1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/emul/src/main/java/java/lang/String.java Fri Sep 28 17:59:03 2012 +0200
1.3 @@ -0,0 +1,3077 @@
1.4 +/*
1.5 + * Copyright (c) 1994, 2010, Oracle and/or its affiliates. All rights reserved.
1.6 + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
1.7 + *
1.8 + * This code is free software; you can redistribute it and/or modify it
1.9 + * under the terms of the GNU General Public License version 2 only, as
1.10 + * published by the Free Software Foundation. Oracle designates this
1.11 + * particular file as subject to the "Classpath" exception as provided
1.12 + * by Oracle in the LICENSE file that accompanied this code.
1.13 + *
1.14 + * This code is distributed in the hope that it will be useful, but WITHOUT
1.15 + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
1.16 + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
1.17 + * version 2 for more details (a copy is included in the LICENSE file that
1.18 + * accompanied this code).
1.19 + *
1.20 + * You should have received a copy of the GNU General Public License version
1.21 + * 2 along with this work; if not, write to the Free Software Foundation,
1.22 + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
1.23 + *
1.24 + * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
1.25 + * or visit www.oracle.com if you need additional information or have any
1.26 + * questions.
1.27 + */
1.28 +
1.29 +package java.lang;
1.30 +
1.31 +import java.io.ObjectStreamClass;
1.32 +import java.io.ObjectStreamField;
1.33 +import java.io.UnsupportedEncodingException;
1.34 +import java.nio.charset.Charset;
1.35 +import java.util.ArrayList;
1.36 +import java.util.Arrays;
1.37 +import java.util.Comparator;
1.38 +import java.util.Formatter;
1.39 +import java.util.Locale;
1.40 +import java.util.regex.Matcher;
1.41 +import java.util.regex.Pattern;
1.42 +import java.util.regex.PatternSyntaxException;
1.43 +
1.44 +/**
1.45 + * The <code>String</code> class represents character strings. All
1.46 + * string literals in Java programs, such as <code>"abc"</code>, are
1.47 + * implemented as instances of this class.
1.48 + * <p>
1.49 + * Strings are constant; their values cannot be changed after they
1.50 + * are created. String buffers support mutable strings.
1.51 + * Because String objects are immutable they can be shared. For example:
1.52 + * <p><blockquote><pre>
1.53 + * String str = "abc";
1.54 + * </pre></blockquote><p>
1.55 + * is equivalent to:
1.56 + * <p><blockquote><pre>
1.57 + * char data[] = {'a', 'b', 'c'};
1.58 + * String str = new String(data);
1.59 + * </pre></blockquote><p>
1.60 + * Here are some more examples of how strings can be used:
1.61 + * <p><blockquote><pre>
1.62 + * System.out.println("abc");
1.63 + * String cde = "cde";
1.64 + * System.out.println("abc" + cde);
1.65 + * String c = "abc".substring(2,3);
1.66 + * String d = cde.substring(1, 2);
1.67 + * </pre></blockquote>
1.68 + * <p>
1.69 + * The class <code>String</code> includes methods for examining
1.70 + * individual characters of the sequence, for comparing strings, for
1.71 + * searching strings, for extracting substrings, and for creating a
1.72 + * copy of a string with all characters translated to uppercase or to
1.73 + * lowercase. Case mapping is based on the Unicode Standard version
1.74 + * specified by the {@link java.lang.Character Character} class.
1.75 + * <p>
1.76 + * The Java language provides special support for the string
1.77 + * concatenation operator ( + ), and for conversion of
1.78 + * other objects to strings. String concatenation is implemented
1.79 + * through the <code>StringBuilder</code>(or <code>StringBuffer</code>)
1.80 + * class and its <code>append</code> method.
1.81 + * String conversions are implemented through the method
1.82 + * <code>toString</code>, defined by <code>Object</code> and
1.83 + * inherited by all classes in Java. For additional information on
1.84 + * string concatenation and conversion, see Gosling, Joy, and Steele,
1.85 + * <i>The Java Language Specification</i>.
1.86 + *
1.87 + * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
1.88 + * or method in this class will cause a {@link NullPointerException} to be
1.89 + * thrown.
1.90 + *
1.91 + * <p>A <code>String</code> represents a string in the UTF-16 format
1.92 + * in which <em>supplementary characters</em> are represented by <em>surrogate
1.93 + * pairs</em> (see the section <a href="Character.html#unicode">Unicode
1.94 + * Character Representations</a> in the <code>Character</code> class for
1.95 + * more information).
1.96 + * Index values refer to <code>char</code> code units, so a supplementary
1.97 + * character uses two positions in a <code>String</code>.
1.98 + * <p>The <code>String</code> class provides methods for dealing with
1.99 + * Unicode code points (i.e., characters), in addition to those for
1.100 + * dealing with Unicode code units (i.e., <code>char</code> values).
1.101 + *
1.102 + * @author Lee Boynton
1.103 + * @author Arthur van Hoff
1.104 + * @author Martin Buchholz
1.105 + * @author Ulf Zibis
1.106 + * @see java.lang.Object#toString()
1.107 + * @see java.lang.StringBuffer
1.108 + * @see java.lang.StringBuilder
1.109 + * @see java.nio.charset.Charset
1.110 + * @since JDK1.0
1.111 + */
1.112 +
1.113 +public final class String
1.114 + implements java.io.Serializable, Comparable<String>, CharSequence
1.115 +{
1.116 + /** The value is used for character storage. */
1.117 + private final char value[];
1.118 +
1.119 + /** The offset is the first index of the storage that is used. */
1.120 + private final int offset;
1.121 +
1.122 + /** The count is the number of characters in the String. */
1.123 + private final int count;
1.124 +
1.125 + /** Cache the hash code for the string */
1.126 + private int hash; // Default to 0
1.127 +
1.128 + /** use serialVersionUID from JDK 1.0.2 for interoperability */
1.129 + private static final long serialVersionUID = -6849794470754667710L;
1.130 +
1.131 + /**
1.132 + * Class String is special cased within the Serialization Stream Protocol.
1.133 + *
1.134 + * A String instance is written initially into an ObjectOutputStream in the
1.135 + * following format:
1.136 + * <pre>
1.137 + * <code>TC_STRING</code> (utf String)
1.138 + * </pre>
1.139 + * The String is written by method <code>DataOutput.writeUTF</code>.
1.140 + * A new handle is generated to refer to all future references to the
1.141 + * string instance within the stream.
1.142 + */
1.143 + private static final ObjectStreamField[] serialPersistentFields =
1.144 + new ObjectStreamField[0];
1.145 +
1.146 + /**
1.147 + * Initializes a newly created {@code String} object so that it represents
1.148 + * an empty character sequence. Note that use of this constructor is
1.149 + * unnecessary since Strings are immutable.
1.150 + */
1.151 + public String() {
1.152 + this.offset = 0;
1.153 + this.count = 0;
1.154 + this.value = new char[0];
1.155 + }
1.156 +
1.157 + /**
1.158 + * Initializes a newly created {@code String} object so that it represents
1.159 + * the same sequence of characters as the argument; in other words, the
1.160 + * newly created string is a copy of the argument string. Unless an
1.161 + * explicit copy of {@code original} is needed, use of this constructor is
1.162 + * unnecessary since Strings are immutable.
1.163 + *
1.164 + * @param original
1.165 + * A {@code String}
1.166 + */
1.167 + public String(String original) {
1.168 + int size = original.count;
1.169 + char[] originalValue = original.value;
1.170 + char[] v;
1.171 + if (originalValue.length > size) {
1.172 + // The array representing the String is bigger than the new
1.173 + // String itself. Perhaps this constructor is being called
1.174 + // in order to trim the baggage, so make a copy of the array.
1.175 + int off = original.offset;
1.176 + v = Arrays.copyOfRange(originalValue, off, off+size);
1.177 + } else {
1.178 + // The array representing the String is the same
1.179 + // size as the String, so no point in making a copy.
1.180 + v = originalValue;
1.181 + }
1.182 + this.offset = 0;
1.183 + this.count = size;
1.184 + this.value = v;
1.185 + }
1.186 +
1.187 + /**
1.188 + * Allocates a new {@code String} so that it represents the sequence of
1.189 + * characters currently contained in the character array argument. The
1.190 + * contents of the character array are copied; subsequent modification of
1.191 + * the character array does not affect the newly created string.
1.192 + *
1.193 + * @param value
1.194 + * The initial value of the string
1.195 + */
1.196 + public String(char value[]) {
1.197 + int size = value.length;
1.198 + this.offset = 0;
1.199 + this.count = size;
1.200 + this.value = Arrays.copyOf(value, size);
1.201 + }
1.202 +
1.203 + /**
1.204 + * Allocates a new {@code String} that contains characters from a subarray
1.205 + * of the character array argument. The {@code offset} argument is the
1.206 + * index of the first character of the subarray and the {@code count}
1.207 + * argument specifies the length of the subarray. The contents of the
1.208 + * subarray are copied; subsequent modification of the character array does
1.209 + * not affect the newly created string.
1.210 + *
1.211 + * @param value
1.212 + * Array that is the source of characters
1.213 + *
1.214 + * @param offset
1.215 + * The initial offset
1.216 + *
1.217 + * @param count
1.218 + * The length
1.219 + *
1.220 + * @throws IndexOutOfBoundsException
1.221 + * If the {@code offset} and {@code count} arguments index
1.222 + * characters outside the bounds of the {@code value} array
1.223 + */
1.224 + public String(char value[], int offset, int count) {
1.225 + if (offset < 0) {
1.226 + throw new StringIndexOutOfBoundsException(offset);
1.227 + }
1.228 + if (count < 0) {
1.229 + throw new StringIndexOutOfBoundsException(count);
1.230 + }
1.231 + // Note: offset or count might be near -1>>>1.
1.232 + if (offset > value.length - count) {
1.233 + throw new StringIndexOutOfBoundsException(offset + count);
1.234 + }
1.235 + this.offset = 0;
1.236 + this.count = count;
1.237 + this.value = Arrays.copyOfRange(value, offset, offset+count);
1.238 + }
1.239 +
1.240 + /**
1.241 + * Allocates a new {@code String} that contains characters from a subarray
1.242 + * of the <a href="Character.html#unicode">Unicode code point</a> array
1.243 + * argument. The {@code offset} argument is the index of the first code
1.244 + * point of the subarray and the {@code count} argument specifies the
1.245 + * length of the subarray. The contents of the subarray are converted to
1.246 + * {@code char}s; subsequent modification of the {@code int} array does not
1.247 + * affect the newly created string.
1.248 + *
1.249 + * @param codePoints
1.250 + * Array that is the source of Unicode code points
1.251 + *
1.252 + * @param offset
1.253 + * The initial offset
1.254 + *
1.255 + * @param count
1.256 + * The length
1.257 + *
1.258 + * @throws IllegalArgumentException
1.259 + * If any invalid Unicode code point is found in {@code
1.260 + * codePoints}
1.261 + *
1.262 + * @throws IndexOutOfBoundsException
1.263 + * If the {@code offset} and {@code count} arguments index
1.264 + * characters outside the bounds of the {@code codePoints} array
1.265 + *
1.266 + * @since 1.5
1.267 + */
1.268 + public String(int[] codePoints, int offset, int count) {
1.269 + if (offset < 0) {
1.270 + throw new StringIndexOutOfBoundsException(offset);
1.271 + }
1.272 + if (count < 0) {
1.273 + throw new StringIndexOutOfBoundsException(count);
1.274 + }
1.275 + // Note: offset or count might be near -1>>>1.
1.276 + if (offset > codePoints.length - count) {
1.277 + throw new StringIndexOutOfBoundsException(offset + count);
1.278 + }
1.279 +
1.280 + final int end = offset + count;
1.281 +
1.282 + // Pass 1: Compute precise size of char[]
1.283 + int n = count;
1.284 + for (int i = offset; i < end; i++) {
1.285 + int c = codePoints[i];
1.286 + if (Character.isBmpCodePoint(c))
1.287 + continue;
1.288 + else if (Character.isValidCodePoint(c))
1.289 + n++;
1.290 + else throw new IllegalArgumentException(Integer.toString(c));
1.291 + }
1.292 +
1.293 + // Pass 2: Allocate and fill in char[]
1.294 + final char[] v = new char[n];
1.295 +
1.296 + for (int i = offset, j = 0; i < end; i++, j++) {
1.297 + int c = codePoints[i];
1.298 + if (Character.isBmpCodePoint(c))
1.299 + v[j] = (char) c;
1.300 + else
1.301 + Character.toSurrogates(c, v, j++);
1.302 + }
1.303 +
1.304 + this.value = v;
1.305 + this.count = n;
1.306 + this.offset = 0;
1.307 + }
1.308 +
1.309 + /**
1.310 + * Allocates a new {@code String} constructed from a subarray of an array
1.311 + * of 8-bit integer values.
1.312 + *
1.313 + * <p> The {@code offset} argument is the index of the first byte of the
1.314 + * subarray, and the {@code count} argument specifies the length of the
1.315 + * subarray.
1.316 + *
1.317 + * <p> Each {@code byte} in the subarray is converted to a {@code char} as
1.318 + * specified in the method above.
1.319 + *
1.320 + * @deprecated This method does not properly convert bytes into characters.
1.321 + * As of JDK 1.1, the preferred way to do this is via the
1.322 + * {@code String} constructors that take a {@link
1.323 + * java.nio.charset.Charset}, charset name, or that use the platform's
1.324 + * default charset.
1.325 + *
1.326 + * @param ascii
1.327 + * The bytes to be converted to characters
1.328 + *
1.329 + * @param hibyte
1.330 + * The top 8 bits of each 16-bit Unicode code unit
1.331 + *
1.332 + * @param offset
1.333 + * The initial offset
1.334 + * @param count
1.335 + * The length
1.336 + *
1.337 + * @throws IndexOutOfBoundsException
1.338 + * If the {@code offset} or {@code count} argument is invalid
1.339 + *
1.340 + * @see #String(byte[], int)
1.341 + * @see #String(byte[], int, int, java.lang.String)
1.342 + * @see #String(byte[], int, int, java.nio.charset.Charset)
1.343 + * @see #String(byte[], int, int)
1.344 + * @see #String(byte[], java.lang.String)
1.345 + * @see #String(byte[], java.nio.charset.Charset)
1.346 + * @see #String(byte[])
1.347 + */
1.348 + @Deprecated
1.349 + public String(byte ascii[], int hibyte, int offset, int count) {
1.350 + checkBounds(ascii, offset, count);
1.351 + char value[] = new char[count];
1.352 +
1.353 + if (hibyte == 0) {
1.354 + for (int i = count ; i-- > 0 ;) {
1.355 + value[i] = (char) (ascii[i + offset] & 0xff);
1.356 + }
1.357 + } else {
1.358 + hibyte <<= 8;
1.359 + for (int i = count ; i-- > 0 ;) {
1.360 + value[i] = (char) (hibyte | (ascii[i + offset] & 0xff));
1.361 + }
1.362 + }
1.363 + this.offset = 0;
1.364 + this.count = count;
1.365 + this.value = value;
1.366 + }
1.367 +
1.368 + /**
1.369 + * Allocates a new {@code String} containing characters constructed from
1.370 + * an array of 8-bit integer values. Each character <i>c</i>in the
1.371 + * resulting string is constructed from the corresponding component
1.372 + * <i>b</i> in the byte array such that:
1.373 + *
1.374 + * <blockquote><pre>
1.375 + * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
1.376 + * | (<b><i>b</i></b> & 0xff))
1.377 + * </pre></blockquote>
1.378 + *
1.379 + * @deprecated This method does not properly convert bytes into
1.380 + * characters. As of JDK 1.1, the preferred way to do this is via the
1.381 + * {@code String} constructors that take a {@link
1.382 + * java.nio.charset.Charset}, charset name, or that use the platform's
1.383 + * default charset.
1.384 + *
1.385 + * @param ascii
1.386 + * The bytes to be converted to characters
1.387 + *
1.388 + * @param hibyte
1.389 + * The top 8 bits of each 16-bit Unicode code unit
1.390 + *
1.391 + * @see #String(byte[], int, int, java.lang.String)
1.392 + * @see #String(byte[], int, int, java.nio.charset.Charset)
1.393 + * @see #String(byte[], int, int)
1.394 + * @see #String(byte[], java.lang.String)
1.395 + * @see #String(byte[], java.nio.charset.Charset)
1.396 + * @see #String(byte[])
1.397 + */
1.398 + @Deprecated
1.399 + public String(byte ascii[], int hibyte) {
1.400 + this(ascii, hibyte, 0, ascii.length);
1.401 + }
1.402 +
1.403 + /* Common private utility method used to bounds check the byte array
1.404 + * and requested offset & length values used by the String(byte[],..)
1.405 + * constructors.
