1 /*
2 * Copyright (c) 1994, 2019, 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.List;
40 import java.util.Locale;
41 import java.util.Objects;
42 import java.util.Optional;
43 import java.util.Spliterator;
44 import java.util.StringJoiner;
45 import java.util.function.Function;
46 import java.util.regex.Matcher;
47 import java.util.regex.Pattern;
48 import java.util.regex.PatternSyntaxException;
49 import java.util.stream.Collectors;
50 import java.util.stream.IntStream;
51 import java.util.stream.Stream;
52 import java.util.stream.StreamSupport;
53 import jdk.internal.HotSpotIntrinsicCandidate;
54 import jdk.internal.vm.annotation.Stable;
55
56 import static java.util.function.Predicate.not;
57
58 /**
59 * The {@code String} class represents character strings. All
60 * string literals in Java programs, such as {@code "abc"}, are
61 * implemented as instances of this class.
62 * <p>
63 * Strings are constant; their values cannot be changed after they
64 * are created. String buffers support mutable strings.
65 * Because String objects are immutable they can be shared. For example:
66 * <blockquote><pre>
67 * String str = "abc";
68 * </pre></blockquote><p>
69 * is equivalent to:
70 * <blockquote><pre>
71 * char data[] = {'a', 'b', 'c'};
72 * String str = new String(data);
73 * </pre></blockquote><p>
74 * Here are some more examples of how strings can be used:
75 * <blockquote><pre>
76 * System.out.println("abc");
77 * String cde = "cde";
78 * System.out.println("abc" + cde);
79 * String c = "abc".substring(2, 3);
80 * String d = cde.substring(1, 2);
81 * </pre></blockquote>
82 * <p>
83 * The class {@code String} includes methods for examining
84 * individual characters of the sequence, for comparing strings, for
85 * searching strings, for extracting substrings, and for creating a
86 * copy of a string with all characters translated to uppercase or to
87 * lowercase. Case mapping is based on the Unicode Standard version
88 * specified by the {@link java.lang.Character Character} class.
89 * <p>
90 * The Java language provides special support for the string
91 * concatenation operator ( + ), and for conversion of
92 * other objects to strings. For additional information on string
93 * concatenation and conversion, see <i>The Java™ Language Specification</i>.
94 *
95 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor
96 * or method in this class will cause a {@link NullPointerException} to be
97 * thrown.
98 *
99 * <p>A {@code String} represents a string in the UTF-16 format
100 * in which <em>supplementary characters</em> are represented by <em>surrogate
101 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
102 * Character Representations</a> in the {@code Character} class for
103 * more information).
104 * Index values refer to {@code char} code units, so a supplementary
105 * character uses two positions in a {@code String}.
106 * <p>The {@code String} class provides methods for dealing with
107 * Unicode code points (i.e., characters), in addition to those for
108 * dealing with Unicode code units (i.e., {@code char} values).
109 *
110 * <p>Unless otherwise noted, methods for comparing Strings do not take locale
111 * into account. The {@link java.text.Collator} class provides methods for
112 * finer-grain, locale-sensitive String comparison.
113 *
114 * @implNote The implementation of the string concatenation operator is left to
115 * the discretion of a Java compiler, as long as the compiler ultimately conforms
116 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler
117 * may implement the operator with {@code StringBuffer}, {@code StringBuilder},
118 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The
119 * implementation of string conversion is typically through the method {@code toString},
120 * defined by {@code Object} and inherited by all classes in Java.
121 *
122 * @author Lee Boynton
123 * @author Arthur van Hoff
124 * @author Martin Buchholz
125 * @author Ulf Zibis
126 * @see java.lang.Object#toString()
127 * @see java.lang.StringBuffer
128 * @see java.lang.StringBuilder
129 * @see java.nio.charset.Charset
130 * @since 1.0
131 * @jls 15.18.1 String Concatenation Operator +
132 */
133
134 public final class String
135 implements java.io.Serializable, Comparable<String>, CharSequence,
136 Constable, ConstantDesc {
137
138 /**
139 * The value is used for character storage.
140 *
141 * @implNote This field is trusted by the VM, and is a subject to
142 * constant folding if String instance is constant. Overwriting this
143 * field after construction will cause problems.
144 *
145 * Additionally, it is marked with {@link Stable} to trust the contents
146 * of the array. No other facility in JDK provides this functionality (yet).
147 * {@link Stable} is safe here, because value is never null.
148 */
149 @Stable
150 private final byte[] value;
151
152 /**
153 * The identifier of the encoding used to encode the bytes in
154 * {@code value}. The supported values in this implementation are
155 *
156 * LATIN1
157 * UTF16
158 *
159 * @implNote This field is trusted by the VM, and is a subject to
160 * constant folding if String instance is constant. Overwriting this
161 * field after construction will cause problems.
162 */
163 private final byte coder;
164
165 /** Cache the hash code for the string */
166 private int hash; // Default to 0
167
168 /**
169 * Cache if the hash has been calculated as actually being zero, enabling
170 * us to avoid recalculating this.
171 */
172 private boolean hashIsZero; // Default to false;
173
174 /** use serialVersionUID from JDK 1.0.2 for interoperability */
175 private static final long serialVersionUID = -6849794470754667710L;
176
177 /**
178 * If String compaction is disabled, the bytes in {@code value} are
179 * always encoded in UTF16.
180 *
181 * For methods with several possible implementation paths, when String
182 * compaction is disabled, only one code path is taken.
183 *
184 * The instance field value is generally opaque to optimizing JIT
185 * compilers. Therefore, in performance-sensitive place, an explicit
186 * check of the static boolean {@code COMPACT_STRINGS} is done first
187 * before checking the {@code coder} field since the static boolean
188 * {@code COMPACT_STRINGS} would be constant folded away by an
189 * optimizing JIT compiler. The idioms for these cases are as follows.
190 *
191 * For code such as:
192 *
193 * if (coder == LATIN1) { ... }
194 *
195 * can be written more optimally as
196 *
197 * if (coder() == LATIN1) { ... }
198 *
199 * or:
200 *
201 * if (COMPACT_STRINGS && coder == LATIN1) { ... }
202 *
203 * An optimizing JIT compiler can fold the above conditional as:
204 *
205 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... }
206 * COMPACT_STRINGS == false => if (false) { ... }
207 *
208 * @implNote
209 * The actual value for this field is injected by JVM. The static
210 * initialization block is used to set the value here to communicate
211 * that this static final field is not statically foldable, and to
212 * avoid any possible circular dependency during vm initialization.
213 */
214 static final boolean COMPACT_STRINGS;
215
216 static {
217 COMPACT_STRINGS = true;
218 }
219
220 /**
221 * Class String is special cased within the Serialization Stream Protocol.
222 *
223 * A String instance is written into an ObjectOutputStream according to
224 * <a href="{@docRoot}/../specs/serialization/protocol.html#stream-elements">
225 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
226 */
227 private static final ObjectStreamField[] serialPersistentFields =
228 new ObjectStreamField[0];
229
230 /**
231 * Initializes a newly created {@code String} object so that it represents
232 * an empty character sequence. Note that use of this constructor is
233 * unnecessary since Strings are immutable.
234 */
235 public String() {
236 this.value = "".value;
237 this.coder = "".coder;
238 }
239
240 /**
241 * Initializes a newly created {@code String} object so that it represents
242 * the same sequence of characters as the argument; in other words, the
243 * newly created string is a copy of the argument string. Unless an
244 * explicit copy of {@code original} is needed, use of this constructor is
245 * unnecessary since Strings are immutable.
246 *
247 * @param original
248 * A {@code String}
249 */
250 @HotSpotIntrinsicCandidate
251 public String(String original) {
252 this.value = original.value;
253 this.coder = original.coder;
254 this.hash = original.hash;
255 }
256
257 /**
258 * Allocates a new {@code String} so that it represents the sequence of
259 * characters currently contained in the character array argument. The
260 * contents of the character array are copied; subsequent modification of
261 * the character array does not affect the newly created string.
262 *
263 * @param value
264 * The initial value of the string
265 */
266 public String(char value[]) {
267 this(value, 0, value.length, null);
268 }
269
270 /**
271 * Allocates a new {@code String} that contains characters from a subarray
272 * of the character array argument. The {@code offset} argument is the
273 * index of the first character of the subarray and the {@code count}
274 * argument specifies the length of the subarray. The contents of the
275 * subarray are copied; subsequent modification of the character array does
276 * not affect the newly created string.
277 *
278 * @param value
279 * Array that is the source of characters
280 *
281 * @param offset
282 * The initial offset
283 *
284 * @param count
285 * The length
286 *
287 * @throws IndexOutOfBoundsException
288 * If {@code offset} is negative, {@code count} is negative, or
289 * {@code offset} is greater than {@code value.length - count}
290 */
291 public String(char value[], int offset, int count) {
292 this(value, offset, count, rangeCheck(value, offset, count));
293 }
294
295 private static Void rangeCheck(char[] value, int offset, int count) {
296 checkBoundsOffCount(offset, count, value.length);
297 return null;
298 }
299
300 /**
301 * Allocates a new {@code String} that contains characters from a subarray
302 * of the <a href="Character.html#unicode">Unicode code point</a> array
303 * argument. The {@code offset} argument is the index of the first code
304 * point of the subarray and the {@code count} argument specifies the
305 * length of the subarray. The contents of the subarray are converted to
306 * {@code char}s; subsequent modification of the {@code int} array does not
307 * affect the newly created string.
308 *
309 * @param codePoints
310 * Array that is the source of Unicode code points
311 *
312 * @param offset
313 * The initial offset
314 *
315 * @param count
316 * The length
317 *
318 * @throws IllegalArgumentException
319 * If any invalid Unicode code point is found in {@code
320 * codePoints}
321 *
322 * @throws IndexOutOfBoundsException
323 * If {@code offset} is negative, {@code count} is negative, or
324 * {@code offset} is greater than {@code codePoints.length - count}
325 *
326 * @since 1.5
327 */
328 public String(int[] codePoints, int offset, int count) {
329 checkBoundsOffCount(offset, count, codePoints.length);
330 if (count == 0) {
331 this.value = "".value;
332 this.coder = "".coder;
333 return;
334 }
335 if (COMPACT_STRINGS) {
336 byte[] val = StringLatin1.toBytes(codePoints, offset, count);
337 if (val != null) {
338 this.coder = LATIN1;
339 this.value = val;
340 return;
341 }
342 }
343 this.coder = UTF16;
344 this.value = StringUTF16.toBytes(codePoints, offset, count);
345 }
346
347 /**
348 * Allocates a new {@code String} constructed from a subarray of an array
349 * of 8-bit integer values.
350 *
351 * <p> The {@code offset} argument is the index of the first byte of the
352 * subarray, and the {@code count} argument specifies the length of the
353 * subarray.
354 *
355 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
356 * specified in the {@link #String(byte[],int) String(byte[],int)} constructor.
357 *
358 * @deprecated This method does not properly convert bytes into characters.
359 * As of JDK 1.1, the preferred way to do this is via the
360 * {@code String} constructors that take a {@link
361 * java.nio.charset.Charset}, charset name, or that use the platform's
362 * default charset.
363 *
364 * @param ascii
365 * The bytes to be converted to characters
366 *
367 * @param hibyte
368 * The top 8 bits of each 16-bit Unicode code unit
369 *
370 * @param offset
371 * The initial offset
372 * @param count
373 * The length
374 *
375 * @throws IndexOutOfBoundsException
376 * If {@code offset} is negative, {@code count} is negative, or
377 * {@code offset} is greater than {@code ascii.length - count}
378 *
379 * @see #String(byte[], int)
380 * @see #String(byte[], int, int, java.lang.String)
381 * @see #String(byte[], int, int, java.nio.charset.Charset)
382 * @see #String(byte[], int, int)
383 * @see #String(byte[], java.lang.String)
384 * @see #String(byte[], java.nio.charset.Charset)
385 * @see #String(byte[])
386 */
387 @Deprecated(since="1.1")
388 public String(byte ascii[], int hibyte, int offset, int count) {
389 checkBoundsOffCount(offset, count, ascii.length);
390 if (count == 0) {
391 this.value = "".value;
392 this.coder = "".coder;
393 return;
394 }
395 if (COMPACT_STRINGS && (byte)hibyte == 0) {
396 this.value = Arrays.copyOfRange(ascii, offset, offset + count);
397 this.coder = LATIN1;
398 } else {
399 hibyte <<= 8;
400 byte[] val = StringUTF16.newBytesFor(count);
401 for (int i = 0; i < count; i++) {
402 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff));
403 }
404 this.value = val;
405 this.coder = UTF16;
406 }
407 }
408
409 /**
410 * Allocates a new {@code String} containing characters constructed from
411 * an array of 8-bit integer values. Each character <i>c</i> in the
412 * resulting string is constructed from the corresponding component
413 * <i>b</i> in the byte array such that:
414 *
415 * <blockquote><pre>
416 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
417 * | (<b><i>b</i></b> & 0xff))
418 * </pre></blockquote>
419 *
420 * @deprecated This method does not properly convert bytes into
421 * characters. As of JDK 1.1, the preferred way to do this is via the
422 * {@code String} constructors that take a {@link
423 * java.nio.charset.Charset}, charset name, or that use the platform's
424 * default charset.
425 *
426 * @param ascii
427 * The bytes to be converted to characters
428 *
429 * @param hibyte
430 * The top 8 bits of each 16-bit Unicode code unit
431 *
432 * @see #String(byte[], int, int, java.lang.String)
433 * @see #String(byte[], int, int, java.nio.charset.Charset)
434 * @see #String(byte[], int, int)
435 * @see #String(byte[], java.lang.String)
436 * @see #String(byte[], java.nio.charset.Charset)
437 * @see #String(byte[])
438 */
439 @Deprecated(since="1.1")
440 public String(byte ascii[], int hibyte) {
441 this(ascii, hibyte, 0, ascii.length);
442 }
443
444 /**
445 * Constructs a new {@code String} by decoding the specified subarray of
446 * bytes using the specified charset. The length of the new {@code String}
447 * is a function of the charset, and hence may not be equal to the length
448 * of the subarray.
449 *
450 * <p> The behavior of this constructor when the given bytes are not valid
451 * in the given charset is unspecified. The {@link
452 * java.nio.charset.CharsetDecoder} class should be used when more control
453 * over the decoding process is required.
454 *
455 * @param bytes
456 * The bytes to be decoded into characters
457 *
458 * @param offset
459 * The index of the first byte to decode
460 *
461 * @param length
462 * The number of bytes to decode
463
464 * @param charsetName
465 * The name of a supported {@linkplain java.nio.charset.Charset
466 * charset}
467 *
468 * @throws UnsupportedEncodingException
469 * If the named charset is not supported
470 *
471 * @throws IndexOutOfBoundsException
472 * If {@code offset} is negative, {@code length} is negative, or
473 * {@code offset} is greater than {@code bytes.length - length}
474 *
475 * @since 1.1
476 */
477 public String(byte bytes[], int offset, int length, String charsetName)
478 throws UnsupportedEncodingException {
479 if (charsetName == null)
480 throw new NullPointerException("charsetName");
481 checkBoundsOffCount(offset, length, bytes.length);
482 StringCoding.Result ret =
483 StringCoding.decode(charsetName, bytes, offset, length);
484 this.value = ret.value;
485 this.coder = ret.coder;
486 }
487
488 /**
489 * Constructs a new {@code String} by decoding the specified subarray of
490 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
491 * The length of the new {@code String} is a function of the charset, and
492 * hence may not be equal to the length of the subarray.
493 *
494 * <p> This method always replaces malformed-input and unmappable-character
495 * sequences with this charset's default replacement string. The {@link
496 * java.nio.charset.CharsetDecoder} class should be used when more control
497 * over the decoding process is required.
