1 /*
2 * Copyright (c) 1994, 2018, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.lang;
27
28 import java.io.ObjectStreamField;
29 import java.io.UnsupportedEncodingException;
30 import java.lang.annotation.Native;
31 import java.nio.charset.Charset;
32 import java.util.ArrayList;
33 import java.util.Arrays;
34 import java.util.Comparator;
35 import java.util.Formatter;
36 import java.util.Locale;
37 import java.util.Objects;
38 import java.util.Spliterator;
39 import java.util.StringJoiner;
40 import java.util.function.Function;
41 import java.util.regex.Matcher;
42 import java.util.regex.Pattern;
43 import java.util.regex.PatternSyntaxException;
44 import java.util.stream.Collectors;
45 import java.util.stream.IntStream;
46 import java.util.stream.Stream;
47 import java.util.stream.StreamSupport;
48 import jdk.internal.HotSpotIntrinsicCandidate;
49 import jdk.internal.vm.annotation.Stable;
50
51 import static java.util.function.Predicate.not;
52
53 /**
54 * The {@code String} class represents character strings. All
55 * string literals in Java programs, such as {@code "abc"}, are
56 * implemented as instances of this class.
57 * <p>
58 * Strings are constant; their values cannot be changed after they
59 * are created. String buffers support mutable strings.
60 * Because String objects are immutable they can be shared. For example:
61 * <blockquote><pre>
62 * String str = "abc";
63 * </pre></blockquote><p>
64 * is equivalent to:
65 * <blockquote><pre>
66 * char data[] = {'a', 'b', 'c'};
67 * String str = new String(data);
68 * </pre></blockquote><p>
69 * Here are some more examples of how strings can be used:
70 * <blockquote><pre>
71 * System.out.println("abc");
72 * String cde = "cde";
73 * System.out.println("abc" + cde);
74 * String c = "abc".substring(2,3);
75 * String d = cde.substring(1, 2);
76 * </pre></blockquote>
77 * <p>
78 * The class {@code String} includes methods for examining
79 * individual characters of the sequence, for comparing strings, for
80 * searching strings, for extracting substrings, and for creating a
81 * copy of a string with all characters translated to uppercase or to
82 * lowercase. Case mapping is based on the Unicode Standard version
83 * specified by the {@link java.lang.Character Character} class.
84 * <p>
85 * The Java language provides special support for the string
86 * concatenation operator ( + ), and for conversion of
87 * other objects to strings. For additional information on string
88 * concatenation and conversion, see <i>The Java™ Language Specification</i>.
89 *
90 * <p> Unless otherwise noted, passing a {@code null} argument to a constructor
91 * or method in this class will cause a {@link NullPointerException} to be
92 * thrown.
93 *
94 * <p>A {@code String} represents a string in the UTF-16 format
95 * in which <em>supplementary characters</em> are represented by <em>surrogate
96 * pairs</em> (see the section <a href="Character.html#unicode">Unicode
97 * Character Representations</a> in the {@code Character} class for
98 * more information).
99 * Index values refer to {@code char} code units, so a supplementary
100 * character uses two positions in a {@code String}.
101 * <p>The {@code String} class provides methods for dealing with
102 * Unicode code points (i.e., characters), in addition to those for
103 * dealing with Unicode code units (i.e., {@code char} values).
104 *
105 * <p>Unless otherwise noted, methods for comparing Strings do not take locale
106 * into account. The {@link java.text.Collator} class provides methods for
107 * finer-grain, locale-sensitive String comparison.
108 *
109 * @implNote The implementation of the string concatenation operator is left to
110 * the discretion of a Java compiler, as long as the compiler ultimately conforms
111 * to <i>The Java™ Language Specification</i>. For example, the {@code javac} compiler
112 * may implement the operator with {@code StringBuffer}, {@code StringBuilder},
113 * or {@code java.lang.invoke.StringConcatFactory} depending on the JDK version. The
114 * implementation of string conversion is typically through the method {@code toString},
115 * defined by {@code Object} and inherited by all classes in Java.
116 *
117 * @author Lee Boynton
118 * @author Arthur van Hoff
119 * @author Martin Buchholz
120 * @author Ulf Zibis
121 * @see java.lang.Object#toString()
122 * @see java.lang.StringBuffer
123 * @see java.lang.StringBuilder
124 * @see java.nio.charset.Charset
125 * @since 1.0
126 * @jls 15.18.1 String Concatenation Operator +
127 */
128
129 public final class String
130 implements java.io.Serializable, Comparable<String>, CharSequence {
131
132 /**
133 * The value is used for character storage.
134 *
135 * @implNote This field is trusted by the VM, and is a subject to
136 * constant folding if String instance is constant. Overwriting this
137 * field after construction will cause problems.
138 *
139 * Additionally, it is marked with {@link Stable} to trust the contents
140 * of the array. No other facility in JDK provides this functionality (yet).
141 * {@link Stable} is safe here, because value is never null.
142 */
143 @Stable
144 private final byte[] value;
145
146 /**
147 * The identifier of the encoding used to encode the bytes in
148 * {@code value}. The supported values in this implementation are
149 *
150 * LATIN1
151 * UTF16
152 *
153 * @implNote This field is trusted by the VM, and is a subject to
154 * constant folding if String instance is constant. Overwriting this
155 * field after construction will cause problems.
156 */
157 private final byte coder;
158
159 /** Cache the hash code for the string */
160 private int hash; // Default to 0
161
162 /** use serialVersionUID from JDK 1.0.2 for interoperability */
163 private static final long serialVersionUID = -6849794470754667710L;
164
165 /**
166 * If String compaction is disabled, the bytes in {@code value} are
167 * always encoded in UTF16.
168 *
169 * For methods with several possible implementation paths, when String
170 * compaction is disabled, only one code path is taken.
171 *
172 * The instance field value is generally opaque to optimizing JIT
173 * compilers. Therefore, in performance-sensitive place, an explicit
174 * check of the static boolean {@code COMPACT_STRINGS} is done first
175 * before checking the {@code coder} field since the static boolean
176 * {@code COMPACT_STRINGS} would be constant folded away by an
177 * optimizing JIT compiler. The idioms for these cases are as follows.
178 *
179 * For code such as:
180 *
181 * if (coder == LATIN1) { ... }
182 *
183 * can be written more optimally as
184 *
185 * if (coder() == LATIN1) { ... }
186 *
187 * or:
188 *
189 * if (COMPACT_STRINGS && coder == LATIN1) { ... }
190 *
191 * An optimizing JIT compiler can fold the above conditional as:
192 *
193 * COMPACT_STRINGS == true => if (coder == LATIN1) { ... }
194 * COMPACT_STRINGS == false => if (false) { ... }
195 *
196 * @implNote
197 * The actual value for this field is injected by JVM. The static
198 * initialization block is used to set the value here to communicate
199 * that this static final field is not statically foldable, and to
200 * avoid any possible circular dependency during vm initialization.
201 */
202 static final boolean COMPACT_STRINGS;
203
204 static {
205 COMPACT_STRINGS = true;
206 }
207
208 /**
209 * Class String is special cased within the Serialization Stream Protocol.
210 *
211 * A String instance is written into an ObjectOutputStream according to
212 * <a href="{@docRoot}/../specs/serialization/protocol.html#stream-elements">
213 * Object Serialization Specification, Section 6.2, "Stream Elements"</a>
214 */
215 private static final ObjectStreamField[] serialPersistentFields =
216 new ObjectStreamField[0];
217
218 /**
219 * Initializes a newly created {@code String} object so that it represents
220 * an empty character sequence. Note that use of this constructor is
221 * unnecessary since Strings are immutable.
222 */
223 public String() {
224 this.value = "".value;
225 this.coder = "".coder;
226 }
227
228 /**
229 * Initializes a newly created {@code String} object so that it represents
230 * the same sequence of characters as the argument; in other words, the
231 * newly created string is a copy of the argument string. Unless an
232 * explicit copy of {@code original} is needed, use of this constructor is
233 * unnecessary since Strings are immutable.
234 *
235 * @param original
236 * A {@code String}
237 */
238 @HotSpotIntrinsicCandidate
239 public String(String original) {
240 this.value = original.value;
241 this.coder = original.coder;
242 this.hash = original.hash;
243 }
244
245 /**
246 * Allocates a new {@code String} so that it represents the sequence of
247 * characters currently contained in the character array argument. The
248 * contents of the character array are copied; subsequent modification of
249 * the character array does not affect the newly created string.
250 *
251 * @param value
252 * The initial value of the string
253 */
254 public String(char value[]) {
255 this(value, 0, value.length, null);
256 }
257
258 /**
259 * Allocates a new {@code String} that contains characters from a subarray
260 * of the character array argument. The {@code offset} argument is the
261 * index of the first character of the subarray and the {@code count}
262 * argument specifies the length of the subarray. The contents of the
263 * subarray are copied; subsequent modification of the character array does
264 * not affect the newly created string.
265 *
266 * @param value
267 * Array that is the source of characters
268 *
269 * @param offset
270 * The initial offset
271 *
272 * @param count
273 * The length
274 *
275 * @throws IndexOutOfBoundsException
276 * If {@code offset} is negative, {@code count} is negative, or
277 * {@code offset} is greater than {@code value.length - count}
278 */
279 public String(char value[], int offset, int count) {
280 this(value, offset, count, rangeCheck(value, offset, count));
281 }
282
283 private static Void rangeCheck(char[] value, int offset, int count) {
284 checkBoundsOffCount(offset, count, value.length);
285 return null;
286 }
287
288 /**
289 * Allocates a new {@code String} that contains characters from a subarray
290 * of the <a href="Character.html#unicode">Unicode code point</a> array
291 * argument. The {@code offset} argument is the index of the first code
292 * point of the subarray and the {@code count} argument specifies the
293 * length of the subarray. The contents of the subarray are converted to
294 * {@code char}s; subsequent modification of the {@code int} array does not
295 * affect the newly created string.
296 *
297 * @param codePoints
298 * Array that is the source of Unicode code points
299 *
300 * @param offset
301 * The initial offset
302 *
303 * @param count
304 * The length
305 *
306 * @throws IllegalArgumentException
307 * If any invalid Unicode code point is found in {@code
308 * codePoints}
309 *
310 * @throws IndexOutOfBoundsException
311 * If {@code offset} is negative, {@code count} is negative, or
312 * {@code offset} is greater than {@code codePoints.length - count}
313 *
314 * @since 1.5
315 */
316 public String(int[] codePoints, int offset, int count) {
317 checkBoundsOffCount(offset, count, codePoints.length);
318 if (count == 0) {
319 this.value = "".value;
320 this.coder = "".coder;
321 return;
322 }
323 if (COMPACT_STRINGS) {
324 byte[] val = StringLatin1.toBytes(codePoints, offset, count);
325 if (val != null) {
326 this.coder = LATIN1;
327 this.value = val;
328 return;
329 }
330 }
331 this.coder = UTF16;
332 this.value = StringUTF16.toBytes(codePoints, offset, count);
333 }
334
335 /**
336 * Allocates a new {@code String} constructed from a subarray of an array
337 * of 8-bit integer values.
338 *
339 * <p> The {@code offset} argument is the index of the first byte of the
340 * subarray, and the {@code count} argument specifies the length of the
341 * subarray.
342 *
343 * <p> Each {@code byte} in the subarray is converted to a {@code char} as
344 * specified in the {@link #String(byte[],int) String(byte[],int)} constructor.
345 *
346 * @deprecated This method does not properly convert bytes into characters.
347 * As of JDK 1.1, the preferred way to do this is via the
348 * {@code String} constructors that take a {@link
349 * java.nio.charset.Charset}, charset name, or that use the platform's
350 * default charset.
351 *
352 * @param ascii
353 * The bytes to be converted to characters
354 *
355 * @param hibyte
356 * The top 8 bits of each 16-bit Unicode code unit
357 *
358 * @param offset
359 * The initial offset
360 * @param count
361 * The length
362 *
363 * @throws IndexOutOfBoundsException
364 * If {@code offset} is negative, {@code count} is negative, or
365 * {@code offset} is greater than {@code ascii.length - count}
366 *
367 * @see #String(byte[], int)
368 * @see #String(byte[], int, int, java.lang.String)
369 * @see #String(byte[], int, int, java.nio.charset.Charset)
370 * @see #String(byte[], int, int)
371 * @see #String(byte[], java.lang.String)
372 * @see #String(byte[], java.nio.charset.Charset)
373 * @see #String(byte[])
374 */
375 @Deprecated(since="1.1")
376 public String(byte ascii[], int hibyte, int offset, int count) {
377 checkBoundsOffCount(offset, count, ascii.length);
378 if (count == 0) {
379 this.value = "".value;
380 this.coder = "".coder;
381 return;
382 }
383 if (COMPACT_STRINGS && (byte)hibyte == 0) {
384 this.value = Arrays.copyOfRange(ascii, offset, offset + count);
385 this.coder = LATIN1;
386 } else {
387 hibyte <<= 8;
388 byte[] val = StringUTF16.newBytesFor(count);
389 for (int i = 0; i < count; i++) {
390 StringUTF16.putChar(val, i, hibyte | (ascii[offset++] & 0xff));
391 }
392 this.value = val;
393 this.coder = UTF16;
394 }
395 }
396
397 /**
398 * Allocates a new {@code String} containing characters constructed from
399 * an array of 8-bit integer values. Each character <i>c</i> in the
400 * resulting string is constructed from the corresponding component
401 * <i>b</i> in the byte array such that:
402 *
403 * <blockquote><pre>
404 * <b><i>c</i></b> == (char)(((hibyte & 0xff) << 8)
405 * | (<b><i>b</i></b> & 0xff))
406 * </pre></blockquote>
407 *
408 * @deprecated This method does not properly convert bytes into
409 * characters. As of JDK 1.1, the preferred way to do this is via the
410 * {@code String} constructors that take a {@link
411 * java.nio.charset.Charset}, charset name, or that use the platform's
412 * default charset.
413 *
414 * @param ascii
415 * The bytes to be converted to characters
416 *
417 * @param hibyte
418 * The top 8 bits of each 16-bit Unicode code unit
419 *
420 * @see #String(byte[], int, int, java.lang.String)
421 * @see #String(byte[], int, int, java.nio.charset.Charset)
422 * @see #String(byte[], int, int)
423 * @see #String(byte[], java.lang.String)
424 * @see #String(byte[], java.nio.charset.Charset)
425 * @see #String(byte[])
426 */
427 @Deprecated(since="1.1")
428 public String(byte ascii[], int hibyte) {
429 this(ascii, hibyte, 0, ascii.length);
430 }
431
432 /**
433 * Constructs a new {@code String} by decoding the specified subarray of
434 * bytes using the specified charset. The length of the new {@code String}
435 * is a function of the charset, and hence may not be equal to the length
436 * of the subarray.
437 *
438 * <p> The behavior of this constructor when the given bytes are not valid
439 * in the given charset is unspecified. The {@link
440 * java.nio.charset.CharsetDecoder} class should be used when more control
441 * over the decoding process is required.
442 *
443 * @param bytes
444 * The bytes to be decoded into characters
445 *
446 * @param offset
447 * The index of the first byte to decode
448 *
449 * @param length
450 * The number of bytes to decode
451
452 * @param charsetName
453 * The name of a supported {@linkplain java.nio.charset.Charset
454 * charset}
455 *
456 * @throws UnsupportedEncodingException
457 * If the named charset is not supported
458 *
459 * @throws IndexOutOfBoundsException
460 * If {@code offset} is negative, {@code length} is negative, or
461 * {@code offset} is greater than {@code bytes.length - length}
462 *
463 * @since 1.1
464 */
465 public String(byte bytes[], int offset, int length, String charsetName)
466 throws UnsupportedEncodingException {
467 if (charsetName == null)
468 throw new NullPointerException("charsetName");
469 checkBoundsOffCount(offset, length, bytes.length);
470 StringCoding.Result ret =
471 StringCoding.decode(charsetName, bytes, offset, length);
472 this.value = ret.value;
473 this.coder = ret.coder;
474 }
475
476 /**
477 * Constructs a new {@code String} by decoding the specified subarray of
478 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
479 * The length of the new {@code String} is a function of the charset, and
480 * hence may not be equal to the length of the subarray.