1.406 + */
1.407 + private static void checkBounds(byte[] bytes, int offset, int length) {
1.408 + if (length < 0)
1.409 + throw new StringIndexOutOfBoundsException(length);
1.410 + if (offset < 0)
1.411 + throw new StringIndexOutOfBoundsException(offset);
1.412 + if (offset > bytes.length - length)
1.413 + throw new StringIndexOutOfBoundsException(offset + length);
1.414 + }
1.415 +
1.416 + /**
1.417 + * Constructs a new {@code String} by decoding the specified subarray of
1.418 + * bytes using the specified charset. The length of the new {@code String}
1.419 + * is a function of the charset, and hence may not be equal to the length
1.420 + * of the subarray.
1.421 + *
1.422 + * <p> The behavior of this constructor when the given bytes are not valid
1.423 + * in the given charset is unspecified. The {@link
1.424 + * java.nio.charset.CharsetDecoder} class should be used when more control
1.425 + * over the decoding process is required.
1.426 + *
1.427 + * @param bytes
1.428 + * The bytes to be decoded into characters
1.429 + *
1.430 + * @param offset
1.431 + * The index of the first byte to decode
1.432 + *
1.433 + * @param length
1.434 + * The number of bytes to decode
1.435 +
1.436 + * @param charsetName
1.437 + * The name of a supported {@linkplain java.nio.charset.Charset
1.438 + * charset}
1.439 + *
1.440 + * @throws UnsupportedEncodingException
1.441 + * If the named charset is not supported
1.442 + *
1.443 + * @throws IndexOutOfBoundsException
1.444 + * If the {@code offset} and {@code length} arguments index
1.445 + * characters outside the bounds of the {@code bytes} array
1.446 + *
1.447 + * @since JDK1.1
1.448 + */
1.449 + public String(byte bytes[], int offset, int length, String charsetName)
1.450 + throws UnsupportedEncodingException
1.451 + {
1.452 + if (charsetName == null)
1.453 + throw new NullPointerException("charsetName");
1.454 + checkBounds(bytes, offset, length);
1.455 + char[] v = StringCoding.decode(charsetName, bytes, offset, length);
1.456 + this.offset = 0;
1.457 + this.count = v.length;
1.458 + this.value = v;
1.459 + }
1.460 +
1.461 + /**
1.462 + * Constructs a new {@code String} by decoding the specified subarray of
1.463 + * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
1.464 + * The length of the new {@code String} is a function of the charset, and
1.465 + * hence may not be equal to the length of the subarray.
1.466 + *
1.467 + * <p> This method always replaces malformed-input and unmappable-character
1.468 + * sequences with this charset's default replacement string. The {@link
1.469 + * java.nio.charset.CharsetDecoder} class should be used when more control
1.470 + * over the decoding process is required.
1.471 + *
1.472 + * @param bytes
1.473 + * The bytes to be decoded into characters
1.474 + *
1.475 + * @param offset
1.476 + * The index of the first byte to decode
1.477 + *
1.478 + * @param length
1.479 + * The number of bytes to decode
1.480 + *
1.481 + * @param charset
1.482 + * The {@linkplain java.nio.charset.Charset charset} to be used to
1.483 + * decode the {@code bytes}
1.484 + *
1.485 + * @throws IndexOutOfBoundsException
1.486 + * If the {@code offset} and {@code length} arguments index
1.487 + * characters outside the bounds of the {@code bytes} array
1.488 + *
1.489 + * @since 1.6
1.490 + */
1.491 + public String(byte bytes[], int offset, int length, Charset charset) {
1.492 + if (charset == null)
1.493 + throw new NullPointerException("charset");
1.494 + checkBounds(bytes, offset, length);
1.495 + char[] v = StringCoding.decode(charset, bytes, offset, length);
1.496 + this.offset = 0;
1.497 + this.count = v.length;
1.498 + this.value = v;
1.499 + }
1.500 +
1.501 + /**
1.502 + * Constructs a new {@code String} by decoding the specified array of bytes
1.503 + * using the specified {@linkplain java.nio.charset.Charset charset}. The
1.504 + * length of the new {@code String} is a function of the charset, and hence
1.505 + * may not be equal to the length of the byte array.
1.506 + *
1.507 + * <p> The behavior of this constructor when the given bytes are not valid
1.508 + * in the given charset is unspecified. The {@link
1.509 + * java.nio.charset.CharsetDecoder} class should be used when more control
1.510 + * over the decoding process is required.
1.511 + *
1.512 + * @param bytes
1.513 + * The bytes to be decoded into characters
1.514 + *
1.515 + * @param charsetName
1.516 + * The name of a supported {@linkplain java.nio.charset.Charset
1.517 + * charset}
1.518 + *
1.519 + * @throws UnsupportedEncodingException
1.520 + * If the named charset is not supported
1.521 + *
1.522 + * @since JDK1.1
1.523 + */
1.524 + public String(byte bytes[], String charsetName)
1.525 + throws UnsupportedEncodingException
1.526 + {
1.527 + this(bytes, 0, bytes.length, charsetName);
1.528 + }
1.529 +
1.530 + /**
1.531 + * Constructs a new {@code String} by decoding the specified array of
1.532 + * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
1.533 + * The length of the new {@code String} is a function of the charset, and
1.534 + * hence may not be equal to the length of the byte array.
1.535 + *
1.536 + * <p> This method always replaces malformed-input and unmappable-character
1.537 + * sequences with this charset's default replacement string. The {@link
1.538 + * java.nio.charset.CharsetDecoder} class should be used when more control
1.539 + * over the decoding process is required.
1.540 + *
1.541 + * @param bytes
1.542 + * The bytes to be decoded into characters
1.543 + *
1.544 + * @param charset
1.545 + * The {@linkplain java.nio.charset.Charset charset} to be used to
1.546 + * decode the {@code bytes}
1.547 + *
1.548 + * @since 1.6
1.549 + */
1.550 + public String(byte bytes[], Charset charset) {
1.551 + this(bytes, 0, bytes.length, charset);
1.552 + }
1.553 +
1.554 + /**
1.555 + * Constructs a new {@code String} by decoding the specified subarray of
1.556 + * bytes using the platform's default charset. The length of the new
1.557 + * {@code String} is a function of the charset, and hence may not be equal
1.558 + * to the length of the subarray.
1.559 + *
1.560 + * <p> The behavior of this constructor when the given bytes are not valid
1.561 + * in the default charset is unspecified. The {@link
1.562 + * java.nio.charset.CharsetDecoder} class should be used when more control
1.563 + * over the decoding process is required.
1.564 + *
1.565 + * @param bytes
1.566 + * The bytes to be decoded into characters
1.567 + *
1.568 + * @param offset
1.569 + * The index of the first byte to decode
1.570 + *
1.571 + * @param length
1.572 + * The number of bytes to decode
1.573 + *
1.574 + * @throws IndexOutOfBoundsException
1.575 + * If the {@code offset} and the {@code length} arguments index
1.576 + * characters outside the bounds of the {@code bytes} array
1.577 + *
1.578 + * @since JDK1.1
1.579 + */
1.580 + public String(byte bytes[], int offset, int length) {
1.581 + checkBounds(bytes, offset, length);
1.582 + char[] v = StringCoding.decode(bytes, offset, length);
1.583 + this.offset = 0;
1.584 + this.count = v.length;
1.585 + this.value = v;
1.586 + }
1.587 +
1.588 + /**
1.589 + * Constructs a new {@code String} by decoding the specified array of bytes
1.590 + * using the platform's default charset. The length of the new {@code
1.591 + * String} is a function of the charset, and hence may not be equal to the
1.592 + * length of the byte array.
1.593 + *
1.594 + * <p> The behavior of this constructor when the given bytes are not valid
1.595 + * in the default charset is unspecified. The {@link
1.596 + * java.nio.charset.CharsetDecoder} class should be used when more control
1.597 + * over the decoding process is required.
1.598 + *
1.599 + * @param bytes
1.600 + * The bytes to be decoded into characters
1.601 + *
1.602 + * @since JDK1.1
1.603 + */
1.604 + public String(byte bytes[]) {
1.605 + this(bytes, 0, bytes.length);
1.606 + }
1.607 +
1.608 + /**
1.609 + * Allocates a new string that contains the sequence of characters
1.610 + * currently contained in the string buffer argument. The contents of the
1.611 + * string buffer are copied; subsequent modification of the string buffer
1.612 + * does not affect the newly created string.
1.613 + *
1.614 + * @param buffer
1.615 + * A {@code StringBuffer}
1.616 + */
1.617 + public String(StringBuffer buffer) {
1.618 + String result = buffer.toString();
1.619 + this.value = result.value;
1.620 + this.count = result.count;
1.621 + this.offset = result.offset;
1.622 + }
1.623 +
1.624 + /**
1.625 + * Allocates a new string that contains the sequence of characters
1.626 + * currently contained in the string builder argument. The contents of the
1.627 + * string builder are copied; subsequent modification of the string builder
1.628 + * does not affect the newly created string.
1.629 + *
1.630 + * <p> This constructor is provided to ease migration to {@code
1.631 + * StringBuilder}. Obtaining a string from a string builder via the {@code
1.632 + * toString} method is likely to run faster and is generally preferred.
1.633 + *
1.634 + * @param builder
1.635 + * A {@code StringBuilder}
1.636 + *
1.637 + * @since 1.5
1.638 + */
1.639 + public String(StringBuilder builder) {
1.640 + String result = builder.toString();
1.641 + this.value = result.value;
1.642 + this.count = result.count;
1.643 + this.offset = result.offset;
1.644 + }
1.645 +
1.646 +
1.647 + // Package private constructor which shares value array for speed.
1.648 + String(int offset, int count, char value[]) {
1.649 + this.value = value;
1.650 + this.offset = offset;
1.651 + this.count = count;
1.652 + }
1.653 +
1.654 + /**
1.655 + * Returns the length of this string.
1.656 + * The length is equal to the number of <a href="Character.html#unicode">Unicode
1.657 + * code units</a> in the string.
1.658 + *
1.659 + * @return the length of the sequence of characters represented by this
1.660 + * object.
1.661 + */
1.662 + public int length() {
1.663 + return count;
1.664 + }
1.665 +
1.666 + /**
1.667 + * Returns <tt>true</tt> if, and only if, {@link #length()} is <tt>0</tt>.
1.668 + *
1.669 + * @return <tt>true</tt> if {@link #length()} is <tt>0</tt>, otherwise
1.670 + * <tt>false</tt>
1.671 + *
1.672 + * @since 1.6
1.673 + */
1.674 + public boolean isEmpty() {
1.675 + return count == 0;
1.676 + }
1.677 +
1.678 + /**
1.679 + * Returns the <code>char</code> value at the
1.680 + * specified index. An index ranges from <code>0</code> to
1.681 + * <code>length() - 1</code>. The first <code>char</code> value of the sequence
1.682 + * is at index <code>0</code>, the next at index <code>1</code>,
1.683 + * and so on, as for array indexing.
1.684 + *
1.685 + * <p>If the <code>char</code> value specified by the index is a
1.686 + * <a href="Character.html#unicode">surrogate</a>, the surrogate
1.687 + * value is returned.
1.688 + *
1.689 + * @param index the index of the <code>char</code> value.
1.690 + * @return the <code>char</code> value at the specified index of this string.
1.691 + * The first <code>char</code> value is at index <code>0</code>.
1.692 + * @exception IndexOutOfBoundsException if the <code>index</code>
1.693 + * argument is negative or not less than the length of this
1.694 + * string.
1.695 + */
1.696 + public char charAt(int index) {
1.697 + if ((index < 0) || (index >= count)) {
1.698 + throw new StringIndexOutOfBoundsException(index);
1.699 + }
1.700 + return value[index + offset];
1.701 + }
1.702 +
1.703 + /**
1.704 + * Returns the character (Unicode code point) at the specified
1.705 + * index. The index refers to <code>char</code> values
1.706 + * (Unicode code units) and ranges from <code>0</code> to
1.707 + * {@link #length()}<code> - 1</code>.
1.708 + *
1.709 + * <p> If the <code>char</code> value specified at the given index
1.710 + * is in the high-surrogate range, the following index is less
1.711 + * than the length of this <code>String</code>, and the
1.712 + * <code>char</code> value at the following index is in the
1.713 + * low-surrogate range, then the supplementary code point
1.714 + * corresponding to this surrogate pair is returned. Otherwise,
1.715 + * the <code>char</code> value at the given index is returned.
1.716 + *
1.717 + * @param index the index to the <code>char</code> values
1.718 + * @return the code point value of the character at the
1.719 + * <code>index</code>
1.720 + * @exception IndexOutOfBoundsException if the <code>index</code>
1.721 + * argument is negative or not less than the length of this
1.722 + * string.
1.723 + * @since 1.5
1.724 + */
1.725 + public int codePointAt(int index) {
1.726 + if ((index < 0) || (index >= count)) {
1.727 + throw new StringIndexOutOfBoundsException(index);
1.728 + }
1.729 + return Character.codePointAtImpl(value, offset + index, offset + count);
1.730 + }
1.731 +
1.732 + /**
1.733 + * Returns the character (Unicode code point) before the specified
1.734 + * index. The index refers to <code>char</code> values
1.735 + * (Unicode code units) and ranges from <code>1</code> to {@link
1.736 + * CharSequence#length() length}.
1.737 + *
1.738 + * <p> If the <code>char</code> value at <code>(index - 1)</code>
1.739 + * is in the low-surrogate range, <code>(index - 2)</code> is not
1.740 + * negative, and the <code>char</code> value at <code>(index -
1.741 + * 2)</code> is in the high-surrogate range, then the
1.742 + * supplementary code point value of the surrogate pair is
1.743 + * returned. If the <code>char</code> value at <code>index -
1.744 + * 1</code> is an unpaired low-surrogate or a high-surrogate, the
1.745 + * surrogate value is returned.
1.746 + *
1.747 + * @param index the index following the code point that should be returned
1.748 + * @return the Unicode code point value before the given index.
1.749 + * @exception IndexOutOfBoundsException if the <code>index</code>
1.750 + * argument is less than 1 or greater than the length
1.751 + * of this string.
1.752 + * @since 1.5
1.753 + */
1.754 + public int codePointBefore(int index) {
1.755 + int i = index - 1;
1.756 + if ((i < 0) || (i >= count)) {
1.757 + throw new StringIndexOutOfBoundsException(index);
1.758 + }
1.759 + return Character.codePointBeforeImpl(value, offset + index, offset);
1.760 + }
1.761 +
1.762 + /**
1.763 + * Returns the number of Unicode code points in the specified text
1.764 + * range of this <code>String</code>. The text range begins at the
1.765 + * specified <code>beginIndex</code> and extends to the
1.766 + * <code>char</code> at index <code>endIndex - 1</code>. Thus the
1.767 + * length (in <code>char</code>s) of the text range is
1.768 + * <code>endIndex-beginIndex</code>. Unpaired surrogates within
1.769 + * the text range count as one code point each.
1.770 + *
1.771 + * @param beginIndex the index to the first <code>char</code> of
1.772 + * the text range.
1.773 + * @param endIndex the index after the last <code>char</code> of
1.774 + * the text range.
1.775 + * @return the number of Unicode code points in the specified text
1.776 + * range
1.777 + * @exception IndexOutOfBoundsException if the
1.778 + * <code>beginIndex</code> is negative, or <code>endIndex</code>
1.779 + * is larger than the length of this <code>String</code>, or
1.780 + * <code>beginIndex</code> is larger than <code>endIndex</code>.
1.781 + * @since 1.5
1.782 + */
1.783 + public int codePointCount(int beginIndex, int endIndex) {
1.784 + if (beginIndex < 0 || endIndex > count || beginIndex > endIndex) {
1.785 + throw new IndexOutOfBoundsException();
1.786 + }
1.787 + return Character.codePointCountImpl(value, offset+beginIndex, endIndex-beginIndex);
1.788 + }
1.789 +
1.790 + /**
1.791 + * Returns the index within this <code>String</code> that is
1.792 + * offset from the given <code>index</code> by
1.793 + * <code>codePointOffset</code> code points. Unpaired surrogates
1.794 + * within the text range given by <code>index</code> and
1.795 + * <code>codePointOffset</code> count as one code point each.
1.796 + *
1.797 + * @param index the index to be offset
1.798 + * @param codePointOffset the offset in code points
1.799 + * @return the index within this <code>String</code>
1.800 + * @exception IndexOutOfBoundsException if <code>index</code>
1.801 + * is negative or larger then the length of this
1.802 + * <code>String</code>, or if <code>codePointOffset</code> is positive
1.803 + * and the substring starting with <code>index</code> has fewer
1.804 + * than <code>codePointOffset</code> code points,
1.805 + * or if <code>codePointOffset</code> is negative and the substring
1.806 + * before <code>index</code> has fewer than the absolute value
1.807 + * of <code>codePointOffset</code> code points.
