diff -r 23b4a344fe02 -r 05224402145d emul/mini/src/main/java/java/lang/Character.java --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/emul/mini/src/main/java/java/lang/Character.java Wed Jan 23 20:39:23 2013 +0100 @@ -0,0 +1,2382 @@ +/* + * Copyright (c) 2002, 2010, Oracle and/or its affiliates. All rights reserved. + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This code is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 only, as + * published by the Free Software Foundation. Oracle designates this + * particular file as subject to the "Classpath" exception as provided + * by Oracle in the LICENSE file that accompanied this code. + * + * This code is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * version 2 for more details (a copy is included in the LICENSE file that + * accompanied this code). + * + * You should have received a copy of the GNU General Public License version + * 2 along with this work; if not, write to the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. + * + * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA + * or visit www.oracle.com if you need additional information or have any + * questions. + */ + +package java.lang; + +import org.apidesign.bck2brwsr.core.JavaScriptBody; + +/** + * The {@code Character} class wraps a value of the primitive + * type {@code char} in an object. An object of type + * {@code Character} contains a single field whose type is + * {@code char}. + *
+ * In addition, this class provides several methods for determining + * a character's category (lowercase letter, digit, etc.) and for converting + * characters from uppercase to lowercase and vice versa. + *
+ * Character information is based on the Unicode Standard, version 6.0.0. + *
+ * The methods and data of class {@code Character} are defined by + * the information in the UnicodeData file that is part of the + * Unicode Character Database maintained by the Unicode + * Consortium. This file specifies various properties including name + * and general category for every defined Unicode code point or + * character range. + *
+ * The file and its description are available from the Unicode Consortium at: + *
The {@code char} data type (and therefore the value that a + * {@code Character} object encapsulates) are based on the + * original Unicode specification, which defined characters as + * fixed-width 16-bit entities. The Unicode Standard has since been + * changed to allow for characters whose representation requires more + * than 16 bits. The range of legal code points is now + * U+0000 to U+10FFFF, known as Unicode scalar value. + * (Refer to the + * definition of the U+n notation in the Unicode + * Standard.) + * + *
The set of characters from U+0000 to U+FFFF is + * sometimes referred to as the Basic Multilingual Plane (BMP). + * Characters whose code points are greater + * than U+FFFF are called supplementary characters. The Java + * platform uses the UTF-16 representation in {@code char} arrays and + * in the {@code String} and {@code StringBuffer} classes. In + * this representation, supplementary characters are represented as a pair + * of {@code char} values, the first from the high-surrogates + * range, (\uD800-\uDBFF), the second from the + * low-surrogates range (\uDC00-\uDFFF). + * + *
A {@code char} value, therefore, represents Basic + * Multilingual Plane (BMP) code points, including the surrogate + * code points, or code units of the UTF-16 encoding. An + * {@code int} value represents all Unicode code points, + * including supplementary code points. The lower (least significant) + * 21 bits of {@code int} are used to represent Unicode code + * points and the upper (most significant) 11 bits must be zero. + * Unless otherwise specified, the behavior with respect to + * supplementary characters and surrogate {@code char} values is + * as follows: + * + *
In the Java SE API documentation, Unicode code point is
+ * used for character values in the range between U+0000 and U+10FFFF,
+ * and Unicode code unit is used for 16-bit
+ * {@code char} values that are code units of the UTF-16
+ * encoding. For more information on Unicode terminology, refer to the
+ * Unicode Glossary.
+ *
+ * @author Lee Boynton
+ * @author Guy Steele
+ * @author Akira Tanaka
+ * @author Martin Buchholz
+ * @author Ulf Zibis
+ * @since 1.0
+ */
+public final
+class Character implements java.io.Serializable, Comparable Such values do not represent characters by themselves,
+ * but are used in the representation of
+ * supplementary characters
+ * in the UTF-16 encoding.
+ *
+ * @param ch the {@code char} value to be tested.
+ * @return {@code true} if the {@code char} value is between
+ * {@link #MIN_HIGH_SURROGATE} and
+ * {@link #MAX_HIGH_SURROGATE} inclusive;
+ * {@code false} otherwise.
+ * @see Character#isLowSurrogate(char)
+ * @see Character.UnicodeBlock#of(int)
+ * @since 1.5
+ */
+ public static boolean isHighSurrogate(char ch) {
+ // Help VM constant-fold; MAX_HIGH_SURROGATE + 1 == MIN_LOW_SURROGATE
+ return ch >= MIN_HIGH_SURROGATE && ch < (MAX_HIGH_SURROGATE + 1);
+ }
+
+ /**
+ * Determines if the given {@code char} value is a
+ *
+ * Unicode low-surrogate code unit
+ * (also known as trailing-surrogate code unit).
+ *
+ * Such values do not represent characters by themselves,
+ * but are used in the representation of
+ * supplementary characters
+ * in the UTF-16 encoding.
+ *
+ * @param ch the {@code char} value to be tested.
+ * @return {@code true} if the {@code char} value is between
+ * {@link #MIN_LOW_SURROGATE} and
+ * {@link #MAX_LOW_SURROGATE} inclusive;
+ * {@code false} otherwise.
+ * @see Character#isHighSurrogate(char)
+ * @since 1.5
+ */
+ public static boolean isLowSurrogate(char ch) {
+ return ch >= MIN_LOW_SURROGATE && ch < (MAX_LOW_SURROGATE + 1);
+ }
+
+ /**
+ * Determines if the given {@code char} value is a Unicode
+ * surrogate code unit.
+ *
+ * Such values do not represent characters by themselves,
+ * but are used in the representation of
+ * supplementary characters
+ * in the UTF-16 encoding.
+ *
+ * A char value is a surrogate code unit if and only if it is either
+ * a {@linkplain #isLowSurrogate(char) low-surrogate code unit} or
+ * a {@linkplain #isHighSurrogate(char) high-surrogate code unit}.
+ *
+ * @param ch the {@code char} value to be tested.
+ * @return {@code true} if the {@code char} value is between
+ * {@link #MIN_SURROGATE} and
+ * {@link #MAX_SURROGATE} inclusive;
+ * {@code false} otherwise.
+ * @since 1.7
+ */
+ public static boolean isSurrogate(char ch) {
+ return ch >= MIN_SURROGATE && ch < (MAX_SURROGATE + 1);
+ }
+
+ /**
+ * Determines whether the specified pair of {@code char}
+ * values is a valid
+ *
+ * Unicode surrogate pair.
+
+ * This method is equivalent to the expression:
+ * This method doesn't validate the specified character to be a
+ * valid Unicode code point. The caller must validate the
+ * character value using {@link #isValidCodePoint(int) isValidCodePoint}
+ * if necessary.
