1 /*
2 * Copyright (c) 1994, 2018, 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.lang.annotation.Native;
31 import java.lang.invoke.MethodHandles;
32 import java.lang.constant.Constable;
33 import java.lang.constant.ConstantDesc;
34 import java.nio.charset.Charset;
35 import java.util.ArrayList;
36 import java.util.Arrays;
37 import java.util.Comparator;
38 import java.util.Formatter;
39 import java.util.Locale;
40 import java.util.Objects;
41 import java.util.Optional;
42 import java.util.Spliterator;
43 import java.util.StringJoiner;
44 import java.util.function.Function;
45 import java.util.regex.Matcher;
46 import java.util.regex.Pattern;
47 import java.util.regex.PatternSyntaxException;
48 import java.util.stream.Collectors;
49 import java.util.stream.IntStream;
50 import java.util.stream.Stream;
51 import java.util.stream.StreamSupport;
52 import jdk.internal.HotSpotIntrinsicCandidate;
53 import jdk.internal.vm.annotation.Stable;
54
55 import static java.util.function.Predicate.not;
56
57 /**
58 * The {@code String} class represents character strings. All
59 * string literals in Java programs, such as {@code "abc"}, are
60 * implemented as instances of this class.
61 * <p>
62 * Strings are constant; their values cannot be changed after they
63 * are created. String buffers support mutable strings.
64 * Because String objects are immutable they can be shared. For example:
65 * <blockquote><pre>
66 * String str = "abc";
67 * </pre></blockquote><p>
68 * is equivalent to:
69 * <blockquote><pre>
70 * char data[] = {'a', 'b', 'c'};
71 * String str = new String(data);
72 * </pre></blockquote><p>
73 * Here are some more examples of how strings can be used:
74 * <blockquote><pre>
75 * System.out.println("abc");
76 * String cde = "cde";
77 * System.out.println("abc" + cde);
78 * String c = "abc".substring(2,3);
79 * String d = cde.substring(1, 2);
80 * </pre></blockquote>
81 * <p>
82 * The class {@code String} includes methods for examining
83 * individual characters of the sequence, for comparing strings, for
84 * searching strings, for extracting substrings, and for creating a
85 * copy of a string with all characters translated to uppercase or to
86 * lowercase. Case mapping is based on the Unicode Standard version
87 * specified by the {@link java.lang.Character Character} class.
88 * <p>
89 * The Java language provides special support for the string
90 * concatenation operator ( + ), and for conversion of
91 * other objects to strings. For additional information on string
92 * concatenation and conversion, see <i>The Java™ Language Specification</i>.
93 *
94 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor
95 * or method in this class will cause a {@link NullPointerException} to be
96 * thrown.
97 *
98 * <p>A {@code String} represents a string in the UTF-16 format
99 * in which <em>supplementary characters</em> are represented by <em>surrogate
100 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
101 * Character Representations</a> in the {@code Character} class for
102 * more information).
103 * Index values refer to {@code char} code units, so a supplementary
104 * character uses two positions in a {@code String}.
105 * <p>The {@code String} class provides methods for dealing with
106 * Unicode code points (i.e., characters), in addition to those for
107 * dealing with Unicode code units (i.e., {@code char} values).
108 *
109 * <p>Unless otherwise noted, methods for comparing Strings do not take locale
110 * into account. The {@link java.text.Collator} class provides methods for
111 * finer-grain, locale-sensitive String comparison.
112 *
113 * @implNote The implementation of the string concatenation operator is left to
114 * the discretion of a Java compiler, as long as the compiler ultimately conforms
115 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler
116 * may implement the operator with {@code StringBuffer}, {@code StringBuilder},
117 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The
118 * implementation of string conversion is typically through the method {@code toString},
119 * defined by {@code Object} and inherited by all classes in Java.
120 *
121 * @author Lee Boynton
122 * @author Arthur van Hoff
123 * @author Martin Buchholz
124 * @author Ulf Zibis
125 * @see java.lang.Object#toString()
126 * @see java.lang.StringBuffer
127 * @see java.lang.StringBuilder
128 * @see java.nio.charset.Charset
129 * @since 1.0
130 * @jls 15.18.1 String Concatenation Operator +
131 */
132
133 public final class String
134 implements java.io.Serializable, Comparable<String>, CharSequence,
135 Constable, ConstantDesc {
136
137 /**
138 * The value is used for character storage.
139 *
140 * @implNote This field is trusted by the VM, and is a subject to
141 * constant folding if String instance is constant. Overwriting this
142 * field after construction will cause problems.
143 *
144 * Additionally, it is marked with {@link Stable} to trust the contents
145 * of the array. No other facility in JDK provides this functionality (yet).
146 * {@link Stable} is safe here, because value is never null.
147 */
148 @Stable
149 private final byte[] value;
150
151 /**
152 * The identifier of the encoding used to encode the bytes in
153 * {@code value}. The supported values in this implementation are
154 *
155 * LATIN1
156 * UTF16
157 *
158 * @implNote This field is trusted by the VM, and is a subject to
159 * constant folding if String instance is constant. Overwriting this
160 * field after construction will cause problems.
161 */
162 private final byte coder;
163
164 /** Cache the hash code for the string */
165 private int hash; // Default to 0
166
167 /** use serialVersionUID from JDK 1.0.2 for interoperability */
168 private static final long serialVersionUID = -6849794470754667710L;
169
170 /**
171 * If String compaction is disabled, the bytes in {@code value} are
172 * always encoded in UTF16.
173 *
174 * For methods with several possible implementation paths, when String
175 * compaction is disabled, only one code path is taken.
176 *
177 * The instance field value is generally opaque to optimizing JIT
178 * compilers. Therefore, in performance-sensitive place, an explicit
179 * check of the static boolean {@code COMPACT_STRINGS} is done first
180 * before checking the {@code coder} field since the static boolean
181 * {@code COMPACT_STRINGS} would be constant folded away by an
182 * optimizing JIT compiler. The idioms for these cases are as follows.
183 *
184 * For code such as:
185 *
186 * if (coder == LATIN1) { ... }
187 *
188 * can be written more optimally as
189 *
190 * if (coder() == LATIN1) { ... }
191 *
192 * or:
193 *
194 * if (COMPACT_STRINGS && coder == LATIN1) { ... }
195 *
196 * An optimizing JIT compiler can fold the above conditional as:
197 *
198 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... }
199 * COMPACT_STRINGS == false => if (false) { ... }
200 *
201 * @implNote
202 * The actual value for this field is injected by JVM. The static
203 * initialization block is used to set the value here to communicate
204 * that this static final field is not statically foldable, and to
205 * avoid any possible circular dependency during vm initialization.
206 */
207 static final boolean COMPACT_STRINGS;
208
209 static {
210 COMPACT_STRINGS = true;
211 }
212
213 /**
214 * Class String is special cased within the Serialization Stream Protocol.
215 *
216 * A String instance is written into an ObjectOutputStream according to
217 * <a href="{@docRoot}/../specs/serialization/protocol.html#stream-elements">
218 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
219 */
220 private static final ObjectStreamField[] serialPersistentFields =
221 new ObjectStreamField[0];
222
223 /**
224 * Initializes a newly created {@code String} object so that it represents
225 * an empty character sequence. Note that use of this constructor is
226 * unnecessary since Strings are immutable.
227 */
228 public String() {
229 this.value = "".value;
230 this.coder = "".coder;
231 }
232
233 /**
234 * Initializes a newly created {@code String} object so that it represents
235 * the same sequence of characters as the argument; in other words, the
236 * newly created string is a copy of the argument string. Unless an
237 * explicit copy of {@code original} is needed, use of this constructor is
238 * unnecessary since Strings are immutable.
239 *
240 * @param original
241 * A {@code String}
242 */
243 @HotSpotIntrinsicCandidate
244 public String(String original) {
245 this.value = original.value;
246 this.coder = original.coder;
247 this.hash = original.hash;
248 }
249
250 /**
251 * Allocates a new {@code String} so that it represents the sequence of
252 * characters currently contained in the character array argument. The
253 * contents of the character array are copied; subsequent modification of
254 * the character array does not affect the newly created string.
255 *
256 * @param value
257 * The initial value of the string
258 */
259 public String(char value[]) {
260 this(value, 0, value.length, null);
261 }
262
263 /**
264 * Allocates a new {@code String} that contains characters from a subarray
265 * of the character array argument. The {@code offset} argument is the
266 * index of the first character of the subarray and the {@code count}
267 * argument specifies the length of the subarray. The contents of the
268 * subarray are copied; subsequent modification of the character array does
269 * not affect the newly created string.
270 *
271 * @param value
272 * Array that is the source of characters
273 *
274 * @param offset
275 * The initial offset
276 *
277 * @param count
278 * The length
279 *
280 * @throws IndexOutOfBoundsException
281 * If {@code offset} is negative, {@code count} is negative, or
282 * {@code offset} is greater than {@code value.length - count}
283 */
284 public String(char value[], int offset, int count) {
285 this(value, offset, count, rangeCheck(value, offset, count));
286 }
287
288 private static Void rangeCheck(char[] value, int offset, int count) {
289 checkBoundsOffCount(offset, count, value.length);
290 return null;
291 }
292
293 /**
294 * Allocates a new {@code String} that contains characters from a subarray
295 * of the <a href="Character.html#unicode">Unicode code point</a> array
296 * argument. The {@code offset} argument is the index of the first code
297 * point of the subarray and the {@code count} argument specifies the
298 * length of the subarray. The contents of the subarray are converted to
299 * {@code char}s; subsequent modification of the {@code int} array does not
300 * affect the newly created string.
301 *
302 * @param codePoints
303 * Array that is the source of Unicode code points
304 *
305 * @param offset
306 * The initial offset
307 *
308 * @param count
309 * The length
310 *
311 * @throws IllegalArgumentException
312 * If any invalid Unicode code point is found in {@code
313 * codePoints}
314 *
315 * @throws IndexOutOfBoundsException
316 * If {@code offset} is negative, {@code count} is negative, or
317 * {@code offset} is greater than {@code codePoints.length - count}
318 *
319 * @since 1.5
320 */
321 public String(int[] codePoints, int offset, int count) {
322 checkBoundsOffCount(offset, count, codePoints.length);
323 if (count == 0) {
324 this.value = "".value;
325 this.coder = "".coder;
326 return;
327 }
328 if (COMPACT_STRINGS) {
329 byte[] val = StringLatin1.toBytes(codePoints, offset, count);
330 if (val != null) {
331 this.coder = LATIN1;
332 this.value = val;
333 return;
334 }
335 }
336 this.coder = UTF16;
337 this.value = StringUTF16.toBytes(codePoints, offset, count);
338 }
339
340 /**
341 * Allocates a new {@code String} constructed from a subarray of an array
342 * of 8-bit integer values.
343 *
344 * <p> The {@code offset} argument is the index of the first byte of the
345 * subarray, and the {@code count} argument specifies the length of the
346 * subarray.
347 *
348 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
349 * specified in the {@link #String(byte[],int) String(byte[],int)} constructor.
350 *
351 * @deprecated This method does not properly convert bytes into characters.
352 * As of JDK 1.1, the preferred way to do this is via the
353 * {@code String} constructors that take a {@link
354 * java.nio.charset.Charset}, charset name, or that use the platform's
355 * default charset.
356 *
357 * @param ascii
358 * The bytes to be converted to characters
359 *
360 * @param hibyte
361 * The top 8 bits of each 16-bit Unicode code unit
362 *
363 * @param offset
364 * The initial offset
365 * @param count
366 * The length
367 *
368 * @throws IndexOutOfBoundsException
369 * If {@code offset} is negative, {@code count} is negative, or
370 * {@code offset} is greater than {@code ascii.length - count}
371 *
372 * @see #String(byte[], int)
373 * @see #String(byte[], int, int, java.lang.String)
374 * @see #String(byte[], int, int, java.nio.charset.Charset)
375 * @see #String(byte[], int, int)
376 * @see #String(byte[], java.lang.String)
377 * @see #String(byte[], java.nio.charset.Charset)
378 * @see #String(byte[])
379 */
380 @Deprecated(since="1.1")
381 public String(byte ascii[], int hibyte, int offset, int count) {
382 checkBoundsOffCount(offset, count, ascii.length);
383 if (count == 0) {
384 this.value = "".value;
385 this.coder = "".coder;
386 return;
387 }
388 if (COMPACT_STRINGS && (byte)hibyte == 0) {
389 this.value = Arrays.copyOfRange(ascii, offset, offset + count);
390 this.coder = LATIN1;
391 } else {
392 hibyte <<= 8;
393 byte[] val = StringUTF16.newBytesFor(count);
394 for (int i = 0; i < count; i++) {
395 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff));
396 }
397 this.value = val;
398 this.coder = UTF16;
399 }
400 }
401
402 /**
403 * Allocates a new {@code String} containing characters constructed from
404 * an array of 8-bit integer values. Each character <i>c</i> in the
405 * resulting string is constructed from the corresponding component
406 * <i>b</i> in the byte array such that:
407 *
408 * <blockquote><pre>
409 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
410 * | (<b><i>b</i></b> & 0xff))
411 * </pre></blockquote>
412 *
413 * @deprecated This method does not properly convert bytes into
414 * characters. As of JDK 1.1, the preferred way to do this is via the
415 * {@code String} constructors that take a {@link
416 * java.nio.charset.Charset}, charset name, or that use the platform's
417 * default charset.
418 *
419 * @param ascii
420 * The bytes to be converted to characters
421 *
422 * @param hibyte
423 * The top 8 bits of each 16-bit Unicode code unit
424 *
425 * @see #String(byte[], int, int, java.lang.String)
426 * @see #String(byte[], int, int, java.nio.charset.Charset)
427 * @see #String(byte[], int, int)
428 * @see #String(byte[], java.lang.String)
429 * @see #String(byte[], java.nio.charset.Charset)
430 * @see #String(byte[])
431 */
432 @Deprecated(since="1.1")
433 public String(byte ascii[], int hibyte) {
434 this(ascii, hibyte, 0, ascii.length);
435 }
436
437 /**
438 * Constructs a new {@code String} by decoding the specified subarray of
439 * bytes using the specified charset. The length of the new {@code String}
440 * is a function of the charset, and hence may not be equal to the length
441 * of the subarray.
442 *
443 * <p> The behavior of this constructor when the given bytes are not valid
444 * in the given charset is unspecified. The {@link
445 * java.nio.charset.CharsetDecoder} class should be used when more control
446 * over the decoding process is required.
447 *
448 * @param bytes
449 * The bytes to be decoded into characters
450 *
451 * @param offset
452 * The index of the first byte to decode
453 *
454 * @param length
455 * The number of bytes to decode
456
457 * @param charsetName
458 * The name of a supported {@linkplain java.nio.charset.Charset
459 * charset}
460 *
461 * @throws UnsupportedEncodingException
462 * If the named charset is not supported
463 *
464 * @throws IndexOutOfBoundsException
465 * If {@code offset} is negative, {@code length} is negative, or
466 * {@code offset} is greater than {@code bytes.length - length}
467 *
468 * @since 1.1
469 */
470 public String(byte bytes[], int offset, int length, String charsetName)
471 throws UnsupportedEncodingException {
472 if (charsetName == null)
473 throw new NullPointerException("charsetName");
474 checkBoundsOffCount(offset, length, bytes.length);
475 StringCoding.Result ret =
476 StringCoding.decode(charsetName, bytes, offset, length);
477 this.value = ret.value;
478 this.coder = ret.coder;
479 }
480
481 /**
482 * Constructs a new {@code String} by decoding the specified subarray of
483 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
484 * The length of the new {@code String} is a function of the charset, and
485 * hence may not be equal to the length of the subarray.
