADIX = 36;
/**
* The constant value of this field is the smallest value of type
* char, '\u0000'.
*
* @since 1.0.2
*/
public static final char MIN_VALUE = '\u0000';
/**
* The constant value of this field is the largest value of type
* char, '\uFFFF'.
*
* @since 1.0.2
*/
public static final char MAX_VALUE = '\uffff';
/**
* The Class instance representing the primitive type
* char.
*
* @since 1.1
*/
public static final Classchar
* values have undefined directionality in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_UNDEFINED = -1;
/**
* Strong bidirectional character type "L" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0;
/**
* Strong bidirectional character type "R" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1;
/**
* Strong bidirectional character type "AL" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2;
/**
* Weak bidirectional character type "EN" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3;
/**
* Weak bidirectional character type "ES" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4;
/**
* Weak bidirectional character type "ET" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5;
/**
* Weak bidirectional character type "AN" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6;
/**
* Weak bidirectional character type "CS" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7;
/**
* Weak bidirectional character type "NSM" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_NONSPACING_MARK = 8;
/**
* Weak bidirectional character type "BN" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9;
/**
* Neutral bidirectional character type "B" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10;
/**
* Neutral bidirectional character type "S" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11;
/**
* Neutral bidirectional character type "WS" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_WHITESPACE = 12;
/**
* Neutral bidirectional character type "ON" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13;
/**
* Strong bidirectional character type "LRE" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14;
/**
* Strong bidirectional character type "LRO" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15;
/**
* Strong bidirectional character type "RLE" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16;
/**
* Strong bidirectional character type "RLO" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17;
/**
* Weak bidirectional character type "PDF" in the Unicode specification.
* @since 1.4
*/
public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18;
/**
* The minimum value of a Unicode high-surrogate code unit in the
* UTF-16 encoding. A high-surrogate is also known as a
* leading-surrogate.
*
* @since 1.5
*/
public static final char MIN_HIGH_SURROGATE = '\uD800';
/**
* The maximum value of a Unicode high-surrogate code unit in the
* UTF-16 encoding. A high-surrogate is also known as a
* leading-surrogate.
*
* @since 1.5
*/
public static final char MAX_HIGH_SURROGATE = '\uDBFF';
/**
* The minimum value of a Unicode low-surrogate code unit in the
* UTF-16 encoding. A low-surrogate is also known as a
* trailing-surrogate.
*
* @since 1.5
*/
public static final char MIN_LOW_SURROGATE = '\uDC00';
/**
* The maximum value of a Unicode low-surrogate code unit in the
* UTF-16 encoding. A low-surrogate is also known as a
* trailing-surrogate.
*
* @since 1.5
*/
public static final char MAX_LOW_SURROGATE = '\uDFFF';
/**
* The minimum value of a Unicode surrogate code unit in the UTF-16 encoding.
*
* @since 1.5
*/
public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE;
/**
* The maximum value of a Unicode surrogate code unit in the UTF-16 encoding.
*
* @since 1.5
*/
public static final char MAX_SURROGATE = MAX_LOW_SURROGATE;
/**
* The minimum value of a supplementary code point.
*
* @since 1.5
*/
public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
/**
* The minimum value of a Unicode code point.
*
* @since 1.5
*/
public static final int MIN_CODE_POINT = 0x000000;
/**
* The maximum value of a Unicode code point.
*
* @since 1.5
*/
public static final int MAX_CODE_POINT = 0x10ffff;
/**
* Instances of this class represent particular subsets of the Unicode
* character set. The only family of subsets defined in the
* Character class is {@link Character.UnicodeBlock
* UnicodeBlock}. Other portions of the Java API may define other
* subsets for their own purposes.
*
* @since 1.2
*/
public static class Subset {
private String name;
/**
* Constructs a new Subset instance.
*
* @exception NullPointerException if name is null
* @param name The name of this subset
*/
protected Subset(String name) {
if (name == null) {
throw new NullPointerException("name");
}
this.name = name;
}
/**
* Compares two Subset objects for equality.
* This method returns true if and only if
* this and the argument refer to the same
* object; since this method is final, this
* guarantee holds for all subclasses.
*/
public final boolean equals(Object obj) {
return (this == obj);
}
/**
* Returns the standard hash code as defined by the
* {@link Object#hashCode} method. This method
* is final in order to ensure that the
* equals and hashCode methods will
* be consistent in all subclasses.
*/
public final int hashCode() {
return super.hashCode();
}
/**
* Returns the name of this subset.
*/
public final String toString() {
return name;
}
}
/**
* 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();
/**
* Create 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.toUpperCase(Locale.US), this);
}
/**
* Create a UnicodeBlock with the given identifier name and
* alias name.
*/
private UnicodeBlock(String idName, String alias) {
this(idName);
map.put(alias.toUpperCase(Locale.US), this);
}
/**
* Create a UnicodeBlock with the given identifier name and
* alias names.
*/
private UnicodeBlock(String idName, String[] aliasName) {
this(idName);
if (aliasName != null) {
for(int x=0; xnull if the character is not a
* member of a defined block.
*
* UnicodeBlock instance representing the
* Unicode block of which this character is a member, or
* 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
* null if the character is not a member of a
* defined block.
*
* @param codePoint the character (Unicode code point) in question.
* @return The UnicodeBlock instance representing the
* Unicode block of which this character is a member, or
* null if the character is not a member of any
* Unicode block
* @exception IllegalArgumentException if the specified
* 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.
*
*
* 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.
* UnicodeBlock name.
* @return The UnicodeBlock instance identified
* by blockName
* @throws IllegalArgumentException if blockName is an
* invalid name
* @throws NullPointerException if blockName is null
* @since 1.5
*/
public static final UnicodeBlock forName(String blockName) {
UnicodeBlock block = (UnicodeBlock)map.get(blockName.toUpperCase(Locale.US));
if (block == null) {
throw new IllegalArgumentException();
}
return block;
}
}
/**
* The value of the Character.
*
* @serial
*/
private final char value;
/** use serialVersionUID from JDK 1.0.2 for interoperability */
private static final long serialVersionUID = 3786198910865385080L;
/**
* Constructs a newly allocated Character object that
* represents the specified char value.
*
* @param value the value to be represented by the
* Character object.
*/
public Character(char value) {
this.value = value;
}
private static class CharacterCache {
private CharacterCache(){}
static final Character cache[] = new Character[127 + 1];
static {
for(int i = 0; i < cache.length; i++)
cache[i] = new Character((char)i);
}
}
/**
* Returns a Character instance representing the specified
* char value.
* If a new Character instance is not required, this method
* should generally be used in preference to the constructor
* {@link #Character(char)}, as this method is likely to yield
* significantly better space and time performance by caching
* frequently requested values.
*
* This method will always cache values in the range '\u0000'
* to '\u007f'", inclusive, and may cache other values outside
* of this range.
*
* @param c a char value.
* @return a Character instance representing c.