498 *
499 * @param bytes
500 * The bytes to be decoded into characters
501 *
502 * @param offset
503 * The index of the first byte to decode
504 *
505 * @param length
506 * The number of bytes to decode
507 *
508 * @param charset
509 * The {@linkplain java.nio.charset.Charset charset} to be used to
510 * decode the {@code bytes}
511 *
512 * @throws IndexOutOfBoundsException
513 * If {@code offset} is negative, {@code length} is negative, or
514 * {@code offset} is greater than {@code bytes.length - length}
515 *
516 * @since 1.6
517 */
518 public String(byte bytes[], int offset, int length, Charset charset) {
519 if (charset == null)
520 throw new NullPointerException("charset");
521 checkBoundsOffCount(offset, length, bytes.length);
522 StringCoding.Result ret =
523 StringCoding.decode(charset, bytes, offset, length);
524 this.value = ret.value;
525 this.coder = ret.coder;
526 }
527
528 /**
529 * Constructs a new {@code String} by decoding the specified array of bytes
530 * using the specified {@linkplain java.nio.charset.Charset charset}. The
531 * length of the new {@code String} is a function of the charset, and hence
532 * may not be equal to the length of the byte array.
533 *
534 * <p> The behavior of this constructor when the given bytes are not valid
535 * in the given charset is unspecified. The {@link
536 * java.nio.charset.CharsetDecoder} class should be used when more control
537 * over the decoding process is required.
538 *
539 * @param bytes
540 * The bytes to be decoded into characters
541 *
542 * @param charsetName
543 * The name of a supported {@linkplain java.nio.charset.Charset
544 * charset}
545 *
546 * @throws UnsupportedEncodingException
547 * If the named charset is not supported
548 *
549 * @since 1.1
550 */
551 public String(byte bytes[], String charsetName)
552 throws UnsupportedEncodingException {
553 this(bytes, 0, bytes.length, charsetName);
554 }
555
556 /**
557 * Constructs a new {@code String} by decoding the specified array of
558 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
559 * The length of the new {@code String} is a function of the charset, and
560 * hence may not be equal to the length of the byte array.
561 *
562 * <p> This method always replaces malformed-input and unmappable-character
563 * sequences with this charset's default replacement string. The {@link
564 * java.nio.charset.CharsetDecoder} class should be used when more control
565 * over the decoding process is required.
566 *
567 * @param bytes
568 * The bytes to be decoded into characters
569 *
570 * @param charset
571 * The {@linkplain java.nio.charset.Charset charset} to be used to
572 * decode the {@code bytes}
573 *
574 * @since 1.6
575 */
576 public String(byte bytes[], Charset charset) {
577 this(bytes, 0, bytes.length, charset);
578 }
579
580 /**
581 * Constructs a new {@code String} by decoding the specified subarray of
582 * bytes using the platform's default charset. The length of the new
583 * {@code String} is a function of the charset, and hence may not be equal
584 * to the length of the subarray.
585 *
586 * <p> The behavior of this constructor when the given bytes are not valid
587 * in the default charset is unspecified. The {@link
588 * java.nio.charset.CharsetDecoder} class should be used when more control
589 * over the decoding process is required.
590 *
591 * @param bytes
592 * The bytes to be decoded into characters
593 *
594 * @param offset
595 * The index of the first byte to decode
596 *
597 * @param length
598 * The number of bytes to decode
599 *
600 * @throws IndexOutOfBoundsException
601 * If {@code offset} is negative, {@code length} is negative, or
602 * {@code offset} is greater than {@code bytes.length - length}
603 *
604 * @since 1.1
605 */
606 public String(byte bytes[], int offset, int length) {
607 checkBoundsOffCount(offset, length, bytes.length);
608 StringCoding.Result ret = StringCoding.decode(bytes, offset, length);
609 this.value = ret.value;
610 this.coder = ret.coder;
611 }
612
613 /**
614 * Constructs a new {@code String} by decoding the specified array of bytes
615 * using the platform's default charset. The length of the new {@code
616 * String} is a function of the charset, and hence may not be equal to the
617 * length of the byte array.
618 *
619 * <p> The behavior of this constructor when the given bytes are not valid
620 * in the default charset is unspecified. The {@link
621 * java.nio.charset.CharsetDecoder} class should be used when more control
622 * over the decoding process is required.
623 *
624 * @param bytes
625 * The bytes to be decoded into characters
626 *
627 * @since 1.1
628 */
629 public String(byte[] bytes) {
630 this(bytes, 0, bytes.length);
631 }
632
633 /**
634 * Allocates a new string that contains the sequence of characters
635 * currently contained in the string buffer argument. The contents of the
636 * string buffer are copied; subsequent modification of the string buffer
637 * does not affect the newly created string.
638 *
639 * @param buffer
640 * A {@code StringBuffer}
641 */
642 public String(StringBuffer buffer) {
643 this(buffer.toString());
644 }
645
646 /**
647 * Allocates a new string that contains the sequence of characters
648 * currently contained in the string builder argument. The contents of the
649 * string builder are copied; subsequent modification of the string builder
650 * does not affect the newly created string.
651 *
652 * <p> This constructor is provided to ease migration to {@code
653 * StringBuilder}. Obtaining a string from a string builder via the {@code
654 * toString} method is likely to run faster and is generally preferred.
655 *
656 * @param builder
657 * A {@code StringBuilder}
658 *
659 * @since 1.5
660 */
661 public String(StringBuilder builder) {
662 this(builder, null);
663 }
664
665 /**
666 * Returns the length of this string.
667 * The length is equal to the number of <a href="Character.html#unicode">Unicode
668 * code units</a> in the string.
669 *
670 * @return the length of the sequence of characters represented by this
671 * object.
672 */
673 public int length() {
674 return value.length >> coder();
675 }
676
677 /**
678 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
679 *
680 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
681 * {@code false}
682 *
683 * @since 1.6
684 */
685 public boolean isEmpty() {
686 return value.length == 0;
687 }
688
689 /**
690 * Returns the {@code char} value at the
691 * specified index. An index ranges from {@code 0} to
692 * {@code length() - 1}. The first {@code char} value of the sequence
693 * is at index {@code 0}, the next at index {@code 1},
694 * and so on, as for array indexing.
695 *
696 * <p>If the {@code char} value specified by the index is a
697 * <a href="Character.html#unicode">surrogate</a>, the surrogate
698 * value is returned.
699 *
700 * @param index the index of the {@code char} value.
701 * @return the {@code char} value at the specified index of this string.
702 * The first {@code char} value is at index {@code 0}.
703 * @exception IndexOutOfBoundsException if the {@code index}
704 * argument is negative or not less than the length of this
705 * string.
706 */
707 public char charAt(int index) {
708 if (isLatin1()) {
709 return StringLatin1.charAt(value, index);
710 } else {
711 return StringUTF16.charAt(value, index);
712 }
713 }
714
715 /**
716 * Returns the character (Unicode code point) at the specified
717 * index. The index refers to {@code char} values
718 * (Unicode code units) and ranges from {@code 0} to
719 * {@link #length()}{@code - 1}.
720 *
721 * <p> If the {@code char} value specified at the given index
722 * is in the high-surrogate range, the following index is less
723 * than the length of this {@code String}, and the
724 * {@code char} value at the following index is in the
725 * low-surrogate range, then the supplementary code point
726 * corresponding to this surrogate pair is returned. Otherwise,
727 * the {@code char} value at the given index is returned.
728 *
729 * @param index the index to the {@code char} values
730 * @return the code point value of the character at the
731 * {@code index}
732 * @exception IndexOutOfBoundsException if the {@code index}
733 * argument is negative or not less than the length of this
734 * string.
735 * @since 1.5
736 */
737 public int codePointAt(int index) {
738 if (isLatin1()) {
739 checkIndex(index, value.length);
740 return value[index] & 0xff;
741 }
742 int length = value.length >> 1;
743 checkIndex(index, length);
744 return StringUTF16.codePointAt(value, index, length);
745 }
746
747 /**
748 * Returns the character (Unicode code point) before the specified
749 * index. The index refers to {@code char} values
750 * (Unicode code units) and ranges from {@code 1} to {@link
751 * CharSequence#length() length}.
752 *
753 * <p> If the {@code char} value at {@code (index - 1)}
754 * is in the low-surrogate range, {@code (index - 2)} is not
755 * negative, and the {@code char} value at {@code (index -
756 * 2)} is in the high-surrogate range, then the
757 * supplementary code point value of the surrogate pair is
758 * returned. If the {@code char} value at {@code index -
759 * 1} is an unpaired low-surrogate or a high-surrogate, the
760 * surrogate value is returned.
761 *
762 * @param index the index following the code point that should be returned
763 * @return the Unicode code point value before the given index.
764 * @exception IndexOutOfBoundsException if the {@code index}
765 * argument is less than 1 or greater than the length
766 * of this string.
767 * @since 1.5
768 */
769 public int codePointBefore(int index) {
770 int i = index - 1;
771 if (i < 0 || i >= length()) {
772 throw new StringIndexOutOfBoundsException(index);
773 }
774 if (isLatin1()) {
775 return (value[i] & 0xff);
776 }
777 return StringUTF16.codePointBefore(value, index);
778 }
779
780 /**
781 * Returns the number of Unicode code points in the specified text
782 * range of this {@code String}. The text range begins at the
783 * specified {@code beginIndex} and extends to the
784 * {@code char} at index {@code endIndex - 1}. Thus the
785 * length (in {@code char}s) of the text range is
786 * {@code endIndex-beginIndex}. Unpaired surrogates within
787 * the text range count as one code point each.
788 *
789 * @param beginIndex the index to the first {@code char} of
790 * the text range.
791 * @param endIndex the index after the last {@code char} of
792 * the text range.
793 * @return the number of Unicode code points in the specified text
794 * range
795 * @exception IndexOutOfBoundsException if the
796 * {@code beginIndex} is negative, or {@code endIndex}
797 * is larger than the length of this {@code String}, or
798 * {@code beginIndex} is larger than {@code endIndex}.
799 * @since 1.5
800 */
801 public int codePointCount(int beginIndex, int endIndex) {
802 if (beginIndex < 0 || beginIndex > endIndex ||
803 endIndex > length()) {
804 throw new IndexOutOfBoundsException();
805 }
806 if (isLatin1()) {
807 return endIndex - beginIndex;
808 }
809 return StringUTF16.codePointCount(value, beginIndex, endIndex);
810 }
811
812 /**
813 * Returns the index within this {@code String} that is
814 * offset from the given {@code index} by
815 * {@code codePointOffset} code points. Unpaired surrogates
816 * within the text range given by {@code index} and
817 * {@code codePointOffset} count as one code point each.
818 *
819 * @param index the index to be offset
820 * @param codePointOffset the offset in code points
821 * @return the index within this {@code String}
822 * @exception IndexOutOfBoundsException if {@code index}
823 * is negative or larger then the length of this
824 * {@code String}, or if {@code codePointOffset} is positive
825 * and the substring starting with {@code index} has fewer
826 * than {@code codePointOffset} code points,
827 * or if {@code codePointOffset} is negative and the substring
828 * before {@code index} has fewer than the absolute value
829 * of {@code codePointOffset} code points.
830 * @since 1.5
831 */
832 public int offsetByCodePoints(int index, int codePointOffset) {
833 if (index < 0 || index > length()) {
834 throw new IndexOutOfBoundsException();
835 }
836 return Character.offsetByCodePoints(this, index, codePointOffset);
837 }
838
839 /**
840 * Copies characters from this string into the destination character
841 * array.
842 * <p>
843 * The first character to be copied is at index {@code srcBegin};
844 * the last character to be copied is at index {@code srcEnd-1}
845 * (thus the total number of characters to be copied is
846 * {@code srcEnd-srcBegin}). The characters are copied into the
847 * subarray of {@code dst} starting at index {@code dstBegin}
848 * and ending at index:
849 * <blockquote><pre>
850 * dstBegin + (srcEnd-srcBegin) - 1
851 * </pre></blockquote>
852 *
853 * @param srcBegin index of the first character in the string
854 * to copy.
855 * @param srcEnd index after the last character in the string
856 * to copy.
857 * @param dst the destination array.
858 * @param dstBegin the start offset in the destination array.
859 * @exception IndexOutOfBoundsException If any of the following
860 * is true:
861 * <ul><li>{@code srcBegin} is negative.
862 * <li>{@code srcBegin} is greater than {@code srcEnd}
863 * <li>{@code srcEnd} is greater than the length of this
864 * string
865 * <li>{@code dstBegin} is negative
866 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
867 * {@code dst.length}</ul>
868 */
869 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
870 checkBoundsBeginEnd(srcBegin, srcEnd, length());
871 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
872 if (isLatin1()) {
873 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin);
874 } else {
875 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin);
876 }
877 }
878
879 /**
880 * Copies characters from this string into the destination byte array. Each
881 * byte receives the 8 low-order bits of the corresponding character. The
882 * eight high-order bits of each character are not copied and do not
883 * participate in the transfer in any way.
884 *
885 * <p> The first character to be copied is at index {@code srcBegin}; the
886 * last character to be copied is at index {@code srcEnd-1}. The total
887 * number of characters to be copied is {@code srcEnd-srcBegin}. The
888 * characters, converted to bytes, are copied into the subarray of {@code
889 * dst} starting at index {@code dstBegin} and ending at index:
890 *
891 * <blockquote><pre>
892 * dstBegin + (srcEnd-srcBegin) - 1
893 * </pre></blockquote>
894 *
895 * @deprecated This method does not properly convert characters into
896 * bytes. As of JDK 1.1, the preferred way to do this is via the
897 * {@link #getBytes()} method, which uses the platform's default charset.
898 *
899 * @param srcBegin
900 * Index of the first character in the string to copy
901 *
902 * @param srcEnd
903 * Index after the last character in the string to copy
904 *
905 * @param dst
906 * The destination array
907 *
908 * @param dstBegin
909 * The start offset in the destination array
910 *
911 * @throws IndexOutOfBoundsException
912 * If any of the following is true:
913 * <ul>
914 * <li> {@code srcBegin} is negative
915 * <li> {@code srcBegin} is greater than {@code srcEnd}
916 * <li> {@code srcEnd} is greater than the length of this String
917 * <li> {@code dstBegin} is negative
918 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
919 * dst.length}
920 * </ul>
921 */
922 @Deprecated(since="1.1")
923 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
924 checkBoundsBeginEnd(srcBegin, srcEnd, length());
925 Objects.requireNonNull(dst);
926 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
927 if (isLatin1()) {
928 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
929 } else {
930 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
931 }
932 }
933
934 /**
935 * Encodes this {@code String} into a sequence of bytes using the named
936 * charset, storing the result into a new byte array.
937 *
938 * <p> The behavior of this method when this string cannot be encoded in
939 * the given charset is unspecified. The {@link
940 * java.nio.charset.CharsetEncoder} class should be used when more control
941 * over the encoding process is required.
942 *
943 * @param charsetName
944 * The name of a supported {@linkplain java.nio.charset.Charset
945 * charset}
946 *
947 * @return The resultant byte array
948 *
949 * @throws UnsupportedEncodingException
950 * If the named charset is not supported
951 *
952 * @since 1.1
953 */
954 public byte[] getBytes(String charsetName)
955 throws UnsupportedEncodingException {
956 if (charsetName == null) throw new NullPointerException();
957 return StringCoding.encode(charsetName, coder(), value);
958 }
959
960 /**
961 * Encodes this {@code String} into a sequence of bytes using the given
962 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
963 * new byte array.
964 *
965 * <p> This method always replaces malformed-input and unmappable-character
966 * sequences with this charset's default replacement byte array. The
967 * {@link java.nio.charset.CharsetEncoder} class should be used when more
968 * control over the encoding process is required.
969 *
970 * @param charset
971 * The {@linkplain java.nio.charset.Charset} to be used to encode
972 * the {@code String}
973 *
974 * @return The resultant byte array
975 *
976 * @since 1.6
977 */
978 public byte[] getBytes(Charset charset) {
979 if (charset == null) throw new NullPointerException();
980 return StringCoding.encode(charset, coder(), value);
981 }
982
983 /**
984 * Encodes this {@code String} into a sequence of bytes using the
985 * platform's default charset, storing the result into a new byte array.
986 *
987 * <p> The behavior of this method when this string cannot be encoded in
988 * the default charset is unspecified. The {@link
989 * java.nio.charset.CharsetEncoder} class should be used when more control
990 * over the encoding process is required.
991 *
992 * @return The resultant byte array
993 *
994 * @since 1.1
995 */
996 public byte[] getBytes() {
997 return StringCoding.encode(coder(), value);
998 }
999
1000 /**
1001 * Compares this string to the specified object. The result is {@code
1002 * true} if and only if the argument is not {@code null} and is a {@code
1003 * String} object that represents the same sequence of characters as this
1004 * object.
1005 *
1006 * <p>For finer-grained String comparison, refer to
1007 * {@link java.text.Collator}.
