1 /*
2 * Copyright (c) 1994, 2014, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import java.io.ObjectStreamField;
29 import java.io.UnsupportedEncodingException;
30 import java.nio.charset.Charset;
31 import java.nio.ByteBuffer;
32 import java.util.ArrayList;
33 import java.util.Arrays;
34 import java.util.Comparator;
35 import java.util.Formatter;
36 import java.util.Locale;
37 import java.util.Objects;
38 import java.util.StringJoiner;
39 import java.util.regex.Matcher;
40 import java.util.regex.Pattern;
41 import java.util.regex.PatternSyntaxException;
42
43 /**
44 * The {@code String} class represents character strings. All
45 * string literals in Java programs, such as {@code "abc"}, are
46 * implemented as instances of this class.
47 * <p>
48 * Strings are constant; their values cannot be changed after they
49 * are created. String buffers support mutable strings.
50 * Because String objects are immutable they can be shared. For example:
51 * <blockquote><pre>
52 * String str = "abc";
53 * </pre></blockquote><p>
54 * is equivalent to:
55 * <blockquote><pre>
56 * char data[] = {'a', 'b', 'c'};
57 * String str = new String(data);
58 * </pre></blockquote><p>
59 * Here are some more examples of how strings can be used:
60 * <blockquote><pre>
61 * System.out.println("abc");
62 * String cde = "cde";
63 * System.out.println("abc" + cde);
64 * String c = "abc".substring(2,3);
65 * String d = cde.substring(1, 2);
66 * </pre></blockquote>
67 * <p>
68 * The class {@code String} includes methods for examining
69 * individual characters of the sequence, for comparing strings, for
70 * searching strings, for extracting substrings, and for creating a
71 * copy of a string with all characters translated to uppercase or to
72 * lowercase. Case mapping is based on the Unicode Standard version
73 * specified by the {@link java.lang.Character Character} class.
74 * <p>
75 * The Java language provides special support for the string
76 * concatenation operator ( + ), and for conversion of
77 * other objects to strings. String concatenation is implemented
78 * through the {@code StringBuilder}(or {@code StringBuffer})
79 * class and its {@code append} method.
80 * String conversions are implemented through the method
81 * {@code toString}, defined by {@code Object} and
82 * inherited by all classes in Java. For additional information on
83 * string concatenation and conversion, see Gosling, Joy, and Steele,
84 * <i>The Java Language Specification</i>.
85 *
86 * <p> Unless otherwise noted, passing a <tt>null</tt> argument to a constructor
87 * or method in this class will cause a {@link NullPointerException} to be
88 * thrown.
89 *
90 * <p>A {@code String} represents a string in the UTF-16 format
91 * in which <em>supplementary characters</em> are represented by <em>surrogate
92 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
93 * Character Representations</a> in the {@code Character} class for
94 * more information).
95 * Index values refer to {@code char} code units, so a supplementary
96 * character uses two positions in a {@code String}.
97 * <p>The {@code String} class provides methods for dealing with
98 * Unicode code points (i.e., characters), in addition to those for
99 * dealing with Unicode code units (i.e., {@code char} values).
100 *
101 * @author Lee Boynton
102 * @author Arthur van Hoff
103 * @author Martin Buchholz
104 * @author Ulf Zibis
105 * @see java.lang.Object#toString()
106 * @see java.lang.StringBuffer
107 * @see java.lang.StringBuilder
108 * @see java.nio.charset.Charset
109 * @since 1.0
110 */
111
112 public final class String
113 implements java.io.Serializable, Comparable<String>, CharSequence {
114 /** The value is used for character storage. */
115 private final char value[];
116
117 /** Cache the hash code for the string */
118 private int hash; // Default to 0
119
120 /** use serialVersionUID from JDK 1.0.2 for interoperability */
121 private static final long serialVersionUID = -6849794470754667710L;
122
123 /**
124 * Class String is special cased within the Serialization Stream Protocol.
125 *
126 * A String instance is written into an ObjectOutputStream according to
127 * <a href="{@docRoot}/../platform/serialization/spec/output.html">
128 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
129 */
130 private static final ObjectStreamField[] serialPersistentFields =
131 new ObjectStreamField[0];
132
133 /**
134 * Initializes a newly created {@code String} object so that it represents
135 * an empty character sequence. Note that use of this constructor is
136 * unnecessary since Strings are immutable.
137 */
138 public String() {
139 this.value = new char[0];
140 }
141
142 /**
143 * Initializes a newly created {@code String} object so that it represents
144 * the same sequence of characters as the argument; in other words, the
145 * newly created string is a copy of the argument string. Unless an
146 * explicit copy of {@code original} is needed, use of this constructor is
147 * unnecessary since Strings are immutable.
148 *
149 * @param original
150 * A {@code String}
151 */
152 public String(String original) {
153 this.value = original.value;
154 this.hash = original.hash;
155 }
156
157 /**
158 * Allocates a new {@code String} so that it represents the sequence of
159 * characters currently contained in the character array argument. The
160 * contents of the character array are copied; subsequent modification of
161 * the character array does not affect the newly created string.
162 *
163 * @param value
164 * The initial value of the string
165 */
166 public String(char value[]) {
167 this.value = Arrays.copyOf(value, value.length);
168 }
169
170 /**
171 * Allocates a new {@code String} that contains characters from a subarray
172 * of the character array argument. The {@code offset} argument is the
173 * index of the first character of the subarray and the {@code count}
174 * argument specifies the length of the subarray. The contents of the
175 * subarray are copied; subsequent modification of the character array does
176 * not affect the newly created string.
177 *
178 * @param value
179 * Array that is the source of characters
180 *
181 * @param offset
182 * The initial offset
183 *
184 * @param count
185 * The length
186 *
187 * @throws IndexOutOfBoundsException
188 * If the {@code offset} and {@code count} arguments index
189 * characters outside the bounds of the {@code value} array
190 */
191 public String(char value[], int offset, int count) {
192 if (offset < 0) {
193 throw new StringIndexOutOfBoundsException(offset);
194 }
195 if (count < 0) {
196 throw new StringIndexOutOfBoundsException(count);
197 }
198 // Note: offset or count might be near -1>>>1.
199 if (offset > value.length - count) {
200 throw new StringIndexOutOfBoundsException(offset + count);
201 }
202 this.value = Arrays.copyOfRange(value, offset, offset+count);
203 }
204
205 /**
206 * Allocates a new {@code String} that contains characters from a subarray
207 * of the <a href="Character.html#unicode">Unicode code point</a> array
208 * argument. The {@code offset} argument is the index of the first code
209 * point of the subarray and the {@code count} argument specifies the
210 * length of the subarray. The contents of the subarray are converted to
211 * {@code char}s; subsequent modification of the {@code int} array does not
212 * affect the newly created string.
213 *
214 * @param codePoints
215 * Array that is the source of Unicode code points
216 *
217 * @param offset
218 * The initial offset
219 *
220 * @param count
221 * The length
222 *
223 * @throws IllegalArgumentException
224 * If any invalid Unicode code point is found in {@code
225 * codePoints}
226 *
227 * @throws IndexOutOfBoundsException
228 * If the {@code offset} and {@code count} arguments index
229 * characters outside the bounds of the {@code codePoints} array
230 *
231 * @since 1.5
232 */
233 public String(int[] codePoints, int offset, int count) {
234 if (offset < 0) {
235 throw new StringIndexOutOfBoundsException(offset);
236 }
237 if (count < 0) {
238 throw new StringIndexOutOfBoundsException(count);
239 }
240 // Note: offset or count might be near -1>>>1.
241 if (offset > codePoints.length - count) {
242 throw new StringIndexOutOfBoundsException(offset + count);
243 }
244
245 final int end = offset + count;
246
247 // Pass 1: Compute precise size of char[]
248 int n = count;
249 for (int i = offset; i < end; i++) {
250 int c = codePoints[i];
251 if (Character.isBmpCodePoint(c))
252 continue;
253 else if (Character.isValidCodePoint(c))
254 n++;
255 else throw new IllegalArgumentException(Integer.toString(c));
256 }
257
258 // Pass 2: Allocate and fill in char[]
259 final char[] v = new char[n];
260
261 for (int i = offset, j = 0; i < end; i++, j++) {
262 int c = codePoints[i];
263 if (Character.isBmpCodePoint(c))
264 v[j] = (char)c;
265 else
266 Character.toSurrogates(c, v, j++);
267 }
268
269 this.value = v;
270 }
271
272 /**
273 * Allocates a new {@code String} constructed from a subarray of an array
274 * of 8-bit integer values.
275 *
276 * <p> The {@code offset} argument is the index of the first byte of the
277 * subarray, and the {@code count} argument specifies the length of the
278 * subarray.
279 *
280 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
281 * specified in the method above.
282 *
283 * @deprecated This method does not properly convert bytes into characters.
284 * As of JDK 1.1, the preferred way to do this is via the
285 * {@code String} constructors that take a {@link
286 * java.nio.charset.Charset}, charset name, or that use the platform's
287 * default charset.
288 *
289 * @param ascii
290 * The bytes to be converted to characters
291 *
292 * @param hibyte
293 * The top 8 bits of each 16-bit Unicode code unit
294 *
295 * @param offset
296 * The initial offset
297 * @param count
298 * The length
299 *
300 * @throws IndexOutOfBoundsException
301 * If the {@code offset} or {@code count} argument is invalid
302 *
303 * @see #String(byte[], int)
304 * @see #String(byte[], int, int, java.lang.String)
305 * @see #String(byte[], int, int, java.nio.charset.Charset)
306 * @see #String(byte[], int, int)
307 * @see #String(byte[], java.lang.String)
308 * @see #String(byte[], java.nio.charset.Charset)
309 * @see #String(byte[])
310 */
311 @Deprecated
312 public String(byte ascii[], int hibyte, int offset, int count) {
313 checkBounds(ascii, offset, count);
314 char value[] = new char[count];
315
316 if (hibyte == 0) {
317 for (int i = count; i-- > 0;) {
318 value[i] = (char)(ascii[i + offset] & 0xff);
319 }
320 } else {
321 hibyte <<= 8;
322 for (int i = count; i-- > 0;) {
323 value[i] = (char)(hibyte | (ascii[i + offset] & 0xff));
324 }
325 }
326 this.value = value;
327 }
328
329 /**
330 * Allocates a new {@code String} containing characters constructed from
331 * an array of 8-bit integer values. Each character <i>c</i>in the
332 * resulting string is constructed from the corresponding component
333 * <i>b</i> in the byte array such that:
334 *
335 * <blockquote><pre>
336 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
337 * | (<b><i>b</i></b> & 0xff))
338 * </pre></blockquote>
339 *
340 * @deprecated This method does not properly convert bytes into
341 * characters. As of JDK 1.1, the preferred way to do this is via the
342 * {@code String} constructors that take a {@link
343 * java.nio.charset.Charset}, charset name, or that use the platform's
344 * default charset.
345 *
346 * @param ascii
347 * The bytes to be converted to characters
348 *
349 * @param hibyte
350 * The top 8 bits of each 16-bit Unicode code unit
351 *
352 * @see #String(byte[], int, int, java.lang.String)
353 * @see #String(byte[], int, int, java.nio.charset.Charset)
354 * @see #String(byte[], int, int)
355 * @see #String(byte[], java.lang.String)
356 * @see #String(byte[], java.nio.charset.Charset)
357 * @see #String(byte[])
358 */
359 @Deprecated
360 public String(byte ascii[], int hibyte) {
361 this(ascii, hibyte, 0, ascii.length);
362 }
363
364 /* Common private utility method used to bounds check the byte array
365 * and requested offset & length values used by the String(byte[],..)
366 * constructors.
367 */
368 private static void checkBounds(byte[] bytes, int offset, int length) {
369 if (length < 0)
370 throw new StringIndexOutOfBoundsException(length);
371 if (offset < 0)
372 throw new StringIndexOutOfBoundsException(offset);
373 if (offset > bytes.length - length)
374 throw new StringIndexOutOfBoundsException(offset + length);
375 }
376
377 /**
378 * Constructs a new {@code String} by decoding the specified subarray of
379 * bytes using the specified charset. The length of the new {@code String}
380 * is a function of the charset, and hence may not be equal to the length
381 * of the subarray.
382 *
383 * <p> The behavior of this constructor when the given bytes are not valid
384 * in the given charset is unspecified. The {@link
385 * java.nio.charset.CharsetDecoder} class should be used when more control
386 * over the decoding process is required.
387 *
388 * @param bytes
389 * The bytes to be decoded into characters
390 *
391 * @param offset
392 * The index of the first byte to decode
393 *
394 * @param length
395 * The number of bytes to decode
396
397 * @param charsetName
398 * The name of a supported {@linkplain java.nio.charset.Charset
399 * charset}
400 *
401 * @throws UnsupportedEncodingException
402 * If the named charset is not supported
403 *
404 * @throws IndexOutOfBoundsException
405 * If the {@code offset} and {@code length} arguments index
406 * characters outside the bounds of the {@code bytes} array
407 *
408 * @since 1.1
409 */
410 public String(byte bytes[], int offset, int length, String charsetName)
411 throws UnsupportedEncodingException {
412 if (charsetName == null)
413 throw new NullPointerException("charsetName");
414 checkBounds(bytes, offset, length);
415 this.value = StringCoding.decode(charsetName, bytes, offset, length);
416 }
417
418 /**
419 * Constructs a new {@code String} by decoding the specified subarray of
420 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
421 * The length of the new {@code String} is a function of the charset, and
422 * hence may not be equal to the length of the subarray.
423 *
424 * <p> This method always replaces malformed-input and unmappable-character
425 * sequences with this charset's default replacement string. The {@link
426 * java.nio.charset.CharsetDecoder} class should be used when more control
427 * over the decoding process is required.
428 *
429 * @param bytes
430 * The bytes to be decoded into characters
431 *
432 * @param offset
433 * The index of the first byte to decode
434 *
435 * @param length
436 * The number of bytes to decode
437 *
438 * @param charset
439 * The {@linkplain java.nio.charset.Charset charset} to be used to
440 * decode the {@code bytes}
441 *
442 * @throws IndexOutOfBoundsException
443 * If the {@code offset} and {@code length} arguments index
444 * characters outside the bounds of the {@code bytes} array
445 *
446 * @since 1.6
447 */
448 public String(byte bytes[], int offset, int length, Charset charset) {
449 if (charset == null)
450 throw new NullPointerException("charset");
451 checkBounds(bytes, offset, length);
452 this.value = StringCoding.decode(charset, bytes, offset, length);
453 }
454
455 /**
456 * Constructs a new {@code String} by decoding the remaining bytes in the specified
457 * {@linkplain java.nio.ByteBuffer byte buffer} using the specified
458 * {@linkplain java.nio.charset.Charset charset}.
