jaroslav@68: /* jaroslav@68: * Copyright (c) 2002, 2010, Oracle and/or its affiliates. All rights reserved. jaroslav@68: * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. jaroslav@68: * jaroslav@68: * This code is free software; you can redistribute it and/or modify it jaroslav@68: * under the terms of the GNU General Public License version 2 only, as jaroslav@68: * published by the Free Software Foundation. Oracle designates this jaroslav@68: * particular file as subject to the "Classpath" exception as provided jaroslav@68: * by Oracle in the LICENSE file that accompanied this code. jaroslav@68: * jaroslav@68: * This code is distributed in the hope that it will be useful, but WITHOUT jaroslav@68: * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or jaroslav@68: * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License jaroslav@68: * version 2 for more details (a copy is included in the LICENSE file that jaroslav@68: * accompanied this code). jaroslav@68: * jaroslav@68: * You should have received a copy of the GNU General Public License version jaroslav@68: * 2 along with this work; if not, write to the Free Software Foundation, jaroslav@68: * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. jaroslav@68: * jaroslav@68: * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA jaroslav@68: * or visit www.oracle.com if you need additional information or have any jaroslav@68: * questions. jaroslav@68: */ jaroslav@68: jaroslav@68: package java.lang; jaroslav@68: jaroslav@68: import java.util.Arrays; jaroslav@68: import java.util.Map; jaroslav@68: import java.util.HashMap; jaroslav@68: import java.util.Locale; jaroslav@68: jaroslav@68: /** jaroslav@68: * The {@code Character} class wraps a value of the primitive jaroslav@68: * type {@code char} in an object. An object of type jaroslav@68: * {@code Character} contains a single field whose type is jaroslav@68: * {@code char}. jaroslav@68: *

jaroslav@68: * In addition, this class provides several methods for determining jaroslav@68: * a character's category (lowercase letter, digit, etc.) and for converting jaroslav@68: * characters from uppercase to lowercase and vice versa. jaroslav@68: *

jaroslav@68: * Character information is based on the Unicode Standard, version 6.0.0. jaroslav@68: *

jaroslav@68: * The methods and data of class {@code Character} are defined by jaroslav@68: * the information in the UnicodeData file that is part of the jaroslav@68: * Unicode Character Database maintained by the Unicode jaroslav@68: * Consortium. This file specifies various properties including name jaroslav@68: * and general category for every defined Unicode code point or jaroslav@68: * character range. jaroslav@68: *

jaroslav@68: * The file and its description are available from the Unicode Consortium at: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Unicode Character Representations

jaroslav@68: * jaroslav@68: *

The {@code char} data type (and therefore the value that a jaroslav@68: * {@code Character} object encapsulates) are based on the jaroslav@68: * original Unicode specification, which defined characters as jaroslav@68: * fixed-width 16-bit entities. The Unicode Standard has since been jaroslav@68: * changed to allow for characters whose representation requires more jaroslav@68: * than 16 bits. The range of legal code points is now jaroslav@68: * U+0000 to U+10FFFF, known as Unicode scalar value. jaroslav@68: * (Refer to the jaroslav@68: * definition of the U+n notation in the Unicode jaroslav@68: * Standard.) jaroslav@68: * jaroslav@68: *

The set of characters from U+0000 to U+FFFF is jaroslav@68: * sometimes referred to as the Basic Multilingual Plane (BMP). jaroslav@68: * Characters whose code points are greater jaroslav@68: * than U+FFFF are called supplementary characters. The Java jaroslav@68: * platform uses the UTF-16 representation in {@code char} arrays and jaroslav@68: * in the {@code String} and {@code StringBuffer} classes. In jaroslav@68: * this representation, supplementary characters are represented as a pair jaroslav@68: * of {@code char} values, the first from the high-surrogates jaroslav@68: * range, (\uD800-\uDBFF), the second from the jaroslav@68: * low-surrogates range (\uDC00-\uDFFF). jaroslav@68: * jaroslav@68: *

A {@code char} value, therefore, represents Basic jaroslav@68: * Multilingual Plane (BMP) code points, including the surrogate jaroslav@68: * code points, or code units of the UTF-16 encoding. An jaroslav@68: * {@code int} value represents all Unicode code points, jaroslav@68: * including supplementary code points. The lower (least significant) jaroslav@68: * 21 bits of {@code int} are used to represent Unicode code jaroslav@68: * points and the upper (most significant) 11 bits must be zero. jaroslav@68: * Unless otherwise specified, the behavior with respect to jaroslav@68: * supplementary characters and surrogate {@code char} values is jaroslav@68: * as follows: jaroslav@68: * jaroslav@68: *

jaroslav@68: * jaroslav@68: *

In the Java SE API documentation, Unicode code point is jaroslav@68: * used for character values in the range between U+0000 and U+10FFFF, jaroslav@68: * and Unicode code unit is used for 16-bit jaroslav@68: * {@code char} values that are code units of the UTF-16 jaroslav@68: * encoding. For more information on Unicode terminology, refer to the jaroslav@68: * Unicode Glossary. jaroslav@68: * jaroslav@68: * @author Lee Boynton jaroslav@68: * @author Guy Steele jaroslav@68: * @author Akira Tanaka jaroslav@68: * @author Martin Buchholz jaroslav@68: * @author Ulf Zibis jaroslav@68: * @since 1.0 jaroslav@68: */ jaroslav@68: public final jaroslav@68: class Character implements java.io.Serializable, Comparable { jaroslav@68: /** jaroslav@68: * The minimum radix available for conversion to and from strings. jaroslav@68: * The constant value of this field is the smallest value permitted jaroslav@68: * for the radix argument in radix-conversion methods such as the jaroslav@68: * {@code digit} method, the {@code forDigit} method, and the jaroslav@68: * {@code toString} method of class {@code Integer}. jaroslav@68: * jaroslav@68: * @see Character#digit(char, int) jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Integer#toString(int, int) jaroslav@68: * @see Integer#valueOf(String) jaroslav@68: */ jaroslav@68: public static final int MIN_RADIX = 2; jaroslav@68: jaroslav@68: /** jaroslav@68: * The maximum radix available for conversion to and from strings. jaroslav@68: * The constant value of this field is the largest value permitted jaroslav@68: * for the radix argument in radix-conversion methods such as the jaroslav@68: * {@code digit} method, the {@code forDigit} method, and the jaroslav@68: * {@code toString} method of class {@code Integer}. jaroslav@68: * jaroslav@68: * @see Character#digit(char, int) jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Integer#toString(int, int) jaroslav@68: * @see Integer#valueOf(String) jaroslav@68: */ jaroslav@68: public static final int MAX_RADIX = 36; jaroslav@68: jaroslav@68: /** jaroslav@68: * The constant value of this field is the smallest value of type jaroslav@68: * {@code char}, {@code '\u005Cu0000'}. jaroslav@68: * jaroslav@68: * @since 1.0.2 jaroslav@68: */ jaroslav@68: public static final char MIN_VALUE = '\u0000'; jaroslav@68: jaroslav@68: /** jaroslav@68: * The constant value of this field is the largest value of type jaroslav@68: * {@code char}, {@code '\u005CuFFFF'}. jaroslav@68: * jaroslav@68: * @since 1.0.2 jaroslav@68: */ jaroslav@68: public static final char MAX_VALUE = '\uFFFF'; jaroslav@68: jaroslav@68: /** jaroslav@68: * The {@code Class} instance representing the primitive type jaroslav@68: * {@code char}. jaroslav@68: * jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: @SuppressWarnings("unchecked") jaroslav@68: public static final Class TYPE = Class.getPrimitiveClass("char"); jaroslav@68: jaroslav@68: /* jaroslav@68: * Normative general types jaroslav@68: */ jaroslav@68: jaroslav@68: /* jaroslav@68: * General character types jaroslav@68: */ jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Cn" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte UNASSIGNED = 0; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Lu" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte UPPERCASE_LETTER = 1; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Ll" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte LOWERCASE_LETTER = 2; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Lt" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte TITLECASE_LETTER = 3; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Lm" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte MODIFIER_LETTER = 4; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Lo" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte OTHER_LETTER = 5; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Mn" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte NON_SPACING_MARK = 6; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Me" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte ENCLOSING_MARK = 7; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Mc" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte COMBINING_SPACING_MARK = 8; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Nd" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte DECIMAL_DIGIT_NUMBER = 9; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Nl" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte LETTER_NUMBER = 10; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "No" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte OTHER_NUMBER = 11; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Zs" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte SPACE_SEPARATOR = 12; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Zl" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte LINE_SEPARATOR = 13; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Zp" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte PARAGRAPH_SEPARATOR = 14; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Cc" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte CONTROL = 15; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Cf" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte FORMAT = 16; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Co" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte PRIVATE_USE = 18; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Cs" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte SURROGATE = 19; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Pd" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte DASH_PUNCTUATION = 20; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Ps" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte START_PUNCTUATION = 21; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Pe" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte END_PUNCTUATION = 22; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Pc" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte CONNECTOR_PUNCTUATION = 23; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Po" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte OTHER_PUNCTUATION = 24; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Sm" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte MATH_SYMBOL = 25; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Sc" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte CURRENCY_SYMBOL = 26; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Sk" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte MODIFIER_SYMBOL = 27; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "So" in the Unicode specification. jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static final byte OTHER_SYMBOL = 28; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Pi" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte INITIAL_QUOTE_PUNCTUATION = 29; jaroslav@68: jaroslav@68: /** jaroslav@68: * General category "Pf" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte FINAL_QUOTE_PUNCTUATION = 30; jaroslav@68: jaroslav@68: /** jaroslav@68: * Error flag. Use int (code point) to avoid confusion with U+FFFF. jaroslav@68: */ jaroslav@68: static final int ERROR = 0xFFFFFFFF; jaroslav@68: jaroslav@68: jaroslav@68: /** jaroslav@68: * Undefined bidirectional character type. Undefined {@code char} jaroslav@68: * values have undefined directionality in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_UNDEFINED = -1; jaroslav@68: jaroslav@68: /** jaroslav@68: * Strong bidirectional character type "L" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0; jaroslav@68: jaroslav@68: /** jaroslav@68: * Strong bidirectional character type "R" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1; jaroslav@68: jaroslav@68: /** jaroslav@68: * Strong bidirectional character type "AL" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "EN" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "ES" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "ET" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "AN" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "CS" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "NSM" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_NONSPACING_MARK = 8; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "BN" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9; jaroslav@68: jaroslav@68: /** jaroslav@68: * Neutral bidirectional character type "B" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10; jaroslav@68: jaroslav@68: /** jaroslav@68: * Neutral bidirectional character type "S" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11; jaroslav@68: jaroslav@68: /** jaroslav@68: * Neutral bidirectional character type "WS" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_WHITESPACE = 12; jaroslav@68: jaroslav@68: /** jaroslav@68: * Neutral bidirectional character type "ON" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13; jaroslav@68: jaroslav@68: /** jaroslav@68: * Strong bidirectional character type "LRE" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14; jaroslav@68: jaroslav@68: /** jaroslav@68: * Strong bidirectional character type "LRO" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15; jaroslav@68: jaroslav@68: /** jaroslav@68: * Strong bidirectional character type "RLE" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16; jaroslav@68: jaroslav@68: /** jaroslav@68: * Strong bidirectional character type "RLO" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17; jaroslav@68: jaroslav@68: /** jaroslav@68: * Weak bidirectional character type "PDF" in the Unicode specification. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18; jaroslav@68: jaroslav@68: /** jaroslav@68: * The minimum value of a jaroslav@68: * jaroslav@68: * Unicode high-surrogate code unit jaroslav@68: * in the UTF-16 encoding, constant {@code '\u005CuD800'}. jaroslav@68: * A high-surrogate is also known as a leading-surrogate. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final char MIN_HIGH_SURROGATE = '\uD800'; jaroslav@68: jaroslav@68: /** jaroslav@68: * The maximum value of a jaroslav@68: * jaroslav@68: * Unicode high-surrogate code unit jaroslav@68: * in the UTF-16 encoding, constant {@code '\u005CuDBFF'}. jaroslav@68: * A high-surrogate is also known as a leading-surrogate. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final char MAX_HIGH_SURROGATE = '\uDBFF'; jaroslav@68: jaroslav@68: /** jaroslav@68: * The minimum value of a jaroslav@68: * jaroslav@68: * Unicode low-surrogate code unit jaroslav@68: * in the UTF-16 encoding, constant {@code '\u005CuDC00'}. jaroslav@68: * A low-surrogate is also known as a trailing-surrogate. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final char MIN_LOW_SURROGATE = '\uDC00'; jaroslav@68: jaroslav@68: /** jaroslav@68: * The maximum value of a jaroslav@68: * jaroslav@68: * Unicode low-surrogate code unit jaroslav@68: * in the UTF-16 encoding, constant {@code '\u005CuDFFF'}. jaroslav@68: * A low-surrogate is also known as a trailing-surrogate. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final char MAX_LOW_SURROGATE = '\uDFFF'; jaroslav@68: jaroslav@68: /** jaroslav@68: * The minimum value of a Unicode surrogate code unit in the jaroslav@68: * UTF-16 encoding, constant {@code '\u005CuD800'}. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE; jaroslav@68: jaroslav@68: /** jaroslav@68: * The maximum value of a Unicode surrogate code unit in the jaroslav@68: * UTF-16 encoding, constant {@code '\u005CuDFFF'}. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final char MAX_SURROGATE = MAX_LOW_SURROGATE; jaroslav@68: jaroslav@68: /** jaroslav@68: * The minimum value of a jaroslav@68: * jaroslav@68: * Unicode supplementary code point, constant {@code U+10000}. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000; jaroslav@68: jaroslav@68: /** jaroslav@68: * The minimum value of a jaroslav@68: * jaroslav@68: * Unicode code point, constant {@code U+0000}. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final int MIN_CODE_POINT = 0x000000; jaroslav@68: jaroslav@68: /** jaroslav@68: * The maximum value of a jaroslav@68: * jaroslav@68: * Unicode code point, constant {@code U+10FFFF}. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final int MAX_CODE_POINT = 0X10FFFF; jaroslav@68: jaroslav@68: jaroslav@68: /** jaroslav@68: * Instances of this class represent particular subsets of the Unicode jaroslav@68: * character set. The only family of subsets defined in the jaroslav@68: * {@code Character} class is {@link Character.UnicodeBlock}. jaroslav@68: * Other portions of the Java API may define other subsets for their jaroslav@68: * own purposes. jaroslav@68: * jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static class Subset { jaroslav@68: jaroslav@68: private String name; jaroslav@68: jaroslav@68: /** jaroslav@68: * Constructs a new {@code Subset} instance. jaroslav@68: * jaroslav@68: * @param name The name of this subset jaroslav@68: * @exception NullPointerException if name is {@code null} jaroslav@68: */ jaroslav@68: protected Subset(String name) { jaroslav@68: if (name == null) { jaroslav@68: throw new NullPointerException("name"); jaroslav@68: } jaroslav@68: this.name = name; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Compares two {@code Subset} objects for equality. jaroslav@68: * This method returns {@code true} if and only if jaroslav@68: * {@code this} and the argument refer to the same jaroslav@68: * object; since this method is {@code final}, this jaroslav@68: * guarantee holds for all subclasses. jaroslav@68: */ jaroslav@68: public final boolean equals(Object obj) { jaroslav@68: return (this == obj); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the standard hash code as defined by the jaroslav@68: * {@link Object#hashCode} method. This method jaroslav@68: * is {@code final} in order to ensure that the jaroslav@68: * {@code equals} and {@code hashCode} methods will jaroslav@68: * be consistent in all subclasses. jaroslav@68: */ jaroslav@68: public final int hashCode() { jaroslav@68: return super.hashCode(); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the name of this subset. jaroslav@68: */ jaroslav@68: public final String toString() { jaroslav@68: return name; jaroslav@68: } jaroslav@68: } jaroslav@68: jaroslav@68: // See http://www.unicode.org/Public/UNIDATA/Blocks.txt jaroslav@68: // for the latest specification of Unicode Blocks. jaroslav@68: jaroslav@68: /** jaroslav@68: * A family of character subsets representing the character blocks in the jaroslav@68: * Unicode specification. Character blocks generally define characters jaroslav@68: * used for a specific script or purpose. A character is contained by jaroslav@68: * at most one Unicode block. jaroslav@68: * jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final class UnicodeBlock extends Subset { jaroslav@68: jaroslav@68: private static Map map = new HashMap<>(256); jaroslav@68: jaroslav@68: /** jaroslav@68: * Creates a UnicodeBlock with the given identifier name. jaroslav@68: * This name must be the same as the block identifier. jaroslav@68: */ jaroslav@68: private UnicodeBlock(String idName) { jaroslav@68: super(idName); jaroslav@68: map.put(idName, this); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Creates a UnicodeBlock with the given identifier name and jaroslav@68: * alias name. jaroslav@68: */ jaroslav@68: private UnicodeBlock(String idName, String alias) { jaroslav@68: this(idName); jaroslav@68: map.put(alias, this); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Creates a UnicodeBlock with the given identifier name and jaroslav@68: * alias names. jaroslav@68: */ jaroslav@68: private UnicodeBlock(String idName, String... aliases) { jaroslav@68: this(idName); jaroslav@68: for (String alias : aliases) jaroslav@68: map.put(alias, this); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Basic Latin" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BASIC_LATIN = jaroslav@68: new UnicodeBlock("BASIC_LATIN", jaroslav@68: "BASIC LATIN", jaroslav@68: "BASICLATIN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Latin-1 Supplement" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LATIN_1_SUPPLEMENT = jaroslav@68: new UnicodeBlock("LATIN_1_SUPPLEMENT", jaroslav@68: "LATIN-1 SUPPLEMENT", jaroslav@68: "LATIN-1SUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Latin Extended-A" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LATIN_EXTENDED_A = jaroslav@68: new UnicodeBlock("LATIN_EXTENDED_A", jaroslav@68: "LATIN EXTENDED-A", jaroslav@68: "LATINEXTENDED-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Latin Extended-B" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LATIN_EXTENDED_B = jaroslav@68: new UnicodeBlock("LATIN_EXTENDED_B", jaroslav@68: "LATIN EXTENDED-B", jaroslav@68: "LATINEXTENDED-B"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "IPA Extensions" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock IPA_EXTENSIONS = jaroslav@68: new UnicodeBlock("IPA_EXTENSIONS", jaroslav@68: "IPA EXTENSIONS", jaroslav@68: "IPAEXTENSIONS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Spacing Modifier Letters" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SPACING_MODIFIER_LETTERS = jaroslav@68: new UnicodeBlock("SPACING_MODIFIER_LETTERS", jaroslav@68: "SPACING MODIFIER LETTERS", jaroslav@68: "SPACINGMODIFIERLETTERS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Combining Diacritical Marks" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS = jaroslav@68: new UnicodeBlock("COMBINING_DIACRITICAL_MARKS", jaroslav@68: "COMBINING DIACRITICAL MARKS", jaroslav@68: "COMBININGDIACRITICALMARKS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Greek and Coptic" Unicode character block. jaroslav@68: *

jaroslav@68: * This block was previously known as the "Greek" block. jaroslav@68: * jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GREEK = jaroslav@68: new UnicodeBlock("GREEK", jaroslav@68: "GREEK AND COPTIC", jaroslav@68: "GREEKANDCOPTIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cyrillic" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CYRILLIC = jaroslav@68: new UnicodeBlock("CYRILLIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Armenian" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ARMENIAN = jaroslav@68: new UnicodeBlock("ARMENIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hebrew" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HEBREW = jaroslav@68: new UnicodeBlock("HEBREW"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Arabic" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ARABIC = jaroslav@68: new UnicodeBlock("ARABIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Devanagari" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock DEVANAGARI = jaroslav@68: new UnicodeBlock("DEVANAGARI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Bengali" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BENGALI = jaroslav@68: new UnicodeBlock("BENGALI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Gurmukhi" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GURMUKHI = jaroslav@68: new UnicodeBlock("GURMUKHI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Gujarati" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GUJARATI = jaroslav@68: new UnicodeBlock("GUJARATI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Oriya" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ORIYA = jaroslav@68: new UnicodeBlock("ORIYA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tamil" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAMIL = jaroslav@68: new UnicodeBlock("TAMIL"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Telugu" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TELUGU = jaroslav@68: new UnicodeBlock("TELUGU"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Kannada" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KANNADA = jaroslav@68: new UnicodeBlock("KANNADA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Malayalam" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MALAYALAM = jaroslav@68: new UnicodeBlock("MALAYALAM"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Thai" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock THAI = jaroslav@68: new UnicodeBlock("THAI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Lao" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LAO = jaroslav@68: new UnicodeBlock("LAO"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tibetan" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TIBETAN = jaroslav@68: new UnicodeBlock("TIBETAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Georgian" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GEORGIAN = jaroslav@68: new UnicodeBlock("GEORGIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hangul Jamo" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HANGUL_JAMO = jaroslav@68: new UnicodeBlock("HANGUL_JAMO", jaroslav@68: "HANGUL JAMO", jaroslav@68: "HANGULJAMO"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Latin Extended Additional" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL = jaroslav@68: new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL", jaroslav@68: "LATIN EXTENDED ADDITIONAL", jaroslav@68: "LATINEXTENDEDADDITIONAL"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Greek Extended" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GREEK_EXTENDED = jaroslav@68: new UnicodeBlock("GREEK_EXTENDED", jaroslav@68: "GREEK EXTENDED", jaroslav@68: "GREEKEXTENDED"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "General Punctuation" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GENERAL_PUNCTUATION = jaroslav@68: new UnicodeBlock("GENERAL_PUNCTUATION", jaroslav@68: "GENERAL PUNCTUATION", jaroslav@68: "GENERALPUNCTUATION"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Superscripts and Subscripts" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS = jaroslav@68: new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS", jaroslav@68: "SUPERSCRIPTS AND SUBSCRIPTS", jaroslav@68: "SUPERSCRIPTSANDSUBSCRIPTS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Currency Symbols" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CURRENCY_SYMBOLS = jaroslav@68: new UnicodeBlock("CURRENCY_SYMBOLS", jaroslav@68: "CURRENCY SYMBOLS", jaroslav@68: "CURRENCYSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Combining Diacritical Marks for Symbols" Unicode jaroslav@68: * character block. jaroslav@68: *