481 *
482 * <p> This method always replaces malformed-input and unmappable-character
483 * sequences with this charset's default replacement string. The {@link
484 * java.nio.charset.CharsetDecoder} class should be used when more control
485 * over the decoding process is required.
486 *
487 * @param bytes
488 * The bytes to be decoded into characters
489 *
490 * @param offset
491 * The index of the first byte to decode
492 *
493 * @param length
494 * The number of bytes to decode
495 *
496 * @param charset
497 * The {@linkplain java.nio.charset.Charset charset} to be used to
498 * decode the {@code bytes}
499 *
500 * @throws IndexOutOfBoundsException
501 * If {@code offset} is negative, {@code length} is negative, or
502 * {@code offset} is greater than {@code bytes.length - length}
503 *
504 * @since 1.6
505 */
506 public String(byte bytes[], int offset, int length, Charset charset) {
507 if (charset == null)
508 throw new NullPointerException("charset");
509 checkBoundsOffCount(offset, length, bytes.length);
510 StringCoding.Result ret =
511 StringCoding.decode(charset, bytes, offset, length);
512 this.value = ret.value;
513 this.coder = ret.coder;
514 }
515
516 /**
517 * Constructs a new {@code String} by decoding the specified array of bytes
518 * using the specified {@linkplain java.nio.charset.Charset charset}. The
519 * length of the new {@code String} is a function of the charset, and hence
520 * may not be equal to the length of the byte array.
521 *
522 * <p> The behavior of this constructor when the given bytes are not valid
523 * in the given charset is unspecified. The {@link
524 * java.nio.charset.CharsetDecoder} class should be used when more control
525 * over the decoding process is required.
526 *
527 * @param bytes
528 * The bytes to be decoded into characters
529 *
530 * @param charsetName
531 * The name of a supported {@linkplain java.nio.charset.Charset
532 * charset}
533 *
534 * @throws UnsupportedEncodingException
535 * If the named charset is not supported
536 *
537 * @since 1.1
538 */
539 public String(byte bytes[], String charsetName)
540 throws UnsupportedEncodingException {
541 this(bytes, 0, bytes.length, charsetName);
542 }
543
544 /**
545 * Constructs a new {@code String} by decoding the specified array of
546 * bytes using the specified {@linkplain java.nio.charset.Charset charset}.
547 * The length of the new {@code String} is a function of the charset, and
548 * hence may not be equal to the length of the byte array.
549 *
550 * <p> This method always replaces malformed-input and unmappable-character
551 * sequences with this charset's default replacement string. The {@link
552 * java.nio.charset.CharsetDecoder} class should be used when more control
553 * over the decoding process is required.
554 *
555 * @param bytes
556 * The bytes to be decoded into characters
557 *
558 * @param charset
559 * The {@linkplain java.nio.charset.Charset charset} to be used to
560 * decode the {@code bytes}
561 *
562 * @since 1.6
563 */
564 public String(byte bytes[], Charset charset) {
565 this(bytes, 0, bytes.length, charset);
566 }
567
568 /**
569 * Constructs a new {@code String} by decoding the specified subarray of
570 * bytes using the platform's default charset. The length of the new
571 * {@code String} is a function of the charset, and hence may not be equal
572 * to the length of the subarray.
573 *
574 * <p> The behavior of this constructor when the given bytes are not valid
575 * in the default charset is unspecified. The {@link
576 * java.nio.charset.CharsetDecoder} class should be used when more control
577 * over the decoding process is required.
578 *
579 * @param bytes
580 * The bytes to be decoded into characters
581 *
582 * @param offset
583 * The index of the first byte to decode
584 *
585 * @param length
586 * The number of bytes to decode
587 *
588 * @throws IndexOutOfBoundsException
589 * If {@code offset} is negative, {@code length} is negative, or
590 * {@code offset} is greater than {@code bytes.length - length}
591 *
592 * @since 1.1
593 */
594 public String(byte bytes[], int offset, int length) {
595 checkBoundsOffCount(offset, length, bytes.length);
596 StringCoding.Result ret = StringCoding.decode(bytes, offset, length);
597 this.value = ret.value;
598 this.coder = ret.coder;
599 }
600
601 /**
602 * Constructs a new {@code String} by decoding the specified array of bytes
603 * using the platform's default charset. The length of the new {@code
604 * String} is a function of the charset, and hence may not be equal to the
605 * length of the byte array.
606 *
607 * <p> The behavior of this constructor when the given bytes are not valid
608 * in the default charset is unspecified. The {@link
609 * java.nio.charset.CharsetDecoder} class should be used when more control
610 * over the decoding process is required.
611 *
612 * @param bytes
613 * The bytes to be decoded into characters
614 *
615 * @since 1.1
616 */
617 public String(byte[] bytes) {
618 this(bytes, 0, bytes.length);
619 }
620
621 /**
622 * Allocates a new string that contains the sequence of characters
623 * currently contained in the string buffer argument. The contents of the
624 * string buffer are copied; subsequent modification of the string buffer
625 * does not affect the newly created string.
626 *
627 * @param buffer
628 * A {@code StringBuffer}
629 */
630 public String(StringBuffer buffer) {
631 this(buffer.toString());
632 }
633
634 /**
635 * Allocates a new string that contains the sequence of characters
636 * currently contained in the string builder argument. The contents of the
637 * string builder are copied; subsequent modification of the string builder
638 * does not affect the newly created string.
639 *
640 * <p> This constructor is provided to ease migration to {@code
641 * StringBuilder}. Obtaining a string from a string builder via the {@code
642 * toString} method is likely to run faster and is generally preferred.
643 *
644 * @param builder
645 * A {@code StringBuilder}
646 *
647 * @since 1.5
648 */
649 public String(StringBuilder builder) {
650 this(builder, null);
651 }
652
653 /**
654 * Returns the length of this string.
655 * The length is equal to the number of <a href="Character.html#unicode">Unicode
656 * code units</a> in the string.
657 *
658 * @return the length of the sequence of characters represented by this
659 * object.
660 */
661 public int length() {
662 return value.length >> coder();
663 }
664
665 /**
666 * Returns {@code true} if, and only if, {@link #length()} is {@code 0}.
667 *
668 * @return {@code true} if {@link #length()} is {@code 0}, otherwise
669 * {@code false}
670 *
671 * @since 1.6
672 */
673 public boolean isEmpty() {
674 return value.length == 0;
675 }
676
677 /**
678 * Returns the {@code char} value at the
679 * specified index. An index ranges from {@code 0} to
680 * {@code length() - 1}. The first {@code char} value of the sequence
681 * is at index {@code 0}, the next at index {@code 1},
682 * and so on, as for array indexing.
683 *
684 * <p>If the {@code char} value specified by the index is a
685 * <a href="Character.html#unicode">surrogate</a>, the surrogate
686 * value is returned.
687 *
688 * @param index the index of the {@code char} value.
689 * @return the {@code char} value at the specified index of this string.
690 * The first {@code char} value is at index {@code 0}.
691 * @exception IndexOutOfBoundsException if the {@code index}
692 * argument is negative or not less than the length of this
693 * string.
694 */
695 public char charAt(int index) {
696 if (isLatin1()) {
697 return StringLatin1.charAt(value, index);
698 } else {
699 return StringUTF16.charAt(value, index);
700 }
701 }
702
703 /**
704 * Returns the character (Unicode code point) at the specified
705 * index. The index refers to {@code char} values
706 * (Unicode code units) and ranges from {@code 0} to
707 * {@link #length()}{@code - 1}.
708 *
709 * <p> If the {@code char} value specified at the given index
710 * is in the high-surrogate range, the following index is less
711 * than the length of this {@code String}, and the
712 * {@code char} value at the following index is in the
713 * low-surrogate range, then the supplementary code point
714 * corresponding to this surrogate pair is returned. Otherwise,
715 * the {@code char} value at the given index is returned.
716 *
717 * @param index the index to the {@code char} values
718 * @return the code point value of the character at the
719 * {@code index}
720 * @exception IndexOutOfBoundsException if the {@code index}
721 * argument is negative or not less than the length of this
722 * string.
723 * @since 1.5
724 */
725 public int codePointAt(int index) {
726 if (isLatin1()) {
727 checkIndex(index, value.length);
728 return value[index] & 0xff;
729 }
730 int length = value.length >> 1;
731 checkIndex(index, length);
732 return StringUTF16.codePointAt(value, index, length);
733 }
734
735 /**
736 * Returns the character (Unicode code point) before the specified
737 * index. The index refers to {@code char} values
738 * (Unicode code units) and ranges from {@code 1} to {@link
739 * CharSequence#length() length}.
740 *
741 * <p> If the {@code char} value at {@code (index - 1)}
742 * is in the low-surrogate range, {@code (index - 2)} is not
743 * negative, and the {@code char} value at {@code (index -
744 * 2)} is in the high-surrogate range, then the
745 * supplementary code point value of the surrogate pair is
746 * returned. If the {@code char} value at {@code index -
747 * 1} is an unpaired low-surrogate or a high-surrogate, the
748 * surrogate value is returned.
749 *
750 * @param index the index following the code point that should be returned
751 * @return the Unicode code point value before the given index.
752 * @exception IndexOutOfBoundsException if the {@code index}
753 * argument is less than 1 or greater than the length
754 * of this string.
755 * @since 1.5
756 */
757 public int codePointBefore(int index) {
758 int i = index - 1;
759 if (i < 0 || i >= length()) {
760 throw new StringIndexOutOfBoundsException(index);
761 }
762 if (isLatin1()) {
763 return (value[i] & 0xff);
764 }
765 return StringUTF16.codePointBefore(value, index);
766 }
767
768 /**
769 * Returns the number of Unicode code points in the specified text
770 * range of this {@code String}. The text range begins at the
771 * specified {@code beginIndex} and extends to the
772 * {@code char} at index {@code endIndex - 1}. Thus the
773 * length (in {@code char}s) of the text range is
774 * {@code endIndex-beginIndex}. Unpaired surrogates within
775 * the text range count as one code point each.
776 *
777 * @param beginIndex the index to the first {@code char} of
778 * the text range.
779 * @param endIndex the index after the last {@code char} of
780 * the text range.
781 * @return the number of Unicode code points in the specified text
782 * range
783 * @exception IndexOutOfBoundsException if the
784 * {@code beginIndex} is negative, or {@code endIndex}
785 * is larger than the length of this {@code String}, or
786 * {@code beginIndex} is larger than {@code endIndex}.
787 * @since 1.5
788 */
789 public int codePointCount(int beginIndex, int endIndex) {
790 if (beginIndex < 0 || beginIndex > endIndex ||
791 endIndex > length()) {
792 throw new IndexOutOfBoundsException();
793 }
794 if (isLatin1()) {
795 return endIndex - beginIndex;
796 }
797 return StringUTF16.codePointCount(value, beginIndex, endIndex);
798 }
799
800 /**
801 * Returns the index within this {@code String} that is
802 * offset from the given {@code index} by
803 * {@code codePointOffset} code points. Unpaired surrogates
804 * within the text range given by {@code index} and
805 * {@code codePointOffset} count as one code point each.
806 *
807 * @param index the index to be offset
808 * @param codePointOffset the offset in code points
809 * @return the index within this {@code String}
810 * @exception IndexOutOfBoundsException if {@code index}
811 * is negative or larger then the length of this
812 * {@code String}, or if {@code codePointOffset} is positive
813 * and the substring starting with {@code index} has fewer
814 * than {@code codePointOffset} code points,
815 * or if {@code codePointOffset} is negative and the substring
816 * before {@code index} has fewer than the absolute value
817 * of {@code codePointOffset} code points.
818 * @since 1.5
819 */
820 public int offsetByCodePoints(int index, int codePointOffset) {
821 if (index < 0 || index > length()) {
822 throw new IndexOutOfBoundsException();
823 }
824 return Character.offsetByCodePoints(this, index, codePointOffset);
825 }
826
827 /**
828 * Copies characters from this string into the destination character
829 * array.
830 * <p>
831 * The first character to be copied is at index {@code srcBegin};
832 * the last character to be copied is at index {@code srcEnd-1}
833 * (thus the total number of characters to be copied is
834 * {@code srcEnd-srcBegin}). The characters are copied into the
835 * subarray of {@code dst} starting at index {@code dstBegin}
836 * and ending at index:
837 * <blockquote><pre>
838 * dstBegin + (srcEnd-srcBegin) - 1
839 * </pre></blockquote>
840 *
841 * @param srcBegin index of the first character in the string
842 * to copy.
843 * @param srcEnd index after the last character in the string
844 * to copy.
845 * @param dst the destination array.
846 * @param dstBegin the start offset in the destination array.
847 * @exception IndexOutOfBoundsException If any of the following
848 * is true:
849 * <ul><li>{@code srcBegin} is negative.
850 * <li>{@code srcBegin} is greater than {@code srcEnd}
851 * <li>{@code srcEnd} is greater than the length of this
852 * string
853 * <li>{@code dstBegin} is negative
854 * <li>{@code dstBegin+(srcEnd-srcBegin)} is larger than
855 * {@code dst.length}</ul>
856 */
857 public void getChars(int srcBegin, int srcEnd, char dst[], int dstBegin) {
858 checkBoundsBeginEnd(srcBegin, srcEnd, length());
859 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
860 if (isLatin1()) {
861 StringLatin1.getChars(value, srcBegin, srcEnd, dst, dstBegin);
862 } else {
863 StringUTF16.getChars(value, srcBegin, srcEnd, dst, dstBegin);
864 }
865 }
866
867 /**
868 * Copies characters from this string into the destination byte array. Each
869 * byte receives the 8 low-order bits of the corresponding character. The
870 * eight high-order bits of each character are not copied and do not
871 * participate in the transfer in any way.
872 *
873 * <p> The first character to be copied is at index {@code srcBegin}; the
874 * last character to be copied is at index {@code srcEnd-1}. The total
875 * number of characters to be copied is {@code srcEnd-srcBegin}. The
876 * characters, converted to bytes, are copied into the subarray of {@code
877 * dst} starting at index {@code dstBegin} and ending at index:
878 *
879 * <blockquote><pre>
880 * dstBegin + (srcEnd-srcBegin) - 1
881 * </pre></blockquote>
882 *
883 * @deprecated This method does not properly convert characters into
884 * bytes. As of JDK 1.1, the preferred way to do this is via the
885 * {@link #getBytes()} method, which uses the platform's default charset.
886 *
887 * @param srcBegin
888 * Index of the first character in the string to copy
889 *
890 * @param srcEnd
891 * Index after the last character in the string to copy
892 *
893 * @param dst
894 * The destination array
895 *
896 * @param dstBegin
897 * The start offset in the destination array
898 *
899 * @throws IndexOutOfBoundsException
900 * If any of the following is true:
901 * <ul>
902 * <li> {@code srcBegin} is negative
903 * <li> {@code srcBegin} is greater than {@code srcEnd}
904 * <li> {@code srcEnd} is greater than the length of this String
905 * <li> {@code dstBegin} is negative
906 * <li> {@code dstBegin+(srcEnd-srcBegin)} is larger than {@code
907 * dst.length}
908 * </ul>
909 */
910 @Deprecated(since="1.1")
911 public void getBytes(int srcBegin, int srcEnd, byte dst[], int dstBegin) {
912 checkBoundsBeginEnd(srcBegin, srcEnd, length());
913 Objects.requireNonNull(dst);
914 checkBoundsOffCount(dstBegin, srcEnd - srcBegin, dst.length);
915 if (isLatin1()) {
916 StringLatin1.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
917 } else {
918 StringUTF16.getBytes(value, srcBegin, srcEnd, dst, dstBegin);
919 }
920 }
921
922 /**
923 * Encodes this {@code String} into a sequence of bytes using the named
924 * charset, storing the result into a new byte array.
925 *
926 * <p> The behavior of this method when this string cannot be encoded in
927 * the given charset is unspecified. The {@link
928 * java.nio.charset.CharsetEncoder} class should be used when more control
929 * over the encoding process is required.
930 *
931 * @param charsetName
932 * The name of a supported {@linkplain java.nio.charset.Charset
933 * charset}
934 *
935 * @return The resultant byte array
936 *
937 * @throws UnsupportedEncodingException
938 * If the named charset is not supported
939 *
940 * @since 1.1
941 */
942 public byte[] getBytes(String charsetName)
943 throws UnsupportedEncodingException {
944 if (charsetName == null) throw new NullPointerException();
945 return StringCoding.encode(charsetName, coder(), value);
946 }
947
948 /**
949 * Encodes this {@code String} into a sequence of bytes using the given
950 * {@linkplain java.nio.charset.Charset charset}, storing the result into a
951 * new byte array.