459 * The length of the new {@code String} is a function of the charset, and
460 * hence may not be equal to the remaining number of bytes in the
461 * {@linkplain java.nio.ByteBuffer byte buffer}.
462 *
463 * <p> This method always replaces malformed-input and unmappable-character
464 * sequences with this charset's default replacement string. The {@link
465 * java.nio.charset.CharsetDecoder} class should be used when more control
466 * over the decoding process is required.
467 *
468 * <p>
469 * Bytes are read between <code>position()</code> and <code>limit()</code>
470 * of the {@link java.nio.ByteBuffer}.
471 * After the bytes have been read the <code>position()</code> will be
472 * advanced to its <code>limit()</code>.
473 *
474 * @param bytes
475 * The bytes to be decoded into characters
476 *
477 * @param charset
478 * The {@linkplain java.nio.charset.Charset charset} to be used to
479 * decode the {@code bytes}
480 *
481 * @since 1.9
482 */
483 public String(ByteBuffer bytes, Charset charset) {
484 Objects.requireNonNull(bytes);
485 Objects.requireNonNull(charset);
486 this.value = StringCoding.decode(charset, bytes);
487 }
488
489 /**
490 * Constructs a new {@code String} by decoding the remaining bytes in the specified
491 * {@linkplain java.nio.ByteBuffer byte buffer} using the specified
492 * charset.
493 * The length of the new {@code String} is a function of the charset, and
494 * hence may not be equal to the remaining number of bytes in the
495 * {@linkplain java.nio.ByteBuffer byte buffer}.
496 *
497 * <p> This method always replaces malformed-input and unmappable-character
498 * sequences with this charset's default replacement string. The {@link
499 * java.nio.charset.CharsetDecoder} class should be used when more control
500 * over the decoding process is required.
501 *
502 * <p>
503 * Bytes are read between <code>position()</code> and <code>limit()</code>
504 * of the {@link java.nio.ByteBuffer}.
505 * After the bytes have been read the <code>position()</code> will be
506 * advanced to its <code>limit()</code>.
507 *
508 * @param bytes
509 * The bytes to be decoded into characters
510 *
511 * @param charsetName
512 * The name of a supported {@linkplain java.nio.charset.Charset
513 * charset}
514 *
515 * @throws UnsupportedEncodingException
516 * If the named charset is not supported
517 *
518 *
519 * @since 1.9
520 */
521 public String(ByteBuffer bytes, String charsetName)
522 throws UnsupportedEncodingException {
523 Objects.requireNonNull(bytes);
524 Objects.requireNonNull(charsetName);
525 this.value = StringCoding.decode(charsetName, bytes);
526 }
527
528 /**
529 * Constructs a new {@code String} by decoding the specified array of bytes
530 * using the specified {@linkplain java.nio.charset.Charset charset}. The
531 * length of the new {@code String} is a function of the charset, and hence
532 * may not be equal to the length of the byte array.
533 *
534 * <p> The behavior of this constructor when the given bytes are not valid
535 * in the given charset is unspecified. The {@link
536 * java.nio.charset.CharsetDecoder} class should be used when more control
537 * over the decoding process is required.
538 *
539 * @param bytes
540 * The bytes to be decoded into characters
541 *
542 * @param charsetName
543 * The name of a supported {@linkplain java.nio.charset.Charset
544 * charset}
545 *
546 * @throws UnsupportedEncodingException
547 * If the named charset is not supported
548 *
549 * @since 1.1
550 */
551 public String(byte bytes[], String charsetName)
552 throws UnsupportedEncodingException {
553 this(bytes, 0, bytes.length, charsetName);
554 }
555
556 /**
557 * Constructs a new {@code String} by decoding the specified array of
558 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
559 * The length of the new {@code String} is a function of the charset, and
560 * hence may not be equal to the length of the byte array.
561 *
562 * <p> This method always replaces malformed-input and unmappable-character
563 * sequences with this charset's default replacement string. The {@link
564 * java.nio.charset.CharsetDecoder} class should be used when more control
565 * over the decoding process is required.
566 *
567 * @param bytes
568 * The bytes to be decoded into characters
569 *
570 * @param charset
571 * The {@linkplain java.nio.charset.Charset charset} to be used to
572 * decode the {@code bytes}
573 *
574 * @since 1.6
575 */
576 public String(byte bytes[], Charset charset) {
577 this(bytes, 0, bytes.length, charset);
578 }
579
580 /**
581 * Constructs a new {@code String} by decoding the specified subarray of
582 * bytes using the platform's default charset. The length of the new
583 * {@code String} is a function of the charset, and hence may not be equal
584 * to the length of the subarray.
585 *
586 * <p> The behavior of this constructor when the given bytes are not valid
587 * in the default charset is unspecified. The {@link
588 * java.nio.charset.CharsetDecoder} class should be used when more control
589 * over the decoding process is required.
590 *
591 * @param bytes
592 * The bytes to be decoded into characters
593 *
594 * @param offset
595 * The index of the first byte to decode
596 *
597 * @param length
598 * The number of bytes to decode
599 *
600 * @throws IndexOutOfBoundsException
601 * If the {@code offset} and the {@code length} arguments index
602 * characters outside the bounds of the {@code bytes} array
603 *
604 * @since 1.1
605 */
606 public String(byte bytes[], int offset, int length) {
607 checkBounds(bytes, offset, length);
608 this.value = StringCoding.decode(bytes, offset, length);
609 }
610
611 /**
612 * Constructs a new {@code String} by decoding the specified array of bytes
613 * using the platform's default charset. The length of the new {@code
614 * String} is a function of the charset, and hence may not be equal to the
615 * length of the byte array.
616 *
617 * <p> The behavior of this constructor when the given bytes are not valid
618 * in the default charset is unspecified. The {@link
619 * java.nio.charset.CharsetDecoder} class should be used when more control
620 * over the decoding process is required.
621 *
622 * @param bytes
623 * The bytes to be decoded into characters
624 *
625 * @since 1.1
626 */
627 public String(byte bytes[]) {
628 this(bytes, 0, bytes.length);
629 }
630
631 /**
632 * Allocates a new string that contains the sequence of characters
633 * currently contained in the string buffer argument. The contents of the
634 * string buffer are copied; subsequent modification of the string buffer
635 * does not affect the newly created string.
636 *
637 * @param buffer
638 * A {@code StringBuffer}
639 */
640 public String(StringBuffer buffer) {
641 synchronized(buffer) {
642 this.value = Arrays.copyOf(buffer.getValue(), buffer.length());
643 }
644 }
645
646 /**
647 * Allocates a new string that contains the sequence of characters
648 * currently contained in the string builder argument. The contents of the
649 * string builder are copied; subsequent modification of the string builder
650 * does not affect the newly created string.
651 *
652 * <p> This constructor is provided to ease migration to {@code
653 * StringBuilder}. Obtaining a string from a string builder via the {@code
654 * toString} method is likely to run faster and is generally preferred.
655 *
656 * @param builder
657 * A {@code StringBuilder}
658 *
659 * @since 1.5
660 */
661 public String(StringBuilder builder) {
662 this.value = Arrays.copyOf(builder.getValue(), builder.length());
663 }
664
665 /*
666 * Package private constructor which shares value array for speed.
667 * this constructor is always expected to be called with share==true.
668 * a separate constructor is needed because we already have a public
669 * String(char[]) constructor that makes a copy of the given char[].
670 */
671 String(char[] value, boolean share) {
672 // assert share : "unshared not supported";
673 this.value = value;
674 }
675
676 /**
677 * Returns the length of this string.
678 * The length is equal to the number of <a href="Character.html#unicode">Unicode
679 * code units</a> in the string.
680 *
681 * @return the length of the sequence of characters represented by this
682 * object.
683 */
684 public int length() {
685 return value.length;
686 }
687
688 /**
689 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
690 *
691 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
692 * {@code false}
693 *
694 * @since 1.6
695 */
696 public boolean isEmpty() {
697 return value.length == 0;
698 }
699
700 /**
701 * Returns the {@code char} value at the
702 * specified index. An index ranges from {@code 0} to
703 * {@code length() - 1}. The first {@code char} value of the sequence
704 * is at index {@code 0}, the next at index {@code 1},
705 * and so on, as for array indexing.
706 *
707 * <p>If the {@code char} value specified by the index is a
708 * <a href="Character.html#unicode">surrogate</a>, the surrogate
709 * value is returned.
710 *
711 * @param index the index of the {@code char} value.
712 * @return the {@code char} value at the specified index of this string.
713 * The first {@code char} value is at index {@code 0}.
714 * @exception IndexOutOfBoundsException if the {@code index}
715 * argument is negative or not less than the length of this
716 * string.
717 */
718 public char charAt(int index) {
719 if ((index < 0) || (index >= value.length)) {
720 throw new StringIndexOutOfBoundsException(index);
721 }
722 return value[index];
723 }
724
725 /**
726 * Returns the character (Unicode code point) at the specified
727 * index. The index refers to {@code char} values
728 * (Unicode code units) and ranges from {@code 0} to
729 * {@link #length()}{@code - 1}.
730 *
731 * <p> If the {@code char} value specified at the given index
732 * is in the high-surrogate range, the following index is less
733 * than the length of this {@code String}, and the
734 * {@code char} value at the following index is in the
735 * low-surrogate range, then the supplementary code point
736 * corresponding to this surrogate pair is returned. Otherwise,
737 * the {@code char} value at the given index is returned.
738 *
739 * @param index the index to the {@code char} values
740 * @return the code point value of the character at the
741 * {@code index}
742 * @exception IndexOutOfBoundsException if the {@code index}
743 * argument is negative or not less than the length of this
744 * string.
745 * @since 1.5
746 */
747 public int codePointAt(int index) {
748 if ((index < 0) || (index >= value.length)) {
749 throw new StringIndexOutOfBoundsException(index);
750 }
751 return Character.codePointAtImpl(value, index, value.length);
752 }
753
754 /**
755 * Returns the character (Unicode code point) before the specified
756 * index. The index refers to {@code char} values
757 * (Unicode code units) and ranges from {@code 1} to {@link
758 * CharSequence#length() length}.
759 *
760 * <p> If the {@code char} value at {@code (index - 1)}
761 * is in the low-surrogate range, {@code (index - 2)} is not
762 * negative, and the {@code char} value at {@code (index -
763 * 2)} is in the high-surrogate range, then the
764 * supplementary code point value of the surrogate pair is
765 * returned. If the {@code char} value at {@code index -
766 * 1} is an unpaired low-surrogate or a high-surrogate, the
767 * surrogate value is returned.
768 *
769 * @param index the index following the code point that should be returned
770 * @return the Unicode code point value before the given index.
771 * @exception IndexOutOfBoundsException if the {@code index}
772 * argument is less than 1 or greater than the length
773 * of this string.
774 * @since 1.5
775 */
776 public int codePointBefore(int index) {
777 int i = index - 1;
778 if ((i < 0) || (i >= value.length)) {
779 throw new StringIndexOutOfBoundsException(index);
780 }
781 return Character.codePointBeforeImpl(value, index, 0);
782 }
783
784 /**
785 * Returns the number of Unicode code points in the specified text
786 * range of this {@code String}. The text range begins at the
787 * specified {@code beginIndex} and extends to the
788 * {@code char} at index {@code endIndex - 1}. Thus the
789 * length (in {@code char}s) of the text range is
790 * {@code endIndex-beginIndex}. Unpaired surrogates within
791 * the text range count as one code point each.
792 *
793 * @param beginIndex the index to the first {@code char} of
794 * the text range.
795 * @param endIndex the index after the last {@code char} of
796 * the text range.
797 * @return the number of Unicode code points in the specified text
798 * range
799 * @exception IndexOutOfBoundsException if the
800 * {@code beginIndex} is negative, or {@code endIndex}
801 * is larger than the length of this {@code String}, or
802 * {@code beginIndex} is larger than {@code endIndex}.
803 * @since 1.5
804 */
805 public int codePointCount(int beginIndex, int endIndex) {
806 if (beginIndex < 0 || endIndex > value.length || beginIndex > endIndex) {
807 throw new IndexOutOfBoundsException();
808 }
809 return Character.codePointCountImpl(value, beginIndex, endIndex - beginIndex);
810 }
811
812 /**
813 * Returns the index within this {@code String} that is
814 * offset from the given {@code index} by
815 * {@code codePointOffset} code points. Unpaired surrogates
816 * within the text range given by {@code index} and
817 * {@code codePointOffset} count as one code point each.
818 *
819 * @param index the index to be offset
820 * @param codePointOffset the offset in code points
821 * @return the index within this {@code String}
822 * @exception IndexOutOfBoundsException if {@code index}
823 * is negative or larger then the length of this
824 * {@code String}, or if {@code codePointOffset} is positive
825 * and the substring starting with {@code index} has fewer
826 * than {@code codePointOffset} code points,
827 * or if {@code codePointOffset} is negative and the substring
828 * before {@code index} has fewer than the absolute value
829 * of {@code codePointOffset} code points.
830 * @since 1.5
831 */
832 public int offsetByCodePoints(int index, int codePointOffset) {
833 if (index < 0 || index > value.length) {
834 throw new IndexOutOfBoundsException();
835 }
836 return Character.offsetByCodePointsImpl(value, 0, value.length,
837 index, codePointOffset);
838 }
839
840 /**
841 * Copy characters from this string into dst starting at dstBegin.
842 * This method doesn't perform any range checking.
843 */
844 void getChars(char dst[], int dstBegin) {
845 System.arraycopy(value, 0, dst, dstBegin, value.length);
846 }
847
848 /**
849 * Copies characters from this string into the destination character
850 * array.
851 * <p>
852 * The first character to be copied is at index {@code srcBegin};
853 * the last character to be copied is at index {@code srcEnd-1}
854 * (thus the total number of characters to be copied is
855 * {@code srcEnd-srcBegin}). The characters are copied into the
856 * subarray of {@code dst} starting at index {@code dstBegin}
857 * and ending at index:
858 * <blockquote><pre>
859 * dstbegin + (srcEnd-srcBegin) - 1
860 * </pre></blockquote>
861 *
862 * @param srcBegin index of the first character in the string
863 * to copy.
864 * @param srcEnd index after the last character in the string
865 * to copy.
866 * @param dst the destination array.
867 * @param dstBegin the start offset in the destination array.
868 * @exception IndexOutOfBoundsException If any of the following
869 * is true:
870 * <ul><li>{@code srcBegin} is negative.
871 * <li>{@code srcBegin} is greater than {@code srcEnd}
872 * <li>{@code srcEnd} is greater than the length of this
873 * string
874 * <li>{@code dstBegin} is negative
875 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
876 * {@code dst.length}</ul>
877 */
878 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
879 if (srcBegin < 0) {
880 throw new StringIndexOutOfBoundsException(srcBegin);
881 }
882 if (srcEnd > value.length) {
883 throw new StringIndexOutOfBoundsException(srcEnd);
884 }
885 if (srcBegin > srcEnd) {
886 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
887 }
888 System.arraycopy(value, srcBegin, dst, dstBegin, srcEnd - srcBegin);
889 }
890
891 /**
892 * Copies characters from this string into the destination byte array. Each
893 * byte receives the 8 low-order bits of the corresponding character. The
894 * eight high-order bits of each character are not copied and do not
895 * participate in the transfer in any way.