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return 2 if the character is a valid supplementary character; 1 otherwise.
+ * @see Character#isSupplementaryCodePoint(int)
+ * @since 1.5
+ */
+ public static int charCount(int codePoint) {
+ return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT ? 2 : 1;
+ }
+
+ /**
+ * Converts the specified surrogate pair to its supplementary code
+ * point value. This method does not validate the specified
+ * surrogate pair. The caller must validate it using {@link
+ * #isSurrogatePair(char, char) isSurrogatePair} if necessary.
+ *
+ * @param high the high-surrogate code unit
+ * @param low the low-surrogate code unit
+ * @return the supplementary code point composed from the
+ * specified surrogate pair.
+ * @since 1.5
+ */
+ public static int toCodePoint(char high, char low) {
+ // Optimized form of:
+ // return ((high - MIN_HIGH_SURROGATE) << 10)
+ // + (low - MIN_LOW_SURROGATE)
+ // + MIN_SUPPLEMENTARY_CODE_POINT;
+ return ((high << 10) + low) + (MIN_SUPPLEMENTARY_CODE_POINT
+ - (MIN_HIGH_SURROGATE << 10)
+ - MIN_LOW_SURROGATE);
+ }
+
+ /**
+ * Returns the code point at the given index of the
+ * {@code CharSequence}. If the {@code char} value at
+ * the given index in the {@code CharSequence} is in the
+ * high-surrogate range, the following index is less than the
+ * length of the {@code CharSequence}, and the
+ * {@code char} value at the following index is in the
+ * low-surrogate range, then the supplementary code point
+ * corresponding to this surrogate pair is returned. Otherwise,
+ * the {@code char} value at the given index is returned.
+ *
+ * @param seq a sequence of {@code char} values (Unicode code
+ * units)
+ * @param index the index to the {@code char} values (Unicode
+ * code units) in {@code seq} to be converted
+ * @return the Unicode code point at the given index
+ * @exception NullPointerException if {@code seq} is null.
+ * @exception IndexOutOfBoundsException if the value
+ * {@code index} is negative or not less than
+ * {@link CharSequence#length() seq.length()}.
+ * @since 1.5
+ */
+ public static int codePointAt(CharSequence seq, int index) {
+ char c1 = seq.charAt(index++);
+ if (isHighSurrogate(c1)) {
+ if (index < seq.length()) {
+ char c2 = seq.charAt(index);
+ if (isLowSurrogate(c2)) {
+ return toCodePoint(c1, c2);
+ }
+ }
+ }
+ return c1;
+ }
+
+ /**
+ * Returns the code point at the given index of the
+ * {@code char} array. If the {@code char} value at
+ * the given index in the {@code char} array is in the
+ * high-surrogate range, the following index is less than the
+ * length of the {@code char} array, and the
+ * {@code char} value at the following index is in the
+ * low-surrogate range, then the supplementary code point
+ * corresponding to this surrogate pair is returned. Otherwise,
+ * the {@code char} value at the given index is returned.
+ *
+ * @param a the {@code char} array
+ * @param index the index to the {@code char} values (Unicode
+ * code units) in the {@code char} array to be converted
+ * @return the Unicode code point at the given index
+ * @exception NullPointerException if {@code a} is null.
+ * @exception IndexOutOfBoundsException if the value
+ * {@code index} is negative or not less than
+ * the length of the {@code char} array.
+ * @since 1.5
+ */
+ public static int codePointAt(char[] a, int index) {
+ return codePointAtImpl(a, index, a.length);
+ }
+
+ /**
+ * Returns the code point at the given index of the
+ * {@code char} array, where only array elements with
+ * {@code index} less than {@code limit} can be used. If
+ * the {@code char} value at the given index in the
+ * {@code char} array is in the high-surrogate range, the
+ * following index is less than the {@code limit}, and the
+ * {@code char} value at the following index is in the
+ * low-surrogate range, then the supplementary code point
+ * corresponding to this surrogate pair is returned. Otherwise,
+ * the {@code char} value at the given index is returned.
+ *
+ * @param a the {@code char} array
+ * @param index the index to the {@code char} values (Unicode
+ * code units) in the {@code char} array to be converted
+ * @param limit the index after the last array element that
+ * can be used in the {@code char} array
+ * @return the Unicode code point at the given index
+ * @exception NullPointerException if {@code a} is null.
+ * @exception IndexOutOfBoundsException if the {@code index}
+ * argument is negative or not less than the {@code limit}
+ * argument, or if the {@code limit} argument is negative or
+ * greater than the length of the {@code char} array.
+ * @since 1.5
+ */
+ public static int codePointAt(char[] a, int index, int limit) {
+ if (index >= limit || limit < 0 || limit > a.length) {
+ throw new IndexOutOfBoundsException();
+ }
+ return codePointAtImpl(a, index, limit);
+ }
+
+ // throws ArrayIndexOutofBoundsException if index out of bounds
+ static int codePointAtImpl(char[] a, int index, int limit) {
+ char c1 = a[index++];
+ if (isHighSurrogate(c1)) {
+ if (index < limit) {
+ char c2 = a[index];
+ if (isLowSurrogate(c2)) {
+ return toCodePoint(c1, c2);
+ }
+ }
+ }
+ return c1;
+ }
+
+ /**
+ * Returns the code point preceding the given index of the
+ * {@code CharSequence}. If the {@code char} value at
+ * {@code (index - 1)} in the {@code CharSequence} is in
+ * the low-surrogate range, {@code (index - 2)} is not
+ * negative, and the {@code char} value at {@code (index - 2)}
+ * in the {@code CharSequence} is in the
+ * high-surrogate range, then the supplementary code point
+ * corresponding to this surrogate pair is returned. Otherwise,
+ * the {@code char} value at {@code (index - 1)} is
+ * returned.
+ *
+ * @param seq the {@code CharSequence} instance
+ * @param index the index following the code point that should be returned
+ * @return the Unicode code point value before the given index.
+ * @exception NullPointerException if {@code seq} is null.
+ * @exception IndexOutOfBoundsException if the {@code index}
+ * argument is less than 1 or greater than {@link
+ * CharSequence#length() seq.length()}.
+ * @since 1.5
+ */
+ public static int codePointBefore(CharSequence seq, int index) {
+ char c2 = seq.charAt(--index);
+ if (isLowSurrogate(c2)) {
+ if (index > 0) {
+ char c1 = seq.charAt(--index);
+ if (isHighSurrogate(c1)) {
+ return toCodePoint(c1, c2);
+ }
+ }
+ }
+ return c2;
+ }
+
+ /**
+ * Returns the code point preceding the given index of the
+ * {@code char} array. If the {@code char} value at
+ * {@code (index - 1)} in the {@code char} array is in
+ * the low-surrogate range, {@code (index - 2)} is not
+ * negative, and the {@code char} value at {@code (index - 2)}
+ * in the {@code char} array is in the
+ * high-surrogate range, then the supplementary code point
+ * corresponding to this surrogate pair is returned. Otherwise,
+ * the {@code char} value at {@code (index - 1)} is
+ * returned.