1.808 + * @since 1.5
1.809 + */
1.810 + public int offsetByCodePoints(int index, int codePointOffset) {
1.811 + if (index < 0 || index > count) {
1.812 + throw new IndexOutOfBoundsException();
1.813 + }
1.814 + return Character.offsetByCodePointsImpl(value, offset, count,
1.815 + offset+index, codePointOffset) - offset;
1.816 + }
1.817 +
1.818 + /**
1.819 + * Copy characters from this string into dst starting at dstBegin.
1.820 + * This method doesn't perform any range checking.
1.821 + */
1.822 + void getChars(char dst[], int dstBegin) {
1.823 + System.arraycopy(value, offset, dst, dstBegin, count);
1.824 + }
1.825 +
1.826 + /**
1.827 + * Copies characters from this string into the destination character
1.828 + * array.
1.829 + * <p>
1.830 + * The first character to be copied is at index <code>srcBegin</code>;
1.831 + * the last character to be copied is at index <code>srcEnd-1</code>
1.832 + * (thus the total number of characters to be copied is
1.833 + * <code>srcEnd-srcBegin</code>). The characters are copied into the
1.834 + * subarray of <code>dst</code> starting at index <code>dstBegin</code>
1.835 + * and ending at index:
1.836 + * <p><blockquote><pre>
1.837 + * dstbegin + (srcEnd-srcBegin) - 1
1.838 + * </pre></blockquote>
1.839 + *
1.840 + * @param srcBegin index of the first character in the string
1.841 + * to copy.
1.842 + * @param srcEnd index after the last character in the string
1.843 + * to copy.
1.844 + * @param dst the destination array.
1.845 + * @param dstBegin the start offset in the destination array.
1.846 + * @exception IndexOutOfBoundsException If any of the following
1.847 + * is true:
1.848 + * <ul><li><code>srcBegin</code> is negative.
1.849 + * <li><code>srcBegin</code> is greater than <code>srcEnd</code>
1.850 + * <li><code>srcEnd</code> is greater than the length of this
1.851 + * string
1.852 + * <li><code>dstBegin</code> is negative
1.853 + * <li><code>dstBegin+(srcEnd-srcBegin)</code> is larger than
1.854 + * <code>dst.length</code></ul>
1.855 + */
1.856 + public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
1.857 + if (srcBegin < 0) {
1.858 + throw new StringIndexOutOfBoundsException(srcBegin);
1.859 + }
1.860 + if (srcEnd > count) {
1.861 + throw new StringIndexOutOfBoundsException(srcEnd);
1.862 + }
1.863 + if (srcBegin > srcEnd) {
1.864 + throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
1.865 + }
1.866 + System.arraycopy(value, offset + srcBegin, dst, dstBegin,
1.867 + srcEnd - srcBegin);
1.868 + }
1.869 +
1.870 + /**
1.871 + * Copies characters from this string into the destination byte array. Each
1.872 + * byte receives the 8 low-order bits of the corresponding character. The
1.873 + * eight high-order bits of each character are not copied and do not
1.874 + * participate in the transfer in any way.
1.875 + *
1.876 + * <p> The first character to be copied is at index {@code srcBegin}; the
1.877 + * last character to be copied is at index {@code srcEnd-1}. The total
1.878 + * number of characters to be copied is {@code srcEnd-srcBegin}. The
1.879 + * characters, converted to bytes, are copied into the subarray of {@code
1.880 + * dst} starting at index {@code dstBegin} and ending at index:
1.881 + *
1.882 + * <blockquote><pre>
1.883 + * dstbegin + (srcEnd-srcBegin) - 1
1.884 + * </pre></blockquote>
1.885 + *
1.886 + * @deprecated This method does not properly convert characters into
1.887 + * bytes. As of JDK 1.1, the preferred way to do this is via the
1.888 + * {@link #getBytes()} method, which uses the platform's default charset.
1.889 + *
1.890 + * @param srcBegin
1.891 + * Index of the first character in the string to copy
1.892 + *
1.893 + * @param srcEnd
1.894 + * Index after the last character in the string to copy
1.895 + *
1.896 + * @param dst
1.897 + * The destination array
1.898 + *
1.899 + * @param dstBegin
1.900 + * The start offset in the destination array
1.901 + *
1.902 + * @throws IndexOutOfBoundsException
1.903 + * If any of the following is true:
1.904 + * <ul>
1.905 + * <li> {@code srcBegin} is negative
1.906 + * <li> {@code srcBegin} is greater than {@code srcEnd}
1.907 + * <li> {@code srcEnd} is greater than the length of this String
1.908 + * <li> {@code dstBegin} is negative
1.909 + * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
1.910 + * dst.length}
1.911 + * </ul>
1.912 + */
1.913 + @Deprecated
1.914 + public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
1.915 + if (srcBegin < 0) {
1.916 + throw new StringIndexOutOfBoundsException(srcBegin);
1.917 + }
1.918 + if (srcEnd > count) {
1.919 + throw new StringIndexOutOfBoundsException(srcEnd);
1.920 + }
1.921 + if (srcBegin > srcEnd) {
1.922 + throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
1.923 + }
1.924 + int j = dstBegin;
1.925 + int n = offset + srcEnd;
1.926 + int i = offset + srcBegin;
1.927 + char[] val = value; /* avoid getfield opcode */
1.928 +
1.929 + while (i < n) {
1.930 + dst[j++] = (byte)val[i++];
1.931 + }
1.932 + }
1.933 +
1.934 + /**
1.935 + * Encodes this {@code String} into a sequence of bytes using the named
1.936 + * charset, storing the result into a new byte array.
1.937 + *
1.938 + * <p> The behavior of this method when this string cannot be encoded in
1.939 + * the given charset is unspecified. The {@link
1.940 + * java.nio.charset.CharsetEncoder} class should be used when more control
1.941 + * over the encoding process is required.
1.942 + *
1.943 + * @param charsetName
1.944 + * The name of a supported {@linkplain java.nio.charset.Charset
1.945 + * charset}
1.946 + *
1.947 + * @return The resultant byte array
1.948 + *
1.949 + * @throws UnsupportedEncodingException
1.950 + * If the named charset is not supported
1.951 + *
1.952 + * @since JDK1.1
1.953 + */
1.954 + public byte[] getBytes(String charsetName)
1.955 + throws UnsupportedEncodingException
1.956 + {
1.957 + if (charsetName == null) throw new NullPointerException();
1.958 + return StringCoding.encode(charsetName, value, offset, count);
1.959 + }
1.960 +
1.961 + /**
1.962 + * Encodes this {@code String} into a sequence of bytes using the given
1.963 + * {@linkplain java.nio.charset.Charset charset}, storing the result into a
1.964 + * new byte array.
1.965 + *
1.966 + * <p> This method always replaces malformed-input and unmappable-character
1.967 + * sequences with this charset's default replacement byte array. The
1.968 + * {@link java.nio.charset.CharsetEncoder} class should be used when more
1.969 + * control over the encoding process is required.
1.970 + *
1.971 + * @param charset
1.972 + * The {@linkplain java.nio.charset.Charset} to be used to encode
1.973 + * the {@code String}
1.974 + *
1.975 + * @return The resultant byte array
1.976 + *
1.977 + * @since 1.6
1.978 + */
1.979 + public byte[] getBytes(Charset charset) {
1.980 + if (charset == null) throw new NullPointerException();
1.981 + return StringCoding.encode(charset, value, offset, count);
1.982 + }
1.983 +
1.984 + /**
1.985 + * Encodes this {@code String} into a sequence of bytes using the
1.986 + * platform's default charset, storing the result into a new byte array.
1.987 + *
1.988 + * <p> The behavior of this method when this string cannot be encoded in
1.989 + * the default charset is unspecified. The {@link
1.990 + * java.nio.charset.CharsetEncoder} class should be used when more control
1.991 + * over the encoding process is required.
1.992 + *
1.993 + * @return The resultant byte array
1.994 + *
1.995 + * @since JDK1.1
1.996 + */
1.997 + public byte[] getBytes() {
1.998 + return StringCoding.encode(value, offset, count);
1.999 + }
1.1000 +
1.1001 + /**
1.1002 + * Compares this string to the specified object. The result is {@code
1.1003 + * true} if and only if the argument is not {@code null} and is a {@code
1.1004 + * String} object that represents the same sequence of characters as this
1.1005 + * object.
1.1006 + *
1.1007 + * @param anObject
1.1008 + * The object to compare this {@code String} against
1.1009 + *
1.1010 + * @return {@code true} if the given object represents a {@code String}
1.1011 + * equivalent to this string, {@code false} otherwise
1.1012 + *
1.1013 + * @see #compareTo(String)
1.1014 + * @see #equalsIgnoreCase(String)
1.1015 + */
1.1016 + public boolean equals(Object anObject) {
1.1017 + if (this == anObject) {
1.1018 + return true;
1.1019 + }
1.1020 + if (anObject instanceof String) {
1.1021 + String anotherString = (String)anObject;
1.1022 + int n = count;
1.1023 + if (n == anotherString.count) {
1.1024 + char v1[] = value;
1.1025 + char v2[] = anotherString.value;
1.1026 + int i = offset;
1.1027 + int j = anotherString.offset;
1.1028 + while (n-- != 0) {
1.1029 + if (v1[i++] != v2[j++])
1.1030 + return false;
1.1031 + }
1.1032 + return true;
1.1033 + }
1.1034 + }
1.1035 + return false;
1.1036 + }
1.1037 +
1.1038 + /**
1.1039 + * Compares this string to the specified {@code StringBuffer}. The result
1.1040 + * is {@code true} if and only if this {@code String} represents the same
1.1041 + * sequence of characters as the specified {@code StringBuffer}.
1.1042 + *
1.1043 + * @param sb
1.1044 + * The {@code StringBuffer} to compare this {@code String} against
1.1045 + *
1.1046 + * @return {@code true} if this {@code String} represents the same
1.1047 + * sequence of characters as the specified {@code StringBuffer},
1.1048 + * {@code false} otherwise
1.1049 + *
1.1050 + * @since 1.4
1.1051 + */
1.1052 + public boolean contentEquals(StringBuffer sb) {
1.1053 + synchronized(sb) {
1.1054 + return contentEquals((CharSequence)sb);
1.1055 + }
1.1056 + }
1.1057 +
1.1058 + /**
1.1059 + * Compares this string to the specified {@code CharSequence}. The result
1.1060 + * is {@code true} if and only if this {@code String} represents the same
1.1061 + * sequence of char values as the specified sequence.
1.1062 + *
1.1063 + * @param cs
1.1064 + * The sequence to compare this {@code String} against
1.1065 + *
1.1066 + * @return {@code true} if this {@code String} represents the same
1.1067 + * sequence of char values as the specified sequence, {@code
1.1068 + * false} otherwise
1.1069 + *
1.1070 + * @since 1.5
1.1071 + */
1.1072 + public boolean contentEquals(CharSequence cs) {
1.1073 + if (count != cs.length())
1.1074 + return false;
1.1075 + // Argument is a StringBuffer, StringBuilder
1.1076 + if (cs instanceof AbstractStringBuilder) {
1.1077 + char v1[] = value;
1.1078 + char v2[] = ((AbstractStringBuilder)cs).getValue();
1.1079 + int i = offset;
1.1080 + int j = 0;
1.1081 + int n = count;
1.1082 + while (n-- != 0) {
1.1083 + if (v1[i++] != v2[j++])
1.1084 + return false;
1.1085 + }
1.1086 + return true;
1.1087 + }
1.1088 + // Argument is a String
1.1089 + if (cs.equals(this))
1.1090 + return true;
1.1091 + // Argument is a generic CharSequence
1.1092 + char v1[] = value;
1.1093 + int i = offset;
1.1094 + int j = 0;
1.1095 + int n = count;
1.1096 + while (n-- != 0) {
1.1097 + if (v1[i++] != cs.charAt(j++))
1.1098 + return false;
1.1099 + }
1.1100 + return true;
1.1101 + }
1.1102 +
1.1103 + /**
1.1104 + * Compares this {@code String} to another {@code String}, ignoring case
1.1105 + * considerations. Two strings are considered equal ignoring case if they
1.1106 + * are of the same length and corresponding characters in the two strings
1.1107 + * are equal ignoring case.
1.1108 + *
1.1109 + * <p> Two characters {@code c1} and {@code c2} are considered the same
1.1110 + * ignoring case if at least one of the following is true:
1.1111 + * <ul>
1.1112 + * <li> The two characters are the same (as compared by the
1.1113 + * {@code ==} operator)
1.1114 + * <li> Applying the method {@link
1.1115 + * java.lang.Character#toUpperCase(char)} to each character
1.1116 + * produces the same result
1.1117 + * <li> Applying the method {@link
1.1118 + * java.lang.Character#toLowerCase(char)} to each character
1.1119 + * produces the same result
1.1120 + * </ul>
1.1121 + *
1.1122 + * @param anotherString
1.1123 + * The {@code String} to compare this {@code String} against
1.1124 + *
1.1125 + * @return {@code true} if the argument is not {@code null} and it
1.1126 + * represents an equivalent {@code String} ignoring case; {@code
1.1127 + * false} otherwise
1.1128 + *
1.1129 + * @see #equals(Object)
1.1130 + */
1.1131 + public boolean equalsIgnoreCase(String anotherString) {
1.1132 + return (this == anotherString) ? true :
1.1133 + (anotherString != null) && (anotherString.count == count) &&
1.1134 + regionMatches(true, 0, anotherString, 0, count);
1.1135 + }
1.1136 +
1.1137 + /**
1.1138 + * Compares two strings lexicographically.
1.1139 + * The comparison is based on the Unicode value of each character in
1.1140 + * the strings. The character sequence represented by this
1.1141 + * <code>String</code> object is compared lexicographically to the
1.1142 + * character sequence represented by the argument string. The result is
1.1143 + * a negative integer if this <code>String</code> object
1.1144 + * lexicographically precedes the argument string. The result is a
1.1145 + * positive integer if this <code>String</code> object lexicographically
1.1146 + * follows the argument string. The result is zero if the strings
1.1147 + * are equal; <code>compareTo</code> returns <code>0</code> exactly when
1.1148 + * the {@link #equals(Object)} method would return <code>true</code>.
1.1149 + * <p>
1.1150 + * This is the definition of lexicographic ordering. If two strings are
1.1151 + * different, then either they have different characters at some index
1.1152 + * that is a valid index for both strings, or their lengths are different,
1.1153 + * or both. If they have different characters at one or more index
1.1154 + * positions, let <i>k</i> be the smallest such index; then the string
1.1155 + * whose character at position <i>k</i> has the smaller value, as
1.1156 + * determined by using the < operator, lexicographically precedes the
1.1157 + * other string. In this case, <code>compareTo</code> returns the
1.1158 + * difference of the two character values at position <code>k</code> in
1.1159 + * the two string -- that is, the value:
1.1160 + * <blockquote><pre>
1.1161 + * this.charAt(k)-anotherString.charAt(k)
1.1162 + * </pre></blockquote>
1.1163 + * If there is no index position at which they differ, then the shorter
1.1164 + * string lexicographically precedes the longer string. In this case,
1.1165 + * <code>compareTo</code> returns the difference of the lengths of the
1.1166 + * strings -- that is, the value:
1.1167 + * <blockquote><pre>
1.1168 + * this.length()-anotherString.length()
1.1169 + * </pre></blockquote>
1.1170 + *
1.1171 + * @param anotherString the <code>String</code> to be compared.
1.1172 + * @return the value <code>0</code> if the argument string is equal to
1.1173 + * this string; a value less than <code>0</code> if this string
1.1174 + * is lexicographically less than the string argument; and a
1.1175 + * value greater than <code>0</code> if this string is
1.1176 + * lexicographically greater than the string argument.
1.1177 + */
1.1178 + public int compareTo(String anotherString) {
1.1179 + int len1 = count;
1.1180 + int len2 = anotherString.count;
1.1181 + int n = Math.min(len1, len2);
1.1182 + char v1[] = value;
1.1183 + char v2[] = anotherString.value;
1.1184 + int i = offset;
1.1185 + int j = anotherString.offset;
1.1186 +
1.1187 + if (i == j) {
1.1188 + int k = i;
1.1189 + int lim = n + i;
1.1190 + while (k < lim) {
1.1191 + char c1 = v1[k];
1.1192 + char c2 = v2[k];
1.1193 + if (c1 != c2) {
1.1194 + return c1 - c2;
1.1195 + }
1.1196 + k++;
1.1197 + }
1.1198 + } else {
1.1199 + while (n-- != 0) {
1.1200 + char c1 = v1[i++];
1.1201 + char c2 = v2[j++];
1.1202 + if (c1 != c2) {
1.1203 + return c1 - c2;
1.1204 + }
1.1205 + }
1.1206 + }
1.1207 + return len1 - len2;
1.1208 + }
1.1209 +
1.1210 + /**
1.1211 + * A Comparator that orders <code>String</code> objects as by
1.1212 + * <code>compareToIgnoreCase</code>. This comparator is serializable.