896 *
897 * <p> The first character to be copied is at index {@code srcBegin}; the
898 * last character to be copied is at index {@code srcEnd-1}. The total
899 * number of characters to be copied is {@code srcEnd-srcBegin}. The
900 * characters, converted to bytes, are copied into the subarray of {@code
901 * dst} starting at index {@code dstBegin} and ending at index:
902 *
903 * <blockquote><pre>
904 * dstbegin + (srcEnd-srcBegin) - 1
905 * </pre></blockquote>
906 *
907 * @deprecated This method does not properly convert characters into
908 * bytes. As of JDK 1.1, the preferred way to do this is via the
909 * {@link #getBytes()} method, which uses the platform's default charset.
910 *
911 * @param srcBegin
912 * Index of the first character in the string to copy
913 *
914 * @param srcEnd
915 * Index after the last character in the string to copy
916 *
917 * @param dst
918 * The destination array
919 *
920 * @param dstBegin
921 * The start offset in the destination array
922 *
923 * @throws IndexOutOfBoundsException
924 * If any of the following is true:
925 * <ul>
926 * <li> {@code srcBegin} is negative
927 * <li> {@code srcBegin} is greater than {@code srcEnd}
928 * <li> {@code srcEnd} is greater than the length of this String
929 * <li> {@code dstBegin} is negative
930 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
931 * dst.length}
932 * </ul>
933 */
934 @Deprecated
935 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
936 if (srcBegin < 0) {
937 throw new StringIndexOutOfBoundsException(srcBegin);
938 }
939 if (srcEnd > value.length) {
940 throw new StringIndexOutOfBoundsException(srcEnd);
941 }
942 if (srcBegin > srcEnd) {
943 throw new StringIndexOutOfBoundsException(srcEnd - srcBegin);
944 }
945 Objects.requireNonNull(dst);
946
947 int j = dstBegin;
948 int n = srcEnd;
949 int i = srcBegin;
950 char[] val = value; /* avoid getfield opcode */
951
952 while (i < n) {
953 dst[j++] = (byte)val[i++];
954 }
955 }
956
957 /**
958 * Encodes this {@code String} into a sequence of bytes using the named
959 * charset, storing the result into a new byte array.
960 *
961 * <p> The behavior of this method when this string cannot be encoded in
962 * the given charset is unspecified. The {@link
963 * java.nio.charset.CharsetEncoder} class should be used when more control
964 * over the encoding process is required.
965 *
966 * @param charsetName
967 * The name of a supported {@linkplain java.nio.charset.Charset
968 * charset}
969 *
970 * @return The resultant byte array
971 *
972 * @throws UnsupportedEncodingException
973 * If the named charset is not supported
974 *
975 * @since 1.1
976 */
977 public byte[] getBytes(String charsetName)
978 throws UnsupportedEncodingException {
979 if (charsetName == null) throw new NullPointerException();
980 return StringCoding.encode(charsetName, value, 0, value.length);
981 }
982
983 /**
984 * Encodes this {@code String} into a sequence of bytes using the given
985 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
986 * new byte array.
987 *
988 * <p> This method always replaces malformed-input and unmappable-character
989 * sequences with this charset's default replacement byte array. The
990 * {@link java.nio.charset.CharsetEncoder} class should be used when more
991 * control over the encoding process is required.
992 *
993 * @param charset
994 * The {@linkplain java.nio.charset.Charset} to be used to encode
995 * the {@code String}
996 *
997 * @return The resultant byte array
998 *
999 * @since 1.6
1000 */
1001 public byte[] getBytes(Charset charset) {
1002 Objects.requireNonNull(charset);
1003 return StringCoding.encode(charset, value, 0, value.length);
1004 }
1005
1006 /**
1007 * Encodes this {@code String} into a sequence of bytes using the given
1008 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
1009 * byte array that has been passed as an argument.
1010 *
1011 * <p> This method always replaces malformed-input and unmappable-character
1012 * sequences with this charset's default replacement byte array. The {@link
1013 * java.nio.charset.CharsetDecoder} class should be used when more control
1014 * over the decoding process is required.
1015 *
1016 * <p> The number of bytes written during encoding is a function of the charset
1017 * used to perform the encoding and is returned from this method. It may not
1018 * be equal to the length of this
1019 * String. At most <code>destBuffer.length - destOffset</code> bytes will be written.
1020 *
1021 * @param destBuffer
1022 * The destination array
1023 *
1024 * @param destOffset
1025 * The start offset in the destination array
1026 *
1027 * @param charset
1028 * The {@linkplain java.nio.charset.Charset} to be used to encode
1029 * the {@code String}
1030 *
1031 * @return the number of bytes written
1032 *
1033 * @since 1.9
1034 */
1035 public int getBytes(byte[] destBuffer, int destOffset, Charset charset) {
1036 Objects.requireNonNull(destBuffer);
1037 Objects.requireNonNull(charset);
1038 return StringCoding.encode(charset, value, 0, value.length, destBuffer, destOffset);
1039 }
1040
1041 /**
1042 * Encodes as many characters as possible from this {@code String} into a
1043 * sequence of bytes using the given
1044 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
1045 * {@linkplain java.nio.ByteBuffer byte buffer} that has been passed as an argument.
1046 *
1047 * <p> The number of bytes written during encoding is a function of the charset
1048 * used to perform the encoding and is returned from this method. It may not
1049 * be equal to the length of this
1050 * String. At most <code>destBuffer.remaining()</code> bytes will be written.
1051 *
1052 * <p> This method always replaces malformed-input and unmappable-character
1053 * sequences with this charset's default replacement byte array. The {@link
1054 * java.nio.charset.CharsetDecoder} class should be used when more control
1055 * over the decoding process is required.
1056 *
1057 * <p> The buffer's position will be advanced to reflect the number of
1058 * the bytes written, but its mark and limit will not be modified.
1059 *
1060 * @param destBuffer
1061 * The destination {@linkplain java.nio.ByteBuffer}
1062 *
1063 * @param charset
1064 * The {@linkplain java.nio.charset.Charset} to be used to encode
1065 * the {@code String}
1066 *
1067 * @return the number of bytes written
1068 *
1069 * @since 1.9
1070 */
1071 public int getBytes(ByteBuffer destBuffer, Charset charset) {
1072 Objects.requireNonNull(destBuffer);
1073 Objects.requireNonNull(charset);
1074 return StringCoding.encode(charset, value, 0, value.length, destBuffer);
1075 }
1076
1077 /**
1078 * Encodes as many characters as possible from this {@code String} into a
1079 * sequence of bytes using the specified charset, storing the result into a
1080 * {@linkplain java.nio.ByteBuffer byte buffer} that has been passed as an argument.
1081 *
1082 * <p> The number of bytes written during encoding is a function of the charset
1083 * used to perform the encoding and is returned from this method. It may not
1084 * be equal to the length of this
1085 * String. At most <code>destBuffer.remaining()</code> bytes will be written.
1086 *
1087 * <p> This method always replaces malformed-input and unmappable-character
1088 * sequences with this charset's default replacement byte array. The {@link
1089 * java.nio.charset.CharsetDecoder} class should be used when more control
1090 * over the decoding process is required.
1091 *
1092 * <p> The buffer's position will be advanced to reflect the number of
1093 * the bytes written, but its mark and limit will not be modified.
1094 *
1095 * @param destBuffer
1096 * The destination {@linkplain java.nio.ByteBuffer}
1097 *
1098 * @param charsetName
1099 * The name of a supported {@linkplain java.nio.charset.Charset
1100 * charset}
1101 *
1102 * @return the number of bytes written
1103 *
1104 * @throws UnsupportedEncodingException
1105 * If the named charset is not supported
1106 *
1107 * @since 1.9
1108 */
1109 public int getBytes(ByteBuffer destBuffer, String charsetName) throws UnsupportedEncodingException {
1110 Objects.requireNonNull(destBuffer);
1111 Objects.requireNonNull(charsetName);
1112 return StringCoding.encode(charsetName, value, 0, value.length, destBuffer);
1113 }
1114
1115 /**
1116 * Encodes as many characters as possible from this {@code String} into a
1117 * sequence of bytes using the specified charset, storing the result into a
1118 * byte array that has been passed as an argument.
1119 *
1120 * <p> The number of bytes written during encoding is a function of the charset
1121 * used to perform the encoding and is returned from this method. It may not
1122 * be equal to the length of this
1123 * String. At most <code>destBuffer.length - destOffset</code> bytes will be written.
1124 *
1125 * <p> This method always replaces malformed-input and unmappable-character
1126 * sequences with this charset's default replacement byte array. The {@link
1127 * java.nio.charset.CharsetDecoder} class should be used when more control
1128 * over the decoding process is required.
1129 *
1130 * @param destBuffer
1131 * The destination array
1132 *
1133 * @param destOffset
1134 * The start offset in the destination array
1135 *
1136 * @param charsetName
1137 * The name of a supported {@linkplain java.nio.charset.Charset
1138 * charset}
1139 *
1140 * @return the number of bytes written
1141 *
1142 * @throws UnsupportedEncodingException
1143 * If the named charset is not supported
1144 *
1145 * @since 1.9
1146 */
1147 public int getBytes(byte[] destBuffer, int destOffset, String charsetName) throws UnsupportedEncodingException {
1148 Objects.requireNonNull(destBuffer);
1149 Objects.requireNonNull(charsetName);
1150 return StringCoding.encode(charsetName, value, 0, value.length, destBuffer, destOffset);
1151 }
1152
1153 /**
1154 * Encodes this {@code String} into a sequence of bytes using the
1155 * platform's default charset, storing the result into a new byte array.
1156 *
1157 * <p> The behavior of this method when this string cannot be encoded in
1158 * the default charset is unspecified. The {@link
1159 * java.nio.charset.CharsetEncoder} class should be used when more control
1160 * over the encoding process is required.
1161 *
1162 * @return The resultant byte array
1163 *
1164 * @since 1.1
1165 */
1166 public byte[] getBytes() {
1167 return StringCoding.encode(value, 0, value.length);
1168 }
1169
1170 /**
1171 * Compares this string to the specified object. The result is {@code
1172 * true} if and only if the argument is not {@code null} and is a {@code
1173 * String} object that represents the same sequence of characters as this
1174 * object.
1175 *
1176 * @param anObject
1177 * The object to compare this {@code String} against
1178 *
1179 * @return {@code true} if the given object represents a {@code String}
1180 * equivalent to this string, {@code false} otherwise
1181 *
1182 * @see #compareTo(String)
1183 * @see #equalsIgnoreCase(String)
1184 */
1185 public boolean equals(Object anObject) {
1186 if (this == anObject) {
1187 return true;
1188 }
1189 if (anObject instanceof String) {
1190 String anotherString = (String)anObject;
1191 int n = value.length;
1192 if (n == anotherString.value.length) {
1193 char v1[] = value;
1194 char v2[] = anotherString.value;
1195 int i = 0;
1196 while (n-- != 0) {
1197 if (v1[i] != v2[i])
1198 return false;
1199 i++;
1200 }
1201 return true;
1202 }
1203 }
1204 return false;
1205 }
1206
1207 /**
1208 * Compares this string to the specified {@code StringBuffer}. The result
1209 * is {@code true} if and only if this {@code String} represents the same
1210 * sequence of characters as the specified {@code StringBuffer}. This method
1211 * synchronizes on the {@code StringBuffer}.
1212 *
1213 * @param sb
1214 * The {@code StringBuffer} to compare this {@code String} against
1215 *
1216 * @return {@code true} if this {@code String} represents the same
1217 * sequence of characters as the specified {@code StringBuffer},
1218 * {@code false} otherwise
1219 *
1220 * @since 1.4
1221 */
1222 public boolean contentEquals(StringBuffer sb) {
1223 return contentEquals((CharSequence)sb);
1224 }
1225
1226 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1227 char v1[] = value;
1228 char v2[] = sb.getValue();
1229 int n = v1.length;
1230 if (n != sb.length()) {
1231 return false;
1232 }
1233 for (int i = 0; i < n; i++) {
1234 if (v1[i] != v2[i]) {
1235 return false;
1236 }
1237 }
1238 return true;
1239 }
1240
1241 /**
1242 * Compares this string to the specified {@code CharSequence}. The
1243 * result is {@code true} if and only if this {@code String} represents the
1244 * same sequence of char values as the specified sequence. Note that if the
1245 * {@code CharSequence} is a {@code StringBuffer} then the method
1246 * synchronizes on it.
1247 *
1248 * @param cs
1249 * The sequence to compare this {@code String} against
1250 *
1251 * @return {@code true} if this {@code String} represents the same
1252 * sequence of char values as the specified sequence, {@code
1253 * false} otherwise
1254 *
1255 * @since 1.5
1256 */
1257 public boolean contentEquals(CharSequence cs) {
1258 // Argument is a StringBuffer, StringBuilder
1259 if (cs instanceof AbstractStringBuilder) {
1260 if (cs instanceof StringBuffer) {
1261 synchronized(cs) {
1262 return nonSyncContentEquals((AbstractStringBuilder)cs);
1263 }
1264 } else {
1265 return nonSyncContentEquals((AbstractStringBuilder)cs);
1266 }
1267 }
1268 // Argument is a String
1269 if (cs instanceof String) {
1270 return equals(cs);
1271 }
1272 // Argument is a generic CharSequence
1273 char v1[] = value;
1274 int n = v1.length;
1275 if (n != cs.length()) {
1276 return false;
1277 }
1278 for (int i = 0; i < n; i++) {
1279 if (v1[i] != cs.charAt(i)) {
1280 return false;
1281 }
1282 }
1283 return true;
1284 }
1285
1286 /**
1287 * Compares this {@code String} to another {@code String}, ignoring case
1288 * considerations. Two strings are considered equal ignoring case if they
1289 * are of the same length and corresponding characters in the two strings
1290 * are equal ignoring case.
1291 *
1292 * <p> Two characters {@code c1} and {@code c2} are considered the same
1293 * ignoring case if at least one of the following is true:
1294 * <ul>
1295 * <li> The two characters are the same (as compared by the
1296 * {@code ==} operator)
1297 * <li> Applying the method {@link
1298 * java.lang.Character#toUpperCase(char)} to each character
1299 * produces the same result
1300 * <li> Applying the method {@link
1301 * java.lang.Character#toLowerCase(char)} to each character
1302 * produces the same result
1303 * </ul>
1304 *
1305 * @param anotherString
1306 * The {@code String} to compare this {@code String} against
1307 *
1308 * @return {@code true} if the argument is not {@code null} and it
1309 * represents an equivalent {@code String} ignoring case; {@code
1310 * false} otherwise
1311 *
1312 * @see #equals(Object)
1313 */
1314 public boolean equalsIgnoreCase(String anotherString) {
1315 return (this == anotherString) ? true
1316 : (anotherString != null)
1317 && (anotherString.value.length == value.length)
1318 && regionMatches(true, 0, anotherString, 0, value.length);
1319 }
1320
1321 /**
1322 * Compares two strings lexicographically.