* @since 1.5
*/
public static Character valueOf(char c) {
if(c <= 127) { // must cache
return CharacterCache.cache[(int)c];
}
return new Character(c);
}
/**
* Returns the value of this Character object.
* @return the primitive char value represented by
* this object.
*/
public char charValue() {
return value;
}
/**
* Returns a hash code for this Character.
* @return a hash code value for this object.
*/
public int hashCode() {
return (int)value;
}
/**
* Compares this object against the specified object.
* The result is true if and only if the argument is not
* null and is a Character object that
* represents the same char value as this object.
*
* @param obj the object to compare with.
* @return true if the objects are the same;
* false otherwise.
*/
public boolean equals(Object obj) {
if (obj instanceof Character) {
return value == ((Character)obj).charValue();
}
return false;
}
/**
* Returns a String object representing this
* Character's value. The result is a string of
* length 1 whose sole component is the primitive
* char value represented by this
* Character object.
*
* @return a string representation of this object.
*/
public String toString() {
char buf[] = {value};
return String.valueOf(buf);
}
/**
* Returns a String object representing the
* specified char. The result is a string of length
* 1 consisting solely of the specified char.
*
* @param c the char to be converted
* @return the string representation of the specified char
* @since 1.4
*/
public static String toString(char c) {
return String.valueOf(c);
}
/**
* Determines whether the specified code point is a valid Unicode
* code point value in the range of 0x0000 to
* 0x10FFFF inclusive. This method is equivalent to
* the expression:
*
*
*
* @param codePoint the Unicode code point to be tested
* @return
* codePoint >= 0x0000 && codePoint <= 0x10FFFF
* true if the specified code point value
* is a valid code point value;
* false otherwise.
* @since 1.5
*/
public static boolean isValidCodePoint(int codePoint) {
return codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT;
}
/**
* Determines whether the specified character (Unicode code point)
* is in the supplementary character range. The method call is
* equivalent to the expression:
*
*
* @param codePoint the character (Unicode code point) to be tested
* @return
* codePoint >= 0x10000 && codePoint <= 0x10FFFF
* true if the specified character is in the Unicode
* supplementary character range; false otherwise.
* @since 1.5
*/
public static boolean isSupplementaryCodePoint(int codePoint) {
return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT
&& codePoint <= MAX_CODE_POINT;
}
/**
* Determines if the given char value is a
* high-surrogate code unit (also known as leading-surrogate
* code unit). Such values do not represent characters by
* themselves, but are used in the representation of supplementary characters in the
* UTF-16 encoding.
*
* true if and only if
*
* is ch >= '\uD800' && ch <= '\uDBFF'
* true.
*
* @param ch the char value to be tested.
* @return true if the char value
* is between '\uD800' and '\uDBFF' inclusive;
* false otherwise.
* @see java.lang.Character#isLowSurrogate(char)
* @see Character.UnicodeBlock#of(int)
* @since 1.5
*/
public static boolean isHighSurrogate(char ch) {
return ch >= MIN_HIGH_SURROGATE && ch <= MAX_HIGH_SURROGATE;
}
/**
* Determines if the given char value is a
* low-surrogate code unit (also known as trailing-surrogate code
* unit). Such values do not represent characters by themselves,
* but are used in the representation of supplementary characters in the UTF-16 encoding.
*
* true if and only if
*
is ch >= '\uDC00' && ch <= '\uDFFF'
* true.
*
* @param ch the char value to be tested.
* @return true if the char value
* is between '\uDC00' and '\uDFFF' inclusive;
* false otherwise.
* @see java.lang.Character#isHighSurrogate(char)
* @since 1.5
*/
public static boolean isLowSurrogate(char ch) {
return ch >= MIN_LOW_SURROGATE && ch <= MAX_LOW_SURROGATE;
}
/**
* Determines whether the specified pair of char
* values is a valid surrogate pair. This method is equivalent to
* the expression:
*
*
* @param high the high-surrogate code value to be tested
* @param low the low-surrogate code value to be tested
* @return
* isHighSurrogate(high) && isLowSurrogate(low)
* true if the specified high and
* low-surrogate code values represent a valid surrogate pair;
* false otherwise.
* @since 1.5
*/
public static boolean isSurrogatePair(char high, char low) {
return isHighSurrogate(high) && isLowSurrogate(low);
}
/**
* Determines the number of char values needed to
* represent the specified character (Unicode code point). If the
* specified character is equal to or greater than 0x10000, then
* the method returns 2. Otherwise, the method returns 1.
*
* CharSequence. If the char value at
* the given index in the CharSequence is in the
* high-surrogate range, the following index is less than the
* length of the CharSequence, and the
* char value at the following index is in the
* low-surrogate range, then the supplementary code point
* corresponding to this surrogate pair is returned. Otherwise,
* the char value at the given index is returned.
*
* @param seq a sequence of char values (Unicode code
* units)
* @param index the index to the char values (Unicode
* code units) in seq to be converted
* @return the Unicode code point at the given index
* @exception NullPointerException if seq is null.
* @exception IndexOutOfBoundsException if the value
* index is negative or not less than
* {@link CharSequence#length() seq.length()}.
* @since 1.5
*/
public static int codePointAt(CharSequence seq, int index) {
char c1 = seq.charAt(index++);
if (isHighSurrogate(c1)) {
if (index < seq.length()) {
char c2 = seq.charAt(index);
if (isLowSurrogate(c2)) {
return toCodePoint(c1, c2);
}
}
}
return c1;
}
/**
* Returns the code point at the given index of the
* char array. If the char value at
* the given index in the char array is in the
* high-surrogate range, the following index is less than the
* length of the char array, and the
* char value at the following index is in the
* low-surrogate range, then the supplementary code point
* corresponding to this surrogate pair is returned. Otherwise,
* the char value at the given index is returned.
*
* @param a the char array
* @param index the index to the char values (Unicode
* code units) in the char array to be converted
* @return the Unicode code point at the given index
* @exception NullPointerException if a is null.
* @exception IndexOutOfBoundsException if the value
* index is negative or not less than
* the length of the char array.
* @since 1.5
*/
public static int codePointAt(char[] a, int index) {
return codePointAtImpl(a, index, a.length);
}
/**
* Returns the code point at the given index of the
* char array, where only array elements with
* index less than limit can be used. If
* the char value at the given index in the
* char array is in the high-surrogate range, the
* following index is less than the limit, and the
* char value at the following index is in the
* low-surrogate range, then the supplementary code point
* corresponding to this surrogate pair is returned. Otherwise,
* the char value at the given index is returned.
*
* @param a the char array
* @param index the index to the char values (Unicode
* code units) in the char array to be converted
* @param limit the index after the last array element that can be used in the
* char array
* @return the Unicode code point at the given index
* @exception NullPointerException if a is null.
* @exception IndexOutOfBoundsException if the index
* argument is negative or not less than the limit
* argument, or if the limit argument is negative or
* greater than the length of the char array.