1008 *
1009 * @param anObject
1010 * The object to compare this {@code String} against
1011 *
1012 * @return {@code true} if the given object represents a {@code String}
1013 * equivalent to this string, {@code false} otherwise
1014 *
1015 * @see #compareTo(String)
1016 * @see #equalsIgnoreCase(String)
1017 */
1018 public boolean equals(Object anObject) {
1019 if (this == anObject) {
1020 return true;
1021 }
1022 if (anObject instanceof String) {
1023 String aString = (String)anObject;
1024 if (!COMPACT_STRINGS || this.coder == aString.coder) {
1025 return StringLatin1.equals(value, aString.value);
1026 }
1027 }
1028 return false;
1029 }
1030
1031 /**
1032 * Compares this string to the specified {@code StringBuffer}. The result
1033 * is {@code true} if and only if this {@code String} represents the same
1034 * sequence of characters as the specified {@code StringBuffer}. This method
1035 * synchronizes on the {@code StringBuffer}.
1036 *
1037 * <p>For finer-grained String comparison, refer to
1038 * {@link java.text.Collator}.
1039 *
1040 * @param sb
1041 * The {@code StringBuffer} to compare this {@code String} against
1042 *
1043 * @return {@code true} if this {@code String} represents the same
1044 * sequence of characters as the specified {@code StringBuffer},
1045 * {@code false} otherwise
1046 *
1047 * @since 1.4
1048 */
1049 public boolean contentEquals(StringBuffer sb) {
1050 return contentEquals((CharSequence)sb);
1051 }
1052
1053 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1054 int len = length();
1055 if (len != sb.length()) {
1056 return false;
1057 }
1058 byte v1[] = value;
1059 byte v2[] = sb.getValue();
1060 byte coder = coder();
1061 if (coder == sb.getCoder()) {
1062 int n = v1.length;
1063 for (int i = 0; i < n; i++) {
1064 if (v1[i] != v2[i]) {
1065 return false;
1066 }
1067 }
1068 } else {
1069 if (coder != LATIN1) { // utf16 str and latin1 abs can never be "equal"
1070 return false;
1071 }
1072 return StringUTF16.contentEquals(v1, v2, len);
1073 }
1074 return true;
1075 }
1076
1077 /**
1078 * Compares this string to the specified {@code CharSequence}. The
1079 * result is {@code true} if and only if this {@code String} represents the
1080 * same sequence of char values as the specified sequence. Note that if the
1081 * {@code CharSequence} is a {@code StringBuffer} then the method
1082 * synchronizes on it.
1083 *
1084 * <p>For finer-grained String comparison, refer to
1085 * {@link java.text.Collator}.
1086 *
1087 * @param cs
1088 * The sequence to compare this {@code String} against
1089 *
1090 * @return {@code true} if this {@code String} represents the same
1091 * sequence of char values as the specified sequence, {@code
1092 * false} otherwise
1093 *
1094 * @since 1.5
1095 */
1096 public boolean contentEquals(CharSequence cs) {
1097 // Argument is a StringBuffer, StringBuilder
1098 if (cs instanceof AbstractStringBuilder) {
1099 if (cs instanceof StringBuffer) {
1100 synchronized(cs) {
1101 return nonSyncContentEquals((AbstractStringBuilder)cs);
1102 }
1103 } else {
1104 return nonSyncContentEquals((AbstractStringBuilder)cs);
1105 }
1106 }
1107 // Argument is a String
1108 if (cs instanceof String) {
1109 return equals(cs);
1110 }
1111 // Argument is a generic CharSequence
1112 int n = cs.length();
1113 if (n != length()) {
1114 return false;
1115 }
1116 byte[] val = this.value;
1117 if (isLatin1()) {
1118 for (int i = 0; i < n; i++) {
1119 if ((val[i] & 0xff) != cs.charAt(i)) {
1120 return false;
1121 }
1122 }
1123 } else {
1124 if (!StringUTF16.contentEquals(val, cs, n)) {
1125 return false;
1126 }
1127 }
1128 return true;
1129 }
1130
1131 /**
1132 * Compares this {@code String} to another {@code String}, ignoring case
1133 * considerations. Two strings are considered equal ignoring case if they
1134 * are of the same length and corresponding characters in the two strings
1135 * are equal ignoring case.
1136 *
1137 * <p> Two characters {@code c1} and {@code c2} are considered the same
1138 * ignoring case if at least one of the following is true:
1139 * <ul>
1140 * <li> The two characters are the same (as compared by the
1141 * {@code ==} operator)
1142 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))}
1143 * on each character produces the same result
1144 * </ul>
1145 *
1146 * <p>Note that this method does <em>not</em> take locale into account, and
1147 * will result in unsatisfactory results for certain locales. The
1148 * {@link java.text.Collator} class provides locale-sensitive comparison.
1149 *
1150 * @param anotherString
1151 * The {@code String} to compare this {@code String} against
1152 *
1153 * @return {@code true} if the argument is not {@code null} and it
1154 * represents an equivalent {@code String} ignoring case; {@code
1155 * false} otherwise
1156 *
1157 * @see #equals(Object)
1158 */
1159 public boolean equalsIgnoreCase(String anotherString) {
1160 return (this == anotherString) ? true
1161 : (anotherString != null)
1162 && (anotherString.length() == length())
1163 && regionMatches(true, 0, anotherString, 0, length());
1164 }
1165
1166 /**
1167 * Compares two strings lexicographically.
1168 * The comparison is based on the Unicode value of each character in
1169 * the strings. The character sequence represented by this
1170 * {@code String} object is compared lexicographically to the
1171 * character sequence represented by the argument string. The result is
1172 * a negative integer if this {@code String} object
1173 * lexicographically precedes the argument string. The result is a
1174 * positive integer if this {@code String} object lexicographically
1175 * follows the argument string. The result is zero if the strings
1176 * are equal; {@code compareTo} returns {@code 0} exactly when
1177 * the {@link #equals(Object)} method would return {@code true}.
1178 * <p>
1179 * This is the definition of lexicographic ordering. If two strings are
1180 * different, then either they have different characters at some index
1181 * that is a valid index for both strings, or their lengths are different,
1182 * or both. If they have different characters at one or more index
1183 * positions, let <i>k</i> be the smallest such index; then the string
1184 * whose character at position <i>k</i> has the smaller value, as
1185 * determined by using the {@code <} operator, lexicographically precedes the
1186 * other string. In this case, {@code compareTo} returns the
1187 * difference of the two character values at position {@code k} in
1188 * the two string -- that is, the value:
1189 * <blockquote><pre>
1190 * this.charAt(k)-anotherString.charAt(k)
1191 * </pre></blockquote>
1192 * If there is no index position at which they differ, then the shorter
1193 * string lexicographically precedes the longer string. In this case,
1194 * {@code compareTo} returns the difference of the lengths of the
1195 * strings -- that is, the value:
1196 * <blockquote><pre>
1197 * this.length()-anotherString.length()
1198 * </pre></blockquote>
1199 *
1200 * <p>For finer-grained String comparison, refer to
1201 * {@link java.text.Collator}.
1202 *
1203 * @param anotherString the {@code String} to be compared.
1204 * @return the value {@code 0} if the argument string is equal to
1205 * this string; a value less than {@code 0} if this string
1206 * is lexicographically less than the string argument; and a
1207 * value greater than {@code 0} if this string is
1208 * lexicographically greater than the string argument.
1209 */
1210 public int compareTo(String anotherString) {
1211 byte v1[] = value;
1212 byte v2[] = anotherString.value;
1213 byte coder = coder();
1214 if (coder == anotherString.coder()) {
1215 return coder == LATIN1 ? StringLatin1.compareTo(v1, v2)
1216 : StringUTF16.compareTo(v1, v2);
1217 }
1218 return coder == LATIN1 ? StringLatin1.compareToUTF16(v1, v2)
1219 : StringUTF16.compareToLatin1(v1, v2);
1220 }
1221
1222 /**
1223 * A Comparator that orders {@code String} objects as by
1224 * {@code compareToIgnoreCase}. This comparator is serializable.
1225 * <p>
1226 * Note that this Comparator does <em>not</em> take locale into account,
1227 * and will result in an unsatisfactory ordering for certain locales.
1228 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1229 *
1230 * @see java.text.Collator
1231 * @since 1.2
1232 */
1233 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1234 = new CaseInsensitiveComparator();
1235 private static class CaseInsensitiveComparator
1236 implements Comparator<String>, java.io.Serializable {
1237 // use serialVersionUID from JDK 1.2.2 for interoperability
1238 private static final long serialVersionUID = 8575799808933029326L;
1239
1240 public int compare(String s1, String s2) {
1241 byte v1[] = s1.value;
1242 byte v2[] = s2.value;
1243 byte coder = s1.coder();
1244 if (coder == s2.coder()) {
1245 return coder == LATIN1 ? StringLatin1.compareToCI(v1, v2)
1246 : StringUTF16.compareToCI(v1, v2);
1247 }
1248 return coder == LATIN1 ? StringLatin1.compareToCI_UTF16(v1, v2)
1249 : StringUTF16.compareToCI_Latin1(v1, v2);
1250 }
1251
1252 /** Replaces the de-serialized object. */
1253 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1254 }
1255
1256 /**
1257 * Compares two strings lexicographically, ignoring case
1258 * differences. This method returns an integer whose sign is that of
1259 * calling {@code compareTo} with normalized versions of the strings
1260 * where case differences have been eliminated by calling
1261 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1262 * each character.
1263 * <p>
1264 * Note that this method does <em>not</em> take locale into account,
1265 * and will result in an unsatisfactory ordering for certain locales.
1266 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1267 *
1268 * @param str the {@code String} to be compared.
1269 * @return a negative integer, zero, or a positive integer as the
1270 * specified String is greater than, equal to, or less
1271 * than this String, ignoring case considerations.
1272 * @see java.text.Collator
1273 * @since 1.2
1274 */
1275 public int compareToIgnoreCase(String str) {
1276 return CASE_INSENSITIVE_ORDER.compare(this, str);
1277 }
1278
1279 /**
1280 * Tests if two string regions are equal.
1281 * <p>
1282 * A substring of this {@code String} object is compared to a substring
1283 * of the argument other. The result is true if these substrings
1284 * represent identical character sequences. The substring of this
1285 * {@code String} object to be compared begins at index {@code toffset}
1286 * and has length {@code len}. The substring of other to be compared
1287 * begins at index {@code ooffset} and has length {@code len}. The
1288 * result is {@code false} if and only if at least one of the following
1289 * is true:
1290 * <ul><li>{@code toffset} is negative.
1291 * <li>{@code ooffset} is negative.
1292 * <li>{@code toffset+len} is greater than the length of this
1293 * {@code String} object.
1294 * <li>{@code ooffset+len} is greater than the length of the other
1295 * argument.
1296 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1297 * such that:
1298 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1299 * <i>k</i>{@code )}
1300 * </ul>
1301 *
1302 * <p>Note that this method does <em>not</em> take locale into account. The
1303 * {@link java.text.Collator} class provides locale-sensitive comparison.
1304 *
1305 * @param toffset the starting offset of the subregion in this string.
1306 * @param other the string argument.
1307 * @param ooffset the starting offset of the subregion in the string
1308 * argument.
1309 * @param len the number of characters to compare.
1310 * @return {@code true} if the specified subregion of this string
1311 * exactly matches the specified subregion of the string argument;
1312 * {@code false} otherwise.
1313 */
1314 public boolean regionMatches(int toffset, String other, int ooffset, int len) {
1315 byte tv[] = value;
1316 byte ov[] = other.value;
1317 // Note: toffset, ooffset, or len might be near -1>>>1.
1318 if ((ooffset < 0) || (toffset < 0) ||
1319 (toffset > (long)length() - len) ||
1320 (ooffset > (long)other.length() - len)) {
1321 return false;
1322 }
1323 byte coder = coder();
1324 if (coder == other.coder()) {
1325 if (!isLatin1() && (len > 0)) {
1326 toffset = toffset << 1;
1327 ooffset = ooffset << 1;
1328 len = len << 1;
1329 }
1330 while (len-- > 0) {
1331 if (tv[toffset++] != ov[ooffset++]) {
1332 return false;
1333 }
1334 }
1335 } else {
1336 if (coder == LATIN1) {
1337 while (len-- > 0) {
1338 if (StringLatin1.getChar(tv, toffset++) !=
1339 StringUTF16.getChar(ov, ooffset++)) {
1340 return false;
1341 }
1342 }
1343 } else {
1344 while (len-- > 0) {
1345 if (StringUTF16.getChar(tv, toffset++) !=
1346 StringLatin1.getChar(ov, ooffset++)) {
1347 return false;
1348 }
1349 }
1350 }
1351 }
1352 return true;
1353 }
1354
1355 /**
1356 * Tests if two string regions are equal.
1357 * <p>
1358 * A substring of this {@code String} object is compared to a substring
1359 * of the argument {@code other}. The result is {@code true} if these
1360 * substrings represent character sequences that are the same, ignoring
1361 * case if and only if {@code ignoreCase} is true. The substring of
1362 * this {@code String} object to be compared begins at index
1363 * {@code toffset} and has length {@code len}. The substring of
1364 * {@code other} to be compared begins at index {@code ooffset} and
1365 * has length {@code len}. The result is {@code false} if and only if
1366 * at least one of the following is true:
1367 * <ul><li>{@code toffset} is negative.
1368 * <li>{@code ooffset} is negative.
1369 * <li>{@code toffset+len} is greater than the length of this
1370 * {@code String} object.
1371 * <li>{@code ooffset+len} is greater than the length of the other
1372 * argument.
1373 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1374 * integer <i>k</i> less than {@code len} such that:
1375 * <blockquote><pre>
1376 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1377 * </pre></blockquote>
1378 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1379 * integer <i>k</i> less than {@code len} such that:
1380 * <blockquote><pre>
1381 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) !=
1382 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k)))
1383 * </pre></blockquote>
1384 * </ul>
1385 *
1386 * <p>Note that this method does <em>not</em> take locale into account,
1387 * and will result in unsatisfactory results for certain locales when
1388 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class
1389 * provides locale-sensitive comparison.
1390 *
1391 * @param ignoreCase if {@code true}, ignore case when comparing
1392 * characters.
1393 * @param toffset the starting offset of the subregion in this
1394 * string.
1395 * @param other the string argument.
1396 * @param ooffset the starting offset of the subregion in the string
1397 * argument.
1398 * @param len the number of characters to compare.
1399 * @return {@code true} if the specified subregion of this string
1400 * matches the specified subregion of the string argument;
1401 * {@code false} otherwise. Whether the matching is exact
1402 * or case insensitive depends on the {@code ignoreCase}
1403 * argument.
1404 */
1405 public boolean regionMatches(boolean ignoreCase, int toffset,
1406 String other, int ooffset, int len) {
1407 if (!ignoreCase) {
1408 return regionMatches(toffset, other, ooffset, len);
1409 }
1410 // Note: toffset, ooffset, or len might be near -1>>>1.
1411 if ((ooffset < 0) || (toffset < 0)
1412 || (toffset > (long)length() - len)
1413 || (ooffset > (long)other.length() - len)) {
1414 return false;
1415 }
1416 byte tv[] = value;
1417 byte ov[] = other.value;
1418 byte coder = coder();
1419 if (coder == other.coder()) {
1420 return coder == LATIN1
1421 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len)
1422 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len);
1423 }
1424 return coder == LATIN1
1425 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len)
1426 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len);
1427 }
1428
1429 /**
1430 * Tests if the substring of this string beginning at the
1431 * specified index starts with the specified prefix.
1432 *
1433 * @param prefix the prefix.
1434 * @param toffset where to begin looking in this string.
1435 * @return {@code true} if the character sequence represented by the
1436 * argument is a prefix of the substring of this object starting
1437 * at index {@code toffset}; {@code false} otherwise.
1438 * The result is {@code false} if {@code toffset} is
1439 * negative or greater than the length of this
1440 * {@code String} object; otherwise the result is the same
1441 * as the result of the expression
1442 * <pre>
1443 * this.substring(toffset).startsWith(prefix)
1444 * </pre>
1445 */
1446 public boolean startsWith(String prefix, int toffset) {
1447 // Note: toffset might be near -1>>>1.