1323 * The comparison is based on the Unicode value of each character in
1324 * the strings. The character sequence represented by this
1325 * {@code String} object is compared lexicographically to the
1326 * character sequence represented by the argument string. The result is
1327 * a negative integer if this {@code String} object
1328 * lexicographically precedes the argument string. The result is a
1329 * positive integer if this {@code String} object lexicographically
1330 * follows the argument string. The result is zero if the strings
1331 * are equal; {@code compareTo} returns {@code 0} exactly when
1332 * the {@link #equals(Object)} method would return {@code true}.
1333 * <p>
1334 * This is the definition of lexicographic ordering. If two strings are
1335 * different, then either they have different characters at some index
1336 * that is a valid index for both strings, or their lengths are different,
1337 * or both. If they have different characters at one or more index
1338 * positions, let <i>k</i> be the smallest such index; then the string
1339 * whose character at position <i>k</i> has the smaller value, as
1340 * determined by using the < operator, lexicographically precedes the
1341 * other string. In this case, {@code compareTo} returns the
1342 * difference of the two character values at position {@code k} in
1343 * the two string -- that is, the value:
1344 * <blockquote><pre>
1345 * this.charAt(k)-anotherString.charAt(k)
1346 * </pre></blockquote>
1347 * If there is no index position at which they differ, then the shorter
1348 * string lexicographically precedes the longer string. In this case,
1349 * {@code compareTo} returns the difference of the lengths of the
1350 * strings -- that is, the value:
1351 * <blockquote><pre>
1352 * this.length()-anotherString.length()
1353 * </pre></blockquote>
1354 *
1355 * @param anotherString the {@code String} to be compared.
1356 * @return the value {@code 0} if the argument string is equal to
1357 * this string; a value less than {@code 0} if this string
1358 * is lexicographically less than the string argument; and a
1359 * value greater than {@code 0} if this string is
1360 * lexicographically greater than the string argument.
1361 */
1362 public int compareTo(String anotherString) {
1363 int len1 = value.length;
1364 int len2 = anotherString.value.length;
1365 int lim = Math.min(len1, len2);
1366 char v1[] = value;
1367 char v2[] = anotherString.value;
1368
1369 int k = 0;
1370 while (k < lim) {
1371 char c1 = v1[k];
1372 char c2 = v2[k];
1373 if (c1 != c2) {
1374 return c1 - c2;
1375 }
1376 k++;
1377 }
1378 return len1 - len2;
1379 }
1380
1381 /**
1382 * A Comparator that orders {@code String} objects as by
1383 * {@code compareToIgnoreCase}. This comparator is serializable.
1384 * <p>
1385 * Note that this Comparator does <em>not</em> take locale into account,
1386 * and will result in an unsatisfactory ordering for certain locales.
1387 * The java.text package provides <em>Collators</em> to allow
1388 * locale-sensitive ordering.
1389 *
1390 * @see java.text.Collator#compare(String, String)
1391 * @since 1.2
1392 */
1393 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1394 = new CaseInsensitiveComparator();
1395 private static class CaseInsensitiveComparator
1396 implements Comparator<String>, java.io.Serializable {
1397 // use serialVersionUID from JDK 1.2.2 for interoperability
1398 private static final long serialVersionUID = 8575799808933029326L;
1399
1400 public int compare(String s1, String s2) {
1401 int n1 = s1.length();
1402 int n2 = s2.length();
1403 int min = Math.min(n1, n2);
1404 for (int i = 0; i < min; i++) {
1405 char c1 = s1.charAt(i);
1406 char c2 = s2.charAt(i);
1407 if (c1 != c2) {
1408 c1 = Character.toUpperCase(c1);
1409 c2 = Character.toUpperCase(c2);
1410 if (c1 != c2) {
1411 c1 = Character.toLowerCase(c1);
1412 c2 = Character.toLowerCase(c2);
1413 if (c1 != c2) {
1414 // No overflow because of numeric promotion
1415 return c1 - c2;
1416 }
1417 }
1418 }
1419 }
1420 return n1 - n2;
1421 }
1422
1423 /** Replaces the de-serialized object. */
1424 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1425 }
1426
1427 /**
1428 * Compares two strings lexicographically, ignoring case
1429 * differences. This method returns an integer whose sign is that of
1430 * calling {@code compareTo} with normalized versions of the strings
1431 * where case differences have been eliminated by calling
1432 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1433 * each character.
1434 * <p>
1435 * Note that this method does <em>not</em> take locale into account,
1436 * and will result in an unsatisfactory ordering for certain locales.
1437 * The java.text package provides <em>collators</em> to allow
1438 * locale-sensitive ordering.
1439 *
1440 * @param str the {@code String} to be compared.
1441 * @return a negative integer, zero, or a positive integer as the
1442 * specified String is greater than, equal to, or less
1443 * than this String, ignoring case considerations.
1444 * @see java.text.Collator#compare(String, String)
1445 * @since 1.2
1446 */
1447 public int compareToIgnoreCase(String str) {
1448 return CASE_INSENSITIVE_ORDER.compare(this, str);
1449 }
1450
1451 /**
1452 * Tests if two string regions are equal.
1453 * <p>
1454 * A substring of this {@code String} object is compared to a substring
1455 * of the argument other. The result is true if these substrings
1456 * represent identical character sequences. The substring of this
1457 * {@code String} object to be compared begins at index {@code toffset}
1458 * and has length {@code len}. The substring of other to be compared
1459 * begins at index {@code ooffset} and has length {@code len}. The
1460 * result is {@code false} if and only if at least one of the following
1461 * is true:
1462 * <ul><li>{@code toffset} is negative.
1463 * <li>{@code ooffset} is negative.
1464 * <li>{@code toffset+len} is greater than the length of this
1465 * {@code String} object.
1466 * <li>{@code ooffset+len} is greater than the length of the other
1467 * argument.
1468 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1469 * such that:
1470 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1471 * <i>k</i>{@code )}
1472 * </ul>
1473 *
1474 * @param toffset the starting offset of the subregion in this string.
1475 * @param other the string argument.
1476 * @param ooffset the starting offset of the subregion in the string
1477 * argument.
1478 * @param len the number of characters to compare.
1479 * @return {@code true} if the specified subregion of this string
1480 * exactly matches the specified subregion of the string argument;
1481 * {@code false} otherwise.
1482 */
1483 public boolean regionMatches(int toffset, String other, int ooffset,
1484 int len) {
1485 char ta[] = value;
1486 int to = toffset;
1487 char pa[] = other.value;
1488 int po = ooffset;
1489 // Note: toffset, ooffset, or len might be near -1>>>1.
1490 if ((ooffset < 0) || (toffset < 0)
1491 || (toffset > (long)value.length - len)
1492 || (ooffset > (long)other.value.length - len)) {
1493 return false;
1494 }
1495 while (len-- > 0) {
1496 if (ta[to++] != pa[po++]) {
1497 return false;
1498 }
1499 }
1500 return true;
1501 }
1502
1503 /**
1504 * Tests if two string regions are equal.
1505 * <p>
1506 * A substring of this {@code String} object is compared to a substring
1507 * of the argument {@code other}. The result is {@code true} if these
1508 * substrings represent character sequences that are the same, ignoring
1509 * case if and only if {@code ignoreCase} is true. The substring of
1510 * this {@code String} object to be compared begins at index
1511 * {@code toffset} and has length {@code len}. The substring of
1512 * {@code other} to be compared begins at index {@code ooffset} and
1513 * has length {@code len}. The result is {@code false} if and only if
1514 * at least one of the following is true:
1515 * <ul><li>{@code toffset} is negative.
1516 * <li>{@code ooffset} is negative.
1517 * <li>{@code toffset+len} is greater than the length of this
1518 * {@code String} object.
1519 * <li>{@code ooffset+len} is greater than the length of the other
1520 * argument.
1521 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1522 * integer <i>k</i> less than {@code len} such that:
1523 * <blockquote><pre>
1524 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1525 * </pre></blockquote>
1526 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1527 * integer <i>k</i> less than {@code len} such that:
1528 * <blockquote><pre>
1529 * Character.toLowerCase(this.charAt(toffset+k)) !=
1530 Character.toLowerCase(other.charAt(ooffset+k))
1531 * </pre></blockquote>
1532 * and:
1533 * <blockquote><pre>
1534 * Character.toUpperCase(this.charAt(toffset+k)) !=
1535 * Character.toUpperCase(other.charAt(ooffset+k))
1536 * </pre></blockquote>
1537 * </ul>
1538 *
1539 * @param ignoreCase if {@code true}, ignore case when comparing
1540 * characters.
1541 * @param toffset the starting offset of the subregion in this
1542 * string.
1543 * @param other the string argument.
1544 * @param ooffset the starting offset of the subregion in the string
1545 * argument.
1546 * @param len the number of characters to compare.
1547 * @return {@code true} if the specified subregion of this string
1548 * matches the specified subregion of the string argument;
1549 * {@code false} otherwise. Whether the matching is exact
1550 * or case insensitive depends on the {@code ignoreCase}
1551 * argument.
1552 */
1553 public boolean regionMatches(boolean ignoreCase, int toffset,
1554 String other, int ooffset, int len) {
1555 char ta[] = value;
1556 int to = toffset;
1557 char pa[] = other.value;
1558 int po = ooffset;
1559 // Note: toffset, ooffset, or len might be near -1>>>1.
1560 if ((ooffset < 0) || (toffset < 0)
1561 || (toffset > (long)value.length - len)
1562 || (ooffset > (long)other.value.length - len)) {
1563 return false;
1564 }
1565 while (len-- > 0) {
1566 char c1 = ta[to++];
1567 char c2 = pa[po++];
1568 if (c1 == c2) {
1569 continue;
1570 }
1571 if (ignoreCase) {
1572 // If characters don't match but case may be ignored,
1573 // try converting both characters to uppercase.
1574 // If the results match, then the comparison scan should
1575 // continue.
1576 char u1 = Character.toUpperCase(c1);
1577 char u2 = Character.toUpperCase(c2);
1578 if (u1 == u2) {
1579 continue;
1580 }
1581 // Unfortunately, conversion to uppercase does not work properly
1582 // for the Georgian alphabet, which has strange rules about case
1583 // conversion. So we need to make one last check before
1584 // exiting.
1585 if (Character.toLowerCase(u1) == Character.toLowerCase(u2)) {
1586 continue;
1587 }
1588 }
1589 return false;
1590 }
1591 return true;
1592 }
1593
1594 /**
1595 * Tests if the substring of this string beginning at the
1596 * specified index starts with the specified prefix.
1597 *
1598 * @param prefix the prefix.
1599 * @param toffset where to begin looking in this string.
1600 * @return {@code true} if the character sequence represented by the
1601 * argument is a prefix of the substring of this object starting
1602 * at index {@code toffset}; {@code false} otherwise.
1603 * The result is {@code false} if {@code toffset} is
1604 * negative or greater than the length of this
1605 * {@code String} object; otherwise the result is the same
1606 * as the result of the expression
1607 * <pre>
1608 * this.substring(toffset).startsWith(prefix)
1609 * </pre>
1610 */
1611 public boolean startsWith(String prefix, int toffset) {
1612 char ta[] = value;
1613 int to = toffset;
1614 char pa[] = prefix.value;
1615 int po = 0;
1616 int pc = prefix.value.length;
1617 // Note: toffset might be near -1>>>1.
1618 if ((toffset < 0) || (toffset > value.length - pc)) {
1619 return false;
1620 }
1621 while (--pc >= 0) {
1622 if (ta[to++] != pa[po++]) {
1623 return false;
1624 }
1625 }
1626 return true;
1627 }
1628
1629 /**
1630 * Tests if this string starts with the specified prefix.
1631 *
1632 * @param prefix the prefix.
1633 * @return {@code true} if the character sequence represented by the
1634 * argument is a prefix of the character sequence represented by
1635 * this string; {@code false} otherwise.
1636 * Note also that {@code true} will be returned if the
1637 * argument is an empty string or is equal to this
1638 * {@code String} object as determined by the
1639 * {@link #equals(Object)} method.
1640 * @since 1.0
1641 */
1642 public boolean startsWith(String prefix) {
1643 return startsWith(prefix, 0);
1644 }
1645
1646 /**
1647 * Tests if this string ends with the specified suffix.
1648 *
1649 * @param suffix the suffix.
1650 * @return {@code true} if the character sequence represented by the
1651 * argument is a suffix of the character sequence represented by
1652 * this object; {@code false} otherwise. Note that the
1653 * result will be {@code true} if the argument is the
1654 * empty string or is equal to this {@code String} object
1655 * as determined by the {@link #equals(Object)} method.
1656 */
1657 public boolean endsWith(String suffix) {
1658 return startsWith(suffix, value.length - suffix.value.length);
1659 }
1660
1661 /**
1662 * Returns a hash code for this string. The hash code for a
1663 * {@code String} object is computed as
1664 * <blockquote><pre>
1665 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1666 * </pre></blockquote>
1667 * using {@code int} arithmetic, where {@code s[i]} is the
1668 * <i>i</i>th character of the string, {@code n} is the length of
1669 * the string, and {@code ^} indicates exponentiation.
1670 * (The hash value of the empty string is zero.)
1671 *
1672 * @return a hash code value for this object.
1673 */
1674 public int hashCode() {
1675 int h = hash;
1676 if (h == 0) {
1677 for (char v : value) {
1678 h = 31 * h + v;
1679 }
1680 hash = h;
1681 }
1682 return h;
1683 }
1684
1685 /**
1686 * Returns the index within this string of the first occurrence of
1687 * the specified character. If a character with value
1688 * {@code ch} occurs in the character sequence represented by
1689 * this {@code String} object, then the index (in Unicode
1690 * code units) of the first such occurrence is returned. For
1691 * values of {@code ch} in the range from 0 to 0xFFFF
1692 * (inclusive), this is the smallest value <i>k</i> such that:
1693 * <blockquote><pre>
1694 * this.charAt(<i>k</i>) == ch
1695 * </pre></blockquote>
1696 * is true. For other values of {@code ch}, it is the
1697 * smallest value <i>k</i> such that:
1698 * <blockquote><pre>
1699 * this.codePointAt(<i>k</i>) == ch
1700 * </pre></blockquote>
1701 * is true. In either case, if no such character occurs in this
1702 * string, then {@code -1} is returned.