* @since 1.5
*/
public static int codePointAt(char[] a, int index, int limit) {
if (index >= limit || limit < 0 || limit > a.length) {
throw new IndexOutOfBoundsException();
}
return codePointAtImpl(a, index, limit);
}
static int codePointAtImpl(char[] a, int index, int limit) {
char c1 = a[index++];
if (isHighSurrogate(c1)) {
if (index < limit) {
char c2 = a[index];
if (isLowSurrogate(c2)) {
return toCodePoint(c1, c2);
}
}
}
return c1;
}
/**
* Returns the code point preceding the given index of the
* CharSequence. If the char value at
* (index - 1) in the CharSequence is in
* the low-surrogate range, (index - 2) is not
* negative, and the char value at (index -
* 2) in the CharSequence is in the
* high-surrogate range, then the supplementary code point
* corresponding to this surrogate pair is returned. Otherwise,
* the char value at (index - 1) is
* returned.
*
* @param seq the CharSequence instance
* @param index the index following the code point that should be returned
* @return the Unicode code point value before the given index.
* @exception NullPointerException if seq is null.
* @exception IndexOutOfBoundsException if the index
* argument is less than 1 or greater than {@link
* CharSequence#length() seq.length()}.
* @since 1.5
*/
public static int codePointBefore(CharSequence seq, int index) {
char c2 = seq.charAt(--index);
if (isLowSurrogate(c2)) {
if (index > 0) {
char c1 = seq.charAt(--index);
if (isHighSurrogate(c1)) {
return toCodePoint(c1, c2);
}
}
}
return c2;
}
/**
* Returns the code point preceding the given index of the
* char array. If the char value at
* (index - 1) in the char array is in
* the low-surrogate range, (index - 2) is not
* negative, and the char value at (index -
* 2) in the char array is in the
* high-surrogate range, then the supplementary code point
* corresponding to this surrogate pair is returned. Otherwise,
* the char value at (index - 1) is
* returned.
*
* @param a the char array
* @param index the index following the code point that should be returned
* @return the Unicode code point value before the given index.
* @exception NullPointerException if a is null.
* @exception IndexOutOfBoundsException if the index
* argument is less than 1 or greater than the length of the
* char array
* @since 1.5
*/
public static int codePointBefore(char[] a, int index) {
return codePointBeforeImpl(a, index, 0);
}
/**
* Returns the code point preceding the given index of the
* char array, where only array elements with
* index greater than or equal to start
* can be used. If the char value at (index -
* 1) in the char array is in the
* low-surrogate range, (index - 2) is not less than
* start, and the char value at
* (index - 2) in the char array is in
* the high-surrogate range, then the supplementary code point
* corresponding to this surrogate pair is returned. Otherwise,
* the char value at (index - 1) is
* returned.
*
* @param a the char array
* @param index the index following the code point that should be returned
* @param start the index of the first array element in the
* char array
* @return the Unicode code point value before the given index.
* @exception NullPointerException if a is null.
* @exception IndexOutOfBoundsException if the index
* argument is not greater than the start argument or
* is greater than the length of the char array, or
* if the start argument is negative or not less than
* the length of the char array.
* @since 1.5
*/
public static int codePointBefore(char[] a, int index, int start) {
if (index <= start || start < 0 || start >= a.length) {
throw new IndexOutOfBoundsException();
}
return codePointBeforeImpl(a, index, start);
}
static int codePointBeforeImpl(char[] a, int index, int start) {
char c2 = a[--index];
if (isLowSurrogate(c2)) {
if (index > start) {
char c1 = a[--index];
if (isHighSurrogate(c1)) {
return toCodePoint(c1, c2);
}
}
}
return c2;
}
/**
* Converts the specified character (Unicode code point) to its
* UTF-16 representation. If the specified code point is a BMP
* (Basic Multilingual Plane or Plane 0) value, the same value is
* stored in dst[dstIndex], and 1 is returned. If the
* specified code point is a supplementary character, its
* surrogate values are stored in dst[dstIndex]
* (high-surrogate) and dst[dstIndex+1]
* (low-surrogate), and 2 is returned.
*
* @param codePoint the character (Unicode code point) to be converted.
* @param dst an array of char in which the
* codePoint's UTF-16 value is stored.
* @param dstIndex the start index into the dst
* array where the converted value is stored.
* @return 1 if the code point is a BMP code point, 2 if the
* code point is a supplementary code point.
* @exception IllegalArgumentException if the specified
* codePoint is not a valid Unicode code point.
* @exception NullPointerException if the specified dst is null.
* @exception IndexOutOfBoundsException if dstIndex
* is negative or not less than dst.length, or if
* dst at dstIndex doesn't have enough
* array element(s) to store the resulting char
* value(s). (If dstIndex is equal to
* dst.length-1 and the specified
* codePoint is a supplementary character, the
* high-surrogate value is not stored in
* dst[dstIndex].)
* @since 1.5
*/
public static int toChars(int codePoint, char[] dst, int dstIndex) {
if (codePoint < 0 || codePoint > MAX_CODE_POINT) {
throw new IllegalArgumentException();
}
if (codePoint < MIN_SUPPLEMENTARY_CODE_POINT) {
dst[dstIndex] = (char) codePoint;
return 1;
}
toSurrogates(codePoint, dst, dstIndex);
return 2;
}
/**
* Converts the specified character (Unicode code point) to its
* UTF-16 representation stored in a char array. If
* the specified code point is a BMP (Basic Multilingual Plane or
* Plane 0) value, the resulting char array has
* the same value as codePoint. If the specified code
* point is a supplementary code point, the resulting
* char array has the corresponding surrogate pair.
*
* @param codePoint a Unicode code point
* @return a char array having
* codePoint's UTF-16 representation.
* @exception IllegalArgumentException if the specified
* codePoint is not a valid Unicode code point.
* @since 1.5
*/
public static char[] toChars(int codePoint) {
if (codePoint < 0 || codePoint > MAX_CODE_POINT) {
throw new IllegalArgumentException();
}
if (codePoint < MIN_SUPPLEMENTARY_CODE_POINT) {
return new char[] { (char) codePoint };
}
char[] result = new char[2];
toSurrogates(codePoint, result, 0);
return result;
}
static void toSurrogates(int codePoint, char[] dst, int index) {
int offset = codePoint - MIN_SUPPLEMENTARY_CODE_POINT;
dst[index+1] = (char)((offset & 0x3ff) + MIN_LOW_SURROGATE);
dst[index] = (char)((offset >>> 10) + MIN_HIGH_SURROGATE);
}
/**
* Returns the number of Unicode code points in the text range of
* the specified char sequence. The text range begins at the
* specified beginIndex and extends to the
* char at index endIndex - 1. Thus the
* length (in chars) of the text range is
* endIndex-beginIndex. Unpaired surrogates within
* the text range count as one code point each.
*
* @param seq the char sequence
* @param beginIndex the index to the first char of
* the text range.
* @param endIndex the index after the last char of
* the text range.
* @return the number of Unicode code points in the specified text
* range
* @exception NullPointerException if seq is null.