jaroslav@68: * This block was previously known as "Combining Marks for Symbols". jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS = jaroslav@68: new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS", jaroslav@68: "COMBINING DIACRITICAL MARKS FOR SYMBOLS", jaroslav@68: "COMBININGDIACRITICALMARKSFORSYMBOLS", jaroslav@68: "COMBINING MARKS FOR SYMBOLS", jaroslav@68: "COMBININGMARKSFORSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Letterlike Symbols" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LETTERLIKE_SYMBOLS = jaroslav@68: new UnicodeBlock("LETTERLIKE_SYMBOLS", jaroslav@68: "LETTERLIKE SYMBOLS", jaroslav@68: "LETTERLIKESYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Number Forms" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock NUMBER_FORMS = jaroslav@68: new UnicodeBlock("NUMBER_FORMS", jaroslav@68: "NUMBER FORMS", jaroslav@68: "NUMBERFORMS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Arrows" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ARROWS = jaroslav@68: new UnicodeBlock("ARROWS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Mathematical Operators" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MATHEMATICAL_OPERATORS = jaroslav@68: new UnicodeBlock("MATHEMATICAL_OPERATORS", jaroslav@68: "MATHEMATICAL OPERATORS", jaroslav@68: "MATHEMATICALOPERATORS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Miscellaneous Technical" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MISCELLANEOUS_TECHNICAL = jaroslav@68: new UnicodeBlock("MISCELLANEOUS_TECHNICAL", jaroslav@68: "MISCELLANEOUS TECHNICAL", jaroslav@68: "MISCELLANEOUSTECHNICAL"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Control Pictures" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CONTROL_PICTURES = jaroslav@68: new UnicodeBlock("CONTROL_PICTURES", jaroslav@68: "CONTROL PICTURES", jaroslav@68: "CONTROLPICTURES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Optical Character Recognition" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION = jaroslav@68: new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION", jaroslav@68: "OPTICAL CHARACTER RECOGNITION", jaroslav@68: "OPTICALCHARACTERRECOGNITION"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Enclosed Alphanumerics" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ENCLOSED_ALPHANUMERICS = jaroslav@68: new UnicodeBlock("ENCLOSED_ALPHANUMERICS", jaroslav@68: "ENCLOSED ALPHANUMERICS", jaroslav@68: "ENCLOSEDALPHANUMERICS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Box Drawing" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BOX_DRAWING = jaroslav@68: new UnicodeBlock("BOX_DRAWING", jaroslav@68: "BOX DRAWING", jaroslav@68: "BOXDRAWING"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Block Elements" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BLOCK_ELEMENTS = jaroslav@68: new UnicodeBlock("BLOCK_ELEMENTS", jaroslav@68: "BLOCK ELEMENTS", jaroslav@68: "BLOCKELEMENTS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Geometric Shapes" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GEOMETRIC_SHAPES = jaroslav@68: new UnicodeBlock("GEOMETRIC_SHAPES", jaroslav@68: "GEOMETRIC SHAPES", jaroslav@68: "GEOMETRICSHAPES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Miscellaneous Symbols" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MISCELLANEOUS_SYMBOLS = jaroslav@68: new UnicodeBlock("MISCELLANEOUS_SYMBOLS", jaroslav@68: "MISCELLANEOUS SYMBOLS", jaroslav@68: "MISCELLANEOUSSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Dingbats" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock DINGBATS = jaroslav@68: new UnicodeBlock("DINGBATS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Symbols and Punctuation" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION = jaroslav@68: new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION", jaroslav@68: "CJK SYMBOLS AND PUNCTUATION", jaroslav@68: "CJKSYMBOLSANDPUNCTUATION"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hiragana" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HIRAGANA = jaroslav@68: new UnicodeBlock("HIRAGANA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Katakana" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KATAKANA = jaroslav@68: new UnicodeBlock("KATAKANA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Bopomofo" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BOPOMOFO = jaroslav@68: new UnicodeBlock("BOPOMOFO"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hangul Compatibility Jamo" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO = jaroslav@68: new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO", jaroslav@68: "HANGUL COMPATIBILITY JAMO", jaroslav@68: "HANGULCOMPATIBILITYJAMO"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Kanbun" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KANBUN = jaroslav@68: new UnicodeBlock("KANBUN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Enclosed CJK Letters and Months" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS = jaroslav@68: new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS", jaroslav@68: "ENCLOSED CJK LETTERS AND MONTHS", jaroslav@68: "ENCLOSEDCJKLETTERSANDMONTHS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Compatibility" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_COMPATIBILITY = jaroslav@68: new UnicodeBlock("CJK_COMPATIBILITY", jaroslav@68: "CJK COMPATIBILITY", jaroslav@68: "CJKCOMPATIBILITY"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Unified Ideographs" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS = jaroslav@68: new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS", jaroslav@68: "CJK UNIFIED IDEOGRAPHS", jaroslav@68: "CJKUNIFIEDIDEOGRAPHS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hangul Syllables" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HANGUL_SYLLABLES = jaroslav@68: new UnicodeBlock("HANGUL_SYLLABLES", jaroslav@68: "HANGUL SYLLABLES", jaroslav@68: "HANGULSYLLABLES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Private Use Area" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock PRIVATE_USE_AREA = jaroslav@68: new UnicodeBlock("PRIVATE_USE_AREA", jaroslav@68: "PRIVATE USE AREA", jaroslav@68: "PRIVATEUSEAREA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Compatibility Ideographs" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS = jaroslav@68: new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS", jaroslav@68: "CJK COMPATIBILITY IDEOGRAPHS", jaroslav@68: "CJKCOMPATIBILITYIDEOGRAPHS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Alphabetic Presentation Forms" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS = jaroslav@68: new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS", jaroslav@68: "ALPHABETIC PRESENTATION FORMS", jaroslav@68: "ALPHABETICPRESENTATIONFORMS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Arabic Presentation Forms-A" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A = jaroslav@68: new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A", jaroslav@68: "ARABIC PRESENTATION FORMS-A", jaroslav@68: "ARABICPRESENTATIONFORMS-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Combining Half Marks" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock COMBINING_HALF_MARKS = jaroslav@68: new UnicodeBlock("COMBINING_HALF_MARKS", jaroslav@68: "COMBINING HALF MARKS", jaroslav@68: "COMBININGHALFMARKS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Compatibility Forms" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_COMPATIBILITY_FORMS = jaroslav@68: new UnicodeBlock("CJK_COMPATIBILITY_FORMS", jaroslav@68: "CJK COMPATIBILITY FORMS", jaroslav@68: "CJKCOMPATIBILITYFORMS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Small Form Variants" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SMALL_FORM_VARIANTS = jaroslav@68: new UnicodeBlock("SMALL_FORM_VARIANTS", jaroslav@68: "SMALL FORM VARIANTS", jaroslav@68: "SMALLFORMVARIANTS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Arabic Presentation Forms-B" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B = jaroslav@68: new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B", jaroslav@68: "ARABIC PRESENTATION FORMS-B", jaroslav@68: "ARABICPRESENTATIONFORMS-B"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Halfwidth and Fullwidth Forms" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS = jaroslav@68: new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS", jaroslav@68: "HALFWIDTH AND FULLWIDTH FORMS", jaroslav@68: "HALFWIDTHANDFULLWIDTHFORMS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Specials" Unicode character block. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SPECIALS = jaroslav@68: new UnicodeBlock("SPECIALS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * @deprecated As of J2SE 5, use {@link #HIGH_SURROGATES}, jaroslav@68: * {@link #HIGH_PRIVATE_USE_SURROGATES}, and jaroslav@68: * {@link #LOW_SURROGATES}. These new constants match jaroslav@68: * the block definitions of the Unicode Standard. jaroslav@68: * The {@link #of(char)} and {@link #of(int)} methods jaroslav@68: * return the new constants, not SURROGATES_AREA. jaroslav@68: */ jaroslav@68: @Deprecated jaroslav@68: public static final UnicodeBlock SURROGATES_AREA = jaroslav@68: new UnicodeBlock("SURROGATES_AREA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Syriac" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SYRIAC = jaroslav@68: new UnicodeBlock("SYRIAC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Thaana" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock THAANA = jaroslav@68: new UnicodeBlock("THAANA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Sinhala" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SINHALA = jaroslav@68: new UnicodeBlock("SINHALA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Myanmar" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MYANMAR = jaroslav@68: new UnicodeBlock("MYANMAR"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ethiopic" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ETHIOPIC = jaroslav@68: new UnicodeBlock("ETHIOPIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cherokee" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CHEROKEE = jaroslav@68: new UnicodeBlock("CHEROKEE"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = jaroslav@68: new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS", jaroslav@68: "UNIFIED CANADIAN ABORIGINAL SYLLABICS", jaroslav@68: "UNIFIEDCANADIANABORIGINALSYLLABICS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ogham" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OGHAM = jaroslav@68: new UnicodeBlock("OGHAM"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Runic" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock RUNIC = jaroslav@68: new UnicodeBlock("RUNIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Khmer" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KHMER = jaroslav@68: new UnicodeBlock("KHMER"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Mongolian" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MONGOLIAN = jaroslav@68: new UnicodeBlock("MONGOLIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Braille Patterns" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BRAILLE_PATTERNS = jaroslav@68: new UnicodeBlock("BRAILLE_PATTERNS", jaroslav@68: "BRAILLE PATTERNS", jaroslav@68: "BRAILLEPATTERNS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Radicals Supplement" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT = jaroslav@68: new UnicodeBlock("CJK_RADICALS_SUPPLEMENT", jaroslav@68: "CJK RADICALS SUPPLEMENT", jaroslav@68: "CJKRADICALSSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Kangxi Radicals" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KANGXI_RADICALS = jaroslav@68: new UnicodeBlock("KANGXI_RADICALS", jaroslav@68: "KANGXI RADICALS", jaroslav@68: "KANGXIRADICALS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ideographic Description Characters" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS = jaroslav@68: new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS", jaroslav@68: "IDEOGRAPHIC DESCRIPTION CHARACTERS", jaroslav@68: "IDEOGRAPHICDESCRIPTIONCHARACTERS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Bopomofo Extended" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BOPOMOFO_EXTENDED = jaroslav@68: new UnicodeBlock("BOPOMOFO_EXTENDED", jaroslav@68: "BOPOMOFO EXTENDED", jaroslav@68: "BOPOMOFOEXTENDED"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Unified Ideographs Extension A" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = jaroslav@68: new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A", jaroslav@68: "CJK UNIFIED IDEOGRAPHS EXTENSION A", jaroslav@68: "CJKUNIFIEDIDEOGRAPHSEXTENSIONA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Yi Syllables" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock YI_SYLLABLES = jaroslav@68: new UnicodeBlock("YI_SYLLABLES", jaroslav@68: "YI SYLLABLES", jaroslav@68: "YISYLLABLES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Yi Radicals" Unicode character block. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock YI_RADICALS = jaroslav@68: new UnicodeBlock("YI_RADICALS", jaroslav@68: "YI RADICALS", jaroslav@68: "YIRADICALS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cyrillic Supplementary" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY = jaroslav@68: new UnicodeBlock("CYRILLIC_SUPPLEMENTARY", jaroslav@68: "CYRILLIC SUPPLEMENTARY", jaroslav@68: "CYRILLICSUPPLEMENTARY", jaroslav@68: "CYRILLIC SUPPLEMENT", jaroslav@68: "CYRILLICSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tagalog" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAGALOG = jaroslav@68: new UnicodeBlock("TAGALOG"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hanunoo" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HANUNOO = jaroslav@68: new UnicodeBlock("HANUNOO"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Buhid" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BUHID = jaroslav@68: new UnicodeBlock("BUHID"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tagbanwa" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAGBANWA = jaroslav@68: new UnicodeBlock("TAGBANWA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Limbu" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LIMBU = jaroslav@68: new UnicodeBlock("LIMBU"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tai Le" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAI_LE = jaroslav@68: new UnicodeBlock("TAI_LE", jaroslav@68: "TAI LE", jaroslav@68: "TAILE"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Khmer Symbols" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KHMER_SYMBOLS = jaroslav@68: new UnicodeBlock("KHMER_SYMBOLS", jaroslav@68: "KHMER SYMBOLS", jaroslav@68: "KHMERSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Phonetic Extensions" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock PHONETIC_EXTENSIONS = jaroslav@68: new UnicodeBlock("PHONETIC_EXTENSIONS", jaroslav@68: "PHONETIC EXTENSIONS", jaroslav@68: "PHONETICEXTENSIONS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = jaroslav@68: new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A", jaroslav@68: "MISCELLANEOUS MATHEMATICAL SYMBOLS-A", jaroslav@68: "MISCELLANEOUSMATHEMATICALSYMBOLS-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Supplemental Arrows-A" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A = jaroslav@68: new UnicodeBlock("SUPPLEMENTAL_ARROWS_A", jaroslav@68: "SUPPLEMENTAL ARROWS-A", jaroslav@68: "SUPPLEMENTALARROWS-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Supplemental Arrows-B" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B = jaroslav@68: new UnicodeBlock("SUPPLEMENTAL_ARROWS_B", jaroslav@68: "SUPPLEMENTAL ARROWS-B", jaroslav@68: "SUPPLEMENTALARROWS-B"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = jaroslav@68: new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B", jaroslav@68: "MISCELLANEOUS MATHEMATICAL SYMBOLS-B", jaroslav@68: "MISCELLANEOUSMATHEMATICALSYMBOLS-B"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Supplemental Mathematical Operators" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS = jaroslav@68: new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS", jaroslav@68: "SUPPLEMENTAL MATHEMATICAL OPERATORS", jaroslav@68: "SUPPLEMENTALMATHEMATICALOPERATORS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Miscellaneous Symbols and Arrows" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS = jaroslav@68: new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS", jaroslav@68: "MISCELLANEOUS SYMBOLS AND ARROWS", jaroslav@68: "MISCELLANEOUSSYMBOLSANDARROWS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Katakana Phonetic Extensions" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS = jaroslav@68: new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS", jaroslav@68: "KATAKANA PHONETIC EXTENSIONS", jaroslav@68: "KATAKANAPHONETICEXTENSIONS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Yijing Hexagram Symbols" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS = jaroslav@68: new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS", jaroslav@68: "YIJING HEXAGRAM SYMBOLS", jaroslav@68: "YIJINGHEXAGRAMSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Variation Selectors" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock VARIATION_SELECTORS = jaroslav@68: new UnicodeBlock("VARIATION_SELECTORS", jaroslav@68: "VARIATION SELECTORS", jaroslav@68: "VARIATIONSELECTORS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Linear B Syllabary" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LINEAR_B_SYLLABARY = jaroslav@68: new UnicodeBlock("LINEAR_B_SYLLABARY", jaroslav@68: "LINEAR B SYLLABARY", jaroslav@68: "LINEARBSYLLABARY"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Linear B Ideograms" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LINEAR_B_IDEOGRAMS = jaroslav@68: new UnicodeBlock("LINEAR_B_IDEOGRAMS", jaroslav@68: "LINEAR B IDEOGRAMS", jaroslav@68: "LINEARBIDEOGRAMS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Aegean Numbers" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock AEGEAN_NUMBERS = jaroslav@68: new UnicodeBlock("AEGEAN_NUMBERS", jaroslav@68: "AEGEAN NUMBERS", jaroslav@68: "AEGEANNUMBERS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Old Italic" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OLD_ITALIC = jaroslav@68: new UnicodeBlock("OLD_ITALIC", jaroslav@68: "OLD ITALIC", jaroslav@68: "OLDITALIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Gothic" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GOTHIC = jaroslav@68: new UnicodeBlock("GOTHIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ugaritic" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock UGARITIC = jaroslav@68: new UnicodeBlock("UGARITIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Deseret" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock DESERET = jaroslav@68: new UnicodeBlock("DESERET"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Shavian" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SHAVIAN = jaroslav@68: new UnicodeBlock("SHAVIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Osmanya" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OSMANYA = jaroslav@68: new UnicodeBlock("OSMANYA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cypriot Syllabary" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CYPRIOT_SYLLABARY = jaroslav@68: new UnicodeBlock("CYPRIOT_SYLLABARY", jaroslav@68: "CYPRIOT SYLLABARY", jaroslav@68: "CYPRIOTSYLLABARY"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Byzantine Musical Symbols" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS = jaroslav@68: new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS", jaroslav@68: "BYZANTINE MUSICAL SYMBOLS", jaroslav@68: "BYZANTINEMUSICALSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Musical Symbols" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MUSICAL_SYMBOLS = jaroslav@68: new UnicodeBlock("MUSICAL_SYMBOLS", jaroslav@68: "MUSICAL SYMBOLS", jaroslav@68: "MUSICALSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tai Xuan Jing Symbols" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS = jaroslav@68: new UnicodeBlock("TAI_XUAN_JING_SYMBOLS", jaroslav@68: "TAI XUAN JING SYMBOLS", jaroslav@68: "TAIXUANJINGSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Mathematical Alphanumeric Symbols" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS = jaroslav@68: new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS", jaroslav@68: "MATHEMATICAL ALPHANUMERIC SYMBOLS", jaroslav@68: "MATHEMATICALALPHANUMERICSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Unified Ideographs Extension B" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = jaroslav@68: new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B", jaroslav@68: "CJK UNIFIED IDEOGRAPHS EXTENSION B", jaroslav@68: "CJKUNIFIEDIDEOGRAPHSEXTENSIONB"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = jaroslav@68: new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT", jaroslav@68: "CJK COMPATIBILITY IDEOGRAPHS SUPPLEMENT", jaroslav@68: "CJKCOMPATIBILITYIDEOGRAPHSSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tags" Unicode character block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAGS = jaroslav@68: new UnicodeBlock("TAGS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Variation Selectors Supplement" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT = jaroslav@68: new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT", jaroslav@68: "VARIATION SELECTORS SUPPLEMENT", jaroslav@68: "VARIATIONSELECTORSSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Supplementary Private Use Area-A" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A = jaroslav@68: new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A", jaroslav@68: "SUPPLEMENTARY PRIVATE USE AREA-A", jaroslav@68: "SUPPLEMENTARYPRIVATEUSEAREA-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Supplementary Private Use Area-B" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B = jaroslav@68: new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B", jaroslav@68: "SUPPLEMENTARY PRIVATE USE AREA-B", jaroslav@68: "SUPPLEMENTARYPRIVATEUSEAREA-B"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "High Surrogates" Unicode character block. jaroslav@68: * This block represents codepoint values in the high surrogate jaroslav@68: * range: U+D800 through U+DB7F jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HIGH_SURROGATES = jaroslav@68: new UnicodeBlock("HIGH_SURROGATES", jaroslav@68: "HIGH SURROGATES", jaroslav@68: "HIGHSURROGATES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "High Private Use Surrogates" Unicode character jaroslav@68: * block. jaroslav@68: * This block represents codepoint values in the private use high jaroslav@68: * surrogate range: U+DB80 through U+DBFF jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES = jaroslav@68: new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES", jaroslav@68: "HIGH PRIVATE USE SURROGATES", jaroslav@68: "HIGHPRIVATEUSESURROGATES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Low Surrogates" Unicode character block. jaroslav@68: * This block represents codepoint values in the low surrogate jaroslav@68: * range: U+DC00 through U+DFFF jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LOW_SURROGATES = jaroslav@68: new UnicodeBlock("LOW_SURROGATES", jaroslav@68: "LOW SURROGATES", jaroslav@68: "LOWSURROGATES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Arabic Supplement" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ARABIC_SUPPLEMENT = jaroslav@68: new UnicodeBlock("ARABIC_SUPPLEMENT", jaroslav@68: "ARABIC SUPPLEMENT", jaroslav@68: "ARABICSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "NKo" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock NKO = jaroslav@68: new UnicodeBlock("NKO"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Samaritan" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SAMARITAN = jaroslav@68: new UnicodeBlock("SAMARITAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Mandaic" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MANDAIC = jaroslav@68: new UnicodeBlock("MANDAIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ethiopic Supplement" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ETHIOPIC_SUPPLEMENT = jaroslav@68: new UnicodeBlock("ETHIOPIC_SUPPLEMENT", jaroslav@68: "ETHIOPIC SUPPLEMENT", jaroslav@68: "ETHIOPICSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Unified Canadian Aboriginal Syllabics Extended" jaroslav@68: * Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = jaroslav@68: new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED", jaroslav@68: "UNIFIED CANADIAN ABORIGINAL SYLLABICS EXTENDED", jaroslav@68: "UNIFIEDCANADIANABORIGINALSYLLABICSEXTENDED"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "New Tai Lue" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock NEW_TAI_LUE = jaroslav@68: new UnicodeBlock("NEW_TAI_LUE", jaroslav@68: "NEW TAI LUE", jaroslav@68: "NEWTAILUE"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Buginese" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BUGINESE = jaroslav@68: new UnicodeBlock("BUGINESE"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tai Tham" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAI_THAM = jaroslav@68: new UnicodeBlock("TAI_THAM", jaroslav@68: "TAI THAM", jaroslav@68: "TAITHAM"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Balinese" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BALINESE = jaroslav@68: new UnicodeBlock("BALINESE"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Sundanese" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUNDANESE = jaroslav@68: new UnicodeBlock("SUNDANESE"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Batak" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BATAK = jaroslav@68: new UnicodeBlock("BATAK"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Lepcha" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LEPCHA = jaroslav@68: new UnicodeBlock("LEPCHA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ol Chiki" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OL_CHIKI = jaroslav@68: new UnicodeBlock("OL_CHIKI", jaroslav@68: "OL CHIKI", jaroslav@68: "OLCHIKI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Vedic Extensions" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock VEDIC_EXTENSIONS = jaroslav@68: new UnicodeBlock("VEDIC_EXTENSIONS", jaroslav@68: "VEDIC EXTENSIONS", jaroslav@68: "VEDICEXTENSIONS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Phonetic Extensions Supplement" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock PHONETIC_EXTENSIONS_SUPPLEMENT = jaroslav@68: new UnicodeBlock("PHONETIC_EXTENSIONS_SUPPLEMENT", jaroslav@68: "PHONETIC EXTENSIONS SUPPLEMENT", jaroslav@68: "PHONETICEXTENSIONSSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Combining Diacritical Marks Supplement" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = jaroslav@68: new UnicodeBlock("COMBINING_DIACRITICAL_MARKS_SUPPLEMENT", jaroslav@68: "COMBINING DIACRITICAL MARKS SUPPLEMENT", jaroslav@68: "COMBININGDIACRITICALMARKSSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Glagolitic" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GLAGOLITIC = jaroslav@68: new UnicodeBlock("GLAGOLITIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Latin Extended-C" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LATIN_EXTENDED_C = jaroslav@68: new UnicodeBlock("LATIN_EXTENDED_C", jaroslav@68: "LATIN EXTENDED-C", jaroslav@68: "LATINEXTENDED-C"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Coptic" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock COPTIC = jaroslav@68: new UnicodeBlock("COPTIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Georgian Supplement" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock GEORGIAN_SUPPLEMENT = jaroslav@68: new UnicodeBlock("GEORGIAN_SUPPLEMENT", jaroslav@68: "GEORGIAN SUPPLEMENT", jaroslav@68: "GEORGIANSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tifinagh" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TIFINAGH = jaroslav@68: new UnicodeBlock("TIFINAGH"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ethiopic Extended" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ETHIOPIC_EXTENDED = jaroslav@68: new UnicodeBlock("ETHIOPIC_EXTENDED", jaroslav@68: "ETHIOPIC EXTENDED", jaroslav@68: "ETHIOPICEXTENDED"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cyrillic Extended-A" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CYRILLIC_EXTENDED_A = jaroslav@68: new UnicodeBlock("CYRILLIC_EXTENDED_A", jaroslav@68: "CYRILLIC EXTENDED-A", jaroslav@68: "CYRILLICEXTENDED-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Supplemental Punctuation" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SUPPLEMENTAL_PUNCTUATION = jaroslav@68: new UnicodeBlock("SUPPLEMENTAL_PUNCTUATION", jaroslav@68: "SUPPLEMENTAL PUNCTUATION", jaroslav@68: "SUPPLEMENTALPUNCTUATION"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Strokes" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_STROKES = jaroslav@68: new UnicodeBlock("CJK_STROKES", jaroslav@68: "CJK STROKES", jaroslav@68: "CJKSTROKES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Lisu" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LISU = jaroslav@68: new UnicodeBlock("LISU"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Vai" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock VAI = jaroslav@68: new UnicodeBlock("VAI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cyrillic Extended-B" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CYRILLIC_EXTENDED_B = jaroslav@68: new UnicodeBlock("CYRILLIC_EXTENDED_B", jaroslav@68: "CYRILLIC EXTENDED-B", jaroslav@68: "CYRILLICEXTENDED-B"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Bamum" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BAMUM = jaroslav@68: new UnicodeBlock("BAMUM"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Modifier Tone Letters" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MODIFIER_TONE_LETTERS = jaroslav@68: new UnicodeBlock("MODIFIER_TONE_LETTERS", jaroslav@68: "MODIFIER TONE LETTERS", jaroslav@68: "MODIFIERTONELETTERS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Latin Extended-D" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LATIN_EXTENDED_D = jaroslav@68: new UnicodeBlock("LATIN_EXTENDED_D", jaroslav@68: "LATIN EXTENDED-D", jaroslav@68: "LATINEXTENDED-D"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Syloti Nagri" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SYLOTI_NAGRI = jaroslav@68: new UnicodeBlock("SYLOTI_NAGRI", jaroslav@68: "SYLOTI NAGRI", jaroslav@68: "SYLOTINAGRI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Common Indic Number Forms" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock COMMON_INDIC_NUMBER_FORMS = jaroslav@68: new UnicodeBlock("COMMON_INDIC_NUMBER_FORMS", jaroslav@68: "COMMON INDIC NUMBER FORMS", jaroslav@68: "COMMONINDICNUMBERFORMS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Phags-pa" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock PHAGS_PA = jaroslav@68: new UnicodeBlock("PHAGS_PA", jaroslav@68: "PHAGS-PA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Saurashtra" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock SAURASHTRA = jaroslav@68: new UnicodeBlock("SAURASHTRA"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Devanagari Extended" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock DEVANAGARI_EXTENDED = jaroslav@68: new UnicodeBlock("DEVANAGARI_EXTENDED", jaroslav@68: "DEVANAGARI EXTENDED", jaroslav@68: "DEVANAGARIEXTENDED"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Kayah Li" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KAYAH_LI = jaroslav@68: new UnicodeBlock("KAYAH_LI", jaroslav@68: "KAYAH LI", jaroslav@68: "KAYAHLI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Rejang" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock REJANG = jaroslav@68: new UnicodeBlock("REJANG"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hangul Jamo Extended-A" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HANGUL_JAMO_EXTENDED_A = jaroslav@68: new UnicodeBlock("HANGUL_JAMO_EXTENDED_A", jaroslav@68: "HANGUL JAMO EXTENDED-A", jaroslav@68: "HANGULJAMOEXTENDED-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Javanese" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock JAVANESE = jaroslav@68: new UnicodeBlock("JAVANESE"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cham" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CHAM = jaroslav@68: new UnicodeBlock("CHAM"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Myanmar Extended-A" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MYANMAR_EXTENDED_A = jaroslav@68: new UnicodeBlock("MYANMAR_EXTENDED_A", jaroslav@68: "MYANMAR EXTENDED-A", jaroslav@68: "MYANMAREXTENDED-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Tai Viet" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TAI_VIET = jaroslav@68: new UnicodeBlock("TAI_VIET", jaroslav@68: "TAI VIET", jaroslav@68: "TAIVIET"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ethiopic Extended-A" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ETHIOPIC_EXTENDED_A = jaroslav@68: new UnicodeBlock("ETHIOPIC_EXTENDED_A", jaroslav@68: "ETHIOPIC EXTENDED-A", jaroslav@68: "ETHIOPICEXTENDED-A"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Meetei Mayek" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MEETEI_MAYEK = jaroslav@68: new UnicodeBlock("MEETEI_MAYEK", jaroslav@68: "MEETEI MAYEK", jaroslav@68: "MEETEIMAYEK"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Hangul Jamo Extended-B" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock HANGUL_JAMO_EXTENDED_B = jaroslav@68: new UnicodeBlock("HANGUL_JAMO_EXTENDED_B", jaroslav@68: "HANGUL JAMO EXTENDED-B", jaroslav@68: "HANGULJAMOEXTENDED-B"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Vertical Forms" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock VERTICAL_FORMS = jaroslav@68: new UnicodeBlock("VERTICAL_FORMS", jaroslav@68: "VERTICAL FORMS", jaroslav@68: "VERTICALFORMS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ancient Greek Numbers" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ANCIENT_GREEK_NUMBERS = jaroslav@68: new UnicodeBlock("ANCIENT_GREEK_NUMBERS", jaroslav@68: "ANCIENT GREEK NUMBERS", jaroslav@68: "ANCIENTGREEKNUMBERS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ancient Symbols" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ANCIENT_SYMBOLS = jaroslav@68: new UnicodeBlock("ANCIENT_SYMBOLS", jaroslav@68: "ANCIENT SYMBOLS", jaroslav@68: "ANCIENTSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Phaistos Disc" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock PHAISTOS_DISC = jaroslav@68: new UnicodeBlock("PHAISTOS_DISC", jaroslav@68: "PHAISTOS DISC", jaroslav@68: "PHAISTOSDISC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Lycian" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LYCIAN = jaroslav@68: new UnicodeBlock("LYCIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Carian" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CARIAN = jaroslav@68: new UnicodeBlock("CARIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Old Persian" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OLD_PERSIAN = jaroslav@68: new UnicodeBlock("OLD_PERSIAN", jaroslav@68: "OLD PERSIAN", jaroslav@68: "OLDPERSIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Imperial Aramaic" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock IMPERIAL_ARAMAIC = jaroslav@68: new UnicodeBlock("IMPERIAL_ARAMAIC", jaroslav@68: "IMPERIAL ARAMAIC", jaroslav@68: "IMPERIALARAMAIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Phoenician" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock PHOENICIAN = jaroslav@68: new UnicodeBlock("PHOENICIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Lydian" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock LYDIAN = jaroslav@68: new UnicodeBlock("LYDIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Kharoshthi" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KHAROSHTHI = jaroslav@68: new UnicodeBlock("KHAROSHTHI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Old South Arabian" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OLD_SOUTH_ARABIAN = jaroslav@68: new UnicodeBlock("OLD_SOUTH_ARABIAN", jaroslav@68: "OLD SOUTH ARABIAN", jaroslav@68: "OLDSOUTHARABIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Avestan" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock AVESTAN = jaroslav@68: new UnicodeBlock("AVESTAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Inscriptional Parthian" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock INSCRIPTIONAL_PARTHIAN = jaroslav@68: new UnicodeBlock("INSCRIPTIONAL_PARTHIAN", jaroslav@68: "INSCRIPTIONAL PARTHIAN", jaroslav@68: "INSCRIPTIONALPARTHIAN"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Inscriptional Pahlavi" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock INSCRIPTIONAL_PAHLAVI = jaroslav@68: new UnicodeBlock("INSCRIPTIONAL_PAHLAVI", jaroslav@68: "INSCRIPTIONAL PAHLAVI", jaroslav@68: "INSCRIPTIONALPAHLAVI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Old Turkic" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock OLD_TURKIC = jaroslav@68: new UnicodeBlock("OLD_TURKIC", jaroslav@68: "OLD TURKIC", jaroslav@68: "OLDTURKIC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Rumi Numeral Symbols" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock RUMI_NUMERAL_SYMBOLS = jaroslav@68: new UnicodeBlock("RUMI_NUMERAL_SYMBOLS", jaroslav@68: "RUMI NUMERAL SYMBOLS", jaroslav@68: "RUMINUMERALSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Brahmi" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BRAHMI = jaroslav@68: new UnicodeBlock("BRAHMI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Kaithi" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KAITHI = jaroslav@68: new UnicodeBlock("KAITHI"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cuneiform" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CUNEIFORM = jaroslav@68: new UnicodeBlock("CUNEIFORM"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Cuneiform Numbers and Punctuation" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CUNEIFORM_NUMBERS_AND_PUNCTUATION = jaroslav@68: new UnicodeBlock("CUNEIFORM_NUMBERS_AND_PUNCTUATION", jaroslav@68: "CUNEIFORM NUMBERS AND PUNCTUATION", jaroslav@68: "CUNEIFORMNUMBERSANDPUNCTUATION"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Egyptian Hieroglyphs" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock EGYPTIAN_HIEROGLYPHS = jaroslav@68: new UnicodeBlock("EGYPTIAN_HIEROGLYPHS", jaroslav@68: "EGYPTIAN HIEROGLYPHS", jaroslav@68: "EGYPTIANHIEROGLYPHS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Bamum Supplement" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock BAMUM_SUPPLEMENT = jaroslav@68: new UnicodeBlock("BAMUM_SUPPLEMENT", jaroslav@68: "BAMUM SUPPLEMENT", jaroslav@68: "BAMUMSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Kana Supplement" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock KANA_SUPPLEMENT = jaroslav@68: new UnicodeBlock("KANA_SUPPLEMENT", jaroslav@68: "KANA SUPPLEMENT", jaroslav@68: "KANASUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Ancient Greek Musical Notation" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ANCIENT_GREEK_MUSICAL_NOTATION = jaroslav@68: new UnicodeBlock("ANCIENT_GREEK_MUSICAL_NOTATION", jaroslav@68: "ANCIENT GREEK MUSICAL NOTATION", jaroslav@68: "ANCIENTGREEKMUSICALNOTATION"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Counting Rod Numerals" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock COUNTING_ROD_NUMERALS = jaroslav@68: new UnicodeBlock("COUNTING_ROD_NUMERALS", jaroslav@68: "COUNTING ROD NUMERALS", jaroslav@68: "COUNTINGRODNUMERALS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Mahjong Tiles" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MAHJONG_TILES = jaroslav@68: new UnicodeBlock("MAHJONG_TILES", jaroslav@68: "MAHJONG TILES", jaroslav@68: "MAHJONGTILES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Domino Tiles" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock DOMINO_TILES = jaroslav@68: new UnicodeBlock("DOMINO_TILES", jaroslav@68: "DOMINO TILES", jaroslav@68: "DOMINOTILES"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Playing Cards" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock PLAYING_CARDS = jaroslav@68: new UnicodeBlock("PLAYING_CARDS", jaroslav@68: "PLAYING CARDS", jaroslav@68: "PLAYINGCARDS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Enclosed Alphanumeric Supplement" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ENCLOSED_ALPHANUMERIC_SUPPLEMENT = jaroslav@68: new UnicodeBlock("ENCLOSED_ALPHANUMERIC_SUPPLEMENT", jaroslav@68: "ENCLOSED ALPHANUMERIC SUPPLEMENT", jaroslav@68: "ENCLOSEDALPHANUMERICSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Enclosed Ideographic Supplement" Unicode character jaroslav@68: * block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = jaroslav@68: new UnicodeBlock("ENCLOSED_IDEOGRAPHIC_SUPPLEMENT", jaroslav@68: "ENCLOSED IDEOGRAPHIC SUPPLEMENT", jaroslav@68: "ENCLOSEDIDEOGRAPHICSUPPLEMENT"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Miscellaneous Symbols And Pictographs" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = jaroslav@68: new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS", jaroslav@68: "MISCELLANEOUS SYMBOLS AND PICTOGRAPHS", jaroslav@68: "MISCELLANEOUSSYMBOLSANDPICTOGRAPHS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Emoticons" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock EMOTICONS = jaroslav@68: new UnicodeBlock("EMOTICONS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Transport And Map Symbols" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock TRANSPORT_AND_MAP_SYMBOLS = jaroslav@68: new UnicodeBlock("TRANSPORT_AND_MAP_SYMBOLS", jaroslav@68: "TRANSPORT AND MAP SYMBOLS", jaroslav@68: "TRANSPORTANDMAPSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "Alchemical Symbols" Unicode character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock ALCHEMICAL_SYMBOLS = jaroslav@68: new UnicodeBlock("ALCHEMICAL_SYMBOLS", jaroslav@68: "ALCHEMICAL SYMBOLS", jaroslav@68: "ALCHEMICALSYMBOLS"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Unified Ideographs Extension C" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = jaroslav@68: new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C", jaroslav@68: "CJK UNIFIED IDEOGRAPHS EXTENSION C", jaroslav@68: "CJKUNIFIEDIDEOGRAPHSEXTENSIONC"); jaroslav@68: jaroslav@68: /** jaroslav@68: * Constant for the "CJK Unified Ideographs Extension D" Unicode jaroslav@68: * character block. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = jaroslav@68: new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D", jaroslav@68: "CJK UNIFIED IDEOGRAPHS EXTENSION D", jaroslav@68: "CJKUNIFIEDIDEOGRAPHSEXTENSIOND"); jaroslav@68: jaroslav@68: private static final int blockStarts[] = { jaroslav@68: 0x0000, // 0000..007F; Basic Latin jaroslav@68: 0x0080, // 0080..00FF; Latin-1 Supplement jaroslav@68: 0x0100, // 0100..017F; Latin Extended-A jaroslav@68: 0x0180, // 0180..024F; Latin Extended-B jaroslav@68: 0x0250, // 0250..02AF; IPA Extensions jaroslav@68: 0x02B0, // 02B0..02FF; Spacing Modifier Letters jaroslav@68: 0x0300, // 0300..036F; Combining Diacritical Marks jaroslav@68: 0x0370, // 0370..03FF; Greek and Coptic jaroslav@68: 0x0400, // 0400..04FF; Cyrillic jaroslav@68: 0x0500, // 0500..052F; Cyrillic Supplement jaroslav@68: 0x0530, // 0530..058F; Armenian jaroslav@68: 0x0590, // 0590..05FF; Hebrew jaroslav@68: 0x0600, // 0600..06FF; Arabic jaroslav@68: 0x0700, // 0700..074F; Syriac jaroslav@68: 0x0750, // 0750..077F; Arabic Supplement jaroslav@68: 0x0780, // 0780..07BF; Thaana jaroslav@68: 0x07C0, // 07C0..07FF; NKo jaroslav@68: 0x0800, // 0800..083F; Samaritan jaroslav@68: 0x0840, // 0840..085F; Mandaic jaroslav@68: 0x0860, // unassigned jaroslav@68: 0x0900, // 0900..097F; Devanagari jaroslav@68: 0x0980, // 0980..09FF; Bengali jaroslav@68: 0x0A00, // 0A00..0A7F; Gurmukhi jaroslav@68: 0x0A80, // 0A80..0AFF; Gujarati jaroslav@68: 0x0B00, // 0B00..0B7F; Oriya jaroslav@68: 0x0B80, // 0B80..0BFF; Tamil jaroslav@68: 0x0C00, // 0C00..0C7F; Telugu jaroslav@68: 0x0C80, // 0C80..0CFF; Kannada jaroslav@68: 0x0D00, // 0D00..0D7F; Malayalam jaroslav@68: 0x0D80, // 0D80..0DFF; Sinhala jaroslav@68: 0x0E00, // 0E00..0E7F; Thai jaroslav@68: 0x0E80, // 0E80..0EFF; Lao jaroslav@68: 0x0F00, // 0F00..0FFF; Tibetan jaroslav@68: 0x1000, // 1000..109F; Myanmar jaroslav@68: 0x10A0, // 10A0..10FF; Georgian jaroslav@68: 0x1100, // 1100..11FF; Hangul Jamo jaroslav@68: 0x1200, // 1200..137F; Ethiopic jaroslav@68: 0x1380, // 1380..139F; Ethiopic Supplement jaroslav@68: 0x13A0, // 13A0..13FF; Cherokee jaroslav@68: 0x1400, // 1400..167F; Unified Canadian Aboriginal Syllabics jaroslav@68: 0x1680, // 1680..169F; Ogham jaroslav@68: 0x16A0, // 16A0..16FF; Runic jaroslav@68: 0x1700, // 1700..171F; Tagalog jaroslav@68: 0x1720, // 1720..173F; Hanunoo jaroslav@68: 0x1740, // 1740..175F; Buhid jaroslav@68: 0x1760, // 1760..177F; Tagbanwa jaroslav@68: 0x1780, // 1780..17FF; Khmer jaroslav@68: 0x1800, // 1800..18AF; Mongolian jaroslav@68: 0x18B0, // 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended jaroslav@68: 0x1900, // 1900..194F; Limbu jaroslav@68: 0x1950, // 1950..197F; Tai Le jaroslav@68: 0x1980, // 1980..19DF; New Tai Lue jaroslav@68: 0x19E0, // 19E0..19FF; Khmer Symbols jaroslav@68: 0x1A00, // 1A00..1A1F; Buginese jaroslav@68: 0x1A20, // 1A20..1AAF; Tai Tham jaroslav@68: 0x1AB0, // unassigned jaroslav@68: 0x1B00, // 1B00..1B7F; Balinese jaroslav@68: 0x1B80, // 1B80..1BBF; Sundanese jaroslav@68: 0x1BC0, // 1BC0..1BFF; Batak jaroslav@68: 0x1C00, // 1C00..1C4F; Lepcha jaroslav@68: 0x1C50, // 1C50..1C7F; Ol Chiki jaroslav@68: 0x1C80, // unassigned jaroslav@68: 0x1CD0, // 1CD0..1CFF; Vedic Extensions jaroslav@68: 0x1D00, // 1D00..1D7F; Phonetic Extensions jaroslav@68: 0x1D80, // 1D80..1DBF; Phonetic Extensions Supplement jaroslav@68: 0x1DC0, // 1DC0..1DFF; Combining Diacritical Marks Supplement jaroslav@68: 0x1E00, // 1E00..1EFF; Latin Extended Additional jaroslav@68: 0x1F00, // 1F00..1FFF; Greek Extended jaroslav@68: 0x2000, // 2000..206F; General Punctuation jaroslav@68: 0x2070, // 2070..209F; Superscripts and Subscripts jaroslav@68: 0x20A0, // 20A0..20CF; Currency Symbols jaroslav@68: 0x20D0, // 20D0..20FF; Combining Diacritical Marks for Symbols jaroslav@68: 0x2100, // 2100..214F; Letterlike Symbols jaroslav@68: 0x2150, // 2150..218F; Number Forms jaroslav@68: 0x2190, // 2190..21FF; Arrows jaroslav@68: 0x2200, // 2200..22FF; Mathematical Operators jaroslav@68: 0x2300, // 2300..23FF; Miscellaneous Technical jaroslav@68: 0x2400, // 2400..243F; Control Pictures jaroslav@68: 0x2440, // 2440..245F; Optical Character Recognition jaroslav@68: 0x2460, // 2460..24FF; Enclosed Alphanumerics jaroslav@68: 0x2500, // 2500..257F; Box Drawing jaroslav@68: 0x2580, // 2580..259F; Block Elements jaroslav@68: 0x25A0, // 25A0..25FF; Geometric Shapes jaroslav@68: 0x2600, // 2600..26FF; Miscellaneous Symbols jaroslav@68: 0x2700, // 2700..27BF; Dingbats jaroslav@68: 0x27C0, // 27C0..27EF; Miscellaneous Mathematical Symbols-A jaroslav@68: 0x27F0, // 27F0..27FF; Supplemental Arrows-A jaroslav@68: 0x2800, // 2800..28FF; Braille Patterns jaroslav@68: 0x2900, // 2900..297F; Supplemental Arrows-B jaroslav@68: 0x2980, // 2980..29FF; Miscellaneous Mathematical Symbols-B jaroslav@68: 0x2A00, // 2A00..2AFF; Supplemental Mathematical Operators jaroslav@68: 0x2B00, // 2B00..2BFF; Miscellaneous Symbols and Arrows jaroslav@68: 0x2C00, // 2C00..2C5F; Glagolitic jaroslav@68: 0x2C60, // 2C60..2C7F; Latin Extended-C jaroslav@68: 0x2C80, // 2C80..2CFF; Coptic jaroslav@68: 0x2D00, // 2D00..2D2F; Georgian Supplement jaroslav@68: 0x2D30, // 2D30..2D7F; Tifinagh jaroslav@68: 0x2D80, // 2D80..2DDF; Ethiopic Extended jaroslav@68: 0x2DE0, // 2DE0..2DFF; Cyrillic Extended-A jaroslav@68: 0x2E00, // 2E00..2E7F; Supplemental Punctuation jaroslav@68: 0x2E80, // 2E80..2EFF; CJK Radicals Supplement jaroslav@68: 0x2F00, // 2F00..2FDF; Kangxi Radicals jaroslav@68: 0x2FE0, // unassigned jaroslav@68: 0x2FF0, // 2FF0..2FFF; Ideographic Description Characters jaroslav@68: 0x3000, // 3000..303F; CJK Symbols and Punctuation jaroslav@68: 0x3040, // 3040..309F; Hiragana jaroslav@68: 0x30A0, // 30A0..30FF; Katakana jaroslav@68: 0x3100, // 3100..312F; Bopomofo jaroslav@68: 0x3130, // 3130..318F; Hangul Compatibility Jamo jaroslav@68: 0x3190, // 3190..319F; Kanbun jaroslav@68: 0x31A0, // 31A0..31BF; Bopomofo Extended jaroslav@68: 0x31C0, // 31C0..31EF; CJK Strokes jaroslav@68: 0x31F0, // 31F0..31FF; Katakana Phonetic Extensions jaroslav@68: 0x3200, // 3200..32FF; Enclosed CJK Letters and Months jaroslav@68: 0x3300, // 3300..33FF; CJK Compatibility jaroslav@68: 0x3400, // 3400..4DBF; CJK Unified Ideographs Extension A jaroslav@68: 0x4DC0, // 4DC0..4DFF; Yijing Hexagram Symbols jaroslav@68: 0x4E00, // 4E00..9FFF; CJK Unified Ideographs jaroslav@68: 0xA000, // A000..A48F; Yi Syllables jaroslav@68: 0xA490, // A490..A4CF; Yi Radicals jaroslav@68: 0xA4D0, // A4D0..A4FF; Lisu jaroslav@68: 0xA500, // A500..A63F; Vai jaroslav@68: 0xA640, // A640..A69F; Cyrillic Extended-B jaroslav@68: 0xA6A0, // A6A0..A6FF; Bamum jaroslav@68: 0xA700, // A700..A71F; Modifier Tone Letters jaroslav@68: 0xA720, // A720..A7FF; Latin Extended-D jaroslav@68: 0xA800, // A800..A82F; Syloti Nagri jaroslav@68: 0xA830, // A830..A83F; Common Indic Number Forms jaroslav@68: 0xA840, // A840..A87F; Phags-pa jaroslav@68: 0xA880, // A880..A8DF; Saurashtra jaroslav@68: 0xA8E0, // A8E0..A8FF; Devanagari Extended jaroslav@68: 0xA900, // A900..A92F; Kayah Li jaroslav@68: 0xA930, // A930..A95F; Rejang jaroslav@68: 0xA960, // A960..A97F; Hangul Jamo Extended-A jaroslav@68: 0xA980, // A980..A9DF; Javanese jaroslav@68: 0xA9E0, // unassigned jaroslav@68: 0xAA00, // AA00..AA5F; Cham jaroslav@68: 0xAA60, // AA60..AA7F; Myanmar Extended-A jaroslav@68: 0xAA80, // AA80..AADF; Tai Viet jaroslav@68: 0xAAE0, // unassigned jaroslav@68: 0xAB00, // AB00..AB2F; Ethiopic Extended-A jaroslav@68: 0xAB30, // unassigned jaroslav@68: 0xABC0, // ABC0..ABFF; Meetei Mayek jaroslav@68: 0xAC00, // AC00..D7AF; Hangul Syllables jaroslav@68: 0xD7B0, // D7B0..D7FF; Hangul Jamo Extended-B jaroslav@68: 0xD800, // D800..DB7F; High Surrogates jaroslav@68: 0xDB80, // DB80..DBFF; High Private Use Surrogates jaroslav@68: 0xDC00, // DC00..DFFF; Low Surrogates jaroslav@68: 0xE000, // E000..F8FF; Private Use Area jaroslav@68: 0xF900, // F900..FAFF; CJK Compatibility Ideographs jaroslav@68: 0xFB00, // FB00..FB4F; Alphabetic Presentation Forms jaroslav@68: 0xFB50, // FB50..FDFF; Arabic Presentation Forms-A jaroslav@68: 0xFE00, // FE00..FE0F; Variation Selectors jaroslav@68: 0xFE10, // FE10..FE1F; Vertical Forms jaroslav@68: 0xFE20, // FE20..FE2F; Combining Half Marks jaroslav@68: 0xFE30, // FE30..FE4F; CJK Compatibility Forms jaroslav@68: 0xFE50, // FE50..FE6F; Small Form Variants jaroslav@68: 0xFE70, // FE70..FEFF; Arabic Presentation Forms-B jaroslav@68: 0xFF00, // FF00..FFEF; Halfwidth and Fullwidth Forms jaroslav@68: 0xFFF0, // FFF0..FFFF; Specials jaroslav@68: 0x10000, // 10000..1007F; Linear B Syllabary jaroslav@68: 0x10080, // 10080..100FF; Linear B Ideograms jaroslav@68: 0x10100, // 10100..1013F; Aegean Numbers jaroslav@68: 0x10140, // 10140..1018F; Ancient Greek Numbers jaroslav@68: 0x10190, // 10190..101CF; Ancient Symbols jaroslav@68: 0x101D0, // 101D0..101FF; Phaistos Disc jaroslav@68: 0x10200, // unassigned jaroslav@68: 0x10280, // 10280..1029F; Lycian jaroslav@68: 0x102A0, // 102A0..102DF; Carian jaroslav@68: 0x102E0, // unassigned jaroslav@68: 0x10300, // 10300..1032F; Old Italic jaroslav@68: 0x10330, // 10330..1034F; Gothic jaroslav@68: 0x10350, // unassigned jaroslav@68: 0x10380, // 10380..1039F; Ugaritic jaroslav@68: 0x103A0, // 103A0..103DF; Old Persian jaroslav@68: 0x103E0, // unassigned jaroslav@68: 0x10400, // 10400..1044F; Deseret jaroslav@68: 0x10450, // 10450..1047F; Shavian jaroslav@68: 0x10480, // 10480..104AF; Osmanya jaroslav@68: 0x104B0, // unassigned jaroslav@68: 0x10800, // 10800..1083F; Cypriot Syllabary jaroslav@68: 0x10840, // 10840..1085F; Imperial Aramaic jaroslav@68: 0x10860, // unassigned jaroslav@68: 0x10900, // 10900..1091F; Phoenician jaroslav@68: 0x10920, // 10920..1093F; Lydian jaroslav@68: 0x10940, // unassigned jaroslav@68: 0x10A00, // 10A00..10A5F; Kharoshthi jaroslav@68: 0x10A60, // 10A60..10A7F; Old South Arabian jaroslav@68: 0x10A80, // unassigned jaroslav@68: 0x10B00, // 10B00..10B3F; Avestan jaroslav@68: 0x10B40, // 10B40..10B5F; Inscriptional Parthian jaroslav@68: 0x10B60, // 10B60..10B7F; Inscriptional Pahlavi jaroslav@68: 0x10B80, // unassigned jaroslav@68: 0x10C00, // 10C00..10C4F; Old Turkic jaroslav@68: 0x10C50, // unassigned jaroslav@68: 0x10E60, // 10E60..10E7F; Rumi Numeral Symbols jaroslav@68: 0x10E80, // unassigned jaroslav@68: 0x11000, // 11000..1107F; Brahmi jaroslav@68: 0x11080, // 11080..110CF; Kaithi jaroslav@68: 0x110D0, // unassigned jaroslav@68: 0x12000, // 12000..123FF; Cuneiform jaroslav@68: 0x12400, // 12400..1247F; Cuneiform Numbers and Punctuation jaroslav@68: 0x12480, // unassigned jaroslav@68: 0x13000, // 13000..1342F; Egyptian Hieroglyphs jaroslav@68: 0x13430, // unassigned jaroslav@68: 0x16800, // 16800..16A3F; Bamum Supplement jaroslav@68: 0x16A40, // unassigned jaroslav@68: 0x1B000, // 1B000..1B0FF; Kana Supplement jaroslav@68: 0x1B100, // unassigned jaroslav@68: 0x1D000, // 1D000..1D0FF; Byzantine Musical Symbols jaroslav@68: 0x1D100, // 1D100..1D1FF; Musical Symbols jaroslav@68: 0x1D200, // 1D200..1D24F; Ancient Greek Musical Notation jaroslav@68: 0x1D250, // unassigned jaroslav@68: 0x1D300, // 1D300..1D35F; Tai Xuan Jing Symbols jaroslav@68: 0x1D360, // 1D360..1D37F; Counting Rod Numerals jaroslav@68: 0x1D380, // unassigned jaroslav@68: 0x1D400, // 1D400..1D7FF; Mathematical Alphanumeric Symbols jaroslav@68: 0x1D800, // unassigned jaroslav@68: 0x1F000, // 1F000..1F02F; Mahjong Tiles jaroslav@68: 0x1F030, // 1F030..1F09F; Domino Tiles jaroslav@68: 0x1F0A0, // 1F0A0..1F0FF; Playing Cards jaroslav@68: 0x1F100, // 1F100..1F1FF; Enclosed Alphanumeric Supplement jaroslav@68: 0x1F200, // 1F200..1F2FF; Enclosed Ideographic Supplement jaroslav@68: 0x1F300, // 1F300..1F5FF; Miscellaneous Symbols And Pictographs jaroslav@68: 0x1F600, // 1F600..1F64F; Emoticons jaroslav@68: 0x1F650, // unassigned jaroslav@68: 0x1F680, // 1F680..1F6FF; Transport And Map Symbols jaroslav@68: 0x1F700, // 1F700..1F77F; Alchemical Symbols jaroslav@68: 0x1F780, // unassigned jaroslav@68: 0x20000, // 20000..2A6DF; CJK Unified Ideographs Extension B jaroslav@68: 0x2A6E0, // unassigned jaroslav@68: 0x2A700, // 2A700..2B73F; CJK Unified Ideographs Extension C jaroslav@68: 0x2B740, // 2B740..2B81F; CJK Unified Ideographs Extension D jaroslav@68: 0x2B820, // unassigned jaroslav@68: 0x2F800, // 2F800..2FA1F; CJK Compatibility Ideographs Supplement jaroslav@68: 0x2FA20, // unassigned jaroslav@68: 0xE0000, // E0000..E007F; Tags jaroslav@68: 0xE0080, // unassigned jaroslav@68: 0xE0100, // E0100..E01EF; Variation Selectors Supplement jaroslav@68: 0xE01F0, // unassigned jaroslav@68: 0xF0000, // F0000..FFFFF; Supplementary Private Use Area-A jaroslav@68: 0x100000 // 100000..10FFFF; Supplementary Private Use Area-B jaroslav@68: }; jaroslav@68: jaroslav@68: private static final UnicodeBlock[] blocks = { jaroslav@68: BASIC_LATIN, jaroslav@68: LATIN_1_SUPPLEMENT, jaroslav@68: LATIN_EXTENDED_A, jaroslav@68: LATIN_EXTENDED_B, jaroslav@68: IPA_EXTENSIONS, jaroslav@68: SPACING_MODIFIER_LETTERS, jaroslav@68: COMBINING_DIACRITICAL_MARKS, jaroslav@68: GREEK, jaroslav@68: CYRILLIC, jaroslav@68: CYRILLIC_SUPPLEMENTARY, jaroslav@68: ARMENIAN, jaroslav@68: HEBREW, jaroslav@68: ARABIC, jaroslav@68: SYRIAC, jaroslav@68: ARABIC_SUPPLEMENT, jaroslav@68: THAANA, jaroslav@68: NKO, jaroslav@68: SAMARITAN, jaroslav@68: MANDAIC, jaroslav@68: null, jaroslav@68: DEVANAGARI, jaroslav@68: BENGALI, jaroslav@68: GURMUKHI, jaroslav@68: GUJARATI, jaroslav@68: ORIYA, jaroslav@68: TAMIL, jaroslav@68: TELUGU, jaroslav@68: KANNADA, jaroslav@68: MALAYALAM, jaroslav@68: SINHALA, jaroslav@68: THAI, jaroslav@68: LAO, jaroslav@68: TIBETAN, jaroslav@68: MYANMAR, jaroslav@68: GEORGIAN, jaroslav@68: HANGUL_JAMO, jaroslav@68: ETHIOPIC, jaroslav@68: ETHIOPIC_SUPPLEMENT, jaroslav@68: CHEROKEE, jaroslav@68: UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS, jaroslav@68: OGHAM, jaroslav@68: RUNIC, jaroslav@68: TAGALOG, jaroslav@68: HANUNOO, jaroslav@68: BUHID, jaroslav@68: TAGBANWA, jaroslav@68: KHMER, jaroslav@68: MONGOLIAN, jaroslav@68: UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED, jaroslav@68: LIMBU, jaroslav@68: TAI_LE, jaroslav@68: NEW_TAI_LUE, jaroslav@68: KHMER_SYMBOLS, jaroslav@68: BUGINESE, jaroslav@68: TAI_THAM, jaroslav@68: null, jaroslav@68: BALINESE, jaroslav@68: SUNDANESE, jaroslav@68: BATAK, jaroslav@68: LEPCHA, jaroslav@68: OL_CHIKI, jaroslav@68: null, jaroslav@68: VEDIC_EXTENSIONS, jaroslav@68: PHONETIC_EXTENSIONS, jaroslav@68: PHONETIC_EXTENSIONS_SUPPLEMENT, jaroslav@68: COMBINING_DIACRITICAL_MARKS_SUPPLEMENT, jaroslav@68: LATIN_EXTENDED_ADDITIONAL, jaroslav@68: GREEK_EXTENDED, jaroslav@68: GENERAL_PUNCTUATION, jaroslav@68: SUPERSCRIPTS_AND_SUBSCRIPTS, jaroslav@68: CURRENCY_SYMBOLS, jaroslav@68: COMBINING_MARKS_FOR_SYMBOLS, jaroslav@68: LETTERLIKE_SYMBOLS, jaroslav@68: NUMBER_FORMS, jaroslav@68: ARROWS, jaroslav@68: MATHEMATICAL_OPERATORS, jaroslav@68: MISCELLANEOUS_TECHNICAL, jaroslav@68: CONTROL_PICTURES, jaroslav@68: OPTICAL_CHARACTER_RECOGNITION, jaroslav@68: ENCLOSED_ALPHANUMERICS, jaroslav@68: BOX_DRAWING, jaroslav@68: BLOCK_ELEMENTS, jaroslav@68: GEOMETRIC_SHAPES, jaroslav@68: MISCELLANEOUS_SYMBOLS, jaroslav@68: DINGBATS, jaroslav@68: MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A, jaroslav@68: SUPPLEMENTAL_ARROWS_A, jaroslav@68: BRAILLE_PATTERNS, jaroslav@68: SUPPLEMENTAL_ARROWS_B, jaroslav@68: MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B, jaroslav@68: SUPPLEMENTAL_MATHEMATICAL_OPERATORS, jaroslav@68: MISCELLANEOUS_SYMBOLS_AND_ARROWS, jaroslav@68: GLAGOLITIC, jaroslav@68: LATIN_EXTENDED_C, jaroslav@68: COPTIC, jaroslav@68: GEORGIAN_SUPPLEMENT, jaroslav@68: TIFINAGH, jaroslav@68: ETHIOPIC_EXTENDED, jaroslav@68: CYRILLIC_EXTENDED_A, jaroslav@68: SUPPLEMENTAL_PUNCTUATION, jaroslav@68: CJK_RADICALS_SUPPLEMENT, jaroslav@68: KANGXI_RADICALS, jaroslav@68: null, jaroslav@68: IDEOGRAPHIC_DESCRIPTION_CHARACTERS, jaroslav@68: CJK_SYMBOLS_AND_PUNCTUATION, jaroslav@68: HIRAGANA, jaroslav@68: KATAKANA, jaroslav@68: BOPOMOFO, jaroslav@68: HANGUL_COMPATIBILITY_JAMO, jaroslav@68: KANBUN, jaroslav@68: BOPOMOFO_EXTENDED, jaroslav@68: CJK_STROKES, jaroslav@68: KATAKANA_PHONETIC_EXTENSIONS, jaroslav@68: ENCLOSED_CJK_LETTERS_AND_MONTHS, jaroslav@68: CJK_COMPATIBILITY, jaroslav@68: CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A, jaroslav@68: YIJING_HEXAGRAM_SYMBOLS, jaroslav@68: CJK_UNIFIED_IDEOGRAPHS, jaroslav@68: YI_SYLLABLES, jaroslav@68: YI_RADICALS, jaroslav@68: LISU, jaroslav@68: VAI, jaroslav@68: CYRILLIC_EXTENDED_B, jaroslav@68: BAMUM, jaroslav@68: MODIFIER_TONE_LETTERS, jaroslav@68: LATIN_EXTENDED_D, jaroslav@68: SYLOTI_NAGRI, jaroslav@68: COMMON_INDIC_NUMBER_FORMS, jaroslav@68: PHAGS_PA, jaroslav@68: SAURASHTRA, jaroslav@68: DEVANAGARI_EXTENDED, jaroslav@68: KAYAH_LI, jaroslav@68: REJANG, jaroslav@68: HANGUL_JAMO_EXTENDED_A, jaroslav@68: JAVANESE, jaroslav@68: null, jaroslav@68: CHAM, jaroslav@68: MYANMAR_EXTENDED_A, jaroslav@68: TAI_VIET, jaroslav@68: null, jaroslav@68: ETHIOPIC_EXTENDED_A, jaroslav@68: null, jaroslav@68: MEETEI_MAYEK, jaroslav@68: HANGUL_SYLLABLES, jaroslav@68: HANGUL_JAMO_EXTENDED_B, jaroslav@68: HIGH_SURROGATES, jaroslav@68: HIGH_PRIVATE_USE_SURROGATES, jaroslav@68: LOW_SURROGATES, jaroslav@68: PRIVATE_USE_AREA, jaroslav@68: CJK_COMPATIBILITY_IDEOGRAPHS, jaroslav@68: ALPHABETIC_PRESENTATION_FORMS, jaroslav@68: ARABIC_PRESENTATION_FORMS_A, jaroslav@68: VARIATION_SELECTORS, jaroslav@68: VERTICAL_FORMS, jaroslav@68: COMBINING_HALF_MARKS, jaroslav@68: CJK_COMPATIBILITY_FORMS, jaroslav@68: SMALL_FORM_VARIANTS, jaroslav@68: ARABIC_PRESENTATION_FORMS_B, jaroslav@68: HALFWIDTH_AND_FULLWIDTH_FORMS, jaroslav@68: SPECIALS, jaroslav@68: LINEAR_B_SYLLABARY, jaroslav@68: LINEAR_B_IDEOGRAMS, jaroslav@68: AEGEAN_NUMBERS, jaroslav@68: ANCIENT_GREEK_NUMBERS, jaroslav@68: ANCIENT_SYMBOLS, jaroslav@68: PHAISTOS_DISC, jaroslav@68: null, jaroslav@68: LYCIAN, jaroslav@68: CARIAN, jaroslav@68: null, jaroslav@68: OLD_ITALIC, jaroslav@68: GOTHIC, jaroslav@68: null, jaroslav@68: UGARITIC, jaroslav@68: OLD_PERSIAN, jaroslav@68: null, jaroslav@68: DESERET, jaroslav@68: SHAVIAN, jaroslav@68: OSMANYA, jaroslav@68: null, jaroslav@68: CYPRIOT_SYLLABARY, jaroslav@68: IMPERIAL_ARAMAIC, jaroslav@68: null, jaroslav@68: PHOENICIAN, jaroslav@68: LYDIAN, jaroslav@68: null, jaroslav@68: KHAROSHTHI, jaroslav@68: OLD_SOUTH_ARABIAN, jaroslav@68: null, jaroslav@68: AVESTAN, jaroslav@68: INSCRIPTIONAL_PARTHIAN, jaroslav@68: INSCRIPTIONAL_PAHLAVI, jaroslav@68: null, jaroslav@68: OLD_TURKIC, jaroslav@68: null, jaroslav@68: RUMI_NUMERAL_SYMBOLS, jaroslav@68: null, jaroslav@68: BRAHMI, jaroslav@68: KAITHI, jaroslav@68: null, jaroslav@68: CUNEIFORM, jaroslav@68: CUNEIFORM_NUMBERS_AND_PUNCTUATION, jaroslav@68: null, jaroslav@68: EGYPTIAN_HIEROGLYPHS, jaroslav@68: null, jaroslav@68: BAMUM_SUPPLEMENT, jaroslav@68: null, jaroslav@68: KANA_SUPPLEMENT, jaroslav@68: null, jaroslav@68: BYZANTINE_MUSICAL_SYMBOLS, jaroslav@68: MUSICAL_SYMBOLS, jaroslav@68: ANCIENT_GREEK_MUSICAL_NOTATION, jaroslav@68: null, jaroslav@68: TAI_XUAN_JING_SYMBOLS, jaroslav@68: COUNTING_ROD_NUMERALS, jaroslav@68: null, jaroslav@68: MATHEMATICAL_ALPHANUMERIC_SYMBOLS, jaroslav@68: null, jaroslav@68: MAHJONG_TILES, jaroslav@68: DOMINO_TILES, jaroslav@68: PLAYING_CARDS, jaroslav@68: ENCLOSED_ALPHANUMERIC_SUPPLEMENT, jaroslav@68: ENCLOSED_IDEOGRAPHIC_SUPPLEMENT, jaroslav@68: MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS, jaroslav@68: EMOTICONS, jaroslav@68: null, jaroslav@68: TRANSPORT_AND_MAP_SYMBOLS, jaroslav@68: ALCHEMICAL_SYMBOLS, jaroslav@68: null, jaroslav@68: CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B, jaroslav@68: null, jaroslav@68: CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C, jaroslav@68: CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D, jaroslav@68: null, jaroslav@68: CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT, jaroslav@68: null, jaroslav@68: TAGS, jaroslav@68: null, jaroslav@68: VARIATION_SELECTORS_SUPPLEMENT, jaroslav@68: null, jaroslav@68: SUPPLEMENTARY_PRIVATE_USE_AREA_A, jaroslav@68: SUPPLEMENTARY_PRIVATE_USE_AREA_B jaroslav@68: }; jaroslav@68: jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the object representing the Unicode block containing the jaroslav@68: * given character, or {@code null} if the character is not a jaroslav@68: * member of a defined block. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle jaroslav@68: * supplementary jaroslav@68: * characters. To support all Unicode characters, including jaroslav@68: * supplementary characters, use the {@link #of(int)} method. jaroslav@68: * jaroslav@68: * @param c The character in question jaroslav@68: * @return The {@code UnicodeBlock} instance representing the jaroslav@68: * Unicode block of which this character is a member, or jaroslav@68: * {@code null} if the character is not a member of any jaroslav@68: * Unicode block jaroslav@68: */ jaroslav@68: public static UnicodeBlock of(char c) { jaroslav@68: return of((int)c); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the object representing the Unicode block jaroslav@68: * containing the given character (Unicode code point), or jaroslav@68: * {@code null} if the character is not a member of a jaroslav@68: * defined block. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) in question. jaroslav@68: * @return The {@code UnicodeBlock} instance representing the jaroslav@68: * Unicode block of which this character is a member, or jaroslav@68: * {@code null} if the character is not a member of any jaroslav@68: * Unicode block jaroslav@68: * @exception IllegalArgumentException if the specified jaroslav@68: * {@code codePoint} is an invalid Unicode code point. jaroslav@68: * @see Character#isValidCodePoint(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static UnicodeBlock of(int codePoint) { jaroslav@68: if (!isValidCodePoint(codePoint)) { jaroslav@68: throw new IllegalArgumentException(); jaroslav@68: } jaroslav@68: jaroslav@68: int top, bottom, current; jaroslav@68: bottom = 0; jaroslav@68: top = blockStarts.length; jaroslav@68: current = top/2; jaroslav@68: jaroslav@68: // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom] jaroslav@68: while (top - bottom > 1) { jaroslav@68: if (codePoint >= blockStarts[current]) { jaroslav@68: bottom = current; jaroslav@68: } else { jaroslav@68: top = current; jaroslav@68: } jaroslav@68: current = (top + bottom) / 2; jaroslav@68: } jaroslav@68: return blocks[current]; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the UnicodeBlock with the given name. Block jaroslav@68: * names are determined by The Unicode Standard. The file jaroslav@68: * Blocks-<version>.txt defines blocks for a particular jaroslav@68: * version of the standard. The {@link Character} class specifies jaroslav@68: * the version of the standard that it supports. jaroslav@68: *