1.1213 + * <p>
1.1214 + * Note that this Comparator does <em>not</em> take locale into account,
1.1215 + * and will result in an unsatisfactory ordering for certain locales.
1.1216 + * The java.text package provides <em>Collators</em> to allow
1.1217 + * locale-sensitive ordering.
1.1218 + *
1.1219 + * @see java.text.Collator#compare(String, String)
1.1220 + * @since 1.2
1.1221 + */
1.1222 + public static final Comparator<String> CASE_INSENSITIVE_ORDER
1.1223 + = new CaseInsensitiveComparator();
1.1224 + private static class CaseInsensitiveComparator
1.1225 + implements Comparator<String>, java.io.Serializable {
1.1226 + // use serialVersionUID from JDK 1.2.2 for interoperability
1.1227 + private static final long serialVersionUID = 8575799808933029326L;
1.1228 +
1.1229 + public int compare(String s1, String s2) {
1.1230 + int n1 = s1.length();
1.1231 + int n2 = s2.length();
1.1232 + int min = Math.min(n1, n2);
1.1233 + for (int i = 0; i < min; i++) {
1.1234 + char c1 = s1.charAt(i);
1.1235 + char c2 = s2.charAt(i);
1.1236 + if (c1 != c2) {
1.1237 + c1 = Character.toUpperCase(c1);
1.1238 + c2 = Character.toUpperCase(c2);
1.1239 + if (c1 != c2) {
1.1240 + c1 = Character.toLowerCase(c1);
1.1241 + c2 = Character.toLowerCase(c2);
1.1242 + if (c1 != c2) {
1.1243 + // No overflow because of numeric promotion
1.1244 + return c1 - c2;
1.1245 + }
1.1246 + }
1.1247 + }
1.1248 + }
1.1249 + return n1 - n2;
1.1250 + }
1.1251 + }
1.1252 +
1.1253 + /**
1.1254 + * Compares two strings lexicographically, ignoring case
1.1255 + * differences. This method returns an integer whose sign is that of
1.1256 + * calling <code>compareTo</code> with normalized versions of the strings
1.1257 + * where case differences have been eliminated by calling
1.1258 + * <code>Character.toLowerCase(Character.toUpperCase(character))</code> on
1.1259 + * each character.
1.1260 + * <p>
1.1261 + * Note that this method does <em>not</em> take locale into account,
1.1262 + * and will result in an unsatisfactory ordering for certain locales.
1.1263 + * The java.text package provides <em>collators</em> to allow
1.1264 + * locale-sensitive ordering.
1.1265 + *
1.1266 + * @param str the <code>String</code> to be compared.
1.1267 + * @return a negative integer, zero, or a positive integer as the
1.1268 + * specified String is greater than, equal to, or less
1.1269 + * than this String, ignoring case considerations.
1.1270 + * @see java.text.Collator#compare(String, String)
1.1271 + * @since 1.2
1.1272 + */
1.1273 + public int compareToIgnoreCase(String str) {
1.1274 + return CASE_INSENSITIVE_ORDER.compare(this, str);
1.1275 + }
1.1276 +
1.1277 + /**
1.1278 + * Tests if two string regions are equal.
1.1279 + * <p>
1.1280 + * A substring of this <tt>String</tt> object is compared to a substring
1.1281 + * of the argument other. The result is true if these substrings
1.1282 + * represent identical character sequences. The substring of this
1.1283 + * <tt>String</tt> object to be compared begins at index <tt>toffset</tt>
1.1284 + * and has length <tt>len</tt>. The substring of other to be compared
1.1285 + * begins at index <tt>ooffset</tt> and has length <tt>len</tt>. The
1.1286 + * result is <tt>false</tt> if and only if at least one of the following
1.1287 + * is true:
1.1288 + * <ul><li><tt>toffset</tt> is negative.
1.1289 + * <li><tt>ooffset</tt> is negative.
1.1290 + * <li><tt>toffset+len</tt> is greater than the length of this
1.1291 + * <tt>String</tt> object.
1.1292 + * <li><tt>ooffset+len</tt> is greater than the length of the other
1.1293 + * argument.
1.1294 + * <li>There is some nonnegative integer <i>k</i> less than <tt>len</tt>
1.1295 + * such that:
1.1296 + * <tt>this.charAt(toffset+<i>k</i>) != other.charAt(ooffset+<i>k</i>)</tt>
1.1297 + * </ul>
1.1298 + *
1.1299 + * @param toffset the starting offset of the subregion in this string.
1.1300 + * @param other the string argument.
1.1301 + * @param ooffset the starting offset of the subregion in the string
1.1302 + * argument.
1.1303 + * @param len the number of characters to compare.
1.1304 + * @return <code>true</code> if the specified subregion of this string
1.1305 + * exactly matches the specified subregion of the string argument;
1.1306 + * <code>false</code> otherwise.
1.1307 + */
1.1308 + public boolean regionMatches(int toffset, String other, int ooffset,
1.1309 + int len) {
1.1310 + char ta[] = value;
1.1311 + int to = offset + toffset;
1.1312 + char pa[] = other.value;
1.1313 + int po = other.offset + ooffset;
1.1314 + // Note: toffset, ooffset, or len might be near -1>>>1.
1.1315 + if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len)
1.1316 + || (ooffset > (long)other.count - len)) {
1.1317 + return false;
1.1318 + }
1.1319 + while (len-- > 0) {
1.1320 + if (ta[to++] != pa[po++]) {
1.1321 + return false;
1.1322 + }
1.1323 + }
1.1324 + return true;
1.1325 + }
1.1326 +
1.1327 + /**
1.1328 + * Tests if two string regions are equal.
1.1329 + * <p>
1.1330 + * A substring of this <tt>String</tt> object is compared to a substring
1.1331 + * of the argument <tt>other</tt>. The result is <tt>true</tt> if these
1.1332 + * substrings represent character sequences that are the same, ignoring
1.1333 + * case if and only if <tt>ignoreCase</tt> is true. The substring of
1.1334 + * this <tt>String</tt> object to be compared begins at index
1.1335 + * <tt>toffset</tt> and has length <tt>len</tt>. The substring of
1.1336 + * <tt>other</tt> to be compared begins at index <tt>ooffset</tt> and
1.1337 + * has length <tt>len</tt>. The result is <tt>false</tt> if and only if
1.1338 + * at least one of the following is true:
1.1339 + * <ul><li><tt>toffset</tt> is negative.
1.1340 + * <li><tt>ooffset</tt> is negative.
1.1341 + * <li><tt>toffset+len</tt> is greater than the length of this
1.1342 + * <tt>String</tt> object.
1.1343 + * <li><tt>ooffset+len</tt> is greater than the length of the other
1.1344 + * argument.
1.1345 + * <li><tt>ignoreCase</tt> is <tt>false</tt> and there is some nonnegative
1.1346 + * integer <i>k</i> less than <tt>len</tt> such that:
1.1347 + * <blockquote><pre>
1.1348 + * this.charAt(toffset+k) != other.charAt(ooffset+k)
1.1349 + * </pre></blockquote>
1.1350 + * <li><tt>ignoreCase</tt> is <tt>true</tt> and there is some nonnegative
1.1351 + * integer <i>k</i> less than <tt>len</tt> such that:
1.1352 + * <blockquote><pre>
1.1353 + * Character.toLowerCase(this.charAt(toffset+k)) !=
1.1354 + Character.toLowerCase(other.charAt(ooffset+k))
1.1355 + * </pre></blockquote>
1.1356 + * and:
1.1357 + * <blockquote><pre>
1.1358 + * Character.toUpperCase(this.charAt(toffset+k)) !=
1.1359 + * Character.toUpperCase(other.charAt(ooffset+k))
1.1360 + * </pre></blockquote>
1.1361 + * </ul>
1.1362 + *
1.1363 + * @param ignoreCase if <code>true</code>, ignore case when comparing
1.1364 + * characters.
1.1365 + * @param toffset the starting offset of the subregion in this
1.1366 + * string.
1.1367 + * @param other the string argument.
1.1368 + * @param ooffset the starting offset of the subregion in the string
1.1369 + * argument.
1.1370 + * @param len the number of characters to compare.
1.1371 + * @return <code>true</code> if the specified subregion of this string
1.1372 + * matches the specified subregion of the string argument;
1.1373 + * <code>false</code> otherwise. Whether the matching is exact
1.1374 + * or case insensitive depends on the <code>ignoreCase</code>
1.1375 + * argument.
1.1376 + */
1.1377 + public boolean regionMatches(boolean ignoreCase, int toffset,
1.1378 + String other, int ooffset, int len) {
1.1379 + char ta[] = value;
1.1380 + int to = offset + toffset;
1.1381 + char pa[] = other.value;
1.1382 + int po = other.offset + ooffset;
1.1383 + // Note: toffset, ooffset, or len might be near -1>>>1.
1.1384 + if ((ooffset < 0) || (toffset < 0) || (toffset > (long)count - len) ||
1.1385 + (ooffset > (long)other.count - len)) {
1.1386 + return false;
1.1387 + }
1.1388 + while (len-- > 0) {
1.1389 + char c1 = ta[to++];
1.1390 + char c2 = pa[po++];
1.1391 + if (c1 == c2) {
1.1392 + continue;
1.1393 + }
1.1394 + if (ignoreCase) {
1.1395 + // If characters don't match but case may be ignored,
1.1396 + // try converting both characters to uppercase.
1.1397 + // If the results match, then the comparison scan should
1.1398 + // continue.
1.1399 + char u1 = Character.toUpperCase(c1);
1.1400 + char u2 = Character.toUpperCase(c2);
1.1401 + if (u1 == u2) {
1.1402 + continue;
1.1403 + }
1.1404 + // Unfortunately, conversion to uppercase does not work properly
1.1405 + // for the Georgian alphabet, which has strange rules about case
1.1406 + // conversion. So we need to make one last check before
1.1407 + // exiting.
1.1408 + if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1.1409 + continue;
1.1410 + }
1.1411 + }
1.1412 + return false;
1.1413 + }
1.1414 + return true;
1.1415 + }
1.1416 +
1.1417 + /**
1.1418 + * Tests if the substring of this string beginning at the
1.1419 + * specified index starts with the specified prefix.
1.1420 + *
1.1421 + * @param prefix the prefix.
1.1422 + * @param toffset where to begin looking in this string.
1.1423 + * @return <code>true</code> if the character sequence represented by the
1.1424 + * argument is a prefix of the substring of this object starting
1.1425 + * at index <code>toffset</code>; <code>false</code> otherwise.
1.1426 + * The result is <code>false</code> if <code>toffset</code> is
1.1427 + * negative or greater than the length of this
1.1428 + * <code>String</code> object; otherwise the result is the same
1.1429 + * as the result of the expression
1.1430 + * <pre>
1.1431 + * this.substring(toffset).startsWith(prefix)
1.1432 + * </pre>
1.1433 + */
1.1434 + public boolean startsWith(String prefix, int toffset) {
1.1435 + char ta[] = value;
1.1436 + int to = offset + toffset;
1.1437 + char pa[] = prefix.value;
1.1438 + int po = prefix.offset;
1.1439 + int pc = prefix.count;
1.1440 + // Note: toffset might be near -1>>>1.
1.1441 + if ((toffset < 0) || (toffset > count - pc)) {
1.1442 + return false;
1.1443 + }
1.1444 + while (--pc >= 0) {
1.1445 + if (ta[to++] != pa[po++]) {
1.1446 + return false;
1.1447 + }
1.1448 + }
1.1449 + return true;
1.1450 + }
1.1451 +
1.1452 + /**
1.1453 + * Tests if this string starts with the specified prefix.
1.1454 + *
1.1455 + * @param prefix the prefix.
1.1456 + * @return <code>true</code> if the character sequence represented by the
1.1457 + * argument is a prefix of the character sequence represented by
1.1458 + * this string; <code>false</code> otherwise.
1.1459 + * Note also that <code>true</code> will be returned if the
1.1460 + * argument is an empty string or is equal to this
1.1461 + * <code>String</code> object as determined by the
1.1462 + * {@link #equals(Object)} method.
1.1463 + * @since 1. 0
1.1464 + */
1.1465 + public boolean startsWith(String prefix) {
1.1466 + return startsWith(prefix, 0);
1.1467 + }
1.1468 +
1.1469 + /**
1.1470 + * Tests if this string ends with the specified suffix.
1.1471 + *
1.1472 + * @param suffix the suffix.
1.1473 + * @return <code>true</code> if the character sequence represented by the
1.1474 + * argument is a suffix of the character sequence represented by
1.1475 + * this object; <code>false</code> otherwise. Note that the
1.1476 + * result will be <code>true</code> if the argument is the
1.1477 + * empty string or is equal to this <code>String</code> object
1.1478 + * as determined by the {@link #equals(Object)} method.
1.1479 + */
1.1480 + public boolean endsWith(String suffix) {
1.1481 + return startsWith(suffix, count - suffix.count);
1.1482 + }
1.1483 +
1.1484 + /**
1.1485 + * Returns a hash code for this string. The hash code for a
1.1486 + * <code>String</code> object is computed as
1.1487 + * <blockquote><pre>
1.1488 + * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1.1489 + * </pre></blockquote>
1.1490 + * using <code>int</code> arithmetic, where <code>s[i]</code> is the
1.1491 + * <i>i</i>th character of the string, <code>n</code> is the length of
1.1492 + * the string, and <code>^</code> indicates exponentiation.
1.1493 + * (The hash value of the empty string is zero.)
1.1494 + *
1.1495 + * @return a hash code value for this object.
1.1496 + */
1.1497 + public int hashCode() {
1.1498 + int h = hash;
1.1499 + if (h == 0 && count > 0) {
1.1500 + int off = offset;
1.1501 + char val[] = value;
1.1502 + int len = count;
1.1503 +
1.1504 + for (int i = 0; i < len; i++) {
1.1505 + h = 31*h + val[off++];
1.1506 + }
1.1507 + hash = h;
1.1508 + }
1.1509 + return h;
1.1510 + }
1.1511 +
1.1512 + /**
1.1513 + * Returns the index within this string of the first occurrence of
1.1514 + * the specified character. If a character with value
1.1515 + * <code>ch</code> occurs in the character sequence represented by
1.1516 + * this <code>String</code> object, then the index (in Unicode
1.1517 + * code units) of the first such occurrence is returned. For
1.1518 + * values of <code>ch</code> in the range from 0 to 0xFFFF
1.1519 + * (inclusive), this is the smallest value <i>k</i> such that:
1.1520 + * <blockquote><pre>
1.1521 + * this.charAt(<i>k</i>) == ch
1.1522 + * </pre></blockquote>
1.1523 + * is true. For other values of <code>ch</code>, it is the
1.1524 + * smallest value <i>k</i> such that:
1.1525 + * <blockquote><pre>
1.1526 + * this.codePointAt(<i>k</i>) == ch
1.1527 + * </pre></blockquote>
1.1528 + * is true. In either case, if no such character occurs in this
1.1529 + * string, then <code>-1</code> is returned.
1.1530 + *
1.1531 + * @param ch a character (Unicode code point).
1.1532 + * @return the index of the first occurrence of the character in the
1.1533 + * character sequence represented by this object, or
1.1534 + * <code>-1</code> if the character does not occur.
1.1535 + */
1.1536 + public int indexOf(int ch) {
1.1537 + return indexOf(ch, 0);
1.1538 + }
1.1539 +
1.1540 + /**
1.1541 + * Returns the index within this string of the first occurrence of the
1.1542 + * specified character, starting the search at the specified index.
1.1543 + * <p>
1.1544 + * If a character with value <code>ch</code> occurs in the
1.1545 + * character sequence represented by this <code>String</code>
1.1546 + * object at an index no smaller than <code>fromIndex</code>, then
1.1547 + * the index of the first such occurrence is returned. For values
1.1548 + * of <code>ch</code> in the range from 0 to 0xFFFF (inclusive),
1.1549 + * this is the smallest value <i>k</i> such that:
1.1550 + * <blockquote><pre>
1.1551 + * (this.charAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1.1552 + * </pre></blockquote>
1.1553 + * is true. For other values of <code>ch</code>, it is the
1.1554 + * smallest value <i>k</i> such that:
1.1555 + * <blockquote><pre>
1.1556 + * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> >= fromIndex)
1.1557 + * </pre></blockquote>
1.1558 + * is true. In either case, if no such character occurs in this
1.1559 + * string at or after position <code>fromIndex</code>, then
1.1560 + * <code>-1</code> is returned.