* @exception IndexOutOfBoundsException if the
* beginIndex is negative, or endIndex
* is larger than the length of the given sequence, or
* beginIndex is larger than endIndex.
* @since 1.5
*/
public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
int length = seq.length();
if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) {
throw new IndexOutOfBoundsException();
}
int n = 0;
for (int i = beginIndex; i < endIndex; ) {
n++;
if (isHighSurrogate(seq.charAt(i++))) {
if (i < endIndex && isLowSurrogate(seq.charAt(i))) {
i++;
}
}
}
return n;
}
/**
* Returns the number of Unicode code points in a subarray of the
* char array argument. The offset
* argument is the index of the first char of the
* subarray and the count argument specifies the
* length of the subarray in chars. Unpaired
* surrogates within the subarray count as one code point each.
*
* @param a the char array
* @param offset the index of the first char in the
* given char array
* @param count the length of the subarray in chars
* @return the number of Unicode code points in the specified subarray
* @exception NullPointerException if a is null.
* @exception IndexOutOfBoundsException if offset or
* count is negative, or if offset +
* count is larger than the length of the given array.
* @since 1.5
*/
public static int codePointCount(char[] a, int offset, int count) {
if (count > a.length - offset || offset < 0 || count < 0) {
throw new IndexOutOfBoundsException();
}
return codePointCountImpl(a, offset, count);
}
static int codePointCountImpl(char[] a, int offset, int count) {
int endIndex = offset + count;
int n = 0;
for (int i = offset; i < endIndex; ) {
n++;
if (isHighSurrogate(a[i++])) {
if (i < endIndex && isLowSurrogate(a[i])) {
i++;
}
}
}
return n;
}
/**
* Returns the index within the given char sequence that is offset
* from the given index by codePointOffset
* code points. Unpaired surrogates within the text range given by
* index and codePointOffset count as
* one code point each.
*
* @param seq the char sequence
* @param index the index to be offset
* @param codePointOffset the offset in code points
* @return the index within the char sequence
* @exception NullPointerException if seq is null.
* @exception IndexOutOfBoundsException if index
* is negative or larger then the length of the char sequence,
* or if codePointOffset is positive and the
* subsequence starting with index has fewer than
* codePointOffset code points, or if
* codePointOffset is negative and the subsequence
* before index has fewer than the absolute value
* of codePointOffset code points.
* @since 1.5
*/
public static int offsetByCodePoints(CharSequence seq, int index,
int codePointOffset) {
int length = seq.length();
if (index < 0 || index > length) {
throw new IndexOutOfBoundsException();
}
int x = index;
if (codePointOffset >= 0) {
int i;
for (i = 0; x < length && i < codePointOffset; i++) {
if (isHighSurrogate(seq.charAt(x++))) {
if (x < length && isLowSurrogate(seq.charAt(x))) {
x++;
}
}
}
if (i < codePointOffset) {
throw new IndexOutOfBoundsException();
}
} else {
int i;
for (i = codePointOffset; x > 0 && i < 0; i++) {
if (isLowSurrogate(seq.charAt(--x))) {
if (x > 0 && isHighSurrogate(seq.charAt(x-1))) {
x--;
}
}
}
if (i < 0) {
throw new IndexOutOfBoundsException();
}
}
return x;
}
/**
* Returns the index within the given char subarray
* that is offset from the given index by
* codePointOffset code points. The
* start and count arguments specify a
* subarray of the char array. Unpaired surrogates
* within the text range given by index and
* codePointOffset count as one code point each.
*
* @param a the char array
* @param start the index of the first char of the
* subarray
* @param count the length of the subarray in chars
* @param index the index to be offset
* @param codePointOffset the offset in code points
* @return the index within the subarray
* @exception NullPointerException if a is null.
* @exception IndexOutOfBoundsException
* if start or count is negative,
* or if start + count is larger than the length of
* the given array,
* or if index is less than start or
* larger then start + count,
* or if codePointOffset is positive and the text range
* starting with index and ending with start
* + count - 1 has fewer than codePointOffset code
* points,
* or if codePointOffset is negative and the text range
* starting with start and ending with index
* - 1 has fewer than the absolute value of
* codePointOffset code points.
* @since 1.5
*/
public static int offsetByCodePoints(char[] a, int start, int count,
int index, int codePointOffset) {
if (count > a.length-start || start < 0 || count < 0
|| index < start || index > start+count) {
throw new IndexOutOfBoundsException();
}
return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
}
static int offsetByCodePointsImpl(char[]a, int start, int count,
int index, int codePointOffset) {
int x = index;
if (codePointOffset >= 0) {
int limit = start + count;
int i;
for (i = 0; x < limit && i < codePointOffset; i++) {
if (isHighSurrogate(a[x++])) {
if (x < limit && isLowSurrogate(a[x])) {
x++;
}
}
}
if (i < codePointOffset) {
throw new IndexOutOfBoundsException();
}
} else {
int i;
for (i = codePointOffset; x > start && i < 0; i++) {
if (isLowSurrogate(a[--x])) {
if (x > start && isHighSurrogate(a[x-1])) {
x--;
}
}
}
if (i < 0) {
throw new IndexOutOfBoundsException();
}
}
return x;
}
/**
* Determines if the specified character is a lowercase character.
* Character.getType(ch), is
* LOWERCASE_LETTER.
*
*
* 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'
* true if the character is lowercase;
* false otherwise.
* @see java.lang.Character#isLowerCase(char)
* @see java.lang.Character#isTitleCase(char)
* @see java.lang.Character#toLowerCase(char)
* @see java.lang.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.
* LOWERCASE_LETTER.
*
*
* 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'
* true if the character is lowercase;
* false otherwise.
* @see java.lang.Character#isLowerCase(int)
* @see java.lang.Character#isTitleCase(int)
* @see java.lang.Character#toLowerCase(int)
* @see java.lang.Character#getType(int)
* @since 1.5
*/
public static boolean isLowerCase(int codePoint) {
return getType(codePoint) == Character.LOWERCASE_LETTER;
}
/**
* Determines if the specified character is an uppercase character.
* Character.getType(ch), is UPPERCASE_LETTER.
*
*
* 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'
* true if the character is uppercase;
* false otherwise.
* @see java.lang.Character#isLowerCase(char)
* @see java.lang.Character#isTitleCase(char)
* @see java.lang.Character#toUpperCase(char)
* @see java.lang.Character#getType(char)
* @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.
* UPPERCASE_LETTER.
*
*
* 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'
* true if the character is uppercase;
* false otherwise.
* @see java.lang.Character#isLowerCase(int)
* @see java.lang.Character#isTitleCase(int)
* @see java.lang.Character#toUpperCase(int)
* @see java.lang.Character#getType(int)
* @since 1.5
*/
public static boolean isUpperCase(int codePoint) {
return getType(codePoint) == Character.UPPERCASE_LETTER;
}
/**
* Determines if the specified character is a titlecase character.
* Character.getType(ch),
* is TITLECASE_LETTER.