1703 *
1704 * @param ch a character (Unicode code point).
1705 * @return the index of the first occurrence of the character in the
1706 * character sequence represented by this object, or
1707 * {@code -1} if the character does not occur.
1708 */
1709 public int indexOf(int ch) {
1710 return indexOf(ch, 0);
1711 }
1712
1713 /**
1714 * Returns the index within this string of the first occurrence of the
1715 * specified character, starting the search at the specified index.
1716 * <p>
1717 * If a character with value {@code ch} occurs in the
1718 * character sequence represented by this {@code String}
1719 * object at an index no smaller than {@code fromIndex}, then
1720 * the index of the first such occurrence is returned. For values
1721 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1722 * this is the smallest value <i>k</i> such that:
1723 * <blockquote><pre>
1724 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1725 * </pre></blockquote>
1726 * is true. For other values of {@code ch}, it is the
1727 * smallest value <i>k</i> such that:
1728 * <blockquote><pre>
1729 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1730 * </pre></blockquote>
1731 * is true. In either case, if no such character occurs in this
1732 * string at or after position {@code fromIndex}, then
1733 * {@code -1} is returned.
1734 *
1735 * <p>
1736 * There is no restriction on the value of {@code fromIndex}. If it
1737 * is negative, it has the same effect as if it were zero: this entire
1738 * string may be searched. If it is greater than the length of this
1739 * string, it has the same effect as if it were equal to the length of
1740 * this string: {@code -1} is returned.
1741 *
1742 * <p>All indices are specified in {@code char} values
1743 * (Unicode code units).
1744 *
1745 * @param ch a character (Unicode code point).
1746 * @param fromIndex the index to start the search from.
1747 * @return the index of the first occurrence of the character in the
1748 * character sequence represented by this object that is greater
1749 * than or equal to {@code fromIndex}, or {@code -1}
1750 * if the character does not occur.
1751 */
1752 public int indexOf(int ch, int fromIndex) {
1753 final int max = value.length;
1754 if (fromIndex < 0) {
1755 fromIndex = 0;
1756 } else if (fromIndex >= max) {
1757 // Note: fromIndex might be near -1>>>1.
1758 return -1;
1759 }
1760
1761 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1762 // handle most cases here (ch is a BMP code point or a
1763 // negative value (invalid code point))
1764 final char[] value = this.value;
1765 for (int i = fromIndex; i < max; i++) {
1766 if (value[i] == ch) {
1767 return i;
1768 }
1769 }
1770 return -1;
1771 } else {
1772 return indexOfSupplementary(ch, fromIndex);
1773 }
1774 }
1775
1776 /**
1777 * Handles (rare) calls of indexOf with a supplementary character.
1778 */
1779 private int indexOfSupplementary(int ch, int fromIndex) {
1780 if (Character.isValidCodePoint(ch)) {
1781 final char[] value = this.value;
1782 final char hi = Character.highSurrogate(ch);
1783 final char lo = Character.lowSurrogate(ch);
1784 final int max = value.length - 1;
1785 for (int i = fromIndex; i < max; i++) {
1786 if (value[i] == hi && value[i + 1] == lo) {
1787 return i;
1788 }
1789 }
1790 }
1791 return -1;
1792 }
1793
1794 /**
1795 * Returns the index within this string of the last occurrence of
1796 * the specified character. For values of {@code ch} in the
1797 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1798 * units) returned is the largest value <i>k</i> such that:
1799 * <blockquote><pre>
1800 * this.charAt(<i>k</i>) == ch
1801 * </pre></blockquote>
1802 * is true. For other values of {@code ch}, it is the
1803 * largest value <i>k</i> such that:
1804 * <blockquote><pre>
1805 * this.codePointAt(<i>k</i>) == ch
1806 * </pre></blockquote>
1807 * is true. In either case, if no such character occurs in this
1808 * string, then {@code -1} is returned. The
1809 * {@code String} is searched backwards starting at the last
1810 * character.
1811 *
1812 * @param ch a character (Unicode code point).
1813 * @return the index of the last occurrence of the character in the
1814 * character sequence represented by this object, or
1815 * {@code -1} if the character does not occur.
1816 */
1817 public int lastIndexOf(int ch) {
1818 return lastIndexOf(ch, value.length - 1);
1819 }
1820
1821 /**
1822 * Returns the index within this string of the last occurrence of
1823 * the specified character, searching backward starting at the
1824 * specified index. For values of {@code ch} in the range
1825 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1826 * value <i>k</i> such that:
1827 * <blockquote><pre>
1828 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1829 * </pre></blockquote>
1830 * is true. For other values of {@code ch}, it is the
1831 * largest value <i>k</i> such that:
1832 * <blockquote><pre>
1833 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1834 * </pre></blockquote>
1835 * is true. In either case, if no such character occurs in this
1836 * string at or before position {@code fromIndex}, then
1837 * {@code -1} is returned.
1838 *
1839 * <p>All indices are specified in {@code char} values
1840 * (Unicode code units).
1841 *
1842 * @param ch a character (Unicode code point).
1843 * @param fromIndex the index to start the search from. There is no
1844 * restriction on the value of {@code fromIndex}. If it is
1845 * greater than or equal to the length of this string, it has
1846 * the same effect as if it were equal to one less than the
1847 * length of this string: this entire string may be searched.
1848 * If it is negative, it has the same effect as if it were -1:
1849 * -1 is returned.
1850 * @return the index of the last occurrence of the character in the
1851 * character sequence represented by this object that is less
1852 * than or equal to {@code fromIndex}, or {@code -1}
1853 * if the character does not occur before that point.
1854 */
1855 public int lastIndexOf(int ch, int fromIndex) {
1856 if (ch < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
1857 // handle most cases here (ch is a BMP code point or a
1858 // negative value (invalid code point))
1859 final char[] value = this.value;
1860 int i = Math.min(fromIndex, value.length - 1);
1861 for (; i >= 0; i--) {
1862 if (value[i] == ch) {
1863 return i;
1864 }
1865 }
1866 return -1;
1867 } else {
1868 return lastIndexOfSupplementary(ch, fromIndex);
1869 }
1870 }
1871
1872 /**
1873 * Handles (rare) calls of lastIndexOf with a supplementary character.
1874 */
1875 private int lastIndexOfSupplementary(int ch, int fromIndex) {
1876 if (Character.isValidCodePoint(ch)) {
1877 final char[] value = this.value;
1878 char hi = Character.highSurrogate(ch);
1879 char lo = Character.lowSurrogate(ch);
1880 int i = Math.min(fromIndex, value.length - 2);
1881 for (; i >= 0; i--) {
1882 if (value[i] == hi && value[i + 1] == lo) {
1883 return i;
1884 }
1885 }
1886 }
1887 return -1;
1888 }
1889
1890 /**
1891 * Returns the index within this string of the first occurrence of the
1892 * specified substring.
1893 *
1894 * <p>The returned index is the smallest value {@code k} for which:
1895 * <pre>{@code
1896 * this.startsWith(str, k)
1897 * }</pre>
1898 * If no such value of {@code k} exists, then {@code -1} is returned.
1899 *
1900 * @param str the substring to search for.
1901 * @return the index of the first occurrence of the specified substring,
1902 * or {@code -1} if there is no such occurrence.
1903 */
1904 public int indexOf(String str) {
1905 return indexOf(str, 0);
1906 }
1907
1908 /**
1909 * Returns the index within this string of the first occurrence of the
1910 * specified substring, starting at the specified index.
1911 *
1912 * <p>The returned index is the smallest value {@code k} for which:
1913 * <pre>{@code
1914 * k >= Math.min(fromIndex, this.length()) &&
1915 * this.startsWith(str, k)
1916 * }</pre>
1917 * If no such value of {@code k} exists, then {@code -1} is returned.
1918 *
1919 * @param str the substring to search for.
1920 * @param fromIndex the index from which to start the search.
1921 * @return the index of the first occurrence of the specified substring,
1922 * starting at the specified index,
1923 * or {@code -1} if there is no such occurrence.
1924 */
1925 public int indexOf(String str, int fromIndex) {
1926 return indexOf(value, 0, value.length,
1927 str.value, 0, str.value.length, fromIndex);
1928 }
1929
1930 /**
1931 * Code shared by String and AbstractStringBuilder to do searches. The
1932 * source is the character array being searched, and the target
1933 * is the string being searched for.
1934 *
1935 * @param source the characters being searched.
1936 * @param sourceOffset offset of the source string.
1937 * @param sourceCount count of the source string.
1938 * @param target the characters being searched for.
1939 * @param fromIndex the index to begin searching from.
1940 */
1941 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1942 String target, int fromIndex) {
1943 return indexOf(source, sourceOffset, sourceCount,
1944 target.value, 0, target.value.length,
1945 fromIndex);
1946 }
1947
1948 /**
1949 * Code shared by String and StringBuffer to do searches. The
1950 * source is the character array being searched, and the target
1951 * is the string being searched for.
1952 *
1953 * @param source the characters being searched.
1954 * @param sourceOffset offset of the source string.
1955 * @param sourceCount count of the source string.
1956 * @param target the characters being searched for.
1957 * @param targetOffset offset of the target string.
1958 * @param targetCount count of the target string.
1959 * @param fromIndex the index to begin searching from.
1960 */
1961 static int indexOf(char[] source, int sourceOffset, int sourceCount,
1962 char[] target, int targetOffset, int targetCount,
1963 int fromIndex) {
1964 if (fromIndex >= sourceCount) {
1965 return (targetCount == 0 ? sourceCount : -1);
1966 }
1967 if (fromIndex < 0) {
1968 fromIndex = 0;
1969 }
1970 if (targetCount == 0) {
1971 return fromIndex;
1972 }
1973
1974 char first = target[targetOffset];
1975 int max = sourceOffset + (sourceCount - targetCount);
1976
1977 for (int i = sourceOffset + fromIndex; i <= max; i++) {
1978 /* Look for first character. */
1979 if (source[i] != first) {
1980 while (++i <= max && source[i] != first);
1981 }
1982
1983 /* Found first character, now look at the rest of v2 */
1984 if (i <= max) {
1985 int j = i + 1;
1986 int end = j + targetCount - 1;
1987 for (int k = targetOffset + 1; j < end && source[j]
1988 == target[k]; j++, k++);
1989
1990 if (j == end) {
1991 /* Found whole string. */
1992 return i - sourceOffset;
1993 }
1994 }
1995 }
1996 return -1;
1997 }
1998
1999 /**
2000 * Returns the index within this string of the last occurrence of the
2001 * specified substring. The last occurrence of the empty string ""
2002 * is considered to occur at the index value {@code this.length()}.
2003 *
2004 * <p>The returned index is the largest value {@code k} for which:
2005 * <pre>{@code
2006 * this.startsWith(str, k)
2007 * }</pre>
2008 * If no such value of {@code k} exists, then {@code -1} is returned.
2009 *
2010 * @param str the substring to search for.
2011 * @return the index of the last occurrence of the specified substring,
2012 * or {@code -1} if there is no such occurrence.
2013 */
2014 public int lastIndexOf(String str) {
2015 return lastIndexOf(str, value.length);
2016 }
2017
2018 /**
2019 * Returns the index within this string of the last occurrence of the
2020 * specified substring, searching backward starting at the specified index.
2021 *
2022 * <p>The returned index is the largest value {@code k} for which:
2023 * <pre>{@code
2024 * k <= Math.min(fromIndex, this.length()) &&
2025 * this.startsWith(str, k)
2026 * }</pre>
2027 * If no such value of {@code k} exists, then {@code -1} is returned.
2028 *
2029 * @param str the substring to search for.
2030 * @param fromIndex the index to start the search from.
2031 * @return the index of the last occurrence of the specified substring,
2032 * searching backward from the specified index,
2033 * or {@code -1} if there is no such occurrence.
2034 */
2035 public int lastIndexOf(String str, int fromIndex) {
2036 return lastIndexOf(value, 0, value.length,
2037 str.value, 0, str.value.length, fromIndex);
2038 }
2039
2040 /**
2041 * Code shared by String and AbstractStringBuilder to do searches. The
2042 * source is the character array being searched, and the target
2043 * is the string being searched for.
2044 *
2045 * @param source the characters being searched.
2046 * @param sourceOffset offset of the source string.
2047 * @param sourceCount count of the source string.
2048 * @param target the characters being searched for.
2049 * @param fromIndex the index to begin searching from.
2050 */
2051 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
2052 String target, int fromIndex) {
2053 return lastIndexOf(source, sourceOffset, sourceCount,
2054 target.value, 0, target.value.length,
2055 fromIndex);
2056 }
2057
2058 /**
2059 * Code shared by String and StringBuffer to do searches. The
2060 * source is the character array being searched, and the target
2061 * is the string being searched for.
2062 *
2063 * @param source the characters being searched.
2064 * @param sourceOffset offset of the source string.
2065 * @param sourceCount count of the source string.
2066 * @param target the characters being searched for.
2067 * @param targetOffset offset of the target string.
2068 * @param targetCount count of the target string.
2069 * @param fromIndex the index to begin searching from.
2070 */
2071 static int lastIndexOf(char[] source, int sourceOffset, int sourceCount,
2072 char[] target, int targetOffset, int targetCount,
2073 int fromIndex) {
2074 /*
2075 * Check arguments; return immediately where possible. For
2076 * consistency, don't check for null str.
2077 */
2078 int rightIndex = sourceCount - targetCount;
2079 if (fromIndex < 0) {
2080 return -1;
2081 }
2082 if (fromIndex > rightIndex) {
2083 fromIndex = rightIndex;
2084 }
2085 /* Empty string always matches. */
2086 if (targetCount == 0) {
2087 return fromIndex;
2088 }
2089
2090 int strLastIndex = targetOffset + targetCount - 1;
2091 char strLastChar = target[strLastIndex];
2092 int min = sourceOffset + targetCount - 1;
2093 int i = min + fromIndex;
2094
2095 startSearchForLastChar:
2096 while (true) {
2097 while (i >= min && source[i] != strLastChar) {
2098 i--;
2099 }
2100 if (i < min) {
2101 return -1;
2102 }
2103 int j = i - 1;
2104 int start = j - (targetCount - 1);
2105 int k = strLastIndex - 1;
2106
2107 while (j > start) {
2108 if (source[j--] != target[k--]) {
2109 i--;
2110 continue startSearchForLastChar;
2111 }
2112 }
2113 return start - sourceOffset + 1;
2114 }
2115 }
2116
2117 /**
2118 * Returns a string that is a substring of this string. The
2119 * substring begins with the character at the specified index and
2120 * extends to the end of this string. <p>
2121 * Examples:
2122 * <blockquote><pre>
2123 * "unhappy".substring(2) returns "happy"
2124 * "Harbison".substring(3) returns "bison"
2125 * "emptiness".substring(9) returns "" (an empty string)
2126 * </pre></blockquote>
2127 *
2128 * @param beginIndex the beginning index, inclusive.