1448 if (toffset < 0 || toffset > length() - prefix.length()) {
1449 return false;
1450 }
1451 byte ta[] = value;
1452 byte pa[] = prefix.value;
1453 int po = 0;
1454 int pc = pa.length;
1455 byte coder = coder();
1456 if (coder == prefix.coder()) {
1457 int to = (coder == LATIN1) ? toffset : toffset << 1;
1458 while (po < pc) {
1459 if (ta[to++] != pa[po++]) {
1460 return false;
1461 }
1462 }
1463 } else {
1464 if (coder == LATIN1) { // && pcoder == UTF16
1465 return false;
1466 }
1467 // coder == UTF16 && pcoder == LATIN1)
1468 while (po < pc) {
1469 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) {
1470 return false;
1471 }
1472 }
1473 }
1474 return true;
1475 }
1476
1477 /**
1478 * Tests if this string starts with the specified prefix.
1479 *
1480 * @param prefix the prefix.
1481 * @return {@code true} if the character sequence represented by the
1482 * argument is a prefix of the character sequence represented by
1483 * this string; {@code false} otherwise.
1484 * Note also that {@code true} will be returned if the
1485 * argument is an empty string or is equal to this
1486 * {@code String} object as determined by the
1487 * {@link #equals(Object)} method.
1488 * @since 1.0
1489 */
1490 public boolean startsWith(String prefix) {
1491 return startsWith(prefix, 0);
1492 }
1493
1494 /**
1495 * Tests if this string ends with the specified suffix.
1496 *
1497 * @param suffix the suffix.
1498 * @return {@code true} if the character sequence represented by the
1499 * argument is a suffix of the character sequence represented by
1500 * this object; {@code false} otherwise. Note that the
1501 * result will be {@code true} if the argument is the
1502 * empty string or is equal to this {@code String} object
1503 * as determined by the {@link #equals(Object)} method.
1504 */
1505 public boolean endsWith(String suffix) {
1506 return startsWith(suffix, length() - suffix.length());
1507 }
1508
1509 /**
1510 * Returns a hash code for this string. The hash code for a
1511 * {@code String} object is computed as
1512 * <blockquote><pre>
1513 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1514 * </pre></blockquote>
1515 * using {@code int} arithmetic, where {@code s[i]} is the
1516 * <i>i</i>th character of the string, {@code n} is the length of
1517 * the string, and {@code ^} indicates exponentiation.
1518 * (The hash value of the empty string is zero.)
1519 *
1520 * @return a hash code value for this object.
1521 */
1522 public int hashCode() {
1523 // The hash or hashIsZero fields are subject to a benign data race,
1524 // making it crucial to ensure that any observable result of the
1525 // calculation in this method stays correct under any possible read of
1526 // these fields. Necessary restrictions to allow this to be correct
1527 // without explicit memory fences or similar concurrency primitives is
1528 // that we can ever only write to one of these two fields for a given
1529 // String instance, and that the computation is idempotent and derived
1530 // from immutable state
1531 int h = hash;
1532 if (h == 0 && !hashIsZero) {
1533 h = isLatin1() ? StringLatin1.hashCode(value)
1534 : StringUTF16.hashCode(value);
1535 if (h == 0) {
1536 hashIsZero = true;
1537 } else {
1538 hash = h;
1539 }
1540 }
1541 return h;
1542 }
1543
1544 /**
1545 * Returns the index within this string of the first occurrence of
1546 * the specified character. If a character with value
1547 * {@code ch} occurs in the character sequence represented by
1548 * this {@code String} object, then the index (in Unicode
1549 * code units) of the first such occurrence is returned. For
1550 * values of {@code ch} in the range from 0 to 0xFFFF
1551 * (inclusive), this is the smallest value <i>k</i> such that:
1552 * <blockquote><pre>
1553 * this.charAt(<i>k</i>) == ch
1554 * </pre></blockquote>
1555 * is true. For other values of {@code ch}, it is the
1556 * smallest value <i>k</i> such that:
1557 * <blockquote><pre>
1558 * this.codePointAt(<i>k</i>) == ch
1559 * </pre></blockquote>
1560 * is true. In either case, if no such character occurs in this
1561 * string, then {@code -1} is returned.
1562 *
1563 * @param ch a character (Unicode code point).
1564 * @return the index of the first occurrence of the character in the
1565 * character sequence represented by this object, or
1566 * {@code -1} if the character does not occur.
1567 */
1568 public int indexOf(int ch) {
1569 return indexOf(ch, 0);
1570 }
1571
1572 /**
1573 * Returns the index within this string of the first occurrence of the
1574 * specified character, starting the search at the specified index.
1575 * <p>
1576 * If a character with value {@code ch} occurs in the
1577 * character sequence represented by this {@code String}
1578 * object at an index no smaller than {@code fromIndex}, then
1579 * the index of the first such occurrence is returned. For values
1580 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1581 * this is the smallest value <i>k</i> such that:
1582 * <blockquote><pre>
1583 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1584 * </pre></blockquote>
1585 * is true. For other values of {@code ch}, it is the
1586 * smallest value <i>k</i> such that:
1587 * <blockquote><pre>
1588 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1589 * </pre></blockquote>
1590 * is true. In either case, if no such character occurs in this
1591 * string at or after position {@code fromIndex}, then
1592 * {@code -1} is returned.
1593 *
1594 * <p>
1595 * There is no restriction on the value of {@code fromIndex}. If it
1596 * is negative, it has the same effect as if it were zero: this entire
1597 * string may be searched. If it is greater than the length of this
1598 * string, it has the same effect as if it were equal to the length of
1599 * this string: {@code -1} is returned.
1600 *
1601 * <p>All indices are specified in {@code char} values
1602 * (Unicode code units).
1603 *
1604 * @param ch a character (Unicode code point).
1605 * @param fromIndex the index to start the search from.
1606 * @return the index of the first occurrence of the character in the
1607 * character sequence represented by this object that is greater
1608 * than or equal to {@code fromIndex}, or {@code -1}
1609 * if the character does not occur.
1610 */
1611 public int indexOf(int ch, int fromIndex) {
1612 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
1613 : StringUTF16.indexOf(value, ch, fromIndex);
1614 }
1615
1616 /**
1617 * Returns the index within this string of the last occurrence of
1618 * the specified character. For values of {@code ch} in the
1619 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1620 * units) returned is the largest value <i>k</i> such that:
1621 * <blockquote><pre>
1622 * this.charAt(<i>k</i>) == ch
1623 * </pre></blockquote>
1624 * is true. For other values of {@code ch}, it is the
1625 * largest value <i>k</i> such that:
1626 * <blockquote><pre>
1627 * this.codePointAt(<i>k</i>) == ch
1628 * </pre></blockquote>
1629 * is true. In either case, if no such character occurs in this
1630 * string, then {@code -1} is returned. The
1631 * {@code String} is searched backwards starting at the last
1632 * character.
1633 *
1634 * @param ch a character (Unicode code point).
1635 * @return the index of the last occurrence of the character in the
1636 * character sequence represented by this object, or
1637 * {@code -1} if the character does not occur.
1638 */
1639 public int lastIndexOf(int ch) {
1640 return lastIndexOf(ch, length() - 1);
1641 }
1642
1643 /**
1644 * Returns the index within this string of the last occurrence of
1645 * the specified character, searching backward starting at the
1646 * specified index. For values of {@code ch} in the range
1647 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1648 * value <i>k</i> such that:
1649 * <blockquote><pre>
1650 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1651 * </pre></blockquote>
1652 * is true. For other values of {@code ch}, it is the
1653 * largest value <i>k</i> such that:
1654 * <blockquote><pre>
1655 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1656 * </pre></blockquote>
1657 * is true. In either case, if no such character occurs in this
1658 * string at or before position {@code fromIndex}, then
1659 * {@code -1} is returned.
1660 *
1661 * <p>All indices are specified in {@code char} values
1662 * (Unicode code units).
1663 *
1664 * @param ch a character (Unicode code point).
1665 * @param fromIndex the index to start the search from. There is no
1666 * restriction on the value of {@code fromIndex}. If it is
1667 * greater than or equal to the length of this string, it has
1668 * the same effect as if it were equal to one less than the
1669 * length of this string: this entire string may be searched.
1670 * If it is negative, it has the same effect as if it were -1:
1671 * -1 is returned.
1672 * @return the index of the last occurrence of the character in the
1673 * character sequence represented by this object that is less
1674 * than or equal to {@code fromIndex}, or {@code -1}
1675 * if the character does not occur before that point.
1676 */
1677 public int lastIndexOf(int ch, int fromIndex) {
1678 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex)
1679 : StringUTF16.lastIndexOf(value, ch, fromIndex);
1680 }
1681
1682 /**
1683 * Returns the index within this string of the first occurrence of the
1684 * specified substring.
1685 *
1686 * <p>The returned index is the smallest value {@code k} for which:
1687 * <pre>{@code
1688 * this.startsWith(str, k)
1689 * }</pre>
1690 * If no such value of {@code k} exists, then {@code -1} is returned.
1691 *
1692 * @param str the substring to search for.
1693 * @return the index of the first occurrence of the specified substring,
1694 * or {@code -1} if there is no such occurrence.
1695 */
1696 public int indexOf(String str) {
1697 byte coder = coder();
1698 if (coder == str.coder()) {
1699 return isLatin1() ? StringLatin1.indexOf(value, str.value)
1700 : StringUTF16.indexOf(value, str.value);
1701 }
1702 if (coder == LATIN1) { // str.coder == UTF16
1703 return -1;
1704 }
1705 return StringUTF16.indexOfLatin1(value, str.value);
1706 }
1707
1708 /**
1709 * Returns the index within this string of the first occurrence of the
1710 * specified substring, starting at the specified index.
1711 *
1712 * <p>The returned index is the smallest value {@code k} for which:
1713 * <pre>{@code
1714 * k >= Math.min(fromIndex, this.length()) &&
1715 * this.startsWith(str, k)
1716 * }</pre>
1717 * If no such value of {@code k} exists, then {@code -1} is returned.
1718 *
1719 * @param str the substring to search for.
1720 * @param fromIndex the index from which to start the search.
1721 * @return the index of the first occurrence of the specified substring,
1722 * starting at the specified index,
1723 * or {@code -1} if there is no such occurrence.
1724 */
1725 public int indexOf(String str, int fromIndex) {
1726 return indexOf(value, coder(), length(), str, fromIndex);
1727 }
1728
1729 /**
1730 * Code shared by String and AbstractStringBuilder to do searches. The
1731 * source is the character array being searched, and the target
1732 * is the string being searched for.
1733 *
1734 * @param src the characters being searched.
1735 * @param srcCoder the coder of the source string.
1736 * @param srcCount length of the source string.
1737 * @param tgtStr the characters being searched for.
1738 * @param fromIndex the index to begin searching from.
1739 */
1740 static int indexOf(byte[] src, byte srcCoder, int srcCount,
1741 String tgtStr, int fromIndex) {
1742 byte[] tgt = tgtStr.value;
1743 byte tgtCoder = tgtStr.coder();
1744 int tgtCount = tgtStr.length();
1745
1746 if (fromIndex >= srcCount) {
1747 return (tgtCount == 0 ? srcCount : -1);
1748 }
1749 if (fromIndex < 0) {
1750 fromIndex = 0;
1751 }
1752 if (tgtCount == 0) {
1753 return fromIndex;
1754 }
1755 if (tgtCount > srcCount) {
1756 return -1;
1757 }
1758 if (srcCoder == tgtCoder) {
1759 return srcCoder == LATIN1
1760 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex)
1761 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex);
1762 }
1763 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1764 return -1;
1765 }
1766 // srcCoder == UTF16 && tgtCoder == LATIN1) {
1767 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1768 }
1769
1770 /**
1771 * Returns the index within this string of the last occurrence of the
1772 * specified substring. The last occurrence of the empty string ""
1773 * is considered to occur at the index value {@code this.length()}.
1774 *
1775 * <p>The returned index is the largest value {@code k} for which:
1776 * <pre>{@code
1777 * this.startsWith(str, k)
1778 * }</pre>
1779 * If no such value of {@code k} exists, then {@code -1} is returned.
1780 *
1781 * @param str the substring to search for.
1782 * @return the index of the last occurrence of the specified substring,
1783 * or {@code -1} if there is no such occurrence.
1784 */
1785 public int lastIndexOf(String str) {
1786 return lastIndexOf(str, length());
1787 }
1788
1789 /**
1790 * Returns the index within this string of the last occurrence of the
1791 * specified substring, searching backward starting at the specified index.
1792 *
1793 * <p>The returned index is the largest value {@code k} for which:
1794 * <pre>{@code
1795 * k <= Math.min(fromIndex, this.length()) &&
1796 * this.startsWith(str, k)
1797 * }</pre>
1798 * If no such value of {@code k} exists, then {@code -1} is returned.
1799 *
1800 * @param str the substring to search for.
1801 * @param fromIndex the index to start the search from.
1802 * @return the index of the last occurrence of the specified substring,
1803 * searching backward from the specified index,
1804 * or {@code -1} if there is no such occurrence.
1805 */
1806 public int lastIndexOf(String str, int fromIndex) {
1807 return lastIndexOf(value, coder(), length(), str, fromIndex);
1808 }
1809
1810 /**
1811 * Code shared by String and AbstractStringBuilder to do searches. The
1812 * source is the character array being searched, and the target
1813 * is the string being searched for.
1814 *
1815 * @param src the characters being searched.
1816 * @param srcCoder coder handles the mapping between bytes/chars
1817 * @param srcCount count of the source string.
1818 * @param tgt the characters being searched for.
1819 * @param fromIndex the index to begin searching from.
1820 */
1821 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount,
1822 String tgtStr, int fromIndex) {
1823 byte[] tgt = tgtStr.value;
1824 byte tgtCoder = tgtStr.coder();
1825 int tgtCount = tgtStr.length();
1826 /*
1827 * Check arguments; return immediately where possible. For
1828 * consistency, don't check for null str.
1829 */
1830 int rightIndex = srcCount - tgtCount;
1831 if (fromIndex > rightIndex) {
1832 fromIndex = rightIndex;
1833 }
1834 if (fromIndex < 0) {
1835 return -1;
1836 }
1837 /* Empty string always matches. */
1838 if (tgtCount == 0) {
1839 return fromIndex;
1840 }
1841 if (srcCoder == tgtCoder) {
1842 return srcCoder == LATIN1
1843 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex)
1844 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex);
1845 }
1846 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1847 return -1;
1848 }
1849 // srcCoder == UTF16 && tgtCoder == LATIN1
1850 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1851 }
1852
1853 /**
1854 * Returns a string that is a substring of this string. The
1855 * substring begins with the character at the specified index and
1856 * extends to the end of this string. <p>
1857 * Examples:
1858 * <blockquote><pre>
1859 * "unhappy".substring(2) returns "happy"
1860 * "Harbison".substring(3) returns "bison"
1861 * "emptiness".substring(9) returns "" (an empty string)
1862 * </pre></blockquote>
1863 *
1864 * @param beginIndex the beginning index, inclusive.
1865 * @return the specified substring.
1866 * @exception IndexOutOfBoundsException if
1867 * {@code beginIndex} is negative or larger than the
1868 * length of this {@code String} object.
1869 */
1870 public String substring(int beginIndex) {
1871 return substring(beginIndex, length());
1872 }
1873
1874 /**
1875 * Returns a string that is a substring of this string. The
1876 * substring begins at the specified {@code beginIndex} and
1877 * extends to the character at index {@code endIndex - 1}.
1878 * Thus the length of the substring is {@code endIndex-beginIndex}.
1879 * <p>
1880 * Examples:
1881 * <blockquote><pre>
1882 * "hamburger".substring(4, 8) returns "urge"
1883 * "smiles".substring(1, 5) returns "mile"
1884 * </pre></blockquote>
1885 *
1886 * @param beginIndex the beginning index, inclusive.
1887 * @param endIndex the ending index, exclusive.
1888 * @return the specified substring.
1889 * @exception IndexOutOfBoundsException if the
1890 * {@code beginIndex} is negative, or
1891 * {@code endIndex} is larger than the length of
1892 * this {@code String} object, or
1893 * {@code beginIndex} is larger than
1894 * {@code endIndex}.