* true:
*
*
* LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
* LATIN CAPITAL LETTER L WITH SMALL LETTER J
* LATIN CAPITAL LETTER N WITH SMALL LETTER J
* LATIN CAPITAL LETTER D WITH SMALL LETTER Z
* true if the character is titlecase;
* false otherwise.
* @see java.lang.Character#isLowerCase(char)
* @see java.lang.Character#isUpperCase(char)
* @see java.lang.Character#toTitleCase(char)
* @see java.lang.Character#getType(char)
* @since 1.0.2
*/
public static boolean isTitleCase(char ch) {
return isTitleCase((int)ch);
}
/**
* Determines if the specified character (Unicode code point) is a titlecase character.
* TITLECASE_LETTER.
* true:
*
*
* LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
* LATIN CAPITAL LETTER L WITH SMALL LETTER J
* LATIN CAPITAL LETTER N WITH SMALL LETTER J
* LATIN CAPITAL LETTER D WITH SMALL LETTER Z
* true if the character is titlecase;
* false otherwise.
* @see java.lang.Character#isLowerCase(int)
* @see java.lang.Character#isUpperCase(int)
* @see java.lang.Character#toTitleCase(int)
* @see java.lang.Character#getType(int)
* @since 1.5
*/
public static boolean isTitleCase(int codePoint) {
return getType(codePoint) == Character.TITLECASE_LETTER;
}
/**
* Determines if the specified character is a digit.
* Character.getType(ch), is
* DECIMAL_DIGIT_NUMBER.
*
*
*
* Many other character ranges contain digits as well.
*
* '\u0030' through '\u0039',
* ISO-LATIN-1 digits ('0' through '9')
* '\u0660' through '\u0669',
* Arabic-Indic digits
* '\u06F0' through '\u06F9',
* Extended Arabic-Indic digits
* '\u0966' through '\u096F',
* Devanagari digits
* '\uFF10' through '\uFF19',
* Fullwidth digits
* true if the character is a digit;
* false otherwise.
* @see java.lang.Character#digit(char, int)
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Character#getType(char)
*/
public static boolean isDigit(char ch) {
return isDigit((int)ch);
}
/**
* Determines if the specified character (Unicode code point) is a digit.
* DECIMAL_DIGIT_NUMBER.
*
*
*
* Many other character ranges contain digits as well.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return '\u0030' through '\u0039',
* ISO-LATIN-1 digits ('0' through '9')
* '\u0660' through '\u0669',
* Arabic-Indic digits
* '\u06F0' through '\u06F9',
* Extended Arabic-Indic digits
* '\u0966' through '\u096F',
* Devanagari digits
* '\uFF10' through '\uFF19',
* Fullwidth digits
* true if the character is a digit;
* false otherwise.
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Character#getType(int)
* @since 1.5
*/
public static boolean isDigit(int codePoint) {
return getType(codePoint) == Character.DECIMAL_DIGIT_NUMBER;
}
/**
* Determines if a character is defined in Unicode.
*
*
*
* true if the character has a defined meaning
* in Unicode; false otherwise.
* @see java.lang.Character#isDigit(char)
* @see java.lang.Character#isLetter(char)
* @see java.lang.Character#isLetterOrDigit(char)
* @see java.lang.Character#isLowerCase(char)
* @see java.lang.Character#isTitleCase(char)
* @see java.lang.Character#isUpperCase(char)
* @since 1.0.2
*/
public static boolean isDefined(char ch) {
return isDefined((int)ch);
}
/**
* Determines if a character (Unicode code point) is defined in Unicode.
*
*
*
* @param codePoint the character (Unicode code point) to be tested.
* @return true if the character has a defined meaning
* in Unicode; false otherwise.
* @see java.lang.Character#isDigit(int)
* @see java.lang.Character#isLetter(int)
* @see java.lang.Character#isLetterOrDigit(int)
* @see java.lang.Character#isLowerCase(int)
* @see java.lang.Character#isTitleCase(int)
* @see java.lang.Character#isUpperCase(int)
* @since 1.5
*/
public static boolean isDefined(int codePoint) {
return getType(codePoint) != Character.UNASSIGNED;
}
/**
* Determines if the specified character is a letter.
* Character.getType(ch),
* is any of the following:
*
*
*
* Not all letters have case. Many characters are
* letters but are neither uppercase nor lowercase nor titlecase.
*
* UPPERCASE_LETTER
* LOWERCASE_LETTER
* TITLECASE_LETTER
* MODIFIER_LETTER
* OTHER_LETTER
* true if the character is a letter;
* false otherwise.
* @see java.lang.Character#isDigit(char)
* @see java.lang.Character#isJavaIdentifierStart(char)
* @see java.lang.Character#isJavaLetter(char)
* @see java.lang.Character#isJavaLetterOrDigit(char)
* @see java.lang.Character#isLetterOrDigit(char)
* @see java.lang.Character#isLowerCase(char)
* @see java.lang.Character#isTitleCase(char)
* @see java.lang.Character#isUnicodeIdentifierStart(char)
* @see java.lang.Character#isUpperCase(char)
*/
public static boolean isLetter(char ch) {
return isLetter((int)ch);
}
/**
* Determines if the specified character (Unicode code point) is a letter.
*
*
*
* Not all letters have case. Many characters are
* letters but are neither uppercase nor lowercase nor titlecase.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return UPPERCASE_LETTER
* LOWERCASE_LETTER
* TITLECASE_LETTER
* MODIFIER_LETTER
* OTHER_LETTER
* true if the character is a letter;
* false otherwise.
* @see java.lang.Character#isDigit(int)
* @see java.lang.Character#isJavaIdentifierStart(int)
* @see java.lang.Character#isLetterOrDigit(int)
* @see java.lang.Character#isLowerCase(int)
* @see java.lang.Character#isTitleCase(int)
* @see java.lang.Character#isUnicodeIdentifierStart(int)
* @see java.lang.Character#isUpperCase(int)
* @since 1.5
*/
public static boolean isLetter(int codePoint) {
return ((((1 << Character.UPPERCASE_LETTER) |
(1 << Character.LOWERCASE_LETTER) |
(1 << Character.TITLECASE_LETTER) |
(1 << Character.MODIFIER_LETTER) |
(1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1)
!= 0;
}
/**
* Determines if the specified character is a letter or digit.
* Character.isLetter(char ch) or
* Character.isDigit(char ch) returns
* true for the character.
*
* true if the character is a letter or digit;
* false otherwise.
* @see java.lang.Character#isDigit(char)
* @see java.lang.Character#isJavaIdentifierPart(char)
* @see java.lang.Character#isJavaLetter(char)
* @see java.lang.Character#isJavaLetterOrDigit(char)
* @see java.lang.Character#isLetter(char)
* @see java.lang.Character#isUnicodeIdentifierPart(char)
* @since 1.0.2
*/
public static boolean isLetterOrDigit(char ch) {
return isLetterOrDigit((int)ch);
}
/**
* Determines if the specified character (Unicode code point) is a letter or digit.