+ *
+ * @param a the {@code char} array
+ * @param index the index following the code point that should be returned
+ * @return the Unicode code point value before the given index.
+ * @exception NullPointerException if {@code a} is null.
+ * @exception IndexOutOfBoundsException if the {@code index}
+ * argument is less than 1 or greater than the length of the
+ * {@code char} array
+ * @since 1.5
+ */
+ public static int codePointBefore(char[] a, int index) {
+ return codePointBeforeImpl(a, index, 0);
+ }
+
+ /**
+ * Returns the code point preceding the given index of the
+ * {@code char} array, where only array elements with
+ * {@code index} greater than or equal to {@code start}
+ * can be used. If the {@code char} value at {@code (index - 1)}
+ * in the {@code char} array is in the
+ * low-surrogate range, {@code (index - 2)} is not less than
+ * {@code start}, and the {@code char} value at
+ * {@code (index - 2)} in the {@code char} array is in
+ * the high-surrogate range, then the supplementary code point
+ * corresponding to this surrogate pair is returned. Otherwise,
+ * the {@code char} value at {@code (index - 1)} is
+ * returned.
+ *
+ * @param a the {@code char} array
+ * @param index the index following the code point that should be returned
+ * @param start the index of the first array element in the
+ * {@code char} array
+ * @return the Unicode code point value before the given index.
+ * @exception NullPointerException if {@code a} is null.
+ * @exception IndexOutOfBoundsException if the {@code index}
+ * argument is not greater than the {@code start} argument or
+ * is greater than the length of the {@code char} array, or
+ * if the {@code start} argument is negative or not less than
+ * the length of the {@code char} array.
+ * @since 1.5
+ */
+ public static int codePointBefore(char[] a, int index, int start) {
+ if (index <= start || start < 0 || start >= a.length) {
+ throw new IndexOutOfBoundsException();
+ }
+ return codePointBeforeImpl(a, index, start);
+ }
+
+ // throws ArrayIndexOutofBoundsException if index-1 out of bounds
+ static int codePointBeforeImpl(char[] a, int index, int start) {
+ char c2 = a[--index];
+ if (isLowSurrogate(c2)) {
+ if (index > start) {
+ char c1 = a[--index];
+ if (isHighSurrogate(c1)) {
+ return toCodePoint(c1, c2);
+ }
+ }
+ }
+ return c2;
+ }
+
+ /**
+ * Returns the leading surrogate (a
+ *
+ * high surrogate code unit) of the
+ *
+ * surrogate pair
+ * representing the specified supplementary character (Unicode
+ * code point) in the UTF-16 encoding. If the specified character
+ * is not a
+ * supplementary character,
+ * an unspecified {@code char} is returned.
+ *
+ * If
+ * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
+ * is {@code true}, then
+ * {@link #isHighSurrogate isHighSurrogate}{@code (highSurrogate(x))} and
+ * {@link #toCodePoint toCodePoint}{@code (highSurrogate(x), }{@link #lowSurrogate lowSurrogate}{@code (x)) == x}
+ * are also always {@code true}.
+ *
+ * @param codePoint a supplementary character (Unicode code point)
+ * @return the leading surrogate code unit used to represent the
+ * character in the UTF-16 encoding
+ * @since 1.7
+ */
+ public static char highSurrogate(int codePoint) {
+ return (char) ((codePoint >>> 10)
+ + (MIN_HIGH_SURROGATE - (MIN_SUPPLEMENTARY_CODE_POINT >>> 10)));
+ }
+
+ /**
+ * Returns the trailing surrogate (a
+ *
+ * low surrogate code unit) of the
+ *
+ * surrogate pair
+ * representing the specified supplementary character (Unicode
+ * code point) in the UTF-16 encoding. If the specified character
+ * is not a
+ * supplementary character,
+ * an unspecified {@code char} is returned.
+ *
+ * If
+ * {@link #isSupplementaryCodePoint isSupplementaryCodePoint(x)}
+ * is {@code true}, then
+ * {@link #isLowSurrogate isLowSurrogate}{@code (lowSurrogate(x))} and
+ * {@link #toCodePoint toCodePoint}{@code (}{@link #highSurrogate highSurrogate}{@code (x), lowSurrogate(x)) == x}
+ * are also always {@code true}.
+ *
+ * @param codePoint a supplementary character (Unicode code point)
+ * @return the trailing surrogate code unit used to represent the
+ * character in the UTF-16 encoding
+ * @since 1.7
+ */
+ public static char lowSurrogate(int codePoint) {
+ return (char) ((codePoint & 0x3ff) + MIN_LOW_SURROGATE);
+ }
+
+ /**
+ * Converts the specified character (Unicode code point) to its
+ * UTF-16 representation. If the specified code point is a BMP
+ * (Basic Multilingual Plane or Plane 0) value, the same value is
+ * stored in {@code dst[dstIndex]}, and 1 is returned. If the
+ * specified code point is a supplementary character, its
+ * surrogate values are stored in {@code dst[dstIndex]}
+ * (high-surrogate) and {@code dst[dstIndex+1]}
+ * (low-surrogate), and 2 is returned.
+ *
+ * @param codePoint the character (Unicode code point) to be converted.
+ * @param dst an array of {@code char} in which the
+ * {@code codePoint}'s UTF-16 value is stored.
+ * @param dstIndex the start index into the {@code dst}
+ * array where the converted value is stored.
+ * @return 1 if the code point is a BMP code point, 2 if the
+ * code point is a supplementary code point.
+ * @exception IllegalArgumentException if the specified
+ * {@code codePoint} is not a valid Unicode code point.
+ * @exception NullPointerException if the specified {@code dst} is null.
+ * @exception IndexOutOfBoundsException if {@code dstIndex}
+ * is negative or not less than {@code dst.length}, or if
+ * {@code dst} at {@code dstIndex} doesn't have enough
+ * array element(s) to store the resulting {@code char}
+ * value(s). (If {@code dstIndex} is equal to
+ * {@code dst.length-1} and the specified
+ * {@code codePoint} is a supplementary character, the
+ * high-surrogate value is not stored in
+ * {@code dst[dstIndex]}.)