1895 */
1896 public String substring(int beginIndex, int endIndex) {
1897 int length = length();
1898 checkBoundsBeginEnd(beginIndex, endIndex, length);
1899 int subLen = endIndex - beginIndex;
1900 if (beginIndex == 0 && endIndex == length) {
1901 return this;
1902 }
1903 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1904 : StringUTF16.newString(value, beginIndex, subLen);
1905 }
1906
1907 /**
1908 * Returns a character sequence that is a subsequence of this sequence.
1909 *
1910 * <p> An invocation of this method of the form
1911 *
1912 * <blockquote><pre>
1913 * str.subSequence(begin, end)</pre></blockquote>
1914 *
1915 * behaves in exactly the same way as the invocation
1916 *
1917 * <blockquote><pre>
1918 * str.substring(begin, end)</pre></blockquote>
1919 *
1920 * @apiNote
1921 * This method is defined so that the {@code String} class can implement
1922 * the {@link CharSequence} interface.
1923 *
1924 * @param beginIndex the begin index, inclusive.
1925 * @param endIndex the end index, exclusive.
1926 * @return the specified subsequence.
1927 *
1928 * @throws IndexOutOfBoundsException
1929 * if {@code beginIndex} or {@code endIndex} is negative,
1930 * if {@code endIndex} is greater than {@code length()},
1931 * or if {@code beginIndex} is greater than {@code endIndex}
1932 *
1933 * @since 1.4
1934 * @spec JSR-51
1935 */
1936 public CharSequence subSequence(int beginIndex, int endIndex) {
1937 return this.substring(beginIndex, endIndex);
1938 }
1939
1940 /**
1941 * Concatenates the specified string to the end of this string.
1942 * <p>
1943 * If the length of the argument string is {@code 0}, then this
1944 * {@code String} object is returned. Otherwise, a
1945 * {@code String} object is returned that represents a character
1946 * sequence that is the concatenation of the character sequence
1947 * represented by this {@code String} object and the character
1948 * sequence represented by the argument string.<p>
1949 * Examples:
1950 * <blockquote><pre>
1951 * "cares".concat("s") returns "caress"
1952 * "to".concat("get").concat("her") returns "together"
1953 * </pre></blockquote>
1954 *
1955 * @param str the {@code String} that is concatenated to the end
1956 * of this {@code String}.
1957 * @return a string that represents the concatenation of this object's
1958 * characters followed by the string argument's characters.
1959 */
1960 public String concat(String str) {
1961 if (str.isEmpty()) {
1962 return this;
1963 }
1964 return StringConcatHelper.simpleConcat(this, str);
1965 }
1966
1967 /**
1968 * Returns a string resulting from replacing all occurrences of
1969 * {@code oldChar} in this string with {@code newChar}.
1970 * <p>
1971 * If the character {@code oldChar} does not occur in the
1972 * character sequence represented by this {@code String} object,
1973 * then a reference to this {@code String} object is returned.
1974 * Otherwise, a {@code String} object is returned that
1975 * represents a character sequence identical to the character sequence
1976 * represented by this {@code String} object, except that every
1977 * occurrence of {@code oldChar} is replaced by an occurrence
1978 * of {@code newChar}.
1979 * <p>
1980 * Examples:
1981 * <blockquote><pre>
1982 * "mesquite in your cellar".replace('e', 'o')
1983 * returns "mosquito in your collar"
1984 * "the war of baronets".replace('r', 'y')
1985 * returns "the way of bayonets"
1986 * "sparring with a purple porpoise".replace('p', 't')
1987 * returns "starring with a turtle tortoise"
1988 * "JonL".replace('q', 'x') returns "JonL" (no change)
1989 * </pre></blockquote>
1990 *
1991 * @param oldChar the old character.
1992 * @param newChar the new character.
1993 * @return a string derived from this string by replacing every
1994 * occurrence of {@code oldChar} with {@code newChar}.
1995 */
1996 public String replace(char oldChar, char newChar) {
1997 if (oldChar != newChar) {
1998 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar)
1999 : StringUTF16.replace(value, oldChar, newChar);
2000 if (ret != null) {
2001 return ret;
2002 }
2003 }
2004 return this;
2005 }
2006
2007 /**
2008 * Tells whether or not this string matches the given <a
2009 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2010 *
2011 * <p> An invocation of this method of the form
2012 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2013 * same result as the expression
2014 *
2015 * <blockquote>
2016 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2017 * matches(<i>regex</i>, <i>str</i>)}
2018 * </blockquote>
2019 *
2020 * @param regex
2021 * the regular expression to which this string is to be matched
2022 *
2023 * @return {@code true} if, and only if, this string matches the
2024 * given regular expression
2025 *
2026 * @throws PatternSyntaxException
2027 * if the regular expression's syntax is invalid
2028 *
2029 * @see java.util.regex.Pattern
2030 *
2031 * @since 1.4
2032 * @spec JSR-51
2033 */
2034 public boolean matches(String regex) {
2035 return Pattern.matches(regex, this);
2036 }
2037
2038 /**
2039 * Returns true if and only if this string contains the specified
2040 * sequence of char values.
2041 *
2042 * @param s the sequence to search for
2043 * @return true if this string contains {@code s}, false otherwise
2044 * @since 1.5
2045 */
2046 public boolean contains(CharSequence s) {
2047 return indexOf(s.toString()) >= 0;
2048 }
2049
2050 /**
2051 * Replaces the first substring of this string that matches the given <a
2052 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2053 * given replacement.
2054 *
2055 * <p> An invocation of this method of the form
2056 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2057 * yields exactly the same result as the expression
2058 *
2059 * <blockquote>
2060 * <code>
2061 * {@link java.util.regex.Pattern}.{@link
2062 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2063 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2064 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2065 * </code>
2066 * </blockquote>
2067 *
2068 *<p>
2069 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2070 * replacement string may cause the results to be different than if it were
2071 * being treated as a literal replacement string; see
2072 * {@link java.util.regex.Matcher#replaceFirst}.
2073 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2074 * meaning of these characters, if desired.
2075 *
2076 * @param regex
2077 * the regular expression to which this string is to be matched
2078 * @param replacement
2079 * the string to be substituted for the first match
2080 *
2081 * @return The resulting {@code String}
2082 *
2083 * @throws PatternSyntaxException
2084 * if the regular expression's syntax is invalid
2085 *
2086 * @see java.util.regex.Pattern
2087 *
2088 * @since 1.4
2089 * @spec JSR-51
2090 */
2091 public String replaceFirst(String regex, String replacement) {
2092 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2093 }
2094
2095 /**
2096 * Replaces each substring of this string that matches the given <a
2097 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2098 * given replacement.
2099 *
2100 * <p> An invocation of this method of the form
2101 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2102 * yields exactly the same result as the expression
2103 *
2104 * <blockquote>
2105 * <code>
2106 * {@link java.util.regex.Pattern}.{@link
2107 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2108 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2109 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2110 * </code>
2111 * </blockquote>
2112 *
2113 *<p>
2114 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2115 * replacement string may cause the results to be different than if it were
2116 * being treated as a literal replacement string; see
2117 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2118 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2119 * meaning of these characters, if desired.
2120 *
2121 * @param regex
2122 * the regular expression to which this string is to be matched
2123 * @param replacement
2124 * the string to be substituted for each match
2125 *
2126 * @return The resulting {@code String}
2127 *
2128 * @throws PatternSyntaxException
2129 * if the regular expression's syntax is invalid
2130 *
2131 * @see java.util.regex.Pattern
2132 *
2133 * @since 1.4
2134 * @spec JSR-51
2135 */
2136 public String replaceAll(String regex, String replacement) {
2137 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2138 }
2139
2140 /**
2141 * Replaces each substring of this string that matches the literal target
2142 * sequence with the specified literal replacement sequence. The
2143 * replacement proceeds from the beginning of the string to the end, for
2144 * example, replacing "aa" with "b" in the string "aaa" will result in
2145 * "ba" rather than "ab".
2146 *
2147 * @param target The sequence of char values to be replaced
2148 * @param replacement The replacement sequence of char values
2149 * @return The resulting string
2150 * @since 1.5
2151 */
2152 public String replace(CharSequence target, CharSequence replacement) {
2153 String trgtStr = target.toString();
2154 String replStr = replacement.toString();
2155 int thisLen = length();
2156 int trgtLen = trgtStr.length();
2157 int replLen = replStr.length();
2158
2159 if (trgtLen > 0) {
2160 if (trgtLen == 1 && replLen == 1) {
2161 return replace(trgtStr.charAt(0), replStr.charAt(0));
2162 }
2163
2164 boolean thisIsLatin1 = this.isLatin1();
2165 boolean trgtIsLatin1 = trgtStr.isLatin1();
2166 boolean replIsLatin1 = replStr.isLatin1();
2167 String ret = (thisIsLatin1 && trgtIsLatin1 && replIsLatin1)
2168 ? StringLatin1.replace(value, thisLen,
2169 trgtStr.value, trgtLen,
2170 replStr.value, replLen)
2171 : StringUTF16.replace(value, thisLen, thisIsLatin1,
2172 trgtStr.value, trgtLen, trgtIsLatin1,
2173 replStr.value, replLen, replIsLatin1);
2174 if (ret != null) {
2175 return ret;
2176 }
2177 return this;
2178
2179 } else { // trgtLen == 0
2180 int resultLen;
2181 try {
2182 resultLen = Math.addExact(thisLen, Math.multiplyExact(
2183 Math.addExact(thisLen, 1), replLen));
2184 } catch (ArithmeticException ignored) {
2185 throw new OutOfMemoryError();
2186 }
2187
2188 StringBuilder sb = new StringBuilder(resultLen);
2189 sb.append(replStr);
2190 for (int i = 0; i < thisLen; ++i) {
2191 sb.append(charAt(i)).append(replStr);
2192 }
2193 return sb.toString();
2194 }
2195 }
2196
2197 /**
2198 * Splits this string around matches of the given
2199 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2200 *
2201 * <p> The array returned by this method contains each substring of this
2202 * string that is terminated by another substring that matches the given
2203 * expression or is terminated by the end of the string. The substrings in
2204 * the array are in the order in which they occur in this string. If the
2205 * expression does not match any part of the input then the resulting array
2206 * has just one element, namely this string.
2207 *
2208 * <p> When there is a positive-width match at the beginning of this
2209 * string then an empty leading substring is included at the beginning
2210 * of the resulting array. A zero-width match at the beginning however
2211 * never produces such empty leading substring.
2212 *
2213 * <p> The {@code limit} parameter controls the number of times the
2214 * pattern is applied and therefore affects the length of the resulting
2215 * array.
2216 * <ul>
2217 * <li><p>
2218 * If the <i>limit</i> is positive then the pattern will be applied
2219 * at most <i>limit</i> - 1 times, the array's length will be
2220 * no greater than <i>limit</i>, and the array's last entry will contain
2221 * all input beyond the last matched delimiter.</p></li>
2222 *
2223 * <li><p>
2224 * If the <i>limit</i> is zero then the pattern will be applied as
2225 * many times as possible, the array can have any length, and trailing
2226 * empty strings will be discarded.</p></li>
2227 *
2228 * <li><p>
2229 * If the <i>limit</i> is negative then the pattern will be applied
2230 * as many times as possible and the array can have any length.</p></li>
2231 * </ul>
2232 *
2233 * <p> The string {@code "boo:and:foo"}, for example, yields the
2234 * following results with these parameters:
2235 *
2236 * <blockquote><table class="plain">
2237 * <caption style="display:none">Split example showing regex, limit, and result</caption>
2238 * <thead>
2239 * <tr>
2240 * <th scope="col">Regex</th>
2241 * <th scope="col">Limit</th>
2242 * <th scope="col">Result</th>
2243 * </tr>
2244 * </thead>
2245 * <tbody>
2246 * <tr><th scope="row" rowspan="3" style="font-weight:normal">:</th>
2247 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">2</th>
2248 * <td>{@code { "boo", "and:foo" }}</td></tr>
2249 * <tr><!-- : -->
2250 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2251 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2252 * <tr><!-- : -->
2253 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2254 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2255 * <tr><th scope="row" rowspan="3" style="font-weight:normal">o</th>
2256 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2257 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2258 * <tr><!-- o -->
2259 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2260 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2261 * <tr><!-- o -->
2262 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">0</th>
2263 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2264 * </tbody>
2265 * </table></blockquote>
2266 *
2267 * <p> An invocation of this method of the form
2268 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2269 * yields the same result as the expression
2270 *
2271 * <blockquote>
2272 * <code>
2273 * {@link java.util.regex.Pattern}.{@link
2274 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2275 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2276 * </code>
2277 * </blockquote>
2278 *
2279 *
2280 * @param regex
2281 * the delimiting regular expression
2282 *
2283 * @param limit
2284 * the result threshold, as described above
2285 *
2286 * @return the array of strings computed by splitting this string
2287 * around matches of the given regular expression
2288 *
2289 * @throws PatternSyntaxException
2290 * if the regular expression's syntax is invalid
2291 *
2292 * @see java.util.regex.Pattern
2293 *
2294 * @since 1.4
2295 * @spec JSR-51
2296 */
2297 public String[] split(String regex, int limit) {
2298 /* fastpath if the regex is a
2299 (1)one-char String and this character is not one of the
2300 RegEx's meta characters ".$|()[{^?*+\\", or
2301 (2)two-char String and the first char is the backslash and
2302 the second is not the ascii digit or ascii letter.
2303 */
2304 char ch = 0;
2305 if (((regex.length() == 1 &&
2306 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2307 (regex.length() == 2 &&
2308 regex.charAt(0) == '\\' &&
2309 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2310 ((ch-'a')|('z'-ch)) < 0 &&
2311 ((ch-'A')|('Z'-ch)) < 0)) &&
2312 (ch < Character.MIN_HIGH_SURROGATE ||
2313 ch > Character.MAX_LOW_SURROGATE))
2314 {
2315 int off = 0;
2316 int next = 0;
2317 boolean limited = limit > 0;
2318 ArrayList<String> list = new ArrayList<>();
2319 while ((next = indexOf(ch, off)) != -1) {
2320 if (!limited || list.size() < limit - 1) {
2321 list.add(substring(off, next));
2322 off = next + 1;
2323 } else { // last one
2324 //assert (list.size() == limit - 1);
2325 int last = length();
2326 list.add(substring(off, last));
2327 off = last;
2328 break;
2329 }
2330 }
2331 // If no match was found, return this
2332 if (off == 0)
2333 return new String[]{this};
2334
2335 // Add remaining segment
2336 if (!limited || list.size() < limit)
2337 list.add(substring(off, length()));
2338
2339 // Construct result
2340 int resultSize = list.size();
2341 if (limit == 0) {
2342 while (resultSize > 0 && list.get(resultSize - 1).isEmpty()) {
2343 resultSize--;
2344 }
2345 }
2346 String[] result = new String[resultSize];
2347 return list.subList(0, resultSize).toArray(result);
2348 }
2349 return Pattern.compile(regex).split(this, limit);
2350 }
2351
2352 /**
2353 * Splits this string around matches of the given <a
2354 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2355 *
2356 * <p> This method works as if by invoking the two-argument {@link
2357 * #split(String, int) split} method with the given expression and a limit
2358 * argument of zero. Trailing empty strings are therefore not included in
2359 * the resulting array.
2360 *
2361 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2362 * results with these expressions:
2363 *
2364 * <blockquote><table class="plain">
2365 * <caption style="display:none">Split examples showing regex and result</caption>
2366 * <thead>
2367 * <tr>
2368 * <th scope="col">Regex</th>
2369 * <th scope="col">Result</th>
2370 * </tr>
2371 * </thead>
2372 * <tbody>
2373 * <tr><th scope="row" style="text-weight:normal">:</th>
2374 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2375 * <tr><th scope="row" style="text-weight:normal">o</th>
2376 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2377 * </tbody>
2378 * </table></blockquote>
2379 *
2380 *
2381 * @param regex
2382 * the delimiting regular expression
2383 *
2384 * @return the array of strings computed by splitting this string
2385 * around matches of the given regular expression
2386 *
2387 * @throws PatternSyntaxException
2388 * if the regular expression's syntax is invalid
2389 *
2390 * @see java.util.regex.Pattern
2391 *
2392 * @since 1.4
2393 * @spec JSR-51
2394 */
2395 public String[] split(String regex) {
2396 return split(regex, 0);
2397 }
2398
2399 /**
2400 * Returns a new String composed of copies of the
2401 * {@code CharSequence elements} joined together with a copy of
2402 * the specified {@code delimiter}.