* true for the character.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return true if the character is a letter or digit;
* false otherwise.
* @see java.lang.Character#isDigit(int)
* @see java.lang.Character#isJavaIdentifierPart(int)
* @see java.lang.Character#isLetter(int)
* @see java.lang.Character#isUnicodeIdentifierPart(int)
* @since 1.5
*/
public static boolean isLetterOrDigit(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.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1)
!= 0;
}
/**
* Determines if the specified character is permissible as the first
* character in a Java identifier.
*
*
*
* @param ch the character to be tested.
* @return true
* LETTER_NUMBER
* true if the character may start a Java
* identifier; false otherwise.
* @see java.lang.Character#isJavaLetterOrDigit(char)
* @see java.lang.Character#isJavaIdentifierStart(char)
* @see java.lang.Character#isJavaIdentifierPart(char)
* @see java.lang.Character#isLetter(char)
* @see java.lang.Character#isLetterOrDigit(char)
* @see java.lang.Character#isUnicodeIdentifierStart(char)
* @since 1.02
* @deprecated Replaced by isJavaIdentifierStart(char).
*/
@Deprecated
public static boolean isJavaLetter(char ch) {
return isJavaIdentifierStart(ch);
}
/**
* Determines if the specified character may be part of a Java
* identifier as other than the first character.
*
*
*
* @param ch the character to be tested.
* @return '$')
* '_')
* isIdentifierIgnorable returns
* true for the character.
* true if the character may be part of a
* Java identifier; false otherwise.
* @see java.lang.Character#isJavaLetter(char)
* @see java.lang.Character#isJavaIdentifierStart(char)
* @see java.lang.Character#isJavaIdentifierPart(char)
* @see java.lang.Character#isLetter(char)
* @see java.lang.Character#isLetterOrDigit(char)
* @see java.lang.Character#isUnicodeIdentifierPart(char)
* @see java.lang.Character#isIdentifierIgnorable(char)
* @since 1.02
* @deprecated Replaced by isJavaIdentifierPart(char).
*/
@Deprecated
public static boolean isJavaLetterOrDigit(char ch) {
return isJavaIdentifierPart(ch);
}
/**
* Determines if the specified character is
* permissible as the first character in a Java identifier.
*
*
*
* true
* LETTER_NUMBER
* true if the character may start a Java identifier;
* false otherwise.
* @see java.lang.Character#isJavaIdentifierPart(char)
* @see java.lang.Character#isLetter(char)
* @see java.lang.Character#isUnicodeIdentifierStart(char)
* @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
* @since 1.1
*/
public static boolean isJavaIdentifierStart(char ch) {
return isJavaIdentifierStart((int)ch);
}
/**
* Determines if the character (Unicode code point) is
* permissible as the first character in a Java identifier.
*
*
*
* @param codePoint the character (Unicode code point) to be tested.
* @return true
* LETTER_NUMBER
* true if the character may start a Java identifier;
* false otherwise.
* @see java.lang.Character#isJavaIdentifierPart(int)
* @see java.lang.Character#isLetter(int)
* @see java.lang.Character#isUnicodeIdentifierStart(int)
* @see javax.lang.model.SourceVersion#isIdentifier(CharSequence)
* @since 1.5
*/
public static boolean isJavaIdentifierStart(int codePoint) {
return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint);
}
/**
* Determines if the specified character may be part of a Java
* identifier as other than the first character.
*
*
*
* '$')
* '_')
* isIdentifierIgnorable returns
* true for the character
* true if the character may be part of a
* Java identifier; false otherwise.
* @see java.lang.Character#isIdentifierIgnorable(char)
* @see java.lang.Character#isJavaIdentifierStart(char)
* @see java.lang.Character#isLetterOrDigit(char)
* @see java.lang.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.
*
*
*
* @param codePoint the character (Unicode code point) to be tested.
* @return '$')
* '_')
* true for
* the character
* true if the character may be part of a
* Java identifier; false otherwise.
* @see java.lang.Character#isIdentifierIgnorable(int)
* @see java.lang.Character#isJavaIdentifierStart(int)
* @see java.lang.Character#isLetterOrDigit(int)
* @see java.lang.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.
*
*
*
* true
* LETTER_NUMBER.
* true if the character may start a Unicode
* identifier; false otherwise.
* @see java.lang.Character#isJavaIdentifierStart(char)
* @see java.lang.Character#isLetter(char)
* @see java.lang.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.
*
*
* @param codePoint the character (Unicode code point) to be tested.
* @return true
* LETTER_NUMBER.
* true if the character may start a Unicode
* identifier; false otherwise.
* @see java.lang.Character#isJavaIdentifierStart(int)
* @see java.lang.Character#isLetter(int)
* @see java.lang.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.
*
*
*
* '_')
* isIdentifierIgnorable returns
* true for this character.
* true if the character may be part of a
* Unicode identifier; false otherwise.
* @see java.lang.Character#isIdentifierIgnorable(char)
* @see java.lang.Character#isJavaIdentifierPart(char)
* @see java.lang.Character#isLetterOrDigit(char)
* @see java.lang.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.
*
*
* @param codePoint the character (Unicode code point) to be tested.
* @return '_')
* isIdentifierIgnorable returns
* true for this character.
* true if the character may be part of a
* Unicode identifier; false otherwise.
* @see java.lang.Character#isIdentifierIgnorable(int)
* @see java.lang.Character#isJavaIdentifierPart(int)
* @see java.lang.Character#isLetterOrDigit(int)
* @see java.lang.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.
*
*
*
*
*
*
* '\u0000' through '\u0008'
* '\u000E' through '\u001B'
* '\u007F' through '\u009F'
* FORMAT general
* category value
* true if the character is an ignorable control
* character that may be part of a Java or Unicode identifier;
* false otherwise.
* @see java.lang.Character#isJavaIdentifierPart(char)
* @see java.lang.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.
*
*
*
* @param codePoint the character (Unicode code point) to be tested.
* @return
*
*
* '\u0000' through '\u0008'
* '\u000E' through '\u001B'
* '\u007F' through '\u009F'
* FORMAT general
* category value
* true if the character is an ignorable control
* character that may be part of a Java or Unicode identifier;
* false otherwise.
* @see java.lang.Character#isJavaIdentifierPart(int)
* @see java.lang.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.
* Character.isLowerCase(Character.toLowerCase(ch))
* does not always return true for some ranges of
* characters, particularly those that are symbols or ideographs.
*
* String case mapping methods
* have several benefits over Character case mapping methods.
* String case mapping methods can perform locale-sensitive
* mappings, context-sensitive mappings, and 1:M character mappings, whereas
* the Character case mapping methods cannot.
*
* Character.isLowerCase(Character.toLowerCase(codePoint))
* does not always return true for some ranges of
* characters, particularly those that are symbols or ideographs.
*
* String case mapping methods
* have several benefits over Character case mapping methods.