jaroslav@68: * This method accepts block names in the following forms: jaroslav@68: *

    jaroslav@68: *
  1. Canonical block names as defined by the Unicode Standard. jaroslav@68: * For example, the standard defines a "Basic Latin" block. Therefore, this jaroslav@68: * method accepts "Basic Latin" as a valid block name. The documentation of jaroslav@68: * each UnicodeBlock provides the canonical name. jaroslav@68: *
  2. Canonical block names with all spaces removed. For example, "BasicLatin" jaroslav@68: * is a valid block name for the "Basic Latin" block. jaroslav@68: *
  3. The text representation of each constant UnicodeBlock identifier. jaroslav@68: * For example, this method will return the {@link #BASIC_LATIN} block if jaroslav@68: * provided with the "BASIC_LATIN" name. This form replaces all spaces and jaroslav@68: * hyphens in the canonical name with underscores. jaroslav@68: *
jaroslav@68: * Finally, character case is ignored for all of the valid block name forms. jaroslav@68: * For example, "BASIC_LATIN" and "basic_latin" are both valid block names. jaroslav@68: * The en_US locale's case mapping rules are used to provide case-insensitive jaroslav@68: * string comparisons for block name validation. jaroslav@68: *

jaroslav@68: * If the Unicode Standard changes block names, both the previous and jaroslav@68: * current names will be accepted. jaroslav@68: * jaroslav@68: * @param blockName A {@code UnicodeBlock} name. jaroslav@68: * @return The {@code UnicodeBlock} instance identified jaroslav@68: * by {@code blockName} jaroslav@68: * @throws IllegalArgumentException if {@code blockName} is an jaroslav@68: * invalid name jaroslav@68: * @throws NullPointerException if {@code blockName} is null jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final UnicodeBlock forName(String blockName) { jaroslav@68: UnicodeBlock block = map.get(blockName.toUpperCase(Locale.US)); jaroslav@68: if (block == null) { jaroslav@68: throw new IllegalArgumentException(); jaroslav@68: } jaroslav@68: return block; jaroslav@68: } jaroslav@68: } jaroslav@68: jaroslav@68: jaroslav@68: /** jaroslav@68: * A family of character subsets representing the character scripts jaroslav@68: * defined in the jaroslav@68: * Unicode Standard Annex #24: Script Names. Every Unicode jaroslav@68: * character is assigned to a single Unicode script, either a specific jaroslav@68: * script, such as {@link Character.UnicodeScript#LATIN Latin}, or jaroslav@68: * one of the following three special values, jaroslav@68: * {@link Character.UnicodeScript#INHERITED Inherited}, jaroslav@68: * {@link Character.UnicodeScript#COMMON Common} or jaroslav@68: * {@link Character.UnicodeScript#UNKNOWN Unknown}. jaroslav@68: * jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static enum UnicodeScript { jaroslav@68: /** jaroslav@68: * Unicode script "Common". jaroslav@68: */ jaroslav@68: COMMON, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Latin". jaroslav@68: */ jaroslav@68: LATIN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Greek". jaroslav@68: */ jaroslav@68: GREEK, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Cyrillic". jaroslav@68: */ jaroslav@68: CYRILLIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Armenian". jaroslav@68: */ jaroslav@68: ARMENIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Hebrew". jaroslav@68: */ jaroslav@68: HEBREW, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Arabic". jaroslav@68: */ jaroslav@68: ARABIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Syriac". jaroslav@68: */ jaroslav@68: SYRIAC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Thaana". jaroslav@68: */ jaroslav@68: THAANA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Devanagari". jaroslav@68: */ jaroslav@68: DEVANAGARI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Bengali". jaroslav@68: */ jaroslav@68: BENGALI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Gurmukhi". jaroslav@68: */ jaroslav@68: GURMUKHI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Gujarati". jaroslav@68: */ jaroslav@68: GUJARATI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Oriya". jaroslav@68: */ jaroslav@68: ORIYA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tamil". jaroslav@68: */ jaroslav@68: TAMIL, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Telugu". jaroslav@68: */ jaroslav@68: TELUGU, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Kannada". jaroslav@68: */ jaroslav@68: KANNADA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Malayalam". jaroslav@68: */ jaroslav@68: MALAYALAM, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Sinhala". jaroslav@68: */ jaroslav@68: SINHALA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Thai". jaroslav@68: */ jaroslav@68: THAI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Lao". jaroslav@68: */ jaroslav@68: LAO, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tibetan". jaroslav@68: */ jaroslav@68: TIBETAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Myanmar". jaroslav@68: */ jaroslav@68: MYANMAR, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Georgian". jaroslav@68: */ jaroslav@68: GEORGIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Hangul". jaroslav@68: */ jaroslav@68: HANGUL, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Ethiopic". jaroslav@68: */ jaroslav@68: ETHIOPIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Cherokee". jaroslav@68: */ jaroslav@68: CHEROKEE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Canadian_Aboriginal". jaroslav@68: */ jaroslav@68: CANADIAN_ABORIGINAL, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Ogham". jaroslav@68: */ jaroslav@68: OGHAM, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Runic". jaroslav@68: */ jaroslav@68: RUNIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Khmer". jaroslav@68: */ jaroslav@68: KHMER, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Mongolian". jaroslav@68: */ jaroslav@68: MONGOLIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Hiragana". jaroslav@68: */ jaroslav@68: HIRAGANA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Katakana". jaroslav@68: */ jaroslav@68: KATAKANA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Bopomofo". jaroslav@68: */ jaroslav@68: BOPOMOFO, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Han". jaroslav@68: */ jaroslav@68: HAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Yi". jaroslav@68: */ jaroslav@68: YI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Old_Italic". jaroslav@68: */ jaroslav@68: OLD_ITALIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Gothic". jaroslav@68: */ jaroslav@68: GOTHIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Deseret". jaroslav@68: */ jaroslav@68: DESERET, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Inherited". jaroslav@68: */ jaroslav@68: INHERITED, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tagalog". jaroslav@68: */ jaroslav@68: TAGALOG, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Hanunoo". jaroslav@68: */ jaroslav@68: HANUNOO, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Buhid". jaroslav@68: */ jaroslav@68: BUHID, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tagbanwa". jaroslav@68: */ jaroslav@68: TAGBANWA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Limbu". jaroslav@68: */ jaroslav@68: LIMBU, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tai_Le". jaroslav@68: */ jaroslav@68: TAI_LE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Linear_B". jaroslav@68: */ jaroslav@68: LINEAR_B, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Ugaritic". jaroslav@68: */ jaroslav@68: UGARITIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Shavian". jaroslav@68: */ jaroslav@68: SHAVIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Osmanya". jaroslav@68: */ jaroslav@68: OSMANYA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Cypriot". jaroslav@68: */ jaroslav@68: CYPRIOT, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Braille". jaroslav@68: */ jaroslav@68: BRAILLE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Buginese". jaroslav@68: */ jaroslav@68: BUGINESE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Coptic". jaroslav@68: */ jaroslav@68: COPTIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "New_Tai_Lue". jaroslav@68: */ jaroslav@68: NEW_TAI_LUE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Glagolitic". jaroslav@68: */ jaroslav@68: GLAGOLITIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tifinagh". jaroslav@68: */ jaroslav@68: TIFINAGH, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Syloti_Nagri". jaroslav@68: */ jaroslav@68: SYLOTI_NAGRI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Old_Persian". jaroslav@68: */ jaroslav@68: OLD_PERSIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Kharoshthi". jaroslav@68: */ jaroslav@68: KHAROSHTHI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Balinese". jaroslav@68: */ jaroslav@68: BALINESE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Cuneiform". jaroslav@68: */ jaroslav@68: CUNEIFORM, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Phoenician". jaroslav@68: */ jaroslav@68: PHOENICIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Phags_Pa". jaroslav@68: */ jaroslav@68: PHAGS_PA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Nko". jaroslav@68: */ jaroslav@68: NKO, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Sundanese". jaroslav@68: */ jaroslav@68: SUNDANESE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Batak". jaroslav@68: */ jaroslav@68: BATAK, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Lepcha". jaroslav@68: */ jaroslav@68: LEPCHA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Ol_Chiki". jaroslav@68: */ jaroslav@68: OL_CHIKI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Vai". jaroslav@68: */ jaroslav@68: VAI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Saurashtra". jaroslav@68: */ jaroslav@68: SAURASHTRA, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Kayah_Li". jaroslav@68: */ jaroslav@68: KAYAH_LI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Rejang". jaroslav@68: */ jaroslav@68: REJANG, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Lycian". jaroslav@68: */ jaroslav@68: LYCIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Carian". jaroslav@68: */ jaroslav@68: CARIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Lydian". jaroslav@68: */ jaroslav@68: LYDIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Cham". jaroslav@68: */ jaroslav@68: CHAM, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tai_Tham". jaroslav@68: */ jaroslav@68: TAI_THAM, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Tai_Viet". jaroslav@68: */ jaroslav@68: TAI_VIET, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Avestan". jaroslav@68: */ jaroslav@68: AVESTAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Egyptian_Hieroglyphs". jaroslav@68: */ jaroslav@68: EGYPTIAN_HIEROGLYPHS, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Samaritan". jaroslav@68: */ jaroslav@68: SAMARITAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Mandaic". jaroslav@68: */ jaroslav@68: MANDAIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Lisu". jaroslav@68: */ jaroslav@68: LISU, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Bamum". jaroslav@68: */ jaroslav@68: BAMUM, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Javanese". jaroslav@68: */ jaroslav@68: JAVANESE, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Meetei_Mayek". jaroslav@68: */ jaroslav@68: MEETEI_MAYEK, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Imperial_Aramaic". jaroslav@68: */ jaroslav@68: IMPERIAL_ARAMAIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Old_South_Arabian". jaroslav@68: */ jaroslav@68: OLD_SOUTH_ARABIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Inscriptional_Parthian". jaroslav@68: */ jaroslav@68: INSCRIPTIONAL_PARTHIAN, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Inscriptional_Pahlavi". jaroslav@68: */ jaroslav@68: INSCRIPTIONAL_PAHLAVI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Old_Turkic". jaroslav@68: */ jaroslav@68: OLD_TURKIC, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Brahmi". jaroslav@68: */ jaroslav@68: BRAHMI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Kaithi". jaroslav@68: */ jaroslav@68: KAITHI, jaroslav@68: jaroslav@68: /** jaroslav@68: * Unicode script "Unknown". jaroslav@68: */ jaroslav@68: UNKNOWN; jaroslav@68: jaroslav@68: private static final int[] scriptStarts = { jaroslav@68: 0x0000, // 0000..0040; COMMON jaroslav@68: 0x0041, // 0041..005A; LATIN jaroslav@68: 0x005B, // 005B..0060; COMMON jaroslav@68: 0x0061, // 0061..007A; LATIN jaroslav@68: 0x007B, // 007B..00A9; COMMON jaroslav@68: 0x00AA, // 00AA..00AA; LATIN jaroslav@68: 0x00AB, // 00AB..00B9; COMMON jaroslav@68: 0x00BA, // 00BA..00BA; LATIN jaroslav@68: 0x00BB, // 00BB..00BF; COMMON jaroslav@68: 0x00C0, // 00C0..00D6; LATIN jaroslav@68: 0x00D7, // 00D7..00D7; COMMON jaroslav@68: 0x00D8, // 00D8..00F6; LATIN jaroslav@68: 0x00F7, // 00F7..00F7; COMMON jaroslav@68: 0x00F8, // 00F8..02B8; LATIN jaroslav@68: 0x02B9, // 02B9..02DF; COMMON jaroslav@68: 0x02E0, // 02E0..02E4; LATIN jaroslav@68: 0x02E5, // 02E5..02E9; COMMON jaroslav@68: 0x02EA, // 02EA..02EB; BOPOMOFO jaroslav@68: 0x02EC, // 02EC..02FF; COMMON jaroslav@68: 0x0300, // 0300..036F; INHERITED jaroslav@68: 0x0370, // 0370..0373; GREEK jaroslav@68: 0x0374, // 0374..0374; COMMON jaroslav@68: 0x0375, // 0375..037D; GREEK jaroslav@68: 0x037E, // 037E..0383; COMMON jaroslav@68: 0x0384, // 0384..0384; GREEK jaroslav@68: 0x0385, // 0385..0385; COMMON jaroslav@68: 0x0386, // 0386..0386; GREEK jaroslav@68: 0x0387, // 0387..0387; COMMON jaroslav@68: 0x0388, // 0388..03E1; GREEK jaroslav@68: 0x03E2, // 03E2..03EF; COPTIC jaroslav@68: 0x03F0, // 03F0..03FF; GREEK jaroslav@68: 0x0400, // 0400..0484; CYRILLIC jaroslav@68: 0x0485, // 0485..0486; INHERITED jaroslav@68: 0x0487, // 0487..0530; CYRILLIC jaroslav@68: 0x0531, // 0531..0588; ARMENIAN jaroslav@68: 0x0589, // 0589..0589; COMMON jaroslav@68: 0x058A, // 058A..0590; ARMENIAN jaroslav@68: 0x0591, // 0591..05FF; HEBREW jaroslav@68: 0x0600, // 0600..060B; ARABIC jaroslav@68: 0x060C, // 060C..060C; COMMON jaroslav@68: 0x060D, // 060D..061A; ARABIC jaroslav@68: 0x061B, // 061B..061D; COMMON jaroslav@68: 0x061E, // 061E..061E; ARABIC jaroslav@68: 0x061F, // 061F..061F; COMMON jaroslav@68: 0x0620, // 0620..063F; ARABIC jaroslav@68: 0x0640, // 0640..0640; COMMON jaroslav@68: 0x0641, // 0641..064A; ARABIC jaroslav@68: 0x064B, // 064B..0655; INHERITED jaroslav@68: 0x0656, // 0656..065E; ARABIC jaroslav@68: 0x065F, // 065F..065F; INHERITED jaroslav@68: 0x0660, // 0660..0669; COMMON jaroslav@68: 0x066A, // 066A..066F; ARABIC jaroslav@68: 0x0670, // 0670..0670; INHERITED jaroslav@68: 0x0671, // 0671..06DC; ARABIC jaroslav@68: 0x06DD, // 06DD..06DD; COMMON jaroslav@68: 0x06DE, // 06DE..06FF; ARABIC jaroslav@68: 0x0700, // 0700..074F; SYRIAC jaroslav@68: 0x0750, // 0750..077F; ARABIC jaroslav@68: 0x0780, // 0780..07BF; THAANA jaroslav@68: 0x07C0, // 07C0..07FF; NKO jaroslav@68: 0x0800, // 0800..083F; SAMARITAN jaroslav@68: 0x0840, // 0840..08FF; MANDAIC jaroslav@68: 0x0900, // 0900..0950; DEVANAGARI jaroslav@68: 0x0951, // 0951..0952; INHERITED jaroslav@68: 0x0953, // 0953..0963; DEVANAGARI jaroslav@68: 0x0964, // 0964..0965; COMMON jaroslav@68: 0x0966, // 0966..096F; DEVANAGARI jaroslav@68: 0x0970, // 0970..0970; COMMON jaroslav@68: 0x0971, // 0971..0980; DEVANAGARI jaroslav@68: 0x0981, // 0981..0A00; BENGALI jaroslav@68: 0x0A01, // 0A01..0A80; GURMUKHI jaroslav@68: 0x0A81, // 0A81..0B00; GUJARATI jaroslav@68: 0x0B01, // 0B01..0B81; ORIYA jaroslav@68: 0x0B82, // 0B82..0C00; TAMIL jaroslav@68: 0x0C01, // 0C01..0C81; TELUGU jaroslav@68: 0x0C82, // 0C82..0CF0; KANNADA jaroslav@68: 0x0D02, // 0D02..0D81; MALAYALAM jaroslav@68: 0x0D82, // 0D82..0E00; SINHALA jaroslav@68: 0x0E01, // 0E01..0E3E; THAI jaroslav@68: 0x0E3F, // 0E3F..0E3F; COMMON jaroslav@68: 0x0E40, // 0E40..0E80; THAI jaroslav@68: 0x0E81, // 0E81..0EFF; LAO jaroslav@68: 0x0F00, // 0F00..0FD4; TIBETAN jaroslav@68: 0x0FD5, // 0FD5..0FD8; COMMON jaroslav@68: 0x0FD9, // 0FD9..0FFF; TIBETAN jaroslav@68: 0x1000, // 1000..109F; MYANMAR jaroslav@68: 0x10A0, // 10A0..10FA; GEORGIAN jaroslav@68: 0x10FB, // 10FB..10FB; COMMON jaroslav@68: 0x10FC, // 10FC..10FF; GEORGIAN jaroslav@68: 0x1100, // 1100..11FF; HANGUL jaroslav@68: 0x1200, // 1200..139F; ETHIOPIC jaroslav@68: 0x13A0, // 13A0..13FF; CHEROKEE jaroslav@68: 0x1400, // 1400..167F; CANADIAN_ABORIGINAL jaroslav@68: 0x1680, // 1680..169F; OGHAM jaroslav@68: 0x16A0, // 16A0..16EA; RUNIC jaroslav@68: 0x16EB, // 16EB..16ED; COMMON jaroslav@68: 0x16EE, // 16EE..16FF; RUNIC jaroslav@68: 0x1700, // 1700..171F; TAGALOG jaroslav@68: 0x1720, // 1720..1734; HANUNOO jaroslav@68: 0x1735, // 1735..173F; COMMON jaroslav@68: 0x1740, // 1740..175F; BUHID jaroslav@68: 0x1760, // 1760..177F; TAGBANWA jaroslav@68: 0x1780, // 1780..17FF; KHMER jaroslav@68: 0x1800, // 1800..1801; MONGOLIAN jaroslav@68: 0x1802, // 1802..1803; COMMON jaroslav@68: 0x1804, // 1804..1804; MONGOLIAN jaroslav@68: 0x1805, // 1805..1805; COMMON jaroslav@68: 0x1806, // 1806..18AF; MONGOLIAN jaroslav@68: 0x18B0, // 18B0..18FF; CANADIAN_ABORIGINAL jaroslav@68: 0x1900, // 1900..194F; LIMBU jaroslav@68: 0x1950, // 1950..197F; TAI_LE jaroslav@68: 0x1980, // 1980..19DF; NEW_TAI_LUE jaroslav@68: 0x19E0, // 19E0..19FF; KHMER jaroslav@68: 0x1A00, // 1A00..1A1F; BUGINESE jaroslav@68: 0x1A20, // 1A20..1AFF; TAI_THAM jaroslav@68: 0x1B00, // 1B00..1B7F; BALINESE jaroslav@68: 0x1B80, // 1B80..1BBF; SUNDANESE jaroslav@68: 0x1BC0, // 1BC0..1BFF; BATAK jaroslav@68: 0x1C00, // 1C00..1C4F; LEPCHA jaroslav@68: 0x1C50, // 1C50..1CCF; OL_CHIKI jaroslav@68: 0x1CD0, // 1CD0..1CD2; INHERITED jaroslav@68: 0x1CD3, // 1CD3..1CD3; COMMON jaroslav@68: 0x1CD4, // 1CD4..1CE0; INHERITED jaroslav@68: 0x1CE1, // 1CE1..1CE1; COMMON jaroslav@68: 0x1CE2, // 1CE2..1CE8; INHERITED jaroslav@68: 0x1CE9, // 1CE9..1CEC; COMMON jaroslav@68: 0x1CED, // 1CED..1CED; INHERITED jaroslav@68: 0x1CEE, // 1CEE..1CFF; COMMON jaroslav@68: 0x1D00, // 1D00..1D25; LATIN jaroslav@68: 0x1D26, // 1D26..1D2A; GREEK jaroslav@68: 0x1D2B, // 1D2B..1D2B; CYRILLIC jaroslav@68: 0x1D2C, // 1D2C..1D5C; LATIN jaroslav@68: 0x1D5D, // 1D5D..1D61; GREEK jaroslav@68: 0x1D62, // 1D62..1D65; LATIN jaroslav@68: 0x1D66, // 1D66..1D6A; GREEK jaroslav@68: 0x1D6B, // 1D6B..1D77; LATIN jaroslav@68: 0x1D78, // 1D78..1D78; CYRILLIC jaroslav@68: 0x1D79, // 1D79..1DBE; LATIN jaroslav@68: 0x1DBF, // 1DBF..1DBF; GREEK jaroslav@68: 0x1DC0, // 1DC0..1DFF; INHERITED jaroslav@68: 0x1E00, // 1E00..1EFF; LATIN jaroslav@68: 0x1F00, // 1F00..1FFF; GREEK jaroslav@68: 0x2000, // 2000..200B; COMMON jaroslav@68: 0x200C, // 200C..200D; INHERITED jaroslav@68: 0x200E, // 200E..2070; COMMON jaroslav@68: 0x2071, // 2071..2073; LATIN jaroslav@68: 0x2074, // 2074..207E; COMMON jaroslav@68: 0x207F, // 207F..207F; LATIN jaroslav@68: 0x2080, // 2080..208F; COMMON jaroslav@68: 0x2090, // 2090..209F; LATIN jaroslav@68: 0x20A0, // 20A0..20CF; COMMON jaroslav@68: 0x20D0, // 20D0..20FF; INHERITED jaroslav@68: 0x2100, // 2100..2125; COMMON jaroslav@68: 0x2126, // 2126..2126; GREEK jaroslav@68: 0x2127, // 2127..2129; COMMON jaroslav@68: 0x212A, // 212A..212B; LATIN jaroslav@68: 0x212C, // 212C..2131; COMMON jaroslav@68: 0x2132, // 2132..2132; LATIN jaroslav@68: 0x2133, // 2133..214D; COMMON jaroslav@68: 0x214E, // 214E..214E; LATIN jaroslav@68: 0x214F, // 214F..215F; COMMON jaroslav@68: 0x2160, // 2160..2188; LATIN jaroslav@68: 0x2189, // 2189..27FF; COMMON jaroslav@68: 0x2800, // 2800..28FF; BRAILLE jaroslav@68: 0x2900, // 2900..2BFF; COMMON jaroslav@68: 0x2C00, // 2C00..2C5F; GLAGOLITIC jaroslav@68: 0x2C60, // 2C60..2C7F; LATIN jaroslav@68: 0x2C80, // 2C80..2CFF; COPTIC jaroslav@68: 0x2D00, // 2D00..2D2F; GEORGIAN jaroslav@68: 0x2D30, // 2D30..2D7F; TIFINAGH jaroslav@68: 0x2D80, // 2D80..2DDF; ETHIOPIC jaroslav@68: 0x2DE0, // 2DE0..2DFF; CYRILLIC jaroslav@68: 0x2E00, // 2E00..2E7F; COMMON jaroslav@68: 0x2E80, // 2E80..2FEF; HAN jaroslav@68: 0x2FF0, // 2FF0..3004; COMMON jaroslav@68: 0x3005, // 3005..3005; HAN jaroslav@68: 0x3006, // 3006..3006; COMMON jaroslav@68: 0x3007, // 3007..3007; HAN jaroslav@68: 0x3008, // 3008..3020; COMMON jaroslav@68: 0x3021, // 3021..3029; HAN jaroslav@68: 0x302A, // 302A..302D; INHERITED jaroslav@68: 0x302E, // 302E..302F; HANGUL jaroslav@68: 0x3030, // 3030..3037; COMMON jaroslav@68: 0x3038, // 3038..303B; HAN jaroslav@68: 0x303C, // 303C..3040; COMMON jaroslav@68: 0x3041, // 3041..3098; HIRAGANA jaroslav@68: 0x3099, // 3099..309A; INHERITED jaroslav@68: 0x309B, // 309B..309C; COMMON jaroslav@68: 0x309D, // 309D..309F; HIRAGANA jaroslav@68: 0x30A0, // 30A0..30A0; COMMON jaroslav@68: 0x30A1, // 30A1..30FA; KATAKANA jaroslav@68: 0x30FB, // 30FB..30FC; COMMON jaroslav@68: 0x30FD, // 30FD..3104; KATAKANA jaroslav@68: 0x3105, // 3105..3130; BOPOMOFO jaroslav@68: 0x3131, // 3131..318F; HANGUL jaroslav@68: 0x3190, // 3190..319F; COMMON jaroslav@68: 0x31A0, // 31A0..31BF; BOPOMOFO jaroslav@68: 0x31C0, // 31C0..31EF; COMMON jaroslav@68: 0x31F0, // 31F0..31FF; KATAKANA jaroslav@68: 0x3200, // 3200..321F; HANGUL jaroslav@68: 0x3220, // 3220..325F; COMMON jaroslav@68: 0x3260, // 3260..327E; HANGUL jaroslav@68: 0x327F, // 327F..32CF; COMMON jaroslav@68: 0x32D0, // 32D0..3357; KATAKANA jaroslav@68: 0x3358, // 3358..33FF; COMMON jaroslav@68: 0x3400, // 3400..4DBF; HAN jaroslav@68: 0x4DC0, // 4DC0..4DFF; COMMON jaroslav@68: 0x4E00, // 4E00..9FFF; HAN jaroslav@68: 0xA000, // A000..A4CF; YI jaroslav@68: 0xA4D0, // A4D0..A4FF; LISU jaroslav@68: 0xA500, // A500..A63F; VAI jaroslav@68: 0xA640, // A640..A69F; CYRILLIC jaroslav@68: 0xA6A0, // A6A0..A6FF; BAMUM jaroslav@68: 0xA700, // A700..A721; COMMON jaroslav@68: 0xA722, // A722..A787; LATIN jaroslav@68: 0xA788, // A788..A78A; COMMON jaroslav@68: 0xA78B, // A78B..A7FF; LATIN jaroslav@68: 0xA800, // A800..A82F; SYLOTI_NAGRI jaroslav@68: 0xA830, // A830..A83F; COMMON jaroslav@68: 0xA840, // A840..A87F; PHAGS_PA jaroslav@68: 0xA880, // A880..A8DF; SAURASHTRA jaroslav@68: 0xA8E0, // A8E0..A8FF; DEVANAGARI jaroslav@68: 0xA900, // A900..A92F; KAYAH_LI jaroslav@68: 0xA930, // A930..A95F; REJANG jaroslav@68: 0xA960, // A960..A97F; HANGUL jaroslav@68: 0xA980, // A980..A9FF; JAVANESE jaroslav@68: 0xAA00, // AA00..AA5F; CHAM jaroslav@68: 0xAA60, // AA60..AA7F; MYANMAR jaroslav@68: 0xAA80, // AA80..AB00; TAI_VIET jaroslav@68: 0xAB01, // AB01..ABBF; ETHIOPIC