2403 *
2404 * <blockquote>For example,
2405 * <pre>{@code
2406 * String message = String.join("-", "Java", "is", "cool");
2407 * // message returned is: "Java-is-cool"
2408 * }</pre></blockquote>
2409 *
2410 * Note that if an element is null, then {@code "null"} is added.
2411 *
2412 * @param delimiter the delimiter that separates each element
2413 * @param elements the elements to join together.
2414 *
2415 * @return a new {@code String} that is composed of the {@code elements}
2416 * separated by the {@code delimiter}
2417 *
2418 * @throws NullPointerException If {@code delimiter} or {@code elements}
2419 * is {@code null}
2420 *
2421 * @see java.util.StringJoiner
2422 * @since 1.8
2423 */
2424 public static String join(CharSequence delimiter, CharSequence... elements) {
2425 Objects.requireNonNull(delimiter);
2426 Objects.requireNonNull(elements);
2427 // Number of elements not likely worth Arrays.stream overhead.
2428 StringJoiner joiner = new StringJoiner(delimiter);
2429 for (CharSequence cs: elements) {
2430 joiner.add(cs);
2431 }
2432 return joiner.toString();
2433 }
2434
2435 /**
2436 * Returns a new {@code String} composed of copies of the
2437 * {@code CharSequence elements} joined together with a copy of the
2438 * specified {@code delimiter}.
2439 *
2440 * <blockquote>For example,
2441 * <pre>{@code
2442 * List<String> strings = List.of("Java", "is", "cool");
2443 * String message = String.join(" ", strings);
2444 * //message returned is: "Java is cool"
2445 *
2446 * Set<String> strings =
2447 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool"));
2448 * String message = String.join("-", strings);
2449 * //message returned is: "Java-is-very-cool"
2450 * }</pre></blockquote>
2451 *
2452 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2453 *
2454 * @param delimiter a sequence of characters that is used to separate each
2455 * of the {@code elements} in the resulting {@code String}
2456 * @param elements an {@code Iterable} that will have its {@code elements}
2457 * joined together.
2458 *
2459 * @return a new {@code String} that is composed from the {@code elements}
2460 * argument
2461 *
2462 * @throws NullPointerException If {@code delimiter} or {@code elements}
2463 * is {@code null}
2464 *
2465 * @see #join(CharSequence,CharSequence...)
2466 * @see java.util.StringJoiner
2467 * @since 1.8
2468 */
2469 public static String join(CharSequence delimiter,
2470 Iterable<? extends CharSequence> elements) {
2471 Objects.requireNonNull(delimiter);
2472 Objects.requireNonNull(elements);
2473 StringJoiner joiner = new StringJoiner(delimiter);
2474 for (CharSequence cs: elements) {
2475 joiner.add(cs);
2476 }
2477 return joiner.toString();
2478 }
2479
2480 /**
2481 * Converts all of the characters in this {@code String} to lower
2482 * case using the rules of the given {@code Locale}. Case mapping is based
2483 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2484 * class. Since case mappings are not always 1:1 char mappings, the resulting
2485 * {@code String} may be a different length than the original {@code String}.
2486 * <p>
2487 * Examples of lowercase mappings are in the following table:
2488 * <table class="plain">
2489 * <caption style="display:none">Lowercase mapping examples showing language code of locale, upper case, lower case, and description</caption>
2490 * <thead>
2491 * <tr>
2492 * <th scope="col">Language Code of Locale</th>
2493 * <th scope="col">Upper Case</th>
2494 * <th scope="col">Lower Case</th>
2495 * <th scope="col">Description</th>
2496 * </tr>
2497 * </thead>
2498 * <tbody>
2499 * <tr>
2500 * <td>tr (Turkish)</td>
2501 * <th scope="row" style="font-weight:normal; text-align:left">\u0130</th>
2502 * <td>\u0069</td>
2503 * <td>capital letter I with dot above -> small letter i</td>
2504 * </tr>
2505 * <tr>
2506 * <td>tr (Turkish)</td>
2507 * <th scope="row" style="font-weight:normal; text-align:left">\u0049</th>
2508 * <td>\u0131</td>
2509 * <td>capital letter I -> small letter dotless i </td>
2510 * </tr>
2511 * <tr>
2512 * <td>(all)</td>
2513 * <th scope="row" style="font-weight:normal; text-align:left">French Fries</th>
2514 * <td>french fries</td>
2515 * <td>lowercased all chars in String</td>
2516 * </tr>
2517 * <tr>
2518 * <td>(all)</td>
2519 * <th scope="row" style="font-weight:normal; text-align:left">
2520 * ΙΧΘΥΣ</th>
2521 * <td>ιχθυσ</td>
2522 * <td>lowercased all chars in String</td>
2523 * </tr>
2524 * </tbody>
2525 * </table>
2526 *
2527 * @param locale use the case transformation rules for this locale
2528 * @return the {@code String}, converted to lowercase.
2529 * @see java.lang.String#toLowerCase()
2530 * @see java.lang.String#toUpperCase()
2531 * @see java.lang.String#toUpperCase(Locale)
2532 * @since 1.1
2533 */
2534 public String toLowerCase(Locale locale) {
2535 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale)
2536 : StringUTF16.toLowerCase(this, value, locale);
2537 }
2538
2539 /**
2540 * Converts all of the characters in this {@code String} to lower
2541 * case using the rules of the default locale. This is equivalent to calling
2542 * {@code toLowerCase(Locale.getDefault())}.
2543 * <p>
2544 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2545 * results if used for strings that are intended to be interpreted locale
2546 * independently.
2547 * Examples are programming language identifiers, protocol keys, and HTML
2548 * tags.
2549 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2550 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2551 * LATIN SMALL LETTER DOTLESS I character.
2552 * To obtain correct results for locale insensitive strings, use
2553 * {@code toLowerCase(Locale.ROOT)}.
2554 *
2555 * @return the {@code String}, converted to lowercase.
2556 * @see java.lang.String#toLowerCase(Locale)
2557 */
2558 public String toLowerCase() {
2559 return toLowerCase(Locale.getDefault());
2560 }
2561
2562 /**
2563 * Converts all of the characters in this {@code String} to upper
2564 * case using the rules of the given {@code Locale}. Case mapping is based
2565 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2566 * class. Since case mappings are not always 1:1 char mappings, the resulting
2567 * {@code String} may be a different length than the original {@code String}.
2568 * <p>
2569 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2570 *
2571 * <table class="plain">
2572 * <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>
2573 * <thead>
2574 * <tr>
2575 * <th scope="col">Language Code of Locale</th>
2576 * <th scope="col">Lower Case</th>
2577 * <th scope="col">Upper Case</th>
2578 * <th scope="col">Description</th>
2579 * </tr>
2580 * </thead>
2581 * <tbody>
2582 * <tr>
2583 * <td>tr (Turkish)</td>
2584 * <th scope="row" style="font-weight:normal; text-align:left">\u0069</th>
2585 * <td>\u0130</td>
2586 * <td>small letter i -> capital letter I with dot above</td>
2587 * </tr>
2588 * <tr>
2589 * <td>tr (Turkish)</td>
2590 * <th scope="row" style="font-weight:normal; text-align:left">\u0131</th>
2591 * <td>\u0049</td>
2592 * <td>small letter dotless i -> capital letter I</td>
2593 * </tr>
2594 * <tr>
2595 * <td>(all)</td>
2596 * <th scope="row" style="font-weight:normal; text-align:left">\u00df</th>
2597 * <td>\u0053 \u0053</td>
2598 * <td>small letter sharp s -> two letters: SS</td>
2599 * </tr>
2600 * <tr>
2601 * <td>(all)</td>
2602 * <th scope="row" style="font-weight:normal; text-align:left">Fahrvergnügen</th>
2603 * <td>FAHRVERGNÜGEN</td>
2604 * <td></td>
2605 * </tr>
2606 * </tbody>
2607 * </table>
2608 * @param locale use the case transformation rules for this locale
2609 * @return the {@code String}, converted to uppercase.
2610 * @see java.lang.String#toUpperCase()
2611 * @see java.lang.String#toLowerCase()
2612 * @see java.lang.String#toLowerCase(Locale)
2613 * @since 1.1
2614 */
2615 public String toUpperCase(Locale locale) {
2616 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale)
2617 : StringUTF16.toUpperCase(this, value, locale);
2618 }
2619
2620 /**
2621 * Converts all of the characters in this {@code String} to upper
2622 * case using the rules of the default locale. This method is equivalent to
2623 * {@code toUpperCase(Locale.getDefault())}.
2624 * <p>
2625 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2626 * results if used for strings that are intended to be interpreted locale
2627 * independently.
2628 * Examples are programming language identifiers, protocol keys, and HTML
2629 * tags.
2630 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2631 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2632 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2633 * To obtain correct results for locale insensitive strings, use
2634 * {@code toUpperCase(Locale.ROOT)}.
2635 *
2636 * @return the {@code String}, converted to uppercase.
2637 * @see java.lang.String#toUpperCase(Locale)
2638 */
2639 public String toUpperCase() {
2640 return toUpperCase(Locale.getDefault());
2641 }
2642
2643 /**
2644 * Returns a string whose value is this string, with all leading
2645 * and trailing space removed, where space is defined
2646 * as any character whose codepoint is less than or equal to
2647 * {@code 'U+0020'} (the space character).
2648 * <p>
2649 * If this {@code String} object represents an empty character
2650 * sequence, or the first and last characters of character sequence
2651 * represented by this {@code String} object both have codes
2652 * that are not space (as defined above), then a
2653 * reference to this {@code String} object is returned.
2654 * <p>
2655 * Otherwise, if all characters in this string are space (as
2656 * defined above), then a {@code String} object representing an
2657 * empty string is returned.
2658 * <p>
2659 * Otherwise, let <i>k</i> be the index of the first character in the
2660 * string whose code is not a space (as defined above) and let
2661 * <i>m</i> be the index of the last character in the string whose code
2662 * is not a space (as defined above). A {@code String}
2663 * object is returned, representing the substring of this string that
2664 * begins with the character at index <i>k</i> and ends with the
2665 * character at index <i>m</i>-that is, the result of
2666 * {@code this.substring(k, m + 1)}.
2667 * <p>
2668 * This method may be used to trim space (as defined above) from
2669 * the beginning and end of a string.
2670 *
2671 * @return a string whose value is this string, with all leading
2672 * and trailing space removed, or this string if it
2673 * has no leading or trailing space.
2674 */
2675 public String trim() {
2676 String ret = isLatin1() ? StringLatin1.trim(value)
2677 : StringUTF16.trim(value);
2678 return ret == null ? this : ret;
2679 }
2680
2681 /**
2682 * Returns a string whose value is this string, with all leading
2683 * and trailing {@linkplain Character#isWhitespace(int) white space}
2684 * removed.
2685 * <p>
2686 * If this {@code String} object represents an empty string,
2687 * or if all code points in this string are
2688 * {@linkplain Character#isWhitespace(int) white space}, then an empty string
2689 * is returned.
2690 * <p>
2691 * Otherwise, returns a substring of this string beginning with the first
2692 * code point that is not a {@linkplain Character#isWhitespace(int) white space}
2693 * up to and including the last code point that is not a
2694 * {@linkplain Character#isWhitespace(int) white space}.
2695 * <p>
2696 * This method may be used to strip
2697 * {@linkplain Character#isWhitespace(int) white space} from
2698 * the beginning and end of a string.
2699 *
2700 * @return a string whose value is this string, with all leading
2701 * and trailing white space removed
2702 *
2703 * @see Character#isWhitespace(int)
2704 *
2705 * @since 11
2706 */
2707 public String strip() {
2708 String ret = isLatin1() ? StringLatin1.strip(value)
2709 : StringUTF16.strip(value);
2710 return ret == null ? this : ret;
2711 }
2712
2713 /**
2714 * Returns a string whose value is this string, with all leading
2715 * {@linkplain Character#isWhitespace(int) white space} removed.
2716 * <p>
2717 * If this {@code String} object represents an empty string,
2718 * or if all code points in this string are
2719 * {@linkplain Character#isWhitespace(int) white space}, then an empty string
2720 * is returned.
2721 * <p>
2722 * Otherwise, returns a substring of this string beginning with the first
2723 * code point that is not a {@linkplain Character#isWhitespace(int) white space}
2724 * up to and including the last code point of this string.
2725 * <p>
2726 * This method may be used to trim
2727 * {@linkplain Character#isWhitespace(int) white space} from
2728 * the beginning of a string.
2729 *
2730 * @return a string whose value is this string, with all leading white
2731 * space removed
2732 *
2733 * @see Character#isWhitespace(int)
2734 *
2735 * @since 11
2736 */
2737 public String stripLeading() {
2738 String ret = isLatin1() ? StringLatin1.stripLeading(value)
2739 : StringUTF16.stripLeading(value);
2740 return ret == null ? this : ret;
2741 }
2742
2743 /**
2744 * Returns a string whose value is this string, with all trailing
2745 * {@linkplain Character#isWhitespace(int) white space} removed.
2746 * <p>
2747 * If this {@code String} object represents an empty string,
2748 * or if all characters in this string are
2749 * {@linkplain Character#isWhitespace(int) white space}, then an empty string
2750 * is returned.
2751 * <p>
2752 * Otherwise, returns a substring of this string beginning with the first
2753 * code point of this string up to and including the last code point
2754 * that is not a {@linkplain Character#isWhitespace(int) white space}.
2755 * <p>
2756 * This method may be used to trim
2757 * {@linkplain Character#isWhitespace(int) white space} from
2758 * the end of a string.
2759 *
2760 * @return a string whose value is this string, with all trailing white
2761 * space removed
2762 *
2763 * @see Character#isWhitespace(int)
2764 *
2765 * @since 11
2766 */
2767 public String stripTrailing() {
2768 String ret = isLatin1() ? StringLatin1.stripTrailing(value)
2769 : StringUTF16.stripTrailing(value);
2770 return ret == null ? this : ret;
2771 }
2772
2773 /**
2774 * Returns {@code true} if the string is empty or contains only
2775 * {@linkplain Character#isWhitespace(int) white space} codepoints,
2776 * otherwise {@code false}.
2777 *
2778 * @return {@code true} if the string is empty or contains only
2779 * {@linkplain Character#isWhitespace(int) white space} codepoints,
2780 * otherwise {@code false}
2781 *
2782 * @see Character#isWhitespace(int)
2783 *
2784 * @since 11
2785 */
2786 public boolean isBlank() {
2787 return indexOfNonWhitespace() == length();
2788 }
2789
2790 /**
2791 * Returns a stream of lines extracted from this string,
2792 * separated by line terminators.
2793 * <p>
2794 * A <i>line terminator</i> is one of the following:
2795 * a line feed character {@code "\n"} (U+000A),
2796 * a carriage return character {@code "\r"} (U+000D),
2797 * or a carriage return followed immediately by a line feed
2798 * {@code "\r\n"} (U+000D U+000A).
2799 * <p>
2800 * A <i>line</i> is either a sequence of zero or more characters
2801 * followed by a line terminator, or it is a sequence of one or
2802 * more characters followed by the end of the string. A
2803 * line does not include the line terminator.
2804 * <p>
2805 * The stream returned by this method contains the lines from
2806 * this string in the order in which they occur.
2807 *
2808 * @apiNote This definition of <i>line</i> implies that an empty
2809 * string has zero lines and that there is no empty line
2810 * following a line terminator at the end of a string.
2811 *
2812 * @implNote This method provides better performance than
2813 * split("\R") by supplying elements lazily and
2814 * by faster search of new line terminators.
2815 *
2816 * @return the stream of lines extracted from this string
2817 *
2818 * @since 11
2819 */
2820 public Stream<String> lines() {
2821 return isLatin1() ? StringLatin1.lines(value) : StringUTF16.lines(value);
2822 }
2823
2824 /**
2825 * Adjusts the indentation of each line of this string based on the value of
2826 * {@code n}, and normalizes line termination characters.
2827 * <p>
2828 * This string is conceptually separated into lines using
2829 * {@link String#lines()}. Each line is then adjusted as described below
2830 * and then suffixed with a line feed {@code "\n"} (U+000A). The resulting
2831 * lines are then concatenated and returned.
2832 * <p>
2833 * If {@code n > 0} then {@code n} spaces (U+0020) are inserted at the
2834 * beginning of each line.