+ * @since 1.5
+ */
+ public static int toChars(int codePoint, char[] dst, int dstIndex) {
+ if (isBmpCodePoint(codePoint)) {
+ dst[dstIndex] = (char) codePoint;
+ return 1;
+ } else if (isValidCodePoint(codePoint)) {
+ toSurrogates(codePoint, dst, dstIndex);
+ return 2;
+ } else {
+ throw new IllegalArgumentException();
+ }
+ }
+
+ /**
+ * Converts the specified character (Unicode code point) to its
+ * UTF-16 representation stored in a {@code char} array. If
+ * the specified code point is a BMP (Basic Multilingual Plane or
+ * Plane 0) value, the resulting {@code char} array has
+ * the same value as {@code codePoint}. If the specified code
+ * point is a supplementary code point, the resulting
+ * {@code char} array has the corresponding surrogate pair.
+ *
+ * @param codePoint a Unicode code point
+ * @return a {@code char} array having
+ * {@code codePoint}'s UTF-16 representation.
+ * @exception IllegalArgumentException if the specified
+ * {@code codePoint} is not a valid Unicode code point.
+ * @since 1.5
+ */
+ public static char[] toChars(int codePoint) {
+ if (isBmpCodePoint(codePoint)) {
+ return new char[] { (char) codePoint };
+ } else if (isValidCodePoint(codePoint)) {
+ char[] result = new char[2];
+ toSurrogates(codePoint, result, 0);
+ return result;
+ } else {
+ throw new IllegalArgumentException();
+ }
+ }
+
+ static void toSurrogates(int codePoint, char[] dst, int index) {
+ // We write elements "backwards" to guarantee all-or-nothing
+ dst[index+1] = lowSurrogate(codePoint);
+ dst[index] = highSurrogate(codePoint);
+ }
+
+ /**
+ * Returns the number of Unicode code points in the text range of
+ * the specified char sequence. The text range begins at the
+ * specified {@code beginIndex} and extends to the
+ * {@code char} at index {@code endIndex - 1}. Thus the
+ * length (in {@code char}s) of the text range is
+ * {@code endIndex-beginIndex}. Unpaired surrogates within
+ * the text range count as one code point each.
+ *
+ * @param seq the char sequence
+ * @param beginIndex the index to the first {@code char} of
+ * the text range.
+ * @param endIndex the index after the last {@code char} of
+ * the text range.
+ * @return the number of Unicode code points in the specified text
+ * range
+ * @exception NullPointerException if {@code seq} is null.
+ * @exception IndexOutOfBoundsException if the
+ * {@code beginIndex} is negative, or {@code endIndex}
+ * is larger than the length of the given sequence, or
+ * {@code beginIndex} is larger than {@code endIndex}.
+ * @since 1.5
+ */
+ public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) {
+ int length = seq.length();
+ if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) {
+ throw new IndexOutOfBoundsException();
+ }
+ int n = endIndex - beginIndex;
+ for (int i = beginIndex; i < endIndex; ) {
+ if (isHighSurrogate(seq.charAt(i++)) && i < endIndex &&
+ isLowSurrogate(seq.charAt(i))) {
+ n--;
+ i++;
+ }
+ }
+ return n;
+ }
+
+ /**
+ * Returns the number of Unicode code points in a subarray of the
+ * {@code char} array argument. The {@code offset}
+ * argument is the index of the first {@code char} of the
+ * subarray and the {@code count} argument specifies the
+ * length of the subarray in {@code char}s. Unpaired
+ * surrogates within the subarray count as one code point each.
+ *
+ * @param a the {@code char} array
+ * @param offset the index of the first {@code char} in the
+ * given {@code char} array
+ * @param count the length of the subarray in {@code char}s
+ * @return the number of Unicode code points in the specified subarray
+ * @exception NullPointerException if {@code a} is null.
+ * @exception IndexOutOfBoundsException if {@code offset} or
+ * {@code count} is negative, or if {@code offset +
+ * count} is larger than the length of the given array.
+ * @since 1.5
+ */
+ public static int codePointCount(char[] a, int offset, int count) {
+ if (count > a.length - offset || offset < 0 || count < 0) {
+ throw new IndexOutOfBoundsException();
+ }
+ return codePointCountImpl(a, offset, count);
+ }
+
+ static int codePointCountImpl(char[] a, int offset, int count) {
+ int endIndex = offset + count;
+ int n = count;
+ for (int i = offset; i < endIndex; ) {
+ if (isHighSurrogate(a[i++]) && i < endIndex &&
+ isLowSurrogate(a[i])) {
+ n--;
+ i++;
+ }
+ }
+ return n;
+ }
+
+ /**
+ * Returns the index within the given char sequence that is offset
+ * from the given {@code index} by {@code codePointOffset}
+ * code points. Unpaired surrogates within the text range given by
+ * {@code index} and {@code codePointOffset} count as
+ * one code point each.
+ *
+ * @param seq the char sequence
+ * @param index the index to be offset
+ * @param codePointOffset the offset in code points
+ * @return the index within the char sequence
+ * @exception NullPointerException if {@code seq} is null.
+ * @exception IndexOutOfBoundsException if {@code index}
+ * is negative or larger then the length of the char sequence,
+ * or if {@code codePointOffset} is positive and the
+ * subsequence starting with {@code index} has fewer than
+ * {@code codePointOffset} code points, or if
+ * {@code codePointOffset} is negative and the subsequence
+ * before {@code index} has fewer than the absolute value
+ * of {@code codePointOffset} code points.
+ * @since 1.5
+ */
+ public static int offsetByCodePoints(CharSequence seq, int index,
+ int codePointOffset) {
+ int length = seq.length();
+ if (index < 0 || index > length) {
+ throw new IndexOutOfBoundsException();
+ }
+
+ int x = index;
+ if (codePointOffset >= 0) {
+ int i;
+ for (i = 0; x < length && i < codePointOffset; i++) {
+ if (isHighSurrogate(seq.charAt(x++)) && x < length &&
+ isLowSurrogate(seq.charAt(x))) {
+ x++;
+ }
+ }
+ if (i < codePointOffset) {
+ throw new IndexOutOfBoundsException();
+ }
+ } else {
+ int i;
+ for (i = codePointOffset; x > 0 && i < 0; i++) {
+ if (isLowSurrogate(seq.charAt(--x)) && x > 0 &&
+ isHighSurrogate(seq.charAt(x-1))) {
+ x--;
+ }
+ }
+ if (i < 0) {
+ throw new IndexOutOfBoundsException();
+ }
+ }
+ return x;
+ }
+
+ /**
+ * Returns the index within the given {@code char} subarray
+ * that is offset from the given {@code index} by
+ * {@code codePointOffset} code points. The
+ * {@code start} and {@code count} arguments specify a
+ * subarray of the {@code char} array. Unpaired surrogates
+ * within the text range given by {@code index} and
+ * {@code codePointOffset} count as one code point each.