jaroslav@68: 0xABC0, // ABC0..ABFF; MEETEI_MAYEK jaroslav@68: 0xAC00, // AC00..D7FB; HANGUL jaroslav@68: 0xD7FC, // D7FC..F8FF; UNKNOWN jaroslav@68: 0xF900, // F900..FAFF; HAN jaroslav@68: 0xFB00, // FB00..FB12; LATIN jaroslav@68: 0xFB13, // FB13..FB1C; ARMENIAN jaroslav@68: 0xFB1D, // FB1D..FB4F; HEBREW jaroslav@68: 0xFB50, // FB50..FD3D; ARABIC jaroslav@68: 0xFD3E, // FD3E..FD4F; COMMON jaroslav@68: 0xFD50, // FD50..FDFC; ARABIC jaroslav@68: 0xFDFD, // FDFD..FDFF; COMMON jaroslav@68: 0xFE00, // FE00..FE0F; INHERITED jaroslav@68: 0xFE10, // FE10..FE1F; COMMON jaroslav@68: 0xFE20, // FE20..FE2F; INHERITED jaroslav@68: 0xFE30, // FE30..FE6F; COMMON jaroslav@68: 0xFE70, // FE70..FEFE; ARABIC jaroslav@68: 0xFEFF, // FEFF..FF20; COMMON jaroslav@68: 0xFF21, // FF21..FF3A; LATIN jaroslav@68: 0xFF3B, // FF3B..FF40; COMMON jaroslav@68: 0xFF41, // FF41..FF5A; LATIN jaroslav@68: 0xFF5B, // FF5B..FF65; COMMON jaroslav@68: 0xFF66, // FF66..FF6F; KATAKANA jaroslav@68: 0xFF70, // FF70..FF70; COMMON jaroslav@68: 0xFF71, // FF71..FF9D; KATAKANA jaroslav@68: 0xFF9E, // FF9E..FF9F; COMMON jaroslav@68: 0xFFA0, // FFA0..FFDF; HANGUL jaroslav@68: 0xFFE0, // FFE0..FFFF; COMMON jaroslav@68: 0x10000, // 10000..100FF; LINEAR_B jaroslav@68: 0x10100, // 10100..1013F; COMMON jaroslav@68: 0x10140, // 10140..1018F; GREEK jaroslav@68: 0x10190, // 10190..101FC; COMMON jaroslav@68: 0x101FD, // 101FD..1027F; INHERITED jaroslav@68: 0x10280, // 10280..1029F; LYCIAN jaroslav@68: 0x102A0, // 102A0..102FF; CARIAN jaroslav@68: 0x10300, // 10300..1032F; OLD_ITALIC jaroslav@68: 0x10330, // 10330..1037F; GOTHIC jaroslav@68: 0x10380, // 10380..1039F; UGARITIC jaroslav@68: 0x103A0, // 103A0..103FF; OLD_PERSIAN jaroslav@68: 0x10400, // 10400..1044F; DESERET jaroslav@68: 0x10450, // 10450..1047F; SHAVIAN jaroslav@68: 0x10480, // 10480..107FF; OSMANYA jaroslav@68: 0x10800, // 10800..1083F; CYPRIOT jaroslav@68: 0x10840, // 10840..108FF; IMPERIAL_ARAMAIC jaroslav@68: 0x10900, // 10900..1091F; PHOENICIAN jaroslav@68: 0x10920, // 10920..109FF; LYDIAN jaroslav@68: 0x10A00, // 10A00..10A5F; KHAROSHTHI jaroslav@68: 0x10A60, // 10A60..10AFF; OLD_SOUTH_ARABIAN jaroslav@68: 0x10B00, // 10B00..10B3F; AVESTAN jaroslav@68: 0x10B40, // 10B40..10B5F; INSCRIPTIONAL_PARTHIAN jaroslav@68: 0x10B60, // 10B60..10BFF; INSCRIPTIONAL_PAHLAVI jaroslav@68: 0x10C00, // 10C00..10E5F; OLD_TURKIC jaroslav@68: 0x10E60, // 10E60..10FFF; ARABIC jaroslav@68: 0x11000, // 11000..1107F; BRAHMI jaroslav@68: 0x11080, // 11080..11FFF; KAITHI jaroslav@68: 0x12000, // 12000..12FFF; CUNEIFORM jaroslav@68: 0x13000, // 13000..167FF; EGYPTIAN_HIEROGLYPHS jaroslav@68: 0x16800, // 16800..16A38; BAMUM jaroslav@68: 0x1B000, // 1B000..1B000; KATAKANA jaroslav@68: 0x1B001, // 1B001..1CFFF; HIRAGANA jaroslav@68: 0x1D000, // 1D000..1D166; COMMON jaroslav@68: 0x1D167, // 1D167..1D169; INHERITED jaroslav@68: 0x1D16A, // 1D16A..1D17A; COMMON jaroslav@68: 0x1D17B, // 1D17B..1D182; INHERITED jaroslav@68: 0x1D183, // 1D183..1D184; COMMON jaroslav@68: 0x1D185, // 1D185..1D18B; INHERITED jaroslav@68: 0x1D18C, // 1D18C..1D1A9; COMMON jaroslav@68: 0x1D1AA, // 1D1AA..1D1AD; INHERITED jaroslav@68: 0x1D1AE, // 1D1AE..1D1FF; COMMON jaroslav@68: 0x1D200, // 1D200..1D2FF; GREEK jaroslav@68: 0x1D300, // 1D300..1F1FF; COMMON jaroslav@68: 0x1F200, // 1F200..1F200; HIRAGANA jaroslav@68: 0x1F201, // 1F210..1FFFF; COMMON jaroslav@68: 0x20000, // 20000..E0000; HAN jaroslav@68: 0xE0001, // E0001..E00FF; COMMON jaroslav@68: 0xE0100, // E0100..E01EF; INHERITED jaroslav@68: 0xE01F0 // E01F0..10FFFF; UNKNOWN jaroslav@68: jaroslav@68: }; jaroslav@68: jaroslav@68: private static final UnicodeScript[] scripts = { jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: BOPOMOFO, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: GREEK, jaroslav@68: COPTIC, jaroslav@68: GREEK, jaroslav@68: CYRILLIC, jaroslav@68: INHERITED, jaroslav@68: CYRILLIC, jaroslav@68: ARMENIAN, jaroslav@68: COMMON, jaroslav@68: ARMENIAN, jaroslav@68: HEBREW, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: INHERITED, jaroslav@68: ARABIC, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: INHERITED, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: SYRIAC, jaroslav@68: ARABIC, jaroslav@68: THAANA, jaroslav@68: NKO, jaroslav@68: SAMARITAN, jaroslav@68: MANDAIC, jaroslav@68: DEVANAGARI, jaroslav@68: INHERITED, jaroslav@68: DEVANAGARI, jaroslav@68: COMMON, jaroslav@68: DEVANAGARI, jaroslav@68: COMMON, jaroslav@68: DEVANAGARI, jaroslav@68: BENGALI, jaroslav@68: GURMUKHI, jaroslav@68: GUJARATI, jaroslav@68: ORIYA, jaroslav@68: TAMIL, jaroslav@68: TELUGU, jaroslav@68: KANNADA, jaroslav@68: MALAYALAM, jaroslav@68: SINHALA, jaroslav@68: THAI, jaroslav@68: COMMON, jaroslav@68: THAI, jaroslav@68: LAO, jaroslav@68: TIBETAN, jaroslav@68: COMMON, jaroslav@68: TIBETAN, jaroslav@68: MYANMAR, jaroslav@68: GEORGIAN, jaroslav@68: COMMON, jaroslav@68: GEORGIAN, jaroslav@68: HANGUL, jaroslav@68: ETHIOPIC, jaroslav@68: CHEROKEE, jaroslav@68: CANADIAN_ABORIGINAL, jaroslav@68: OGHAM, jaroslav@68: RUNIC, jaroslav@68: COMMON, jaroslav@68: RUNIC, jaroslav@68: TAGALOG, jaroslav@68: HANUNOO, jaroslav@68: COMMON, jaroslav@68: BUHID, jaroslav@68: TAGBANWA, jaroslav@68: KHMER, jaroslav@68: MONGOLIAN, jaroslav@68: COMMON, jaroslav@68: MONGOLIAN, jaroslav@68: COMMON, jaroslav@68: MONGOLIAN, jaroslav@68: CANADIAN_ABORIGINAL, jaroslav@68: LIMBU, jaroslav@68: TAI_LE, jaroslav@68: NEW_TAI_LUE, jaroslav@68: KHMER, jaroslav@68: BUGINESE, jaroslav@68: TAI_THAM, jaroslav@68: BALINESE, jaroslav@68: SUNDANESE, jaroslav@68: BATAK, jaroslav@68: LEPCHA, jaroslav@68: OL_CHIKI, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: GREEK, jaroslav@68: CYRILLIC, jaroslav@68: LATIN, jaroslav@68: GREEK, jaroslav@68: LATIN, jaroslav@68: GREEK, jaroslav@68: LATIN, jaroslav@68: CYRILLIC, jaroslav@68: LATIN, jaroslav@68: GREEK, jaroslav@68: INHERITED, jaroslav@68: LATIN, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: BRAILLE, jaroslav@68: COMMON, jaroslav@68: GLAGOLITIC, jaroslav@68: LATIN, jaroslav@68: COPTIC, jaroslav@68: GEORGIAN, jaroslav@68: TIFINAGH, jaroslav@68: ETHIOPIC, jaroslav@68: CYRILLIC, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: INHERITED, jaroslav@68: HANGUL, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: COMMON, jaroslav@68: HIRAGANA, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: HIRAGANA, jaroslav@68: COMMON, jaroslav@68: KATAKANA, jaroslav@68: COMMON, jaroslav@68: KATAKANA, jaroslav@68: BOPOMOFO, jaroslav@68: HANGUL, jaroslav@68: COMMON, jaroslav@68: BOPOMOFO, jaroslav@68: COMMON, jaroslav@68: KATAKANA, jaroslav@68: HANGUL, jaroslav@68: COMMON, jaroslav@68: HANGUL, jaroslav@68: COMMON, jaroslav@68: KATAKANA, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: YI, jaroslav@68: LISU, jaroslav@68: VAI, jaroslav@68: CYRILLIC, jaroslav@68: BAMUM, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: SYLOTI_NAGRI, jaroslav@68: COMMON, jaroslav@68: PHAGS_PA, jaroslav@68: SAURASHTRA, jaroslav@68: DEVANAGARI, jaroslav@68: KAYAH_LI, jaroslav@68: REJANG, jaroslav@68: HANGUL, jaroslav@68: JAVANESE, jaroslav@68: CHAM, jaroslav@68: MYANMAR, jaroslav@68: TAI_VIET, jaroslav@68: ETHIOPIC, jaroslav@68: MEETEI_MAYEK, jaroslav@68: HANGUL, jaroslav@68: UNKNOWN, jaroslav@68: HAN, jaroslav@68: LATIN, jaroslav@68: ARMENIAN, jaroslav@68: HEBREW, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: ARABIC, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: LATIN, jaroslav@68: COMMON, jaroslav@68: KATAKANA, jaroslav@68: COMMON, jaroslav@68: KATAKANA, jaroslav@68: COMMON, jaroslav@68: HANGUL, jaroslav@68: COMMON, jaroslav@68: LINEAR_B, jaroslav@68: COMMON, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: LYCIAN, jaroslav@68: CARIAN, jaroslav@68: OLD_ITALIC, jaroslav@68: GOTHIC, jaroslav@68: UGARITIC, jaroslav@68: OLD_PERSIAN, jaroslav@68: DESERET, jaroslav@68: SHAVIAN, jaroslav@68: OSMANYA, jaroslav@68: CYPRIOT, jaroslav@68: IMPERIAL_ARAMAIC, jaroslav@68: PHOENICIAN, jaroslav@68: LYDIAN, jaroslav@68: KHAROSHTHI, jaroslav@68: OLD_SOUTH_ARABIAN, jaroslav@68: AVESTAN, jaroslav@68: INSCRIPTIONAL_PARTHIAN, jaroslav@68: INSCRIPTIONAL_PAHLAVI, jaroslav@68: OLD_TURKIC, jaroslav@68: ARABIC, jaroslav@68: BRAHMI, jaroslav@68: KAITHI, jaroslav@68: CUNEIFORM, jaroslav@68: EGYPTIAN_HIEROGLYPHS, jaroslav@68: BAMUM, jaroslav@68: KATAKANA, jaroslav@68: HIRAGANA, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: COMMON, jaroslav@68: GREEK, jaroslav@68: COMMON, jaroslav@68: HIRAGANA, jaroslav@68: COMMON, jaroslav@68: HAN, jaroslav@68: COMMON, jaroslav@68: INHERITED, jaroslav@68: UNKNOWN jaroslav@68: }; jaroslav@68: jaroslav@68: private static HashMap aliases; jaroslav@68: static { jaroslav@68: aliases = new HashMap<>(128); jaroslav@68: aliases.put("ARAB", ARABIC); jaroslav@68: aliases.put("ARMI", IMPERIAL_ARAMAIC); jaroslav@68: aliases.put("ARMN", ARMENIAN); jaroslav@68: aliases.put("AVST", AVESTAN); jaroslav@68: aliases.put("BALI", BALINESE); jaroslav@68: aliases.put("BAMU", BAMUM); jaroslav@68: aliases.put("BATK", BATAK); jaroslav@68: aliases.put("BENG", BENGALI); jaroslav@68: aliases.put("BOPO", BOPOMOFO); jaroslav@68: aliases.put("BRAI", BRAILLE); jaroslav@68: aliases.put("BRAH", BRAHMI); jaroslav@68: aliases.put("BUGI", BUGINESE); jaroslav@68: aliases.put("BUHD", BUHID); jaroslav@68: aliases.put("CANS", CANADIAN_ABORIGINAL); jaroslav@68: aliases.put("CARI", CARIAN); jaroslav@68: aliases.put("CHAM", CHAM); jaroslav@68: aliases.put("CHER", CHEROKEE); jaroslav@68: aliases.put("COPT", COPTIC); jaroslav@68: aliases.put("CPRT", CYPRIOT); jaroslav@68: aliases.put("CYRL", CYRILLIC); jaroslav@68: aliases.put("DEVA", DEVANAGARI); jaroslav@68: aliases.put("DSRT", DESERET); jaroslav@68: aliases.put("EGYP", EGYPTIAN_HIEROGLYPHS); jaroslav@68: aliases.put("ETHI", ETHIOPIC); jaroslav@68: aliases.put("GEOR", GEORGIAN); jaroslav@68: aliases.put("GLAG", GLAGOLITIC); jaroslav@68: aliases.put("GOTH", GOTHIC); jaroslav@68: aliases.put("GREK", GREEK); jaroslav@68: aliases.put("GUJR", GUJARATI); jaroslav@68: aliases.put("GURU", GURMUKHI); jaroslav@68: aliases.put("HANG", HANGUL); jaroslav@68: aliases.put("HANI", HAN); jaroslav@68: aliases.put("HANO", HANUNOO); jaroslav@68: aliases.put("HEBR", HEBREW); jaroslav@68: aliases.put("HIRA", HIRAGANA); jaroslav@68: // it appears we don't have the KATAKANA_OR_HIRAGANA jaroslav@68: //aliases.put("HRKT", KATAKANA_OR_HIRAGANA); jaroslav@68: aliases.put("ITAL", OLD_ITALIC); jaroslav@68: aliases.put("JAVA", JAVANESE); jaroslav@68: aliases.put("KALI", KAYAH_LI); jaroslav@68: aliases.put("KANA", KATAKANA); jaroslav@68: aliases.put("KHAR", KHAROSHTHI); jaroslav@68: aliases.put("KHMR", KHMER); jaroslav@68: aliases.put("KNDA", KANNADA); jaroslav@68: aliases.put("KTHI", KAITHI); jaroslav@68: aliases.put("LANA", TAI_THAM); jaroslav@68: aliases.put("LAOO", LAO); jaroslav@68: aliases.put("LATN", LATIN); jaroslav@68: aliases.put("LEPC", LEPCHA); jaroslav@68: aliases.put("LIMB", LIMBU); jaroslav@68: aliases.put("LINB", LINEAR_B); jaroslav@68: aliases.put("LISU", LISU); jaroslav@68: aliases.put("LYCI", LYCIAN); jaroslav@68: aliases.put("LYDI", LYDIAN); jaroslav@68: aliases.put("MAND", MANDAIC); jaroslav@68: aliases.put("MLYM", MALAYALAM); jaroslav@68: aliases.put("MONG", MONGOLIAN); jaroslav@68: aliases.put("MTEI", MEETEI_MAYEK); jaroslav@68: aliases.put("MYMR", MYANMAR); jaroslav@68: aliases.put("NKOO", NKO); jaroslav@68: aliases.put("OGAM", OGHAM); jaroslav@68: aliases.put("OLCK", OL_CHIKI); jaroslav@68: aliases.put("ORKH", OLD_TURKIC); jaroslav@68: aliases.put("ORYA", ORIYA); jaroslav@68: aliases.put("OSMA", OSMANYA); jaroslav@68: aliases.put("PHAG", PHAGS_PA); jaroslav@68: aliases.put("PHLI", INSCRIPTIONAL_PAHLAVI); jaroslav@68: aliases.put("PHNX", PHOENICIAN); jaroslav@68: aliases.put("PRTI", INSCRIPTIONAL_PARTHIAN); jaroslav@68: aliases.put("RJNG", REJANG); jaroslav@68: aliases.put("RUNR", RUNIC); jaroslav@68: aliases.put("SAMR", SAMARITAN); jaroslav@68: aliases.put("SARB", OLD_SOUTH_ARABIAN); jaroslav@68: aliases.put("SAUR", SAURASHTRA); jaroslav@68: aliases.put("SHAW", SHAVIAN); jaroslav@68: aliases.put("SINH", SINHALA); jaroslav@68: aliases.put("SUND", SUNDANESE); jaroslav@68: aliases.put("SYLO", SYLOTI_NAGRI); jaroslav@68: aliases.put("SYRC", SYRIAC); jaroslav@68: aliases.put("TAGB", TAGBANWA); jaroslav@68: aliases.put("TALE", TAI_LE); jaroslav@68: aliases.put("TALU", NEW_TAI_LUE); jaroslav@68: aliases.put("TAML", TAMIL); jaroslav@68: aliases.put("TAVT", TAI_VIET); jaroslav@68: aliases.put("TELU", TELUGU); jaroslav@68: aliases.put("TFNG", TIFINAGH); jaroslav@68: aliases.put("TGLG", TAGALOG); jaroslav@68: aliases.put("THAA", THAANA); jaroslav@68: aliases.put("THAI", THAI); jaroslav@68: aliases.put("TIBT", TIBETAN); jaroslav@68: aliases.put("UGAR", UGARITIC); jaroslav@68: aliases.put("VAII", VAI); jaroslav@68: aliases.put("XPEO", OLD_PERSIAN); jaroslav@68: aliases.put("XSUX", CUNEIFORM); jaroslav@68: aliases.put("YIII", YI); jaroslav@68: aliases.put("ZINH", INHERITED); jaroslav@68: aliases.put("ZYYY", COMMON); jaroslav@68: aliases.put("ZZZZ", UNKNOWN); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the enum constant representing the Unicode script of which jaroslav@68: * the given character (Unicode code point) is assigned to. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) in question. jaroslav@68: * @return The {@code UnicodeScript} constant representing the jaroslav@68: * Unicode script of which this character is assigned to. jaroslav@68: * jaroslav@68: * @exception IllegalArgumentException if the specified jaroslav@68: * {@code codePoint} is an invalid Unicode code point. jaroslav@68: * @see Character#isValidCodePoint(int) jaroslav@68: * jaroslav@68: */ jaroslav@68: public static UnicodeScript of(int codePoint) { jaroslav@68: if (!isValidCodePoint(codePoint)) jaroslav@68: throw new IllegalArgumentException(); jaroslav@68: int type = getType(codePoint); jaroslav@68: // leave SURROGATE and PRIVATE_USE for table lookup jaroslav@68: if (type == UNASSIGNED) jaroslav@68: return UNKNOWN; jaroslav@68: int index = Arrays.binarySearch(scriptStarts, codePoint); jaroslav@68: if (index < 0) jaroslav@68: index = -index - 2; jaroslav@68: return scripts[index]; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the UnicodeScript constant with the given Unicode script jaroslav@68: * name or the script name alias. Script names and their aliases are jaroslav@68: * determined by The Unicode Standard. The files Scripts<version>.txt jaroslav@68: * and PropertyValueAliases<version>.txt define script names jaroslav@68: * and the script name aliases for a particular version of the jaroslav@68: * standard. The {@link Character} class specifies the version of jaroslav@68: * the standard that it supports. jaroslav@68: *

jaroslav@68: * Character case is ignored for all of the valid script names. jaroslav@68: * The en_US locale's case mapping rules are used to provide jaroslav@68: * case-insensitive string comparisons for script name validation. jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param scriptName A {@code UnicodeScript} name. jaroslav@68: * @return The {@code UnicodeScript} constant identified jaroslav@68: * by {@code scriptName} jaroslav@68: * @throws IllegalArgumentException if {@code scriptName} is an jaroslav@68: * invalid name jaroslav@68: * @throws NullPointerException if {@code scriptName} is null jaroslav@68: */ jaroslav@68: public static final UnicodeScript forName(String scriptName) { jaroslav@68: scriptName = scriptName.toUpperCase(Locale.ENGLISH); jaroslav@68: //.replace(' ', '_')); jaroslav@68: UnicodeScript sc = aliases.get(scriptName); jaroslav@68: if (sc != null) jaroslav@68: return sc; jaroslav@68: return valueOf(scriptName); jaroslav@68: } jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * The value of the {@code Character}. jaroslav@68: * jaroslav@68: * @serial jaroslav@68: */ jaroslav@68: private final char value; jaroslav@68: jaroslav@68: /** use serialVersionUID from JDK 1.0.2 for interoperability */ jaroslav@68: private static final long serialVersionUID = 3786198910865385080L; jaroslav@68: jaroslav@68: /** jaroslav@68: * Constructs a newly allocated {@code Character} object that jaroslav@68: * represents the specified {@code char} value. jaroslav@68: * jaroslav@68: * @param value the value to be represented by the jaroslav@68: * {@code Character} object. jaroslav@68: */ jaroslav@68: public Character(char value) { jaroslav@68: this.value = value; jaroslav@68: } jaroslav@68: jaroslav@68: private static class CharacterCache { jaroslav@68: private CharacterCache(){} jaroslav@68: jaroslav@68: static final Character cache[] = new Character[127 + 1]; jaroslav@68: jaroslav@68: static { jaroslav@68: for (int i = 0; i < cache.length; i++) jaroslav@68: cache[i] = new Character((char)i); jaroslav@68: } jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns a Character instance representing the specified jaroslav@68: * char value. jaroslav@68: * If a new Character instance is not required, this method jaroslav@68: * should generally be used in preference to the constructor jaroslav@68: * {@link #Character(char)}, as this method is likely to yield jaroslav@68: * significantly better space and time performance by caching jaroslav@68: * frequently requested values. jaroslav@68: * jaroslav@68: * This method will always cache values in the range {@code jaroslav@68: * '\u005Cu0000'} to {@code '\u005Cu007F'}, inclusive, and may jaroslav@68: * cache other values outside of this range. jaroslav@68: * jaroslav@68: * @param c a char value. jaroslav@68: * @return a Character instance representing c. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static Character valueOf(char c) { jaroslav@68: if (c <= 127) { // must cache jaroslav@68: return CharacterCache.cache[(int)c]; jaroslav@68: } jaroslav@68: return new Character(c); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the value of this {@code Character} object. jaroslav@68: * @return the primitive {@code char} value represented by jaroslav@68: * this object. jaroslav@68: */ jaroslav@68: public char charValue() { jaroslav@68: return value; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns a hash code for this {@code Character}; equal to the result jaroslav@68: * of invoking {@code charValue()}. jaroslav@68: * jaroslav@68: * @return a hash code value for this {@code Character} jaroslav@68: */ jaroslav@68: public int hashCode() { jaroslav@68: return (int)value; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Compares this object against the specified object. jaroslav@68: * The result is {@code true} if and only if the argument is not jaroslav@68: * {@code null} and is a {@code Character} object that jaroslav@68: * represents the same {@code char} value as this object. jaroslav@68: * jaroslav@68: * @param obj the object to compare with. jaroslav@68: * @return {@code true} if the objects are the same; jaroslav@68: * {@code false} otherwise. jaroslav@68: */ jaroslav@68: public boolean equals(Object obj) { jaroslav@68: if (obj instanceof Character) { jaroslav@68: return value == ((Character)obj).charValue(); jaroslav@68: } jaroslav@68: return false; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns a {@code String} object representing this jaroslav@68: * {@code Character}'s value. The result is a string of jaroslav@68: * length 1 whose sole component is the primitive jaroslav@68: * {@code char} value represented by this jaroslav@68: * {@code Character} object. jaroslav@68: * jaroslav@68: * @return a string representation of this object. jaroslav@68: */ jaroslav@68: public String toString() { jaroslav@68: char buf[] = {value}; jaroslav@68: return String.valueOf(buf); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns a {@code String} object representing the jaroslav@68: * specified {@code char}. The result is a string of length jaroslav@68: * 1 consisting solely of the specified {@code char}. jaroslav@68: * jaroslav@68: * @param c the {@code char} to be converted jaroslav@68: * @return the string representation of the specified {@code char} jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static String toString(char c) { jaroslav@68: return String.valueOf(c); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines whether the specified code point is a valid jaroslav@68: * jaroslav@68: * Unicode code point value. jaroslav@68: * jaroslav@68: * @param codePoint the Unicode code point to be tested jaroslav@68: * @return {@code true} if the specified code point value is between jaroslav@68: * {@link #MIN_CODE_POINT} and jaroslav@68: * {@link #MAX_CODE_POINT} inclusive; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isValidCodePoint(int codePoint) { jaroslav@68: // Optimized form of: jaroslav@68: // codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT jaroslav@68: int plane = codePoint >>> 16; jaroslav@68: return plane < ((MAX_CODE_POINT + 1) >>> 16); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines whether the specified character (Unicode code point) jaroslav@68: * is in the Basic Multilingual Plane (BMP). jaroslav@68: * Such code points can be represented using a single {@code char}. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested jaroslav@68: * @return {@code true} if the specified code point is between jaroslav@68: * {@link #MIN_VALUE} and {@link #MAX_VALUE} inclusive; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static boolean isBmpCodePoint(int codePoint) { jaroslav@68: return codePoint >>> 16 == 0; jaroslav@68: // Optimized form of: jaroslav@68: // codePoint >= MIN_VALUE && codePoint <= MAX_VALUE jaroslav@68: // We consistently use logical shift (>>>) to facilitate jaroslav@68: // additional runtime optimizations. jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines whether the specified character (Unicode code point) jaroslav@68: * is in the supplementary character range. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested jaroslav@68: * @return {@code true} if the specified code point is between jaroslav@68: * {@link #MIN_SUPPLEMENTARY_CODE_POINT} and jaroslav@68: * {@link #MAX_CODE_POINT} inclusive; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isSupplementaryCodePoint(int codePoint) { jaroslav@68: return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT jaroslav@68: && codePoint < MAX_CODE_POINT + 1; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the given {@code char} value is a jaroslav@68: * jaroslav@68: * Unicode high-surrogate code unit jaroslav@68: * (also known as leading-surrogate code unit). jaroslav@68: * jaroslav@68: *

