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