2835 * <p>
2836 * If {@code n < 0} then up to {@code n}
2837 * {@linkplain Character#isWhitespace(int) white space characters} are removed
2838 * from the beginning of each line. If a given line does not contain
2839 * sufficient white space then all leading
2840 * {@linkplain Character#isWhitespace(int) white space characters} are removed.
2841 * Each white space character is treated as a single character. In
2842 * particular, the tab character {@code "\t"} (U+0009) is considered a
2843 * single character; it is not expanded.
2844 * <p>
2845 * If {@code n == 0} then the line remains unchanged. However, line
2846 * terminators are still normalized.
2847 *
2848 * @param n number of leading
2849 * {@linkplain Character#isWhitespace(int) white space characters}
2850 * to add or remove
2851 *
2852 * @return string with indentation adjusted and line endings normalized
2853 *
2854 * @see String#lines()
2855 * @see String#isBlank()
2856 * @see Character#isWhitespace(int)
2857 *
2858 * @since 12
2859 */
2860 public String indent(int n) {
2861 if (isEmpty()) {
2862 return "";
2863 }
2864 Stream<String> stream = lines();
2865 if (n > 0) {
2866 final String spaces = " ".repeat(n);
2867 stream = stream.map(s -> spaces + s);
2868 } else if (n == Integer.MIN_VALUE) {
2869 stream = stream.map(s -> s.stripLeading());
2870 } else if (n < 0) {
2871 stream = stream.map(s -> s.substring(Math.min(-n, s.indexOfNonWhitespace())));
2872 }
2873 return stream.collect(Collectors.joining("\n", "", "\n"));
2874 }
2875
2876 private int indexOfNonWhitespace() {
2877 return isLatin1() ? StringLatin1.indexOfNonWhitespace(value)
2878 : StringUTF16.indexOfNonWhitespace(value);
2879 }
2880
2881 private int lastIndexOfNonWhitespace() {
2882 return isLatin1() ? StringLatin1.lastIndexOfNonWhitespace(value)
2883 : StringUTF16.lastIndexOfNonWhitespace(value);
2884 }
2885
2886 /**
2887 * Returns a string whose value is this string, with incidental
2888 * {@linkplain Character#isWhitespace(int) white space} removed from
2889 * the beginning and end of every line.
2890 * <p>
2891 * Incidental {@linkplain Character#isWhitespace(int) white space}
2892 * is often present in a text block to align the content with the opening
2893 * delimiter. For example, in the following code, dots represent incidental
2894 * {@linkplain Character#isWhitespace(int) white space}:
2895 * <blockquote><pre>
2896 * String html = """
2897 * ..............<html>
2898 * .............. <body>
2899 * .............. <p>Hello, world</p>
2900 * .............. </body>
2901 * ..............</html>
2902 * ..............""";
2903 * </pre></blockquote>
2904 * This method treats the incidental
2905 * {@linkplain Character#isWhitespace(int) white space} as indentation to be
2906 * stripped, producing a string that preserves the relative indentation of
2907 * the content. Using | to visualize the start of each line of the string:
2908 * <blockquote><pre>
2909 * |<html>
2910 * | <body>
2911 * | <p>Hello, world</p>
2912 * | </body>
2913 * |</html>
2914 * </pre></blockquote>
2915 * First, the individual lines of this string are extracted as if by using
2916 * {@link String#lines()}.
2917 * <p>
2918 * Then, the <i>minimum indentation</i> (min) is determined as follows.
2919 * For each non-blank line (as defined by {@link String#isBlank()}), the
2920 * leading {@linkplain Character#isWhitespace(int) white space} characters are
2921 * counted. The leading {@linkplain Character#isWhitespace(int) white space}
2922 * characters on the last line are also counted even if
2923 * {@linkplain String#isBlank() blank}. The <i>min</i> value is the smallest
2924 * of these counts.
2925 * <p>
2926 * For each {@linkplain String#isBlank() non-blank} line, <i>min</i> leading
2927 * {@linkplain Character#isWhitespace(int) white space} characters are removed,
2928 * and any trailing {@linkplain Character#isWhitespace(int) white space}
2929 * characters are removed. {@linkplain String#isBlank() Blank} lines are
2930 * replaced with the empty string.
2931 *
2932 * <p>
2933 * Finally, the lines are joined into a new string, using the LF character
2934 * {@code "\n"} (U+000A) to separate lines.
2935 *
2936 * @apiNote
2937 * This method's primary purpose is to shift a block of lines as far as
2938 * possible to the left, while preserving relative indentation. Lines
2939 * that were indented the least will thus have no leading
2940 * {@linkplain Character#isWhitespace(int) white space}.
2941 * The line count of the result will be the same as line count of this
2942 * string.
2943 * If this string ends with a line terminator then the result will end
2944 * with a line terminator.
2945 *
2946 * @implNote
2947 * This method treats all {@linkplain Character#isWhitespace(int) white space}
2948 * characters as having equal width. As long as the indentation on every
2949 * line is consistently composed of the same character sequences, then the
2950 * result will be as described above.
2951 *
2952 * @return string with incidental indentation removed and line
2953 * terminators normalized
2954 *
2955 * @see String#lines()
2956 * @see String#isBlank()
2957 * @see String#indent(int)
2958 * @see Character#isWhitespace(int)
2959 *
2960 * @since 13
2961 *
2962 * @deprecated This method is associated with text blocks, a preview language feature.
2963 * Text blocks and/or this method may be changed or removed in a future release.
2964 */
2965 @Deprecated(forRemoval=true, since="13")
2966 public String stripIndent() {
2967 int length = length();
2968 if (length == 0) {
2969 return "";
2970 }
2971 char lastChar = charAt(length - 1);
2972 boolean optOut = lastChar == '\n' || lastChar == '\r';
2973 List<String> lines = lines().collect(Collectors.toList());
2974 final int outdent = optOut ? 0 : outdent(lines);
2975 return lines.stream()
2976 .map(line -> {
2977 int firstNonWhitespace = line.indexOfNonWhitespace();
2978 int lastNonWhitespace = line.lastIndexOfNonWhitespace();
2979 int incidentalWhitespace = Math.min(outdent, firstNonWhitespace);
2980 return firstNonWhitespace > lastNonWhitespace
2981 ? "" : line.substring(incidentalWhitespace, lastNonWhitespace);
2982 })
2983 .collect(Collectors.joining("\n", "", optOut ? "\n" : ""));
2984 }
2985
2986 private static int outdent(List<String> lines) {
2987 // Note: outdent is guaranteed to be zero or positive number.
2988 // If there isn't a non-blank line then the last must be blank
2989 int outdent = Integer.MAX_VALUE;
2990 for (String line : lines) {
2991 int leadingWhitespace = line.indexOfNonWhitespace();
2992 if (leadingWhitespace != line.length()) {
2993 outdent = Integer.min(outdent, leadingWhitespace);
2994 }
2995 }
2996 String lastLine = lines.get(lines.size() - 1);
2997 if (lastLine.isBlank()) {
2998 outdent = Integer.min(outdent, lastLine.length());
2999 }
3000 return outdent;
3001 }
3002
3003 /**
3004 * Returns a string whose value is this string, with escape sequences
3005 * translated as if in a string literal.
3006 * <p>
3007 * Escape sequences are translated as follows;
3008 * <table class="striped">
3009 * <caption style="display:none">Translation</caption>
3010 * <thead>
3011 * <tr>
3012 * <th scope="col">Escape</th>
3013 * <th scope="col">Name</th>
3014 * <th scope="col">Translation</th>
3015 * </tr>
3016 * </thead>
3017 * <tbody>
3018 * <tr>
3019 * <th scope="row">{@code \u005Cb}</th>
3020 * <td>backspace</td>
3021 * <td>{@code U+0008}</td>
3022 * </tr>
3023 * <tr>
3024 * <th scope="row">{@code \u005Ct}</th>
3025 * <td>horizontal tab</td>
3026 * <td>{@code U+0009}</td>
3027 * </tr>
3028 * <tr>
3029 * <th scope="row">{@code \u005Cn}</th>
3030 * <td>line feed</td>
3031 * <td>{@code U+000A}</td>
3032 * </tr>
3033 * <tr>
3034 * <th scope="row">{@code \u005Cf}</th>
3035 * <td>form feed</td>
3036 * <td>{@code U+000C}</td>
3037 * </tr>
3038 * <tr>
3039 * <th scope="row">{@code \u005Cr}</th>
3040 * <td>carriage return</td>
3041 * <td>{@code U+000D}</td>
3042 * </tr>
3043 * <tr>
3044 * <th scope="row">{@code \u005C"}</th>
3045 * <td>double quote</td>
3046 * <td>{@code U+0022}</td>
3047 * </tr>
3048 * <tr>
3049 * <th scope="row">{@code \u005C'}</th>
3050 * <td>single quote</td>
3051 * <td>{@code U+0027}</td>
3052 * </tr>
3053 * <tr>
3054 * <th scope="row">{@code \u005C\u005C}</th>
3055 * <td>backslash</td>
3056 * <td>{@code U+005C}</td>
3057 * </tr>
3058 * <tr>
3059 * <th scope="row">{@code \u005C0 - \u005C377}</th>
3060 * <td>octal escape</td>
3061 * <td>code point equivalents</td>
3062 * </tr>
3063 * </tbody>
3064 * </table>
3065 *
3066 * @implNote
3067 * This method does <em>not</em> translate Unicode escapes such as "{@code \u005cu2022}".
3068 * Unicode escapes are translated by the Java compiler when reading input characters and
3069 * are not part of the string literal specification.
3070 *
3071 * @throws IllegalArgumentException when an escape sequence is malformed.
3072 *
3073 * @return String with escape sequences translated.
3074 *
3075 * @jls 3.10.7 Escape Sequences
3076 *
3077 * @since 13
3078 *
3079 * @deprecated This method is associated with text blocks, a preview language feature.
3080 * Text blocks and/or this method may be changed or removed in a future release.
3081 */
3082 @Deprecated(forRemoval=true, since="13")
3083 public String translateEscapes() {
3084 if (isEmpty()) {
3085 return "";
3086 }
3087 char[] chars = toCharArray();
3088 int length = chars.length;
3089 int from = 0;
3090 int to = 0;
3091 while (from < length) {
3092 char ch = chars[from++];
3093 if (ch == '\\') {
3094 ch = from < length ? chars[from++] : '\0';
3095 switch (ch) {
3096 case 'b':
3097 ch = '\b';
3098 break;
3099 case 'f':
3100 ch = '\f';
3101 break;
3102 case 'n':
3103 ch = '\n';
3104 break;
3105 case 'r':
3106 ch = '\r';
3107 break;
3108 case 't':
3109 ch = '\t';
3110 break;
3111 case '\'':
3112 case '\"':
3113 case '\\':
3114 // as is
3115 break;
3116 case '0': case '1': case '2': case '3':
3117 case '4': case '5': case '6': case '7':
3118 int limit = Integer.min(from + (ch <= '3' ? 2 : 1), length);
3119 int code = ch - '0';
3120 while (from < limit) {
3121 ch = chars[from];
3122 if (ch < '0' || '7' < ch) {
3123 break;
3124 }
3125 from++;
3126 code = (code << 3) | (ch - '0');
3127 }
3128 ch = (char)code;
3129 break;
3130 default: {
3131 String msg = String.format(
3132 "Invalid escape sequence: \\%c \\\\u%04X",
3133 ch, (int)ch);
3134 throw new IllegalArgumentException(msg);
3135 }
3136 }
3137 }
3138
3139 chars[to++] = ch;
3140 }
3141
3142 return new String(chars, 0, to);
3143 }
3144
3145 /**
3146 * This method allows the application of a function to {@code this}
3147 * string. The function should expect a single String argument
3148 * and produce an {@code R} result.
3149 * <p>
3150 * Any exception thrown by {@code f()} will be propagated to the
3151 * caller.
3152 *
3153 * @param f functional interface to a apply
3154 *
3155 * @param <R> class of the result
3156 *
3157 * @return the result of applying the function to this string
3158 *
3159 * @see java.util.function.Function
3160 *
3161 * @since 12
3162 */
3163 public <R> R transform(Function<? super String, ? extends R> f) {
3164 return f.apply(this);
3165 }
3166
3167 /**
3168 * This object (which is already a string!) is itself returned.
3169 *
3170 * @return the string itself.
3171 */
3172 public String toString() {
3173 return this;
3174 }
3175
3176 /**
3177 * Returns a stream of {@code int} zero-extending the {@code char} values
3178 * from this sequence. Any char which maps to a <a
3179 * href="{@docRoot}/java.base/java/lang/Character.html#unicode">surrogate code
3180 * point</a> is passed through uninterpreted.
3181 *
3182 * @return an IntStream of char values from this sequence
3183 * @since 9
3184 */
3185 @Override
3186 public IntStream chars() {
3187 return StreamSupport.intStream(
3188 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
3189 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE),
3190 false);
3191 }
3192
3193
3194 /**
3195 * Returns a stream of code point values from this sequence. Any surrogate
3196 * pairs encountered in the sequence are combined as if by {@linkplain
3197 * Character#toCodePoint Character.toCodePoint} and the result is passed
3198 * to the stream. Any other code units, including ordinary BMP characters,
3199 * unpaired surrogates, and undefined code units, are zero-extended to
3200 * {@code int} values which are then passed to the stream.
3201 *
3202 * @return an IntStream of Unicode code points from this sequence
3203 * @since 9
3204 */
3205 @Override
3206 public IntStream codePoints() {
3207 return StreamSupport.intStream(
3208 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
3209 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE),
3210 false);
3211 }
3212
3213 /**
3214 * Converts this string to a new character array.
3215 *
3216 * @return a newly allocated character array whose length is the length
3217 * of this string and whose contents are initialized to contain
3218 * the character sequence represented by this string.
3219 */
3220 public char[] toCharArray() {
3221 return isLatin1() ? StringLatin1.toChars(value)
3222 : StringUTF16.toChars(value);
3223 }
3224
3225 /**
3226 * Returns a formatted string using the specified format string and
3227 * arguments.
3228 *
3229 * <p> The locale always used is the one returned by {@link
3230 * java.util.Locale#getDefault(java.util.Locale.Category)
3231 * Locale.getDefault(Locale.Category)} with
3232 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified.
3233 *
3234 * @param format
3235 * A <a href="../util/Formatter.html#syntax">format string</a>
3236 *
3237 * @param args
3238 * Arguments referenced by the format specifiers in the format
3239 * string. If there are more arguments than format specifiers, the
3240 * extra arguments are ignored. The number of arguments is
3241 * variable and may be zero. The maximum number of arguments is
3242 * limited by the maximum dimension of a Java array as defined by
3243 * <cite>The Java™ Virtual Machine Specification</cite>.
3244 * The behaviour on a
3245 * {@code null} argument depends on the <a
3246 * href="../util/Formatter.html#syntax">conversion</a>.
3247 *
3248 * @throws java.util.IllegalFormatException
3249 * If a format string contains an illegal syntax, a format
3250 * specifier that is incompatible with the given arguments,
3251 * insufficient arguments given the format string, or other
3252 * illegal conditions. For specification of all possible
3253 * formatting errors, see the <a
3254 * href="../util/Formatter.html#detail">Details</a> section of the
3255 * formatter class specification.
3256 *
3257 * @return A formatted string
3258 *
3259 * @see java.util.Formatter
3260 * @since 1.5
3261 */
3262 public static String format(String format, Object... args) {
3263 return new Formatter().format(format, args).toString();
3264 }
3265
3266 /**
3267 * Returns a formatted string using the specified locale, format string,
3268 * and arguments.
3269 *
3270 * @param l
3271 * The {@linkplain java.util.Locale locale} to apply during
3272 * formatting. If {@code l} is {@code null} then no localization
3273 * is applied.
3274 *
3275 * @param format
3276 * A <a href="../util/Formatter.html#syntax">format string</a>
3277 *
3278 * @param args
3279 * Arguments referenced by the format specifiers in the format
3280 * string. If there are more arguments than format specifiers, the
3281 * extra arguments are ignored. The number of arguments is
3282 * variable and may be zero. The maximum number of arguments is
3283 * limited by the maximum dimension of a Java array as defined by
3284 * <cite>The Java™ Virtual Machine Specification</cite>.