952 *
953 * <p> This method always replaces malformed-input and unmappable-character
954 * sequences with this charset's default replacement byte array. The
955 * {@link java.nio.charset.CharsetEncoder} class should be used when more
956 * control over the encoding process is required.
957 *
958 * @param charset
959 * The {@linkplain java.nio.charset.Charset} to be used to encode
960 * the {@code String}
961 *
962 * @return The resultant byte array
963 *
964 * @since 1.6
965 */
966 public byte[] getBytes(Charset charset) {
967 if (charset == null) throw new NullPointerException();
968 return StringCoding.encode(charset, coder(), value);
969 }
970
971 /**
972 * Encodes this {@code String} into a sequence of bytes using the
973 * platform's default charset, storing the result into a new byte array.
974 *
975 * <p> The behavior of this method when this string cannot be encoded in
976 * the default charset is unspecified. The {@link
977 * java.nio.charset.CharsetEncoder} class should be used when more control
978 * over the encoding process is required.
979 *
980 * @return The resultant byte array
981 *
982 * @since 1.1
983 */
984 public byte[] getBytes() {
985 return StringCoding.encode(coder(), value);
986 }
987
988 /**
989 * Compares this string to the specified object. The result is {@code
990 * true} if and only if the argument is not {@code null} and is a {@code
991 * String} object that represents the same sequence of characters as this
992 * object.
993 *
994 * <p>For finer-grained String comparison, refer to
995 * {@link java.text.Collator}.
996 *
997 * @param anObject
998 * The object to compare this {@code String} against
999 *
1000 * @return {@code true} if the given object represents a {@code String}
1001 * equivalent to this string, {@code false} otherwise
1002 *
1003 * @see #compareTo(String)
1004 * @see #equalsIgnoreCase(String)
1005 */
1006 public boolean equals(Object anObject) {
1007 if (this == anObject) {
1008 return true;
1009 }
1010 if (anObject instanceof String) {
1011 String aString = (String)anObject;
1012 if (coder() == aString.coder()) {
1013 return isLatin1() ? StringLatin1.equals(value, aString.value)
1014 : StringUTF16.equals(value, aString.value);
1015 }
1016 }
1017 return false;
1018 }
1019
1020 /**
1021 * Compares this string to the specified {@code StringBuffer}. The result
1022 * is {@code true} if and only if this {@code String} represents the same
1023 * sequence of characters as the specified {@code StringBuffer}. This method
1024 * synchronizes on the {@code StringBuffer}.
1025 *
1026 * <p>For finer-grained String comparison, refer to
1027 * {@link java.text.Collator}.
1028 *
1029 * @param sb
1030 * The {@code StringBuffer} to compare this {@code String} against
1031 *
1032 * @return {@code true} if this {@code String} represents the same
1033 * sequence of characters as the specified {@code StringBuffer},
1034 * {@code false} otherwise
1035 *
1036 * @since 1.4
1037 */
1038 public boolean contentEquals(StringBuffer sb) {
1039 return contentEquals((CharSequence)sb);
1040 }
1041
1042 private boolean nonSyncContentEquals(AbstractStringBuilder sb) {
1043 int len = length();
1044 if (len != sb.length()) {
1045 return false;
1046 }
1047 byte v1[] = value;
1048 byte v2[] = sb.getValue();
1049 if (coder() == sb.getCoder()) {
1050 int n = v1.length;
1051 for (int i = 0; i < n; i++) {
1052 if (v1[i] != v2[i]) {
1053 return false;
1054 }
1055 }
1056 } else {
1057 if (!isLatin1()) { // utf16 str and latin1 abs can never be "equal"
1058 return false;
1059 }
1060 return StringUTF16.contentEquals(v1, v2, len);
1061 }
1062 return true;
1063 }
1064
1065 /**
1066 * Compares this string to the specified {@code CharSequence}. The
1067 * result is {@code true} if and only if this {@code String} represents the
1068 * same sequence of char values as the specified sequence. Note that if the
1069 * {@code CharSequence} is a {@code StringBuffer} then the method
1070 * synchronizes on it.
1071 *
1072 * <p>For finer-grained String comparison, refer to
1073 * {@link java.text.Collator}.
1074 *
1075 * @param cs
1076 * The sequence to compare this {@code String} against
1077 *
1078 * @return {@code true} if this {@code String} represents the same
1079 * sequence of char values as the specified sequence, {@code
1080 * false} otherwise
1081 *
1082 * @since 1.5
1083 */
1084 public boolean contentEquals(CharSequence cs) {
1085 // Argument is a StringBuffer, StringBuilder
1086 if (cs instanceof AbstractStringBuilder) {
1087 if (cs instanceof StringBuffer) {
1088 synchronized(cs) {
1089 return nonSyncContentEquals((AbstractStringBuilder)cs);
1090 }
1091 } else {
1092 return nonSyncContentEquals((AbstractStringBuilder)cs);
1093 }
1094 }
1095 // Argument is a String
1096 if (cs instanceof String) {
1097 return equals(cs);
1098 }
1099 // Argument is a generic CharSequence
1100 int n = cs.length();
1101 if (n != length()) {
1102 return false;
1103 }
1104 byte[] val = this.value;
1105 if (isLatin1()) {
1106 for (int i = 0; i < n; i++) {
1107 if ((val[i] & 0xff) != cs.charAt(i)) {
1108 return false;
1109 }
1110 }
1111 } else {
1112 if (!StringUTF16.contentEquals(val, cs, n)) {
1113 return false;
1114 }
1115 }
1116 return true;
1117 }
1118
1119 /**
1120 * Compares this {@code String} to another {@code String}, ignoring case
1121 * considerations. Two strings are considered equal ignoring case if they
1122 * are of the same length and corresponding characters in the two strings
1123 * are equal ignoring case.
1124 *
1125 * <p> Two characters {@code c1} and {@code c2} are considered the same
1126 * ignoring case if at least one of the following is true:
1127 * <ul>
1128 * <li> The two characters are the same (as compared by the
1129 * {@code ==} operator)
1130 * <li> Calling {@code Character.toLowerCase(Character.toUpperCase(char))}
1131 * on each character produces the same result
1132 * </ul>
1133 *
1134 * <p>Note that this method does <em>not</em> take locale into account, and
1135 * will result in unsatisfactory results for certain locales. The
1136 * {@link java.text.Collator} class provides locale-sensitive comparison.
1137 *
1138 * @param anotherString
1139 * The {@code String} to compare this {@code String} against
1140 *
1141 * @return {@code true} if the argument is not {@code null} and it
1142 * represents an equivalent {@code String} ignoring case; {@code
1143 * false} otherwise
1144 *
1145 * @see #equals(Object)
1146 */
1147 public boolean equalsIgnoreCase(String anotherString) {
1148 return (this == anotherString) ? true
1149 : (anotherString != null)
1150 && (anotherString.length() == length())
1151 && regionMatches(true, 0, anotherString, 0, length());
1152 }
1153
1154 /**
1155 * Compares two strings lexicographically.
1156 * The comparison is based on the Unicode value of each character in
1157 * the strings. The character sequence represented by this
1158 * {@code String} object is compared lexicographically to the
1159 * character sequence represented by the argument string. The result is
1160 * a negative integer if this {@code String} object
1161 * lexicographically precedes the argument string. The result is a
1162 * positive integer if this {@code String} object lexicographically
1163 * follows the argument string. The result is zero if the strings
1164 * are equal; {@code compareTo} returns {@code 0} exactly when
1165 * the {@link #equals(Object)} method would return {@code true}.
1166 * <p>
1167 * This is the definition of lexicographic ordering. If two strings are
1168 * different, then either they have different characters at some index
1169 * that is a valid index for both strings, or their lengths are different,
1170 * or both. If they have different characters at one or more index
1171 * positions, let <i>k</i> be the smallest such index; then the string
1172 * whose character at position <i>k</i> has the smaller value, as
1173 * determined by using the {@code <} operator, lexicographically precedes the
1174 * other string. In this case, {@code compareTo} returns the
1175 * difference of the two character values at position {@code k} in
1176 * the two string -- that is, the value:
1177 * <blockquote><pre>
1178 * this.charAt(k)-anotherString.charAt(k)
1179 * </pre></blockquote>
1180 * If there is no index position at which they differ, then the shorter
1181 * string lexicographically precedes the longer string. In this case,
1182 * {@code compareTo} returns the difference of the lengths of the
1183 * strings -- that is, the value:
1184 * <blockquote><pre>
1185 * this.length()-anotherString.length()
1186 * </pre></blockquote>
1187 *
1188 * <p>For finer-grained String comparison, refer to
1189 * {@link java.text.Collator}.
1190 *
1191 * @param anotherString the {@code String} to be compared.
1192 * @return the value {@code 0} if the argument string is equal to
1193 * this string; a value less than {@code 0} if this string
1194 * is lexicographically less than the string argument; and a
1195 * value greater than {@code 0} if this string is
1196 * lexicographically greater than the string argument.
1197 */
1198 public int compareTo(String anotherString) {
1199 byte v1[] = value;
1200 byte v2[] = anotherString.value;
1201 if (coder() == anotherString.coder()) {
1202 return isLatin1() ? StringLatin1.compareTo(v1, v2)
1203 : StringUTF16.compareTo(v1, v2);
1204 }
1205 return isLatin1() ? StringLatin1.compareToUTF16(v1, v2)
1206 : StringUTF16.compareToLatin1(v1, v2);
1207 }
1208
1209 /**
1210 * A Comparator that orders {@code String} objects as by
1211 * {@code compareToIgnoreCase}. This comparator is serializable.
1212 * <p>
1213 * Note that this Comparator does <em>not</em> take locale into account,
1214 * and will result in an unsatisfactory ordering for certain locales.
1215 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1216 *
1217 * @see java.text.Collator
1218 * @since 1.2
1219 */
1220 public static final Comparator<String> CASE_INSENSITIVE_ORDER
1221 = new CaseInsensitiveComparator();
1222 private static class CaseInsensitiveComparator
1223 implements Comparator<String>, java.io.Serializable {
1224 // use serialVersionUID from JDK 1.2.2 for interoperability
1225 private static final long serialVersionUID = 8575799808933029326L;
1226
1227 public int compare(String s1, String s2) {
1228 byte v1[] = s1.value;
1229 byte v2[] = s2.value;
1230 if (s1.coder() == s2.coder()) {
1231 return s1.isLatin1() ? StringLatin1.compareToCI(v1, v2)
1232 : StringUTF16.compareToCI(v1, v2);
1233 }
1234 return s1.isLatin1() ? StringLatin1.compareToCI_UTF16(v1, v2)
1235 : StringUTF16.compareToCI_Latin1(v1, v2);
1236 }
1237
1238 /** Replaces the de-serialized object. */
1239 private Object readResolve() { return CASE_INSENSITIVE_ORDER; }
1240 }
1241
1242 /**
1243 * Compares two strings lexicographically, ignoring case
1244 * differences. This method returns an integer whose sign is that of
1245 * calling {@code compareTo} with normalized versions of the strings
1246 * where case differences have been eliminated by calling
1247 * {@code Character.toLowerCase(Character.toUpperCase(character))} on
1248 * each character.
1249 * <p>
1250 * Note that this method does <em>not</em> take locale into account,
1251 * and will result in an unsatisfactory ordering for certain locales.
1252 * The {@link java.text.Collator} class provides locale-sensitive comparison.
1253 *
1254 * @param str the {@code String} to be compared.
1255 * @return a negative integer, zero, or a positive integer as the
1256 * specified String is greater than, equal to, or less
1257 * than this String, ignoring case considerations.
1258 * @see java.text.Collator
1259 * @since 1.2
1260 */
1261 public int compareToIgnoreCase(String str) {
1262 return CASE_INSENSITIVE_ORDER.compare(this, str);
1263 }
1264
1265 /**
1266 * Tests if two string regions are equal.
1267 * <p>
1268 * A substring of this {@code String} object is compared to a substring
1269 * of the argument other. The result is true if these substrings
1270 * represent identical character sequences. The substring of this
1271 * {@code String} object to be compared begins at index {@code toffset}
1272 * and has length {@code len}. The substring of other to be compared
1273 * begins at index {@code ooffset} and has length {@code len}. The
1274 * result is {@code false} if and only if at least one of the following
1275 * is true:
1276 * <ul><li>{@code toffset} is negative.
1277 * <li>{@code ooffset} is negative.
1278 * <li>{@code toffset+len} is greater than the length of this
1279 * {@code String} object.
1280 * <li>{@code ooffset+len} is greater than the length of the other
1281 * argument.
1282 * <li>There is some nonnegative integer <i>k</i> less than {@code len}
1283 * such that:
1284 * {@code this.charAt(toffset + }<i>k</i>{@code ) != other.charAt(ooffset + }
1285 * <i>k</i>{@code )}
1286 * </ul>
1287 *
1288 * <p>Note that this method does <em>not</em> take locale into account. The
1289 * {@link java.text.Collator} class provides locale-sensitive comparison.
1290 *
1291 * @param toffset the starting offset of the subregion in this string.
1292 * @param other the string argument.
1293 * @param ooffset the starting offset of the subregion in the string
1294 * argument.
1295 * @param len the number of characters to compare.
1296 * @return {@code true} if the specified subregion of this string
1297 * exactly matches the specified subregion of the string argument;
1298 * {@code false} otherwise.
1299 */
1300 public boolean regionMatches(int toffset, String other, int ooffset, int len) {
1301 byte tv[] = value;
1302 byte ov[] = other.value;
1303 // Note: toffset, ooffset, or len might be near -1>>>1.
1304 if ((ooffset < 0) || (toffset < 0) ||
1305 (toffset > (long)length() - len) ||
1306 (ooffset > (long)other.length() - len)) {
1307 return false;
1308 }
1309 if (coder() == other.coder()) {
1310 if (!isLatin1() && (len > 0)) {
1311 toffset = toffset << 1;
1312 ooffset = ooffset << 1;
1313 len = len << 1;
1314 }
1315 while (len-- > 0) {
1316 if (tv[toffset++] != ov[ooffset++]) {
1317 return false;
1318 }
1319 }
1320 } else {
1321 if (coder() == LATIN1) {
1322 while (len-- > 0) {
1323 if (StringLatin1.getChar(tv, toffset++) !=
1324 StringUTF16.getChar(ov, ooffset++)) {
1325 return false;
1326 }
1327 }
1328 } else {
1329 while (len-- > 0) {
1330 if (StringUTF16.getChar(tv, toffset++) !=
1331 StringLatin1.getChar(ov, ooffset++)) {
1332 return false;
1333 }
1334 }
1335 }
1336 }
1337 return true;
1338 }
1339
1340 /**
1341 * Tests if two string regions are equal.
1342 * <p>
1343 * A substring of this {@code String} object is compared to a substring
1344 * of the argument {@code other}. The result is {@code true} if these
1345 * substrings represent character sequences that are the same, ignoring
1346 * case if and only if {@code ignoreCase} is true. The substring of
1347 * this {@code String} object to be compared begins at index
1348 * {@code toffset} and has length {@code len}. The substring of
1349 * {@code other} to be compared begins at index {@code ooffset} and
1350 * has length {@code len}. The result is {@code false} if and only if
1351 * at least one of the following is true:
1352 * <ul><li>{@code toffset} is negative.
1353 * <li>{@code ooffset} is negative.
1354 * <li>{@code toffset+len} is greater than the length of this
1355 * {@code String} object.
1356 * <li>{@code ooffset+len} is greater than the length of the other
1357 * argument.
