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