+ *
+ * @param a the {@code char} array
+ * @param start the index of the first {@code char} of the
+ * subarray
+ * @param count the length of the subarray in {@code char}s
+ * @param index the index to be offset
+ * @param codePointOffset the offset in code points
+ * @return the index within the subarray
+ * @exception NullPointerException if {@code a} is null.
+ * @exception IndexOutOfBoundsException
+ * if {@code start} or {@code count} is negative,
+ * or if {@code start + count} is larger than the length of
+ * the given array,
+ * or if {@code index} is less than {@code start} or
+ * larger then {@code start + count},
+ * or if {@code codePointOffset} is positive and the text range
+ * starting with {@code index} and ending with {@code start + count - 1}
+ * has fewer than {@code codePointOffset} code
+ * points,
+ * or if {@code codePointOffset} is negative and the text range
+ * starting with {@code start} and ending with {@code index - 1}
+ * has fewer than the absolute value of
+ * {@code codePointOffset} code points.
+ * @since 1.5
+ */
+ public static int offsetByCodePoints(char[] a, int start, int count,
+ int index, int codePointOffset) {
+ if (count > a.length-start || start < 0 || count < 0
+ || index < start || index > start+count) {
+ throw new IndexOutOfBoundsException();
+ }
+ return offsetByCodePointsImpl(a, start, count, index, codePointOffset);
+ }
+
+ static int offsetByCodePointsImpl(char[]a, int start, int count,
+ int index, int codePointOffset) {
+ int x = index;
+ if (codePointOffset >= 0) {
+ int limit = start + count;
+ int i;
+ for (i = 0; x < limit && i < codePointOffset; i++) {
+ if (isHighSurrogate(a[x++]) && x < limit &&
+ isLowSurrogate(a[x])) {
+ x++;
+ }
+ }
+ if (i < codePointOffset) {
+ throw new IndexOutOfBoundsException();
+ }
+ } else {
+ int i;
+ for (i = codePointOffset; x > start && i < 0; i++) {
+ if (isLowSurrogate(a[--x]) && x > start &&
+ isHighSurrogate(a[x-1])) {
+ x--;
+ }
+ }
+ if (i < 0) {
+ throw new IndexOutOfBoundsException();
+ }
+ }
+ return x;
+ }
+
+ /**
+ * Determines if the specified character is a lowercase character.
+ *
+ * A character is lowercase if its general category type, provided
+ * by {@code Character.getType(ch)}, is
+ * {@code LOWERCASE_LETTER}, or it has contributory property
+ * Other_Lowercase as defined by the Unicode Standard.
+ *
+ * The following are examples of lowercase characters:
+ * Many other Unicode characters are lowercase too.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isLowerCase(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is lowercase;
+ * {@code false} otherwise.
+ * @see Character#isLowerCase(char)
+ * @see Character#isTitleCase(char)
+ * @see Character#toLowerCase(char)
+ * @see Character#getType(char)
+ */
+ public static boolean isLowerCase(char ch) {
+ return ch == toLowerCase(ch);
+ }
+
+ /**
+ * Determines if the specified character is an uppercase character.
+ *
+ * A character is uppercase if its general category type, provided by
+ * {@code Character.getType(ch)}, is {@code UPPERCASE_LETTER}.
+ * or it has contributory property Other_Uppercase as defined by the Unicode Standard.
+ *
+ * The following are examples of uppercase characters:
+ * Many other Unicode characters are uppercase too.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isUpperCase(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is uppercase;
+ * {@code false} otherwise.
+ * @see Character#isLowerCase(char)
+ * @see Character#isTitleCase(char)
+ * @see Character#toUpperCase(char)
+ * @see Character#getType(char)
+ * @since 1.0
+ */
+ public static boolean isUpperCase(char ch) {
+ return ch == toUpperCase(ch);
+ }
+
+ /**
+ * Determines if the specified character is a titlecase character.
+ *
+ * A character is a titlecase character if its general
+ * category type, provided by {@code Character.getType(ch)},
+ * is {@code TITLECASE_LETTER}.
+ *
+ * Some characters look like pairs of Latin letters. For example, there
+ * is an uppercase letter that looks like "LJ" and has a corresponding
+ * lowercase letter that looks like "lj". A third form, which looks like "Lj",
+ * is the appropriate form to use when rendering a word in lowercase
+ * with initial capitals, as for a book title.
+ *
+ * These are some of the Unicode characters for which this method returns
+ * {@code true}:
+ * Many other Unicode characters are titlecase too.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isTitleCase(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is titlecase;
+ * {@code false} otherwise.
+ * @see Character#isLowerCase(char)
+ * @see Character#isUpperCase(char)
+ * @see Character#toTitleCase(char)
+ * @see Character#getType(char)
+ * @since 1.0.2
+ */
+ public static boolean isTitleCase(char ch) {
+ return isTitleCase((int)ch);
+ }
+
+ /**
+ * Determines if the specified character (Unicode code point) is a titlecase character.
+ *
+ * A character is a titlecase character if its general
+ * category type, provided by {@link Character#getType(int) getType(codePoint)},
+ * is {@code TITLECASE_LETTER}.
+ *
+ * Some characters look like pairs of Latin letters. For example, there
+ * is an uppercase letter that looks like "LJ" and has a corresponding
+ * lowercase letter that looks like "lj". A third form, which looks like "Lj",
+ * is the appropriate form to use when rendering a word in lowercase
+ * with initial capitals, as for a book title.
+ *
+ * These are some of the Unicode characters for which this method returns
+ * {@code true}:
+ * Many other Unicode characters are titlecase too.
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return {@code true} if the character is titlecase;
+ * {@code false} otherwise.
+ * @see Character#isLowerCase(int)
+ * @see Character#isUpperCase(int)
+ * @see Character#toTitleCase(int)
+ * @see Character#getType(int)
+ * @since 1.5
+ */
+ public static boolean isTitleCase(int codePoint) {
+ return getType(codePoint) == Character.TITLECASE_LETTER;
+ }
+
+ /**
+ * Determines if the specified character is a digit.
+ *
+ * A character is a digit if its general category type, provided
+ * by {@code Character.getType(ch)}, is
+ * {@code DECIMAL_DIGIT_NUMBER}.
+ *
+ * Some Unicode character ranges that contain digits:
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isDigit(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is a digit;
+ * {@code false} otherwise.
+ * @see Character#digit(char, int)
+ * @see Character#forDigit(int, int)
+ * @see Character#getType(char)
+ */
+ public static boolean isDigit(char ch) {
+ return String.valueOf(ch).matches("\\d");
+ }
+
+ /**
+ * Determines if the specified character (Unicode code point) is a digit.