Such values do not represent characters by themselves, jaroslav@68: * but are used in the representation of jaroslav@68: * supplementary characters jaroslav@68: * in the UTF-16 encoding. jaroslav@68: * jaroslav@68: * @param ch the {@code char} value to be tested. jaroslav@68: * @return {@code true} if the {@code char} value is between jaroslav@68: * {@link #MIN_HIGH_SURROGATE} and jaroslav@68: * {@link #MAX_HIGH_SURROGATE} inclusive; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isLowSurrogate(char) jaroslav@68: * @see Character.UnicodeBlock#of(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isHighSurrogate(char ch) { jaroslav@68: // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE jaroslav@68: return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the given {@code char} value is a jaroslav@68: * jaroslav@68: * Unicode low-surrogate code unit jaroslav@68: * (also known as trailing-surrogate code unit). jaroslav@68: * jaroslav@68: *

Such values do not represent characters by themselves, jaroslav@68: * but are used in the representation of jaroslav@68: * supplementary characters jaroslav@68: * in the UTF-16 encoding. jaroslav@68: * jaroslav@68: * @param ch the {@code char} value to be tested. jaroslav@68: * @return {@code true} if the {@code char} value is between jaroslav@68: * {@link #MIN_LOW_SURROGATE} and jaroslav@68: * {@link #MAX_LOW_SURROGATE} inclusive; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isHighSurrogate(char) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isLowSurrogate(char ch) { jaroslav@68: return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the given {@code char} value is a Unicode jaroslav@68: * surrogate code unit. jaroslav@68: * jaroslav@68: *

Such values do not represent characters by themselves, jaroslav@68: * but are used in the representation of jaroslav@68: * supplementary characters jaroslav@68: * in the UTF-16 encoding. jaroslav@68: * jaroslav@68: *

A char value is a surrogate code unit if and only if it is either jaroslav@68: * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or jaroslav@68: * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}. jaroslav@68: * jaroslav@68: * @param ch the {@code char} value to be tested. jaroslav@68: * @return {@code true} if the {@code char} value is between jaroslav@68: * {@link #MIN_SURROGATE} and jaroslav@68: * {@link #MAX_SURROGATE} inclusive; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static boolean isSurrogate(char ch) { jaroslav@68: return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines whether the specified pair of {@code char} jaroslav@68: * values is a valid jaroslav@68: * jaroslav@68: * Unicode surrogate pair. jaroslav@68: jaroslav@68: *

This method is equivalent to the expression: jaroslav@68: * 

jaroslav@68:      * isHighSurrogate(high) && isLowSurrogate(low)
jaroslav@68:      *
jaroslav@68: * jaroslav@68: * @param high the high-surrogate code value to be tested jaroslav@68: * @param low the low-surrogate code value to be tested jaroslav@68: * @return {@code true} if the specified high and jaroslav@68: * low-surrogate code values represent a valid surrogate pair; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isSurrogatePair(char high, char low) { jaroslav@68: return isHighSurrogate(high) && isLowSurrogate(low); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines the number of {@code char} values needed to jaroslav@68: * represent the specified character (Unicode code point). If the jaroslav@68: * specified character is equal to or greater than 0x10000, then jaroslav@68: * the method returns 2. Otherwise, the method returns 1. jaroslav@68: * jaroslav@68: *

This method doesn't validate the specified character to be a jaroslav@68: * valid Unicode code point. The caller must validate the jaroslav@68: * character value using {@link #isValidCodePoint(int) isValidCodePoint} jaroslav@68: * if necessary. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return 2 if the character is a valid supplementary character; 1 otherwise. jaroslav@68: * @see Character#isSupplementaryCodePoint(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int charCount(int codePoint) { jaroslav@68: return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the specified surrogate pair to its supplementary code jaroslav@68: * point value. This method does not validate the specified jaroslav@68: * surrogate pair. The caller must validate it using {@link jaroslav@68: * #isSurrogatePair(char, char) isSurrogatePair} if necessary. jaroslav@68: * jaroslav@68: * @param high the high-surrogate code unit jaroslav@68: * @param low the low-surrogate code unit jaroslav@68: * @return the supplementary code point composed from the jaroslav@68: * specified surrogate pair. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int toCodePoint(char high, char low) { jaroslav@68: // Optimized form of: jaroslav@68: // return ((high - MIN_HIGH_SURROGATE) << 10) jaroslav@68: // + (low - MIN_LOW_SURROGATE) jaroslav@68: // + MIN_SUPPLEMENTARY_CODE_POINT; jaroslav@68: return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT jaroslav@68: - (MIN_HIGH_SURROGATE << 10) jaroslav@68: - MIN_LOW_SURROGATE); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the code point at the given index of the jaroslav@68: * {@code CharSequence}. If the {@code char} value at jaroslav@68: * the given index in the {@code CharSequence} is in the jaroslav@68: * high-surrogate range, the following index is less than the jaroslav@68: * length of the {@code CharSequence}, and the jaroslav@68: * {@code char} value at the following index is in the jaroslav@68: * low-surrogate range, then the supplementary code point jaroslav@68: * corresponding to this surrogate pair is returned. Otherwise, jaroslav@68: * the {@code char} value at the given index is returned. jaroslav@68: * jaroslav@68: * @param seq a sequence of {@code char} values (Unicode code jaroslav@68: * units) jaroslav@68: * @param index the index to the {@code char} values (Unicode jaroslav@68: * code units) in {@code seq} to be converted jaroslav@68: * @return the Unicode code point at the given index jaroslav@68: * @exception NullPointerException if {@code seq} is null. jaroslav@68: * @exception IndexOutOfBoundsException if the value jaroslav@68: * {@code index} is negative or not less than jaroslav@68: * {@link CharSequence#length() seq.length()}. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointAt(CharSequence seq, int index) { jaroslav@68: char c1 = seq.charAt(index++); jaroslav@68: if (isHighSurrogate(c1)) { jaroslav@68: if (index < seq.length()) { jaroslav@68: char c2 = seq.charAt(index); jaroslav@68: if (isLowSurrogate(c2)) { jaroslav@68: return toCodePoint(c1, c2); jaroslav@68: } jaroslav@68: } jaroslav@68: } jaroslav@68: return c1; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the code point at the given index of the jaroslav@68: * {@code char} array. If the {@code char} value at jaroslav@68: * the given index in the {@code char} array is in the jaroslav@68: * high-surrogate range, the following index is less than the jaroslav@68: * length of the {@code char} array, and the jaroslav@68: * {@code char} value at the following index is in the jaroslav@68: * low-surrogate range, then the supplementary code point jaroslav@68: * corresponding to this surrogate pair is returned. Otherwise, jaroslav@68: * the {@code char} value at the given index is returned. jaroslav@68: * jaroslav@68: * @param a the {@code char} array jaroslav@68: * @param index the index to the {@code char} values (Unicode jaroslav@68: * code units) in the {@code char} array to be converted jaroslav@68: * @return the Unicode code point at the given index jaroslav@68: * @exception NullPointerException if {@code a} is null. jaroslav@68: * @exception IndexOutOfBoundsException if the value jaroslav@68: * {@code index} is negative or not less than jaroslav@68: * the length of the {@code char} array. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointAt(char[] a, int index) { jaroslav@68: return codePointAtImpl(a, index, a.length); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the code point at the given index of the jaroslav@68: * {@code char} array, where only array elements with jaroslav@68: * {@code index} less than {@code limit} can be used. If jaroslav@68: * the {@code char} value at the given index in the jaroslav@68: * {@code char} array is in the high-surrogate range, the jaroslav@68: * following index is less than the {@code limit}, and the jaroslav@68: * {@code char} value at the following index is in the jaroslav@68: * low-surrogate range, then the supplementary code point jaroslav@68: * corresponding to this surrogate pair is returned. Otherwise, jaroslav@68: * the {@code char} value at the given index is returned. jaroslav@68: * jaroslav@68: * @param a the {@code char} array jaroslav@68: * @param index the index to the {@code char} values (Unicode jaroslav@68: * code units) in the {@code char} array to be converted jaroslav@68: * @param limit the index after the last array element that jaroslav@68: * can be used in the {@code char} array jaroslav@68: * @return the Unicode code point at the given index jaroslav@68: * @exception NullPointerException if {@code a} is null. jaroslav@68: * @exception IndexOutOfBoundsException if the {@code index} jaroslav@68: * argument is negative or not less than the {@code limit} jaroslav@68: * argument, or if the {@code limit} argument is negative or jaroslav@68: * greater than the length of the {@code char} array. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointAt(char[] a, int index, int limit) { jaroslav@68: if (index >= limit || limit < 0 || limit > a.length) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: return codePointAtImpl(a, index, limit); jaroslav@68: } jaroslav@68: jaroslav@68: // throws ArrayIndexOutofBoundsException if index out of bounds jaroslav@68: static int codePointAtImpl(char[] a, int index, int limit) { jaroslav@68: char c1 = a[index++]; jaroslav@68: if (isHighSurrogate(c1)) { jaroslav@68: if (index < limit) { jaroslav@68: char c2 = a[index]; jaroslav@68: if (isLowSurrogate(c2)) { jaroslav@68: return toCodePoint(c1, c2); jaroslav@68: } jaroslav@68: } jaroslav@68: } jaroslav@68: return c1; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the code point preceding the given index of the jaroslav@68: * {@code CharSequence}. If the {@code char} value at jaroslav@68: * {@code (index - 1)} in the {@code CharSequence} is in jaroslav@68: * the low-surrogate range, {@code (index - 2)} is not jaroslav@68: * negative, and the {@code char} value at {@code (index - 2)} jaroslav@68: * in the {@code CharSequence} is in the jaroslav@68: * high-surrogate range, then the supplementary code point jaroslav@68: * corresponding to this surrogate pair is returned. Otherwise, jaroslav@68: * the {@code char} value at {@code (index - 1)} is jaroslav@68: * returned. jaroslav@68: * jaroslav@68: * @param seq the {@code CharSequence} instance jaroslav@68: * @param index the index following the code point that should be returned jaroslav@68: * @return the Unicode code point value before the given index. jaroslav@68: * @exception NullPointerException if {@code seq} is null. jaroslav@68: * @exception IndexOutOfBoundsException if the {@code index} jaroslav@68: * argument is less than 1 or greater than {@link jaroslav@68: * CharSequence#length() seq.length()}. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointBefore(CharSequence seq, int index) { jaroslav@68: char c2 = seq.charAt(--index); jaroslav@68: if (isLowSurrogate(c2)) { jaroslav@68: if (index > 0) { jaroslav@68: char c1 = seq.charAt(--index); jaroslav@68: if (isHighSurrogate(c1)) { jaroslav@68: return toCodePoint(c1, c2); jaroslav@68: } jaroslav@68: } jaroslav@68: } jaroslav@68: return c2; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the code point preceding the given index of the jaroslav@68: * {@code char} array. If the {@code char} value at jaroslav@68: * {@code (index - 1)} in the {@code char} array is in jaroslav@68: * the low-surrogate range, {@code (index - 2)} is not jaroslav@68: * negative, and the {@code char} value at {@code (index - 2)} jaroslav@68: * in the {@code char} array is in the jaroslav@68: * high-surrogate range, then the supplementary code point jaroslav@68: * corresponding to this surrogate pair is returned. Otherwise, jaroslav@68: * the {@code char} value at {@code (index - 1)} is jaroslav@68: * returned. jaroslav@68: * jaroslav@68: * @param a the {@code char} array jaroslav@68: * @param index the index following the code point that should be returned jaroslav@68: * @return the Unicode code point value before the given index. jaroslav@68: * @exception NullPointerException if {@code a} is null. jaroslav@68: * @exception IndexOutOfBoundsException if the {@code index} jaroslav@68: * argument is less than 1 or greater than the length of the jaroslav@68: * {@code char} array jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointBefore(char[] a, int index) { jaroslav@68: return codePointBeforeImpl(a, index, 0); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the code point preceding the given index of the jaroslav@68: * {@code char} array, where only array elements with jaroslav@68: * {@code index} greater than or equal to {@code start} jaroslav@68: * can be used. If the {@code char} value at {@code (index - 1)} jaroslav@68: * in the {@code char} array is in the jaroslav@68: * low-surrogate range, {@code (index - 2)} is not less than jaroslav@68: * {@code start}, and the {@code char} value at jaroslav@68: * {@code (index - 2)} in the {@code char} array is in jaroslav@68: * the high-surrogate range, then the supplementary code point jaroslav@68: * corresponding to this surrogate pair is returned. Otherwise, jaroslav@68: * the {@code char} value at {@code (index - 1)} is jaroslav@68: * returned. jaroslav@68: * jaroslav@68: * @param a the {@code char} array jaroslav@68: * @param index the index following the code point that should be returned jaroslav@68: * @param start the index of the first array element in the jaroslav@68: * {@code char} array jaroslav@68: * @return the Unicode code point value before the given index. jaroslav@68: * @exception NullPointerException if {@code a} is null. jaroslav@68: * @exception IndexOutOfBoundsException if the {@code index} jaroslav@68: * argument is not greater than the {@code start} argument or jaroslav@68: * is greater than the length of the {@code char} array, or jaroslav@68: * if the {@code start} argument is negative or not less than jaroslav@68: * the length of the {@code char} array. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointBefore(char[] a, int index, int start) { jaroslav@68: if (index <= start || start < 0 || start >= a.length) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: return codePointBeforeImpl(a, index, start); jaroslav@68: } jaroslav@68: jaroslav@68: // throws ArrayIndexOutofBoundsException if index-1 out of bounds jaroslav@68: static int codePointBeforeImpl(char[] a, int index, int start) { jaroslav@68: char c2 = a[--index]; jaroslav@68: if (isLowSurrogate(c2)) { jaroslav@68: if (index > start) { jaroslav@68: char c1 = a[--index]; jaroslav@68: if (isHighSurrogate(c1)) { jaroslav@68: return toCodePoint(c1, c2); jaroslav@68: } jaroslav@68: } jaroslav@68: } jaroslav@68: return c2; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the leading surrogate (a jaroslav@68: * jaroslav@68: * high surrogate code unit) of the jaroslav@68: * jaroslav@68: * surrogate pair jaroslav@68: * representing the specified supplementary character (Unicode jaroslav@68: * code point) in the UTF-16 encoding. If the specified character jaroslav@68: * is not a jaroslav@68: * supplementary character, jaroslav@68: * an unspecified {@code char} is returned. jaroslav@68: * jaroslav@68: *

If jaroslav@68: * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)} jaroslav@68: * is {@code true}, then jaroslav@68: * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and jaroslav@68: * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x} jaroslav@68: * are also always {@code true}. jaroslav@68: * jaroslav@68: * @param codePoint a supplementary character (Unicode code point) jaroslav@68: * @return the leading surrogate code unit used to represent the jaroslav@68: * character in the UTF-16 encoding jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static char highSurrogate(int codePoint) { jaroslav@68: return (char) ((codePoint >>> 10) jaroslav@68: + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10))); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the trailing surrogate (a jaroslav@68: * jaroslav@68: * low surrogate code unit) of the jaroslav@68: * jaroslav@68: * surrogate pair jaroslav@68: * representing the specified supplementary character (Unicode jaroslav@68: * code point) in the UTF-16 encoding. If the specified character jaroslav@68: * is not a jaroslav@68: * supplementary character, jaroslav@68: * an unspecified {@code char} is returned. jaroslav@68: * jaroslav@68: *

If jaroslav@68: * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)} jaroslav@68: * is {@code true}, then jaroslav@68: * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and jaroslav@68: * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x} jaroslav@68: * are also always {@code true}. jaroslav@68: * jaroslav@68: * @param codePoint a supplementary character (Unicode code point) jaroslav@68: * @return the trailing surrogate code unit used to represent the jaroslav@68: * character in the UTF-16 encoding jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static char lowSurrogate(int codePoint) { jaroslav@68: return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the specified character (Unicode code point) to its jaroslav@68: * UTF-16 representation. If the specified code point is a BMP jaroslav@68: * (Basic Multilingual Plane or Plane 0) value, the same value is jaroslav@68: * stored in {@code dst[dstIndex]}, and 1 is returned. If the jaroslav@68: * specified code point is a supplementary character, its jaroslav@68: * surrogate values are stored in {@code dst[dstIndex]} jaroslav@68: * (high-surrogate) and {@code dst[dstIndex+1]} jaroslav@68: * (low-surrogate), and 2 is returned. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @param dst an array of {@code char} in which the jaroslav@68: * {@code codePoint}'s UTF-16 value is stored. jaroslav@68: * @param dstIndex the start index into the {@code dst} jaroslav@68: * array where the converted value is stored. jaroslav@68: * @return 1 if the code point is a BMP code point, 2 if the jaroslav@68: * code point is a supplementary code point. jaroslav@68: * @exception IllegalArgumentException if the specified jaroslav@68: * {@code codePoint} is not a valid Unicode code point. jaroslav@68: * @exception NullPointerException if the specified {@code dst} is null. jaroslav@68: * @exception IndexOutOfBoundsException if {@code dstIndex} jaroslav@68: * is negative or not less than {@code dst.length}, or if jaroslav@68: * {@code dst} at {@code dstIndex} doesn't have enough jaroslav@68: * array element(s) to store the resulting {@code char} jaroslav@68: * value(s). (If {@code dstIndex} is equal to jaroslav@68: * {@code dst.length-1} and the specified jaroslav@68: * {@code codePoint} is a supplementary character, the jaroslav@68: * high-surrogate value is not stored in jaroslav@68: * {@code dst[dstIndex]}.) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int toChars(int codePoint, char[] dst, int dstIndex) { jaroslav@68: if (isBmpCodePoint(codePoint)) { jaroslav@68: dst[dstIndex] = (char) codePoint; jaroslav@68: return 1; jaroslav@68: } else if (isValidCodePoint(codePoint)) { jaroslav@68: toSurrogates(codePoint, dst, dstIndex); jaroslav@68: return 2; jaroslav@68: } else { jaroslav@68: throw new IllegalArgumentException(); jaroslav@68: } jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the specified character (Unicode code point) to its jaroslav@68: * UTF-16 representation stored in a {@code char} array. If jaroslav@68: * the specified code point is a BMP (Basic Multilingual Plane or jaroslav@68: * Plane 0) value, the resulting {@code char} array has jaroslav@68: * the same value as {@code codePoint}. If the specified code jaroslav@68: * point is a supplementary code point, the resulting jaroslav@68: * {@code char} array has the corresponding surrogate pair. jaroslav@68: * jaroslav@68: * @param codePoint a Unicode code point jaroslav@68: * @return a {@code char} array having jaroslav@68: * {@code codePoint}'s UTF-16 representation. jaroslav@68: * @exception IllegalArgumentException if the specified jaroslav@68: * {@code codePoint} is not a valid Unicode code point. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static char[] toChars(int codePoint) { jaroslav@68: if (isBmpCodePoint(codePoint)) { jaroslav@68: return new char[] { (char) codePoint }; jaroslav@68: } else if (isValidCodePoint(codePoint)) { jaroslav@68: char[] result = new char[2]; jaroslav@68: toSurrogates(codePoint, result, 0); jaroslav@68: return result; jaroslav@68: } else { jaroslav@68: throw new IllegalArgumentException(); jaroslav@68: } jaroslav@68: } jaroslav@68: jaroslav@68: static void toSurrogates(int codePoint, char[] dst, int index) { jaroslav@68: // We write elements "backwards" to guarantee all-or-nothing jaroslav@68: dst[index+1] = lowSurrogate(codePoint); jaroslav@68: dst[index] = highSurrogate(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the number of Unicode code points in the text range of jaroslav@68: * the specified char sequence. The text range begins at the jaroslav@68: * specified {@code beginIndex} and extends to the jaroslav@68: * {@code char} at index {@code endIndex - 1}. Thus the jaroslav@68: * length (in {@code char}s) of the text range is jaroslav@68: * {@code endIndex-beginIndex}. Unpaired surrogates within jaroslav@68: * the text range count as one code point each. jaroslav@68: * jaroslav@68: * @param seq the char sequence jaroslav@68: * @param beginIndex the index to the first {@code char} of jaroslav@68: * the text range. jaroslav@68: * @param endIndex the index after the last {@code char} of jaroslav@68: * the text range. jaroslav@68: * @return the number of Unicode code points in the specified text jaroslav@68: * range jaroslav@68: * @exception NullPointerException if {@code seq} is null. jaroslav@68: * @exception IndexOutOfBoundsException if the jaroslav@68: * {@code beginIndex} is negative, or {@code endIndex} jaroslav@68: * is larger than the length of the given sequence, or jaroslav@68: * {@code beginIndex} is larger than {@code endIndex}. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) { jaroslav@68: int length = seq.length(); jaroslav@68: if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: int n = endIndex - beginIndex; jaroslav@68: for (int i = beginIndex; i < endIndex; ) { jaroslav@68: if (isHighSurrogate(seq.charAt(i++)) && i < endIndex && jaroslav@68: isLowSurrogate(seq.charAt(i))) { jaroslav@68: n--; jaroslav@68: i++; jaroslav@68: } jaroslav@68: } jaroslav@68: return n; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the number of Unicode code points in a subarray of the jaroslav@68: * {@code char} array argument. The {@code offset} jaroslav@68: * argument is the index of the first {@code char} of the jaroslav@68: * subarray and the {@code count} argument specifies the jaroslav@68: * length of the subarray in {@code char}s. Unpaired jaroslav@68: * surrogates within the subarray count as one code point each. jaroslav@68: * jaroslav@68: * @param a the {@code char} array jaroslav@68: * @param offset the index of the first {@code char} in the jaroslav@68: * given {@code char} array jaroslav@68: * @param count the length of the subarray in {@code char}s jaroslav@68: * @return the number of Unicode code points in the specified subarray jaroslav@68: * @exception NullPointerException if {@code a} is null. jaroslav@68: * @exception IndexOutOfBoundsException if {@code offset} or jaroslav@68: * {@code count} is negative, or if {@code offset + jaroslav@68: * count} is larger than the length of the given array. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int codePointCount(char[] a, int offset, int count) { jaroslav@68: if (count > a.length - offset || offset < 0 || count < 0) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: return codePointCountImpl(a, offset, count); jaroslav@68: } jaroslav@68: jaroslav@68: static int codePointCountImpl(char[] a, int offset, int count) { jaroslav@68: int endIndex = offset + count; jaroslav@68: int n = count; jaroslav@68: for (int i = offset; i < endIndex; ) { jaroslav@68: if (isHighSurrogate(a[i++]) && i < endIndex && jaroslav@68: isLowSurrogate(a[i])) { jaroslav@68: n--; jaroslav@68: i++; jaroslav@68: } jaroslav@68: } jaroslav@68: return n; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the index within the given char sequence that is offset jaroslav@68: * from the given {@code index} by {@code codePointOffset} jaroslav@68: * code points. Unpaired surrogates within the text range given by jaroslav@68: * {@code index} and {@code codePointOffset} count as jaroslav@68: * one code point each. jaroslav@68: * jaroslav@68: * @param seq the char sequence jaroslav@68: * @param index the index to be offset jaroslav@68: * @param codePointOffset the offset in code points jaroslav@68: * @return the index within the char sequence jaroslav@68: * @exception NullPointerException if {@code seq} is null. jaroslav@68: * @exception IndexOutOfBoundsException if {@code index} jaroslav@68: * is negative or larger then the length of the char sequence, jaroslav@68: * or if {@code codePointOffset} is positive and the jaroslav@68: * subsequence starting with {@code index} has fewer than jaroslav@68: * {@code codePointOffset} code points, or if jaroslav@68: * {@code codePointOffset} is negative and the subsequence jaroslav@68: * before {@code index} has fewer than the absolute value jaroslav@68: * of {@code codePointOffset} code points. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int offsetByCodePoints(CharSequence seq, int index, jaroslav@68: int codePointOffset) { jaroslav@68: int length = seq.length(); jaroslav@68: if (index < 0 || index > length) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: jaroslav@68: int x = index; jaroslav@68: if (codePointOffset >= 0) { jaroslav@68: int i; jaroslav@68: for (i = 0; x < length && i < codePointOffset; i++) { jaroslav@68: if (isHighSurrogate(seq.charAt(x++)) && x < length && jaroslav@68: isLowSurrogate(seq.charAt(x))) { jaroslav@68: x++; jaroslav@68: } jaroslav@68: } jaroslav@68: if (i < codePointOffset) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: } else { jaroslav@68: int i; jaroslav@68: for (i = codePointOffset; x > 0 && i < 0; i++) { jaroslav@68: if (isLowSurrogate(seq.charAt(--x)) && x > 0 && jaroslav@68: isHighSurrogate(seq.charAt(x-1))) { jaroslav@68: x--; jaroslav@68: } jaroslav@68: } jaroslav@68: if (i < 0) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: } jaroslav@68: return x; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the index within the given {@code char} subarray jaroslav@68: * that is offset from the given {@code index} by jaroslav@68: * {@code codePointOffset} code points. The jaroslav@68: * {@code start} and {@code count} arguments specify a jaroslav@68: * subarray of the {@code char} array. Unpaired surrogates jaroslav@68: * within the text range given by {@code index} and jaroslav@68: * {@code codePointOffset} count as one code point each. jaroslav@68: * jaroslav@68: * @param a the {@code char} array jaroslav@68: * @param start the index of the first {@code char} of the jaroslav@68: * subarray jaroslav@68: * @param count the length of the subarray in {@code char}s jaroslav@68: * @param index the index to be offset jaroslav@68: * @param codePointOffset the offset in code points jaroslav@68: * @return the index within the subarray jaroslav@68: * @exception NullPointerException if {@code a} is null. jaroslav@68: * @exception IndexOutOfBoundsException jaroslav@68: * if {@code start} or {@code count} is negative, jaroslav@68: * or if {@code start + count} is larger than the length of jaroslav@68: * the given array, jaroslav@68: * or if {@code index} is less than {@code start} or jaroslav@68: * larger then {@code start + count}, jaroslav@68: * or if {@code codePointOffset} is positive and the text range jaroslav@68: * starting with {@code index} and ending with {@code start + count - 1} jaroslav@68: * has fewer than {@code codePointOffset} code jaroslav@68: * points, jaroslav@68: * or if {@code codePointOffset} is negative and the text range jaroslav@68: * starting with {@code start} and ending with {@code index - 1} jaroslav@68: * has fewer than the absolute value of jaroslav@68: * {@code codePointOffset} code points. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int offsetByCodePoints(char[] a, int start, int count, jaroslav@68: int index, int codePointOffset) { jaroslav@68: if (count > a.length-start || start < 0 || count < 0 jaroslav@68: || index < start || index > start+count) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: return offsetByCodePointsImpl(a, start, count, index, codePointOffset); jaroslav@68: } jaroslav@68: jaroslav@68: static int offsetByCodePointsImpl(char[]a, int start, int count, jaroslav@68: int index, int codePointOffset) { jaroslav@68: int x = index; jaroslav@68: if (codePointOffset >= 0) { jaroslav@68: int limit = start + count; jaroslav@68: int i; jaroslav@68: for (i = 0; x < limit && i < codePointOffset; i++) { jaroslav@68: if (isHighSurrogate(a[x++]) && x < limit && jaroslav@68: isLowSurrogate(a[x])) { jaroslav@68: x++; jaroslav@68: } jaroslav@68: } jaroslav@68: if (i < codePointOffset) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: } else { jaroslav@68: int i; jaroslav@68: for (i = codePointOffset; x > start && i < 0; i++) { jaroslav@68: if (isLowSurrogate(a[--x]) && x > start && jaroslav@68: isHighSurrogate(a[x-1])) { jaroslav@68: x--; jaroslav@68: } jaroslav@68: } jaroslav@68: if (i < 0) { jaroslav@68: throw new IndexOutOfBoundsException(); jaroslav@68: } jaroslav@68: } jaroslav@68: return x; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is a lowercase character. jaroslav@68: *