486 *
487 * <p> This method always replaces malformed-input and unmappable-character
488 * sequences with this charset's default replacement string. The {@link
489 * java.nio.charset.CharsetDecoder} class should be used when more control
490 * over the decoding process is required.
491 *
492 * @param bytes
493 * The bytes to be decoded into characters
494 *
495 * @param offset
496 * The index of the first byte to decode
497 *
498 * @param length
499 * The number of bytes to decode
500 *
501 * @param charset
502 * The {@linkplain java.nio.charset.Charset charset} to be used to
503 * decode the {@code bytes}
504 *
505 * @throws IndexOutOfBoundsException
506 * If {@code offset} is negative, {@code length} is negative, or
507 * {@code offset} is greater than {@code bytes.length - length}
508 *
509 * @since 1.6
510 */
511 public String(byte bytes[], int offset, int length, Charset charset) {
512 if (charset == null)
513 throw new NullPointerException("charset");
514 checkBoundsOffCount(offset, length, bytes.length);
515 StringCoding.Result ret =
516 StringCoding.decode(charset, bytes, offset, length);
517 this.value = ret.value;
518 this.coder = ret.coder;
519 }
520
521 /**
522 * Constructs a new {@code String} by decoding the specified array of bytes
523 * using the specified {@linkplain java.nio.charset.Charset charset}. The
524 * length of the new {@code String} is a function of the charset, and hence
525 * may not be equal to the length of the byte array.
526 *
527 * <p> The behavior of this constructor when the given bytes are not valid
528 * in the given charset is unspecified. The {@link
529 * java.nio.charset.CharsetDecoder} class should be used when more control
530 * over the decoding process is required.
531 *
532 * @param bytes
533 * The bytes to be decoded into characters
534 *
535 * @param charsetName
536 * The name of a supported {@linkplain java.nio.charset.Charset
537 * charset}
538 *
539 * @throws UnsupportedEncodingException
540 * If the named charset is not supported
541 *
542 * @since 1.1
543 */
544 public String(byte bytes[], String charsetName)
545 throws UnsupportedEncodingException {
546 this(bytes, 0, bytes.length, charsetName);
547 }
548
549 /**
550 * Constructs a new {@code String} by decoding the specified array of
551 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
552 * The length of the new {@code String} is a function of the charset, and
553 * hence may not be equal to the length of the byte array.
554 *
555 * <p> This method always replaces malformed-input and unmappable-character
556 * sequences with this charset's default replacement string. The {@link
557 * java.nio.charset.CharsetDecoder} class should be used when more control
558 * over the decoding process is required.
559 *
560 * @param bytes
561 * The bytes to be decoded into characters
562 *
563 * @param charset
564 * The {@linkplain java.nio.charset.Charset charset} to be used to
565 * decode the {@code bytes}
566 *
567 * @since 1.6
568 */
569 public String(byte bytes[], Charset charset) {
570 this(bytes, 0, bytes.length, charset);
571 }
572
573 /**
574 * Constructs a new {@code String} by decoding the specified subarray of
575 * bytes using the platform's default charset. The length of the new
576 * {@code String} is a function of the charset, and hence may not be equal
577 * to the length of the subarray.
578 *
579 * <p> The behavior of this constructor when the given bytes are not valid
580 * in the default charset is unspecified. The {@link
581 * java.nio.charset.CharsetDecoder} class should be used when more control
582 * over the decoding process is required.
583 *
584 * @param bytes
585 * The bytes to be decoded into characters
586 *
587 * @param offset
588 * The index of the first byte to decode
589 *
590 * @param length
591 * The number of bytes to decode
592 *
593 * @throws IndexOutOfBoundsException
594 * If {@code offset} is negative, {@code length} is negative, or
595 * {@code offset} is greater than {@code bytes.length - length}
596 *
597 * @since 1.1
598 */
599 public String(byte bytes[], int offset, int length) {
600 checkBoundsOffCount(offset, length, bytes.length);
601 StringCoding.Result ret = StringCoding.decode(bytes, offset, length);
602 this.value = ret.value;
603 this.coder = ret.coder;
604 }
605
606 /**
607 * Constructs a new {@code String} by decoding the specified array of bytes
608 * using the platform's default charset. The length of the new {@code
609 * String} is a function of the charset, and hence may not be equal to the
610 * length of the byte array.
611 *
612 * <p> The behavior of this constructor when the given bytes are not valid
613 * in the default charset is unspecified. The {@link
614 * java.nio.charset.CharsetDecoder} class should be used when more control
615 * over the decoding process is required.
616 *
617 * @param bytes
618 * The bytes to be decoded into characters
619 *
620 * @since 1.1
621 */
622 public String(byte[] bytes) {
623 this(bytes, 0, bytes.length);
624 }
625
626 /**
627 * Allocates a new string that contains the sequence of characters
628 * currently contained in the string buffer argument. The contents of the
629 * string buffer are copied; subsequent modification of the string buffer
630 * does not affect the newly created string.
631 *
632 * @param buffer
633 * A {@code StringBuffer}
634 */
635 public String(StringBuffer buffer) {
636 this(buffer.toString());
637 }
638
639 /**
640 * Allocates a new string that contains the sequence of characters
641 * currently contained in the string builder argument. The contents of the
642 * string builder are copied; subsequent modification of the string builder
643 * does not affect the newly created string.
644 *
645 * <p> This constructor is provided to ease migration to {@code
646 * StringBuilder}. Obtaining a string from a string builder via the {@code
647 * toString} method is likely to run faster and is generally preferred.
648 *
649 * @param builder
650 * A {@code StringBuilder}
651 *
652 * @since 1.5
653 */
654 public String(StringBuilder builder) {
655 this(builder, null);
656 }
657
658 /**
659 * Returns the length of this string.
660 * The length is equal to the number of <a href="Character.html#unicode">Unicode
661 * code units</a> in the string.
662 *
663 * @return the length of the sequence of characters represented by this
664 * object.
665 */
666 public int length() {
667 return value.length >> coder();
668 }
669
670 /**
671 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
672 *
673 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
674 * {@code false}
675 *
676 * @since 1.6
677 */
678 public boolean isEmpty() {
679 return value.length == 0;
680 }
681
682 /**
683 * Returns the {@code char} value at the
684 * specified index. An index ranges from {@code 0} to
685 * {@code length() - 1}. The first {@code char} value of the sequence
686 * is at index {@code 0}, the next at index {@code 1},
687 * and so on, as for array indexing.
688 *
689 * <p>If the {@code char} value specified by the index is a
690 * <a href="Character.html#unicode">surrogate</a>, the surrogate
691 * value is returned.
692 *
693 * @param index the index of the {@code char} value.
694 * @return the {@code char} value at the specified index of this string.
695 * The first {@code char} value is at index {@code 0}.
696 * @exception IndexOutOfBoundsException if the {@code index}
697 * argument is negative or not less than the length of this
698 * string.
699 */
700 public char charAt(int index) {
701 if (isLatin1()) {
702 return StringLatin1.charAt(value, index);
703 } else {
704 return StringUTF16.charAt(value, index);
705 }
706 }
707
708 /**
709 * Returns the character (Unicode code point) at the specified
710 * index. The index refers to {@code char} values
711 * (Unicode code units) and ranges from {@code 0} to
712 * {@link #length()}{@code - 1}.
713 *
714 * <p> If the {@code char} value specified at the given index
715 * is in the high-surrogate range, the following index is less
716 * than the length of this {@code String}, and the
717 * {@code char} value at the following index is in the
718 * low-surrogate range, then the supplementary code point
719 * corresponding to this surrogate pair is returned. Otherwise,
720 * the {@code char} value at the given index is returned.
721 *
722 * @param index the index to the {@code char} values
723 * @return the code point value of the character at the
724 * {@code index}
725 * @exception IndexOutOfBoundsException if the {@code index}
726 * argument is negative or not less than the length of this
727 * string.
728 * @since 1.5
729 */
730 public int codePointAt(int index) {
731 if (isLatin1()) {
732 checkIndex(index, value.length);
733 return value[index] & 0xff;
734 }
735 int length = value.length >> 1;
736 checkIndex(index, length);
737 return StringUTF16.codePointAt(value, index, length);
738 }
739
740 /**
741 * Returns the character (Unicode code point) before the specified
742 * index. The index refers to {@code char} values
743 * (Unicode code units) and ranges from {@code 1} to {@link
744 * CharSequence#length() length}.
745 *
746 * <p> If the {@code char} value at {@code (index - 1)}
747 * is in the low-surrogate range, {@code (index - 2)} is not
748 * negative, and the {@code char} value at {@code (index -
749 * 2)} is in the high-surrogate range, then the
750 * supplementary code point value of the surrogate pair is
751 * returned. If the {@code char} value at {@code index -
752 * 1} is an unpaired low-surrogate or a high-surrogate, the
753 * surrogate value is returned.
754 *
755 * @param index the index following the code point that should be returned
756 * @return the Unicode code point value before the given index.
757 * @exception IndexOutOfBoundsException if the {@code index}
758 * argument is less than 1 or greater than the length
759 * of this string.
760 * @since 1.5
761 */
762 public int codePointBefore(int index) {
763 int i = index - 1;
764 if (i < 0 || i >= length()) {
765 throw new StringIndexOutOfBoundsException(index);
766 }
767 if (isLatin1()) {
768 return (value[i] & 0xff);
769 }
770 return StringUTF16.codePointBefore(value, index);
771 }
772
773 /**
774 * Returns the number of Unicode code points in the specified text
775 * range of this {@code String}. The text range begins at the
776 * specified {@code beginIndex} and extends to the
777 * {@code char} at index {@code endIndex - 1}. Thus the
778 * length (in {@code char}s) of the text range is
779 * {@code endIndex-beginIndex}. Unpaired surrogates within
780 * the text range count as one code point each.
781 *
782 * @param beginIndex the index to the first {@code char} of
783 * the text range.
784 * @param endIndex the index after the last {@code char} of
785 * the text range.
786 * @return the number of Unicode code points in the specified text
787 * range
788 * @exception IndexOutOfBoundsException if the
789 * {@code beginIndex} is negative, or {@code endIndex}
790 * is larger than the length of this {@code String}, or
791 * {@code beginIndex} is larger than {@code endIndex}.
792 * @since 1.5
793 */
794 public int codePointCount(int beginIndex, int endIndex) {
795 if (beginIndex < 0 || beginIndex > endIndex ||
796 endIndex > length()) {
797 throw new IndexOutOfBoundsException();
798 }
799 if (isLatin1()) {
800 return endIndex - beginIndex;
801 }
802 return StringUTF16.codePointCount(value, beginIndex, endIndex);
803 }
804
805 /**
806 * Returns the index within this {@code String} that is
807 * offset from the given {@code index} by
808 * {@code codePointOffset} code points. Unpaired surrogates
809 * within the text range given by {@code index} and
810 * {@code codePointOffset} count as one code point each.
811 *
812 * @param index the index to be offset
813 * @param codePointOffset the offset in code points
814 * @return the index within this {@code String}
815 * @exception IndexOutOfBoundsException if {@code index}
816 * is negative or larger then the length of this
817 * {@code String}, or if {@code codePointOffset} is positive
818 * and the substring starting with {@code index} has fewer
819 * than {@code codePointOffset} code points,
820 * or if {@code codePointOffset} is negative and the substring
821 * before {@code index} has fewer than the absolute value
822 * of {@code codePointOffset} code points.
823 * @since 1.5
824 */
825 public int offsetByCodePoints(int index, int codePointOffset) {
826 if (index < 0 || index > length()) {
827 throw new IndexOutOfBoundsException();
828 }
829 return Character.offsetByCodePoints(this, index, codePointOffset);
830 }
831
832 /**
833 * Copies characters from this string into the destination character
834 * array.
835 * <p>
836 * The first character to be copied is at index {@code srcBegin};
837 * the last character to be copied is at index {@code srcEnd-1}
838 * (thus the total number of characters to be copied is
839 * {@code srcEnd-srcBegin}). The characters are copied into the
840 * subarray of {@code dst} starting at index {@code dstBegin}
841 * and ending at index:
842 * <blockquote><pre>
843 * dstBegin + (srcEnd-srcBegin) - 1
844 * </pre></blockquote>
845 *
846 * @param srcBegin index of the first character in the string
847 * to copy.
848 * @param srcEnd index after the last character in the string
849 * to copy.
850 * @param dst the destination array.
851 * @param dstBegin the start offset in the destination array.
852 * @exception IndexOutOfBoundsException If any of the following
853 * is true:
854 * <ul><li>{@code srcBegin} is negative.
855 * <li>{@code srcBegin} is greater than {@code srcEnd}
856 * <li>{@code srcEnd} is greater than the length of this
857 * string
858 * <li>{@code dstBegin} is negative
859 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
860 * {@code dst.length}</ul>
861 */
862 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
863 checkBoundsBeginEnd(srcBegin, srcEnd, length());
864 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
865 if (isLatin1()) {
866 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin);
867 } else {
868 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin);
869 }
870 }
871
872 /**
873 * Copies characters from this string into the destination byte array. Each
874 * byte receives the 8 low-order bits of the corresponding character. The
875 * eight high-order bits of each character are not copied and do not
876 * participate in the transfer in any way.
877 *
878 * <p> The first character to be copied is at index {@code srcBegin}; the
879 * last character to be copied is at index {@code srcEnd-1}. The total
880 * number of characters to be copied is {@code srcEnd-srcBegin}. The
881 * characters, converted to bytes, are copied into the subarray of {@code
882 * dst} starting at index {@code dstBegin} and ending at index:
883 *
884 * <blockquote><pre>
885 * dstBegin + (srcEnd-srcBegin) - 1
886 * </pre></blockquote>
887 *
888 * @deprecated This method does not properly convert characters into
889 * bytes. As of JDK 1.1, the preferred way to do this is via the
890 * {@link #getBytes()} method, which uses the platform's default charset.
891 *
892 * @param srcBegin
893 * Index of the first character in the string to copy
894 *
895 * @param srcEnd
896 * Index after the last character in the string to copy
897 *
898 * @param dst
899 * The destination array
900 *
901 * @param dstBegin
902 * The start offset in the destination array
903 *
904 * @throws IndexOutOfBoundsException
905 * If any of the following is true:
906 * <ul>
907 * <li> {@code srcBegin} is negative
908 * <li> {@code srcBegin} is greater than {@code srcEnd}
909 * <li> {@code srcEnd} is greater than the length of this String
910 * <li> {@code dstBegin} is negative
911 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
912 * dst.length}
913 * </ul>
914 */
915 @Deprecated(since="1.1")
916 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
917 checkBoundsBeginEnd(srcBegin, srcEnd, length());
918 Objects.requireNonNull(dst);
919 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
920 if (isLatin1()) {
921 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
922 } else {
923 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
924 }
925 }
926
927 /**
928 * Encodes this {@code String} into a sequence of bytes using the named
929 * charset, storing the result into a new byte array.
930 *
931 * <p> The behavior of this method when this string cannot be encoded in
932 * the given charset is unspecified. The {@link
933 * java.nio.charset.CharsetEncoder} class should be used when more control
934 * over the encoding process is required.