* String case mapping methods can perform locale-sensitive
* mappings, context-sensitive mappings, and 1:M character mappings, whereas
* the 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 java.lang.Character#isLowerCase(int)
* @see java.lang.String#toLowerCase()
*
* @since 1.5
*/
public static int toLowerCase(int codePoint) {
return CharacterData.of(codePoint).toLowerCase(codePoint);
}
/**
* Converts the character argument to uppercase using case mapping
* information from the UnicodeData file.
* Character.isUpperCase(Character.toUpperCase(ch))
* does not always return true for some ranges of
* characters, particularly those that are symbols or ideographs.
*
* String case mapping methods
* have several benefits over Character case mapping methods.
* String case mapping methods can perform locale-sensitive
* mappings, context-sensitive mappings, and 1:M character mappings, whereas
* the Character case mapping methods cannot.
*
* Character.isUpperCase(Character.toUpperCase(codePoint))
* does not always return true for some ranges of
* characters, particularly those that are symbols or ideographs.
*
* String case mapping methods
* have several benefits over Character case mapping methods.
* String case mapping methods can perform locale-sensitive
* mappings, context-sensitive mappings, and 1:M character mappings, whereas
* the 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 java.lang.Character#isUpperCase(int)
* @see java.lang.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
* char argument is already a titlecase
* char, the same char value will be
* returned.
* Character.isTitleCase(Character.toTitleCase(ch))
* does not always return true for some ranges of
* characters.
*
* Character.isTitleCase(Character.toTitleCase(codePoint))
* does not always return 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 java.lang.Character#isTitleCase(int)
* @see java.lang.Character#toLowerCase(int)
* @see java.lang.Character#toUpperCase(int)
* @since 1.5
*/
public static int toTitleCase(int codePoint) {
return CharacterData.of(codePoint).toTitleCase(codePoint);
}
/**
* Returns the numeric value of the character ch in the
* specified radix.
* MIN_RADIX <=
* radix <= MAX_RADIX or if the
* value of ch is not a valid digit in the specified
* radix, -1 is returned. A character is a valid digit
* if at least one of the following is true:
*
*
*
* isDigit is true of the character
* and the Unicode decimal digit value of the character (or its
* single-character decomposition) is less than the specified radix.
* In this case the decimal digit value is returned.
* 'A' through 'Z' and its code is less than
* radix + 'A' - 10.
* In this case, ch - 'A' + 10
* is returned.
* 'a' through 'z' and its code is less than
* radix + 'a' - 10.
* In this case, ch - 'a' + 10
* is returned.
* MIN_RADIX <=
* radix <= MAX_RADIX or if the
* character is not a valid digit in the specified
* radix, -1 is returned. A character is a valid digit
* if at least one of the following is true:
*
*
*
* @param codePoint the character (Unicode code point) to be converted.
* @param radix the radix.
* @return the numeric value represented by the character in the
* specified radix.
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Character#isDigit(int)
* @since 1.5
*/
public static int digit(int codePoint, int radix) {
return CharacterData.of(codePoint).digit(codePoint, radix);
}
/**
* Returns the true of the character
* and the Unicode decimal digit value of the character (or its
* single-character decomposition) is less than the specified radix.
* In this case the decimal digit value is returned.
* 'A' through 'Z' and its code is less than
* radix + 'A' - 10.
* In this case, ch - 'A' + 10
* is returned.
* 'a' through 'z' and its code is less than
* radix + 'a' - 10.
* In this case, ch - 'a' + 10
* is returned.
* int value that the specified Unicode
* character represents. For example, the character
* '\u216C' (the roman numeral fifty) will return
* an int with a value of 50.
* '\u0041' through
* '\u005A'), lowercase
* ('\u0061' through '\u007A'), and
* full width variant ('\uFF21' through
* '\uFF3A' and '\uFF41' through
* '\uFF5A') forms have numeric values from 10
* through 35. This is independent of the Unicode specification,
* which does not assign numeric values to these char
* values.
* int
* value; -2 if the character has a numeric value that is not a
* nonnegative integer; -1 if the character has no numeric value.
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Character#isDigit(char)
* @since 1.1
*/
public static int getNumericValue(char ch) {
return getNumericValue((int)ch);
}
/**
* Returns the int value that the specified
* character (Unicode code point) represents. For example, the character
* '\u216C' (the Roman numeral fifty) will return
* an int with a value of 50.
* '\u0041' through
* '\u005A'), lowercase
* ('\u0061' through '\u007A'), and
* full width variant ('\uFF21' through
* '\uFF3A' and '\uFF41' through
* '\uFF5A') forms have numeric values from 10
* through 35. This is independent of the Unicode specification,
* which does not assign numeric values to these char
* values.
* int
* value; -2 if the character has a numeric value that is not a
* nonnegative integer; -1 if the character has no numeric value.
* @see java.lang.Character#forDigit(int, int)
* @see java.lang.Character#isDigit(int)
* @since 1.5
*/
public static int getNumericValue(int codePoint) {
return CharacterData.of(codePoint).getNumericValue(codePoint);
}
/**
* Determines if the specified character is ISO-LATIN-1 white space.
* This method returns true for the following five
* characters only:
*
*
*
* @param ch the character to be tested.
* @return '\t''\u0009'HORIZONTAL TABULATION'\n''\u000A'NEW LINE'\f''\u000C'FORM FEED'\r''\u000D'CARRIAGE RETURN' ''\u0020'SPACEtrue if the character is ISO-LATIN-1 white
* space; false otherwise.
* @see java.lang.Character#isSpaceChar(char)
* @see java.lang.Character#isWhitespace(char)
* @deprecated Replaced by isWhitespace(char).
*/
@Deprecated
public static boolean isSpace(char ch) {
return (ch <= 0x0020) &&
(((((1L << 0x0009) |
(1L << 0x000A) |
(1L << 0x000C) |
(1L << 0x000D) |
(1L << 0x0020)) >> ch) & 1L) != 0);
}
/**
* 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:
*
*
*
* SPACE_SEPARATOR
* LINE_SEPARATOR
* PARAGRAPH_SEPARATOR
* true if the character is a space character;
* false otherwise.
* @see java.lang.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:
*
*
*
*
* @param codePoint the character (Unicode code point) to be tested.
* @return true if the character is a space character;
* false otherwise.
* @see java.lang.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.
* A character is a Java whitespace character if and only if it satisfies
* one of the following criteria:
*
*
*
* SPACE_SEPARATOR,
* LINE_SEPARATOR, or PARAGRAPH_SEPARATOR)
* but is not also a non-breaking space ('\u00A0',
* '\u2007', '\u202F').
* '\u0009', HORIZONTAL TABULATION.
* '\u000A', LINE FEED.
* '\u000B', VERTICAL TABULATION.
* '\u000C', FORM FEED.
* '\u000D', CARRIAGE RETURN.
* '\u001C', FILE SEPARATOR.
* '\u001D', GROUP SEPARATOR.
* '\u001E', RECORD SEPARATOR.
* '\u001F', UNIT SEPARATOR.
* true if the character is a Java whitespace
* character; false otherwise.