jaroslav@68: * A character is lowercase if its general category type, provided jaroslav@68: * by {@code Character.getType(ch)}, is jaroslav@68: * {@code LOWERCASE_LETTER}, or it has contributory property jaroslav@68: * Other_Lowercase as defined by the Unicode Standard. jaroslav@68: *

jaroslav@68: * The following are examples of lowercase characters: jaroslav@68: * 

jaroslav@68:      * 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
jaroslav@68:      * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
jaroslav@68:      * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
jaroslav@68:      * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
jaroslav@68:      * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
jaroslav@68:      *
jaroslav@68: *

Many other Unicode characters are lowercase too. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isLowerCase(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is lowercase; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isLowerCase(char) jaroslav@68: * @see Character#isTitleCase(char) jaroslav@68: * @see Character#toLowerCase(char) jaroslav@68: * @see Character#getType(char) jaroslav@68: */ jaroslav@68: public static boolean isLowerCase(char ch) { jaroslav@68: return isLowerCase((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is a jaroslav@68: * lowercase character. jaroslav@68: *

jaroslav@68: * A character is lowercase if its general category type, provided jaroslav@68: * by {@link Character#getType getType(codePoint)}, is jaroslav@68: * {@code LOWERCASE_LETTER}, or it has contributory property jaroslav@68: * Other_Lowercase as defined by the Unicode Standard. jaroslav@68: *

jaroslav@68: * The following are examples of lowercase characters: jaroslav@68: * 

jaroslav@68:      * 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
jaroslav@68:      * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
jaroslav@68:      * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
jaroslav@68:      * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
jaroslav@68:      * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
jaroslav@68:      *
jaroslav@68: *

Many other Unicode characters are lowercase too. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is lowercase; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isLowerCase(int) jaroslav@68: * @see Character#isTitleCase(int) jaroslav@68: * @see Character#toLowerCase(int) jaroslav@68: * @see Character#getType(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isLowerCase(int codePoint) { jaroslav@68: return getType(codePoint) == Character.LOWERCASE_LETTER || jaroslav@68: CharacterData.of(codePoint).isOtherLowercase(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is an uppercase character. jaroslav@68: *

jaroslav@68: * A character is uppercase if its general category type, provided by jaroslav@68: * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}. jaroslav@68: * or it has contributory property Other_Uppercase as defined by the Unicode Standard. jaroslav@68: *

jaroslav@68: * The following are examples of uppercase characters: jaroslav@68: * 

jaroslav@68:      * 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
jaroslav@68:      * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
jaroslav@68:      * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
jaroslav@68:      * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
jaroslav@68:      * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
jaroslav@68:      *
jaroslav@68: *

Many other Unicode characters are uppercase too.

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isUpperCase(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is uppercase; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isLowerCase(char) jaroslav@68: * @see Character#isTitleCase(char) jaroslav@68: * @see Character#toUpperCase(char) jaroslav@68: * @see Character#getType(char) jaroslav@68: * @since 1.0 jaroslav@68: */ jaroslav@68: public static boolean isUpperCase(char ch) { jaroslav@68: return isUpperCase((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is an uppercase character. jaroslav@68: *

jaroslav@68: * A character is uppercase if its general category type, provided by jaroslav@68: * {@link Character#getType(int) getType(codePoint)}, is {@code UPPERCASE_LETTER}, jaroslav@68: * or it has contributory property Other_Uppercase as defined by the Unicode Standard. jaroslav@68: *

jaroslav@68: * The following are examples of uppercase characters: jaroslav@68: * 

jaroslav@68:      * 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
jaroslav@68:      * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
jaroslav@68:      * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
jaroslav@68:      * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
jaroslav@68:      * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
jaroslav@68:      *
jaroslav@68: *

Many other Unicode characters are uppercase too.

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is uppercase; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isLowerCase(int) jaroslav@68: * @see Character#isTitleCase(int) jaroslav@68: * @see Character#toUpperCase(int) jaroslav@68: * @see Character#getType(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isUpperCase(int codePoint) { jaroslav@68: return getType(codePoint) == Character.UPPERCASE_LETTER || jaroslav@68: CharacterData.of(codePoint).isOtherUppercase(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is a titlecase character. jaroslav@68: *

jaroslav@68: * A character is a titlecase character if its general jaroslav@68: * category type, provided by {@code Character.getType(ch)}, jaroslav@68: * is {@code TITLECASE_LETTER}. jaroslav@68: *

jaroslav@68: * Some characters look like pairs of Latin letters. For example, there jaroslav@68: * is an uppercase letter that looks like "LJ" and has a corresponding jaroslav@68: * lowercase letter that looks like "lj". A third form, which looks like "Lj", jaroslav@68: * is the appropriate form to use when rendering a word in lowercase jaroslav@68: * with initial capitals, as for a book title. jaroslav@68: *

jaroslav@68: * These are some of the Unicode characters for which this method returns jaroslav@68: * {@code true}: jaroslav@68: *

jaroslav@68: *

Many other Unicode characters are titlecase too.

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isTitleCase(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is titlecase; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isLowerCase(char) jaroslav@68: * @see Character#isUpperCase(char) jaroslav@68: * @see Character#toTitleCase(char) jaroslav@68: * @see Character#getType(char) jaroslav@68: * @since 1.0.2 jaroslav@68: */ jaroslav@68: public static boolean isTitleCase(char ch) { jaroslav@68: return isTitleCase((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is a titlecase character. jaroslav@68: *

jaroslav@68: * A character is a titlecase character if its general jaroslav@68: * category type, provided by {@link Character#getType(int) getType(codePoint)}, jaroslav@68: * is {@code TITLECASE_LETTER}. jaroslav@68: *

jaroslav@68: * Some characters look like pairs of Latin letters. For example, there jaroslav@68: * is an uppercase letter that looks like "LJ" and has a corresponding jaroslav@68: * lowercase letter that looks like "lj". A third form, which looks like "Lj", jaroslav@68: * is the appropriate form to use when rendering a word in lowercase jaroslav@68: * with initial capitals, as for a book title. jaroslav@68: *

jaroslav@68: * These are some of the Unicode characters for which this method returns jaroslav@68: * {@code true}: jaroslav@68: *

jaroslav@68: *

Many other Unicode characters are titlecase too.

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is titlecase; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isLowerCase(int) jaroslav@68: * @see Character#isUpperCase(int) jaroslav@68: * @see Character#toTitleCase(int) jaroslav@68: * @see Character#getType(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isTitleCase(int codePoint) { jaroslav@68: return getType(codePoint) == Character.TITLECASE_LETTER; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is a digit. jaroslav@68: *

jaroslav@68: * A character is a digit if its general category type, provided jaroslav@68: * by {@code Character.getType(ch)}, is jaroslav@68: * {@code DECIMAL_DIGIT_NUMBER}. jaroslav@68: *

jaroslav@68: * Some Unicode character ranges that contain digits: jaroslav@68: *

jaroslav@68: * jaroslav@68: * Many other character ranges contain digits as well. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isDigit(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is a digit; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#digit(char, int) jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Character#getType(char) jaroslav@68: */ jaroslav@68: public static boolean isDigit(char ch) { jaroslav@68: return isDigit((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is a digit. jaroslav@68: *

jaroslav@68: * A character is a digit if its general category type, provided jaroslav@68: * by {@link Character#getType(int) getType(codePoint)}, is jaroslav@68: * {@code DECIMAL_DIGIT_NUMBER}. jaroslav@68: *

jaroslav@68: * Some Unicode character ranges that contain digits: jaroslav@68: *

jaroslav@68: * jaroslav@68: * Many other character ranges contain digits as well. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is a digit; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Character#getType(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isDigit(int codePoint) { jaroslav@68: return getType(codePoint) == Character.DECIMAL_DIGIT_NUMBER; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if a character is defined in Unicode. jaroslav@68: *

jaroslav@68: * A character is defined if at least one of the following is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isDefined(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested jaroslav@68: * @return {@code true} if the character has a defined meaning jaroslav@68: * in Unicode; {@code false} otherwise. jaroslav@68: * @see Character#isDigit(char) jaroslav@68: * @see Character#isLetter(char) jaroslav@68: * @see Character#isLetterOrDigit(char) jaroslav@68: * @see Character#isLowerCase(char) jaroslav@68: * @see Character#isTitleCase(char) jaroslav@68: * @see Character#isUpperCase(char) jaroslav@68: * @since 1.0.2 jaroslav@68: */ jaroslav@68: public static boolean isDefined(char ch) { jaroslav@68: return isDefined((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if a character (Unicode code point) is defined in Unicode. jaroslav@68: *

jaroslav@68: * A character is defined if at least one of the following is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character has a defined meaning jaroslav@68: * in Unicode; {@code false} otherwise. jaroslav@68: * @see Character#isDigit(int) jaroslav@68: * @see Character#isLetter(int) jaroslav@68: * @see Character#isLetterOrDigit(int) jaroslav@68: * @see Character#isLowerCase(int) jaroslav@68: * @see Character#isTitleCase(int) jaroslav@68: * @see Character#isUpperCase(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isDefined(int codePoint) { jaroslav@68: return getType(codePoint) != Character.UNASSIGNED; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is a letter. jaroslav@68: *

jaroslav@68: * A character is considered to be a letter if its general jaroslav@68: * category type, provided by {@code Character.getType(ch)}, jaroslav@68: * is any of the following: jaroslav@68: *

jaroslav@68: * jaroslav@68: * Not all letters have case. Many characters are jaroslav@68: * letters but are neither uppercase nor lowercase nor titlecase. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isLetter(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is a letter; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isDigit(char) jaroslav@68: * @see Character#isJavaIdentifierStart(char) jaroslav@68: * @see Character#isJavaLetter(char) jaroslav@68: * @see Character#isJavaLetterOrDigit(char) jaroslav@68: * @see Character#isLetterOrDigit(char) jaroslav@68: * @see Character#isLowerCase(char) jaroslav@68: * @see Character#isTitleCase(char) jaroslav@68: * @see Character#isUnicodeIdentifierStart(char) jaroslav@68: * @see Character#isUpperCase(char) jaroslav@68: */ jaroslav@68: public static boolean isLetter(char ch) { jaroslav@68: return isLetter((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is a letter. jaroslav@68: *

jaroslav@68: * A character is considered to be a letter if its general jaroslav@68: * category type, provided by {@link Character#getType(int) getType(codePoint)}, jaroslav@68: * is any of the following: jaroslav@68: *

jaroslav@68: * jaroslav@68: * Not all letters have case. Many characters are jaroslav@68: * letters but are neither uppercase nor lowercase nor titlecase. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is a letter; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isDigit(int) jaroslav@68: * @see Character#isJavaIdentifierStart(int) jaroslav@68: * @see Character#isLetterOrDigit(int) jaroslav@68: * @see Character#isLowerCase(int) jaroslav@68: * @see Character#isTitleCase(int) jaroslav@68: * @see Character#isUnicodeIdentifierStart(int) jaroslav@68: * @see Character#isUpperCase(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isLetter(int codePoint) { jaroslav@68: return ((((1 << Character.UPPERCASE_LETTER) | jaroslav@68: (1 << Character.LOWERCASE_LETTER) | jaroslav@68: (1 << Character.TITLECASE_LETTER) | jaroslav@68: (1 << Character.MODIFIER_LETTER) | jaroslav@68: (1 << Character.OTHER_LETTER)) >> getType(codePoint)) & 1) jaroslav@68: != 0; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is a letter or digit. jaroslav@68: *

jaroslav@68: * A character is considered to be a letter or digit if either jaroslav@68: * {@code Character.isLetter(char ch)} or jaroslav@68: * {@code Character.isDigit(char ch)} returns jaroslav@68: * {@code true} for the character. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isLetterOrDigit(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is a letter or digit; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isDigit(char) jaroslav@68: * @see Character#isJavaIdentifierPart(char) jaroslav@68: * @see Character#isJavaLetter(char) jaroslav@68: * @see Character#isJavaLetterOrDigit(char) jaroslav@68: * @see Character#isLetter(char) jaroslav@68: * @see Character#isUnicodeIdentifierPart(char) jaroslav@68: * @since 1.0.2 jaroslav@68: */ jaroslav@68: public static boolean isLetterOrDigit(char ch) { jaroslav@68: return isLetterOrDigit((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is a letter or digit. jaroslav@68: *

jaroslav@68: * A character is considered to be a letter or digit if either jaroslav@68: * {@link #isLetter(int) isLetter(codePoint)} or jaroslav@68: * {@link #isDigit(int) isDigit(codePoint)} returns jaroslav@68: * {@code true} for the character. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is a letter or digit; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isDigit(int) jaroslav@68: * @see Character#isJavaIdentifierPart(int) jaroslav@68: * @see Character#isLetter(int) jaroslav@68: * @see Character#isUnicodeIdentifierPart(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isLetterOrDigit(int codePoint) { jaroslav@68: return ((((1 << Character.UPPERCASE_LETTER) | jaroslav@68: (1 << Character.LOWERCASE_LETTER) | jaroslav@68: (1 << Character.TITLECASE_LETTER) | jaroslav@68: (1 << Character.MODIFIER_LETTER) | jaroslav@68: (1 << Character.OTHER_LETTER) | jaroslav@68: (1 << Character.DECIMAL_DIGIT_NUMBER)) >> getType(codePoint)) & 1) jaroslav@68: != 0; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is permissible as the first jaroslav@68: * character in a Java identifier. jaroslav@68: *

jaroslav@68: * A character may start a Java identifier if and only if jaroslav@68: * one of the following is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character may start a Java jaroslav@68: * identifier; {@code false} otherwise. jaroslav@68: * @see Character#isJavaLetterOrDigit(char) jaroslav@68: * @see Character#isJavaIdentifierStart(char) jaroslav@68: * @see Character#isJavaIdentifierPart(char) jaroslav@68: * @see Character#isLetter(char) jaroslav@68: * @see Character#isLetterOrDigit(char) jaroslav@68: * @see Character#isUnicodeIdentifierStart(char) jaroslav@68: * @since 1.02 jaroslav@68: * @deprecated Replaced by isJavaIdentifierStart(char). jaroslav@68: */ jaroslav@68: @Deprecated jaroslav@68: public static boolean isJavaLetter(char ch) { jaroslav@68: return isJavaIdentifierStart(ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character may be part of a Java jaroslav@68: * identifier as other than the first character. jaroslav@68: *

jaroslav@68: * A character may be part of a Java identifier if and only if any jaroslav@68: * of the following are true: jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character may be part of a jaroslav@68: * Java identifier; {@code false} otherwise. jaroslav@68: * @see Character#isJavaLetter(char) jaroslav@68: * @see Character#isJavaIdentifierStart(char) jaroslav@68: * @see Character#isJavaIdentifierPart(char) jaroslav@68: * @see Character#isLetter(char) jaroslav@68: * @see Character#isLetterOrDigit(char) jaroslav@68: * @see Character#isUnicodeIdentifierPart(char) jaroslav@68: * @see Character#isIdentifierIgnorable(char) jaroslav@68: * @since 1.02 jaroslav@68: * @deprecated Replaced by isJavaIdentifierPart(char). jaroslav@68: */ jaroslav@68: @Deprecated jaroslav@68: public static boolean isJavaLetterOrDigit(char ch) { jaroslav@68: return isJavaIdentifierPart(ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is an alphabet. jaroslav@68: *

jaroslav@68: * A character is considered to be alphabetic if its general category type, jaroslav@68: * provided by {@link Character#getType(int) getType(codePoint)}, is any of jaroslav@68: * the following: jaroslav@68: *

jaroslav@68: * or it has contributory property Other_Alphabetic as defined by the jaroslav@68: * Unicode Standard. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return true if the character is a Unicode alphabet jaroslav@68: * character, false otherwise. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static boolean isAlphabetic(int codePoint) { jaroslav@68: return (((((1 << Character.UPPERCASE_LETTER) | jaroslav@68: (1 << Character.LOWERCASE_LETTER) | jaroslav@68: (1 << Character.TITLECASE_LETTER) | jaroslav@68: (1 << Character.MODIFIER_LETTER) | jaroslav@68: (1 << Character.OTHER_LETTER) | jaroslav@68: (1 << Character.LETTER_NUMBER)) >> getType(codePoint)) & 1) != 0) || jaroslav@68: CharacterData.of(codePoint).isOtherAlphabetic(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is a CJKV jaroslav@68: * (Chinese, Japanese, Korean and Vietnamese) ideograph, as defined by jaroslav@68: * the Unicode Standard. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return true if the character is a Unicode ideograph jaroslav@68: * character, false otherwise. jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static boolean isIdeographic(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isIdeographic(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is jaroslav@68: * permissible as the first character in a Java identifier. jaroslav@68: *

jaroslav@68: * A character may start a Java identifier if and only if jaroslav@68: * one of the following conditions is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isJavaIdentifierStart(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character may start a Java identifier; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isJavaIdentifierPart(char) jaroslav@68: * @see Character#isLetter(char) jaroslav@68: * @see Character#isUnicodeIdentifierStart(char) jaroslav@68: * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isJavaIdentifierStart(char ch) { jaroslav@68: return isJavaIdentifierStart((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the character (Unicode code point) is jaroslav@68: * permissible as the first character in a Java identifier. jaroslav@68: *

jaroslav@68: * A character may start a Java identifier if and only if jaroslav@68: * one of the following conditions is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character may start a Java identifier; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isJavaIdentifierPart(int) jaroslav@68: * @see Character#isLetter(int) jaroslav@68: * @see Character#isUnicodeIdentifierStart(int) jaroslav@68: * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isJavaIdentifierStart(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isJavaIdentifierStart(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character may be part of a Java jaroslav@68: * identifier as other than the first character. jaroslav@68: *

jaroslav@68: * A character may be part of a Java identifier if any of the following jaroslav@68: * are true: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isJavaIdentifierPart(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character may be part of a jaroslav@68: * Java identifier; {@code false} otherwise. jaroslav@68: * @see Character#isIdentifierIgnorable(char) jaroslav@68: * @see Character#isJavaIdentifierStart(char) jaroslav@68: * @see Character#isLetterOrDigit(char) jaroslav@68: * @see Character#isUnicodeIdentifierPart(char) jaroslav@68: * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isJavaIdentifierPart(char ch) { jaroslav@68: return isJavaIdentifierPart((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the character (Unicode code point) may be part of a Java jaroslav@68: * identifier as other than the first character. jaroslav@68: *

jaroslav@68: * A character may be part of a Java identifier if any of the following jaroslav@68: * are true: jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character may be part of a jaroslav@68: * Java identifier; {@code false} otherwise. jaroslav@68: * @see Character#isIdentifierIgnorable(int) jaroslav@68: * @see Character#isJavaIdentifierStart(int) jaroslav@68: * @see Character#isLetterOrDigit(int) jaroslav@68: * @see Character#isUnicodeIdentifierPart(int) jaroslav@68: * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isJavaIdentifierPart(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isJavaIdentifierPart(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is permissible as the jaroslav@68: * first character in a Unicode identifier. jaroslav@68: *

jaroslav@68: * A character may start a Unicode identifier if and only if jaroslav@68: * one of the following conditions is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isUnicodeIdentifierStart(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character may start a Unicode jaroslav@68: * identifier; {@code false} otherwise. jaroslav@68: * @see Character#isJavaIdentifierStart(char) jaroslav@68: * @see Character#isLetter(char) jaroslav@68: * @see Character#isUnicodeIdentifierPart(char) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isUnicodeIdentifierStart(char ch) { jaroslav@68: return isUnicodeIdentifierStart((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is permissible as the jaroslav@68: * first character in a Unicode identifier. jaroslav@68: *

jaroslav@68: * A character may start a Unicode identifier if and only if jaroslav@68: * one of the following conditions is true: jaroslav@68: *

jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character may start a Unicode jaroslav@68: * identifier; {@code false} otherwise. jaroslav@68: * @see Character#isJavaIdentifierStart(int) jaroslav@68: * @see Character#isLetter(int) jaroslav@68: * @see Character#isUnicodeIdentifierPart(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isUnicodeIdentifierStart(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isUnicodeIdentifierStart(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character may be part of a Unicode jaroslav@68: * identifier as other than the first character. jaroslav@68: *

jaroslav@68: * A character may be part of a Unicode identifier if and only if jaroslav@68: * one of the following statements is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isUnicodeIdentifierPart(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character may be part of a jaroslav@68: * Unicode identifier; {@code false} otherwise. jaroslav@68: * @see Character#isIdentifierIgnorable(char) jaroslav@68: * @see Character#isJavaIdentifierPart(char) jaroslav@68: * @see Character#isLetterOrDigit(char) jaroslav@68: * @see Character#isUnicodeIdentifierStart(char) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isUnicodeIdentifierPart(char ch) { jaroslav@68: return isUnicodeIdentifierPart((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) may be part of a Unicode jaroslav@68: * identifier as other than the first character. jaroslav@68: *

jaroslav@68: * A character may be part of a Unicode identifier if and only if jaroslav@68: * one of the following statements is true: jaroslav@68: *

jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character may be part of a jaroslav@68: * Unicode identifier; {@code false} otherwise. jaroslav@68: * @see Character#isIdentifierIgnorable(int) jaroslav@68: * @see Character#isJavaIdentifierPart(int) jaroslav@68: * @see Character#isLetterOrDigit(int) jaroslav@68: * @see Character#isUnicodeIdentifierStart(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isUnicodeIdentifierPart(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isUnicodeIdentifierPart(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character should be regarded as jaroslav@68: * an ignorable character in a Java identifier or a Unicode identifier. jaroslav@68: *

jaroslav@68: * The following Unicode characters are ignorable in a Java identifier jaroslav@68: * or a Unicode identifier: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isIdentifierIgnorable(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is an ignorable control jaroslav@68: * character that may be part of a Java or Unicode identifier; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isJavaIdentifierPart(char) jaroslav@68: * @see Character#isUnicodeIdentifierPart(char) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isIdentifierIgnorable(char ch) { jaroslav@68: return isIdentifierIgnorable((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) should be regarded as jaroslav@68: * an ignorable character in a Java identifier or a Unicode identifier. jaroslav@68: *

jaroslav@68: * The following Unicode characters are ignorable in a Java identifier jaroslav@68: * or a Unicode identifier: jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is an ignorable control jaroslav@68: * character that may be part of a Java or Unicode identifier; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isJavaIdentifierPart(int) jaroslav@68: * @see Character#isUnicodeIdentifierPart(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isIdentifierIgnorable(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isIdentifierIgnorable(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character argument to lowercase using case jaroslav@68: * mapping information from the UnicodeData file. jaroslav@68: *

jaroslav@68: * Note that jaroslav@68: * {@code Character.isLowerCase(Character.toLowerCase(ch))} jaroslav@68: * does not always return {@code true} for some ranges of jaroslav@68: * characters, particularly those that are symbols or ideographs. jaroslav@68: * jaroslav@68: *

In general, {@link String#toLowerCase()} should be used to map jaroslav@68: * characters to lowercase. {@code String} case mapping methods jaroslav@68: * have several benefits over {@code Character} case mapping methods. jaroslav@68: * {@code String} case mapping methods can perform locale-sensitive jaroslav@68: * mappings, context-sensitive mappings, and 1:M character mappings, whereas jaroslav@68: * the {@code Character} case mapping methods cannot. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #toLowerCase(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be converted. jaroslav@68: * @return the lowercase equivalent of the character, if any; jaroslav@68: * otherwise, the character itself. jaroslav@68: * @see Character#isLowerCase(char) jaroslav@68: * @see String#toLowerCase() jaroslav@68: */ jaroslav@68: public static char toLowerCase(char ch) { jaroslav@68: return (char)toLowerCase((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character (Unicode code point) argument to jaroslav@68: * lowercase using case mapping information from the UnicodeData jaroslav@68: * file. jaroslav@68: * jaroslav@68: *

Note that jaroslav@68: * {@code Character.isLowerCase(Character.toLowerCase(codePoint))} jaroslav@68: * does not always return {@code true} for some ranges of jaroslav@68: * characters, particularly those that are symbols or ideographs. jaroslav@68: * jaroslav@68: *