935 *
936 * @param charsetName
937 * The name of a supported {@linkplain java.nio.charset.Charset
938 * charset}
939 *
940 * @return The resultant byte array
941 *
942 * @throws UnsupportedEncodingException
943 * If the named charset is not supported
944 *
945 * @since 1.1
946 */
947 public byte[] getBytes(String charsetName)
948 throws UnsupportedEncodingException {
949 if (charsetName == null) throw new NullPointerException();
950 return StringCoding.encode(charsetName, coder(), value);
951 }
952
953 /**
954 * Encodes this {@code String} into a sequence of bytes using the given
955 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
956 * new byte array.
957 *
958 * <p> This method always replaces malformed-input and unmappable-character
959 * sequences with this charset's default replacement byte array. The
960 * {@link java.nio.charset.CharsetEncoder} class should be used when more
961 * control over the encoding process is required.
962 *
963 * @param charset
964 * The {@linkplain java.nio.charset.Charset} to be used to encode
965 * the {@code String}
966 *
967 * @return The resultant byte array
968 *
969 * @since 1.6
970 */
971 public byte[] getBytes(Charset charset) {
972 if (charset == null) throw new NullPointerException();
973 return StringCoding.encode(charset, coder(), value);
974 }
975
976 /**
977 * Encodes this {@code String} into a sequence of bytes using the
978 * platform's default charset, storing the result into a new byte array.
979 *
980 * <p> The behavior of this method when this string cannot be encoded in
981 * the default charset is unspecified. The {@link
982 * java.nio.charset.CharsetEncoder} class should be used when more control
983 * over the encoding process is required.
984 *
985 * @return The resultant byte array
986 *
987 * @since 1.1
988 */
989 public byte[] getBytes() {
990 return StringCoding.encode(coder(), value);
991 }
992
993 /**
994 * Compares this string to the specified object. The result is {@code
995 * true} if and only if the argument is not {@code null} and is a {@code
996 * String} object that represents the same sequence of characters as this
997 * object.
998 *
999 * <p>For finer-grained String comparison, refer to
1000 * {@link java.text.Collator}.
1001 *
1002 * @param anObject
1003 * The object to compare this {@code String} against
1004 *
1005 * @return {@code true} if the given object represents a {@code String}
1006 * equivalent to this string, {@code false} otherwise
1007 *
1008 * @see #compareTo(String)
1009 * @see #equalsIgnoreCase(String)
1010 */
1011 public boolean equals(Object anObject) {
1012 if (this == anObject) {
1013 return true;
1014 }
1015 if (anObject instanceof String) {
1016 String aString = (String)anObject;
1017 if (coder() == aString.coder()) {
1018 return isLatin1() ? StringLatin1.equals(value, aString.value)
1019 : StringUTF16.equals(value, aString.value);
1020 }
1021 }
1022 return false;
1023 }
1024
1025 /**
1026 * Compares this string to the specified {@code StringBuffer}. The result
1027 * is {@code true} if and only if this {@code String} represents the same
1028 * sequence of characters as the specified {@code StringBuffer}. This method
1029 * synchronizes on the {@code StringBuffer}.
1030 *
1031 * <p>For finer-grained String comparison, refer to
1032 * {@link java.text.Collator}.
1033 *
1034 * @param sb
1035 * The {@code StringBuffer} to compare this {@code String} against
1036 *
1037 * @return {@code true} if this {@code String} represents the same
1038 * sequence of characters as the specified {@code StringBuffer},
1039 * {@code false} otherwise
1040 *
1041 * @since 1.4
1042 */
1043 public boolean contentEquals(StringBuffer sb) {
1044 return contentEquals((CharSequence)sb);
1045 }
1046
1047 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1048 int len = length();
1049 if (len != sb.length()) {
1050 return false;
1051 }
1052 byte v1[] = value;
1053 byte v2[] = sb.getValue();
1054 if (coder() == sb.getCoder()) {
1055 int n = v1.length;
1056 for (int i = 0; i < n; i++) {
1057 if (v1[i] != v2[i]) {
1058 return false;
1059 }
1060 }
1061 } else {
1062 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal"
1063 return false;
1064 }
1065 return StringUTF16.contentEquals(v1, v2, len);
1066 }
1067 return true;
1068 }
1069
1070 /**
1071 * Compares this string to the specified {@code CharSequence}. The
1072 * result is {@code true} if and only if this {@code String} represents the
1073 * same sequence of char values as the specified sequence. Note that if the
1074 * {@code CharSequence} is a {@code StringBuffer} then the method
1075 * synchronizes on it.
1076 *
1077 * <p>For finer-grained String comparison, refer to
1078 * {@link java.text.Collator}.
1079 *
1080 * @param cs
1081 * The sequence to compare this {@code String} against
1082 *
1083 * @return {@code true} if this {@code String} represents the same
1084 * sequence of char values as the specified sequence, {@code
1085 * false} otherwise
1086 *
1087 * @since 1.5
1088 */
1089 public boolean contentEquals(CharSequence cs) {
1090 // Argument is a StringBuffer, StringBuilder
1091 if (cs instanceof AbstractStringBuilder) {
1092 if (cs instanceof StringBuffer) {
1093 synchronized(cs) {
1094 return nonSyncContentEquals((AbstractStringBuilder)cs);
1095 }
1096 } else {
1097 return nonSyncContentEquals((AbstractStringBuilder)cs);
1098 }
1099 }
1100 // Argument is a String
1101 if (cs instanceof String) {
1102 return equals(cs);
1103 }
1104 // Argument is a generic CharSequence
1105 int n = cs.length();
1106 if (n != length()) {
1107 return false;
1108 }
1109 byte[] val = this.value;
1110 if (isLatin1()) {
1111 for (int i = 0; i < n; i++) {
1112 if ((val[i] & 0xff) != cs.charAt(i)) {
1113 return false;
1114 }
1115 }
1116 } else {
1117 if (!StringUTF16.contentEquals(val, cs, n)) {
1118 return false;
1119 }
1120 }
1121 return true;
1122 }
1123
1124 /**
1125 * Compares this {@code String} to another {@code String}, ignoring case
1126 * considerations. Two strings are considered equal ignoring case if they
1127 * are of the same length and corresponding characters in the two strings
1128 * are equal ignoring case.
1129 *
1130 * <p> Two characters {@code c1} and {@code c2} are considered the same
1131 * ignoring case if at least one of the following is true:
1132 * <ul>
1133 * <li> The two characters are the same (as compared by the
1134 * {@code ==} operator)
1135 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))}
1136 * on each character produces the same result
1137 * </ul>
1138 *
1139 * <p>Note that this method does <em>not</em> take locale into account, and
1140 * will result in unsatisfactory results for certain locales. The
1141 * {@link java.text.Collator} class provides locale-sensitive comparison.
1142 *
1143 * @param anotherString
1144 * The {@code String} to compare this {@code String} against
1145 *
1146 * @return {@code true} if the argument is not {@code null} and it
1147 * represents an equivalent {@code String} ignoring case; {@code
1148 * false} otherwise
1149 *
1150 * @see #equals(Object)
1151 */
1152 public boolean equalsIgnoreCase(String anotherString) {
1153 return (this == anotherString) ? true
1154 : (anotherString != null)
1155 && (anotherString.length() == length())
1156 && regionMatches(true, 0, anotherString, 0, length());
1157 }
1158
1159 /**
1160 * Compares two strings lexicographically.
1161 * The comparison is based on the Unicode value of each character in
1162 * the strings. The character sequence represented by this
1163 * {@code String} object is compared lexicographically to the
1164 * character sequence represented by the argument string. The result is
1165 * a negative integer if this {@code String} object
1166 * lexicographically precedes the argument string. The result is a
1167 * positive integer if this {@code String} object lexicographically
1168 * follows the argument string. The result is zero if the strings
1169 * are equal; {@code compareTo} returns {@code 0} exactly when
1170 * the {@link #equals(Object)} method would return {@code true}.
1171 * <p>
1172 * This is the definition of lexicographic ordering. If two strings are
1173 * different, then either they have different characters at some index
1174 * that is a valid index for both strings, or their lengths are different,
1175 * or both. If they have different characters at one or more index
1176 * positions, let <i>k</i> be the smallest such index; then the string
1177 * whose character at position <i>k</i> has the smaller value, as
1178 * determined by using the {@code <} operator, lexicographically precedes the
1179 * other string. In this case, {@code compareTo} returns the
1180 * difference of the two character values at position {@code k} in
1181 * the two string -- that is, the value:
1182 * <blockquote><pre>
1183 * this.charAt(k)-anotherString.charAt(k)
1184 * </pre></blockquote>
1185 * If there is no index position at which they differ, then the shorter
1186 * string lexicographically precedes the longer string. In this case,
1187 * {@code compareTo} returns the difference of the lengths of the
1188 * strings -- that is, the value:
1189 * <blockquote><pre>
1190 * this.length()-anotherString.length()
1191 * </pre></blockquote>
1192 *
1193 * <p>For finer-grained String comparison, refer to
1194 * {@link java.text.Collator}.
1195 *
1196 * @param anotherString the {@code String} to be compared.
1197 * @return the value {@code 0} if the argument string is equal to
1198 * this string; a value less than {@code 0} if this string
1199 * is lexicographically less than the string argument; and a
1200 * value greater than {@code 0} if this string is
1201 * lexicographically greater than the string argument.
1202 */
1203 public int compareTo(String anotherString) {
1204 byte v1[] = value;
1205 byte v2[] = anotherString.value;
1206 if (coder() == anotherString.coder()) {
1207 return isLatin1() ? StringLatin1.compareTo(v1, v2)
1208 : StringUTF16.compareTo(v1, v2);
1209 }
1210 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2)
1211 : StringUTF16.compareToLatin1(v1, v2);
1212 }
1213
1214 /**
1215 * A Comparator that orders {@code String} objects as by
1216 * {@code compareToIgnoreCase}. This comparator is serializable.
1217 * <p>
1218 * Note that this Comparator does <em>not</em> take locale into account,
1219 * and will result in an unsatisfactory ordering for certain locales.
1220 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1221 *
1222 * @see java.text.Collator
1223 * @since 1.2
1224 */
1225 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1226 = new CaseInsensitiveComparator();
1227 private static class CaseInsensitiveComparator
1228 implements Comparator<String>, java.io.Serializable {
1229 // use serialVersionUID from JDK 1.2.2 for interoperability
1230 private static final long serialVersionUID = 8575799808933029326L;
1231
1232 public int compare(String s1, String s2) {
1233 byte v1[] = s1.value;
1234 byte v2[] = s2.value;
1235 if (s1.coder() == s2.coder()) {
1236 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2)
1237 : StringUTF16.compareToCI(v1, v2);
1238 }
1239 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2)
1240 : StringUTF16.compareToCI_Latin1(v1, v2);
1241 }
1242
1243 /** Replaces the de-serialized object. */
1244 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1245 }
1246
1247 /**
1248 * Compares two strings lexicographically, ignoring case
1249 * differences. This method returns an integer whose sign is that of
1250 * calling {@code compareTo} with normalized versions of the strings
1251 * where case differences have been eliminated by calling
1252 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1253 * each character.
1254 * <p>
1255 * Note that this method does <em>not</em> take locale into account,
1256 * and will result in an unsatisfactory ordering for certain locales.
1257 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1258 *
1259 * @param str the {@code String} to be compared.
1260 * @return a negative integer, zero, or a positive integer as the
1261 * specified String is greater than, equal to, or less
1262 * than this String, ignoring case considerations.
1263 * @see java.text.Collator
1264 * @since 1.2
1265 */
1266 public int compareToIgnoreCase(String str) {
1267 return CASE_INSENSITIVE_ORDER.compare(this, str);
1268 }
1269
1270 /**
1271 * Tests if two string regions are equal.
1272 * <p>
1273 * A substring of this {@code String} object is compared to a substring
1274 * of the argument other. The result is true if these substrings
1275 * represent identical character sequences. The substring of this
1276 * {@code String} object to be compared begins at index {@code toffset}
1277 * and has length {@code len}. The substring of other to be compared
1278 * begins at index {@code ooffset} and has length {@code len}. The
1279 * result is {@code false} if and only if at least one of the following
1280 * is true:
1281 * <ul><li>{@code toffset} is negative.
1282 * <li>{@code ooffset} is negative.
1283 * <li>{@code toffset+len} is greater than the length of this
1284 * {@code String} object.
1285 * <li>{@code ooffset+len} is greater than the length of the other
1286 * argument.
1287 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1288 * such that:
1289 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1290 * <i>k</i>{@code )}
1291 * </ul>
1292 *
1293 * <p>Note that this method does <em>not</em> take locale into account. The
1294 * {@link java.text.Collator} class provides locale-sensitive comparison.
1295 *
1296 * @param toffset the starting offset of the subregion in this string.
1297 * @param other the string argument.
1298 * @param ooffset the starting offset of the subregion in the string
1299 * argument.
1300 * @param len the number of characters to compare.
1301 * @return {@code true} if the specified subregion of this string
1302 * exactly matches the specified subregion of the string argument;
1303 * {@code false} otherwise.
1304 */
1305 public boolean regionMatches(int toffset, String other, int ooffset, int len) {
1306 byte tv[] = value;
1307 byte ov[] = other.value;
1308 // Note: toffset, ooffset, or len might be near -1>>>1.
1309 if ((ooffset < 0) || (toffset < 0) ||
1310 (toffset > (long)length() - len) ||
1311 (ooffset > (long)other.length() - len)) {
1312 return false;
1313 }
1314 if (coder() == other.coder()) {
1315 if (!isLatin1() && (len > 0)) {
1316 toffset = toffset << 1;
1317 ooffset = ooffset << 1;
1318 len = len << 1;
1319 }
1320 while (len-- > 0) {
1321 if (tv[toffset++] != ov[ooffset++]) {
1322 return false;
1323 }
1324 }
1325 } else {
1326 if (coder() == LATIN1) {
1327 while (len-- > 0) {
1328 if (StringLatin1.getChar(tv, toffset++) !=
1329 StringUTF16.getChar(ov, ooffset++)) {
1330 return false;
1331 }
1332 }
1333 } else {
1334 while (len-- > 0) {
1335 if (StringUTF16.getChar(tv, toffset++) !=
1336 StringLatin1.getChar(ov, ooffset++)) {
1337 return false;
1338 }
1339 }
1340 }
1341 }
1342 return true;
1343 }
1344
1345 /**
1346 * Tests if two string regions are equal.
1347 * <p>
1348 * A substring of this {@code String} object is compared to a substring
1349 * of the argument {@code other}. The result is {@code true} if these
1350 * substrings represent character sequences that are the same, ignoring
1351 * case if and only if {@code ignoreCase} is true. The substring of
1352 * this {@code String} object to be compared begins at index
1353 * {@code toffset} and has length {@code len}. The substring of
1354 * {@code other} to be compared begins at index {@code ooffset} and
1355 * has length {@code len}. The result is {@code false} if and only if
1356 * at least one of the following is true:
1357 * <ul><li>{@code toffset} is negative.
1358 * <li>{@code ooffset} is negative.
1359 * <li>{@code toffset+len} is greater than the length of this
1360 * {@code String} object.
1361 * <li>{@code ooffset+len} is greater than the length of the other
1362 * argument.