2129 * @return the specified substring.
2130 * @exception IndexOutOfBoundsException if
2131 * {@code beginIndex} is negative or larger than the
2132 * length of this {@code String} object.
2133 */
2134 public String substring(int beginIndex) {
2135 if (beginIndex < 0) {
2136 throw new StringIndexOutOfBoundsException(beginIndex);
2137 }
2138 int subLen = value.length - beginIndex;
2139 if (subLen < 0) {
2140 throw new StringIndexOutOfBoundsException(subLen);
2141 }
2142 return (beginIndex == 0) ? this : new String(value, beginIndex, subLen);
2143 }
2144
2145 /**
2146 * Returns a string that is a substring of this string. The
2147 * substring begins at the specified {@code beginIndex} and
2148 * extends to the character at index {@code endIndex - 1}.
2149 * Thus the length of the substring is {@code endIndex-beginIndex}.
2150 * <p>
2151 * Examples:
2152 * <blockquote><pre>
2153 * "hamburger".substring(4, 8) returns "urge"
2154 * "smiles".substring(1, 5) returns "mile"
2155 * </pre></blockquote>
2156 *
2157 * @param beginIndex the beginning index, inclusive.
2158 * @param endIndex the ending index, exclusive.
2159 * @return the specified substring.
2160 * @exception IndexOutOfBoundsException if the
2161 * {@code beginIndex} is negative, or
2162 * {@code endIndex} is larger than the length of
2163 * this {@code String} object, or
2164 * {@code beginIndex} is larger than
2165 * {@code endIndex}.
2166 */
2167 public String substring(int beginIndex, int endIndex) {
2168 if (beginIndex < 0) {
2169 throw new StringIndexOutOfBoundsException(beginIndex);
2170 }
2171 if (endIndex > value.length) {
2172 throw new StringIndexOutOfBoundsException(endIndex);
2173 }
2174 int subLen = endIndex - beginIndex;
2175 if (subLen < 0) {
2176 throw new StringIndexOutOfBoundsException(subLen);
2177 }
2178 return ((beginIndex == 0) && (endIndex == value.length)) ? this
2179 : new String(value, beginIndex, subLen);
2180 }
2181
2182 /**
2183 * Returns a character sequence that is a subsequence of this sequence.
2184 *
2185 * <p> An invocation of this method of the form
2186 *
2187 * <blockquote><pre>
2188 * str.subSequence(begin, end)</pre></blockquote>
2189 *
2190 * behaves in exactly the same way as the invocation
2191 *
2192 * <blockquote><pre>
2193 * str.substring(begin, end)</pre></blockquote>
2194 *
2195 * @apiNote
2196 * This method is defined so that the {@code String} class can implement
2197 * the {@link CharSequence} interface.
2198 *
2199 * @param beginIndex the begin index, inclusive.
2200 * @param endIndex the end index, exclusive.
2201 * @return the specified subsequence.
2202 *
2203 * @throws IndexOutOfBoundsException
2204 * if {@code beginIndex} or {@code endIndex} is negative,
2205 * if {@code endIndex} is greater than {@code length()},
2206 * or if {@code beginIndex} is greater than {@code endIndex}
2207 *
2208 * @since 1.4
2209 * @spec JSR-51
2210 */
2211 public CharSequence subSequence(int beginIndex, int endIndex) {
2212 return this.substring(beginIndex, endIndex);
2213 }
2214
2215 /**
2216 * Concatenates the specified string to the end of this string.
2217 * <p>
2218 * If the length of the argument string is {@code 0}, then this
2219 * {@code String} object is returned. Otherwise, a
2220 * {@code String} object is returned that represents a character
2221 * sequence that is the concatenation of the character sequence
2222 * represented by this {@code String} object and the character
2223 * sequence represented by the argument string.<p>
2224 * Examples:
2225 * <blockquote><pre>
2226 * "cares".concat("s") returns "caress"
2227 * "to".concat("get").concat("her") returns "together"
2228 * </pre></blockquote>
2229 *
2230 * @param str the {@code String} that is concatenated to the end
2231 * of this {@code String}.
2232 * @return a string that represents the concatenation of this object's
2233 * characters followed by the string argument's characters.
2234 */
2235 public String concat(String str) {
2236 int otherLen = str.length();
2237 if (otherLen == 0) {
2238 return this;
2239 }
2240 int len = value.length;
2241 char buf[] = Arrays.copyOf(value, len + otherLen);
2242 str.getChars(buf, len);
2243 return new String(buf, true);
2244 }
2245
2246 /**
2247 * Returns a string resulting from replacing all occurrences of
2248 * {@code oldChar} in this string with {@code newChar}.
2249 * <p>
2250 * If the character {@code oldChar} does not occur in the
2251 * character sequence represented by this {@code String} object,
2252 * then a reference to this {@code String} object is returned.
2253 * Otherwise, a {@code String} object is returned that
2254 * represents a character sequence identical to the character sequence
2255 * represented by this {@code String} object, except that every
2256 * occurrence of {@code oldChar} is replaced by an occurrence
2257 * of {@code newChar}.
2258 * <p>
2259 * Examples:
2260 * <blockquote><pre>
2261 * "mesquite in your cellar".replace('e', 'o')
2262 * returns "mosquito in your collar"
2263 * "the war of baronets".replace('r', 'y')
2264 * returns "the way of bayonets"
2265 * "sparring with a purple porpoise".replace('p', 't')
2266 * returns "starring with a turtle tortoise"
2267 * "JonL".replace('q', 'x') returns "JonL" (no change)
2268 * </pre></blockquote>
2269 *
2270 * @param oldChar the old character.
2271 * @param newChar the new character.
2272 * @return a string derived from this string by replacing every
2273 * occurrence of {@code oldChar} with {@code newChar}.
2274 */
2275 public String replace(char oldChar, char newChar) {
2276 if (oldChar != newChar) {
2277 int len = value.length;
2278 int i = -1;
2279 char[] val = value; /* avoid getfield opcode */
2280
2281 while (++i < len) {
2282 if (val[i] == oldChar) {
2283 break;
2284 }
2285 }
2286 if (i < len) {
2287 char buf[] = new char[len];
2288 for (int j = 0; j < i; j++) {
2289 buf[j] = val[j];
2290 }
2291 while (i < len) {
2292 char c = val[i];
2293 buf[i] = (c == oldChar) ? newChar : c;
2294 i++;
2295 }
2296 return new String(buf, true);
2297 }
2298 }
2299 return this;
2300 }
2301
2302 /**
2303 * Tells whether or not this string matches the given <a
2304 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2305 *
2306 * <p> An invocation of this method of the form
2307 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2308 * same result as the expression
2309 *
2310 * <blockquote>
2311 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2312 * matches(<i>regex</i>, <i>str</i>)}
2313 * </blockquote>
2314 *
2315 * @param regex
2316 * the regular expression to which this string is to be matched
2317 *
2318 * @return {@code true} if, and only if, this string matches the
2319 * given regular expression
2320 *
2321 * @throws PatternSyntaxException
2322 * if the regular expression's syntax is invalid
2323 *
2324 * @see java.util.regex.Pattern
2325 *
2326 * @since 1.4
2327 * @spec JSR-51
2328 */
2329 public boolean matches(String regex) {
2330 return Pattern.matches(regex, this);
2331 }
2332
2333 /**
2334 * Returns true if and only if this string contains the specified
2335 * sequence of char values.
2336 *
2337 * @param s the sequence to search for
2338 * @return true if this string contains {@code s}, false otherwise
2339 * @since 1.5
2340 */
2341 public boolean contains(CharSequence s) {
2342 return indexOf(s.toString()) >= 0;
2343 }
2344
2345 /**
2346 * Replaces the first substring of this string that matches the given <a
2347 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2348 * given replacement.
2349 *
2350 * <p> An invocation of this method of the form
2351 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2352 * yields exactly the same result as the expression
2353 *
2354 * <blockquote>
2355 * <code>
2356 * {@link java.util.regex.Pattern}.{@link
2357 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2358 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2359 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2360 * </code>
2361 * </blockquote>
2362 *
2363 *<p>
2364 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2365 * replacement string may cause the results to be different than if it were
2366 * being treated as a literal replacement string; see
2367 * {@link java.util.regex.Matcher#replaceFirst}.
2368 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2369 * meaning of these characters, if desired.
2370 *
2371 * @param regex
2372 * the regular expression to which this string is to be matched
2373 * @param replacement
2374 * the string to be substituted for the first match
2375 *
2376 * @return The resulting {@code String}
2377 *
2378 * @throws PatternSyntaxException
2379 * if the regular expression's syntax is invalid
2380 *
2381 * @see java.util.regex.Pattern
2382 *
2383 * @since 1.4
2384 * @spec JSR-51
2385 */
2386 public String replaceFirst(String regex, String replacement) {
2387 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2388 }
2389
2390 /**
2391 * Replaces each substring of this string that matches the given <a
2392 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2393 * given replacement.
2394 *
2395 * <p> An invocation of this method of the form
2396 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2397 * yields exactly the same result as the expression
2398 *
2399 * <blockquote>
2400 * <code>
2401 * {@link java.util.regex.Pattern}.{@link
2402 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2403 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2404 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2405 * </code>
2406 * </blockquote>
2407 *
2408 *<p>
2409 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2410 * replacement string may cause the results to be different than if it were
2411 * being treated as a literal replacement string; see
2412 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2413 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2414 * meaning of these characters, if desired.
2415 *
2416 * @param regex
2417 * the regular expression to which this string is to be matched
2418 * @param replacement
2419 * the string to be substituted for each match
2420 *
2421 * @return The resulting {@code String}
2422 *
2423 * @throws PatternSyntaxException
2424 * if the regular expression's syntax is invalid
2425 *
2426 * @see java.util.regex.Pattern
2427 *
2428 * @since 1.4
2429 * @spec JSR-51
2430 */
2431 public String replaceAll(String regex, String replacement) {
2432 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2433 }
2434
2435 /**
2436 * Replaces each substring of this string that matches the literal target
2437 * sequence with the specified literal replacement sequence. The
2438 * replacement proceeds from the beginning of the string to the end, for
2439 * example, replacing "aa" with "b" in the string "aaa" will result in
2440 * "ba" rather than "ab".
2441 *
2442 * @param target The sequence of char values to be replaced
2443 * @param replacement The replacement sequence of char values
2444 * @return The resulting string
2445 * @since 1.5
2446 */
2447 public String replace(CharSequence target, CharSequence replacement) {
2448 return Pattern.compile(target.toString(), Pattern.LITERAL).matcher(
2449 this).replaceAll(Matcher.quoteReplacement(replacement.toString()));
2450 }
2451
2452 /**
2453 * Splits this string around matches of the given
2454 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2455 *
2456 * <p> The array returned by this method contains each substring of this
2457 * string that is terminated by another substring that matches the given
2458 * expression or is terminated by the end of the string. The substrings in
2459 * the array are in the order in which they occur in this string. If the
2460 * expression does not match any part of the input then the resulting array
2461 * has just one element, namely this string.
2462 *
2463 * <p> When there is a positive-width match at the beginning of this
2464 * string then an empty leading substring is included at the beginning
2465 * of the resulting array. A zero-width match at the beginning however
2466 * never produces such empty leading substring.
2467 *
2468 * <p> The {@code limit} parameter controls the number of times the
2469 * pattern is applied and therefore affects the length of the resulting
2470 * array. If the limit <i>n</i> is greater than zero then the pattern
2471 * will be applied at most <i>n</i> - 1 times, the array's
2472 * length will be no greater than <i>n</i>, and the array's last entry
2473 * will contain all input beyond the last matched delimiter. If <i>n</i>
2474 * is non-positive then the pattern will be applied as many times as
2475 * possible and the array can have any length. If <i>n</i> is zero then
2476 * the pattern will be applied as many times as possible, the array can
2477 * have any length, and trailing empty strings will be discarded.
2478 *
2479 * <p> The string {@code "boo:and:foo"}, for example, yields the
2480 * following results with these parameters:
2481 *
2482 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split example showing regex, limit, and result">
2483 * <tr>
2484 * <th>Regex</th>
2485 * <th>Limit</th>
2486 * <th>Result</th>
2487 * </tr>
2488 * <tr><td align=center>:</td>
2489 * <td align=center>2</td>
2490 * <td>{@code { "boo", "and:foo" }}</td></tr>
2491 * <tr><td align=center>:</td>
2492 * <td align=center>5</td>
2493 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2494 * <tr><td align=center>:</td>
2495 * <td align=center>-2</td>
2496 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2497 * <tr><td align=center>o</td>
2498 * <td align=center>5</td>
2499 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2500 * <tr><td align=center>o</td>
2501 * <td align=center>-2</td>
2502 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2503 * <tr><td align=center>o</td>
2504 * <td align=center>0</td>
2505 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2506 * </table></blockquote>
2507 *
2508 * <p> An invocation of this method of the form
2509 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2510 * yields the same result as the expression
2511 *
2512 * <blockquote>
2513 * <code>
2514 * {@link java.util.regex.Pattern}.{@link
2515 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2516 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2517 * </code>
2518 * </blockquote>
2519 *
2520 *
2521 * @param regex
2522 * the delimiting regular expression
2523 *
2524 * @param limit
2525 * the result threshold, as described above
2526 *
2527 * @return the array of strings computed by splitting this string
2528 * around matches of the given regular expression
2529 *
2530 * @throws PatternSyntaxException
2531 * if the regular expression's syntax is invalid
2532 *
2533 * @see java.util.regex.Pattern
2534 *
2535 * @since 1.4
2536 * @spec JSR-51
2537 */
2538 public String[] split(String regex, int limit) {
2539 /* fastpath if the regex is a
2540 (1)one-char String and this character is not one of the
2541 RegEx's meta characters ".$|()[{^?*+\\", or
2542 (2)two-char String and the first char is the backslash and
2543 the second is not the ascii digit or ascii letter.
2544 */
2545 char ch = 0;
2546 if (((regex.value.length == 1 &&
2547 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2548 (regex.length() == 2 &&
2549 regex.charAt(0) == '\\' &&
2550 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2551 ((ch-'a')|('z'-ch)) < 0 &&
2552 ((ch-'A')|('Z'-ch)) < 0)) &&
2553 (ch < Character.MIN_HIGH_SURROGATE ||
2554 ch > Character.MAX_LOW_SURROGATE))
2555 {
2556 int off = 0;
2557 int next = 0;
2558 boolean limited = limit > 0;
2559 ArrayList<String> list = new ArrayList<>();
2560 while ((next = indexOf(ch, off)) != -1) {
2561 if (!limited || list.size() < limit - 1) {
2562 list.add(substring(off, next));
2563 off = next + 1;
2564 } else { // last one
2565 //assert (list.size() == limit - 1);
2566 list.add(substring(off, value.length));
2567 off = value.length;
2568 break;
2569 }
2570 }
2571 // If no match was found, return this
2572 if (off == 0)
2573 return new String[]{this};
2574
2575 // Add remaining segment
2576 if (!limited || list.size() < limit)
2577 list.add(substring(off, value.length));
2578
2579 // Construct result
2580 int resultSize = list.size();
2581 if (limit == 0) {
2582 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2583 resultSize--;
2584 }
2585 }
2586 String[] result = new String[resultSize];
2587 return list.subList(0, resultSize).toArray(result);
2588 }
2589 return Pattern.compile(regex).split(this, limit);
2590 }
2591
2592 /**
2593 * Splits this string around matches of the given <a
2594 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2595 *
2596 * <p> This method works as if by invoking the two-argument {@link
2597 * #split(String, int) split} method with the given expression and a limit
2598 * argument of zero. Trailing empty strings are therefore not included in
2599 * the resulting array.