+ *
+ * A character is a digit if its general category type, provided
+ * by {@link Character#getType(int) getType(codePoint)}, is
+ * {@code DECIMAL_DIGIT_NUMBER}.
+ *
+ * Some Unicode character ranges that contain digits:
+ *
+ * A character is defined if at least one of the following is true:
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isDefined(int)} method.
+ *
+ * @param ch the character to be tested
+ * @return {@code true} if the character has a defined meaning
+ * in Unicode; {@code false} otherwise.
+ * @see Character#isDigit(char)
+ * @see Character#isLetter(char)
+ * @see Character#isLetterOrDigit(char)
+ * @see Character#isLowerCase(char)
+ * @see Character#isTitleCase(char)
+ * @see Character#isUpperCase(char)
+ * @since 1.0.2
+ */
+ public static boolean isDefined(char ch) {
+ return isDefined((int)ch);
+ }
+
+ /**
+ * Determines if a character (Unicode code point) is defined in Unicode.
+ *
+ * A character is defined if at least one of the following is true:
+ *
+ * A character is considered to be a letter if its general
+ * category type, provided by {@code Character.getType(ch)},
+ * is any of the following:
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isLetter(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is a letter;
+ * {@code false} otherwise.
+ * @see Character#isDigit(char)
+ * @see Character#isJavaIdentifierStart(char)
+ * @see Character#isJavaLetter(char)
+ * @see Character#isJavaLetterOrDigit(char)
+ * @see Character#isLetterOrDigit(char)
+ * @see Character#isLowerCase(char)
+ * @see Character#isTitleCase(char)
+ * @see Character#isUnicodeIdentifierStart(char)
+ * @see Character#isUpperCase(char)
+ */
+ public static boolean isLetter(char ch) {
+ return String.valueOf(ch).matches("\\w") && !isDigit(ch);
+ }
+
+ /**
+ * Determines if the specified character (Unicode code point) is a letter.
+ *
+ * A character is considered to be a letter if its general
+ * category type, provided by {@link Character#getType(int) getType(codePoint)},
+ * is any of the following:
+ *
+ * A character is considered to be a letter or digit if either
+ * {@code Character.isLetter(char ch)} or
+ * {@code Character.isDigit(char ch)} returns
+ * {@code true} for the character.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isLetterOrDigit(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is a letter or digit;
+ * {@code false} otherwise.
+ * @see Character#isDigit(char)
+ * @see Character#isJavaIdentifierPart(char)
+ * @see Character#isJavaLetter(char)
+ * @see Character#isJavaLetterOrDigit(char)
+ * @see Character#isLetter(char)
+ * @see Character#isUnicodeIdentifierPart(char)
+ * @since 1.0.2
+ */
+ public static boolean isLetterOrDigit(char ch) {
+ return String.valueOf(ch).matches("\\w");
+ }
+
+ /**
+ * Determines if the specified character (Unicode code point) is a letter or digit.
+ *
+ * A character is considered to be a letter or digit if either
+ * {@link #isLetter(int) isLetter(codePoint)} or
+ * {@link #isDigit(int) isDigit(codePoint)} returns
+ * {@code true} for the character.
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return {@code true} if the character is a letter or digit;
+ * {@code false} otherwise.
+ * @see Character#isDigit(int)
+ * @see Character#isJavaIdentifierPart(int)
+ * @see Character#isLetter(int)
+ * @see Character#isUnicodeIdentifierPart(int)
+ * @since 1.5
+ */
+ public static boolean isLetterOrDigit(int codePoint) {
+ return fromCodeChars(codePoint).matches("\\w");
+ }
+
+ static int getType(int x) {
+ throw new UnsupportedOperationException();
+ }
+
+ /**
+ * Converts the character argument to lowercase using case
+ * mapping information from the UnicodeData file.
+ *
+ * Note that
+ * {@code Character.isLowerCase(Character.toLowerCase(ch))}
+ * does not always return {@code true} for some ranges of
+ * characters, particularly those that are symbols or ideographs.
+ *
+ * In general, {@link String#toLowerCase()} should be used to map
+ * characters to lowercase. {@code String} case mapping methods
+ * have several benefits over {@code Character} case mapping methods.
+ * {@code String} case mapping methods can perform locale-sensitive
+ * mappings, context-sensitive mappings, and 1:M character mappings, whereas
+ * the {@code Character} case mapping methods cannot.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #toLowerCase(int)} method.
+ *
+ * @param ch the character to be converted.
+ * @return the lowercase equivalent of the character, if any;
+ * otherwise, the character itself.
+ * @see Character#isLowerCase(char)
+ * @see String#toLowerCase()
+ */
+ public static char toLowerCase(char ch) {
+ return String.valueOf(ch).toLowerCase().charAt(0);
+ }
+
+ /**
+ * Converts the character argument to uppercase using case mapping
+ * information from the UnicodeData file.
+ *
+ * Note that
+ * {@code Character.isUpperCase(Character.toUpperCase(ch))}
+ * does not always return {@code true} for some ranges of
+ * characters, particularly those that are symbols or ideographs.
+ *
+ * In general, {@link String#toUpperCase()} should be used to map
+ * characters to uppercase. {@code String} case mapping methods
+ * have several benefits over {@code Character} case mapping methods.
+ * {@code String} case mapping methods can perform locale-sensitive
+ * mappings, context-sensitive mappings, and 1:M character mappings, whereas
+ * the {@code Character} case mapping methods cannot.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #toUpperCase(int)} method.
+ *
+ * @param ch the character to be converted.
+ * @return the uppercase equivalent of the character, if any;
+ * otherwise, the character itself.
+ * @see Character#isUpperCase(char)
+ * @see String#toUpperCase()
+ */
+ public static char toUpperCase(char ch) {
+ return String.valueOf(ch).toUpperCase().charAt(0);
+ }
+
+ /**
+ * Returns the numeric value of the character {@code ch} in the
+ * specified radix.
+ *
+ * If the radix is not in the range {@code MIN_RADIX} ≤
+ * {@code radix} ≤ {@code MAX_RADIX} or if the
+ * value of {@code ch} is not a valid digit in the specified
+ * radix, {@code -1} is returned. A character is a valid digit
+ * if at least one of the following is true:
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #digit(int, int)} method.
+ *
+ * @param ch the character to be converted.
+ * @param radix the radix.
+ * @return the numeric value represented by the character in the
+ * specified radix.
+ * @see Character#forDigit(int, int)
+ * @see Character#isDigit(char)
+ */
+ public static int digit(char ch, int radix) {
+ return digit((int)ch, radix);
+ }
+
+ /**
+ * Returns the numeric value of the specified character (Unicode
+ * code point) in the specified radix.