1358 * <li>{@code ignoreCase} is {@code false} and there is some nonnegative
1359 * integer <i>k</i> less than {@code len} such that:
1360 * <blockquote><pre>
1361 * this.charAt(toffset+k) != other.charAt(ooffset+k)
1362 * </pre></blockquote>
1363 * <li>{@code ignoreCase} is {@code true} and there is some nonnegative
1364 * integer <i>k</i> less than {@code len} such that:
1365 * <blockquote><pre>
1366 * Character.toLowerCase(Character.toUpperCase(this.charAt(toffset+k))) !=
1367 Character.toLowerCase(Character.toUpperCase(other.charAt(ooffset+k)))
1368 * </pre></blockquote>
1369 * </ul>
1370 *
1371 * <p>Note that this method does <em>not</em> take locale into account,
1372 * and will result in unsatisfactory results for certain locales when
1373 * {@code ignoreCase} is {@code true}. The {@link java.text.Collator} class
1374 * provides locale-sensitive comparison.
1375 *
1376 * @param ignoreCase if {@code true}, ignore case when comparing
1377 * characters.
1378 * @param toffset the starting offset of the subregion in this
1379 * string.
1380 * @param other the string argument.
1381 * @param ooffset the starting offset of the subregion in the string
1382 * argument.
1383 * @param len the number of characters to compare.
1384 * @return {@code true} if the specified subregion of this string
1385 * matches the specified subregion of the string argument;
1386 * {@code false} otherwise. Whether the matching is exact
1387 * or case insensitive depends on the {@code ignoreCase}
1388 * argument.
1389 */
1390 public boolean regionMatches(boolean ignoreCase, int toffset,
1391 String other, int ooffset, int len) {
1392 if (!ignoreCase) {
1393 return regionMatches(toffset, other, ooffset, len);
1394 }
1395 // Note: toffset, ooffset, or len might be near -1>>>1.
1396 if ((ooffset < 0) || (toffset < 0)
1397 || (toffset > (long)length() - len)
1398 || (ooffset > (long)other.length() - len)) {
1399 return false;
1400 }
1401 byte tv[] = value;
1402 byte ov[] = other.value;
1403 if (coder() == other.coder()) {
1404 return isLatin1()
1405 ? StringLatin1.regionMatchesCI(tv, toffset, ov, ooffset, len)
1406 : StringUTF16.regionMatchesCI(tv, toffset, ov, ooffset, len);
1407 }
1408 return isLatin1()
1409 ? StringLatin1.regionMatchesCI_UTF16(tv, toffset, ov, ooffset, len)
1410 : StringUTF16.regionMatchesCI_Latin1(tv, toffset, ov, ooffset, len);
1411 }
1412
1413 /**
1414 * Tests if the substring of this string beginning at the
1415 * specified index starts with the specified prefix.
1416 *
1417 * @param prefix the prefix.
1418 * @param toffset where to begin looking in this string.
1419 * @return {@code true} if the character sequence represented by the
1420 * argument is a prefix of the substring of this object starting
1421 * at index {@code toffset}; {@code false} otherwise.
1422 * The result is {@code false} if {@code toffset} is
1423 * negative or greater than the length of this
1424 * {@code String} object; otherwise the result is the same
1425 * as the result of the expression
1426 * <pre>
1427 * this.substring(toffset).startsWith(prefix)
1428 * </pre>
1429 */
1430 public boolean startsWith(String prefix, int toffset) {
1431 // Note: toffset might be near -1>>>1.
1432 if (toffset < 0 || toffset > length() - prefix.length()) {
1433 return false;
1434 }
1435 byte ta[] = value;
1436 byte pa[] = prefix.value;
1437 int po = 0;
1438 int pc = pa.length;
1439 if (coder() == prefix.coder()) {
1440 int to = isLatin1() ? toffset : toffset << 1;
1441 while (po < pc) {
1442 if (ta[to++] != pa[po++]) {
1443 return false;
1444 }
1445 }
1446 } else {
1447 if (isLatin1()) { // && pcoder == UTF16
1448 return false;
1449 }
1450 // coder == UTF16 && pcoder == LATIN1)
1451 while (po < pc) {
1452 if (StringUTF16.getChar(ta, toffset++) != (pa[po++] & 0xff)) {
1453 return false;
1454 }
1455 }
1456 }
1457 return true;
1458 }
1459
1460 /**
1461 * Tests if this string starts with the specified prefix.
1462 *
1463 * @param prefix the prefix.
1464 * @return {@code true} if the character sequence represented by the
1465 * argument is a prefix of the character sequence represented by
1466 * this string; {@code false} otherwise.
1467 * Note also that {@code true} will be returned if the
1468 * argument is an empty string or is equal to this
1469 * {@code String} object as determined by the
1470 * {@link #equals(Object)} method.
1471 * @since 1.0
1472 */
1473 public boolean startsWith(String prefix) {
1474 return startsWith(prefix, 0);
1475 }
1476
1477 /**
1478 * Tests if this string ends with the specified suffix.
1479 *
1480 * @param suffix the suffix.
1481 * @return {@code true} if the character sequence represented by the
1482 * argument is a suffix of the character sequence represented by
1483 * this object; {@code false} otherwise. Note that the
1484 * result will be {@code true} if the argument is the
1485 * empty string or is equal to this {@code String} object
1486 * as determined by the {@link #equals(Object)} method.
1487 */
1488 public boolean endsWith(String suffix) {
1489 return startsWith(suffix, length() - suffix.length());
1490 }
1491
1492 /**
1493 * Returns a hash code for this string. The hash code for a
1494 * {@code String} object is computed as
1495 * <blockquote><pre>
1496 * s[0]*31^(n-1) + s[1]*31^(n-2) + ... + s[n-1]
1497 * </pre></blockquote>
1498 * using {@code int} arithmetic, where {@code s[i]} is the
1499 * <i>i</i>th character of the string, {@code n} is the length of
1500 * the string, and {@code ^} indicates exponentiation.
1501 * (The hash value of the empty string is zero.)
1502 *
1503 * @return a hash code value for this object.
1504 */
1505 public int hashCode() {
1506 int h = hash;
1507 if (h == 0 && value.length > 0) {
1508 hash = h = isLatin1() ? StringLatin1.hashCode(value)
1509 : StringUTF16.hashCode(value);
1510 }
1511 return h;
1512 }
1513
1514 /**
1515 * Returns the index within this string of the first occurrence of
1516 * the specified character. If a character with value
1517 * {@code ch} occurs in the character sequence represented by
1518 * this {@code String} object, then the index (in Unicode
1519 * code units) of the first such occurrence is returned. For
1520 * values of {@code ch} in the range from 0 to 0xFFFF
1521 * (inclusive), this is the smallest value <i>k</i> such that:
1522 * <blockquote><pre>
1523 * this.charAt(<i>k</i>) == ch
1524 * </pre></blockquote>
1525 * is true. For other values of {@code ch}, it is the
1526 * smallest value <i>k</i> such that:
1527 * <blockquote><pre>
1528 * this.codePointAt(<i>k</i>) == ch
1529 * </pre></blockquote>
1530 * is true. In either case, if no such character occurs in this
1531 * string, then {@code -1} is returned.
1532 *
1533 * @param ch a character (Unicode code point).
1534 * @return the index of the first occurrence of the character in the
1535 * character sequence represented by this object, or
1536 * {@code -1} if the character does not occur.
1537 */
1538 public int indexOf(int ch) {
1539 return indexOf(ch, 0);
1540 }
1541
1542 /**
1543 * Returns the index within this string of the first occurrence of the
1544 * specified character, starting the search at the specified index.
1545 * <p>
1546 * If a character with value {@code ch} occurs in the
1547 * character sequence represented by this {@code String}
1548 * object at an index no smaller than {@code fromIndex}, then
1549 * the index of the first such occurrence is returned. For values
1550 * of {@code ch} in the range from 0 to 0xFFFF (inclusive),
1551 * this is the smallest value <i>k</i> such that:
1552 * <blockquote><pre>
1553 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1554 * </pre></blockquote>
1555 * is true. For other values of {@code ch}, it is the
1556 * smallest value <i>k</i> such that:
1557 * <blockquote><pre>
1558 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> >= fromIndex)
1559 * </pre></blockquote>
1560 * is true. In either case, if no such character occurs in this
1561 * string at or after position {@code fromIndex}, then
1562 * {@code -1} is returned.
1563 *
1564 * <p>
1565 * There is no restriction on the value of {@code fromIndex}. If it
1566 * is negative, it has the same effect as if it were zero: this entire
1567 * string may be searched. If it is greater than the length of this
1568 * string, it has the same effect as if it were equal to the length of
1569 * this string: {@code -1} is returned.
1570 *
1571 * <p>All indices are specified in {@code char} values
1572 * (Unicode code units).
1573 *
1574 * @param ch a character (Unicode code point).
1575 * @param fromIndex the index to start the search from.
1576 * @return the index of the first occurrence of the character in the
1577 * character sequence represented by this object that is greater
1578 * than or equal to {@code fromIndex}, or {@code -1}
1579 * if the character does not occur.
1580 */
1581 public int indexOf(int ch, int fromIndex) {
1582 return isLatin1() ? StringLatin1.indexOf(value, ch, fromIndex)
1583 : StringUTF16.indexOf(value, ch, fromIndex);
1584 }
1585
1586 /**
1587 * Returns the index within this string of the last occurrence of
1588 * the specified character. For values of {@code ch} in the
1589 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
1590 * units) returned is the largest value <i>k</i> such that:
1591 * <blockquote><pre>
1592 * this.charAt(<i>k</i>) == ch
1593 * </pre></blockquote>
1594 * is true. For other values of {@code ch}, it is the
1595 * largest value <i>k</i> such that:
1596 * <blockquote><pre>
1597 * this.codePointAt(<i>k</i>) == ch
1598 * </pre></blockquote>
1599 * is true. In either case, if no such character occurs in this
1600 * string, then {@code -1} is returned. The
1601 * {@code String} is searched backwards starting at the last
1602 * character.
1603 *
1604 * @param ch a character (Unicode code point).
1605 * @return the index of the last occurrence of the character in the
1606 * character sequence represented by this object, or
1607 * {@code -1} if the character does not occur.
1608 */
1609 public int lastIndexOf(int ch) {
1610 return lastIndexOf(ch, length() - 1);
1611 }
1612
1613 /**
1614 * Returns the index within this string of the last occurrence of
1615 * the specified character, searching backward starting at the
1616 * specified index. For values of {@code ch} in the range
1617 * from 0 to 0xFFFF (inclusive), the index returned is the largest
1618 * value <i>k</i> such that:
1619 * <blockquote><pre>
1620 * (this.charAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1621 * </pre></blockquote>
1622 * is true. For other values of {@code ch}, it is the
1623 * largest value <i>k</i> such that:
1624 * <blockquote><pre>
1625 * (this.codePointAt(<i>k</i>) == ch) {@code &&} (<i>k</i> <= fromIndex)
1626 * </pre></blockquote>
1627 * is true. In either case, if no such character occurs in this
1628 * string at or before position {@code fromIndex}, then
1629 * {@code -1} is returned.
1630 *
1631 * <p>All indices are specified in {@code char} values
1632 * (Unicode code units).
1633 *
1634 * @param ch a character (Unicode code point).
1635 * @param fromIndex the index to start the search from. There is no
1636 * restriction on the value of {@code fromIndex}. If it is
1637 * greater than or equal to the length of this string, it has
1638 * the same effect as if it were equal to one less than the
1639 * length of this string: this entire string may be searched.
1640 * If it is negative, it has the same effect as if it were -1:
1641 * -1 is returned.
1642 * @return the index of the last occurrence of the character in the
1643 * character sequence represented by this object that is less
1644 * than or equal to {@code fromIndex}, or {@code -1}
1645 * if the character does not occur before that point.
1646 */
1647 public int lastIndexOf(int ch, int fromIndex) {
1648 return isLatin1() ? StringLatin1.lastIndexOf(value, ch, fromIndex)
1649 : StringUTF16.lastIndexOf(value, ch, fromIndex);
1650 }
1651
1652 /**
1653 * Returns the index within this string of the first occurrence of the
1654 * specified substring.
1655 *
1656 * <p>The returned index is the smallest value {@code k} for which:
1657 * <pre>{@code
1658 * this.startsWith(str, k)
1659 * }</pre>
1660 * If no such value of {@code k} exists, then {@code -1} is returned.
1661 *
1662 * @param str the substring to search for.
1663 * @return the index of the first occurrence of the specified substring,
1664 * or {@code -1} if there is no such occurrence.
1665 */
1666 public int indexOf(String str) {
1667 if (coder() == str.coder()) {
1668 return isLatin1() ? StringLatin1.indexOf(value, str.value)
1669 : StringUTF16.indexOf(value, str.value);
1670 }
1671 if (coder() == LATIN1) { // str.coder == UTF16
1672 return -1;
1673 }
1674 return StringUTF16.indexOfLatin1(value, str.value);
1675 }
1676
1677 /**
1678 * Returns the index within this string of the first occurrence of the
1679 * specified substring, starting at the specified index.
1680 *
1681 * <p>The returned index is the smallest value {@code k} for which:
1682 * <pre>{@code
1683 * k >= Math.min(fromIndex, this.length()) &&
1684 * this.startsWith(str, k)
1685 * }</pre>
1686 * If no such value of {@code k} exists, then {@code -1} is returned.
1687 *
1688 * @param str the substring to search for.
1689 * @param fromIndex the index from which to start the search.
1690 * @return the index of the first occurrence of the specified substring,
1691 * starting at the specified index,
1692 * or {@code -1} if there is no such occurrence.
1693 */
1694 public int indexOf(String str, int fromIndex) {
1695 return indexOf(value, coder(), length(), str, fromIndex);
1696 }
1697
1698 /**
1699 * Code shared by String and AbstractStringBuilder to do searches. The
1700 * source is the character array being searched, and the target
1701 * is the string being searched for.
1702 *
1703 * @param src the characters being searched.
1704 * @param srcCoder the coder of the source string.
1705 * @param srcCount length of the source string.
1706 * @param tgtStr the characters being searched for.
1707 * @param fromIndex the index to begin searching from.
1708 */
1709 static int indexOf(byte[] src, byte srcCoder, int srcCount,
1710 String tgtStr, int fromIndex) {
1711 byte[] tgt = tgtStr.value;
1712 byte tgtCoder = tgtStr.coder();
1713 int tgtCount = tgtStr.length();
1714
1715 if (fromIndex >= srcCount) {
1716 return (tgtCount == 0 ? srcCount : -1);
1717 }
1718 if (fromIndex < 0) {
1719 fromIndex = 0;
1720 }
1721 if (tgtCount == 0) {
1722 return fromIndex;
1723 }
1724 if (tgtCount > srcCount) {
1725 return -1;
1726 }
1727 if (srcCoder == tgtCoder) {
1728 return srcCoder == LATIN1
1729 ? StringLatin1.indexOf(src, srcCount, tgt, tgtCount, fromIndex)
1730 : StringUTF16.indexOf(src, srcCount, tgt, tgtCount, fromIndex);
1731 }
1732 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1733 return -1;
1734 }
1735 // srcCoder == UTF16 && tgtCoder == LATIN1) {
1736 return StringUTF16.indexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1737 }
1738
1739 /**
1740 * Returns the index within this string of the last occurrence of the
1741 * specified substring. The last occurrence of the empty string ""
1742 * is considered to occur at the index value {@code this.length()}.
1743 *
1744 * <p>The returned index is the largest value {@code k} for which:
1745 * <pre>{@code
1746 * this.startsWith(str, k)
1747 * }</pre>
1748 * If no such value of {@code k} exists, then {@code -1} is returned.
1749 *
1750 * @param str the substring to search for.
1751 * @return the index of the last occurrence of the specified substring,
1752 * or {@code -1} if there is no such occurrence.
1753 */
1754 public int lastIndexOf(String str) {
1755 return lastIndexOf(str, length());
1756 }
1757
1758 /**
1759 * Returns the index within this string of the last occurrence of the
1760 * specified substring, searching backward starting at the specified index.
1761 *
1762 * <p>The returned index is the largest value {@code k} for which:
1763 * <pre>{@code
1764 * k <= Math.min(fromIndex, this.length()) &&
1765 * this.startsWith(str, k)
1766 * }</pre>
1767 * If no such value of {@code k} exists, then {@code -1} is returned.
1768 *
1769 * @param str the substring to search for.
1770 * @param fromIndex the index to start the search from.
1771 * @return the index of the last occurrence of the specified substring,
1772 * searching backward from the specified index,
1773 * or {@code -1} if there is no such occurrence.