1363 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1364 * integer <i>k</i> less than {@code len} such that:
1365 * <blockquote><pre>
1366 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1367 * </pre></blockquote>
1368 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1369 * integer <i>k</i> less than {@code len} such that:
1370 * <blockquote><pre>
1371 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) !=
1372 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k)))
1373 * </pre></blockquote>
1374 * </ul>
1375 *
1376 * <p>Note that this method does <em>not</em> take locale into account,
1377 * and will result in unsatisfactory results for certain locales when
1378 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class
1379 * provides locale-sensitive comparison.
1380 *
1381 * @param ignoreCase if {@code true}, ignore case when comparing
1382 * characters.
1383 * @param toffset the starting offset of the subregion in this
1384 * string.
1385 * @param other the string argument.
1386 * @param ooffset the starting offset of the subregion in the string
1387 * argument.
1388 * @param len the number of characters to compare.
1389 * @return {@code true} if the specified subregion of this string
1390 * matches the specified subregion of the string argument;
1391 * {@code false} otherwise. Whether the matching is exact
1392 * or case insensitive depends on the {@code ignoreCase}
1393 * argument.
1394 */
1395 public boolean regionMatches(boolean ignoreCase, int toffset,
1396 String other, int ooffset, int len) {
1397 if (!ignoreCase) {
1398 return regionMatches(toffset, other, ooffset, len);
1399 }
1400 // Note: toffset, ooffset, or len might be near -1>>>1.
1401 if ((ooffset < 0) || (toffset < 0)
1402 || (toffset > (long)length() - len)
1403 || (ooffset > (long)other.length() - len)) {
1404 return false;
1405 }
1406 byte tv[] = value;
1407 byte ov[] = other.value;
1408 if (coder() == other.coder()) {
1409 return isLatin1()
1410 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len)
1411 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len);
1412 }
1413 return isLatin1()
1414 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len)
1415 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len);
1416 }
1417
1418 /**
1419 * Tests if the substring of this string beginning at the
1420 * specified index starts with the specified prefix.
1421 *
1422 * @param prefix the prefix.
1423 * @param toffset where to begin looking in this string.
1424 * @return {@code true} if the character sequence represented by the
1425 * argument is a prefix of the substring of this object starting
1426 * at index {@code toffset}; {@code false} otherwise.
1427 * The result is {@code false} if {@code toffset} is
1428 * negative or greater than the length of this
1429 * {@code String} object; otherwise the result is the same
1430 * as the result of the expression
1431 * <pre>
1432 * this.substring(toffset).startsWith(prefix)
1433 * </pre>
1434 */
1435 public boolean startsWith(String prefix, int toffset) {
1436 // Note: toffset might be near -1>>>1.
1437 if (toffset < 0 || toffset > length() - prefix.length()) {
1438 return false;
1439 }
1440 byte ta[] = value;
1441 byte pa[] = prefix.value;
1442 int po = 0;
1443 int pc = pa.length;
1444 if (coder() == prefix.coder()) {
1445 int to = isLatin1() ? toffset : toffset << 1;
1446 while (po < pc) {
1447 if (ta[to++] != pa[po++]) {
1448 return false;
1449 }
1450 }
1451 } else {
1452 if (isLatin1()) { // && pcoder == UTF16
1453 return false;
1454 }
1455 // coder == UTF16 && pcoder == LATIN1)
1456 while (po < pc) {
1457 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) {
1458 return false;
1459 }
1460 }
1461 }
1462 return true;
1463 }
1464
1465 /**
1466 * Tests if this string starts with the specified prefix.
1467 *
1468 * @param prefix the prefix.
1469 * @return {@code true} if the character sequence represented by the
1470 * argument is a prefix of the character sequence represented by
1471 * this string; {@code false} otherwise.
1472 * Note also that {@code true} will be returned if the
1473 * argument is an empty string or is equal to this
1474 * {@code String} object as determined by the
1475 * {@link #equals(Object)} method.
1476 * @since 1.0
1477 */
1478 public boolean startsWith(String prefix) {
1479 return startsWith(prefix, 0);
1480 }
1481
1482 /**
1483 * Tests if this string ends with the specified suffix.
1484 *
1485 * @param suffix the suffix.
1486 * @return {@code true} if the character sequence represented by the
1487 * argument is a suffix of the character sequence represented by
1488 * this object; {@code false} otherwise. Note that the
1489 * result will be {@code true} if the argument is the
1490 * empty string or is equal to this {@code String} object
1491 * as determined by the {@link #equals(Object)} method.
1492 */
1493 public boolean endsWith(String suffix) {
1494 return startsWith(suffix, length() - suffix.length());
1495 }
1496
1497 /**
1498 * Returns a hash code for this string. The hash code for a
1499 * {@code String} object is computed as
1500 * <blockquote><pre>
1501 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1502 * </pre></blockquote>
1503 * using {@code int} arithmetic, where {@code s[i]} is the
1504 * <i>i</i>th character of the string, {@code n} is the length of
1505 * the string, and {@code ^} indicates exponentiation.
1506 * (The hash value of the empty string is zero.)
1507 *
1508 * @return a hash code value for this object.
1509 */
1510 public int hashCode() {
1511 int h = hash;
1512 if (h == 0 && value.length > 0) {
1513 hash = h = isLatin1() ? StringLatin1.hashCode(value)
1514 : StringUTF16.hashCode(value);
1515 }
1516 return h;
1517 }
1518
1519 /**
1520 * Returns the index within this string of the first occurrence of
1521 * the specified character. If a character with value
1522 * {@code ch} occurs in the character sequence represented by
1523 * this {@code String} object, then the index (in Unicode
1524 * code units) of the first such occurrence is returned. For
1525 * values of {@code ch} in the range from 0 to 0xFFFF
1526 * (inclusive), this is the smallest value <i>k</i> such that:
1527 * <blockquote><pre>
1528 * this.charAt(<i>k</i>) == ch
1529 * </pre></blockquote>
1530 * is true. For other values of {@code ch}, it is the
1531 * smallest value <i>k</i> such that:
1532 * <blockquote><pre>
1533 * this.codePointAt(<i>k</i>) == ch
1534 * </pre></blockquote>
1535 * is true. In either case, if no such character occurs in this
1536 * string, then {@code -1} is returned.
1537 *
1538 * @param ch a character (Unicode code point).
1539 * @return the index of the first occurrence of the character in the
1540 * character sequence represented by this object, or
1541 * {@code -1} if the character does not occur.
1542 */
1543 public int indexOf(int ch) {
1544 return indexOf(ch, 0);
1545 }
1546
1547 /**
1548 * Returns the index within this string of the first occurrence of the
1549 * specified character, starting the search at the specified index.
1550 * <p>
1551 * If a character with value {@code ch} occurs in the
1552 * character sequence represented by this {@code String}
1553 * object at an index no smaller than {@code fromIndex}, then
1554 * the index of the first such occurrence is returned. For values
1555 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1556 * this is the smallest value <i>k</i> such that:
1557 * <blockquote><pre>
1558 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1559 * </pre></blockquote>
1560 * is true. For other values of {@code ch}, it is the
1561 * smallest value <i>k</i> such that:
1562 * <blockquote><pre>
1563 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1564 * </pre></blockquote>
1565 * is true. In either case, if no such character occurs in this
1566 * string at or after position {@code fromIndex}, then
1567 * {@code -1} is returned.
1568 *
1569 * <p>
1570 * There is no restriction on the value of {@code fromIndex}. If it
1571 * is negative, it has the same effect as if it were zero: this entire
1572 * string may be searched. If it is greater than the length of this
1573 * string, it has the same effect as if it were equal to the length of
1574 * this string: {@code -1} is returned.
1575 *
1576 * <p>All indices are specified in {@code char} values
1577 * (Unicode code units).
1578 *
1579 * @param ch a character (Unicode code point).
1580 * @param fromIndex the index to start the search from.
1581 * @return the index of the first occurrence of the character in the
1582 * character sequence represented by this object that is greater
1583 * than or equal to {@code fromIndex}, or {@code -1}
1584 * if the character does not occur.
1585 */
1586 public int indexOf(int ch, int fromIndex) {
1587 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
1588 : StringUTF16.indexOf(value, ch, fromIndex);
1589 }
1590
1591 /**
1592 * Returns the index within this string of the last occurrence of
1593 * the specified character. For values of {@code ch} in the
1594 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1595 * units) returned is the largest value <i>k</i> such that:
1596 * <blockquote><pre>
1597 * this.charAt(<i>k</i>) == ch
1598 * </pre></blockquote>
1599 * is true. For other values of {@code ch}, it is the
1600 * largest value <i>k</i> such that:
1601 * <blockquote><pre>
1602 * this.codePointAt(<i>k</i>) == ch
1603 * </pre></blockquote>
1604 * is true. In either case, if no such character occurs in this
1605 * string, then {@code -1} is returned. The
1606 * {@code String} is searched backwards starting at the last
1607 * character.
1608 *
1609 * @param ch a character (Unicode code point).
1610 * @return the index of the last occurrence of the character in the
1611 * character sequence represented by this object, or
1612 * {@code -1} if the character does not occur.
1613 */
1614 public int lastIndexOf(int ch) {
1615 return lastIndexOf(ch, length() - 1);
1616 }
1617
1618 /**
1619 * Returns the index within this string of the last occurrence of
1620 * the specified character, searching backward starting at the
1621 * specified index. For values of {@code ch} in the range
1622 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1623 * value <i>k</i> such that:
1624 * <blockquote><pre>
1625 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1626 * </pre></blockquote>
1627 * is true. For other values of {@code ch}, it is the
1628 * largest value <i>k</i> such that:
1629 * <blockquote><pre>
1630 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1631 * </pre></blockquote>
1632 * is true. In either case, if no such character occurs in this
1633 * string at or before position {@code fromIndex}, then
1634 * {@code -1} is returned.
1635 *
1636 * <p>All indices are specified in {@code char} values
1637 * (Unicode code units).
1638 *
1639 * @param ch a character (Unicode code point).
1640 * @param fromIndex the index to start the search from. There is no
1641 * restriction on the value of {@code fromIndex}. If it is
1642 * greater than or equal to the length of this string, it has
1643 * the same effect as if it were equal to one less than the
1644 * length of this string: this entire string may be searched.
1645 * If it is negative, it has the same effect as if it were -1:
1646 * -1 is returned.
1647 * @return the index of the last occurrence of the character in the
1648 * character sequence represented by this object that is less
1649 * than or equal to {@code fromIndex}, or {@code -1}
1650 * if the character does not occur before that point.
1651 */
1652 public int lastIndexOf(int ch, int fromIndex) {
1653 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex)
1654 : StringUTF16.lastIndexOf(value, ch, fromIndex);
1655 }
1656
1657 /**
1658 * Returns the index within this string of the first occurrence of the
1659 * specified substring.
1660 *
1661 * <p>The returned index is the smallest value {@code k} for which:
1662 * <pre>{@code
1663 * this.startsWith(str, k)
1664 * }</pre>
1665 * If no such value of {@code k} exists, then {@code -1} is returned.
1666 *
1667 * @param str the substring to search for.
1668 * @return the index of the first occurrence of the specified substring,
1669 * or {@code -1} if there is no such occurrence.
1670 */
1671 public int indexOf(String str) {
1672 if (coder() == str.coder()) {
1673 return isLatin1() ? StringLatin1.indexOf(value, str.value)
1674 : StringUTF16.indexOf(value, str.value);
1675 }
1676 if (coder() == LATIN1) { // str.coder == UTF16
1677 return -1;
1678 }
1679 return StringUTF16.indexOfLatin1(value, str.value);
1680 }
1681
1682 /**
1683 * Returns the index within this string of the first occurrence of the
1684 * specified substring, starting at the specified index.
1685 *
1686 * <p>The returned index is the smallest value {@code k} for which:
1687 * <pre>{@code
1688 * k >= Math.min(fromIndex, this.length()) &&
1689 * this.startsWith(str, k)
1690 * }</pre>
1691 * If no such value of {@code k} exists, then {@code -1} is returned.
1692 *
1693 * @param str the substring to search for.
1694 * @param fromIndex the index from which to start the search.
1695 * @return the index of the first occurrence of the specified substring,
1696 * starting at the specified index,
1697 * or {@code -1} if there is no such occurrence.
1698 */
1699 public int indexOf(String str, int fromIndex) {
1700 return indexOf(value, coder(), length(), str, fromIndex);
1701 }
1702
1703 /**
1704 * Code shared by String and AbstractStringBuilder to do searches. The
1705 * source is the character array being searched, and the target
1706 * is the string being searched for.
1707 *
1708 * @param src the characters being searched.
1709 * @param srcCoder the coder of the source string.
1710 * @param srcCount length of the source string.
1711 * @param tgtStr the characters being searched for.
1712 * @param fromIndex the index to begin searching from.
1713 */
1714 static int indexOf(byte[] src, byte srcCoder, int srcCount,
1715 String tgtStr, int fromIndex) {
1716 byte[] tgt = tgtStr.value;
1717 byte tgtCoder = tgtStr.coder();
1718 int tgtCount = tgtStr.length();
1719
1720 if (fromIndex >= srcCount) {
1721 return (tgtCount == 0 ? srcCount : -1);
1722 }
1723 if (fromIndex < 0) {
1724 fromIndex = 0;
1725 }
1726 if (tgtCount == 0) {
1727 return fromIndex;
1728 }
1729 if (tgtCount > srcCount) {
1730 return -1;
1731 }
1732 if (srcCoder == tgtCoder) {
1733 return srcCoder == LATIN1
1734 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex)
1735 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex);
1736 }
1737 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1738 return -1;
1739 }
1740 // srcCoder == UTF16 && tgtCoder == LATIN1) {
1741 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1742 }
1743
1744 /**
1745 * Returns the index within this string of the last occurrence of the
1746 * specified substring. The last occurrence of the empty string ""
1747 * is considered to occur at the index value {@code this.length()}.
1748 *
1749 * <p>The returned index is the largest value {@code k} for which:
1750 * <pre>{@code
1751 * this.startsWith(str, k)
1752 * }</pre>
1753 * If no such value of {@code k} exists, then {@code -1} is returned.
1754 *
1755 * @param str the substring to search for.
1756 * @return the index of the last occurrence of the specified substring,
1757 * or {@code -1} if there is no such occurrence.
1758 */
1759 public int lastIndexOf(String str) {
1760 return lastIndexOf(str, length());
1761 }
1762
1763 /**
1764 * Returns the index within this string of the last occurrence of the
1765 * specified substring, searching backward starting at the specified index.
1766 *
1767 * <p>The returned index is the largest value {@code k} for which:
1768 * <pre>{@code
1769 * k <= Math.min(fromIndex, this.length()) &&
1770 * this.startsWith(str, k)
1771 * }</pre>
1772 * If no such value of {@code k} exists, then {@code -1} is returned.
1773 *
1774 * @param str the substring to search for.
1775 * @param fromIndex the index to start the search from.
1776 * @return the index of the last occurrence of the specified substring,
1777 * searching backward from the specified index,
1778 * or {@code -1} if there is no such occurrence.
1779 */
1780 public int lastIndexOf(String str, int fromIndex) {
1781 return lastIndexOf(value, coder(), length(), str, fromIndex);
1782 }
1783
1784 /**
1785 * Code shared by String and AbstractStringBuilder to do searches. The
1786 * source is the character array being searched, and the target
1787 * is the string being searched for.
1788 *
1789 * @param src the characters being searched.
1790 * @param srcCoder coder handles the mapping between bytes/chars
1791 * @param srcCount count of the source string.