+ *
+ * If the radix is not in the range {@code MIN_RADIX} ≤
+ * {@code radix} ≤ {@code MAX_RADIX} or if the
+ * character is not a valid digit in the specified
+ * radix, {@code -1} is returned. A character is a valid digit
+ * if at least one of the following is true:
+ *
+ * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
+ * {@code '\u005Cu005A'}), lowercase
+ * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
+ * full width variant ({@code '\u005CuFF21'} through
+ * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
+ * {@code '\u005CuFF5A'}) forms have numeric values from 10
+ * through 35. This is independent of the Unicode specification,
+ * which does not assign numeric values to these {@code char}
+ * values.
+ *
+ * If the character does not have a numeric value, then -1 is returned.
+ * If the character has a numeric value that cannot be represented as a
+ * nonnegative integer (for example, a fractional value), then -2
+ * is returned.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #getNumericValue(int)} method.
+ *
+ * @param ch the character to be converted.
+ * @return the numeric value of the character, as a nonnegative {@code int}
+ * value; -2 if the character has a numeric value that is not a
+ * nonnegative integer; -1 if the character has no numeric value.
+ * @see Character#forDigit(int, int)
+ * @see Character#isDigit(char)
+ * @since 1.1
+ */
+ public static int getNumericValue(char ch) {
+ return getNumericValue((int)ch);
+ }
+
+ /**
+ * Returns the {@code int} value that the specified
+ * character (Unicode code point) represents. For example, the character
+ * {@code '\u005Cu216C'} (the Roman numeral fifty) will return
+ * an {@code int} with a value of 50.
+ *
+ * The letters A-Z in their uppercase ({@code '\u005Cu0041'} through
+ * {@code '\u005Cu005A'}), lowercase
+ * ({@code '\u005Cu0061'} through {@code '\u005Cu007A'}), and
+ * full width variant ({@code '\u005CuFF21'} through
+ * {@code '\u005CuFF3A'} and {@code '\u005CuFF41'} through
+ * {@code '\u005CuFF5A'}) forms have numeric values from 10
+ * through 35. This is independent of the Unicode specification,
+ * which does not assign numeric values to these {@code char}
+ * values.
+ *
+ * If the character does not have a numeric value, then -1 is returned.
+ * If the character has a numeric value that cannot be represented as a
+ * nonnegative integer (for example, a fractional value), then -2
+ * is returned.
+ *
+ * @param codePoint the character (Unicode code point) to be converted.
+ * @return the numeric value of the character, as a nonnegative {@code int}
+ * value; -2 if the character has a numeric value that is not a
+ * nonnegative integer; -1 if the character has no numeric value.
+ * @see Character#forDigit(int, int)
+ * @see Character#isDigit(int)
+ * @since 1.5
+ */
+ public static int getNumericValue(int codePoint) {
+ throw new UnsupportedOperationException();
+ }
+
+ /**
+ * Determines if the specified character is ISO-LATIN-1 white space.
+ * This method returns {@code true} for the following five
+ * characters only:
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isWhitespace(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is a Java whitespace
+ * character; {@code false} otherwise.
+ * @see Character#isSpaceChar(char)
+ * @since 1.1
+ */
+ public static boolean isWhitespace(char ch) {
+ return isWhitespace((int)ch);
+ }
+
+ /**
+ * Determines if the specified character (Unicode code point) is
+ * white space according to Java. A character is a Java
+ * whitespace character if and only if it satisfies one of the
+ * following criteria:
+ *
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return {@code true} if the character is a Java whitespace
+ * character; {@code false} otherwise.
+ * @see Character#isSpaceChar(int)
+ * @since 1.5
+ */
+ public static boolean isWhitespace(int codePoint) {
+ throw new UnsupportedOperationException();
+ }
+
+ /**
+ * Determines if the specified character is an ISO control
+ * character. A character is considered to be an ISO control
+ * character if its code is in the range {@code '\u005Cu0000'}
+ * through {@code '\u005Cu001F'} or in the range
+ * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
+ *
+ * Note: This method cannot handle supplementary characters. To support
+ * all Unicode characters, including supplementary characters, use
+ * the {@link #isISOControl(int)} method.
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is an ISO control character;
+ * {@code false} otherwise.
+ *
+ * @see Character#isSpaceChar(char)
+ * @see Character#isWhitespace(char)
+ * @since 1.1
+ */
+ public static boolean isISOControl(char ch) {
+ return isISOControl((int)ch);
+ }
+
+ /**
+ * Determines if the referenced character (Unicode code point) is an ISO control
+ * character. A character is considered to be an ISO control
+ * character if its code is in the range {@code '\u005Cu0000'}
+ * through {@code '\u005Cu001F'} or in the range
+ * {@code '\u005Cu007F'} through {@code '\u005Cu009F'}.
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return {@code true} if the character is an ISO control character;
+ * {@code false} otherwise.
+ * @see Character#isSpaceChar(int)
+ * @see Character#isWhitespace(int)
+ * @since 1.5
+ */
+ public static boolean isISOControl(int codePoint) {
+ // Optimized form of:
+ // (codePoint >= 0x00 && codePoint <= 0x1F) ||
+ // (codePoint >= 0x7F && codePoint <= 0x9F);
+ return codePoint <= 0x9F &&
+ (codePoint >= 0x7F || (codePoint >>> 5 == 0));
+ }
+
+ /**
+ * Determines the character representation for a specific digit in
+ * the specified radix. If the value of {@code radix} is not a
+ * valid radix, or the value of {@code digit} is not a valid
+ * digit in the specified radix, the null character
+ * ({@code '\u005Cu0000'}) is returned.
+ *
+ * The {@code radix} argument is valid if it is greater than or
+ * equal to {@code MIN_RADIX} and less than or equal to
+ * {@code MAX_RADIX}. The {@code digit} argument is valid if
+ * {@code 0 <= digit < radix}.
+ *
+ * If the digit is less than 10, then
+ * {@code '0' + digit} is returned. Otherwise, the value
+ * {@code 'a' + digit - 10} is returned.
+ *
+ * @param digit the number to convert to a character.
+ * @param radix the radix.
+ * @return the {@code char} representation of the specified digit
+ * in the specified radix.
+ * @see Character#MIN_RADIX
+ * @see Character#MAX_RADIX
+ * @see Character#digit(char, int)
+ */
+ public static char forDigit(int digit, int radix) {
+ if ((digit >= radix) || (digit < 0)) {
+ return '\0';
+ }
+ if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) {
+ return '\0';
+ }
+ if (digit < 10) {
+ return (char)('0' + digit);
+ }
+ return (char)('a' - 10 + digit);
+ }
+
+ /**
+ * Compares two {@code Character} objects numerically.
+ *
+ * @param anotherCharacter the {@code Character} to be compared.