1774 */
1775 public int lastIndexOf(String str, int fromIndex) {
1776 return lastIndexOf(value, coder(), length(), str, fromIndex);
1777 }
1778
1779 /**
1780 * Code shared by String and AbstractStringBuilder to do searches. The
1781 * source is the character array being searched, and the target
1782 * is the string being searched for.
1783 *
1784 * @param src the characters being searched.
1785 * @param srcCoder coder handles the mapping between bytes/chars
1786 * @param srcCount count of the source string.
1787 * @param tgt the characters being searched for.
1788 * @param fromIndex the index to begin searching from.
1789 */
1790 static int lastIndexOf(byte[] src, byte srcCoder, int srcCount,
1791 String tgtStr, int fromIndex) {
1792 byte[] tgt = tgtStr.value;
1793 byte tgtCoder = tgtStr.coder();
1794 int tgtCount = tgtStr.length();
1795 /*
1796 * Check arguments; return immediately where possible. For
1797 * consistency, don't check for null str.
1798 */
1799 int rightIndex = srcCount - tgtCount;
1800 if (fromIndex > rightIndex) {
1801 fromIndex = rightIndex;
1802 }
1803 if (fromIndex < 0) {
1804 return -1;
1805 }
1806 /* Empty string always matches. */
1807 if (tgtCount == 0) {
1808 return fromIndex;
1809 }
1810 if (srcCoder == tgtCoder) {
1811 return srcCoder == LATIN1
1812 ? StringLatin1.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex)
1813 : StringUTF16.lastIndexOf(src, srcCount, tgt, tgtCount, fromIndex);
1814 }
1815 if (srcCoder == LATIN1) { // && tgtCoder == UTF16
1816 return -1;
1817 }
1818 // srcCoder == UTF16 && tgtCoder == LATIN1
1819 return StringUTF16.lastIndexOfLatin1(src, srcCount, tgt, tgtCount, fromIndex);
1820 }
1821
1822 /**
1823 * Returns a string that is a substring of this string. The
1824 * substring begins with the character at the specified index and
1825 * extends to the end of this string. <p>
1826 * Examples:
1827 * <blockquote><pre>
1828 * "unhappy".substring(2) returns "happy"
1829 * "Harbison".substring(3) returns "bison"
1830 * "emptiness".substring(9) returns "" (an empty string)
1831 * </pre></blockquote>
1832 *
1833 * @param beginIndex the beginning index, inclusive.
1834 * @return the specified substring.
1835 * @exception IndexOutOfBoundsException if
1836 * {@code beginIndex} is negative or larger than the
1837 * length of this {@code String} object.
1838 */
1839 public String substring(int beginIndex) {
1840 if (beginIndex < 0) {
1841 throw new StringIndexOutOfBoundsException(beginIndex);
1842 }
1843 int subLen = length() - beginIndex;
1844 if (subLen < 0) {
1845 throw new StringIndexOutOfBoundsException(subLen);
1846 }
1847 if (beginIndex == 0) {
1848 return this;
1849 }
1850 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1851 : StringUTF16.newString(value, beginIndex, subLen);
1852 }
1853
1854 /**
1855 * Returns a string that is a substring of this string. The
1856 * substring begins at the specified {@code beginIndex} and
1857 * extends to the character at index {@code endIndex - 1}.
1858 * Thus the length of the substring is {@code endIndex-beginIndex}.
1859 * <p>
1860 * Examples:
1861 * <blockquote><pre>
1862 * "hamburger".substring(4, 8) returns "urge"
1863 * "smiles".substring(1, 5) returns "mile"
1864 * </pre></blockquote>
1865 *
1866 * @param beginIndex the beginning index, inclusive.
1867 * @param endIndex the ending index, exclusive.
1868 * @return the specified substring.
1869 * @exception IndexOutOfBoundsException if the
1870 * {@code beginIndex} is negative, or
1871 * {@code endIndex} is larger than the length of
1872 * this {@code String} object, or
1873 * {@code beginIndex} is larger than
1874 * {@code endIndex}.
1875 */
1876 public String substring(int beginIndex, int endIndex) {
1877 int length = length();
1878 checkBoundsBeginEnd(beginIndex, endIndex, length);
1879 int subLen = endIndex - beginIndex;
1880 if (beginIndex == 0 && endIndex == length) {
1881 return this;
1882 }
1883 return isLatin1() ? StringLatin1.newString(value, beginIndex, subLen)
1884 : StringUTF16.newString(value, beginIndex, subLen);
1885 }
1886
1887 /**
1888 * Returns a character sequence that is a subsequence of this sequence.
1889 *
1890 * <p> An invocation of this method of the form
1891 *
1892 * <blockquote><pre>
1893 * str.subSequence(begin, end)</pre></blockquote>
1894 *
1895 * behaves in exactly the same way as the invocation
1896 *
1897 * <blockquote><pre>
1898 * str.substring(begin, end)</pre></blockquote>
1899 *
1900 * @apiNote
1901 * This method is defined so that the {@code String} class can implement
1902 * the {@link CharSequence} interface.
1903 *
1904 * @param beginIndex the begin index, inclusive.
1905 * @param endIndex the end index, exclusive.
1906 * @return the specified subsequence.
1907 *
1908 * @throws IndexOutOfBoundsException
1909 * if {@code beginIndex} or {@code endIndex} is negative,
1910 * if {@code endIndex} is greater than {@code length()},
1911 * or if {@code beginIndex} is greater than {@code endIndex}
1912 *
1913 * @since 1.4
1914 * @spec JSR-51
1915 */
1916 public CharSequence subSequence(int beginIndex, int endIndex) {
1917 return this.substring(beginIndex, endIndex);
1918 }
1919
1920 /**
1921 * Concatenates the specified string to the end of this string.
1922 * <p>
1923 * If the length of the argument string is {@code 0}, then this
1924 * {@code String} object is returned. Otherwise, a
1925 * {@code String} object is returned that represents a character
1926 * sequence that is the concatenation of the character sequence
1927 * represented by this {@code String} object and the character
1928 * sequence represented by the argument string.<p>
1929 * Examples:
1930 * <blockquote><pre>
1931 * "cares".concat("s") returns "caress"
1932 * "to".concat("get").concat("her") returns "together"
1933 * </pre></blockquote>
1934 *
1935 * @param str the {@code String} that is concatenated to the end
1936 * of this {@code String}.
1937 * @return a string that represents the concatenation of this object's
1938 * characters followed by the string argument's characters.
1939 */
1940 public String concat(String str) {
1941 int olen = str.length();
1942 if (olen == 0) {
1943 return this;
1944 }
1945 if (coder() == str.coder()) {
1946 byte[] val = this.value;
1947 byte[] oval = str.value;
1948 int len = val.length + oval.length;
1949 byte[] buf = Arrays.copyOf(val, len);
1950 System.arraycopy(oval, 0, buf, val.length, oval.length);
1951 return new String(buf, coder);
1952 }
1953 int len = length();
1954 byte[] buf = StringUTF16.newBytesFor(len + olen);
1955 getBytes(buf, 0, UTF16);
1956 str.getBytes(buf, len, UTF16);
1957 return new String(buf, UTF16);
1958 }
1959
1960 /**
1961 * Returns a string resulting from replacing all occurrences of
1962 * {@code oldChar} in this string with {@code newChar}.
1963 * <p>
1964 * If the character {@code oldChar} does not occur in the
1965 * character sequence represented by this {@code String} object,
1966 * then a reference to this {@code String} object is returned.
1967 * Otherwise, a {@code String} object is returned that
1968 * represents a character sequence identical to the character sequence
1969 * represented by this {@code String} object, except that every
1970 * occurrence of {@code oldChar} is replaced by an occurrence
1971 * of {@code newChar}.
1972 * <p>
1973 * Examples:
1974 * <blockquote><pre>
1975 * "mesquite in your cellar".replace('e', 'o')
1976 * returns "mosquito in your collar"
1977 * "the war of baronets".replace('r', 'y')
1978 * returns "the way of bayonets"
1979 * "sparring with a purple porpoise".replace('p', 't')
1980 * returns "starring with a turtle tortoise"
1981 * "JonL".replace('q', 'x') returns "JonL" (no change)
1982 * </pre></blockquote>
1983 *
1984 * @param oldChar the old character.
1985 * @param newChar the new character.
1986 * @return a string derived from this string by replacing every
1987 * occurrence of {@code oldChar} with {@code newChar}.
1988 */
1989 public String replace(char oldChar, char newChar) {
1990 if (oldChar != newChar) {
1991 String ret = isLatin1() ? StringLatin1.replace(value, oldChar, newChar)
1992 : StringUTF16.replace(value, oldChar, newChar);
1993 if (ret != null) {
1994 return ret;
1995 }
1996 }
1997 return this;
1998 }
1999
2000 /**
2001 * Tells whether or not this string matches the given <a
2002 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2003 *
2004 * <p> An invocation of this method of the form
2005 * <i>str</i>{@code .matches(}<i>regex</i>{@code )} yields exactly the
2006 * same result as the expression
2007 *
2008 * <blockquote>
2009 * {@link java.util.regex.Pattern}.{@link java.util.regex.Pattern#matches(String,CharSequence)
2010 * matches(<i>regex</i>, <i>str</i>)}
2011 * </blockquote>
2012 *
2013 * @param regex
2014 * the regular expression to which this string is to be matched
2015 *
2016 * @return {@code true} if, and only if, this string matches the
2017 * given regular expression
2018 *
2019 * @throws PatternSyntaxException
2020 * if the regular expression's syntax is invalid
2021 *
2022 * @see java.util.regex.Pattern
2023 *
2024 * @since 1.4
2025 * @spec JSR-51
2026 */
2027 public boolean matches(String regex) {
2028 return Pattern.matches(regex, this);
2029 }
2030
2031 /**
2032 * Returns true if and only if this string contains the specified
2033 * sequence of char values.
2034 *
2035 * @param s the sequence to search for
2036 * @return true if this string contains {@code s}, false otherwise
2037 * @since 1.5
2038 */
2039 public boolean contains(CharSequence s) {
2040 return indexOf(s.toString()) >= 0;
2041 }
2042
2043 /**
2044 * Replaces the first substring of this string that matches the given <a
2045 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2046 * given replacement.
2047 *
2048 * <p> An invocation of this method of the form
2049 * <i>str</i>{@code .replaceFirst(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2050 * yields exactly the same result as the expression
2051 *
2052 * <blockquote>
2053 * <code>
2054 * {@link java.util.regex.Pattern}.{@link
2055 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2056 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2057 * java.util.regex.Matcher#replaceFirst replaceFirst}(<i>repl</i>)
2058 * </code>
2059 * </blockquote>
2060 *
2061 *<p>
2062 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2063 * replacement string may cause the results to be different than if it were
2064 * being treated as a literal replacement string; see
2065 * {@link java.util.regex.Matcher#replaceFirst}.
2066 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2067 * meaning of these characters, if desired.
2068 *
2069 * @param regex
2070 * the regular expression to which this string is to be matched
2071 * @param replacement
2072 * the string to be substituted for the first match
2073 *
2074 * @return The resulting {@code String}
2075 *
2076 * @throws PatternSyntaxException
2077 * if the regular expression's syntax is invalid
2078 *
2079 * @see java.util.regex.Pattern
2080 *
2081 * @since 1.4
2082 * @spec JSR-51
2083 */
2084 public String replaceFirst(String regex, String replacement) {
2085 return Pattern.compile(regex).matcher(this).replaceFirst(replacement);
2086 }
2087
2088 /**
2089 * Replaces each substring of this string that matches the given <a
2090 * href="../util/regex/Pattern.html#sum">regular expression</a> with the
2091 * given replacement.
2092 *
2093 * <p> An invocation of this method of the form
2094 * <i>str</i>{@code .replaceAll(}<i>regex</i>{@code ,} <i>repl</i>{@code )}
2095 * yields exactly the same result as the expression
2096 *
2097 * <blockquote>
2098 * <code>
2099 * {@link java.util.regex.Pattern}.{@link
2100 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2101 * java.util.regex.Pattern#matcher(java.lang.CharSequence) matcher}(<i>str</i>).{@link
2102 * java.util.regex.Matcher#replaceAll replaceAll}(<i>repl</i>)
2103 * </code>
2104 * </blockquote>
2105 *
2106 *<p>
2107 * Note that backslashes ({@code \}) and dollar signs ({@code $}) in the
2108 * replacement string may cause the results to be different than if it were
2109 * being treated as a literal replacement string; see
2110 * {@link java.util.regex.Matcher#replaceAll Matcher.replaceAll}.
2111 * Use {@link java.util.regex.Matcher#quoteReplacement} to suppress the special
2112 * meaning of these characters, if desired.
2113 *
2114 * @param regex
2115 * the regular expression to which this string is to be matched
2116 * @param replacement
2117 * the string to be substituted for each match
2118 *
2119 * @return The resulting {@code String}
2120 *
2121 * @throws PatternSyntaxException
2122 * if the regular expression's syntax is invalid
2123 *
2124 * @see java.util.regex.Pattern
2125 *
2126 * @since 1.4
2127 * @spec JSR-51
2128 */
2129 public String replaceAll(String regex, String replacement) {
2130 return Pattern.compile(regex).matcher(this).replaceAll(replacement);
2131 }
2132
2133 /**
2134 * Replaces each substring of this string that matches the literal target
2135 * sequence with the specified literal replacement sequence. The
2136 * replacement proceeds from the beginning of the string to the end, for
2137 * example, replacing "aa" with "b" in the string "aaa" will result in
2138 * "ba" rather than "ab".
2139 *
2140 * @param target The sequence of char values to be replaced
2141 * @param replacement The replacement sequence of char values
2142 * @return The resulting string
2143 * @since 1.5
2144 */
2145 public String replace(CharSequence target, CharSequence replacement) {
2146 String tgtStr = target.toString();
2147 String replStr = replacement.toString();
2148 int j = indexOf(tgtStr);
2149 if (j < 0) {
2150 return this;
2151 }
2152 int tgtLen = tgtStr.length();
2153 int tgtLen1 = Math.max(tgtLen, 1);
2154 int thisLen = length();
2155
2156 int newLenHint = thisLen - tgtLen + replStr.length();
2157 if (newLenHint < 0) {
2158 throw new OutOfMemoryError();
2159 }
2160 StringBuilder sb = new StringBuilder(newLenHint);
2161 int i = 0;
2162 do {
2163 sb.append(this, i, j).append(replStr);
2164 i = j + tgtLen;
2165 } while (j < thisLen && (j = indexOf(tgtStr, j + tgtLen1)) > 0);
2166 return sb.append(this, i, thisLen).toString();
2167 }
2168
2169 /**
2170 * Splits this string around matches of the given
2171 * <a href="../util/regex/Pattern.html#sum">regular expression</a>.
2172 *
2173 * <p> The array returned by this method contains each substring of this
2174 * string that is terminated by another substring that matches the given
2175 * expression or is terminated by the end of the string. The substrings in
2176 * the array are in the order in which they occur in this string. If the
2177 * expression does not match any part of the input then the resulting array
2178 * has just one element, namely this string.
2179 *
2180 * <p> When there is a positive-width match at the beginning of this
2181 * string then an empty leading substring is included at the beginning
2182 * of the resulting array. A zero-width match at the beginning however
2183 * never produces such empty leading substring.
2184 *
2185 * <p> The {@code limit} parameter controls the number of times the
2186 * pattern is applied and therefore affects the length of the resulting
2187 * array.