1792 * @param tgt the characters being searched for.
1793 * @param fromIndex the index to begin searching from.
1794 */
1795 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount,
1796 String tgtStr, int fromIndex) {
1797 byte[] tgt = tgtStr.value;
1798 byte tgtCoder = tgtStr.coder();
1799 int tgtCount = tgtStr.length();
1800 /*
1801 * Check arguments; return immediately where possible. For
1802 * consistency, don't check for null str.
1803 */
1804 int rightIndex = srcCount - tgtCount;
1805 if (fromIndex > rightIndex) {
1806 fromIndex = rightIndex;
1807 }
1808 if (fromIndex < 0) {
1809 return -1;
1810 }
1811 /* Empty string always matches. */
1812 if (tgtCount == 0) {
1813 return fromIndex;
1814 }
1815 if (srcCoder == tgtCoder) {
1816 return srcCoder == LATIN1
1817 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex)
1818 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex);
1819 }
1820 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1821 return -1;
1822 }
1823 // srcCoder == UTF16 && tgtCoder == LATIN1
1824 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1825 }
1826
1827 /**
1828 * Returns a string that is a substring of this string. The
1829 * substring begins with the character at the specified index and
1830 * extends to the end of this string. <p>
1831 * Examples:
1832 * <blockquote><pre>
1833 * "unhappy".substring(2) returns "happy"
1834 * "Harbison".substring(3) returns "bison"
1835 * "emptiness".substring(9) returns "" (an empty string)
1836 * </pre></blockquote>
1837 *
1838 * @param beginIndex the beginning index, inclusive.
1839 * @return the specified substring.
1840 * @exception IndexOutOfBoundsException if
1841 * {@code beginIndex} is negative or larger than the
1842 * length of this {@code String} object.
1843 */
1844 public String substring(int beginIndex) {
1845 if (beginIndex < 0) {
1846 throw new StringIndexOutOfBoundsException(beginIndex);
1847 }
1848 int subLen = length() - beginIndex;
1849 if (subLen < 0) {
1850 throw new StringIndexOutOfBoundsException(subLen);
1851 }
1852 if (beginIndex == 0) {
1853 return this;
1854 }
1855 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1856 : StringUTF16.newString(value, beginIndex, subLen);
1857 }
1858
1859 /**
1860 * Returns a string that is a substring of this string. The
1861 * substring begins at the specified {@code beginIndex} and
1862 * extends to the character at index {@code endIndex - 1}.
1863 * Thus the length of the substring is {@code endIndex-beginIndex}.
1864 * <p>
1865 * Examples:
1866 * <blockquote><pre>
1867 * "hamburger".substring(4, 8) returns "urge"
1868 * "smiles".substring(1, 5) returns "mile"
1869 * </pre></blockquote>
1870 *
1871 * @param beginIndex the beginning index, inclusive.
1872 * @param endIndex the ending index, exclusive.
1873 * @return the specified substring.
1874 * @exception IndexOutOfBoundsException if the
1875 * {@code beginIndex} is negative, or
1876 * {@code endIndex} is larger than the length of
1877 * this {@code String} object, or
1878 * {@code beginIndex} is larger than
1879 * {@code endIndex}.
1880 */
1881 public String substring(int beginIndex, int endIndex) {
1882 int length = length();
1883 checkBoundsBeginEnd(beginIndex, endIndex, length);
1884 int subLen = endIndex - beginIndex;
1885 if (beginIndex == 0 && endIndex == length) {
1886 return this;
1887 }
1888 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1889 : StringUTF16.newString(value, beginIndex, subLen);
1890 }
1891
1892 /**
1893 * Returns a character sequence that is a subsequence of this sequence.
1894 *
1895 * <p> An invocation of this method of the form
1896 *
1897 * <blockquote><pre>
1898 * str.subSequence(begin, end)</pre></blockquote>
1899 *
1900 * behaves in exactly the same way as the invocation
1901 *
1902 * <blockquote><pre>
1903 * str.substring(begin, end)</pre></blockquote>
1904 *
1905 * @apiNote
1906 * This method is defined so that the {@code String} class can implement
1907 * the {@link CharSequence} interface.
1908 *
1909 * @param beginIndex the begin index, inclusive.
1910 * @param endIndex the end index, exclusive.
1911 * @return the specified subsequence.
1912 *
1913 * @throws IndexOutOfBoundsException
1914 * if {@code beginIndex} or {@code endIndex} is negative,
1915 * if {@code endIndex} is greater than {@code length()},
1916 * or if {@code beginIndex} is greater than {@code endIndex}
1917 *
1918 * @since 1.4
1919 * @spec JSR-51
1920 */
1921 public CharSequence subSequence(int beginIndex, int endIndex) {
1922 return this.substring(beginIndex, endIndex);
1923 }
1924
1925 /**
1926 * Concatenates the specified string to the end of this string.
1927 * <p>
1928 * If the length of the argument string is {@code 0}, then this
1929 * {@code String} object is returned. Otherwise, a
1930 * {@code String} object is returned that represents a character
1931 * sequence that is the concatenation of the character sequence
1932 * represented by this {@code String} object and the character
1933 * sequence represented by the argument string.<p>
1934 * Examples:
1935 * <blockquote><pre>
1936 * "cares".concat("s") returns "caress"
1937 * "to".concat("get").concat("her") returns "together"
1938 * </pre></blockquote>
1939 *
1940 * @param str the {@code String} that is concatenated to the end
1941 * of this {@code String}.
1942 * @return a string that represents the concatenation of this object's
1943 * characters followed by the string argument's characters.
1944 */
1945 public String concat(String str) {
1946 if (str.isEmpty()) {
1947 return this;
1948 }
1949 if (coder() == str.coder()) {
1950 byte[] val = this.value;
1951 byte[] oval = str.value;
1952 int len = val.length + oval.length;
1953 byte[] buf = Arrays.copyOf(val, len);
1954 System.arraycopy(oval, 0, buf, val.length, oval.length);
1955 return new String(buf, coder);
1956 }
1957 int len = length();
1958 int olen = str.length();
1959 byte[] buf = StringUTF16.newBytesFor(len + olen);
1960 getBytes(buf, 0, UTF16);
1961 str.getBytes(buf, len, UTF16);
1962 return new String(buf, UTF16);
1963 }
1964
1965 /**
1966 * Returns a string resulting from replacing all occurrences of
1967 * {@code oldChar} in this string with {@code newChar}.
1968 * <p>
1969 * If the character {@code oldChar} does not occur in the
1970 * character sequence represented by this {@code String} object,
1971 * then a reference to this {@code String} object is returned.
1972 * Otherwise, a {@code String} object is returned that
1973 * represents a character sequence identical to the character sequence
1974 * represented by this {@code String} object, except that every
1975 * occurrence of {@code oldChar} is replaced by an occurrence
1976 * of {@code newChar}.
1977 * <p>
1978 * Examples:
1979 * <blockquote><pre>
1980 * "mesquite in your cellar".replace('e', 'o')
1981 * returns "mosquito in your collar"
1982 * "the war of baronets".replace('r', 'y')
1983 * returns "the way of bayonets"
1984 * "sparring with a purple porpoise".replace('p', 't')
1985 * returns "starring with a turtle tortoise"
1986 * "JonL".replace('q', 'x') returns "JonL" (no change)
1987 * </pre></blockquote>
1988 *
1989 * @param oldChar the old character.
1990 * @param newChar the new character.
1991 * @return a string derived from this string by replacing every
1992 * occurrence of {@code oldChar} with {@code newChar}.
1993 */
1994 public String replace(char oldChar, char newChar) {
1995 if (oldChar != newChar) {
1996 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar)
1997 : StringUTF16.replace(value, oldChar, newChar);
1998 if (ret != null) {
1999 return ret;
2000 }
2001 }
2002 return this;
2003 }
2004
2005 /**
2006 * Tells whether or not this string matches the given <a
2007 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2008 *
2009 * <p> An invocation of this method of the form
2010 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2011 * same result as the expression
2012 *
2013 * <blockquote>
2014 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2015 * matches(<i>regex</i>, <i>str</i>)}
2016 * </blockquote>
2017 *
2018 * @param regex
2019 * the regular expression to which this string is to be matched
2020 *
2021 * @return {@code true} if, and only if, this string matches the
2022 * given regular expression
2023 *
2024 * @throws PatternSyntaxException
2025 * if the regular expression's syntax is invalid
2026 *
2027 * @see java.util.regex.Pattern
2028 *
2029 * @since 1.4
2030 * @spec JSR-51
2031 */
2032 public boolean matches(String regex) {
2033 return Pattern.matches(regex, this);
2034 }
2035
2036 /**
2037 * Returns true if and only if this string contains the specified
2038 * sequence of char values.
2039 *
2040 * @param s the sequence to search for
2041 * @return true if this string contains {@code s}, false otherwise
2042 * @since 1.5
2043 */
2044 public boolean contains(CharSequence s) {
2045 return indexOf(s.toString()) >= 0;
2046 }
2047
2048 /**
2049 * Replaces the first substring of this string that matches the given <a
2050 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2051 * given replacement.
2052 *
2053 * <p> An invocation of this method of the form
2054 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2055 * yields exactly the same result as the expression
2056 *
2057 * <blockquote>
2058 * <code>
2059 * {@link java.util.regex.Pattern}.{@link
2060 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2061 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2062 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2063 * </code>
2064 * </blockquote>
2065 *
2066 *<p>
2067 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2068 * replacement string may cause the results to be different than if it were
2069 * being treated as a literal replacement string; see
2070 * {@link java.util.regex.Matcher#replaceFirst}.
2071 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2072 * meaning of these characters, if desired.
2073 *
2074 * @param regex
2075 * the regular expression to which this string is to be matched
2076 * @param replacement
2077 * the string to be substituted for the first match
2078 *
2079 * @return The resulting {@code String}
2080 *
2081 * @throws PatternSyntaxException
2082 * if the regular expression's syntax is invalid
2083 *
2084 * @see java.util.regex.Pattern
2085 *
2086 * @since 1.4
2087 * @spec JSR-51
2088 */
2089 public String replaceFirst(String regex, String replacement) {
2090 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2091 }
2092
2093 /**
2094 * Replaces each substring of this string that matches the given <a
2095 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2096 * given replacement.
2097 *
2098 * <p> An invocation of this method of the form
2099 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2100 * yields exactly the same result as the expression
2101 *
2102 * <blockquote>
2103 * <code>
2104 * {@link java.util.regex.Pattern}.{@link
2105 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2106 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2107 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2108 * </code>
2109 * </blockquote>
2110 *
2111 *<p>
2112 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2113 * replacement string may cause the results to be different than if it were
2114 * being treated as a literal replacement string; see
2115 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2116 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2117 * meaning of these characters, if desired.
2118 *
2119 * @param regex
2120 * the regular expression to which this string is to be matched
2121 * @param replacement
2122 * the string to be substituted for each match
2123 *
2124 * @return The resulting {@code String}
2125 *
2126 * @throws PatternSyntaxException
2127 * if the regular expression's syntax is invalid
2128 *
2129 * @see java.util.regex.Pattern
2130 *
2131 * @since 1.4
2132 * @spec JSR-51
2133 */
2134 public String replaceAll(String regex, String replacement) {
2135 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2136 }
2137
2138 /**
2139 * Replaces each substring of this string that matches the literal target
2140 * sequence with the specified literal replacement sequence. The
2141 * replacement proceeds from the beginning of the string to the end, for
2142 * example, replacing "aa" with "b" in the string "aaa" will result in
2143 * "ba" rather than "ab".
2144 *
2145 * @param target The sequence of char values to be replaced
2146 * @param replacement The replacement sequence of char values
2147 * @return The resulting string
2148 * @since 1.5
2149 */
2150 public String replace(CharSequence target, CharSequence replacement) {
2151 String tgtStr = target.toString();
2152 String replStr = replacement.toString();
2153 int j = indexOf(tgtStr);
2154 if (j < 0) {
2155 return this;
2156 }
2157 int tgtLen = tgtStr.length();
2158 int tgtLen1 = Math.max(tgtLen, 1);
2159 int thisLen = length();
2160
2161 int newLenHint = thisLen - tgtLen + replStr.length();
2162 if (newLenHint < 0) {
2163 throw new OutOfMemoryError();
2164 }
2165 StringBuilder sb = new StringBuilder(newLenHint);
2166 int i = 0;
2167 do {
2168 sb.append(this, i, j).append(replStr);
2169 i = j + tgtLen;
2170 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0);
2171 return sb.append(this, i, thisLen).toString();
2172 }
2173
2174 /**
2175 * Splits this string around matches of the given
2176 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2177 *
2178 * <p> The array returned by this method contains each substring of this
2179 * string that is terminated by another substring that matches the given
2180 * expression or is terminated by the end of the string. The substrings in
2181 * the array are in the order in which they occur in this string. If the
2182 * expression does not match any part of the input then the resulting array
2183 * has just one element, namely this string.
2184 *
2185 * <p> When there is a positive-width match at the beginning of this
2186 * string then an empty leading substring is included at the beginning
2187 * of the resulting array. A zero-width match at the beginning however
2188 * never produces such empty leading substring.
2189 *
2190 * <p> The {@code limit} parameter controls the number of times the
2191 * pattern is applied and therefore affects the length of the resulting
2192 * array.
2193 * <ul>
2194 * <li><p>
2195 * If the <i>limit</i> is positive then the pattern will be applied
2196 * at most <i>limit</i> - 1 times, the array's length will be
2197 * no greater than <i>limit</i>, and the array's last entry will contain
2198 * all input beyond the last matched delimiter.</p></li>
2199 *
2200 * <li><p>
2201 * If the <i>limit</i> is zero then the pattern will be applied as
2202 * many times as possible, the array can have any length, and trailing
2203 * empty strings will be discarded.</p></li>
2204 *
2205 * <li><p>
2206 * If the <i>limit</i> is negative then the pattern will be applied
2207 * as many times as possible and the array can have any length.</p></li>
2208 * </ul>
2209 *
2210 * <p> The string {@code "boo:and:foo"}, for example, yields the
2211 * following results with these parameters:
2212 *
2213 * <blockquote><table class="plain">
2214 * <caption style="display:none">Split example showing regex, limit, and result</caption>
2215 * <thead>
2216 * <tr>
2217 * <th scope="col">Regex</th>
2218 * <th scope="col">Limit</th>
2219 * <th scope="col">Result</th>
2220 * </tr>
2221 * </thead>
2222 * <tbody>
2223 * <tr><th scope="row" rowspan="3" style="font-weight:normal">:</th>
2224 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">2</th>
2225 * <td>{@code { "boo", "and:foo" }}</td></tr>
2226 * <tr><!-- : -->
2227 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2228 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2229 * <tr><!-- : -->
2230 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2231 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2232 * <tr><th scope="row" rowspan="3" style="font-weight:normal">o</th>
2233 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2234 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2235 * <tr><!-- o -->
2236 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2237 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2238 * <tr><!-- o -->
2239 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">0</th>
2240 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2241 * </tbody>
2242 * </table></blockquote>
2243 *
2244 * <p> An invocation of this method of the form
2245 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2246 * yields the same result as the expression
2247 *
2248 * <blockquote>
2249 * <code>
2250 * {@link java.util.regex.Pattern}.{@link
2251 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2252 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2253 * </code>
2254 * </blockquote>
2255 *
2256 *
2257 * @param regex
2258 * the delimiting regular expression
2259 *
2260 * @param limit
2261 * the result threshold, as described above
2262 *
2263 * @return the array of strings computed by splitting this string
2264 * around matches of the given regular expression
2265 *
2266 * @throws PatternSyntaxException
2267 * if the regular expression's syntax is invalid
2268 *
2269 * @see java.util.regex.Pattern
2270 *
2271 * @since 1.4
2272 * @spec JSR-51
2273 */
2274 public String[] split(String regex, int limit) {
2275 /* fastpath if the regex is a
2276 (1)one-char String and this character is not one of the
2277 RegEx's meta characters ".$|()[{^?*+\\", or
2278 (2)two-char String and the first char is the backslash and
2279 the second is not the ascii digit or ascii letter.