1.1561 + *
1.1562 + * <p>
1.1563 + * There is no restriction on the value of <code>fromIndex</code>. If it
1.1564 + * is negative, it has the same effect as if it were zero: this entire
1.1565 + * string may be searched. If it is greater than the length of this
1.1566 + * string, it has the same effect as if it were equal to the length of
1.1567 + * this string: <code>-1</code> is returned.
1.1568 + *
1.1569 + * <p>All indices are specified in <code>char</code> values
1.1570 + * (Unicode code units).
1.1571 + *
1.1572 + * @param ch a character (Unicode code point).
1.1573 + * @param fromIndex the index to start the search from.
1.1574 + * @return the index of the first occurrence of the character in the
1.1575 + * character sequence represented by this object that is greater
1.1576 + * than or equal to <code>fromIndex</code>, or <code>-1</code>
1.1577 + * if the character does not occur.
1.1578 + */
1.1579 + public int indexOf(int ch, int fromIndex) {
1.1580 + if (fromIndex < 0) {
1.1581 + fromIndex = 0;
1.1582 + } else if (fromIndex >= count) {
1.1583 + // Note: fromIndex might be near -1>>>1.
1.1584 + return -1;
1.1585 + }
1.1586 +
1.1587 + if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1.1588 + // handle most cases here (ch is a BMP code point or a
1.1589 + // negative value (invalid code point))
1.1590 + final char[] value = this.value;
1.1591 + final int offset = this.offset;
1.1592 + final int max = offset + count;
1.1593 + for (int i = offset + fromIndex; i < max ; i++) {
1.1594 + if (value[i] == ch) {
1.1595 + return i - offset;
1.1596 + }
1.1597 + }
1.1598 + return -1;
1.1599 + } else {
1.1600 + return indexOfSupplementary(ch, fromIndex);
1.1601 + }
1.1602 + }
1.1603 +
1.1604 + /**
1.1605 + * Handles (rare) calls of indexOf with a supplementary character.
1.1606 + */
1.1607 + private int indexOfSupplementary(int ch, int fromIndex) {
1.1608 + if (Character.isValidCodePoint(ch)) {
1.1609 + final char[] value = this.value;
1.1610 + final int offset = this.offset;
1.1611 + final char hi = Character.highSurrogate(ch);
1.1612 + final char lo = Character.lowSurrogate(ch);
1.1613 + final int max = offset + count - 1;
1.1614 + for (int i = offset + fromIndex; i < max; i++) {
1.1615 + if (value[i] == hi && value[i+1] == lo) {
1.1616 + return i - offset;
1.1617 + }
1.1618 + }
1.1619 + }
1.1620 + return -1;
1.1621 + }
1.1622 +
1.1623 + /**
1.1624 + * Returns the index within this string of the last occurrence of
1.1625 + * the specified character. For values of <code>ch</code> in the
1.1626 + * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1.1627 + * units) returned is the largest value <i>k</i> such that:
1.1628 + * <blockquote><pre>
1.1629 + * this.charAt(<i>k</i>) == ch
1.1630 + * </pre></blockquote>
1.1631 + * is true. For other values of <code>ch</code>, it is the
1.1632 + * largest value <i>k</i> such that:
1.1633 + * <blockquote><pre>
1.1634 + * this.codePointAt(<i>k</i>) == ch
1.1635 + * </pre></blockquote>
1.1636 + * is true. In either case, if no such character occurs in this
1.1637 + * string, then <code>-1</code> is returned. The
1.1638 + * <code>String</code> is searched backwards starting at the last
1.1639 + * character.
1.1640 + *
1.1641 + * @param ch a character (Unicode code point).
1.1642 + * @return the index of the last occurrence of the character in the
1.1643 + * character sequence represented by this object, or
1.1644 + * <code>-1</code> if the character does not occur.
1.1645 + */
1.1646 + public int lastIndexOf(int ch) {
1.1647 + return lastIndexOf(ch, count - 1);
1.1648 + }
1.1649 +
1.1650 + /**
1.1651 + * Returns the index within this string of the last occurrence of
1.1652 + * the specified character, searching backward starting at the
1.1653 + * specified index. For values of <code>ch</code> in the range
1.1654 + * from 0 to 0xFFFF (inclusive), the index returned is the largest
1.1655 + * value <i>k</i> such that:
1.1656 + * <blockquote><pre>
1.1657 + * (this.charAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1.1658 + * </pre></blockquote>
1.1659 + * is true. For other values of <code>ch</code>, it is the
1.1660 + * largest value <i>k</i> such that:
1.1661 + * <blockquote><pre>
1.1662 + * (this.codePointAt(<i>k</i>) == ch) && (<i>k</i> <= fromIndex)
1.1663 + * </pre></blockquote>
1.1664 + * is true. In either case, if no such character occurs in this
1.1665 + * string at or before position <code>fromIndex</code>, then
1.1666 + * <code>-1</code> is returned.
1.1667 + *
1.1668 + * <p>All indices are specified in <code>char</code> values
1.1669 + * (Unicode code units).
1.1670 + *
1.1671 + * @param ch a character (Unicode code point).
1.1672 + * @param fromIndex the index to start the search from. There is no
1.1673 + * restriction on the value of <code>fromIndex</code>. If it is
1.1674 + * greater than or equal to the length of this string, it has
1.1675 + * the same effect as if it were equal to one less than the
1.1676 + * length of this string: this entire string may be searched.
1.1677 + * If it is negative, it has the same effect as if it were -1:
1.1678 + * -1 is returned.
1.1679 + * @return the index of the last occurrence of the character in the
1.1680 + * character sequence represented by this object that is less
1.1681 + * than or equal to <code>fromIndex</code>, or <code>-1</code>
1.1682 + * if the character does not occur before that point.
1.1683 + */
1.1684 + public int lastIndexOf(int ch, int fromIndex) {
1.1685 + if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1.1686 + // handle most cases here (ch is a BMP code point or a
1.1687 + // negative value (invalid code point))
1.1688 + final char[] value = this.value;
1.1689 + final int offset = this.offset;
1.1690 + int i = offset + Math.min(fromIndex, count - 1);
1.1691 + for (; i >= offset ; i--) {
1.1692 + if (value[i] == ch) {
1.1693 + return i - offset;
1.1694 + }
1.1695 + }
1.1696 + return -1;
1.1697 + } else {
1.1698 + return lastIndexOfSupplementary(ch, fromIndex);
1.1699 + }
1.1700 + }
1.1701 +
1.1702 + /**
1.1703 + * Handles (rare) calls of lastIndexOf with a supplementary character.
1.1704 + */
1.1705 + private int lastIndexOfSupplementary(int ch, int fromIndex) {
1.1706 + if (Character.isValidCodePoint(ch)) {
1.1707 + final char[] value = this.value;
1.1708 + final int offset = this.offset;
1.1709 + char hi = Character.highSurrogate(ch);
1.1710 + char lo = Character.lowSurrogate(ch);
1.1711 + int i = offset + Math.min(fromIndex, count - 2);
1.1712 + for (; i >= offset; i--) {
1.1713 + if (value[i] == hi && value[i+1] == lo) {
1.1714 + return i - offset;
1.1715 + }
1.1716 + }
1.1717 + }
1.1718 + return -1;
1.1719 + }
1.1720 +
1.1721 + /**
1.1722 + * Returns the index within this string of the first occurrence of the
1.1723 + * specified substring.
1.1724 + *
1.1725 + * <p>The returned index is the smallest value <i>k</i> for which:
1.1726 + * <blockquote><pre>
1.1727 + * this.startsWith(str, <i>k</i>)
1.1728 + * </pre></blockquote>
1.1729 + * If no such value of <i>k</i> exists, then {@code -1} is returned.
1.1730 + *
1.1731 + * @param str the substring to search for.
1.1732 + * @return the index of the first occurrence of the specified substring,
1.1733 + * or {@code -1} if there is no such occurrence.
1.1734 + */
1.1735 + public int indexOf(String str) {
1.1736 + return indexOf(str, 0);
1.1737 + }
1.1738 +
1.1739 + /**
1.1740 + * Returns the index within this string of the first occurrence of the
1.1741 + * specified substring, starting at the specified index.
1.1742 + *
1.1743 + * <p>The returned index is the smallest value <i>k</i> for which:
1.1744 + * <blockquote><pre>
1.1745 + * <i>k</i> >= fromIndex && this.startsWith(str, <i>k</i>)
1.1746 + * </pre></blockquote>
1.1747 + * If no such value of <i>k</i> exists, then {@code -1} is returned.
1.1748 + *
1.1749 + * @param str the substring to search for.
1.1750 + * @param fromIndex the index from which to start the search.
1.1751 + * @return the index of the first occurrence of the specified substring,
1.1752 + * starting at the specified index,
1.1753 + * or {@code -1} if there is no such occurrence.
1.1754 + */
1.1755 + public int indexOf(String str, int fromIndex) {
1.1756 + return indexOf(value, offset, count,
1.1757 + str.value, str.offset, str.count, fromIndex);
1.1758 + }
1.1759 +
1.1760 + /**
1.1761 + * Code shared by String and StringBuffer to do searches. The
1.1762 + * source is the character array being searched, and the target
1.1763 + * is the string being searched for.
1.1764 + *
1.1765 + * @param source the characters being searched.
1.1766 + * @param sourceOffset offset of the source string.
1.1767 + * @param sourceCount count of the source string.
1.1768 + * @param target the characters being searched for.
1.1769 + * @param targetOffset offset of the target string.
1.1770 + * @param targetCount count of the target string.
1.1771 + * @param fromIndex the index to begin searching from.
1.1772 + */
1.1773 + static int indexOf(char[] source, int sourceOffset, int sourceCount,
1.1774 + char[] target, int targetOffset, int targetCount,
1.1775 + int fromIndex) {
1.1776 + if (fromIndex >= sourceCount) {
1.1777 + return (targetCount == 0 ? sourceCount : -1);
1.1778 + }
1.1779 + if (fromIndex < 0) {
1.1780 + fromIndex = 0;
1.1781 + }
1.1782 + if (targetCount == 0) {
1.1783 + return fromIndex;
1.1784 + }
1.1785 +
1.1786 + char first = target[targetOffset];
1.1787 + int max = sourceOffset + (sourceCount - targetCount);
1.1788 +
1.1789 + for (int i = sourceOffset + fromIndex; i <= max; i++) {
1.1790 + /* Look for first character. */
1.1791 + if (source[i] != first) {
1.1792 + while (++i <= max && source[i] != first);
1.1793 + }
1.1794 +
1.1795 + /* Found first character, now look at the rest of v2 */
1.1796 + if (i <= max) {
1.1797 + int j = i + 1;
1.1798 + int end = j + targetCount - 1;
1.1799 + for (int k = targetOffset + 1; j < end && source[j] ==
1.1800 + target[k]; j++, k++);
1.1801 +
1.1802 + if (j == end) {
1.1803 + /* Found whole string. */
1.1804 + return i - sourceOffset;
1.1805 + }
1.1806 + }
1.1807 + }
1.1808 + return -1;
1.1809 + }
1.1810 +
1.1811 + /**
1.1812 + * Returns the index within this string of the last occurrence of the
1.1813 + * specified substring. The last occurrence of the empty string ""
1.1814 + * is considered to occur at the index value {@code this.length()}.
1.1815 + *
1.1816 + * <p>The returned index is the largest value <i>k</i> for which:
1.1817 + * <blockquote><pre>
1.1818 + * this.startsWith(str, <i>k</i>)
1.1819 + * </pre></blockquote>
1.1820 + * If no such value of <i>k</i> exists, then {@code -1} is returned.
1.1821 + *
1.1822 + * @param str the substring to search for.
1.1823 + * @return the index of the last occurrence of the specified substring,
1.1824 + * or {@code -1} if there is no such occurrence.
1.1825 + */
1.1826 + public int lastIndexOf(String str) {
1.1827 + return lastIndexOf(str, count);
1.1828 + }
1.1829 +
1.1830 + /**
1.1831 + * Returns the index within this string of the last occurrence of the
1.1832 + * specified substring, searching backward starting at the specified index.
1.1833 + *
1.1834 + * <p>The returned index is the largest value <i>k</i> for which:
1.1835 + * <blockquote><pre>
1.1836 + * <i>k</i> <= fromIndex && this.startsWith(str, <i>k</i>)
1.1837 + * </pre></blockquote>
1.1838 + * If no such value of <i>k</i> exists, then {@code -1} is returned.
1.1839 + *
1.1840 + * @param str the substring to search for.
1.1841 + * @param fromIndex the index to start the search from.
1.1842 + * @return the index of the last occurrence of the specified substring,
1.1843 + * searching backward from the specified index,
1.1844 + * or {@code -1} if there is no such occurrence.
1.1845 + */
1.1846 + public int lastIndexOf(String str, int fromIndex) {
1.1847 + return lastIndexOf(value, offset, count,
1.1848 + str.value, str.offset, str.count, fromIndex);
1.1849 + }
1.1850 +
1.1851 + /**
1.1852 + * Code shared by String and StringBuffer to do searches. The
1.1853 + * source is the character array being searched, and the target
1.1854 + * is the string being searched for.
1.1855 + *
1.1856 + * @param source the characters being searched.
1.1857 + * @param sourceOffset offset of the source string.
1.1858 + * @param sourceCount count of the source string.
1.1859 + * @param target the characters being searched for.
1.1860 + * @param targetOffset offset of the target string.
1.1861 + * @param targetCount count of the target string.
1.1862 + * @param fromIndex the index to begin searching from.
1.1863 + */
1.1864 + static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
1.1865 + char[] target, int targetOffset, int targetCount,
1.1866 + int fromIndex) {
1.1867 + /*
1.1868 + * Check arguments; return immediately where possible. For
1.1869 + * consistency, don't check for null str.
1.1870 + */
1.1871 + int rightIndex = sourceCount - targetCount;
1.1872 + if (fromIndex < 0) {
1.1873 + return -1;
1.1874 + }
1.1875 + if (fromIndex > rightIndex) {
1.1876 + fromIndex = rightIndex;
1.1877 + }
1.1878 + /* Empty string always matches. */
1.1879 + if (targetCount == 0) {
1.1880 + return fromIndex;
1.1881 + }
1.1882 +
1.1883 + int strLastIndex = targetOffset + targetCount - 1;
1.1884 + char strLastChar = target[strLastIndex];
1.1885 + int min = sourceOffset + targetCount - 1;
1.1886 + int i = min + fromIndex;
1.1887 +
1.1888 + startSearchForLastChar:
1.1889 + while (true) {
1.1890 + while (i >= min && source[i] != strLastChar) {
1.1891 + i--;
1.1892 + }
1.1893 + if (i < min) {
1.1894 + return -1;
1.1895 + }
1.1896 + int j = i - 1;
1.1897 + int start = j - (targetCount - 1);
1.1898 + int k = strLastIndex - 1;
1.1899 +
1.1900 + while (j > start) {
1.1901 + if (source[j--] != target[k--]) {
1.1902 + i--;
1.1903 + continue startSearchForLastChar;
1.1904 + }
1.1905 + }
1.1906 + return start - sourceOffset + 1;
1.1907 + }
1.1908 + }
1.1909 +
1.1910 + /**
1.1911 + * Returns a new string that is a substring of this string. The
1.1912 + * substring begins with the character at the specified index and
1.1913 + * extends to the end of this string. <p>
1.1914 + * Examples:
1.1915 + * <blockquote><pre>
1.1916 + * "unhappy".substring(2) returns "happy"
1.1917 + * "Harbison".substring(3) returns "bison"
1.1918 + * "emptiness".substring(9) returns "" (an empty string)
1.1919 + * </pre></blockquote>
1.1920 + *
1.1921 + * @param beginIndex the beginning index, inclusive.
1.1922 + * @return the specified substring.
1.1923 + * @exception IndexOutOfBoundsException if
1.1924 + * <code>beginIndex</code> is negative or larger than the
1.1925 + * length of this <code>String</code> object.
1.1926 + */
1.1927 + public String substring(int beginIndex) {
1.1928 + return substring(beginIndex, count);
1.1929 + }
1.1930 +
1.1931 + /**
1.1932 + * Returns a new string that is a substring of this string. The
1.1933 + * substring begins at the specified <code>beginIndex</code> and
1.1934 + * extends to the character at index <code>endIndex - 1</code>.
1.1935 + * Thus the length of the substring is <code>endIndex-beginIndex</code>.
1.1936 + * <p>
1.1937 + * Examples:
1.1938 + * <blockquote><pre>
1.1939 + * "hamburger".substring(4, 8) returns "urge"
1.1940 + * "smiles".substring(1, 5) returns "mile"
1.1941 + * </pre></blockquote>
1.1942 + *
1.1943 + * @param beginIndex the beginning index, inclusive.