+
+ * @return the value {@code 0} if the argument {@code Character}
+ * is equal to this {@code Character}; a value less than
+ * {@code 0} if this {@code Character} is numerically less
+ * than the {@code Character} argument; and a value greater than
+ * {@code 0} if this {@code Character} is numerically greater
+ * than the {@code Character} argument (unsigned comparison).
+ * Note that this is strictly a numerical comparison; it is not
+ * locale-dependent.
+ * @since 1.2
+ */
+ public int compareTo(Character anotherCharacter) {
+ return compare(this.value, anotherCharacter.value);
+ }
+
+ /**
+ * Compares two {@code char} values numerically.
+ * The value returned is identical to what would be returned by:
+ *
+ *
+ * @param high the high-surrogate code value to be tested
+ * @param low the low-surrogate code value to be tested
+ * @return {@code true} if the specified high and
+ * low-surrogate code values represent a valid surrogate pair;
+ * {@code false} otherwise.
+ * @since 1.5
+ */
+ public static boolean isSurrogatePair(char high, char low) {
+ return isHighSurrogate(high) && isLowSurrogate(low);
+ }
+
+ /**
+ * Determines the number of {@code char} values needed to
+ * represent the specified character (Unicode code point). If the
+ * specified character is equal to or greater than 0x10000, then
+ * the method returns 2. Otherwise, the method returns 1.
+ *
+ *
+ * isHighSurrogate(high) && isLowSurrogate(low)
+ *
+ *
+ * a b c d e f g h i j k l m n o p q r s t u v w x y z
+ * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6'
+ * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE'
+ * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6'
+ * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF'
+ *
+ *
+ * A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
+ * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7'
+ * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF'
+ * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8'
+ * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE'
+ *
+ *
+ *
+ *
+ *
+ *
+ *
+ * Many other character ranges contain digits as well.
+ *
+ *
+ *
+ *
+ * Many other character ranges contain digits as well.
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return {@code true} if the character is a digit;
+ * {@code false} otherwise.
+ * @see Character#forDigit(int, int)
+ * @see Character#getType(int)
+ * @since 1.5
+ */
+ public static boolean isDigit(int codePoint) {
+ return fromCodeChars(codePoint).matches("\\d");
+ }
+
+ @JavaScriptBody(args = "c", body = "return String.fromCharCode(c);")
+ private native static String fromCodeChars(int codePoint);
+
+ /**
+ * Determines if a character is defined in Unicode.
+ *
+ *
+ *
+ *
+ *
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return {@code true} if the character has a defined meaning
+ * in Unicode; {@code false} otherwise.
+ * @see Character#isDigit(int)
+ * @see Character#isLetter(int)
+ * @see Character#isLetterOrDigit(int)
+ * @see Character#isLowerCase(int)
+ * @see Character#isTitleCase(int)
+ * @see Character#isUpperCase(int)
+ * @since 1.5
+ */
+ public static boolean isDefined(int codePoint) {
+ return getType(codePoint) != Character.UNASSIGNED;
+ }
+
+ /**
+ * Determines if the specified character is a letter.
+ *
+ *
+ *
+ * Not all letters have case. Many characters are
+ * letters but are neither uppercase nor lowercase nor titlecase.
+ *
+ *
+ *
+ *
+ * Not all letters have case. Many characters are
+ * letters but are neither uppercase nor lowercase nor titlecase.
+ *
+ * @param codePoint the character (Unicode code point) to be tested.
+ * @return {@code true} if the character is a letter;
+ * {@code false} otherwise.
+ * @see Character#isDigit(int)
+ * @see Character#isJavaIdentifierStart(int)
+ * @see Character#isLetterOrDigit(int)
+ * @see Character#isLowerCase(int)
+ * @see Character#isTitleCase(int)
+ * @see Character#isUnicodeIdentifierStart(int)
+ * @see Character#isUpperCase(int)
+ * @since 1.5
+ */
+ public static boolean isLetter(int codePoint) {
+ return fromCodeChars(codePoint).matches("\\w") && !isDigit(codePoint);
+ }
+
+ /**
+ * Determines if the specified character is a letter or digit.
+ *
+ *
+ *
+ *
+ *
+ *
+ * @param codePoint the character (Unicode code point) to be converted.
+ * @param radix the radix.
+ * @return the numeric value represented by the character in the
+ * specified radix.
+ * @see Character#forDigit(int, int)
+ * @see Character#isDigit(int)
+ * @since 1.5
+ */
+ public static int digit(int codePoint, int radix) {
+ throw new UnsupportedOperationException();
+ }
+
+ /**
+ * Returns the {@code int} value that the specified Unicode
+ * character represents. For example, the character
+ * {@code '\u005Cu216C'} (the roman numeral fifty) will return
+ * an int with a value of 50.
+ *
+ *
+ *
+ * @param ch the character to be tested.
+ * @return {@code true} if the character is ISO-LATIN-1 white
+ * space; {@code false} otherwise.
+ * @see Character#isSpaceChar(char)
+ * @see Character#isWhitespace(char)
+ * @deprecated Replaced by isWhitespace(char).
+ */
+ @Deprecated
+ public static boolean isSpace(char ch) {
+ return (ch <= 0x0020) &&
+ (((((1L << 0x0009) |
+ (1L << 0x000A) |
+ (1L << 0x000C) |
+ (1L << 0x000D) |
+ (1L << 0x0020)) >> ch) & 1L) != 0);
+ }
+
+
+
+ /**
+ * Determines if the specified character is white space according to Java.
+ * A character is a Java whitespace character if and only if it satisfies
+ * one of the following criteria:
+ *
+ * {@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}
+ *
+ *
+ *
+ *
+ *
+ * Character.valueOf(x).compareTo(Character.valueOf(y))
+ *
+ *
+ * @param x the first {@code char} to compare
+ * @param y the second {@code char} to compare
+ * @return the value {@code 0} if {@code x == y};
+ * a value less than {@code 0} if {@code x < y}; and
+ * a value greater than {@code 0} if {@code x > y}
+ * @since 1.7
+ */
+ public static int compare(char x, char y) {
+ return x - y;
+ }
+
+
+ /**
+ * The number of bits used to represent a char value in unsigned
+ * binary form, constant {@code 16}.
+ *
+ * @since 1.5
+ */
+ public static final int SIZE = 16;
+
+ /**
+ * Returns the value obtained by reversing the order of the bytes in the
+ * specified char value.
+ *
+ * @return the value obtained by reversing (or, equivalently, swapping)
+ * the bytes in the specified char value.
+ * @since 1.5
+ */
+ public static char reverseBytes(char ch) {
+ return (char) (((ch & 0xFF00) >> 8) | (ch << 8));
+ }
+
+}