2280 */
2281 char ch = 0;
2282 if (((regex.length() == 1 &&
2283 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2284 (regex.length() == 2 &&
2285 regex.charAt(0) == '\\' &&
2286 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2287 ((ch-'a')|('z'-ch)) < 0 &&
2288 ((ch-'A')|('Z'-ch)) < 0)) &&
2289 (ch < Character.MIN_HIGH_SURROGATE ||
2290 ch > Character.MAX_LOW_SURROGATE))
2291 {
2292 int off = 0;
2293 int next = 0;
2294 boolean limited = limit > 0;
2295 ArrayList<String> list = new ArrayList<>();
2296 while ((next = indexOf(ch, off)) != -1) {
2297 if (!limited || list.size() < limit - 1) {
2298 list.add(substring(off, next));
2299 off = next + 1;
2300 } else { // last one
2301 //assert (list.size() == limit - 1);
2302 int last = length();
2303 list.add(substring(off, last));
2304 off = last;
2305 break;
2306 }
2307 }
2308 // If no match was found, return this
2309 if (off == 0)
2310 return new String[]{this};
2311
2312 // Add remaining segment
2313 if (!limited || list.size() < limit)
2314 list.add(substring(off, length()));
2315
2316 // Construct result
2317 int resultSize = list.size();
2318 if (limit == 0) {
2319 while (resultSize > 0 && list.get(resultSize - 1).isEmpty()) {
2320 resultSize--;
2321 }
2322 }
2323 String[] result = new String[resultSize];
2324 return list.subList(0, resultSize).toArray(result);
2325 }
2326 return Pattern.compile(regex).split(this, limit);
2327 }
2328
2329 /**
2330 * Splits this string around matches of the given <a
2331 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2332 *
2333 * <p> This method works as if by invoking the two-argument {@link
2334 * #split(String, int) split} method with the given expression and a limit
2335 * argument of zero. Trailing empty strings are therefore not included in
2336 * the resulting array.
2337 *
2338 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2339 * results with these expressions:
2340 *
2341 * <blockquote><table class="plain">
2342 * <caption style="display:none">Split examples showing regex and result</caption>
2343 * <thead>
2344 * <tr>
2345 * <th scope="col">Regex</th>
2346 * <th scope="col">Result</th>
2347 * </tr>
2348 * </thead>
2349 * <tbody>
2350 * <tr><th scope="row" style="text-weight:normal">:</th>
2351 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2352 * <tr><th scope="row" style="text-weight:normal">o</th>
2353 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2354 * </tbody>
2355 * </table></blockquote>
2356 *
2357 *
2358 * @param regex
2359 * the delimiting regular expression
2360 *
2361 * @return the array of strings computed by splitting this string
2362 * around matches of the given regular expression
2363 *
2364 * @throws PatternSyntaxException
2365 * if the regular expression's syntax is invalid
2366 *
2367 * @see java.util.regex.Pattern
2368 *
2369 * @since 1.4
2370 * @spec JSR-51
2371 */
2372 public String[] split(String regex) {
2373 return split(regex, 0);
2374 }
2375
2376 /**
2377 * Returns a new String composed of copies of the
2378 * {@code CharSequence elements} joined together with a copy of
2379 * the specified {@code delimiter}.
2380 *
2381 * <blockquote>For example,
2382 * <pre>{@code
2383 * String message = String.join("-", "Java", "is", "cool");
2384 * // message returned is: "Java-is-cool"
2385 * }</pre></blockquote>
2386 *
2387 * Note that if an element is null, then {@code "null"} is added.
2388 *
2389 * @param delimiter the delimiter that separates each element
2390 * @param elements the elements to join together.
2391 *
2392 * @return a new {@code String} that is composed of the {@code elements}
2393 * separated by the {@code delimiter}
2394 *
2395 * @throws NullPointerException If {@code delimiter} or {@code elements}
2396 * is {@code null}
2397 *
2398 * @see java.util.StringJoiner
2399 * @since 1.8
2400 */
2401 public static String join(CharSequence delimiter, CharSequence... elements) {
2402 Objects.requireNonNull(delimiter);
2403 Objects.requireNonNull(elements);
2404 // Number of elements not likely worth Arrays.stream overhead.
2405 StringJoiner joiner = new StringJoiner(delimiter);
2406 for (CharSequence cs: elements) {
2407 joiner.add(cs);
2408 }
2409 return joiner.toString();
2410 }
2411
2412 /**
2413 * Returns a new {@code String} composed of copies of the
2414 * {@code CharSequence elements} joined together with a copy of the
2415 * specified {@code delimiter}.
2416 *
2417 * <blockquote>For example,
2418 * <pre>{@code
2419 * List<String> strings = List.of("Java", "is", "cool");
2420 * String message = String.join(" ", strings);
2421 * //message returned is: "Java is cool"
2422 *
2423 * Set<String> strings =
2424 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool"));
2425 * String message = String.join("-", strings);
2426 * //message returned is: "Java-is-very-cool"
2427 * }</pre></blockquote>
2428 *
2429 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2430 *
2431 * @param delimiter a sequence of characters that is used to separate each
2432 * of the {@code elements} in the resulting {@code String}
2433 * @param elements an {@code Iterable} that will have its {@code elements}
2434 * joined together.
2435 *
2436 * @return a new {@code String} that is composed from the {@code elements}
2437 * argument
2438 *
2439 * @throws NullPointerException If {@code delimiter} or {@code elements}
2440 * is {@code null}
2441 *
2442 * @see #join(CharSequence,CharSequence...)
2443 * @see java.util.StringJoiner
2444 * @since 1.8
2445 */
2446 public static String join(CharSequence delimiter,
2447 Iterable<? extends CharSequence> elements) {
2448 Objects.requireNonNull(delimiter);
2449 Objects.requireNonNull(elements);
2450 StringJoiner joiner = new StringJoiner(delimiter);
2451 for (CharSequence cs: elements) {
2452 joiner.add(cs);
2453 }
2454 return joiner.toString();
2455 }
2456
2457 /**
2458 * Converts all of the characters in this {@code String} to lower
2459 * case using the rules of the given {@code Locale}. Case mapping is based
2460 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2461 * class. Since case mappings are not always 1:1 char mappings, the resulting
2462 * {@code String} may be a different length than the original {@code String}.
2463 * <p>
2464 * Examples of lowercase mappings are in the following table:
2465 * <table class="plain">
2466 * <caption style="display:none">Lowercase mapping examples showing language code of locale, upper case, lower case, and description</caption>
2467 * <thead>
2468 * <tr>
2469 * <th scope="col">Language Code of Locale</th>
2470 * <th scope="col">Upper Case</th>
2471 * <th scope="col">Lower Case</th>
2472 * <th scope="col">Description</th>
2473 * </tr>
2474 * </thead>
2475 * <tbody>
2476 * <tr>
2477 * <td>tr (Turkish)</td>
2478 * <th scope="row" style="font-weight:normal; text-align:left">\u0130</th>
2479 * <td>\u0069</td>
2480 * <td>capital letter I with dot above -> small letter i</td>
2481 * </tr>
2482 * <tr>
2483 * <td>tr (Turkish)</td>
2484 * <th scope="row" style="font-weight:normal; text-align:left">\u0049</th>
2485 * <td>\u0131</td>
2486 * <td>capital letter I -> small letter dotless i </td>
2487 * </tr>
2488 * <tr>
2489 * <td>(all)</td>
2490 * <th scope="row" style="font-weight:normal; text-align:left">French Fries</th>
2491 * <td>french fries</td>
2492 * <td>lowercased all chars in String</td>
2493 * </tr>
2494 * <tr>
2495 * <td>(all)</td>
2496 * <th scope="row" style="font-weight:normal; text-align:left">
2497 * ΙΧΘΥΣ</th>
2498 * <td>ιχθυσ</td>
2499 * <td>lowercased all chars in String</td>
2500 * </tr>
2501 * </tbody>
2502 * </table>
2503 *
2504 * @param locale use the case transformation rules for this locale
2505 * @return the {@code String}, converted to lowercase.
2506 * @see java.lang.String#toLowerCase()
2507 * @see java.lang.String#toUpperCase()
2508 * @see java.lang.String#toUpperCase(Locale)
2509 * @since 1.1
2510 */
2511 public String toLowerCase(Locale locale) {
2512 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale)
2513 : StringUTF16.toLowerCase(this, value, locale);
2514 }
2515
2516 /**
2517 * Converts all of the characters in this {@code String} to lower
2518 * case using the rules of the default locale. This is equivalent to calling
2519 * {@code toLowerCase(Locale.getDefault())}.
2520 * <p>
2521 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2522 * results if used for strings that are intended to be interpreted locale
2523 * independently.
2524 * Examples are programming language identifiers, protocol keys, and HTML
2525 * tags.
2526 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2527 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2528 * LATIN SMALL LETTER DOTLESS I character.
2529 * To obtain correct results for locale insensitive strings, use
2530 * {@code toLowerCase(Locale.ROOT)}.
2531 *
2532 * @return the {@code String}, converted to lowercase.
2533 * @see java.lang.String#toLowerCase(Locale)
2534 */
2535 public String toLowerCase() {
2536 return toLowerCase(Locale.getDefault());
2537 }
2538
2539 /**
2540 * Converts all of the characters in this {@code String} to upper
2541 * case using the rules of the given {@code Locale}. Case mapping is based
2542 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2543 * class. Since case mappings are not always 1:1 char mappings, the resulting
2544 * {@code String} may be a different length than the original {@code String}.
2545 * <p>
2546 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2547 *
2548 * <table class="plain">
2549 * <caption style="display:none">Examples of locale-sensitive and 1:M case mappings. Shows Language code of locale, lower case, upper case, and description.</caption>
2550 * <thead>
2551 * <tr>
2552 * <th scope="col">Language Code of Locale</th>
2553 * <th scope="col">Lower Case</th>
2554 * <th scope="col">Upper Case</th>
2555 * <th scope="col">Description</th>
2556 * </tr>
2557 * </thead>
2558 * <tbody>
2559 * <tr>
2560 * <td>tr (Turkish)</td>
2561 * <th scope="row" style="font-weight:normal; text-align:left">\u0069</th>
2562 * <td>\u0130</td>
2563 * <td>small letter i -> capital letter I with dot above</td>
2564 * </tr>
2565 * <tr>
2566 * <td>tr (Turkish)</td>
2567 * <th scope="row" style="font-weight:normal; text-align:left">\u0131</th>
2568 * <td>\u0049</td>
2569 * <td>small letter dotless i -> capital letter I</td>
2570 * </tr>
2571 * <tr>
2572 * <td>(all)</td>
2573 * <th scope="row" style="font-weight:normal; text-align:left">\u00df</th>
2574 * <td>\u0053 \u0053</td>
2575 * <td>small letter sharp s -> two letters: SS</td>
2576 * </tr>
2577 * <tr>
2578 * <td>(all)</td>
2579 * <th scope="row" style="font-weight:normal; text-align:left">Fahrvergnügen</th>
2580 * <td>FAHRVERGNÜGEN</td>
2581 * <td></td>
2582 * </tr>
2583 * </tbody>
2584 * </table>
2585 * @param locale use the case transformation rules for this locale
2586 * @return the {@code String}, converted to uppercase.
2587 * @see java.lang.String#toUpperCase()
2588 * @see java.lang.String#toLowerCase()
2589 * @see java.lang.String#toLowerCase(Locale)
2590 * @since 1.1
2591 */
2592 public String toUpperCase(Locale locale) {
2593 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale)
2594 : StringUTF16.toUpperCase(this, value, locale);
2595 }
2596
2597 /**
2598 * Converts all of the characters in this {@code String} to upper
2599 * case using the rules of the default locale. This method is equivalent to
2600 * {@code toUpperCase(Locale.getDefault())}.
2601 * <p>
2602 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2603 * results if used for strings that are intended to be interpreted locale
2604 * independently.
2605 * Examples are programming language identifiers, protocol keys, and HTML
2606 * tags.
2607 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2608 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2609 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2610 * To obtain correct results for locale insensitive strings, use
2611 * {@code toUpperCase(Locale.ROOT)}.
2612 *
2613 * @return the {@code String}, converted to uppercase.
2614 * @see java.lang.String#toUpperCase(Locale)
2615 */
2616 public String toUpperCase() {
2617 return toUpperCase(Locale.getDefault());
2618 }
2619
2620 /**
2621 * Returns a string whose value is this string, with all leading
2622 * and trailing space removed, where space is defined
2623 * as any character whose codepoint is less than or equal to
2624 * {@code 'U+0020'} (the space character).
2625 * <p>
2626 * If this {@code String} object represents an empty character
2627 * sequence, or the first and last characters of character sequence
2628 * represented by this {@code String} object both have codes
2629 * that are not space (as defined above), then a
2630 * reference to this {@code String} object is returned.
2631 * <p>
2632 * Otherwise, if all characters in this string are space (as
2633 * defined above), then a {@code String} object representing an
2634 * empty string is returned.
2635 * <p>
2636 * Otherwise, let <i>k</i> be the index of the first character in the
2637 * string whose code is not a space (as defined above) and let
2638 * <i>m</i> be the index of the last character in the string whose code
2639 * is not a space (as defined above). A {@code String}
2640 * object is returned, representing the substring of this string that
2641 * begins with the character at index <i>k</i> and ends with the
2642 * character at index <i>m</i>-that is, the result of
2643 * {@code this.substring(k, m + 1)}.
2644 * <p>
2645 * This method may be used to trim space (as defined above) from
2646 * the beginning and end of a string.
2647 *
2648 * @return a string whose value is this string, with all leading
2649 * and trailing space removed, or this string if it
2650 * has no leading or trailing space.
2651 */
2652 public String trim() {
2653 String ret = isLatin1() ? StringLatin1.trim(value)
2654 : StringUTF16.trim(value);
2655 return ret == null ? this : ret;
2656 }
2657
2658 /**
2659 * Returns a string whose value is this string, with all leading
2660 * and trailing {@link Character#isWhitespace(int) white space}
2661 * removed.
2662 * <p>
2663 * If this {@code String} object represents an empty string,
2664 * or if all code points in this string are
2665 * {@link Character#isWhitespace(int) white space}, then an empty string
2666 * is returned.
2667 * <p>
2668 * Otherwise, returns a substring of this string beginning with the first
2669 * code point that is not a {@link Character#isWhitespace(int) white space}
2670 * up to and including the last code point that is not a
2671 * {@link Character#isWhitespace(int) white space}.
2672 * <p>
2673 * This method may be used to strip
2674 * {@link Character#isWhitespace(int) white space} from
2675 * the beginning and end of a string.