1.1944 + * @param endIndex the ending index, exclusive.
1.1945 + * @return the specified substring.
1.1946 + * @exception IndexOutOfBoundsException if the
1.1947 + * <code>beginIndex</code> is negative, or
1.1948 + * <code>endIndex</code> is larger than the length of
1.1949 + * this <code>String</code> object, or
1.1950 + * <code>beginIndex</code> is larger than
1.1951 + * <code>endIndex</code>.
1.1952 + */
1.1953 + public String substring(int beginIndex, int endIndex) {
1.1954 + if (beginIndex < 0) {
1.1955 + throw new StringIndexOutOfBoundsException(beginIndex);
1.1956 + }
1.1957 + if (endIndex > count) {
1.1958 + throw new StringIndexOutOfBoundsException(endIndex);
1.1959 + }
1.1960 + if (beginIndex > endIndex) {
1.1961 + throw new StringIndexOutOfBoundsException(endIndex - beginIndex);
1.1962 + }
1.1963 + return ((beginIndex == 0) && (endIndex == count)) ? this :
1.1964 + new String(offset + beginIndex, endIndex - beginIndex, value);
1.1965 + }
1.1966 +
1.1967 + /**
1.1968 + * Returns a new character sequence that is a subsequence of this sequence.
1.1969 + *
1.1970 + * <p> An invocation of this method of the form
1.1971 + *
1.1972 + * <blockquote><pre>
1.1973 + * str.subSequence(begin, end)</pre></blockquote>
1.1974 + *
1.1975 + * behaves in exactly the same way as the invocation
1.1976 + *
1.1977 + * <blockquote><pre>
1.1978 + * str.substring(begin, end)</pre></blockquote>
1.1979 + *
1.1980 + * This method is defined so that the <tt>String</tt> class can implement
1.1981 + * the {@link CharSequence} interface. </p>
1.1982 + *
1.1983 + * @param beginIndex the begin index, inclusive.
1.1984 + * @param endIndex the end index, exclusive.
1.1985 + * @return the specified subsequence.
1.1986 + *
1.1987 + * @throws IndexOutOfBoundsException
1.1988 + * if <tt>beginIndex</tt> or <tt>endIndex</tt> are negative,
1.1989 + * if <tt>endIndex</tt> is greater than <tt>length()</tt>,
1.1990 + * or if <tt>beginIndex</tt> is greater than <tt>startIndex</tt>
1.1991 + *
1.1992 + * @since 1.4
1.1993 + * @spec JSR-51
1.1994 + */
1.1995 + public CharSequence subSequence(int beginIndex, int endIndex) {
1.1996 + return this.substring(beginIndex, endIndex);
1.1997 + }
1.1998 +
1.1999 + /**
1.2000 + * Concatenates the specified string to the end of this string.
1.2001 + * <p>
1.2002 + * If the length of the argument string is <code>0</code>, then this
1.2003 + * <code>String</code> object is returned. Otherwise, a new
1.2004 + * <code>String</code> object is created, representing a character
1.2005 + * sequence that is the concatenation of the character sequence
1.2006 + * represented by this <code>String</code> object and the character
1.2007 + * sequence represented by the argument string.<p>
1.2008 + * Examples:
1.2009 + * <blockquote><pre>
1.2010 + * "cares".concat("s") returns "caress"
1.2011 + * "to".concat("get").concat("her") returns "together"
1.2012 + * </pre></blockquote>
1.2013 + *
1.2014 + * @param str the <code>String</code> that is concatenated to the end
1.2015 + * of this <code>String</code>.
1.2016 + * @return a string that represents the concatenation of this object's
1.2017 + * characters followed by the string argument's characters.
1.2018 + */
1.2019 + public String concat(String str) {
1.2020 + int otherLen = str.length();
1.2021 + if (otherLen == 0) {
1.2022 + return this;
1.2023 + }
1.2024 + char buf[] = new char[count + otherLen];
1.2025 + getChars(0, count, buf, 0);
1.2026 + str.getChars(0, otherLen, buf, count);
1.2027 + return new String(0, count + otherLen, buf);
1.2028 + }
1.2029 +
1.2030 + /**
1.2031 + * Returns a new string resulting from replacing all occurrences of
1.2032 + * <code>oldChar</code> in this string with <code>newChar</code>.
1.2033 + * <p>
1.2034 + * If the character <code>oldChar</code> does not occur in the
1.2035 + * character sequence represented by this <code>String</code> object,
1.2036 + * then a reference to this <code>String</code> object is returned.
1.2037 + * Otherwise, a new <code>String</code> object is created that
1.2038 + * represents a character sequence identical to the character sequence
1.2039 + * represented by this <code>String</code> object, except that every
1.2040 + * occurrence of <code>oldChar</code> is replaced by an occurrence
1.2041 + * of <code>newChar</code>.
1.2042 + * <p>
1.2043 + * Examples:
1.2044 + * <blockquote><pre>
1.2045 + * "mesquite in your cellar".replace('e', 'o')
1.2046 + * returns "mosquito in your collar"
1.2047 + * "the war of baronets".replace('r', 'y')
1.2048 + * returns "the way of bayonets"
1.2049 + * "sparring with a purple porpoise".replace('p', 't')
1.2050 + * returns "starring with a turtle tortoise"
1.2051 + * "JonL".replace('q', 'x') returns "JonL" (no change)
1.2052 + * </pre></blockquote>
1.2053 + *
1.2054 + * @param oldChar the old character.
1.2055 + * @param newChar the new character.
1.2056 + * @return a string derived from this string by replacing every
1.2057 + * occurrence of <code>oldChar</code> with <code>newChar</code>.
1.2058 + */
1.2059 + public String replace(char oldChar, char newChar) {
1.2060 + if (oldChar != newChar) {
1.2061 + int len = count;
1.2062 + int i = -1;
1.2063 + char[] val = value; /* avoid getfield opcode */
1.2064 + int off = offset; /* avoid getfield opcode */
1.2065 +
1.2066 + while (++i < len) {
1.2067 + if (val[off + i] == oldChar) {
1.2068 + break;
1.2069 + }
1.2070 + }
1.2071 + if (i < len) {
1.2072 + char buf[] = new char[len];
1.2073 + for (int j = 0 ; j < i ; j++) {
1.2074 + buf[j] = val[off+j];
1.2075 + }
1.2076 + while (i < len) {
1.2077 + char c = val[off + i];
1.2078 + buf[i] = (c == oldChar) ? newChar : c;
1.2079 + i++;
1.2080 + }
1.2081 + return new String(0, len, buf);
1.2082 + }
1.2083 + }
1.2084 + return this;
1.2085 + }
1.2086 +
1.2087 + /**
1.2088 + * Tells whether or not this string matches the given <a
1.2089 + * href="../util/regex/Pattern.html#sum">regular expression</a>.
1.2090 + *
1.2091 + * <p> An invocation of this method of the form
1.2092 + * <i>str</i><tt>.matches(</tt><i>regex</i><tt>)</tt> yields exactly the
1.2093 + * same result as the expression
1.2094 + *
1.2095 + * <blockquote><tt> {@link java.util.regex.Pattern}.{@link
1.2096 + * java.util.regex.Pattern#matches(String,CharSequence)
1.2097 + * matches}(</tt><i>regex</i><tt>,</tt> <i>str</i><tt>)</tt></blockquote>
1.2098 + *
1.2099 + * @param regex
1.2100 + * the regular expression to which this string is to be matched
1.2101 + *
1.2102 + * @return <tt>true</tt> if, and only if, this string matches the
1.2103 + * given regular expression
1.2104 + *
1.2105 + * @throws PatternSyntaxException
1.2106 + * if the regular expression's syntax is invalid
1.2107 + *
1.2108 + * @see java.util.regex.Pattern
1.2109 + *
1.2110 + * @since 1.4
1.2111 + * @spec JSR-51
1.2112 + */
1.2113 + public boolean matches(String regex) {
1.2114 + return Pattern.matches(regex, this);
1.2115 + }
1.2116 +
1.2117 + /**
1.2118 + * Returns true if and only if this string contains the specified
1.2119 + * sequence of char values.
1.2120 + *
1.2121 + * @param s the sequence to search for
1.2122 + * @return true if this string contains <code>s</code>, false otherwise
1.2123 + * @throws NullPointerException if <code>s</code> is <code>null</code>
1.2124 + * @since 1.5
1.2125 + */
1.2126 + public boolean contains(CharSequence s) {
1.2127 + return indexOf(s.toString()) > -1;
1.2128 + }
1.2129 +
1.2130 + /**
1.2131 + * Replaces the first substring of this string that matches the given <a
1.2132 + * href="../util/regex/Pattern.html#sum">regular expression</a> with the
1.2133 + * given replacement.
1.2134 + *
1.2135 + * <p> An invocation of this method of the form
1.2136 + * <i>str</i><tt>.replaceFirst(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
1.2137 + * yields exactly the same result as the expression
1.2138 + *
1.2139 + * <blockquote><tt>
1.2140 + * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
1.2141 + * compile}(</tt><i>regex</i><tt>).{@link
1.2142 + * java.util.regex.Pattern#matcher(java.lang.CharSequence)
1.2143 + * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceFirst
1.2144 + * replaceFirst}(</tt><i>repl</i><tt>)</tt></blockquote>
1.2145 + *
1.2146 + *<p>
1.2147 + * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
1.2148 + * replacement string may cause the results to be different than if it were
1.2149 + * being treated as a literal replacement string; see
1.2150 + * {@link java.util.regex.Matcher#replaceFirst}.
1.2151 + * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
1.2152 + * meaning of these characters, if desired.
1.2153 + *
1.2154 + * @param regex
1.2155 + * the regular expression to which this string is to be matched
1.2156 + * @param replacement
1.2157 + * the string to be substituted for the first match
1.2158 + *
1.2159 + * @return The resulting <tt>String</tt>
1.2160 + *
1.2161 + * @throws PatternSyntaxException
1.2162 + * if the regular expression's syntax is invalid
1.2163 + *
1.2164 + * @see java.util.regex.Pattern
1.2165 + *
1.2166 + * @since 1.4
1.2167 + * @spec JSR-51
1.2168 + */
1.2169 + public String replaceFirst(String regex, String replacement) {
1.2170 + return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
1.2171 + }
1.2172 +
1.2173 + /**
1.2174 + * Replaces each substring of this string that matches the given <a
1.2175 + * href="../util/regex/Pattern.html#sum">regular expression</a> with the
1.2176 + * given replacement.
1.2177 + *
1.2178 + * <p> An invocation of this method of the form
1.2179 + * <i>str</i><tt>.replaceAll(</tt><i>regex</i><tt>,</tt> <i>repl</i><tt>)</tt>
1.2180 + * yields exactly the same result as the expression
1.2181 + *
1.2182 + * <blockquote><tt>
1.2183 + * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
1.2184 + * compile}(</tt><i>regex</i><tt>).{@link
1.2185 + * java.util.regex.Pattern#matcher(java.lang.CharSequence)
1.2186 + * matcher}(</tt><i>str</i><tt>).{@link java.util.regex.Matcher#replaceAll
1.2187 + * replaceAll}(</tt><i>repl</i><tt>)</tt></blockquote>
1.2188 + *
1.2189 + *<p>
1.2190 + * Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in the
1.2191 + * replacement string may cause the results to be different than if it were
1.2192 + * being treated as a literal replacement string; see
1.2193 + * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
1.2194 + * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
1.2195 + * meaning of these characters, if desired.
1.2196 + *
1.2197 + * @param regex
1.2198 + * the regular expression to which this string is to be matched
1.2199 + * @param replacement
1.2200 + * the string to be substituted for each match
1.2201 + *
1.2202 + * @return The resulting <tt>String</tt>
1.2203 + *
1.2204 + * @throws PatternSyntaxException
1.2205 + * if the regular expression's syntax is invalid
1.2206 + *
1.2207 + * @see java.util.regex.Pattern
1.2208 + *
1.2209 + * @since 1.4
1.2210 + * @spec JSR-51
1.2211 + */
1.2212 + public String replaceAll(String regex, String replacement) {
1.2213 + return Pattern.compile(regex).matcher(this).replaceAll(replacement);
1.2214 + }
1.2215 +
1.2216 + /**
1.2217 + * Replaces each substring of this string that matches the literal target
1.2218 + * sequence with the specified literal replacement sequence. The
1.2219 + * replacement proceeds from the beginning of the string to the end, for
1.2220 + * example, replacing "aa" with "b" in the string "aaa" will result in
1.2221 + * "ba" rather than "ab".
1.2222 + *
1.2223 + * @param target The sequence of char values to be replaced
1.2224 + * @param replacement The replacement sequence of char values
1.2225 + * @return The resulting string
1.2226 + * @throws NullPointerException if <code>target</code> or
1.2227 + * <code>replacement</code> is <code>null</code>.
1.2228 + * @since 1.5
1.2229 + */
1.2230 + public String replace(CharSequence target, CharSequence replacement) {
1.2231 + return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
1.2232 + this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
1.2233 + }
1.2234 +
1.2235 + /**
1.2236 + * Splits this string around matches of the given
1.2237 + * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
1.2238 + *
1.2239 + * <p> The array returned by this method contains each substring of this
1.2240 + * string that is terminated by another substring that matches the given
1.2241 + * expression or is terminated by the end of the string. The substrings in
1.2242 + * the array are in the order in which they occur in this string. If the
1.2243 + * expression does not match any part of the input then the resulting array
1.2244 + * has just one element, namely this string.
1.2245 + *
1.2246 + * <p> The <tt>limit</tt> parameter controls the number of times the
1.2247 + * pattern is applied and therefore affects the length of the resulting
1.2248 + * array. If the limit <i>n</i> is greater than zero then the pattern
1.2249 + * will be applied at most <i>n</i> - 1 times, the array's
1.2250 + * length will be no greater than <i>n</i>, and the array's last entry
1.2251 + * will contain all input beyond the last matched delimiter. If <i>n</i>
1.2252 + * is non-positive then the pattern will be applied as many times as
1.2253 + * possible and the array can have any length. If <i>n</i> is zero then
1.2254 + * the pattern will be applied as many times as possible, the array can
1.2255 + * have any length, and trailing empty strings will be discarded.
1.2256 + *
1.2257 + * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the
1.2258 + * following results with these parameters:
1.2259 + *
1.2260 + * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
1.2261 + * <tr>
1.2262 + * <th>Regex</th>
1.2263 + * <th>Limit</th>
1.2264 + * <th>Result</th>
1.2265 + * </tr>
1.2266 + * <tr><td align=center>:</td>
1.2267 + * <td align=center>2</td>
1.2268 + * <td><tt>{ "boo", "and:foo" }</tt></td></tr>
1.2269 + * <tr><td align=center>:</td>
1.2270 + * <td align=center>5</td>
1.2271 + * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
1.2272 + * <tr><td align=center>:</td>
1.2273 + * <td align=center>-2</td>
1.2274 + * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
1.2275 + * <tr><td align=center>o</td>
1.2276 + * <td align=center>5</td>
1.2277 + * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
1.2278 + * <tr><td align=center>o</td>
1.2279 + * <td align=center>-2</td>
1.2280 + * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr>
1.2281 + * <tr><td align=center>o</td>
1.2282 + * <td align=center>0</td>
1.2283 + * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
1.2284 + * </table></blockquote>
1.2285 + *
1.2286 + * <p> An invocation of this method of the form
1.2287 + * <i>str.</i><tt>split(</tt><i>regex</i><tt>,</tt> <i>n</i><tt>)</tt>
1.2288 + * yields the same result as the expression
1.2289 + *
1.2290 + * <blockquote>
1.2291 + * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#compile
1.2292 + * compile}<tt>(</tt><i>regex</i><tt>)</tt>.{@link
1.2293 + * java.util.regex.Pattern#split(java.lang.CharSequence,int)
1.2294 + * split}<tt>(</tt><i>str</i><tt>,</tt> <i>n</i><tt>)</tt>
1.2295 + * </blockquote>
1.2296 + *
1.2297 + *
1.2298 + * @param regex
1.2299 + * the delimiting regular expression
1.2300 + *
1.2301 + * @param limit
1.2302 + * the result threshold, as described above
1.2303 + *
1.2304 + * @return the array of strings computed by splitting this string
1.2305 + * around matches of the given regular expression
1.2306 + *
1.2307 + * @throws PatternSyntaxException
1.2308 + * if the regular expression's syntax is invalid
1.2309 + *
1.2310 + * @see java.util.regex.Pattern
1.2311 + *
1.2312 + * @since 1.4
1.2313 + * @spec JSR-51
1.2314 + */
1.2315 + public String[] split(String regex, int limit) {
1.2316 + /* fastpath if the regex is a
1.2317 + (1)one-char String and this character is not one of the
1.2318 + RegEx's meta characters ".$|()[{^?*+\\", or
1.2319 + (2)two-char String and the first char is the backslash and
1.2320 + the second is not the ascii digit or ascii letter.