In general, {@link String#toLowerCase()} should be used to map jaroslav@68: * characters to lowercase. {@code String} case mapping methods jaroslav@68: * have several benefits over {@code Character} case mapping methods. jaroslav@68: * {@code String} case mapping methods can perform locale-sensitive jaroslav@68: * mappings, context-sensitive mappings, and 1:M character mappings, whereas jaroslav@68: * the {@code Character} case mapping methods cannot. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @return the lowercase equivalent of the character (Unicode code jaroslav@68: * point), if any; otherwise, the character itself. jaroslav@68: * @see Character#isLowerCase(int) jaroslav@68: * @see String#toLowerCase() jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int toLowerCase(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).toLowerCase(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character argument to uppercase using case mapping jaroslav@68: * information from the UnicodeData file. jaroslav@68: *

jaroslav@68: * Note that jaroslav@68: * {@code Character.isUpperCase(Character.toUpperCase(ch))} jaroslav@68: * does not always return {@code true} for some ranges of jaroslav@68: * characters, particularly those that are symbols or ideographs. jaroslav@68: * jaroslav@68: *

In general, {@link String#toUpperCase()} should be used to map jaroslav@68: * characters to uppercase. {@code String} case mapping methods jaroslav@68: * have several benefits over {@code Character} case mapping methods. jaroslav@68: * {@code String} case mapping methods can perform locale-sensitive jaroslav@68: * mappings, context-sensitive mappings, and 1:M character mappings, whereas jaroslav@68: * the {@code Character} case mapping methods cannot. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #toUpperCase(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be converted. jaroslav@68: * @return the uppercase equivalent of the character, if any; jaroslav@68: * otherwise, the character itself. jaroslav@68: * @see Character#isUpperCase(char) jaroslav@68: * @see String#toUpperCase() jaroslav@68: */ jaroslav@68: public static char toUpperCase(char ch) { jaroslav@68: return (char)toUpperCase((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character (Unicode code point) argument to jaroslav@68: * uppercase using case mapping information from the UnicodeData jaroslav@68: * file. jaroslav@68: * jaroslav@68: *

Note that jaroslav@68: * {@code Character.isUpperCase(Character.toUpperCase(codePoint))} jaroslav@68: * does not always return {@code true} for some ranges of jaroslav@68: * characters, particularly those that are symbols or ideographs. jaroslav@68: * jaroslav@68: *

In general, {@link String#toUpperCase()} should be used to map jaroslav@68: * characters to uppercase. {@code String} case mapping methods jaroslav@68: * have several benefits over {@code Character} case mapping methods. jaroslav@68: * {@code String} case mapping methods can perform locale-sensitive jaroslav@68: * mappings, context-sensitive mappings, and 1:M character mappings, whereas jaroslav@68: * the {@code Character} case mapping methods cannot. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @return the uppercase equivalent of the character, if any; jaroslav@68: * otherwise, the character itself. jaroslav@68: * @see Character#isUpperCase(int) jaroslav@68: * @see String#toUpperCase() jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int toUpperCase(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).toUpperCase(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character argument to titlecase using case mapping jaroslav@68: * information from the UnicodeData file. If a character has no jaroslav@68: * explicit titlecase mapping and is not itself a titlecase char jaroslav@68: * according to UnicodeData, then the uppercase mapping is jaroslav@68: * returned as an equivalent titlecase mapping. If the jaroslav@68: * {@code char} argument is already a titlecase jaroslav@68: * {@code char}, the same {@code char} value will be jaroslav@68: * returned. jaroslav@68: *

jaroslav@68: * Note that jaroslav@68: * {@code Character.isTitleCase(Character.toTitleCase(ch))} jaroslav@68: * does not always return {@code true} for some ranges of jaroslav@68: * characters. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #toTitleCase(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be converted. jaroslav@68: * @return the titlecase equivalent of the character, if any; jaroslav@68: * otherwise, the character itself. jaroslav@68: * @see Character#isTitleCase(char) jaroslav@68: * @see Character#toLowerCase(char) jaroslav@68: * @see Character#toUpperCase(char) jaroslav@68: * @since 1.0.2 jaroslav@68: */ jaroslav@68: public static char toTitleCase(char ch) { jaroslav@68: return (char)toTitleCase((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character (Unicode code point) argument to titlecase using case mapping jaroslav@68: * information from the UnicodeData file. If a character has no jaroslav@68: * explicit titlecase mapping and is not itself a titlecase char jaroslav@68: * according to UnicodeData, then the uppercase mapping is jaroslav@68: * returned as an equivalent titlecase mapping. If the jaroslav@68: * character argument is already a titlecase jaroslav@68: * character, the same character value will be jaroslav@68: * returned. jaroslav@68: * jaroslav@68: *

Note that jaroslav@68: * {@code Character.isTitleCase(Character.toTitleCase(codePoint))} jaroslav@68: * does not always return {@code true} for some ranges of jaroslav@68: * characters. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @return the titlecase equivalent of the character, if any; jaroslav@68: * otherwise, the character itself. jaroslav@68: * @see Character#isTitleCase(int) jaroslav@68: * @see Character#toLowerCase(int) jaroslav@68: * @see Character#toUpperCase(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int toTitleCase(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).toTitleCase(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the numeric value of the character {@code ch} in the jaroslav@68: * specified radix. jaroslav@68: *

jaroslav@68: * If the radix is not in the range {@code MIN_RADIX} ≤ jaroslav@68: * {@code radix} ≤ {@code MAX_RADIX} or if the jaroslav@68: * value of {@code ch} is not a valid digit in the specified jaroslav@68: * radix, {@code -1} is returned. A character is a valid digit jaroslav@68: * if at least one of the following is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #digit(int, int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be converted. jaroslav@68: * @param radix the radix. jaroslav@68: * @return the numeric value represented by the character in the jaroslav@68: * specified radix. jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Character#isDigit(char) jaroslav@68: */ jaroslav@68: public static int digit(char ch, int radix) { jaroslav@68: return digit((int)ch, radix); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the numeric value of the specified character (Unicode jaroslav@68: * code point) in the specified radix. jaroslav@68: * jaroslav@68: *

If the radix is not in the range {@code MIN_RADIX} ≤ jaroslav@68: * {@code radix} ≤ {@code MAX_RADIX} or if the jaroslav@68: * character is not a valid digit in the specified jaroslav@68: * radix, {@code -1} is returned. A character is a valid digit jaroslav@68: * if at least one of the following is true: jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @param radix the radix. jaroslav@68: * @return the numeric value represented by the character in the jaroslav@68: * specified radix. jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Character#isDigit(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int digit(int codePoint, int radix) { jaroslav@68: return CharacterData.of(codePoint).digit(codePoint, radix); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the {@code int} value that the specified Unicode jaroslav@68: * character represents. For example, the character jaroslav@68: * {@code '\u005Cu216C'} (the roman numeral fifty) will return jaroslav@68: * an int with a value of 50. jaroslav@68: *

jaroslav@68: * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through jaroslav@68: * {@code '\u005Cu005A'}), lowercase jaroslav@68: * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and jaroslav@68: * full width variant ({@code '\u005CuFF21'} through jaroslav@68: * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through jaroslav@68: * {@code '\u005CuFF5A'}) forms have numeric values from 10 jaroslav@68: * through 35. This is independent of the Unicode specification, jaroslav@68: * which does not assign numeric values to these {@code char} jaroslav@68: * values. jaroslav@68: *

jaroslav@68: * If the character does not have a numeric value, then -1 is returned. jaroslav@68: * If the character has a numeric value that cannot be represented as a jaroslav@68: * nonnegative integer (for example, a fractional value), then -2 jaroslav@68: * is returned. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #getNumericValue(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be converted. jaroslav@68: * @return the numeric value of the character, as a nonnegative {@code int} jaroslav@68: * value; -2 if the character has a numeric value that is not a jaroslav@68: * nonnegative integer; -1 if the character has no numeric value. jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Character#isDigit(char) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static int getNumericValue(char ch) { jaroslav@68: return getNumericValue((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the {@code int} value that the specified jaroslav@68: * character (Unicode code point) represents. For example, the character jaroslav@68: * {@code '\u005Cu216C'} (the Roman numeral fifty) will return jaroslav@68: * an {@code int} with a value of 50. jaroslav@68: *

jaroslav@68: * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through jaroslav@68: * {@code '\u005Cu005A'}), lowercase jaroslav@68: * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and jaroslav@68: * full width variant ({@code '\u005CuFF21'} through jaroslav@68: * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through jaroslav@68: * {@code '\u005CuFF5A'}) forms have numeric values from 10 jaroslav@68: * through 35. This is independent of the Unicode specification, jaroslav@68: * which does not assign numeric values to these {@code char} jaroslav@68: * values. jaroslav@68: *

jaroslav@68: * If the character does not have a numeric value, then -1 is returned. jaroslav@68: * If the character has a numeric value that cannot be represented as a jaroslav@68: * nonnegative integer (for example, a fractional value), then -2 jaroslav@68: * is returned. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @return the numeric value of the character, as a nonnegative {@code int} jaroslav@68: * value; -2 if the character has a numeric value that is not a jaroslav@68: * nonnegative integer; -1 if the character has no numeric value. jaroslav@68: * @see Character#forDigit(int, int) jaroslav@68: * @see Character#isDigit(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int getNumericValue(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).getNumericValue(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is ISO-LATIN-1 white space. jaroslav@68: * This method returns {@code true} for the following five jaroslav@68: * characters only: jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: * jaroslav@68: *
{@code '\t'} {@code U+0009}{@code HORIZONTAL TABULATION}
{@code '\n'} {@code U+000A}{@code NEW LINE}
{@code '\f'} {@code U+000C}{@code FORM FEED}
{@code '\r'} {@code U+000D}{@code CARRIAGE RETURN}
{@code ' '} {@code U+0020}{@code SPACE}
jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is ISO-LATIN-1 white jaroslav@68: * space; {@code false} otherwise. jaroslav@68: * @see Character#isSpaceChar(char) jaroslav@68: * @see Character#isWhitespace(char) jaroslav@68: * @deprecated Replaced by isWhitespace(char). jaroslav@68: */ jaroslav@68: @Deprecated jaroslav@68: public static boolean isSpace(char ch) { jaroslav@68: return (ch <= 0x0020) && jaroslav@68: (((((1L << 0x0009) | jaroslav@68: (1L << 0x000A) | jaroslav@68: (1L << 0x000C) | jaroslav@68: (1L << 0x000D) | jaroslav@68: (1L << 0x0020)) >> ch) & 1L) != 0); jaroslav@68: } jaroslav@68: jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is a Unicode space character. jaroslav@68: * A character is considered to be a space character if and only if jaroslav@68: * it is specified to be a space character by the Unicode Standard. This jaroslav@68: * method returns true if the character's general category type is any of jaroslav@68: * the following: jaroslav@68: *

jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isSpaceChar(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is a space character; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isWhitespace(char) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isSpaceChar(char ch) { jaroslav@68: return isSpaceChar((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is a jaroslav@68: * Unicode space character. A character is considered to be a jaroslav@68: * space character if and only if it is specified to be a space jaroslav@68: * character by the Unicode Standard. This method returns true if jaroslav@68: * the character's general category type is any of the following: jaroslav@68: * jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is a space character; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isWhitespace(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isSpaceChar(int codePoint) { jaroslav@68: return ((((1 << Character.SPACE_SEPARATOR) | jaroslav@68: (1 << Character.LINE_SEPARATOR) | jaroslav@68: (1 << Character.PARAGRAPH_SEPARATOR)) >> getType(codePoint)) & 1) jaroslav@68: != 0; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is white space according to Java. jaroslav@68: * A character is a Java whitespace character if and only if it satisfies jaroslav@68: * one of the following criteria: jaroslav@68: * jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isWhitespace(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is a Java whitespace jaroslav@68: * character; {@code false} otherwise. jaroslav@68: * @see Character#isSpaceChar(char) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isWhitespace(char ch) { jaroslav@68: return isWhitespace((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character (Unicode code point) is jaroslav@68: * white space according to Java. A character is a Java jaroslav@68: * whitespace character if and only if it satisfies one of the jaroslav@68: * following criteria: jaroslav@68: *

jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is a Java whitespace jaroslav@68: * character; {@code false} otherwise. jaroslav@68: * @see Character#isSpaceChar(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isWhitespace(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isWhitespace(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the specified character is an ISO control jaroslav@68: * character. A character is considered to be an ISO control jaroslav@68: * character if its code is in the range {@code '\u005Cu0000'} jaroslav@68: * through {@code '\u005Cu001F'} or in the range jaroslav@68: * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isISOControl(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return {@code true} if the character is an ISO control character; jaroslav@68: * {@code false} otherwise. jaroslav@68: * jaroslav@68: * @see Character#isSpaceChar(char) jaroslav@68: * @see Character#isWhitespace(char) jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static boolean isISOControl(char ch) { jaroslav@68: return isISOControl((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines if the referenced character (Unicode code point) is an ISO control jaroslav@68: * character. A character is considered to be an ISO control jaroslav@68: * character if its code is in the range {@code '\u005Cu0000'} jaroslav@68: * through {@code '\u005Cu001F'} or in the range jaroslav@68: * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is an ISO control character; jaroslav@68: * {@code false} otherwise. jaroslav@68: * @see Character#isSpaceChar(int) jaroslav@68: * @see Character#isWhitespace(int) jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isISOControl(int codePoint) { jaroslav@68: // Optimized form of: jaroslav@68: // (codePoint >= 0x00 && codePoint <= 0x1F) || jaroslav@68: // (codePoint >= 0x7F && codePoint <= 0x9F); jaroslav@68: return codePoint <= 0x9F && jaroslav@68: (codePoint >= 0x7F || (codePoint >>> 5 == 0)); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns a value indicating a character's general category. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #getType(int)} method. jaroslav@68: * jaroslav@68: * @param ch the character to be tested. jaroslav@68: * @return a value of type {@code int} representing the jaroslav@68: * character's general category. jaroslav@68: * @see Character#COMBINING_SPACING_MARK jaroslav@68: * @see Character#CONNECTOR_PUNCTUATION jaroslav@68: * @see Character#CONTROL jaroslav@68: * @see Character#CURRENCY_SYMBOL jaroslav@68: * @see Character#DASH_PUNCTUATION jaroslav@68: * @see Character#DECIMAL_DIGIT_NUMBER jaroslav@68: * @see Character#ENCLOSING_MARK jaroslav@68: * @see Character#END_PUNCTUATION jaroslav@68: * @see Character#FINAL_QUOTE_PUNCTUATION jaroslav@68: * @see Character#FORMAT jaroslav@68: * @see Character#INITIAL_QUOTE_PUNCTUATION jaroslav@68: * @see Character#LETTER_NUMBER jaroslav@68: * @see Character#LINE_SEPARATOR jaroslav@68: * @see Character#LOWERCASE_LETTER jaroslav@68: * @see Character#MATH_SYMBOL jaroslav@68: * @see Character#MODIFIER_LETTER jaroslav@68: * @see Character#MODIFIER_SYMBOL jaroslav@68: * @see Character#NON_SPACING_MARK jaroslav@68: * @see Character#OTHER_LETTER jaroslav@68: * @see Character#OTHER_NUMBER jaroslav@68: * @see Character#OTHER_PUNCTUATION jaroslav@68: * @see Character#OTHER_SYMBOL jaroslav@68: * @see Character#PARAGRAPH_SEPARATOR jaroslav@68: * @see Character#PRIVATE_USE jaroslav@68: * @see Character#SPACE_SEPARATOR jaroslav@68: * @see Character#START_PUNCTUATION jaroslav@68: * @see Character#SURROGATE jaroslav@68: * @see Character#TITLECASE_LETTER jaroslav@68: * @see Character#UNASSIGNED jaroslav@68: * @see Character#UPPERCASE_LETTER jaroslav@68: * @since 1.1 jaroslav@68: */ jaroslav@68: public static int getType(char ch) { jaroslav@68: return getType((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns a value indicating a character's general category. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return a value of type {@code int} representing the jaroslav@68: * character's general category. jaroslav@68: * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK jaroslav@68: * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION jaroslav@68: * @see Character#CONTROL CONTROL jaroslav@68: * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL jaroslav@68: * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION jaroslav@68: * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER jaroslav@68: * @see Character#ENCLOSING_MARK ENCLOSING_MARK jaroslav@68: * @see Character#END_PUNCTUATION END_PUNCTUATION jaroslav@68: * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION jaroslav@68: * @see Character#FORMAT FORMAT jaroslav@68: * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION jaroslav@68: * @see Character#LETTER_NUMBER LETTER_NUMBER jaroslav@68: * @see Character#LINE_SEPARATOR LINE_SEPARATOR jaroslav@68: * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER jaroslav@68: * @see Character#MATH_SYMBOL MATH_SYMBOL jaroslav@68: * @see Character#MODIFIER_LETTER MODIFIER_LETTER jaroslav@68: * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL jaroslav@68: * @see Character#NON_SPACING_MARK NON_SPACING_MARK jaroslav@68: * @see Character#OTHER_LETTER OTHER_LETTER jaroslav@68: * @see Character#OTHER_NUMBER OTHER_NUMBER jaroslav@68: * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION jaroslav@68: * @see Character#OTHER_SYMBOL OTHER_SYMBOL jaroslav@68: * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR jaroslav@68: * @see Character#PRIVATE_USE PRIVATE_USE jaroslav@68: * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR jaroslav@68: * @see Character#START_PUNCTUATION START_PUNCTUATION jaroslav@68: * @see Character#SURROGATE SURROGATE jaroslav@68: * @see Character#TITLECASE_LETTER TITLECASE_LETTER jaroslav@68: * @see Character#UNASSIGNED UNASSIGNED jaroslav@68: * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static int getType(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).getType(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines the character representation for a specific digit in jaroslav@68: * the specified radix. If the value of {@code radix} is not a jaroslav@68: * valid radix, or the value of {@code digit} is not a valid jaroslav@68: * digit in the specified radix, the null character jaroslav@68: * ({@code '\u005Cu0000'}) is returned. jaroslav@68: *

jaroslav@68: * The {@code radix} argument is valid if it is greater than or jaroslav@68: * equal to {@code MIN_RADIX} and less than or equal to jaroslav@68: * {@code MAX_RADIX}. The {@code digit} argument is valid if jaroslav@68: * {@code 0 <= digit < radix}. jaroslav@68: *

jaroslav@68: * If the digit is less than 10, then jaroslav@68: * {@code '0' + digit} is returned. Otherwise, the value jaroslav@68: * {@code 'a' + digit - 10} is returned. jaroslav@68: * jaroslav@68: * @param digit the number to convert to a character. jaroslav@68: * @param radix the radix. jaroslav@68: * @return the {@code char} representation of the specified digit jaroslav@68: * in the specified radix. jaroslav@68: * @see Character#MIN_RADIX jaroslav@68: * @see Character#MAX_RADIX jaroslav@68: * @see Character#digit(char, int) jaroslav@68: */ jaroslav@68: public static char forDigit(int digit, int radix) { jaroslav@68: if ((digit >= radix) || (digit < 0)) { jaroslav@68: return '\0'; jaroslav@68: } jaroslav@68: if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) { jaroslav@68: return '\0'; jaroslav@68: } jaroslav@68: if (digit < 10) { jaroslav@68: return (char)('0' + digit); jaroslav@68: } jaroslav@68: return (char)('a' - 10 + digit); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the Unicode directionality property for the given jaroslav@68: * character. Character directionality is used to calculate the jaroslav@68: * visual ordering of text. The directionality value of undefined jaroslav@68: * {@code char} values is {@code DIRECTIONALITY_UNDEFINED}. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #getDirectionality(int)} method. jaroslav@68: * jaroslav@68: * @param ch {@code char} for which the directionality property jaroslav@68: * is requested. jaroslav@68: * @return the directionality property of the {@code char} value. jaroslav@68: * jaroslav@68: * @see Character#DIRECTIONALITY_UNDEFINED jaroslav@68: * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC jaroslav@68: * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER jaroslav@68: * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR jaroslav@68: * @see Character#DIRECTIONALITY_ARABIC_NUMBER jaroslav@68: * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_NONSPACING_MARK jaroslav@68: * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL jaroslav@68: * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_WHITESPACE jaroslav@68: * @see Character#DIRECTIONALITY_OTHER_NEUTRALS jaroslav@68: * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING jaroslav@68: * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE jaroslav@68: * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static byte getDirectionality(char ch) { jaroslav@68: return getDirectionality((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the Unicode directionality property for the given jaroslav@68: * character (Unicode code point). Character directionality is jaroslav@68: * used to calculate the visual ordering of text. The jaroslav@68: * directionality value of undefined character is {@link jaroslav@68: * #DIRECTIONALITY_UNDEFINED}. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) for which jaroslav@68: * the directionality property is requested. jaroslav@68: * @return the directionality property of the character. jaroslav@68: * jaroslav@68: * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED jaroslav@68: * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC jaroslav@68: * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER jaroslav@68: * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR jaroslav@68: * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER jaroslav@68: * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK jaroslav@68: * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL jaroslav@68: * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR jaroslav@68: * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE jaroslav@68: * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS jaroslav@68: * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING jaroslav@68: * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING jaroslav@68: * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE jaroslav@68: * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static byte getDirectionality(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).getDirectionality(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines whether the character is mirrored according to the jaroslav@68: * Unicode specification. Mirrored characters should have their jaroslav@68: * glyphs horizontally mirrored when displayed in text that is jaroslav@68: * right-to-left. For example, {@code '\u005Cu0028'} LEFT jaroslav@68: * PARENTHESIS is semantically defined to be an opening jaroslav@68: * parenthesis. This will appear as a "(" in text that is jaroslav@68: * left-to-right but as a ")" in text that is right-to-left. jaroslav@68: * jaroslav@68: *

Note: This method cannot handle supplementary characters. To support jaroslav@68: * all Unicode characters, including supplementary characters, use jaroslav@68: * the {@link #isMirrored(int)} method. jaroslav@68: * jaroslav@68: * @param ch {@code char} for which the mirrored property is requested jaroslav@68: * @return {@code true} if the char is mirrored, {@code false} jaroslav@68: * if the {@code char} is not mirrored or is not defined. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: public static boolean isMirrored(char ch) { jaroslav@68: return isMirrored((int)ch); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Determines whether the specified character (Unicode code point) jaroslav@68: * is mirrored according to the Unicode specification. Mirrored jaroslav@68: * characters should have their glyphs horizontally mirrored when jaroslav@68: * displayed in text that is right-to-left. For example, jaroslav@68: * {@code '\u005Cu0028'} LEFT PARENTHESIS is semantically jaroslav@68: * defined to be an opening parenthesis. This will appear jaroslav@68: * as a "(" in text that is left-to-right but as a ")" in text jaroslav@68: * that is right-to-left. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be tested. jaroslav@68: * @return {@code true} if the character is mirrored, {@code false} jaroslav@68: * if the character is not mirrored or is not defined. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static boolean isMirrored(int codePoint) { jaroslav@68: return CharacterData.of(codePoint).isMirrored(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Compares two {@code Character} objects numerically. jaroslav@68: * jaroslav@68: * @param anotherCharacter the {@code Character} to be compared. jaroslav@68: jaroslav@68: * @return the value {@code 0} if the argument {@code Character} jaroslav@68: * is equal to this {@code Character}; a value less than jaroslav@68: * {@code 0} if this {@code Character} is numerically less jaroslav@68: * than the {@code Character} argument; and a value greater than jaroslav@68: * {@code 0} if this {@code Character} is numerically greater jaroslav@68: * than the {@code Character} argument (unsigned comparison). jaroslav@68: * Note that this is strictly a numerical comparison; it is not jaroslav@68: * locale-dependent. jaroslav@68: * @since 1.2 jaroslav@68: */ jaroslav@68: public int compareTo(Character anotherCharacter) { jaroslav@68: return compare(this.value, anotherCharacter.value); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Compares two {@code char} values numerically. jaroslav@68: * The value returned is identical to what would be returned by: jaroslav@68: * 

jaroslav@68:      *    Character.valueOf(x).compareTo(Character.valueOf(y))
jaroslav@68:      *
jaroslav@68: * jaroslav@68: * @param x the first {@code char} to compare jaroslav@68: * @param y the second {@code char} to compare jaroslav@68: * @return the value {@code 0} if {@code x == y}; jaroslav@68: * a value less than {@code 0} if {@code x < y}; and jaroslav@68: * a value greater than {@code 0} if {@code x > y} jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static int compare(char x, char y) { jaroslav@68: return x - y; jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character (Unicode code point) argument to uppercase using jaroslav@68: * information from the UnicodeData file. jaroslav@68: *

jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @return either the uppercase equivalent of the character, if jaroslav@68: * any, or an error flag ({@code Character.ERROR}) jaroslav@68: * that indicates that a 1:M {@code char} mapping exists. jaroslav@68: * @see Character#isLowerCase(char) jaroslav@68: * @see Character#isUpperCase(char) jaroslav@68: * @see Character#toLowerCase(char) jaroslav@68: * @see Character#toTitleCase(char) jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: static int toUpperCaseEx(int codePoint) { jaroslav@68: assert isValidCodePoint(codePoint); jaroslav@68: return CharacterData.of(codePoint).toUpperCaseEx(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Converts the character (Unicode code point) argument to uppercase using case jaroslav@68: * mapping information from the SpecialCasing file in the Unicode jaroslav@68: * specification. If a character has no explicit uppercase jaroslav@68: * mapping, then the {@code char} itself is returned in the jaroslav@68: * {@code char[]}. jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) to be converted. jaroslav@68: * @return a {@code char[]} with the uppercased character. jaroslav@68: * @since 1.4 jaroslav@68: */ jaroslav@68: static char[] toUpperCaseCharArray(int codePoint) { jaroslav@68: // As of Unicode 6.0, 1:M uppercasings only happen in the BMP. jaroslav@68: assert isBmpCodePoint(codePoint); jaroslav@68: return CharacterData.of(codePoint).toUpperCaseCharArray(codePoint); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * The number of bits used to represent a char value in unsigned jaroslav@68: * binary form, constant {@code 16}. jaroslav@68: * jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static final int SIZE = 16; jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the value obtained by reversing the order of the bytes in the jaroslav@68: * specified char value. jaroslav@68: * jaroslav@68: * @return the value obtained by reversing (or, equivalently, swapping) jaroslav@68: * the bytes in the specified char value. jaroslav@68: * @since 1.5 jaroslav@68: */ jaroslav@68: public static char reverseBytes(char ch) { jaroslav@68: return (char) (((ch & 0xFF00) >> 8) | (ch << 8)); jaroslav@68: } jaroslav@68: jaroslav@68: /** jaroslav@68: * Returns the Unicode name of the specified character jaroslav@68: * {@code codePoint}, or null if the code point is jaroslav@68: * {@link #UNASSIGNED unassigned}. jaroslav@68: *

jaroslav@68: * Note: if the specified character is not assigned a name by jaroslav@68: * the UnicodeData file (part of the Unicode Character jaroslav@68: * Database maintained by the Unicode Consortium), the returned jaroslav@68: * name is the same as the result of expression. jaroslav@68: * jaroslav@68: *

{@code jaroslav@68: * Character.UnicodeBlock.of(codePoint).toString().replace('_', ' ') jaroslav@68: * + " " jaroslav@68: * + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); jaroslav@68: * jaroslav@68: * }
jaroslav@68: * jaroslav@68: * @param codePoint the character (Unicode code point) jaroslav@68: * jaroslav@68: * @return the Unicode name of the specified character, or null if jaroslav@68: * the code point is unassigned. jaroslav@68: * jaroslav@68: * @exception IllegalArgumentException if the specified jaroslav@68: * {@code codePoint} is not a valid Unicode jaroslav@68: * code point. jaroslav@68: * jaroslav@68: * @since 1.7 jaroslav@68: */ jaroslav@68: public static String getName(int codePoint) { jaroslav@68: if (!isValidCodePoint(codePoint)) { jaroslav@68: throw new IllegalArgumentException(); jaroslav@68: } jaroslav@68: String name = CharacterName.get(codePoint); jaroslav@68: if (name != null) jaroslav@68: return name; jaroslav@68: if (getType(codePoint) == UNASSIGNED) jaroslav@68: return null; jaroslav@68: UnicodeBlock block = UnicodeBlock.of(codePoint); jaroslav@68: if (block != null) jaroslav@68: return block.toString().replace('_', ' ') + " " jaroslav@68: + Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); jaroslav@68: // should never come here jaroslav@68: return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); jaroslav@68: } jaroslav@68: }