2676 *
2677 * @return a string whose value is this string, with all leading
2678 * and trailing white space removed
2679 *
2680 * @see Character#isWhitespace(int)
2681 *
2682 * @since 11
2683 */
2684 public String strip() {
2685 String ret = isLatin1() ? StringLatin1.strip(value)
2686 : StringUTF16.strip(value);
2687 return ret == null ? this : ret;
2688 }
2689
2690 /**
2691 * Returns a string whose value is this string, with all leading
2692 * {@link Character#isWhitespace(int) white space} removed.
2693 * <p>
2694 * If this {@code String} object represents an empty string,
2695 * or if all code points in this string are
2696 * {@link Character#isWhitespace(int) white space}, then an empty string
2697 * is returned.
2698 * <p>
2699 * Otherwise, returns a substring of this string beginning with the first
2700 * code point that is not a {@link Character#isWhitespace(int) white space}
2701 * up to to and including the last code point of this string.
2702 * <p>
2703 * This method may be used to trim
2704 * {@link Character#isWhitespace(int) white space} from
2705 * the beginning of a string.
2706 *
2707 * @return a string whose value is this string, with all leading white
2708 * space removed
2709 *
2710 * @see Character#isWhitespace(int)
2711 *
2712 * @since 11
2713 */
2714 public String stripLeading() {
2715 String ret = isLatin1() ? StringLatin1.stripLeading(value)
2716 : StringUTF16.stripLeading(value);
2717 return ret == null ? this : ret;
2718 }
2719
2720 /**
2721 * Returns a string whose value is this string, with all trailing
2722 * {@link Character#isWhitespace(int) white space} removed.
2723 * <p>
2724 * If this {@code String} object represents an empty string,
2725 * or if all characters in this string are
2726 * {@link Character#isWhitespace(int) white space}, then an empty string
2727 * is returned.
2728 * <p>
2729 * Otherwise, returns a substring of this string beginning with the first
2730 * code point of this string up to and including the last code point
2731 * that is not a {@link Character#isWhitespace(int) white space}.
2732 * <p>
2733 * This method may be used to trim
2734 * {@link Character#isWhitespace(int) white space} from
2735 * the end of a string.
2736 *
2737 * @return a string whose value is this string, with all trailing white
2738 * space removed
2739 *
2740 * @see Character#isWhitespace(int)
2741 *
2742 * @since 11
2743 */
2744 public String stripTrailing() {
2745 String ret = isLatin1() ? StringLatin1.stripTrailing(value)
2746 : StringUTF16.stripTrailing(value);
2747 return ret == null ? this : ret;
2748 }
2749
2750 /**
2751 * Returns {@code true} if the string is empty or contains only
2752 * {@link Character#isWhitespace(int) white space} codepoints,
2753 * otherwise {@code false}.
2754 *
2755 * @return {@code true} if the string is empty or contains only
2756 * {@link Character#isWhitespace(int) white space} codepoints,
2757 * otherwise {@code false}
2758 *
2759 * @see Character#isWhitespace(int)
2760 *
2761 * @since 11
2762 */
2763 public boolean isBlank() {
2764 return indexOfNonWhitespace() == length();
2765 }
2766
2767 private Stream<String> lines(int maxLeading, int maxTrailing) {
2768 return isLatin1() ? StringLatin1.lines(value, maxLeading, maxTrailing)
2769 : StringUTF16.lines(value, maxLeading, maxTrailing);
2770 }
2771
2772 /**
2773 * Returns a stream of lines extracted from this string,
2774 * separated by line terminators.
2775 * <p>
2776 * A <i>line terminator</i> is one of the following:
2777 * a line feed character {@code "\n"} (U+000A),
2778 * a carriage return character {@code "\r"} (U+000D),
2779 * or a carriage return followed immediately by a line feed
2780 * {@code "\r\n"} (U+000D U+000A).
2781 * <p>
2782 * A <i>line</i> is either a sequence of zero or more characters
2783 * followed by a line terminator, or it is a sequence of one or
2784 * more characters followed by the end of the string. A
2785 * line does not include the line terminator.
2786 * <p>
2787 * The stream returned by this method contains the lines from
2788 * this string in the order in which they occur.
2789 *
2790 * @apiNote This definition of <i>line</i> implies that an empty
2791 * string has zero lines and that there is no empty line
2792 * following a line terminator at the end of a string.
2793 *
2794 * @implNote This method provides better performance than
2795 * split("\R") by supplying elements lazily and
2796 * by faster search of new line terminators.
2797 *
2798 * @return the stream of lines extracted from this string
2799 *
2800 * @since 11
2801 */
2802 public Stream<String> lines() {
2803 return lines(0, 0);
2804 }
2805
2806 /**
2807 * Adjusts the indentation of each line of this string based on the value of
2808 * {@code n}, and normalizes line termination characters.
2809 * <p>
2810 * This string is conceptually separated into lines using
2811 * {@link String#lines()}. Each line is then adjusted as described below
2812 * and then suffixed with a line feed {@code "\n"} (U+000A). The resulting
2813 * lines are then concatenated and returned.
2814 * <p>
2815 * If {@code n > 0} then {@code n} spaces (U+0020) are inserted at the
2816 * beginning of each line.
2817 * <p>
2818 * If {@code n < 0} then up to {@code n}
2819 * {@link Character#isWhitespace(int) white space characters} are removed
2820 * from the beginning of each line. If a given line does not contain
2821 * sufficient white space then all leading
2822 * {@link Character#isWhitespace(int) white space characters} are removed.
2823 * Each white space character is treated as a single character. In
2824 * particular, the tab character {@code "\t"} (U+0009) is considered a
2825 * single character; it is not expanded.
2826 * <p>
2827 * If {@code n == 0} then the line remains unchanged. However, line
2828 * terminators are still normalized.
2829 *
2830 * @param n number of leading
2831 * {@link Character#isWhitespace(int) white space characters}
2832 * to add or remove
2833 *
2834 * @return string with indentation adjusted and line endings normalized
2835 *
2836 * @see String#lines()
2837 * @see String#isBlank()
2838 * @see Character#isWhitespace(int)
2839 *
2840 * @since 12
2841 */
2842 public String indent(int n) {
2843 return isEmpty() ? "" : indent(n, false);
2844 }
2845
2846 private String indent(int n, boolean removeBlanks) {
2847 Stream<String> stream = removeBlanks ? lines(Integer.MAX_VALUE, Integer.MAX_VALUE)
2848 : lines();
2849 if (n > 0) {
2850 final String spaces = " ".repeat(n);
2851 stream = stream.map(s -> spaces + s);
2852 } else if (n == Integer.MIN_VALUE) {
2853 stream = stream.map(s -> s.stripLeading());
2854 } else if (n < 0) {
2855 stream = stream.map(s -> s.substring(Math.min(-n, s.indexOfNonWhitespace())));
2856 }
2857 return stream.collect(Collectors.joining("\n", "", "\n"));
2858 }
2859
2860 private int indexOfNonWhitespace() {
2861 return isLatin1() ? StringLatin1.indexOfNonWhitespace(value)
2862 : StringUTF16.indexOfNonWhitespace(value);
2863 }
2864
2865 private int lastIndexOfNonWhitespace() {
2866 return isLatin1() ? StringLatin1.lastIndexOfNonWhitespace(value)
2867 : StringUTF16.lastIndexOfNonWhitespace(value);
2868 }
2869
2870 /**
2871 * Removes vertical and horizontal white space margins from around the
2872 * essential body of a multi-line string, while preserving relative
2873 * indentation.
2874 * <p>
2875 * This string is first conceptually separated into lines as if by
2876 * {@link String#lines()}.
2877 * <p>
2878 * Then, the <i>minimum indentation</i> (min) is determined as follows. For
2879 * each non-blank line (as defined by {@link String#isBlank()}), the
2880 * leading {@link Character#isWhitespace(int) white space} characters are
2881 * counted. The <i>min</i> value is the smallest of these counts.
2882 * <p>
2883 * For each non-blank line, <i>min</i> leading white space characters are
2884 * removed. Each white space character is treated as a single character. In
2885 * particular, the tab character {@code "\t"} (U+0009) is considered a
2886 * single character; it is not expanded.
2887 * <p>
2888 * Leading and trailing blank lines, if any, are removed. Trailing spaces are
2889 * preserved.
2890 * <p>
2891 * Each line is suffixed with a line feed character {@code "\n"} (U+000A).
2892 * <p>
2893 * Finally, the lines are concatenated into a single string and returned.
2894 *
2895 * @apiNote
2896 * This method's primary purpose is to shift a block of lines as far as
2897 * possible to the left, while preserving relative indentation. Lines
2898 * that were indented the least will thus have no leading white space.
2899 *
2900 * Example:
2901 * <blockquote><pre>
2902 * `
2903 * This is the first line
2904 * This is the second line
2905 * `.align();
2906 *
2907 * returns
2908 * This is the first line
2909 * This is the second line
2910 * </pre></blockquote>
2911 *
2912 * @return string with margins removed and line terminators normalized
2913 *
2914 * @see String#lines()
2915 * @see String#isBlank()
2916 * @see String#indent(int)
2917 * @see Character#isWhitespace(int)
2918 *
2919 * @since 12
2920 */
2921 public String align() {
2922 return align(0);
2923 }
2924
2925 /**
2926 * Removes vertical and horizontal white space margins from around the
2927 * essential body of a multi-line string, while preserving relative
2928 * indentation and with optional indentation adjustment.
2929 * <p>
2930 * Invoking this method is equivalent to:
2931 * <blockquote>
2932 * {@code this.align().indent(n)}
2933 * </blockquote>
2934 *
2935 * @apiNote
2936 * Examples:
2937 * <blockquote><pre>
2938 * `
2939 * This is the first line
2940 * This is the second line
2941 * `.align(0);
2942 *
2943 * returns
2944 * This is the first line
2945 * This is the second line
2946 *
2947 *
2948 * `
2949 * This is the first line
2950 * This is the second line
2951 * `.align(4);
2952 * returns
2953 * This is the first line
2954 * This is the second line
2955 * </pre></blockquote>
2956 *
2957 * @param n number of leading white space characters
2958 * to add or remove
2959 *
2960 * @return string with margins removed, indentation adjusted and
2961 * line terminators normalized
2962 *
2963 * @see String#align()
2964 *
2965 * @since 12
2966 */
2967 public String align(int n) {
2968 if (isEmpty()) {
2969 return "";
2970 }
2971 int outdent = lines().filter(not(String::isBlank))
2972 .mapToInt(String::indexOfNonWhitespace)
2973 .min()
2974 .orElse(0);
2975 // overflow-conscious code
2976 int indent = n - outdent;
2977 return indent(indent > n ? Integer.MIN_VALUE : indent, true);
2978 }
2979
2980 /**
2981 * This method allows the application of a function to {@code this}
2982 * string. The function should expect a single String argument
2983 * and produce an {@code R} result.
2984 *
2985 * @param f functional interface to a apply
2986 *
2987 * @param <R> class of the result
2988 *
2989 * @return the result of applying the function to this string
2990 *
2991 * @see java.util.function.Function
2992 *
2993 * @since 12
2994 */
2995 public <R> R transform(Function<? super String, ? extends R> f) {
2996 return f.apply(this);
2997 }
2998
2999 /**
3000 * This object (which is already a string!) is itself returned.
3001 *
3002 * @return the string itself.
3003 */
3004 public String toString() {
3005 return this;
3006 }
3007
3008 /**
3009 * Returns a stream of {@code int} zero-extending the {@code char} values
3010 * from this sequence. Any char which maps to a <a
3011 * href="{@docRoot}/java.base/java/lang/Character.html#unicode">surrogate code
3012 * point</a> is passed through uninterpreted.
3013 *
3014 * @return an IntStream of char values from this sequence
3015 * @since 9
3016 */
3017 @Override
3018 public IntStream chars() {
3019 return StreamSupport.intStream(
3020 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
3021 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE),
3022 false);
3023 }
3024
3025
3026 /**
3027 * Returns a stream of code point values from this sequence. Any surrogate
3028 * pairs encountered in the sequence are combined as if by {@linkplain
3029 * Character#toCodePoint Character.toCodePoint} and the result is passed
3030 * to the stream. Any other code units, including ordinary BMP characters,
3031 * unpaired surrogates, and undefined code units, are zero-extended to
3032 * {@code int} values which are then passed to the stream.
3033 *
3034 * @return an IntStream of Unicode code points from this sequence
3035 * @since 9
3036 */
3037 @Override
3038 public IntStream codePoints() {
3039 return StreamSupport.intStream(
3040 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
3041 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE),
3042 false);
3043 }
3044
3045 /**
3046 * Converts this string to a new character array.
3047 *
3048 * @return a newly allocated character array whose length is the length
3049 * of this string and whose contents are initialized to contain
3050 * the character sequence represented by this string.
3051 */
3052 public char[] toCharArray() {
3053 return isLatin1() ? StringLatin1.toChars(value)
3054 : StringUTF16.toChars(value);
3055 }
3056
3057 /**
3058 * Returns a formatted string using the specified format string and
3059 * arguments.
3060 *
3061 * <p> The locale always used is the one returned by {@link
3062 * java.util.Locale#getDefault(java.util.Locale.Category)
3063 * Locale.getDefault(Locale.Category)} with
3064 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified.
3065 *
3066 * @param format
3067 * A <a href="../util/Formatter.html#syntax">format string</a>
3068 *
3069 * @param args
3070 * Arguments referenced by the format specifiers in the format
3071 * string. If there are more arguments than format specifiers, the
3072 * extra arguments are ignored. The number of arguments is
3073 * variable and may be zero. The maximum number of arguments is
3074 * limited by the maximum dimension of a Java array as defined by
3075 * <cite>The Java™ Virtual Machine Specification</cite>.
3076 * The behaviour on a
3077 * {@code null} argument depends on the <a
3078 * href="../util/Formatter.html#syntax">conversion</a>.
3079 *
3080 * @throws java.util.IllegalFormatException
3081 * If a format string contains an illegal syntax, a format
3082 * specifier that is incompatible with the given arguments,
3083 * insufficient arguments given the format string, or other
3084 * illegal conditions. For specification of all possible
3085 * formatting errors, see the <a
3086 * href="../util/Formatter.html#detail">Details</a> section of the
3087 * formatter class specification.
3088 *
3089 * @return A formatted string
3090 *
3091 * @see java.util.Formatter
3092 * @since 1.5
3093 */
3094 public static String format(String format, Object... args) {
3095 return new Formatter().format(format, args).toString();
3096 }
3097
3098 /**
3099 * Returns a formatted string using the specified locale, format string,
3100 * and arguments.
3101 *
3102 * @param l
3103 * The {@linkplain java.util.Locale locale} to apply during
3104 * formatting. If {@code l} is {@code null} then no localization
3105 * is applied.
3106 *
3107 * @param format
3108 * A <a href="../util/Formatter.html#syntax">format string</a>
3109 *
3110 * @param args
3111 * Arguments referenced by the format specifiers in the format
3112 * string. If there are more arguments than format specifiers, the
3113 * extra arguments are ignored. The number of arguments is
3114 * variable and may be zero. The maximum number of arguments is
3115 * limited by the maximum dimension of a Java array as defined by
3116 * <cite>The Java™ Virtual Machine Specification</cite>.
3117 * The behaviour on a
3118 * {@code null} argument depends on the
3119 * <a href="../util/Formatter.html#syntax">conversion</a>.