1.2321 + */
1.2322 + char ch = 0;
1.2323 + if (((regex.count == 1 &&
1.2324 + ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
1.2325 + (regex.length() == 2 &&
1.2326 + regex.charAt(0) == '\\' &&
1.2327 + (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
1.2328 + ((ch-'a')|('z'-ch)) < 0 &&
1.2329 + ((ch-'A')|('Z'-ch)) < 0)) &&
1.2330 + (ch < Character.MIN_HIGH_SURROGATE ||
1.2331 + ch > Character.MAX_LOW_SURROGATE))
1.2332 + {
1.2333 + int off = 0;
1.2334 + int next = 0;
1.2335 + boolean limited = limit > 0;
1.2336 + ArrayList<String> list = new ArrayList<>();
1.2337 + while ((next = indexOf(ch, off)) != -1) {
1.2338 + if (!limited || list.size() < limit - 1) {
1.2339 + list.add(substring(off, next));
1.2340 + off = next + 1;
1.2341 + } else { // last one
1.2342 + //assert (list.size() == limit - 1);
1.2343 + list.add(substring(off, count));
1.2344 + off = count;
1.2345 + break;
1.2346 + }
1.2347 + }
1.2348 + // If no match was found, return this
1.2349 + if (off == 0)
1.2350 + return new String[] { this };
1.2351 +
1.2352 + // Add remaining segment
1.2353 + if (!limited || list.size() < limit)
1.2354 + list.add(substring(off, count));
1.2355 +
1.2356 + // Construct result
1.2357 + int resultSize = list.size();
1.2358 + if (limit == 0)
1.2359 + while (resultSize > 0 && list.get(resultSize-1).length() == 0)
1.2360 + resultSize--;
1.2361 + String[] result = new String[resultSize];
1.2362 + return list.subList(0, resultSize).toArray(result);
1.2363 + }
1.2364 + return Pattern.compile(regex).split(this, limit);
1.2365 + }
1.2366 +
1.2367 + /**
1.2368 + * Splits this string around matches of the given <a
1.2369 + * href="../util/regex/Pattern.html#sum">regular expression</a>.
1.2370 + *
1.2371 + * <p> This method works as if by invoking the two-argument {@link
1.2372 + * #split(String, int) split} method with the given expression and a limit
1.2373 + * argument of zero. Trailing empty strings are therefore not included in
1.2374 + * the resulting array.
1.2375 + *
1.2376 + * <p> The string <tt>"boo:and:foo"</tt>, for example, yields the following
1.2377 + * results with these expressions:
1.2378 + *
1.2379 + * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
1.2380 + * <tr>
1.2381 + * <th>Regex</th>
1.2382 + * <th>Result</th>
1.2383 + * </tr>
1.2384 + * <tr><td align=center>:</td>
1.2385 + * <td><tt>{ "boo", "and", "foo" }</tt></td></tr>
1.2386 + * <tr><td align=center>o</td>
1.2387 + * <td><tt>{ "b", "", ":and:f" }</tt></td></tr>
1.2388 + * </table></blockquote>
1.2389 + *
1.2390 + *
1.2391 + * @param regex
1.2392 + * the delimiting regular expression
1.2393 + *
1.2394 + * @return the array of strings computed by splitting this string
1.2395 + * around matches of the given regular expression
1.2396 + *
1.2397 + * @throws PatternSyntaxException
1.2398 + * if the regular expression's syntax is invalid
1.2399 + *
1.2400 + * @see java.util.regex.Pattern
1.2401 + *
1.2402 + * @since 1.4
1.2403 + * @spec JSR-51
1.2404 + */
1.2405 + public String[] split(String regex) {
1.2406 + return split(regex, 0);
1.2407 + }
1.2408 +
1.2409 + /**
1.2410 + * Converts all of the characters in this <code>String</code> to lower
1.2411 + * case using the rules of the given <code>Locale</code>. Case mapping is based
1.2412 + * on the Unicode Standard version specified by the {@link java.lang.Character Character}
1.2413 + * class. Since case mappings are not always 1:1 char mappings, the resulting
1.2414 + * <code>String</code> may be a different length than the original <code>String</code>.
1.2415 + * <p>
1.2416 + * Examples of lowercase mappings are in the following table:
1.2417 + * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
1.2418 + * <tr>
1.2419 + * <th>Language Code of Locale</th>
1.2420 + * <th>Upper Case</th>
1.2421 + * <th>Lower Case</th>
1.2422 + * <th>Description</th>
1.2423 + * </tr>
1.2424 + * <tr>
1.2425 + * <td>tr (Turkish)</td>
1.2426 + * <td>\u0130</td>
1.2427 + * <td>\u0069</td>
1.2428 + * <td>capital letter I with dot above -> small letter i</td>
1.2429 + * </tr>
1.2430 + * <tr>
1.2431 + * <td>tr (Turkish)</td>
1.2432 + * <td>\u0049</td>
1.2433 + * <td>\u0131</td>
1.2434 + * <td>capital letter I -> small letter dotless i </td>
1.2435 + * </tr>
1.2436 + * <tr>
1.2437 + * <td>(all)</td>
1.2438 + * <td>French Fries</td>
1.2439 + * <td>french fries</td>
1.2440 + * <td>lowercased all chars in String</td>
1.2441 + * </tr>
1.2442 + * <tr>
1.2443 + * <td>(all)</td>
1.2444 + * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
1.2445 + * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
1.2446 + * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
1.2447 + * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
1.2448 + * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
1.2449 + * <img src="doc-files/sigma1.gif" alt="sigma"></td>
1.2450 + * <td>lowercased all chars in String</td>
1.2451 + * </tr>
1.2452 + * </table>
1.2453 + *
1.2454 + * @param locale use the case transformation rules for this locale
1.2455 + * @return the <code>String</code>, converted to lowercase.
1.2456 + * @see java.lang.String#toLowerCase()
1.2457 + * @see java.lang.String#toUpperCase()
1.2458 + * @see java.lang.String#toUpperCase(Locale)
1.2459 + * @since 1.1
1.2460 + */
1.2461 + public String toLowerCase(Locale locale) {
1.2462 + if (locale == null) {
1.2463 + throw new NullPointerException();
1.2464 + }
1.2465 +
1.2466 + int firstUpper;
1.2467 +
1.2468 + /* Now check if there are any characters that need to be changed. */
1.2469 + scan: {
1.2470 + for (firstUpper = 0 ; firstUpper < count; ) {
1.2471 + char c = value[offset+firstUpper];
1.2472 + if ((c >= Character.MIN_HIGH_SURROGATE) &&
1.2473 + (c <= Character.MAX_HIGH_SURROGATE)) {
1.2474 + int supplChar = codePointAt(firstUpper);
1.2475 + if (supplChar != Character.toLowerCase(supplChar)) {
1.2476 + break scan;
1.2477 + }
1.2478 + firstUpper += Character.charCount(supplChar);
1.2479 + } else {
1.2480 + if (c != Character.toLowerCase(c)) {
1.2481 + break scan;
1.2482 + }
1.2483 + firstUpper++;
1.2484 + }
1.2485 + }
1.2486 + return this;
1.2487 + }
1.2488 +
1.2489 + char[] result = new char[count];
1.2490 + int resultOffset = 0; /* result may grow, so i+resultOffset
1.2491 + * is the write location in result */
1.2492 +
1.2493 + /* Just copy the first few lowerCase characters. */
1.2494 + System.arraycopy(value, offset, result, 0, firstUpper);
1.2495 +
1.2496 + String lang = locale.getLanguage();
1.2497 + boolean localeDependent =
1.2498 + (lang == "tr" || lang == "az" || lang == "lt");
1.2499 + char[] lowerCharArray;
1.2500 + int lowerChar;
1.2501 + int srcChar;
1.2502 + int srcCount;
1.2503 + for (int i = firstUpper; i < count; i += srcCount) {
1.2504 + srcChar = (int)value[offset+i];
1.2505 + if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
1.2506 + (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
1.2507 + srcChar = codePointAt(i);
1.2508 + srcCount = Character.charCount(srcChar);
1.2509 + } else {
1.2510 + srcCount = 1;
1.2511 + }
1.2512 + if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
1.2513 + lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
1.2514 + } else if (srcChar == '\u0130') { // LATIN CAPITAL LETTER I DOT
1.2515 + lowerChar = Character.ERROR;
1.2516 + } else {
1.2517 + lowerChar = Character.toLowerCase(srcChar);
1.2518 + }
1.2519 + if ((lowerChar == Character.ERROR) ||
1.2520 + (lowerChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
1.2521 + if (lowerChar == Character.ERROR) {
1.2522 + if (!localeDependent && srcChar == '\u0130') {
1.2523 + lowerCharArray =
1.2524 + ConditionalSpecialCasing.toLowerCaseCharArray(this, i, Locale.ENGLISH);
1.2525 + } else {
1.2526 + lowerCharArray =
1.2527 + ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
1.2528 + }
1.2529 + } else if (srcCount == 2) {
1.2530 + resultOffset += Character.toChars(lowerChar, result, i + resultOffset) - srcCount;
1.2531 + continue;
1.2532 + } else {
1.2533 + lowerCharArray = Character.toChars(lowerChar);
1.2534 + }
1.2535 +
1.2536 + /* Grow result if needed */
1.2537 + int mapLen = lowerCharArray.length;
1.2538 + if (mapLen > srcCount) {
1.2539 + char[] result2 = new char[result.length + mapLen - srcCount];
1.2540 + System.arraycopy(result, 0, result2, 0,
1.2541 + i + resultOffset);
1.2542 + result = result2;
1.2543 + }
1.2544 + for (int x=0; x<mapLen; ++x) {
1.2545 + result[i+resultOffset+x] = lowerCharArray[x];
1.2546 + }
1.2547 + resultOffset += (mapLen - srcCount);
1.2548 + } else {
1.2549 + result[i+resultOffset] = (char)lowerChar;
1.2550 + }
1.2551 + }
1.2552 + return new String(0, count+resultOffset, result);
1.2553 + }
1.2554 +
1.2555 + /**
1.2556 + * Converts all of the characters in this <code>String</code> to lower
1.2557 + * case using the rules of the default locale. This is equivalent to calling
1.2558 + * <code>toLowerCase(Locale.getDefault())</code>.
1.2559 + * <p>
1.2560 + * <b>Note:</b> This method is locale sensitive, and may produce unexpected
1.2561 + * results if used for strings that are intended to be interpreted locale
1.2562 + * independently.
1.2563 + * Examples are programming language identifiers, protocol keys, and HTML
1.2564 + * tags.
1.2565 + * For instance, <code>"TITLE".toLowerCase()</code> in a Turkish locale
1.2566 + * returns <code>"t\u005Cu0131tle"</code>, where '\u005Cu0131' is the
1.2567 + * LATIN SMALL LETTER DOTLESS I character.
1.2568 + * To obtain correct results for locale insensitive strings, use
1.2569 + * <code>toLowerCase(Locale.ENGLISH)</code>.
1.2570 + * <p>
1.2571 + * @return the <code>String</code>, converted to lowercase.
1.2572 + * @see java.lang.String#toLowerCase(Locale)
1.2573 + */
1.2574 + public String toLowerCase() {
1.2575 + return toLowerCase(Locale.getDefault());
1.2576 + }
1.2577 +
1.2578 + /**
1.2579 + * Converts all of the characters in this <code>String</code> to upper
1.2580 + * case using the rules of the given <code>Locale</code>. Case mapping is based
1.2581 + * on the Unicode Standard version specified by the {@link java.lang.Character Character}
1.2582 + * class. Since case mappings are not always 1:1 char mappings, the resulting
1.2583 + * <code>String</code> may be a different length than the original <code>String</code>.
1.2584 + * <p>
1.2585 + * Examples of locale-sensitive and 1:M case mappings are in the following table.
1.2586 + * <p>
1.2587 + * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
1.2588 + * <tr>
1.2589 + * <th>Language Code of Locale</th>
1.2590 + * <th>Lower Case</th>
1.2591 + * <th>Upper Case</th>
1.2592 + * <th>Description</th>
1.2593 + * </tr>
1.2594 + * <tr>
1.2595 + * <td>tr (Turkish)</td>
1.2596 + * <td>\u0069</td>
1.2597 + * <td>\u0130</td>
1.2598 + * <td>small letter i -> capital letter I with dot above</td>
1.2599 + * </tr>
1.2600 + * <tr>
1.2601 + * <td>tr (Turkish)</td>
1.2602 + * <td>\u0131</td>
1.2603 + * <td>\u0049</td>
1.2604 + * <td>small letter dotless i -> capital letter I</td>
1.2605 + * </tr>
1.2606 + * <tr>
1.2607 + * <td>(all)</td>
1.2608 + * <td>\u00df</td>
1.2609 + * <td>\u0053 \u0053</td>
1.2610 + * <td>small letter sharp s -> two letters: SS</td>
1.2611 + * </tr>
1.2612 + * <tr>
1.2613 + * <td>(all)</td>
1.2614 + * <td>Fahrvergnügen</td>
1.2615 + * <td>FAHRVERGNÜGEN</td>
1.2616 + * <td></td>
1.2617 + * </tr>
1.2618 + * </table>
1.2619 + * @param locale use the case transformation rules for this locale
1.2620 + * @return the <code>String</code>, converted to uppercase.
1.2621 + * @see java.lang.String#toUpperCase()
1.2622 + * @see java.lang.String#toLowerCase()
1.2623 + * @see java.lang.String#toLowerCase(Locale)
1.2624 + * @since 1.1
1.2625 + */
1.2626 + public String toUpperCase(Locale locale) {
1.2627 + if (locale == null) {
1.2628 + throw new NullPointerException();
1.2629 + }
1.2630 +
1.2631 + int firstLower;
1.2632 +
1.2633 + /* Now check if there are any characters that need to be changed. */
1.2634 + scan: {
1.2635 + for (firstLower = 0 ; firstLower < count; ) {
1.2636 + int c = (int)value[offset+firstLower];
1.2637 + int srcCount;
1.2638 + if ((c >= Character.MIN_HIGH_SURROGATE) &&
1.2639 + (c <= Character.MAX_HIGH_SURROGATE)) {
1.2640 + c = codePointAt(firstLower);
1.2641 + srcCount = Character.charCount(c);
1.2642 + } else {
1.2643 + srcCount = 1;
1.2644 + }
1.2645 + int upperCaseChar = Character.toUpperCaseEx(c);
1.2646 + if ((upperCaseChar == Character.ERROR) ||
1.2647 + (c != upperCaseChar)) {
1.2648 + break scan;
1.2649 + }
1.2650 + firstLower += srcCount;
1.2651 + }
1.2652 + return this;
1.2653 + }
1.2654 +
1.2655 + char[] result = new char[count]; /* may grow */
1.2656 + int resultOffset = 0; /* result may grow, so i+resultOffset
1.2657 + * is the write location in result */
1.2658 +
1.2659 + /* Just copy the first few upperCase characters. */
1.2660 + System.arraycopy(value, offset, result, 0, firstLower);
1.2661 +
1.2662 + String lang = locale.getLanguage();
1.2663 + boolean localeDependent =
1.2664 + (lang == "tr" || lang == "az" || lang == "lt");
1.2665 + char[] upperCharArray;
1.2666 + int upperChar;
1.2667 + int srcChar;
1.2668 + int srcCount;
1.2669 + for (int i = firstLower; i < count; i += srcCount) {
1.2670 + srcChar = (int)value[offset+i];
1.2671 + if ((char)srcChar >= Character.MIN_HIGH_SURROGATE &&
1.2672 + (char)srcChar <= Character.MAX_HIGH_SURROGATE) {
1.2673 + srcChar = codePointAt(i);
1.2674 + srcCount = Character.charCount(srcChar);
1.2675 + } else {
1.2676 + srcCount = 1;
1.2677 + }
1.2678 + if (localeDependent) {
1.2679 + upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
1.2680 + } else {
1.2681 + upperChar = Character.toUpperCaseEx(srcChar);
1.2682 + }
1.2683 + if ((upperChar == Character.ERROR) ||
1.2684 + (upperChar >= Character.MIN_SUPPLEMENTARY_CODE_POINT)) {
1.2685 + if (upperChar == Character.ERROR) {
1.2686 + if (localeDependent) {
1.2687 + upperCharArray =
1.2688 + ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
1.2689 + } else {
1.2690 + upperCharArray = Character.toUpperCaseCharArray(srcChar);
1.2691 + }
1.2692 + } else if (srcCount == 2) {
1.2693 + resultOffset += Character.toChars(upperChar, result, i + resultOffset) - srcCount;
1.2694 + continue;
1.2695 + } else {
1.2696 + upperCharArray = Character.toChars(upperChar);
1.2697 + }
1.2698 +
1.2699 + /* Grow result if needed */
1.2700 + int mapLen = upperCharArray.length;
1.2701 + if (mapLen > srcCount) {
1.2702 + char[] result2 = new char[result.length + mapLen - srcCount];
1.2703 + System.arraycopy(result, 0, result2, 0,
1.2704 + i + resultOffset);
1.2705 + result = result2;
1.2706 + }
1.2707 + for (int x=0; x<mapLen; ++x) {
1.2708 + result[i+resultOffset+x] = upperCharArray[x];
1.2709 + }
1.2710 + resultOffset += (mapLen - srcCount);
1.2711 + } else {
1.2712 + result[i+resultOffset] = (char)upperChar;
1.2713 + }
1.2714 + }
1.2715 + return new String(0, count+resultOffset, result);
1.2716 + }
1.2717 +
1.2718 + /**
1.2719 + * Converts all of the characters in this <code>String</code> to upper
1.2720 + * case using the rules of the default locale. This method is equivalent to
1.2721 + * <code>toUpperCase(Locale.getDefault())</code>.