* @see java.lang.Character#isSpaceChar(char)
* @since 1.1
*/
public static boolean isWhitespace(char ch) {
return isWhitespace((int)ch);
}
/**
* Determines if the specified character (Unicode code point) is
* white space according to Java. A character is a Java
* whitespace character if and only if it satisfies one of the
* following criteria:
*
*
* '\u00A0',
* '\u2007', '\u202F').
* '\u0009', HORIZONTAL TABULATION.
* '\u000A', LINE FEED.
* '\u000B', VERTICAL TABULATION.
* '\u000C', FORM FEED.
* '\u000D', CARRIAGE RETURN.
* '\u001C', FILE SEPARATOR.
* '\u001D', GROUP SEPARATOR.
* '\u001E', RECORD SEPARATOR.
* '\u001F', UNIT SEPARATOR.
* true if the character is a Java whitespace
* character; false otherwise.
* @see java.lang.Character#isSpaceChar(int)
* @since 1.5
*/
public static boolean isWhitespace(int codePoint) {
return CharacterData.of(codePoint).isWhitespace(codePoint);
}
/**
* Determines if the specified character is an ISO control
* character. A character is considered to be an ISO control
* character if its code is in the range '\u0000'
* through '\u001F' or in the range
* '\u007F' through '\u009F'.
*
* true if the character is an ISO control character;
* false otherwise.
*
* @see java.lang.Character#isSpaceChar(char)
* @see java.lang.Character#isWhitespace(char)
* @since 1.1
*/
public static boolean isISOControl(char ch) {
return isISOControl((int)ch);
}
/**
* Determines if the referenced character (Unicode code point) is an ISO control
* character. A character is considered to be an ISO control
* character if its code is in the range '\u0000'
* through '\u001F' or in the range
* '\u007F' through '\u009F'.
*
* @param codePoint the character (Unicode code point) to be tested.
* @return true if the character is an ISO control character;
* false otherwise.
* @see java.lang.Character#isSpaceChar(int)
* @see java.lang.Character#isWhitespace(int)
* @since 1.5
*/
public static boolean isISOControl(int codePoint) {
return (codePoint >= 0x0000 && codePoint <= 0x001F) ||
(codePoint >= 0x007F && codePoint <= 0x009F);
}
/**
* Returns a value indicating a character's general category.
*
* int representing the
* character's general category.
* @see java.lang.Character#COMBINING_SPACING_MARK
* @see java.lang.Character#CONNECTOR_PUNCTUATION
* @see java.lang.Character#CONTROL
* @see java.lang.Character#CURRENCY_SYMBOL
* @see java.lang.Character#DASH_PUNCTUATION
* @see java.lang.Character#DECIMAL_DIGIT_NUMBER
* @see java.lang.Character#ENCLOSING_MARK
* @see java.lang.Character#END_PUNCTUATION
* @see java.lang.Character#FINAL_QUOTE_PUNCTUATION
* @see java.lang.Character#FORMAT
* @see java.lang.Character#INITIAL_QUOTE_PUNCTUATION
* @see java.lang.Character#LETTER_NUMBER
* @see java.lang.Character#LINE_SEPARATOR
* @see java.lang.Character#LOWERCASE_LETTER
* @see java.lang.Character#MATH_SYMBOL
* @see java.lang.Character#MODIFIER_LETTER
* @see java.lang.Character#MODIFIER_SYMBOL
* @see java.lang.Character#NON_SPACING_MARK
* @see java.lang.Character#OTHER_LETTER
* @see java.lang.Character#OTHER_NUMBER
* @see java.lang.Character#OTHER_PUNCTUATION
* @see java.lang.Character#OTHER_SYMBOL
* @see java.lang.Character#PARAGRAPH_SEPARATOR
* @see java.lang.Character#PRIVATE_USE
* @see java.lang.Character#SPACE_SEPARATOR
* @see java.lang.Character#START_PUNCTUATION
* @see java.lang.Character#SURROGATE
* @see java.lang.Character#TITLECASE_LETTER
* @see java.lang.Character#UNASSIGNED
* @see java.lang.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 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 radix is not a
* valid radix, or the value of digit is not a valid
* digit in the specified radix, the null character
* ('\u0000') is returned.
* radix argument is valid if it is greater than or
* equal to MIN_RADIX and less than or equal to
* MAX_RADIX. The digit argument is valid if
* 0 <=digit < radix.
* '0' + digit is returned. Otherwise, the value
* 'a' + digit - 10 is returned.
*
* @param digit the number to convert to a character.
* @param radix the radix.
* @return the char representation of the specified digit
* in the specified radix.
* @see java.lang.Character#MIN_RADIX
* @see java.lang.Character#MAX_RADIX
* @see java.lang.Character#digit(char, int)
*/
public static char forDigit(int digit, int radix) {
if ((digit >= radix) || (digit < 0)) {
return '\0';
}
if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
return '\0';
}
if (digit < 10) {
return (char)('0' + digit);
}
return (char)('a' - 10 + digit);
}
/**
* 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
* char values is DIRECTIONALITY_UNDEFINED.
*
* char for which the directionality property
* is requested.
* @return the directionality property of the 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, '\u0028' 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.
*
* char for which the mirrored property is requested
* @return true if the char is mirrored, false
* if the 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,
* '\u0028' 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 true if the character is mirrored, 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 Character objects numerically.
*
* @param anotherCharacter the Character to be compared.
* @return the value 0 if the argument Character
* is equal to this Character; a value less than
* 0 if this Character is numerically less
* than the Character argument; and a value greater than
* 0 if this Character is numerically greater
* than the Character argument (unsigned comparison).
* Note that this is strictly a numerical comparison; it is not
* locale-dependent.
* @since 1.2
*/
public int compareTo(Character anotherCharacter) {
return this.value - anotherCharacter.value;
}
/**
* Converts the character (Unicode code point) argument to uppercase using
* information from the UnicodeData file.
* Character.ERROR)
* that indicates that a 1:M char mapping exists.
* @see java.lang.Character#isLowerCase(char)
* @see java.lang.Character#isUpperCase(char)
* @see java.lang.Character#toLowerCase(char)
* @see java.lang.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 char itself is returned in the
* char[].
*
* @param codePoint the character (Unicode code point) to be converted.
* @return a char[] with the uppercased character.
* @since 1.4
*/
static char[] toUpperCaseCharArray(int codePoint) {
// As of Unicode 4.0, 1:M uppercasings only happen in the BMP.
assert isValidCodePoint(codePoint) &&
!isSupplementaryCodePoint(codePoint);
return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint);
}
/**
* The number of bits used to represent a char value in unsigned
* binary form.
*
* @since 1.5
*/
public static final int SIZE = 16;
/**
* Returns the value obtained by reversing the order of the bytes in the
* specified char value.
*
* @return the value obtained by reversing (or, equivalently, swapping)
* the bytes in the specified char value.
* @since 1.5
*/
public static char reverseBytes(char ch) {
return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
}
}