2188 * <ul>
2189 * <li><p>
2190 * If the <i>limit</i> is positive then the pattern will be applied
2191 * at most <i>limit</i> - 1 times, the array's length will be
2192 * no greater than <i>limit</i>, and the array's last entry will contain
2193 * all input beyond the last matched delimiter.</p></li>
2194 *
2195 * <li><p>
2196 * If the <i>limit</i> is zero then the pattern will be applied as
2197 * many times as possible, the array can have any length, and trailing
2198 * empty strings will be discarded.</p></li>
2199 *
2200 * <li><p>
2201 * If the <i>limit</i> is negative then the pattern will be applied
2202 * as many times as possible and the array can have any length.</p></li>
2203 * </ul>
2204 *
2205 * <p> The string {@code "boo:and:foo"}, for example, yields the
2206 * following results with these parameters:
2207 *
2208 * <blockquote><table class="plain">
2209 * <caption style="display:none">Split example showing regex, limit, and result</caption>
2210 * <thead>
2211 * <tr>
2212 * <th scope="col">Regex</th>
2213 * <th scope="col">Limit</th>
2214 * <th scope="col">Result</th>
2215 * </tr>
2216 * </thead>
2217 * <tbody>
2218 * <tr><th scope="row" rowspan="3" style="font-weight:normal">:</th>
2219 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">2</th>
2220 * <td>{@code { "boo", "and:foo" }}</td></tr>
2221 * <tr><!-- : -->
2222 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2223 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2224 * <tr><!-- : -->
2225 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2226 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2227 * <tr><th scope="row" rowspan="3" style="font-weight:normal">o</th>
2228 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">5</th>
2229 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2230 * <tr><!-- o -->
2231 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">-2</th>
2232 * <td>{@code { "b", "", ":and:f", "", "" }}</td></tr>
2233 * <tr><!-- o -->
2234 * <th scope="row" style="font-weight:normal; text-align:right; padding-right:1em">0</th>
2235 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2236 * </tbody>
2237 * </table></blockquote>
2238 *
2239 * <p> An invocation of this method of the form
2240 * <i>str.</i>{@code split(}<i>regex</i>{@code ,} <i>n</i>{@code )}
2241 * yields the same result as the expression
2242 *
2243 * <blockquote>
2244 * <code>
2245 * {@link java.util.regex.Pattern}.{@link
2246 * java.util.regex.Pattern#compile compile}(<i>regex</i>).{@link
2247 * java.util.regex.Pattern#split(java.lang.CharSequence,int) split}(<i>str</i>, <i>n</i>)
2248 * </code>
2249 * </blockquote>
2250 *
2251 *
2252 * @param regex
2253 * the delimiting regular expression
2254 *
2255 * @param limit
2256 * the result threshold, as described above
2257 *
2258 * @return the array of strings computed by splitting this string
2259 * around matches of the given regular expression
2260 *
2261 * @throws PatternSyntaxException
2262 * if the regular expression's syntax is invalid
2263 *
2264 * @see java.util.regex.Pattern
2265 *
2266 * @since 1.4
2267 * @spec JSR-51
2268 */
2269 public String[] split(String regex, int limit) {
2270 /* fastpath if the regex is a
2271 (1)one-char String and this character is not one of the
2272 RegEx's meta characters ".$|()[{^?*+\\", or
2273 (2)two-char String and the first char is the backslash and
2274 the second is not the ascii digit or ascii letter.
2275 */
2276 char ch = 0;
2277 if (((regex.length() == 1 &&
2278 ".$|()[{^?*+\\".indexOf(ch = regex.charAt(0)) == -1) ||
2279 (regex.length() == 2 &&
2280 regex.charAt(0) == '\\' &&
2281 (((ch = regex.charAt(1))-'0')|('9'-ch)) < 0 &&
2282 ((ch-'a')|('z'-ch)) < 0 &&
2283 ((ch-'A')|('Z'-ch)) < 0)) &&
2284 (ch < Character.MIN_HIGH_SURROGATE ||
2285 ch > Character.MAX_LOW_SURROGATE))
2286 {
2287 int off = 0;
2288 int next = 0;
2289 boolean limited = limit > 0;
2290 ArrayList<String> list = new ArrayList<>();
2291 while ((next = indexOf(ch, off)) != -1) {
2292 if (!limited || list.size() < limit - 1) {
2293 list.add(substring(off, next));
2294 off = next + 1;
2295 } else { // last one
2296 //assert (list.size() == limit - 1);
2297 int last = length();
2298 list.add(substring(off, last));
2299 off = last;
2300 break;
2301 }
2302 }
2303 // If no match was found, return this
2304 if (off == 0)
2305 return new String[]{this};
2306
2307 // Add remaining segment
2308 if (!limited || list.size() < limit)
2309 list.add(substring(off, length()));
2310
2311 // Construct result
2312 int resultSize = list.size();
2313 if (limit == 0) {
2314 while (resultSize > 0 && list.get(resultSize - 1).length() == 0) {
2315 resultSize--;
2316 }
2317 }
2318 String[] result = new String[resultSize];
2319 return list.subList(0, resultSize).toArray(result);
2320 }
2321 return Pattern.compile(regex).split(this, limit);
2322 }
2323
2324 /**
2325 * Splits this string around matches of the given <a
2326 * href="../util/regex/Pattern.html#sum">regular expression</a>.
2327 *
2328 * <p> This method works as if by invoking the two-argument {@link
2329 * #split(String, int) split} method with the given expression and a limit
2330 * argument of zero. Trailing empty strings are therefore not included in
2331 * the resulting array.
2332 *
2333 * <p> The string {@code "boo:and:foo"}, for example, yields the following
2334 * results with these expressions:
2335 *
2336 * <blockquote><table class="plain">
2337 * <caption style="display:none">Split examples showing regex and result</caption>
2338 * <thead>
2339 * <tr>
2340 * <th scope="col">Regex</th>
2341 * <th scope="col">Result</th>
2342 * </tr>
2343 * </thead>
2344 * <tbody>
2345 * <tr><th scope="row" style="text-weight:normal">:</th>
2346 * <td>{@code { "boo", "and", "foo" }}</td></tr>
2347 * <tr><th scope="row" style="text-weight:normal">o</th>
2348 * <td>{@code { "b", "", ":and:f" }}</td></tr>
2349 * </tbody>
2350 * </table></blockquote>
2351 *
2352 *
2353 * @param regex
2354 * the delimiting regular expression
2355 *
2356 * @return the array of strings computed by splitting this string
2357 * around matches of the given regular expression
2358 *
2359 * @throws PatternSyntaxException
2360 * if the regular expression's syntax is invalid
2361 *
2362 * @see java.util.regex.Pattern
2363 *
2364 * @since 1.4
2365 * @spec JSR-51
2366 */
2367 public String[] split(String regex) {
2368 return split(regex, 0);
2369 }
2370
2371 /**
2372 * Returns a new String composed of copies of the
2373 * {@code CharSequence elements} joined together with a copy of
2374 * the specified {@code delimiter}.
2375 *
2376 * <blockquote>For example,
2377 * <pre>{@code
2378 * String message = String.join("-", "Java", "is", "cool");
2379 * // message returned is: "Java-is-cool"
2380 * }</pre></blockquote>
2381 *
2382 * Note that if an element is null, then {@code "null"} is added.
2383 *
2384 * @param delimiter the delimiter that separates each element
2385 * @param elements the elements to join together.
2386 *
2387 * @return a new {@code String} that is composed of the {@code elements}
2388 * separated by the {@code delimiter}
2389 *
2390 * @throws NullPointerException If {@code delimiter} or {@code elements}
2391 * is {@code null}
2392 *
2393 * @see java.util.StringJoiner
2394 * @since 1.8
2395 */
2396 public static String join(CharSequence delimiter, CharSequence... elements) {
2397 Objects.requireNonNull(delimiter);
2398 Objects.requireNonNull(elements);
2399 // Number of elements not likely worth Arrays.stream overhead.
2400 StringJoiner joiner = new StringJoiner(delimiter);
2401 for (CharSequence cs: elements) {
2402 joiner.add(cs);
2403 }
2404 return joiner.toString();
2405 }
2406
2407 /**
2408 * Returns a new {@code String} composed of copies of the
2409 * {@code CharSequence elements} joined together with a copy of the
2410 * specified {@code delimiter}.
2411 *
2412 * <blockquote>For example,
2413 * <pre>{@code
2414 * List<String> strings = List.of("Java", "is", "cool");
2415 * String message = String.join(" ", strings);
2416 * //message returned is: "Java is cool"
2417 *
2418 * Set<String> strings =
2419 * new LinkedHashSet<>(List.of("Java", "is", "very", "cool"));
2420 * String message = String.join("-", strings);
2421 * //message returned is: "Java-is-very-cool"
2422 * }</pre></blockquote>
2423 *
2424 * Note that if an individual element is {@code null}, then {@code "null"} is added.
2425 *
2426 * @param delimiter a sequence of characters that is used to separate each
2427 * of the {@code elements} in the resulting {@code String}
2428 * @param elements an {@code Iterable} that will have its {@code elements}
2429 * joined together.
2430 *
2431 * @return a new {@code String} that is composed from the {@code elements}
2432 * argument
2433 *
2434 * @throws NullPointerException If {@code delimiter} or {@code elements}
2435 * is {@code null}
2436 *
2437 * @see #join(CharSequence,CharSequence...)
2438 * @see java.util.StringJoiner
2439 * @since 1.8
2440 */
2441 public static String join(CharSequence delimiter,
2442 Iterable<? extends CharSequence> elements) {
2443 Objects.requireNonNull(delimiter);
2444 Objects.requireNonNull(elements);
2445 StringJoiner joiner = new StringJoiner(delimiter);
2446 for (CharSequence cs: elements) {
2447 joiner.add(cs);
2448 }
2449 return joiner.toString();
2450 }
2451
2452 /**
2453 * Converts all of the characters in this {@code String} to lower
2454 * case using the rules of the given {@code Locale}. Case mapping is based
2455 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2456 * class. Since case mappings are not always 1:1 char mappings, the resulting
2457 * {@code String} may be a different length than the original {@code String}.
2458 * <p>
2459 * Examples of lowercase mappings are in the following table:
2460 * <table class="plain">
2461 * <caption style="display:none">Lowercase mapping examples showing language code of locale, upper case, lower case, and description</caption>
2462 * <thead>
2463 * <tr>
2464 * <th scope="col">Language Code of Locale</th>
2465 * <th scope="col">Upper Case</th>
2466 * <th scope="col">Lower Case</th>
2467 * <th scope="col">Description</th>
2468 * </tr>
2469 * </thead>
2470 * <tbody>
2471 * <tr>
2472 * <td>tr (Turkish)</td>
2473 * <th scope="row" style="font-weight:normal; text-align:left">\u0130</th>
2474 * <td>\u0069</td>
2475 * <td>capital letter I with dot above -> small letter i</td>
2476 * </tr>
2477 * <tr>
2478 * <td>tr (Turkish)</td>
2479 * <th scope="row" style="font-weight:normal; text-align:left">\u0049</th>
2480 * <td>\u0131</td>
2481 * <td>capital letter I -> small letter dotless i </td>
2482 * </tr>
2483 * <tr>
2484 * <td>(all)</td>
2485 * <th scope="row" style="font-weight:normal; text-align:left">French Fries</th>
2486 * <td>french fries</td>
2487 * <td>lowercased all chars in String</td>
2488 * </tr>
2489 * <tr>
2490 * <td>(all)</td>
2491 * <th scope="row" style="font-weight:normal; text-align:left">
2492 * ΙΧΘΥΣ</th>
2493 * <td>ιχθυσ</td>
2494 * <td>lowercased all chars in String</td>
2495 * </tr>
2496 * </tbody>
2497 * </table>
2498 *
2499 * @param locale use the case transformation rules for this locale
2500 * @return the {@code String}, converted to lowercase.
2501 * @see java.lang.String#toLowerCase()
2502 * @see java.lang.String#toUpperCase()
2503 * @see java.lang.String#toUpperCase(Locale)
2504 * @since 1.1
2505 */
2506 public String toLowerCase(Locale locale) {
2507 return isLatin1() ? StringLatin1.toLowerCase(this, value, locale)
2508 : StringUTF16.toLowerCase(this, value, locale);
2509 }
2510
2511 /**
2512 * Converts all of the characters in this {@code String} to lower
2513 * case using the rules of the default locale. This is equivalent to calling
2514 * {@code toLowerCase(Locale.getDefault())}.
2515 * <p>
2516 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2517 * results if used for strings that are intended to be interpreted locale
2518 * independently.
2519 * Examples are programming language identifiers, protocol keys, and HTML
2520 * tags.
2521 * For instance, {@code "TITLE".toLowerCase()} in a Turkish locale
2522 * returns {@code "t\u005Cu0131tle"}, where '\u005Cu0131' is the
2523 * LATIN SMALL LETTER DOTLESS I character.
2524 * To obtain correct results for locale insensitive strings, use
2525 * {@code toLowerCase(Locale.ROOT)}.
2526 *
2527 * @return the {@code String}, converted to lowercase.
2528 * @see java.lang.String#toLowerCase(Locale)
2529 */
2530 public String toLowerCase() {
2531 return toLowerCase(Locale.getDefault());
2532 }
2533
2534 /**
2535 * Converts all of the characters in this {@code String} to upper
2536 * case using the rules of the given {@code Locale}. Case mapping is based
2537 * on the Unicode Standard version specified by the {@link java.lang.Character Character}
2538 * class. Since case mappings are not always 1:1 char mappings, the resulting
2539 * {@code String} may be a different length than the original {@code String}.
2540 * <p>
2541 * Examples of locale-sensitive and 1:M case mappings are in the following table.
2542 *
2543 * <table class="plain">
2544 * <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>
2545 * <thead>
2546 * <tr>
2547 * <th scope="col">Language Code of Locale</th>
2548 * <th scope="col">Lower Case</th>
2549 * <th scope="col">Upper Case</th>
2550 * <th scope="col">Description</th>
2551 * </tr>
2552 * </thead>
2553 * <tbody>
2554 * <tr>
2555 * <td>tr (Turkish)</td>
2556 * <th scope="row" style="font-weight:normal; text-align:left">\u0069</th>
2557 * <td>\u0130</td>
2558 * <td>small letter i -> capital letter I with dot above</td>
2559 * </tr>
2560 * <tr>
2561 * <td>tr (Turkish)</td>
2562 * <th scope="row" style="font-weight:normal; text-align:left">\u0131</th>
2563 * <td>\u0049</td>
2564 * <td>small letter dotless i -> capital letter I</td>
2565 * </tr>
2566 * <tr>
2567 * <td>(all)</td>
2568 * <th scope="row" style="font-weight:normal; text-align:left">\u00df</th>
2569 * <td>\u0053 \u0053</td>
2570 * <td>small letter sharp s -> two letters: SS</td>
2571 * </tr>
2572 * <tr>
2573 * <td>(all)</td>
2574 * <th scope="row" style="font-weight:normal; text-align:left">Fahrvergnügen</th>
2575 * <td>FAHRVERGNÜGEN</td>
2576 * <td></td>
2577 * </tr>
2578 * </tbody>
2579 * </table>
2580 * @param locale use the case transformation rules for this locale
2581 * @return the {@code String}, converted to uppercase.
2582 * @see java.lang.String#toUpperCase()
2583 * @see java.lang.String#toLowerCase()
2584 * @see java.lang.String#toLowerCase(Locale)
2585 * @since 1.1
2586 */
2587 public String toUpperCase(Locale locale) {
2588 return isLatin1() ? StringLatin1.toUpperCase(this, value, locale)
2589 : StringUTF16.toUpperCase(this, value, locale);
2590 }
2591
2592 /**
2593 * Converts all of the characters in this {@code String} to upper
2594 * case using the rules of the default locale. This method is equivalent to
2595 * {@code toUpperCase(Locale.getDefault())}.
2596 * <p>
2597 * <b>Note:</b> This method is locale sensitive, and may produce unexpected
2598 * results if used for strings that are intended to be interpreted locale
2599 * independently.
2600 * Examples are programming language identifiers, protocol keys, and HTML
2601 * tags.
2602 * For instance, {@code "title".toUpperCase()} in a Turkish locale
2603 * returns {@code "T\u005Cu0130TLE"}, where '\u005Cu0130' is the
2604 * LATIN CAPITAL LETTER I WITH DOT ABOVE character.
2605 * To obtain correct results for locale insensitive strings, use
2606 * {@code toUpperCase(Locale.ROOT)}.
2607 *
2608 * @return the {@code String}, converted to uppercase.
2609 * @see java.lang.String#toUpperCase(Locale)
2610 */
2611 public String toUpperCase() {
2612 return toUpperCase(Locale.getDefault());
2613 }
2614
2615 /**
2616 * Returns a string whose value is this string, with all leading
2617 * and trailing space removed, where space is defined
2618 * as any character whose codepoint is less than or equal to
2619 * {@code 'U+0020'} (the space character).
2620 * <p>
2621 * If this {@code String} object represents an empty character
2622 * sequence, or the first and last characters of character sequence
2623 * represented by this {@code String} object both have codes
2624 * that are not space (as defined above), then a
2625 * reference to this {@code String} object is returned.