3285 * The behaviour on a
3286 * {@code null} argument depends on the
3287 * <a href="../util/Formatter.html#syntax">conversion</a>.
3288 *
3289 * @throws java.util.IllegalFormatException
3290 * If a format string contains an illegal syntax, a format
3291 * specifier that is incompatible with the given arguments,
3292 * insufficient arguments given the format string, or other
3293 * illegal conditions. For specification of all possible
3294 * formatting errors, see the <a
3295 * href="../util/Formatter.html#detail">Details</a> section of the
3296 * formatter class specification
3297 *
3298 * @return A formatted string
3299 *
3300 * @see java.util.Formatter
3301 * @since 1.5
3302 */
3303 public static String format(Locale l, String format, Object... args) {
3304 return new Formatter(l).format(format, args).toString();
3305 }
3306
3307 /**
3308 * Formats using this string as the format string, and the supplied
3309 * arguments.
3310 *
3311 * @implSpec This method is equivalent to {@code String.format(this, args)}.
3312 *
3313 * @param args
3314 * Arguments referenced by the format specifiers in this string.
3315 *
3316 * @return A formatted string
3317 *
3318 * @see java.lang.String#format(String,Object...)
3319 * @see java.util.Formatter
3320 *
3321 * @since 13
3322 *
3323 * @deprecated This method is associated with text blocks, a preview language feature.
3324 * Text blocks and/or this method may be changed or removed in a future release.
3325 */
3326 @Deprecated(forRemoval=true, since="13")
3327 public String formatted(Object... args) {
3328 return new Formatter().format(this, args).toString();
3329 }
3330
3331 /**
3332 * Returns the string representation of the {@code Object} argument.
3333 *
3334 * @param obj an {@code Object}.
3335 * @return if the argument is {@code null}, then a string equal to
3336 * {@code "null"}; otherwise, the value of
3337 * {@code obj.toString()} is returned.
3338 * @see java.lang.Object#toString()
3339 */
3340 public static String valueOf(Object obj) {
3341 return (obj == null) ? "null" : obj.toString();
3342 }
3343
3344 /**
3345 * Returns the string representation of the {@code char} array
3346 * argument. The contents of the character array are copied; subsequent
3347 * modification of the character array does not affect the returned
3348 * string.
3349 *
3350 * @param data the character array.
3351 * @return a {@code String} that contains the characters of the
3352 * character array.
3353 */
3354 public static String valueOf(char data[]) {
3355 return new String(data);
3356 }
3357
3358 /**
3359 * Returns the string representation of a specific subarray of the
3360 * {@code char} array argument.
3361 * <p>
3362 * The {@code offset} argument is the index of the first
3363 * character of the subarray. The {@code count} argument
3364 * specifies the length of the subarray. The contents of the subarray
3365 * are copied; subsequent modification of the character array does not
3366 * affect the returned string.
3367 *
3368 * @param data the character array.
3369 * @param offset initial offset of the subarray.
3370 * @param count length of the subarray.
3371 * @return a {@code String} that contains the characters of the
3372 * specified subarray of the character array.
3373 * @exception IndexOutOfBoundsException if {@code offset} is
3374 * negative, or {@code count} is negative, or
3375 * {@code offset+count} is larger than
3376 * {@code data.length}.
3377 */
3378 public static String valueOf(char data[], int offset, int count) {
3379 return new String(data, offset, count);
3380 }
3381
3382 /**
3383 * Equivalent to {@link #valueOf(char[], int, int)}.
3384 *
3385 * @param data the character array.
3386 * @param offset initial offset of the subarray.
3387 * @param count length of the subarray.
3388 * @return a {@code String} that contains the characters of the
3389 * specified subarray of the character array.
3390 * @exception IndexOutOfBoundsException if {@code offset} is
3391 * negative, or {@code count} is negative, or
3392 * {@code offset+count} is larger than
3393 * {@code data.length}.
3394 */
3395 public static String copyValueOf(char data[], int offset, int count) {
3396 return new String(data, offset, count);
3397 }
3398
3399 /**
3400 * Equivalent to {@link #valueOf(char[])}.
3401 *
3402 * @param data the character array.
3403 * @return a {@code String} that contains the characters of the
3404 * character array.
3405 */
3406 public static String copyValueOf(char data[]) {
3407 return new String(data);
3408 }
3409
3410 /**
3411 * Returns the string representation of the {@code boolean} argument.
3412 *
3413 * @param b a {@code boolean}.
3414 * @return if the argument is {@code true}, a string equal to
3415 * {@code "true"} is returned; otherwise, a string equal to
3416 * {@code "false"} is returned.
3417 */
3418 public static String valueOf(boolean b) {
3419 return b ? "true" : "false";
3420 }
3421
3422 /**
3423 * Returns the string representation of the {@code char}
3424 * argument.
3425 *
3426 * @param c a {@code char}.
3427 * @return a string of length {@code 1} containing
3428 * as its single character the argument {@code c}.
3429 */
3430 public static String valueOf(char c) {
3431 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) {
3432 return new String(StringLatin1.toBytes(c), LATIN1);
3433 }
3434 return new String(StringUTF16.toBytes(c), UTF16);
3435 }
3436
3437 /**
3438 * Returns the string representation of the {@code int} argument.
3439 * <p>
3440 * The representation is exactly the one returned by the
3441 * {@code Integer.toString} method of one argument.
3442 *
3443 * @param i an {@code int}.
3444 * @return a string representation of the {@code int} argument.
3445 * @see java.lang.Integer#toString(int, int)
3446 */
3447 public static String valueOf(int i) {
3448 return Integer.toString(i);
3449 }
3450
3451 /**
3452 * Returns the string representation of the {@code long} argument.
3453 * <p>
3454 * The representation is exactly the one returned by the
3455 * {@code Long.toString} method of one argument.
3456 *
3457 * @param l a {@code long}.
3458 * @return a string representation of the {@code long} argument.
3459 * @see java.lang.Long#toString(long)
3460 */
3461 public static String valueOf(long l) {
3462 return Long.toString(l);
3463 }
3464
3465 /**
3466 * Returns the string representation of the {@code float} argument.
3467 * <p>
3468 * The representation is exactly the one returned by the
3469 * {@code Float.toString} method of one argument.
3470 *
3471 * @param f a {@code float}.
3472 * @return a string representation of the {@code float} argument.
3473 * @see java.lang.Float#toString(float)
3474 */
3475 public static String valueOf(float f) {
3476 return Float.toString(f);
3477 }
3478
3479 /**
3480 * Returns the string representation of the {@code double} argument.
3481 * <p>
3482 * The representation is exactly the one returned by the
3483 * {@code Double.toString} method of one argument.
3484 *
3485 * @param d a {@code double}.
3486 * @return a string representation of the {@code double} argument.
3487 * @see java.lang.Double#toString(double)
3488 */
3489 public static String valueOf(double d) {
3490 return Double.toString(d);
3491 }
3492
3493 /**
3494 * Returns a canonical representation for the string object.
3495 * <p>
3496 * A pool of strings, initially empty, is maintained privately by the
3497 * class {@code String}.
3498 * <p>
3499 * When the intern method is invoked, if the pool already contains a
3500 * string equal to this {@code String} object as determined by
3501 * the {@link #equals(Object)} method, then the string from the pool is
3502 * returned. Otherwise, this {@code String} object is added to the
3503 * pool and a reference to this {@code String} object is returned.
3504 * <p>
3505 * It follows that for any two strings {@code s} and {@code t},
3506 * {@code s.intern() == t.intern()} is {@code true}
3507 * if and only if {@code s.equals(t)} is {@code true}.
3508 * <p>
3509 * All literal strings and string-valued constant expressions are
3510 * interned. String literals are defined in section 3.10.5 of the
3511 * <cite>The Java™ Language Specification</cite>.
3512 *
3513 * @return a string that has the same contents as this string, but is
3514 * guaranteed to be from a pool of unique strings.
3515 * @jls 3.10.5 String Literals
3516 */
3517 public native String intern();
3518
3519 /**
3520 * Returns a string whose value is the concatenation of this
3521 * string repeated {@code count} times.
3522 * <p>
3523 * If this string is empty or count is zero then the empty
3524 * string is returned.
3525 *
3526 * @param count number of times to repeat
3527 *
3528 * @return A string composed of this string repeated
3529 * {@code count} times or the empty string if this
3530 * string is empty or count is zero
3531 *
3532 * @throws IllegalArgumentException if the {@code count} is
3533 * negative.
3534 *
3535 * @since 11
3536 */
3537 public String repeat(int count) {
3538 if (count < 0) {
3539 throw new IllegalArgumentException("count is negative: " + count);
3540 }
3541 if (count == 1) {
3542 return this;
3543 }
3544 final int len = value.length;
3545 if (len == 0 || count == 0) {
3546 return "";
3547 }
3548 if (len == 1) {
3549 final byte[] single = new byte[count];
3550 Arrays.fill(single, value[0]);
3551 return new String(single, coder);
3552 }
3553 if (Integer.MAX_VALUE / count < len) {
3554 throw new OutOfMemoryError("Repeating " + len + " bytes String " + count +
3555 " times will produce a String exceeding maximum size.");
3556 }
3557 final int limit = len * count;
3558 final byte[] multiple = new byte[limit];
3559 System.arraycopy(value, 0, multiple, 0, len);
3560 int copied = len;
3561 for (; copied < limit - copied; copied <<= 1) {
3562 System.arraycopy(multiple, 0, multiple, copied, copied);
3563 }
3564 System.arraycopy(multiple, 0, multiple, copied, limit - copied);
3565 return new String(multiple, coder);
3566 }
3567
3568 ////////////////////////////////////////////////////////////////
3569
3570 /**
3571 * Copy character bytes from this string into dst starting at dstBegin.
3572 * This method doesn't perform any range checking.
3573 *
3574 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two
3575 * coders are different, and dst is big enough (range check)
3576 *
3577 * @param dstBegin the char index, not offset of byte[]
3578 * @param coder the coder of dst[]
3579 */
3580 void getBytes(byte dst[], int dstBegin, byte coder) {
3581 if (coder() == coder) {
3582 System.arraycopy(value, 0, dst, dstBegin << coder, value.length);
3583 } else { // this.coder == LATIN && coder == UTF16
3584 StringLatin1.inflate(value, 0, dst, dstBegin, value.length);
3585 }
3586 }
3587
3588 /*
3589 * Package private constructor. Trailing Void argument is there for
3590 * disambiguating it against other (public) constructors.
3591 *
3592 * Stores the char[] value into a byte[] that each byte represents
3593 * the8 low-order bits of the corresponding character, if the char[]
3594 * contains only latin1 character. Or a byte[] that stores all
3595 * characters in their byte sequences defined by the {@code StringUTF16}.
3596 */
3597 String(char[] value, int off, int len, Void sig) {
3598 if (len == 0) {
3599 this.value = "".value;
3600 this.coder = "".coder;
3601 return;
3602 }
3603 if (COMPACT_STRINGS) {
3604 byte[] val = StringUTF16.compress(value, off, len);
3605 if (val != null) {
3606 this.value = val;
3607 this.coder = LATIN1;
3608 return;
3609 }
3610 }
3611 this.coder = UTF16;
3612 this.value = StringUTF16.toBytes(value, off, len);
3613 }
3614
3615 /*
3616 * Package private constructor. Trailing Void argument is there for
3617 * disambiguating it against other (public) constructors.
3618 */
3619 String(AbstractStringBuilder asb, Void sig) {
3620 byte[] val = asb.getValue();
3621 int length = asb.length();
3622 if (asb.isLatin1()) {
3623 this.coder = LATIN1;
3624 this.value = Arrays.copyOfRange(val, 0, length);
3625 } else {
3626 if (COMPACT_STRINGS) {
3627 byte[] buf = StringUTF16.compress(val, 0, length);
3628 if (buf != null) {
3629 this.coder = LATIN1;
3630 this.value = buf;
3631 return;
3632 }
3633 }
3634 this.coder = UTF16;
3635 this.value = Arrays.copyOfRange(val, 0, length << 1);
3636 }
3637 }
3638
3639 /*
3640 * Package private constructor which shares value array for speed.
3641 */
3642 String(byte[] value, byte coder) {
3643 this.value = value;
3644 this.coder = coder;
3645 }
3646
3647 byte coder() {
3648 return COMPACT_STRINGS ? coder : UTF16;
3649 }
3650
3651 byte[] value() {
3652 return value;
3653 }
3654
3655 boolean isLatin1() {
3656 return COMPACT_STRINGS && coder == LATIN1;
3657 }
3658
3659 @Native static final byte LATIN1 = 0;
3660 @Native static final byte UTF16 = 1;
3661
3662 /*
3663 * StringIndexOutOfBoundsException if {@code index} is
3664 * negative or greater than or equal to {@code length}.
3665 */
3666 static void checkIndex(int index, int length) {
3667 if (index < 0 || index >= length) {
3668 throw new StringIndexOutOfBoundsException("index " + index +
3669 ", length " + length);
3670 }
3671 }
3672
3673 /*
3674 * StringIndexOutOfBoundsException if {@code offset}
3675 * is negative or greater than {@code length}.
3676 */
3677 static void checkOffset(int offset, int length) {
3678 if (offset < 0 || offset > length) {
3679 throw new StringIndexOutOfBoundsException("offset " + offset +
3680 ", length " + length);
3681 }
3682 }
3683
3684 /*
3685 * Check {@code offset}, {@code count} against {@code 0} and {@code length}
3686 * bounds.
3687 *
3688 * @throws StringIndexOutOfBoundsException
3689 * If {@code offset} is negative, {@code count} is negative,
3690 * or {@code offset} is greater than {@code length - count}
3691 */
3692 static void checkBoundsOffCount(int offset, int count, int length) {
3693 if (offset < 0 || count < 0 || offset > length - count) {
3694 throw new StringIndexOutOfBoundsException(
3695 "offset " + offset + ", count " + count + ", length " + length);
3696 }
3697 }
3698
3699 /*
3700 * Check {@code begin}, {@code end} against {@code 0} and {@code length}
3701 * bounds.
3702 *
3703 * @throws StringIndexOutOfBoundsException
3704 * If {@code begin} is negative, {@code begin} is greater than
3705 * {@code end}, or {@code end} is greater than {@code length}.
3706 */
3707 static void checkBoundsBeginEnd(int begin, int end, int length) {
3708 if (begin < 0 || begin > end || end > length) {
3709 throw new StringIndexOutOfBoundsException(
3710 "begin " + begin + ", end " + end + ", length " + length);
3711 }
3712 }
3713
3714 /**
3715 * Returns the string representation of the {@code codePoint}
3716 * argument.
3717 *
3718 * @param codePoint a {@code codePoint}.
3719 * @return a string of length {@code 1} or {@code 2} containing
3720 * as its single character the argument {@code codePoint}.
3721 * @throws IllegalArgumentException if the specified
3722 * {@code codePoint} is not a {@linkplain Character#isValidCodePoint
3723 * valid Unicode code point}.
3724 */
3725 static String valueOfCodePoint(int codePoint) {
3726 if (COMPACT_STRINGS && StringLatin1.canEncode(codePoint)) {
3727 return new String(StringLatin1.toBytes((char)codePoint), LATIN1);
3728 } else if (Character.isBmpCodePoint(codePoint)) {
3729 return new String(StringUTF16.toBytes((char)codePoint), UTF16);
3730 } else if (Character.isSupplementaryCodePoint(codePoint)) {
3731 return new String(StringUTF16.toBytesSupplementary(codePoint), UTF16);
3732 }
3733
3734 throw new IllegalArgumentException(
3735 format("Not a valid Unicode code point: 0x%X", codePoint));
3736 }
3737
3738 /**
3739 * Returns an {@link Optional} containing the nominal descriptor for this
3740 * instance, which is the instance itself.
3741 *
3742 * @return an {@link Optional} describing the {@linkplain String} instance
3743 * @since 12
3744 */
3745 @Override
3746 public Optional<String> describeConstable() {
3747 return Optional.of(this);
3748 }
3749
3750 /**
3751 * Resolves this instance as a {@link ConstantDesc}, the result of which is
3752 * the instance itself.
3753 *
3754 * @param lookup ignored
3755 * @return the {@linkplain String} instance
3756 * @since 12
3757 */
3758 @Override
3759 public String resolveConstantDesc(MethodHandles.Lookup lookup) {
3760 return this;
3761 }
3762
3763 }