2600 *
2601 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2602 * results with these expressions:
2603 *
2604 * <blockquote><table cellpadding=1 cellspacing=0 summary="Split examples showing regex and result">
2605 * <tr>
2606 * <th>Regex</th>
2607 * <th>Result</th>
2608 * </tr>
2609 * <tr><td align=center>:</td>
2610 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2611 * <tr><td align=center>o</td>
2612 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2613 * </table></blockquote>
2614 *
2615 *
2616 * @param regex
2617 * the delimiting regular expression
2618 *
2619 * @return the array of strings computed by splitting this string
2620 * around matches of the given regular expression
2621 *
2622 * @throws PatternSyntaxException
2623 * if the regular expression's syntax is invalid
2624 *
2625 * @see java.util.regex.Pattern
2626 *
2627 * @since 1.4
2628 * @spec JSR-51
2629 */
2630 public String[] split(String regex) {
2631 return split(regex, 0);
2632 }
2633
2634 /**
2635 * Returns a new String composed of copies of the
2636 * {@code CharSequence elements} joined together with a copy of
2637 * the specified {@code delimiter}.
2638 *
2639 * <blockquote>For example,
2640 * <pre>{@code
2641 * String message = String.join("-", "Java", "is", "cool");
2642 * // message returned is: "Java-is-cool"
2643 * }</pre></blockquote>
2644 *
2645 * Note that if an element is null, then {@code "null"} is added.
2646 *
2647 * @param delimiter the delimiter that separates each element
2648 * @param elements the elements to join together.
2649 *
2650 * @return a new {@code String} that is composed of the {@code elements}
2651 * separated by the {@code delimiter}
2652 *
2653 * @throws NullPointerException If {@code delimiter} or {@code elements}
2654 * is {@code null}
2655 *
2656 * @see java.util.StringJoiner
2657 * @since 1.8
2658 */
2659 public static String join(CharSequence delimiter, CharSequence... elements) {
2660 Objects.requireNonNull(delimiter);
2661 Objects.requireNonNull(elements);
2662 // Number of elements not likely worth Arrays.stream overhead.
2663 StringJoiner joiner = new StringJoiner(delimiter);
2664 for (CharSequence cs: elements) {
2665 joiner.add(cs);
2666 }
2667 return joiner.toString();
2668 }
2669
2670 /**
2671 * Returns a new {@code String} composed of copies of the
2672 * {@code CharSequence elements} joined together with a copy of the
2673 * specified {@code delimiter}.
2674 *
2675 * <blockquote>For example,
2676 * <pre>{@code
2677 * List<String> strings = new LinkedList<>();
2678 * strings.add("Java");strings.add("is");
2679 * strings.add("cool");
2680 * String message = String.join(" ", strings);
2681 * //message returned is: "Java is cool"
2682 *
2683 * Set<String> strings = new LinkedHashSet<>();
2684 * strings.add("Java"); strings.add("is");
2685 * strings.add("very"); strings.add("cool");
2686 * String message = String.join("-", strings);
2687 * //message returned is: "Java-is-very-cool"
2688 * }</pre></blockquote>
2689 *
2690 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2691 *
2692 * @param delimiter a sequence of characters that is used to separate each
2693 * of the {@code elements} in the resulting {@code String}
2694 * @param elements an {@code Iterable} that will have its {@code elements}
2695 * joined together.
2696 *
2697 * @return a new {@code String} that is composed from the {@code elements}
2698 * argument
2699 *
2700 * @throws NullPointerException If {@code delimiter} or {@code elements}
2701 * is {@code null}
2702 *
2703 * @see #join(CharSequence,CharSequence...)
2704 * @see java.util.StringJoiner
2705 * @since 1.8
2706 */
2707 public static String join(CharSequence delimiter,
2708 Iterable<? extends CharSequence> elements) {
2709 Objects.requireNonNull(delimiter);
2710 Objects.requireNonNull(elements);
2711 StringJoiner joiner = new StringJoiner(delimiter);
2712 for (CharSequence cs: elements) {
2713 joiner.add(cs);
2714 }
2715 return joiner.toString();
2716 }
2717
2718 /**
2719 * Converts all of the characters in this {@code String} to lower
2720 * case using the rules of the given {@code Locale}. Case mapping is based
2721 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2722 * class. Since case mappings are not always 1:1 char mappings, the resulting
2723 * {@code String} may be a different length than the original {@code String}.
2724 * <p>
2725 * Examples of lowercase mappings are in the following table:
2726 * <table border="1" summary="Lowercase mapping examples showing language code of locale, upper case, lower case, and description">
2727 * <tr>
2728 * <th>Language Code of Locale</th>
2729 * <th>Upper Case</th>
2730 * <th>Lower Case</th>
2731 * <th>Description</th>
2732 * </tr>
2733 * <tr>
2734 * <td>tr (Turkish)</td>
2735 * <td>\u0130</td>
2736 * <td>\u0069</td>
2737 * <td>capital letter I with dot above -> small letter i</td>
2738 * </tr>
2739 * <tr>
2740 * <td>tr (Turkish)</td>
2741 * <td>\u0049</td>
2742 * <td>\u0131</td>
2743 * <td>capital letter I -> small letter dotless i </td>
2744 * </tr>
2745 * <tr>
2746 * <td>(all)</td>
2747 * <td>French Fries</td>
2748 * <td>french fries</td>
2749 * <td>lowercased all chars in String</td>
2750 * </tr>
2751 * <tr>
2752 * <td>(all)</td>
2753 * <td><img src="doc-files/capiota.gif" alt="capiota"><img src="doc-files/capchi.gif" alt="capchi">
2754 * <img src="doc-files/captheta.gif" alt="captheta"><img src="doc-files/capupsil.gif" alt="capupsil">
2755 * <img src="doc-files/capsigma.gif" alt="capsigma"></td>
2756 * <td><img src="doc-files/iota.gif" alt="iota"><img src="doc-files/chi.gif" alt="chi">
2757 * <img src="doc-files/theta.gif" alt="theta"><img src="doc-files/upsilon.gif" alt="upsilon">
2758 * <img src="doc-files/sigma1.gif" alt="sigma"></td>
2759 * <td>lowercased all chars in String</td>
2760 * </tr>
2761 * </table>
2762 *
2763 * @param locale use the case transformation rules for this locale
2764 * @return the {@code String}, converted to lowercase.
2765 * @see java.lang.String#toLowerCase()
2766 * @see java.lang.String#toUpperCase()
2767 * @see java.lang.String#toUpperCase(Locale)
2768 * @since 1.1
2769 */
2770 public String toLowerCase(Locale locale) {
2771 if (locale == null) {
2772 throw new NullPointerException();
2773 }
2774 int first;
2775 boolean hasSurr = false;
2776 final int len = value.length;
2777
2778 // Now check if there are any characters that need to be changed, or are surrogate
2779 for (first = 0 ; first < len; first++) {
2780 int cp = (int)value[first];
2781 if (Character.isSurrogate((char)cp)) {
2782 hasSurr = true;
2783 break;
2784 }
2785 if (cp != Character.toLowerCase(cp)) { // no need to check Character.ERROR
2786 break;
2787 }
2788 }
2789 if (first == len)
2790 return this;
2791 char[] result = new char[len];
2792 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2793 // lowerCase characters.
2794 String lang = locale.getLanguage();
2795 if (lang == "tr" || lang == "az" || lang == "lt") {
2796 return toLowerCaseEx(result, first, locale, true);
2797 }
2798 if (hasSurr) {
2799 return toLowerCaseEx(result, first, locale, false);
2800 }
2801 for (int i = first; i < len; i++) {
2802 int cp = (int)value[i];
2803 if (cp == '\u03A3' || // GREEK CAPITAL LETTER SIGMA
2804 Character.isSurrogate((char)cp)) {
2805 return toLowerCaseEx(result, i, locale, false);
2806 }
2807 if (cp == '\u0130') { // LATIN CAPITAL LETTER I WITH DOT ABOVE
2808 return toLowerCaseEx(result, i, locale, true);
2809 }
2810 cp = Character.toLowerCase(cp);
2811 if (!Character.isBmpCodePoint(cp)) {
2812 return toLowerCaseEx(result, i, locale, false);
2813 }
2814 result[i] = (char)cp;
2815 }
2816 return new String(result, true);
2817 }
2818
2819 private String toLowerCaseEx(char[] result, int first, Locale locale, boolean localeDependent) {
2820 int resultOffset = first;
2821 int srcCount;
2822 for (int i = first; i < value.length; i += srcCount) {
2823 int srcChar = (int)value[i];
2824 int lowerChar;
2825 char[] lowerCharArray;
2826 srcCount = 1;
2827 if (Character.isSurrogate((char)srcChar)) {
2828 srcChar = codePointAt(i);
2829 srcCount = Character.charCount(srcChar);
2830 }
2831 if (localeDependent || srcChar == '\u03A3') { // GREEK CAPITAL LETTER SIGMA
2832 lowerChar = ConditionalSpecialCasing.toLowerCaseEx(this, i, locale);
2833 } else {
2834 lowerChar = Character.toLowerCase(srcChar);
2835 }
2836 if (Character.isBmpCodePoint(lowerChar)) { // Character.ERROR is not a bmp
2837 result[resultOffset++] = (char)lowerChar;
2838 } else {
2839 if (lowerChar == Character.ERROR) {
2840 lowerCharArray = ConditionalSpecialCasing.toLowerCaseCharArray(this, i, locale);
2841 } else if (srcCount == 2) {
2842 resultOffset += Character.toChars(lowerChar, result, resultOffset);
2843 continue;
2844 } else {
2845 lowerCharArray = Character.toChars(lowerChar);
2846 }
2847 /* Grow result if needed */
2848 int mapLen = lowerCharArray.length;
2849 if (mapLen > srcCount) {
2850 char[] result2 = new char[result.length + mapLen - srcCount];
2851 System.arraycopy(result, 0, result2, 0, resultOffset);
2852 result = result2;
2853 }
2854 for (int x = 0; x < mapLen; ++x) {
2855 result[resultOffset++] = lowerCharArray[x];
2856 }
2857 }
2858 }
2859 return new String(result, 0, resultOffset);
2860 }
2861
2862 /**
2863 * Converts all of the characters in this {@code String} to lower
2864 * case using the rules of the default locale. This is equivalent to calling
2865 * {@code toLowerCase(Locale.getDefault())}.
2866 * <p>
2867 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2868 * results if used for strings that are intended to be interpreted locale
2869 * independently.
2870 * Examples are programming language identifiers, protocol keys, and HTML
2871 * tags.
2872 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2873 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2874 * LATIN SMALL LETTER DOTLESS I character.
2875 * To obtain correct results for locale insensitive strings, use
2876 * {@code toLowerCase(Locale.ROOT)}.
2877 *
2878 * @return the {@code String}, converted to lowercase.
2879 * @see java.lang.String#toLowerCase(Locale)
2880 */
2881 public String toLowerCase() {
2882 return toLowerCase(Locale.getDefault());
2883 }
2884
2885 /**
2886 * Converts all of the characters in this {@code String} to upper
2887 * case using the rules of the given {@code Locale}. Case mapping is based
2888 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2889 * class. Since case mappings are not always 1:1 char mappings, the resulting
2890 * {@code String} may be a different length than the original {@code String}.
2891 * <p>
2892 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2893 *
2894 * <table border="1" summary="Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.">
2895 * <tr>
2896 * <th>Language Code of Locale</th>
2897 * <th>Lower Case</th>
2898 * <th>Upper Case</th>
2899 * <th>Description</th>
2900 * </tr>
2901 * <tr>
2902 * <td>tr (Turkish)</td>
2903 * <td>\u0069</td>
2904 * <td>\u0130</td>
2905 * <td>small letter i -> capital letter I with dot above</td>
2906 * </tr>
2907 * <tr>
2908 * <td>tr (Turkish)</td>
2909 * <td>\u0131</td>
2910 * <td>\u0049</td>
2911 * <td>small letter dotless i -> capital letter I</td>
2912 * </tr>
2913 * <tr>
2914 * <td>(all)</td>
2915 * <td>\u00df</td>
2916 * <td>\u0053 \u0053</td>
2917 * <td>small letter sharp s -> two letters: SS</td>
2918 * </tr>
2919 * <tr>
2920 * <td>(all)</td>
2921 * <td>Fahrvergnügen</td>
2922 * <td>FAHRVERGNÜGEN</td>
2923 * <td></td>
2924 * </tr>
2925 * </table>
2926 * @param locale use the case transformation rules for this locale
2927 * @return the {@code String}, converted to uppercase.
2928 * @see java.lang.String#toUpperCase()
2929 * @see java.lang.String#toLowerCase()
2930 * @see java.lang.String#toLowerCase(Locale)
2931 * @since 1.1
2932 */
2933 public String toUpperCase(Locale locale) {
2934 if (locale == null) {
2935 throw new NullPointerException();
2936 }
2937 int first;
2938 boolean hasSurr = false;
2939 final int len = value.length;
2940
2941 // Now check if there are any characters that need to be changed, or are surrogate
2942 for (first = 0 ; first < len; first++ ) {
2943 int cp = (int)value[first];
2944 if (Character.isSurrogate((char)cp)) {
2945 hasSurr = true;
2946 break;
2947 }
2948 if (cp != Character.toUpperCaseEx(cp)) { // no need to check Character.ERROR
2949 break;
2950 }
2951 }
2952 if (first == len) {
2953 return this;
2954 }
2955 char[] result = new char[len];
2956 System.arraycopy(value, 0, result, 0, first); // Just copy the first few
2957 // upperCase characters.