2626 * <p>
2627 * Otherwise, if all characters in this string are space (as
2628 * defined above), then a {@code String} object representing an
2629 * empty string is returned.
2630 * <p>
2631 * Otherwise, let <i>k</i> be the index of the first character in the
2632 * string whose code is not a space (as defined above) and let
2633 * <i>m</i> be the index of the last character in the string whose code
2634 * is not a space (as defined above). A {@code String}
2635 * object is returned, representing the substring of this string that
2636 * begins with the character at index <i>k</i> and ends with the
2637 * character at index <i>m</i>-that is, the result of
2638 * {@code this.substring(k, m + 1)}.
2639 * <p>
2640 * This method may be used to trim space (as defined above) from
2641 * the beginning and end of a string.
2642 *
2643 * @return a string whose value is this string, with all leading
2644 * and trailing space removed, or this string if it
2645 * has no leading or trailing space.
2646 */
2647 public String trim() {
2648 String ret = isLatin1() ? StringLatin1.trim(value)
2649 : StringUTF16.trim(value);
2650 return ret == null ? this : ret;
2651 }
2652
2653 /**
2654 * Returns a string whose value is this string, with all leading
2655 * and trailing {@link Character#isWhitespace(int) white space}
2656 * removed.
2657 * <p>
2658 * If this {@code String} object represents an empty string,
2659 * or if all code points in this string are
2660 * {@link Character#isWhitespace(int) white space}, then an empty string
2661 * is returned.
2662 * <p>
2663 * Otherwise, returns a substring of this string beginning with the first
2664 * code point that is not a {@link Character#isWhitespace(int) white space}
2665 * up to and including the last code point that is not a
2666 * {@link Character#isWhitespace(int) white space}.
2667 * <p>
2668 * This method may be used to strip
2669 * {@link Character#isWhitespace(int) white space} from
2670 * the beginning and end of a string.
2671 *
2672 * @return a string whose value is this string, with all leading
2673 * and trailing white space removed
2674 *
2675 * @see Character#isWhitespace(int)
2676 *
2677 * @since 11
2678 */
2679 public String strip() {
2680 String ret = isLatin1() ? StringLatin1.strip(value)
2681 : StringUTF16.strip(value);
2682 return ret == null ? this : ret;
2683 }
2684
2685 /**
2686 * Returns a string whose value is this string, with all leading
2687 * {@link Character#isWhitespace(int) white space} removed.
2688 * <p>
2689 * If this {@code String} object represents an empty string,
2690 * or if all code points in this string are
2691 * {@link Character#isWhitespace(int) white space}, then an empty string
2692 * is returned.
2693 * <p>
2694 * Otherwise, returns a substring of this string beginning with the first
2695 * code point that is not a {@link Character#isWhitespace(int) white space}
2696 * up to to and including the last code point of this string.
2697 * <p>
2698 * This method may be used to trim
2699 * {@link Character#isWhitespace(int) white space} from
2700 * the beginning of a string.
2701 *
2702 * @return a string whose value is this string, with all leading white
2703 * space removed
2704 *
2705 * @see Character#isWhitespace(int)
2706 *
2707 * @since 11
2708 */
2709 public String stripLeading() {
2710 String ret = isLatin1() ? StringLatin1.stripLeading(value)
2711 : StringUTF16.stripLeading(value);
2712 return ret == null ? this : ret;
2713 }
2714
2715 /**
2716 * Returns a string whose value is this string, with all trailing
2717 * {@link Character#isWhitespace(int) white space} removed.
2718 * <p>
2719 * If this {@code String} object represents an empty string,
2720 * or if all characters in this string are
2721 * {@link Character#isWhitespace(int) white space}, then an empty string
2722 * is returned.
2723 * <p>
2724 * Otherwise, returns a substring of this string beginning with the first
2725 * code point of this string up to and including the last code point
2726 * that is not a {@link Character#isWhitespace(int) white space}.
2727 * <p>
2728 * This method may be used to trim
2729 * {@link Character#isWhitespace(int) white space} from
2730 * the end of a string.
2731 *
2732 * @return a string whose value is this string, with all trailing white
2733 * space removed
2734 *
2735 * @see Character#isWhitespace(int)
2736 *
2737 * @since 11
2738 */
2739 public String stripTrailing() {
2740 String ret = isLatin1() ? StringLatin1.stripTrailing(value)
2741 : StringUTF16.stripTrailing(value);
2742 return ret == null ? this : ret;
2743 }
2744
2745 /**
2746 * Returns {@code true} if the string is empty or contains only
2747 * {@link Character#isWhitespace(int) white space} codepoints,
2748 * otherwise {@code false}.
2749 *
2750 * @return {@code true} if the string is empty or contains only
2751 * {@link Character#isWhitespace(int) white space} codepoints,
2752 * otherwise {@code false}
2753 *
2754 * @see Character#isWhitespace(int)
2755 *
2756 * @since 11
2757 */
2758 public boolean isBlank() {
2759 return indexOfNonWhitespace() == length();
2760 }
2761
2762 private Stream<String> lines(int maxLeading, int maxTrailing) {
2763 return isLatin1() ? StringLatin1.lines(value, maxLeading, maxTrailing)
2764 : StringUTF16.lines(value, maxLeading, maxTrailing);
2765 }
2766
2767 /**
2768 * Returns a stream of lines extracted from this string,
2769 * separated by line terminators.
2770 * <p>
2771 * A <i>line terminator</i> is one of the following:
2772 * a line feed character {@code "\n"} (U+000A),
2773 * a carriage return character {@code "\r"} (U+000D),
2774 * or a carriage return followed immediately by a line feed
2775 * {@code "\r\n"} (U+000D U+000A).
2776 * <p>
2777 * A <i>line</i> is either a sequence of zero or more characters
2778 * followed by a line terminator, or it is a sequence of one or
2779 * more characters followed by the end of the string. A
2780 * line does not include the line terminator.
2781 * <p>
2782 * The stream returned by this method contains the lines from
2783 * this string in the order in which they occur.
2784 *
2785 * @apiNote This definition of <i>line</i> implies that an empty
2786 * string has zero lines and that there is no empty line
2787 * following a line terminator at the end of a string.
2788 *
2789 * @implNote This method provides better performance than
2790 * split("\R") by supplying elements lazily and
2791 * by faster search of new line terminators.
2792 *
2793 * @return the stream of lines extracted from this string
2794 *
2795 * @since 11
2796 */
2797 public Stream<String> lines() {
2798 return lines(0, 0);
2799 }
2800
2801 /**
2802 * Adjusts the indentation of each line of this string based on the value of
2803 * {@code n}, and normalizes line termination characters.
2804 * <p>
2805 * This string is conceptually separated into lines using
2806 * {@link String#lines()}. Each line is then adjusted as described below
2807 * and then suffixed with a line feed {@code "\n"} (U+000A). The resulting
2808 * lines are then concatenated and returned.
2809 * <p>
2810 * If {@code n > 0} then {@code n} spaces (U+0020) are inserted at the
2811 * beginning of each line. {@link String#isBlank() Blank lines} are
2812 * unaffected.
2813 * <p>
2814 * If {@code n < 0} then up to {@code n}
2815 * {@link Character#isWhitespace(int) white space characters} are removed
2816 * from the beginning of each line. If a given line does not contain
2817 * sufficient white space then all leading
2818 * {@link Character#isWhitespace(int) white space characters} are removed.
2819 * Each white space character is treated as a single character. In
2820 * particular, the tab character {@code "\t"} (U+0009) is considered a
2821 * single character; it is not expanded.
2822 * <p>
2823 * If {@code n == 0} then the line remains unchanged. However, line
2824 * terminators are still normalized.
2825 * <p>
2826 *
2827 * @param n number of leading
2828 * {@link Character#isWhitespace(int) white space characters}
2829 * to add or remove
2830 *
2831 * @return string with indentation adjusted and line endings normalized
2832 *
2833 * @see String#lines()
2834 * @see String#isBlank()
2835 * @see Character#isWhitespace(int)
2836 *
2837 * @since 12
2838 */
2839 public String indent(int n) {
2840 return isEmpty() ? "" : indent(n, false);
2841 }
2842
2843 private String indent(int n, boolean removeBlanks) {
2844 Stream<String> stream = removeBlanks ? lines(Integer.MAX_VALUE, Integer.MAX_VALUE)
2845 : lines();
2846 if (n > 0) {
2847 final String spaces = " ".repeat(n);
2848 stream = stream.map(s -> s.isBlank() ? s : spaces + s);
2849 } else if (n == Integer.MIN_VALUE) {
2850 stream = stream.map(s -> s.stripLeading());
2851 } else if (n < 0) {
2852 stream = stream.map(s -> s.substring(Math.min(-n, s.indexOfNonWhitespace())));
2853 }
2854 return stream.collect(Collectors.joining("\n", "", "\n"));
2855 }
2856
2857 private int indexOfNonWhitespace() {
2858 return isLatin1() ? StringLatin1.indexOfNonWhitespace(value)
2859 : StringUTF16.indexOfNonWhitespace(value);
2860 }
2861
2862 private int lastIndexOfNonWhitespace() {
2863 return isLatin1() ? StringLatin1.lastIndexOfNonWhitespace(value)
2864 : StringUTF16.lastIndexOfNonWhitespace(value);
2865 }
2866
2867 /**
2868 * Removes vertical and horizontal white space margins from around the
2869 * essential body of a multi-line string, while preserving relative
2870 * indentation.
2871 * <p>
2872 * This string is first conceptually separated into lines as if by
2873 * {@link String#lines()}.
2874 * <p>
2875 * Then, the <i>minimum indentation</i> (min) is determined as follows. For
2876 * each non-blank line (as defined by {@link String#isBlank()}), the
2877 * leading {@link Character#isWhitespace(int) white space} characters are
2878 * counted. The <i>min</i> value is the smallest of these counts.
2879 * <p>
2880 * For each non-blank line, <i>min</i> leading white space characters are
2881 * removed. Each white space character is treated as a single character. In
2882 * particular, the tab character {@code "\t"} (U+0009) is considered a
2883 * single character; it is not expanded.
2884 * <p>
2885 * Leading and trailing blank lines, if any, are removed. Trailing spaces are
2886 * preserved.
2887 * <p>
2888 * Each line is suffixed with a line feed character {@code "\n"} (U+000A).
2889 * <p>
2890 * Finally, the lines are concatenated into a single string and returned.
2891 *
2892 * @apiNote
2893 * This method's primary purpose is to shift a block of lines as far as
2894 * possible to the left, while preserving relative indentation. Lines
2895 * that were indented the least will thus have no leading white space.
2896 *
2897 * Example:
2898 * <blockquote><pre>
2899 * `
2900 * This is the first line
2901 * This is the second line
2902 * `.align();
2903 *
2904 * returns
2905 * This is the first line
2906 * This is the second line
2907 * </pre></blockquote>
2908 *
2909 * @return string with margins removed and line terminators normalized
2910 *
2911 * @see String#lines()
2912 * @see String#isBlank()
2913 * @see String#indent(int)
2914 * @see Character#isWhitespace(int)
2915 *
2916 * @since 12
2917 */
2918 public String align() {
2919 return align(0);
2920 }
2921
2922 /**
2923 * Removes vertical and horizontal white space margins from around the
2924 * essential body of a multi-line string, while preserving relative
2925 * indentation and with optional indentation adjustment.
2926 * <p>
2927 * Invoking this method is equivalent to:
2928 * <blockquote>
2929 * {@code this.align().indent(n)}
2930 * </blockquote>
2931 *
2932 * @apiNote
2933 * Examples:
2934 * <blockquote><pre>
2935 * `
2936 * This is the first line
2937 * This is the second line
2938 * `.align(0);
2939 *
2940 * returns
2941 * This is the first line
2942 * This is the second line
2943 *
2944 *
2945 * `
2946 * This is the first line
2947 * This is the second line
2948 * `.align(4);
2949 * returns
2950 * This is the first line
2951 * This is the second line
2952 * </pre></blockquote>
2953 *
2954 * @param n number of leading white space characters
2955 * to add or remove
2956 *
2957 * @return string with margins removed, indentation adjusted and
2958 * line terminators normalized
2959 *
2960 * @see String#align()
2961 *
2962 * @since 12
2963 */
2964 public String align(int n) {
2965 if (isEmpty()) {
2966 return "";
2967 }
2968 int outdent = lines().filter(not(String::isBlank))
2969 .mapToInt(String::indexOfNonWhitespace)
2970 .min()
2971 .orElse(0);
2972 return indent(n - outdent, true);
2973 }
2974
2975 /**
2976 * This method allows the application of a function to {@code this}
2977 * string. The function should expect a single String argument
2978 * and produce an {@code R} result.
2979 *
2980 * @param f functional interface to a apply
2981 *
2982 * @param <R> class of the result
2983 *
2984 * @return the result of applying the function to this string
2985 *
2986 * @see java.util.function.Function
2987 *
2988 * @since 12
2989 */
2990 public <R> R transform(Function<? super String, ? extends R> f) {
2991 return f.apply(this);
2992 }
2993
2994 /**
2995 * This object (which is already a string!) is itself returned.
2996 *
2997 * @return the string itself.
2998 */
2999 public String toString() {
3000 return this;
3001 }
3002
3003 /**
3004 * Returns a stream of {@code int} zero-extending the {@code char} values
3005 * from this sequence. Any char which maps to a <a
3006 * href="{@docRoot}/java.base/java/lang/Character.html#unicode">surrogate code
3007 * point</a> is passed through uninterpreted.
3008 *
3009 * @return an IntStream of char values from this sequence
3010 * @since 9
3011 */
3012 @Override
3013 public IntStream chars() {
3014 return StreamSupport.intStream(
3015 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
3016 : new StringUTF16.CharsSpliterator(value, Spliterator.IMMUTABLE),
3017 false);
3018 }
3019
3020
3021 /**
3022 * Returns a stream of code point values from this sequence. Any surrogate
3023 * pairs encountered in the sequence are combined as if by {@linkplain
3024 * Character#toCodePoint Character.toCodePoint} and the result is passed
3025 * to the stream. Any other code units, including ordinary BMP characters,
3026 * unpaired surrogates, and undefined code units, are zero-extended to
3027 * {@code int} values which are then passed to the stream.
3028 *
3029 * @return an IntStream of Unicode code points from this sequence
3030 * @since 9
3031 */
3032 @Override
3033 public IntStream codePoints() {
3034 return StreamSupport.intStream(
3035 isLatin1() ? new StringLatin1.CharsSpliterator(value, Spliterator.IMMUTABLE)
3036 : new StringUTF16.CodePointsSpliterator(value, Spliterator.IMMUTABLE),
3037 false);
3038 }
3039
3040 /**
3041 * Converts this string to a new character array.
3042 *
3043 * @return a newly allocated character array whose length is the length
3044 * of this string and whose contents are initialized to contain
3045 * the character sequence represented by this string.
3046 */
3047 public char[] toCharArray() {
3048 return isLatin1() ? StringLatin1.toChars(value)
3049 : StringUTF16.toChars(value);
3050 }
3051
3052 /**
3053 * Returns a formatted string using the specified format string and
3054 * arguments.
3055 *
3056 * <p> The locale always used is the one returned by {@link
3057 * java.util.Locale#getDefault(java.util.Locale.Category)
3058 * Locale.getDefault(Locale.Category)} with
3059 * {@link java.util.Locale.Category#FORMAT FORMAT} category specified.
3060 *
3061 * @param format
3062 * A <a href="../util/Formatter.html#syntax">format string</a>
3063 *
3064 * @param args
3065 * Arguments referenced by the format specifiers in the format
3066 * string. If there are more arguments than format specifiers, the
3067 * extra arguments are ignored. The number of arguments is
3068 * variable and may be zero. The maximum number of arguments is
3069 * limited by the maximum dimension of a Java array as defined by
3070 * <cite>The Java™ Virtual Machine Specification</cite>.
3071 * The behaviour on a
3072 * {@code null} argument depends on the <a
3073 * href="../util/Formatter.html#syntax">conversion</a>.