1.2722 + * <p>
1.2723 + * <b>Note:</b> This method is locale sensitive, and may produce unexpected
1.2724 + * results if used for strings that are intended to be interpreted locale
1.2725 + * independently.
1.2726 + * Examples are programming language identifiers, protocol keys, and HTML
1.2727 + * tags.
1.2728 + * For instance, <code>"title".toUpperCase()</code> in a Turkish locale
1.2729 + * returns <code>"T\u005Cu0130TLE"</code>, where '\u005Cu0130' is the
1.2730 + * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
1.2731 + * To obtain correct results for locale insensitive strings, use
1.2732 + * <code>toUpperCase(Locale.ENGLISH)</code>.
1.2733 + * <p>
1.2734 + * @return the <code>String</code>, converted to uppercase.
1.2735 + * @see java.lang.String#toUpperCase(Locale)
1.2736 + */
1.2737 + public String toUpperCase() {
1.2738 + return toUpperCase(Locale.getDefault());
1.2739 + }
1.2740 +
1.2741 + /**
1.2742 + * Returns a copy of the string, with leading and trailing whitespace
1.2743 + * omitted.
1.2744 + * <p>
1.2745 + * If this <code>String</code> object represents an empty character
1.2746 + * sequence, or the first and last characters of character sequence
1.2747 + * represented by this <code>String</code> object both have codes
1.2748 + * greater than <code>'\u0020'</code> (the space character), then a
1.2749 + * reference to this <code>String</code> object is returned.
1.2750 + * <p>
1.2751 + * Otherwise, if there is no character with a code greater than
1.2752 + * <code>'\u0020'</code> in the string, then a new
1.2753 + * <code>String</code> object representing an empty string is created
1.2754 + * and returned.
1.2755 + * <p>
1.2756 + * Otherwise, let <i>k</i> be the index of the first character in the
1.2757 + * string whose code is greater than <code>'\u0020'</code>, and let
1.2758 + * <i>m</i> be the index of the last character in the string whose code
1.2759 + * is greater than <code>'\u0020'</code>. A new <code>String</code>
1.2760 + * object is created, representing the substring of this string that
1.2761 + * begins with the character at index <i>k</i> and ends with the
1.2762 + * character at index <i>m</i>-that is, the result of
1.2763 + * <code>this.substring(<i>k</i>, <i>m</i>+1)</code>.
1.2764 + * <p>
1.2765 + * This method may be used to trim whitespace (as defined above) from
1.2766 + * the beginning and end of a string.
1.2767 + *
1.2768 + * @return A copy of this string with leading and trailing white
1.2769 + * space removed, or this string if it has no leading or
1.2770 + * trailing white space.
1.2771 + */
1.2772 + public String trim() {
1.2773 + int len = count;
1.2774 + int st = 0;
1.2775 + int off = offset; /* avoid getfield opcode */
1.2776 + char[] val = value; /* avoid getfield opcode */
1.2777 +
1.2778 + while ((st < len) && (val[off + st] <= ' ')) {
1.2779 + st++;
1.2780 + }
1.2781 + while ((st < len) && (val[off + len - 1] <= ' ')) {
1.2782 + len--;
1.2783 + }
1.2784 + return ((st > 0) || (len < count)) ? substring(st, len) : this;
1.2785 + }
1.2786 +
1.2787 + /**
1.2788 + * This object (which is already a string!) is itself returned.
1.2789 + *
1.2790 + * @return the string itself.
1.2791 + */
1.2792 + public String toString() {
1.2793 + return this;
1.2794 + }
1.2795 +
1.2796 + /**
1.2797 + * Converts this string to a new character array.
1.2798 + *
1.2799 + * @return a newly allocated character array whose length is the length
1.2800 + * of this string and whose contents are initialized to contain
1.2801 + * the character sequence represented by this string.
1.2802 + */
1.2803 + public char[] toCharArray() {
1.2804 + char result[] = new char[count];
1.2805 + getChars(0, count, result, 0);
1.2806 + return result;
1.2807 + }
1.2808 +
1.2809 + /**
1.2810 + * Returns a formatted string using the specified format string and
1.2811 + * arguments.
1.2812 + *
1.2813 + * <p> The locale always used is the one returned by {@link
1.2814 + * java.util.Locale#getDefault() Locale.getDefault()}.
1.2815 + *
1.2816 + * @param format
1.2817 + * A <a href="../util/Formatter.html#syntax">format string</a>
1.2818 + *
1.2819 + * @param args
1.2820 + * Arguments referenced by the format specifiers in the format
1.2821 + * string. If there are more arguments than format specifiers, the
1.2822 + * extra arguments are ignored. The number of arguments is
1.2823 + * variable and may be zero. The maximum number of arguments is
1.2824 + * limited by the maximum dimension of a Java array as defined by
1.2825 + * <cite>The Java™ Virtual Machine Specification</cite>.
1.2826 + * The behaviour on a
1.2827 + * <tt>null</tt> argument depends on the <a
1.2828 + * href="../util/Formatter.html#syntax">conversion</a>.
1.2829 + *
1.2830 + * @throws IllegalFormatException
1.2831 + * If a format string contains an illegal syntax, a format
1.2832 + * specifier that is incompatible with the given arguments,
1.2833 + * insufficient arguments given the format string, or other
1.2834 + * illegal conditions. For specification of all possible
1.2835 + * formatting errors, see the <a
1.2836 + * href="../util/Formatter.html#detail">Details</a> section of the
1.2837 + * formatter class specification.
1.2838 + *
1.2839 + * @throws NullPointerException
1.2840 + * If the <tt>format</tt> is <tt>null</tt>
1.2841 + *
1.2842 + * @return A formatted string
1.2843 + *
1.2844 + * @see java.util.Formatter
1.2845 + * @since 1.5
1.2846 + */
1.2847 + public static String format(String format, Object ... args) {
1.2848 + return new Formatter().format(format, args).toString();
1.2849 + }
1.2850 +
1.2851 + /**
1.2852 + * Returns a formatted string using the specified locale, format string,
1.2853 + * and arguments.
1.2854 + *
1.2855 + * @param l
1.2856 + * The {@linkplain java.util.Locale locale} to apply during
1.2857 + * formatting. If <tt>l</tt> is <tt>null</tt> then no localization
1.2858 + * is applied.
1.2859 + *
1.2860 + * @param format
1.2861 + * A <a href="../util/Formatter.html#syntax">format string</a>
1.2862 + *
1.2863 + * @param args
1.2864 + * Arguments referenced by the format specifiers in the format
1.2865 + * string. If there are more arguments than format specifiers, the
1.2866 + * extra arguments are ignored. The number of arguments is
1.2867 + * variable and may be zero. The maximum number of arguments is
1.2868 + * limited by the maximum dimension of a Java array as defined by
1.2869 + * <cite>The Java™ Virtual Machine Specification</cite>.
1.2870 + * The behaviour on a
1.2871 + * <tt>null</tt> argument depends on the <a
1.2872 + * href="../util/Formatter.html#syntax">conversion</a>.
1.2873 + *
1.2874 + * @throws IllegalFormatException
1.2875 + * If a format string contains an illegal syntax, a format
1.2876 + * specifier that is incompatible with the given arguments,
1.2877 + * insufficient arguments given the format string, or other
1.2878 + * illegal conditions. For specification of all possible
1.2879 + * formatting errors, see the <a
1.2880 + * href="../util/Formatter.html#detail">Details</a> section of the
1.2881 + * formatter class specification
1.2882 + *
1.2883 + * @throws NullPointerException
1.2884 + * If the <tt>format</tt> is <tt>null</tt>
1.2885 + *
1.2886 + * @return A formatted string
1.2887 + *
1.2888 + * @see java.util.Formatter
1.2889 + * @since 1.5
1.2890 + */
1.2891 + public static String format(Locale l, String format, Object ... args) {
1.2892 + return new Formatter(l).format(format, args).toString();
1.2893 + }
1.2894 +
1.2895 + /**
1.2896 + * Returns the string representation of the <code>Object</code> argument.
1.2897 + *
1.2898 + * @param obj an <code>Object</code>.
1.2899 + * @return if the argument is <code>null</code>, then a string equal to
1.2900 + * <code>"null"</code>; otherwise, the value of
1.2901 + * <code>obj.toString()</code> is returned.
1.2902 + * @see java.lang.Object#toString()
1.2903 + */
1.2904 + public static String valueOf(Object obj) {
1.2905 + return (obj == null) ? "null" : obj.toString();
1.2906 + }
1.2907 +
1.2908 + /**
1.2909 + * Returns the string representation of the <code>char</code> array
1.2910 + * argument. The contents of the character array are copied; subsequent
1.2911 + * modification of the character array does not affect the newly
1.2912 + * created string.
1.2913 + *
1.2914 + * @param data a <code>char</code> array.
1.2915 + * @return a newly allocated string representing the same sequence of
1.2916 + * characters contained in the character array argument.
1.2917 + */
1.2918 + public static String valueOf(char data[]) {
1.2919 + return new String(data);
1.2920 + }
1.2921 +
1.2922 + /**
1.2923 + * Returns the string representation of a specific subarray of the
1.2924 + * <code>char</code> array argument.
1.2925 + * <p>
1.2926 + * The <code>offset</code> argument is the index of the first
1.2927 + * character of the subarray. The <code>count</code> argument
1.2928 + * specifies the length of the subarray. The contents of the subarray
1.2929 + * are copied; subsequent modification of the character array does not
1.2930 + * affect the newly created string.
1.2931 + *
1.2932 + * @param data the character array.
1.2933 + * @param offset the initial offset into the value of the
1.2934 + * <code>String</code>.
1.2935 + * @param count the length of the value of the <code>String</code>.
1.2936 + * @return a string representing the sequence of characters contained
1.2937 + * in the subarray of the character array argument.
1.2938 + * @exception IndexOutOfBoundsException if <code>offset</code> is
1.2939 + * negative, or <code>count</code> is negative, or
1.2940 + * <code>offset+count</code> is larger than
1.2941 + * <code>data.length</code>.
1.2942 + */
1.2943 + public static String valueOf(char data[], int offset, int count) {
1.2944 + return new String(data, offset, count);
1.2945 + }
1.2946 +
1.2947 + /**
1.2948 + * Returns a String that represents the character sequence in the
1.2949 + * array specified.
1.2950 + *
1.2951 + * @param data the character array.
1.2952 + * @param offset initial offset of the subarray.
1.2953 + * @param count length of the subarray.
1.2954 + * @return a <code>String</code> that contains the characters of the
1.2955 + * specified subarray of the character array.
1.2956 + */
1.2957 + public static String copyValueOf(char data[], int offset, int count) {
1.2958 + // All public String constructors now copy the data.
1.2959 + return new String(data, offset, count);
1.2960 + }
1.2961 +
1.2962 + /**
1.2963 + * Returns a String that represents the character sequence in the
1.2964 + * array specified.
1.2965 + *
1.2966 + * @param data the character array.
1.2967 + * @return a <code>String</code> that contains the characters of the
1.2968 + * character array.
1.2969 + */
1.2970 + public static String copyValueOf(char data[]) {
1.2971 + return copyValueOf(data, 0, data.length);
1.2972 + }
1.2973 +
1.2974 + /**
1.2975 + * Returns the string representation of the <code>boolean</code> argument.
1.2976 + *
1.2977 + * @param b a <code>boolean</code>.
1.2978 + * @return if the argument is <code>true</code>, a string equal to
1.2979 + * <code>"true"</code> is returned; otherwise, a string equal to
1.2980 + * <code>"false"</code> is returned.
1.2981 + */
1.2982 + public static String valueOf(boolean b) {
1.2983 + return b ? "true" : "false";
1.2984 + }
1.2985 +
1.2986 + /**
1.2987 + * Returns the string representation of the <code>char</code>
1.2988 + * argument.
1.2989 + *
1.2990 + * @param c a <code>char</code>.
1.2991 + * @return a string of length <code>1</code> containing
1.2992 + * as its single character the argument <code>c</code>.
1.2993 + */
1.2994 + public static String valueOf(char c) {
1.2995 + char data[] = {c};
1.2996 + return new String(0, 1, data);
1.2997 + }
1.2998 +
1.2999 + /**
1.3000 + * Returns the string representation of the <code>int</code> argument.
1.3001 + * <p>
1.3002 + * The representation is exactly the one returned by the
1.3003 + * <code>Integer.toString</code> method of one argument.
1.3004 + *
1.3005 + * @param i an <code>int</code>.
1.3006 + * @return a string representation of the <code>int</code> argument.
1.3007 + * @see java.lang.Integer#toString(int, int)
1.3008 + */
1.3009 + public static String valueOf(int i) {
1.3010 + return Integer.toString(i);
1.3011 + }
1.3012 +
1.3013 + /**
1.3014 + * Returns the string representation of the <code>long</code> argument.
1.3015 + * <p>
1.3016 + * The representation is exactly the one returned by the
1.3017 + * <code>Long.toString</code> method of one argument.
1.3018 + *
1.3019 + * @param l a <code>long</code>.
1.3020 + * @return a string representation of the <code>long</code> argument.
1.3021 + * @see java.lang.Long#toString(long)
1.3022 + */
1.3023 + public static String valueOf(long l) {
1.3024 + return Long.toString(l);
1.3025 + }
1.3026 +
1.3027 + /**
1.3028 + * Returns the string representation of the <code>float</code> argument.
1.3029 + * <p>
1.3030 + * The representation is exactly the one returned by the
1.3031 + * <code>Float.toString</code> method of one argument.
1.3032 + *
1.3033 + * @param f a <code>float</code>.
1.3034 + * @return a string representation of the <code>float</code> argument.
1.3035 + * @see java.lang.Float#toString(float)
1.3036 + */
1.3037 + public static String valueOf(float f) {
1.3038 + return Float.toString(f);
1.3039 + }
1.3040 +
1.3041 + /**
1.3042 + * Returns the string representation of the <code>double</code> argument.
1.3043 + * <p>
1.3044 + * The representation is exactly the one returned by the
1.3045 + * <code>Double.toString</code> method of one argument.
1.3046 + *
1.3047 + * @param d a <code>double</code>.
1.3048 + * @return a string representation of the <code>double</code> argument.
1.3049 + * @see java.lang.Double#toString(double)
1.3050 + */
1.3051 + public static String valueOf(double d) {
1.3052 + return Double.toString(d);
1.3053 + }
1.3054 +
1.3055 + /**
1.3056 + * Returns a canonical representation for the string object.
1.3057 + * <p>
1.3058 + * A pool of strings, initially empty, is maintained privately by the
1.3059 + * class <code>String</code>.
1.3060 + * <p>
1.3061 + * When the intern method is invoked, if the pool already contains a
1.3062 + * string equal to this <code>String</code> object as determined by
1.3063 + * the {@link #equals(Object)} method, then the string from the pool is
1.3064 + * returned. Otherwise, this <code>String</code> object is added to the
1.3065 + * pool and a reference to this <code>String</code> object is returned.
1.3066 + * <p>
1.3067 + * It follows that for any two strings <code>s</code> and <code>t</code>,
1.3068 + * <code>s.intern() == t.intern()</code> is <code>true</code>
1.3069 + * if and only if <code>s.equals(t)</code> is <code>true</code>.
1.3070 + * <p>
1.3071 + * All literal strings and string-valued constant expressions are
1.3072 + * interned. String literals are defined in section 3.10.5 of the
1.3073 + * <cite>The Java™ Language Specification</cite>.
1.3074 + *
1.3075 + * @return a string that has the same contents as this string, but is
1.3076 + * guaranteed to be from a pool of unique strings.
1.3077 + */
1.3078 + public native String intern();
1.3079 +
1.3080 +}