2958 String lang = locale.getLanguage();
2959 if (lang == "tr" || lang == "az" || lang == "lt") {
2960 return toUpperCaseEx(result, first, locale, true);
2961 }
2962 if (hasSurr) {
2963 return toUpperCaseEx(result, first, locale, false);
2964 }
2965 for (int i = first; i < len; i++) {
2966 int cp = (int)value[i];
2967 if (Character.isSurrogate((char)cp)) {
2968 return toUpperCaseEx(result, i, locale, false);
2969 }
2970 cp = Character.toUpperCaseEx(cp);
2971 if (!Character.isBmpCodePoint(cp)) { // Character.ERROR is not bmp
2972 return toUpperCaseEx(result, i, locale, false);
2973 }
2974 result[i] = (char)cp;
2975 }
2976 return new String(result, true);
2977 }
2978
2979 private String toUpperCaseEx(char[] result, int first, Locale locale,
2980 boolean localeDependent) {
2981 int resultOffset = first;
2982 int srcCount;
2983 for (int i = first; i < value.length; i += srcCount) {
2984 int srcChar = (int)value[i];
2985 int upperChar;
2986 char[] upperCharArray;
2987 srcCount = 1;
2988 if (Character.isSurrogate((char)srcChar)) {
2989 srcChar = codePointAt(i);
2990 srcCount = Character.charCount(srcChar);
2991 }
2992 if (localeDependent) {
2993 upperChar = ConditionalSpecialCasing.toUpperCaseEx(this, i, locale);
2994 } else {
2995 upperChar = Character.toUpperCaseEx(srcChar);
2996 }
2997 if (Character.isBmpCodePoint(upperChar)) {
2998 result[resultOffset++] = (char)upperChar;
2999 } else {
3000 if (upperChar == Character.ERROR) {
3001 if (localeDependent) {
3002 upperCharArray =
3003 ConditionalSpecialCasing.toUpperCaseCharArray(this, i, locale);
3004 } else {
3005 upperCharArray = Character.toUpperCaseCharArray(srcChar);
3006 }
3007 } else if (srcCount == 2) {
3008 resultOffset += Character.toChars(upperChar, result, resultOffset);
3009 continue;
3010 } else {
3011 upperCharArray = Character.toChars(upperChar);
3012 }
3013 /* Grow result if needed */
3014 int mapLen = upperCharArray.length;
3015 if (mapLen > srcCount) {
3016 char[] result2 = new char[result.length + mapLen - srcCount];
3017 System.arraycopy(result, 0, result2, 0, resultOffset);
3018 result = result2;
3019 }
3020 for (int x = 0; x < mapLen; ++x) {
3021 result[resultOffset++] = upperCharArray[x];
3022 }
3023 }
3024 }
3025 return new String(result, 0, resultOffset);
3026 }
3027
3028 /**
3029 * Converts all of the characters in this {@code String} to upper
3030 * case using the rules of the default locale. This method is equivalent to
3031 * {@code toUpperCase(Locale.getDefault())}.
3032 * <p>
3033 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
3034 * results if used for strings that are intended to be interpreted locale
3035 * independently.
3036 * Examples are programming language identifiers, protocol keys, and HTML
3037 * tags.
3038 * For instance, {@code "title".toUpperCase()} in a Turkish locale
3039 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
3040 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
3041 * To obtain correct results for locale insensitive strings, use
3042 * {@code toUpperCase(Locale.ROOT)}.
3043 *
3044 * @return the {@code String}, converted to uppercase.
3045 * @see java.lang.String#toUpperCase(Locale)
3046 */
3047 public String toUpperCase() {
3048 return toUpperCase(Locale.getDefault());
3049 }
3050
3051 /**
3052 * Returns a string whose value is this string, with any leading and trailing
3053 * whitespace removed.
3054 * <p>
3055 * If this {@code String} object represents an empty character
3056 * sequence, or the first and last characters of character sequence
3057 * represented by this {@code String} object both have codes
3058 * greater than {@code '\u005Cu0020'} (the space character), then a
3059 * reference to this {@code String} object is returned.
3060 * <p>
3061 * Otherwise, if there is no character with a code greater than
3062 * {@code '\u005Cu0020'} in the string, then a
3063 * {@code String} object representing an empty string is
3064 * returned.
3065 * <p>
3066 * Otherwise, let <i>k</i> be the index of the first character in the
3067 * string whose code is greater than {@code '\u005Cu0020'}, and let
3068 * <i>m</i> be the index of the last character in the string whose code
3069 * is greater than {@code '\u005Cu0020'}. A {@code String}
3070 * object is returned, representing the substring of this string that
3071 * begins with the character at index <i>k</i> and ends with the
3072 * character at index <i>m</i>-that is, the result of
3073 * {@code this.substring(k, m + 1)}.
3074 * <p>
3075 * This method may be used to trim whitespace (as defined above) from
3076 * the beginning and end of a string.
3077 *
3078 * @return A string whose value is this string, with any leading and trailing white
3079 * space removed, or this string if it has no leading or
3080 * trailing white space.
3081 */
3082 public String trim() {
3083 int len = value.length;
3084 int st = 0;
3085 char[] val = value; /* avoid getfield opcode */
3086
3087 while ((st < len) && (val[st] <= ' ')) {
3088 st++;
3089 }
3090 while ((st < len) && (val[len - 1] <= ' ')) {
3091 len--;
3092 }
3093 return ((st > 0) || (len < value.length)) ? substring(st, len) : this;
3094 }
3095
3096 /**
3097 * This object (which is already a string!) is itself returned.
3098 *
3099 * @return the string itself.
3100 */
3101 public String toString() {
3102 return this;
3103 }
3104
3105 /**
3106 * Converts this string to a new character array.
3107 *
3108 * @return a newly allocated character array whose length is the length
3109 * of this string and whose contents are initialized to contain
3110 * the character sequence represented by this string.
3111 */
3112 public char[] toCharArray() {
3113 // Cannot use Arrays.copyOf because of class initialization order issues
3114 char result[] = new char[value.length];
3115 System.arraycopy(value, 0, result, 0, value.length);
3116 return result;
3117 }
3118
3119 /**
3120 * Returns a formatted string using the specified format string and
3121 * arguments.
3122 *
3123 * <p> The locale always used is the one returned by {@link
3124 * java.util.Locale#getDefault() Locale.getDefault()}.
3125 *
3126 * @param format
3127 * A <a href="../util/Formatter.html#syntax">format string</a>
3128 *
3129 * @param args
3130 * Arguments referenced by the format specifiers in the format
3131 * string. If there are more arguments than format specifiers, the
3132 * extra arguments are ignored. The number of arguments is
3133 * variable and may be zero. The maximum number of arguments is
3134 * limited by the maximum dimension of a Java array as defined by
3135 * <cite>The Java™ Virtual Machine Specification</cite>.
3136 * The behaviour on a
3137 * {@code null} argument depends on the <a
3138 * href="../util/Formatter.html#syntax">conversion</a>.
3139 *
3140 * @throws java.util.IllegalFormatException
3141 * If a format string contains an illegal syntax, a format
3142 * specifier that is incompatible with the given arguments,
3143 * insufficient arguments given the format string, or other
3144 * illegal conditions. For specification of all possible
3145 * formatting errors, see the <a
3146 * href="../util/Formatter.html#detail">Details</a> section of the
3147 * formatter class specification.
3148 *
3149 * @return A formatted string
3150 *
3151 * @see java.util.Formatter
3152 * @since 1.5
3153 */
3154 public static String format(String format, Object... args) {
3155 return new Formatter().format(format, args).toString();
3156 }
3157
3158 /**
3159 * Returns a formatted string using the specified locale, format string,
3160 * and arguments.
3161 *
3162 * @param l
3163 * The {@linkplain java.util.Locale locale} to apply during
3164 * formatting. If {@code l} is {@code null} then no localization
3165 * is applied.
3166 *
3167 * @param format
3168 * A <a href="../util/Formatter.html#syntax">format string</a>
3169 *
3170 * @param args
3171 * Arguments referenced by the format specifiers in the format
3172 * string. If there are more arguments than format specifiers, the
3173 * extra arguments are ignored. The number of arguments is
3174 * variable and may be zero. The maximum number of arguments is
3175 * limited by the maximum dimension of a Java array as defined by
3176 * <cite>The Java™ Virtual Machine Specification</cite>.
3177 * The behaviour on a
3178 * {@code null} argument depends on the
3179 * <a href="../util/Formatter.html#syntax">conversion</a>.
3180 *
3181 * @throws java.util.IllegalFormatException
3182 * If a format string contains an illegal syntax, a format
3183 * specifier that is incompatible with the given arguments,
3184 * insufficient arguments given the format string, or other
3185 * illegal conditions. For specification of all possible
3186 * formatting errors, see the <a
3187 * href="../util/Formatter.html#detail">Details</a> section of the
3188 * formatter class specification
3189 *
3190 * @return A formatted string
3191 *
3192 * @see java.util.Formatter
3193 * @since 1.5
3194 */
3195 public static String format(Locale l, String format, Object... args) {
3196 return new Formatter(l).format(format, args).toString();
3197 }
3198
3199 /**
3200 * Returns the string representation of the {@code Object} argument.
3201 *
3202 * @param obj an {@code Object}.
3203 * @return if the argument is {@code null}, then a string equal to
3204 * {@code "null"}; otherwise, the value of
3205 * {@code obj.toString()} is returned.
3206 * @see java.lang.Object#toString()
3207 */
3208 public static String valueOf(Object obj) {
3209 return (obj == null) ? "null" : obj.toString();
3210 }
3211
3212 /**
3213 * Returns the string representation of the {@code char} array
3214 * argument. The contents of the character array are copied; subsequent
3215 * modification of the character array does not affect the returned
3216 * string.
3217 *
3218 * @param data the character array.
3219 * @return a {@code String} that contains the characters of the
3220 * character array.
3221 */
3222 public static String valueOf(char data[]) {
3223 return new String(data);
3224 }
3225
3226 /**
3227 * Returns the string representation of a specific subarray of the
3228 * {@code char} array argument.
3229 * <p>
3230 * The {@code offset} argument is the index of the first
3231 * character of the subarray. The {@code count} argument
3232 * specifies the length of the subarray. The contents of the subarray
3233 * are copied; subsequent modification of the character array does not
3234 * affect the returned string.
3235 *
3236 * @param data the character array.
3237 * @param offset initial offset of the subarray.
3238 * @param count length of the subarray.
3239 * @return a {@code String} that contains the characters of the
3240 * specified subarray of the character array.
3241 * @exception IndexOutOfBoundsException if {@code offset} is
3242 * negative, or {@code count} is negative, or
3243 * {@code offset+count} is larger than
3244 * {@code data.length}.
3245 */
3246 public static String valueOf(char data[], int offset, int count) {
3247 return new String(data, offset, count);
3248 }
3249
3250 /**
3251 * Equivalent to {@link #valueOf(char[], int, int)}.
3252 *
3253 * @param data the character array.
3254 * @param offset initial offset of the subarray.
3255 * @param count length of the subarray.
3256 * @return a {@code String} that contains the characters of the
3257 * specified subarray of the character array.
3258 * @exception IndexOutOfBoundsException if {@code offset} is
3259 * negative, or {@code count} is negative, or
3260 * {@code offset+count} is larger than
3261 * {@code data.length}.
3262 */
3263 public static String copyValueOf(char data[], int offset, int count) {
3264 return new String(data, offset, count);
3265 }
3266
3267 /**
3268 * Equivalent to {@link #valueOf(char[])}.
3269 *
3270 * @param data the character array.
3271 * @return a {@code String} that contains the characters of the
3272 * character array.
3273 */
3274 public static String copyValueOf(char data[]) {
3275 return new String(data);
3276 }
3277
3278 /**
3279 * Returns the string representation of the {@code boolean} argument.
3280 *
3281 * @param b a {@code boolean}.
3282 * @return if the argument is {@code true}, a string equal to
3283 * {@code "true"} is returned; otherwise, a string equal to
3284 * {@code "false"} is returned.
3285 */
3286 public static String valueOf(boolean b) {
3287 return b ? "true" : "false";
3288 }
3289
3290 /**
3291 * Returns the string representation of the {@code char}
3292 * argument.
3293 *
3294 * @param c a {@code char}.
3295 * @return a string of length {@code 1} containing
3296 * as its single character the argument {@code c}.
3297 */
3298 public static String valueOf(char c) {
3299 char data[] = {c};
3300 return new String(data, true);
3301 }
3302
3303 /**
3304 * Returns the string representation of the {@code int} argument.
3305 * <p>
3306 * The representation is exactly the one returned by the
3307 * {@code Integer.toString} method of one argument.
3308 *
3309 * @param i an {@code int}.
3310 * @return a string representation of the {@code int} argument.
3311 * @see java.lang.Integer#toString(int, int)
3312 */
3313 public static String valueOf(int i) {
3314 return Integer.toString(i);
3315 }
3316
3317 /**
3318 * Returns the string representation of the {@code long} argument.
3319 * <p>
3320 * The representation is exactly the one returned by the
3321 * {@code Long.toString} method of one argument.
3322 *
3323 * @param l a {@code long}.
3324 * @return a string representation of the {@code long} argument.
3325 * @see java.lang.Long#toString(long)
3326 */
3327 public static String valueOf(long l) {
3328 return Long.toString(l);
3329 }
3330
3331 /**
3332 * Returns the string representation of the {@code float} argument.
3333 * <p>
3334 * The representation is exactly the one returned by the
3335 * {@code Float.toString} method of one argument.
3336 *
3337 * @param f a {@code float}.
3338 * @return a string representation of the {@code float} argument.
3339 * @see java.lang.Float#toString(float)
3340 */
3341 public static String valueOf(float f) {
3342 return Float.toString(f);
3343 }
3344
3345 /**
3346 * Returns the string representation of the {@code double} argument.
3347 * <p>
3348 * The representation is exactly the one returned by the
3349 * {@code Double.toString} method of one argument.
3350 *
3351 * @param d a {@code double}.
3352 * @return a string representation of the {@code double} argument.
3353 * @see java.lang.Double#toString(double)
3354 */
3355 public static String valueOf(double d) {
3356 return Double.toString(d);
3357 }
3358
3359 /**
3360 * Returns a canonical representation for the string object.
3361 * <p>
3362 * A pool of strings, initially empty, is maintained privately by the
3363 * class {@code String}.
3364 * <p>
3365 * When the intern method is invoked, if the pool already contains a
3366 * string equal to this {@code String} object as determined by
3367 * the {@link #equals(Object)} method, then the string from the pool is
3368 * returned. Otherwise, this {@code String} object is added to the
3369 * pool and a reference to this {@code String} object is returned.
3370 * <p>
3371 * It follows that for any two strings {@code s} and {@code t},
3372 * {@code s.intern() == t.intern()} is {@code true}
3373 * if and only if {@code s.equals(t)} is {@code true}.
3374 * <p>
3375 * All literal strings and string-valued constant expressions are
3376 * interned. String literals are defined in section 3.10.5 of the
3377 * <cite>The Java™ Language Specification</cite>.
3378 *
3379 * @return a string that has the same contents as this string, but is
3380 * guaranteed to be from a pool of unique strings.
3381 */
3382 public native String intern();
3383 }