3074 *
3075 * @throws java.util.IllegalFormatException
3076 * If a format string contains an illegal syntax, a format
3077 * specifier that is incompatible with the given arguments,
3078 * insufficient arguments given the format string, or other
3079 * illegal conditions. For specification of all possible
3080 * formatting errors, see the <a
3081 * href="../util/Formatter.html#detail">Details</a> section of the
3082 * formatter class specification.
3083 *
3084 * @return A formatted string
3085 *
3086 * @see java.util.Formatter
3087 * @since 1.5
3088 */
3089 public static String format(String format, Object... args) {
3090 return new Formatter().format(format, args).toString();
3091 }
3092
3093 /**
3094 * Returns a formatted string using the specified locale, format string,
3095 * and arguments.
3096 *
3097 * @param l
3098 * The {@linkplain java.util.Locale locale} to apply during
3099 * formatting. If {@code l} is {@code null} then no localization
3100 * is applied.
3101 *
3102 * @param format
3103 * A <a href="../util/Formatter.html#syntax">format string</a>
3104 *
3105 * @param args
3106 * Arguments referenced by the format specifiers in the format
3107 * string. If there are more arguments than format specifiers, the
3108 * extra arguments are ignored. The number of arguments is
3109 * variable and may be zero. The maximum number of arguments is
3110 * limited by the maximum dimension of a Java array as defined by
3111 * <cite>The Java™ Virtual Machine Specification</cite>.
3112 * The behaviour on a
3113 * {@code null} argument depends on the
3114 * <a href="../util/Formatter.html#syntax">conversion</a>.
3115 *
3116 * @throws java.util.IllegalFormatException
3117 * If a format string contains an illegal syntax, a format
3118 * specifier that is incompatible with the given arguments,
3119 * insufficient arguments given the format string, or other
3120 * illegal conditions. For specification of all possible
3121 * formatting errors, see the <a
3122 * href="../util/Formatter.html#detail">Details</a> section of the
3123 * formatter class specification
3124 *
3125 * @return A formatted string
3126 *
3127 * @see java.util.Formatter
3128 * @since 1.5
3129 */
3130 public static String format(Locale l, String format, Object... args) {
3131 return new Formatter(l).format(format, args).toString();
3132 }
3133
3134 /**
3135 * Returns the string representation of the {@code Object} argument.
3136 *
3137 * @param obj an {@code Object}.
3138 * @return if the argument is {@code null}, then a string equal to
3139 * {@code "null"}; otherwise, the value of
3140 * {@code obj.toString()} is returned.
3141 * @see java.lang.Object#toString()
3142 */
3143 public static String valueOf(Object obj) {
3144 return (obj == null) ? "null" : obj.toString();
3145 }
3146
3147 /**
3148 * Returns the string representation of the {@code char} array
3149 * argument. The contents of the character array are copied; subsequent
3150 * modification of the character array does not affect the returned
3151 * string.
3152 *
3153 * @param data the character array.
3154 * @return a {@code String} that contains the characters of the
3155 * character array.
3156 */
3157 public static String valueOf(char data[]) {
3158 return new String(data);
3159 }
3160
3161 /**
3162 * Returns the string representation of a specific subarray of the
3163 * {@code char} array argument.
3164 * <p>
3165 * The {@code offset} argument is the index of the first
3166 * character of the subarray. The {@code count} argument
3167 * specifies the length of the subarray. The contents of the subarray
3168 * are copied; subsequent modification of the character array does not
3169 * affect the returned string.
3170 *
3171 * @param data the character array.
3172 * @param offset initial offset of the subarray.
3173 * @param count length of the subarray.
3174 * @return a {@code String} that contains the characters of the
3175 * specified subarray of the character array.
3176 * @exception IndexOutOfBoundsException if {@code offset} is
3177 * negative, or {@code count} is negative, or
3178 * {@code offset+count} is larger than
3179 * {@code data.length}.
3180 */
3181 public static String valueOf(char data[], int offset, int count) {
3182 return new String(data, offset, count);
3183 }
3184
3185 /**
3186 * Equivalent to {@link #valueOf(char[], int, int)}.
3187 *
3188 * @param data the character array.
3189 * @param offset initial offset of the subarray.
3190 * @param count length of the subarray.
3191 * @return a {@code String} that contains the characters of the
3192 * specified subarray of the character array.
3193 * @exception IndexOutOfBoundsException if {@code offset} is
3194 * negative, or {@code count} is negative, or
3195 * {@code offset+count} is larger than
3196 * {@code data.length}.
3197 */
3198 public static String copyValueOf(char data[], int offset, int count) {
3199 return new String(data, offset, count);
3200 }
3201
3202 /**
3203 * Equivalent to {@link #valueOf(char[])}.
3204 *
3205 * @param data the character array.
3206 * @return a {@code String} that contains the characters of the
3207 * character array.
3208 */
3209 public static String copyValueOf(char data[]) {
3210 return new String(data);
3211 }
3212
3213 /**
3214 * Returns the string representation of the {@code boolean} argument.
3215 *
3216 * @param b a {@code boolean}.
3217 * @return if the argument is {@code true}, a string equal to
3218 * {@code "true"} is returned; otherwise, a string equal to
3219 * {@code "false"} is returned.
3220 */
3221 public static String valueOf(boolean b) {
3222 return b ? "true" : "false";
3223 }
3224
3225 /**
3226 * Returns the string representation of the {@code char}
3227 * argument.
3228 *
3229 * @param c a {@code char}.
3230 * @return a string of length {@code 1} containing
3231 * as its single character the argument {@code c}.
3232 */
3233 public static String valueOf(char c) {
3234 if (COMPACT_STRINGS && StringLatin1.canEncode(c)) {
3235 return new String(StringLatin1.toBytes(c), LATIN1);
3236 }
3237 return new String(StringUTF16.toBytes(c), UTF16);
3238 }
3239
3240 /**
3241 * Returns the string representation of the {@code int} argument.
3242 * <p>
3243 * The representation is exactly the one returned by the
3244 * {@code Integer.toString} method of one argument.
3245 *
3246 * @param i an {@code int}.
3247 * @return a string representation of the {@code int} argument.
3248 * @see java.lang.Integer#toString(int, int)
3249 */
3250 public static String valueOf(int i) {
3251 return Integer.toString(i);
3252 }
3253
3254 /**
3255 * Returns the string representation of the {@code long} argument.
3256 * <p>
3257 * The representation is exactly the one returned by the
3258 * {@code Long.toString} method of one argument.
3259 *
3260 * @param l a {@code long}.
3261 * @return a string representation of the {@code long} argument.
3262 * @see java.lang.Long#toString(long)
3263 */
3264 public static String valueOf(long l) {
3265 return Long.toString(l);
3266 }
3267
3268 /**
3269 * Returns the string representation of the {@code float} argument.
3270 * <p>
3271 * The representation is exactly the one returned by the
3272 * {@code Float.toString} method of one argument.
3273 *
3274 * @param f a {@code float}.
3275 * @return a string representation of the {@code float} argument.
3276 * @see java.lang.Float#toString(float)
3277 */
3278 public static String valueOf(float f) {
3279 return Float.toString(f);
3280 }
3281
3282 /**
3283 * Returns the string representation of the {@code double} argument.
3284 * <p>
3285 * The representation is exactly the one returned by the
3286 * {@code Double.toString} method of one argument.
3287 *
3288 * @param d a {@code double}.
3289 * @return a string representation of the {@code double} argument.
3290 * @see java.lang.Double#toString(double)
3291 */
3292 public static String valueOf(double d) {
3293 return Double.toString(d);
3294 }
3295
3296 /**
3297 * Returns a canonical representation for the string object.
3298 * <p>
3299 * A pool of strings, initially empty, is maintained privately by the
3300 * class {@code String}.
3301 * <p>
3302 * When the intern method is invoked, if the pool already contains a
3303 * string equal to this {@code String} object as determined by
3304 * the {@link #equals(Object)} method, then the string from the pool is
3305 * returned. Otherwise, this {@code String} object is added to the
3306 * pool and a reference to this {@code String} object is returned.
3307 * <p>
3308 * It follows that for any two strings {@code s} and {@code t},
3309 * {@code s.intern() == t.intern()} is {@code true}
3310 * if and only if {@code s.equals(t)} is {@code true}.
3311 * <p>
3312 * All literal strings and string-valued constant expressions are
3313 * interned. String literals are defined in section 3.10.5 of the
3314 * <cite>The Java™ Language Specification</cite>.
3315 *
3316 * @return a string that has the same contents as this string, but is
3317 * guaranteed to be from a pool of unique strings.
3318 * @jls 3.10.5 String Literals
3319 */
3320 public native String intern();
3321
3322 /**
3323 * Returns a string whose value is the concatenation of this
3324 * string repeated {@code count} times.
3325 * <p>
3326 * If this string is empty or count is zero then the empty
3327 * string is returned.
3328 *
3329 * @param count number of times to repeat
3330 *
3331 * @return A string composed of this string repeated
3332 * {@code count} times or the empty string if this
3333 * string is empty or count is zero
3334 *
3335 * @throws IllegalArgumentException if the {@code count} is
3336 * negative.
3337 *
3338 * @since 11
3339 */
3340 public String repeat(int count) {
3341 if (count < 0) {
3342 throw new IllegalArgumentException("count is negative: " + count);
3343 }
3344 if (count == 1) {
3345 return this;
3346 }
3347 final int len = value.length;
3348 if (len == 0 || count == 0) {
3349 return "";
3350 }
3351 if (len == 1) {
3352 final byte[] single = new byte[count];
3353 Arrays.fill(single, value[0]);
3354 return new String(single, coder);
3355 }
3356 if (Integer.MAX_VALUE / count < len) {
3357 throw new OutOfMemoryError("Repeating " + len + " bytes String " + count +
3358 " times will produce a String exceeding maximum size.");
3359 }
3360 final int limit = len * count;
3361 final byte[] multiple = new byte[limit];
3362 System.arraycopy(value, 0, multiple, 0, len);
3363 int copied = len;
3364 for (; copied < limit - copied; copied <<= 1) {
3365 System.arraycopy(multiple, 0, multiple, copied, copied);
3366 }
3367 System.arraycopy(multiple, 0, multiple, copied, limit - copied);
3368 return new String(multiple, coder);
3369 }
3370
3371 ////////////////////////////////////////////////////////////////
3372
3373 /**
3374 * Copy character bytes from this string into dst starting at dstBegin.
3375 * This method doesn't perform any range checking.
3376 *
3377 * Invoker guarantees: dst is in UTF16 (inflate itself for asb), if two
3378 * coders are different, and dst is big enough (range check)
3379 *
3380 * @param dstBegin the char index, not offset of byte[]
3381 * @param coder the coder of dst[]
3382 */
3383 void getBytes(byte dst[], int dstBegin, byte coder) {
3384 if (coder() == coder) {
3385 System.arraycopy(value, 0, dst, dstBegin << coder, value.length);
3386 } else { // this.coder == LATIN && coder == UTF16
3387 StringLatin1.inflate(value, 0, dst, dstBegin, value.length);
3388 }
3389 }
3390
3391 /*
3392 * Package private constructor. Trailing Void argument is there for
3393 * disambiguating it against other (public) constructors.
3394 *
3395 * Stores the char[] value into a byte[] that each byte represents
3396 * the8 low-order bits of the corresponding character, if the char[]
3397 * contains only latin1 character. Or a byte[] that stores all
3398 * characters in their byte sequences defined by the {@code StringUTF16}.
3399 */
3400 String(char[] value, int off, int len, Void sig) {
3401 if (len == 0) {
3402 this.value = "".value;
3403 this.coder = "".coder;
3404 return;
3405 }
3406 if (COMPACT_STRINGS) {
3407 byte[] val = StringUTF16.compress(value, off, len);
3408 if (val != null) {
3409 this.value = val;
3410 this.coder = LATIN1;
3411 return;
3412 }
3413 }
3414 this.coder = UTF16;
3415 this.value = StringUTF16.toBytes(value, off, len);
3416 }
3417
3418 /*
3419 * Package private constructor. Trailing Void argument is there for
3420 * disambiguating it against other (public) constructors.
3421 */
3422 String(AbstractStringBuilder asb, Void sig) {
3423 byte[] val = asb.getValue();
3424 int length = asb.length();
3425 if (asb.isLatin1()) {
3426 this.coder = LATIN1;
3427 this.value = Arrays.copyOfRange(val, 0, length);
3428 } else {
3429 if (COMPACT_STRINGS) {
3430 byte[] buf = StringUTF16.compress(val, 0, length);
3431 if (buf != null) {
3432 this.coder = LATIN1;
3433 this.value = buf;
3434 return;
3435 }
3436 }
3437 this.coder = UTF16;
3438 this.value = Arrays.copyOfRange(val, 0, length << 1);
3439 }
3440 }
3441
3442 /*
3443 * Package private constructor which shares value array for speed.
3444 */
3445 String(byte[] value, byte coder) {
3446 this.value = value;
3447 this.coder = coder;
3448 }
3449
3450 byte coder() {
3451 return COMPACT_STRINGS ? coder : UTF16;
3452 }
3453
3454 byte[] value() {
3455 return value;
3456 }
3457
3458 private boolean isLatin1() {
3459 return COMPACT_STRINGS && coder == LATIN1;
3460 }
3461
3462 @Native static final byte LATIN1 = 0;
3463 @Native static final byte UTF16 = 1;
3464
3465 /*
3466 * StringIndexOutOfBoundsException if {@code index} is
3467 * negative or greater than or equal to {@code length}.
3468 */
3469 static void checkIndex(int index, int length) {
3470 if (index < 0 || index >= length) {
3471 throw new StringIndexOutOfBoundsException("index " + index +
3472 ",length " + length);
3473 }
3474 }
3475
3476 /*
3477 * StringIndexOutOfBoundsException if {@code offset}
3478 * is negative or greater than {@code length}.
3479 */
3480 static void checkOffset(int offset, int length) {
3481 if (offset < 0 || offset > length) {
3482 throw new StringIndexOutOfBoundsException("offset " + offset +
3483 ",length " + length);
3484 }
3485 }
3486
3487 /*
3488 * Check {@code offset}, {@code count} against {@code 0} and {@code length}
3489 * bounds.
3490 *
3491 * @throws StringIndexOutOfBoundsException
3492 * If {@code offset} is negative, {@code count} is negative,
3493 * or {@code offset} is greater than {@code length - count}
3494 */
3495 static void checkBoundsOffCount(int offset, int count, int length) {
3496 if (offset < 0 || count < 0 || offset > length - count) {
3497 throw new StringIndexOutOfBoundsException(
3498 "offset " + offset + ", count " + count + ", length " + length);
3499 }
3500 }
3501
3502 /*
3503 * Check {@code begin}, {@code end} against {@code 0} and {@code length}
3504 * bounds.
3505 *
3506 * @throws StringIndexOutOfBoundsException
3507 * If {@code begin} is negative, {@code begin} is greater than
3508 * {@code end}, or {@code end} is greater than {@code length}.
3509 */
3510 static void checkBoundsBeginEnd(int begin, int end, int length) {
3511 if (begin < 0 || begin > end || end > length) {
3512 throw new StringIndexOutOfBoundsException(
3513 "begin " + begin + ", end " + end + ", length " + length);
3514 }
3515 }
3516
3517 /**
3518 * Returns the string representation of the {@code codePoint}
3519 * argument.
3520 *
3521 * @param codePoint a {@code codePoint}.
3522 * @return a string of length {@code 1} or {@code 2} containing
3523 * as its single character the argument {@code codePoint}.
3524 * @throws IllegalArgumentException if the specified
3525 * {@code codePoint} is not a {@linkplain Character#isValidCodePoint
3526 * valid Unicode code point}.
3527 */
3528 static String valueOfCodePoint(int codePoint) {
3529 if (COMPACT_STRINGS && StringLatin1.canEncode(codePoint)) {
3530 return new String(StringLatin1.toBytes((char)codePoint), LATIN1);
3531 } else if (Character.isBmpCodePoint(codePoint)) {
3532 return new String(StringUTF16.toBytes((char)codePoint), UTF16);
3533 } else if (Character.isSupplementaryCodePoint(codePoint)) {
3534 return new String(StringUTF16.toBytesSupplementary(codePoint), UTF16);
3535 }
3536
3537 throw new IllegalArgumentException(
3538 format("Not a valid Unicode code point: 0x%X", codePoint));
3539 }
3540 }