3120 *
3121 * @throws java.util.IllegalFormatException
3122 * If a format string contains an illegal syntax, a format
3123 * specifier that is incompatible with the given arguments,
3124 * insufficient arguments given the format string, or other
3125 * illegal conditions. For specification of all possible
3126 * formatting errors, see the <a
3127 * href="../util/Formatter.html#detail">Details</a> section of the
3128 * formatter class specification
3129 *
3130 * @return A formatted string
3131 *
3132 * @see java.util.Formatter
3133 * @since 1.5
3134 */
3135 public static String format(Locale l, String format, Object... args) {
3136 return new Formatter(l).format(format, args).toString();
3137 }
3138
3139 /**
3140 * Returns the string representation of the {@code Object} argument.
3141 *
3142 * @param obj an {@code Object}.
3143 * @return if the argument is {@code null}, then a string equal to
3144 * {@code "null"}; otherwise, the value of
3145 * {@code obj.toString()} is returned.
3146 * @see java.lang.Object#toString()
3147 */
3148 public static String valueOf(Object obj) {
3149 return (obj == null) ? "null" : obj.toString();
3150 }
3151
3152 /**
3153 * Returns the string representation of the {@code char} array
3154 * argument. The contents of the character array are copied; subsequent
3155 * modification of the character array does not affect the returned
3156 * string.
3157 *
3158 * @param data the character array.
3159 * @return a {@code String} that contains the characters of the
3160 * character array.
3161 */
3162 public static String valueOf(char data[]) {
3163 return new String(data);
3164 }
3165
3166 /**
3167 * Returns the string representation of a specific subarray of the
3168 * {@code char} array argument.
3169 * <p>
3170 * The {@code offset} argument is the index of the first
3171 * character of the subarray. The {@code count} argument
3172 * specifies the length of the subarray. The contents of the subarray
3173 * are copied; subsequent modification of the character array does not
3174 * affect the returned string.
3175 *
3176 * @param data the character array.
3177 * @param offset initial offset of the subarray.
3178 * @param count length of the subarray.
3179 * @return a {@code String} that contains the characters of the
3180 * specified subarray of the character array.
3181 * @exception IndexOutOfBoundsException if {@code offset} is
3182 * negative, or {@code count} is negative, or
3183 * {@code offset+count} is larger than
3184 * {@code data.length}.
3185 */
3186 public static String valueOf(char data[], int offset, int count) {
3187 return new String(data, offset, count);
3188 }
3189
3190 /**
3191 * Equivalent to {@link #valueOf(char[], int, int)}.
3192 *
3193 * @param data the character array.
3194 * @param offset initial offset of the subarray.
3195 * @param count length of the subarray.
3196 * @return a {@code String} that contains the characters of the
3197 * specified subarray of the character array.
3198 * @exception IndexOutOfBoundsException if {@code offset} is
3199 * negative, or {@code count} is negative, or
3200 * {@code offset+count} is larger than
3201 * {@code data.length}.
3202 */
3203 public static String copyValueOf(char data[], int offset, int count) {
3204 return new String(data, offset, count);
3205 }
3206
3207 /**
3208 * Equivalent to {@link #valueOf(char[])}.
3209 *
3210 * @param data the character array.
3211 * @return a {@code String} that contains the characters of the
3212 * character array.
3213 */
3214 public static String copyValueOf(char data[]) {
3215 return new String(data);
3216 }
3217
3218 /**
3219 * Returns the string representation of the {@code boolean} argument.
3220 *
3221 * @param b a {@code boolean}.
3222 * @return if the argument is {@code true}, a string equal to
3223 * {@code "true"} is returned; otherwise, a string equal to
3224 * {@code "false"} is returned.
3225 */
3226 public static String valueOf(boolean b) {
3227 return b ? "true" : "false";
3228 }
3229
3230 /**
3231 * Returns the string representation of the {@code char}
3232 * argument.
3233 *
3234 * @param c a {@code char}.
3235 * @return a string of length {@code 1} containing
3236 * as its single character the argument {@code c}.
3237 */
3238 public static String valueOf(char c) {
3239 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) {
3240 return new String(StringLatin1.toBytes(c), LATIN1);
3241 }
3242 return new String(StringUTF16.toBytes(c), UTF16);
3243 }
3244
3245 /**
3246 * Returns the string representation of the {@code int} argument.
3247 * <p>
3248 * The representation is exactly the one returned by the
3249 * {@code Integer.toString} method of one argument.
3250 *
3251 * @param i an {@code int}.
3252 * @return a string representation of the {@code int} argument.
3253 * @see java.lang.Integer#toString(int, int)
3254 */
3255 public static String valueOf(int i) {
3256 return Integer.toString(i);
3257 }
3258
3259 /**
3260 * Returns the string representation of the {@code long} argument.
3261 * <p>
3262 * The representation is exactly the one returned by the
3263 * {@code Long.toString} method of one argument.
3264 *
3265 * @param l a {@code long}.
3266 * @return a string representation of the {@code long} argument.
3267 * @see java.lang.Long#toString(long)
3268 */
3269 public static String valueOf(long l) {
3270 return Long.toString(l);
3271 }
3272
3273 /**
3274 * Returns the string representation of the {@code float} argument.
3275 * <p>
3276 * The representation is exactly the one returned by the
3277 * {@code Float.toString} method of one argument.
3278 *
3279 * @param f a {@code float}.
3280 * @return a string representation of the {@code float} argument.
3281 * @see java.lang.Float#toString(float)
3282 */
3283 public static String valueOf(float f) {
3284 return Float.toString(f);
3285 }
3286
3287 /**
3288 * Returns the string representation of the {@code double} argument.
3289 * <p>
3290 * The representation is exactly the one returned by the
3291 * {@code Double.toString} method of one argument.
3292 *
3293 * @param d a {@code double}.
3294 * @return a string representation of the {@code double} argument.
3295 * @see java.lang.Double#toString(double)
3296 */
3297 public static String valueOf(double d) {
3298 return Double.toString(d);
3299 }
3300
3301 /**
3302 * Returns a canonical representation for the string object.
3303 * <p>
3304 * A pool of strings, initially empty, is maintained privately by the
3305 * class {@code String}.
3306 * <p>
3307 * When the intern method is invoked, if the pool already contains a
3308 * string equal to this {@code String} object as determined by
3309 * the {@link #equals(Object)} method, then the string from the pool is
3310 * returned. Otherwise, this {@code String} object is added to the
3311 * pool and a reference to this {@code String} object is returned.
3312 * <p>
3313 * It follows that for any two strings {@code s} and {@code t},
3314 * {@code s.intern() == t.intern()} is {@code true}
3315 * if and only if {@code s.equals(t)} is {@code true}.
3316 * <p>
3317 * All literal strings and string-valued constant expressions are
3318 * interned. String literals are defined in section 3.10.5 of the
3319 * <cite>The Java™ Language Specification</cite>.
3320 *
3321 * @return a string that has the same contents as this string, but is
3322 * guaranteed to be from a pool of unique strings.
3323 * @jls 3.10.5 String Literals
3324 */
3325 public native String intern();
3326
3327 /**
3328 * Returns a string whose value is the concatenation of this
3329 * string repeated {@code count} times.
3330 * <p>
3331 * If this string is empty or count is zero then the empty
3332 * string is returned.
3333 *
3334 * @param count number of times to repeat
3335 *
3336 * @return A string composed of this string repeated
3337 * {@code count} times or the empty string if this
3338 * string is empty or count is zero
3339 *
3340 * @throws IllegalArgumentException if the {@code count} is
3341 * negative.
3342 *
3343 * @since 11
3344 */
3345 public String repeat(int count) {
3346 if (count < 0) {
3347 throw new IllegalArgumentException("count is negative: " + count);
3348 }
3349 if (count == 1) {
3350 return this;
3351 }
3352 final int len = value.length;
3353 if (len == 0 || count == 0) {
3354 return "";
3355 }
3356 if (len == 1) {
3357 final byte[] single = new byte[count];
3358 Arrays.fill(single, value[0]);
3359 return new String(single, coder);
3360 }
3361 if (Integer.MAX_VALUE / count < len) {
3362 throw new OutOfMemoryError("Repeating " + len + " bytes String " + count +
3363 " times will produce a String exceeding maximum size.");
3364 }
3365 final int limit = len * count;
3366 final byte[] multiple = new byte[limit];
3367 System.arraycopy(value, 0, multiple, 0, len);
3368 int copied = len;
3369 for (; copied < limit - copied; copied <<= 1) {
3370 System.arraycopy(multiple, 0, multiple, copied, copied);
3371 }
3372 System.arraycopy(multiple, 0, multiple, copied, limit - copied);
3373 return new String(multiple, coder);
3374 }
3375
3376 ////////////////////////////////////////////////////////////////
3377
3378 /**
3379 * Copy character bytes from this string into dst starting at dstBegin.
3380 * This method doesn't perform any range checking.
3381 *
3382 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two
3383 * coders are different, and dst is big enough (range check)
3384 *
3385 * @param dstBegin the char index, not offset of byte[]
3386 * @param coder the coder of dst[]
3387 */
3388 void getBytes(byte dst[], int dstBegin, byte coder) {
3389 if (coder() == coder) {
3390 System.arraycopy(value, 0, dst, dstBegin << coder, value.length);
3391 } else { // this.coder == LATIN && coder == UTF16
3392 StringLatin1.inflate(value, 0, dst, dstBegin, value.length);
3393 }
3394 }
3395
3396 /*
3397 * Package private constructor. Trailing Void argument is there for
3398 * disambiguating it against other (public) constructors.
3399 *
3400 * Stores the char[] value into a byte[] that each byte represents
3401 * the8 low-order bits of the corresponding character, if the char[]
3402 * contains only latin1 character. Or a byte[] that stores all
3403 * characters in their byte sequences defined by the {@code StringUTF16}.
3404 */
3405 String(char[] value, int off, int len, Void sig) {
3406 if (len == 0) {
3407 this.value = "".value;
3408 this.coder = "".coder;
3409 return;
3410 }
3411 if (COMPACT_STRINGS) {
3412 byte[] val = StringUTF16.compress(value, off, len);
3413 if (val != null) {
3414 this.value = val;
3415 this.coder = LATIN1;
3416 return;
3417 }
3418 }
3419 this.coder = UTF16;
3420 this.value = StringUTF16.toBytes(value, off, len);
3421 }
3422
3423 /*
3424 * Package private constructor. Trailing Void argument is there for
3425 * disambiguating it against other (public) constructors.
3426 */
3427 String(AbstractStringBuilder asb, Void sig) {
3428 byte[] val = asb.getValue();
3429 int length = asb.length();
3430 if (asb.isLatin1()) {
3431 this.coder = LATIN1;
3432 this.value = Arrays.copyOfRange(val, 0, length);
3433 } else {
3434 if (COMPACT_STRINGS) {
3435 byte[] buf = StringUTF16.compress(val, 0, length);
3436 if (buf != null) {
3437 this.coder = LATIN1;
3438 this.value = buf;
3439 return;
3440 }
3441 }
3442 this.coder = UTF16;
3443 this.value = Arrays.copyOfRange(val, 0, length << 1);
3444 }
3445 }
3446
3447 /*
3448 * Package private constructor which shares value array for speed.
3449 */
3450 String(byte[] value, byte coder) {
3451 this.value = value;
3452 this.coder = coder;
3453 }
3454
3455 byte coder() {
3456 return COMPACT_STRINGS ? coder : UTF16;
3457 }
3458
3459 byte[] value() {
3460 return value;
3461 }
3462
3463 private boolean isLatin1() {
3464 return COMPACT_STRINGS && coder == LATIN1;
3465 }
3466
3467 @Native static final byte LATIN1 = 0;
3468 @Native static final byte UTF16 = 1;
3469
3470 /*
3471 * StringIndexOutOfBoundsException if {@code index} is
3472 * negative or greater than or equal to {@code length}.
3473 */
3474 static void checkIndex(int index, int length) {
3475 if (index < 0 || index >= length) {
3476 throw new StringIndexOutOfBoundsException("index " + index +
3477 ",length " + length);
3478 }
3479 }
3480
3481 /*
3482 * StringIndexOutOfBoundsException if {@code offset}
3483 * is negative or greater than {@code length}.
3484 */
3485 static void checkOffset(int offset, int length) {
3486 if (offset < 0 || offset > length) {
3487 throw new StringIndexOutOfBoundsException("offset " + offset +
3488 ",length " + length);
3489 }
3490 }
3491
3492 /*
3493 * Check {@code offset}, {@code count} against {@code 0} and {@code length}
3494 * bounds.
3495 *
3496 * @throws StringIndexOutOfBoundsException
3497 * If {@code offset} is negative, {@code count} is negative,
3498 * or {@code offset} is greater than {@code length - count}
3499 */
3500 static void checkBoundsOffCount(int offset, int count, int length) {
3501 if (offset < 0 || count < 0 || offset > length - count) {
3502 throw new StringIndexOutOfBoundsException(
3503 "offset " + offset + ", count " + count + ", length " + length);
3504 }
3505 }
3506
3507 /*
3508 * Check {@code begin}, {@code end} against {@code 0} and {@code length}
3509 * bounds.
3510 *
3511 * @throws StringIndexOutOfBoundsException
3512 * If {@code begin} is negative, {@code begin} is greater than
3513 * {@code end}, or {@code end} is greater than {@code length}.
3514 */
3515 static void checkBoundsBeginEnd(int begin, int end, int length) {
3516 if (begin < 0 || begin > end || end > length) {
3517 throw new StringIndexOutOfBoundsException(
3518 "begin " + begin + ", end " + end + ", length " + length);
3519 }
3520 }
3521
3522 /**
3523 * Returns the string representation of the {@code codePoint}
3524 * argument.
3525 *
3526 * @param codePoint a {@code codePoint}.
3527 * @return a string of length {@code 1} or {@code 2} containing
3528 * as its single character the argument {@code codePoint}.
3529 * @throws IllegalArgumentException if the specified
3530 * {@code codePoint} is not a {@linkplain Character#isValidCodePoint
3531 * valid Unicode code point}.
3532 */
3533 static String valueOfCodePoint(int codePoint) {
3534 if (COMPACT_STRINGS && StringLatin1.canEncode(codePoint)) {
3535 return new String(StringLatin1.toBytes((char)codePoint), LATIN1);
3536 } else if (Character.isBmpCodePoint(codePoint)) {
3537 return new String(StringUTF16.toBytes((char)codePoint), UTF16);
3538 } else if (Character.isSupplementaryCodePoint(codePoint)) {
3539 return new String(StringUTF16.toBytesSupplementary(codePoint), UTF16);
3540 }
3541
3542 throw new IllegalArgumentException(
3543 format("Not a valid Unicode code point: 0x%X", codePoint));
3544 }
3545
3546 /**
3547 * Returns an {@link Optional} containing the nominal descriptor for this
3548 * instance, which is the instance itself.
3549 *
3550 * @return an {@link Optional} describing the {@linkplain String} instance
3551 * @since 12
3552 */
3553 @Override
3554 public Optional<String> describeConstable() {
3555 return Optional.of(this);
3556 }
3557
3558 /**
3559 * Resolves this instance as a {@link ConstantDesc}, the result of which is
3560 * the instance itself.
3561 *
3562 * @param lookup ignored
3563 * @return the {@linkplain String} instance
3564 * @since 12
3565 */
3566 @Override
3567 public String resolveConstantDesc(MethodHandles.Lookup lookup) {
3568 return this;
3569 }
3570
3571 }